Merge commit 'v3.0-rc5' into sched/core

Merge reason: Move to a (much) newer base.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

2032 files changed, 52386 insertions, 28109 deletions

diff --git a/CREDITS b/CREDITS
index a7ea8e343836..d78359f5f64d 100644
--- a/CREDITS
+++ b/CREDITS
@@ -518,6 +518,14 @@ N: Zach Brown
 E: zab@zabbo.net
 D: maestro pci sound
 
+M: David Brownell
+D: Kernel engineer, mentor, and friend.  Maintained USB EHCI and
+D: gadget layers, SPI subsystem, GPIO subsystem, and more than a few
+D: device drivers.  His encouragement also helped many engineers get
+D: started working on the Linux kernel.  David passed away in early
+D: 2011, and will be greatly missed.
+W: https://lkml.org/lkml/2011/4/5/36
+
 N: Gary Brubaker
 E: xavyer@ix.netcom.com
 D: USB Serial Empeg Empeg-car Mark I/II Driver
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 1b777b960492..1f89424c36a6 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -192,10 +192,6 @@ kernel-docs.txt
 	- listing of various WWW + books that document kernel internals.
 kernel-parameters.txt
 	- summary listing of command line / boot prompt args for the kernel.
-keys-request-key.txt
-	- description of the kernel key request service.
-keys.txt
-	- description of the kernel key retention service.
 kobject.txt
 	- info of the kobject infrastructure of the Linux kernel.
 kprobes.txt
@@ -294,6 +290,8 @@ scheduler/
 	- directory with info on the scheduler.
 scsi/
 	- directory with info on Linux scsi support.
+security/
+	- directory that contains security-related info
 serial/
 	- directory with info on the low level serial API.
 serial-console.txt
diff --git a/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870 b/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870
new file mode 100644
index 000000000000..aa11dbdd794b
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870
@@ -0,0 +1,56 @@
+What:		/sys/class/backlight/<backlight>/<ambient light zone>_max
+What:		/sys/class/backlight/<backlight>/l1_daylight_max
+What:		/sys/class/backlight/<backlight>/l2_bright_max
+What:		/sys/class/backlight/<backlight>/l3_office_max
+What:		/sys/class/backlight/<backlight>/l4_indoor_max
+What:		/sys/class/backlight/<backlight>/l5_dark_max
+Date:		Mai 2011
+KernelVersion:	2.6.40
+Contact:	device-drivers-devel@blackfin.uclinux.org
+Description:
+		Control the maximum brightness for <ambient light zone>
+		on this <backlight>. Values are between 0 and 127. This file
+		will also show the brightness level stored for this
+		<ambient light zone>.
+
+What:		/sys/class/backlight/<backlight>/<ambient light zone>_dim
+What:		/sys/class/backlight/<backlight>/l2_bright_dim
+What:		/sys/class/backlight/<backlight>/l3_office_dim
+What:		/sys/class/backlight/<backlight>/l4_indoor_dim
+What:		/sys/class/backlight/<backlight>/l5_dark_dim
+Date:		Mai 2011
+KernelVersion:	2.6.40
+Contact:	device-drivers-devel@blackfin.uclinux.org
+Description:
+		Control the dim brightness for <ambient light zone>
+		on this <backlight>. Values are between 0 and 127, typically
+		set to 0. Full off when the backlight is disabled.
+		This file will also show the dim brightness level stored for
+		this <ambient light zone>.
+
+What:		/sys/class/backlight/<backlight>/ambient_light_level
+Date:		Mai 2011
+KernelVersion:	2.6.40
+Contact:	device-drivers-devel@blackfin.uclinux.org
+Description:
+		Get conversion value of the light sensor.
+		This value is updated every 80 ms (when the light sensor
+		is enabled). Returns integer between 0 (dark) and
+		8000 (max ambient brightness)
+
+What:		/sys/class/backlight/<backlight>/ambient_light_zone
+Date:		Mai 2011
+KernelVersion:	2.6.40
+Contact:	device-drivers-devel@blackfin.uclinux.org
+Description:
+		Get/Set current ambient light zone. Reading returns
+		integer between 1..5 (1 = daylight, 2 = bright, ..., 5 = dark).
+		Writing a value between 1..5 forces the backlight controller
+		to enter the corresponding ambient light zone.
+		Writing 0 returns to normal/automatic ambient light level
+		operation. The ambient light sensing feature on these devices
+		is an extension to the API documented in
+		Documentation/ABI/stable/sysfs-class-backlight.
+		It can be enabled by writing the value stored in
+		/sys/class/backlight/<backlight>/max_brightness to
+		/sys/class/backlight/<backlight>/brightness.
\ No newline at end of file
diff --git a/Documentation/DocBook/dvb/dvbproperty.xml b/Documentation/DocBook/dvb/dvbproperty.xml
index 52d5e3c7cf6c..b5365f61d69b 100644
--- a/Documentation/DocBook/dvb/dvbproperty.xml
+++ b/Documentation/DocBook/dvb/dvbproperty.xml
@@ -141,13 +141,15 @@ struct dtv_properties {
  </row></tbody></tgroup></informaltable>
 </section>
 
+<section>
+	<title>Property types</title>
 <para>
 On <link linkend="FE_GET_PROPERTY">FE_GET_PROPERTY</link>/<link linkend="FE_SET_PROPERTY">FE_SET_PROPERTY</link>,
 the actual action is determined by the dtv_property cmd/data pairs. With one single ioctl, is possible to
 get/set up to 64 properties. The actual meaning of each property is described on the next sections.
 </para>
 
-<para>The Available frontend property types are:</para>
+<para>The available frontend property types are:</para>
 <programlisting>
 #define DTV_UNDEFINED		0
 #define DTV_TUNE		1
@@ -193,6 +195,7 @@ get/set up to 64 properties. The actual meaning of each property is described on
 #define DTV_ISDBT_LAYER_ENABLED	41
 #define DTV_ISDBS_TS_ID		42
 </programlisting>
+</section>
 
 <section id="fe_property_common">
 	<title>Parameters that are common to all Digital TV standards</title>
diff --git a/Documentation/DocBook/media-entities.tmpl b/Documentation/DocBook/media-entities.tmpl
index c8abb23ef1e7..e5fe09430fd9 100644
--- a/Documentation/DocBook/media-entities.tmpl
+++ b/Documentation/DocBook/media-entities.tmpl
@@ -293,6 +293,7 @@
 <!ENTITY sub-yuyv SYSTEM "v4l/pixfmt-yuyv.xml">
 <!ENTITY sub-yvyu SYSTEM "v4l/pixfmt-yvyu.xml">
 <!ENTITY sub-srggb10 SYSTEM "v4l/pixfmt-srggb10.xml">
+<!ENTITY sub-srggb12 SYSTEM "v4l/pixfmt-srggb12.xml">
 <!ENTITY sub-srggb8 SYSTEM "v4l/pixfmt-srggb8.xml">
 <!ENTITY sub-y10 SYSTEM "v4l/pixfmt-y10.xml">
 <!ENTITY sub-y12 SYSTEM "v4l/pixfmt-y12.xml">
@@ -373,9 +374,9 @@
 <!ENTITY sub-media-indices SYSTEM "media-indices.tmpl">
 
 <!ENTITY sub-media-controller SYSTEM "v4l/media-controller.xml">
-<!ENTITY sub-media-open SYSTEM "v4l/media-func-open.xml">
-<!ENTITY sub-media-close SYSTEM "v4l/media-func-close.xml">
-<!ENTITY sub-media-ioctl SYSTEM "v4l/media-func-ioctl.xml">
+<!ENTITY sub-media-func-open SYSTEM "v4l/media-func-open.xml">
+<!ENTITY sub-media-func-close SYSTEM "v4l/media-func-close.xml">
+<!ENTITY sub-media-func-ioctl SYSTEM "v4l/media-func-ioctl.xml">
 <!ENTITY sub-media-ioc-device-info SYSTEM "v4l/media-ioc-device-info.xml">
 <!ENTITY sub-media-ioc-enum-entities SYSTEM "v4l/media-ioc-enum-entities.xml">
 <!ENTITY sub-media-ioc-enum-links SYSTEM "v4l/media-ioc-enum-links.xml">
diff --git a/Documentation/DocBook/mtdnand.tmpl b/Documentation/DocBook/mtdnand.tmpl
index 6f242d5dee9a..17910e2052ad 100644
--- a/Documentation/DocBook/mtdnand.tmpl
+++ b/Documentation/DocBook/mtdnand.tmpl
@@ -189,8 +189,7 @@ static void __iomem *baseaddr;
 		<title>Partition defines</title>
 		<para>
 			If you want to divide your device into partitions, then
-			enable the configuration switch CONFIG_MTD_PARTITIONS and define
-			a partitioning scheme suitable to your board.
+			define a partitioning scheme suitable to your board.
 		</para>
 		<programlisting>
 #define NUM_PARTITIONS 2
diff --git a/Documentation/DocBook/v4l/media-controller.xml b/Documentation/DocBook/v4l/media-controller.xml
index 2dc25e1d4089..873ac3a621f0 100644
--- a/Documentation/DocBook/v4l/media-controller.xml
+++ b/Documentation/DocBook/v4l/media-controller.xml
@@ -78,9 +78,9 @@
 <appendix id="media-user-func">
   <title>Function Reference</title>
   <!-- Keep this alphabetically sorted. -->
-  &sub-media-open;
-  &sub-media-close;
-  &sub-media-ioctl;
+  &sub-media-func-open;
+  &sub-media-func-close;
+  &sub-media-func-ioctl;
   <!-- All ioctls go here. -->
   &sub-media-ioc-device-info;
   &sub-media-ioc-enum-entities;
diff --git a/Documentation/DocBook/v4l/pixfmt.xml b/Documentation/DocBook/v4l/pixfmt.xml
index dbfe3b08435f..deb660207f94 100644
--- a/Documentation/DocBook/v4l/pixfmt.xml
+++ b/Documentation/DocBook/v4l/pixfmt.xml
@@ -673,6 +673,7 @@ access the palette, this must be done with ioctls of the Linux framebuffer API.<
     &sub-srggb8;
     &sub-sbggr16;
     &sub-srggb10;
+    &sub-srggb12;
   </section>
 
   <section id="yuv-formats">
diff --git a/Documentation/DocBook/v4l/subdev-formats.xml b/Documentation/DocBook/v4l/subdev-formats.xml
index a26b10c07857..8d3409d2c632 100644
--- a/Documentation/DocBook/v4l/subdev-formats.xml
+++ b/Documentation/DocBook/v4l/subdev-formats.xml
@@ -2531,13 +2531,13 @@
 	<constant>_JPEG</constant> prefix the format code is made of
 	the following information.
 	<itemizedlist>
-	  <listitem>The number of bus samples per entropy encoded byte.</listitem>
-	  <listitem>The bus width.</listitem>
+	  <listitem><para>The number of bus samples per entropy encoded byte.</para></listitem>
+	  <listitem><para>The bus width.</para></listitem>
 	</itemizedlist>
+      </para>
 
-	<para>For instance, for a JPEG baseline process and an 8-bit bus width
-	  the format will be named <constant>V4L2_MBUS_FMT_JPEG_1X8</constant>.
-	</para>
+      <para>For instance, for a JPEG baseline process and an 8-bit bus width
+        the format will be named <constant>V4L2_MBUS_FMT_JPEG_1X8</constant>.
       </para>
 
       <para>The following table lists existing JPEG compressed formats.</para>
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index c078ad48f7a1..8173cec473aa 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -99,18 +99,11 @@ o	"qp" indicates that RCU still expects a quiescent state from
 
 o	"dt" is the current value of the dyntick counter that is incremented
 	when entering or leaving dynticks idle state, either by the
-	scheduler or by irq.  The number after the "/" is the interrupt
-	nesting depth when in dyntick-idle state, or one greater than
-	the interrupt-nesting depth otherwise.
-
-	This field is displayed only for CONFIG_NO_HZ kernels.
-
-o	"dn" is the current value of the dyntick counter that is incremented
-	when entering or leaving dynticks idle state via NMI.  If both
-	the "dt" and "dn" values are even, then this CPU is in dynticks
-	idle mode and may be ignored by RCU.  If either of these two
-	counters is odd, then RCU must be alert to the possibility of
-	an RCU read-side critical section running on this CPU.
+	scheduler or by irq.  This number is even if the CPU is in
+	dyntick idle mode and odd otherwise.  The number after the first
+	"/" is the interrupt nesting depth when in dyntick-idle state,
+	or one greater than the interrupt-nesting depth otherwise.
+	The number after the second "/" is the NMI nesting depth.
 
 	This field is displayed only for CONFIG_NO_HZ kernels.
 
diff --git a/Documentation/accounting/cgroupstats.txt b/Documentation/accounting/cgroupstats.txt
index eda40fd39cad..d16a9849e60e 100644
--- a/Documentation/accounting/cgroupstats.txt
+++ b/Documentation/accounting/cgroupstats.txt
@@ -21,7 +21,7 @@ information will not be available.
 To extract cgroup statistics a utility very similar to getdelays.c
 has been developed, the sample output of the utility is shown below
 
-~/balbir/cgroupstats # ./getdelays  -C "/cgroup/a"
+~/balbir/cgroupstats # ./getdelays  -C "/sys/fs/cgroup/a"
 sleeping 1, blocked 0, running 1, stopped 0, uninterruptible 0
-~/balbir/cgroupstats # ./getdelays  -C "/cgroup"
+~/balbir/cgroupstats # ./getdelays  -C "/sys/fs/cgroup"
 sleeping 155, blocked 0, running 1, stopped 0, uninterruptible 2
diff --git a/Documentation/acpi/method-customizing.txt b/Documentation/acpi/method-customizing.txt
index 3e1d25aee3fb..5f55373dd53b 100644
--- a/Documentation/acpi/method-customizing.txt
+++ b/Documentation/acpi/method-customizing.txt
@@ -66,3 +66,8 @@ Note: We can use a kernel with multiple custom ACPI method running,
       But each individual write to debugfs can implement a SINGLE
       method override. i.e. if we want to insert/override multiple
       ACPI methods, we need to redo step c) ~ g) for multiple times.
+
+Note: Be aware that root can mis-use this driver to modify arbitrary
+      memory and gain additional rights, if root's privileges got
+      restricted (for example if root is not allowed to load additional
+      modules after boot).
diff --git a/Documentation/arm/Booting b/Documentation/arm/Booting
index 76850295af8f..4e686a2ed91e 100644
--- a/Documentation/arm/Booting
+++ b/Documentation/arm/Booting
@@ -65,13 +65,19 @@ looks at the connected hardware is beyond the scope of this document.
 The boot loader must ultimately be able to provide a MACH_TYPE_xxx
 value to the kernel. (see linux/arch/arm/tools/mach-types).
 
-
-4. Setup the kernel tagged list
--------------------------------
+4. Setup boot data
+------------------
 
 Existing boot loaders:		OPTIONAL, HIGHLY RECOMMENDED
 New boot loaders:		MANDATORY
 
+The boot loader must provide either a tagged list or a dtb image for
+passing configuration data to the kernel.  The physical address of the
+boot data is passed to the kernel in register r2.
+
+4a. Setup the kernel tagged list
+--------------------------------
+
 The boot loader must create and initialise the kernel tagged list.
 A valid tagged list starts with ATAG_CORE and ends with ATAG_NONE.
 The ATAG_CORE tag may or may not be empty.  An empty ATAG_CORE tag
@@ -101,6 +107,24 @@ The tagged list must be placed in a region of memory where neither
 the kernel decompressor nor initrd 'bootp' program will overwrite
 it.  The recommended placement is in the first 16KiB of RAM.
 
+4b. Setup the device tree
+-------------------------
+
+The boot loader must load a device tree image (dtb) into system ram
+at a 64bit aligned address and initialize it with the boot data.  The
+dtb format is documented in Documentation/devicetree/booting-without-of.txt.
+The kernel will look for the dtb magic value of 0xd00dfeed at the dtb
+physical address to determine if a dtb has been passed instead of a
+tagged list.
+
+The boot loader must pass at a minimum the size and location of the
+system memory, and the root filesystem location.  The dtb must be
+placed in a region of memory where the kernel decompressor will not
+overwrite it.  The recommended placement is in the first 16KiB of RAM
+with the caveat that it may not be located at physical address 0 since
+the kernel interprets a value of 0 in r2 to mean neither a tagged list
+nor a dtb were passed.
+
 5. Calling the kernel image
 ---------------------------
 
@@ -125,7 +149,8 @@ In either case, the following conditions must be met:
 - CPU register settings
   r0 = 0,
   r1 = machine type number discovered in (3) above.
-  r2 = physical address of tagged list in system RAM.
+  r2 = physical address of tagged list in system RAM, or
+       physical address of device tree block (dtb) in system RAM
 
 - CPU mode
   All forms of interrupts must be disabled (IRQs and FIQs)
diff --git a/Documentation/arm/Samsung/Overview.txt b/Documentation/arm/Samsung/Overview.txt
index c3094ea51aa7..658abb258cef 100644
--- a/Documentation/arm/Samsung/Overview.txt
+++ b/Documentation/arm/Samsung/Overview.txt
@@ -14,7 +14,6 @@ Introduction
   - S3C24XX: See Documentation/arm/Samsung-S3C24XX/Overview.txt for full list
   - S3C64XX: S3C6400 and S3C6410
   - S5P6440
-  - S5P6442
   - S5PC100
   - S5PC110 / S5PV210
 
@@ -36,7 +35,6 @@ Configuration
   unifying all the SoCs into one kernel.
 
   s5p6440_defconfig - S5P6440 specific default configuration
-  s5p6442_defconfig - S5P6442 specific default configuration
   s5pc100_defconfig - S5PC100 specific default configuration
   s5pc110_defconfig - S5PC110 specific default configuration
   s5pv210_defconfig - S5PV210 specific default configuration
diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt
index 465351d4cf85..cd45c8ea7463 100644
--- a/Documentation/cgroups/blkio-controller.txt
+++ b/Documentation/cgroups/blkio-controller.txt
@@ -28,16 +28,19 @@ cgroups. Here is what you can do.
 - Enable group scheduling in CFQ
 	CONFIG_CFQ_GROUP_IOSCHED=y
 
-- Compile and boot into kernel and mount IO controller (blkio).
+- Compile and boot into kernel and mount IO controller (blkio); see
+  cgroups.txt, Why are cgroups needed?.
 
-	mount -t cgroup -o blkio none /cgroup
+	mount -t tmpfs cgroup_root /sys/fs/cgroup
+	mkdir /sys/fs/cgroup/blkio
+	mount -t cgroup -o blkio none /sys/fs/cgroup/blkio
 
 - Create two cgroups
-	mkdir -p /cgroup/test1/ /cgroup/test2
+	mkdir -p /sys/fs/cgroup/blkio/test1/ /sys/fs/cgroup/blkio/test2
 
 - Set weights of group test1 and test2
-	echo 1000 > /cgroup/test1/blkio.weight
-	echo 500 > /cgroup/test2/blkio.weight
+	echo 1000 > /sys/fs/cgroup/blkio/test1/blkio.weight
+	echo 500 > /sys/fs/cgroup/blkio/test2/blkio.weight
 
 - Create two same size files (say 512MB each) on same disk (file1, file2) and
   launch two dd threads in different cgroup to read those files.
@@ -46,12 +49,12 @@ cgroups. Here is what you can do.
 	echo 3 > /proc/sys/vm/drop_caches
 
 	dd if=/mnt/sdb/zerofile1 of=/dev/null &
-	echo $! > /cgroup/test1/tasks
-	cat /cgroup/test1/tasks
+	echo $! > /sys/fs/cgroup/blkio/test1/tasks
+	cat /sys/fs/cgroup/blkio/test1/tasks
 
 	dd if=/mnt/sdb/zerofile2 of=/dev/null &
-	echo $! > /cgroup/test2/tasks
-	cat /cgroup/test2/tasks
+	echo $! > /sys/fs/cgroup/blkio/test2/tasks
+	cat /sys/fs/cgroup/blkio/test2/tasks
 
 - At macro level, first dd should finish first. To get more precise data, keep
   on looking at (with the help of script), at blkio.disk_time and
@@ -68,13 +71,13 @@ Throttling/Upper Limit policy
 - Enable throttling in block layer
 	CONFIG_BLK_DEV_THROTTLING=y
 
-- Mount blkio controller
-        mount -t cgroup -o blkio none /cgroup/blkio
+- Mount blkio controller (see cgroups.txt, Why are cgroups needed?)
+        mount -t cgroup -o blkio none /sys/fs/cgroup/blkio
 
 - Specify a bandwidth rate on particular device for root group. The format
   for policy is "<major>:<minor>  <byes_per_second>".
 
-        echo "8:16  1048576" > /cgroup/blkio/blkio.read_bps_device
+        echo "8:16  1048576" > /sys/fs/cgroup/blkio/blkio.read_bps_device
 
   Above will put a limit of 1MB/second on reads happening for root group
   on device having major/minor number 8:16.
@@ -108,7 +111,7 @@ Hierarchical Cgroups
   CFQ and throttling will practically treat all groups at same level.
 
 				pivot
-			     /  |   \  \
+			     /  /   \  \
 			root  test1 test2  test3
 
   Down the line we can implement hierarchical accounting/control support
@@ -149,7 +152,7 @@ Proportional weight policy files
 
 	  Following is the format.
 
-	  #echo dev_maj:dev_minor weight > /path/to/cgroup/blkio.weight_device
+	  # echo dev_maj:dev_minor weight > blkio.weight_device
 	  Configure weight=300 on /dev/sdb (8:16) in this cgroup
 	  # echo 8:16 300 > blkio.weight_device
 	  # cat blkio.weight_device
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 0ed99f08f1f3..cd67e90003c0 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -138,11 +138,11 @@ With the ability to classify tasks differently for different resources
 the admin can easily set up a script which receives exec notifications
 and depending on who is launching the browser he can
 
-       # echo browser_pid > /mnt/<restype>/<userclass>/tasks
+    # echo browser_pid > /sys/fs/cgroup/<restype>/<userclass>/tasks
 
 With only a single hierarchy, he now would potentially have to create
 a separate cgroup for every browser launched and associate it with
-approp network and other resource class.  This may lead to
+appropriate network and other resource class.  This may lead to
 proliferation of such cgroups.
 
 Also lets say that the administrator would like to give enhanced network
@@ -153,9 +153,9 @@ apps enhanced CPU power,
 With ability to write pids directly to resource classes, it's just a
 matter of :
 
-       # echo pid > /mnt/network/<new_class>/tasks
+       # echo pid > /sys/fs/cgroup/network/<new_class>/tasks
        (after some time)
-       # echo pid > /mnt/network/<orig_class>/tasks
+       # echo pid > /sys/fs/cgroup/network/<orig_class>/tasks
 
 Without this ability, he would have to split the cgroup into
 multiple separate ones and then associate the new cgroups with the
@@ -310,21 +310,24 @@ subsystem, this is the case for the cpuset.
 To start a new job that is to be contained within a cgroup, using
 the "cpuset" cgroup subsystem, the steps are something like:
 
- 1) mkdir /dev/cgroup
- 2) mount -t cgroup -ocpuset cpuset /dev/cgroup
- 3) Create the new cgroup by doing mkdir's and write's (or echo's) in
-    the /dev/cgroup virtual file system.
- 4) Start a task that will be the "founding father" of the new job.
- 5) Attach that task to the new cgroup by writing its pid to the
-    /dev/cgroup tasks file for that cgroup.
- 6) fork, exec or clone the job tasks from this founding father task.
+ 1) mount -t tmpfs cgroup_root /sys/fs/cgroup
+ 2) mkdir /sys/fs/cgroup/cpuset
+ 3) mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset
+ 4) Create the new cgroup by doing mkdir's and write's (or echo's) in
+    the /sys/fs/cgroup virtual file system.
+ 5) Start a task that will be the "founding father" of the new job.
+ 6) Attach that task to the new cgroup by writing its pid to the
+    /sys/fs/cgroup/cpuset/tasks file for that cgroup.
+ 7) fork, exec or clone the job tasks from this founding father task.
 
 For example, the following sequence of commands will setup a cgroup
 named "Charlie", containing just CPUs 2 and 3, and Memory Node 1,
 and then start a subshell 'sh' in that cgroup:
 
-  mount -t cgroup cpuset -ocpuset /dev/cgroup
-  cd /dev/cgroup
+  mount -t tmpfs cgroup_root /sys/fs/cgroup
+  mkdir /sys/fs/cgroup/cpuset
+  mount -t cgroup cpuset -ocpuset /sys/fs/cgroup/cpuset
+  cd /sys/fs/cgroup/cpuset
   mkdir Charlie
   cd Charlie
   /bin/echo 2-3 > cpuset.cpus
@@ -345,7 +348,7 @@ Creating, modifying, using the cgroups can be done through the cgroup
 virtual filesystem.
 
 To mount a cgroup hierarchy with all available subsystems, type:
-# mount -t cgroup xxx /dev/cgroup
+# mount -t cgroup xxx /sys/fs/cgroup
 
 The "xxx" is not interpreted by the cgroup code, but will appear in
 /proc/mounts so may be any useful identifying string that you like.
@@ -354,23 +357,32 @@ Note: Some subsystems do not work without some user input first.  For instance,
 if cpusets are enabled the user will have to populate the cpus and mems files
 for each new cgroup created before that group can be used.
 
+As explained in section `1.2 Why are cgroups needed?' you should create
+different hierarchies of cgroups for each single resource or group of
+resources you want to control. Therefore, you should mount a tmpfs on
+/sys/fs/cgroup and create directories for each cgroup resource or resource
+group.
+
+# mount -t tmpfs cgroup_root /sys/fs/cgroup
+# mkdir /sys/fs/cgroup/rg1
+
 To mount a cgroup hierarchy with just the cpuset and memory
 subsystems, type:
-# mount -t cgroup -o cpuset,memory hier1 /dev/cgroup
+# mount -t cgroup -o cpuset,memory hier1 /sys/fs/cgroup/rg1
 
 To change the set of subsystems bound to a mounted hierarchy, just
 remount with different options:
-# mount -o remount,cpuset,blkio hier1 /dev/cgroup
+# mount -o remount,cpuset,blkio hier1 /sys/fs/cgroup/rg1
 
 Now memory is removed from the hierarchy and blkio is added.
 
 Note this will add blkio to the hierarchy but won't remove memory or
 cpuset, because the new options are appended to the old ones:
-# mount -o remount,blkio /dev/cgroup
+# mount -o remount,blkio /sys/fs/cgroup/rg1
 
 To Specify a hierarchy's release_agent:
 # mount -t cgroup -o cpuset,release_agent="/sbin/cpuset_release_agent" \
-  xxx /dev/cgroup
+  xxx /sys/fs/cgroup/rg1
 
 Note that specifying 'release_agent' more than once will return failure.
 
@@ -379,17 +391,17 @@ when the hierarchy consists of a single (root) cgroup. Supporting
 the ability to arbitrarily bind/unbind subsystems from an existing
 cgroup hierarchy is intended to be implemented in the future.
 
-Then under /dev/cgroup you can find a tree that corresponds to the
-tree of the cgroups in the system. For instance, /dev/cgroup
+Then under /sys/fs/cgroup/rg1 you can find a tree that corresponds to the
+tree of the cgroups in the system. For instance, /sys/fs/cgroup/rg1
 is the cgroup that holds the whole system.
 
 If you want to change the value of release_agent:
-# echo "/sbin/new_release_agent" > /dev/cgroup/release_agent
+# echo "/sbin/new_release_agent" > /sys/fs/cgroup/rg1/release_agent
 
 It can also be changed via remount.
 
-If you want to create a new cgroup under /dev/cgroup:
-# cd /dev/cgroup
+If you want to create a new cgroup under /sys/fs/cgroup/rg1:
+# cd /sys/fs/cgroup/rg1
 # mkdir my_cgroup
 
 Now you want to do something with this cgroup.
diff --git a/Documentation/cgroups/cpuacct.txt b/Documentation/cgroups/cpuacct.txt
index 8b930946c52a..9ad85df4b983 100644
--- a/Documentation/cgroups/cpuacct.txt
+++ b/Documentation/cgroups/cpuacct.txt
@@ -10,26 +10,25 @@ 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
+# mount -t cgroup -ocpuacct none /sys/fs/cgroup
+
+With the above step, the initial or the parent accounting group becomes
+visible at /sys/fs/cgroup. At bootup, this group includes all the tasks in
+the system. /sys/fs/cgroup/tasks lists the tasks in this cgroup.
+/sys/fs/cgroup/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.
+New accounting groups can be created under the parent group /sys/fs/cgroup.
 
-# cd /cgroups
+# cd /sys/fs/cgroup
 # 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.
+/sys/fs/cgroup/cpuacct.usage also.
 
 cpuacct.stat file lists a few statistics which further divide the
 CPU time obtained by the cgroup into user and system times. Currently
diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt
index 98a30829af7a..5b0d78e55ccc 100644
--- a/Documentation/cgroups/cpusets.txt
+++ b/Documentation/cgroups/cpusets.txt
@@ -661,21 +661,21 @@ than stress the kernel.
 
 To start a new job that is to be contained within a cpuset, the steps are:
 
- 1) mkdir /dev/cpuset
- 2) mount -t cgroup -ocpuset cpuset /dev/cpuset
+ 1) mkdir /sys/fs/cgroup/cpuset
+ 2) mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset
  3) Create the new cpuset by doing mkdir's and write's (or echo's) in
-    the /dev/cpuset virtual file system.
+    the /sys/fs/cgroup/cpuset virtual file system.
  4) Start a task that will be the "founding father" of the new job.
  5) Attach that task to the new cpuset by writing its pid to the
-    /dev/cpuset tasks file for that cpuset.
+    /sys/fs/cgroup/cpuset tasks file for that cpuset.
  6) fork, exec or clone the job tasks from this founding father task.
 
 For example, the following sequence of commands will setup a cpuset
 named "Charlie", containing just CPUs 2 and 3, and Memory Node 1,
 and then start a subshell 'sh' in that cpuset:
 
-  mount -t cgroup -ocpuset cpuset /dev/cpuset
-  cd /dev/cpuset
+  mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset
+  cd /sys/fs/cgroup/cpuset
   mkdir Charlie
   cd Charlie
   /bin/echo 2-3 > cpuset.cpus
@@ -710,14 +710,14 @@ Creating, modifying, using the cpusets can be done through the cpuset
 virtual filesystem.
 
 To mount it, type:
-# mount -t cgroup -o cpuset cpuset /dev/cpuset
+# mount -t cgroup -o cpuset cpuset /sys/fs/cgroup/cpuset
 
-Then under /dev/cpuset you can find a tree that corresponds to the
-tree of the cpusets in the system. For instance, /dev/cpuset
+Then under /sys/fs/cgroup/cpuset you can find a tree that corresponds to the
+tree of the cpusets in the system. For instance, /sys/fs/cgroup/cpuset
 is the cpuset that holds the whole system.
 
-If you want to create a new cpuset under /dev/cpuset:
-# cd /dev/cpuset
+If you want to create a new cpuset under /sys/fs/cgroup/cpuset:
+# cd /sys/fs/cgroup/cpuset
 # mkdir my_cpuset
 
 Now you want to do something with this cpuset.
@@ -765,12 +765,12 @@ wrapper around the cgroup filesystem.
 
 The command
 
-mount -t cpuset X /dev/cpuset
+mount -t cpuset X /sys/fs/cgroup/cpuset
 
 is equivalent to
 
-mount -t cgroup -ocpuset,noprefix X /dev/cpuset
-echo "/sbin/cpuset_release_agent" > /dev/cpuset/release_agent
+mount -t cgroup -ocpuset,noprefix X /sys/fs/cgroup/cpuset
+echo "/sbin/cpuset_release_agent" > /sys/fs/cgroup/cpuset/release_agent
 
 2.2 Adding/removing cpus
 ------------------------
diff --git a/Documentation/cgroups/devices.txt b/Documentation/cgroups/devices.txt
index 57ca4c89fe5c..16624a7f8222 100644
--- a/Documentation/cgroups/devices.txt
+++ b/Documentation/cgroups/devices.txt
@@ -22,16 +22,16 @@ removed from the child(ren).
 An entry is added using devices.allow, and removed using
 devices.deny.  For instance
 
-	echo 'c 1:3 mr' > /cgroups/1/devices.allow
+	echo 'c 1:3 mr' > /sys/fs/cgroup/1/devices.allow
 
 allows cgroup 1 to read and mknod the device usually known as
 /dev/null.  Doing
 
-	echo a > /cgroups/1/devices.deny
+	echo a > /sys/fs/cgroup/1/devices.deny
 
 will remove the default 'a *:* rwm' entry. Doing
 
-	echo a > /cgroups/1/devices.allow
+	echo a > /sys/fs/cgroup/1/devices.allow
 
 will add the 'a *:* rwm' entry to the whitelist.
 
diff --git a/Documentation/cgroups/freezer-subsystem.txt b/Documentation/cgroups/freezer-subsystem.txt
index 41f37fea1276..c21d77742a07 100644
--- a/Documentation/cgroups/freezer-subsystem.txt
+++ b/Documentation/cgroups/freezer-subsystem.txt
@@ -59,28 +59,28 @@ is non-freezable.
 
 * Examples of usage :
 
-   # mkdir /containers
-   # mount -t cgroup -ofreezer freezer  /containers
-   # mkdir /containers/0
-   # echo $some_pid > /containers/0/tasks
+   # mkdir /sys/fs/cgroup/freezer
+   # mount -t cgroup -ofreezer freezer /sys/fs/cgroup/freezer
+   # mkdir /sys/fs/cgroup/freezer/0
+   # echo $some_pid > /sys/fs/cgroup/freezer/0/tasks
 
 to get status of the freezer subsystem :
 
-   # cat /containers/0/freezer.state
+   # cat /sys/fs/cgroup/freezer/0/freezer.state
    THAWED
 
 to freeze all tasks in the container :
 
-   # echo FROZEN > /containers/0/freezer.state
-   # cat /containers/0/freezer.state
+   # echo FROZEN > /sys/fs/cgroup/freezer/0/freezer.state
+   # cat /sys/fs/cgroup/freezer/0/freezer.state
    FREEZING
-   # cat /containers/0/freezer.state
+   # cat /sys/fs/cgroup/freezer/0/freezer.state
    FROZEN
 
 to unfreeze all tasks in the container :
 
-   # echo THAWED > /containers/0/freezer.state
-   # cat /containers/0/freezer.state
+   # echo THAWED > /sys/fs/cgroup/freezer/0/freezer.state
+   # cat /sys/fs/cgroup/freezer/0/freezer.state
    THAWED
 
 This is the basic mechanism which should do the right thing for user space task
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 7c163477fcd8..06eb6d957c83 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -1,8 +1,8 @@
 Memory Resource Controller
 
-NOTE: The Memory Resource Controller has been generically been referred
-      to as the memory controller in this document. Do not confuse memory
-      controller used here with the memory controller that is used in hardware.
+NOTE: The Memory Resource Controller has generically been referred to as the
+      memory controller in this document. Do not confuse memory controller
+      used here with the memory controller that is used in hardware.
 
 (For editors)
 In this document:
@@ -70,6 +70,7 @@ Brief summary of control files.
 				 (See sysctl's vm.swappiness)
  memory.move_charge_at_immigrate # set/show controls of moving charges
  memory.oom_control		 # set/show oom controls.
+ memory.numa_stat		 # show the number of memory usage per numa node
 
 1. History
 
@@ -181,7 +182,7 @@ behind this approach is that a cgroup that aggressively uses a shared
 page will eventually get charged for it (once it is uncharged from
 the cgroup that brought it in -- this will happen on memory pressure).
 
-Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used..
+Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used.
 When you do swapoff and make swapped-out pages of shmem(tmpfs) to
 be backed into memory in force, charges for pages are accounted against the
 caller of swapoff rather than the users of shmem.
@@ -213,7 +214,7 @@ affecting global LRU, memory+swap limit is better than just limiting swap from
 OS point of view.
 
 * What happens when a cgroup hits memory.memsw.limit_in_bytes
-When a cgroup his memory.memsw.limit_in_bytes, it's useless to do swap-out
+When a cgroup hits memory.memsw.limit_in_bytes, it's useless to do swap-out
 in this cgroup. Then, swap-out will not be done by cgroup routine and file
 caches are dropped. But as mentioned above, global LRU can do swapout memory
 from it for sanity of the system's memory management state. You can't forbid
@@ -263,16 +264,17 @@ b. Enable CONFIG_RESOURCE_COUNTERS
 c. Enable CONFIG_CGROUP_MEM_RES_CTLR
 d. Enable CONFIG_CGROUP_MEM_RES_CTLR_SWAP (to use swap extension)
 
-1. Prepare the cgroups
-# mkdir -p /cgroups
-# mount -t cgroup none /cgroups -o memory
+1. Prepare the cgroups (see cgroups.txt, Why are cgroups needed?)
+# mount -t tmpfs none /sys/fs/cgroup
+# mkdir /sys/fs/cgroup/memory
+# mount -t cgroup none /sys/fs/cgroup/memory -o memory
 
 2. Make the new group and move bash into it
-# mkdir /cgroups/0
-# echo $$ > /cgroups/0/tasks
+# mkdir /sys/fs/cgroup/memory/0
+# echo $$ > /sys/fs/cgroup/memory/0/tasks
 
 Since now we're in the 0 cgroup, we can alter the memory limit:
-# echo 4M > /cgroups/0/memory.limit_in_bytes
+# echo 4M > /sys/fs/cgroup/memory/0/memory.limit_in_bytes
 
 NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo,
 mega or gigabytes. (Here, Kilo, Mega, Giga are Kibibytes, Mebibytes, Gibibytes.)
@@ -280,11 +282,11 @@ mega or gigabytes. (Here, Kilo, Mega, Giga are Kibibytes, Mebibytes, Gibibytes.)
 NOTE: We can write "-1" to reset the *.limit_in_bytes(unlimited).
 NOTE: We cannot set limits on the root cgroup any more.
 
-# cat /cgroups/0/memory.limit_in_bytes
+# cat /sys/fs/cgroup/memory/0/memory.limit_in_bytes
 4194304
 
 We can check the usage:
-# cat /cgroups/0/memory.usage_in_bytes
+# cat /sys/fs/cgroup/memory/0/memory.usage_in_bytes
 1216512
 
 A successful write to this file does not guarantee a successful set of
@@ -464,6 +466,24 @@ value for efficient access. (Of course, when necessary, it's synchronized.)
 If you want to know more exact memory usage, you should use RSS+CACHE(+SWAP)
 value in memory.stat(see 5.2).
 
+5.6 numa_stat
+
+This is similar to numa_maps but operates on a per-memcg basis.  This is
+useful for providing visibility into the numa locality information within
+an memcg since the pages are allowed to be allocated from any physical
+node.  One of the usecases is evaluating application performance by
+combining this information with the application's cpu allocation.
+
+We export "total", "file", "anon" and "unevictable" pages per-node for
+each memcg.  The ouput format of memory.numa_stat is:
+
+total=<total pages> N0=<node 0 pages> N1=<node 1 pages> ...
+file=<total file pages> N0=<node 0 pages> N1=<node 1 pages> ...
+anon=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ...
+unevictable=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ...
+
+And we have total = file + anon + unevictable.
+
 6. Hierarchy support
 
 The memory controller supports a deep hierarchy and hierarchical accounting.
@@ -471,13 +491,13 @@ The hierarchy is created by creating the appropriate cgroups in the
 cgroup filesystem. Consider for example, the following cgroup filesystem
 hierarchy
 
-		root
+	       root
 	     /  |   \
-           /	|    \
-	  a	b	c
-			| \
-			|  \
-			d   e
+            /	|    \
+	   a	b     c
+		      | \
+		      |  \
+		      d   e
 
 In the diagram above, with hierarchical accounting enabled, all memory
 usage of e, is accounted to its ancestors up until the root (i.e, c and root),
diff --git a/Documentation/devicetree/booting-without-of.txt b/Documentation/devicetree/booting-without-of.txt
index 50619a0720a8..7c1329de0596 100644
--- a/Documentation/devicetree/booting-without-of.txt
+++ b/Documentation/devicetree/booting-without-of.txt
@@ -12,8 +12,9 @@ Table of Contents
 =================
 
   I - Introduction
-    1) Entry point for arch/powerpc
-    2) Entry point for arch/x86
+    1) Entry point for arch/arm
+    2) Entry point for arch/powerpc
+    3) Entry point for arch/x86
 
   II - The DT block format
     1) Header
@@ -148,7 +149,46 @@ upgrades without significantly impacting the kernel code or cluttering
 it with special cases.
 
 
-1) Entry point for arch/powerpc
+1) Entry point for arch/arm
+---------------------------
+
+   There is one single entry point to the kernel, at the start
+   of the kernel image. That entry point supports two calling
+   conventions.  A summary of the interface is described here.  A full
+   description of the boot requirements is documented in
+   Documentation/arm/Booting
+
+        a) ATAGS interface.  Minimal information is passed from firmware
+        to the kernel with a tagged list of predefined parameters.
+
+                r0 : 0
+
+                r1 : Machine type number
+
+                r2 : Physical address of tagged list in system RAM
+
+        b) Entry with a flattened device-tree block.  Firmware loads the
+        physical address of the flattened device tree block (dtb) into r2,
+        r1 is not used, but it is considered good practise to use a valid
+        machine number as described in Documentation/arm/Booting.
+
+                r0 : 0
+
+                r1 : Valid machine type number.  When using a device tree,
+                a single machine type number will often be assigned to
+                represent a class or family of SoCs.
+
+                r2 : physical pointer to the device-tree block
+                (defined in chapter II) in RAM.  Device tree can be located
+                anywhere in system RAM, but it should be aligned on a 64 bit
+                boundary.
+
+   The kernel will differentiate between ATAGS and device tree booting by
+   reading the memory pointed to by r2 and looking for either the flattened
+   device tree block magic value (0xd00dfeed) or the ATAG_CORE value at
+   offset 0x4 from r2 (0x54410001).
+
+2) Entry point for arch/powerpc
 -------------------------------
 
    There is one single entry point to the kernel, at the start
@@ -226,7 +266,7 @@ it with special cases.
   cannot support both configurations with Book E and configurations
   with classic Powerpc architectures.
 
-2) Entry point for arch/x86
+3) Entry point for arch/x86
 -------------------------------
 
   There is one single 32bit entry point to the kernel at code32_start,
diff --git a/Documentation/dmaengine.txt b/Documentation/dmaengine.txt
index 0c1c2f63c0a9..5a0cb1ef6164 100644
--- a/Documentation/dmaengine.txt
+++ b/Documentation/dmaengine.txt
@@ -1 +1,96 @@
-See Documentation/crypto/async-tx-api.txt
+			DMA Engine API Guide
+			====================
+
+		 Vinod Koul <vinod dot koul at intel.com>
+
+NOTE: For DMA Engine usage in async_tx please see:
+	Documentation/crypto/async-tx-api.txt
+
+
+Below is a guide to device driver writers on how to use the Slave-DMA API of the
+DMA Engine. This is applicable only for slave DMA usage only.
+
+The slave DMA usage consists of following steps
+1. Allocate a DMA slave channel
+2. Set slave and controller specific parameters
+3. Get a descriptor for transaction
+4. Submit the transaction and wait for callback notification
+
+1. Allocate a DMA slave channel
+Channel allocation is slightly different in the slave DMA context, client
+drivers typically need a channel from a particular DMA controller only and even
+in some cases a specific channel is desired. To request a channel
+dma_request_channel() API is used.
+
+Interface:
+struct dma_chan *dma_request_channel(dma_cap_mask_t mask,
+		dma_filter_fn filter_fn,
+		void *filter_param);
+where dma_filter_fn is defined as:
+typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
+
+When the optional 'filter_fn' parameter is set to NULL dma_request_channel
+simply returns the first channel that satisfies the capability mask.  Otherwise,
+when the mask parameter is insufficient for specifying the necessary channel,
+the filter_fn routine can be used to disposition the available channels in the
+system. The filter_fn routine is called once for each free channel in the
+system.  Upon seeing a suitable channel filter_fn returns DMA_ACK which flags
+that channel to be the return value from dma_request_channel.  A channel
+allocated via this interface is exclusive to the caller, until
+dma_release_channel() is called.
+
+2. Set slave and controller specific parameters
+Next step is always to pass some specific information to the DMA driver. Most of
+the generic information which a slave DMA can use is in struct dma_slave_config.
+It allows the clients to specify DMA direction, DMA addresses, bus widths, DMA
+burst lengths etc. If some DMA controllers have more parameters to be sent then
+they should try to embed struct dma_slave_config in their controller specific
+structure. That gives flexibility to client to pass more parameters, if
+required.
+
+Interface:
+int dmaengine_slave_config(struct dma_chan *chan,
+					  struct dma_slave_config *config)
+
+3. Get a descriptor for transaction
+For slave usage the various modes of slave transfers supported by the
+DMA-engine are:
+slave_sg	- DMA a list of scatter gather buffers from/to a peripheral
+dma_cyclic	- Perform a cyclic DMA operation from/to a peripheral till the
+		  operation is explicitly stopped.
+The non NULL return of this transfer API represents a "descriptor" for the given
+transaction.
+
+Interface:
+struct dma_async_tx_descriptor *(*chan->device->device_prep_dma_sg)(
+		struct dma_chan *chan,
+		struct scatterlist *dst_sg, unsigned int dst_nents,
+		struct scatterlist *src_sg, unsigned int src_nents,
+		unsigned long flags);
+struct dma_async_tx_descriptor *(*chan->device->device_prep_dma_cyclic)(
+		struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+		size_t period_len, enum dma_data_direction direction);
+
+4. Submit the transaction and wait for callback notification
+To schedule the transaction to be scheduled by dma device, the "descriptor"
+returned in above (3) needs to be submitted.
+To tell the dma driver that a transaction is ready to be serviced, the
+descriptor->submit() callback needs to be invoked. This chains the descriptor to
+the pending queue.
+The transactions in the pending queue can be activated by calling the
+issue_pending API. If channel is idle then the first transaction in queue is
+started and subsequent ones queued up.
+On completion of the DMA operation the next in queue is submitted and a tasklet
+triggered. The tasklet would then call the client driver completion callback
+routine for notification, if set.
+Interface:
+void dma_async_issue_pending(struct dma_chan *chan);
+
+==============================================================================
+
+Additional usage notes for dma driver writers
+1/ Although DMA engine specifies that completion callback routines cannot submit
+any new operations, but typically for slave DMA subsequent transaction may not
+be available for submit prior to callback routine being called. This requirement
+is not a requirement for DMA-slave devices. But they should take care to drop
+the spin-lock they might be holding before calling the callback routine
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index ff31b1cc50aa..72e238465b0b 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -6,6 +6,42 @@ be removed from this file.
 
 ---------------------------
 
+What:	x86 floppy disable_hlt
+When:	2012
+Why:	ancient workaround of dubious utility clutters the
+	code used by everybody else.
+Who:	Len Brown <len.brown@intel.com>
+
+---------------------------
+
+What:	CONFIG_APM_CPU_IDLE, and its ability to call APM BIOS in idle
+When:	2012
+Why:	This optional sub-feature of APM is of dubious reliability,
+	and ancient APM laptops are likely better served by calling HLT.
+	Deleting CONFIG_APM_CPU_IDLE allows x86 to stop exporting
+	the pm_idle function pointer to modules.
+Who:	Len Brown <len.brown@intel.com>
+
+----------------------------
+
+What:	x86_32 "no-hlt" cmdline param
+When:	2012
+Why:	remove a branch from idle path, simplify code used by everybody.
+	This option disabled the use of HLT in idle and machine_halt()
+	for hardware that was flakey 15-years ago.  Today we have
+	"idle=poll" that removed HLT from idle, and so if such a machine
+	is still running the upstream kernel, "idle=poll" is likely sufficient.
+Who:	Len Brown <len.brown@intel.com>
+
+----------------------------
+
+What:	x86 "idle=mwait" cmdline param
+When:	2012
+Why:	simplify x86 idle code
+Who:	Len Brown <len.brown@intel.com>
+
+----------------------------
+
 What:	PRISM54
 When:	2.6.34
 
@@ -445,23 +481,6 @@ Who:	FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
 
 ----------------------------
 
-What:   namespace cgroup (ns_cgroup)
-When:   2.6.38
-Why:    The ns_cgroup leads to some problems:
-	* cgroup creation is out-of-control
-	* cgroup name can conflict when pids are looping
-	* it is not possible to have a single process handling
-	a lot of namespaces without falling in a exponential creation time
-	* we may want to create a namespace without creating a cgroup
-
-	The ns_cgroup is replaced by a compatibility flag 'clone_children',
-	where a newly created cgroup will copy the parent cgroup values.
-	The userspace has to manually create a cgroup and add a task to
-	the 'tasks' file.
-Who:    Daniel Lezcano <daniel.lezcano@free.fr>
-
-----------------------------
-
 What:	iwlwifi disable_hw_scan module parameters
 When:	2.6.40
 Why:	Hareware scan is the prefer method for iwlwifi devices for
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 61b31acb9176..57d827d6071d 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -104,7 +104,7 @@ of the locking scheme for directory operations.
 prototypes:
 	struct inode *(*alloc_inode)(struct super_block *sb);
 	void (*destroy_inode)(struct inode *);
-	void (*dirty_inode) (struct inode *);
+	void (*dirty_inode) (struct inode *, int flags);
 	int (*write_inode) (struct inode *, struct writeback_control *wbc);
 	int (*drop_inode) (struct inode *);
 	void (*evict_inode) (struct inode *);
@@ -126,7 +126,7 @@ locking rules:
 			s_umount
 alloc_inode:
 destroy_inode:
-dirty_inode:				(must not sleep)
+dirty_inode:
 write_inode:
 drop_inode:				!!!inode->i_lock!!!
 evict_inode:
diff --git a/Documentation/filesystems/nfs/idmapper.txt b/Documentation/filesystems/nfs/idmapper.txt
index b9b4192ea8b5..9c8fd6148656 100644
--- a/Documentation/filesystems/nfs/idmapper.txt
+++ b/Documentation/filesystems/nfs/idmapper.txt
@@ -47,8 +47,8 @@ request-key will find the first matching line and corresponding program.  In
 this case, /some/other/program will handle all uid lookups and
 /usr/sbin/nfs.idmap will handle gid, user, and group lookups.
 
-See <file:Documentation/keys-request-keys.txt> for more information about the
-request-key function.
+See <file:Documentation/security/keys-request-keys.txt> for more information
+about the request-key function.
 
 
 =========
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index f48178024067..db3b1aba32a3 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -843,6 +843,7 @@ Provides counts of softirq handlers serviced since boot time, for each cpu.
  TASKLET:          0          0          0        290
    SCHED:      27035      26983      26971      26746
  HRTIMER:          0          0          0          0
+     RCU:       1678       1769       2178       2250
 
 
 1.3 IDE devices in /proc/ide
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 21a7dc467bba..88b9f5519af9 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -211,7 +211,7 @@ struct super_operations {
         struct inode *(*alloc_inode)(struct super_block *sb);
         void (*destroy_inode)(struct inode *);
 
-        void (*dirty_inode) (struct inode *);
+        void (*dirty_inode) (struct inode *, int flags);
         int (*write_inode) (struct inode *, int);
         void (*drop_inode) (struct inode *);
         void (*delete_inode) (struct inode *);
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 5438a2d7907f..fd248a318211 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -999,7 +999,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			With this option on every unmap_single operation will
 			result in a hardware IOTLB flush operation as opposed
 			to batching them for performance.
-
+		sp_off [Default Off]
+			By default, super page will be supported if Intel IOMMU
+			has the capability. With this option, super page will
+			not be supported.
 	intremap=	[X86-64, Intel-IOMMU]
 			Format: { on (default) | off | nosid }
 			on	enable Interrupt Remapping (default)
@@ -2595,6 +2598,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 					unlock ejectable media);
 				m = MAX_SECTORS_64 (don't transfer more
 					than 64 sectors = 32 KB at a time);
+				n = INITIAL_READ10 (force a retry of the
+					initial READ(10) command);
 				o = CAPACITY_OK (accept the capacity
 					reported by the device);
 				r = IGNORE_RESIDUE (the device reports
diff --git a/Documentation/kmemleak.txt b/Documentation/kmemleak.txt
index 090e6ee04536..51063e681ca4 100644
--- a/Documentation/kmemleak.txt
+++ b/Documentation/kmemleak.txt
@@ -11,7 +11,9 @@ with the difference that the orphan objects are not freed but only
 reported via /sys/kernel/debug/kmemleak. A similar method is used by the
 Valgrind tool (memcheck --leak-check) to detect the memory leaks in
 user-space applications.
-Kmemleak is supported on x86, arm, powerpc, sparc, sh, microblaze and tile.
+
+Please check DEBUG_KMEMLEAK dependencies in lib/Kconfig.debug for supported
+architectures.
 
 Usage
 -----
diff --git a/Documentation/laptops/acer-wmi.txt b/Documentation/laptops/acer-wmi.txt
deleted file mode 100644
index 4beafa663dd6..000000000000
--- a/Documentation/laptops/acer-wmi.txt
+++ /dev/null
@@ -1,184 +0,0 @@
-Acer Laptop WMI Extras Driver
-http://code.google.com/p/aceracpi
-Version 0.3
-4th April 2009
-
-Copyright 2007-2009 Carlos Corbacho <carlos@strangeworlds.co.uk>
-
-acer-wmi is a driver to allow you to control various parts of your Acer laptop
-hardware under Linux which are exposed via ACPI-WMI.
-
-This driver completely replaces the old out-of-tree acer_acpi, which I am
-currently maintaining for bug fixes only on pre-2.6.25 kernels. All development
-work is now focused solely on acer-wmi.
-
-Disclaimer
-**********
-
-Acer and Wistron have provided nothing towards the development acer_acpi or
-acer-wmi. All information we have has been through the efforts of the developers
-and the users to discover as much as possible about the hardware.
-
-As such, I do warn that this could break your hardware - this is extremely
-unlikely of course, but please bear this in mind.
-
-Background
-**********
-
-acer-wmi is derived from acer_acpi, originally developed by Mark
-Smith in 2005, then taken over by Carlos Corbacho in 2007, in order to activate
-the wireless LAN card under a 64-bit version of Linux, as acerhk[1] (the
-previous solution to the problem) relied on making 32 bit BIOS calls which are
-not possible in kernel space from a 64 bit OS.
-
-[1] acerhk: http://www.cakey.de/acerhk/
-
-Supported Hardware
-******************
-
-NOTE: The Acer Aspire One is not supported hardware. It cannot work with
-acer-wmi until Acer fix their ACPI-WMI implementation on them, so has been
-blacklisted until that happens.
-
-Please see the website for the current list of known working hardware:
-
-http://code.google.com/p/aceracpi/wiki/SupportedHardware
-
-If your laptop is not listed, or listed as unknown, and works with acer-wmi,
-please contact me with a copy of the DSDT.
-
-If your Acer laptop doesn't work with acer-wmi, I would also like to see the
-DSDT.
-
-To send me the DSDT, as root/sudo:
-
-cat /sys/firmware/acpi/tables/DSDT > dsdt
-
-And send me the resulting 'dsdt' file.
-
-Usage
-*****
-
-On Acer laptops, acer-wmi should already be autoloaded based on DMI matching.
-For non-Acer laptops, until WMI based autoloading support is added, you will
-need to manually load acer-wmi.
-
-acer-wmi creates /sys/devices/platform/acer-wmi, and fills it with various
-files whose usage is detailed below, which enables you to control some of the
-following (varies between models):
-
-* the wireless LAN card radio
-* inbuilt Bluetooth adapter
-* inbuilt 3G card
-* mail LED of your laptop
-* brightness of the LCD panel
-
-Wireless
-********
-
-With regards to wireless, all acer-wmi does is enable the radio on the card. It
-is not responsible for the wireless LED - once the radio is enabled, this is
-down to the wireless driver for your card. So the behaviour of the wireless LED,
-once you enable the radio, will depend on your hardware and driver combination.
-
-e.g. With the BCM4318 on the Acer Aspire 5020 series:
-
-ndiswrapper: Light blinks on when transmitting
-b43: Solid light, blinks off when transmitting
-
-Wireless radio control is unconditionally enabled - all Acer laptops that support
-acer-wmi come with built-in wireless. However, should you feel so inclined to
-ever wish to remove the card, or swap it out at some point, please get in touch
-with me, as we may well be able to gain some data on wireless card detection.
-
-The wireless radio is exposed through rfkill.
-
-Bluetooth
-*********
-
-For bluetooth, this is an internal USB dongle, so once enabled, you will get
-a USB device connection event, and a new USB device appears. When you disable
-bluetooth, you get the reverse - a USB device disconnect event, followed by the
-device disappearing again.
-
-Bluetooth is autodetected by acer-wmi, so if you do not have a bluetooth module
-installed in your laptop, this file won't exist (please be aware that it is
-quite common for Acer not to fit bluetooth to their laptops - so just because
-you have a bluetooth button on the laptop, doesn't mean that bluetooth is
-installed).
-
-For the adventurously minded - if you want to buy an internal bluetooth
-module off the internet that is compatible with your laptop and fit it, then
-it will work just fine with acer-wmi.
-
-Bluetooth is exposed through rfkill.
-
-3G
-**
-
-3G is currently not autodetected, so the 'threeg' file is always created under
-sysfs. So far, no-one in possession of an Acer laptop with 3G built-in appears to
-have tried Linux, or reported back, so we don't have any information on this.
-
-If you have an Acer laptop that does have a 3G card in, please contact me so we
-can properly detect these, and find out a bit more about them.
-
-To read the status of the 3G card (0=off, 1=on):
-cat /sys/devices/platform/acer-wmi/threeg
-
-To enable the 3G card:
-echo 1 > /sys/devices/platform/acer-wmi/threeg
-
-To disable the 3G card:
-echo 0 > /sys/devices/platform/acer-wmi/threeg
-
-To set the state of the 3G card when loading acer-wmi, pass:
-threeg=X (where X is 0 or 1)
-
-Mail LED
-********
-
-This can be found in most older Acer laptops supported by acer-wmi, and many
-newer ones - it is built into the 'mail' button, and blinks when active.
-
-On newer (WMID) laptops though, we have no way of detecting the mail LED. If
-your laptop identifies itself in dmesg as a WMID model, then please try loading
-acer_acpi with:
-
-force_series=2490
-
-This will use a known alternative method of reading/ writing the mail LED. If
-it works, please report back to me with the DMI data from your laptop so this
-can be added to acer-wmi.
-
-The LED is exposed through the LED subsystem, and can be found in:
-
-/sys/devices/platform/acer-wmi/leds/acer-wmi::mail/
-
-The mail LED is autodetected, so if you don't have one, the LED device won't
-be registered.
-
-Backlight
-*********
-
-The backlight brightness control is available on all acer-wmi supported
-hardware. The maximum brightness level is usually 15, but on some newer laptops
-it's 10 (this is again autodetected).
-
-The backlight is exposed through the backlight subsystem, and can be found in:
-
-/sys/devices/platform/acer-wmi/backlight/acer-wmi/
-
-Credits
-*******
-
-Olaf Tauber, who did the real hard work when he developed acerhk
-http://www.cakey.de/acerhk/
-All the authors of laptop ACPI modules in the kernel, whose work
-was an inspiration in the early days of acer_acpi
-Mathieu Segaud, who solved the problem with having to modprobe the driver
-twice in acer_acpi 0.2.
-Jim Ramsay, who added support for the WMID interface
-Mark Smith, who started the original acer_acpi
-
-And the many people who have used both acer_acpi and acer-wmi.
diff --git a/Documentation/lockstat.txt b/Documentation/lockstat.txt
index 9c0a80d17a23..cef00d42ed5b 100644
--- a/Documentation/lockstat.txt
+++ b/Documentation/lockstat.txt
@@ -12,8 +12,9 @@ Because things like lock contention can severely impact performance.
 - HOW
 
 Lockdep already has hooks in the lock functions and maps lock instances to
-lock classes. We build on that. The graph below shows the relation between
-the lock functions and the various hooks therein.
+lock classes. We build on that (see Documentation/lockdep-design.txt).
+The graph below shows the relation between the lock functions and the various
+hooks therein.
 
         __acquire
             |
@@ -128,6 +129,37 @@ points are the points we're contending with.
 
 The integer part of the time values is in us.
 
+Dealing with nested locks, subclasses may appear:
+
+32...............................................................................................................................................................................................
+33
+34                               &rq->lock:         13128          13128           0.43         190.53      103881.26          97454        3453404           0.00         401.11    13224683.11
+35                               ---------
+36                               &rq->lock            645          [<ffffffff8103bfc4>] task_rq_lock+0x43/0x75
+37                               &rq->lock            297          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
+38                               &rq->lock            360          [<ffffffff8103c4c5>] select_task_rq_fair+0x1f0/0x74a
+39                               &rq->lock            428          [<ffffffff81045f98>] scheduler_tick+0x46/0x1fb
+40                               ---------
+41                               &rq->lock             77          [<ffffffff8103bfc4>] task_rq_lock+0x43/0x75
+42                               &rq->lock            174          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
+43                               &rq->lock           4715          [<ffffffff8103ed4b>] double_rq_lock+0x42/0x54
+44                               &rq->lock            893          [<ffffffff81340524>] schedule+0x157/0x7b8
+45
+46...............................................................................................................................................................................................
+47
+48                             &rq->lock/1:         11526          11488           0.33         388.73      136294.31          21461          38404           0.00          37.93      109388.53
+49                             -----------
+50                             &rq->lock/1          11526          [<ffffffff8103ed58>] double_rq_lock+0x4f/0x54
+51                             -----------
+52                             &rq->lock/1           5645          [<ffffffff8103ed4b>] double_rq_lock+0x42/0x54
+53                             &rq->lock/1           1224          [<ffffffff81340524>] schedule+0x157/0x7b8
+54                             &rq->lock/1           4336          [<ffffffff8103ed58>] double_rq_lock+0x4f/0x54
+55                             &rq->lock/1            181          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
+
+Line 48 shows statistics for the second subclass (/1) of &rq->lock class
+(subclass starts from 0), since in this case, as line 50 suggests,
+double_rq_lock actually acquires a nested lock of two spinlocks.
+
 View the top contending locks:
 
 # grep : /proc/lock_stat | head
diff --git a/Documentation/md.txt b/Documentation/md.txt
index 2366b1c8cf19..f0eee83ff78a 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -555,7 +555,7 @@ also have
    sync_min
    sync_max
      The two values, given as numbers of sectors, indicate a range
-     withing the array where 'check'/'repair' will operate. Must be
+     within the array where 'check'/'repair' will operate. Must be
      a multiple of chunk_size. When it reaches "sync_max" it will
      pause, rather than complete.
      You can use 'select' or 'poll' on "sync_completed" to wait for
diff --git a/Documentation/networking/dns_resolver.txt b/Documentation/networking/dns_resolver.txt
index 04ca06325b08..7f531ad83285 100644
--- a/Documentation/networking/dns_resolver.txt
+++ b/Documentation/networking/dns_resolver.txt
@@ -139,8 +139,8 @@ the key will be discarded and recreated when the data it holds has expired.
 dns_query() returns a copy of the value attached to the key, or an error if
 that is indicated instead.
 
-See <file:Documentation/keys-request-key.txt> for further information about
-request-key function.
+See <file:Documentation/security/keys-request-key.txt> for further
+information about request-key function.
 
 
 =========
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index 88880839ece4..64565aac6e40 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -520,59 +520,20 @@ Support for power domains is provided through the pwr_domain field of struct
 device.  This field is a pointer to an object of type struct dev_power_domain,
 defined in include/linux/pm.h, providing a set of power management callbacks
 analogous to the subsystem-level and device driver callbacks that are executed
-for the given device during all power transitions, in addition to the respective
-subsystem-level callbacks.  Specifically, the power domain "suspend" callbacks
-(i.e. ->runtime_suspend(), ->suspend(), ->freeze(), ->poweroff(), etc.) are
-executed after the analogous subsystem-level callbacks, while the power domain
-"resume" callbacks (i.e. ->runtime_resume(), ->resume(), ->thaw(), ->restore,
-etc.) are executed before the analogous subsystem-level callbacks.  Error codes
-returned by the "suspend" and "resume" power domain callbacks are ignored.
-
-Power domain ->runtime_idle() callback is executed before the subsystem-level
-->runtime_idle() callback and the result returned by it is not ignored.  Namely,
-if it returns error code, the subsystem-level ->runtime_idle() callback will not
-be called and the helper function rpm_idle() executing it will return error
-code.  This mechanism is intended to help platforms where saving device state
-is a time consuming operation and should only be carried out if all devices
-in the power domain are idle, before turning off the shared power resource(s).
-Namely, the power domain ->runtime_idle() callback may return error code until
-the pm_runtime_idle() helper (or its asychronous version) has been called for
-all devices in the power domain (it is recommended that the returned error code
-be -EBUSY in those cases), preventing the subsystem-level ->runtime_idle()
-callback from being run prematurely.
-
-The support for device power domains is only relevant to platforms needing to
-use the same subsystem-level (e.g. platform bus type) and device driver power
-management callbacks in many different power domain configurations and wanting
-to avoid incorporating the support for power domains into the subsystem-level
-callbacks.  The other platforms need not implement it or take it into account
-in any way.
-
-
-System Devices
---------------
-System devices (sysdevs) follow a slightly different API, which can be found in
-
-	include/linux/sysdev.h
-	drivers/base/sys.c
-
-System devices will be suspended with interrupts disabled, and after all other
-devices have been suspended.  On resume, they will be resumed before any other
-devices, and also with interrupts disabled.  These things occur in special
-"sysdev_driver" phases, which affect only system devices.
-
-Thus, after the suspend_noirq (or freeze_noirq or poweroff_noirq) phase, when
-the non-boot CPUs are all offline and IRQs are disabled on the remaining online
-CPU, then a sysdev_driver.suspend phase is carried out, and the system enters a
-sleep state (or a system image is created).  During resume (or after the image
-has been created or loaded) a sysdev_driver.resume phase is carried out, IRQs
-are enabled on the only online CPU, the non-boot CPUs are enabled, and the
-resume_noirq (or thaw_noirq or restore_noirq) phase begins.
-
-Code to actually enter and exit the system-wide low power state sometimes
-involves hardware details that are only known to the boot firmware, and
-may leave a CPU running software (from SRAM or flash memory) that monitors
-the system and manages its wakeup sequence.
+for the given device during all power transitions, instead of the respective
+subsystem-level callbacks.  Specifically, if a device's pm_domain pointer is
+not NULL, the ->suspend() callback from the object pointed to by it will be
+executed instead of its subsystem's (e.g. bus type's) ->suspend() callback and
+anlogously for all of the remaining callbacks.  In other words, power management
+domain callbacks, if defined for the given device, always take precedence over
+the callbacks provided by the device's subsystem (e.g. bus type).
+
+The support for device power management domains is only relevant to platforms
+needing to use the same device driver power management callbacks in many
+different power domain configurations and wanting to avoid incorporating the
+support for power domains into subsystem-level callbacks, for example by
+modifying the platform bus type.  Other platforms need not implement it or take
+it into account in any way.
 
 
 Device Low Power (suspend) States
diff --git a/Documentation/power/regulator/machine.txt b/Documentation/power/regulator/machine.txt
index bdec39b9bd75..b42419b52e44 100644
--- a/Documentation/power/regulator/machine.txt
+++ b/Documentation/power/regulator/machine.txt
@@ -53,11 +53,11 @@ static struct regulator_init_data regulator1_data = {
 
 Regulator-1 supplies power to Regulator-2. This relationship must be registered
 with the core so that Regulator-1 is also enabled when Consumer A enables its
-supply (Regulator-2). The supply regulator is set by the supply_regulator_dev
+supply (Regulator-2). The supply regulator is set by the supply_regulator
 field below:-
 
 static struct regulator_init_data regulator2_data = {
-	.supply_regulator_dev = &platform_regulator1_device.dev,
+	.supply_regulator = "regulator_name",
 	.constraints = {
 		.min_uV = 1800000,
 		.max_uV = 2000000,
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 654097b130b4..22accb3eb40e 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -566,11 +566,6 @@ to do this is:
 	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
 
-The PM core always increments the run-time usage counter before calling the
-->prepare() callback and decrements it after calling the ->complete() callback.
-Hence disabling run-time PM temporarily like this will not cause any run-time
-suspend callbacks to be lost.
-
 7. Generic subsystem callbacks
 
 Subsystems may wish to conserve code space by using the set of generic power
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index 1b5a5ddbc3ef..5df176ed59b8 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -9,7 +9,121 @@ If variable is of Type,		use printk format specifier:
 		size_t			%zu or %zx
 		ssize_t			%zd or %zx
 
-Raw pointer value SHOULD be printed with %p.
+Raw pointer value SHOULD be printed with %p. The kernel supports
+the following extended format specifiers for pointer types:
+
+Symbols/Function Pointers:
+
+	%pF	versatile_init+0x0/0x110
+	%pf	versatile_init
+	%pS	versatile_init+0x0/0x110
+	%ps	versatile_init
+	%pB	prev_fn_of_versatile_init+0x88/0x88
+
+	For printing symbols and function pointers. The 'S' and 's' specifiers
+	result in the symbol name with ('S') or without ('s') offsets. Where
+	this is used on a kernel without KALLSYMS - the symbol address is
+	printed instead.
+
+	The 'B' specifier results in the symbol name with offsets and should be
+	used when printing stack backtraces. The specifier takes into
+	consideration the effect of compiler optimisations which may occur
+	when tail-call's are used and marked with the noreturn GCC attribute.
+
+	On ia64, ppc64 and parisc64 architectures function pointers are
+	actually function descriptors which must first be resolved. The 'F' and
+	'f' specifiers perform this resolution and then provide the same
+	functionality as the 'S' and 's' specifiers.
+
+Kernel Pointers:
+
+	%pK	0x01234567 or 0x0123456789abcdef
+
+	For printing kernel pointers which should be hidden from unprivileged
+	users. The behaviour of %pK depends on the kptr_restrict sysctl - see
+	Documentation/sysctl/kernel.txt for more details.
+
+Struct Resources:
+
+	%pr	[mem 0x60000000-0x6fffffff flags 0x2200] or
+		[mem 0x0000000060000000-0x000000006fffffff flags 0x2200]
+	%pR	[mem 0x60000000-0x6fffffff pref] or
+		[mem 0x0000000060000000-0x000000006fffffff pref]
+
+	For printing struct resources. The 'R' and 'r' specifiers result in a
+	printed resource with ('R') or without ('r') a decoded flags member.
+
+MAC/FDDI addresses:
+
+	%pM	00:01:02:03:04:05
+	%pMF	00-01-02-03-04-05
+	%pm	000102030405
+
+	For printing 6-byte MAC/FDDI addresses in hex notation. The 'M' and 'm'
+	specifiers result in a printed address with ('M') or without ('m') byte
+	separators. The default byte separator is the colon (':').
+
+	Where FDDI addresses are concerned the 'F' specifier can be used after
+	the 'M' specifier to use dash ('-') separators instead of the default
+	separator.
+
+IPv4 addresses:
+
+	%pI4	1.2.3.4
+	%pi4	001.002.003.004
+	%p[Ii][hnbl]
+
+	For printing IPv4 dot-separated decimal addresses. The 'I4' and 'i4'
+	specifiers result in a printed address with ('i4') or without ('I4')
+	leading zeros.
+
+	The additional 'h', 'n', 'b', and 'l' specifiers are used to specify
+	host, network, big or little endian order addresses respectively. Where
+	no specifier is provided the default network/big endian order is used.
+
+IPv6 addresses:
+
+	%pI6	0001:0002:0003:0004:0005:0006:0007:0008
+	%pi6	00010002000300040005000600070008
+	%pI6c	1:2:3:4:5:6:7:8
+
+	For printing IPv6 network-order 16-bit hex addresses. The 'I6' and 'i6'
+	specifiers result in a printed address with ('I6') or without ('i6')
+	colon-separators. Leading zeros are always used.
+
+	The additional 'c' specifier can be used with the 'I' specifier to
+	print a compressed IPv6 address as described by
+	http://tools.ietf.org/html/rfc5952
+
+UUID/GUID addresses:
+
+	%pUb	00010203-0405-0607-0809-0a0b0c0d0e0f
+	%pUB	00010203-0405-0607-0809-0A0B0C0D0E0F
+	%pUl	03020100-0504-0706-0809-0a0b0c0e0e0f
+	%pUL	03020100-0504-0706-0809-0A0B0C0E0E0F
+
+	For printing 16-byte UUID/GUIDs addresses. The additional 'l', 'L',
+	'b' and 'B' specifiers are used to specify a little endian order in
+	lower ('l') or upper case ('L') hex characters - and big endian order
+	in lower ('b') or upper case ('B') hex characters.
+
+	Where no additional specifiers are used the default little endian
+	order with lower case hex characters will be printed.
+
+struct va_format:
+
+	%pV
+
+	For printing struct va_format structures. These contain a format string
+	and va_list as follows:
+
+	struct va_format {
+		const char *fmt;
+		va_list *va;
+	};
+
+	Do not use this feature without some mechanism to verify the
+	correctness of the format string and va_list arguments.
 
 u64 SHOULD be printed with %llu/%llx, (unsigned long long):
 
@@ -32,4 +146,5 @@ Reminder: sizeof() result is of type size_t.
 Thank you for your cooperation and attention.
 
 
-By Randy Dunlap <rdunlap@xenotime.net>
+By Randy Dunlap <rdunlap@xenotime.net> and
+Andrew Murray <amurray@mpc-data.co.uk>
diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt
index 99961993257a..91ecff07cede 100644
--- a/Documentation/scheduler/sched-design-CFS.txt
+++ b/Documentation/scheduler/sched-design-CFS.txt
@@ -223,9 +223,10 @@ When CONFIG_FAIR_GROUP_SCHED is defined, a "cpu.shares" file is created for each
 group created using the pseudo filesystem.  See example steps below to create
 task groups and modify their CPU share using the "cgroups" pseudo filesystem.
 
-	# mkdir /dev/cpuctl
-	# mount -t cgroup -ocpu none /dev/cpuctl
-	# cd /dev/cpuctl
+	# mount -t tmpfs cgroup_root /sys/fs/cgroup
+	# mkdir /sys/fs/cgroup/cpu
+	# mount -t cgroup -ocpu none /sys/fs/cgroup/cpu
+	# cd /sys/fs/cgroup/cpu
 
 	# mkdir multimedia	# create "multimedia" group of tasks
 	# mkdir browser		# create "browser" group of tasks
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 605b0d40329d..71b54d549987 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -129,9 +129,8 @@ priority!
 Enabling CONFIG_RT_GROUP_SCHED lets you explicitly allocate real
 CPU bandwidth to task groups.
 
-This uses the /cgroup virtual file system and
-"/cgroup/<cgroup>/cpu.rt_runtime_us" to control the CPU time reserved for each
-control group.
+This uses the cgroup virtual file system and "<cgroup>/cpu.rt_runtime_us"
+to control the CPU time reserved for each control group.
 
 For more information on working with control groups, you should read
 Documentation/cgroups/cgroups.txt as well.
@@ -150,7 +149,7 @@ For now, this can be simplified to just the following (but see Future plans):
 ===============
 
 There is work in progress to make the scheduling period for each group
-("/cgroup/<cgroup>/cpu.rt_period_us") configurable as well.
+("<cgroup>/cpu.rt_period_us") configurable as well.
 
 The constraint on the period is that a subgroup must have a smaller or
 equal period to its parent. But realistically its not very useful _yet_
diff --git a/Documentation/scsi/ChangeLog.megaraid_sas b/Documentation/scsi/ChangeLog.megaraid_sas
index 4d9ce73ff730..9ed1d9d96783 100644
--- a/Documentation/scsi/ChangeLog.megaraid_sas
+++ b/Documentation/scsi/ChangeLog.megaraid_sas
@@ -1,3 +1,17 @@
+Release Date    : Wed. May 11, 2011 17:00:00 PST 2010 -
+			(emaild-id:megaraidlinux@lsi.com)
+			Adam Radford
+Current Version : 00.00.05.38-rc1
+Old Version     : 00.00.05.34-rc1
+    1. Remove MSI-X black list, use MFI_REG_STATE.ready.msiEnable.
+    2. Remove un-used function megasas_return_cmd_for_smid().
+    3. Check MFI_REG_STATE.fault.resetAdapter in megasas_reset_fusion().
+    4. Disable interrupts/free_irq() in megasas_shutdown().
+    5. Fix bug where AENs could be lost in probe() and resume().
+    6. Convert 6,10,12 byte CDB's to 16 byte CDB for large LBA's for FastPath
+       IO.
+    7. Add 1078 OCR support.
+-------------------------------------------------------------------------------
 Release Date    : Thu. Feb 24, 2011 17:00:00 PST 2010 -
 			(emaild-id:megaraidlinux@lsi.com)
 			Adam Radford
diff --git a/Documentation/security/00-INDEX b/Documentation/security/00-INDEX
new file mode 100644
index 000000000000..19bc49439cac
--- /dev/null
+++ b/Documentation/security/00-INDEX
@@ -0,0 +1,18 @@
+00-INDEX
+	- this file.
+SELinux.txt
+	- how to get started with the SELinux security enhancement.
+Smack.txt
+	- documentation on the Smack Linux Security Module.
+apparmor.txt
+	- documentation on the AppArmor security extension.
+credentials.txt
+	- documentation about credentials in Linux.
+keys-request-key.txt
+	- description of the kernel key request service.
+keys-trusted-encrypted.txt
+	- info on the Trusted and Encrypted keys in the kernel key ring service.
+keys.txt
+	- description of the kernel key retention service.
+tomoyo.txt
+	- documentation on the TOMOYO Linux Security Module.
diff --git a/Documentation/SELinux.txt b/Documentation/security/SELinux.txt
index 07eae00f3314..07eae00f3314 100644
--- a/Documentation/SELinux.txt
+++ b/Documentation/security/SELinux.txt
diff --git a/Documentation/Smack.txt b/Documentation/security/Smack.txt
index e9dab41c0fe0..e9dab41c0fe0 100644
--- a/Documentation/Smack.txt
+++ b/Documentation/security/Smack.txt
diff --git a/Documentation/apparmor.txt b/Documentation/security/apparmor.txt
index 93c1fd7d0635..93c1fd7d0635 100644
--- a/Documentation/apparmor.txt
+++ b/Documentation/security/apparmor.txt
diff --git a/Documentation/credentials.txt b/Documentation/security/credentials.txt
index 995baf379c07..fc0366cbd7ce 100644
--- a/Documentation/credentials.txt
+++ b/Documentation/security/credentials.txt
@@ -216,7 +216,7 @@ The Linux kernel supports the following types of credentials:
      When a process accesses a key, if not already present, it will normally be
      cached on one of these keyrings for future accesses to find.
 
-     For more information on using keys, see Documentation/keys.txt.
+     For more information on using keys, see Documentation/security/keys.txt.
 
  (5) LSM
 
diff --git a/Documentation/keys-request-key.txt b/Documentation/security/keys-request-key.txt
index 69686ad12c66..51987bfecfed 100644
--- a/Documentation/keys-request-key.txt
+++ b/Documentation/security/keys-request-key.txt
@@ -3,8 +3,8 @@
 			      ===================
 
 The key request service is part of the key retention service (refer to
-Documentation/keys.txt).  This document explains more fully how the requesting
-algorithm works.
+Documentation/security/keys.txt).  This document explains more fully how
+the requesting algorithm works.
 
 The process starts by either the kernel requesting a service by calling
 request_key*():
diff --git a/Documentation/keys-trusted-encrypted.txt b/Documentation/security/keys-trusted-encrypted.txt
index 8fb79bc1ac4b..8fb79bc1ac4b 100644
--- a/Documentation/keys-trusted-encrypted.txt
+++ b/Documentation/security/keys-trusted-encrypted.txt
diff --git a/Documentation/keys.txt b/Documentation/security/keys.txt
index 6523a9e6f293..4d75931d2d79 100644
--- a/Documentation/keys.txt
+++ b/Documentation/security/keys.txt
@@ -434,7 +434,7 @@ The main syscalls are:
      /sbin/request-key will be invoked in an attempt to obtain a key. The
      callout_info string will be passed as an argument to the program.
 
-     See also Documentation/keys-request-key.txt.
+     See also Documentation/security/keys-request-key.txt.
 
 
 The keyctl syscall functions are:
@@ -864,7 +864,7 @@ payload contents" for more information.
     If successful, the key will have been attached to the default keyring for
     implicitly obtained request-key keys, as set by KEYCTL_SET_REQKEY_KEYRING.
 
-    See also Documentation/keys-request-key.txt.
+    See also Documentation/security/keys-request-key.txt.
 
 
 (*) To search for a key, passing auxiliary data to the upcaller, call:
diff --git a/Documentation/tomoyo.txt b/Documentation/security/tomoyo.txt
index 200a2d37cbc8..200a2d37cbc8 100644
--- a/Documentation/tomoyo.txt
+++ b/Documentation/security/tomoyo.txt
diff --git a/Documentation/virtual/lguest/Makefile b/Documentation/virtual/lguest/Makefile
index bebac6b4f332..0ac34206f7a7 100644
--- a/Documentation/virtual/lguest/Makefile
+++ b/Documentation/virtual/lguest/Makefile
@@ -1,5 +1,5 @@
 # This creates the demonstration utility "lguest" which runs a Linux guest.
-# Missing headers?  Add "-I../../include -I../../arch/x86/include"
+# Missing headers?  Add "-I../../../include -I../../../arch/x86/include"
 CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE
 
 all: lguest
diff --git a/Documentation/virtual/lguest/lguest.c b/Documentation/virtual/lguest/lguest.c
index d9da7e148538..cd9d6af61d07 100644
--- a/Documentation/virtual/lguest/lguest.c
+++ b/Documentation/virtual/lguest/lguest.c
@@ -49,7 +49,7 @@
 #include <linux/virtio_rng.h>
 #include <linux/virtio_ring.h>
 #include <asm/bootparam.h>
-#include "../../include/linux/lguest_launcher.h"
+#include "../../../include/linux/lguest_launcher.h"
 /*L:110
  * We can ignore the 42 include files we need for this program, but I do want
  * to draw attention to the use of kernel-style types.
@@ -135,9 +135,6 @@ struct device {
 	/* Is it operational */
 	bool running;
 
-	/* Does Guest want an intrrupt on empty? */
-	bool irq_on_empty;
-
 	/* Device-specific data. */
 	void *priv;
 };
@@ -637,10 +634,7 @@ static void trigger_irq(struct virtqueue *vq)
 
 	/* If they don't want an interrupt, don't send one... */
 	if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) {
-		/* ... unless they've asked us to force one on empty. */
-		if (!vq->dev->irq_on_empty
-		    || lg_last_avail(vq) != vq->vring.avail->idx)
-			return;
+		return;
 	}
 
 	/* Send the Guest an interrupt tell them we used something up. */
@@ -1057,15 +1051,6 @@ static void create_thread(struct virtqueue *vq)
 	close(vq->eventfd);
 }
 
-static bool accepted_feature(struct device *dev, unsigned int bit)
-{
-	const u8 *features = get_feature_bits(dev) + dev->feature_len;
-
-	if (dev->feature_len < bit / CHAR_BIT)
-		return false;
-	return features[bit / CHAR_BIT] & (1 << (bit % CHAR_BIT));
-}
-
 static void start_device(struct device *dev)
 {
 	unsigned int i;
@@ -1079,8 +1064,6 @@ static void start_device(struct device *dev)
 		verbose(" %02x", get_feature_bits(dev)
 			[dev->feature_len+i]);
 
-	dev->irq_on_empty = accepted_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
-
 	for (vq = dev->vq; vq; vq = vq->next) {
 		if (vq->service)
 			create_thread(vq);
@@ -1564,7 +1547,6 @@ static void setup_tun_net(char *arg)
 	/* Set up the tun device. */
 	configure_device(ipfd, tapif, ip);
 
-	add_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
 	/* Expect Guest to handle everything except UFO */
 	add_feature(dev, VIRTIO_NET_F_CSUM);
 	add_feature(dev, VIRTIO_NET_F_GUEST_CSUM);
diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.txt
index 12f9ba20ccb7..550068466605 100644
--- a/Documentation/vm/hwpoison.txt
+++ b/Documentation/vm/hwpoison.txt
@@ -129,12 +129,12 @@ Limit injection to pages owned by memgroup. Specified by inode number
 of the memcg.
 
 Example:
-        mkdir /cgroup/hwpoison
+        mkdir /sys/fs/cgroup/mem/hwpoison
 
         usemem -m 100 -s 1000 &
-        echo `jobs -p` > /cgroup/hwpoison/tasks
+        echo `jobs -p` > /sys/fs/cgroup/mem/hwpoison/tasks
 
-        memcg_ino=$(ls -id /cgroup/hwpoison | cut -f1 -d' ')
+        memcg_ino=$(ls -id /sys/fs/cgroup/mem/hwpoison | cut -f1 -d' ')
         echo $memcg_ino > /debug/hwpoison/corrupt-filter-memcg
 
         page-types -p `pidof init`   --hwpoison  # shall do nothing
diff --git a/MAINTAINERS b/MAINTAINERS
index c4fc1daddcb6..f0358cd91de3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -223,10 +223,8 @@ S:	Maintained
 F:	drivers/platform/x86/acerhdf.c
 
 ACER WMI LAPTOP EXTRAS
-M:	Carlos Corbacho <carlos@strangeworlds.co.uk>
-L:	aceracpi@googlegroups.com (subscribers-only)
+M:	Joey Lee <jlee@novell.com>
 L:	platform-driver-x86@vger.kernel.org
-W:	http://code.google.com/p/aceracpi
 S:	Maintained
 F:	drivers/platform/x86/acer-wmi.c
 
@@ -271,10 +269,8 @@ S:	Supported
 F:	drivers/acpi/video.c
 
 ACPI WMI DRIVER
-M:	Carlos Corbacho <carlos@strangeworlds.co.uk>
 L:	platform-driver-x86@vger.kernel.org
-W:	http://www.lesswatts.org/projects/acpi/
-S:	Maintained
+S:	Orphan
 F:	drivers/platform/x86/wmi.c
 
 AD1889 ALSA SOUND DRIVER
@@ -1743,7 +1739,7 @@ S:	Supported
 F:	drivers/net/enic/
 
 CIRRUS LOGIC EP93XX ETHERNET DRIVER
-M:	Lennert Buytenhek <kernel@wantstofly.org>
+M:	Hartley Sweeten <hsweeten@visionengravers.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/arm/ep93xx_eth.c
@@ -1893,7 +1889,6 @@ L:	cpufreq@vger.kernel.org
 W:	http://www.codemonkey.org.uk/projects/cpufreq/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/davej/cpufreq.git
 S:	Maintained
-F:	arch/x86/kernel/cpu/cpufreq/
 F:	drivers/cpufreq/
 F:	include/linux/cpufreq.h
 
@@ -2178,6 +2173,8 @@ M:	Dan Williams <dan.j.williams@intel.com>
 S:	Supported
 F:	drivers/dma/
 F:	include/linux/dma*
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx.git
+T:	git git://git.infradead.org/users/vkoul/slave-dma.git (slave-dma)
 
 DME1737 HARDWARE MONITOR DRIVER
 M:	Juerg Haefliger <juergh@gmail.com>
@@ -2294,8 +2291,7 @@ F:	drivers/scsi/eata_pio.*
 
 EBTABLES
 M:	Bart De Schuymer <bart.de.schuymer@pandora.be>
-L:	ebtables-user@lists.sourceforge.net
-L:	ebtables-devel@lists.sourceforge.net
+L:	netfilter-devel@vger.kernel.org
 W:	http://ebtables.sourceforge.net/
 S:	Maintained
 F:	include/linux/netfilter_bridge/ebt_*.h
@@ -2304,7 +2300,7 @@ F:	net/bridge/netfilter/ebt*.c
 ECRYPT FILE SYSTEM
 M:	Tyler Hicks <tyhicks@linux.vnet.ibm.com>
 M:	Dustin Kirkland <kirkland@canonical.com>
-L:	ecryptfs-devel@lists.launchpad.net
+L:	ecryptfs@vger.kernel.org
 W:	https://launchpad.net/ecryptfs
 S:	Supported
 F:	Documentation/filesystems/ecryptfs.txt
@@ -2584,6 +2580,13 @@ S:	Maintained
 F:	drivers/hwmon/f75375s.c
 F:	include/linux/f75375s.h
 
+FIREWIRE AUDIO DRIVERS
+M:	Clemens Ladisch <clemens@ladisch.de>
+L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+T:	git git://git.alsa-project.org/alsa-kernel.git
+S:	Maintained
+F:	sound/firewire/
+
 FIREWIRE SUBSYSTEM
 M:	Stefan Richter <stefanr@s5r6.in-berlin.de>
 L:	linux1394-devel@lists.sourceforge.net
@@ -3024,9 +3027,8 @@ S:	Maintained
 F:	drivers/net/wireless/hostap/
 
 HP COMPAQ TC1100 TABLET WMI EXTRAS DRIVER
-M:	Carlos Corbacho <carlos@strangeworlds.co.uk>
 L:	platform-driver-x86@vger.kernel.org
-S:	Odd Fixes
+S:	Orphan
 F:	drivers/platform/x86/tc1100-wmi.c
 
 HP100:	Driver for HP 10/100 Mbit/s Voice Grade Network Adapter Series
@@ -3719,7 +3721,7 @@ KEYS/KEYRINGS:
 M:	David Howells <dhowells@redhat.com>
 L:	keyrings@linux-nfs.org
 S:	Maintained
-F:	Documentation/keys.txt
+F:	Documentation/security/keys.txt
 F:	include/linux/key.h
 F:	include/linux/key-type.h
 F:	include/keys/
@@ -3731,7 +3733,7 @@ M:	Mimi Zohar <zohar@us.ibm.com>
 L:	linux-security-module@vger.kernel.org
 L:	keyrings@linux-nfs.org
 S:	Supported
-F:	Documentation/keys-trusted-encrypted.txt
+F:	Documentation/security/keys-trusted-encrypted.txt
 F:	include/keys/trusted-type.h
 F:	security/keys/trusted.c
 F:	security/keys/trusted.h
@@ -3742,7 +3744,7 @@ M:	David Safford <safford@watson.ibm.com>
 L:	linux-security-module@vger.kernel.org
 L:	keyrings@linux-nfs.org
 S:	Supported
-F:	Documentation/keys-trusted-encrypted.txt
+F:	Documentation/security/keys-trusted-encrypted.txt
 F:	include/keys/encrypted-type.h
 F:	security/keys/encrypted.c
 F:	security/keys/encrypted.h
@@ -3816,6 +3818,12 @@ S:	Maintained
 F:	drivers/leds/
 F:	include/linux/leds.h
 
+LEGACY EEPROM DRIVER
+M:	Jean Delvare <khali@linux-fr.org>
+S:	Maintained
+F:	Documentation/misc-devices/eeprom
+F:	drivers/misc/eeprom/eeprom.c
+
 LEGO USB Tower driver
 M:	Juergen Stuber <starblue@users.sourceforge.net>
 L:	legousb-devel@lists.sourceforge.net
@@ -4141,7 +4149,7 @@ F:	include/linux/mm.h
 F:	mm/
 
 MEMORY RESOURCE CONTROLLER
-M:	Balbir Singh <balbir@linux.vnet.ibm.com>
+M:	Balbir Singh <bsingharora@gmail.com>
 M:	Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
 M:	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
 L:	linux-mm@kvack.org
@@ -4248,8 +4256,7 @@ F:	drivers/mmc/
 F:	include/linux/mmc/
 
 MULTIMEDIA CARD (MMC) ETC. OVER SPI
-M:	David Brownell <dbrownell@users.sourceforge.net>
-S:	Odd Fixes
+S:	Orphan
 F:	drivers/mmc/host/mmc_spi.c
 F:	include/linux/spi/mmc_spi.h
 
@@ -4599,7 +4606,6 @@ F:	drivers/media/video/omap3isp/*
 
 OMAP USB SUPPORT
 M:	Felipe Balbi <balbi@ti.com>
-M:	David Brownell <dbrownell@users.sourceforge.net>
 L:	linux-usb@vger.kernel.org
 L:	linux-omap@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
@@ -4888,7 +4894,7 @@ F:	mm/percpu*.c
 F:	arch/*/include/asm/percpu.h
 
 PER-TASK DELAY ACCOUNTING
-M:	Balbir Singh <balbir@linux.vnet.ibm.com>
+M:	Balbir Singh <bsingharora@gmail.com>
 S:	Maintained
 F:	include/linux/delayacct.h
 F:	kernel/delayacct.c
@@ -4943,6 +4949,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/epip/linux-2.6-unicore32.gi
 F:	drivers/input/serio/i8042-unicore32io.h
 F:	drivers/i2c/busses/i2c-puv3.c
 F:	drivers/video/fb-puv3.c
+F:	drivers/rtc/rtc-puv3.c
 
 PMC SIERRA MaxRAID DRIVER
 M:	Anil Ravindranath <anil_ravindranath@pmc-sierra.com>
@@ -5444,6 +5451,13 @@ L:	linux-serial@vger.kernel.org
 S:	Maintained
 F:	drivers/tty/serial
 
+SYNOPSYS DESIGNWARE DMAC DRIVER
+M:	Viresh Kumar <viresh.kumar@st.com>
+S:	Maintained
+F:	include/linux/dw_dmac.h
+F:	drivers/dma/dw_dmac_regs.h
+F:	drivers/dma/dw_dmac.c
+
 TIMEKEEPING, NTP
 M:	John Stultz <johnstul@us.ibm.com>
 M:	Thomas Gleixner <tglx@linutronix.de>
@@ -5508,7 +5522,7 @@ F:	drivers/scsi/sg.c
 F:	include/scsi/sg.h
 
 SCSI SUBSYSTEM
-M:	"James E.J. Bottomley" <James.Bottomley@suse.de>
+M:	"James E.J. Bottomley" <JBottomley@parallels.com>
 L:	linux-scsi@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi-rc-fixes-2.6.git
@@ -5973,7 +5987,6 @@ F:	Documentation/serial/specialix.txt
 F:	drivers/staging/tty/specialix*
 
 SPI SUBSYSTEM
-M:	David Brownell <dbrownell@users.sourceforge.net>
 M:	Grant Likely <grant.likely@secretlab.ca>
 L:	spi-devel-general@lists.sourceforge.net
 Q:	http://patchwork.kernel.org/project/spi-devel-general/list/
@@ -6077,8 +6090,19 @@ F:	Documentation/filesystems/sysv-fs.txt
 F:	fs/sysv/
 F:	include/linux/sysv_fs.h
 
+TARGET SUBSYSTEM
+M:	Nicholas A. Bellinger <nab@linux-iscsi.org>
+L:	linux-scsi@vger.kernel.org
+L:	http://groups.google.com/group/linux-iscsi-target-dev
+W:	http://www.linux-iscsi.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/nab/lio-core-2.6.git master
+S:	Supported
+F:	drivers/target/
+F:	include/target/
+F:	Documentation/target/
+
 TASKSTATS STATISTICS INTERFACE
-M:	Balbir Singh <balbir@linux.vnet.ibm.com>
+M:	Balbir Singh <bsingharora@gmail.com>
 S:	Maintained
 F:	Documentation/accounting/taskstats*
 F:	include/linux/taskstats*
@@ -6410,9 +6434,8 @@ S:	Maintained
 F:	drivers/usb/misc/rio500*
 
 USB EHCI DRIVER
-M:	David Brownell <dbrownell@users.sourceforge.net>
 L:	linux-usb@vger.kernel.org
-S:	Odd Fixes
+S:	Orphan
 F:	Documentation/usb/ehci.txt
 F:	drivers/usb/host/ehci*
 
@@ -6426,9 +6449,10 @@ S:	Maintained
 F:	drivers/media/video/et61x251/
 
 USB GADGET/PERIPHERAL SUBSYSTEM
-M:	David Brownell <dbrownell@users.sourceforge.net>
+M:	Felipe Balbi <balbi@ti.com>
 L:	linux-usb@vger.kernel.org
 W:	http://www.linux-usb.org/gadget
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
 S:	Maintained
 F:	drivers/usb/gadget/
 F:	include/linux/usb/gadget*
@@ -6438,7 +6462,7 @@ M:	Jiri Kosina <jkosina@suse.cz>
 L:	linux-usb@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git
 S:	Maintained
-F:	Documentation/usb/hiddev.txt
+F:	Documentation/hid/hiddev.txt
 F:	drivers/hid/usbhid/
 
 USB ISP116X DRIVER
@@ -6470,9 +6494,8 @@ S:	Maintained
 F:	sound/usb/midi.*
 
 USB OHCI DRIVER
-M:	David Brownell <dbrownell@users.sourceforge.net>
 L:	linux-usb@vger.kernel.org
-S:	Odd Fixes
+S:	Orphan
 F:	Documentation/usb/ohci.txt
 F:	drivers/usb/host/ohci*
 
@@ -6698,6 +6721,14 @@ S:	Maintained
 F:	Documentation/filesystems/vfat.txt
 F:	fs/fat/
 
+VIDEOBUF2 FRAMEWORK
+M:	Pawel Osciak <pawel@osciak.com>
+M:	Marek Szyprowski <m.szyprowski@samsung.com>
+L:	linux-media@vger.kernel.org
+S:	Maintained
+F:	drivers/media/video/videobuf2-*
+F:	include/media/videobuf2-*
+
 VIRTIO CONSOLE DRIVER
 M:	Amit Shah <amit.shah@redhat.com>
 L:	virtualization@lists.linux-foundation.org
@@ -6975,6 +7006,13 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86.
 S:	Maintained
 F:	drivers/platform/x86
 
+X86 MCE INFRASTRUCTURE
+M:	Tony Luck <tony.luck@intel.com>
+M:	Borislav Petkov <bp@amd64.org>
+L:	linux-edac@vger.kernel.org
+S:	Maintained
+F:	arch/x86/kernel/cpu/mcheck/*
+
 XEN HYPERVISOR INTERFACE
 M:	Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
diff --git a/Makefile b/Makefile
index 529d93fa2430..dc670467fb8c 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
-VERSION = 2
-PATCHLEVEL = 6
-SUBLEVEL = 39
-EXTRAVERSION =
-NAME = Flesh-Eating Bats with Fangs
+VERSION = 3
+PATCHLEVEL = 0
+SUBLEVEL = 0
+EXTRAVERSION = -rc5
+NAME = Sneaky Weasel
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
@@ -378,7 +378,7 @@ KBUILD_LDFLAGS_MODULE := -T $(srctree)/scripts/module-common.lds
 
 # Read KERNELRELEASE from include/config/kernel.release (if it exists)
 KERNELRELEASE = $(shell cat include/config/kernel.release 2> /dev/null)
-KERNELVERSION = $(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(EXTRAVERSION)
+KERNELVERSION = $(VERSION)$(if $(PATCHLEVEL),.$(PATCHLEVEL)$(if $(SUBLEVEL),.$(SUBLEVEL)))$(EXTRAVERSION)
 
 export VERSION PATCHLEVEL SUBLEVEL KERNELRELEASE KERNELVERSION
 export ARCH SRCARCH CONFIG_SHELL HOSTCC HOSTCFLAGS CROSS_COMPILE AS LD CC
@@ -1005,7 +1005,7 @@ endef
 
 define filechk_version.h
 	(echo \#define LINUX_VERSION_CODE $(shell                             \
-	expr $(VERSION) \* 65536 + $(PATCHLEVEL) \* 256 + $(SUBLEVEL));     \
+	expr $(VERSION) \* 65536 + 0$(PATCHLEVEL) \* 256 + 0$(SUBLEVEL));    \
 	echo '#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c))';)
 endef
 
@@ -1110,11 +1110,6 @@ modules_install: _modinst_ _modinst_post
 
 PHONY += _modinst_
 _modinst_:
-	@if [ -z "`$(DEPMOD) -V 2>/dev/null | grep module-init-tools`" ]; then \
-		echo "Warning: you may need to install module-init-tools"; \
-		echo "See http://www.codemonkey.org.uk/docs/post-halloween-2.6.txt";\
-		sleep 1; \
-	fi
 	@rm -rf $(MODLIB)/kernel
 	@rm -f $(MODLIB)/source
 	@mkdir -p $(MODLIB)/kernel
@@ -1531,12 +1526,8 @@ quiet_cmd_rmfiles = $(if $(wildcard $(rm-files)),CLEAN   $(wildcard $(rm-files))
 
 # Run depmod only if we have System.map and depmod is executable
 quiet_cmd_depmod = DEPMOD  $(KERNELRELEASE)
-      cmd_depmod = \
-	if [ -r System.map -a -x $(DEPMOD) ]; then                              \
-		$(DEPMOD) -ae -F System.map                                     \
-		$(if $(strip $(INSTALL_MOD_PATH)), -b $(INSTALL_MOD_PATH) )     \
-		$(KERNELRELEASE);                                               \
-	fi
+      cmd_depmod = $(CONFIG_SHELL) $(srctree)/scripts/depmod.sh $(DEPMOD) \
+                   $(KERNELRELEASE)
 
 # Create temporary dir for module support files
 # clean it up only when building all modules
diff --git a/arch/alpha/include/asm/mmzone.h b/arch/alpha/include/asm/mmzone.h
index 8af56ce346ad..445dc42e0334 100644
--- a/arch/alpha/include/asm/mmzone.h
+++ b/arch/alpha/include/asm/mmzone.h
@@ -56,7 +56,6 @@ PLAT_NODE_DATA_LOCALNR(unsigned long p, int n)
  * Given a kernel address, find the home node of the underlying memory.
  */
 #define kvaddr_to_nid(kaddr)	pa_to_nid(__pa(kaddr))
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
 
 /*
  * Given a kaddr, LOCAL_BASE_ADDR finds the owning node of the memory
diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h
index b1834166922d..4ac48a095f3a 100644
--- a/arch/alpha/include/asm/unistd.h
+++ b/arch/alpha/include/asm/unistd.h
@@ -456,10 +456,11 @@
 #define __NR_open_by_handle_at		498
 #define __NR_clock_adjtime		499
 #define __NR_syncfs			500
+#define __NR_setns			501
 
 #ifdef __KERNEL__
 
-#define NR_SYSCALLS			501
+#define NR_SYSCALLS			502
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 376f22130791..326f0a2d56e5 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -409,7 +409,7 @@ SYSCALL_DEFINE2(osf_getdomainname, char __user *, name, int, namelen)
 		return -EFAULT;
 
 	len = namelen;
-	if (namelen > 32)
+	if (len > 32)
 		len = 32;
 
 	down_read(&uts_sem);
@@ -594,7 +594,7 @@ SYSCALL_DEFINE3(osf_sysinfo, int, command, char __user *, buf, long, count)
 	down_read(&uts_sem);
 	res = sysinfo_table[offset];
 	len = strlen(res)+1;
-	if (len > count)
+	if ((unsigned long)len > (unsigned long)count)
 		len = count;
 	if (copy_to_user(buf, res, len))
 		err = -EFAULT;
@@ -649,7 +649,7 @@ SYSCALL_DEFINE5(osf_getsysinfo, unsigned long, op, void __user *, buffer,
 		return 1;
 
 	case GSI_GET_HWRPB:
-		if (nbytes < sizeof(*hwrpb))
+		if (nbytes > sizeof(*hwrpb))
 			return -EINVAL;
 		if (copy_to_user(buffer, hwrpb, nbytes) != 0)
 			return -EFAULT;
@@ -1008,6 +1008,7 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 {
 	struct rusage r;
 	long ret, err;
+	unsigned int status = 0;
 	mm_segment_t old_fs;
 
 	if (!ur)
@@ -1016,13 +1017,15 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 	old_fs = get_fs();
 		
 	set_fs (KERNEL_DS);
-	ret = sys_wait4(pid, ustatus, options, (struct rusage __user *) &r);
+	ret = sys_wait4(pid, (unsigned int __user *) &status, options,
+			(struct rusage __user *) &r);
 	set_fs (old_fs);
 
 	if (!access_ok(VERIFY_WRITE, ur, sizeof(*ur)))
 		return -EFAULT;
 
 	err = 0;
+	err |= put_user(status, ustatus);
 	err |= __put_user(r.ru_utime.tv_sec, &ur->ru_utime.tv_sec);
 	err |= __put_user(r.ru_utime.tv_usec, &ur->ru_utime.tv_usec);
 	err |= __put_user(r.ru_stime.tv_sec, &ur->ru_stime.tv_sec);
diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S
index 15f999d41c75..b9c28f3f1956 100644
--- a/arch/alpha/kernel/systbls.S
+++ b/arch/alpha/kernel/systbls.S
@@ -519,6 +519,7 @@ sys_call_table:
 	.quad sys_open_by_handle_at
 	.quad sys_clock_adjtime
 	.quad sys_syncfs			/* 500 */
+	.quad sys_setns
 
 	.size sys_call_table, . - sys_call_table
 	.type sys_call_table, @object
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 7275009686e6..9adc278a22ab 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -294,6 +294,8 @@ config ARCH_AT91
 	bool "Atmel AT91"
 	select ARCH_REQUIRE_GPIOLIB
 	select HAVE_CLK
+	select CLKDEV_LOOKUP
+	select ARM_PATCH_PHYS_VIRT if MMU
 	help
 	  This enables support for systems based on the Atmel AT91RM9200,
 	  AT91SAM9 and AT91CAP9 processors.
@@ -730,16 +732,6 @@ config ARCH_S5P64X0
 	  Samsung S5P64X0 CPU based systems, such as the Samsung SMDK6440,
 	  SMDK6450.
 
-config ARCH_S5P6442
-	bool "Samsung S5P6442"
-	select CPU_V6
-	select GENERIC_GPIO
-	select HAVE_CLK
-	select ARCH_USES_GETTIMEOFFSET
-	select HAVE_S3C2410_WATCHDOG if WATCHDOG
-	help
-	  Samsung S5P6442 CPU based systems
-
 config ARCH_S5PC100
 	bool "Samsung S5PC100"
 	select GENERIC_GPIO
@@ -991,8 +983,6 @@ endif
 
 source "arch/arm/mach-s5p64x0/Kconfig"
 
-source "arch/arm/mach-s5p6442/Kconfig"
-
 source "arch/arm/mach-s5pc100/Kconfig"
 
 source "arch/arm/mach-s5pv210/Kconfig"
@@ -1399,7 +1389,6 @@ config NR_CPUS
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
 	depends on SMP && HOTPLUG && EXPERIMENTAL
-	depends on !ARCH_MSM
 	help
 	  Say Y here to experiment with turning CPUs off and on.  CPUs
 	  can be controlled through /sys/devices/system/cpu.
@@ -1420,7 +1409,7 @@ source kernel/Kconfig.preempt
 config HZ
 	int
 	default 200 if ARCH_EBSA110 || ARCH_S3C2410 || ARCH_S5P64X0 || \
-		ARCH_S5P6442 || ARCH_S5PV210 || ARCH_EXYNOS4
+		ARCH_S5PV210 || ARCH_EXYNOS4
 	default OMAP_32K_TIMER_HZ if ARCH_OMAP && OMAP_32K_TIMER
 	default AT91_TIMER_HZ if ARCH_AT91
 	default SHMOBILE_TIMER_HZ if ARCH_SHMOBILE
@@ -1516,6 +1505,9 @@ config ARCH_SPARSEMEM_DEFAULT
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool ARCH_SPARSEMEM_ENABLE
 
+config HAVE_ARCH_PFN_VALID
+	def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
+
 config HIGHMEM
 	bool "High Memory Support"
 	depends on MMU
@@ -1683,6 +1675,13 @@ endmenu
 
 menu "Boot options"
 
+config USE_OF
+	bool "Flattened Device Tree support"
+	select OF
+	select OF_EARLY_FLATTREE
+	help
+	  Include support for flattened device tree machine descriptions.
+
 # Compressed boot loader in ROM.  Yes, we really want to ask about
 # TEXT and BSS so we preserve their values in the config files.
 config ZBOOT_ROM_TEXT
@@ -2021,7 +2020,7 @@ menu "Power management options"
 source "kernel/power/Kconfig"
 
 config ARCH_SUSPEND_POSSIBLE
-	depends on !ARCH_S5P64X0 && !ARCH_S5P6442 && !ARCH_S5PC100
+	depends on !ARCH_S5P64X0 && !ARCH_S5PC100
 	depends on CPU_ARM920T || CPU_ARM926T || CPU_SA1100 || \
 		CPU_V6 || CPU_V6K || CPU_V7 || CPU_XSC3 || CPU_XSCALE
 	def_bool y
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 25750bcb3397..f5b2b390c8f2 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -176,7 +176,6 @@ machine-$(CONFIG_ARCH_S3C2410)		:= s3c2410 s3c2400 s3c2412 s3c2416 s3c2440 s3c24
 machine-$(CONFIG_ARCH_S3C24A0)		:= s3c24a0
 machine-$(CONFIG_ARCH_S3C64XX)		:= s3c64xx
 machine-$(CONFIG_ARCH_S5P64X0)		:= s5p64x0
-machine-$(CONFIG_ARCH_S5P6442)		:= s5p6442
 machine-$(CONFIG_ARCH_S5PC100)		:= s5pc100
 machine-$(CONFIG_ARCH_S5PV210)		:= s5pv210
 machine-$(CONFIG_ARCH_EXYNOS4)		:= exynos4
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index f9da41921c52..940b20178107 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -597,6 +597,8 @@ __common_mmu_cache_on:
 		sub	pc, lr, r0, lsr #32	@ properly flush pipeline
 #endif
 
+#define PROC_ENTRY_SIZE (4*5)
+
 /*
  * Here follow the relocatable cache support functions for the
  * various processors.  This is a generic hook for locating an
@@ -624,7 +626,7 @@ call_cache_fn:	adr	r12, proc_types
  ARM(		addeq	pc, r12, r3		) @ call cache function
  THUMB(		addeq	r12, r3			)
  THUMB(		moveq	pc, r12			) @ call cache function
-		add	r12, r12, #4*5
+		add	r12, r12, #PROC_ENTRY_SIZE
 		b	1b
 
 /*
@@ -691,9 +693,9 @@ proc_types:
 
 		.word	0x41069260		@ ARM926EJ-S (v5TEJ)
 		.word	0xff0ffff0
-		b	__arm926ejs_mmu_cache_on
-		b	__armv4_mmu_cache_off
-		b	__armv5tej_mmu_cache_flush
+		W(b)	__arm926ejs_mmu_cache_on
+		W(b)	__armv4_mmu_cache_off
+		W(b)	__armv5tej_mmu_cache_flush
 
 		.word	0x00007000		@ ARM7 IDs
 		.word	0x0000f000
@@ -794,6 +796,16 @@ proc_types:
 
 		.size	proc_types, . - proc_types
 
+		/*
+		 * If you get a "non-constant expression in ".if" statement"
+		 * error from the assembler on this line, check that you have
+		 * not accidentally written a "b" instruction where you should
+		 * have written W(b).
+		 */
+		.if (. - proc_types) % PROC_ENTRY_SIZE != 0
+		.error "The size of one or more proc_types entries is wrong."
+		.endif
+
 /*
  * Turn off the Cache and MMU.  ARMv3 does not support
  * reading the control register, but ARMv4 does.
diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig
index ea5ee4d067f3..4b71766fb21d 100644
--- a/arch/arm/common/Kconfig
+++ b/arch/arm/common/Kconfig
@@ -7,7 +7,7 @@ config ARM_VIC
 config ARM_VIC_NR
 	int
 	default 4 if ARCH_S5PV210
-	default 3 if ARCH_S5P6442 || ARCH_S5PC100
+	default 3 if ARCH_S5PC100
 	default 2
 	depends on ARM_VIC
 	help
diff --git a/arch/arm/configs/at572d940hfek_defconfig b/arch/arm/configs/at572d940hfek_defconfig
deleted file mode 100644
index 1b1158ae8f82..000000000000
--- a/arch/arm/configs/at572d940hfek_defconfig
+++ /dev/null
@@ -1,358 +0,0 @@
-CONFIG_EXPERIMENTAL=y
-CONFIG_LOCALVERSION="-AT572D940HF"
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_TASKSTATS=y
-CONFIG_TASK_XACCT=y
-CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_AUDIT=y
-CONFIG_CGROUPS=y
-CONFIG_CGROUP_CPUACCT=y
-CONFIG_CGROUP_SCHED=y
-CONFIG_RT_GROUP_SCHED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-CONFIG_EXPERT=y
-CONFIG_SLAB=y
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_KPROBES=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_MODULE_SRCVERSION_ALL=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_ARCH_AT91=y
-CONFIG_ARCH_AT572D940HF=y
-CONFIG_MACH_AT572D940HFEB=y
-CONFIG_AT91_PROGRAMMABLE_CLOCKS=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_PREEMPT=y
-CONFIG_CMDLINE="mem=48M console=ttyS0 initrd=0x21100000,3145728 root=/dev/ram0 rw ip=172.16.1.181"
-CONFIG_KEXEC=y
-CONFIG_FPE_NWFPE=y
-CONFIG_FPE_NWFPE_XP=y
-CONFIG_NET=y
-CONFIG_PACKET=m
-CONFIG_UNIX=y
-CONFIG_INET=y
-# 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_IPV6 is not set
-CONFIG_NET_PKTGEN=m
-CONFIG_NET_TCPPROBE=m
-CONFIG_CAN=m
-CONFIG_CAN_RAW=m
-CONFIG_CAN_BCM=m
-CONFIG_CAN_VCAN=m
-CONFIG_CAN_DEBUG_DEVICES=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_CONNECTOR=m
-CONFIG_MTD=m
-CONFIG_MTD_DEBUG=y
-CONFIG_MTD_DEBUG_VERBOSE=1
-CONFIG_MTD_CONCAT=m
-CONFIG_MTD_PARTITIONS=y
-CONFIG_MTD_CHAR=m
-CONFIG_MTD_BLOCK=m
-CONFIG_MTD_BLOCK_RO=m
-CONFIG_FTL=m
-CONFIG_NFTL=m
-CONFIG_NFTL_RW=y
-CONFIG_INFTL=m
-CONFIG_RFD_FTL=m
-CONFIG_SSFDC=m
-CONFIG_MTD_OOPS=m
-CONFIG_MTD_CFI=m
-CONFIG_MTD_JEDECPROBE=m
-CONFIG_MTD_CFI_INTELEXT=m
-CONFIG_MTD_CFI_AMDSTD=m
-CONFIG_MTD_CFI_STAA=m
-CONFIG_MTD_ROM=m
-CONFIG_MTD_ABSENT=m
-CONFIG_MTD_COMPLEX_MAPPINGS=y
-CONFIG_MTD_PHYSMAP=m
-CONFIG_MTD_PLATRAM=m
-CONFIG_MTD_DATAFLASH=m
-CONFIG_MTD_M25P80=m
-CONFIG_MTD_SLRAM=m
-CONFIG_MTD_PHRAM=m
-CONFIG_MTD_MTDRAM=m
-CONFIG_MTD_BLOCK2MTD=m
-CONFIG_MTD_NAND=m
-CONFIG_MTD_NAND_VERIFY_WRITE=y
-CONFIG_MTD_NAND_DISKONCHIP=m
-CONFIG_MTD_NAND_NANDSIM=m
-CONFIG_MTD_NAND_PLATFORM=m
-CONFIG_MTD_ALAUDA=m
-CONFIG_MTD_UBI=m
-CONFIG_MTD_UBI_GLUEBI=m
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=65536
-CONFIG_ATMEL_TCLIB=y
-CONFIG_ATMEL_SSC=m
-CONFIG_SENSORS_TSL2550=m
-CONFIG_DS1682=m
-CONFIG_RAID_ATTRS=m
-CONFIG_SCSI=m
-CONFIG_SCSI_TGT=m
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=m
-CONFIG_BLK_DEV_SR=m
-CONFIG_CHR_DEV_SG=m
-CONFIG_CHR_DEV_SCH=m
-CONFIG_SCSI_MULTI_LUN=y
-CONFIG_SCSI_CONSTANTS=y
-CONFIG_SCSI_LOGGING=y
-CONFIG_SCSI_SCAN_ASYNC=y
-CONFIG_SCSI_ISCSI_ATTRS=m
-CONFIG_NETDEVICES=y
-CONFIG_DUMMY=m
-CONFIG_BONDING=m
-CONFIG_MACVLAN=m
-CONFIG_EQUALIZER=m
-CONFIG_TUN=m
-CONFIG_VETH=m
-CONFIG_PHYLIB=y
-CONFIG_MARVELL_PHY=m
-CONFIG_DAVICOM_PHY=m
-CONFIG_QSEMI_PHY=m
-CONFIG_LXT_PHY=m
-CONFIG_CICADA_PHY=m
-CONFIG_VITESSE_PHY=m
-CONFIG_SMSC_PHY=m
-CONFIG_BROADCOM_PHY=m
-CONFIG_ICPLUS_PHY=m
-CONFIG_MDIO_BITBANG=m
-CONFIG_NET_ETHERNET=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
-CONFIG_USB_ZD1201=m
-CONFIG_HOSTAP=m
-CONFIG_HOSTAP_FIRMWARE=y
-CONFIG_HOSTAP_FIRMWARE_NVRAM=y
-CONFIG_USB_CATC=m
-CONFIG_USB_KAWETH=m
-CONFIG_USB_PEGASUS=m
-CONFIG_USB_RTL8150=m
-CONFIG_USB_USBNET=m
-CONFIG_USB_NET_DM9601=m
-CONFIG_USB_NET_GL620A=m
-CONFIG_USB_NET_PLUSB=m
-CONFIG_USB_NET_MCS7830=m
-CONFIG_USB_NET_RNDIS_HOST=m
-CONFIG_USB_ALI_M5632=y
-CONFIG_USB_AN2720=y
-CONFIG_USB_EPSON2888=y
-CONFIG_USB_KC2190=y
-# CONFIG_USB_NET_ZAURUS is not set
-CONFIG_INPUT_MOUSEDEV=m
-CONFIG_INPUT_EVDEV=m
-CONFIG_INPUT_EVBUG=m
-CONFIG_KEYBOARD_LKKBD=m
-CONFIG_KEYBOARD_GPIO=m
-CONFIG_KEYBOARD_NEWTON=m
-CONFIG_KEYBOARD_STOWAWAY=m
-CONFIG_KEYBOARD_SUNKBD=m
-CONFIG_KEYBOARD_XTKBD=m
-CONFIG_MOUSE_PS2=m
-CONFIG_MOUSE_SERIAL=m
-CONFIG_MOUSE_APPLETOUCH=m
-CONFIG_MOUSE_VSXXXAA=m
-CONFIG_MOUSE_GPIO=m
-CONFIG_INPUT_MISC=y
-CONFIG_INPUT_UINPUT=m
-CONFIG_SERIO_SERPORT=m
-CONFIG_SERIO_RAW=m
-CONFIG_VT_HW_CONSOLE_BINDING=y
-CONFIG_SERIAL_NONSTANDARD=y
-CONFIG_N_HDLC=m
-CONFIG_SPECIALIX=m
-CONFIG_STALDRV=y
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-CONFIG_IPMI_HANDLER=m
-CONFIG_IPMI_DEVICE_INTERFACE=m
-CONFIG_IPMI_SI=m
-CONFIG_IPMI_WATCHDOG=m
-CONFIG_IPMI_POWEROFF=m
-CONFIG_HW_RANDOM=y
-CONFIG_R3964=m
-CONFIG_RAW_DRIVER=m
-CONFIG_TCG_TPM=m
-CONFIG_TCG_NSC=m
-CONFIG_TCG_ATMEL=m
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_BITBANG=m
-CONFIG_SPI_SPIDEV=m
-# CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_SEQUENCER=m
-CONFIG_SND_SEQ_DUMMY=m
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-# CONFIG_SND_PCM_OSS_PLUGINS is not set
-CONFIG_SND_SEQUENCER_OSS=y
-CONFIG_SND_DYNAMIC_MINORS=y
-# CONFIG_SND_VERBOSE_PROCFS is not set
-CONFIG_SND_DUMMY=m
-CONFIG_SND_VIRMIDI=m
-CONFIG_SND_USB_AUDIO=m
-CONFIG_SND_USB_CAIAQ=m
-CONFIG_SND_USB_CAIAQ_INPUT=y
-CONFIG_HID=m
-CONFIG_HIDRAW=y
-CONFIG_USB_HID=m
-CONFIG_USB_HIDDEV=y
-CONFIG_USB_KBD=m
-CONFIG_USB_MOUSE=m
-CONFIG_HID_A4TECH=m
-CONFIG_HID_APPLE=m
-CONFIG_HID_BELKIN=m
-CONFIG_HID_CHERRY=m
-CONFIG_HID_CHICONY=m
-CONFIG_HID_CYPRESS=m
-CONFIG_HID_EZKEY=m
-CONFIG_HID_GYRATION=m
-CONFIG_HID_LOGITECH=m
-CONFIG_HID_MICROSOFT=m
-CONFIG_HID_MONTEREY=m
-CONFIG_HID_PANTHERLORD=m
-CONFIG_HID_PETALYNX=m
-CONFIG_HID_SAMSUNG=m
-CONFIG_HID_SONY=m
-CONFIG_HID_SUNPLUS=m
-CONFIG_USB=y
-CONFIG_USB_DEVICEFS=y
-# CONFIG_USB_DEVICE_CLASS is not set
-CONFIG_USB_DYNAMIC_MINORS=y
-CONFIG_USB_MON=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_STORAGE=m
-CONFIG_USB_STORAGE_DATAFAB=m
-CONFIG_USB_STORAGE_FREECOM=m
-CONFIG_USB_STORAGE_ISD200=m
-CONFIG_USB_STORAGE_USBAT=m
-CONFIG_USB_STORAGE_SDDR09=m
-CONFIG_USB_STORAGE_SDDR55=m
-CONFIG_USB_STORAGE_JUMPSHOT=m
-CONFIG_USB_STORAGE_ALAUDA=m
-CONFIG_USB_STORAGE_KARMA=m
-CONFIG_USB_LIBUSUAL=y
-CONFIG_USB_SERIAL=m
-CONFIG_USB_EZUSB=y
-CONFIG_USB_SERIAL_GENERIC=y
-CONFIG_USB_SERIAL_PL2303=m
-CONFIG_USB_SERIAL_SPCP8X5=m
-CONFIG_USB_SERIAL_DEBUG=m
-CONFIG_USB_EMI62=m
-CONFIG_USB_EMI26=m
-CONFIG_USB_ADUTUX=m
-CONFIG_USB_TEST=m
-CONFIG_USB_GADGET=m
-CONFIG_USB_GADGET_DEBUG_FILES=y
-CONFIG_USB_GADGET_DEBUG_FS=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_FILE_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_MIDI_GADGET=m
-CONFIG_MMC=y
-CONFIG_SDIO_UART=m
-CONFIG_MMC_AT91=m
-CONFIG_MMC_SPI=m
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=m
-CONFIG_LEDS_GPIO=m
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=m
-CONFIG_LEDS_TRIGGER_HEARTBEAT=m
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_INTF_DEV_UIE_EMUL=y
-CONFIG_RTC_DRV_DS1307=m
-CONFIG_RTC_DRV_DS1305=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
-CONFIG_JBD_DEBUG=y
-CONFIG_REISERFS_FS=m
-CONFIG_REISERFS_CHECK=y
-CONFIG_REISERFS_PROC_INFO=y
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
-CONFIG_INOTIFY=y
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=y
-CONFIG_NTFS_FS=m
-CONFIG_NTFS_RW=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_JFFS2_FS=m
-CONFIG_JFFS2_COMPRESSION_OPTIONS=y
-CONFIG_JFFS2_LZO=y
-CONFIG_JFFS2_CMODE_FAVOURLZO=y
-CONFIG_CRAMFS=m
-CONFIG_NFS_FS=m
-CONFIG_NFS_V3=y
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3_ACL=y
-CONFIG_NFSD_V4=y
-CONFIG_CIFS=m
-CONFIG_CIFS_WEAK_PW_HASH=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAC_PARTITION=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_MINIX_SUBPARTITION=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_LDM_PARTITION=y
-CONFIG_LDM_DEBUG=y
-CONFIG_SGI_PARTITION=y
-CONFIG_SUN_PARTITION=y
-CONFIG_NLS_DEFAULT="cp437"
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ASCII=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_UTF8=m
-CONFIG_DLM=m
-CONFIG_PRINTK_TIME=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_UNUSED_SYMBOLS=y
-CONFIG_DEBUG_FS=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_CRYPTO=y
-CONFIG_CRYPTO_GF128MUL=m
-CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPTO_MD5=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=m
-CONFIG_CRC16=m
diff --git a/arch/arm/configs/at91sam9261ek_defconfig b/arch/arm/configs/at91sam9261_defconfig
index b46025b66b64..ade6b2f23116 100644
--- a/arch/arm/configs/at91sam9261ek_defconfig
+++ b/arch/arm/configs/at91sam9261_defconfig
@@ -1,9 +1,13 @@
 CONFIG_EXPERIMENTAL=y
 # CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_KERNEL_LZMA=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
+CONFIG_NAMESPACES=y
+CONFIG_EMBEDDED=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
@@ -15,18 +19,27 @@ CONFIG_ARCH_AT91SAM9261=y
 CONFIG_MACH_AT91SAM9261EK=y
 CONFIG_AT91_PROGRAMMABLE_CLOCKS=y
 # CONFIG_ARM_THUMB is not set
+CONFIG_AEABI=y
+# CONFIG_OABI_COMPAT is not set
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_CMDLINE="mem=64M console=ttyS0,115200 initrd=0x21100000,3145728 root=/dev/ram0 rw"
-CONFIG_FPE_NWFPE=y
+CONFIG_AUTO_ZRELADDR=y
+CONFIG_VFP=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
+CONFIG_CFG80211=y
+CONFIG_LIB80211=y
+CONFIG_MAC80211=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
 CONFIG_MTD_PARTITIONS=y
@@ -34,8 +47,12 @@ CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_ATMEL=y
+CONFIG_MTD_UBI=y
+CONFIG_MTD_UBI_GLUEBI=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_MISC_DEVICES=y
+CONFIG_ATMEL_TCLIB=y
 CONFIG_ATMEL_SSC=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
@@ -45,12 +62,27 @@ CONFIG_NET_ETHERNET=y
 CONFIG_DM9000=y
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
+CONFIG_USB_ZD1201=m
+CONFIG_RTL8187=m
+CONFIG_LIBERTAS=m
+CONFIG_LIBERTAS_USB=m
+CONFIG_LIBERTAS_SDIO=m
+CONFIG_LIBERTAS_SPI=m
+CONFIG_RT2X00=m
+CONFIG_RT2500USB=m
+CONFIG_RT73USB=m
+CONFIG_ZD1211RW=m
+CONFIG_INPUT_POLLDEV=m
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
+CONFIG_INPUT_MOUSEDEV_SCREEN_X=240
+CONFIG_INPUT_MOUSEDEV_SCREEN_Y=320
+CONFIG_INPUT_EVDEV=y
 # CONFIG_KEYBOARD_ATKBD is not set
 CONFIG_KEYBOARD_GPIO=y
 # CONFIG_INPUT_MOUSE is not set
 CONFIG_INPUT_TOUCHSCREEN=y
 CONFIG_TOUCHSCREEN_ADS7846=y
+CONFIG_DEVPTS_MULTIPLE_INSTANCES=y
 CONFIG_SERIAL_ATMEL=y
 CONFIG_SERIAL_ATMEL_CONSOLE=y
 CONFIG_HW_RANDOM=y
@@ -65,31 +97,62 @@ CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_AT91SAM9X_WATCHDOG=y
 CONFIG_FB=y
 CONFIG_FB_ATMEL=y
-# CONFIG_VGA_CONSOLE is not set
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+# CONFIG_LCD_CLASS_DEVICE is not set
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
+CONFIG_BACKLIGHT_ATMEL_LCDC=y
+# CONFIG_BACKLIGHT_GENERIC is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
+CONFIG_LOGO=y
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_SEQUENCER=y
+CONFIG_SND_MIXER_OSS=y
+CONFIG_SND_PCM_OSS=y
+# CONFIG_SND_SUPPORT_OLD_API is not set
+# CONFIG_SND_VERBOSE_PROCFS is not set
+# CONFIG_SND_DRIVERS is not set
+# CONFIG_SND_ARM is not set
+CONFIG_SND_AT73C213=y
+CONFIG_SND_USB_AUDIO=m
 # CONFIG_USB_HID is not set
 CONFIG_USB=y
 CONFIG_USB_DEVICEFS=y
-CONFIG_USB_MON=y
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_STORAGE=y
-CONFIG_USB_STORAGE_DEBUG=y
 CONFIG_USB_GADGET=y
 CONFIG_USB_ZERO=m
+CONFIG_USB_ETH=m
 CONFIG_USB_GADGETFS=m
 CONFIG_USB_FILE_STORAGE=m
 CONFIG_USB_G_SERIAL=m
 CONFIG_MMC=y
 CONFIG_MMC_AT91=m
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_TIMER=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_LEDS_TRIGGER_GPIO=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_AT91SAM9=y
-CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
+CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
+CONFIG_UBIFS_FS=y
+CONFIG_UBIFS_FS_ADVANCED_COMPR=y
+CONFIG_SQUASHFS=y
+CONFIG_SQUASHFS_LZO=y
+CONFIG_SQUASHFS_XZ=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_ROOT_NFS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_CODEPAGE_850=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_USER=y
-CONFIG_DEBUG_LL=y
+CONFIG_NLS_ISO8859_15=y
+CONFIG_NLS_UTF8=y
+CONFIG_FTRACE=y
+CONFIG_CRC_CCITT=m
diff --git a/arch/arm/configs/at91sam9263ek_defconfig b/arch/arm/configs/at91sam9263_defconfig
index 8a04d6f4e065..1cf96264cba1 100644
--- a/arch/arm/configs/at91sam9263ek_defconfig
+++ b/arch/arm/configs/at91sam9263_defconfig
@@ -1,9 +1,13 @@
 CONFIG_EXPERIMENTAL=y
 # CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_KERNEL_LZMA=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
+CONFIG_NAMESPACES=y
+CONFIG_EMBEDDED=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
@@ -13,53 +17,81 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_ARCH_AT91=y
 CONFIG_ARCH_AT91SAM9263=y
 CONFIG_MACH_AT91SAM9263EK=y
+CONFIG_MACH_USB_A9263=y
+CONFIG_MACH_NEOCORE926=y
 CONFIG_MTD_AT91_DATAFLASH_CARD=y
 # CONFIG_ARM_THUMB is not set
+CONFIG_AEABI=y
+# CONFIG_OABI_COMPAT is not set
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_CMDLINE="mem=64M console=ttyS0,115200 initrd=0x21100000,3145728 root=/dev/ram0 rw"
-CONFIG_FPE_NWFPE=y
+CONFIG_AUTO_ZRELADDR=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
+CONFIG_NET_KEY=y
 CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_ROUTE_VERBOSE=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_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
 # 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_IPV6 is not set
+CONFIG_IPV6=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
 CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
+CONFIG_NFTL=y
+CONFIG_NFTL_RW=y
 CONFIG_MTD_DATAFLASH=y
+CONFIG_MTD_BLOCK2MTD=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_ATMEL=y
+CONFIG_MTD_NAND_ATMEL_ECC_SOFT=y
+CONFIG_MTD_UBI=y
+CONFIG_MTD_UBI_GLUEBI=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_ATMEL_SSC=y
+CONFIG_MISC_DEVICES=y
+CONFIG_ATMEL_PWM=y
+CONFIG_ATMEL_TCLIB=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_SCSI_MULTI_LUN=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
+CONFIG_SMSC_PHY=y
+CONFIG_NET_ETHERNET=y
 CONFIG_MACB=y
+# CONFIG_NETDEV_1000 is not set
+# CONFIG_NETDEV_10000 is not set
+CONFIG_USB_ZD1201=m
+CONFIG_INPUT_POLLDEV=m
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
+CONFIG_INPUT_MOUSEDEV_SCREEN_X=240
+CONFIG_INPUT_MOUSEDEV_SCREEN_Y=320
 CONFIG_INPUT_EVDEV=y
 # CONFIG_KEYBOARD_ATKBD is not set
 CONFIG_KEYBOARD_GPIO=y
 # CONFIG_INPUT_MOUSE is not set
 CONFIG_INPUT_TOUCHSCREEN=y
 CONFIG_TOUCHSCREEN_ADS7846=y
-# CONFIG_SERIO is not set
+CONFIG_LEGACY_PTY_COUNT=4
 CONFIG_SERIAL_ATMEL=y
 CONFIG_SERIAL_ATMEL_CONSOLE=y
 CONFIG_HW_RANDOM=y
@@ -74,8 +106,25 @@ CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_AT91SAM9X_WATCHDOG=y
 CONFIG_FB=y
 CONFIG_FB_ATMEL=y
-# CONFIG_VGA_CONSOLE is not set
-# CONFIG_USB_HID is not set
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_LCD_CLASS_DEVICE=y
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
+CONFIG_BACKLIGHT_ATMEL_LCDC=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
+CONFIG_LOGO=y
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_SEQUENCER=y
+CONFIG_SND_MIXER_OSS=y
+CONFIG_SND_PCM_OSS=y
+# CONFIG_SND_SUPPORT_OLD_API is not set
+# CONFIG_SND_VERBOSE_PROCFS is not set
+# CONFIG_SND_DRIVERS is not set
+# CONFIG_SND_ARM is not set
+CONFIG_SND_ATMEL_AC97C=y
+# CONFIG_SND_SPI is not set
+CONFIG_SND_USB_AUDIO=m
 CONFIG_USB=y
 CONFIG_USB_DEVICEFS=y
 CONFIG_USB_MON=y
@@ -83,24 +132,37 @@ CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_USB_GADGET=y
 CONFIG_USB_ZERO=m
+CONFIG_USB_ETH=m
 CONFIG_USB_GADGETFS=m
 CONFIG_USB_FILE_STORAGE=m
 CONFIG_USB_G_SERIAL=m
 CONFIG_MMC=y
+CONFIG_SDIO_UART=m
 CONFIG_MMC_AT91=m
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_ATMEL_PWM=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_AT91SAM9=y
 CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
+CONFIG_FUSE_FS=m
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
+CONFIG_UBIFS_FS=y
+CONFIG_UBIFS_FS_ADVANCED_COMPR=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_CODEPAGE_850=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_DEBUG_KERNEL=y
+CONFIG_FTRACE=y
 CONFIG_DEBUG_USER=y
-CONFIG_DEBUG_LL=y
+CONFIG_XZ_DEC=y
diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig
index 889922ad229c..67b5abb6f857 100644
--- a/arch/arm/configs/davinci_all_defconfig
+++ b/arch/arm/configs/davinci_all_defconfig
@@ -157,7 +157,7 @@ CONFIG_LEDS_GPIO=m
 CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=m
 CONFIG_LEDS_TRIGGER_HEARTBEAT=m
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_CLASS=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 CONFIG_XFS_FS=m
diff --git a/arch/arm/configs/exynos4_defconfig b/arch/arm/configs/exynos4_defconfig
index 2ffba24d2e2a..da53ff3b4d70 100644
--- a/arch/arm/configs/exynos4_defconfig
+++ b/arch/arm/configs/exynos4_defconfig
@@ -8,7 +8,9 @@ CONFIG_ARCH_EXYNOS4=y
 CONFIG_S3C_LOWLEVEL_UART_PORT=1
 CONFIG_MACH_SMDKC210=y
 CONFIG_MACH_SMDKV310=y
+CONFIG_MACH_ARMLEX4210=y
 CONFIG_MACH_UNIVERSAL_C210=y
+CONFIG_MACH_NURI=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_SMP=y
diff --git a/arch/arm/configs/neocore926_defconfig b/arch/arm/configs/neocore926_defconfig
deleted file mode 100644
index 462dd1850d15..000000000000
--- a/arch/arm/configs/neocore926_defconfig
+++ /dev/null
@@ -1,104 +0,0 @@
-CONFIG_EXPERIMENTAL=y
-# CONFIG_LOCALVERSION_AUTO is not set
-# CONFIG_SWAP is not set
-CONFIG_SYSVIPC=y
-CONFIG_BLK_DEV_INITRD=y
-# CONFIG_COMPAT_BRK is not set
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARCH_AT91=y
-CONFIG_ARCH_AT91SAM9263=y
-CONFIG_MACH_NEOCORE926=y
-CONFIG_MTD_AT91_DATAFLASH_CARD=y
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_FPE_NWFPE=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_NET_KEY=y
-CONFIG_INET=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_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
-CONFIG_MTD_CHAR=y
-CONFIG_MTD_BLOCK=y
-CONFIG_NFTL=y
-CONFIG_NFTL_RW=y
-CONFIG_MTD_BLOCK2MTD=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ECC_SMC=y
-CONFIG_MTD_NAND_VERIFY_WRITE=y
-CONFIG_MTD_NAND_ATMEL=y
-CONFIG_MTD_NAND_PLATFORM=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_NBD=y
-CONFIG_ATMEL_PWM=y
-CONFIG_ATMEL_TCLIB=y
-CONFIG_SCSI=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_NETDEVICES=y
-CONFIG_SMSC_PHY=y
-CONFIG_NET_ETHERNET=y
-CONFIG_MACB=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
-CONFIG_INPUT_EVDEV=y
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_ADS7846=y
-CONFIG_VT_HW_CONSOLE_BINDING=y
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_NONSTANDARD=y
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_SERIAL_ATMEL_PDC is not set
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-# CONFIG_HWMON is not set
-CONFIG_VIDEO_OUTPUT_CONTROL=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
-CONFIG_LCD_CLASS_DEVICE=y
-CONFIG_BACKLIGHT_CLASS_DEVICE=y
-CONFIG_BACKLIGHT_ATMEL_LCDC=y
-# CONFIG_VGA_CONSOLE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
-CONFIG_LOGO=y
-CONFIG_USB=y
-CONFIG_USB_DEVICEFS=y
-CONFIG_USB_MON=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_STORAGE=y
-CONFIG_MMC=y
-CONFIG_SDIO_UART=y
-CONFIG_MMC_AT91=m
-CONFIG_EXT2_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_AUTOFS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=y
-CONFIG_JFFS2_FS_WBUF_VERIFY=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-# CONFIG_ENABLE_WARN_DEPRECATED is not set
-# CONFIG_ENABLE_MUST_CHECK is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-# CONFIG_CRYPTO_HW is not set
diff --git a/arch/arm/configs/netx_defconfig b/arch/arm/configs/netx_defconfig
index 316af5479d90..9c0ad7993986 100644
--- a/arch/arm/configs/netx_defconfig
+++ b/arch/arm/configs/netx_defconfig
@@ -60,7 +60,7 @@ CONFIG_FB_ARMCLCD=y
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_CLASS=y
 CONFIG_INOTIFY=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/arm/configs/s5p6442_defconfig b/arch/arm/configs/s5p6442_defconfig
deleted file mode 100644
index 0e92a784af66..000000000000
--- a/arch/arm/configs/s5p6442_defconfig
+++ /dev/null
@@ -1,65 +0,0 @@
-CONFIG_EXPERIMENTAL=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_ARCH_S5P6442=y
-CONFIG_S3C_LOWLEVEL_UART_PORT=1
-CONFIG_MACH_SMDK6442=y
-CONFIG_CPU_32v6K=y
-CONFIG_AEABI=y
-CONFIG_CMDLINE="root=/dev/ram0 rw ramdisk=8192 initrd=0x20800000,8M console=ttySAC1,115200 init=/linuxrc"
-CONFIG_FPE_NWFPE=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=8192
-# CONFIG_MISC_DEVICES is not set
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_INPUT_EVDEV=y
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_NR_UARTS=3
-CONFIG_SERIAL_SAMSUNG=y
-CONFIG_SERIAL_SAMSUNG_CONSOLE=y
-CONFIG_HW_RANDOM=y
-# CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
-# CONFIG_HID_SUPPORT is not set
-# CONFIG_USB_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_CRAMFS=y
-CONFIG_ROMFS_FS=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ASCII=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_RT_MUTEXES=y
-CONFIG_DEBUG_SPINLOCK=y
-CONFIG_DEBUG_MUTEXES=y
-CONFIG_DEBUG_SPINLOCK_SLEEP=y
-CONFIG_DEBUG_INFO=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-# CONFIG_ARM_UNWIND is not set
-CONFIG_DEBUG_USER=y
-CONFIG_DEBUG_ERRORS=y
-CONFIG_DEBUG_LL=y
-CONFIG_DEBUG_S3C_UART=1
-CONFIG_CRC_CCITT=y
diff --git a/arch/arm/configs/usb-a9263_defconfig b/arch/arm/configs/usb-a9263_defconfig
deleted file mode 100644
index ee82d09249c6..000000000000
--- a/arch/arm/configs/usb-a9263_defconfig
+++ /dev/null
@@ -1,106 +0,0 @@
-CONFIG_EXPERIMENTAL=y
-# CONFIG_LOCALVERSION_AUTO is not set
-# CONFIG_SWAP is not set
-CONFIG_SYSVIPC=y
-CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-CONFIG_SLAB=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARCH_AT91=y
-CONFIG_ARCH_AT91SAM9263=y
-CONFIG_MACH_USB_A9263=y
-CONFIG_AT91_SLOW_CLOCK=y
-# CONFIG_ARM_THUMB is not set
-CONFIG_AEABI=y
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_CMDLINE="mem=64M console=ttyS0,115200"
-CONFIG_FPE_NWFPE=y
-CONFIG_PM=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_ROUTE_VERBOSE=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_IP_PNP_RARP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_IP_PIMSM_V2=y
-# 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_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ATMEL=y
-CONFIG_MTD_NAND_ATMEL_ECC_SOFT=y
-CONFIG_BLK_DEV_LOOP=y
-# CONFIG_MISC_DEVICES is not set
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_SCSI_MULTI_LUN=y
-CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_MII=y
-CONFIG_MACB=y
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
-CONFIG_INPUT_EVDEV=y
-CONFIG_INPUT_EVBUG=y
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=y
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-CONFIG_HW_RANDOM=y
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-# CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
-# CONFIG_USB_HID is not set
-CONFIG_USB=y
-CONFIG_USB_DEVICEFS=y
-CONFIG_USB_MON=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_STORAGE=y
-CONFIG_USB_GADGET=y
-CONFIG_USB_ETH=m
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
-CONFIG_FUSE_FS=m
-CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_850=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_USER=y
-CONFIG_DEBUG_LL=y
-# CONFIG_CRYPTO_HW is not set
diff --git a/arch/arm/configs/viper_defconfig b/arch/arm/configs/viper_defconfig
index 8b0c717378fa..1d01ddd33122 100644
--- a/arch/arm/configs/viper_defconfig
+++ b/arch/arm/configs/viper_defconfig
@@ -142,7 +142,7 @@ CONFIG_USB_GADGETFS=m
 CONFIG_USB_FILE_STORAGE=m
 CONFIG_USB_G_SERIAL=m
 CONFIG_USB_G_PRINTER=m
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=m
 CONFIG_RTC_DRV_SA1100=m
 CONFIG_EXT2_FS=m
diff --git a/arch/arm/configs/xcep_defconfig b/arch/arm/configs/xcep_defconfig
index 5b5504143647..721832ffe2d7 100644
--- a/arch/arm/configs/xcep_defconfig
+++ b/arch/arm/configs/xcep_defconfig
@@ -73,7 +73,7 @@ CONFIG_SENSORS_MAX6650=m
 # CONFIG_VGA_CONSOLE is not set
 # CONFIG_HID_SUPPORT is not set
 # CONFIG_USB_SUPPORT is not set
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_SA1100=m
 CONFIG_DMADEVICES=y
 # CONFIG_DNOTIFY is not set
diff --git a/arch/arm/configs/zeus_defconfig b/arch/arm/configs/zeus_defconfig
index 960f65514d88..59577ad3f4ef 100644
--- a/arch/arm/configs/zeus_defconfig
+++ b/arch/arm/configs/zeus_defconfig
@@ -158,7 +158,7 @@ CONFIG_LEDS_TRIGGER_HEARTBEAT=m
 CONFIG_LEDS_TRIGGER_BACKLIGHT=m
 CONFIG_LEDS_TRIGGER_GPIO=m
 CONFIG_LEDS_TRIGGER_DEFAULT_ON=m
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_ISL1208=m
 CONFIG_RTC_DRV_PXA=m
 CONFIG_EXT2_FS=y
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index bc2d2d75f706..65c3f2474f5e 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -13,6 +13,9 @@
  *  Do not include any C declarations in this file - it is included by
  *  assembler source.
  */
+#ifndef __ASM_ASSEMBLER_H__
+#define __ASM_ASSEMBLER_H__
+
 #ifndef __ASSEMBLY__
 #error "Only include this from assembly code"
 #endif
@@ -290,3 +293,4 @@
 	.macro	ldrusr, reg, ptr, inc, cond=al, rept=1, abort=9001f
 	usracc	ldr, \reg, \ptr, \inc, \cond, \rept, \abort
 	.endm
+#endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S
index ec0bbf79c71f..2da8547de6d6 100644
--- a/arch/arm/include/asm/entry-macro-multi.S
+++ b/arch/arm/include/asm/entry-macro-multi.S
@@ -1,3 +1,5 @@
+#include <asm/assembler.h>
+
 /*
  * Interrupt handling.  Preserves r7, r8, r9
  */
diff --git a/arch/arm/include/asm/fiq.h b/arch/arm/include/asm/fiq.h
index 2242ce22ec6c..d493d0b742a1 100644
--- a/arch/arm/include/asm/fiq.h
+++ b/arch/arm/include/asm/fiq.h
@@ -4,6 +4,13 @@
  * Support for FIQ on ARM architectures.
  * Written by Philip Blundell <philb@gnu.org>, 1998
  * Re-written by Russell King
+ *
+ * NOTE: The FIQ mode registers are not magically preserved across
+ * suspend/resume.
+ *
+ * Drivers which require these registers to be preserved across power
+ * management operations must implement appropriate suspend/resume handlers to
+ * save and restore them.
  */
 
 #ifndef __ASM_FIQ_H
@@ -29,9 +36,21 @@ struct fiq_handler {
 extern int claim_fiq(struct fiq_handler *f);
 extern void release_fiq(struct fiq_handler *f);
 extern void set_fiq_handler(void *start, unsigned int length);
-extern void set_fiq_regs(struct pt_regs *regs);
-extern void get_fiq_regs(struct pt_regs *regs);
 extern void enable_fiq(int fiq);
 extern void disable_fiq(int fiq);
 
+/* helpers defined in fiqasm.S: */
+extern void __set_fiq_regs(unsigned long const *regs);
+extern void __get_fiq_regs(unsigned long *regs);
+
+static inline void set_fiq_regs(struct pt_regs const *regs)
+{
+	__set_fiq_regs(&regs->ARM_r8);
+}
+
+static inline void get_fiq_regs(struct pt_regs *regs)
+{
+	__get_fiq_regs(&regs->ARM_r8);
+}
+
 #endif
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index bf13b814c1b8..946f4d778f71 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -18,6 +18,8 @@ struct machine_desc {
 	unsigned int		nr;		/* architecture number	*/
 	const char		*name;		/* architecture name	*/
 	unsigned long		boot_params;	/* tagged list		*/
+	const char		**dt_compat;	/* array of device tree
+						 * 'compatible' strings	*/
 
 	unsigned int		nr_irqs;	/* number of IRQs */
 
@@ -48,6 +50,13 @@ struct machine_desc {
 extern struct machine_desc *machine_desc;
 
 /*
+ * Machine type table - also only accessible during boot
+ */
+extern struct machine_desc __arch_info_begin[], __arch_info_end[];
+#define for_each_machine_desc(p)			\
+	for (p = __arch_info_begin; p < __arch_info_end; p++)
+
+/*
  * Set of macros to define architecture features.  This is built into
  * a table by the linker.
  */
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index f51a69595f6e..ac75d0848889 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -197,7 +197,7 @@ typedef unsigned long pgprot_t;
 
 typedef struct page *pgtable_t;
 
-#ifndef CONFIG_SPARSEMEM
+#ifdef CONFIG_HAVE_ARCH_PFN_VALID
 extern int pfn_valid(unsigned long);
 #endif
 
diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h
new file mode 100644
index 000000000000..11b8708fc4db
--- /dev/null
+++ b/arch/arm/include/asm/prom.h
@@ -0,0 +1,37 @@
+/*
+ *  arch/arm/include/asm/prom.h
+ *
+ *  Copyright (C) 2009 Canonical Ltd. <jeremy.kerr@canonical.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.
+ *
+ */
+#ifndef __ASMARM_PROM_H
+#define __ASMARM_PROM_H
+
+#ifdef CONFIG_OF
+
+#include <asm/setup.h>
+#include <asm/irq.h>
+
+static inline void irq_dispose_mapping(unsigned int virq)
+{
+	return;
+}
+
+extern struct machine_desc *setup_machine_fdt(unsigned int dt_phys);
+extern void arm_dt_memblock_reserve(void);
+
+#else /* CONFIG_OF */
+
+static inline struct machine_desc *setup_machine_fdt(unsigned int dt_phys)
+{
+	return NULL;
+}
+
+static inline void arm_dt_memblock_reserve(void) { }
+
+#endif /* CONFIG_OF */
+#endif /* ASMARM_PROM_H */
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index 95176af3df8c..ee2ad8ae07af 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -217,6 +217,10 @@ extern struct meminfo meminfo;
 #define bank_phys_end(bank)	((bank)->start + (bank)->size)
 #define bank_phys_size(bank)	(bank)->size
 
+extern int arm_add_memory(phys_addr_t start, unsigned long size);
+extern void early_print(const char *str, ...);
+extern void dump_machine_table(void);
+
 #endif  /*  __KERNEL__  */
 
 #endif
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index d2b514fd76f4..e42d96a45d3e 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -70,6 +70,7 @@ extern void platform_smp_prepare_cpus(unsigned int);
  */
 struct secondary_data {
 	unsigned long pgdir;
+	unsigned long swapper_pg_dir;
 	void *stack;
 };
 extern struct secondary_data secondary_data;
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 87dbe3e21970..2c04ed5efeb5 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -400,6 +400,8 @@
 #define __NR_open_by_handle_at		(__NR_SYSCALL_BASE+371)
 #define __NR_clock_adjtime		(__NR_SYSCALL_BASE+372)
 #define __NR_syncfs			(__NR_SYSCALL_BASE+373)
+#define __NR_sendmmsg			(__NR_SYSCALL_BASE+374)
+#define __NR_setns			(__NR_SYSCALL_BASE+375)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 8d95446150a3..a5b31af5c2b8 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -24,7 +24,7 @@ obj-$(CONFIG_OC_ETM)		+= etm.o
 
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
 obj-$(CONFIG_ARCH_ACORN)	+= ecard.o 
-obj-$(CONFIG_FIQ)		+= fiq.o
+obj-$(CONFIG_FIQ)		+= fiq.o fiqasm.o
 obj-$(CONFIG_MODULES)		+= armksyms.o module.o
 obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
@@ -44,6 +44,7 @@ obj-$(CONFIG_ARM_THUMBEE)	+= thumbee.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_ARM_UNWIND)	+= unwind.o
 obj-$(CONFIG_HAVE_TCM)		+= tcm.o
+obj-$(CONFIG_OF)		+= devtree.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_SWP_EMULATE)	+= swp_emulate.o
 CFLAGS_swp_emulate.o		:= -Wa,-march=armv7-a
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 7fbf28c35bb2..80f7896cc016 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -383,6 +383,8 @@
 		CALL(sys_open_by_handle_at)
 		CALL(sys_clock_adjtime)
 		CALL(sys_syncfs)
+		CALL(sys_sendmmsg)
+/* 375 */	CALL(sys_setns)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
new file mode 100644
index 000000000000..0cdd7b456cb2
--- /dev/null
+++ b/arch/arm/kernel/devtree.c
@@ -0,0 +1,148 @@
+/*
+ *  linux/arch/arm/kernel/devtree.c
+ *
+ *  Copyright (C) 2009 Canonical Ltd. <jeremy.kerr@canonical.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/init.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/bootmem.h>
+#include <linux/memblock.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+
+#include <asm/setup.h>
+#include <asm/page.h>
+#include <asm/mach/arch.h>
+#include <asm/mach-types.h>
+
+void __init early_init_dt_add_memory_arch(u64 base, u64 size)
+{
+	arm_add_memory(base, size);
+}
+
+void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
+{
+	return alloc_bootmem_align(size, align);
+}
+
+void __init arm_dt_memblock_reserve(void)
+{
+	u64 *reserve_map, base, size;
+
+	if (!initial_boot_params)
+		return;
+
+	/* Reserve the dtb region */
+	memblock_reserve(virt_to_phys(initial_boot_params),
+			 be32_to_cpu(initial_boot_params->totalsize));
+
+	/*
+	 * Process the reserve map.  This will probably overlap the initrd
+	 * and dtb locations which are already reserved, but overlaping
+	 * doesn't hurt anything
+	 */
+	reserve_map = ((void*)initial_boot_params) +
+			be32_to_cpu(initial_boot_params->off_mem_rsvmap);
+	while (1) {
+		base = be64_to_cpup(reserve_map++);
+		size = be64_to_cpup(reserve_map++);
+		if (!size)
+			break;
+		memblock_reserve(base, size);
+	}
+}
+
+/**
+ * setup_machine_fdt - Machine setup when an dtb was passed to the kernel
+ * @dt_phys: physical address of dt blob
+ *
+ * If a dtb was passed to the kernel in r2, then use it to choose the
+ * correct machine_desc and to setup the system.
+ */
+struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
+{
+	struct boot_param_header *devtree;
+	struct machine_desc *mdesc, *mdesc_best = NULL;
+	unsigned int score, mdesc_score = ~1;
+	unsigned long dt_root;
+	const char *model;
+
+	if (!dt_phys)
+		return NULL;
+
+	devtree = phys_to_virt(dt_phys);
+
+	/* check device tree validity */
+	if (be32_to_cpu(devtree->magic) != OF_DT_HEADER)
+		return NULL;
+
+	/* Search the mdescs for the 'best' compatible value match */
+	initial_boot_params = devtree;
+	dt_root = of_get_flat_dt_root();
+	for_each_machine_desc(mdesc) {
+		score = of_flat_dt_match(dt_root, mdesc->dt_compat);
+		if (score > 0 && score < mdesc_score) {
+			mdesc_best = mdesc;
+			mdesc_score = score;
+		}
+	}
+	if (!mdesc_best) {
+		const char *prop;
+		long size;
+
+		early_print("\nError: unrecognized/unsupported "
+			    "device tree compatible list:\n[ ");
+
+		prop = of_get_flat_dt_prop(dt_root, "compatible", &size);
+		while (size > 0) {
+			early_print("'%s' ", prop);
+			size -= strlen(prop) + 1;
+			prop += strlen(prop) + 1;
+		}
+		early_print("]\n\n");
+
+		dump_machine_table(); /* does not return */
+	}
+
+	model = of_get_flat_dt_prop(dt_root, "model", NULL);
+	if (!model)
+		model = of_get_flat_dt_prop(dt_root, "compatible", NULL);
+	if (!model)
+		model = "<unknown>";
+	pr_info("Machine: %s, model: %s\n", mdesc_best->name, model);
+
+	/* Retrieve various information from the /chosen node */
+	of_scan_flat_dt(early_init_dt_scan_chosen, boot_command_line);
+	/* Initialize {size,address}-cells info */
+	of_scan_flat_dt(early_init_dt_scan_root, NULL);
+	/* Setup memory, calling early_init_dt_add_memory_arch */
+	of_scan_flat_dt(early_init_dt_scan_memory, NULL);
+
+	/* Change machine number to match the mdesc we're using */
+	__machine_arch_type = mdesc_best->nr;
+
+	return mdesc_best;
+}
+
+/**
+ * irq_create_of_mapping - Hook to resolve OF irq specifier into a Linux irq#
+ *
+ * Currently the mapping mechanism is trivial; simple flat hwirq numbers are
+ * mapped 1:1 onto Linux irq numbers.  Cascaded irq controllers are not
+ * supported.
+ */
+unsigned int irq_create_of_mapping(struct device_node *controller,
+				   const u32 *intspec, unsigned int intsize)
+{
+	return intspec[0];
+}
+EXPORT_SYMBOL_GPL(irq_create_of_mapping);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index e8d885676807..90c62cd51ca9 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -435,6 +435,10 @@ __irq_usr:
 	usr_entry
 	kuser_cmpxchg_check
 
+#ifdef CONFIG_IRQSOFF_TRACER
+	bl	trace_hardirqs_off
+#endif
+
 	get_thread_info tsk
 #ifdef CONFIG_PREEMPT
 	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
@@ -453,7 +457,7 @@ __irq_usr:
 #endif
 
 	mov	why, #0
-	b	ret_to_user
+	b	ret_to_user_from_irq
  UNWIND(.fnend		)
 ENDPROC(__irq_usr)
 
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 1e7b04a40a31..b2a27b6b0046 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -64,6 +64,7 @@ work_resched:
 ENTRY(ret_to_user)
 ret_slow_syscall:
 	disable_irq				@ disable interrupts
+ENTRY(ret_to_user_from_irq)
 	ldr	r1, [tsk, #TI_FLAGS]
 	tst	r1, #_TIF_WORK_MASK
 	bne	work_pending
@@ -75,6 +76,7 @@ no_work_pending:
 	arch_ret_to_user r1, lr
 
 	restore_user_regs fast = 0, offset = 0
+ENDPROC(ret_to_user_from_irq)
 ENDPROC(ret_to_user)
 
 /*
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index e72dc34eea1c..4c164ece5891 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -89,47 +89,6 @@ void set_fiq_handler(void *start, unsigned int length)
 		flush_icache_range(0x1c, 0x1c + length);
 }
 
-/*
- * Taking an interrupt in FIQ mode is death, so both these functions
- * disable irqs for the duration.  Note - these functions are almost
- * entirely coded in assembly.
- */
-void __naked set_fiq_regs(struct pt_regs *regs)
-{
-	register unsigned long tmp;
-	asm volatile (
-	"mov	ip, sp\n\
-	stmfd	sp!, {fp, ip, lr, pc}\n\
-	sub	fp, ip, #4\n\
-	mrs	%0, cpsr\n\
-	msr	cpsr_c, %2	@ select FIQ mode\n\
-	mov	r0, r0\n\
-	ldmia	%1, {r8 - r14}\n\
-	msr	cpsr_c, %0	@ return to SVC mode\n\
-	mov	r0, r0\n\
-	ldmfd	sp, {fp, sp, pc}"
-	: "=&r" (tmp)
-	: "r" (&regs->ARM_r8), "I" (PSR_I_BIT | PSR_F_BIT | FIQ_MODE));
-}
-
-void __naked get_fiq_regs(struct pt_regs *regs)
-{
-	register unsigned long tmp;
-	asm volatile (
-	"mov	ip, sp\n\
-	stmfd	sp!, {fp, ip, lr, pc}\n\
-	sub	fp, ip, #4\n\
-	mrs	%0, cpsr\n\
-	msr	cpsr_c, %2	@ select FIQ mode\n\
-	mov	r0, r0\n\
-	stmia	%1, {r8 - r14}\n\
-	msr	cpsr_c, %0	@ return to SVC mode\n\
-	mov	r0, r0\n\
-	ldmfd	sp, {fp, sp, pc}"
-	: "=&r" (tmp)
-	: "r" (&regs->ARM_r8), "I" (PSR_I_BIT | PSR_F_BIT | FIQ_MODE));
-}
-
 int claim_fiq(struct fiq_handler *f)
 {
 	int ret = 0;
@@ -174,8 +133,8 @@ void disable_fiq(int fiq)
 }
 
 EXPORT_SYMBOL(set_fiq_handler);
-EXPORT_SYMBOL(set_fiq_regs);
-EXPORT_SYMBOL(get_fiq_regs);
+EXPORT_SYMBOL(__set_fiq_regs);	/* defined in fiqasm.S */
+EXPORT_SYMBOL(__get_fiq_regs);	/* defined in fiqasm.S */
 EXPORT_SYMBOL(claim_fiq);
 EXPORT_SYMBOL(release_fiq);
 EXPORT_SYMBOL(enable_fiq);
diff --git a/arch/arm/kernel/fiqasm.S b/arch/arm/kernel/fiqasm.S
new file mode 100644
index 000000000000..207f9d652010
--- /dev/null
+++ b/arch/arm/kernel/fiqasm.S
@@ -0,0 +1,49 @@
+/*
+ *  linux/arch/arm/kernel/fiqasm.S
+ *
+ *  Derived from code originally in linux/arch/arm/kernel/fiq.c:
+ *
+ *  Copyright (C) 1998 Russell King
+ *  Copyright (C) 1998, 1999 Phil Blundell
+ *  Copyright (C) 2011, Linaro Limited
+ *
+ *  FIQ support written by Philip Blundell <philb@gnu.org>, 1998.
+ *
+ *  FIQ support re-written by Russell King to be more generic
+ *
+ *  v7/Thumb-2 compatibility modifications by Linaro Limited, 2011.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * Taking an interrupt in FIQ mode is death, so both these functions
+ * disable irqs for the duration.
+ */
+
+ENTRY(__set_fiq_regs)
+	mov	r2, #PSR_I_BIT | PSR_F_BIT | FIQ_MODE
+	mrs	r1, cpsr
+	msr	cpsr_c, r2	@ select FIQ mode
+	mov	r0, r0		@ avoid hazard prior to ARMv4
+	ldmia	r0!, {r8 - r12}
+	ldr	sp, [r0], #4
+	ldr	lr, [r0]
+	msr	cpsr_c, r1	@ return to SVC mode
+	mov	r0, r0		@ avoid hazard prior to ARMv4
+	mov	pc, lr
+ENDPROC(__set_fiq_regs)
+
+ENTRY(__get_fiq_regs)
+	mov	r2, #PSR_I_BIT | PSR_F_BIT | FIQ_MODE
+	mrs	r1, cpsr
+	msr	cpsr_c, r2	@ select FIQ mode
+	mov	r0, r0		@ avoid hazard prior to ARMv4
+	stmia	r0!, {r8 - r12}
+	str	sp, [r0], #4
+	str	lr, [r0]
+	msr	cpsr_c, r1	@ return to SVC mode
+	mov	r0, r0		@ avoid hazard prior to ARMv4
+	mov	pc, lr
+ENDPROC(__get_fiq_regs)
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index c84b57d27d07..854bd22380d3 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -15,6 +15,12 @@
 #define ATAG_CORE_SIZE ((2*4 + 3*4) >> 2)
 #define ATAG_CORE_SIZE_EMPTY ((2*4) >> 2)
 
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define OF_DT_MAGIC 0xd00dfeed
+#else
+#define OF_DT_MAGIC 0xedfe0dd0 /* 0xd00dfeed in big-endian */
+#endif
+
 /*
  * Exception handling.  Something went wrong and we can't proceed.  We
  * ought to tell the user, but since we don't have any guarantee that
@@ -28,20 +34,26 @@
 
 /* Determine validity of the r2 atags pointer.  The heuristic requires
  * that the pointer be aligned, in the first 16k of physical RAM and
- * that the ATAG_CORE marker is first and present.  Future revisions
+ * that the ATAG_CORE marker is first and present.  If CONFIG_OF_FLATTREE
+ * is selected, then it will also accept a dtb pointer.  Future revisions
  * of this function may be more lenient with the physical address and
  * may also be able to move the ATAGS block if necessary.
  *
  * Returns:
- *  r2 either valid atags pointer, or zero
+ *  r2 either valid atags pointer, valid dtb pointer, or zero
  *  r5, r6 corrupted
  */
 __vet_atags:
 	tst	r2, #0x3			@ aligned?
 	bne	1f
 
-	ldr	r5, [r2, #0]			@ is first tag ATAG_CORE?
-	cmp	r5, #ATAG_CORE_SIZE
+	ldr	r5, [r2, #0]
+#ifdef CONFIG_OF_FLATTREE
+	ldr	r6, =OF_DT_MAGIC		@ is it a DTB?
+	cmp	r5, r6
+	beq	2f
+#endif
+	cmp	r5, #ATAG_CORE_SIZE		@ is first tag ATAG_CORE?
 	cmpne	r5, #ATAG_CORE_SIZE_EMPTY
 	bne	1f
 	ldr	r5, [r2, #4]
@@ -49,7 +61,7 @@ __vet_atags:
 	cmp	r5, r6
 	bne	1f
 
-	mov	pc, lr				@ atag pointer is ok
+2:	mov	pc, lr				@ atag/dtb pointer is ok
 
 1:	mov	r2, #0
 	mov	pc, lr
@@ -61,7 +73,7 @@ ENDPROC(__vet_atags)
  *
  *  r0  = cp#15 control register
  *  r1  = machine ID
- *  r2  = atags pointer
+ *  r2  = atags/dtb pointer
  *  r9  = processor ID
  */
 	__INIT
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index c9173cfbbc74..278c1b0ebb2e 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -59,7 +59,7 @@
  *
  * This is normally called from the decompressor code.  The requirements
  * are: MMU = off, D-cache = off, I-cache = dont care, r0 = 0,
- * r1 = machine nr, r2 = atags pointer.
+ * r1 = machine nr, r2 = atags or dtb pointer.
  *
  * This code is mostly position independent, so if you link the kernel at
  * 0xc0008000, you call this at __pa(0xc0008000).
@@ -91,7 +91,7 @@ ENTRY(stext)
 #endif
 
 	/*
-	 * r1 = machine no, r2 = atags,
+	 * r1 = machine no, r2 = atags or dtb,
 	 * r8 = phys_offset, r9 = cpuid, r10 = procinfo
 	 */
 	bl	__vet_atags
@@ -113,6 +113,7 @@ ENTRY(stext)
 	ldr	r13, =__mmap_switched		@ address to jump to after
 						@ mmu has been enabled
 	adr	lr, BSYM(1f)			@ return (PIC) address
+	mov	r8, r4				@ set TTBR1 to swapper_pg_dir
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
  THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
  THUMB(	mov	pc, r12				)
@@ -302,8 +303,10 @@ ENTRY(secondary_startup)
 	 */
 	adr	r4, __secondary_data
 	ldmia	r4, {r5, r7, r12}		@ address to jump to after
-	sub	r4, r4, r5			@ mmu has been enabled
-	ldr	r4, [r7, r4]			@ get secondary_data.pgdir
+	sub	lr, r4, r5			@ mmu has been enabled
+	ldr	r4, [r7, lr]			@ get secondary_data.pgdir
+	add	r7, r7, #4
+	ldr	r8, [r7, lr]			@ get secondary_data.swapper_pg_dir
 	adr	lr, BSYM(__enable_mmu)		@ return address
 	mov	r13, r12			@ __secondary_switched address
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	) @ initialise processor
@@ -339,7 +342,7 @@ __secondary_data:
  *
  *  r0  = cp#15 control register
  *  r1  = machine ID
- *  r2  = atags pointer
+ *  r2  = atags or dtb pointer
  *  r4  = page table pointer
  *  r9  = processor ID
  *  r13 = *virtual* address to jump to upon completion
@@ -376,7 +379,7 @@ ENDPROC(__enable_mmu)
  *
  *  r0  = cp#15 control register
  *  r1  = machine ID
- *  r2  = atags pointer
+ *  r2  = atags or dtb pointer
  *  r9  = processor ID
  *  r13 = *virtual* address to jump to upon completion
  *
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index fee7c36349eb..016d6a0830a3 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -193,8 +193,17 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 				offset -= 0x02000000;
 			offset += sym->st_value - loc;
 
-			/* only Thumb addresses allowed (no interworking) */
-			if (!(offset & 1) ||
+			/*
+			 * For function symbols, only Thumb addresses are
+			 * allowed (no interworking).
+			 *
+			 * For non-function symbols, the destination
+			 * has no specific ARM/Thumb disposition, so
+			 * the branch is resolved under the assumption
+			 * that interworking is not required.
+			 */
+			if ((ELF32_ST_TYPE(sym->st_info) == STT_FUNC &&
+				!(offset & 1)) ||
 			    offset <= (s32)0xff000000 ||
 			    offset >= (s32)0x01000000) {
 				pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 6dce209a623b..ed11fb08b05a 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -20,6 +20,7 @@
 #include <linux/screen_info.h>
 #include <linux/init.h>
 #include <linux/kexec.h>
+#include <linux/of_fdt.h>
 #include <linux/crash_dump.h>
 #include <linux/root_dev.h>
 #include <linux/cpu.h>
@@ -42,6 +43,7 @@
 #include <asm/cachetype.h>
 #include <asm/tlbflush.h>
 
+#include <asm/prom.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
@@ -309,7 +311,7 @@ static void __init cacheid_init(void)
  */
 extern struct proc_info_list *lookup_processor_type(unsigned int);
 
-static void __init early_print(const char *str, ...)
+void __init early_print(const char *str, ...)
 {
 	extern void printascii(const char *);
 	char buf[256];
@@ -439,25 +441,12 @@ void cpu_init(void)
 	    : "r14");
 }
 
-static struct machine_desc * __init setup_machine(unsigned int nr)
+void __init dump_machine_table(void)
 {
-	extern struct machine_desc __arch_info_begin[], __arch_info_end[];
 	struct machine_desc *p;
 
-	/*
-	 * locate machine in the list of supported machines.
-	 */
-	for (p = __arch_info_begin; p < __arch_info_end; p++)
-		if (nr == p->nr) {
-			printk("Machine: %s\n", p->name);
-			return p;
-		}
-
-	early_print("\n"
-		"Error: unrecognized/unsupported machine ID (r1 = 0x%08x).\n\n"
-		"Available machine support:\n\nID (hex)\tNAME\n", nr);
-
-	for (p = __arch_info_begin; p < __arch_info_end; p++)
+	early_print("Available machine support:\n\nID (hex)\tNAME\n");
+	for_each_machine_desc(p)
 		early_print("%08x\t%s\n", p->nr, p->name);
 
 	early_print("\nPlease check your kernel config and/or bootloader.\n");
@@ -466,7 +455,7 @@ static struct machine_desc * __init setup_machine(unsigned int nr)
 		/* can't use cpu_relax() here as it may require MMU setup */;
 }
 
-static int __init arm_add_memory(phys_addr_t start, unsigned long size)
+int __init arm_add_memory(phys_addr_t start, unsigned long size)
 {
 	struct membank *bank = &meminfo.bank[meminfo.nr_banks];
 
@@ -801,23 +790,29 @@ static void __init squash_mem_tags(struct tag *tag)
 			tag->hdr.tag = ATAG_NONE;
 }
 
-void __init setup_arch(char **cmdline_p)
+static struct machine_desc * __init setup_machine_tags(unsigned int nr)
 {
 	struct tag *tags = (struct tag *)&init_tags;
-	struct machine_desc *mdesc;
+	struct machine_desc *mdesc = NULL, *p;
 	char *from = default_command_line;
 
 	init_tags.mem.start = PHYS_OFFSET;
 
-	unwind_init();
-
-	setup_processor();
-	mdesc = setup_machine(machine_arch_type);
-	machine_desc = mdesc;
-	machine_name = mdesc->name;
+	/*
+	 * locate machine in the list of supported machines.
+	 */
+	for_each_machine_desc(p)
+		if (nr == p->nr) {
+			printk("Machine: %s\n", p->name);
+			mdesc = p;
+			break;
+		}
 
-	if (mdesc->soft_reboot)
-		reboot_setup("s");
+	if (!mdesc) {
+		early_print("\nError: unrecognized/unsupported machine ID"
+			" (r1 = 0x%08x).\n\n", nr);
+		dump_machine_table(); /* does not return */
+	}
 
 	if (__atags_pointer)
 		tags = phys_to_virt(__atags_pointer);
@@ -849,8 +844,17 @@ void __init setup_arch(char **cmdline_p)
 	if (tags->hdr.tag != ATAG_CORE)
 		convert_to_tag_list(tags);
 #endif
-	if (tags->hdr.tag != ATAG_CORE)
+
+	if (tags->hdr.tag != ATAG_CORE) {
+#if defined(CONFIG_OF)
+		/*
+		 * If CONFIG_OF is set, then assume this is a reasonably
+		 * modern system that should pass boot parameters
+		 */
+		early_print("Warning: Neither atags nor dtb found\n");
+#endif
 		tags = (struct tag *)&init_tags;
+	}
 
 	if (mdesc->fixup)
 		mdesc->fixup(mdesc, tags, &from, &meminfo);
@@ -862,14 +866,34 @@ void __init setup_arch(char **cmdline_p)
 		parse_tags(tags);
 	}
 
+	/* parse_early_param needs a boot_command_line */
+	strlcpy(boot_command_line, from, COMMAND_LINE_SIZE);
+
+	return mdesc;
+}
+
+
+void __init setup_arch(char **cmdline_p)
+{
+	struct machine_desc *mdesc;
+
+	unwind_init();
+
+	setup_processor();
+	mdesc = setup_machine_fdt(__atags_pointer);
+	if (!mdesc)
+		mdesc = setup_machine_tags(machine_arch_type);
+	machine_desc = mdesc;
+	machine_name = mdesc->name;
+
+	if (mdesc->soft_reboot)
+		reboot_setup("s");
+
 	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;
 
-	/* parse_early_param needs a boot_command_line */
-	strlcpy(boot_command_line, from, COMMAND_LINE_SIZE);
-
 	/* populate cmd_line too for later use, preserving boot_command_line */
 	strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = cmd_line;
@@ -881,6 +905,8 @@ void __init setup_arch(char **cmdline_p)
 	paging_init(mdesc);
 	request_standard_resources(mdesc);
 
+	unflatten_device_tree();
+
 #ifdef CONFIG_SMP
 	if (is_smp())
 		smp_init_cpus();
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index d439a8f4c078..e7f92a4321f3 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -105,6 +105,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	 */
 	secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
 	secondary_data.pgdir = virt_to_phys(pgd);
+	secondary_data.swapper_pg_dir = virt_to_phys(swapper_pg_dir);
 	__cpuc_flush_dcache_area(&secondary_data, sizeof(secondary_data));
 	outer_clean_range(__pa(&secondary_data), __pa(&secondary_data + 1));
 
@@ -317,9 +318,13 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	smp_store_cpu_info(cpu);
 
 	/*
-	 * OK, now it's safe to let the boot CPU continue
+	 * OK, now it's safe to let the boot CPU continue.  Wait for
+	 * the CPU migration code to notice that the CPU is online
+	 * before we continue.
 	 */
 	set_cpu_online(cpu, true);
+	while (!cpu_active(cpu))
+		cpu_relax();
 
 	/*
 	 * OK, it's off to the idle thread for us
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index d52eec268b47..6807cb1e76dd 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -139,7 +139,7 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 	fs = get_fs();
 	set_fs(KERNEL_DS);
 
-	for (i = -4; i < 1; i++) {
+	for (i = -4; i < 1 + !!thumb; i++) {
 		unsigned int val, bad;
 
 		if (thumb)
@@ -563,7 +563,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 		if (!pmd_present(*pmd))
 			goto bad_access;
 		pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
-		if (!pte_present(*pte) || !pte_dirty(*pte)) {
+		if (!pte_present(*pte) || !pte_write(*pte) || !pte_dirty(*pte)) {
 			pte_unmap_unlock(pte, ptl);
 			goto bad_access;
 		}
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index 6dc06487f3c3..c562f649734c 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -35,7 +35,7 @@ Boston, MA 02111-1307, USA.  */
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
-
+#include <asm/unwind.h>
 
 .macro ARM_DIV_BODY dividend, divisor, result, curbit
 
@@ -207,6 +207,7 @@ Boston, MA 02111-1307, USA.  */
 
 ENTRY(__udivsi3)
 ENTRY(__aeabi_uidiv)
+UNWIND(.fnstart)
 
 	subs	r2, r1, #1
 	moveq	pc, lr
@@ -230,10 +231,12 @@ ENTRY(__aeabi_uidiv)
 	mov	r0, r0, lsr r2
 	mov	pc, lr
 
+UNWIND(.fnend)
 ENDPROC(__udivsi3)
 ENDPROC(__aeabi_uidiv)
 
 ENTRY(__umodsi3)
+UNWIND(.fnstart)
 
 	subs	r2, r1, #1			@ compare divisor with 1
 	bcc	Ldiv0
@@ -247,10 +250,12 @@ ENTRY(__umodsi3)
 
 	mov	pc, lr
 
+UNWIND(.fnend)
 ENDPROC(__umodsi3)
 
 ENTRY(__divsi3)
 ENTRY(__aeabi_idiv)
+UNWIND(.fnstart)
 
 	cmp	r1, #0
 	eor	ip, r0, r1			@ save the sign of the result.
@@ -287,10 +292,12 @@ ENTRY(__aeabi_idiv)
 	rsbmi	r0, r0, #0
 	mov	pc, lr
 
+UNWIND(.fnend)
 ENDPROC(__divsi3)
 ENDPROC(__aeabi_idiv)
 
 ENTRY(__modsi3)
+UNWIND(.fnstart)
 
 	cmp	r1, #0
 	beq	Ldiv0
@@ -310,11 +317,14 @@ ENTRY(__modsi3)
 	rsbmi	r0, r0, #0
 	mov	pc, lr
 
+UNWIND(.fnend)
 ENDPROC(__modsi3)
 
 #ifdef CONFIG_AEABI
 
 ENTRY(__aeabi_uidivmod)
+UNWIND(.fnstart)
+UNWIND(.save {r0, r1, ip, lr}	)
 
 	stmfd	sp!, {r0, r1, ip, lr}
 	bl	__aeabi_uidiv
@@ -323,10 +333,12 @@ ENTRY(__aeabi_uidivmod)
 	sub	r1, r1, r3
 	mov	pc, lr
 
+UNWIND(.fnend)
 ENDPROC(__aeabi_uidivmod)
 
 ENTRY(__aeabi_idivmod)
-
+UNWIND(.fnstart)
+UNWIND(.save {r0, r1, ip, lr}	)
 	stmfd	sp!, {r0, r1, ip, lr}
 	bl	__aeabi_idiv
 	ldmfd	sp!, {r1, r2, ip, lr}
@@ -334,15 +346,18 @@ ENTRY(__aeabi_idivmod)
 	sub	r1, r1, r3
 	mov	pc, lr
 
+UNWIND(.fnend)
 ENDPROC(__aeabi_idivmod)
 
 #endif
 
 Ldiv0:
-
+UNWIND(.fnstart)
+UNWIND(.pad #4)
+UNWIND(.save {lr})
 	str	lr, [sp, #-8]!
 	bl	__div0
 	mov	r0, #0			@ About as wrong as it could be.
 	ldr	pc, [sp], #8
-
-
+UNWIND(.fnend)
+ENDPROC(Ldiv0)
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 2d299bf5d72f..22484670e7ba 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -3,9 +3,6 @@ if ARCH_AT91
 config HAVE_AT91_DATAFLASH_CARD
 	bool
 
-config HAVE_NAND_ATMEL_BUSWIDTH_16
-	bool
-
 config HAVE_AT91_USART3
 	bool
 
@@ -85,11 +82,6 @@ config ARCH_AT91CAP9
 	select HAVE_FB_ATMEL
 	select HAVE_NET_MACB
 
-config ARCH_AT572D940HF
-	bool "AT572D940HF"
-	select CPU_ARM926T
-	select GENERIC_CLOCKEVENTS
-
 config ARCH_AT91X40
 	bool "AT91x40"
 	select ARCH_USES_GETTIMEOFFSET
@@ -209,7 +201,6 @@ comment "AT91SAM9260 / AT91SAM9XE Board Type"
 config MACH_AT91SAM9260EK
 	bool "Atmel AT91SAM9260-EK / AT91SAM9XE Evaluation Kit"
 	select HAVE_AT91_DATAFLASH_CARD
-	select HAVE_NAND_ATMEL_BUSWIDTH_16
 	help
 	  Select this if you are using Atmel's AT91SAM9260-EK or AT91SAM9XE Evaluation Kit
 	  <http://www.atmel.com/dyn/products/tools_card.asp?tool_id=3933>
@@ -270,7 +261,6 @@ comment "AT91SAM9261 Board Type"
 config MACH_AT91SAM9261EK
 	bool "Atmel AT91SAM9261-EK Evaluation Kit"
 	select HAVE_AT91_DATAFLASH_CARD
-	select HAVE_NAND_ATMEL_BUSWIDTH_16
 	help
 	  Select this if you are using Atmel's AT91SAM9261-EK Evaluation Kit.
 	  <http://www.atmel.com/dyn/products/tools_card.asp?tool_id=3820>
@@ -286,7 +276,6 @@ comment "AT91SAM9G10 Board Type"
 config MACH_AT91SAM9G10EK
 	bool "Atmel AT91SAM9G10-EK Evaluation Kit"
 	select HAVE_AT91_DATAFLASH_CARD
-	select HAVE_NAND_ATMEL_BUSWIDTH_16
 	help
 	  Select this if you are using Atmel's AT91SAM9G10-EK Evaluation Kit.
 	  <http://www.atmel.com/dyn/products/tools_card.asp?tool_id=4588>
@@ -302,7 +291,6 @@ comment "AT91SAM9263 Board Type"
 config MACH_AT91SAM9263EK
 	bool "Atmel AT91SAM9263-EK Evaluation Kit"
 	select HAVE_AT91_DATAFLASH_CARD
-	select HAVE_NAND_ATMEL_BUSWIDTH_16
 	help
 	  Select this if you are using Atmel's AT91SAM9263-EK Evaluation Kit.
 	  <http://www.atmel.com/dyn/products/tools_card.asp?tool_id=4057>
@@ -343,7 +331,6 @@ comment "AT91SAM9G20 Board Type"
 config MACH_AT91SAM9G20EK
 	bool "Atmel AT91SAM9G20-EK Evaluation Kit"
 	select HAVE_AT91_DATAFLASH_CARD
-	select HAVE_NAND_ATMEL_BUSWIDTH_16
 	help
 	  Select this if you are using Atmel's AT91SAM9G20-EK Evaluation Kit
 	  that embeds only one SD/MMC slot.
@@ -351,7 +338,6 @@ config MACH_AT91SAM9G20EK
 config MACH_AT91SAM9G20EK_2MMC
 	depends on MACH_AT91SAM9G20EK
 	bool "Atmel AT91SAM9G20-EK Evaluation Kit with 2 SD/MMC Slots"
-	select HAVE_NAND_ATMEL_BUSWIDTH_16
 	help
 	  Select this if you are using an Atmel AT91SAM9G20-EK Evaluation Kit
 	  with 2 SD/MMC Slots. This is the case for AT91SAM9G20-EK rev. C and
@@ -416,7 +402,6 @@ comment "AT91SAM9G45 Board Type"
 
 config MACH_AT91SAM9M10G45EK
 	bool "Atmel AT91SAM9M10G45-EK Evaluation Kits"
-	select HAVE_NAND_ATMEL_BUSWIDTH_16
 	help
 	  Select this if you are using Atmel's AT91SAM9G45-EKES Evaluation Kit.
 	  "ES" at the end of the name means that this board is an
@@ -433,7 +418,6 @@ comment "AT91CAP9 Board Type"
 config MACH_AT91CAP9ADK
 	bool "Atmel AT91CAP9A-DK Evaluation Kit"
 	select HAVE_AT91_DATAFLASH_CARD
-	select HAVE_NAND_ATMEL_BUSWIDTH_16
 	help
 	  Select this if you are using Atmel's AT91CAP9A-DK Evaluation Kit.
 	  <http://www.atmel.com/dyn/products/tools_card.asp?tool_id=4138>
@@ -442,23 +426,6 @@ endif
 
 # ----------------------------------------------------------
 
-if ARCH_AT572D940HF
-
-comment "AT572D940HF Board Type"
-
-config MACH_AT572D940HFEB
-	bool "AT572D940HF-EK"
-	depends on ARCH_AT572D940HF
-	select HAVE_AT91_DATAFLASH_CARD
-	select HAVE_NAND_ATMEL_BUSWIDTH_16
-	help
-	  Select this if you are using Atmel's AT572D940HF-EK evaluation kit.
-	  <http://www.atmel.com/products/diopsis/default.asp>
-
-endif
-
-# ----------------------------------------------------------
-
 if ARCH_AT91X40
 
 comment "AT91X40 Board Type"
@@ -483,13 +450,6 @@ config MTD_AT91_DATAFLASH_CARD
 	help
 	  Enable support for the DataFlash card.
 
-config MTD_NAND_ATMEL_BUSWIDTH_16
-	bool "Enable 16-bit data bus interface to NAND flash"
-	depends on HAVE_NAND_ATMEL_BUSWIDTH_16
-	help
-	  On AT91SAM926x boards both types of NAND flash can be present
-	  (8 and 16 bit data bus width).
-
 # ----------------------------------------------------------
 
 comment "AT91 Feature Selections"
diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile
index a83835e0c185..96966231920c 100644
--- a/arch/arm/mach-at91/Makefile
+++ b/arch/arm/mach-at91/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_ARCH_AT91SAM9RL)	+= at91sam9rl.o at91sam926x_time.o at91sam9rl_devi
 obj-$(CONFIG_ARCH_AT91SAM9G20)	+= at91sam9260.o at91sam926x_time.o at91sam9260_devices.o sam9_smc.o at91sam9_alt_reset.o
 obj-$(CONFIG_ARCH_AT91SAM9G45)	+= at91sam9g45.o at91sam926x_time.o at91sam9g45_devices.o sam9_smc.o
 obj-$(CONFIG_ARCH_AT91CAP9)	+= at91cap9.o at91sam926x_time.o at91cap9_devices.o sam9_smc.o
-obj-$(CONFIG_ARCH_AT572D940HF)  += at572d940hf.o at91sam926x_time.o at572d940hf_devices.o sam9_smc.o
 obj-$(CONFIG_ARCH_AT91X40)	+= at91x40.o at91x40_time.o
 
 # AT91RM9200 board-specific support
@@ -78,9 +77,6 @@ obj-$(CONFIG_MACH_AT91SAM9M10G45EK) += board-sam9m10g45ek.o
 # AT91CAP9 board-specific support
 obj-$(CONFIG_MACH_AT91CAP9ADK)	+= board-cap9adk.o
 
-# AT572D940HF board-specific support
-obj-$(CONFIG_MACH_AT572D940HFEB) += board-at572d940hf_ek.o
-
 # AT91X40 board-specific support
 obj-$(CONFIG_MACH_AT91EB01)	+= board-eb01.o
 
diff --git a/arch/arm/mach-at91/at572d940hf.c b/arch/arm/mach-at91/at572d940hf.c
deleted file mode 100644
index a6b9c68c003a..000000000000
--- a/arch/arm/mach-at91/at572d940hf.c
+++ /dev/null
@@ -1,377 +0,0 @@
-/*
- * arch/arm/mach-at91/at572d940hf.c
- *
- * Antonio R. Costa <costa.antonior@gmail.com>
- * Copyright (C) 2008 Atmel
- *
- * Copyright (C) 2005 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
- *
- */
-
-#include <linux/module.h>
-
-#include <asm/mach/irq.h>
-#include <asm/mach/arch.h>
-#include <asm/mach/map.h>
-#include <mach/at572d940hf.h>
-#include <mach/at91_pmc.h>
-#include <mach/at91_rstc.h>
-
-#include "generic.h"
-#include "clock.h"
-
-static struct map_desc at572d940hf_io_desc[] __initdata = {
-	{
-		.virtual	= AT91_VA_BASE_SYS,
-		.pfn		= __phys_to_pfn(AT91_BASE_SYS),
-		.length		= SZ_16K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= AT91_IO_VIRT_BASE - AT572D940HF_SRAM_SIZE,
-		.pfn		= __phys_to_pfn(AT572D940HF_SRAM_BASE),
-		.length		= AT572D940HF_SRAM_SIZE,
-		.type		= MT_DEVICE,
-	},
-};
-
-/* --------------------------------------------------------------------
- *  Clocks
- * -------------------------------------------------------------------- */
-
-/*
- * The peripheral clocks.
- */
-static struct clk pioA_clk = {
-	.name		= "pioA_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_PIOA,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk pioB_clk = {
-	.name		= "pioB_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_PIOB,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk pioC_clk = {
-	.name		= "pioC_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_PIOC,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk macb_clk = {
-	.name		= "macb_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_EMAC,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk usart0_clk = {
-	.name		= "usart0_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_US0,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk usart1_clk = {
-	.name		= "usart1_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_US1,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk usart2_clk = {
-	.name		= "usart2_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_US2,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk mmc_clk = {
-	.name		= "mci_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_MCI,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk udc_clk = {
-	.name		= "udc_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_UDP,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk twi0_clk = {
-	.name		= "twi0_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_TWI0,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk spi0_clk = {
-	.name		= "spi0_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_SPI0,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk spi1_clk = {
-	.name		= "spi1_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_SPI1,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk ssc0_clk = {
-	.name		= "ssc0_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_SSC0,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk ssc1_clk = {
-	.name		= "ssc1_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_SSC1,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk ssc2_clk = {
-	.name		= "ssc2_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_SSC2,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk tc0_clk = {
-	.name		= "tc0_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_TC0,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk tc1_clk = {
-	.name		= "tc1_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_TC1,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk tc2_clk = {
-	.name		= "tc2_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_TC2,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk ohci_clk = {
-	.name		= "ohci_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_UHP,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk ssc3_clk = {
-	.name		= "ssc3_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_SSC3,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk twi1_clk = {
-	.name		= "twi1_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_TWI1,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk can0_clk = {
-	.name		= "can0_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_CAN0,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk can1_clk = {
-	.name		= "can1_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_CAN1,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-static struct clk mAgicV_clk = {
-	.name		= "mAgicV_clk",
-	.pmc_mask	= 1 << AT572D940HF_ID_MSIRQ0,
-	.type		= CLK_TYPE_PERIPHERAL,
-};
-
-
-static struct clk *periph_clocks[] __initdata = {
-	&pioA_clk,
-	&pioB_clk,
-	&pioC_clk,
-	&macb_clk,
-	&usart0_clk,
-	&usart1_clk,
-	&usart2_clk,
-	&mmc_clk,
-	&udc_clk,
-	&twi0_clk,
-	&spi0_clk,
-	&spi1_clk,
-	&ssc0_clk,
-	&ssc1_clk,
-	&ssc2_clk,
-	&tc0_clk,
-	&tc1_clk,
-	&tc2_clk,
-	&ohci_clk,
-	&ssc3_clk,
-	&twi1_clk,
-	&can0_clk,
-	&can1_clk,
-	&mAgicV_clk,
-	/* irq0 .. irq2 */
-};
-
-/*
- * The five programmable clocks.
- * You must configure pin multiplexing to bring these signals out.
- */
-static struct clk pck0 = {
-	.name		= "pck0",
-	.pmc_mask	= AT91_PMC_PCK0,
-	.type		= CLK_TYPE_PROGRAMMABLE,
-	.id		= 0,
-};
-static struct clk pck1 = {
-	.name		= "pck1",
-	.pmc_mask	= AT91_PMC_PCK1,
-	.type		= CLK_TYPE_PROGRAMMABLE,
-	.id		= 1,
-};
-static struct clk pck2 = {
-	.name		= "pck2",
-	.pmc_mask	= AT91_PMC_PCK2,
-	.type		= CLK_TYPE_PROGRAMMABLE,
-	.id		= 2,
-};
-static struct clk pck3 = {
-	.name		= "pck3",
-	.pmc_mask	= AT91_PMC_PCK3,
-	.type		= CLK_TYPE_PROGRAMMABLE,
-	.id		= 3,
-};
-
-static struct clk mAgicV_mem_clk = {
-	.name		= "mAgicV_mem_clk",
-	.pmc_mask	= AT91_PMC_PCK4,
-	.type		= CLK_TYPE_PROGRAMMABLE,
-	.id		= 4,
-};
-
-/* HClocks */
-static struct clk hck0 = {
-	.name		= "hck0",
-	.pmc_mask	= AT91_PMC_HCK0,
-	.type		= CLK_TYPE_SYSTEM,
-	.id		= 0,
-};
-static struct clk hck1 = {
-	.name		= "hck1",
-	.pmc_mask	= AT91_PMC_HCK1,
-	.type		= CLK_TYPE_SYSTEM,
-	.id		= 1,
-};
-
-static void __init at572d940hf_register_clocks(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(periph_clocks); i++)
-		clk_register(periph_clocks[i]);
-
-	clk_register(&pck0);
-	clk_register(&pck1);
-	clk_register(&pck2);
-	clk_register(&pck3);
-	clk_register(&mAgicV_mem_clk);
-
-	clk_register(&hck0);
-	clk_register(&hck1);
-}
-
-/* --------------------------------------------------------------------
- *  GPIO
- * -------------------------------------------------------------------- */
-
-static struct at91_gpio_bank at572d940hf_gpio[] = {
-	{
-		.id		= AT572D940HF_ID_PIOA,
-		.offset		= AT91_PIOA,
-		.clock		= &pioA_clk,
-	}, {
-		.id		= AT572D940HF_ID_PIOB,
-		.offset		= AT91_PIOB,
-		.clock		= &pioB_clk,
-	}, {
-		.id		= AT572D940HF_ID_PIOC,
-		.offset		= AT91_PIOC,
-		.clock		= &pioC_clk,
-	}
-};
-
-static void at572d940hf_reset(void)
-{
-	at91_sys_write(AT91_RSTC_CR, AT91_RSTC_KEY | AT91_RSTC_PROCRST | AT91_RSTC_PERRST);
-}
-
-
-/* --------------------------------------------------------------------
- *  AT572D940HF processor initialization
- * -------------------------------------------------------------------- */
-
-void __init at572d940hf_initialize(unsigned long main_clock)
-{
-	/* Map peripherals */
-	iotable_init(at572d940hf_io_desc, ARRAY_SIZE(at572d940hf_io_desc));
-
-	at91_arch_reset = at572d940hf_reset;
-	at91_extern_irq = (1 << AT572D940HF_ID_IRQ0) | (1 << AT572D940HF_ID_IRQ1)
-			| (1 << AT572D940HF_ID_IRQ2);
-
-	/* Init clock subsystem */
-	at91_clock_init(main_clock);
-
-	/* Register the processor-specific clocks */
-	at572d940hf_register_clocks();
-
-	/* Register GPIO subsystem */
-	at91_gpio_init(at572d940hf_gpio, 3);
-}
-
-/* --------------------------------------------------------------------
- *  Interrupt initialization
- * -------------------------------------------------------------------- */
-
-/*
- * The default interrupt priority levels (0 = lowest, 7 = highest).
- */
-static unsigned int at572d940hf_default_irq_priority[NR_AIC_IRQS] __initdata = {
-	7,	/* Advanced Interrupt Controller */
-	7,	/* System Peripherals */
-	0,	/* Parallel IO Controller A */
-	0,	/* Parallel IO Controller B */
-	0,	/* Parallel IO Controller C */
-	3,	/* Ethernet */
-	6,	/* USART 0 */
-	6,	/* USART 1 */
-	6,	/* USART 2 */
-	0,	/* Multimedia Card Interface */
-	4,	/* USB Device Port */
-	0,	/* Two-Wire Interface 0 */
-	6,	/* Serial Peripheral Interface 0 */
-	6,	/* Serial Peripheral Interface 1 */
-	5,	/* Serial Synchronous Controller 0 */
-	5,	/* Serial Synchronous Controller 1 */
-	5,	/* Serial Synchronous Controller 2 */
-	0,	/* Timer Counter 0 */
-	0,	/* Timer Counter 1 */
-	0,	/* Timer Counter 2 */
-	3,	/* USB Host port */
-	3,	/* Serial Synchronous Controller 3 */
-	0,	/* Two-Wire Interface 1 */
-	0,	/* CAN Controller 0 */
-	0,	/* CAN Controller 1 */
-	0,	/* mAgicV HALT line */
-	0,	/* mAgicV SIRQ0 line */
-	0,	/* mAgicV exception line */
-	0,	/* mAgicV end of DMA line */
-	0,	/* Advanced Interrupt Controller */
-	0,	/* Advanced Interrupt Controller */
-	0,	/* Advanced Interrupt Controller */
-};
-
-void __init at572d940hf_init_interrupts(unsigned int priority[NR_AIC_IRQS])
-{
-	if (!priority)
-		priority = at572d940hf_default_irq_priority;
-
-	/* Initialize the AIC interrupt controller */
-	at91_aic_init(priority);
-
-	/* Enable GPIO interrupts */
-	at91_gpio_irq_setup();
-}
-
diff --git a/arch/arm/mach-at91/at572d940hf_devices.c b/arch/arm/mach-at91/at572d940hf_devices.c
deleted file mode 100644
index 0fc20a240782..000000000000
--- a/arch/arm/mach-at91/at572d940hf_devices.c
+++ /dev/null
@@ -1,970 +0,0 @@
-/*
- * arch/arm/mach-at91/at572d940hf_devices.c
- *
- * Copyright (C) 2008 Atmel Antonio R. Costa <costa.antonior@gmail.com>
- * Copyright (C) 2005 Thibaut VARENE <varenet@parisc-linux.org>
- * Copyright (C) 2005 David Brownell
- *
- * 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 <asm/mach/arch.h>
-#include <asm/mach/map.h>
-
-#include <linux/dma-mapping.h>
-#include <linux/platform_device.h>
-
-#include <mach/board.h>
-#include <mach/gpio.h>
-#include <mach/at572d940hf.h>
-#include <mach/at572d940hf_matrix.h>
-#include <mach/at91sam9_smc.h>
-
-#include "generic.h"
-#include "sam9_smc.h"
-
-
-/* --------------------------------------------------------------------
- *  USB Host
- * -------------------------------------------------------------------- */
-
-#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
-static u64 ohci_dmamask = DMA_BIT_MASK(32);
-static struct at91_usbh_data usbh_data;
-
-static struct resource usbh_resources[] = {
-	[0] = {
-		.start	= AT572D940HF_UHP_BASE,
-		.end	= AT572D940HF_UHP_BASE + SZ_1M - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AT572D940HF_ID_UHP,
-		.end	= AT572D940HF_ID_UHP,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device at572d940hf_usbh_device = {
-	.name		= "at91_ohci",
-	.id		= -1,
-	.dev		= {
-				.dma_mask		= &ohci_dmamask,
-				.coherent_dma_mask	= DMA_BIT_MASK(32),
-				.platform_data		= &usbh_data,
-	},
-	.resource	= usbh_resources,
-	.num_resources	= ARRAY_SIZE(usbh_resources),
-};
-
-void __init at91_add_device_usbh(struct at91_usbh_data *data)
-{
-	if (!data)
-		return;
-
-	usbh_data = *data;
-	platform_device_register(&at572d940hf_usbh_device);
-
-}
-#else
-void __init at91_add_device_usbh(struct at91_usbh_data *data) {}
-#endif
-
-
-/* --------------------------------------------------------------------
- *  USB Device (Gadget)
- * -------------------------------------------------------------------- */
-
-#ifdef CONFIG_USB_GADGET_AT91
-static struct at91_udc_data udc_data;
-
-static struct resource udc_resources[] = {
-	[0] = {
-		.start	= AT572D940HF_BASE_UDP,
-		.end	= AT572D940HF_BASE_UDP + SZ_16K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AT572D940HF_ID_UDP,
-		.end	= AT572D940HF_ID_UDP,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device at572d940hf_udc_device = {
-	.name		= "at91_udc",
-	.id		= -1,
-	.dev		= {
-				.platform_data		= &udc_data,
-	},
-	.resource	= udc_resources,
-	.num_resources	= ARRAY_SIZE(udc_resources),
-};
-
-void __init at91_add_device_udc(struct at91_udc_data *data)
-{
-	if (!data)
-		return;
-
-	if (data->vbus_pin) {
-		at91_set_gpio_input(data->vbus_pin, 0);
-		at91_set_deglitch(data->vbus_pin, 1);
-	}
-
-	/* Pullup pin is handled internally */
-
-	udc_data = *data;
-	platform_device_register(&at572d940hf_udc_device);
-}
-#else
-void __init at91_add_device_udc(struct at91_udc_data *data) {}
-#endif
-
-
-/* --------------------------------------------------------------------
- *  Ethernet
- * -------------------------------------------------------------------- */
-
-#if defined(CONFIG_MACB) || defined(CONFIG_MACB_MODULE)
-static u64 eth_dmamask = DMA_BIT_MASK(32);
-static struct at91_eth_data eth_data;
-
-static struct resource eth_resources[] = {
-	[0] = {
-		.start	= AT572D940HF_BASE_EMAC,
-		.end	= AT572D940HF_BASE_EMAC + SZ_16K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AT572D940HF_ID_EMAC,
-		.end	= AT572D940HF_ID_EMAC,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device at572d940hf_eth_device = {
-	.name		= "macb",
-	.id		= -1,
-	.dev		= {
-			.dma_mask		= &eth_dmamask,
-			.coherent_dma_mask	= DMA_BIT_MASK(32),
-			.platform_data		= &eth_data,
-	},
-	.resource	= eth_resources,
-	.num_resources	= ARRAY_SIZE(eth_resources),
-};
-
-void __init at91_add_device_eth(struct at91_eth_data *data)
-{
-	if (!data)
-		return;
-
-	if (data->phy_irq_pin) {
-		at91_set_gpio_input(data->phy_irq_pin, 0);
-		at91_set_deglitch(data->phy_irq_pin, 1);
-	}
-
-	/* Only RMII is supported */
-	data->is_rmii = 1;
-
-	/* Pins used for RMII */
-	at91_set_A_periph(AT91_PIN_PA16, 0);	/* ETXCK_EREFCK */
-	at91_set_A_periph(AT91_PIN_PA17, 0);	/* ERXDV */
-	at91_set_A_periph(AT91_PIN_PA18, 0);	/* ERX0 */
-	at91_set_A_periph(AT91_PIN_PA19, 0);	/* ERX1 */
-	at91_set_A_periph(AT91_PIN_PA20, 0);	/* ERXER */
-	at91_set_A_periph(AT91_PIN_PA23, 0);	/* ETXEN */
-	at91_set_A_periph(AT91_PIN_PA21, 0);	/* ETX0 */
-	at91_set_A_periph(AT91_PIN_PA22, 0);	/* ETX1 */
-	at91_set_A_periph(AT91_PIN_PA13, 0);	/* EMDIO */
-	at91_set_A_periph(AT91_PIN_PA14, 0);	/* EMDC */
-
-	eth_data = *data;
-	platform_device_register(&at572d940hf_eth_device);
-}
-#else
-void __init at91_add_device_eth(struct at91_eth_data *data) {}
-#endif
-
-
-/* --------------------------------------------------------------------
- *  MMC / SD
- * -------------------------------------------------------------------- */
-
-#if defined(CONFIG_MMC_AT91) || defined(CONFIG_MMC_AT91_MODULE)
-static u64 mmc_dmamask = DMA_BIT_MASK(32);
-static struct at91_mmc_data mmc_data;
-
-static struct resource mmc_resources[] = {
-	[0] = {
-		.start	= AT572D940HF_BASE_MCI,
-		.end	= AT572D940HF_BASE_MCI + SZ_16K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AT572D940HF_ID_MCI,
-		.end	= AT572D940HF_ID_MCI,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device at572d940hf_mmc_device = {
-	.name		= "at91_mci",
-	.id		= -1,
-	.dev		= {
-				.dma_mask		= &mmc_dmamask,
-				.coherent_dma_mask	= DMA_BIT_MASK(32),
-				.platform_data		= &mmc_data,
-	},
-	.resource	= mmc_resources,
-	.num_resources	= ARRAY_SIZE(mmc_resources),
-};
-
-void __init at91_add_device_mmc(short mmc_id, struct at91_mmc_data *data)
-{
-	if (!data)
-		return;
-
-	/* input/irq */
-	if (data->det_pin) {
-		at91_set_gpio_input(data->det_pin, 1);
-		at91_set_deglitch(data->det_pin, 1);
-	}
-	if (data->wp_pin)
-		at91_set_gpio_input(data->wp_pin, 1);
-	if (data->vcc_pin)
-		at91_set_gpio_output(data->vcc_pin, 0);
-
-	/* CLK */
-	at91_set_A_periph(AT91_PIN_PC22, 0);
-
-	/* CMD */
-	at91_set_A_periph(AT91_PIN_PC23, 1);
-
-	/* DAT0, maybe DAT1..DAT3 */
-	at91_set_A_periph(AT91_PIN_PC24, 1);
-	if (data->wire4) {
-		at91_set_A_periph(AT91_PIN_PC25, 1);
-		at91_set_A_periph(AT91_PIN_PC26, 1);
-		at91_set_A_periph(AT91_PIN_PC27, 1);
-	}
-
-	mmc_data = *data;
-	platform_device_register(&at572d940hf_mmc_device);
-}
-#else
-void __init at91_add_device_mmc(short mmc_id, struct at91_mmc_data *data) {}
-#endif
-
-
-/* --------------------------------------------------------------------
- *  NAND / SmartMedia
- * -------------------------------------------------------------------- */
-
-#if defined(CONFIG_MTD_NAND_ATMEL) || defined(CONFIG_MTD_NAND_ATMEL_MODULE)
-static struct atmel_nand_data nand_data;
-
-#define NAND_BASE	AT91_CHIPSELECT_3
-
-static struct resource nand_resources[] = {
-	{
-		.start	= NAND_BASE,
-		.end	= NAND_BASE + SZ_256M - 1,
-		.flags	= IORESOURCE_MEM,
-	}
-};
-
-static struct platform_device at572d940hf_nand_device = {
-	.name		= "atmel_nand",
-	.id		= -1,
-	.dev		= {
-				.platform_data	= &nand_data,
-	},
-	.resource	= nand_resources,
-	.num_resources	= ARRAY_SIZE(nand_resources),
-};
-
-void __init at91_add_device_nand(struct atmel_nand_data *data)
-{
-	unsigned long csa;
-
-	if (!data)
-		return;
-
-	csa = at91_sys_read(AT91_MATRIX_EBICSA);
-	at91_sys_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_CS3A_SMC_SMARTMEDIA);
-
-	/* enable pin */
-	if (data->enable_pin)
-		at91_set_gpio_output(data->enable_pin, 1);
-
-	/* ready/busy pin */
-	if (data->rdy_pin)
-		at91_set_gpio_input(data->rdy_pin, 1);
-
-	/* card detect pin */
-	if (data->det_pin)
-		at91_set_gpio_input(data->det_pin, 1);
-
-	at91_set_A_periph(AT91_PIN_PB28, 0);		/* A[22] */
-	at91_set_B_periph(AT91_PIN_PA28, 0);		/* NANDOE */
-	at91_set_B_periph(AT91_PIN_PA29, 0);		/* NANDWE */
-
-	nand_data = *data;
-	platform_device_register(&at572d940hf_nand_device);
-}
-
-#else
-void __init at91_add_device_nand(struct atmel_nand_data *data) {}
-#endif
-
-
-/* --------------------------------------------------------------------
- *  TWI (i2c)
- * -------------------------------------------------------------------- */
-
-/*
- * Prefer the GPIO code since the TWI controller isn't robust
- * (gets overruns and underruns under load) and can only issue
- * repeated STARTs in one scenario (the driver doesn't yet handle them).
- */
-
-#if defined(CONFIG_I2C_GPIO) || defined(CONFIG_I2C_GPIO_MODULE)
-
-static struct i2c_gpio_platform_data pdata = {
-	.sda_pin		= AT91_PIN_PC7,
-	.sda_is_open_drain	= 1,
-	.scl_pin		= AT91_PIN_PC8,
-	.scl_is_open_drain	= 1,
-	.udelay			= 2,		/* ~100 kHz */
-};
-
-static struct platform_device at572d940hf_twi_device {
-	.name			= "i2c-gpio",
-	.id			= -1,
-	.dev.platform_data	= &pdata,
-};
-
-void __init at91_add_device_i2c(struct i2c_board_info *devices, int nr_devices)
-{
-	at91_set_GPIO_periph(AT91_PIN_PC7, 1);		/* TWD (SDA) */
-	at91_set_multi_drive(AT91_PIN_PC7, 1);
-
-	at91_set_GPIO_periph(AT91_PIN_PA8, 1);		/* TWCK (SCL) */
-	at91_set_multi_drive(AT91_PIN_PC8, 1);
-
-	i2c_register_board_info(0, devices, nr_devices);
-	platform_device_register(&at572d940hf_twi_device);
-}
-
-#elif defined(CONFIG_I2C_AT91) || defined(CONFIG_I2C_AT91_MODULE)
-
-static struct resource twi0_resources[] = {
-	[0] = {
-		.start	= AT572D940HF_BASE_TWI0,
-		.end	= AT572D940HF_BASE_TWI0 + SZ_16K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AT572D940HF_ID_TWI0,
-		.end	= AT572D940HF_ID_TWI0,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device at572d940hf_twi0_device = {
-	.name		= "at91_i2c",
-	.id		= 0,
-	.resource	= twi0_resources,
-	.num_resources	= ARRAY_SIZE(twi0_resources),
-};
-
-static struct resource twi1_resources[] = {
-	[0] = {
-		.start	= AT572D940HF_BASE_TWI1,
-		.end	= AT572D940HF_BASE_TWI1 + SZ_16K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AT572D940HF_ID_TWI1,
-		.end	= AT572D940HF_ID_TWI1,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device at572d940hf_twi1_device = {
-	.name		= "at91_i2c",
-	.id		= 1,
-	.resource	= twi1_resources,
-	.num_resources	= ARRAY_SIZE(twi1_resources),
-};
-
-void __init at91_add_device_i2c(struct i2c_board_info *devices, int nr_devices)
-{
-	/* pins used for TWI0 interface */
-	at91_set_A_periph(AT91_PIN_PC7, 0);		/* TWD */
-	at91_set_multi_drive(AT91_PIN_PC7, 1);
-
-	at91_set_A_periph(AT91_PIN_PC8, 0);		/* TWCK */
-	at91_set_multi_drive(AT91_PIN_PC8, 1);
-
-	/* pins used for TWI1 interface */
-	at91_set_A_periph(AT91_PIN_PC20, 0);		/* TWD */
-	at91_set_multi_drive(AT91_PIN_PC20, 1);
-
-	at91_set_A_periph(AT91_PIN_PC21, 0);		/* TWCK */
-	at91_set_multi_drive(AT91_PIN_PC21, 1);
-
-	i2c_register_board_info(0, devices, nr_devices);
-	platform_device_register(&at572d940hf_twi0_device);
-	platform_device_register(&at572d940hf_twi1_device);
-}
-#else
-void __init at91_add_device_i2c(struct i2c_board_info *devices, int nr_devices) {}
-#endif
-
-
-/* --------------------------------------------------------------------
- *  SPI
- * -------------------------------------------------------------------- */
-
-#if defined(CONFIG_SPI_ATMEL) || defined(CONFIG_SPI_ATMEL_MODULE)
-static u64 spi_dmamask = DMA_BIT_MASK(32);
-
-static struct resource spi0_resources[] = {
-	[0] = {
-		.start	= AT572D940HF_BASE_SPI0,
-		.end	= AT572D940HF_BASE_SPI0 + SZ_16K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AT572D940HF_ID_SPI0,
-		.end	= AT572D940HF_ID_SPI0,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device at572d940hf_spi0_device = {
-	.name		= "atmel_spi",
-	.id		= 0,
-	.dev		= {
-				.dma_mask		= &spi_dmamask,
-				.coherent_dma_mask	= DMA_BIT_MASK(32),
-	},
-	.resource	= spi0_resources,
-	.num_resources	= ARRAY_SIZE(spi0_resources),
-};
-
-static const unsigned spi0_standard_cs[4] = { AT91_PIN_PA3, AT91_PIN_PA4, AT91_PIN_PA5, AT91_PIN_PA6 };
-
-static struct resource spi1_resources[] = {
-	[0] = {
-		.start	= AT572D940HF_BASE_SPI1,
-		.end	= AT572D940HF_BASE_SPI1 + SZ_16K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AT572D940HF_ID_SPI1,
-		.end	= AT572D940HF_ID_SPI1,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device at572d940hf_spi1_device = {
-	.name		= "atmel_spi",
-	.id		= 1,
-	.dev		= {
-				.dma_mask		= &spi_dmamask,
-				.coherent_dma_mask	= DMA_BIT_MASK(32),
-	},
-	.resource	= spi1_resources,
-	.num_resources	= ARRAY_SIZE(spi1_resources),
-};
-
-static const unsigned spi1_standard_cs[4] = { AT91_PIN_PC3, AT91_PIN_PC4, AT91_PIN_PC5, AT91_PIN_PC6 };
-
-void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
-{
-	int i;
-	unsigned long cs_pin;
-	short enable_spi0 = 0;
-	short enable_spi1 = 0;
-
-	/* Choose SPI chip-selects */
-	for (i = 0; i < nr_devices; i++) {
-		if (devices[i].controller_data)
-			cs_pin = (unsigned long) devices[i].controller_data;
-		else if (devices[i].bus_num == 0)
-			cs_pin = spi0_standard_cs[devices[i].chip_select];
-		else
-			cs_pin = spi1_standard_cs[devices[i].chip_select];
-
-		if (devices[i].bus_num == 0)
-			enable_spi0 = 1;
-		else
-			enable_spi1 = 1;
-
-		/* enable chip-select pin */
-		at91_set_gpio_output(cs_pin, 1);
-
-		/* pass chip-select pin to driver */
-		devices[i].controller_data = (void *) cs_pin;
-	}
-
-	spi_register_board_info(devices, nr_devices);
-
-	/* Configure SPI bus(es) */
-	if (enable_spi0) {
-		at91_set_A_periph(AT91_PIN_PA0, 0);	/* SPI0_MISO */
-		at91_set_A_periph(AT91_PIN_PA1, 0);	/* SPI0_MOSI */
-		at91_set_A_periph(AT91_PIN_PA2, 0);	/* SPI0_SPCK */
-
-		at91_clock_associate("spi0_clk", &at572d940hf_spi0_device.dev, "spi_clk");
-		platform_device_register(&at572d940hf_spi0_device);
-	}
-	if (enable_spi1) {
-		at91_set_A_periph(AT91_PIN_PC0, 0);	/* SPI1_MISO */
-		at91_set_A_periph(AT91_PIN_PC1, 0);	/* SPI1_MOSI */
-		at91_set_A_periph(AT91_PIN_PC2, 0);	/* SPI1_SPCK */
-
-		at91_clock_associate("spi1_clk", &at572d940hf_spi1_device.dev, "spi_clk");
-		platform_device_register(&at572d940hf_spi1_device);
-	}
-}
-#else
-void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices) {}
-#endif
-
-
-/* --------------------------------------------------------------------
- *  Timer/Counter blocks
- * -------------------------------------------------------------------- */
-
-#ifdef CONFIG_ATMEL_TCLIB
-
-static struct resource tcb_resources[] = {
-	[0] = {
-		.start	= AT572D940HF_BASE_TCB,
-		.end	= AT572D940HF_BASE_TCB + SZ_16K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AT572D940HF_ID_TC0,
-		.end	= AT572D940HF_ID_TC0,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = {
-		.start	= AT572D940HF_ID_TC1,
-		.end	= AT572D940HF_ID_TC1,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[3] = {
-		.start	= AT572D940HF_ID_TC2,
-		.end	= AT572D940HF_ID_TC2,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device at572d940hf_tcb_device = {
-	.name		= "atmel_tcb",
-	.id		= 0,
-	.resource	= tcb_resources,
-	.num_resources	= ARRAY_SIZE(tcb_resources),
-};
-
-static void __init at91_add_device_tc(void)
-{
-	/* this chip has a separate clock and irq for each TC channel */
-	at91_clock_associate("tc0_clk", &at572d940hf_tcb_device.dev, "t0_clk");
-	at91_clock_associate("tc1_clk", &at572d940hf_tcb_device.dev, "t1_clk");
-	at91_clock_associate("tc2_clk", &at572d940hf_tcb_device.dev, "t2_clk");
-	platform_device_register(&at572d940hf_tcb_device);
-}
-#else
-static void __init at91_add_device_tc(void) { }
-#endif
-
-
-/* --------------------------------------------------------------------
- *  RTT
- * -------------------------------------------------------------------- */
-
-static struct resource rtt_resources[] = {
-	{
-		.start	= AT91_BASE_SYS + AT91_RTT,
-		.end	= AT91_BASE_SYS + AT91_RTT + SZ_16 - 1,
-		.flags	= IORESOURCE_MEM,
-	}
-};
-
-static struct platform_device at572d940hf_rtt_device = {
-	.name		= "at91_rtt",
-	.id		= 0,
-	.resource	= rtt_resources,
-	.num_resources	= ARRAY_SIZE(rtt_resources),
-};
-
-static void __init at91_add_device_rtt(void)
-{
-	platform_device_register(&at572d940hf_rtt_device);
-}
-
-
-/* --------------------------------------------------------------------
- *  Watchdog
- * -------------------------------------------------------------------- */
-
-#if defined(CONFIG_AT91SAM9X_WATCHDOG) || defined(CONFIG_AT91SAM9X_WATCHDOG_MODULE)
-static struct platform_device at572d940hf_wdt_device = {
-	.name		= "at91_wdt",
-	.id		= -1,
-	.num_resources	= 0,
-};
-
-static void __init at91_add_device_watchdog(void)
-{
-	platform_device_register(&at572d940hf_wdt_device);
-}
-#else
-static void __init at91_add_device_watchdog(void) {}
-#endif
-
-
-/* --------------------------------------------------------------------
- *  UART
- * -------------------------------------------------------------------- */
-
-#if defined(CONFIG_SERIAL_ATMEL)
-static struct resource dbgu_resources[] = {
-	[0] = {
-		.start	= AT91_VA_BASE_SYS + AT91_DBGU,
-		.end	= AT91_VA_BASE_SYS + AT91_DBGU + SZ_512 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AT91_ID_SYS,
-		.end	= AT91_ID_SYS,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct atmel_uart_data dbgu_data = {
-	.use_dma_tx	= 0,
-	.use_dma_rx	= 0,		/* DBGU not capable of receive DMA */
-	.regs		= (void __iomem *)(AT91_VA_BASE_SYS + AT91_DBGU),
-};
-
-static u64 dbgu_dmamask = DMA_BIT_MASK(32);
-
-static struct platform_device at572d940hf_dbgu_device = {
-	.name		= "atmel_usart",
-	.id		= 0,
-	.dev		= {
-				.dma_mask		= &dbgu_dmamask,
-				.coherent_dma_mask	= DMA_BIT_MASK(32),
-				.platform_data		= &dbgu_data,
-	},
-	.resource	= dbgu_resources,
-	.num_resources	= ARRAY_SIZE(dbgu_resources),
-};
-
-static inline void configure_dbgu_pins(void)
-{
-	at91_set_A_periph(AT91_PIN_PC31, 1);		/* DTXD */
-	at91_set_A_periph(AT91_PIN_PC30, 0);		/* DRXD */
-}
-
-static struct resource uart0_resources[] = {
-	[0] = {
-		.start	= AT572D940HF_BASE_US0,
-		.end	= AT572D940HF_BASE_US0 + SZ_16K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AT572D940HF_ID_US0,
-		.end	= AT572D940HF_ID_US0,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct atmel_uart_data uart0_data = {
-	.use_dma_tx	= 1,
-	.use_dma_rx	= 1,
-};
-
-static u64 uart0_dmamask = DMA_BIT_MASK(32);
-
-static struct platform_device at572d940hf_uart0_device = {
-	.name		= "atmel_usart",
-	.id		= 1,
-	.dev		= {
-				.dma_mask		= &uart0_dmamask,
-				.coherent_dma_mask	= DMA_BIT_MASK(32),
-				.platform_data		= &uart0_data,
-	},
-	.resource	= uart0_resources,
-	.num_resources	= ARRAY_SIZE(uart0_resources),
-};
-
-static inline void configure_usart0_pins(unsigned pins)
-{
-	at91_set_A_periph(AT91_PIN_PA8, 1);		/* TXD0 */
-	at91_set_A_periph(AT91_PIN_PA7, 0);		/* RXD0 */
-
-	if (pins & ATMEL_UART_RTS)
-		at91_set_A_periph(AT91_PIN_PA10, 0);	/* RTS0 */
-	if (pins & ATMEL_UART_CTS)
-		at91_set_A_periph(AT91_PIN_PA9, 0);	/* CTS0 */
-}
-
-static struct resource uart1_resources[] = {
-	[0] = {
-		.start	= AT572D940HF_BASE_US1,
-		.end	= AT572D940HF_BASE_US1 + SZ_16K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AT572D940HF_ID_US1,
-		.end	= AT572D940HF_ID_US1,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct atmel_uart_data uart1_data = {
-	.use_dma_tx	= 1,
-	.use_dma_rx	= 1,
-};
-
-static u64 uart1_dmamask = DMA_BIT_MASK(32);
-
-static struct platform_device at572d940hf_uart1_device = {
-	.name		= "atmel_usart",
-	.id		= 2,
-	.dev		= {
-				.dma_mask		= &uart1_dmamask,
-				.coherent_dma_mask	= DMA_BIT_MASK(32),
-				.platform_data		= &uart1_data,
-	},
-	.resource	= uart1_resources,
-	.num_resources	= ARRAY_SIZE(uart1_resources),
-};
-
-static inline void configure_usart1_pins(unsigned pins)
-{
-	at91_set_A_periph(AT91_PIN_PC10, 1);		/* TXD1 */
-	at91_set_A_periph(AT91_PIN_PC9 , 0);		/* RXD1 */
-
-	if (pins & ATMEL_UART_RTS)
-		at91_set_A_periph(AT91_PIN_PC12, 0);	/* RTS1 */
-	if (pins & ATMEL_UART_CTS)
-		at91_set_A_periph(AT91_PIN_PC11, 0);	/* CTS1 */
-}
-
-static struct resource uart2_resources[] = {
-	[0] = {
-		.start	= AT572D940HF_BASE_US2,
-		.end	= AT572D940HF_BASE_US2 + SZ_16K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AT572D940HF_ID_US2,
-		.end	= AT572D940HF_ID_US2,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct atmel_uart_data uart2_data = {
-	.use_dma_tx	= 1,
-	.use_dma_rx	= 1,
-};
-
-static u64 uart2_dmamask = DMA_BIT_MASK(32);
-
-static struct platform_device at572d940hf_uart2_device = {
-	.name		= "atmel_usart",
-	.id		= 3,
-	.dev		= {
-				.dma_mask		= &uart2_dmamask,
-				.coherent_dma_mask	= DMA_BIT_MASK(32),
-				.platform_data		= &uart2_data,
-	},
-	.resource	= uart2_resources,
-	.num_resources	= ARRAY_SIZE(uart2_resources),
-};
-
-static inline void configure_usart2_pins(unsigned pins)
-{
-	at91_set_A_periph(AT91_PIN_PC15, 1);		/* TXD2 */
-	at91_set_A_periph(AT91_PIN_PC14, 0);		/* RXD2 */
-
-	if (pins & ATMEL_UART_RTS)
-		at91_set_A_periph(AT91_PIN_PC17, 0);	/* RTS2 */
-	if (pins & ATMEL_UART_CTS)
-		at91_set_A_periph(AT91_PIN_PC16, 0);	/* CTS2 */
-}
-
-static struct platform_device *__initdata at91_uarts[ATMEL_MAX_UART];	/* the UARTs to use */
-struct platform_device *atmel_default_console_device;	/* the serial console device */
-
-void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
-{
-	struct platform_device *pdev;
-
-	switch (id) {
-		case 0:		/* DBGU */
-			pdev = &at572d940hf_dbgu_device;
-			configure_dbgu_pins();
-			at91_clock_associate("mck", &pdev->dev, "usart");
-			break;
-		case AT572D940HF_ID_US0:
-			pdev = &at572d940hf_uart0_device;
-			configure_usart0_pins(pins);
-			at91_clock_associate("usart0_clk", &pdev->dev, "usart");
-			break;
-		case AT572D940HF_ID_US1:
-			pdev = &at572d940hf_uart1_device;
-			configure_usart1_pins(pins);
-			at91_clock_associate("usart1_clk", &pdev->dev, "usart");
-			break;
-		case AT572D940HF_ID_US2:
-			pdev = &at572d940hf_uart2_device;
-			configure_usart2_pins(pins);
-			at91_clock_associate("usart2_clk", &pdev->dev, "usart");
-			break;
-		default:
-			return;
-	}
-	pdev->id = portnr;		/* update to mapped ID */
-
-	if (portnr < ATMEL_MAX_UART)
-		at91_uarts[portnr] = pdev;
-}
-
-void __init at91_set_serial_console(unsigned portnr)
-{
-	if (portnr < ATMEL_MAX_UART)
-		atmel_default_console_device = at91_uarts[portnr];
-}
-
-void __init at91_add_device_serial(void)
-{
-	int i;
-
-	for (i = 0; i < ATMEL_MAX_UART; i++) {
-		if (at91_uarts[i])
-			platform_device_register(at91_uarts[i]);
-	}
-
-	if (!atmel_default_console_device)
-		printk(KERN_INFO "AT91: No default serial console defined.\n");
-}
-
-#else
-void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins) {}
-void __init at91_set_serial_console(unsigned portnr) {}
-void __init at91_add_device_serial(void) {}
-#endif
-
-
-/* --------------------------------------------------------------------
- *  mAgic
- * -------------------------------------------------------------------- */
-
-#ifdef CONFIG_MAGICV
-static struct resource mAgic_resources[] = {
-	{
-		.start = AT91_MAGIC_PM_BASE,
-		.end   = AT91_MAGIC_PM_BASE + AT91_MAGIC_PM_SIZE - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.start = AT91_MAGIC_DM_I_BASE,
-		.end   = AT91_MAGIC_DM_I_BASE + AT91_MAGIC_DM_I_SIZE - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.start = AT91_MAGIC_DM_F_BASE,
-		.end   = AT91_MAGIC_DM_F_BASE + AT91_MAGIC_DM_F_SIZE - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.start = AT91_MAGIC_DM_DB_BASE,
-		.end   = AT91_MAGIC_DM_DB_BASE + AT91_MAGIC_DM_DB_SIZE - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.start = AT91_MAGIC_REGS_BASE,
-		.end   = AT91_MAGIC_REGS_BASE + AT91_MAGIC_REGS_SIZE - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.start = AT91_MAGIC_EXTPAGE_BASE,
-		.end   = AT91_MAGIC_EXTPAGE_BASE + AT91_MAGIC_EXTPAGE_SIZE - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.start  = AT572D940HF_ID_MSIRQ0,
-		.end    = AT572D940HF_ID_MSIRQ0,
-		.flags  = IORESOURCE_IRQ,
-	},
-	{
-		.start  = AT572D940HF_ID_MHALT,
-		.end    = AT572D940HF_ID_MHALT,
-		.flags  = IORESOURCE_IRQ,
-	},
-	{
-		.start  = AT572D940HF_ID_MEXC,
-		.end    = AT572D940HF_ID_MEXC,
-		.flags  = IORESOURCE_IRQ,
-	},
-	{
-		.start  = AT572D940HF_ID_MEDMA,
-		.end    = AT572D940HF_ID_MEDMA,
-		.flags  = IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device mAgic_device = {
-	.name           = "mAgic",
-	.id             = -1,
-	.num_resources  = ARRAY_SIZE(mAgic_resources),
-	.resource       = mAgic_resources,
-};
-
-void __init at91_add_device_mAgic(void)
-{
-	platform_device_register(&mAgic_device);
-}
-#else
-void __init at91_add_device_mAgic(void) {}
-#endif
-
-
-/* -------------------------------------------------------------------- */
-
-/*
- * These devices are always present and don't need any board-specific
- * setup.
- */
-static int __init at91_add_standard_devices(void)
-{
-	at91_add_device_rtt();
-	at91_add_device_watchdog();
-	at91_add_device_tc();
-	return 0;
-}
-
-arch_initcall(at91_add_standard_devices);
diff --git a/arch/arm/mach-at91/at91cap9.c b/arch/arm/mach-at91/at91cap9.c
index 73376170fb91..17fae4a42ab5 100644
--- a/arch/arm/mach-at91/at91cap9.c
+++ b/arch/arm/mach-at91/at91cap9.c
@@ -222,6 +222,25 @@ static struct clk *periph_clocks[] __initdata = {
 	// irq0 .. irq1
 };
 
+static struct clk_lookup periph_clocks_lookups[] = {
+	CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc.0", &utmi_clk),
+	CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc.0", &udphs_clk),
+	CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.0", &mmc0_clk),
+	CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.1", &mmc1_clk),
+	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.0", &spi0_clk),
+	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk),
+	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tcb_clk),
+	CLKDEV_CON_DEV_ID("ssc", "ssc.0", &ssc0_clk),
+	CLKDEV_CON_DEV_ID("ssc", "ssc.1", &ssc1_clk),
+};
+
+static struct clk_lookup usart_clocks_lookups[] = {
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.0", &mck),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.1", &usart0_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.2", &usart1_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.3", &usart2_clk),
+};
+
 /*
  * The four programmable clocks.
  * You must configure pin multiplexing to bring these signals out.
@@ -258,12 +277,29 @@ static void __init at91cap9_register_clocks(void)
 	for (i = 0; i < ARRAY_SIZE(periph_clocks); i++)
 		clk_register(periph_clocks[i]);
 
+	clkdev_add_table(periph_clocks_lookups,
+			 ARRAY_SIZE(periph_clocks_lookups));
+	clkdev_add_table(usart_clocks_lookups,
+			 ARRAY_SIZE(usart_clocks_lookups));
+
 	clk_register(&pck0);
 	clk_register(&pck1);
 	clk_register(&pck2);
 	clk_register(&pck3);
 }
 
+static struct clk_lookup console_clock_lookup;
+
+void __init at91cap9_set_console_clock(int id)
+{
+	if (id >= ARRAY_SIZE(usart_clocks_lookups))
+		return;
+
+	console_clock_lookup.con_id = "usart";
+	console_clock_lookup.clk = usart_clocks_lookups[id].clk;
+	clkdev_add(&console_clock_lookup);
+}
+
 /* --------------------------------------------------------------------
  *  GPIO
  * -------------------------------------------------------------------- */
@@ -303,11 +339,14 @@ static void at91cap9_poweroff(void)
  *  AT91CAP9 processor initialization
  * -------------------------------------------------------------------- */
 
-void __init at91cap9_initialize(unsigned long main_clock)
+void __init at91cap9_map_io(void)
 {
 	/* Map peripherals */
 	iotable_init(at91cap9_io_desc, ARRAY_SIZE(at91cap9_io_desc));
+}
 
+void __init at91cap9_initialize(unsigned long main_clock)
+{
 	at91_arch_reset = at91cap9_reset;
 	pm_power_off = at91cap9_poweroff;
 	at91_extern_irq = (1 << AT91CAP9_ID_IRQ0) | (1 << AT91CAP9_ID_IRQ1);
diff --git a/arch/arm/mach-at91/at91cap9_devices.c b/arch/arm/mach-at91/at91cap9_devices.c
index 21020ceb2f3a..cd850ed6f335 100644
--- a/arch/arm/mach-at91/at91cap9_devices.c
+++ b/arch/arm/mach-at91/at91cap9_devices.c
@@ -181,10 +181,6 @@ void __init at91_add_device_usba(struct usba_platform_data *data)
 
 	/* Pullup pin is handled internally by USB device peripheral */
 
-	/* Clocks */
-	at91_clock_associate("utmi_clk", &at91_usba_udc_device.dev, "hclk");
-	at91_clock_associate("udphs_clk", &at91_usba_udc_device.dev, "pclk");
-
 	platform_device_register(&at91_usba_udc_device);
 }
 #else
@@ -355,7 +351,6 @@ void __init at91_add_device_mmc(short mmc_id, struct at91_mmc_data *data)
 		}
 
 		mmc0_data = *data;
-		at91_clock_associate("mci0_clk", &at91cap9_mmc0_device.dev, "mci_clk");
 		platform_device_register(&at91cap9_mmc0_device);
 	} else {			/* MCI1 */
 		/* CLK */
@@ -373,7 +368,6 @@ void __init at91_add_device_mmc(short mmc_id, struct at91_mmc_data *data)
 		}
 
 		mmc1_data = *data;
-		at91_clock_associate("mci1_clk", &at91cap9_mmc1_device.dev, "mci_clk");
 		platform_device_register(&at91cap9_mmc1_device);
 	}
 }
@@ -614,7 +608,6 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		at91_set_B_periph(AT91_PIN_PA1, 0);	/* SPI0_MOSI */
 		at91_set_B_periph(AT91_PIN_PA2, 0);	/* SPI0_SPCK */
 
-		at91_clock_associate("spi0_clk", &at91cap9_spi0_device.dev, "spi_clk");
 		platform_device_register(&at91cap9_spi0_device);
 	}
 	if (enable_spi1) {
@@ -622,7 +615,6 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		at91_set_A_periph(AT91_PIN_PB13, 0);	/* SPI1_MOSI */
 		at91_set_A_periph(AT91_PIN_PB14, 0);	/* SPI1_SPCK */
 
-		at91_clock_associate("spi1_clk", &at91cap9_spi1_device.dev, "spi_clk");
 		platform_device_register(&at91cap9_spi1_device);
 	}
 }
@@ -659,8 +651,6 @@ static struct platform_device at91cap9_tcb_device = {
 
 static void __init at91_add_device_tc(void)
 {
-	/* this chip has one clock and irq for all three TC channels */
-	at91_clock_associate("tcb_clk", &at91cap9_tcb_device.dev, "t0_clk");
 	platform_device_register(&at91cap9_tcb_device);
 }
 #else
@@ -1001,12 +991,10 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins)
 	case AT91CAP9_ID_SSC0:
 		pdev = &at91cap9_ssc0_device;
 		configure_ssc0_pins(pins);
-		at91_clock_associate("ssc0_clk", &pdev->dev, "ssc");
 		break;
 	case AT91CAP9_ID_SSC1:
 		pdev = &at91cap9_ssc1_device;
 		configure_ssc1_pins(pins);
-		at91_clock_associate("ssc1_clk", &pdev->dev, "ssc");
 		break;
 	default:
 		return;
@@ -1199,32 +1187,30 @@ struct platform_device *atmel_default_console_device;	/* the serial console devi
 void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 {
 	struct platform_device *pdev;
+	struct atmel_uart_data *pdata;
 
 	switch (id) {
 		case 0:		/* DBGU */
 			pdev = &at91cap9_dbgu_device;
 			configure_dbgu_pins();
-			at91_clock_associate("mck", &pdev->dev, "usart");
 			break;
 		case AT91CAP9_ID_US0:
 			pdev = &at91cap9_uart0_device;
 			configure_usart0_pins(pins);
-			at91_clock_associate("usart0_clk", &pdev->dev, "usart");
 			break;
 		case AT91CAP9_ID_US1:
 			pdev = &at91cap9_uart1_device;
 			configure_usart1_pins(pins);
-			at91_clock_associate("usart1_clk", &pdev->dev, "usart");
 			break;
 		case AT91CAP9_ID_US2:
 			pdev = &at91cap9_uart2_device;
 			configure_usart2_pins(pins);
-			at91_clock_associate("usart2_clk", &pdev->dev, "usart");
 			break;
 		default:
 			return;
 	}
-	pdev->id = portnr;		/* update to mapped ID */
+	pdata = pdev->dev.platform_data;
+	pdata->num = portnr;		/* update to mapped ID */
 
 	if (portnr < ATMEL_MAX_UART)
 		at91_uarts[portnr] = pdev;
@@ -1232,8 +1218,10 @@ void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 
 void __init at91_set_serial_console(unsigned portnr)
 {
-	if (portnr < ATMEL_MAX_UART)
+	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
+		at91cap9_set_console_clock(portnr);
+	}
 }
 
 void __init at91_add_device_serial(void)
diff --git a/arch/arm/mach-at91/at91rm9200.c b/arch/arm/mach-at91/at91rm9200.c
index 2e9ecad97f3d..b228ce9e21a1 100644
--- a/arch/arm/mach-at91/at91rm9200.c
+++ b/arch/arm/mach-at91/at91rm9200.c
@@ -18,6 +18,7 @@
 #include <mach/at91rm9200.h>
 #include <mach/at91_pmc.h>
 #include <mach/at91_st.h>
+#include <mach/cpu.h>
 
 #include "generic.h"
 #include "clock.h"
@@ -191,6 +192,26 @@ static struct clk *periph_clocks[] __initdata = {
 	// irq0 .. irq6
 };
 
+static struct clk_lookup periph_clocks_lookups[] = {
+	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk),
+	CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk),
+	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc2_clk),
+	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.1", &tc3_clk),
+	CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.1", &tc4_clk),
+	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.1", &tc5_clk),
+	CLKDEV_CON_DEV_ID("ssc", "ssc.0", &ssc0_clk),
+	CLKDEV_CON_DEV_ID("ssc", "ssc.1", &ssc1_clk),
+	CLKDEV_CON_DEV_ID("ssc", "ssc.2", &ssc2_clk),
+};
+
+static struct clk_lookup usart_clocks_lookups[] = {
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.0", &mck),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.1", &usart0_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.2", &usart1_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.3", &usart2_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.4", &usart3_clk),
+};
+
 /*
  * The four programmable clocks.
  * You must configure pin multiplexing to bring these signals out.
@@ -227,12 +248,29 @@ static void __init at91rm9200_register_clocks(void)
 	for (i = 0; i < ARRAY_SIZE(periph_clocks); i++)
 		clk_register(periph_clocks[i]);
 
+	clkdev_add_table(periph_clocks_lookups,
+			 ARRAY_SIZE(periph_clocks_lookups));
+	clkdev_add_table(usart_clocks_lookups,
+			 ARRAY_SIZE(usart_clocks_lookups));
+
 	clk_register(&pck0);
 	clk_register(&pck1);
 	clk_register(&pck2);
 	clk_register(&pck3);
 }
 
+static struct clk_lookup console_clock_lookup;
+
+void __init at91rm9200_set_console_clock(int id)
+{
+	if (id >= ARRAY_SIZE(usart_clocks_lookups))
+		return;
+
+	console_clock_lookup.con_id = "usart";
+	console_clock_lookup.clk = usart_clocks_lookups[id].clk;
+	clkdev_add(&console_clock_lookup);
+}
+
 /* --------------------------------------------------------------------
  *  GPIO
  * -------------------------------------------------------------------- */
@@ -266,15 +304,25 @@ static void at91rm9200_reset(void)
 	at91_sys_write(AT91_ST_CR, AT91_ST_WDRST);
 }
 
+int rm9200_type;
+EXPORT_SYMBOL(rm9200_type);
+
+void __init at91rm9200_set_type(int type)
+{
+	rm9200_type = type;
+}
 
 /* --------------------------------------------------------------------
  *  AT91RM9200 processor initialization
  * -------------------------------------------------------------------- */
-void __init at91rm9200_initialize(unsigned long main_clock, unsigned short banks)
+void __init at91rm9200_map_io(void)
 {
 	/* Map peripherals */
 	iotable_init(at91rm9200_io_desc, ARRAY_SIZE(at91rm9200_io_desc));
+}
 
+void __init at91rm9200_initialize(unsigned long main_clock)
+{
 	at91_arch_reset = at91rm9200_reset;
 	at91_extern_irq = (1 << AT91RM9200_ID_IRQ0) | (1 << AT91RM9200_ID_IRQ1)
 			| (1 << AT91RM9200_ID_IRQ2) | (1 << AT91RM9200_ID_IRQ3)
@@ -288,7 +336,8 @@ void __init at91rm9200_initialize(unsigned long main_clock, unsigned short banks
 	at91rm9200_register_clocks();
 
 	/* Initialize GPIO subsystem */
-	at91_gpio_init(at91rm9200_gpio, banks);
+	at91_gpio_init(at91rm9200_gpio,
+		cpu_is_at91rm9200_bga() ? AT91RM9200_BGA : AT91RM9200_PQFP);
 }
 
 
diff --git a/arch/arm/mach-at91/at91rm9200_devices.c b/arch/arm/mach-at91/at91rm9200_devices.c
index 7b539228e0ef..a0ba475be04c 100644
--- a/arch/arm/mach-at91/at91rm9200_devices.c
+++ b/arch/arm/mach-at91/at91rm9200_devices.c
@@ -644,15 +644,7 @@ static struct platform_device at91rm9200_tcb1_device = {
 
 static void __init at91_add_device_tc(void)
 {
-	/* this chip has a separate clock and irq for each TC channel */
-	at91_clock_associate("tc0_clk", &at91rm9200_tcb0_device.dev, "t0_clk");
-	at91_clock_associate("tc1_clk", &at91rm9200_tcb0_device.dev, "t1_clk");
-	at91_clock_associate("tc2_clk", &at91rm9200_tcb0_device.dev, "t2_clk");
 	platform_device_register(&at91rm9200_tcb0_device);
-
-	at91_clock_associate("tc3_clk", &at91rm9200_tcb1_device.dev, "t0_clk");
-	at91_clock_associate("tc4_clk", &at91rm9200_tcb1_device.dev, "t1_clk");
-	at91_clock_associate("tc5_clk", &at91rm9200_tcb1_device.dev, "t2_clk");
 	platform_device_register(&at91rm9200_tcb1_device);
 }
 #else
@@ -849,17 +841,14 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins)
 	case AT91RM9200_ID_SSC0:
 		pdev = &at91rm9200_ssc0_device;
 		configure_ssc0_pins(pins);
-		at91_clock_associate("ssc0_clk", &pdev->dev, "ssc");
 		break;
 	case AT91RM9200_ID_SSC1:
 		pdev = &at91rm9200_ssc1_device;
 		configure_ssc1_pins(pins);
-		at91_clock_associate("ssc1_clk", &pdev->dev, "ssc");
 		break;
 	case AT91RM9200_ID_SSC2:
 		pdev = &at91rm9200_ssc2_device;
 		configure_ssc2_pins(pins);
-		at91_clock_associate("ssc2_clk", &pdev->dev, "ssc");
 		break;
 	default:
 		return;
@@ -1109,37 +1098,34 @@ struct platform_device *atmel_default_console_device;	/* the serial console devi
 void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 {
 	struct platform_device *pdev;
+	struct atmel_uart_data *pdata;
 
 	switch (id) {
 		case 0:		/* DBGU */
 			pdev = &at91rm9200_dbgu_device;
 			configure_dbgu_pins();
-			at91_clock_associate("mck", &pdev->dev, "usart");
 			break;
 		case AT91RM9200_ID_US0:
 			pdev = &at91rm9200_uart0_device;
 			configure_usart0_pins(pins);
-			at91_clock_associate("usart0_clk", &pdev->dev, "usart");
 			break;
 		case AT91RM9200_ID_US1:
 			pdev = &at91rm9200_uart1_device;
 			configure_usart1_pins(pins);
-			at91_clock_associate("usart1_clk", &pdev->dev, "usart");
 			break;
 		case AT91RM9200_ID_US2:
 			pdev = &at91rm9200_uart2_device;
 			configure_usart2_pins(pins);
-			at91_clock_associate("usart2_clk", &pdev->dev, "usart");
 			break;
 		case AT91RM9200_ID_US3:
 			pdev = &at91rm9200_uart3_device;
 			configure_usart3_pins(pins);
-			at91_clock_associate("usart3_clk", &pdev->dev, "usart");
 			break;
 		default:
 			return;
 	}
-	pdev->id = portnr;		/* update to mapped ID */
+	pdata = pdev->dev.platform_data;
+	pdata->num = portnr;		/* update to mapped ID */
 
 	if (portnr < ATMEL_MAX_UART)
 		at91_uarts[portnr] = pdev;
@@ -1147,8 +1133,10 @@ void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 
 void __init at91_set_serial_console(unsigned portnr)
 {
-	if (portnr < ATMEL_MAX_UART)
+	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
+		at91rm9200_set_console_clock(portnr);
+	}
 }
 
 void __init at91_add_device_serial(void)
diff --git a/arch/arm/mach-at91/at91sam9260.c b/arch/arm/mach-at91/at91sam9260.c
index 195208b30024..7d606b04d313 100644
--- a/arch/arm/mach-at91/at91sam9260.c
+++ b/arch/arm/mach-at91/at91sam9260.c
@@ -231,6 +231,28 @@ static struct clk *periph_clocks[] __initdata = {
 	// irq0 .. irq2
 };
 
+static struct clk_lookup periph_clocks_lookups[] = {
+	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.0", &spi0_clk),
+	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk),
+	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk),
+	CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk),
+	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc2_clk),
+	CLKDEV_CON_DEV_ID("t3_clk", "atmel_tcb.1", &tc3_clk),
+	CLKDEV_CON_DEV_ID("t4_clk", "atmel_tcb.1", &tc4_clk),
+	CLKDEV_CON_DEV_ID("t5_clk", "atmel_tcb.1", &tc5_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc_clk),
+};
+
+static struct clk_lookup usart_clocks_lookups[] = {
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.0", &mck),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.1", &usart0_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.2", &usart1_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.3", &usart2_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.4", &usart3_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.5", &usart4_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.6", &usart5_clk),
+};
+
 /*
  * The two programmable clocks.
  * You must configure pin multiplexing to bring these signals out.
@@ -255,10 +277,27 @@ static void __init at91sam9260_register_clocks(void)
 	for (i = 0; i < ARRAY_SIZE(periph_clocks); i++)
 		clk_register(periph_clocks[i]);
 
+	clkdev_add_table(periph_clocks_lookups,
+			 ARRAY_SIZE(periph_clocks_lookups));
+	clkdev_add_table(usart_clocks_lookups,
+			 ARRAY_SIZE(usart_clocks_lookups));
+
 	clk_register(&pck0);
 	clk_register(&pck1);
 }
 
+static struct clk_lookup console_clock_lookup;
+
+void __init at91sam9260_set_console_clock(int id)
+{
+	if (id >= ARRAY_SIZE(usart_clocks_lookups))
+		return;
+
+	console_clock_lookup.con_id = "usart";
+	console_clock_lookup.clk = usart_clocks_lookups[id].clk;
+	clkdev_add(&console_clock_lookup);
+}
+
 /* --------------------------------------------------------------------
  *  GPIO
  * -------------------------------------------------------------------- */
@@ -289,7 +328,7 @@ static void at91sam9260_poweroff(void)
  *  AT91SAM9260 processor initialization
  * -------------------------------------------------------------------- */
 
-static void __init at91sam9xe_initialize(void)
+static void __init at91sam9xe_map_io(void)
 {
 	unsigned long cidr, sram_size;
 
@@ -310,18 +349,21 @@ static void __init at91sam9xe_initialize(void)
 	iotable_init(at91sam9xe_sram_desc, ARRAY_SIZE(at91sam9xe_sram_desc));
 }
 
-void __init at91sam9260_initialize(unsigned long main_clock)
+void __init at91sam9260_map_io(void)
 {
 	/* Map peripherals */
 	iotable_init(at91sam9260_io_desc, ARRAY_SIZE(at91sam9260_io_desc));
 
 	if (cpu_is_at91sam9xe())
-		at91sam9xe_initialize();
+		at91sam9xe_map_io();
 	else if (cpu_is_at91sam9g20())
 		iotable_init(at91sam9g20_sram_desc, ARRAY_SIZE(at91sam9g20_sram_desc));
 	else
 		iotable_init(at91sam9260_sram_desc, ARRAY_SIZE(at91sam9260_sram_desc));
+}
 
+void __init at91sam9260_initialize(unsigned long main_clock)
+{
 	at91_arch_reset = at91sam9_alt_reset;
 	pm_power_off = at91sam9260_poweroff;
 	at91_extern_irq = (1 << AT91SAM9260_ID_IRQ0) | (1 << AT91SAM9260_ID_IRQ1)
diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
index 07eb7b07e442..1fdeb9058a76 100644
--- a/arch/arm/mach-at91/at91sam9260_devices.c
+++ b/arch/arm/mach-at91/at91sam9260_devices.c
@@ -609,7 +609,6 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		at91_set_A_periph(AT91_PIN_PA1, 0);	/* SPI0_MOSI */
 		at91_set_A_periph(AT91_PIN_PA2, 0);	/* SPI1_SPCK */
 
-		at91_clock_associate("spi0_clk", &at91sam9260_spi0_device.dev, "spi_clk");
 		platform_device_register(&at91sam9260_spi0_device);
 	}
 	if (enable_spi1) {
@@ -617,7 +616,6 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		at91_set_A_periph(AT91_PIN_PB1, 0);	/* SPI1_MOSI */
 		at91_set_A_periph(AT91_PIN_PB2, 0);	/* SPI1_SPCK */
 
-		at91_clock_associate("spi1_clk", &at91sam9260_spi1_device.dev, "spi_clk");
 		platform_device_register(&at91sam9260_spi1_device);
 	}
 }
@@ -694,15 +692,7 @@ static struct platform_device at91sam9260_tcb1_device = {
 
 static void __init at91_add_device_tc(void)
 {
-	/* this chip has a separate clock and irq for each TC channel */
-	at91_clock_associate("tc0_clk", &at91sam9260_tcb0_device.dev, "t0_clk");
-	at91_clock_associate("tc1_clk", &at91sam9260_tcb0_device.dev, "t1_clk");
-	at91_clock_associate("tc2_clk", &at91sam9260_tcb0_device.dev, "t2_clk");
 	platform_device_register(&at91sam9260_tcb0_device);
-
-	at91_clock_associate("tc3_clk", &at91sam9260_tcb1_device.dev, "t0_clk");
-	at91_clock_associate("tc4_clk", &at91sam9260_tcb1_device.dev, "t1_clk");
-	at91_clock_associate("tc5_clk", &at91sam9260_tcb1_device.dev, "t2_clk");
 	platform_device_register(&at91sam9260_tcb1_device);
 }
 #else
@@ -820,7 +810,6 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins)
 	case AT91SAM9260_ID_SSC:
 		pdev = &at91sam9260_ssc_device;
 		configure_ssc_pins(pins);
-		at91_clock_associate("ssc_clk", &pdev->dev, "pclk");
 		break;
 	default:
 		return;
@@ -1139,47 +1128,42 @@ struct platform_device *atmel_default_console_device;	/* the serial console devi
 void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 {
 	struct platform_device *pdev;
+	struct atmel_uart_data *pdata;
 
 	switch (id) {
 		case 0:		/* DBGU */
 			pdev = &at91sam9260_dbgu_device;
 			configure_dbgu_pins();
-			at91_clock_associate("mck", &pdev->dev, "usart");
 			break;
 		case AT91SAM9260_ID_US0:
 			pdev = &at91sam9260_uart0_device;
 			configure_usart0_pins(pins);
-			at91_clock_associate("usart0_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9260_ID_US1:
 			pdev = &at91sam9260_uart1_device;
 			configure_usart1_pins(pins);
-			at91_clock_associate("usart1_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9260_ID_US2:
 			pdev = &at91sam9260_uart2_device;
 			configure_usart2_pins(pins);
-			at91_clock_associate("usart2_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9260_ID_US3:
 			pdev = &at91sam9260_uart3_device;
 			configure_usart3_pins(pins);
-			at91_clock_associate("usart3_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9260_ID_US4:
 			pdev = &at91sam9260_uart4_device;
 			configure_usart4_pins();
-			at91_clock_associate("usart4_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9260_ID_US5:
 			pdev = &at91sam9260_uart5_device;
 			configure_usart5_pins();
-			at91_clock_associate("usart5_clk", &pdev->dev, "usart");
 			break;
 		default:
 			return;
 	}
-	pdev->id = portnr;		/* update to mapped ID */
+	pdata = pdev->dev.platform_data;
+	pdata->num = portnr;		/* update to mapped ID */
 
 	if (portnr < ATMEL_MAX_UART)
 		at91_uarts[portnr] = pdev;
@@ -1187,8 +1171,10 @@ void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 
 void __init at91_set_serial_console(unsigned portnr)
 {
-	if (portnr < ATMEL_MAX_UART)
+	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
+		at91sam9260_set_console_clock(portnr);
+	}
 }
 
 void __init at91_add_device_serial(void)
diff --git a/arch/arm/mach-at91/at91sam9261.c b/arch/arm/mach-at91/at91sam9261.c
index fcad88668504..c1483168c97a 100644
--- a/arch/arm/mach-at91/at91sam9261.c
+++ b/arch/arm/mach-at91/at91sam9261.c
@@ -178,6 +178,24 @@ static struct clk *periph_clocks[] __initdata = {
 	// irq0 .. irq2
 };
 
+static struct clk_lookup periph_clocks_lookups[] = {
+	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.0", &spi0_clk),
+	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk),
+	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk),
+	CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk),
+	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc1_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.2", &ssc2_clk),
+};
+
+static struct clk_lookup usart_clocks_lookups[] = {
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.0", &mck),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.1", &usart0_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.2", &usart1_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.3", &usart2_clk),
+};
+
 /*
  * The four programmable clocks.
  * You must configure pin multiplexing to bring these signals out.
@@ -228,6 +246,11 @@ static void __init at91sam9261_register_clocks(void)
 	for (i = 0; i < ARRAY_SIZE(periph_clocks); i++)
 		clk_register(periph_clocks[i]);
 
+	clkdev_add_table(periph_clocks_lookups,
+			 ARRAY_SIZE(periph_clocks_lookups));
+	clkdev_add_table(usart_clocks_lookups,
+			 ARRAY_SIZE(usart_clocks_lookups));
+
 	clk_register(&pck0);
 	clk_register(&pck1);
 	clk_register(&pck2);
@@ -237,6 +260,18 @@ static void __init at91sam9261_register_clocks(void)
 	clk_register(&hck1);
 }
 
+static struct clk_lookup console_clock_lookup;
+
+void __init at91sam9261_set_console_clock(int id)
+{
+	if (id >= ARRAY_SIZE(usart_clocks_lookups))
+		return;
+
+	console_clock_lookup.con_id = "usart";
+	console_clock_lookup.clk = usart_clocks_lookups[id].clk;
+	clkdev_add(&console_clock_lookup);
+}
+
 /* --------------------------------------------------------------------
  *  GPIO
  * -------------------------------------------------------------------- */
@@ -267,7 +302,7 @@ static void at91sam9261_poweroff(void)
  *  AT91SAM9261 processor initialization
  * -------------------------------------------------------------------- */
 
-void __init at91sam9261_initialize(unsigned long main_clock)
+void __init at91sam9261_map_io(void)
 {
 	/* Map peripherals */
 	iotable_init(at91sam9261_io_desc, ARRAY_SIZE(at91sam9261_io_desc));
@@ -276,8 +311,10 @@ void __init at91sam9261_initialize(unsigned long main_clock)
 		iotable_init(at91sam9g10_sram_desc, ARRAY_SIZE(at91sam9g10_sram_desc));
 	else
 		iotable_init(at91sam9261_sram_desc, ARRAY_SIZE(at91sam9261_sram_desc));
+}
 
-
+void __init at91sam9261_initialize(unsigned long main_clock)
+{
 	at91_arch_reset = at91sam9_alt_reset;
 	pm_power_off = at91sam9261_poweroff;
 	at91_extern_irq = (1 << AT91SAM9261_ID_IRQ0) | (1 << AT91SAM9261_ID_IRQ1)
diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index 59fc48311fb0..3eb4538fceeb 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -426,7 +426,6 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		at91_set_A_periph(AT91_PIN_PA1, 0);	/* SPI0_MOSI */
 		at91_set_A_periph(AT91_PIN_PA2, 0);	/* SPI0_SPCK */
 
-		at91_clock_associate("spi0_clk", &at91sam9261_spi0_device.dev, "spi_clk");
 		platform_device_register(&at91sam9261_spi0_device);
 	}
 	if (enable_spi1) {
@@ -434,7 +433,6 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		at91_set_A_periph(AT91_PIN_PB31, 0);	/* SPI1_MOSI */
 		at91_set_A_periph(AT91_PIN_PB29, 0);	/* SPI1_SPCK */
 
-		at91_clock_associate("spi1_clk", &at91sam9261_spi1_device.dev, "spi_clk");
 		platform_device_register(&at91sam9261_spi1_device);
 	}
 }
@@ -581,10 +579,6 @@ static struct platform_device at91sam9261_tcb_device = {
 
 static void __init at91_add_device_tc(void)
 {
-	/* this chip has a separate clock and irq for each TC channel */
-	at91_clock_associate("tc0_clk", &at91sam9261_tcb_device.dev, "t0_clk");
-	at91_clock_associate("tc1_clk", &at91sam9261_tcb_device.dev, "t1_clk");
-	at91_clock_associate("tc2_clk", &at91sam9261_tcb_device.dev, "t2_clk");
 	platform_device_register(&at91sam9261_tcb_device);
 }
 #else
@@ -786,17 +780,14 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins)
 	case AT91SAM9261_ID_SSC0:
 		pdev = &at91sam9261_ssc0_device;
 		configure_ssc0_pins(pins);
-		at91_clock_associate("ssc0_clk", &pdev->dev, "pclk");
 		break;
 	case AT91SAM9261_ID_SSC1:
 		pdev = &at91sam9261_ssc1_device;
 		configure_ssc1_pins(pins);
-		at91_clock_associate("ssc1_clk", &pdev->dev, "pclk");
 		break;
 	case AT91SAM9261_ID_SSC2:
 		pdev = &at91sam9261_ssc2_device;
 		configure_ssc2_pins(pins);
-		at91_clock_associate("ssc2_clk", &pdev->dev, "pclk");
 		break;
 	default:
 		return;
@@ -989,32 +980,30 @@ struct platform_device *atmel_default_console_device;	/* the serial console devi
 void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 {
 	struct platform_device *pdev;
+	struct atmel_uart_data *pdata;
 
 	switch (id) {
 		case 0:		/* DBGU */
 			pdev = &at91sam9261_dbgu_device;
 			configure_dbgu_pins();
-			at91_clock_associate("mck", &pdev->dev, "usart");
 			break;
 		case AT91SAM9261_ID_US0:
 			pdev = &at91sam9261_uart0_device;
 			configure_usart0_pins(pins);
-			at91_clock_associate("usart0_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9261_ID_US1:
 			pdev = &at91sam9261_uart1_device;
 			configure_usart1_pins(pins);
-			at91_clock_associate("usart1_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9261_ID_US2:
 			pdev = &at91sam9261_uart2_device;
 			configure_usart2_pins(pins);
-			at91_clock_associate("usart2_clk", &pdev->dev, "usart");
 			break;
 		default:
 			return;
 	}
-	pdev->id = portnr;		/* update to mapped ID */
+	pdata = pdev->dev.platform_data;
+	pdata->num = portnr;		/* update to mapped ID */
 
 	if (portnr < ATMEL_MAX_UART)
 		at91_uarts[portnr] = pdev;
@@ -1022,8 +1011,10 @@ void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 
 void __init at91_set_serial_console(unsigned portnr)
 {
-	if (portnr < ATMEL_MAX_UART)
+	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
+		at91sam9261_set_console_clock(portnr);
+	}
 }
 
 void __init at91_add_device_serial(void)
diff --git a/arch/arm/mach-at91/at91sam9263.c b/arch/arm/mach-at91/at91sam9263.c
index 249f900954d8..dc28477d14ff 100644
--- a/arch/arm/mach-at91/at91sam9263.c
+++ b/arch/arm/mach-at91/at91sam9263.c
@@ -199,6 +199,23 @@ static struct clk *periph_clocks[] __initdata = {
 	// irq0 .. irq1
 };
 
+static struct clk_lookup periph_clocks_lookups[] = {
+	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
+	CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.0", &mmc0_clk),
+	CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.1", &mmc1_clk),
+	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.0", &spi0_clk),
+	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk),
+	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tcb_clk),
+};
+
+static struct clk_lookup usart_clocks_lookups[] = {
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.0", &mck),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.1", &usart0_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.2", &usart1_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.3", &usart2_clk),
+};
+
 /*
  * The four programmable clocks.
  * You must configure pin multiplexing to bring these signals out.
@@ -235,12 +252,29 @@ static void __init at91sam9263_register_clocks(void)
 	for (i = 0; i < ARRAY_SIZE(periph_clocks); i++)
 		clk_register(periph_clocks[i]);
 
+	clkdev_add_table(periph_clocks_lookups,
+			 ARRAY_SIZE(periph_clocks_lookups));
+	clkdev_add_table(usart_clocks_lookups,
+			 ARRAY_SIZE(usart_clocks_lookups));
+
 	clk_register(&pck0);
 	clk_register(&pck1);
 	clk_register(&pck2);
 	clk_register(&pck3);
 }
 
+static struct clk_lookup console_clock_lookup;
+
+void __init at91sam9263_set_console_clock(int id)
+{
+	if (id >= ARRAY_SIZE(usart_clocks_lookups))
+		return;
+
+	console_clock_lookup.con_id = "usart";
+	console_clock_lookup.clk = usart_clocks_lookups[id].clk;
+	clkdev_add(&console_clock_lookup);
+}
+
 /* --------------------------------------------------------------------
  *  GPIO
  * -------------------------------------------------------------------- */
@@ -279,11 +313,14 @@ static void at91sam9263_poweroff(void)
  *  AT91SAM9263 processor initialization
  * -------------------------------------------------------------------- */
 
-void __init at91sam9263_initialize(unsigned long main_clock)
+void __init at91sam9263_map_io(void)
 {
 	/* Map peripherals */
 	iotable_init(at91sam9263_io_desc, ARRAY_SIZE(at91sam9263_io_desc));
+}
 
+void __init at91sam9263_initialize(unsigned long main_clock)
+{
 	at91_arch_reset = at91sam9_alt_reset;
 	pm_power_off = at91sam9263_poweroff;
 	at91_extern_irq = (1 << AT91SAM9263_ID_IRQ0) | (1 << AT91SAM9263_ID_IRQ1);
diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
index fb5c23af1017..ffe081b77ed0 100644
--- a/arch/arm/mach-at91/at91sam9263_devices.c
+++ b/arch/arm/mach-at91/at91sam9263_devices.c
@@ -308,7 +308,6 @@ void __init at91_add_device_mmc(short mmc_id, struct at91_mmc_data *data)
 		}
 
 		mmc0_data = *data;
-		at91_clock_associate("mci0_clk", &at91sam9263_mmc0_device.dev, "mci_clk");
 		platform_device_register(&at91sam9263_mmc0_device);
 	} else {			/* MCI1 */
 		/* CLK */
@@ -339,7 +338,6 @@ void __init at91_add_device_mmc(short mmc_id, struct at91_mmc_data *data)
 		}
 
 		mmc1_data = *data;
-		at91_clock_associate("mci1_clk", &at91sam9263_mmc1_device.dev, "mci_clk");
 		platform_device_register(&at91sam9263_mmc1_device);
 	}
 }
@@ -686,7 +684,6 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		at91_set_B_periph(AT91_PIN_PA1, 0);	/* SPI0_MOSI */
 		at91_set_B_periph(AT91_PIN_PA2, 0);	/* SPI0_SPCK */
 
-		at91_clock_associate("spi0_clk", &at91sam9263_spi0_device.dev, "spi_clk");
 		platform_device_register(&at91sam9263_spi0_device);
 	}
 	if (enable_spi1) {
@@ -694,7 +691,6 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		at91_set_A_periph(AT91_PIN_PB13, 0);	/* SPI1_MOSI */
 		at91_set_A_periph(AT91_PIN_PB14, 0);	/* SPI1_SPCK */
 
-		at91_clock_associate("spi1_clk", &at91sam9263_spi1_device.dev, "spi_clk");
 		platform_device_register(&at91sam9263_spi1_device);
 	}
 }
@@ -941,8 +937,6 @@ static struct platform_device at91sam9263_tcb_device = {
 
 static void __init at91_add_device_tc(void)
 {
-	/* this chip has one clock and irq for all three TC channels */
-	at91_clock_associate("tcb_clk", &at91sam9263_tcb_device.dev, "t0_clk");
 	platform_device_register(&at91sam9263_tcb_device);
 }
 #else
@@ -1171,12 +1165,10 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins)
 	case AT91SAM9263_ID_SSC0:
 		pdev = &at91sam9263_ssc0_device;
 		configure_ssc0_pins(pins);
-		at91_clock_associate("ssc0_clk", &pdev->dev, "pclk");
 		break;
 	case AT91SAM9263_ID_SSC1:
 		pdev = &at91sam9263_ssc1_device;
 		configure_ssc1_pins(pins);
-		at91_clock_associate("ssc1_clk", &pdev->dev, "pclk");
 		break;
 	default:
 		return;
@@ -1370,32 +1362,30 @@ struct platform_device *atmel_default_console_device;	/* the serial console devi
 void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 {
 	struct platform_device *pdev;
+	struct atmel_uart_data *pdata;
 
 	switch (id) {
 		case 0:		/* DBGU */
 			pdev = &at91sam9263_dbgu_device;
 			configure_dbgu_pins();
-			at91_clock_associate("mck", &pdev->dev, "usart");
 			break;
 		case AT91SAM9263_ID_US0:
 			pdev = &at91sam9263_uart0_device;
 			configure_usart0_pins(pins);
-			at91_clock_associate("usart0_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9263_ID_US1:
 			pdev = &at91sam9263_uart1_device;
 			configure_usart1_pins(pins);
-			at91_clock_associate("usart1_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9263_ID_US2:
 			pdev = &at91sam9263_uart2_device;
 			configure_usart2_pins(pins);
-			at91_clock_associate("usart2_clk", &pdev->dev, "usart");
 			break;
 		default:
 			return;
 	}
-	pdev->id = portnr;		/* update to mapped ID */
+	pdata = pdev->dev.platform_data;
+	pdata->num = portnr;		/* update to mapped ID */
 
 	if (portnr < ATMEL_MAX_UART)
 		at91_uarts[portnr] = pdev;
@@ -1403,8 +1393,10 @@ void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 
 void __init at91_set_serial_console(unsigned portnr)
 {
-	if (portnr < ATMEL_MAX_UART)
+	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
+		at91sam9263_set_console_clock(portnr);
+	}
 }
 
 void __init at91_add_device_serial(void)
diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c
index c67b47f1c0fd..2bb6ff9af1c7 100644
--- a/arch/arm/mach-at91/at91sam9g45.c
+++ b/arch/arm/mach-at91/at91sam9g45.c
@@ -184,22 +184,6 @@ static struct clk vdec_clk = {
 	.type		= CLK_TYPE_PERIPHERAL,
 };
 
-/* One additional fake clock for ohci */
-static struct clk ohci_clk = {
-	.name		= "ohci_clk",
-	.pmc_mask	= 0,
-	.type		= CLK_TYPE_PERIPHERAL,
-	.parent		= &uhphs_clk,
-};
-
-/* One additional fake clock for second TC block */
-static struct clk tcb1_clk = {
-	.name		= "tcb1_clk",
-	.pmc_mask	= 0,
-	.type		= CLK_TYPE_PERIPHERAL,
-	.parent		= &tcb0_clk,
-};
-
 static struct clk *periph_clocks[] __initdata = {
 	&pioA_clk,
 	&pioB_clk,
@@ -228,8 +212,30 @@ static struct clk *periph_clocks[] __initdata = {
 	&udphs_clk,
 	&mmc1_clk,
 	// irq0
-	&ohci_clk,
-	&tcb1_clk,
+};
+
+static struct clk_lookup periph_clocks_lookups[] = {
+	/* One additional fake clock for ohci */
+	CLKDEV_CON_ID("ohci_clk", &uhphs_clk),
+	CLKDEV_CON_DEV_ID("ehci_clk", "atmel-ehci.0", &uhphs_clk),
+	CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc.0", &utmi_clk),
+	CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc.0", &udphs_clk),
+	CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.0", &mmc0_clk),
+	CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.1", &mmc1_clk),
+	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.0", &spi0_clk),
+	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk),
+	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tcb0_clk),
+	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.1", &tcb0_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
+};
+
+static struct clk_lookup usart_clocks_lookups[] = {
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.0", &mck),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.1", &usart0_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.2", &usart1_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.3", &usart2_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.4", &usart3_clk),
 };
 
 /*
@@ -256,6 +262,11 @@ static void __init at91sam9g45_register_clocks(void)
 	for (i = 0; i < ARRAY_SIZE(periph_clocks); i++)
 		clk_register(periph_clocks[i]);
 
+	clkdev_add_table(periph_clocks_lookups,
+			 ARRAY_SIZE(periph_clocks_lookups));
+	clkdev_add_table(usart_clocks_lookups,
+			 ARRAY_SIZE(usart_clocks_lookups));
+
 	if (cpu_is_at91sam9m10() || cpu_is_at91sam9m11())
 		clk_register(&vdec_clk);
 
@@ -263,6 +274,18 @@ static void __init at91sam9g45_register_clocks(void)
 	clk_register(&pck1);
 }
 
+static struct clk_lookup console_clock_lookup;
+
+void __init at91sam9g45_set_console_clock(int id)
+{
+	if (id >= ARRAY_SIZE(usart_clocks_lookups))
+		return;
+
+	console_clock_lookup.con_id = "usart";
+	console_clock_lookup.clk = usart_clocks_lookups[id].clk;
+	clkdev_add(&console_clock_lookup);
+}
+
 /* --------------------------------------------------------------------
  *  GPIO
  * -------------------------------------------------------------------- */
@@ -306,11 +329,14 @@ static void at91sam9g45_poweroff(void)
  *  AT91SAM9G45 processor initialization
  * -------------------------------------------------------------------- */
 
-void __init at91sam9g45_initialize(unsigned long main_clock)
+void __init at91sam9g45_map_io(void)
 {
 	/* Map peripherals */
 	iotable_init(at91sam9g45_io_desc, ARRAY_SIZE(at91sam9g45_io_desc));
+}
 
+void __init at91sam9g45_initialize(unsigned long main_clock)
+{
 	at91_arch_reset = at91sam9g45_reset;
 	pm_power_off = at91sam9g45_poweroff;
 	at91_extern_irq = (1 << AT91SAM9G45_ID_IRQ0);
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index 5e9f8a4c38df..05674865bc21 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -180,7 +180,6 @@ void __init at91_add_device_usbh_ehci(struct at91_usbh_data *data)
 	}
 
 	usbh_ehci_data = *data;
-	at91_clock_associate("uhphs_clk", &at91_usbh_ehci_device.dev, "ehci_clk");
 	platform_device_register(&at91_usbh_ehci_device);
 }
 #else
@@ -266,10 +265,6 @@ void __init at91_add_device_usba(struct usba_platform_data *data)
 
 	/* Pullup pin is handled internally by USB device peripheral */
 
-	/* Clocks */
-	at91_clock_associate("utmi_clk", &at91_usba_udc_device.dev, "hclk");
-	at91_clock_associate("udphs_clk", &at91_usba_udc_device.dev, "pclk");
-
 	platform_device_register(&at91_usba_udc_device);
 }
 #else
@@ -478,7 +473,6 @@ void __init at91_add_device_mci(short mmc_id, struct mci_platform_data *data)
 		}
 
 		mmc0_data = *data;
-		at91_clock_associate("mci0_clk", &at91sam9g45_mmc0_device.dev, "mci_clk");
 		platform_device_register(&at91sam9g45_mmc0_device);
 
 	} else {			/* MCI1 */
@@ -504,7 +498,6 @@ void __init at91_add_device_mci(short mmc_id, struct mci_platform_data *data)
 		}
 
 		mmc1_data = *data;
-		at91_clock_associate("mci1_clk", &at91sam9g45_mmc1_device.dev, "mci_clk");
 		platform_device_register(&at91sam9g45_mmc1_device);
 
 	}
@@ -801,7 +794,6 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		at91_set_A_periph(AT91_PIN_PB1, 0);	/* SPI0_MOSI */
 		at91_set_A_periph(AT91_PIN_PB2, 0);	/* SPI0_SPCK */
 
-		at91_clock_associate("spi0_clk", &at91sam9g45_spi0_device.dev, "spi_clk");
 		platform_device_register(&at91sam9g45_spi0_device);
 	}
 	if (enable_spi1) {
@@ -809,7 +801,6 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		at91_set_A_periph(AT91_PIN_PB15, 0);	/* SPI1_MOSI */
 		at91_set_A_periph(AT91_PIN_PB16, 0);	/* SPI1_SPCK */
 
-		at91_clock_associate("spi1_clk", &at91sam9g45_spi1_device.dev, "spi_clk");
 		platform_device_register(&at91sam9g45_spi1_device);
 	}
 }
@@ -999,10 +990,7 @@ static struct platform_device at91sam9g45_tcb1_device = {
 
 static void __init at91_add_device_tc(void)
 {
-	/* this chip has one clock and irq for all six TC channels */
-	at91_clock_associate("tcb0_clk", &at91sam9g45_tcb0_device.dev, "t0_clk");
 	platform_device_register(&at91sam9g45_tcb0_device);
-	at91_clock_associate("tcb1_clk", &at91sam9g45_tcb1_device.dev, "t0_clk");
 	platform_device_register(&at91sam9g45_tcb1_device);
 }
 #else
@@ -1286,12 +1274,10 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins)
 	case AT91SAM9G45_ID_SSC0:
 		pdev = &at91sam9g45_ssc0_device;
 		configure_ssc0_pins(pins);
-		at91_clock_associate("ssc0_clk", &pdev->dev, "pclk");
 		break;
 	case AT91SAM9G45_ID_SSC1:
 		pdev = &at91sam9g45_ssc1_device;
 		configure_ssc1_pins(pins);
-		at91_clock_associate("ssc1_clk", &pdev->dev, "pclk");
 		break;
 	default:
 		return;
@@ -1527,37 +1513,34 @@ struct platform_device *atmel_default_console_device;	/* the serial console devi
 void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 {
 	struct platform_device *pdev;
+	struct atmel_uart_data *pdata;
 
 	switch (id) {
 		case 0:		/* DBGU */
 			pdev = &at91sam9g45_dbgu_device;
 			configure_dbgu_pins();
-			at91_clock_associate("mck", &pdev->dev, "usart");
 			break;
 		case AT91SAM9G45_ID_US0:
 			pdev = &at91sam9g45_uart0_device;
 			configure_usart0_pins(pins);
-			at91_clock_associate("usart0_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9G45_ID_US1:
 			pdev = &at91sam9g45_uart1_device;
 			configure_usart1_pins(pins);
-			at91_clock_associate("usart1_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9G45_ID_US2:
 			pdev = &at91sam9g45_uart2_device;
 			configure_usart2_pins(pins);
-			at91_clock_associate("usart2_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9G45_ID_US3:
 			pdev = &at91sam9g45_uart3_device;
 			configure_usart3_pins(pins);
-			at91_clock_associate("usart3_clk", &pdev->dev, "usart");
 			break;
 		default:
 			return;
 	}
-	pdev->id = portnr;		/* update to mapped ID */
+	pdata = pdev->dev.platform_data;
+	pdata->num = portnr;		/* update to mapped ID */
 
 	if (portnr < ATMEL_MAX_UART)
 		at91_uarts[portnr] = pdev;
@@ -1565,8 +1548,10 @@ void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 
 void __init at91_set_serial_console(unsigned portnr)
 {
-	if (portnr < ATMEL_MAX_UART)
+	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
+		at91sam9g45_set_console_clock(portnr);
+	}
 }
 
 void __init at91_add_device_serial(void)
diff --git a/arch/arm/mach-at91/at91sam9rl.c b/arch/arm/mach-at91/at91sam9rl.c
index 6a9d24e5ed8e..1a40f16b66c8 100644
--- a/arch/arm/mach-at91/at91sam9rl.c
+++ b/arch/arm/mach-at91/at91sam9rl.c
@@ -190,6 +190,24 @@ static struct clk *periph_clocks[] __initdata = {
 	// irq0
 };
 
+static struct clk_lookup periph_clocks_lookups[] = {
+	CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc.0", &utmi_clk),
+	CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc.0", &udphs_clk),
+	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk),
+	CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk),
+	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc2_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
+};
+
+static struct clk_lookup usart_clocks_lookups[] = {
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.0", &mck),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.1", &usart0_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.2", &usart1_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.3", &usart2_clk),
+	CLKDEV_CON_DEV_ID("usart", "atmel_usart.4", &usart3_clk),
+};
+
 /*
  * The two programmable clocks.
  * You must configure pin multiplexing to bring these signals out.
@@ -214,10 +232,27 @@ static void __init at91sam9rl_register_clocks(void)
 	for (i = 0; i < ARRAY_SIZE(periph_clocks); i++)
 		clk_register(periph_clocks[i]);
 
+	clkdev_add_table(periph_clocks_lookups,
+			 ARRAY_SIZE(periph_clocks_lookups));
+	clkdev_add_table(usart_clocks_lookups,
+			 ARRAY_SIZE(usart_clocks_lookups));
+
 	clk_register(&pck0);
 	clk_register(&pck1);
 }
 
+static struct clk_lookup console_clock_lookup;
+
+void __init at91sam9rl_set_console_clock(int id)
+{
+	if (id >= ARRAY_SIZE(usart_clocks_lookups))
+		return;
+
+	console_clock_lookup.con_id = "usart";
+	console_clock_lookup.clk = usart_clocks_lookups[id].clk;
+	clkdev_add(&console_clock_lookup);
+}
+
 /* --------------------------------------------------------------------
  *  GPIO
  * -------------------------------------------------------------------- */
@@ -252,7 +287,7 @@ static void at91sam9rl_poweroff(void)
  *  AT91SAM9RL processor initialization
  * -------------------------------------------------------------------- */
 
-void __init at91sam9rl_initialize(unsigned long main_clock)
+void __init at91sam9rl_map_io(void)
 {
 	unsigned long cidr, sram_size;
 
@@ -275,7 +310,10 @@ void __init at91sam9rl_initialize(unsigned long main_clock)
 
 	/* Map SRAM */
 	iotable_init(at91sam9rl_sram_desc, ARRAY_SIZE(at91sam9rl_sram_desc));
+}
 
+void __init at91sam9rl_initialize(unsigned long main_clock)
+{
 	at91_arch_reset = at91sam9_alt_reset;
 	pm_power_off = at91sam9rl_poweroff;
 	at91_extern_irq = (1 << AT91SAM9RL_ID_IRQ0);
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index c49262bddd85..c296045f2b6a 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -155,10 +155,6 @@ void __init at91_add_device_usba(struct usba_platform_data *data)
 
 	/* Pullup pin is handled internally by USB device peripheral */
 
-	/* Clocks */
-	at91_clock_associate("utmi_clk", &at91_usba_udc_device.dev, "hclk");
-	at91_clock_associate("udphs_clk", &at91_usba_udc_device.dev, "pclk");
-
 	platform_device_register(&at91_usba_udc_device);
 }
 #else
@@ -605,10 +601,6 @@ static struct platform_device at91sam9rl_tcb_device = {
 
 static void __init at91_add_device_tc(void)
 {
-	/* this chip has a separate clock and irq for each TC channel */
-	at91_clock_associate("tc0_clk", &at91sam9rl_tcb_device.dev, "t0_clk");
-	at91_clock_associate("tc1_clk", &at91sam9rl_tcb_device.dev, "t1_clk");
-	at91_clock_associate("tc2_clk", &at91sam9rl_tcb_device.dev, "t2_clk");
 	platform_device_register(&at91sam9rl_tcb_device);
 }
 #else
@@ -892,12 +884,10 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins)
 	case AT91SAM9RL_ID_SSC0:
 		pdev = &at91sam9rl_ssc0_device;
 		configure_ssc0_pins(pins);
-		at91_clock_associate("ssc0_clk", &pdev->dev, "pclk");
 		break;
 	case AT91SAM9RL_ID_SSC1:
 		pdev = &at91sam9rl_ssc1_device;
 		configure_ssc1_pins(pins);
-		at91_clock_associate("ssc1_clk", &pdev->dev, "pclk");
 		break;
 	default:
 		return;
@@ -1141,37 +1131,34 @@ struct platform_device *atmel_default_console_device;	/* the serial console devi
 void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 {
 	struct platform_device *pdev;
+	struct atmel_uart_data *pdata;
 
 	switch (id) {
 		case 0:		/* DBGU */
 			pdev = &at91sam9rl_dbgu_device;
 			configure_dbgu_pins();
-			at91_clock_associate("mck", &pdev->dev, "usart");
 			break;
 		case AT91SAM9RL_ID_US0:
 			pdev = &at91sam9rl_uart0_device;
 			configure_usart0_pins(pins);
-			at91_clock_associate("usart0_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9RL_ID_US1:
 			pdev = &at91sam9rl_uart1_device;
 			configure_usart1_pins(pins);
-			at91_clock_associate("usart1_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9RL_ID_US2:
 			pdev = &at91sam9rl_uart2_device;
 			configure_usart2_pins(pins);
-			at91_clock_associate("usart2_clk", &pdev->dev, "usart");
 			break;
 		case AT91SAM9RL_ID_US3:
 			pdev = &at91sam9rl_uart3_device;
 			configure_usart3_pins(pins);
-			at91_clock_associate("usart3_clk", &pdev->dev, "usart");
 			break;
 		default:
 			return;
 	}
-	pdev->id = portnr;		/* update to mapped ID */
+	pdata = pdev->dev.platform_data;
+	pdata->num = portnr;		/* update to mapped ID */
 
 	if (portnr < ATMEL_MAX_UART)
 		at91_uarts[portnr] = pdev;
@@ -1179,8 +1166,10 @@ void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
 
 void __init at91_set_serial_console(unsigned portnr)
 {
-	if (portnr < ATMEL_MAX_UART)
+	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
+		at91sam9rl_set_console_clock(portnr);
+	}
 }
 
 void __init at91_add_device_serial(void)
diff --git a/arch/arm/mach-at91/at91x40.c b/arch/arm/mach-at91/at91x40.c
index ad3ec85b2790..56ba3bd035ae 100644
--- a/arch/arm/mach-at91/at91x40.c
+++ b/arch/arm/mach-at91/at91x40.c
@@ -37,11 +37,6 @@ unsigned long clk_get_rate(struct clk *clk)
 	return AT91X40_MASTER_CLOCK;
 }
 
-struct clk *clk_get(struct device *dev, const char *id)
-{
-	return NULL;
-}
-
 void __init at91x40_initialize(unsigned long main_clock)
 {
 	at91_extern_irq = (1 << AT91X40_ID_IRQ0) | (1 << AT91X40_ID_IRQ1)
diff --git a/arch/arm/mach-at91/board-1arm.c b/arch/arm/mach-at91/board-1arm.c
index 8a3fc84847c1..ab1d463aa47d 100644
--- a/arch/arm/mach-at91/board-1arm.c
+++ b/arch/arm/mach-at91/board-1arm.c
@@ -35,14 +35,18 @@
 
 #include <mach/board.h>
 #include <mach/gpio.h>
+#include <mach/cpu.h>
 
 #include "generic.h"
 
 
-static void __init onearm_map_io(void)
+static void __init onearm_init_early(void)
 {
+	/* Set cpu type: PQFP */
+	at91rm9200_set_type(ARCH_REVISON_9200_PQFP);
+
 	/* Initialize processor: 18.432 MHz crystal */
-	at91rm9200_initialize(18432000, AT91RM9200_PQFP);
+	at91rm9200_initialize(18432000);
 
 	/* DBGU on ttyS0. (Rx & Tx only) */
 	at91_register_uart(0, 0, 0);
@@ -92,9 +96,9 @@ static void __init onearm_board_init(void)
 
 MACHINE_START(ONEARM, "Ajeco 1ARM single board computer")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= onearm_map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= onearm_init_early,
 	.init_irq	= onearm_init_irq,
 	.init_machine	= onearm_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-afeb-9260v1.c b/arch/arm/mach-at91/board-afeb-9260v1.c
index cba7f7771fee..a4924de48c36 100644
--- a/arch/arm/mach-at91/board-afeb-9260v1.c
+++ b/arch/arm/mach-at91/board-afeb-9260v1.c
@@ -48,7 +48,7 @@
 #include "generic.h"
 
 
-static void __init afeb9260_map_io(void)
+static void __init afeb9260_init_early(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
 	at91sam9260_initialize(18432000);
@@ -218,9 +218,9 @@ static void __init afeb9260_board_init(void)
 
 MACHINE_START(AFEB9260, "Custom afeb9260 board")
 	/* Maintainer: Sergey Lapin <slapin@ossfans.org> */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= afeb9260_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= afeb9260_init_early,
 	.init_irq	= afeb9260_init_irq,
 	.init_machine	= afeb9260_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-at572d940hf_ek.c b/arch/arm/mach-at91/board-at572d940hf_ek.c
deleted file mode 100644
index 3929f1c9e4e5..000000000000
--- a/arch/arm/mach-at91/board-at572d940hf_ek.c
+++ /dev/null
@@ -1,326 +0,0 @@
-/*
- * linux/arch/arm/mach-at91/board-at572d940hf_ek.c
- *
- * Copyright (C) 2008 Atmel Antonio R. Costa <costa.antonior@gmail.com>
- * Copyright (C) 2005 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
- */
-
-#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/ds1305.h>
-#include <linux/irq.h>
-#include <linux/mtd/physmap.h>
-
-#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/at91sam9_smc.h>
-
-#include "sam9_smc.h"
-#include "generic.h"
-
-
-static void __init eb_map_io(void)
-{
-	/* Initialize processor: 12.500 MHz crystal */
-	at572d940hf_initialize(12000000);
-
-	/* DBGU on ttyS0. (Rx & Tx only) */
-	at91_register_uart(0, 0, 0);
-
-	/* USART0 on ttyS1. (Rx & Tx only) */
-	at91_register_uart(AT572D940HF_ID_US0, 1, 0);
-
-	/* USART1 on ttyS2. (Rx & Tx only) */
-	at91_register_uart(AT572D940HF_ID_US1, 2, 0);
-
-	/* USART2 on ttyS3. (Tx & Rx only */
-	at91_register_uart(AT572D940HF_ID_US2, 3, 0);
-
-	/* set serial console to ttyS0 (ie, DBGU) */
-	at91_set_serial_console(0);
-}
-
-static void __init eb_init_irq(void)
-{
-	at572d940hf_init_interrupts(NULL);
-}
-
-
-/*
- * USB Host Port
- */
-static struct at91_usbh_data __initdata eb_usbh_data = {
-	.ports		= 2,
-};
-
-
-/*
- * USB Device Port
- */
-static struct at91_udc_data __initdata eb_udc_data = {
-	.vbus_pin	= 0,		/* no VBUS detection,UDC always on */
-	.pullup_pin	= 0,		/* pull-up driven by UDC */
-};
-
-
-/*
- * MCI (SD/MMC)
- */
-static struct at91_mmc_data __initdata eb_mmc_data = {
-	.wire4		= 1,
-/*	.det_pin	= ... not connected */
-/*	.wp_pin		= ... not connected */
-/*	.vcc_pin	= ... not connected */
-};
-
-
-/*
- * MACB Ethernet device
- */
-static struct at91_eth_data __initdata eb_eth_data = {
-	.phy_irq_pin	= AT91_PIN_PB25,
-	.is_rmii	= 1,
-};
-
-/*
- * NOR flash
- */
-
-static struct mtd_partition eb_nor_partitions[] = {
-	{
-		.name		= "Raw Environment",
-		.offset		= 0,
-		.size		= SZ_4M,
-		.mask_flags	= 0,
-	},
-	{
-		.name		= "OS FS",
-		.offset		= MTDPART_OFS_APPEND,
-		.size		= 3 * SZ_1M,
-		.mask_flags	= 0,
-	},
-	{
-		.name		= "APP FS",
-		.offset		= MTDPART_OFS_APPEND,
-		.size		= MTDPART_SIZ_FULL,
-		.mask_flags	= 0,
-	},
-};
-
-static void nor_flash_set_vpp(struct map_info* mi, int i) {
-};
-
-static struct physmap_flash_data nor_flash_data = {
-	.width		= 4,
-	.parts		= eb_nor_partitions,
-	.nr_parts	= ARRAY_SIZE(eb_nor_partitions),
-	.set_vpp	= nor_flash_set_vpp,
-};
-
-static struct resource nor_flash_resources[] = {
-	{
-		.start	= AT91_CHIPSELECT_0,
-		.end	= AT91_CHIPSELECT_0 + SZ_16M - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device nor_flash = {
-	.name		= "physmap-flash",
-	.id		= 0,
-	.dev		= {
-				.platform_data = &nor_flash_data,
-			},
-	.resource	= nor_flash_resources,
-	.num_resources	= ARRAY_SIZE(nor_flash_resources),
-};
-
-static struct sam9_smc_config __initdata eb_nor_smc_config = {
-	.ncs_read_setup		= 1,
-	.nrd_setup		= 1,
-	.ncs_write_setup	= 1,
-	.nwe_setup		= 1,
-
-	.ncs_read_pulse		= 7,
-	.nrd_pulse		= 7,
-	.ncs_write_pulse	= 7,
-	.nwe_pulse		= 7,
-
-	.read_cycle		= 9,
-	.write_cycle		= 9,
-
-	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_BAT_WRITE | AT91_SMC_DBW_32,
-	.tdf_cycles		= 1,
-};
-
-static void __init eb_add_device_nor(void)
-{
-	/* configure chip-select 0 (NOR) */
-	sam9_smc_configure(0, &eb_nor_smc_config);
-	platform_device_register(&nor_flash);
-}
-
-/*
- * NAND flash
- */
-static struct mtd_partition __initdata eb_nand_partition[] = {
-	{
-		.name	= "Partition 1",
-		.offset	= 0,
-		.size	= SZ_16M,
-	},
-	{
-		.name	= "Partition 2",
-		.offset = MTDPART_OFS_NXTBLK,
-		.size	= MTDPART_SIZ_FULL,
-	}
-};
-
-static struct mtd_partition * __init nand_partitions(int size, int *num_partitions)
-{
-	*num_partitions = ARRAY_SIZE(eb_nand_partition);
-	return eb_nand_partition;
-}
-
-static struct atmel_nand_data __initdata eb_nand_data = {
-	.ale		= 22,
-	.cle		= 21,
-/*	.det_pin	= ... not connected */
-/*	.rdy_pin	= AT91_PIN_PC16, */
-	.enable_pin	= AT91_PIN_PA15,
-	.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 eb_nand_smc_config = {
-	.ncs_read_setup		= 0,
-	.nrd_setup		= 0,
-	.ncs_write_setup	= 1,
-	.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		= 12,
-};
-
-static void __init eb_add_device_nand(void)
-{
-	/* setup bus-width (8 or 16) */
-	if (eb_nand_data.bus_width_16)
-		eb_nand_smc_config.mode |= AT91_SMC_DBW_16;
-	else
-		eb_nand_smc_config.mode |= AT91_SMC_DBW_8;
-
-	/* configure chip-select 3 (NAND) */
-	sam9_smc_configure(3, &eb_nand_smc_config);
-
-	at91_add_device_nand(&eb_nand_data);
-}
-
-
-/*
- * SPI devices
- */
-static struct resource rtc_resources[] = {
-	[0] = {
-		.start	= AT572D940HF_ID_IRQ1,
-		.end	= AT572D940HF_ID_IRQ1,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct ds1305_platform_data ds1306_data = {
-	.is_ds1306	= true,
-	.en_1hz		= false,
-};
-
-static struct spi_board_info eb_spi_devices[] = {
-	{	/* RTC Dallas DS1306 */
-		.modalias	= "rtc-ds1305",
-		.chip_select	= 3,
-		.mode		= SPI_CS_HIGH | SPI_CPOL | SPI_CPHA,
-		.max_speed_hz	= 500000,
-		.bus_num	= 0,
-		.irq		= AT572D940HF_ID_IRQ1,
-		.platform_data	= (void *) &ds1306_data,
-	},
-#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
-};
-
-static void __init eb_board_init(void)
-{
-	/* Serial */
-	at91_add_device_serial();
-	/* USB Host */
-	at91_add_device_usbh(&eb_usbh_data);
-	/* USB Device */
-	at91_add_device_udc(&eb_udc_data);
-	/* I2C */
-	at91_add_device_i2c(NULL, 0);
-	/* NOR */
-	eb_add_device_nor();
-	/* NAND */
-	eb_add_device_nand();
-	/* SPI */
-	at91_add_device_spi(eb_spi_devices, ARRAY_SIZE(eb_spi_devices));
-	/* MMC */
-	at91_add_device_mmc(0, &eb_mmc_data);
-	/* Ethernet */
-	at91_add_device_eth(&eb_eth_data);
-	/* mAgic */
-	at91_add_device_mAgic();
-}
-
-MACHINE_START(AT572D940HFEB, "Atmel AT91D940HF-EB")
-	/* Maintainer: Atmel <costa.antonior@gmail.com> */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
-	.timer		= &at91sam926x_timer,
-	.map_io		= eb_map_io,
-	.init_irq	= eb_init_irq,
-	.init_machine	= eb_board_init,
-MACHINE_END
diff --git a/arch/arm/mach-at91/board-cam60.c b/arch/arm/mach-at91/board-cam60.c
index b54e3e6fceb6..148fccb9a25a 100644
--- a/arch/arm/mach-at91/board-cam60.c
+++ b/arch/arm/mach-at91/board-cam60.c
@@ -45,7 +45,7 @@
 #include "generic.h"
 
 
-static void __init cam60_map_io(void)
+static void __init cam60_init_early(void)
 {
 	/* Initialize processor: 10 MHz crystal */
 	at91sam9260_initialize(10000000);
@@ -198,9 +198,9 @@ static void __init cam60_board_init(void)
 
 MACHINE_START(CAM60, "KwikByte CAM60")
 	/* Maintainer: KwikByte */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= cam60_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= cam60_init_early,
 	.init_irq	= cam60_init_irq,
 	.init_machine	= cam60_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-cap9adk.c b/arch/arm/mach-at91/board-cap9adk.c
index e7274440ead9..1904fdf87613 100644
--- a/arch/arm/mach-at91/board-cap9adk.c
+++ b/arch/arm/mach-at91/board-cap9adk.c
@@ -44,12 +44,13 @@
 #include <mach/gpio.h>
 #include <mach/at91cap9_matrix.h>
 #include <mach/at91sam9_smc.h>
+#include <mach/system_rev.h>
 
 #include "sam9_smc.h"
 #include "generic.h"
 
 
-static void __init cap9adk_map_io(void)
+static void __init cap9adk_init_early(void)
 {
 	/* Initialize processor: 12 MHz crystal */
 	at91cap9_initialize(12000000);
@@ -187,11 +188,6 @@ static struct atmel_nand_data __initdata cap9adk_nand_data = {
 //	.rdy_pin	= ... not connected
 	.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 cap9adk_nand_smc_config = {
@@ -219,6 +215,7 @@ static void __init cap9adk_add_device_nand(void)
 	csa = at91_sys_read(AT91_MATRIX_EBICSA);
 	at91_sys_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_EBI_VDDIOMSEL_3_3V);
 
+	cap9adk_nand_data.bus_width_16 = !board_have_nand_8bit();
 	/* setup bus-width (8 or 16) */
 	if (cap9adk_nand_data.bus_width_16)
 		cap9adk_nand_smc_config.mode |= AT91_SMC_DBW_16;
@@ -399,9 +396,9 @@ static void __init cap9adk_board_init(void)
 
 MACHINE_START(AT91CAP9ADK, "Atmel AT91CAP9A-DK")
 	/* Maintainer: Stelian Pop <stelian.pop@leadtechdesign.com> */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= cap9adk_map_io,
+	.map_io		= at91cap9_map_io,
+	.init_early	= cap9adk_init_early,
 	.init_irq	= cap9adk_init_irq,
 	.init_machine	= cap9adk_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-carmeva.c b/arch/arm/mach-at91/board-carmeva.c
index 295e1e77fa60..f36b18687494 100644
--- a/arch/arm/mach-at91/board-carmeva.c
+++ b/arch/arm/mach-at91/board-carmeva.c
@@ -40,10 +40,10 @@
 #include "generic.h"
 
 
-static void __init carmeva_map_io(void)
+static void __init carmeva_init_early(void)
 {
 	/* Initialize processor: 20.000 MHz crystal */
-	at91rm9200_initialize(20000000, AT91RM9200_BGA);
+	at91rm9200_initialize(20000000);
 
 	/* DBGU on ttyS0. (Rx & Tx only) */
 	at91_register_uart(0, 0, 0);
@@ -162,9 +162,9 @@ static void __init carmeva_board_init(void)
 
 MACHINE_START(CARMEVA, "Carmeva")
 	/* Maintainer: Conitec Datasystems */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= carmeva_map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= carmeva_init_early,
 	.init_irq	= carmeva_init_irq,
 	.init_machine	= carmeva_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-cpu9krea.c b/arch/arm/mach-at91/board-cpu9krea.c
index 3838594578f3..980511084fe4 100644
--- a/arch/arm/mach-at91/board-cpu9krea.c
+++ b/arch/arm/mach-at91/board-cpu9krea.c
@@ -47,7 +47,7 @@
 #include "sam9_smc.h"
 #include "generic.h"
 
-static void __init cpu9krea_map_io(void)
+static void __init cpu9krea_init_early(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
 	at91sam9260_initialize(18432000);
@@ -375,9 +375,9 @@ MACHINE_START(CPUAT9260, "Eukrea CPU9260")
 MACHINE_START(CPUAT9G20, "Eukrea CPU9G20")
 #endif
 	/* Maintainer: Eric Benard - EUKREA Electromatique */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= cpu9krea_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= cpu9krea_init_early,
 	.init_irq	= cpu9krea_init_irq,
 	.init_machine	= cpu9krea_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-cpuat91.c b/arch/arm/mach-at91/board-cpuat91.c
index 2f4dd8cdd484..6daabe3907a1 100644
--- a/arch/arm/mach-at91/board-cpuat91.c
+++ b/arch/arm/mach-at91/board-cpuat91.c
@@ -38,6 +38,7 @@
 #include <mach/board.h>
 #include <mach/gpio.h>
 #include <mach/at91rm9200_mc.h>
+#include <mach/cpu.h>
 
 #include "generic.h"
 
@@ -50,10 +51,13 @@ static struct gpio_led cpuat91_leds[] = {
 	},
 };
 
-static void __init cpuat91_map_io(void)
+static void __init cpuat91_init_early(void)
 {
+	/* Set cpu type: PQFP */
+	at91rm9200_set_type(ARCH_REVISON_9200_PQFP);
+
 	/* Initialize processor: 18.432 MHz crystal */
-	at91rm9200_initialize(18432000, AT91RM9200_PQFP);
+	at91rm9200_initialize(18432000);
 
 	/* DBGU on ttyS0. (Rx & Tx only) */
 	at91_register_uart(0, 0, 0);
@@ -175,9 +179,9 @@ static void __init cpuat91_board_init(void)
 
 MACHINE_START(CPUAT91, "Eukrea")
 	/* Maintainer: Eric Benard - EUKREA Electromatique */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= cpuat91_map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= cpuat91_init_early,
 	.init_irq	= cpuat91_init_irq,
 	.init_machine	= cpuat91_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-csb337.c b/arch/arm/mach-at91/board-csb337.c
index 464839dc39bd..d98bcec1dfe0 100644
--- a/arch/arm/mach-at91/board-csb337.c
+++ b/arch/arm/mach-at91/board-csb337.c
@@ -43,10 +43,10 @@
 #include "generic.h"
 
 
-static void __init csb337_map_io(void)
+static void __init csb337_init_early(void)
 {
 	/* Initialize processor: 3.6864 MHz crystal */
-	at91rm9200_initialize(3686400, AT91RM9200_BGA);
+	at91rm9200_initialize(3686400);
 
 	/* Setup the LEDs */
 	at91_init_leds(AT91_PIN_PB0, AT91_PIN_PB1);
@@ -257,9 +257,9 @@ static void __init csb337_board_init(void)
 
 MACHINE_START(CSB337, "Cogent CSB337")
 	/* Maintainer: Bill Gatliff */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= csb337_map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= csb337_init_early,
 	.init_irq	= csb337_init_irq,
 	.init_machine	= csb337_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-csb637.c b/arch/arm/mach-at91/board-csb637.c
index 431688c61412..019aab4e20b0 100644
--- a/arch/arm/mach-at91/board-csb637.c
+++ b/arch/arm/mach-at91/board-csb637.c
@@ -40,10 +40,10 @@
 #include "generic.h"
 
 
-static void __init csb637_map_io(void)
+static void __init csb637_init_early(void)
 {
 	/* Initialize processor: 3.6864 MHz crystal */
-	at91rm9200_initialize(3686400, AT91RM9200_BGA);
+	at91rm9200_initialize(3686400);
 
 	/* DBGU on ttyS0. (Rx & Tx only) */
 	at91_register_uart(0, 0, 0);
@@ -138,9 +138,9 @@ static void __init csb637_board_init(void)
 
 MACHINE_START(CSB637, "Cogent CSB637")
 	/* Maintainer: Bill Gatliff */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= csb637_map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= csb637_init_early,
 	.init_irq	= csb637_init_irq,
 	.init_machine	= csb637_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-eb01.c b/arch/arm/mach-at91/board-eb01.c
index d8df59a3426d..d2023f27c652 100644
--- a/arch/arm/mach-at91/board-eb01.c
+++ b/arch/arm/mach-at91/board-eb01.c
@@ -35,7 +35,7 @@ static void __init at91eb01_init_irq(void)
 	at91x40_init_interrupts(NULL);
 }
 
-static void __init at91eb01_map_io(void)
+static void __init at91eb01_init_early(void)
 {
 	at91x40_initialize(40000000);
 }
@@ -43,7 +43,7 @@ static void __init at91eb01_map_io(void)
 MACHINE_START(AT91EB01, "Atmel AT91 EB01")
 	/* Maintainer: Greg Ungerer <gerg@snapgear.com> */
 	.timer		= &at91x40_timer,
+	.init_early	= at91eb01_init_early,
 	.init_irq	= at91eb01_init_irq,
-	.map_io		= at91eb01_map_io,
 MACHINE_END
 
diff --git a/arch/arm/mach-at91/board-eb9200.c b/arch/arm/mach-at91/board-eb9200.c
index 6cf6566ae346..e9484535cbc8 100644
--- a/arch/arm/mach-at91/board-eb9200.c
+++ b/arch/arm/mach-at91/board-eb9200.c
@@ -40,10 +40,10 @@
 #include "generic.h"
 
 
-static void __init eb9200_map_io(void)
+static void __init eb9200_init_early(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
-	at91rm9200_initialize(18432000, AT91RM9200_BGA);
+	at91rm9200_initialize(18432000);
 
 	/* DBGU on ttyS0. (Rx & Tx only) */
 	at91_register_uart(0, 0, 0);
@@ -120,9 +120,9 @@ static void __init eb9200_board_init(void)
 }
 
 MACHINE_START(ATEB9200, "Embest ATEB9200")
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= eb9200_map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= eb9200_init_early,
 	.init_irq	= eb9200_init_irq,
 	.init_machine	= eb9200_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-ecbat91.c b/arch/arm/mach-at91/board-ecbat91.c
index de2fd04e7c8a..a6f57faa10a7 100644
--- a/arch/arm/mach-at91/board-ecbat91.c
+++ b/arch/arm/mach-at91/board-ecbat91.c
@@ -38,14 +38,18 @@
 
 #include <mach/board.h>
 #include <mach/gpio.h>
+#include <mach/cpu.h>
 
 #include "generic.h"
 
 
-static void __init ecb_at91map_io(void)
+static void __init ecb_at91init_early(void)
 {
+	/* Set cpu type: PQFP */
+	at91rm9200_set_type(ARCH_REVISON_9200_PQFP);
+
 	/* Initialize processor: 18.432 MHz crystal */
-	at91rm9200_initialize(18432000, AT91RM9200_PQFP);
+	at91rm9200_initialize(18432000);
 
 	/* Setup the LEDs */
 	at91_init_leds(AT91_PIN_PC7, AT91_PIN_PC7);
@@ -168,9 +172,9 @@ static void __init ecb_at91board_init(void)
 
 MACHINE_START(ECBAT91, "emQbit's ECB_AT91")
 	/* Maintainer: emQbit.com */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= ecb_at91map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= ecb_at91init_early,
 	.init_irq	= ecb_at91init_irq,
 	.init_machine	= ecb_at91board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-eco920.c b/arch/arm/mach-at91/board-eco920.c
index a158a0ce458f..bfc0062d1483 100644
--- a/arch/arm/mach-at91/board-eco920.c
+++ b/arch/arm/mach-at91/board-eco920.c
@@ -26,11 +26,16 @@
 
 #include <mach/board.h>
 #include <mach/at91rm9200_mc.h>
+#include <mach/cpu.h>
+
 #include "generic.h"
 
-static void __init eco920_map_io(void)
+static void __init eco920_init_early(void)
 {
-	at91rm9200_initialize(18432000, AT91RM9200_PQFP);
+	/* Set cpu type: PQFP */
+	at91rm9200_set_type(ARCH_REVISON_9200_PQFP);
+
+	at91rm9200_initialize(18432000);
 
 	/* Setup the LEDs */
 	at91_init_leds(AT91_PIN_PB0, AT91_PIN_PB1);
@@ -86,21 +91,6 @@ static struct platform_device eco920_flash = {
 	.num_resources  = 1,
 };
 
-static struct resource at91_beeper_resources[] = {
-	[0] = {
-		.start          = AT91RM9200_BASE_TC3,
-		.end            = AT91RM9200_BASE_TC3 + 0x39,
-		.flags          = IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device at91_beeper = {
-	.name           = "at91_beeper",
-	.id             = 0,
-	.resource       = at91_beeper_resources,
-	.num_resources  = ARRAY_SIZE(at91_beeper_resources),
-};
-
 static struct spi_board_info eco920_spi_devices[] = {
 	{	/* CAN controller */
 		.modalias	= "tlv5638",
@@ -139,18 +129,14 @@ static void __init eco920_board_init(void)
 		AT91_SMC_TDF_(1)	/* float time */
 	);
 
-	at91_clock_associate("tc3_clk", &at91_beeper.dev, "at91_beeper");
-	at91_set_B_periph(AT91_PIN_PB6, 0);
-	platform_device_register(&at91_beeper);
-
 	at91_add_device_spi(eco920_spi_devices, ARRAY_SIZE(eco920_spi_devices));
 }
 
 MACHINE_START(ECO920, "eco920")
 	/* Maintainer: Sascha Hauer */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= eco920_map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= eco920_init_early,
 	.init_irq	= eco920_init_irq,
 	.init_machine	= eco920_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-flexibity.c b/arch/arm/mach-at91/board-flexibity.c
index c8a62dc8fa65..466c063b8d21 100644
--- a/arch/arm/mach-at91/board-flexibity.c
+++ b/arch/arm/mach-at91/board-flexibity.c
@@ -37,7 +37,7 @@
 
 #include "generic.h"
 
-static void __init flexibity_map_io(void)
+static void __init flexibity_init_early(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
 	at91sam9260_initialize(18432000);
@@ -154,9 +154,9 @@ static void __init flexibity_board_init(void)
 
 MACHINE_START(FLEXIBITY, "Flexibity Connect")
 	/* Maintainer: Maxim Osipov */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= flexibity_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= flexibity_init_early,
 	.init_irq	= flexibity_init_irq,
 	.init_machine	= flexibity_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-foxg20.c b/arch/arm/mach-at91/board-foxg20.c
index dfc7dfe738e4..e2d1dc9eff45 100644
--- a/arch/arm/mach-at91/board-foxg20.c
+++ b/arch/arm/mach-at91/board-foxg20.c
@@ -57,7 +57,7 @@
  */
 
 
-static void __init foxg20_map_io(void)
+static void __init foxg20_init_early(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
 	at91sam9260_initialize(18432000);
@@ -266,9 +266,9 @@ static void __init foxg20_board_init(void)
 
 MACHINE_START(ACMENETUSFOXG20, "Acme Systems srl FOX Board G20")
 	/* Maintainer: Sergio Tanzilli */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= foxg20_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= foxg20_init_early,
 	.init_irq	= foxg20_init_irq,
 	.init_machine	= foxg20_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-gsia18s.c b/arch/arm/mach-at91/board-gsia18s.c
index bc28136ee249..1d4f36b3cb27 100644
--- a/arch/arm/mach-at91/board-gsia18s.c
+++ b/arch/arm/mach-at91/board-gsia18s.c
@@ -38,9 +38,9 @@
 #include "sam9_smc.h"
 #include "generic.h"
 
-static void __init gsia18s_map_io(void)
+static void __init gsia18s_init_early(void)
 {
-	stamp9g20_map_io();
+	stamp9g20_init_early();
 
 	/*
 	 * USART0 on ttyS1 (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI).
@@ -576,9 +576,9 @@ static void __init gsia18s_board_init(void)
 }
 
 MACHINE_START(GSIA18S, "GS_IA18_S")
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= gsia18s_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= gsia18s_init_early,
 	.init_irq	= init_irq,
 	.init_machine	= gsia18s_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-kafa.c b/arch/arm/mach-at91/board-kafa.c
index d2e1f4ec1fcc..9b003ff744ba 100644
--- a/arch/arm/mach-at91/board-kafa.c
+++ b/arch/arm/mach-at91/board-kafa.c
@@ -35,14 +35,18 @@
 
 #include <mach/board.h>
 #include <mach/gpio.h>
+#include <mach/cpu.h>
 
 #include "generic.h"
 
 
-static void __init kafa_map_io(void)
+static void __init kafa_init_early(void)
 {
+	/* Set cpu type: PQFP */
+	at91rm9200_set_type(ARCH_REVISON_9200_PQFP);
+
 	/* Initialize processor: 18.432 MHz crystal */
-	at91rm9200_initialize(18432000, AT91RM9200_PQFP);
+	at91rm9200_initialize(18432000);
 
 	/* Set up the LEDs */
 	at91_init_leds(AT91_PIN_PB4, AT91_PIN_PB4);
@@ -94,9 +98,9 @@ static void __init kafa_board_init(void)
 
 MACHINE_START(KAFA, "Sperry-Sun KAFA")
 	/* Maintainer: Sergei Sharonov */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= kafa_map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= kafa_init_early,
 	.init_irq	= kafa_init_irq,
 	.init_machine	= kafa_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-kb9202.c b/arch/arm/mach-at91/board-kb9202.c
index a13d2063faff..a813a74b65f9 100644
--- a/arch/arm/mach-at91/board-kb9202.c
+++ b/arch/arm/mach-at91/board-kb9202.c
@@ -36,16 +36,19 @@
 
 #include <mach/board.h>
 #include <mach/gpio.h>
-
+#include <mach/cpu.h>
 #include <mach/at91rm9200_mc.h>
 
 #include "generic.h"
 
 
-static void __init kb9202_map_io(void)
+static void __init kb9202_init_early(void)
 {
+	/* Set cpu type: PQFP */
+	at91rm9200_set_type(ARCH_REVISON_9200_PQFP);
+
 	/* Initialize processor: 10 MHz crystal */
-	at91rm9200_initialize(10000000, AT91RM9200_PQFP);
+	at91rm9200_initialize(10000000);
 
 	/* Set up the LEDs */
 	at91_init_leds(AT91_PIN_PC19, AT91_PIN_PC18);
@@ -136,9 +139,9 @@ static void __init kb9202_board_init(void)
 
 MACHINE_START(KB9200, "KB920x")
 	/* Maintainer: KwikByte, Inc. */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= kb9202_map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= kb9202_init_early,
 	.init_irq	= kb9202_init_irq,
 	.init_machine	= kb9202_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-neocore926.c b/arch/arm/mach-at91/board-neocore926.c
index fe5f1d47e6e2..961e805db68c 100644
--- a/arch/arm/mach-at91/board-neocore926.c
+++ b/arch/arm/mach-at91/board-neocore926.c
@@ -51,7 +51,7 @@
 #include "generic.h"
 
 
-static void __init neocore926_map_io(void)
+static void __init neocore926_init_early(void)
 {
 	/* Initialize processor: 20 MHz crystal */
 	at91sam9263_initialize(20000000);
@@ -387,9 +387,9 @@ static void __init neocore926_board_init(void)
 
 MACHINE_START(NEOCORE926, "ADENEO NEOCORE 926")
 	/* Maintainer: ADENEO */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= neocore926_map_io,
+	.map_io		= at91sam9263_map_io,
+	.init_early	= neocore926_init_early,
 	.init_irq	= neocore926_init_irq,
 	.init_machine	= neocore926_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-pcontrol-g20.c b/arch/arm/mach-at91/board-pcontrol-g20.c
index feb65787c30b..21a21af25878 100644
--- a/arch/arm/mach-at91/board-pcontrol-g20.c
+++ b/arch/arm/mach-at91/board-pcontrol-g20.c
@@ -37,9 +37,9 @@
 #include "generic.h"
 
 
-static void __init pcontrol_g20_map_io(void)
+static void __init pcontrol_g20_init_early(void)
 {
-	stamp9g20_map_io();
+	stamp9g20_init_early();
 
 	/* USART0 on ttyS1. (Rx, Tx, CTS, RTS) piggyback  A2 */
 	at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS
@@ -222,9 +222,9 @@ static void __init pcontrol_g20_board_init(void)
 
 MACHINE_START(PCONTROL_G20, "PControl G20")
 	/* Maintainer: pgsellmann@portner-elektronik.at */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= pcontrol_g20_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= pcontrol_g20_init_early,
 	.init_irq	= init_irq,
 	.init_machine	= pcontrol_g20_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-picotux200.c b/arch/arm/mach-at91/board-picotux200.c
index 55dad3a46547..756cc2a745dd 100644
--- a/arch/arm/mach-at91/board-picotux200.c
+++ b/arch/arm/mach-at91/board-picotux200.c
@@ -43,10 +43,10 @@
 #include "generic.h"
 
 
-static void __init picotux200_map_io(void)
+static void __init picotux200_init_early(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
-	at91rm9200_initialize(18432000, AT91RM9200_BGA);
+	at91rm9200_initialize(18432000);
 
 	/* DBGU on ttyS0. (Rx & Tx only) */
 	at91_register_uart(0, 0, 0);
@@ -123,9 +123,9 @@ static void __init picotux200_board_init(void)
 
 MACHINE_START(PICOTUX2XX, "picotux 200")
 	/* Maintainer: Kleinhenz Elektronik GmbH */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= picotux200_map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= picotux200_init_early,
 	.init_irq	= picotux200_init_irq,
 	.init_machine	= picotux200_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 69d15a875b66..d1a6001b0bd8 100644
--- a/arch/arm/mach-at91/board-qil-a9260.c
+++ b/arch/arm/mach-at91/board-qil-a9260.c
@@ -48,7 +48,7 @@
 #include "generic.h"
 
 
-static void __init ek_map_io(void)
+static void __init ek_init_early(void)
 {
 	/* Initialize processor: 12.000 MHz crystal */
 	at91sam9260_initialize(12000000);
@@ -268,9 +268,9 @@ static void __init ek_board_init(void)
 
 MACHINE_START(QIL_A9260, "CALAO QIL_A9260")
 	/* Maintainer: calao-systems */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= ek_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= ek_init_early,
 	.init_irq	= ek_init_irq,
 	.init_machine	= ek_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-rm9200dk.c b/arch/arm/mach-at91/board-rm9200dk.c
index 4c1047c8200d..aef9627710b0 100644
--- a/arch/arm/mach-at91/board-rm9200dk.c
+++ b/arch/arm/mach-at91/board-rm9200dk.c
@@ -45,10 +45,10 @@
 #include "generic.h"
 
 
-static void __init dk_map_io(void)
+static void __init dk_init_early(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
-	at91rm9200_initialize(18432000, AT91RM9200_BGA);
+	at91rm9200_initialize(18432000);
 
 	/* Setup the LEDs */
 	at91_init_leds(AT91_PIN_PB2, AT91_PIN_PB2);
@@ -227,9 +227,9 @@ static void __init dk_board_init(void)
 
 MACHINE_START(AT91RM9200DK, "Atmel AT91RM9200-DK")
 	/* Maintainer: SAN People/Atmel */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= dk_map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= dk_init_early,
 	.init_irq	= dk_init_irq,
 	.init_machine	= dk_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-rm9200ek.c b/arch/arm/mach-at91/board-rm9200ek.c
index 9df1be8818c0..015a02183080 100644
--- a/arch/arm/mach-at91/board-rm9200ek.c
+++ b/arch/arm/mach-at91/board-rm9200ek.c
@@ -45,10 +45,10 @@
 #include "generic.h"
 
 
-static void __init ek_map_io(void)
+static void __init ek_init_early(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
-	at91rm9200_initialize(18432000, AT91RM9200_BGA);
+	at91rm9200_initialize(18432000);
 
 	/* Setup the LEDs */
 	at91_init_leds(AT91_PIN_PB1, AT91_PIN_PB2);
@@ -193,9 +193,9 @@ static void __init ek_board_init(void)
 
 MACHINE_START(AT91RM9200EK, "Atmel AT91RM9200-EK")
 	/* Maintainer: SAN People/Atmel */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= ek_map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= ek_init_early,
 	.init_irq	= ek_init_irq,
 	.init_machine	= ek_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-sam9-l9260.c b/arch/arm/mach-at91/board-sam9-l9260.c
index 25a26beaa728..aaf1bf0989b3 100644
--- a/arch/arm/mach-at91/board-sam9-l9260.c
+++ b/arch/arm/mach-at91/board-sam9-l9260.c
@@ -44,7 +44,7 @@
 #include "generic.h"
 
 
-static void __init ek_map_io(void)
+static void __init ek_init_early(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
 	at91sam9260_initialize(18432000);
@@ -212,9 +212,9 @@ static void __init ek_board_init(void)
 
 MACHINE_START(SAM9_L9260, "Olimex SAM9-L9260")
 	/* Maintainer: Olimex */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= ek_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= ek_init_early,
 	.init_irq	= ek_init_irq,
 	.init_machine	= ek_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-sam9260ek.c b/arch/arm/mach-at91/board-sam9260ek.c
index de1816e0e1d9..d600dc123227 100644
--- a/arch/arm/mach-at91/board-sam9260ek.c
+++ b/arch/arm/mach-at91/board-sam9260ek.c
@@ -44,12 +44,13 @@
 #include <mach/gpio.h>
 #include <mach/at91sam9_smc.h>
 #include <mach/at91_shdwc.h>
+#include <mach/system_rev.h>
 
 #include "sam9_smc.h"
 #include "generic.h"
 
 
-static void __init ek_map_io(void)
+static void __init ek_init_early(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
 	at91sam9260_initialize(18432000);
@@ -191,11 +192,6 @@ 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 = {
@@ -218,6 +214,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
+	ek_nand_data.bus_width_16 = !board_have_nand_8bit();
 	/* setup bus-width (8 or 16) */
 	if (ek_nand_data.bus_width_16)
 		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
@@ -356,9 +353,9 @@ static void __init ek_board_init(void)
 
 MACHINE_START(AT91SAM9260EK, "Atmel AT91SAM9260-EK")
 	/* Maintainer: Atmel */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= ek_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= ek_init_early,
 	.init_irq	= ek_init_irq,
 	.init_machine	= ek_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-sam9261ek.c b/arch/arm/mach-at91/board-sam9261ek.c
index 14acc901e24c..f897f84d43dc 100644
--- a/arch/arm/mach-at91/board-sam9261ek.c
+++ b/arch/arm/mach-at91/board-sam9261ek.c
@@ -48,12 +48,13 @@
 #include <mach/gpio.h>
 #include <mach/at91sam9_smc.h>
 #include <mach/at91_shdwc.h>
+#include <mach/system_rev.h>
 
 #include "sam9_smc.h"
 #include "generic.h"
 
 
-static void __init ek_map_io(void)
+static void __init ek_init_early(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
 	at91sam9261_initialize(18432000);
@@ -197,11 +198,6 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.rdy_pin	= AT91_PIN_PC15,
 	.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 = {
@@ -224,6 +220,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
+	ek_nand_data.bus_width_16 = !board_have_nand_8bit();
 	/* setup bus-width (8 or 16) */
 	if (ek_nand_data.bus_width_16)
 		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
@@ -623,9 +620,9 @@ MACHINE_START(AT91SAM9261EK, "Atmel AT91SAM9261-EK")
 MACHINE_START(AT91SAM9G10EK, "Atmel AT91SAM9G10-EK")
 #endif
 	/* Maintainer: Atmel */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= ek_map_io,
+	.map_io		= at91sam9261_map_io,
+	.init_early	= ek_init_early,
 	.init_irq	= ek_init_irq,
 	.init_machine	= ek_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-sam9263ek.c b/arch/arm/mach-at91/board-sam9263ek.c
index bfe490df58be..605b26f40a4c 100644
--- a/arch/arm/mach-at91/board-sam9263ek.c
+++ b/arch/arm/mach-at91/board-sam9263ek.c
@@ -47,12 +47,13 @@
 #include <mach/gpio.h>
 #include <mach/at91sam9_smc.h>
 #include <mach/at91_shdwc.h>
+#include <mach/system_rev.h>
 
 #include "sam9_smc.h"
 #include "generic.h"
 
 
-static void __init ek_map_io(void)
+static void __init ek_init_early(void)
 {
 	/* Initialize processor: 16.367 MHz crystal */
 	at91sam9263_initialize(16367660);
@@ -198,11 +199,6 @@ 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 = {
@@ -225,6 +221,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
+	ek_nand_data.bus_width_16 = !board_have_nand_8bit();
 	/* setup bus-width (8 or 16) */
 	if (ek_nand_data.bus_width_16)
 		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
@@ -454,9 +451,9 @@ static void __init ek_board_init(void)
 
 MACHINE_START(AT91SAM9263EK, "Atmel AT91SAM9263-EK")
 	/* Maintainer: Atmel */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= ek_map_io,
+	.map_io		= at91sam9263_map_io,
+	.init_early	= ek_init_early,
 	.init_irq	= ek_init_irq,
 	.init_machine	= ek_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-sam9g20ek.c b/arch/arm/mach-at91/board-sam9g20ek.c
index ca8198b3c168..7624cf0d006b 100644
--- a/arch/arm/mach-at91/board-sam9g20ek.c
+++ b/arch/arm/mach-at91/board-sam9g20ek.c
@@ -43,6 +43,7 @@
 #include <mach/board.h>
 #include <mach/gpio.h>
 #include <mach/at91sam9_smc.h>
+#include <mach/system_rev.h>
 
 #include "sam9_smc.h"
 #include "generic.h"
@@ -60,7 +61,7 @@ static int inline ek_have_2mmc(void)
 }
 
 
-static void __init ek_map_io(void)
+static void __init ek_init_early(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
 	at91sam9260_initialize(18432000);
@@ -175,11 +176,6 @@ 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 = {
@@ -202,6 +198,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
+	ek_nand_data.bus_width_16 = !board_have_nand_8bit();
 	/* setup bus-width (8 or 16) */
 	if (ek_nand_data.bus_width_16)
 		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
@@ -406,18 +403,18 @@ static void __init ek_board_init(void)
 
 MACHINE_START(AT91SAM9G20EK, "Atmel AT91SAM9G20-EK")
 	/* Maintainer: Atmel */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= ek_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= ek_init_early,
 	.init_irq	= ek_init_irq,
 	.init_machine	= ek_board_init,
 MACHINE_END
 
 MACHINE_START(AT91SAM9G20EK_2MMC, "Atmel AT91SAM9G20-EK 2 MMC Slot Mod")
 	/* Maintainer: Atmel */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= ek_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= ek_init_early,
 	.init_irq	= ek_init_irq,
 	.init_machine	= ek_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-sam9m10g45ek.c b/arch/arm/mach-at91/board-sam9m10g45ek.c
index 6c999dbd2bcf..063c95d0e8f0 100644
--- a/arch/arm/mach-at91/board-sam9m10g45ek.c
+++ b/arch/arm/mach-at91/board-sam9m10g45ek.c
@@ -41,12 +41,13 @@
 #include <mach/gpio.h>
 #include <mach/at91sam9_smc.h>
 #include <mach/at91_shdwc.h>
+#include <mach/system_rev.h>
 
 #include "sam9_smc.h"
 #include "generic.h"
 
 
-static void __init ek_map_io(void)
+static void __init ek_init_early(void)
 {
 	/* Initialize processor: 12.000 MHz crystal */
 	at91sam9g45_initialize(12000000);
@@ -155,11 +156,6 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.rdy_pin	= AT91_PIN_PC8,
 	.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 = {
@@ -182,6 +178,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
+	ek_nand_data.bus_width_16 = !board_have_nand_8bit();
 	/* setup bus-width (8 or 16) */
 	if (ek_nand_data.bus_width_16)
 		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
@@ -424,9 +421,9 @@ static void __init ek_board_init(void)
 
 MACHINE_START(AT91SAM9M10G45EK, "Atmel AT91SAM9M10G45-EK")
 	/* Maintainer: Atmel */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= ek_map_io,
+	.map_io		= at91sam9g45_map_io,
+	.init_early	= ek_init_early,
 	.init_irq	= ek_init_irq,
 	.init_machine	= ek_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-sam9rlek.c b/arch/arm/mach-at91/board-sam9rlek.c
index 3bf3408e94c1..effb399a80a6 100644
--- a/arch/arm/mach-at91/board-sam9rlek.c
+++ b/arch/arm/mach-at91/board-sam9rlek.c
@@ -38,7 +38,7 @@
 #include "generic.h"
 
 
-static void __init ek_map_io(void)
+static void __init ek_init_early(void)
 {
 	/* Initialize processor: 12.000 MHz crystal */
 	at91sam9rl_initialize(12000000);
@@ -329,9 +329,9 @@ static void __init ek_board_init(void)
 
 MACHINE_START(AT91SAM9RLEK, "Atmel AT91SAM9RL-EK")
 	/* Maintainer: Atmel */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= ek_map_io,
+	.map_io		= at91sam9rl_map_io,
+	.init_early	= ek_init_early,
 	.init_irq	= ek_init_irq,
 	.init_machine	= ek_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-snapper9260.c b/arch/arm/mach-at91/board-snapper9260.c
index 17f7d9b32142..3eb0a1153cc8 100644
--- a/arch/arm/mach-at91/board-snapper9260.c
+++ b/arch/arm/mach-at91/board-snapper9260.c
@@ -40,7 +40,7 @@
 
 #define SNAPPER9260_IO_EXP_GPIO(x)	(NR_BUILTIN_GPIO + (x))
 
-static void __init snapper9260_map_io(void)
+static void __init snapper9260_init_early(void)
 {
 	at91sam9260_initialize(18432000);
 
@@ -178,9 +178,9 @@ static void __init snapper9260_board_init(void)
 }
 
 MACHINE_START(SNAPPER_9260, "Bluewater Systems Snapper 9260/9G20 module")
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= snapper9260_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= snapper9260_init_early,
 	.init_irq	= snapper9260_init_irq,
 	.init_machine	= snapper9260_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-stamp9g20.c b/arch/arm/mach-at91/board-stamp9g20.c
index f8902b118960..5e5c85688f5f 100644
--- a/arch/arm/mach-at91/board-stamp9g20.c
+++ b/arch/arm/mach-at91/board-stamp9g20.c
@@ -32,7 +32,7 @@
 #include "generic.h"
 
 
-void __init stamp9g20_map_io(void)
+void __init stamp9g20_init_early(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
 	at91sam9260_initialize(18432000);
@@ -44,9 +44,9 @@ void __init stamp9g20_map_io(void)
 	at91_set_serial_console(0);
 }
 
-static void __init stamp9g20evb_map_io(void)
+static void __init stamp9g20evb_init_early(void)
 {
-	stamp9g20_map_io();
+	stamp9g20_init_early();
 
 	/* USART0 on ttyS1. (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */
 	at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS
@@ -54,9 +54,9 @@ static void __init stamp9g20evb_map_io(void)
 						| ATMEL_UART_DCD | ATMEL_UART_RI);
 }
 
-static void __init portuxg20_map_io(void)
+static void __init portuxg20_init_early(void)
 {
-	stamp9g20_map_io();
+	stamp9g20_init_early();
 
 	/* USART0 on ttyS1. (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */
 	at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS
@@ -298,18 +298,18 @@ static void __init stamp9g20evb_board_init(void)
 
 MACHINE_START(PORTUXG20, "taskit PortuxG20")
 	/* Maintainer: taskit GmbH */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= portuxg20_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= portuxg20_init_early,
 	.init_irq	= init_irq,
 	.init_machine	= portuxg20_board_init,
 MACHINE_END
 
 MACHINE_START(STAMP9G20, "taskit Stamp9G20")
 	/* Maintainer: taskit GmbH */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= stamp9g20evb_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= stamp9g20evb_init_early,
 	.init_irq	= init_irq,
 	.init_machine	= stamp9g20evb_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-usb-a9260.c b/arch/arm/mach-at91/board-usb-a9260.c
index 07784baeae84..0e784e6fedec 100644
--- a/arch/arm/mach-at91/board-usb-a9260.c
+++ b/arch/arm/mach-at91/board-usb-a9260.c
@@ -48,7 +48,7 @@
 #include "generic.h"
 
 
-static void __init ek_map_io(void)
+static void __init ek_init_early(void)
 {
 	/* Initialize processor: 12.000 MHz crystal */
 	at91sam9260_initialize(12000000);
@@ -228,9 +228,9 @@ static void __init ek_board_init(void)
 
 MACHINE_START(USB_A9260, "CALAO USB_A9260")
 	/* Maintainer: calao-systems */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= ek_map_io,
+	.map_io		= at91sam9260_map_io,
+	.init_early	= ek_init_early,
 	.init_irq	= ek_init_irq,
 	.init_machine	= ek_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-usb-a9263.c b/arch/arm/mach-at91/board-usb-a9263.c
index b614508931fd..cf626dd14b2c 100644
--- a/arch/arm/mach-at91/board-usb-a9263.c
+++ b/arch/arm/mach-at91/board-usb-a9263.c
@@ -47,7 +47,7 @@
 #include "generic.h"
 
 
-static void __init ek_map_io(void)
+static void __init ek_init_early(void)
 {
 	/* Initialize processor: 12.00 MHz crystal */
 	at91sam9263_initialize(12000000);
@@ -244,9 +244,9 @@ static void __init ek_board_init(void)
 
 MACHINE_START(USB_A9263, "CALAO USB_A9263")
 	/* Maintainer: calao-systems */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= ek_map_io,
+	.map_io		= at91sam9263_map_io,
+	.init_early	= ek_init_early,
 	.init_irq	= ek_init_irq,
 	.init_machine	= ek_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/board-yl-9200.c b/arch/arm/mach-at91/board-yl-9200.c
index e0f0080eb639..c208cc334d7d 100644
--- a/arch/arm/mach-at91/board-yl-9200.c
+++ b/arch/arm/mach-at91/board-yl-9200.c
@@ -45,14 +45,18 @@
 #include <mach/board.h>
 #include <mach/gpio.h>
 #include <mach/at91rm9200_mc.h>
+#include <mach/cpu.h>
 
 #include "generic.h"
 
 
-static void __init yl9200_map_io(void)
+static void __init yl9200_init_early(void)
 {
+	/* Set cpu type: PQFP */
+	at91rm9200_set_type(ARCH_REVISON_9200_PQFP);
+
 	/* Initialize processor: 18.432 MHz crystal */
-	at91rm9200_initialize(18432000, AT91RM9200_PQFP);
+	at91rm9200_initialize(18432000);
 
 	/* Setup the LEDs D2=PB17 (timer), D3=PB16 (cpu) */
 	at91_init_leds(AT91_PIN_PB16, AT91_PIN_PB17);
@@ -594,9 +598,9 @@ static void __init yl9200_board_init(void)
 
 MACHINE_START(YL9200, "uCdragon YL-9200")
 	/* Maintainer: S.Birtles */
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
-	.map_io		= yl9200_map_io,
+	.map_io		= at91rm9200_map_io,
+	.init_early	= yl9200_init_early,
 	.init_irq	= yl9200_init_irq,
 	.init_machine	= yl9200_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c
index 9113da6845f1..61873f3aa92d 100644
--- a/arch/arm/mach-at91/clock.c
+++ b/arch/arm/mach-at91/clock.c
@@ -163,7 +163,7 @@ static struct clk udpck = {
 	.parent		= &pllb,
 	.mode		= pmc_sys_mode,
 };
-static struct clk utmi_clk = {
+struct clk utmi_clk = {
 	.name		= "utmi_clk",
 	.parent		= &main_clk,
 	.pmc_mask	= AT91_PMC_UPLLEN,	/* in CKGR_UCKR */
@@ -182,7 +182,7 @@ static struct clk uhpck = {
  * memory, interfaces to on-chip peripherals, the AIC, and sometimes more
  * (e.g baud rate generation).  It's sourced from one of the primary clocks.
  */
-static struct clk mck = {
+struct clk mck = {
 	.name		= "mck",
 	.pmc_mask	= AT91_PMC_MCKRDY,	/* in PMC_SR */
 };
@@ -215,43 +215,6 @@ static struct clk __init *at91_css_to_clk(unsigned long css)
 	return NULL;
 }
 
-/*
- * Associate a particular clock with a function (eg, "uart") and device.
- * The drivers can then request the same 'function' with several different
- * devices and not care about which clock name to use.
- */
-void __init at91_clock_associate(const char *id, struct device *dev, const char *func)
-{
-	struct clk *clk = clk_get(NULL, id);
-
-	if (!dev || !clk || !IS_ERR(clk_get(dev, func)))
-		return;
-
-	clk->function = func;
-	clk->dev = dev;
-}
-
-/* clocks cannot be de-registered no refcounting necessary */
-struct clk *clk_get(struct device *dev, const char *id)
-{
-	struct clk *clk;
-
-	list_for_each_entry(clk, &clocks, node) {
-		if (strcmp(id, clk->name) == 0)
-			return clk;
-		if (clk->function && (dev == clk->dev) && strcmp(id, clk->function) == 0)
-			return clk;
-	}
-
-	return ERR_PTR(-ENOENT);
-}
-EXPORT_SYMBOL(clk_get);
-
-void clk_put(struct clk *clk)
-{
-}
-EXPORT_SYMBOL(clk_put);
-
 static void __clk_enable(struct clk *clk)
 {
 	if (clk->parent)
@@ -498,32 +461,38 @@ postcore_initcall(at91_clk_debugfs_init);
 /*------------------------------------------------------------------------*/
 
 /* Register a new clock */
+static void __init at91_clk_add(struct clk *clk)
+{
+	list_add_tail(&clk->node, &clocks);
+
+	clk->cl.con_id = clk->name;
+	clk->cl.clk = clk;
+	clkdev_add(&clk->cl);
+}
+
 int __init clk_register(struct clk *clk)
 {
 	if (clk_is_peripheral(clk)) {
 		if (!clk->parent)
 			clk->parent = &mck;
 		clk->mode = pmc_periph_mode;
-		list_add_tail(&clk->node, &clocks);
 	}
 	else if (clk_is_sys(clk)) {
 		clk->parent = &mck;
 		clk->mode = pmc_sys_mode;
-
-		list_add_tail(&clk->node, &clocks);
 	}
 #ifdef CONFIG_AT91_PROGRAMMABLE_CLOCKS
 	else if (clk_is_programmable(clk)) {
 		clk->mode = pmc_sys_mode;
 		init_programmable_clock(clk);
-		list_add_tail(&clk->node, &clocks);
 	}
 #endif
 
+	at91_clk_add(clk);
+
 	return 0;
 }
 
-
 /*------------------------------------------------------------------------*/
 
 static u32 __init at91_pll_rate(struct clk *pll, u32 freq, u32 reg)
@@ -630,7 +599,7 @@ static void __init at91_pllb_usbfs_clock_init(unsigned long main_clock)
 		at91_sys_write(AT91_PMC_SCER, AT91RM9200_PMC_MCKUDP);
 	} else if (cpu_is_at91sam9260() || cpu_is_at91sam9261() ||
 		   cpu_is_at91sam9263() || cpu_is_at91sam9g20() ||
-		   cpu_is_at91sam9g10() || cpu_is_at572d940hf()) {
+		   cpu_is_at91sam9g10()) {
 		uhpck.pmc_mask = AT91SAM926x_PMC_UHP;
 		udpck.pmc_mask = AT91SAM926x_PMC_UDP;
 	} else if (cpu_is_at91cap9()) {
@@ -754,19 +723,19 @@ int __init at91_clock_init(unsigned long main_clock)
 
 	/* Register the PMC's standard clocks */
 	for (i = 0; i < ARRAY_SIZE(standard_pmc_clocks); i++)
-		list_add_tail(&standard_pmc_clocks[i]->node, &clocks);
+		at91_clk_add(standard_pmc_clocks[i]);
 
 	if (cpu_has_pllb())
-		list_add_tail(&pllb.node, &clocks);
+		at91_clk_add(&pllb);
 
 	if (cpu_has_uhp())
-		list_add_tail(&uhpck.node, &clocks);
+		at91_clk_add(&uhpck);
 
 	if (cpu_has_udpfs())
-		list_add_tail(&udpck.node, &clocks);
+		at91_clk_add(&udpck);
 
 	if (cpu_has_utmi())
-		list_add_tail(&utmi_clk.node, &clocks);
+		at91_clk_add(&utmi_clk);
 
 	/* MCK and CPU clock are "always on" */
 	clk_enable(&mck);
diff --git a/arch/arm/mach-at91/clock.h b/arch/arm/mach-at91/clock.h
index 6cf4b78e175d..c2e63e47dcbe 100644
--- a/arch/arm/mach-at91/clock.h
+++ b/arch/arm/mach-at91/clock.h
@@ -6,6 +6,8 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/clkdev.h>
+
 #define CLK_TYPE_PRIMARY	0x1
 #define CLK_TYPE_PLL		0x2
 #define CLK_TYPE_PROGRAMMABLE	0x4
@@ -16,8 +18,7 @@
 struct clk {
 	struct list_head node;
 	const char	*name;		/* unique clock name */
-	const char	*function;	/* function of the clock */
-	struct device	*dev;		/* device associated with function */
+	struct clk_lookup cl;
 	unsigned long	rate_hz;
 	struct clk	*parent;
 	u32		pmc_mask;
@@ -29,3 +30,18 @@ struct clk {
 
 
 extern int __init clk_register(struct clk *clk);
+extern struct clk mck;
+extern struct clk utmi_clk;
+
+#define CLKDEV_CON_ID(_id, _clk)			\
+	{						\
+		.con_id = _id,				\
+		.clk = _clk,				\
+	}
+
+#define CLKDEV_CON_DEV_ID(_con_id, _dev_id, _clk)	\
+	{						\
+		.con_id = _con_id,			\
+		.dev_id = _dev_id,			\
+		.clk = _clk,				\
+	}
diff --git a/arch/arm/mach-at91/generic.h b/arch/arm/mach-at91/generic.h
index 0c66deb2db39..8ff3418f3430 100644
--- a/arch/arm/mach-at91/generic.h
+++ b/arch/arm/mach-at91/generic.h
@@ -8,8 +8,21 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/clkdev.h>
+
+ /* Map io */
+extern void __init at91rm9200_map_io(void);
+extern void __init at91sam9260_map_io(void);
+extern void __init at91sam9261_map_io(void);
+extern void __init at91sam9263_map_io(void);
+extern void __init at91sam9rl_map_io(void);
+extern void __init at91sam9g45_map_io(void);
+extern void __init at91x40_map_io(void);
+extern void __init at91cap9_map_io(void);
+
  /* Processors */
-extern void __init at91rm9200_initialize(unsigned long main_clock, unsigned short banks);
+extern void __init at91rm9200_set_type(int type);
+extern void __init at91rm9200_initialize(unsigned long main_clock);
 extern void __init at91sam9260_initialize(unsigned long main_clock);
 extern void __init at91sam9261_initialize(unsigned long main_clock);
 extern void __init at91sam9263_initialize(unsigned long main_clock);
@@ -17,7 +30,6 @@ extern void __init at91sam9rl_initialize(unsigned long main_clock);
 extern void __init at91sam9g45_initialize(unsigned long main_clock);
 extern void __init at91x40_initialize(unsigned long main_clock);
 extern void __init at91cap9_initialize(unsigned long main_clock);
-extern void __init at572d940hf_initialize(unsigned long main_clock);
 
  /* Interrupts */
 extern void __init at91rm9200_init_interrupts(unsigned int priority[]);
@@ -28,7 +40,6 @@ extern void __init at91sam9rl_init_interrupts(unsigned int priority[]);
 extern void __init at91sam9g45_init_interrupts(unsigned int priority[]);
 extern void __init at91x40_init_interrupts(unsigned int priority[]);
 extern void __init at91cap9_init_interrupts(unsigned int priority[]);
-extern void __init at572d940hf_init_interrupts(unsigned int priority[]);
 extern void __init at91_aic_init(unsigned int priority[]);
 
  /* Timer */
@@ -39,8 +50,19 @@ extern struct sys_timer at91x40_timer;
 
  /* Clocks */
 extern int __init at91_clock_init(unsigned long main_clock);
+/*
+ * function to specify the clock of the default console. As we do not
+ * use the device/driver bus, the dev_name is not intialize. So we need
+ * to link the clock to a specific con_id only "usart"
+ */
+extern void __init at91rm9200_set_console_clock(int id);
+extern void __init at91sam9260_set_console_clock(int id);
+extern void __init at91sam9261_set_console_clock(int id);
+extern void __init at91sam9263_set_console_clock(int id);
+extern void __init at91sam9rl_set_console_clock(int id);
+extern void __init at91sam9g45_set_console_clock(int id);
+extern void __init at91cap9_set_console_clock(int id);
 struct device;
-extern void __init at91_clock_associate(const char *id, struct device *dev, const char *func);
 
  /* Power Management */
 extern void at91_irq_suspend(void);
diff --git a/arch/arm/mach-at91/include/mach/at572d940hf.h b/arch/arm/mach-at91/include/mach/at572d940hf.h
deleted file mode 100644
index be510cfc56be..000000000000
--- a/arch/arm/mach-at91/include/mach/at572d940hf.h
+++ /dev/null
@@ -1,123 +0,0 @@
-/*
- * include/mach/at572d940hf.h
- *
- * Antonio R. Costa <costa.antonior@gmail.com>
- * Copyright (C) 2008 Atmel
- *
- * 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
- *
- */
-
-#ifndef AT572D940HF_H
-#define AT572D940HF_H
-
-/*
- * Peripheral identifiers/interrupts.
- */
-#define AT91_ID_FIQ		0	/* Advanced Interrupt Controller (FIQ) */
-#define AT91_ID_SYS		1	/* System Peripherals */
-#define AT572D940HF_ID_PIOA	2	/* Parallel IO Controller A */
-#define AT572D940HF_ID_PIOB	3	/* Parallel IO Controller B */
-#define AT572D940HF_ID_PIOC	4	/* Parallel IO Controller C */
-#define AT572D940HF_ID_EMAC	5	/* MACB ethernet controller */
-#define AT572D940HF_ID_US0	6	/* USART 0 */
-#define AT572D940HF_ID_US1	7	/* USART 1 */
-#define AT572D940HF_ID_US2	8	/* USART 2 */
-#define AT572D940HF_ID_MCI	9	/* Multimedia Card Interface */
-#define AT572D940HF_ID_UDP	10	/* USB Device Port */
-#define AT572D940HF_ID_TWI0	11	/* Two-Wire Interface 0 */
-#define AT572D940HF_ID_SPI0	12	/* Serial Peripheral Interface 0 */
-#define AT572D940HF_ID_SPI1	13	/* Serial Peripheral Interface 1 */
-#define AT572D940HF_ID_SSC0	14	/* Serial Synchronous Controller 0 */
-#define AT572D940HF_ID_SSC1	15	/* Serial Synchronous Controller 1 */
-#define AT572D940HF_ID_SSC2	16	/* Serial Synchronous Controller 2 */
-#define AT572D940HF_ID_TC0	17	/* Timer Counter 0 */
-#define AT572D940HF_ID_TC1	18	/* Timer Counter 1 */
-#define AT572D940HF_ID_TC2	19	/* Timer Counter 2 */
-#define AT572D940HF_ID_UHP	20	/* USB Host port */
-#define AT572D940HF_ID_SSC3	21	/* Serial Synchronous Controller 3 */
-#define AT572D940HF_ID_TWI1	22	/* Two-Wire Interface 1 */
-#define AT572D940HF_ID_CAN0	23	/* CAN Controller 0 */
-#define AT572D940HF_ID_CAN1	24	/* CAN Controller 1 */
-#define AT572D940HF_ID_MHALT	25	/* mAgicV HALT line */
-#define AT572D940HF_ID_MSIRQ0	26	/* mAgicV SIRQ0 line */
-#define AT572D940HF_ID_MEXC	27	/* mAgicV exception line */
-#define AT572D940HF_ID_MEDMA	28	/* mAgicV end of DMA line */
-#define AT572D940HF_ID_IRQ0	29	/* External Interrupt Source (IRQ0) */
-#define AT572D940HF_ID_IRQ1	30	/* External Interrupt Source (IRQ1) */
-#define AT572D940HF_ID_IRQ2	31	/* External Interrupt Source (IRQ2) */
-
-
-/*
- * User Peripheral physical base addresses.
- */
-#define AT572D940HF_BASE_TCB	0xfffa0000
-#define AT572D940HF_BASE_TC0	0xfffa0000
-#define AT572D940HF_BASE_TC1	0xfffa0040
-#define AT572D940HF_BASE_TC2	0xfffa0080
-#define AT572D940HF_BASE_UDP	0xfffa4000
-#define AT572D940HF_BASE_MCI	0xfffa8000
-#define AT572D940HF_BASE_TWI0	0xfffac000
-#define AT572D940HF_BASE_US0	0xfffb0000
-#define AT572D940HF_BASE_US1	0xfffb4000
-#define AT572D940HF_BASE_US2	0xfffb8000
-#define AT572D940HF_BASE_SSC0	0xfffbc000
-#define AT572D940HF_BASE_SSC1	0xfffc0000
-#define AT572D940HF_BASE_SSC2	0xfffc4000
-#define AT572D940HF_BASE_SPI0	0xfffc8000
-#define AT572D940HF_BASE_SPI1	0xfffcc000
-#define AT572D940HF_BASE_SSC3	0xfffd0000
-#define AT572D940HF_BASE_TWI1	0xfffd4000
-#define AT572D940HF_BASE_EMAC	0xfffd8000
-#define AT572D940HF_BASE_CAN0	0xfffdc000
-#define AT572D940HF_BASE_CAN1	0xfffe0000
-#define AT91_BASE_SYS		0xffffea00
-
-
-/*
- * System Peripherals (offset from AT91_BASE_SYS)
- */
-#define AT91_SDRAMC0	(0xffffea00 - AT91_BASE_SYS)
-#define AT91_SMC	(0xffffec00 - AT91_BASE_SYS)
-#define AT91_MATRIX	(0xffffee00 - AT91_BASE_SYS)
-#define AT91_AIC	(0xfffff000 - AT91_BASE_SYS)
-#define AT91_DBGU	(0xfffff200 - AT91_BASE_SYS)
-#define AT91_PIOA	(0xfffff400 - AT91_BASE_SYS)
-#define AT91_PIOB	(0xfffff600 - AT91_BASE_SYS)
-#define AT91_PIOC	(0xfffff800 - AT91_BASE_SYS)
-#define AT91_PMC	(0xfffffc00 - AT91_BASE_SYS)
-#define AT91_RSTC	(0xfffffd00 - AT91_BASE_SYS)
-#define AT91_RTT	(0xfffffd20 - AT91_BASE_SYS)
-#define AT91_PIT	(0xfffffd30 - AT91_BASE_SYS)
-#define AT91_WDT	(0xfffffd40 - AT91_BASE_SYS)
-
-#define AT91_USART0	AT572D940HF_ID_US0
-#define AT91_USART1	AT572D940HF_ID_US1
-#define AT91_USART2	AT572D940HF_ID_US2
-
-
-/*
- * Internal Memory.
- */
-#define AT572D940HF_SRAM_BASE	0x00300000	/* Internal SRAM base address */
-#define AT572D940HF_SRAM_SIZE	(48 * SZ_1K)	/* Internal SRAM size (48Kb) */
-
-#define AT572D940HF_ROM_BASE	0x00400000	/* Internal ROM base address */
-#define AT572D940HF_ROM_SIZE	SZ_32K		/* Internal ROM size (32Kb) */
-
-#define AT572D940HF_UHP_BASE	0x00500000	/* USB Host controller */
-
-
-#endif
diff --git a/arch/arm/mach-at91/include/mach/at572d940hf_matrix.h b/arch/arm/mach-at91/include/mach/at572d940hf_matrix.h
deleted file mode 100644
index b6751df09488..000000000000
--- a/arch/arm/mach-at91/include/mach/at572d940hf_matrix.h
+++ /dev/null
@@ -1,123 +0,0 @@
-/*
- * include/mach//at572d940hf_matrix.h
- *
- * Antonio R. Costa <costa.antonior@gmail.com>
- * Copyright (C) 2008 Atmel
- *
- * Copyright (C) 2005 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
- */
-
-#ifndef AT572D940HF_MATRIX_H
-#define AT572D940HF_MATRIX_H
-
-#define AT91_MATRIX_MCFG0	(AT91_MATRIX + 0x00)	/* Master Configuration Register 0 */
-#define AT91_MATRIX_MCFG1	(AT91_MATRIX + 0x04)	/* Master Configuration Register 1 */
-#define AT91_MATRIX_MCFG2	(AT91_MATRIX + 0x08)	/* Master Configuration Register 2 */
-#define AT91_MATRIX_MCFG3	(AT91_MATRIX + 0x0C)	/* Master Configuration Register 3 */
-#define AT91_MATRIX_MCFG4	(AT91_MATRIX + 0x10)	/* Master Configuration Register 4 */
-#define AT91_MATRIX_MCFG5	(AT91_MATRIX + 0x14)	/* Master Configuration Register 5 */
-
-#define		AT91_MATRIX_ULBT	(7 << 0)	/* Undefined Length Burst Type */
-#define			AT91_MATRIX_ULBT_INFINITE	(0 << 0)
-#define			AT91_MATRIX_ULBT_SINGLE		(1 << 0)
-#define			AT91_MATRIX_ULBT_FOUR		(2 << 0)
-#define			AT91_MATRIX_ULBT_EIGHT		(3 << 0)
-#define			AT91_MATRIX_ULBT_SIXTEEN	(4 << 0)
-
-#define AT91_MATRIX_SCFG0	(AT91_MATRIX + 0x40)	/* Slave Configuration Register 0 */
-#define AT91_MATRIX_SCFG1	(AT91_MATRIX + 0x44)	/* Slave Configuration Register 1 */
-#define AT91_MATRIX_SCFG2	(AT91_MATRIX + 0x48)	/* Slave Configuration Register 2 */
-#define AT91_MATRIX_SCFG3	(AT91_MATRIX + 0x4C)	/* Slave Configuration Register 3 */
-#define AT91_MATRIX_SCFG4	(AT91_MATRIX + 0x50)	/* Slave Configuration Register 4 */
-#define		AT91_MATRIX_SLOT_CYCLE		(0xff << 0)	/* Maximum Number of Allowed Cycles for a Burst */
-#define		AT91_MATRIX_DEFMSTR_TYPE	(3    << 16)	/* Default Master Type */
-#define			AT91_MATRIX_DEFMSTR_TYPE_NONE	(0 << 16)
-#define			AT91_MATRIX_DEFMSTR_TYPE_LAST	(1 << 16)
-#define			AT91_MATRIX_DEFMSTR_TYPE_FIXED	(2 << 16)
-#define		AT91_MATRIX_FIXED_DEFMSTR	(0x7  << 18)	/* Fixed Index of Default Master */
-#define		AT91_MATRIX_ARBT		(3    << 24)	/* Arbitration Type */
-#define			AT91_MATRIX_ARBT_ROUND_ROBIN	(0 << 24)
-#define			AT91_MATRIX_ARBT_FIXED_PRIORITY	(1 << 24)
-
-#define AT91_MATRIX_PRAS0	(AT91_MATRIX + 0x80)	/* Priority Register A for Slave 0 */
-#define AT91_MATRIX_PRAS1	(AT91_MATRIX + 0x88)	/* Priority Register A for Slave 1 */
-#define AT91_MATRIX_PRAS2	(AT91_MATRIX + 0x90)	/* Priority Register A for Slave 2 */
-#define AT91_MATRIX_PRAS3	(AT91_MATRIX + 0x98)	/* Priority Register A for Slave 3 */
-#define AT91_MATRIX_PRAS4	(AT91_MATRIX + 0xA0)	/* Priority Register A for Slave 4 */
-
-#define		AT91_MATRIX_M0PR		(3 << 0)	/* Master 0 Priority */
-#define		AT91_MATRIX_M1PR		(3 << 4)	/* Master 1 Priority */
-#define		AT91_MATRIX_M2PR		(3 << 8)	/* Master 2 Priority */
-#define		AT91_MATRIX_M3PR		(3 << 12)	/* Master 3 Priority */
-#define		AT91_MATRIX_M4PR		(3 << 16)	/* Master 4 Priority */
-#define		AT91_MATRIX_M5PR		(3 << 20)	/* Master 5 Priority */
-#define		AT91_MATRIX_M6PR		(3 << 24)	/* Master 6 Priority */
-
-#define AT91_MATRIX_MRCR	(AT91_MATRIX + 0x100)	/* Master Remap Control Register */
-#define		AT91_MATRIX_RCB0		(1 << 0)	/* Remap Command for AHB Master 0 (ARM926EJ-S Instruction Master) */
-#define		AT91_MATRIX_RCB1		(1 << 1)	/* Remap Command for AHB Master 1 (ARM926EJ-S Data Master) */
-
-#define AT91_MATRIX_SFR0	(AT91_MATRIX + 0x110)	/* Special Function Register 0 */
-#define AT91_MATRIX_SFR1	(AT91_MATRIX + 0x114)	/* Special Function Register 1 */
-#define AT91_MATRIX_SFR2	(AT91_MATRIX + 0x118)	/* Special Function Register 2 */
-#define AT91_MATRIX_SFR3	(AT91_MATRIX + 0x11C)	/* Special Function Register 3 */
-#define AT91_MATRIX_SFR4	(AT91_MATRIX + 0x120)	/* Special Function Register 4 */
-#define AT91_MATRIX_SFR5	(AT91_MATRIX + 0x124)	/* Special Function Register 5 */
-#define AT91_MATRIX_SFR6	(AT91_MATRIX + 0x128)	/* Special Function Register 6 */
-#define AT91_MATRIX_SFR7	(AT91_MATRIX + 0x12C)	/* Special Function Register 7 */
-#define AT91_MATRIX_SFR8	(AT91_MATRIX + 0x130)	/* Special Function Register 8 */
-#define AT91_MATRIX_SFR9	(AT91_MATRIX + 0x134)	/* Special Function Register 9 */
-#define AT91_MATRIX_SFR10	(AT91_MATRIX + 0x138)	/* Special Function Register 10 */
-#define AT91_MATRIX_SFR11	(AT91_MATRIX + 0x13C)	/* Special Function Register 11 */
-#define AT91_MATRIX_SFR12	(AT91_MATRIX + 0x140)	/* Special Function Register 12 */
-#define AT91_MATRIX_SFR13	(AT91_MATRIX + 0x144)	/* Special Function Register 13 */
-#define AT91_MATRIX_SFR14	(AT91_MATRIX + 0x148)	/* Special Function Register 14 */
-#define AT91_MATRIX_SFR15	(AT91_MATRIX + 0x14C)	/* Special Function Register 15 */
-
-
-/*
- * The following registers / bits are not defined in the Datasheet (Revision A)
- */
-
-#define AT91_MATRIX_TCR		(AT91_MATRIX + 0x100)	/* TCM Configuration Register */
-#define		AT91_MATRIX_ITCM_SIZE		(0xf << 0)	/* Size of ITCM enabled memory block */
-#define			AT91_MATRIX_ITCM_0		(0 << 0)
-#define			AT91_MATRIX_ITCM_16		(5 << 0)
-#define			AT91_MATRIX_ITCM_32		(6 << 0)
-#define			AT91_MATRIX_ITCM_64		(7 << 0)
-#define		AT91_MATRIX_DTCM_SIZE		(0xf << 4)	/* Size of DTCM enabled memory block */
-#define			AT91_MATRIX_DTCM_0		(0 << 4)
-#define			AT91_MATRIX_DTCM_16		(5 << 4)
-#define			AT91_MATRIX_DTCM_32		(6 << 4)
-#define			AT91_MATRIX_DTCM_64		(7 << 4)
-
-#define AT91_MATRIX_EBICSA	(AT91_MATRIX + 0x11C)	/* EBI Chip Select Assignment Register */
-#define		AT91_MATRIX_CS1A		(1 << 1)	/* Chip Select 1 Assignment */
-#define			AT91_MATRIX_CS1A_SMC		(0 << 1)
-#define			AT91_MATRIX_CS1A_SDRAMC		(1 << 1)
-#define		AT91_MATRIX_CS3A		(1 << 3)	/* Chip Select 3 Assignment */
-#define			AT91_MATRIX_CS3A_SMC		(0 << 3)
-#define			AT91_MATRIX_CS3A_SMC_SMARTMEDIA	(1 << 3)
-#define		AT91_MATRIX_CS4A		(1 << 4)	/* Chip Select 4 Assignment */
-#define			AT91_MATRIX_CS4A_SMC		(0 << 4)
-#define			AT91_MATRIX_CS4A_SMC_CF1	(1 << 4)
-#define		AT91_MATRIX_CS5A		(1 << 5)	/* Chip Select 5 Assignment */
-#define			AT91_MATRIX_CS5A_SMC		(0 << 5)
-#define			AT91_MATRIX_CS5A_SMC_CF2	(1 << 5)
-#define		AT91_MATRIX_DBPUC		(1 << 8)	/* Data Bus Pull-up Configuration */
-
-#endif
diff --git a/arch/arm/mach-at91/include/mach/at91cap9.h b/arch/arm/mach-at91/include/mach/at91cap9.h
index 9c6af9737485..665993849a7b 100644
--- a/arch/arm/mach-at91/include/mach/at91cap9.h
+++ b/arch/arm/mach-at91/include/mach/at91cap9.h
@@ -20,8 +20,6 @@
 /*
  * Peripheral identifiers/interrupts.
  */
-#define AT91_ID_FIQ		0	/* Advanced Interrupt Controller (FIQ) */
-#define AT91_ID_SYS		1	/* System Peripherals */
 #define AT91CAP9_ID_PIOABCD	2	/* Parallel IO Controller A, B, C and D */
 #define AT91CAP9_ID_MPB0	3	/* MP Block Peripheral 0 */
 #define AT91CAP9_ID_MPB1	4	/* MP Block Peripheral 1 */
@@ -123,6 +121,4 @@
 #define AT91CAP9_UDPHS_FIFO	0x00600000	/* USB High Speed Device Port */
 #define AT91CAP9_UHP_BASE	0x00700000	/* USB Host controller */
 
-#define CONFIG_DRAM_BASE	AT91_CHIPSELECT_6
-
 #endif
diff --git a/arch/arm/mach-at91/include/mach/at91rm9200.h b/arch/arm/mach-at91/include/mach/at91rm9200.h
index 78983155a074..99e0f8d02d7b 100644
--- a/arch/arm/mach-at91/include/mach/at91rm9200.h
+++ b/arch/arm/mach-at91/include/mach/at91rm9200.h
@@ -19,8 +19,6 @@
 /*
  * Peripheral identifiers/interrupts.
  */
-#define AT91_ID_FIQ		0	/* Advanced Interrupt Controller (FIQ) */
-#define AT91_ID_SYS		1	/* System Peripheral */
 #define AT91RM9200_ID_PIOA	2	/* Parallel IO Controller A */
 #define AT91RM9200_ID_PIOB	3	/* Parallel IO Controller B */
 #define AT91RM9200_ID_PIOC	4	/* Parallel IO Controller C */
diff --git a/arch/arm/mach-at91/include/mach/at91sam9260.h b/arch/arm/mach-at91/include/mach/at91sam9260.h
index 4e79036d3b80..8b6bf835cd73 100644
--- a/arch/arm/mach-at91/include/mach/at91sam9260.h
+++ b/arch/arm/mach-at91/include/mach/at91sam9260.h
@@ -20,8 +20,6 @@
 /*
  * Peripheral identifiers/interrupts.
  */
-#define AT91_ID_FIQ		0	/* Advanced Interrupt Controller (FIQ) */
-#define AT91_ID_SYS		1	/* System Peripherals */
 #define AT91SAM9260_ID_PIOA	2	/* Parallel IO Controller A */
 #define AT91SAM9260_ID_PIOB	3	/* Parallel IO Controller B */
 #define AT91SAM9260_ID_PIOC	4	/* Parallel IO Controller C */
diff --git a/arch/arm/mach-at91/include/mach/at91sam9261.h b/arch/arm/mach-at91/include/mach/at91sam9261.h
index 2b5618518129..eafbddaf523c 100644
--- a/arch/arm/mach-at91/include/mach/at91sam9261.h
+++ b/arch/arm/mach-at91/include/mach/at91sam9261.h
@@ -18,8 +18,6 @@
 /*
  * Peripheral identifiers/interrupts.
  */
-#define AT91_ID_FIQ		0	/* Advanced Interrupt Controller (FIQ) */
-#define AT91_ID_SYS		1	/* System Peripherals */
 #define AT91SAM9261_ID_PIOA	2	/* Parallel IO Controller A */
 #define AT91SAM9261_ID_PIOB	3	/* Parallel IO Controller B */
 #define AT91SAM9261_ID_PIOC	4	/* Parallel IO Controller C */
diff --git a/arch/arm/mach-at91/include/mach/at91sam9263.h b/arch/arm/mach-at91/include/mach/at91sam9263.h
index 2091f1e42d43..e2d348213a7b 100644
--- a/arch/arm/mach-at91/include/mach/at91sam9263.h
+++ b/arch/arm/mach-at91/include/mach/at91sam9263.h
@@ -18,8 +18,6 @@
 /*
  * Peripheral identifiers/interrupts.
  */
-#define AT91_ID_FIQ		0	/* Advanced Interrupt Controller (FIQ) */
-#define AT91_ID_SYS		1	/* System Peripherals */
 #define AT91SAM9263_ID_PIOA	2	/* Parallel IO Controller A */
 #define AT91SAM9263_ID_PIOB	3	/* Parallel IO Controller B */
 #define AT91SAM9263_ID_PIOCDE	4	/* Parallel IO Controller C, D and E */
diff --git a/arch/arm/mach-at91/include/mach/at91sam9g45.h b/arch/arm/mach-at91/include/mach/at91sam9g45.h
index a526869aee37..659304aa73d9 100644
--- a/arch/arm/mach-at91/include/mach/at91sam9g45.h
+++ b/arch/arm/mach-at91/include/mach/at91sam9g45.h
@@ -18,8 +18,6 @@
 /*
  * Peripheral identifiers/interrupts.
  */
-#define AT91_ID_FIQ		0	/* Advanced Interrupt Controller (FIQ) */
-#define AT91_ID_SYS		1	/* System Controller Interrupt */
 #define AT91SAM9G45_ID_PIOA	2	/* Parallel I/O Controller A */
 #define AT91SAM9G45_ID_PIOB	3	/* Parallel I/O Controller B */
 #define AT91SAM9G45_ID_PIOC	4	/* Parallel I/O Controller C */
@@ -131,8 +129,6 @@
 #define AT91SAM9G45_EHCI_BASE	0x00800000	/* USB Host controller (EHCI) */
 #define AT91SAM9G45_VDEC_BASE	0x00900000	/* Video Decoder Controller */
 
-#define CONFIG_DRAM_BASE	AT91_CHIPSELECT_6
-
 #define CONSISTENT_DMA_SIZE	SZ_4M
 
 /*
diff --git a/arch/arm/mach-at91/include/mach/at91sam9rl.h b/arch/arm/mach-at91/include/mach/at91sam9rl.h
index 87ba8517ad98..41dbbe61055c 100644
--- a/arch/arm/mach-at91/include/mach/at91sam9rl.h
+++ b/arch/arm/mach-at91/include/mach/at91sam9rl.h
@@ -17,8 +17,6 @@
 /*
  * Peripheral identifiers/interrupts.
  */
-#define AT91_ID_FIQ		0	/* Advanced Interrupt Controller (FIQ) */
-#define AT91_ID_SYS		1	/* System Controller */
 #define AT91SAM9RL_ID_PIOA	2	/* Parallel IO Controller A */
 #define AT91SAM9RL_ID_PIOB	3	/* Parallel IO Controller B */
 #define AT91SAM9RL_ID_PIOC	4	/* Parallel IO Controller C */
diff --git a/arch/arm/mach-at91/include/mach/at91x40.h b/arch/arm/mach-at91/include/mach/at91x40.h
index 063ac44a0204..a152ff87e688 100644
--- a/arch/arm/mach-at91/include/mach/at91x40.h
+++ b/arch/arm/mach-at91/include/mach/at91x40.h
@@ -15,8 +15,6 @@
 /*
  *	IRQ list.
  */
-#define AT91_ID_FIQ		0	/* FIQ */
-#define AT91_ID_SYS		1	/* System Peripheral */
 #define AT91X40_ID_USART0	2	/* USART port 0 */
 #define AT91X40_ID_USART1	3	/* USART port 1 */
 #define AT91X40_ID_TC0		4	/* Timer/Counter 0 */
diff --git a/arch/arm/mach-at91/include/mach/board.h b/arch/arm/mach-at91/include/mach/board.h
index 2b499eb343a1..ed544a0d5a1d 100644
--- a/arch/arm/mach-at91/include/mach/board.h
+++ b/arch/arm/mach-at91/include/mach/board.h
@@ -90,7 +90,7 @@ struct at91_eth_data {
 extern void __init at91_add_device_eth(struct at91_eth_data *data);
 
 #if defined(CONFIG_ARCH_AT91SAM9260) || defined(CONFIG_ARCH_AT91SAM9263) || defined(CONFIG_ARCH_AT91SAM9G20) || defined(CONFIG_ARCH_AT91CAP9) \
-	|| defined(CONFIG_ARCH_AT91SAM9G45) || defined(CONFIG_ARCH_AT572D940HF)
+	|| defined(CONFIG_ARCH_AT91SAM9G45)
 #define eth_platform_data	at91_eth_data
 #endif
 
@@ -140,6 +140,7 @@ extern void __init at91_set_serial_console(unsigned portnr);
 extern struct platform_device *atmel_default_console_device;
 
 struct atmel_uart_data {
+	int			num;		/* port num */
 	short			use_dma_tx;	/* use transmit DMA? */
 	short			use_dma_rx;	/* use receive DMA? */
 	void __iomem		*regs;		/* virt. base address, if any */
@@ -203,9 +204,6 @@ extern void __init at91_init_leds(u8 cpu_led, u8 timer_led);
 extern void __init at91_gpio_leds(struct gpio_led *leds, int nr);
 extern void __init at91_pwm_leds(struct gpio_led *leds, int nr);
 
- /* AT572D940HF DSP */
-extern void __init at91_add_device_mAgic(void);
-
 /* FIXME: this needs a better location, but gets stuff building again */
 extern int at91_suspend_entering_slow_clock(void);
 
diff --git a/arch/arm/mach-at91/include/mach/clkdev.h b/arch/arm/mach-at91/include/mach/clkdev.h
new file mode 100644
index 000000000000..04b37a89801c
--- /dev/null
+++ b/arch/arm/mach-at91/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-at91/include/mach/cpu.h b/arch/arm/mach-at91/include/mach/cpu.h
index 0700f2125305..df966c2bc2d4 100644
--- a/arch/arm/mach-at91/include/mach/cpu.h
+++ b/arch/arm/mach-at91/include/mach/cpu.h
@@ -34,8 +34,6 @@
 #define ARCH_ID_AT91SAM9XE256	0x329a93a0
 #define ARCH_ID_AT91SAM9XE512	0x329aa3a0
 
-#define ARCH_ID_AT572D940HF	0x0e0303e0
-
 #define ARCH_ID_AT91M40800	0x14080044
 #define ARCH_ID_AT91R40807	0x44080746
 #define ARCH_ID_AT91M40807	0x14080745
@@ -90,9 +88,16 @@ static inline unsigned long at91cap9_rev_identify(void)
 #endif
 
 #ifdef CONFIG_ARCH_AT91RM9200
+extern int rm9200_type;
+#define ARCH_REVISON_9200_BGA	(0 << 0)
+#define ARCH_REVISON_9200_PQFP	(1 << 0)
 #define cpu_is_at91rm9200()	(at91_cpu_identify() == ARCH_ID_AT91RM9200)
+#define cpu_is_at91rm9200_bga()	(!cpu_is_at91rm9200_pqfp())
+#define cpu_is_at91rm9200_pqfp() (cpu_is_at91rm9200() && rm9200_type & ARCH_REVISON_9200_PQFP)
 #else
 #define cpu_is_at91rm9200()	(0)
+#define cpu_is_at91rm9200_bga()	(0)
+#define cpu_is_at91rm9200_pqfp() (0)
 #endif
 
 #ifdef CONFIG_ARCH_AT91SAM9260
@@ -181,12 +186,6 @@ static inline unsigned long at91cap9_rev_identify(void)
 #define cpu_is_at91cap9_revC()	(0)
 #endif
 
-#ifdef CONFIG_ARCH_AT572D940HF
-#define cpu_is_at572d940hf() (at91_cpu_identify() == ARCH_ID_AT572D940HF)
-#else
-#define cpu_is_at572d940hf() (0)
-#endif
-
 /*
  * Since this is ARM, we will never run on any AVR32 CPU. But these
  * definitions may reduce clutter in common drivers.
diff --git a/arch/arm/mach-at91/include/mach/hardware.h b/arch/arm/mach-at91/include/mach/hardware.h
index 3d64a75e3ed5..1008b9fb5074 100644
--- a/arch/arm/mach-at91/include/mach/hardware.h
+++ b/arch/arm/mach-at91/include/mach/hardware.h
@@ -32,13 +32,17 @@
 #include <mach/at91cap9.h>
 #elif defined(CONFIG_ARCH_AT91X40)
 #include <mach/at91x40.h>
-#elif defined(CONFIG_ARCH_AT572D940HF)
-#include <mach/at572d940hf.h>
 #else
 #error "Unsupported AT91 processor"
 #endif
 
 
+/*
+ * Peripheral identifiers/interrupts.
+ */
+#define AT91_ID_FIQ		0	/* Advanced Interrupt Controller (FIQ) */
+#define AT91_ID_SYS		1	/* System Peripherals */
+
 #ifdef CONFIG_MMU
 /*
  * Remap the peripherals from address 0xFFF78000 .. 0xFFFFFFFF
@@ -82,13 +86,6 @@
 #define AT91_CHIPSELECT_6	0x70000000
 #define AT91_CHIPSELECT_7	0x80000000
 
-/* SDRAM */
-#ifdef CONFIG_DRAM_BASE
-#define AT91_SDRAM_BASE		CONFIG_DRAM_BASE
-#else
-#define AT91_SDRAM_BASE		AT91_CHIPSELECT_1
-#endif
-
 /* Clocks */
 #define AT91_SLOW_CLOCK		32768		/* slow clock */
 
diff --git a/arch/arm/mach-at91/include/mach/memory.h b/arch/arm/mach-at91/include/mach/memory.h
index c2cfe5040642..401c207f2f39 100644
--- a/arch/arm/mach-at91/include/mach/memory.h
+++ b/arch/arm/mach-at91/include/mach/memory.h
@@ -23,6 +23,4 @@
 
 #include <mach/hardware.h>
 
-#define PLAT_PHYS_OFFSET	(AT91_SDRAM_BASE)
-
 #endif
diff --git a/arch/arm/mach-at91/include/mach/stamp9g20.h b/arch/arm/mach-at91/include/mach/stamp9g20.h
index 6120f9c46d59..f62c0abca4b4 100644
--- a/arch/arm/mach-at91/include/mach/stamp9g20.h
+++ b/arch/arm/mach-at91/include/mach/stamp9g20.h
@@ -1,7 +1,7 @@
 #ifndef __MACH_STAMP9G20_H
 #define __MACH_STAMP9G20_H
 
-void stamp9g20_map_io(void);
+void stamp9g20_init_early(void);
 void stamp9g20_board_init(void);
 
 #endif
diff --git a/arch/arm/mach-at91/include/mach/system_rev.h b/arch/arm/mach-at91/include/mach/system_rev.h
new file mode 100644
index 000000000000..b855ee75f72c
--- /dev/null
+++ b/arch/arm/mach-at91/include/mach/system_rev.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2011 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
+ *
+ * Under GPLv2 only
+ */
+
+#ifndef __ARCH_SYSTEM_REV_H__
+#define __ARCH_SYSTEM_REV_H__
+
+/*
+ * board revision encoding
+ * mach specific
+ * the 16-31 bit are reserved for at91 generic information
+ *
+ * bit 31:
+ *	0 => nand 16 bit
+ *	1 => nand 8 bit
+ */
+#define BOARD_HAVE_NAND_8BIT	(1 << 31)
+static int inline board_have_nand_8bit(void)
+{
+	return system_rev & BOARD_HAVE_NAND_8BIT;
+}
+
+#endif /* __ARCH_SYSTEM_REV_H__ */
diff --git a/arch/arm/mach-at91/include/mach/timex.h b/arch/arm/mach-at91/include/mach/timex.h
index 05a6e8af80c4..31ac2d97f14c 100644
--- a/arch/arm/mach-at91/include/mach/timex.h
+++ b/arch/arm/mach-at91/include/mach/timex.h
@@ -82,11 +82,6 @@
 #define AT91X40_MASTER_CLOCK	40000000
 #define CLOCK_TICK_RATE		(AT91X40_MASTER_CLOCK)
 
-#elif defined(CONFIG_ARCH_AT572D940HF)
-
-#define AT572D940HF_MASTER_CLOCK	80000000
-#define CLOCK_TICK_RATE		(AT572D940HF_MASTER_CLOCK/16)
-
 #endif
 
 #endif
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index b95b9196deed..133aac405853 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -1055,7 +1055,7 @@ int da850_register_pm(struct platform_device *pdev)
 	if (!pdata->cpupll_reg_base)
 		return -ENOMEM;
 
-	pdata->ddrpll_reg_base = ioremap(DA8XX_PLL1_BASE, SZ_4K);
+	pdata->ddrpll_reg_base = ioremap(DA850_PLL1_BASE, SZ_4K);
 	if (!pdata->ddrpll_reg_base) {
 		ret = -ENOMEM;
 		goto no_ddrpll_mem;
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index 58a02dc7b15a..fc4e98ea7543 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -24,23 +24,25 @@
 #include "clock.h"
 
 #define DA8XX_TPCC_BASE			0x01c00000
-#define DA850_MMCSD1_BASE		0x01e1b000
-#define DA850_TPCC1_BASE		0x01e30000
 #define DA8XX_TPTC0_BASE		0x01c08000
 #define DA8XX_TPTC1_BASE		0x01c08400
-#define DA850_TPTC2_BASE		0x01e38000
 #define DA8XX_WDOG_BASE			0x01c21000 /* DA8XX_TIMER64P1_BASE */
 #define DA8XX_I2C0_BASE			0x01c22000
-#define DA8XX_RTC_BASE			0x01C23000
+#define DA8XX_RTC_BASE			0x01c23000
+#define DA8XX_MMCSD0_BASE		0x01c40000
+#define DA8XX_SPI0_BASE			0x01c41000
+#define DA830_SPI1_BASE			0x01e12000
+#define DA8XX_LCD_CNTRL_BASE		0x01e13000
+#define DA850_MMCSD1_BASE		0x01e1b000
 #define DA8XX_EMAC_CPPI_PORT_BASE	0x01e20000
 #define DA8XX_EMAC_CPGMACSS_BASE	0x01e22000
 #define DA8XX_EMAC_CPGMAC_BASE		0x01e23000
 #define DA8XX_EMAC_MDIO_BASE		0x01e24000
-#define DA8XX_GPIO_BASE			0x01e26000
 #define DA8XX_I2C1_BASE			0x01e28000
-#define DA8XX_SPI0_BASE			0x01c41000
-#define DA830_SPI1_BASE			0x01e12000
+#define DA850_TPCC1_BASE		0x01e30000
+#define DA850_TPTC2_BASE		0x01e38000
 #define DA850_SPI1_BASE			0x01f0e000
+#define DA8XX_DDR2_CTL_BASE		0xb0000000
 
 #define DA8XX_EMAC_CTRL_REG_OFFSET	0x3000
 #define DA8XX_EMAC_MOD_REG_OFFSET	0x2000
@@ -492,7 +494,7 @@ static struct platform_device da850_mcasp_device = {
 	.resource	= da850_mcasp_resources,
 };
 
-struct platform_device davinci_pcm_device = {
+static struct platform_device davinci_pcm_device = {
 	.name	= "davinci-pcm-audio",
 	.id	= -1,
 };
diff --git a/arch/arm/mach-davinci/devices.c b/arch/arm/mach-davinci/devices.c
index 22ebc64bc9d9..806a2f02b980 100644
--- a/arch/arm/mach-davinci/devices.c
+++ b/arch/arm/mach-davinci/devices.c
@@ -33,6 +33,9 @@
 #define DM365_MMCSD0_BASE	     0x01D11000
 #define DM365_MMCSD1_BASE	     0x01D00000
 
+/* System control register offsets */
+#define DM64XX_VDD3P3V_PWDN	0x48
+
 static struct resource i2c_resources[] = {
 	{
 		.start		= DAVINCI_I2C_BASE,
@@ -295,7 +298,7 @@ static void davinci_init_wdt(void)
 
 /*-------------------------------------------------------------------------*/
 
-struct platform_device davinci_pcm_device = {
+static struct platform_device davinci_pcm_device = {
 	.name		= "davinci-pcm-audio",
 	.id		= -1,
 };
diff --git a/arch/arm/mach-davinci/gpio.c b/arch/arm/mach-davinci/gpio.c
index a0b838894ac9..e7221398e5af 100644
--- a/arch/arm/mach-davinci/gpio.c
+++ b/arch/arm/mach-davinci/gpio.c
@@ -252,9 +252,11 @@ static struct irq_chip gpio_irqchip = {
 static void
 gpio_irq_handler(unsigned irq, struct irq_desc *desc)
 {
-	struct davinci_gpio_regs __iomem *g = irq2regs(irq);
+	struct davinci_gpio_regs __iomem *g;
 	u32 mask = 0xffff;
 
+	g = (__force struct davinci_gpio_regs __iomem *) irq_desc_get_handler_data(desc);
+
 	/* we only care about one bank */
 	if (irq & 1)
 		mask <<= 16;
@@ -422,8 +424,7 @@ static int __init davinci_gpio_irq_setup(void)
 
 		/* set up all irqs in this bank */
 		irq_set_chained_handler(bank_irq, gpio_irq_handler);
-		irq_set_chip_data(bank_irq, (__force void *)g);
-		irq_set_handler_data(bank_irq, (void *)irq);
+		irq_set_handler_data(bank_irq, (__force void *)g);
 
 		for (i = 0; i < 16 && gpio < ngpio; i++, irq++, gpio++) {
 			irq_set_chip(irq, &gpio_irqchip);
diff --git a/arch/arm/mach-davinci/include/mach/da8xx.h b/arch/arm/mach-davinci/include/mach/da8xx.h
index e4fc1af8500e..ad64da713fc8 100644
--- a/arch/arm/mach-davinci/include/mach/da8xx.h
+++ b/arch/arm/mach-davinci/include/mach/da8xx.h
@@ -64,13 +64,9 @@ extern unsigned int da850_max_speed;
 #define DA8XX_TIMER64P1_BASE	0x01c21000
 #define DA8XX_GPIO_BASE		0x01e26000
 #define DA8XX_PSC1_BASE		0x01e27000
-#define DA8XX_LCD_CNTRL_BASE	0x01e13000
-#define DA8XX_PLL1_BASE		0x01e1a000
-#define DA8XX_MMCSD0_BASE	0x01c40000
 #define DA8XX_AEMIF_CS2_BASE	0x60000000
 #define DA8XX_AEMIF_CS3_BASE	0x62000000
 #define DA8XX_AEMIF_CTL_BASE	0x68000000
-#define DA8XX_DDR2_CTL_BASE	0xb0000000
 #define DA8XX_ARM_RAM_BASE	0xffff0000
 
 void __init da830_init(void);
diff --git a/arch/arm/mach-davinci/include/mach/hardware.h b/arch/arm/mach-davinci/include/mach/hardware.h
index c45ba1f62a11..414e0b93e741 100644
--- a/arch/arm/mach-davinci/include/mach/hardware.h
+++ b/arch/arm/mach-davinci/include/mach/hardware.h
@@ -21,9 +21,6 @@
  */
 #define DAVINCI_SYSTEM_MODULE_BASE        0x01C40000
 
-/* System control register offsets */
-#define DM64XX_VDD3P3V_PWDN	0x48
-
 /*
  * I/O mapping
  */
diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c
index 82079545adc4..1d4b65fd673e 100644
--- a/arch/arm/mach-ep93xx/core.c
+++ b/arch/arm/mach-ep93xx/core.c
@@ -402,11 +402,15 @@ static struct resource ep93xx_eth_resource[] = {
 	}
 };
 
+static u64 ep93xx_eth_dma_mask = DMA_BIT_MASK(32);
+
 static struct platform_device ep93xx_eth_device = {
 	.name		= "ep93xx-eth",
 	.id		= -1,
 	.dev		= {
-		.platform_data	= &ep93xx_eth_data,
+		.platform_data		= &ep93xx_eth_data,
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+		.dma_mask		= &ep93xx_eth_dma_mask,
 	},
 	.num_resources	= ARRAY_SIZE(ep93xx_eth_resource),
 	.resource	= ep93xx_eth_resource,
diff --git a/arch/arm/mach-exynos4/Kconfig b/arch/arm/mach-exynos4/Kconfig
index 805196207ce8..1435fc31c4b2 100644
--- a/arch/arm/mach-exynos4/Kconfig
+++ b/arch/arm/mach-exynos4/Kconfig
@@ -91,6 +91,11 @@ config EXYNOS4_SETUP_FIMC
 	help
 	  Common setup code for the camera interfaces.
 
+config EXYNOS4_SETUP_USB_PHY
+	bool
+	help
+	  Common setup code for USB PHY controller
+
 # machine support
 
 menu "EXYNOS4 Machines"
@@ -169,11 +174,14 @@ config MACH_NURI
 	select S3C_DEV_HSMMC2
 	select S3C_DEV_HSMMC3
 	select S3C_DEV_I2C1
+	select S3C_DEV_I2C3
 	select S3C_DEV_I2C5
 	select S5P_DEV_USB_EHCI
 	select EXYNOS4_SETUP_I2C1
+	select EXYNOS4_SETUP_I2C3
 	select EXYNOS4_SETUP_I2C5
 	select EXYNOS4_SETUP_SDHCI
+	select EXYNOS4_SETUP_USB_PHY
 	select SAMSUNG_DEV_PWM
 	help
 	  Machine support for Samsung Mobile NURI Board.
diff --git a/arch/arm/mach-exynos4/Makefile b/arch/arm/mach-exynos4/Makefile
index 777897551e42..60fe5ecf3599 100644
--- a/arch/arm/mach-exynos4/Makefile
+++ b/arch/arm/mach-exynos4/Makefile
@@ -13,9 +13,10 @@ obj-				:=
 # Core support for EXYNOS4 system
 
 obj-$(CONFIG_CPU_EXYNOS4210)	+= cpu.o init.o clock.o irq-combiner.o
-obj-$(CONFIG_CPU_EXYNOS4210)	+= setup-i2c0.o gpiolib.o irq-eint.o dma.o
+obj-$(CONFIG_CPU_EXYNOS4210)	+= setup-i2c0.o irq-eint.o dma.o
 obj-$(CONFIG_PM)		+= pm.o sleep.o
 obj-$(CONFIG_CPU_FREQ)		+= cpufreq.o
+obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 
 obj-$(CONFIG_SMP)		+= platsmp.o headsmp.o
 
@@ -55,4 +56,4 @@ obj-$(CONFIG_EXYNOS4_SETUP_KEYPAD)	+= setup-keypad.o
 obj-$(CONFIG_EXYNOS4_SETUP_SDHCI)	+= setup-sdhci.o
 obj-$(CONFIG_EXYNOS4_SETUP_SDHCI_GPIO)	+= setup-sdhci-gpio.o
 
-obj-$(CONFIG_USB_SUPPORT)		+= usb-phy.o
+obj-$(CONFIG_EXYNOS4_SETUP_USB_PHY)	+= setup-usb-phy.o
diff --git a/arch/arm/mach-exynos4/cpu.c b/arch/arm/mach-exynos4/cpu.c
index 08813a6f66b1..9babe4473e88 100644
--- a/arch/arm/mach-exynos4/cpu.c
+++ b/arch/arm/mach-exynos4/cpu.c
@@ -98,7 +98,7 @@ static struct map_desc exynos4_iodesc[] __initdata = {
 		.length		= SZ_4K,
 		.type		= MT_DEVICE,
 	}, {
-		.virtual	= (unsigned long)S5P_VA_USB_HSPHY,
+		.virtual	= (unsigned long)S3C_VA_USB_HSPHY,
 		.pfn		= __phys_to_pfn(EXYNOS4_PA_HSPHY),
 		.length		= SZ_4K,
 		.type		= MT_DEVICE,
diff --git a/arch/arm/mach-exynos4/cpuidle.c b/arch/arm/mach-exynos4/cpuidle.c
new file mode 100644
index 000000000000..bf7e96f2793a
--- /dev/null
+++ b/arch/arm/mach-exynos4/cpuidle.c
@@ -0,0 +1,86 @@
+/* linux/arch/arm/mach-exynos4/cpuidle.c
+ *
+ * Copyright (c) 2011 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.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/init.h>
+#include <linux/cpuidle.h>
+#include <linux/io.h>
+
+#include <asm/proc-fns.h>
+
+static int exynos4_enter_idle(struct cpuidle_device *dev,
+			      struct cpuidle_state *state);
+
+static struct cpuidle_state exynos4_cpuidle_set[] = {
+	[0] = {
+		.enter			= exynos4_enter_idle,
+		.exit_latency		= 1,
+		.target_residency	= 100000,
+		.flags			= CPUIDLE_FLAG_TIME_VALID,
+		.name			= "IDLE",
+		.desc			= "ARM clock gating(WFI)",
+	},
+};
+
+static DEFINE_PER_CPU(struct cpuidle_device, exynos4_cpuidle_device);
+
+static struct cpuidle_driver exynos4_idle_driver = {
+	.name		= "exynos4_idle",
+	.owner		= THIS_MODULE,
+};
+
+static int exynos4_enter_idle(struct cpuidle_device *dev,
+			      struct cpuidle_state *state)
+{
+	struct timeval before, after;
+	int idle_time;
+
+	local_irq_disable();
+	do_gettimeofday(&before);
+
+	cpu_do_idle();
+
+	do_gettimeofday(&after);
+	local_irq_enable();
+	idle_time = (after.tv_sec - before.tv_sec) * USEC_PER_SEC +
+		    (after.tv_usec - before.tv_usec);
+
+	return idle_time;
+}
+
+static int __init exynos4_init_cpuidle(void)
+{
+	int i, max_cpuidle_state, cpu_id;
+	struct cpuidle_device *device;
+
+	cpuidle_register_driver(&exynos4_idle_driver);
+
+	for_each_cpu(cpu_id, cpu_online_mask) {
+		device = &per_cpu(exynos4_cpuidle_device, cpu_id);
+		device->cpu = cpu_id;
+
+		device->state_count = (sizeof(exynos4_cpuidle_set) /
+					       sizeof(struct cpuidle_state));
+
+		max_cpuidle_state = device->state_count;
+
+		for (i = 0; i < max_cpuidle_state; i++) {
+			memcpy(&device->states[i], &exynos4_cpuidle_set[i],
+					sizeof(struct cpuidle_state));
+		}
+
+		if (cpuidle_register_device(device)) {
+			printk(KERN_ERR "CPUidle register device failed\n,");
+			return -EIO;
+		}
+	}
+	return 0;
+}
+device_initcall(exynos4_init_cpuidle);
diff --git a/arch/arm/mach-exynos4/include/mach/regs-usb-phy.h b/arch/arm/mach-exynos4/include/mach/regs-usb-phy.h
index 703118d5173c..c337cf3a71bf 100644
--- a/arch/arm/mach-exynos4/include/mach/regs-usb-phy.h
+++ b/arch/arm/mach-exynos4/include/mach/regs-usb-phy.h
@@ -11,7 +11,7 @@
 #ifndef __PLAT_S5P_REGS_USB_PHY_H
 #define __PLAT_S5P_REGS_USB_PHY_H
 
-#define EXYNOS4_HSOTG_PHYREG(x)		((x) + S5P_VA_USB_HSPHY)
+#define EXYNOS4_HSOTG_PHYREG(x)		((x) + S3C_VA_USB_HSPHY)
 
 #define EXYNOS4_PHYPWR			EXYNOS4_HSOTG_PHYREG(0x00)
 #define PHY1_HSIC_NORMAL_MASK		(0xf << 9)
diff --git a/arch/arm/mach-exynos4/mach-nuri.c b/arch/arm/mach-exynos4/mach-nuri.c
index bb5d12f43af8..642702bb5b12 100644
--- a/arch/arm/mach-exynos4/mach-nuri.c
+++ b/arch/arm/mach-exynos4/mach-nuri.c
@@ -12,6 +12,7 @@
 #include <linux/serial_core.h>
 #include <linux/input.h>
 #include <linux/i2c.h>
+#include <linux/i2c/atmel_mxt_ts.h>
 #include <linux/gpio_keys.h>
 #include <linux/gpio.h>
 #include <linux/regulator/machine.h>
@@ -32,6 +33,8 @@
 #include <plat/sdhci.h>
 #include <plat/ehci.h>
 #include <plat/clock.h>
+#include <plat/gpio-cfg.h>
+#include <plat/iic.h>
 
 #include <mach/map.h>
 
@@ -259,6 +262,88 @@ static struct i2c_board_info i2c1_devs[] __initdata = {
 	/* Gyro, To be updated */
 };
 
+/* TSP */
+static u8 mxt_init_vals[] = {
+	/* MXT_GEN_COMMAND(6) */
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* MXT_GEN_POWER(7) */
+	0x20, 0xff, 0x32,
+	/* MXT_GEN_ACQUIRE(8) */
+	0x0a, 0x00, 0x05, 0x00, 0x00, 0x00, 0x09, 0x23,
+	/* MXT_TOUCH_MULTI(9) */
+	0x00, 0x00, 0x00, 0x13, 0x0b, 0x00, 0x00, 0x00, 0x02, 0x00,
+	0x00, 0x01, 0x01, 0x0e, 0x0a, 0x0a, 0x0a, 0x0a, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00,
+	/* MXT_TOUCH_KEYARRAY(15) */
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00,
+	0x00,
+	/* MXT_SPT_GPIOPWM(19) */
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* MXT_PROCI_GRIPFACE(20) */
+	0x07, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x50, 0x28, 0x04,
+	0x0f, 0x0a,
+	/* MXT_PROCG_NOISE(22) */
+	0x05, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03, 0x23, 0x00,
+	0x00, 0x05, 0x0f, 0x19, 0x23, 0x2d, 0x03,
+	/* MXT_TOUCH_PROXIMITY(23) */
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00,
+	/* MXT_PROCI_ONETOUCH(24) */
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* MXT_SPT_SELFTEST(25) */
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	/* MXT_PROCI_TWOTOUCH(27) */
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* MXT_SPT_CTECONFIG(28) */
+	0x00, 0x00, 0x02, 0x08, 0x10, 0x00,
+};
+
+static struct mxt_platform_data mxt_platform_data = {
+	.config			= mxt_init_vals,
+	.config_length		= ARRAY_SIZE(mxt_init_vals),
+
+	.x_line			= 18,
+	.y_line			= 11,
+	.x_size			= 1024,
+	.y_size			= 600,
+	.blen			= 0x1,
+	.threshold		= 0x28,
+	.voltage		= 2800000,		/* 2.8V */
+	.orient			= MXT_DIAGONAL_COUNTER,
+	.irqflags		= IRQF_TRIGGER_FALLING,
+};
+
+static struct s3c2410_platform_i2c i2c3_data __initdata = {
+	.flags		= 0,
+	.bus_num	= 3,
+	.slave_addr	= 0x10,
+	.frequency	= 400 * 1000,
+	.sda_delay	= 100,
+};
+
+static struct i2c_board_info i2c3_devs[] __initdata = {
+	{
+		I2C_BOARD_INFO("atmel_mxt_ts", 0x4a),
+		.platform_data	= &mxt_platform_data,
+		.irq		= IRQ_EINT(4),
+	},
+};
+
+static void __init nuri_tsp_init(void)
+{
+	int gpio;
+
+	/* TOUCH_INT: XEINT_4 */
+	gpio = EXYNOS4_GPX0(4);
+	gpio_request(gpio, "TOUCH_INT");
+	s3c_gpio_cfgpin(gpio, S3C_GPIO_SFN(0xf));
+	s3c_gpio_setpull(gpio, S3C_GPIO_PULL_UP);
+}
+
 /* GPIO I2C 5 (PMIC) */
 static struct i2c_board_info i2c5_devs[] __initdata = {
 	/* max8997, To be updated */
@@ -283,6 +368,7 @@ static struct platform_device *nuri_devices[] __initdata = {
 	&s3c_device_wdt,
 	&s3c_device_timer[0],
 	&s5p_device_ehci,
+	&s3c_device_i2c3,
 
 	/* NURI Devices */
 	&nuri_gpio_keys,
@@ -300,8 +386,11 @@ static void __init nuri_map_io(void)
 static void __init nuri_machine_init(void)
 {
 	nuri_sdhci_init();
+	nuri_tsp_init();
 
 	i2c_register_board_info(1, i2c1_devs, ARRAY_SIZE(i2c1_devs));
+	s3c_i2c3_set_platdata(&i2c3_data);
+	i2c_register_board_info(3, i2c3_devs, ARRAY_SIZE(i2c3_devs));
 	i2c_register_board_info(5, i2c5_devs, ARRAY_SIZE(i2c5_devs));
 
 	nuri_ehci_init();
diff --git a/arch/arm/mach-exynos4/usb-phy.c b/arch/arm/mach-exynos4/setup-usb-phy.c
index 0883c1b824b9..0883c1b824b9 100644
--- a/arch/arm/mach-exynos4/usb-phy.c
+++ b/arch/arm/mach-exynos4/setup-usb-phy.c
diff --git a/arch/arm/mach-exynos4/time.c b/arch/arm/mach-exynos4/time.c
index 86b9fa0d3639..ebb8f38d5405 100644
--- a/arch/arm/mach-exynos4/time.c
+++ b/arch/arm/mach-exynos4/time.c
@@ -206,6 +206,7 @@ static cycle_t exynos4_pwm4_read(struct clocksource *cs)
 	return (cycle_t) ~__raw_readl(S3C_TIMERREG(0x40));
 }
 
+#ifdef CONFIG_PM
 static void exynos4_pwm4_resume(struct clocksource *cs)
 {
 	unsigned long pclk;
@@ -218,6 +219,7 @@ static void exynos4_pwm4_resume(struct clocksource *cs)
 	exynos4_pwm_init(4, ~0);
 	exynos4_pwm_start(4, 1);
 }
+#endif
 
 struct clocksource pwm_clocksource = {
 	.name		= "pwm_timer4",
diff --git a/arch/arm/mach-footbridge/dc21285-timer.c b/arch/arm/mach-footbridge/dc21285-timer.c
index 5f1f9867fc70..121ad1d4fa39 100644
--- a/arch/arm/mach-footbridge/dc21285-timer.c
+++ b/arch/arm/mach-footbridge/dc21285-timer.c
@@ -103,6 +103,7 @@ static void __init footbridge_timer_init(void)
 	clockevents_calc_mult_shift(ce, mem_fclk_21285, 5);
 	ce->max_delta_ns = clockevent_delta2ns(0xffffff, ce);
 	ce->min_delta_ns = clockevent_delta2ns(0x000004, ce);
+	ce->cpumask = cpumask_of(smp_processor_id());
 
 	clockevents_register_device(ce);
 }
diff --git a/arch/arm/mach-footbridge/include/mach/debug-macro.S b/arch/arm/mach-footbridge/include/mach/debug-macro.S
index 30b971d65815..1be2eeb7a0a0 100644
--- a/arch/arm/mach-footbridge/include/mach/debug-macro.S
+++ b/arch/arm/mach-footbridge/include/mach/debug-macro.S
@@ -26,6 +26,7 @@
 #include <asm/hardware/debug-8250.S>
 
 #else
+#include <mach/hardware.h>
 	/* For EBSA285 debugging */
 		.equ	dc21285_high, ARMCSR_BASE & 0xff000000
 		.equ	dc21285_low,  ARMCSR_BASE & 0x00ffffff
@@ -36,8 +37,8 @@
 		.else
 		mov	\rp, #0
 		.endif
-		orr	\rv, \rp, #0x42000000
-		orr	\rp, \rp, #dc21285_high
+		orr	\rv, \rp, #dc21285_high
+		orr	\rp, \rp, #0x42000000
 		.endm
 
 		.macro	senduart,rd,rx
diff --git a/arch/arm/mach-gemini/board-wbd111.c b/arch/arm/mach-gemini/board-wbd111.c
index af7b68a6b258..88cc422ee444 100644
--- a/arch/arm/mach-gemini/board-wbd111.c
+++ b/arch/arm/mach-gemini/board-wbd111.c
@@ -84,7 +84,6 @@ static struct sys_timer wbd111_timer = {
 	.init	= gemini_timer_init,
 };
 
-#ifdef CONFIG_MTD_PARTITIONS
 static struct mtd_partition wbd111_partitions[] = {
 	{
 		.name		= "RedBoot",
@@ -116,11 +115,7 @@ static struct mtd_partition wbd111_partitions[] = {
 		.mask_flags	= MTD_WRITEABLE,
 	}
 };
-#define wbd111_num_partitions	ARRAY_SIZE(wbd111_partitions)
-#else
-#define wbd111_partitions	NULL
-#define wbd111_num_partitions	0
-#endif /* CONFIG_MTD_PARTITIONS */
+#define wbd111_num_partitions  ARRAY_SIZE(wbd111_partitions)
 
 static void __init wbd111_init(void)
 {
diff --git a/arch/arm/mach-gemini/board-wbd222.c b/arch/arm/mach-gemini/board-wbd222.c
index 99e5bbecf923..3a220347bc88 100644
--- a/arch/arm/mach-gemini/board-wbd222.c
+++ b/arch/arm/mach-gemini/board-wbd222.c
@@ -84,7 +84,6 @@ static struct sys_timer wbd222_timer = {
 	.init	= gemini_timer_init,
 };
 
-#ifdef CONFIG_MTD_PARTITIONS
 static struct mtd_partition wbd222_partitions[] = {
 	{
 		.name		= "RedBoot",
@@ -116,11 +115,7 @@ static struct mtd_partition wbd222_partitions[] = {
 		.mask_flags	= MTD_WRITEABLE,
 	}
 };
-#define wbd222_num_partitions	ARRAY_SIZE(wbd222_partitions)
-#else
-#define wbd222_partitions	NULL
-#define wbd222_num_partitions	0
-#endif /* CONFIG_MTD_PARTITIONS */
+#define wbd222_num_partitions  ARRAY_SIZE(wbd222_partitions)
 
 static void __init wbd222_init(void)
 {
diff --git a/arch/arm/mach-h720x/Kconfig b/arch/arm/mach-h720x/Kconfig
index 9b6982efbd22..abf356c02343 100644
--- a/arch/arm/mach-h720x/Kconfig
+++ b/arch/arm/mach-h720x/Kconfig
@@ -6,12 +6,14 @@ config ARCH_H7201
 	bool "gms30c7201"
 	depends on ARCH_H720X
 	select CPU_H7201
+	select ZONE_DMA
 	help
 	  Say Y here if you are using the Hynix GMS30C7201 Reference Board
 
 config ARCH_H7202
 	bool "hms30c7202"
 	select CPU_H7202
+	select ZONE_DMA
 	depends on ARCH_H720X
 	help
 	  Say Y here if you are using the Hynix HMS30C7202 Reference Board
diff --git a/arch/arm/mach-ixp4xx/ixdp425-setup.c b/arch/arm/mach-ixp4xx/ixdp425-setup.c
index 140783386785..dca4f7f9f4f7 100644
--- a/arch/arm/mach-ixp4xx/ixdp425-setup.c
+++ b/arch/arm/mach-ixp4xx/ixdp425-setup.c
@@ -60,7 +60,6 @@ static struct platform_device ixdp425_flash = {
 #if defined(CONFIG_MTD_NAND_PLATFORM) || \
     defined(CONFIG_MTD_NAND_PLATFORM_MODULE)
 
-#ifdef CONFIG_MTD_PARTITIONS
 const char *part_probes[] = { "cmdlinepart", NULL };
 
 static struct mtd_partition ixdp425_partitions[] = {
@@ -74,7 +73,6 @@ static struct mtd_partition ixdp425_partitions[] = {
 		.size	= MTDPART_SIZ_FULL
 	},
 };
-#endif
 
 static void
 ixdp425_flash_nand_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl)
@@ -103,11 +101,9 @@ static struct platform_nand_data ixdp425_flash_nand_data = {
 		.nr_chips		= 1,
 		.chip_delay		= 30,
 		.options		= NAND_NO_AUTOINCR,
-#ifdef CONFIG_MTD_PARTITIONS
 		.part_probe_types 	= part_probes,
 		.partitions	 	= ixdp425_partitions,
 		.nr_partitions	 	= ARRAY_SIZE(ixdp425_partitions),
-#endif
 	},
 	.ctrl = {
 		.cmd_ctrl 		= ixdp425_flash_nand_cmd_ctrl
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 38b95e949d13..63621f152c98 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -23,6 +23,8 @@
 #include <linux/io.h>
 
 #include <asm/mach/time.h>
+#include <asm/hardware/gic.h>
+
 #include <mach/msm_iomap.h>
 #include <mach/cpu.h>
 
@@ -55,10 +57,12 @@ enum timer_location {
 #if defined(CONFIG_ARCH_QSD8X50)
 #define DGT_HZ (19200000 / 4) /* 19.2 MHz / 4 by default */
 #define MSM_DGT_SHIFT (0)
-#elif defined(CONFIG_ARCH_MSM7X30) || defined(CONFIG_ARCH_MSM8X60) || \
-				      defined(CONFIG_ARCH_MSM8960)
+#elif defined(CONFIG_ARCH_MSM7X30)
 #define DGT_HZ (24576000 / 4) /* 24.576 MHz (LPXO) / 4 by default */
 #define MSM_DGT_SHIFT (0)
+#elif defined(CONFIG_ARCH_MSM8X60) || defined(CONFIG_ARCH_MSM8960)
+#define DGT_HZ (27000000 / 4) /* 27 MHz (PXO) / 4 by default */
+#define MSM_DGT_SHIFT (0)
 #else
 #define DGT_HZ 19200000 /* 19.2 MHz or 600 KHz after shift */
 #define MSM_DGT_SHIFT (5)
@@ -100,7 +104,11 @@ static cycle_t msm_read_timer_count(struct clocksource *cs)
 {
 	struct msm_clock *clk = container_of(cs, struct msm_clock, clocksource);
 
-	return readl(clk->global_counter);
+	/*
+	 * Shift timer count down by a constant due to unreliable lower bits
+	 * on some targets.
+	 */
+	return readl(clk->global_counter) >> clk->shift;
 }
 
 static struct msm_clock *clockevent_to_clock(struct clock_event_device *evt)
diff --git a/arch/arm/mach-mxs/ocotp.c b/arch/arm/mach-mxs/ocotp.c
index 65157a35dbba..54add60f94c9 100644
--- a/arch/arm/mach-mxs/ocotp.c
+++ b/arch/arm/mach-mxs/ocotp.c
@@ -16,6 +16,8 @@
 #include <linux/err.h>
 #include <linux/mutex.h>
 
+#include <asm/processor.h>	/* for cpu_relax() */
+
 #include <mach/mxs.h>
 
 #define OCOTP_WORD_OFFSET		0x20
diff --git a/arch/arm/mach-netx/fb.c b/arch/arm/mach-netx/fb.c
index 5b84bcd30271..b9913234bbf6 100644
--- a/arch/arm/mach-netx/fb.c
+++ b/arch/arm/mach-netx/fb.c
@@ -103,7 +103,6 @@ static struct amba_device fb_device = {
 		.flags	= IORESOURCE_MEM,
 	},
 	.irq		= { NETX_IRQ_LCD, NO_IRQ },
-	.periphid	= 0x10112400,
 };
 
 int netx_fb_init(struct clcd_board *board, struct clcd_panel *panel)
diff --git a/arch/arm/mach-nomadik/Kconfig b/arch/arm/mach-nomadik/Kconfig
index 71f3ea623974..3c5e0f522e9c 100644
--- a/arch/arm/mach-nomadik/Kconfig
+++ b/arch/arm/mach-nomadik/Kconfig
@@ -6,7 +6,6 @@ config MACH_NOMADIK_8815NHK
 	bool "ST 8815 Nomadik Hardware Kit (evaluation board)"
 	select NOMADIK_8815
 	select HAS_MTU
-	select NOMADIK_GPIO
 
 endmenu
 
diff --git a/arch/arm/mach-omap1/Makefile b/arch/arm/mach-omap1/Makefile
index af98117043d2..5b114d1558c8 100644
--- a/arch/arm/mach-omap1/Makefile
+++ b/arch/arm/mach-omap1/Makefile
@@ -4,14 +4,14 @@
 
 # Common support
 obj-y := io.o id.o sram.o time.o irq.o mux.o flash.o serial.o devices.o dma.o
-obj-y += clock.o clock_data.o opp_data.o reset.o
+obj-y += clock.o clock_data.o opp_data.o reset.o pm_bus.o
 
 obj-$(CONFIG_OMAP_MCBSP) += mcbsp.o
 
 obj-$(CONFIG_OMAP_32K_TIMER)	+= timer32k.o
 
 # Power Management
-obj-$(CONFIG_PM) += pm.o sleep.o pm_bus.o
+obj-$(CONFIG_PM) += pm.o sleep.o
 
 # DSP
 obj-$(CONFIG_OMAP_MBOX_FWK)	+= mailbox_mach.o
diff --git a/arch/arm/mach-omap1/dma.c b/arch/arm/mach-omap1/dma.c
index d8559344c6e2..f5a52204b89f 100644
--- a/arch/arm/mach-omap1/dma.c
+++ b/arch/arm/mach-omap1/dma.c
@@ -284,14 +284,15 @@ static int __init omap1_system_dma_init(void)
 	dma_base = ioremap(res[0].start, resource_size(&res[0]));
 	if (!dma_base) {
 		pr_err("%s: Unable to ioremap\n", __func__);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto exit_device_put;
 	}
 
 	ret = platform_device_add_resources(pdev, res, ARRAY_SIZE(res));
 	if (ret) {
 		dev_err(&pdev->dev, "%s: Unable to add resources for %s%d\n",
 			__func__, pdev->name, pdev->id);
-		goto exit_device_del;
+		goto exit_device_put;
 	}
 
 	p = kzalloc(sizeof(struct omap_system_dma_plat_info), GFP_KERNEL);
@@ -299,7 +300,7 @@ static int __init omap1_system_dma_init(void)
 		dev_err(&pdev->dev, "%s: Unable to allocate 'p' for %s\n",
 			__func__, pdev->name);
 		ret = -ENOMEM;
-		goto exit_device_put;
+		goto exit_device_del;
 	}
 
 	d = kzalloc(sizeof(struct omap_dma_dev_attr), GFP_KERNEL);
@@ -380,10 +381,10 @@ exit_release_d:
 	kfree(d);
 exit_release_p:
 	kfree(p);
-exit_device_put:
-	platform_device_put(pdev);
 exit_device_del:
 	platform_device_del(pdev);
+exit_device_put:
+	platform_device_put(pdev);
 
 	return ret;
 }
diff --git a/arch/arm/mach-omap1/pm_bus.c b/arch/arm/mach-omap1/pm_bus.c
index fe31d933f0ed..334fb8871bc3 100644
--- a/arch/arm/mach-omap1/pm_bus.c
+++ b/arch/arm/mach-omap1/pm_bus.c
@@ -56,9 +56,13 @@ static struct dev_power_domain default_power_domain = {
 		USE_PLATFORM_PM_SLEEP_OPS
 	},
 };
+#define OMAP1_PWR_DOMAIN (&default_power_domain)
+#else
+#define OMAP1_PWR_DOMAIN NULL
+#endif /* CONFIG_PM_RUNTIME */
 
 static struct pm_clk_notifier_block platform_bus_notifier = {
-	.pwr_domain = &default_power_domain,
+	.pwr_domain = OMAP1_PWR_DOMAIN,
 	.con_ids = { "ick", "fck", NULL, },
 };
 
@@ -72,4 +76,4 @@ static int __init omap1_pm_runtime_init(void)
 	return 0;
 }
 core_initcall(omap1_pm_runtime_init);
-#endif /* CONFIG_PM_RUNTIME */
+
diff --git a/arch/arm/mach-omap2/board-2430sdp.c b/arch/arm/mach-omap2/board-2430sdp.c
index d54969be0a54..5de6eac0a725 100644
--- a/arch/arm/mach-omap2/board-2430sdp.c
+++ b/arch/arm/mach-omap2/board-2430sdp.c
@@ -26,13 +26,13 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/gpio.h>
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <mach/gpio.h>
 #include <plat/board.h>
 #include <plat/common.h>
 #include <plat/gpmc.h>
diff --git a/arch/arm/mach-omap2/board-3430sdp.c b/arch/arm/mach-omap2/board-3430sdp.c
index ae2963a98041..5dac974be625 100644
--- a/arch/arm/mach-omap2/board-3430sdp.c
+++ b/arch/arm/mach-omap2/board-3430sdp.c
@@ -622,19 +622,19 @@ static struct omap_device_pad serial3_pads[] __initdata = {
 			 OMAP_MUX_MODE0),
 };
 
-static struct omap_board_data serial1_data = {
+static struct omap_board_data serial1_data __initdata = {
 	.id		= 0,
 	.pads		= serial1_pads,
 	.pads_cnt	= ARRAY_SIZE(serial1_pads),
 };
 
-static struct omap_board_data serial2_data = {
+static struct omap_board_data serial2_data __initdata = {
 	.id		= 1,
 	.pads		= serial2_pads,
 	.pads_cnt	= ARRAY_SIZE(serial2_pads),
 };
 
-static struct omap_board_data serial3_data = {
+static struct omap_board_data serial3_data __initdata = {
 	.id		= 2,
 	.pads		= serial3_pads,
 	.pads_cnt	= ARRAY_SIZE(serial3_pads),
diff --git a/arch/arm/mach-omap2/board-4430sdp.c b/arch/arm/mach-omap2/board-4430sdp.c
index 73fa90bb6953..63de2d396e2d 100644
--- a/arch/arm/mach-omap2/board-4430sdp.c
+++ b/arch/arm/mach-omap2/board-4430sdp.c
@@ -258,7 +258,7 @@ static struct gpio sdp4430_eth_gpios[] __initdata = {
 	{ ETH_KS8851_IRQ,	GPIOF_IN,		"eth_irq"	},
 };
 
-static int omap_ethernet_init(void)
+static int __init omap_ethernet_init(void)
 {
 	int status;
 
@@ -322,6 +322,7 @@ static struct omap2_hsmmc_info mmc[] = {
 		.gpio_wp	= -EINVAL,
 		.nonremovable   = true,
 		.ocr_mask	= MMC_VDD_29_30,
+		.no_off_init	= true,
 	},
 	{
 		.mmc		= 1,
@@ -681,19 +682,19 @@ static struct omap_device_pad serial4_pads[] __initdata = {
 			 OMAP_PIN_OUTPUT | OMAP_MUX_MODE0),
 };
 
-static struct omap_board_data serial2_data = {
+static struct omap_board_data serial2_data __initdata = {
 	.id		= 1,
 	.pads		= serial2_pads,
 	.pads_cnt	= ARRAY_SIZE(serial2_pads),
 };
 
-static struct omap_board_data serial3_data = {
+static struct omap_board_data serial3_data __initdata = {
 	.id		= 2,
 	.pads		= serial3_pads,
 	.pads_cnt	= ARRAY_SIZE(serial3_pads),
 };
 
-static struct omap_board_data serial4_data = {
+static struct omap_board_data serial4_data __initdata = {
 	.id		= 3,
 	.pads		= serial4_pads,
 	.pads_cnt	= ARRAY_SIZE(serial4_pads),
@@ -729,7 +730,7 @@ static void __init omap_4430sdp_init(void)
 
 	if (omap_rev() == OMAP4430_REV_ES1_0)
 		package = OMAP_PACKAGE_CBL;
-	omap4_mux_init(board_mux, package);
+	omap4_mux_init(board_mux, NULL, package);
 
 	omap_board_config = sdp4430_config;
 	omap_board_config_size = ARRAY_SIZE(sdp4430_config);
diff --git a/arch/arm/mach-omap2/board-apollon.c b/arch/arm/mach-omap2/board-apollon.c
index f3beb8eeef77..b124bdfb4239 100644
--- a/arch/arm/mach-omap2/board-apollon.c
+++ b/arch/arm/mach-omap2/board-apollon.c
@@ -27,13 +27,13 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/smc91x.h>
+#include <linux/gpio.h>
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 
-#include <mach/gpio.h>
 #include <plat/led.h>
 #include <plat/usb.h>
 #include <plat/board.h>
diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c
index c63115bc1536..77456dec93ea 100644
--- a/arch/arm/mach-omap2/board-cm-t35.c
+++ b/arch/arm/mach-omap2/board-cm-t35.c
@@ -63,8 +63,6 @@
 #define SB_T35_SMSC911X_CS	4
 #define SB_T35_SMSC911X_GPIO	65
 
-#define NAND_BLOCK_SIZE		SZ_128K
-
 #if defined(CONFIG_SMSC911X) || defined(CONFIG_SMSC911X_MODULE)
 #include <linux/smsc911x.h>
 #include <plat/gpmc-smsc911x.h>
diff --git a/arch/arm/mach-omap2/board-cm-t3517.c b/arch/arm/mach-omap2/board-cm-t3517.c
index 08f08e812492..c3a9fd35034a 100644
--- a/arch/arm/mach-omap2/board-cm-t3517.c
+++ b/arch/arm/mach-omap2/board-cm-t3517.c
@@ -48,6 +48,7 @@
 
 #include "mux.h"
 #include "control.h"
+#include "common-board-devices.h"
 
 #if defined(CONFIG_LEDS_GPIO) || defined(CONFIG_LEDS_GPIO_MODULE)
 static struct gpio_led cm_t3517_leds[] = {
@@ -177,7 +178,7 @@ static struct usbhs_omap_board_data cm_t3517_ehci_pdata __initdata = {
 	.reset_gpio_port[2]  = -EINVAL,
 };
 
-static int cm_t3517_init_usbh(void)
+static int __init cm_t3517_init_usbh(void)
 {
 	int err;
 
@@ -203,8 +204,6 @@ static inline int cm_t3517_init_usbh(void)
 #endif
 
 #if defined(CONFIG_MTD_NAND_OMAP2) || defined(CONFIG_MTD_NAND_OMAP2_MODULE)
-#define NAND_BLOCK_SIZE		SZ_128K
-
 static struct mtd_partition cm_t3517_nand_partitions[] = {
 	{
 		.name           = "xloader",
diff --git a/arch/arm/mach-omap2/board-devkit8000.c b/arch/arm/mach-omap2/board-devkit8000.c
index cf520d7dd614..34956ec83296 100644
--- a/arch/arm/mach-omap2/board-devkit8000.c
+++ b/arch/arm/mach-omap2/board-devkit8000.c
@@ -61,8 +61,6 @@
 #include "timer-gp.h"
 #include "common-board-devices.h"
 
-#define NAND_BLOCK_SIZE		SZ_128K
-
 #define OMAP_DM9000_GPIO_IRQ	25
 #define OMAP3_DEVKIT_TS_GPIO	27
 
diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c
index be71426359f2..7f21d24bd437 100644
--- a/arch/arm/mach-omap2/board-omap3beagle.c
+++ b/arch/arm/mach-omap2/board-omap3beagle.c
@@ -54,8 +54,6 @@
 #include "pm.h"
 #include "common-board-devices.h"
 
-#define NAND_BLOCK_SIZE		SZ_128K
-
 /*
  * OMAP3 Beagle revision
  * Run time detection of Beagle revision is done by reading GPIO.
@@ -106,6 +104,9 @@ static void __init omap3_beagle_init_rev(void)
 	beagle_rev = gpio_get_value(171) | (gpio_get_value(172) << 1)
 			| (gpio_get_value(173) << 2);
 
+	gpio_free_array(omap3_beagle_rev_gpios,
+			ARRAY_SIZE(omap3_beagle_rev_gpios));
+
 	switch (beagle_rev) {
 	case 7:
 		printk(KERN_INFO "OMAP3 Beagle Rev: Ax/Bx\n");
@@ -579,6 +580,9 @@ static void __init omap3_beagle_init(void)
 	omap_nand_flash_init(NAND_BUSWIDTH_16, omap3beagle_nand_partitions,
 			     ARRAY_SIZE(omap3beagle_nand_partitions));
 
+	/* Ensure msecure is mux'd to be able to set the RTC. */
+	omap_mux_init_signal("sys_drm_msecure", OMAP_PIN_OFF_OUTPUT_HIGH);
+
 	/* Ensure SDRC pins are mux'd for self-refresh */
 	omap_mux_init_signal("sdrc_cke0", OMAP_PIN_OUTPUT);
 	omap_mux_init_signal("sdrc_cke1", OMAP_PIN_OUTPUT);
diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c
index 1d10736c6d3c..23f71d40883e 100644
--- a/arch/arm/mach-omap2/board-omap3pandora.c
+++ b/arch/arm/mach-omap2/board-omap3pandora.c
@@ -30,6 +30,7 @@
 #include <linux/leds.h>
 #include <linux/input.h>
 #include <linux/input/matrix_keypad.h>
+#include <linux/gpio.h>
 #include <linux/gpio_keys.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/card.h>
@@ -41,7 +42,6 @@
 
 #include <plat/board.h>
 #include <plat/common.h>
-#include <mach/gpio.h>
 #include <mach/hardware.h>
 #include <plat/mcspi.h>
 #include <plat/usb.h>
@@ -57,8 +57,6 @@
 #define PANDORA_WIFI_NRESET_GPIO	23
 #define OMAP3_PANDORA_TS_GPIO		94
 
-#define NAND_BLOCK_SIZE			SZ_128K
-
 static struct mtd_partition omap3pandora_nand_partitions[] = {
 	{
 		.name           = "xloader",
@@ -86,7 +84,8 @@ static struct mtd_partition omap3pandora_nand_partitions[] = {
 
 static struct omap_nand_platform_data pandora_nand_data = {
 	.cs		= 0,
-	.devsize	= 1,	/* '0' for 8-bit, '1' for 16-bit device */
+	.devsize	= NAND_BUSWIDTH_16,
+	.xfer_type	= NAND_OMAP_PREFETCH_DMA,
 	.parts		= omap3pandora_nand_partitions,
 	.nr_parts	= ARRAY_SIZE(omap3pandora_nand_partitions),
 };
diff --git a/arch/arm/mach-omap2/board-omap3touchbook.c b/arch/arm/mach-omap2/board-omap3touchbook.c
index 82872d7d313b..5f649faf7377 100644
--- a/arch/arm/mach-omap2/board-omap3touchbook.c
+++ b/arch/arm/mach-omap2/board-omap3touchbook.c
@@ -56,8 +56,6 @@
 
 #include <asm/setup.h>
 
-#define NAND_BLOCK_SIZE		SZ_128K
-
 #define OMAP3_AC_GPIO		136
 #define OMAP3_TS_GPIO		162
 #define TB_BL_PWM_TIMER		9
diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c
index 90485fced973..0cfe2005cb50 100644
--- a/arch/arm/mach-omap2/board-omap4panda.c
+++ b/arch/arm/mach-omap2/board-omap4panda.c
@@ -526,19 +526,19 @@ static struct omap_device_pad serial4_pads[] __initdata = {
 			 OMAP_PIN_OUTPUT | OMAP_MUX_MODE0),
 };
 
-static struct omap_board_data serial2_data = {
+static struct omap_board_data serial2_data __initdata = {
 	.id             = 1,
 	.pads           = serial2_pads,
 	.pads_cnt       = ARRAY_SIZE(serial2_pads),
 };
 
-static struct omap_board_data serial3_data = {
+static struct omap_board_data serial3_data __initdata = {
 	.id             = 2,
 	.pads           = serial3_pads,
 	.pads_cnt       = ARRAY_SIZE(serial3_pads),
 };
 
-static struct omap_board_data serial4_data = {
+static struct omap_board_data serial4_data __initdata = {
 	.id             = 3,
 	.pads           = serial4_pads,
 	.pads_cnt       = ARRAY_SIZE(serial4_pads),
@@ -687,7 +687,7 @@ static void __init omap4_panda_init(void)
 
 	if (omap_rev() == OMAP4430_REV_ES1_0)
 		package = OMAP_PACKAGE_CBL;
-	omap4_mux_init(board_mux, package);
+	omap4_mux_init(board_mux, NULL, package);
 
 	if (wl12xx_set_platform_data(&omap_panda_wlan_data))
 		pr_err("error setting wl12xx data\n");
diff --git a/arch/arm/mach-omap2/board-overo.c b/arch/arm/mach-omap2/board-overo.c
index 1555918e3ffa..175e1ab2b04d 100644
--- a/arch/arm/mach-omap2/board-overo.c
+++ b/arch/arm/mach-omap2/board-overo.c
@@ -24,6 +24,7 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/gpio.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/i2c/twl.h>
@@ -45,7 +46,6 @@
 #include <plat/common.h>
 #include <video/omapdss.h>
 #include <video/omap-panel-generic-dpi.h>
-#include <mach/gpio.h>
 #include <plat/gpmc.h>
 #include <mach/hardware.h>
 #include <plat/nand.h>
@@ -65,8 +65,6 @@
 #define OVERO_GPIO_USBH_CPEN	168
 #define OVERO_GPIO_USBH_NRESET	183
 
-#define NAND_BLOCK_SIZE SZ_128K
-
 #define OVERO_SMSC911X_CS      5
 #define OVERO_SMSC911X_GPIO    176
 #define OVERO_SMSC911X2_CS     4
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index 2b00f72e8e36..990366726c58 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -23,6 +23,7 @@
 #include <linux/gpio.h>
 #include <linux/gpio_keys.h>
 #include <linux/mmc/host.h>
+#include <linux/power/isp1704_charger.h>
 
 #include <plat/mcspi.h>
 #include <plat/board.h>
@@ -53,6 +54,8 @@
 #define RX51_FMTX_RESET_GPIO		163
 #define RX51_FMTX_IRQ			53
 
+#define RX51_USB_TRANSCEIVER_RST_GPIO	67
+
 /* list all spi devices here */
 enum {
 	RX51_SPI_WL1251,
@@ -111,10 +114,30 @@ static struct spi_board_info rx51_peripherals_spi_board_info[] __initdata = {
 	},
 };
 
+static void rx51_charger_set_power(bool on)
+{
+	gpio_set_value(RX51_USB_TRANSCEIVER_RST_GPIO, on);
+}
+
+static struct isp1704_charger_data rx51_charger_data = {
+	.set_power	= rx51_charger_set_power,
+};
+
 static struct platform_device rx51_charger_device = {
-	.name = "isp1704_charger",
+	.name	= "isp1704_charger",
+	.dev	= {
+		.platform_data = &rx51_charger_data,
+	},
 };
 
+static void __init rx51_charger_init(void)
+{
+	WARN_ON(gpio_request_one(RX51_USB_TRANSCEIVER_RST_GPIO,
+		GPIOF_OUT_INIT_LOW, "isp1704_reset"));
+
+	platform_device_register(&rx51_charger_device);
+}
+
 #if defined(CONFIG_KEYBOARD_GPIO) || defined(CONFIG_KEYBOARD_GPIO_MODULE)
 
 #define RX51_GPIO_CAMERA_LENS_COVER	110
@@ -465,6 +488,7 @@ static struct regulator_init_data rx51_vmmc2 = {
 		.name			= "V28_A",
 		.min_uV			= 2800000,
 		.max_uV			= 3000000,
+		.always_on		= true, /* due VIO leak to AIC34 VDDs */
 		.apply_uV		= true,
 		.valid_modes_mask	= REGULATOR_MODE_NORMAL
 					| REGULATOR_MODE_STANDBY,
@@ -559,7 +583,7 @@ static int rx51_twlgpio_setup(struct device *dev, unsigned gpio, unsigned n)
 {
 	/* FIXME this gpio setup is just a placeholder for now */
 	gpio_request_one(gpio + 6, GPIOF_OUT_INIT_LOW, "backlight_pwm");
-	gpio_request_one(gpio + 7, GPIOF_OUT_INIT_HIGH, "speaker_en");
+	gpio_request_one(gpio + 7, GPIOF_OUT_INIT_LOW, "speaker_en");
 
 	return 0;
 }
@@ -961,6 +985,6 @@ void __init rx51_peripherals_init(void)
 	if (partition)
 		omap2_hsmmc_init(mmc);
 
-	platform_device_register(&rx51_charger_device);
+	rx51_charger_init();
 }
 
diff --git a/arch/arm/mach-omap2/board-zoom-display.c b/arch/arm/mach-omap2/board-zoom-display.c
index c7c6beb1ec24..d4683ba5f721 100644
--- a/arch/arm/mach-omap2/board-zoom-display.c
+++ b/arch/arm/mach-omap2/board-zoom-display.c
@@ -26,7 +26,7 @@ static struct gpio zoom_lcd_gpios[] __initdata = {
 	{ LCD_PANEL_QVGA_GPIO,	GPIOF_OUT_INIT_HIGH, "lcd qvga"	 },
 };
 
-static void zoom_lcd_panel_init(void)
+static void __init zoom_lcd_panel_init(void)
 {
 	zoom_lcd_gpios[0].gpio = (omap_rev() > OMAP3430_REV_ES3_0) ?
 			LCD_PANEL_RESET_GPIO_PROD :
diff --git a/arch/arm/mach-omap2/common-board-devices.c b/arch/arm/mach-omap2/common-board-devices.c
index e94903b2c65b..94ccf464677b 100644
--- a/arch/arm/mach-omap2/common-board-devices.c
+++ b/arch/arm/mach-omap2/common-board-devices.c
@@ -85,17 +85,17 @@ void __init omap_ads7846_init(int bus_num, int gpio_pendown, int gpio_debounce,
 	struct spi_board_info *spi_bi = &ads7846_spi_board_info;
 	int err;
 
-	err = gpio_request(gpio_pendown, "TS PenDown");
-	if (err) {
-		pr_err("Could not obtain gpio for TS PenDown: %d\n", err);
-		return;
-	}
-
-	gpio_direction_input(gpio_pendown);
-	gpio_export(gpio_pendown, 0);
+	if (board_pdata && board_pdata->get_pendown_state) {
+		err = gpio_request_one(gpio_pendown, GPIOF_IN, "TSPenDown");
+		if (err) {
+			pr_err("Couldn't obtain gpio for TSPenDown: %d\n", err);
+			return;
+		}
+		gpio_export(gpio_pendown, 0);
 
-	if (gpio_debounce)
-		gpio_set_debounce(gpio_pendown, gpio_debounce);
+		if (gpio_debounce)
+			gpio_set_debounce(gpio_pendown, gpio_debounce);
+	}
 
 	ads7846_config.gpio_pendown = gpio_pendown;
 
diff --git a/arch/arm/mach-omap2/common-board-devices.h b/arch/arm/mach-omap2/common-board-devices.h
index eb80b3b0ef47..679719051df5 100644
--- a/arch/arm/mach-omap2/common-board-devices.h
+++ b/arch/arm/mach-omap2/common-board-devices.h
@@ -1,6 +1,8 @@
 #ifndef __OMAP_COMMON_BOARD_DEVICES__
 #define __OMAP_COMMON_BOARD_DEVICES__
 
+#define NAND_BLOCK_SIZE	SZ_128K
+
 struct twl4030_platform_data;
 struct mtd_partition;
 
diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c
index 7b8558564591..5b8ca680ed93 100644
--- a/arch/arm/mach-omap2/devices.c
+++ b/arch/arm/mach-omap2/devices.c
@@ -97,7 +97,7 @@ static int __init omap4_l3_init(void)
 
 	WARN(IS_ERR(od), "could not build omap_device for %s\n", oh_name);
 
-	return PTR_ERR(od);
+	return IS_ERR(od) ? PTR_ERR(od) : 0;
 }
 postcore_initcall(omap4_l3_init);
 
diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c
index b2f30bed5a20..66868c5d5a29 100644
--- a/arch/arm/mach-omap2/hsmmc.c
+++ b/arch/arm/mach-omap2/hsmmc.c
@@ -145,6 +145,7 @@ static void omap4_hsmmc1_after_set_reg(struct device *dev, int slot,
 				 int power_on, int vdd)
 {
 	u32 reg;
+	unsigned long timeout;
 
 	if (power_on) {
 		reg = omap4_ctrl_pad_readl(control_pbias_offset);
@@ -157,9 +158,15 @@ static void omap4_hsmmc1_after_set_reg(struct device *dev, int slot,
 			OMAP4_MMC1_PWRDNZ_MASK |
 			OMAP4_USBC1_ICUSB_PWRDNZ_MASK);
 		omap4_ctrl_pad_writel(reg, control_pbias_offset);
-		/* 4 microsec delay for comparator to generate an error*/
-		udelay(4);
-		reg = omap4_ctrl_pad_readl(control_pbias_offset);
+
+		timeout = jiffies + msecs_to_jiffies(5);
+		do {
+			reg = omap4_ctrl_pad_readl(control_pbias_offset);
+			if (!(reg & OMAP4_MMC1_PBIASLITE_VMODE_ERROR_MASK))
+				break;
+			usleep_range(100, 200);
+		} while (!time_after(jiffies, timeout));
+
 		if (reg & OMAP4_MMC1_PBIASLITE_VMODE_ERROR_MASK) {
 			pr_err("Pbias Voltage is not same as LDO\n");
 			/* Caution : On VMODE_ERROR Power Down MMC IO */
@@ -331,6 +338,9 @@ static int __init omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c,
 	if (c->no_off)
 		mmc->slots[0].no_off = 1;
 
+	if (c->no_off_init)
+		mmc->slots[0].no_regulator_off_init = c->no_off_init;
+
 	if (c->vcc_aux_disable_is_sleep)
 		mmc->slots[0].vcc_aux_disable_is_sleep = 1;
 
diff --git a/arch/arm/mach-omap2/hsmmc.h b/arch/arm/mach-omap2/hsmmc.h
index f119348827d4..f757e78d4d4f 100644
--- a/arch/arm/mach-omap2/hsmmc.h
+++ b/arch/arm/mach-omap2/hsmmc.h
@@ -18,6 +18,7 @@ struct omap2_hsmmc_info {
 	bool	nonremovable;	/* Nonremovable e.g. eMMC */
 	bool	power_saving;	/* Try to sleep or power off when possible */
 	bool	no_off;		/* power_saving and power is not to go off */
+	bool	no_off_init;	/* no power off when not in MMC sleep state */
 	bool	vcc_aux_disable_is_sleep; /* Regulator off remapped to sleep */
 	int	gpio_cd;	/* or -EINVAL */
 	int	gpio_wp;	/* or -EINVAL */
diff --git a/arch/arm/mach-omap2/mux.c b/arch/arm/mach-omap2/mux.c
index a4ab1e364313..c7fb22abc219 100644
--- a/arch/arm/mach-omap2/mux.c
+++ b/arch/arm/mach-omap2/mux.c
@@ -83,6 +83,9 @@ void omap_mux_write(struct omap_mux_partition *partition, u16 val,
 void omap_mux_write_array(struct omap_mux_partition *partition,
 				 struct omap_board_mux *board_mux)
 {
+	if (!board_mux)
+		return;
+
 	while (board_mux->reg_offset != OMAP_MUX_TERMINATOR) {
 		omap_mux_write(partition, board_mux->value,
 			       board_mux->reg_offset);
@@ -906,7 +909,7 @@ static struct omap_mux *omap_mux_get_by_gpio(
 u16 omap_mux_get_gpio(int gpio)
 {
 	struct omap_mux_partition *partition;
-	struct omap_mux *m;
+	struct omap_mux *m = NULL;
 
 	list_for_each_entry(partition, &mux_partitions, node) {
 		m = omap_mux_get_by_gpio(partition, gpio);
diff --git a/arch/arm/mach-omap2/mux.h b/arch/arm/mach-omap2/mux.h
index 137f321c029f..2132308ad1e4 100644
--- a/arch/arm/mach-omap2/mux.h
+++ b/arch/arm/mach-omap2/mux.h
@@ -323,10 +323,12 @@ int omap3_mux_init(struct omap_board_mux *board_mux, int flags);
 
 /**
  * omap4_mux_init() - initialize mux system with board specific set
- * @board_mux:		Board specific mux table
+ * @board_subset:	Board specific mux table
+ * @board_wkup_subset:	Board specific mux table for wakeup instance
  * @flags:		OMAP package type used for the board
  */
-int omap4_mux_init(struct omap_board_mux *board_mux, int flags);
+int omap4_mux_init(struct omap_board_mux *board_subset,
+	struct omap_board_mux *board_wkup_subset, int flags);
 
 /**
  * omap_mux_init - private mux init function, do not call
diff --git a/arch/arm/mach-omap2/mux44xx.c b/arch/arm/mach-omap2/mux44xx.c
index 9a66445112ae..f5a74daab2ff 100644
--- a/arch/arm/mach-omap2/mux44xx.c
+++ b/arch/arm/mach-omap2/mux44xx.c
@@ -1309,7 +1309,8 @@ static struct omap_ball __initdata omap4_wkup_cbl_cbs_ball[] = {
 #define omap4_wkup_cbl_cbs_ball  NULL
 #endif
 
-int __init omap4_mux_init(struct omap_board_mux *board_subset, int flags)
+int __init omap4_mux_init(struct omap_board_mux *board_subset,
+	struct omap_board_mux *board_wkup_subset, int flags)
 {
 	struct omap_ball *package_balls_core;
 	struct omap_ball *package_balls_wkup = omap4_wkup_cbl_cbs_ball;
@@ -1347,7 +1348,7 @@ int __init omap4_mux_init(struct omap_board_mux *board_subset, int flags)
 			    OMAP_MUX_GPIO_IN_MODE3,
 			    OMAP4_CTRL_MODULE_PAD_WKUP_MUX_PBASE,
 			    OMAP4_CTRL_MODULE_PAD_WKUP_MUX_SIZE,
-			    omap4_wkup_muxmodes, NULL, board_subset,
+			    omap4_wkup_muxmodes, NULL, board_wkup_subset,
 			    package_balls_wkup);
 
 	return ret;
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index e03429453ce7..293fa6cd50e1 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1628,7 +1628,7 @@ int omap_hwmod_for_each(int (*fn)(struct omap_hwmod *oh, void *data),
 			void *data)
 {
 	struct omap_hwmod *temp_oh;
-	int ret;
+	int ret = 0;
 
 	if (!fn)
 		return -EINVAL;
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index abc548a0c98d..e1c69ffe0f69 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -5109,7 +5109,7 @@ static __initdata struct omap_hwmod *omap44xx_hwmods[] = {
 	&omap44xx_iva_seq1_hwmod,
 
 	/* kbd class */
-/*	&omap44xx_kbd_hwmod, */
+	&omap44xx_kbd_hwmod,
 
 	/* mailbox class */
 	&omap44xx_mailbox_hwmod,
diff --git a/arch/arm/mach-omap2/omap_phy_internal.c b/arch/arm/mach-omap2/omap_phy_internal.c
index f47813edd951..58775e3c8476 100644
--- a/arch/arm/mach-omap2/omap_phy_internal.c
+++ b/arch/arm/mach-omap2/omap_phy_internal.c
@@ -56,8 +56,10 @@ int omap4430_phy_init(struct device *dev)
 	/* Power down the phy */
 	__raw_writel(PHY_PD, ctrl_base + CONTROL_DEV_CONF);
 
-	if (!dev)
+	if (!dev) {
+		iounmap(ctrl_base);
 		return 0;
+	}
 
 	phyclk = clk_get(dev, "ocp2scp_usb_phy_ick");
 	if (IS_ERR(phyclk)) {
diff --git a/arch/arm/mach-omap2/pm-debug.c b/arch/arm/mach-omap2/pm-debug.c
index a5a83b358ddd..e01da45c0537 100644
--- a/arch/arm/mach-omap2/pm-debug.c
+++ b/arch/arm/mach-omap2/pm-debug.c
@@ -189,7 +189,7 @@ static struct dentry *pm_dbg_dir;
 
 static int pm_dbg_init_done;
 
-static int __init pm_dbg_init(void);
+static int pm_dbg_init(void);
 
 enum {
 	DEBUG_FILE_COUNTERS = 0,
@@ -595,7 +595,7 @@ static int option_set(void *data, u64 val)
 
 DEFINE_SIMPLE_ATTRIBUTE(pm_dbg_option_fops, option_get, option_set, "%llu\n");
 
-static int __init pm_dbg_init(void)
+static int pm_dbg_init(void)
 {
 	int i;
 	struct dentry *d;
diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig
index 2fc9f94cdd29..cd19309fd3b8 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -153,7 +153,6 @@ config MACH_XCEP
 	bool "Iskratel Electronics XCEP"
 	select PXA25x
 	select MTD
-	select MTD_PARTITIONS
 	select MTD_PHYSMAP
 	select MTD_CFI_INTELEXT
 	select MTD_CFI
diff --git a/arch/arm/mach-pxa/spitz_pm.c b/arch/arm/mach-pxa/spitz_pm.c
index 7fe74067d85f..094279aefe9c 100644
--- a/arch/arm/mach-pxa/spitz_pm.c
+++ b/arch/arm/mach-pxa/spitz_pm.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
+#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/apm-emulation.h>
diff --git a/arch/arm/mach-s3c2410/Makefile b/arch/arm/mach-s3c2410/Makefile
index 0d468e96e83e..81695353d8f4 100644
--- a/arch/arm/mach-s3c2410/Makefile
+++ b/arch/arm/mach-s3c2410/Makefile
@@ -10,7 +10,6 @@ obj-n				:=
 obj-				:=
 
 obj-$(CONFIG_CPU_S3C2410)	+= s3c2410.o
-obj-$(CONFIG_CPU_S3C2410)	+= irq.o
 obj-$(CONFIG_CPU_S3C2410_DMA)	+= dma.o
 obj-$(CONFIG_CPU_S3C2410_DMA)	+= dma.o
 obj-$(CONFIG_S3C2410_PM)	+= pm.o sleep.o
diff --git a/arch/arm/mach-s3c2410/irq.c b/arch/arm/mach-s3c2410/irq.c
deleted file mode 100644
index 2854129f8cc7..000000000000
--- a/arch/arm/mach-s3c2410/irq.c
+++ /dev/null
@@ -1,34 +0,0 @@
-/* linux/arch/arm/mach-s3c2410/irq.c
- *
- * Copyright (c) 2006 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * 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/module.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/syscore_ops.h>
-
-#include <plat/cpu.h>
-#include <plat/pm.h>
-
-struct syscore_ops s3c24xx_irq_syscore_ops = {
-	.suspend	= s3c24xx_irq_suspend,
-	.resume		= s3c24xx_irq_resume,
-};
diff --git a/arch/arm/mach-s3c2410/mach-amlm5900.c b/arch/arm/mach-s3c2410/mach-amlm5900.c
index 44440cbd7620..dabc141243f3 100644
--- a/arch/arm/mach-s3c2410/mach-amlm5900.c
+++ b/arch/arm/mach-s3c2410/mach-amlm5900.c
@@ -58,8 +58,6 @@
 #include <plat/cpu.h>
 #include <plat/gpio-cfg.h>
 
-#ifdef CONFIG_MTD_PARTITIONS
-
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/map.h>
@@ -113,7 +111,6 @@ static struct platform_device amlm5900_device_nor = {
 	.num_resources	= 1,
 	.resource	= &amlm5900_nor_resource,
 };
-#endif
 
 static struct map_desc amlm5900_iodesc[] __initdata = {
 };
@@ -158,9 +155,7 @@ static struct platform_device *amlm5900_devices[] __initdata = {
  	&s3c_device_rtc,
 	&s3c_device_usbgadget,
         &s3c_device_sdi,
-#ifdef CONFIG_MTD_PARTITIONS
 	&amlm5900_device_nor,
-#endif
 };
 
 static void __init amlm5900_map_io(void)
diff --git a/arch/arm/mach-s3c2410/mach-tct_hammer.c b/arch/arm/mach-s3c2410/mach-tct_hammer.c
index a15d0621c22f..43c2b831b9e8 100644
--- a/arch/arm/mach-s3c2410/mach-tct_hammer.c
+++ b/arch/arm/mach-s3c2410/mach-tct_hammer.c
@@ -49,8 +49,6 @@
 #include <plat/devs.h>
 #include <plat/cpu.h>
 
-#ifdef CONFIG_MTD_PARTITIONS
-
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/map.h>
@@ -91,8 +89,6 @@ static struct platform_device tct_hammer_device_nor = {
 	.resource	= &tct_hammer_nor_resource,
 };
 
-#endif
-
 static struct map_desc tct_hammer_iodesc[] __initdata = {
 };
 
@@ -133,9 +129,7 @@ static struct platform_device *tct_hammer_devices[] __initdata = {
 	&s3c_device_rtc,
 	&s3c_device_usbgadget,
 	&s3c_device_sdi,
-#ifdef CONFIG_MTD_PARTITIONS
 	&tct_hammer_device_nor,
-#endif
 };
 
 static void __init tct_hammer_map_io(void)
diff --git a/arch/arm/mach-s3c64xx/dev-spi.c b/arch/arm/mach-s3c64xx/dev-spi.c
index 405e62128917..82db072cb836 100644
--- a/arch/arm/mach-s3c64xx/dev-spi.c
+++ b/arch/arm/mach-s3c64xx/dev-spi.c
@@ -16,7 +16,6 @@
 
 #include <mach/dma.h>
 #include <mach/map.h>
-#include <mach/gpio-bank-c.h>
 #include <mach/spi-clocks.h>
 #include <mach/irqs.h>
 
@@ -40,23 +39,15 @@ static char *spi_src_clks[] = {
  */
 static int s3c64xx_spi_cfg_gpio(struct platform_device *pdev)
 {
+	unsigned int base;
+
 	switch (pdev->id) {
 	case 0:
-		s3c_gpio_cfgpin(S3C64XX_GPC(0), S3C64XX_GPC0_SPI_MISO0);
-		s3c_gpio_cfgpin(S3C64XX_GPC(1), S3C64XX_GPC1_SPI_CLKO);
-		s3c_gpio_cfgpin(S3C64XX_GPC(2), S3C64XX_GPC2_SPI_MOSIO);
-		s3c_gpio_setpull(S3C64XX_GPC(0), S3C_GPIO_PULL_UP);
-		s3c_gpio_setpull(S3C64XX_GPC(1), S3C_GPIO_PULL_UP);
-		s3c_gpio_setpull(S3C64XX_GPC(2), S3C_GPIO_PULL_UP);
+		base = S3C64XX_GPC(0);
 		break;
 
 	case 1:
-		s3c_gpio_cfgpin(S3C64XX_GPC(4), S3C64XX_GPC4_SPI_MISO1);
-		s3c_gpio_cfgpin(S3C64XX_GPC(5), S3C64XX_GPC5_SPI_CLK1);
-		s3c_gpio_cfgpin(S3C64XX_GPC(6), S3C64XX_GPC6_SPI_MOSI1);
-		s3c_gpio_setpull(S3C64XX_GPC(4), S3C_GPIO_PULL_UP);
-		s3c_gpio_setpull(S3C64XX_GPC(5), S3C_GPIO_PULL_UP);
-		s3c_gpio_setpull(S3C64XX_GPC(6), S3C_GPIO_PULL_UP);
+		base = S3C64XX_GPC(4);
 		break;
 
 	default:
@@ -64,6 +55,9 @@ static int s3c64xx_spi_cfg_gpio(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	s3c_gpio_cfgall_range(base, 3,
+			      S3C_GPIO_SFN(2), S3C_GPIO_PULL_UP);
+
 	return 0;
 }
 
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-a.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-a.h
deleted file mode 100644
index 34212e1a7e81..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-a.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-a.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank A register and configuration definitions
- *
- * 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 S3C64XX_GPACON			(S3C64XX_GPA_BASE + 0x00)
-#define S3C64XX_GPADAT			(S3C64XX_GPA_BASE + 0x04)
-#define S3C64XX_GPAPUD			(S3C64XX_GPA_BASE + 0x08)
-#define S3C64XX_GPACONSLP		(S3C64XX_GPA_BASE + 0x0c)
-#define S3C64XX_GPAPUDSLP		(S3C64XX_GPA_BASE + 0x10)
-
-#define S3C64XX_GPA_CONMASK(__gpio)	(0xf << ((__gpio) * 4))
-#define S3C64XX_GPA_INPUT(__gpio)	(0x0 << ((__gpio) * 4))
-#define S3C64XX_GPA_OUTPUT(__gpio)	(0x1 << ((__gpio) * 4))
-
-#define S3C64XX_GPA0_UART_RXD0		(0x02 << 0)
-#define S3C64XX_GPA0_EINT_G1_0		(0x07 << 0)
-
-#define S3C64XX_GPA1_UART_TXD0		(0x02 << 4)
-#define S3C64XX_GPA1_EINT_G1_1		(0x07 << 4)
-
-#define S3C64XX_GPA2_UART_nCTS0		(0x02 << 8)
-#define S3C64XX_GPA2_EINT_G1_2		(0x07 << 8)
-
-#define S3C64XX_GPA3_UART_nRTS0		(0x02 << 12)
-#define S3C64XX_GPA3_EINT_G1_3		(0x07 << 12)
-
-#define S3C64XX_GPA4_UART_RXD1		(0x02 << 16)
-#define S3C64XX_GPA4_EINT_G1_4		(0x07 << 16)
-
-#define S3C64XX_GPA5_UART_TXD1		(0x02 << 20)
-#define S3C64XX_GPA5_EINT_G1_5		(0x07 << 20)
-
-#define S3C64XX_GPA6_UART_nCTS1		(0x02 << 24)
-#define S3C64XX_GPA6_EINT_G1_6		(0x07 << 24)
-
-#define S3C64XX_GPA7_UART_nRTS1		(0x02 << 28)
-#define S3C64XX_GPA7_EINT_G1_7		(0x07 << 28)
-
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-b.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-b.h
deleted file mode 100644
index 7232c037e642..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-b.h
+++ /dev/null
@@ -1,60 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-b.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank B register and configuration definitions
- *
- * 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 S3C64XX_GPBCON			(S3C64XX_GPB_BASE + 0x00)
-#define S3C64XX_GPBDAT			(S3C64XX_GPB_BASE + 0x04)
-#define S3C64XX_GPBPUD			(S3C64XX_GPB_BASE + 0x08)
-#define S3C64XX_GPBCONSLP		(S3C64XX_GPB_BASE + 0x0c)
-#define S3C64XX_GPBPUDSLP		(S3C64XX_GPB_BASE + 0x10)
-
-#define S3C64XX_GPB_CONMASK(__gpio)	(0xf << ((__gpio) * 4))
-#define S3C64XX_GPB_INPUT(__gpio)	(0x0 << ((__gpio) * 4))
-#define S3C64XX_GPB_OUTPUT(__gpio)	(0x1 << ((__gpio) * 4))
-
-#define S3C64XX_GPB0_UART_RXD2		(0x02 << 0)
-#define S3C64XX_GPB0_EXTDMA_REQ		(0x03 << 0)
-#define S3C64XX_GPB0_IrDA_RXD		(0x04 << 0)
-#define S3C64XX_GPB0_ADDR_CF0		(0x05 << 0)
-#define S3C64XX_GPB0_EINT_G1_8		(0x07 << 0)
-
-#define S3C64XX_GPB1_UART_TXD2		(0x02 << 4)
-#define S3C64XX_GPB1_EXTDMA_ACK		(0x03 << 4)
-#define S3C64XX_GPB1_IrDA_TXD		(0x04 << 4)
-#define S3C64XX_GPB1_ADDR_CF1		(0x05 << 4)
-#define S3C64XX_GPB1_EINT_G1_9		(0x07 << 4)
-
-#define S3C64XX_GPB2_UART_RXD3		(0x02 << 8)
-#define S3C64XX_GPB2_IrDA_RXD		(0x03 << 8)
-#define S3C64XX_GPB2_EXTDMA_REQ		(0x04 << 8)
-#define S3C64XX_GPB2_ADDR_CF2		(0x05 << 8)
-#define S3C64XX_GPB2_I2C_SCL1		(0x06 << 8)
-#define S3C64XX_GPB2_EINT_G1_10		(0x07 << 8)
-
-#define S3C64XX_GPB3_UART_TXD3		(0x02 << 12)
-#define S3C64XX_GPB3_IrDA_TXD		(0x03 << 12)
-#define S3C64XX_GPB3_EXTDMA_ACK		(0x04 << 12)
-#define S3C64XX_GPB3_I2C_SDA1		(0x06 << 12)
-#define S3C64XX_GPB3_EINT_G1_11		(0x07 << 12)
-
-#define S3C64XX_GPB4_IrDA_SDBW		(0x02 << 16)
-#define S3C64XX_GPB4_CAM_FIELD		(0x03 << 16)
-#define S3C64XX_GPB4_CF_DATA_DIR	(0x04 << 16)
-#define S3C64XX_GPB4_EINT_G1_12		(0x07 << 16)
-
-#define S3C64XX_GPB5_I2C_SCL0		(0x02 << 20)
-#define S3C64XX_GPB5_EINT_G1_13		(0x07 << 20)
-
-#define S3C64XX_GPB6_I2C_SDA0		(0x02 << 24)
-#define S3C64XX_GPB6_EINT_G1_14		(0x07 << 24)
-
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-c.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-c.h
deleted file mode 100644
index db189ab1639a..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-c.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-c.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank C register and configuration definitions
- *
- * 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 S3C64XX_GPCCON			(S3C64XX_GPC_BASE + 0x00)
-#define S3C64XX_GPCDAT			(S3C64XX_GPC_BASE + 0x04)
-#define S3C64XX_GPCPUD			(S3C64XX_GPC_BASE + 0x08)
-#define S3C64XX_GPCCONSLP		(S3C64XX_GPC_BASE + 0x0c)
-#define S3C64XX_GPCPUDSLP		(S3C64XX_GPC_BASE + 0x10)
-
-#define S3C64XX_GPC_CONMASK(__gpio)	(0xf << ((__gpio) * 4))
-#define S3C64XX_GPC_INPUT(__gpio)	(0x0 << ((__gpio) * 4))
-#define S3C64XX_GPC_OUTPUT(__gpio)	(0x1 << ((__gpio) * 4))
-
-#define S3C64XX_GPC0_SPI_MISO0		(0x02 << 0)
-#define S3C64XX_GPC0_EINT_G2_0		(0x07 << 0)
-
-#define S3C64XX_GPC1_SPI_CLKO		(0x02 << 4)
-#define S3C64XX_GPC1_EINT_G2_1		(0x07 << 4)
-
-#define S3C64XX_GPC2_SPI_MOSIO		(0x02 << 8)
-#define S3C64XX_GPC2_EINT_G2_2		(0x07 << 8)
-
-#define S3C64XX_GPC3_SPI_nCSO		(0x02 << 12)
-#define S3C64XX_GPC3_EINT_G2_3		(0x07 << 12)
-
-#define S3C64XX_GPC4_SPI_MISO1		(0x02 << 16)
-#define S3C64XX_GPC4_MMC2_CMD		(0x03 << 16)
-#define S3C64XX_GPC4_I2S_V40_DO0	(0x05 << 16)
-#define S3C64XX_GPC4_EINT_G2_4		(0x07 << 16)
-
-#define S3C64XX_GPC5_SPI_CLK1		(0x02 << 20)
-#define S3C64XX_GPC5_MMC2_CLK		(0x03 << 20)
-#define S3C64XX_GPC5_I2S_V40_DO1	(0x05 << 20)
-#define S3C64XX_GPC5_EINT_G2_5		(0x07 << 20)
-
-#define S3C64XX_GPC6_SPI_MOSI1		(0x02 << 24)
-#define S3C64XX_GPC6_EINT_G2_6		(0x07 << 24)
-
-#define S3C64XX_GPC7_SPI_nCS1		(0x02 << 28)
-#define S3C64XX_GPC7_I2S_V40_DO2	(0x05 << 28)
-#define S3C64XX_GPC7_EINT_G2_7		(0x07 << 28)
-
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-d.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-d.h
deleted file mode 100644
index 1a01cee7aca3..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-d.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-d.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank D register and configuration definitions
- *
- * 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 S3C64XX_GPDCON			(S3C64XX_GPD_BASE + 0x00)
-#define S3C64XX_GPDDAT			(S3C64XX_GPD_BASE + 0x04)
-#define S3C64XX_GPDPUD			(S3C64XX_GPD_BASE + 0x08)
-#define S3C64XX_GPDCONSLP		(S3C64XX_GPD_BASE + 0x0c)
-#define S3C64XX_GPDPUDSLP		(S3C64XX_GPD_BASE + 0x10)
-
-#define S3C64XX_GPD_CONMASK(__gpio)	(0xf << ((__gpio) * 4))
-#define S3C64XX_GPD_INPUT(__gpio)	(0x0 << ((__gpio) * 4))
-#define S3C64XX_GPD_OUTPUT(__gpio)	(0x1 << ((__gpio) * 4))
-
-#define S3C64XX_GPD0_PCM0_SCLK		(0x02 << 0)
-#define S3C64XX_GPD0_I2S0_CLK		(0x03 << 0)
-#define S3C64XX_GPD0_AC97_BITCLK	(0x04 << 0)
-#define S3C64XX_GPD0_EINT_G3_0		(0x07 << 0)
-
-#define S3C64XX_GPD1_PCM0_EXTCLK	(0x02 << 4)
-#define S3C64XX_GPD1_I2S0_CDCLK		(0x03 << 4)
-#define S3C64XX_GPD1_AC97_nRESET	(0x04 << 4)
-#define S3C64XX_GPD1_EINT_G3_1		(0x07 << 4)
-
-#define S3C64XX_GPD2_PCM0_FSYNC		(0x02 << 8)
-#define S3C64XX_GPD2_I2S0_LRCLK		(0x03 << 8)
-#define S3C64XX_GPD2_AC97_SYNC		(0x04 << 8)
-#define S3C64XX_GPD2_EINT_G3_2		(0x07 << 8)
-
-#define S3C64XX_GPD3_PCM0_SIN		(0x02 << 12)
-#define S3C64XX_GPD3_I2S0_DI		(0x03 << 12)
-#define S3C64XX_GPD3_AC97_SDI		(0x04 << 12)
-#define S3C64XX_GPD3_EINT_G3_3		(0x07 << 12)
-
-#define S3C64XX_GPD4_PCM0_SOUT		(0x02 << 16)
-#define S3C64XX_GPD4_I2S0_D0		(0x03 << 16)
-#define S3C64XX_GPD4_AC97_SDO		(0x04 << 16)
-#define S3C64XX_GPD4_EINT_G3_4		(0x07 << 16)
-
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-e.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-e.h
deleted file mode 100644
index f057adb627dd..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-e.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-e.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank E register and configuration definitions
- *
- * 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 S3C64XX_GPECON			(S3C64XX_GPE_BASE + 0x00)
-#define S3C64XX_GPEDAT			(S3C64XX_GPE_BASE + 0x04)
-#define S3C64XX_GPEPUD			(S3C64XX_GPE_BASE + 0x08)
-#define S3C64XX_GPECONSLP		(S3C64XX_GPE_BASE + 0x0c)
-#define S3C64XX_GPEPUDSLP		(S3C64XX_GPE_BASE + 0x10)
-
-#define S3C64XX_GPE_CONMASK(__gpio)	(0xf << ((__gpio) * 4))
-#define S3C64XX_GPE_INPUT(__gpio)	(0x0 << ((__gpio) * 4))
-#define S3C64XX_GPE_OUTPUT(__gpio)	(0x1 << ((__gpio) * 4))
-
-#define S3C64XX_GPE0_PCM1_SCLK		(0x02 << 0)
-#define S3C64XX_GPE0_I2S1_CLK		(0x03 << 0)
-#define S3C64XX_GPE0_AC97_BITCLK	(0x04 << 0)
-
-#define S3C64XX_GPE1_PCM1_EXTCLK	(0x02 << 4)
-#define S3C64XX_GPE1_I2S1_CDCLK		(0x03 << 4)
-#define S3C64XX_GPE1_AC97_nRESET	(0x04 << 4)
-
-#define S3C64XX_GPE2_PCM1_FSYNC		(0x02 << 8)
-#define S3C64XX_GPE2_I2S1_LRCLK		(0x03 << 8)
-#define S3C64XX_GPE2_AC97_SYNC		(0x04 << 8)
-
-#define S3C64XX_GPE3_PCM1_SIN		(0x02 << 12)
-#define S3C64XX_GPE3_I2S1_DI		(0x03 << 12)
-#define S3C64XX_GPE3_AC97_SDI		(0x04 << 12)
-
-#define S3C64XX_GPE4_PCM1_SOUT		(0x02 << 16)
-#define S3C64XX_GPE4_I2S1_D0		(0x03 << 16)
-#define S3C64XX_GPE4_AC97_SDO		(0x04 << 16)
-
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-f.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-f.h
deleted file mode 100644
index 62ab8f5e7835..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-f.h
+++ /dev/null
@@ -1,71 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-f.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank F register and configuration definitions
- *
- * 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 S3C64XX_GPFCON			(S3C64XX_GPF_BASE + 0x00)
-#define S3C64XX_GPFDAT			(S3C64XX_GPF_BASE + 0x04)
-#define S3C64XX_GPFPUD			(S3C64XX_GPF_BASE + 0x08)
-#define S3C64XX_GPFCONSLP		(S3C64XX_GPF_BASE + 0x0c)
-#define S3C64XX_GPFPUDSLP		(S3C64XX_GPF_BASE + 0x10)
-
-#define S3C64XX_GPF_CONMASK(__gpio)	(0x3 << ((__gpio) * 2))
-#define S3C64XX_GPF_INPUT(__gpio)	(0x0 << ((__gpio) * 2))
-#define S3C64XX_GPF_OUTPUT(__gpio)	(0x1 << ((__gpio) * 2))
-
-#define S3C64XX_GPF0_CAMIF_CLK		(0x02 << 0)
-#define S3C64XX_GPF0_EINT_G4_0		(0x03 << 0)
-
-#define S3C64XX_GPF1_CAMIF_HREF		(0x02 << 2)
-#define S3C64XX_GPF1_EINT_G4_1		(0x03 << 2)
-
-#define S3C64XX_GPF2_CAMIF_PCLK		(0x02 << 4)
-#define S3C64XX_GPF2_EINT_G4_2		(0x03 << 4)
-
-#define S3C64XX_GPF3_CAMIF_nRST		(0x02 << 6)
-#define S3C64XX_GPF3_EINT_G4_3		(0x03 << 6)
-
-#define S3C64XX_GPF4_CAMIF_VSYNC	(0x02 << 8)
-#define S3C64XX_GPF4_EINT_G4_4		(0x03 << 8)
-
-#define S3C64XX_GPF5_CAMIF_YDATA0	(0x02 << 10)
-#define S3C64XX_GPF5_EINT_G4_5		(0x03 << 10)
-
-#define S3C64XX_GPF6_CAMIF_YDATA1	(0x02 << 12)
-#define S3C64XX_GPF6_EINT_G4_6		(0x03 << 12)
-
-#define S3C64XX_GPF7_CAMIF_YDATA2	(0x02 << 14)
-#define S3C64XX_GPF7_EINT_G4_7		(0x03 << 14)
-
-#define S3C64XX_GPF8_CAMIF_YDATA3	(0x02 << 16)
-#define S3C64XX_GPF8_EINT_G4_8		(0x03 << 16)
-
-#define S3C64XX_GPF9_CAMIF_YDATA4	(0x02 << 18)
-#define S3C64XX_GPF9_EINT_G4_9		(0x03 << 18)
-
-#define S3C64XX_GPF10_CAMIF_YDATA5	(0x02 << 20)
-#define S3C64XX_GPF10_EINT_G4_10	(0x03 << 20)
-
-#define S3C64XX_GPF11_CAMIF_YDATA6	(0x02 << 22)
-#define S3C64XX_GPF11_EINT_G4_11	(0x03 << 22)
-
-#define S3C64XX_GPF12_CAMIF_YDATA7	(0x02 << 24)
-#define S3C64XX_GPF12_EINT_G4_12	(0x03 << 24)
-
-#define S3C64XX_GPF13_PWM_ECLK		(0x02 << 26)
-#define S3C64XX_GPF13_EINT_G4_13	(0x03 << 26)
-
-#define S3C64XX_GPF14_PWM_TOUT0		(0x02 << 28)
-#define S3C64XX_GPF14_CLKOUT0		(0x03 << 28)
-
-#define S3C64XX_GPF15_PWM_TOUT1		(0x02 << 30)
-
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-g.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-g.h
deleted file mode 100644
index b94954af1598..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-g.h
+++ /dev/null
@@ -1,42 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-g.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank G register and configuration definitions
- *
- * 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 S3C64XX_GPGCON			(S3C64XX_GPG_BASE + 0x00)
-#define S3C64XX_GPGDAT			(S3C64XX_GPG_BASE + 0x04)
-#define S3C64XX_GPGPUD			(S3C64XX_GPG_BASE + 0x08)
-#define S3C64XX_GPGCONSLP		(S3C64XX_GPG_BASE + 0x0c)
-#define S3C64XX_GPGPUDSLP		(S3C64XX_GPG_BASE + 0x10)
-
-#define S3C64XX_GPG_CONMASK(__gpio)	(0xf << ((__gpio) * 4))
-#define S3C64XX_GPG_INPUT(__gpio)	(0x0 << ((__gpio) * 4))
-#define S3C64XX_GPG_OUTPUT(__gpio)	(0x1 << ((__gpio) * 4))
-
-#define S3C64XX_GPG0_MMC0_CLK		(0x02 << 0)
-#define S3C64XX_GPG0_EINT_G5_0		(0x07 << 0)
-
-#define S3C64XX_GPG1_MMC0_CMD		(0x02 << 4)
-#define S3C64XX_GPG1_EINT_G5_1		(0x07 << 4)
-
-#define S3C64XX_GPG2_MMC0_DATA0		(0x02 << 8)
-#define S3C64XX_GPG2_EINT_G5_2		(0x07 << 8)
-
-#define S3C64XX_GPG3_MMC0_DATA1		(0x02 << 12)
-#define S3C64XX_GPG3_EINT_G5_3		(0x07 << 12)
-
-#define S3C64XX_GPG4_MMC0_DATA2		(0x02 << 16)
-#define S3C64XX_GPG4_EINT_G5_4		(0x07 << 16)
-
-#define S3C64XX_GPG5_MMC0_DATA3		(0x02 << 20)
-#define S3C64XX_GPG5_EINT_G5_5		(0x07 << 20)
-
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-h.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-h.h
deleted file mode 100644
index 5d75aaad865e..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-h.h
+++ /dev/null
@@ -1,74 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-h.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank H register and configuration definitions
- *
- * 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 S3C64XX_GPHCON0			(S3C64XX_GPH_BASE + 0x00)
-#define S3C64XX_GPHCON1			(S3C64XX_GPH_BASE + 0x04)
-#define S3C64XX_GPHDAT			(S3C64XX_GPH_BASE + 0x08)
-#define S3C64XX_GPHPUD			(S3C64XX_GPH_BASE + 0x0c)
-#define S3C64XX_GPHCONSLP		(S3C64XX_GPH_BASE + 0x10)
-#define S3C64XX_GPHPUDSLP		(S3C64XX_GPH_BASE + 0x14)
-
-#define S3C64XX_GPH_CONMASK(__gpio)	(0xf << ((__gpio) * 4))
-#define S3C64XX_GPH_INPUT(__gpio)	(0x0 << ((__gpio) * 4))
-#define S3C64XX_GPH_OUTPUT(__gpio)	(0x1 << ((__gpio) * 4))
-
-#define S3C64XX_GPH0_MMC1_CLK		(0x02 << 0)
-#define S3C64XX_GPH0_KP_COL0		(0x04 << 0)
-#define S3C64XX_GPH0_EINT_G6_0		(0x07 << 0)
-
-#define S3C64XX_GPH1_MMC1_CMD		(0x02 << 4)
-#define S3C64XX_GPH1_KP_COL1		(0x04 << 4)
-#define S3C64XX_GPH1_EINT_G6_1		(0x07 << 4)
-
-#define S3C64XX_GPH2_MMC1_DATA0		(0x02 << 8)
-#define S3C64XX_GPH2_KP_COL2		(0x04 << 8)
-#define S3C64XX_GPH2_EINT_G6_2		(0x07 << 8)
-
-#define S3C64XX_GPH3_MMC1_DATA1		(0x02 << 12)
-#define S3C64XX_GPH3_KP_COL3		(0x04 << 12)
-#define S3C64XX_GPH3_EINT_G6_3		(0x07 << 12)
-
-#define S3C64XX_GPH4_MMC1_DATA2		(0x02 << 16)
-#define S3C64XX_GPH4_KP_COL4		(0x04 << 16)
-#define S3C64XX_GPH4_EINT_G6_4		(0x07 << 16)
-
-#define S3C64XX_GPH5_MMC1_DATA3		(0x02 << 20)
-#define S3C64XX_GPH5_KP_COL5		(0x04 << 20)
-#define S3C64XX_GPH5_EINT_G6_5		(0x07 << 20)
-
-#define S3C64XX_GPH6_MMC1_DATA4		(0x02 << 24)
-#define S3C64XX_GPH6_MMC2_DATA0		(0x03 << 24)
-#define S3C64XX_GPH6_KP_COL6		(0x04 << 24)
-#define S3C64XX_GPH6_I2S_V40_BCLK	(0x05 << 24)
-#define S3C64XX_GPH6_ADDR_CF0		(0x06 << 24)
-#define S3C64XX_GPH6_EINT_G6_6		(0x07 << 24)
-
-#define S3C64XX_GPH7_MMC1_DATA5		(0x02 << 28)
-#define S3C64XX_GPH7_MMC2_DATA1		(0x03 << 28)
-#define S3C64XX_GPH7_KP_COL7		(0x04 << 28)
-#define S3C64XX_GPH7_I2S_V40_CDCLK	(0x05 << 28)
-#define S3C64XX_GPH7_ADDR_CF1		(0x06 << 28)
-#define S3C64XX_GPH7_EINT_G6_7		(0x07 << 28)
-
-#define S3C64XX_GPH8_MMC1_DATA6		(0x02 <<  0)
-#define S3C64XX_GPH8_MMC2_DATA2		(0x03 <<  0)
-#define S3C64XX_GPH8_I2S_V40_LRCLK	(0x05 <<  0)
-#define S3C64XX_GPH8_ADDR_CF2		(0x06 <<  0)
-#define S3C64XX_GPH8_EINT_G6_8		(0x07 <<  0)
-
-#define S3C64XX_GPH9_OUTPUT		(0x01 <<  4)
-#define S3C64XX_GPH9_MMC1_DATA7		(0x02 <<  4)
-#define S3C64XX_GPH9_MMC2_DATA3		(0x03 <<  4)
-#define S3C64XX_GPH9_I2S_V40_DI		(0x05 <<  4)
-#define S3C64XX_GPH9_EINT_G6_9		(0x07 <<  4)
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-i.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-i.h
deleted file mode 100644
index 4ceaa6098bc7..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-i.h
+++ /dev/null
@@ -1,40 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-i.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank I register and configuration definitions
- *
- * 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 S3C64XX_GPICON			(S3C64XX_GPI_BASE + 0x00)
-#define S3C64XX_GPIDAT			(S3C64XX_GPI_BASE + 0x04)
-#define S3C64XX_GPIPUD			(S3C64XX_GPI_BASE + 0x08)
-#define S3C64XX_GPICONSLP		(S3C64XX_GPI_BASE + 0x0c)
-#define S3C64XX_GPIPUDSLP		(S3C64XX_GPI_BASE + 0x10)
-
-#define S3C64XX_GPI_CONMASK(__gpio)	(0x3 << ((__gpio) * 2))
-#define S3C64XX_GPI_INPUT(__gpio)	(0x0 << ((__gpio) * 2))
-#define S3C64XX_GPI_OUTPUT(__gpio)	(0x1 << ((__gpio) * 2))
-
-#define S3C64XX_GPI0_VD0		(0x02 << 0)
-#define S3C64XX_GPI1_VD1		(0x02 << 2)
-#define S3C64XX_GPI2_VD2		(0x02 << 4)
-#define S3C64XX_GPI3_VD3		(0x02 << 6)
-#define S3C64XX_GPI4_VD4		(0x02 << 8)
-#define S3C64XX_GPI5_VD5		(0x02 << 10)
-#define S3C64XX_GPI6_VD6		(0x02 << 12)
-#define S3C64XX_GPI7_VD7		(0x02 << 14)
-#define S3C64XX_GPI8_VD8		(0x02 << 16)
-#define S3C64XX_GPI9_VD9		(0x02 << 18)
-#define S3C64XX_GPI10_VD10		(0x02 << 20)
-#define S3C64XX_GPI11_VD11		(0x02 << 22)
-#define S3C64XX_GPI12_VD12		(0x02 << 24)
-#define S3C64XX_GPI13_VD13		(0x02 << 26)
-#define S3C64XX_GPI14_VD14		(0x02 << 28)
-#define S3C64XX_GPI15_VD15		(0x02 << 30)
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-j.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-j.h
deleted file mode 100644
index 6f25cd079a40..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-j.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-j.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank J register and configuration definitions
- *
- * 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 S3C64XX_GPJCON			(S3C64XX_GPJ_BASE + 0x00)
-#define S3C64XX_GPJDAT			(S3C64XX_GPJ_BASE + 0x04)
-#define S3C64XX_GPJPUD			(S3C64XX_GPJ_BASE + 0x08)
-#define S3C64XX_GPJCONSLP		(S3C64XX_GPJ_BASE + 0x0c)
-#define S3C64XX_GPJPUDSLP		(S3C64XX_GPJ_BASE + 0x10)
-
-#define S3C64XX_GPJ_CONMASK(__gpio)	(0x3 << ((__gpio) * 2))
-#define S3C64XX_GPJ_INPUT(__gpio)	(0x0 << ((__gpio) * 2))
-#define S3C64XX_GPJ_OUTPUT(__gpio)	(0x1 << ((__gpio) * 2))
-
-#define S3C64XX_GPJ0_VD16		(0x02 << 0)
-#define S3C64XX_GPJ1_VD17		(0x02 << 2)
-#define S3C64XX_GPJ2_VD18		(0x02 << 4)
-#define S3C64XX_GPJ3_VD19		(0x02 << 6)
-#define S3C64XX_GPJ4_VD20		(0x02 << 8)
-#define S3C64XX_GPJ5_VD21		(0x02 << 10)
-#define S3C64XX_GPJ6_VD22		(0x02 << 12)
-#define S3C64XX_GPJ7_VD23		(0x02 << 14)
-#define S3C64XX_GPJ8_LCD_HSYNC		(0x02 << 16)
-#define S3C64XX_GPJ9_LCD_VSYNC		(0x02 << 18)
-#define S3C64XX_GPJ10_LCD_VDEN		(0x02 << 20)
-#define S3C64XX_GPJ11_LCD_VCLK		(0x02 << 22)
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-n.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-n.h
deleted file mode 100644
index d0aeda1cd9de..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-n.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-n.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank N register and configuration definitions
- *
- * 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 S3C64XX_GPNCON			(S3C64XX_GPN_BASE + 0x00)
-#define S3C64XX_GPNDAT			(S3C64XX_GPN_BASE + 0x04)
-#define S3C64XX_GPNPUD			(S3C64XX_GPN_BASE + 0x08)
-
-#define S3C64XX_GPN_CONMASK(__gpio)	(0x3 << ((__gpio) * 2))
-#define S3C64XX_GPN_INPUT(__gpio)	(0x0 << ((__gpio) * 2))
-#define S3C64XX_GPN_OUTPUT(__gpio)	(0x1 << ((__gpio) * 2))
-
-#define S3C64XX_GPN0_EINT0		(0x02 << 0)
-#define S3C64XX_GPN0_KP_ROW0		(0x03 << 0)
-
-#define S3C64XX_GPN1_EINT1		(0x02 << 2)
-#define S3C64XX_GPN1_KP_ROW1		(0x03 << 2)
-
-#define S3C64XX_GPN2_EINT2		(0x02 << 4)
-#define S3C64XX_GPN2_KP_ROW2		(0x03 << 4)
-
-#define S3C64XX_GPN3_EINT3		(0x02 << 6)
-#define S3C64XX_GPN3_KP_ROW3		(0x03 << 6)
-
-#define S3C64XX_GPN4_EINT4		(0x02 << 8)
-#define S3C64XX_GPN4_KP_ROW4		(0x03 << 8)
-
-#define S3C64XX_GPN5_EINT5		(0x02 << 10)
-#define S3C64XX_GPN5_KP_ROW5		(0x03 << 10)
-
-#define S3C64XX_GPN6_EINT6		(0x02 << 12)
-#define S3C64XX_GPN6_KP_ROW6		(0x03 << 12)
-
-#define S3C64XX_GPN7_EINT7		(0x02 << 14)
-#define S3C64XX_GPN7_KP_ROW7		(0x03 << 14)
-
-#define S3C64XX_GPN8_EINT8		(0x02 << 16)
-#define S3C64XX_GPN9_EINT9		(0x02 << 18)
-#define S3C64XX_GPN10_EINT10		(0x02 << 20)
-#define S3C64XX_GPN11_EINT11		(0x02 << 22)
-#define S3C64XX_GPN12_EINT12		(0x02 << 24)
-#define S3C64XX_GPN13_EINT13		(0x02 << 26)
-#define S3C64XX_GPN14_EINT14		(0x02 << 28)
-#define S3C64XX_GPN15_EINT15		(0x02 << 30)
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-o.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-o.h
deleted file mode 100644
index 21868fa102d0..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-o.h
+++ /dev/null
@@ -1,70 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-o.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank O register and configuration definitions
- *
- * 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 S3C64XX_GPOCON			(S3C64XX_GPO_BASE + 0x00)
-#define S3C64XX_GPODAT			(S3C64XX_GPO_BASE + 0x04)
-#define S3C64XX_GPOPUD			(S3C64XX_GPO_BASE + 0x08)
-#define S3C64XX_GPOCONSLP		(S3C64XX_GPO_BASE + 0x0c)
-#define S3C64XX_GPOPUDSLP		(S3C64XX_GPO_BASE + 0x10)
-
-#define S3C64XX_GPO_CONMASK(__gpio)	(0x3 << ((__gpio) * 2))
-#define S3C64XX_GPO_INPUT(__gpio)	(0x0 << ((__gpio) * 2))
-#define S3C64XX_GPO_OUTPUT(__gpio)	(0x1 << ((__gpio) * 2))
-
-#define S3C64XX_GPO0_MEM0_nCS2		(0x02 << 0)
-#define S3C64XX_GPO0_EINT_G7_0		(0x03 << 0)
-
-#define S3C64XX_GPO1_MEM0_nCS3		(0x02 << 2)
-#define S3C64XX_GPO1_EINT_G7_1		(0x03 << 2)
-
-#define S3C64XX_GPO2_MEM0_nCS4		(0x02 << 4)
-#define S3C64XX_GPO2_EINT_G7_2		(0x03 << 4)
-
-#define S3C64XX_GPO3_MEM0_nCS5		(0x02 << 6)
-#define S3C64XX_GPO3_EINT_G7_3		(0x03 << 6)
-
-#define S3C64XX_GPO4_EINT_G7_4		(0x03 << 8)
-
-#define S3C64XX_GPO5_EINT_G7_5		(0x03 << 10)
-
-#define S3C64XX_GPO6_MEM0_ADDR6		(0x02 << 12)
-#define S3C64XX_GPO6_EINT_G7_6		(0x03 << 12)
-
-#define S3C64XX_GPO7_MEM0_ADDR7		(0x02 << 14)
-#define S3C64XX_GPO7_EINT_G7_7		(0x03 << 14)
-
-#define S3C64XX_GPO8_MEM0_ADDR8		(0x02 << 16)
-#define S3C64XX_GPO8_EINT_G7_8		(0x03 << 16)
-
-#define S3C64XX_GPO9_MEM0_ADDR9		(0x02 << 18)
-#define S3C64XX_GPO9_EINT_G7_9		(0x03 << 18)
-
-#define S3C64XX_GPO10_MEM0_ADDR10	(0x02 << 20)
-#define S3C64XX_GPO10_EINT_G7_10	(0x03 << 20)
-
-#define S3C64XX_GPO11_MEM0_ADDR11	(0x02 << 22)
-#define S3C64XX_GPO11_EINT_G7_11	(0x03 << 22)
-
-#define S3C64XX_GPO12_MEM0_ADDR12	(0x02 << 24)
-#define S3C64XX_GPO12_EINT_G7_12	(0x03 << 24)
-
-#define S3C64XX_GPO13_MEM0_ADDR13	(0x02 << 26)
-#define S3C64XX_GPO13_EINT_G7_13	(0x03 << 26)
-
-#define S3C64XX_GPO14_MEM0_ADDR14	(0x02 << 28)
-#define S3C64XX_GPO14_EINT_G7_14	(0x03 << 28)
-
-#define S3C64XX_GPO15_MEM0_ADDR15	(0x02 << 30)
-#define S3C64XX_GPO15_EINT_G7_15	(0x03 << 30)
-
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-p.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-p.h
deleted file mode 100644
index 46bcfb63b8de..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-p.h
+++ /dev/null
@@ -1,69 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-p.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank P register and configuration definitions
- *
- * 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 S3C64XX_GPPCON			(S3C64XX_GPP_BASE + 0x00)
-#define S3C64XX_GPPDAT			(S3C64XX_GPP_BASE + 0x04)
-#define S3C64XX_GPPPUD			(S3C64XX_GPP_BASE + 0x08)
-#define S3C64XX_GPPCONSLP		(S3C64XX_GPP_BASE + 0x0c)
-#define S3C64XX_GPPPUDSLP		(S3C64XX_GPP_BASE + 0x10)
-
-#define S3C64XX_GPP_CONMASK(__gpio)	(0x3 << ((__gpio) * 2))
-#define S3C64XX_GPP_INPUT(__gpio)	(0x0 << ((__gpio) * 2))
-#define S3C64XX_GPP_OUTPUT(__gpio)	(0x1 << ((__gpio) * 2))
-
-#define S3C64XX_GPP0_MEM0_ADDRV		(0x02 << 0)
-#define S3C64XX_GPP0_EINT_G8_0		(0x03 << 0)
-
-#define S3C64XX_GPP1_MEM0_SMCLK		(0x02 << 2)
-#define S3C64XX_GPP1_EINT_G8_1		(0x03 << 2)
-
-#define S3C64XX_GPP2_MEM0_nWAIT		(0x02 << 4)
-#define S3C64XX_GPP2_EINT_G8_2		(0x03 << 4)
-
-#define S3C64XX_GPP3_MEM0_RDY0_ALE	(0x02 << 6)
-#define S3C64XX_GPP3_EINT_G8_3		(0x03 << 6)
-
-#define S3C64XX_GPP4_MEM0_RDY1_CLE	(0x02 << 8)
-#define S3C64XX_GPP4_EINT_G8_4		(0x03 << 8)
-
-#define S3C64XX_GPP5_MEM0_INTsm0_FWE	(0x02 << 10)
-#define S3C64XX_GPP5_EINT_G8_5		(0x03 << 10)
-
-#define S3C64XX_GPP6_MEM0_(null)	(0x02 << 12)
-#define S3C64XX_GPP6_EINT_G8_6		(0x03 << 12)
-
-#define S3C64XX_GPP7_MEM0_INTsm1_FRE	(0x02 << 14)
-#define S3C64XX_GPP7_EINT_G8_7		(0x03 << 14)
-
-#define S3C64XX_GPP8_MEM0_RPn_RnB	(0x02 << 16)
-#define S3C64XX_GPP8_EINT_G8_8		(0x03 << 16)
-
-#define S3C64XX_GPP9_MEM0_ATA_RESET	(0x02 << 18)
-#define S3C64XX_GPP9_EINT_G8_9		(0x03 << 18)
-
-#define S3C64XX_GPP10_MEM0_ATA_INPACK	(0x02 << 20)
-#define S3C64XX_GPP10_EINT_G8_10	(0x03 << 20)
-
-#define S3C64XX_GPP11_MEM0_ATA_REG	(0x02 << 22)
-#define S3C64XX_GPP11_EINT_G8_11	(0x03 << 22)
-
-#define S3C64XX_GPP12_MEM0_ATA_WE	(0x02 << 24)
-#define S3C64XX_GPP12_EINT_G8_12	(0x03 << 24)
-
-#define S3C64XX_GPP13_MEM0_ATA_OE	(0x02 << 26)
-#define S3C64XX_GPP13_EINT_G8_13	(0x03 << 26)
-
-#define S3C64XX_GPP14_MEM0_ATA_CD	(0x02 << 28)
-#define S3C64XX_GPP14_EINT_G8_14	(0x03 << 28)
-
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-q.h b/arch/arm/mach-s3c64xx/include/mach/gpio-bank-q.h
deleted file mode 100644
index 1712223487b0..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-bank-q.h
+++ /dev/null
@@ -1,46 +0,0 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/gpio-bank-q.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- * 	Ben Dooks <ben@simtec.co.uk>
- * 	http://armlinux.simtec.co.uk/
- *
- * GPIO Bank Q register and configuration definitions
- *
- * 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 S3C64XX_GPQCON			(S3C64XX_GPQ_BASE + 0x00)
-#define S3C64XX_GPQDAT			(S3C64XX_GPQ_BASE + 0x04)
-#define S3C64XX_GPQPUD			(S3C64XX_GPQ_BASE + 0x08)
-#define S3C64XX_GPQCONSLP		(S3C64XX_GPQ_BASE + 0x0c)
-#define S3C64XX_GPQPUDSLP		(S3C64XX_GPQ_BASE + 0x10)
-
-#define S3C64XX_GPQ_CONMASK(__gpio)	(0x3 << ((__gpio) * 2))
-#define S3C64XX_GPQ_INPUT(__gpio)	(0x0 << ((__gpio) * 2))
-#define S3C64XX_GPQ_OUTPUT(__gpio)	(0x1 << ((__gpio) * 2))
-
-#define S3C64XX_GPQ0_MEM0_ADDR18_RAS	(0x02 << 0)
-#define S3C64XX_GPQ0_EINT_G9_0		(0x03 << 0)
-
-#define S3C64XX_GPQ1_MEM0_ADDR19_CAS	(0x02 << 2)
-#define S3C64XX_GPQ1_EINT_G9_1		(0x03 << 2)
-
-#define S3C64XX_GPQ2_EINT_G9_2		(0x03 << 4)
-
-#define S3C64XX_GPQ3_EINT_G9_3		(0x03 << 6)
-
-#define S3C64XX_GPQ4_EINT_G9_4		(0x03 << 8)
-
-#define S3C64XX_GPQ5_EINT_G9_5		(0x03 << 10)
-
-#define S3C64XX_GPQ6_EINT_G9_6		(0x03 << 12)
-
-#define S3C64XX_GPQ7_MEM0_ADDR17_WENDMC	(0x02 << 14)
-#define S3C64XX_GPQ7_EINT_G9_7		(0x03 << 14)
-
-#define S3C64XX_GPQ8_MEM0_ADDR16_APDMC	(0x02 << 16)
-#define S3C64XX_GPQ8_EINT_G9_8		(0x03 << 16)
-
diff --git a/arch/arm/mach-s3c64xx/mach-smdk6410.c b/arch/arm/mach-s3c64xx/mach-smdk6410.c
index 686a4f270b12..2c0353a80906 100644
--- a/arch/arm/mach-s3c64xx/mach-smdk6410.c
+++ b/arch/arm/mach-s3c64xx/mach-smdk6410.c
@@ -50,7 +50,6 @@
 #include <mach/hardware.h>
 #include <mach/regs-fb.h>
 #include <mach/map.h>
-#include <mach/gpio-bank-f.h>
 
 #include <asm/irq.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-s3c64xx/pm.c b/arch/arm/mach-s3c64xx/pm.c
index 79412f735a8d..bc1c470b7de6 100644
--- a/arch/arm/mach-s3c64xx/pm.c
+++ b/arch/arm/mach-s3c64xx/pm.c
@@ -30,26 +30,18 @@
 #include <mach/regs-gpio-memport.h>
 
 #ifdef CONFIG_S3C_PM_DEBUG_LED_SMDK
-#include <mach/gpio-bank-n.h>
-
 void s3c_pm_debug_smdkled(u32 set, u32 clear)
 {
 	unsigned long flags;
-	u32 reg;
+	int i;
 
 	local_irq_save(flags);
-	reg = __raw_readl(S3C64XX_GPNCON);
-	reg &= ~(S3C64XX_GPN_CONMASK(12) | S3C64XX_GPN_CONMASK(13) |
-		 S3C64XX_GPN_CONMASK(14) | S3C64XX_GPN_CONMASK(15));
-	reg |= S3C64XX_GPN_OUTPUT(12) | S3C64XX_GPN_OUTPUT(13) |
-	       S3C64XX_GPN_OUTPUT(14) | S3C64XX_GPN_OUTPUT(15);
-	__raw_writel(reg, S3C64XX_GPNCON);
-
-	reg = __raw_readl(S3C64XX_GPNDAT);
-	reg &= ~(clear << 12);
-	reg |= set << 12;
-	__raw_writel(reg, S3C64XX_GPNDAT);
-
+	for (i = 0; i < 4; i++) {
+		if (clear & (1 << i))
+			gpio_set_value(S3C64XX_GPN(12 + i), 0);
+		if (set & (1 << i))
+			gpio_set_value(S3C64XX_GPN(12 + i), 1);
+	}
 	local_irq_restore(flags);
 }
 #endif
@@ -187,6 +179,18 @@ static int s3c64xx_pm_init(void)
 	pm_cpu_prep = s3c64xx_pm_prepare;
 	pm_cpu_sleep = s3c64xx_cpu_suspend;
 	pm_uart_udivslot = 1;
+
+#ifdef CONFIG_S3C_PM_DEBUG_LED_SMDK
+	gpio_request(S3C64XX_GPN(12), "DEBUG_LED0");
+	gpio_request(S3C64XX_GPN(13), "DEBUG_LED1");
+	gpio_request(S3C64XX_GPN(14), "DEBUG_LED2");
+	gpio_request(S3C64XX_GPN(15), "DEBUG_LED3");
+	gpio_direction_output(S3C64XX_GPN(12), 0);
+	gpio_direction_output(S3C64XX_GPN(13), 0);
+	gpio_direction_output(S3C64XX_GPN(14), 0);
+	gpio_direction_output(S3C64XX_GPN(15), 0);
+#endif
+
 	return 0;
 }
 
diff --git a/arch/arm/mach-s3c64xx/setup-i2c0.c b/arch/arm/mach-s3c64xx/setup-i2c0.c
index 406192a43c6e..241af94a9e70 100644
--- a/arch/arm/mach-s3c64xx/setup-i2c0.c
+++ b/arch/arm/mach-s3c64xx/setup-i2c0.c
@@ -18,14 +18,11 @@
 
 struct platform_device; /* don't need the contents */
 
-#include <mach/gpio-bank-b.h>
 #include <plat/iic.h>
 #include <plat/gpio-cfg.h>
 
 void s3c_i2c0_cfg_gpio(struct platform_device *dev)
 {
-	s3c_gpio_cfgpin(S3C64XX_GPB(5), S3C64XX_GPB5_I2C_SCL0);
-	s3c_gpio_cfgpin(S3C64XX_GPB(6), S3C64XX_GPB6_I2C_SDA0);
-	s3c_gpio_setpull(S3C64XX_GPB(5), S3C_GPIO_PULL_UP);
-	s3c_gpio_setpull(S3C64XX_GPB(6), S3C_GPIO_PULL_UP);
+	s3c_gpio_cfgall_range(S3C64XX_GPB(5), 2,
+			      S3C_GPIO_SFN(2), S3C_GPIO_PULL_UP);
 }
diff --git a/arch/arm/mach-s3c64xx/setup-i2c1.c b/arch/arm/mach-s3c64xx/setup-i2c1.c
index 1ee62c97cd7f..3d13a961986d 100644
--- a/arch/arm/mach-s3c64xx/setup-i2c1.c
+++ b/arch/arm/mach-s3c64xx/setup-i2c1.c
@@ -18,14 +18,11 @@
 
 struct platform_device; /* don't need the contents */
 
-#include <mach/gpio-bank-b.h>
 #include <plat/iic.h>
 #include <plat/gpio-cfg.h>
 
 void s3c_i2c1_cfg_gpio(struct platform_device *dev)
 {
-	s3c_gpio_cfgpin(S3C64XX_GPB(2), S3C64XX_GPB2_I2C_SCL1);
-	s3c_gpio_cfgpin(S3C64XX_GPB(3), S3C64XX_GPB3_I2C_SDA1);
-	s3c_gpio_setpull(S3C64XX_GPB(2), S3C_GPIO_PULL_UP);
-	s3c_gpio_setpull(S3C64XX_GPB(3), S3C_GPIO_PULL_UP);
+	s3c_gpio_cfgall_range(S3C64XX_GPB(2), 2,
+			      S3C_GPIO_SFN(6), S3C_GPIO_PULL_UP);
 }
diff --git a/arch/arm/mach-s3c64xx/sleep.S b/arch/arm/mach-s3c64xx/sleep.S
index afe5a762f46e..1f87732b2320 100644
--- a/arch/arm/mach-s3c64xx/sleep.S
+++ b/arch/arm/mach-s3c64xx/sleep.S
@@ -20,7 +20,6 @@
 #define S3C64XX_VA_GPIO (0x0)
 
 #include <mach/regs-gpio.h>
-#include <mach/gpio-bank-n.h>
 
 #define LL_UART (S3C_PA_UART + (0x400 * CONFIG_S3C_LOWLEVEL_UART_PORT))
 
@@ -68,6 +67,13 @@ ENTRY(s3c_cpu_resume)
 	ldr	r2, =LL_UART		/* for debug */
 
 #ifdef CONFIG_S3C_PM_DEBUG_LED_SMDK
+
+#define S3C64XX_GPNCON			(S3C64XX_GPN_BASE + 0x00)
+#define S3C64XX_GPNDAT			(S3C64XX_GPN_BASE + 0x04)
+
+#define S3C64XX_GPN_CONMASK(__gpio)	(0x3 << ((__gpio) * 2))
+#define S3C64XX_GPN_OUTPUT(__gpio)	(0x1 << ((__gpio) * 2))
+
 	/* Initialise the GPIO state if we are debugging via the SMDK LEDs,
 	 * as the uboot version supplied resets these to inputs during the
 	 * resume checks.
diff --git a/arch/arm/mach-s5p6442/Kconfig b/arch/arm/mach-s5p6442/Kconfig
deleted file mode 100644
index 33569e4007c4..000000000000
--- a/arch/arm/mach-s5p6442/Kconfig
+++ /dev/null
@@ -1,25 +0,0 @@
-# arch/arm/mach-s5p6442/Kconfig
-#
-# Copyright (c) 2010 Samsung Electronics Co., Ltd.
-#		http://www.samsung.com/
-#
-# Licensed under GPLv2
-
-# Configuration options for the S5P6442
-
-if ARCH_S5P6442
-
-config CPU_S5P6442
-	bool
-	select S3C_PL330_DMA
-	help
-	  Enable S5P6442 CPU support
-
-config MACH_SMDK6442
-	bool "SMDK6442"
-	select CPU_S5P6442
-	select S3C_DEV_WDT
-	help
-	  Machine support for Samsung SMDK6442
-
-endif
diff --git a/arch/arm/mach-s5p6442/Makefile b/arch/arm/mach-s5p6442/Makefile
deleted file mode 100644
index 90a3d8373416..000000000000
--- a/arch/arm/mach-s5p6442/Makefile
+++ /dev/null
@@ -1,24 +0,0 @@
-# arch/arm/mach-s5p6442/Makefile
-#
-# Copyright (c) 2010 Samsung Electronics Co., Ltd.
-# 		http://www.samsung.com/
-#
-# Licensed under GPLv2
-
-obj-y				:=
-obj-m				:=
-obj-n				:=
-obj-				:=
-
-# Core support for S5P6442 system
-
-obj-$(CONFIG_CPU_S5P6442)	+= cpu.o init.o clock.o dma.o
-obj-$(CONFIG_CPU_S5P6442)	+= setup-i2c0.o
-
-# machine support
-
-obj-$(CONFIG_MACH_SMDK6442)	+= mach-smdk6442.o
-
-# device support
-obj-y				+= dev-audio.o
-obj-$(CONFIG_S3C64XX_DEV_SPI)	+= dev-spi.o
diff --git a/arch/arm/mach-s5p6442/Makefile.boot b/arch/arm/mach-s5p6442/Makefile.boot
deleted file mode 100644
index ff90aa13bd67..000000000000
--- a/arch/arm/mach-s5p6442/Makefile.boot
+++ /dev/null
@@ -1,2 +0,0 @@
-   zreladdr-y	:= 0x20008000
-params_phys-y	:= 0x20000100
diff --git a/arch/arm/mach-s5p6442/clock.c b/arch/arm/mach-s5p6442/clock.c
deleted file mode 100644
index fbbc7bede685..000000000000
--- a/arch/arm/mach-s5p6442/clock.c
+++ /dev/null
@@ -1,420 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/clock.c
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6442 - Clock support
- *
- * 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/module.h>
-#include <linux/kernel.h>
-#include <linux/list.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-
-#include <mach/map.h>
-
-#include <plat/cpu-freq.h>
-#include <mach/regs-clock.h>
-#include <plat/clock.h>
-#include <plat/cpu.h>
-#include <plat/pll.h>
-#include <plat/s5p-clock.h>
-#include <plat/clock-clksrc.h>
-#include <plat/s5p6442.h>
-
-static struct clksrc_clk clk_mout_apll = {
-	.clk	= {
-		.name		= "mout_apll",
-		.id		= -1,
-	},
-	.sources	= &clk_src_apll,
-	.reg_src	= { .reg = S5P_CLK_SRC0, .shift = 0, .size = 1 },
-};
-
-static struct clksrc_clk clk_mout_mpll = {
-	.clk = {
-		.name		= "mout_mpll",
-		.id		= -1,
-	},
-	.sources	= &clk_src_mpll,
-	.reg_src	= { .reg = S5P_CLK_SRC0, .shift = 4, .size = 1 },
-};
-
-static struct clksrc_clk clk_mout_epll = {
-	.clk	= {
-		.name		= "mout_epll",
-		.id		= -1,
-	},
-	.sources	= &clk_src_epll,
-	.reg_src	= { .reg = S5P_CLK_SRC0, .shift = 8, .size = 1 },
-};
-
-/* Possible clock sources for ARM Mux */
-static struct clk *clk_src_arm_list[] = {
-	[1] = &clk_mout_apll.clk,
-	[2] = &clk_mout_mpll.clk,
-};
-
-static struct clksrc_sources clk_src_arm = {
-	.sources	= clk_src_arm_list,
-	.nr_sources	= ARRAY_SIZE(clk_src_arm_list),
-};
-
-static struct clksrc_clk clk_mout_arm = {
-	.clk	= {
-		.name		= "mout_arm",
-		.id		= -1,
-	},
-	.sources	= &clk_src_arm,
-	.reg_src	= { .reg = S5P_CLK_MUX_STAT0, .shift = 16, .size = 3 },
-};
-
-static struct clk clk_dout_a2m = {
-	.name		= "dout_a2m",
-	.id		= -1,
-	.parent		= &clk_mout_apll.clk,
-};
-
-/* Possible clock sources for D0 Mux */
-static struct clk *clk_src_d0_list[] = {
-	[1] = &clk_mout_mpll.clk,
-	[2] = &clk_dout_a2m,
-};
-
-static struct clksrc_sources clk_src_d0 = {
-	.sources	= clk_src_d0_list,
-	.nr_sources	= ARRAY_SIZE(clk_src_d0_list),
-};
-
-static struct clksrc_clk clk_mout_d0 = {
-	.clk = {
-		.name		= "mout_d0",
-		.id		= -1,
-	},
-	.sources	= &clk_src_d0,
-	.reg_src	= { .reg = S5P_CLK_MUX_STAT0, .shift = 20, .size = 3 },
-};
-
-static struct clk clk_dout_apll = {
-	.name		= "dout_apll",
-	.id		= -1,
-	.parent		= &clk_mout_arm.clk,
-};
-
-/* Possible clock sources for D0SYNC Mux */
-static struct clk *clk_src_d0sync_list[] = {
-	[1] = &clk_mout_d0.clk,
-	[2] = &clk_dout_apll,
-};
-
-static struct clksrc_sources clk_src_d0sync = {
-	.sources	= clk_src_d0sync_list,
-	.nr_sources	= ARRAY_SIZE(clk_src_d0sync_list),
-};
-
-static struct clksrc_clk clk_mout_d0sync = {
-	.clk	= {
-		.name		= "mout_d0sync",
-		.id		= -1,
-	},
-	.sources	= &clk_src_d0sync,
-	.reg_src	= { .reg = S5P_CLK_MUX_STAT1, .shift = 28, .size = 3 },
-};
-
-/* Possible clock sources for D1 Mux */
-static struct clk *clk_src_d1_list[] = {
-	[1] = &clk_mout_mpll.clk,
-	[2] = &clk_dout_a2m,
-};
-
-static struct clksrc_sources clk_src_d1 = {
-	.sources	= clk_src_d1_list,
-	.nr_sources	= ARRAY_SIZE(clk_src_d1_list),
-};
-
-static struct clksrc_clk clk_mout_d1 = {
-	.clk	= {
-		.name		= "mout_d1",
-		.id		= -1,
-	},
-	.sources	= &clk_src_d1,
-	.reg_src	= { .reg = S5P_CLK_MUX_STAT0, .shift = 24, .size = 3 },
-};
-
-/* Possible clock sources for D1SYNC Mux */
-static struct clk *clk_src_d1sync_list[] = {
-	[1] = &clk_mout_d1.clk,
-	[2] = &clk_dout_apll,
-};
-
-static struct clksrc_sources clk_src_d1sync = {
-	.sources	= clk_src_d1sync_list,
-	.nr_sources	= ARRAY_SIZE(clk_src_d1sync_list),
-};
-
-static struct clksrc_clk clk_mout_d1sync = {
-	.clk	= {
-		.name		= "mout_d1sync",
-		.id		= -1,
-	},
-	.sources	= &clk_src_d1sync,
-	.reg_src	= { .reg = S5P_CLK_MUX_STAT1, .shift = 24, .size = 3 },
-};
-
-static struct clk clk_hclkd0 = {
-	.name		= "hclkd0",
-	.id		= -1,
-	.parent		= &clk_mout_d0sync.clk,
-};
-
-static struct clk clk_hclkd1 = {
-	.name		= "hclkd1",
-	.id		= -1,
-	.parent		= &clk_mout_d1sync.clk,
-};
-
-static struct clk clk_pclkd0 = {
-	.name		= "pclkd0",
-	.id		= -1,
-	.parent		= &clk_hclkd0,
-};
-
-static struct clk clk_pclkd1 = {
-	.name		= "pclkd1",
-	.id		= -1,
-	.parent		= &clk_hclkd1,
-};
-
-int s5p6442_clk_ip0_ctrl(struct clk *clk, int enable)
-{
-	return s5p_gatectrl(S5P_CLKGATE_IP0, clk, enable);
-}
-
-int s5p6442_clk_ip3_ctrl(struct clk *clk, int enable)
-{
-	return s5p_gatectrl(S5P_CLKGATE_IP3, clk, enable);
-}
-
-static struct clksrc_clk clksrcs[] = {
-	{
-		.clk	= {
-			.name		= "dout_a2m",
-			.id		= -1,
-			.parent		= &clk_mout_apll.clk,
-		},
-		.sources = &clk_src_apll,
-		.reg_src = { .reg = S5P_CLK_SRC0, .shift = 0, .size = 1 },
-		.reg_div = { .reg = S5P_CLK_DIV0, .shift = 4, .size = 3 },
-	}, {
-		.clk	= {
-			.name		= "dout_apll",
-			.id		= -1,
-			.parent		= &clk_mout_arm.clk,
-		},
-		.sources = &clk_src_arm,
-		.reg_src = { .reg = S5P_CLK_MUX_STAT0, .shift = 16, .size = 3 },
-		.reg_div = { .reg = S5P_CLK_DIV0, .shift = 0, .size = 3 },
-	}, {
-		.clk	= {
-			.name		= "hclkd1",
-			.id		= -1,
-			.parent		= &clk_mout_d1sync.clk,
-		},
-		.sources = &clk_src_d1sync,
-		.reg_src = { .reg = S5P_CLK_MUX_STAT1, .shift = 24, .size = 3 },
-		.reg_div = { .reg = S5P_CLK_DIV0, .shift = 24, .size = 4 },
-	}, {
-		.clk	= {
-			.name		= "hclkd0",
-			.id		= -1,
-			.parent		= &clk_mout_d0sync.clk,
-		},
-		.sources = &clk_src_d0sync,
-		.reg_src = { .reg = S5P_CLK_MUX_STAT1, .shift = 28, .size = 3 },
-		.reg_div = { .reg = S5P_CLK_DIV0, .shift = 16, .size = 4 },
-	}, {
-		.clk	= {
-			.name		= "pclkd0",
-			.id		= -1,
-			.parent		= &clk_hclkd0,
-		},
-		.sources = &clk_src_d0sync,
-		.reg_src = { .reg = S5P_CLK_MUX_STAT1, .shift = 28, .size = 3 },
-		.reg_div = { .reg = S5P_CLK_DIV0, .shift = 20, .size = 3 },
-	}, {
-		.clk	= {
-			.name		= "pclkd1",
-			.id		= -1,
-			.parent		= &clk_hclkd1,
-		},
-		.sources = &clk_src_d1sync,
-		.reg_src = { .reg = S5P_CLK_MUX_STAT1, .shift = 24, .size = 3 },
-		.reg_div = { .reg = S5P_CLK_DIV0, .shift = 28, .size = 3 },
-	}
-};
-
-/* Clock initialisation code */
-static struct clksrc_clk *init_parents[] = {
-	&clk_mout_apll,
-	&clk_mout_mpll,
-	&clk_mout_epll,
-	&clk_mout_arm,
-	&clk_mout_d0,
-	&clk_mout_d0sync,
-	&clk_mout_d1,
-	&clk_mout_d1sync,
-};
-
-void __init_or_cpufreq s5p6442_setup_clocks(void)
-{
-	struct clk *pclkd0_clk;
-	struct clk *pclkd1_clk;
-
-	unsigned long xtal;
-	unsigned long arm;
-	unsigned long hclkd0 = 0;
-	unsigned long hclkd1 = 0;
-	unsigned long pclkd0 = 0;
-	unsigned long pclkd1 = 0;
-
-	unsigned long apll;
-	unsigned long mpll;
-	unsigned long epll;
-	unsigned int ptr;
-
-	printk(KERN_DEBUG "%s: registering clocks\n", __func__);
-
-	xtal = clk_get_rate(&clk_xtal);
-
-	printk(KERN_DEBUG "%s: xtal is %ld\n", __func__, xtal);
-
-	apll = s5p_get_pll45xx(xtal, __raw_readl(S5P_APLL_CON), pll_4508);
-	mpll = s5p_get_pll45xx(xtal, __raw_readl(S5P_MPLL_CON), pll_4502);
-	epll = s5p_get_pll45xx(xtal, __raw_readl(S5P_EPLL_CON), pll_4500);
-
-	printk(KERN_INFO "S5P6442: PLL settings, A=%ld, M=%ld, E=%ld",
-			apll, mpll, epll);
-
-	clk_fout_apll.rate = apll;
-	clk_fout_mpll.rate = mpll;
-	clk_fout_epll.rate = epll;
-
-	for (ptr = 0; ptr < ARRAY_SIZE(init_parents); ptr++)
-		s3c_set_clksrc(init_parents[ptr], true);
-
-	for (ptr = 0; ptr < ARRAY_SIZE(clksrcs); ptr++)
-		s3c_set_clksrc(&clksrcs[ptr], true);
-
-	arm = clk_get_rate(&clk_dout_apll);
-	hclkd0 = clk_get_rate(&clk_hclkd0);
-	hclkd1 = clk_get_rate(&clk_hclkd1);
-
-	pclkd0_clk = clk_get(NULL, "pclkd0");
-	BUG_ON(IS_ERR(pclkd0_clk));
-
-	pclkd0 = clk_get_rate(pclkd0_clk);
-	clk_put(pclkd0_clk);
-
-	pclkd1_clk = clk_get(NULL, "pclkd1");
-	BUG_ON(IS_ERR(pclkd1_clk));
-
-	pclkd1 = clk_get_rate(pclkd1_clk);
-	clk_put(pclkd1_clk);
-
-	printk(KERN_INFO "S5P6442: HCLKD0=%ld, HCLKD1=%ld, PCLKD0=%ld, PCLKD1=%ld\n",
-			hclkd0, hclkd1, pclkd0, pclkd1);
-
-	/* For backward compatibility */
-	clk_f.rate = arm;
-	clk_h.rate = hclkd1;
-	clk_p.rate = pclkd1;
-
-	clk_pclkd0.rate = pclkd0;
-	clk_pclkd1.rate = pclkd1;
-}
-
-static struct clk init_clocks_off[] = {
-	{
-		.name		= "pdma",
-		.id		= -1,
-		.parent		= &clk_pclkd1,
-		.enable		= s5p6442_clk_ip0_ctrl,
-		.ctrlbit	= (1 << 3),
-	},
-};
-
-static struct clk init_clocks[] = {
-	{
-		.name		= "systimer",
-		.id		= -1,
-		.parent		= &clk_pclkd1,
-		.enable		= s5p6442_clk_ip3_ctrl,
-		.ctrlbit	= (1<<16),
-	}, {
-		.name		= "uart",
-		.id		= 0,
-		.parent		= &clk_pclkd1,
-		.enable		= s5p6442_clk_ip3_ctrl,
-		.ctrlbit	= (1<<17),
-	}, {
-		.name		= "uart",
-		.id		= 1,
-		.parent		= &clk_pclkd1,
-		.enable		= s5p6442_clk_ip3_ctrl,
-		.ctrlbit	= (1<<18),
-	}, {
-		.name		= "uart",
-		.id		= 2,
-		.parent		= &clk_pclkd1,
-		.enable		= s5p6442_clk_ip3_ctrl,
-		.ctrlbit	= (1<<19),
-	}, {
-		.name		= "watchdog",
-		.id		= -1,
-		.parent		= &clk_pclkd1,
-		.enable		= s5p6442_clk_ip3_ctrl,
-		.ctrlbit	= (1 << 22),
-	}, {
-		.name		= "timers",
-		.id		= -1,
-		.parent		= &clk_pclkd1,
-		.enable		= s5p6442_clk_ip3_ctrl,
-		.ctrlbit	= (1<<23),
-	},
-};
-
-static struct clk *clks[] __initdata = {
-	&clk_ext,
-	&clk_epll,
-	&clk_mout_apll.clk,
-	&clk_mout_mpll.clk,
-	&clk_mout_epll.clk,
-	&clk_mout_d0.clk,
-	&clk_mout_d0sync.clk,
-	&clk_mout_d1.clk,
-	&clk_mout_d1sync.clk,
-	&clk_hclkd0,
-	&clk_pclkd0,
-	&clk_hclkd1,
-	&clk_pclkd1,
-};
-
-void __init s5p6442_register_clocks(void)
-{
-	s3c24xx_register_clocks(clks, ARRAY_SIZE(clks));
-
-	s3c_register_clksrc(clksrcs, ARRAY_SIZE(clksrcs));
-	s3c_register_clocks(init_clocks, ARRAY_SIZE(init_clocks));
-
-	s3c_register_clocks(init_clocks_off, ARRAY_SIZE(init_clocks_off));
-	s3c_disable_clocks(init_clocks_off, ARRAY_SIZE(init_clocks_off));
-
-	s3c_pwmclk_init();
-}
diff --git a/arch/arm/mach-s5p6442/cpu.c b/arch/arm/mach-s5p6442/cpu.c
deleted file mode 100644
index 842af86bda6d..000000000000
--- a/arch/arm/mach-s5p6442/cpu.c
+++ /dev/null
@@ -1,143 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/cpu.c
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.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/types.h>
-#include <linux/interrupt.h>
-#include <linux/list.h>
-#include <linux/timer.h>
-#include <linux/init.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-#include <linux/sysdev.h>
-#include <linux/serial_core.h>
-#include <linux/platform_device.h>
-#include <linux/sched.h>
-
-#include <asm/mach/arch.h>
-#include <asm/mach/map.h>
-#include <asm/mach/irq.h>
-
-#include <asm/proc-fns.h>
-
-#include <mach/hardware.h>
-#include <mach/map.h>
-#include <asm/irq.h>
-
-#include <plat/regs-serial.h>
-#include <mach/regs-clock.h>
-
-#include <plat/cpu.h>
-#include <plat/devs.h>
-#include <plat/clock.h>
-#include <plat/s5p6442.h>
-
-/* Initial IO mappings */
-
-static struct map_desc s5p6442_iodesc[] __initdata = {
-	{
-		.virtual	= (unsigned long)S5P_VA_SYSTIMER,
-		.pfn		= __phys_to_pfn(S5P6442_PA_SYSTIMER),
-		.length		= SZ_16K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= (unsigned long)S5P_VA_GPIO,
-		.pfn		= __phys_to_pfn(S5P6442_PA_GPIO),
-		.length		= SZ_4K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= (unsigned long)VA_VIC0,
-		.pfn		= __phys_to_pfn(S5P6442_PA_VIC0),
-		.length		= SZ_16K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= (unsigned long)VA_VIC1,
-		.pfn		= __phys_to_pfn(S5P6442_PA_VIC1),
-		.length		= SZ_16K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= (unsigned long)VA_VIC2,
-		.pfn		= __phys_to_pfn(S5P6442_PA_VIC2),
-		.length		= SZ_16K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= (unsigned long)S3C_VA_UART,
-		.pfn		= __phys_to_pfn(S3C_PA_UART),
-		.length		= SZ_512K,
-		.type		= MT_DEVICE,
-	}
-};
-
-static void s5p6442_idle(void)
-{
-	if (!need_resched())
-		cpu_do_idle();
-
-	local_irq_enable();
-}
-
-/*
- * s5p6442_map_io
- *
- * register the standard cpu IO areas
- */
-
-void __init s5p6442_map_io(void)
-{
-	iotable_init(s5p6442_iodesc, ARRAY_SIZE(s5p6442_iodesc));
-}
-
-void __init s5p6442_init_clocks(int xtal)
-{
-	printk(KERN_DEBUG "%s: initializing clocks\n", __func__);
-
-	s3c24xx_register_baseclocks(xtal);
-	s5p_register_clocks(xtal);
-	s5p6442_register_clocks();
-	s5p6442_setup_clocks();
-}
-
-void __init s5p6442_init_irq(void)
-{
-	/* S5P6442 supports 3 VIC */
-	u32 vic[3];
-
-	/* VIC0, VIC1, and VIC2: some interrupt reserved */
-	vic[0] = 0x7fefffff;
-	vic[1] = 0X7f389c81;
-	vic[2] = 0X1bbbcfff;
-
-	s5p_init_irq(vic, ARRAY_SIZE(vic));
-}
-
-struct sysdev_class s5p6442_sysclass = {
-	.name	= "s5p6442-core",
-};
-
-static struct sys_device s5p6442_sysdev = {
-	.cls	= &s5p6442_sysclass,
-};
-
-static int __init s5p6442_core_init(void)
-{
-	return sysdev_class_register(&s5p6442_sysclass);
-}
-
-core_initcall(s5p6442_core_init);
-
-int __init s5p6442_init(void)
-{
-	printk(KERN_INFO "S5P6442: Initializing architecture\n");
-
-	/* set idle function */
-	pm_idle = s5p6442_idle;
-
-	return sysdev_register(&s5p6442_sysdev);
-}
diff --git a/arch/arm/mach-s5p6442/dev-audio.c b/arch/arm/mach-s5p6442/dev-audio.c
deleted file mode 100644
index 8719dc41fe32..000000000000
--- a/arch/arm/mach-s5p6442/dev-audio.c
+++ /dev/null
@@ -1,217 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/dev-audio.c
- *
- * Copyright (c) 2010 Samsung Electronics Co. Ltd
- *	Jaswinder Singh <jassi.brar@samsung.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/platform_device.h>
-#include <linux/dma-mapping.h>
-#include <linux/gpio.h>
-
-#include <plat/gpio-cfg.h>
-#include <plat/audio.h>
-
-#include <mach/map.h>
-#include <mach/dma.h>
-#include <mach/irqs.h>
-
-static int s5p6442_cfg_i2s(struct platform_device *pdev)
-{
-	unsigned int base;
-
-	/* configure GPIO for i2s port */
-	switch (pdev->id) {
-	case 1:
-		base = S5P6442_GPC1(0);
-		break;
-
-	case 0:
-		base = S5P6442_GPC0(0);
-		break;
-
-	default:
-		printk(KERN_ERR "Invalid Device %d\n", pdev->id);
-		return -EINVAL;
-	}
-
-	s3c_gpio_cfgpin_range(base, 5, S3C_GPIO_SFN(2));
-	return 0;
-}
-
-static const char *rclksrc_v35[] = {
-	[0] = "busclk",
-	[1] = "i2sclk",
-};
-
-static struct s3c_audio_pdata i2sv35_pdata = {
-	.cfg_gpio = s5p6442_cfg_i2s,
-	.type = {
-		.i2s = {
-			.quirks = QUIRK_SEC_DAI | QUIRK_NEED_RSTCLR,
-			.src_clk = rclksrc_v35,
-		},
-	},
-};
-
-static struct resource s5p6442_iis0_resource[] = {
-	[0] = {
-		.start = S5P6442_PA_I2S0,
-		.end   = S5P6442_PA_I2S0 + 0x100 - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = DMACH_I2S0_TX,
-		.end   = DMACH_I2S0_TX,
-		.flags = IORESOURCE_DMA,
-	},
-	[2] = {
-		.start = DMACH_I2S0_RX,
-		.end   = DMACH_I2S0_RX,
-		.flags = IORESOURCE_DMA,
-	},
-	[3] = {
-		.start = DMACH_I2S0S_TX,
-		.end = DMACH_I2S0S_TX,
-		.flags = IORESOURCE_DMA,
-	},
-};
-
-struct platform_device s5p6442_device_iis0 = {
-	.name = "samsung-i2s",
-	.id = 0,
-	.num_resources	  = ARRAY_SIZE(s5p6442_iis0_resource),
-	.resource	  = s5p6442_iis0_resource,
-	.dev = {
-		.platform_data = &i2sv35_pdata,
-	},
-};
-
-static const char *rclksrc_v3[] = {
-	[0] = "iis",
-	[1] = "sclk_audio",
-};
-
-static struct s3c_audio_pdata i2sv3_pdata = {
-	.cfg_gpio = s5p6442_cfg_i2s,
-	.type = {
-		.i2s = {
-			.src_clk = rclksrc_v3,
-		},
-	},
-};
-
-static struct resource s5p6442_iis1_resource[] = {
-	[0] = {
-		.start = S5P6442_PA_I2S1,
-		.end   = S5P6442_PA_I2S1 + 0x100 - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = DMACH_I2S1_TX,
-		.end   = DMACH_I2S1_TX,
-		.flags = IORESOURCE_DMA,
-	},
-	[2] = {
-		.start = DMACH_I2S1_RX,
-		.end   = DMACH_I2S1_RX,
-		.flags = IORESOURCE_DMA,
-	},
-};
-
-struct platform_device s5p6442_device_iis1 = {
-	.name		  = "samsung-i2s",
-	.id		  = 1,
-	.num_resources	  = ARRAY_SIZE(s5p6442_iis1_resource),
-	.resource	  = s5p6442_iis1_resource,
-	.dev = {
-		.platform_data = &i2sv3_pdata,
-	},
-};
-
-/* PCM Controller platform_devices */
-
-static int s5p6442_pcm_cfg_gpio(struct platform_device *pdev)
-{
-	unsigned int base;
-
-	switch (pdev->id) {
-	case 0:
-		base = S5P6442_GPC0(0);
-		break;
-
-	case 1:
-		base = S5P6442_GPC1(0);
-		break;
-
-	default:
-		printk(KERN_DEBUG "Invalid PCM Controller number!");
-		return -EINVAL;
-	}
-
-	s3c_gpio_cfgpin_range(base, 5, S3C_GPIO_SFN(3));
-	return 0;
-}
-
-static struct s3c_audio_pdata s3c_pcm_pdata = {
-	.cfg_gpio = s5p6442_pcm_cfg_gpio,
-};
-
-static struct resource s5p6442_pcm0_resource[] = {
-	[0] = {
-		.start = S5P6442_PA_PCM0,
-		.end   = S5P6442_PA_PCM0 + 0x100 - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = DMACH_PCM0_TX,
-		.end   = DMACH_PCM0_TX,
-		.flags = IORESOURCE_DMA,
-	},
-	[2] = {
-		.start = DMACH_PCM0_RX,
-		.end   = DMACH_PCM0_RX,
-		.flags = IORESOURCE_DMA,
-	},
-};
-
-struct platform_device s5p6442_device_pcm0 = {
-	.name		  = "samsung-pcm",
-	.id		  = 0,
-	.num_resources	  = ARRAY_SIZE(s5p6442_pcm0_resource),
-	.resource	  = s5p6442_pcm0_resource,
-	.dev = {
-		.platform_data = &s3c_pcm_pdata,
-	},
-};
-
-static struct resource s5p6442_pcm1_resource[] = {
-	[0] = {
-		.start = S5P6442_PA_PCM1,
-		.end   = S5P6442_PA_PCM1 + 0x100 - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = DMACH_PCM1_TX,
-		.end   = DMACH_PCM1_TX,
-		.flags = IORESOURCE_DMA,
-	},
-	[2] = {
-		.start = DMACH_PCM1_RX,
-		.end   = DMACH_PCM1_RX,
-		.flags = IORESOURCE_DMA,
-	},
-};
-
-struct platform_device s5p6442_device_pcm1 = {
-	.name		  = "samsung-pcm",
-	.id		  = 1,
-	.num_resources	  = ARRAY_SIZE(s5p6442_pcm1_resource),
-	.resource	  = s5p6442_pcm1_resource,
-	.dev = {
-		.platform_data = &s3c_pcm_pdata,
-	},
-};
diff --git a/arch/arm/mach-s5p6442/dev-spi.c b/arch/arm/mach-s5p6442/dev-spi.c
deleted file mode 100644
index cce8c2470709..000000000000
--- a/arch/arm/mach-s5p6442/dev-spi.c
+++ /dev/null
@@ -1,121 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/dev-spi.c
- *
- * Copyright (C) 2010 Samsung Electronics Co. Ltd.
- *	Jaswinder Singh <jassi.brar@samsung.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/platform_device.h>
-#include <linux/dma-mapping.h>
-#include <linux/gpio.h>
-
-#include <mach/dma.h>
-#include <mach/map.h>
-#include <mach/irqs.h>
-#include <mach/spi-clocks.h>
-
-#include <plat/s3c64xx-spi.h>
-#include <plat/gpio-cfg.h>
-
-static char *spi_src_clks[] = {
-	[S5P6442_SPI_SRCCLK_PCLK] = "pclk",
-	[S5P6442_SPI_SRCCLK_SCLK] = "spi_epll",
-};
-
-/* SPI Controller platform_devices */
-
-/* Since we emulate multi-cs capability, we do not touch the CS.
- * The emulated CS is toggled by board specific mechanism, as it can
- * be either some immediate GPIO or some signal out of some other
- * chip in between ... or some yet another way.
- * We simply do not assume anything about CS.
- */
-static int s5p6442_spi_cfg_gpio(struct platform_device *pdev)
-{
-	switch (pdev->id) {
-	case 0:
-		s3c_gpio_cfgpin(S5P6442_GPB(0), S3C_GPIO_SFN(2));
-		s3c_gpio_setpull(S5P6442_GPB(0), S3C_GPIO_PULL_UP);
-		s3c_gpio_cfgall_range(S5P6442_GPB(2), 2,
-				      S3C_GPIO_SFN(2), S3C_GPIO_PULL_UP);
-		break;
-
-	default:
-		dev_err(&pdev->dev, "Invalid SPI Controller number!");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static struct resource s5p6442_spi0_resource[] = {
-	[0] = {
-		.start = S5P6442_PA_SPI,
-		.end   = S5P6442_PA_SPI + 0x100 - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = DMACH_SPI0_TX,
-		.end   = DMACH_SPI0_TX,
-		.flags = IORESOURCE_DMA,
-	},
-	[2] = {
-		.start = DMACH_SPI0_RX,
-		.end   = DMACH_SPI0_RX,
-		.flags = IORESOURCE_DMA,
-	},
-	[3] = {
-		.start = IRQ_SPI0,
-		.end   = IRQ_SPI0,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct s3c64xx_spi_info s5p6442_spi0_pdata = {
-	.cfg_gpio = s5p6442_spi_cfg_gpio,
-	.fifo_lvl_mask = 0x1ff,
-	.rx_lvl_offset = 15,
-};
-
-static u64 spi_dmamask = DMA_BIT_MASK(32);
-
-struct platform_device s5p6442_device_spi = {
-	.name		  = "s3c64xx-spi",
-	.id		  = 0,
-	.num_resources	  = ARRAY_SIZE(s5p6442_spi0_resource),
-	.resource	  = s5p6442_spi0_resource,
-	.dev = {
-		.dma_mask		= &spi_dmamask,
-		.coherent_dma_mask	= DMA_BIT_MASK(32),
-		.platform_data = &s5p6442_spi0_pdata,
-	},
-};
-
-void __init s5p6442_spi_set_info(int cntrlr, int src_clk_nr, int num_cs)
-{
-	struct s3c64xx_spi_info *pd;
-
-	/* Reject invalid configuration */
-	if (!num_cs || src_clk_nr < 0
-			|| src_clk_nr > S5P6442_SPI_SRCCLK_SCLK) {
-		printk(KERN_ERR "%s: Invalid SPI configuration\n", __func__);
-		return;
-	}
-
-	switch (cntrlr) {
-	case 0:
-		pd = &s5p6442_spi0_pdata;
-		break;
-	default:
-		printk(KERN_ERR "%s: Invalid SPI controller(%d)\n",
-							__func__, cntrlr);
-		return;
-	}
-
-	pd->num_cs = num_cs;
-	pd->src_clk_nr = src_clk_nr;
-	pd->src_clk_name = spi_src_clks[src_clk_nr];
-}
diff --git a/arch/arm/mach-s5p6442/dma.c b/arch/arm/mach-s5p6442/dma.c
deleted file mode 100644
index 7dfb13654f8a..000000000000
--- a/arch/arm/mach-s5p6442/dma.c
+++ /dev/null
@@ -1,105 +0,0 @@
-/*
- * Copyright (C) 2010 Samsung Electronics Co. Ltd.
- *	Jaswinder Singh <jassi.brar@samsung.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.
- *
- * 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/platform_device.h>
-#include <linux/dma-mapping.h>
-
-#include <plat/devs.h>
-#include <plat/irqs.h>
-
-#include <mach/map.h>
-#include <mach/irqs.h>
-
-#include <plat/s3c-pl330-pdata.h>
-
-static u64 dma_dmamask = DMA_BIT_MASK(32);
-
-static struct resource s5p6442_pdma_resource[] = {
-	[0] = {
-		.start  = S5P6442_PA_PDMA,
-		.end    = S5P6442_PA_PDMA + SZ_4K,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= IRQ_PDMA,
-		.end	= IRQ_PDMA,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct s3c_pl330_platdata s5p6442_pdma_pdata = {
-	.peri = {
-		[0] = DMACH_UART0_RX,
-		[1] = DMACH_UART0_TX,
-		[2] = DMACH_UART1_RX,
-		[3] = DMACH_UART1_TX,
-		[4] = DMACH_UART2_RX,
-		[5] = DMACH_UART2_TX,
-		[6] = DMACH_MAX,
-		[7] = DMACH_MAX,
-		[8] = DMACH_MAX,
-		[9] = DMACH_I2S0_RX,
-		[10] = DMACH_I2S0_TX,
-		[11] = DMACH_I2S0S_TX,
-		[12] = DMACH_I2S1_RX,
-		[13] = DMACH_I2S1_TX,
-		[14] = DMACH_MAX,
-		[15] = DMACH_MAX,
-		[16] = DMACH_SPI0_RX,
-		[17] = DMACH_SPI0_TX,
-		[18] = DMACH_MAX,
-		[19] = DMACH_MAX,
-		[20] = DMACH_PCM0_RX,
-		[21] = DMACH_PCM0_TX,
-		[22] = DMACH_PCM1_RX,
-		[23] = DMACH_PCM1_TX,
-		[24] = DMACH_MAX,
-		[25] = DMACH_MAX,
-		[26] = DMACH_MAX,
-		[27] = DMACH_MSM_REQ0,
-		[28] = DMACH_MSM_REQ1,
-		[29] = DMACH_MSM_REQ2,
-		[30] = DMACH_MSM_REQ3,
-		[31] = DMACH_MAX,
-	},
-};
-
-static struct platform_device s5p6442_device_pdma = {
-	.name		= "s3c-pl330",
-	.id		= -1,
-	.num_resources	= ARRAY_SIZE(s5p6442_pdma_resource),
-	.resource	= s5p6442_pdma_resource,
-	.dev		= {
-		.dma_mask = &dma_dmamask,
-		.coherent_dma_mask = DMA_BIT_MASK(32),
-		.platform_data = &s5p6442_pdma_pdata,
-	},
-};
-
-static struct platform_device *s5p6442_dmacs[] __initdata = {
-	&s5p6442_device_pdma,
-};
-
-static int __init s5p6442_dma_init(void)
-{
-	platform_add_devices(s5p6442_dmacs, ARRAY_SIZE(s5p6442_dmacs));
-
-	return 0;
-}
-arch_initcall(s5p6442_dma_init);
diff --git a/arch/arm/mach-s5p6442/include/mach/debug-macro.S b/arch/arm/mach-s5p6442/include/mach/debug-macro.S
deleted file mode 100644
index e2213205d780..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/debug-macro.S
+++ /dev/null
@@ -1,35 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/debug-macro.S
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * Based on arch/arm/mach-s3c6400/include/mach/debug-macro.S
- *
- * 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.
-*/
-
-/* pull in the relevant register and map files. */
-
-#include <mach/map.h>
-#include <plat/regs-serial.h>
-
-	.macro addruart, rp, rv
-		ldr	\rp, = S3C_PA_UART
-		ldr	\rv, = S3C_VA_UART
-#if CONFIG_DEBUG_S3C_UART != 0
-		add	\rp, \rp, #(0x400 * CONFIG_DEBUG_S3C_UART)
-		add	\rv, \rv, #(0x400 * CONFIG_DEBUG_S3C_UART)
-#endif
-	.endm
-
-#define fifo_full fifo_full_s5pv210
-#define fifo_level fifo_level_s5pv210
-
-/* include the reset of the code which will do the work, we're only
- * compiling for a single cpu processor type so the default of s3c2440
- * will be fine with us.
- */
-
-#include <plat/debug-macro.S>
diff --git a/arch/arm/mach-s5p6442/include/mach/entry-macro.S b/arch/arm/mach-s5p6442/include/mach/entry-macro.S
deleted file mode 100644
index 6d574edbf1ae..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/entry-macro.S
+++ /dev/null
@@ -1,48 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/entry-macro.S
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * Low-level IRQ helper macros for the Samsung S5P6442
- *
- * 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 <asm/hardware/vic.h>
-#include <mach/map.h>
-#include <plat/irqs.h>
-
-	.macro	disable_fiq
-	.endm
-
-	.macro	get_irqnr_preamble, base, tmp
-	ldr	\base, =VA_VIC0
-	.endm
-
-	.macro	arch_ret_to_user, tmp1, tmp2
-	.endm
-
-	.macro	get_irqnr_and_base, irqnr, irqstat, base, tmp
-
-	@ check the vic0
-	mov	\irqnr, # S5P_IRQ_OFFSET + 31
-	ldr	\irqstat, [ \base, # VIC_IRQ_STATUS ]
-	teq	\irqstat, #0
-
-	@ otherwise try vic1
-	addeq	\tmp, \base, #(VA_VIC1 - VA_VIC0)
-	addeq	\irqnr, \irqnr, #32
-	ldreq	\irqstat, [ \tmp, # VIC_IRQ_STATUS ]
-	teqeq	\irqstat, #0
-
-	@ otherwise try vic2
-	addeq	\tmp, \base, #(VA_VIC2 - VA_VIC0)
-	addeq	\irqnr, \irqnr, #32
-	ldreq	\irqstat, [ \tmp, # VIC_IRQ_STATUS ]
-	teqeq	\irqstat, #0
-
-	clzne	\irqstat, \irqstat
-	subne	\irqnr, \irqnr, \irqstat
-	.endm
diff --git a/arch/arm/mach-s5p6442/include/mach/gpio.h b/arch/arm/mach-s5p6442/include/mach/gpio.h
deleted file mode 100644
index b8715df2fdab..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/gpio.h
+++ /dev/null
@@ -1,123 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/gpio.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6442 - GPIO lib support
- *
- * 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_GPIO_H
-#define __ASM_ARCH_GPIO_H __FILE__
-
-#define gpio_get_value	__gpio_get_value
-#define gpio_set_value	__gpio_set_value
-#define gpio_cansleep	__gpio_cansleep
-#define gpio_to_irq	__gpio_to_irq
-
-/* GPIO bank sizes */
-#define S5P6442_GPIO_A0_NR	(8)
-#define S5P6442_GPIO_A1_NR	(2)
-#define S5P6442_GPIO_B_NR	(4)
-#define S5P6442_GPIO_C0_NR	(5)
-#define S5P6442_GPIO_C1_NR	(5)
-#define S5P6442_GPIO_D0_NR	(2)
-#define S5P6442_GPIO_D1_NR	(6)
-#define S5P6442_GPIO_E0_NR	(8)
-#define S5P6442_GPIO_E1_NR	(5)
-#define S5P6442_GPIO_F0_NR	(8)
-#define S5P6442_GPIO_F1_NR	(8)
-#define S5P6442_GPIO_F2_NR	(8)
-#define S5P6442_GPIO_F3_NR	(6)
-#define S5P6442_GPIO_G0_NR	(7)
-#define S5P6442_GPIO_G1_NR	(7)
-#define S5P6442_GPIO_G2_NR	(7)
-#define S5P6442_GPIO_H0_NR	(8)
-#define S5P6442_GPIO_H1_NR	(8)
-#define S5P6442_GPIO_H2_NR	(8)
-#define S5P6442_GPIO_H3_NR	(8)
-#define S5P6442_GPIO_J0_NR	(8)
-#define S5P6442_GPIO_J1_NR	(6)
-#define S5P6442_GPIO_J2_NR	(8)
-#define S5P6442_GPIO_J3_NR	(8)
-#define S5P6442_GPIO_J4_NR	(5)
-
-/* GPIO bank numbers */
-
-/* CONFIG_S3C_GPIO_SPACE allows the user to select extra
- * space for debugging purposes so that any accidental
- * change from one gpio bank to another can be caught.
-*/
-
-#define S5P6442_GPIO_NEXT(__gpio) \
-	((__gpio##_START) + (__gpio##_NR) + CONFIG_S3C_GPIO_SPACE + 1)
-
-enum s5p_gpio_number {
-	S5P6442_GPIO_A0_START	= 0,
-	S5P6442_GPIO_A1_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_A0),
-	S5P6442_GPIO_B_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_A1),
-	S5P6442_GPIO_C0_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_B),
-	S5P6442_GPIO_C1_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_C0),
-	S5P6442_GPIO_D0_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_C1),
-	S5P6442_GPIO_D1_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_D0),
-	S5P6442_GPIO_E0_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_D1),
-	S5P6442_GPIO_E1_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_E0),
-	S5P6442_GPIO_F0_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_E1),
-	S5P6442_GPIO_F1_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_F0),
-	S5P6442_GPIO_F2_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_F1),
-	S5P6442_GPIO_F3_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_F2),
-	S5P6442_GPIO_G0_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_F3),
-	S5P6442_GPIO_G1_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_G0),
-	S5P6442_GPIO_G2_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_G1),
-	S5P6442_GPIO_H0_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_G2),
-	S5P6442_GPIO_H1_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_H0),
-	S5P6442_GPIO_H2_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_H1),
-	S5P6442_GPIO_H3_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_H2),
-	S5P6442_GPIO_J0_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_H3),
-	S5P6442_GPIO_J1_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_J0),
-	S5P6442_GPIO_J2_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_J1),
-	S5P6442_GPIO_J3_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_J2),
-	S5P6442_GPIO_J4_START	= S5P6442_GPIO_NEXT(S5P6442_GPIO_J3),
-};
-
-/* S5P6442 GPIO number definitions. */
-#define S5P6442_GPA0(_nr)	(S5P6442_GPIO_A0_START + (_nr))
-#define S5P6442_GPA1(_nr)	(S5P6442_GPIO_A1_START + (_nr))
-#define S5P6442_GPB(_nr)	(S5P6442_GPIO_B_START + (_nr))
-#define S5P6442_GPC0(_nr)	(S5P6442_GPIO_C0_START + (_nr))
-#define S5P6442_GPC1(_nr)	(S5P6442_GPIO_C1_START + (_nr))
-#define S5P6442_GPD0(_nr)	(S5P6442_GPIO_D0_START + (_nr))
-#define S5P6442_GPD1(_nr)	(S5P6442_GPIO_D1_START + (_nr))
-#define S5P6442_GPE0(_nr)	(S5P6442_GPIO_E0_START + (_nr))
-#define S5P6442_GPE1(_nr)	(S5P6442_GPIO_E1_START + (_nr))
-#define S5P6442_GPF0(_nr)	(S5P6442_GPIO_F0_START + (_nr))
-#define S5P6442_GPF1(_nr)	(S5P6442_GPIO_F1_START + (_nr))
-#define S5P6442_GPF2(_nr)	(S5P6442_GPIO_F2_START + (_nr))
-#define S5P6442_GPF3(_nr)	(S5P6442_GPIO_F3_START + (_nr))
-#define S5P6442_GPG0(_nr)	(S5P6442_GPIO_G0_START + (_nr))
-#define S5P6442_GPG1(_nr)	(S5P6442_GPIO_G1_START + (_nr))
-#define S5P6442_GPG2(_nr)	(S5P6442_GPIO_G2_START + (_nr))
-#define S5P6442_GPH0(_nr)	(S5P6442_GPIO_H0_START + (_nr))
-#define S5P6442_GPH1(_nr)	(S5P6442_GPIO_H1_START + (_nr))
-#define S5P6442_GPH2(_nr)	(S5P6442_GPIO_H2_START + (_nr))
-#define S5P6442_GPH3(_nr)	(S5P6442_GPIO_H3_START + (_nr))
-#define S5P6442_GPJ0(_nr)	(S5P6442_GPIO_J0_START + (_nr))
-#define S5P6442_GPJ1(_nr)	(S5P6442_GPIO_J1_START + (_nr))
-#define S5P6442_GPJ2(_nr)	(S5P6442_GPIO_J2_START + (_nr))
-#define S5P6442_GPJ3(_nr)	(S5P6442_GPIO_J3_START + (_nr))
-#define S5P6442_GPJ4(_nr)	(S5P6442_GPIO_J4_START + (_nr))
-
-/* the end of the S5P6442 specific gpios */
-#define S5P6442_GPIO_END	(S5P6442_GPJ4(S5P6442_GPIO_J4_NR) + 1)
-#define S3C_GPIO_END		S5P6442_GPIO_END
-
-/* define the number of gpios we need to the one after the GPJ4() range */
-#define ARCH_NR_GPIOS		(S5P6442_GPJ4(S5P6442_GPIO_J4_NR) +	\
-				 CONFIG_SAMSUNG_GPIO_EXTRA + 1)
-
-#include <asm-generic/gpio.h>
-
-#endif /* __ASM_ARCH_GPIO_H */
diff --git a/arch/arm/mach-s5p6442/include/mach/hardware.h b/arch/arm/mach-s5p6442/include/mach/hardware.h
deleted file mode 100644
index 8cd7b67b49d4..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/hardware.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/hardware.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6442 - Hardware support
- *
- * 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_HARDWARE_H
-#define __ASM_ARCH_HARDWARE_H __FILE__
-
-/* currently nothing here, placeholder */
-
-#endif /* __ASM_ARCH_HARDWARE_H */
diff --git a/arch/arm/mach-s5p6442/include/mach/io.h b/arch/arm/mach-s5p6442/include/mach/io.h
deleted file mode 100644
index 5d2195ad0b67..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/io.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* arch/arm/mach-s5p6442/include/mach/io.h
- *
- * Copyright 2008-2010 Ben Dooks <ben-linux@fluff.org>
- *
- * Default IO routines for S5P6442
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-/* No current ISA/PCI bus support. */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#define IO_SPACE_LIMIT (0xFFFFFFFF)
-
-#endif
diff --git a/arch/arm/mach-s5p6442/include/mach/irqs.h b/arch/arm/mach-s5p6442/include/mach/irqs.h
deleted file mode 100644
index 3fbc6c3ad2da..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/irqs.h
+++ /dev/null
@@ -1,87 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/irqs.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6442 - IRQ definitions
- *
- * 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_IRQS_H
-#define __ASM_ARCH_IRQS_H __FILE__
-
-#include <plat/irqs.h>
-
-/* VIC0 */
-#define IRQ_EINT16_31 		S5P_IRQ_VIC0(16)
-#define IRQ_BATF 		S5P_IRQ_VIC0(17)
-#define IRQ_MDMA 		S5P_IRQ_VIC0(18)
-#define IRQ_PDMA 		S5P_IRQ_VIC0(19)
-#define IRQ_TIMER0_VIC		S5P_IRQ_VIC0(21)
-#define IRQ_TIMER1_VIC		S5P_IRQ_VIC0(22)
-#define IRQ_TIMER2_VIC		S5P_IRQ_VIC0(23)
-#define IRQ_TIMER3_VIC		S5P_IRQ_VIC0(24)
-#define IRQ_TIMER4_VIC		S5P_IRQ_VIC0(25)
-#define IRQ_SYSTIMER		S5P_IRQ_VIC0(26)
-#define IRQ_WDT			S5P_IRQ_VIC0(27)
-#define IRQ_RTC_ALARM		S5P_IRQ_VIC0(28)
-#define IRQ_RTC_TIC		S5P_IRQ_VIC0(29)
-#define IRQ_GPIOINT		S5P_IRQ_VIC0(30)
-
-/* VIC1 */
-#define IRQ_PMU			S5P_IRQ_VIC1(0)
-#define IRQ_ONENAND 		S5P_IRQ_VIC1(7)
-#define IRQ_UART0 		S5P_IRQ_VIC1(10)
-#define IRQ_UART1 		S5P_IRQ_VIC1(11)
-#define IRQ_UART2 		S5P_IRQ_VIC1(12)
-#define IRQ_SPI0 		S5P_IRQ_VIC1(15)
-#define IRQ_IIC 		S5P_IRQ_VIC1(19)
-#define IRQ_IIC1 		S5P_IRQ_VIC1(20)
-#define IRQ_IIC2 		S5P_IRQ_VIC1(21)
-#define IRQ_OTG 		S5P_IRQ_VIC1(24)
-#define IRQ_MSM 		S5P_IRQ_VIC1(25)
-#define IRQ_HSMMC0 		S5P_IRQ_VIC1(26)
-#define IRQ_HSMMC1 		S5P_IRQ_VIC1(27)
-#define IRQ_HSMMC2 		S5P_IRQ_VIC1(28)
-#define IRQ_COMMRX 		S5P_IRQ_VIC1(29)
-#define IRQ_COMMTX 		S5P_IRQ_VIC1(30)
-
-/* VIC2 */
-#define IRQ_LCD0 		S5P_IRQ_VIC2(0)
-#define IRQ_LCD1 		S5P_IRQ_VIC2(1)
-#define IRQ_LCD2 		S5P_IRQ_VIC2(2)
-#define IRQ_LCD3 		S5P_IRQ_VIC2(3)
-#define IRQ_ROTATOR 		S5P_IRQ_VIC2(4)
-#define IRQ_FIMC0 		S5P_IRQ_VIC2(5)
-#define IRQ_FIMC1 		S5P_IRQ_VIC2(6)
-#define IRQ_FIMC2 		S5P_IRQ_VIC2(7)
-#define IRQ_JPEG 		S5P_IRQ_VIC2(8)
-#define IRQ_3D 			S5P_IRQ_VIC2(10)
-#define IRQ_Mixer 		S5P_IRQ_VIC2(11)
-#define IRQ_MFC 		S5P_IRQ_VIC2(14)
-#define IRQ_TVENC 		S5P_IRQ_VIC2(15)
-#define IRQ_I2S0 		S5P_IRQ_VIC2(16)
-#define IRQ_I2S1 		S5P_IRQ_VIC2(17)
-#define IRQ_RP 			S5P_IRQ_VIC2(19)
-#define IRQ_PCM0 		S5P_IRQ_VIC2(20)
-#define IRQ_PCM1 		S5P_IRQ_VIC2(21)
-#define IRQ_ADC 		S5P_IRQ_VIC2(23)
-#define IRQ_PENDN 		S5P_IRQ_VIC2(24)
-#define IRQ_KEYPAD 		S5P_IRQ_VIC2(25)
-#define IRQ_SSS_INT 		S5P_IRQ_VIC2(27)
-#define IRQ_SSS_HASH 		S5P_IRQ_VIC2(28)
-#define IRQ_VIC_END 		S5P_IRQ_VIC2(31)
-
-#define S5P_IRQ_EINT_BASE	(IRQ_VIC_END + 1)
-
-#define S5P_EINT_BASE1		(S5P_IRQ_VIC0(0))
-#define S5P_EINT_BASE2		(S5P_IRQ_EINT_BASE)
-
-/* Set the default NR_IRQS */
-
-#define NR_IRQS 		(IRQ_EINT(31) + 1)
-
-#endif /* __ASM_ARCH_IRQS_H */
diff --git a/arch/arm/mach-s5p6442/include/mach/map.h b/arch/arm/mach-s5p6442/include/mach/map.h
deleted file mode 100644
index 058dab4482a1..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/map.h
+++ /dev/null
@@ -1,76 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/map.h
- *
- * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6442 - Memory map definitions
- *
- * 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_MAP_H
-#define __ASM_ARCH_MAP_H __FILE__
-
-#include <plat/map-base.h>
-#include <plat/map-s5p.h>
-
-#define S5P6442_PA_SDRAM	0x20000000
-
-#define S5P6442_PA_I2S0		0xC0B00000
-#define S5P6442_PA_I2S1		0xF2200000
-
-#define S5P6442_PA_CHIPID	0xE0000000
-
-#define S5P6442_PA_SYSCON	0xE0100000
-
-#define S5P6442_PA_GPIO		0xE0200000
-
-#define S5P6442_PA_VIC0		0xE4000000
-#define S5P6442_PA_VIC1		0xE4100000
-#define S5P6442_PA_VIC2		0xE4200000
-
-#define S5P6442_PA_SROMC	0xE7000000
-
-#define S5P6442_PA_MDMA		0xE8000000
-#define S5P6442_PA_PDMA		0xE9000000
-
-#define S5P6442_PA_TIMER	0xEA000000
-
-#define S5P6442_PA_SYSTIMER	0xEA100000
-
-#define S5P6442_PA_WATCHDOG	0xEA200000
-
-#define S5P6442_PA_UART		0xEC000000
-
-#define S5P6442_PA_IIC0		0xEC100000
-
-#define S5P6442_PA_SPI		0xEC300000
-
-#define S5P6442_PA_PCM0		0xF2400000
-#define S5P6442_PA_PCM1		0xF2500000
-
-/* Compatibiltiy Defines */
-
-#define S3C_PA_IIC		S5P6442_PA_IIC0
-#define S3C_PA_WDT		S5P6442_PA_WATCHDOG
-
-#define S5P_PA_CHIPID		S5P6442_PA_CHIPID
-#define S5P_PA_SDRAM		S5P6442_PA_SDRAM
-#define S5P_PA_SROMC		S5P6442_PA_SROMC
-#define S5P_PA_SYSCON		S5P6442_PA_SYSCON
-#define S5P_PA_TIMER		S5P6442_PA_TIMER
-
-/* UART */
-
-#define S3C_PA_UART		S5P6442_PA_UART
-
-#define S5P_PA_UART(x)		(S3C_PA_UART + ((x) * S3C_UART_OFFSET))
-#define S5P_PA_UART0		S5P_PA_UART(0)
-#define S5P_PA_UART1		S5P_PA_UART(1)
-#define S5P_PA_UART2		S5P_PA_UART(2)
-
-#define S5P_SZ_UART		SZ_256
-
-#endif /* __ASM_ARCH_MAP_H */
diff --git a/arch/arm/mach-s5p6442/include/mach/memory.h b/arch/arm/mach-s5p6442/include/mach/memory.h
deleted file mode 100644
index cfe259dded33..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/memory.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/memory.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6442 - Memory definitions
- *
- * 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_MEMORY_H
-#define __ASM_ARCH_MEMORY_H
-
-#define PLAT_PHYS_OFFSET		UL(0x20000000)
-#define CONSISTENT_DMA_SIZE	SZ_8M
-
-#endif /* __ASM_ARCH_MEMORY_H */
diff --git a/arch/arm/mach-s5p6442/include/mach/pwm-clock.h b/arch/arm/mach-s5p6442/include/mach/pwm-clock.h
deleted file mode 100644
index 2724b37def31..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/pwm-clock.h
+++ /dev/null
@@ -1,70 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/pwm-clock.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *      Ben Dooks <ben@simtec.co.uk>
- *      http://armlinux.simtec.co.uk/
- *
- * Based on arch/arm/mach-s3c64xx/include/mach/pwm-clock.h
- *
- * S5P6442 - pwm clock and timer support
- *
- * 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_PWMCLK_H
-#define __ASM_ARCH_PWMCLK_H __FILE__
-
-/**
- * pwm_cfg_src_is_tclk() - return whether the given mux config is a tclk
- * @tcfg: The timer TCFG1 register bits shifted down to 0.
- *
- * Return true if the given configuration from TCFG1 is a TCLK instead
- * any of the TDIV clocks.
- */
-static inline int pwm_cfg_src_is_tclk(unsigned long tcfg)
-{
-	return tcfg == S3C64XX_TCFG1_MUX_TCLK;
-}
-
-/**
- * tcfg_to_divisor() - convert tcfg1 setting to a divisor
- * @tcfg1: The tcfg1 setting, shifted down.
- *
- * Get the divisor value for the given tcfg1 setting. We assume the
- * caller has already checked to see if this is not a TCLK source.
- */
-static inline unsigned long tcfg_to_divisor(unsigned long tcfg1)
-{
-	return 1 << tcfg1;
-}
-
-/**
- * pwm_tdiv_has_div1() - does the tdiv setting have a /1
- *
- * Return true if we have a /1 in the tdiv setting.
- */
-static inline unsigned int pwm_tdiv_has_div1(void)
-{
-	return 1;
-}
-
-/**
- * pwm_tdiv_div_bits() - calculate TCFG1 divisor value.
- * @div: The divisor to calculate the bit information for.
- *
- * Turn a divisor into the necessary bit field for TCFG1.
- */
-static inline unsigned long pwm_tdiv_div_bits(unsigned int div)
-{
-	return ilog2(div);
-}
-
-#define S3C_TCFG1_MUX_TCLK S3C64XX_TCFG1_MUX_TCLK
-
-#endif /* __ASM_ARCH_PWMCLK_H */
diff --git a/arch/arm/mach-s5p6442/include/mach/regs-clock.h b/arch/arm/mach-s5p6442/include/mach/regs-clock.h
deleted file mode 100644
index 00828a336991..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/regs-clock.h
+++ /dev/null
@@ -1,104 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/regs-clock.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6442 - Clock register definitions
- *
- * 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_REGS_CLOCK_H
-#define __ASM_ARCH_REGS_CLOCK_H __FILE__
-
-#include <mach/map.h>
-
-#define S5P_CLKREG(x)		(S3C_VA_SYS + (x))
-
-#define S5P_APLL_LOCK		S5P_CLKREG(0x00)
-#define S5P_MPLL_LOCK		S5P_CLKREG(0x08)
-#define S5P_EPLL_LOCK		S5P_CLKREG(0x10)
-#define S5P_VPLL_LOCK		S5P_CLKREG(0x20)
-
-#define S5P_APLL_CON		S5P_CLKREG(0x100)
-#define S5P_MPLL_CON		S5P_CLKREG(0x108)
-#define S5P_EPLL_CON		S5P_CLKREG(0x110)
-#define S5P_VPLL_CON		S5P_CLKREG(0x120)
-
-#define S5P_CLK_SRC0		S5P_CLKREG(0x200)
-#define S5P_CLK_SRC1		S5P_CLKREG(0x204)
-#define S5P_CLK_SRC2		S5P_CLKREG(0x208)
-#define S5P_CLK_SRC3		S5P_CLKREG(0x20C)
-#define S5P_CLK_SRC4		S5P_CLKREG(0x210)
-#define S5P_CLK_SRC5		S5P_CLKREG(0x214)
-#define S5P_CLK_SRC6		S5P_CLKREG(0x218)
-
-#define S5P_CLK_SRC_MASK0	S5P_CLKREG(0x280)
-#define S5P_CLK_SRC_MASK1	S5P_CLKREG(0x284)
-
-#define S5P_CLK_DIV0		S5P_CLKREG(0x300)
-#define S5P_CLK_DIV1		S5P_CLKREG(0x304)
-#define S5P_CLK_DIV2		S5P_CLKREG(0x308)
-#define S5P_CLK_DIV3		S5P_CLKREG(0x30C)
-#define S5P_CLK_DIV4		S5P_CLKREG(0x310)
-#define S5P_CLK_DIV5		S5P_CLKREG(0x314)
-#define S5P_CLK_DIV6		S5P_CLKREG(0x318)
-
-#define S5P_CLKGATE_IP0		S5P_CLKREG(0x460)
-#define S5P_CLKGATE_IP3		S5P_CLKREG(0x46C)
-
-/* CLK_OUT */
-#define S5P_CLK_OUT_SHIFT	(12)
-#define S5P_CLK_OUT_MASK	(0x1F << S5P_CLK_OUT_SHIFT)
-#define S5P_CLK_OUT		S5P_CLKREG(0x500)
-
-#define S5P_CLK_DIV_STAT0	S5P_CLKREG(0x1000)
-#define S5P_CLK_DIV_STAT1	S5P_CLKREG(0x1004)
-
-#define S5P_CLK_MUX_STAT0	S5P_CLKREG(0x1100)
-#define S5P_CLK_MUX_STAT1	S5P_CLKREG(0x1104)
-
-#define S5P_MDNIE_SEL		S5P_CLKREG(0x7008)
-
-/* Register Bit definition */
-#define S5P_EPLL_EN     		(1<<31)
-#define S5P_EPLL_MASK   		0xffffffff
-#define S5P_EPLLVAL(_m, _p, _s)   	((_m) << 16 | ((_p) << 8) | ((_s)))
-
-/* CLKDIV0 */
-#define S5P_CLKDIV0_APLL_SHIFT		(0)
-#define S5P_CLKDIV0_APLL_MASK		(0x7 << S5P_CLKDIV0_APLL_SHIFT)
-#define S5P_CLKDIV0_A2M_SHIFT		(4)
-#define S5P_CLKDIV0_A2M_MASK		(0x7 << S5P_CLKDIV0_A2M_SHIFT)
-#define S5P_CLKDIV0_D0CLK_SHIFT		(16)
-#define S5P_CLKDIV0_D0CLK_MASK		(0xF << S5P_CLKDIV0_D0CLK_SHIFT)
-#define S5P_CLKDIV0_P0CLK_SHIFT		(20)
-#define S5P_CLKDIV0_P0CLK_MASK		(0x7 << S5P_CLKDIV0_P0CLK_SHIFT)
-#define S5P_CLKDIV0_D1CLK_SHIFT		(24)
-#define S5P_CLKDIV0_D1CLK_MASK		(0xF << S5P_CLKDIV0_D1CLK_SHIFT)
-#define S5P_CLKDIV0_P1CLK_SHIFT		(28)
-#define S5P_CLKDIV0_P1CLK_MASK		(0x7 << S5P_CLKDIV0_P1CLK_SHIFT)
-
-/* Clock MUX status Registers */
-#define S5P_CLK_MUX_STAT0_APLL_SHIFT	(0)
-#define S5P_CLK_MUX_STAT0_APLL_MASK	(0x7 << S5P_CLK_MUX_STAT0_APLL_SHIFT)
-#define S5P_CLK_MUX_STAT0_MPLL_SHIFT	(4)
-#define S5P_CLK_MUX_STAT0_MPLL_MASK	(0x7 << S5P_CLK_MUX_STAT0_MPLL_SHIFT)
-#define S5P_CLK_MUX_STAT0_EPLL_SHIFT	(8)
-#define S5P_CLK_MUX_STAT0_EPLL_MASK	(0x7 << S5P_CLK_MUX_STAT0_EPLL_SHIFT)
-#define S5P_CLK_MUX_STAT0_VPLL_SHIFT	(12)
-#define S5P_CLK_MUX_STAT0_VPLL_MASK	(0x7 << S5P_CLK_MUX_STAT0_VPLL_SHIFT)
-#define S5P_CLK_MUX_STAT0_MUXARM_SHIFT	(16)
-#define S5P_CLK_MUX_STAT0_MUXARM_MASK	(0x7 << S5P_CLK_MUX_STAT0_MUXARM_SHIFT)
-#define S5P_CLK_MUX_STAT0_MUXD0_SHIFT	(20)
-#define S5P_CLK_MUX_STAT0_MUXD0_MASK	(0x7 << S5P_CLK_MUX_STAT0_MUXD0_SHIFT)
-#define S5P_CLK_MUX_STAT0_MUXD1_SHIFT	(24)
-#define S5P_CLK_MUX_STAT0_MUXD1_MASK	(0x7 << S5P_CLK_MUX_STAT0_MUXD1_SHIFT)
-#define S5P_CLK_MUX_STAT1_D1SYNC_SHIFT	(24)
-#define S5P_CLK_MUX_STAT1_D1SYNC_MASK	(0x7 << S5P_CLK_MUX_STAT1_D1SYNC_SHIFT)
-#define S5P_CLK_MUX_STAT1_D0SYNC_SHIFT	(28)
-#define S5P_CLK_MUX_STAT1_D0SYNC_MASK	(0x7 << S5P_CLK_MUX_STAT1_D0SYNC_SHIFT)
-
-#endif /* __ASM_ARCH_REGS_CLOCK_H */
diff --git a/arch/arm/mach-s5p6442/include/mach/regs-irq.h b/arch/arm/mach-s5p6442/include/mach/regs-irq.h
deleted file mode 100644
index 73782b52a83b..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/regs-irq.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/regs-irq.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6442 - IRQ register definitions
- *
- * 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_REGS_IRQ_H
-#define __ASM_ARCH_REGS_IRQ_H __FILE__
-
-#include <asm/hardware/vic.h>
-#include <mach/map.h>
-
-#endif /* __ASM_ARCH_REGS_IRQ_H */
diff --git a/arch/arm/mach-s5p6442/include/mach/spi-clocks.h b/arch/arm/mach-s5p6442/include/mach/spi-clocks.h
deleted file mode 100644
index 7fd88205a97c..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/spi-clocks.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/spi-clocks.h
- *
- * Copyright (C) 2010 Samsung Electronics Co. Ltd.
- *	Jaswinder Singh <jassi.brar@samsung.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.
- */
-
-#ifndef __S5P6442_PLAT_SPI_CLKS_H
-#define __S5P6442_PLAT_SPI_CLKS_H __FILE__
-
-#define S5P6442_SPI_SRCCLK_PCLK		0
-#define S5P6442_SPI_SRCCLK_SCLK		1
-
-#endif /* __S5P6442_PLAT_SPI_CLKS_H */
diff --git a/arch/arm/mach-s5p6442/include/mach/system.h b/arch/arm/mach-s5p6442/include/mach/system.h
deleted file mode 100644
index c30c1cc1b97e..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/system.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/system.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6442 - system support header
- *
- * 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_SYSTEM_H
-#define __ASM_ARCH_SYSTEM_H __FILE__
-
-#include <plat/system-reset.h>
-
-static void arch_idle(void)
-{
-	/* nothing here yet */
-}
-
-#endif /* __ASM_ARCH_SYSTEM_H */
diff --git a/arch/arm/mach-s5p6442/include/mach/tick.h b/arch/arm/mach-s5p6442/include/mach/tick.h
deleted file mode 100644
index e1d4cabf8297..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/tick.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/tick.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * Based on arch/arm/mach-s3c6400/include/mach/tick.h
- *
- * S5P6442 - Timer tick support definitions
- *
- * 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_TICK_H
-#define __ASM_ARCH_TICK_H __FILE__
-
-static inline u32 s3c24xx_ostimer_pending(void)
-{
-	u32 pend = __raw_readl(VA_VIC0 + VIC_RAW_STATUS);
-	return pend & (1 << (IRQ_TIMER4_VIC - S5P_IRQ_VIC0(0)));
-}
-
-#define TICK_MAX	(0xffffffff)
-
-#endif /* __ASM_ARCH_TICK_H */
diff --git a/arch/arm/mach-s5p6442/include/mach/timex.h b/arch/arm/mach-s5p6442/include/mach/timex.h
deleted file mode 100644
index ff8f2fcadeb7..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/timex.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* arch/arm/mach-s5p6442/include/mach/timex.h
- *
- * Copyright (c) 2003-2010 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S5P6442 - time parameters
- *
- * 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_TIMEX_H
-#define __ASM_ARCH_TIMEX_H
-
-/* CLOCK_TICK_RATE needs to be evaluatable by the cpp, so making it
- * a variable is useless. It seems as long as we make our timers an
- * exact multiple of HZ, any value that makes a 1->1 correspondence
- * for the time conversion functions to/from jiffies is acceptable.
-*/
-
-#define CLOCK_TICK_RATE 12000000
-
-#endif /* __ASM_ARCH_TIMEX_H */
diff --git a/arch/arm/mach-s5p6442/include/mach/uncompress.h b/arch/arm/mach-s5p6442/include/mach/uncompress.h
deleted file mode 100644
index 5ac7cbeeb987..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/uncompress.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/include/mach/uncompress.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6442 - uncompress code
- *
- * 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_UNCOMPRESS_H
-#define __ASM_ARCH_UNCOMPRESS_H
-
-#include <mach/map.h>
-#include <plat/uncompress.h>
-
-static void arch_detect_cpu(void)
-{
-	/* we do not need to do any cpu detection here at the moment. */
-}
-
-#endif /* __ASM_ARCH_UNCOMPRESS_H */
diff --git a/arch/arm/mach-s5p6442/include/mach/vmalloc.h b/arch/arm/mach-s5p6442/include/mach/vmalloc.h
deleted file mode 100644
index 4aa55e55ac47..000000000000
--- a/arch/arm/mach-s5p6442/include/mach/vmalloc.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* arch/arm/mach-s5p6442/include/mach/vmalloc.h
- *
- * Copyright 2010 Ben Dooks <ben-linux@fluff.org>
- *
- * 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.
- *
- * S5P6442 vmalloc definition
-*/
-
-#ifndef __ASM_ARCH_VMALLOC_H
-#define __ASM_ARCH_VMALLOC_H
-
-#define VMALLOC_END	0xF6000000UL
-
-#endif /* __ASM_ARCH_VMALLOC_H */
diff --git a/arch/arm/mach-s5p6442/init.c b/arch/arm/mach-s5p6442/init.c
deleted file mode 100644
index 1874bdb71e1d..000000000000
--- a/arch/arm/mach-s5p6442/init.c
+++ /dev/null
@@ -1,44 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/s5p6442-init.c
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.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/types.h>
-#include <linux/init.h>
-#include <linux/serial_core.h>
-
-#include <plat/cpu.h>
-#include <plat/devs.h>
-#include <plat/s5p6442.h>
-#include <plat/regs-serial.h>
-
-static struct s3c24xx_uart_clksrc s5p6442_serial_clocks[] = {
-	[0] = {
-		.name		= "pclk",
-		.divisor	= 1,
-		.min_baud	= 0,
-		.max_baud	= 0,
-	},
-};
-
-/* uart registration process */
-void __init s5p6442_common_init_uarts(struct s3c2410_uartcfg *cfg, int no)
-{
-	struct s3c2410_uartcfg *tcfg = cfg;
-	u32 ucnt;
-
-	for (ucnt = 0; ucnt < no; ucnt++, tcfg++) {
-		if (!tcfg->clocks) {
-			tcfg->clocks = s5p6442_serial_clocks;
-			tcfg->clocks_size = ARRAY_SIZE(s5p6442_serial_clocks);
-		}
-	}
-
-	s3c24xx_init_uartdevs("s5pv210-uart", s5p_uart_resources, cfg, no);
-}
diff --git a/arch/arm/mach-s5p6442/mach-smdk6442.c b/arch/arm/mach-s5p6442/mach-smdk6442.c
deleted file mode 100644
index eaf6b9c489ff..000000000000
--- a/arch/arm/mach-s5p6442/mach-smdk6442.c
+++ /dev/null
@@ -1,102 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/mach-smdk6442.c
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.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/types.h>
-#include <linux/init.h>
-#include <linux/serial_core.h>
-#include <linux/i2c.h>
-
-#include <asm/mach/arch.h>
-#include <asm/mach/map.h>
-#include <asm/setup.h>
-#include <asm/mach-types.h>
-
-#include <mach/map.h>
-#include <mach/regs-clock.h>
-
-#include <plat/regs-serial.h>
-#include <plat/s5p6442.h>
-#include <plat/devs.h>
-#include <plat/cpu.h>
-#include <plat/iic.h>
-
-/* Following are default values for UCON, ULCON and UFCON UART registers */
-#define SMDK6442_UCON_DEFAULT	(S3C2410_UCON_TXILEVEL |	\
-				 S3C2410_UCON_RXILEVEL |	\
-				 S3C2410_UCON_TXIRQMODE |	\
-				 S3C2410_UCON_RXIRQMODE |	\
-				 S3C2410_UCON_RXFIFO_TOI |	\
-				 S3C2443_UCON_RXERR_IRQEN)
-
-#define SMDK6442_ULCON_DEFAULT	S3C2410_LCON_CS8
-
-#define SMDK6442_UFCON_DEFAULT	(S3C2410_UFCON_FIFOMODE |	\
-				 S5PV210_UFCON_TXTRIG4 |	\
-				 S5PV210_UFCON_RXTRIG4)
-
-static struct s3c2410_uartcfg smdk6442_uartcfgs[] __initdata = {
-	[0] = {
-		.hwport		= 0,
-		.flags		= 0,
-		.ucon		= SMDK6442_UCON_DEFAULT,
-		.ulcon		= SMDK6442_ULCON_DEFAULT,
-		.ufcon		= SMDK6442_UFCON_DEFAULT,
-	},
-	[1] = {
-		.hwport		= 1,
-		.flags		= 0,
-		.ucon		= SMDK6442_UCON_DEFAULT,
-		.ulcon		= SMDK6442_ULCON_DEFAULT,
-		.ufcon		= SMDK6442_UFCON_DEFAULT,
-	},
-	[2] = {
-		.hwport		= 2,
-		.flags		= 0,
-		.ucon		= SMDK6442_UCON_DEFAULT,
-		.ulcon		= SMDK6442_ULCON_DEFAULT,
-		.ufcon		= SMDK6442_UFCON_DEFAULT,
-	},
-};
-
-static struct platform_device *smdk6442_devices[] __initdata = {
-	&s3c_device_i2c0,
-	&samsung_asoc_dma,
-	&s5p6442_device_iis0,
-	&s3c_device_wdt,
-};
-
-static struct i2c_board_info smdk6442_i2c_devs0[] __initdata = {
-	{ I2C_BOARD_INFO("wm8580", 0x1b), },
-};
-
-static void __init smdk6442_map_io(void)
-{
-	s5p_init_io(NULL, 0, S5P_VA_CHIPID);
-	s3c24xx_init_clocks(12000000);
-	s3c24xx_init_uarts(smdk6442_uartcfgs, ARRAY_SIZE(smdk6442_uartcfgs));
-}
-
-static void __init smdk6442_machine_init(void)
-{
-	s3c_i2c0_set_platdata(NULL);
-	i2c_register_board_info(0, smdk6442_i2c_devs0,
-			ARRAY_SIZE(smdk6442_i2c_devs0));
-	platform_add_devices(smdk6442_devices, ARRAY_SIZE(smdk6442_devices));
-}
-
-MACHINE_START(SMDK6442, "SMDK6442")
-	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
-	.boot_params	= S5P_PA_SDRAM + 0x100,
-	.init_irq	= s5p6442_init_irq,
-	.map_io		= smdk6442_map_io,
-	.init_machine	= smdk6442_machine_init,
-	.timer		= &s3c24xx_timer,
-MACHINE_END
diff --git a/arch/arm/mach-s5p6442/setup-i2c0.c b/arch/arm/mach-s5p6442/setup-i2c0.c
deleted file mode 100644
index aad85656b0cc..000000000000
--- a/arch/arm/mach-s5p6442/setup-i2c0.c
+++ /dev/null
@@ -1,28 +0,0 @@
-/* linux/arch/arm/mach-s5p6442/setup-i2c0.c
- *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * I2C0 GPIO configuration.
- *
- * Based on plat-s3c64xx/setup-i2c0.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/kernel.h>
-#include <linux/types.h>
-#include <linux/gpio.h>
-
-struct platform_device; /* don't need the contents */
-
-#include <plat/gpio-cfg.h>
-#include <plat/iic.h>
-
-void s3c_i2c0_cfg_gpio(struct platform_device *dev)
-{
-	s3c_gpio_cfgall_range(S5P6442_GPD1(0), 2,
-			      S3C_GPIO_SFN(2), S3C_GPIO_PULL_UP);
-}
diff --git a/arch/arm/mach-s5pc100/Makefile b/arch/arm/mach-s5pc100/Makefile
index eecab57d2e5d..a5e6e608b498 100644
--- a/arch/arm/mach-s5pc100/Makefile
+++ b/arch/arm/mach-s5pc100/Makefile
@@ -11,7 +11,7 @@ obj-				:=
 
 # Core support for S5PC100 system
 
-obj-$(CONFIG_CPU_S5PC100)	+= cpu.o init.o clock.o gpiolib.o
+obj-$(CONFIG_CPU_S5PC100)	+= cpu.o init.o clock.o
 obj-$(CONFIG_CPU_S5PC100)	+= setup-i2c0.o
 obj-$(CONFIG_CPU_S5PC100)	+= dma.o
 
diff --git a/arch/arm/mach-s5pv210/Makefile b/arch/arm/mach-s5pv210/Makefile
index 11f17907b4e8..50907aca006c 100644
--- a/arch/arm/mach-s5pv210/Makefile
+++ b/arch/arm/mach-s5pv210/Makefile
@@ -12,7 +12,7 @@ obj-				:=
 
 # Core support for S5PV210 system
 
-obj-$(CONFIG_CPU_S5PV210)	+= cpu.o init.o clock.o dma.o gpiolib.o
+obj-$(CONFIG_CPU_S5PV210)	+= cpu.o init.o clock.o dma.o
 obj-$(CONFIG_CPU_S5PV210)	+= setup-i2c0.o
 obj-$(CONFIG_S5PV210_PM)	+= pm.o sleep.o
 obj-$(CONFIG_CPU_FREQ)		+= cpufreq.o
diff --git a/arch/arm/mach-s5pv210/cpufreq.c b/arch/arm/mach-s5pv210/cpufreq.c
index 22046e2f53c2..153af8b359ec 100644
--- a/arch/arm/mach-s5pv210/cpufreq.c
+++ b/arch/arm/mach-s5pv210/cpufreq.c
@@ -101,12 +101,14 @@ static void s5pv210_set_refresh(enum s5pv210_dmc_port ch, unsigned long freq)
 	unsigned long tmp, tmp1;
 	void __iomem *reg = NULL;
 
-	if (ch == DMC0)
+	if (ch == DMC0) {
 		reg = (S5P_VA_DMC0 + 0x30);
-	else if (ch == DMC1)
+	} else if (ch == DMC1) {
 		reg = (S5P_VA_DMC1 + 0x30);
-	else
+	} else {
 		printk(KERN_ERR "Cannot find DMC port\n");
+		return;
+	}
 
 	/* Find current DRAM frequency */
 	tmp = s5pv210_dram_conf[ch].freq;
diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c
index c95258c274c1..1e2aba23e0d6 100644
--- a/arch/arm/mach-shmobile/board-ag5evm.c
+++ b/arch/arm/mach-shmobile/board-ag5evm.c
@@ -382,10 +382,8 @@ void ag5evm_sdhi1_set_pwr(struct platform_device *pdev, int state)
 }
 
 static struct sh_mobile_sdhi_info sh_sdhi1_platdata = {
-	.dma_slave_tx	= SHDMA_SLAVE_SDHI1_TX,
-	.dma_slave_rx	= SHDMA_SLAVE_SDHI1_RX,
 	.tmio_flags	= TMIO_MMC_WRPROTECT_DISABLE,
-	.tmio_caps	= MMC_CAP_NONREMOVABLE,
+	.tmio_caps	= MMC_CAP_NONREMOVABLE | MMC_CAP_SDIO_IRQ,
 	.tmio_ocr_mask	= MMC_VDD_32_33 | MMC_VDD_33_34,
 	.set_pwr	= ag5evm_sdhi1_set_pwr,
 };
diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c
index 08acb6ec8139..f6b687f61c28 100644
--- a/arch/arm/mach-shmobile/board-ap4evb.c
+++ b/arch/arm/mach-shmobile/board-ap4evb.c
@@ -249,6 +249,29 @@ static int slot_cn7_get_cd(struct platform_device *pdev)
 {
 	return !gpio_get_value(GPIO_PORT41);
 }
+/* MERAM */
+static struct sh_mobile_meram_info meram_info = {
+	.addr_mode      = SH_MOBILE_MERAM_MODE1,
+};
+
+static struct resource meram_resources[] = {
+	[0] = {
+		.name   = "MERAM",
+		.start  = 0xe8000000,
+		.end    = 0xe81fffff,
+		.flags  = IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device meram_device = {
+	.name           = "sh_mobile_meram",
+	.id             = 0,
+	.num_resources  = ARRAY_SIZE(meram_resources),
+	.resource       = meram_resources,
+	.dev            = {
+		.platform_data = &meram_info,
+	},
+};
 
 /* SH_MMCIF */
 static struct resource sh_mmcif_resources[] = {
@@ -447,13 +470,29 @@ const static struct fb_videomode ap4evb_lcdc_modes[] = {
 #endif
 	},
 };
+static struct sh_mobile_meram_cfg lcd_meram_cfg = {
+	.icb[0] = {
+		.marker_icb     = 28,
+		.cache_icb      = 24,
+		.meram_offset   = 0x0,
+		.meram_size     = 0x40,
+	},
+	.icb[1] = {
+		.marker_icb     = 29,
+		.cache_icb      = 25,
+		.meram_offset   = 0x40,
+		.meram_size     = 0x40,
+	},
+};
 
 static struct sh_mobile_lcdc_info lcdc_info = {
+	.meram_dev = &meram_info,
 	.ch[0] = {
 		.chan = LCDC_CHAN_MAINLCD,
 		.bpp = 16,
 		.lcd_cfg = ap4evb_lcdc_modes,
 		.num_cfg = ARRAY_SIZE(ap4evb_lcdc_modes),
+		.meram_cfg = &lcd_meram_cfg,
 	}
 };
 
@@ -724,15 +763,31 @@ static struct platform_device fsi_device = {
 static struct platform_device fsi_ak4643_device = {
 	.name		= "sh_fsi2_a_ak4643",
 };
+static struct sh_mobile_meram_cfg hdmi_meram_cfg = {
+	.icb[0] = {
+		.marker_icb     = 30,
+		.cache_icb      = 26,
+		.meram_offset   = 0x80,
+		.meram_size     = 0x100,
+	},
+	.icb[1] = {
+		.marker_icb     = 31,
+		.cache_icb      = 27,
+		.meram_offset   = 0x180,
+		.meram_size     = 0x100,
+	},
+};
 
 static struct sh_mobile_lcdc_info sh_mobile_lcdc1_info = {
 	.clock_source = LCDC_CLK_EXTERNAL,
+	.meram_dev = &meram_info,
 	.ch[0] = {
 		.chan = LCDC_CHAN_MAINLCD,
 		.bpp = 16,
 		.interface_type = RGB24,
 		.clock_divider = 1,
 		.flags = LCDC_FLAGS_DWPOL,
+		.meram_cfg = &hdmi_meram_cfg,
 	}
 };
 
@@ -961,6 +1016,7 @@ static struct platform_device *ap4evb_devices[] __initdata = {
 	&csi2_device,
 	&ceu_device,
 	&ap4evb_camera,
+	&meram_device,
 };
 
 static void __init hdmi_init_pm_clock(void)
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index 448ddbe43335..7e1d37584321 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -39,6 +39,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
+#include <linux/pm_runtime.h>
 #include <linux/smsc911x.h>
 #include <linux/sh_intc.h>
 #include <linux/tca6416_keypad.h>
@@ -125,7 +126,7 @@
  * ------+--------------------+--------------------+-------
  * IRQ0  | ICR1A.IRQ0SA=0010  | SDHI2 card detect  | Low
  * IRQ6  | ICR1A.IRQ6SA=0011  | Ether(LAN9220)     | High
- * IRQ7  | ICR1A.IRQ7SA=0010  | LCD Tuch Panel     | Low
+ * IRQ7  | ICR1A.IRQ7SA=0010  | LCD Touch Panel    | Low
  * IRQ8  | ICR2A.IRQ8SA=0010  | MMC/SD card detect | Low
  * IRQ9  | ICR2A.IRQ9SA=0010  | KEY(TCA6408)       | Low
  * IRQ21 | ICR4A.IRQ21SA=0011 | Sensor(ADXL345)    | High
@@ -164,10 +165,10 @@
  * USB1 can become Host by r8a66597, and become Function by renesas_usbhs.
  * But don't select both drivers in same time.
  * These uses same IRQ number for request_irq(), and aren't supporting
- * IRQF_SHARD / IORESOURCE_IRQ_SHAREABLE.
+ * IRQF_SHARED / IORESOURCE_IRQ_SHAREABLE.
  *
  * Actually these are old/new version of USB driver.
- * This mean its register will be broken if it supports SHARD IRQ,
+ * This mean its register will be broken if it supports shared IRQ,
  */
 
 /*
@@ -314,6 +315,30 @@ static struct platform_device smc911x_device = {
 	},
 };
 
+/* MERAM */
+static struct sh_mobile_meram_info mackerel_meram_info = {
+	.addr_mode	= SH_MOBILE_MERAM_MODE1,
+};
+
+static struct resource meram_resources[] = {
+	[0] = {
+		.name	= "MERAM",
+		.start	= 0xe8000000,
+		.end	= 0xe81fffff,
+		.flags	= IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device meram_device = {
+	.name		= "sh_mobile_meram",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(meram_resources),
+	.resource	= meram_resources,
+	.dev		= {
+		.platform_data = &mackerel_meram_info,
+	},
+};
+
 /* LCDC */
 static struct fb_videomode mackerel_lcdc_modes[] = {
 	{
@@ -342,7 +367,23 @@ static int mackerel_get_brightness(void *board_data)
 	return gpio_get_value(GPIO_PORT31);
 }
 
+static struct sh_mobile_meram_cfg lcd_meram_cfg = {
+	.icb[0] = {
+		.marker_icb     = 28,
+		.cache_icb      = 24,
+		.meram_offset   = 0x0,
+		.meram_size     = 0x40,
+	},
+	.icb[1] = {
+		.marker_icb     = 29,
+		.cache_icb      = 25,
+		.meram_offset   = 0x40,
+		.meram_size     = 0x40,
+	},
+};
+
 static struct sh_mobile_lcdc_info lcdc_info = {
+	.meram_dev = &mackerel_meram_info,
 	.clock_source = LCDC_CLK_BUS,
 	.ch[0] = {
 		.chan = LCDC_CHAN_MAINLCD,
@@ -362,6 +403,7 @@ static struct sh_mobile_lcdc_info lcdc_info = {
 			.name = "sh_mobile_lcdc_bl",
 			.max_brightness = 1,
 		},
+		.meram_cfg = &lcd_meram_cfg,
 	}
 };
 
@@ -388,8 +430,23 @@ static struct platform_device lcdc_device = {
 	},
 };
 
+static struct sh_mobile_meram_cfg hdmi_meram_cfg = {
+	.icb[0] = {
+		.marker_icb     = 30,
+		.cache_icb      = 26,
+		.meram_offset   = 0x80,
+		.meram_size     = 0x100,
+	},
+	.icb[1] = {
+		.marker_icb     = 31,
+		.cache_icb      = 27,
+		.meram_offset   = 0x180,
+		.meram_size     = 0x100,
+	},
+};
 /* HDMI */
 static struct sh_mobile_lcdc_info hdmi_lcdc_info = {
+	.meram_dev = &mackerel_meram_info,
 	.clock_source = LCDC_CLK_EXTERNAL,
 	.ch[0] = {
 		.chan = LCDC_CHAN_MAINLCD,
@@ -397,6 +454,7 @@ static struct sh_mobile_lcdc_info hdmi_lcdc_info = {
 		.interface_type = RGB24,
 		.clock_divider = 1,
 		.flags = LCDC_FLAGS_DWPOL,
+		.meram_cfg = &hdmi_meram_cfg,
 	}
 };
 
@@ -504,7 +562,121 @@ out:
 		clk_put(hdmi_ick);
 }
 
-/* USB1 (Host) */
+/* USBHS0 is connected to CN22 which takes a USB Mini-B plug
+ *
+ * The sh7372 SoC has IRQ7 set aside for USBHS0 hotplug,
+ * but on this particular board IRQ7 is already used by
+ * the touch screen. This leaves us with software polling.
+ */
+#define USBHS0_POLL_INTERVAL (HZ * 5)
+
+struct usbhs_private {
+	unsigned int usbphyaddr;
+	unsigned int usbcrcaddr;
+	struct renesas_usbhs_platform_info info;
+	struct delayed_work work;
+	struct platform_device *pdev;
+};
+
+#define usbhs_get_priv(pdev)				\
+	container_of(renesas_usbhs_get_info(pdev),	\
+		     struct usbhs_private, info)
+
+#define usbhs_is_connected(priv)			\
+	(!((1 << 7) & __raw_readw(priv->usbcrcaddr)))
+
+static int usbhs_get_vbus(struct platform_device *pdev)
+{
+	return usbhs_is_connected(usbhs_get_priv(pdev));
+}
+
+static void usbhs_phy_reset(struct platform_device *pdev)
+{
+	struct usbhs_private *priv = usbhs_get_priv(pdev);
+
+	/* init phy */
+	__raw_writew(0x8a0a, priv->usbcrcaddr);
+}
+
+static int usbhs0_get_id(struct platform_device *pdev)
+{
+	return USBHS_GADGET;
+}
+
+static void usbhs0_work_function(struct work_struct *work)
+{
+	struct usbhs_private *priv = container_of(work, struct usbhs_private,
+						  work.work);
+
+	renesas_usbhs_call_notify_hotplug(priv->pdev);
+	schedule_delayed_work(&priv->work, USBHS0_POLL_INTERVAL);
+}
+
+static int usbhs0_hardware_init(struct platform_device *pdev)
+{
+	struct usbhs_private *priv = usbhs_get_priv(pdev);
+
+	priv->pdev = pdev;
+	INIT_DELAYED_WORK(&priv->work, usbhs0_work_function);
+	schedule_delayed_work(&priv->work, USBHS0_POLL_INTERVAL);
+	return 0;
+}
+
+static void usbhs0_hardware_exit(struct platform_device *pdev)
+{
+	struct usbhs_private *priv = usbhs_get_priv(pdev);
+
+	cancel_delayed_work_sync(&priv->work);
+}
+
+static struct usbhs_private usbhs0_private = {
+	.usbcrcaddr	= 0xe605810c,		/* USBCR2 */
+	.info = {
+		.platform_callback = {
+			.hardware_init	= usbhs0_hardware_init,
+			.hardware_exit	= usbhs0_hardware_exit,
+			.phy_reset	= usbhs_phy_reset,
+			.get_id		= usbhs0_get_id,
+			.get_vbus	= usbhs_get_vbus,
+		},
+		.driver_param = {
+			.buswait_bwait	= 4,
+		},
+	},
+};
+
+static struct resource usbhs0_resources[] = {
+	[0] = {
+		.name	= "USBHS0",
+		.start	= 0xe6890000,
+		.end	= 0xe68900e6 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= evt2irq(0x1ca0) /* USB0_USB0I0 */,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device usbhs0_device = {
+	.name	= "renesas_usbhs",
+	.id	= 0,
+	.dev = {
+		.platform_data		= &usbhs0_private.info,
+	},
+	.num_resources	= ARRAY_SIZE(usbhs0_resources),
+	.resource	= usbhs0_resources,
+};
+
+/* USBHS1 is connected to CN31 which takes a USB Mini-AB plug
+ *
+ * Use J30 to select between Host and Function. This setting
+ * can however not be detected by software. Hotplug of USBHS1
+ * is provided via IRQ8.
+ */
+#define IRQ8 evt2irq(0x0300)
+
+/* USBHS1 USB Host support via r8a66597_hcd */
 static void usb1_host_port_power(int port, int power)
 {
 	if (!power) /* only power-on is supported for now */
@@ -521,9 +693,9 @@ static struct r8a66597_platdata usb1_host_data = {
 
 static struct resource usb1_host_resources[] = {
 	[0] = {
-		.name	= "USBHS",
-		.start	= 0xE68B0000,
-		.end	= 0xE68B00E6 - 1,
+		.name	= "USBHS1",
+		.start	= 0xe68b0000,
+		.end	= 0xe68b00e6 - 1,
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
@@ -544,37 +716,14 @@ static struct platform_device usb1_host_device = {
 	.resource	= usb1_host_resources,
 };
 
-/* USB1 (Function) */
+/* USBHS1 USB Function support via renesas_usbhs */
+
 #define USB_PHY_MODE		(1 << 4)
 #define USB_PHY_INT_EN		((1 << 3) | (1 << 2))
 #define USB_PHY_ON		(1 << 1)
 #define USB_PHY_OFF		(1 << 0)
 #define USB_PHY_INT_CLR		(USB_PHY_ON | USB_PHY_OFF)
 
-struct usbhs_private {
-	unsigned int irq;
-	unsigned int usbphyaddr;
-	unsigned int usbcrcaddr;
-	struct renesas_usbhs_platform_info info;
-};
-
-#define usbhs_get_priv(pdev)				\
-	container_of(renesas_usbhs_get_info(pdev),	\
-		     struct usbhs_private, info)
-
-#define usbhs_is_connected(priv)			\
-	(!((1 << 7) & __raw_readw(priv->usbcrcaddr)))
-
-static int usbhs1_get_id(struct platform_device *pdev)
-{
-	return USBHS_GADGET;
-}
-
-static int usbhs1_get_vbus(struct platform_device *pdev)
-{
-	return usbhs_is_connected(usbhs_get_priv(pdev));
-}
-
 static irqreturn_t usbhs1_interrupt(int irq, void *data)
 {
 	struct platform_device *pdev = data;
@@ -596,12 +745,10 @@ static int usbhs1_hardware_init(struct platform_device *pdev)
 	struct usbhs_private *priv = usbhs_get_priv(pdev);
 	int ret;
 
-	irq_set_irq_type(priv->irq, IRQ_TYPE_LEVEL_HIGH);
-
 	/* clear interrupt status */
 	__raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->usbphyaddr);
 
-	ret = request_irq(priv->irq, usbhs1_interrupt, 0,
+	ret = request_irq(IRQ8, usbhs1_interrupt, IRQF_TRIGGER_HIGH,
 			  dev_name(&pdev->dev), pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "request_irq err\n");
@@ -621,15 +768,12 @@ static void usbhs1_hardware_exit(struct platform_device *pdev)
 	/* clear interrupt status */
 	__raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->usbphyaddr);
 
-	free_irq(priv->irq, pdev);
+	free_irq(IRQ8, pdev);
 }
 
-static void usbhs1_phy_reset(struct platform_device *pdev)
+static int usbhs1_get_id(struct platform_device *pdev)
 {
-	struct usbhs_private *priv = usbhs_get_priv(pdev);
-
-	/* init phy */
-	__raw_writew(0x8a0a, priv->usbcrcaddr);
+	return USBHS_GADGET;
 }
 
 static u32 usbhs1_pipe_cfg[] = {
@@ -652,16 +796,15 @@ static u32 usbhs1_pipe_cfg[] = {
 };
 
 static struct usbhs_private usbhs1_private = {
-	.irq		= evt2irq(0x0300),	/* IRQ8 */
-	.usbphyaddr	= 0xE60581E2,		/* USBPHY1INTAP */
-	.usbcrcaddr	= 0xE6058130,		/* USBCR4 */
+	.usbphyaddr	= 0xe60581e2,		/* USBPHY1INTAP */
+	.usbcrcaddr	= 0xe6058130,		/* USBCR4 */
 	.info = {
 		.platform_callback = {
 			.hardware_init	= usbhs1_hardware_init,
 			.hardware_exit	= usbhs1_hardware_exit,
-			.phy_reset	= usbhs1_phy_reset,
 			.get_id		= usbhs1_get_id,
-			.get_vbus	= usbhs1_get_vbus,
+			.phy_reset	= usbhs_phy_reset,
+			.get_vbus	= usbhs_get_vbus,
 		},
 		.driver_param = {
 			.buswait_bwait	= 4,
@@ -673,9 +816,9 @@ static struct usbhs_private usbhs1_private = {
 
 static struct resource usbhs1_resources[] = {
 	[0] = {
-		.name	= "USBHS",
-		.start	= 0xE68B0000,
-		.end	= 0xE68B00E6 - 1,
+		.name	= "USBHS1",
+		.start	= 0xe68b0000,
+		.end	= 0xe68b00e6 - 1,
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
@@ -694,7 +837,6 @@ static struct platform_device usbhs1_device = {
 	.resource	= usbhs1_resources,
 };
 
-
 /* LED */
 static struct gpio_led mackerel_leds[] = {
 	{
@@ -856,6 +998,17 @@ static int slot_cn7_get_cd(struct platform_device *pdev)
 }
 
 /* SDHI0 */
+static irqreturn_t mackerel_sdhi0_gpio_cd(int irq, void *arg)
+{
+	struct device *dev = arg;
+	struct sh_mobile_sdhi_info *info = dev->platform_data;
+	struct tmio_mmc_data *pdata = info->pdata;
+
+	tmio_mmc_cd_wakeup(pdata);
+
+	return IRQ_HANDLED;
+}
+
 static struct sh_mobile_sdhi_info sdhi0_info = {
 	.dma_slave_tx	= SHDMA_SLAVE_SDHI0_TX,
 	.dma_slave_rx	= SHDMA_SLAVE_SDHI0_RX,
@@ -1134,6 +1287,7 @@ static struct platform_device *mackerel_devices[] __initdata = {
 	&nor_flash_device,
 	&smc911x_device,
 	&lcdc_device,
+	&usbhs0_device,
 	&usb1_host_device,
 	&usbhs1_device,
 	&leds_device,
@@ -1150,6 +1304,7 @@ static struct platform_device *mackerel_devices[] __initdata = {
 	&mackerel_camera,
 	&hdmi_lcdc_device,
 	&hdmi_device,
+	&meram_device,
 };
 
 /* Keypad Initialization */
@@ -1231,6 +1386,7 @@ static void __init mackerel_map_io(void)
 
 #define GPIO_PORT9CR	0xE6051009
 #define GPIO_PORT10CR	0xE605100A
+#define GPIO_PORT167CR	0xE60520A7
 #define GPIO_PORT168CR	0xE60520A8
 #define SRCR4		0xe61580bc
 #define USCCR1		0xE6058144
@@ -1238,6 +1394,7 @@ static void __init mackerel_init(void)
 {
 	u32 srcr4;
 	struct clk *clk;
+	int ret;
 
 	sh7372_pinmux_init();
 
@@ -1283,17 +1440,17 @@ static void __init mackerel_init(void)
 	gpio_request(GPIO_PORT151, NULL); /* LCDDON */
 	gpio_direction_output(GPIO_PORT151, 1);
 
-	/* USB enable */
-	gpio_request(GPIO_FN_VBUS0_1,    NULL);
-	gpio_request(GPIO_FN_IDIN_1_18,  NULL);
-	gpio_request(GPIO_FN_PWEN_1_115, NULL);
-	gpio_request(GPIO_FN_OVCN_1_114, NULL);
-	gpio_request(GPIO_FN_EXTLP_1,    NULL);
-	gpio_request(GPIO_FN_OVCN2_1,    NULL);
-	gpio_pull_down(GPIO_PORT168CR);
+	/* USBHS0 */
+	gpio_request(GPIO_FN_VBUS0_0, NULL);
+	gpio_pull_down(GPIO_PORT168CR); /* VBUS0_0 pull down */
 
-	/* setup USB phy */
-	__raw_writew(0x8a0a, 0xE6058130);	/* USBCR4 */
+	/* USBHS1 */
+	gpio_request(GPIO_FN_VBUS0_1, NULL);
+	gpio_pull_down(GPIO_PORT167CR); /* VBUS0_1 pull down */
+	gpio_request(GPIO_FN_IDIN_1_113, NULL);
+
+	/* USB phy tweak to make the r8a66597_hcd host driver work */
+	__raw_writew(0x8a0a, 0xe6058130);       /* USBCR4 */
 
 	/* enable FSI2 port A (ak4643) */
 	gpio_request(GPIO_FN_FSIAIBT,	NULL);
@@ -1343,6 +1500,13 @@ static void __init mackerel_init(void)
 	gpio_request(GPIO_FN_SDHID0_1, NULL);
 	gpio_request(GPIO_FN_SDHID0_0, NULL);
 
+	ret = request_irq(evt2irq(0x3340), mackerel_sdhi0_gpio_cd,
+			  IRQF_TRIGGER_FALLING, "sdhi0 cd", &sdhi0_device.dev);
+	if (!ret)
+		sdhi0_info.tmio_flags |= TMIO_MMC_HAS_COLD_CD;
+	else
+		pr_err("Cannot get IRQ #%d: %d\n", evt2irq(0x3340), ret);
+
 #if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE)
 	/* enable SDHI1 */
 	gpio_request(GPIO_FN_SDHICMD1, NULL);
diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c
index d17eb66f4ac2..c0800d83971e 100644
--- a/arch/arm/mach-shmobile/clock-sh7372.c
+++ b/arch/arm/mach-shmobile/clock-sh7372.c
@@ -509,6 +509,7 @@ enum { MSTP001,
        MSTP118, MSTP117, MSTP116, MSTP113,
        MSTP106, MSTP101, MSTP100,
        MSTP223,
+       MSTP218, MSTP217, MSTP216,
        MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
        MSTP329, MSTP328, MSTP323, MSTP322, MSTP314, MSTP313, MSTP312,
        MSTP423, MSTP415, MSTP413, MSTP411, MSTP410, MSTP406, MSTP403,
@@ -534,6 +535,9 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP101] = MSTP(&div4_clks[DIV4_M1], SMSTPCR1, 1, 0), /* VPU */
 	[MSTP100] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 0, 0), /* LCDC0 */
 	[MSTP223] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR2, 23, 0), /* SPU2 */
+	[MSTP218] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 18, 0), /* DMAC1 */
+	[MSTP217] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 17, 0), /* DMAC2 */
+	[MSTP216] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 16, 0), /* DMAC3 */
 	[MSTP207] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 7, 0), /* SCIFA5 */
 	[MSTP206] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 6, 0), /* SCIFB */
 	[MSTP204] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 4, 0), /* SCIFA0 */
@@ -626,6 +630,9 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("sh_mobile_lcdc_fb.0", &mstp_clks[MSTP100]), /* LCDC0 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.6", &mstp_clks[MSTP223]), /* SPU2DSP0 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.7", &mstp_clks[MSTP223]), /* SPU2DSP1 */
+	CLKDEV_DEV_ID("sh-dma-engine.0", &mstp_clks[MSTP218]), /* DMAC1 */
+	CLKDEV_DEV_ID("sh-dma-engine.1", &mstp_clks[MSTP217]), /* DMAC2 */
+	CLKDEV_DEV_ID("sh-dma-engine.2", &mstp_clks[MSTP216]), /* DMAC3 */
 	CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP207]), /* SCIFA5 */
 	CLKDEV_DEV_ID("sh-sci.6", &mstp_clks[MSTP206]), /* SCIFB */
 	CLKDEV_DEV_ID("sh-sci.0", &mstp_clks[MSTP204]), /* SCIFA0 */
diff --git a/arch/arm/mach-shmobile/intc-sh73a0.c b/arch/arm/mach-shmobile/intc-sh73a0.c
index 5d0e1503ece6..a911a60e7719 100644
--- a/arch/arm/mach-shmobile/intc-sh73a0.c
+++ b/arch/arm/mach-shmobile/intc-sh73a0.c
@@ -250,6 +250,11 @@ static irqreturn_t sh73a0_intcs_demux(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static int sh73a0_set_wake(struct irq_data *data, unsigned int on)
+{
+	return 0; /* always allow wakeup */
+}
+
 void __init sh73a0_init_irq(void)
 {
 	void __iomem *gic_dist_base = __io(0xf0001000);
@@ -257,6 +262,7 @@ void __init sh73a0_init_irq(void)
 	void __iomem *intevtsa = ioremap_nocache(0xffd20100, PAGE_SIZE);
 
 	gic_init(0, 29, gic_dist_base, gic_cpu_base);
+	gic_arch_extn.irq_set_wake = sh73a0_set_wake;
 
 	register_intc_controller(&intcs_desc);
 
diff --git a/arch/arm/mach-shmobile/setup-sh7367.c b/arch/arm/mach-shmobile/setup-sh7367.c
index 2c10190dbb55..e546017f15de 100644
--- a/arch/arm/mach-shmobile/setup-sh7367.c
+++ b/arch/arm/mach-shmobile/setup-sh7367.c
@@ -38,7 +38,7 @@ static struct plat_sci_port scif0_platform_data = {
 	.flags		= UPF_BOOT_AUTOCONF,
 	.scscr		= SCSCR_RE | SCSCR_TE,
 	.scbrr_algo_id	= SCBRR_ALGO_4,
-	.type		= PORT_SCIF,
+	.type		= PORT_SCIFA,
 	.irqs		= { evt2irq(0xc00), evt2irq(0xc00),
 			    evt2irq(0xc00), evt2irq(0xc00) },
 };
@@ -57,7 +57,7 @@ static struct plat_sci_port scif1_platform_data = {
 	.flags		= UPF_BOOT_AUTOCONF,
 	.scscr		= SCSCR_RE | SCSCR_TE,
 	.scbrr_algo_id	= SCBRR_ALGO_4,
-	.type		= PORT_SCIF,
+	.type		= PORT_SCIFA,
 	.irqs		= { evt2irq(0xc20), evt2irq(0xc20),
 			    evt2irq(0xc20), evt2irq(0xc20) },
 };
@@ -76,7 +76,7 @@ static struct plat_sci_port scif2_platform_data = {
 	.flags		= UPF_BOOT_AUTOCONF,
 	.scscr		= SCSCR_RE | SCSCR_TE,
 	.scbrr_algo_id	= SCBRR_ALGO_4,
-	.type		= PORT_SCIF,
+	.type		= PORT_SCIFA,
 	.irqs		= { evt2irq(0xc40), evt2irq(0xc40),
 			    evt2irq(0xc40), evt2irq(0xc40) },
 };
@@ -95,7 +95,7 @@ static struct plat_sci_port scif3_platform_data = {
 	.flags		= UPF_BOOT_AUTOCONF,
 	.scscr		= SCSCR_RE | SCSCR_TE,
 	.scbrr_algo_id	= SCBRR_ALGO_4,
-	.type		= PORT_SCIF,
+	.type		= PORT_SCIFA,
 	.irqs		= { evt2irq(0xc60), evt2irq(0xc60),
 			    evt2irq(0xc60), evt2irq(0xc60) },
 };
@@ -114,7 +114,7 @@ static struct plat_sci_port scif4_platform_data = {
 	.flags		= UPF_BOOT_AUTOCONF,
 	.scscr		= SCSCR_RE | SCSCR_TE,
 	.scbrr_algo_id	= SCBRR_ALGO_4,
-	.type		= PORT_SCIF,
+	.type		= PORT_SCIFA,
 	.irqs		= { evt2irq(0xd20), evt2irq(0xd20),
 			    evt2irq(0xd20), evt2irq(0xd20) },
 };
@@ -133,7 +133,7 @@ static struct plat_sci_port scif5_platform_data = {
 	.flags		= UPF_BOOT_AUTOCONF,
 	.scscr		= SCSCR_RE | SCSCR_TE,
 	.scbrr_algo_id	= SCBRR_ALGO_4,
-	.type		= PORT_SCIF,
+	.type		= PORT_SCIFA,
 	.irqs		= { evt2irq(0xd40), evt2irq(0xd40),
 			    evt2irq(0xd40), evt2irq(0xd40) },
 };
@@ -152,7 +152,7 @@ static struct plat_sci_port scif6_platform_data = {
 	.flags		= UPF_BOOT_AUTOCONF,
 	.scscr		= SCSCR_RE | SCSCR_TE,
 	.scbrr_algo_id	= SCBRR_ALGO_4,
-	.type		= PORT_SCIF,
+	.type		= PORT_SCIFB,
 	.irqs		= { evt2irq(0xd60), evt2irq(0xd60),
 			    evt2irq(0xd60), evt2irq(0xd60) },
 };
diff --git a/arch/arm/mach-tegra/board-harmony-power.c b/arch/arm/mach-tegra/board-harmony-power.c
index c84442cabe07..5ad8b2f94f8d 100644
--- a/arch/arm/mach-tegra/board-harmony-power.c
+++ b/arch/arm/mach-tegra/board-harmony-power.c
@@ -24,6 +24,8 @@
 
 #include <mach/irqs.h>
 
+#include "board-harmony.h"
+
 #define PMC_CTRL		0x0
 #define PMC_CTRL_INTR_LOW	(1 << 17)
 
@@ -98,7 +100,7 @@ static struct tps6586x_platform_data tps_platform = {
 	.irq_base	= TEGRA_NR_IRQS,
 	.num_subdevs	= ARRAY_SIZE(tps_devs),
 	.subdevs	= tps_devs,
-	.gpio_base	= TEGRA_NR_GPIOS,
+	.gpio_base	= HARMONY_GPIO_TPS6586X(0),
 };
 
 static struct i2c_board_info __initdata harmony_regulators[] = {
diff --git a/arch/arm/mach-tegra/board-harmony.h b/arch/arm/mach-tegra/board-harmony.h
index 1e57b071f52d..d85142edaf6b 100644
--- a/arch/arm/mach-tegra/board-harmony.h
+++ b/arch/arm/mach-tegra/board-harmony.h
@@ -17,7 +17,8 @@
 #ifndef _MACH_TEGRA_BOARD_HARMONY_H
 #define _MACH_TEGRA_BOARD_HARMONY_H
 
-#define HARMONY_GPIO_WM8903(_x_)	(TEGRA_NR_GPIOS + (_x_))
+#define HARMONY_GPIO_TPS6586X(_x_)	(TEGRA_NR_GPIOS + (_x_))
+#define HARMONY_GPIO_WM8903(_x_)	(HARMONY_GPIO_TPS6586X(4) + (_x_))
 
 #define TEGRA_GPIO_SD2_CD		TEGRA_GPIO_PI5
 #define TEGRA_GPIO_SD2_WP		TEGRA_GPIO_PH1
diff --git a/arch/arm/mach-u300/Makefile b/arch/arm/mach-u300/Makefile
index fab46fe9a71f..8fd354aaf0a7 100644
--- a/arch/arm/mach-u300/Makefile
+++ b/arch/arm/mach-u300/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the linux kernel, U300 machine.
 #
 
-obj-y		:= core.o clock.o timer.o gpio.o padmux.o
+obj-y		:= core.o clock.o timer.o padmux.o
 obj-m		:=
 obj-n		:=
 obj-		:=
diff --git a/arch/arm/mach-u300/clock.h b/arch/arm/mach-u300/clock.h
index c34f3ea3017c..4f50ca8f901e 100644
--- a/arch/arm/mach-u300/clock.h
+++ b/arch/arm/mach-u300/clock.h
@@ -31,7 +31,7 @@ struct clk {
 	bool reset;
 	__u16 clk_val;
 	__s8 usecount;
-	__u32 res_reg;
+	void __iomem * res_reg;
 	__u16 res_mask;
 
 	bool hw_ctrld;
diff --git a/arch/arm/mach-u300/include/mach/u300-regs.h b/arch/arm/mach-u300/include/mach/u300-regs.h
index 8b85df4c8d8f..035fdc9dbdb0 100644
--- a/arch/arm/mach-u300/include/mach/u300-regs.h
+++ b/arch/arm/mach-u300/include/mach/u300-regs.h
@@ -18,6 +18,12 @@
  * the defines are used for setting up the I/O memory mapping.
  */
 
+#ifdef __ASSEMBLER__
+#define IOMEM(a) (a)
+#else
+#define IOMEM(a) (void __iomem *) a
+#endif
+
 /* NAND Flash CS0 */
 #define U300_NAND_CS0_PHYS_BASE		0x80000000
 
@@ -48,13 +54,6 @@
 #endif
 
 /*
- * All the following peripherals are specified at their PHYSICAL address,
- * so if you need to access them (in the kernel), you MUST use the macros
- * defined in <asm/io.h> to map to the IO_ADDRESS_AHB() IO_ADDRESS_FAST()
- * etc.
- */
-
-/*
  * AHB peripherals
  */
 
@@ -63,11 +62,11 @@
 
 /* Vectored Interrupt Controller 0, servicing 32 interrupts */
 #define U300_INTCON0_BASE		(U300_AHB_PER_PHYS_BASE+0x1000)
-#define U300_INTCON0_VBASE		(U300_AHB_PER_VIRT_BASE+0x1000)
+#define U300_INTCON0_VBASE		IOMEM(U300_AHB_PER_VIRT_BASE+0x1000)
 
 /* Vectored Interrupt Controller 1, servicing 32 interrupts */
 #define U300_INTCON1_BASE		(U300_AHB_PER_PHYS_BASE+0x2000)
-#define U300_INTCON1_VBASE		(U300_AHB_PER_VIRT_BASE+0x2000)
+#define U300_INTCON1_VBASE		IOMEM(U300_AHB_PER_VIRT_BASE+0x2000)
 
 /* Memory Stick Pro (MSPRO) controller */
 #define U300_MSPRO_BASE			(U300_AHB_PER_PHYS_BASE+0x3000)
@@ -115,7 +114,7 @@
 
 /* SYSCON */
 #define U300_SYSCON_BASE		(U300_SLOW_PER_PHYS_BASE+0x1000)
-#define U300_SYSCON_VBASE		(U300_SLOW_PER_VIRT_BASE+0x1000)
+#define U300_SYSCON_VBASE		IOMEM(U300_SLOW_PER_VIRT_BASE+0x1000)
 
 /* Watchdog */
 #define U300_WDOG_BASE			(U300_SLOW_PER_PHYS_BASE+0x2000)
@@ -125,7 +124,7 @@
 
 /* APP side special timer */
 #define U300_TIMER_APP_BASE		(U300_SLOW_PER_PHYS_BASE+0x4000)
-#define U300_TIMER_APP_VBASE		(U300_SLOW_PER_VIRT_BASE+0x4000)
+#define U300_TIMER_APP_VBASE		IOMEM(U300_SLOW_PER_VIRT_BASE+0x4000)
 
 /* Keypad */
 #define U300_KEYPAD_BASE		(U300_SLOW_PER_PHYS_BASE+0x5000)
@@ -181,5 +180,4 @@
  * Virtual accessor macros for static devices
  */
 
-
 #endif
diff --git a/arch/arm/mach-u300/timer.c b/arch/arm/mach-u300/timer.c
index 891cf44591e0..18d7fa0603c2 100644
--- a/arch/arm/mach-u300/timer.c
+++ b/arch/arm/mach-u300/timer.c
@@ -411,8 +411,7 @@ static void __init u300_timer_init(void)
 	/* Use general purpose timer 2 as clock source */
 	if (clocksource_mmio_init(U300_TIMER_APP_VBASE + U300_TIMER_APP_GPT2CC,
 			"GPT2", rate, 300, 32, clocksource_mmio_readl_up))
-		printk(KERN_ERR "timer: failed to initialize clock "
-		       "source %s\n", clocksource_u300_1mhz.name);
+		pr_err("timer: failed to initialize U300 clock source\n");
 
 	clockevents_calc_mult_shift(&clockevent_u300_1mhz,
 				    rate, APPTIMER_MIN_RANGE);
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index 54429d015954..f8b9392ee347 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -5,7 +5,6 @@ config UX500_SOC_COMMON
 	default y
 	select ARM_GIC
 	select HAS_MTU
-	select NOMADIK_GPIO
 	select ARM_ERRATA_753970
 
 menu "Ux500 SoC"
diff --git a/arch/arm/mach-ux500/board-mop500-sdi.c b/arch/arm/mach-ux500/board-mop500-sdi.c
index bf0b02414e5b..7c6cb4fa47a9 100644
--- a/arch/arm/mach-ux500/board-mop500-sdi.c
+++ b/arch/arm/mach-ux500/board-mop500-sdi.c
@@ -99,8 +99,11 @@ static void sdi0_configure(void)
 	gpio_direction_output(sdi0_vsel, 0);
 	gpio_direction_output(sdi0_en, 1);
 
-	/* Add the device */
-	db8500_add_sdi0(&mop500_sdi0_data);
+	/* Add the device, force v2 to subrevision 1 */
+	if (cpu_is_u8500v2())
+		db8500_add_sdi0(&mop500_sdi0_data, 0x10480180);
+	else
+		db8500_add_sdi0(&mop500_sdi0_data, 0);
 }
 
 void mop500_sdi_tc35892_init(void)
@@ -188,13 +191,18 @@ static struct mmci_platform_data mop500_sdi4_data = {
 
 void __init mop500_sdi_init(void)
 {
+	u32 periphid = 0;
+
+	/* v2 has a new version of this block that need to be forced */
+	if (cpu_is_u8500v2())
+		periphid = 0x10480180;
 	/* PoP:ed eMMC on top of DB8500 v1.0 has problems with high speed */
 	if (!cpu_is_u8500v10())
 		mop500_sdi2_data.capabilities |= MMC_CAP_MMC_HIGHSPEED;
-	db8500_add_sdi2(&mop500_sdi2_data);
+	db8500_add_sdi2(&mop500_sdi2_data, periphid);
 
 	/* On-board eMMC */
-	db8500_add_sdi4(&mop500_sdi4_data);
+	db8500_add_sdi4(&mop500_sdi4_data, periphid);
 
 	if (machine_is_hrefv60()) {
 		mop500_sdi0_data.gpio_cd = HREFV60_SDMMC_CD_GPIO;
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index c3c417656bd9..4598b06c8c55 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -159,6 +159,9 @@ static void __init db8500_add_gpios(void)
 		/* No custom data yet */
 	};
 
+	if (cpu_is_u8500v2())
+		pdata.supports_sleepmode = true;
+
 	dbx500_add_gpios(ARRAY_AND_SIZE(db8500_gpio_base),
 			 IRQ_DB8500_GPIO0, &pdata);
 }
diff --git a/arch/arm/mach-ux500/devices-common.h b/arch/arm/mach-ux500/devices-common.h
index c719b5a1d913..7825705033bf 100644
--- a/arch/arm/mach-ux500/devices-common.h
+++ b/arch/arm/mach-ux500/devices-common.h
@@ -28,18 +28,20 @@ dbx500_add_msp_spi(const char *name, resource_size_t base, int irq,
 
 static inline struct amba_device *
 dbx500_add_spi(const char *name, resource_size_t base, int irq,
-				   struct spi_master_cntlr *pdata)
+	       struct spi_master_cntlr *pdata,
+	       u32 periphid)
 {
-	return dbx500_add_amba_device(name, base, irq, pdata, 0);
+	return dbx500_add_amba_device(name, base, irq, pdata, periphid);
 }
 
 struct mmci_platform_data;
 
 static inline struct amba_device *
 dbx500_add_sdi(const char *name, resource_size_t base, int irq,
-	       struct mmci_platform_data *pdata)
+	       struct mmci_platform_data *pdata,
+	       u32 periphid)
 {
-	return dbx500_add_amba_device(name, base, irq, pdata, 0);
+	return dbx500_add_amba_device(name, base, irq, pdata, periphid);
 }
 
 struct amba_pl011_data;
diff --git a/arch/arm/mach-ux500/devices-db5500.h b/arch/arm/mach-ux500/devices-db5500.h
index 94627f7783b0..0c4bccd02b90 100644
--- a/arch/arm/mach-ux500/devices-db5500.h
+++ b/arch/arm/mach-ux500/devices-db5500.h
@@ -38,24 +38,34 @@
 	ux500_add_usb(U5500_USBOTG_BASE, IRQ_DB5500_USBOTG, rx_cfg, tx_cfg)
 
 #define db5500_add_sdi0(pdata) \
-	dbx500_add_sdi("sdi0", U5500_SDI0_BASE, IRQ_DB5500_SDMMC0, pdata)
+	dbx500_add_sdi("sdi0", U5500_SDI0_BASE, IRQ_DB5500_SDMMC0, pdata, \
+		       0x10480180)
 #define db5500_add_sdi1(pdata) \
-	dbx500_add_sdi("sdi1", U5500_SDI1_BASE, IRQ_DB5500_SDMMC1, pdata)
+	dbx500_add_sdi("sdi1", U5500_SDI1_BASE, IRQ_DB5500_SDMMC1, pdata, \
+		       0x10480180)
 #define db5500_add_sdi2(pdata) \
-	dbx500_add_sdi("sdi2", U5500_SDI2_BASE, IRQ_DB5500_SDMMC2, pdata)
+	dbx500_add_sdi("sdi2", U5500_SDI2_BASE, IRQ_DB5500_SDMMC2, pdata \
+		       0x10480180)
 #define db5500_add_sdi3(pdata) \
-	dbx500_add_sdi("sdi3", U5500_SDI3_BASE, IRQ_DB5500_SDMMC3, pdata)
+	dbx500_add_sdi("sdi3", U5500_SDI3_BASE, IRQ_DB5500_SDMMC3, pdata \
+		       0x10480180)
 #define db5500_add_sdi4(pdata) \
-	dbx500_add_sdi("sdi4", U5500_SDI4_BASE, IRQ_DB5500_SDMMC4, pdata)
+	dbx500_add_sdi("sdi4", U5500_SDI4_BASE, IRQ_DB5500_SDMMC4, pdata \
+		       0x10480180)
 
+/* This one has a bad peripheral ID in the U5500 silicon */
 #define db5500_add_spi0(pdata) \
-	dbx500_add_spi("spi0", U5500_SPI0_BASE, IRQ_DB5500_SPI0, pdata)
+	dbx500_add_spi("spi0", U5500_SPI0_BASE, IRQ_DB5500_SPI0, pdata, \
+		       0x10080023)
 #define db5500_add_spi1(pdata) \
-	dbx500_add_spi("spi1", U5500_SPI1_BASE, IRQ_DB5500_SPI1, pdata)
+	dbx500_add_spi("spi1", U5500_SPI1_BASE, IRQ_DB5500_SPI1, pdata, \
+		       0x10080023)
 #define db5500_add_spi2(pdata) \
-	dbx500_add_spi("spi2", U5500_SPI2_BASE, IRQ_DB5500_SPI2, pdata)
+	dbx500_add_spi("spi2", U5500_SPI2_BASE, IRQ_DB5500_SPI2, pdata \
+		       0x10080023)
 #define db5500_add_spi3(pdata) \
-	dbx500_add_spi("spi3", U5500_SPI3_BASE, IRQ_DB5500_SPI3, pdata)
+	dbx500_add_spi("spi3", U5500_SPI3_BASE, IRQ_DB5500_SPI3, pdata \
+		       0x10080023)
 
 #define db5500_add_uart0(plat) \
 	dbx500_add_uart("uart0", U5500_UART0_BASE, IRQ_DB5500_UART0, plat)
diff --git a/arch/arm/mach-ux500/devices-db8500.h b/arch/arm/mach-ux500/devices-db8500.h
index 9cc6f8f5d3e6..cbd4a9ae8109 100644
--- a/arch/arm/mach-ux500/devices-db8500.h
+++ b/arch/arm/mach-ux500/devices-db8500.h
@@ -25,7 +25,7 @@ static inline struct amba_device *
 db8500_add_ssp(const char *name, resource_size_t base, int irq,
 	       struct pl022_ssp_controller *pdata)
 {
-	return dbx500_add_amba_device(name, base, irq, pdata, SSP_PER_ID);
+	return dbx500_add_amba_device(name, base, irq, pdata, 0);
 }
 
 
@@ -64,18 +64,18 @@ db8500_add_ssp(const char *name, resource_size_t base, int irq,
 #define db8500_add_usb(rx_cfg, tx_cfg) \
 	ux500_add_usb(U8500_USBOTG_BASE, IRQ_DB8500_USBOTG, rx_cfg, tx_cfg)
 
-#define db8500_add_sdi0(pdata) \
-	dbx500_add_sdi("sdi0", U8500_SDI0_BASE, IRQ_DB8500_SDMMC0, pdata)
-#define db8500_add_sdi1(pdata) \
-	dbx500_add_sdi("sdi1", U8500_SDI1_BASE, IRQ_DB8500_SDMMC1, pdata)
-#define db8500_add_sdi2(pdata) \
-	dbx500_add_sdi("sdi2", U8500_SDI2_BASE, IRQ_DB8500_SDMMC2, pdata)
-#define db8500_add_sdi3(pdata) \
-	dbx500_add_sdi("sdi3", U8500_SDI3_BASE, IRQ_DB8500_SDMMC3, pdata)
-#define db8500_add_sdi4(pdata) \
-	dbx500_add_sdi("sdi4", U8500_SDI4_BASE, IRQ_DB8500_SDMMC4, pdata)
-#define db8500_add_sdi5(pdata) \
-	dbx500_add_sdi("sdi5", U8500_SDI5_BASE, IRQ_DB8500_SDMMC5, pdata)
+#define db8500_add_sdi0(pdata, pid) \
+	dbx500_add_sdi("sdi0", U8500_SDI0_BASE, IRQ_DB8500_SDMMC0, pdata, pid)
+#define db8500_add_sdi1(pdata, pid) \
+	dbx500_add_sdi("sdi1", U8500_SDI1_BASE, IRQ_DB8500_SDMMC1, pdata, pid)
+#define db8500_add_sdi2(pdata, pid) \
+	dbx500_add_sdi("sdi2", U8500_SDI2_BASE, IRQ_DB8500_SDMMC2, pdata, pid)
+#define db8500_add_sdi3(pdata, pid) \
+	dbx500_add_sdi("sdi3", U8500_SDI3_BASE, IRQ_DB8500_SDMMC3, pdata, pid)
+#define db8500_add_sdi4(pdata, pid) \
+	dbx500_add_sdi("sdi4", U8500_SDI4_BASE, IRQ_DB8500_SDMMC4, pdata, pid)
+#define db8500_add_sdi5(pdata, pid) \
+	dbx500_add_sdi("sdi5", U8500_SDI5_BASE, IRQ_DB8500_SDMMC5, pdata, pid)
 
 #define db8500_add_ssp0(pdata) \
 	db8500_add_ssp("ssp0", U8500_SSP0_BASE, IRQ_DB8500_SSP0, pdata)
@@ -83,13 +83,13 @@ db8500_add_ssp(const char *name, resource_size_t base, int irq,
 	db8500_add_ssp("ssp1", U8500_SSP1_BASE, IRQ_DB8500_SSP1, pdata)
 
 #define db8500_add_spi0(pdata) \
-	dbx500_add_spi("spi0", U8500_SPI0_BASE, IRQ_DB8500_SPI0, pdata)
+	dbx500_add_spi("spi0", U8500_SPI0_BASE, IRQ_DB8500_SPI0, pdata, 0)
 #define db8500_add_spi1(pdata) \
-	dbx500_add_spi("spi1", U8500_SPI1_BASE, IRQ_DB8500_SPI1, pdata)
+	dbx500_add_spi("spi1", U8500_SPI1_BASE, IRQ_DB8500_SPI1, pdata, 0)
 #define db8500_add_spi2(pdata) \
-	dbx500_add_spi("spi2", U8500_SPI2_BASE, IRQ_DB8500_SPI2, pdata)
+	dbx500_add_spi("spi2", U8500_SPI2_BASE, IRQ_DB8500_SPI2, pdata, 0)
 #define db8500_add_spi3(pdata) \
-	dbx500_add_spi("spi3", U8500_SPI3_BASE, IRQ_DB8500_SPI3, pdata)
+	dbx500_add_spi("spi3", U8500_SPI3_BASE, IRQ_DB8500_SPI3, pdata, 0)
 
 #define db8500_add_uart0(pdata) \
 	dbx500_add_uart("uart0", U8500_UART0_BASE, IRQ_DB8500_UART0, pdata)
diff --git a/arch/arm/mach-ux500/include/mach/hardware.h b/arch/arm/mach-ux500/include/mach/hardware.h
index 2c6f71049f2e..470ac52663d6 100644
--- a/arch/arm/mach-ux500/include/mach/hardware.h
+++ b/arch/arm/mach-ux500/include/mach/hardware.h
@@ -29,9 +29,6 @@
 #include <mach/db8500-regs.h>
 #include <mach/db5500-regs.h>
 
-/* ST-Ericsson modified pl022 id */
-#define SSP_PER_ID		0x01080022
-
 #ifndef __ASSEMBLY__
 
 #include <mach/id.h>
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 285edcd2da2a..9e6b93b1a043 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -46,12 +46,6 @@ static struct map_desc v2m_io_desc[] __initdata = {
 	},
 };
 
-static void __init v2m_init_early(void)
-{
-	ct_desc->init_early();
-	versatile_sched_clock_init(MMIO_P2V(V2M_SYS_24MHZ), 24000000);
-}
-
 static void __init v2m_timer_init(void)
 {
 	u32 scctrl;
@@ -365,6 +359,13 @@ static struct clk_lookup v2m_lookups[] = {
 	},
 };
 
+static void __init v2m_init_early(void)
+{
+	ct_desc->init_early();
+	clkdev_add_table(v2m_lookups, ARRAY_SIZE(v2m_lookups));
+	versatile_sched_clock_init(MMIO_P2V(V2M_SYS_24MHZ), 24000000);
+}
+
 static void v2m_power_off(void)
 {
 	if (v2m_cfg_write(SYS_CFG_SHUTDOWN | SYS_CFG_SITE_MB, 0))
@@ -418,8 +419,6 @@ static void __init v2m_init(void)
 {
 	int i;
 
-	clkdev_add_table(v2m_lookups, ARRAY_SIZE(v2m_lookups));
-
 	platform_device_register(&v2m_pcie_i2c_device);
 	platform_device_register(&v2m_ddc_i2c_device);
 	platform_device_register(&v2m_flash_device);
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index c96fa1b3f49f..73b4a8b66a57 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -176,6 +176,7 @@ ENDPROC(v6_coherent_kern_range)
  */
 ENTRY(v6_flush_kern_dcache_area)
 	add	r1, r0, r1
+	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 1:
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D line
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index dc18d81ef8ce..d32f02b61866 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -221,6 +221,8 @@ ENDPROC(v7_coherent_user_range)
 ENTRY(v7_flush_kern_dcache_area)
 	dcache_line_size r2, r3
 	add	r1, r0, r1
+	sub	r3, r2, #1
+	bic	r0, r0, r3
 1:
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D line / unified line
 	add	r0, r0, r2
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 3f17ea146f0e..c19571c40a21 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -15,12 +15,14 @@
 #include <linux/mman.h>
 #include <linux/nodemask.h>
 #include <linux/initrd.h>
+#include <linux/of_fdt.h>
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
 #include <linux/sort.h>
 
 #include <asm/mach-types.h>
+#include <asm/prom.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/sizes.h>
@@ -71,6 +73,14 @@ static int __init parse_tag_initrd2(const struct tag *tag)
 
 __tagtable(ATAG_INITRD2, parse_tag_initrd2);
 
+#ifdef CONFIG_OF_FLATTREE
+void __init early_init_dt_setup_initrd_arch(unsigned long start, unsigned long end)
+{
+	phys_initrd_start = start;
+	phys_initrd_size = end - start;
+}
+#endif /* CONFIG_OF_FLATTREE */
+
 /*
  * This keeps memory configuration data used by a couple memory
  * initialization functions, as well as show_mem() for the skipping
@@ -273,13 +283,15 @@ static void __init arm_bootmem_free(unsigned long min, unsigned long max_low,
 	free_area_init_node(0, zone_size, min, zhole_size);
 }
 
-#ifndef CONFIG_SPARSEMEM
+#ifdef CONFIG_HAVE_ARCH_PFN_VALID
 int pfn_valid(unsigned long pfn)
 {
 	return memblock_is_memory(pfn << PAGE_SHIFT);
 }
 EXPORT_SYMBOL(pfn_valid);
+#endif
 
+#ifndef CONFIG_SPARSEMEM
 static void arm_memory_present(void)
 {
 }
@@ -319,6 +331,12 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
 #endif
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (phys_initrd_size &&
+	    !memblock_is_region_memory(phys_initrd_start, phys_initrd_size)) {
+		pr_err("INITRD: 0x%08lx+0x%08lx is not a memory region - disabling initrd\n",
+		       phys_initrd_start, phys_initrd_size);
+		phys_initrd_start = phys_initrd_size = 0;
+	}
+	if (phys_initrd_size &&
 	    memblock_is_region_reserved(phys_initrd_start, phys_initrd_size)) {
 		pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region - disabling initrd\n",
 		       phys_initrd_start, phys_initrd_size);
@@ -334,6 +352,7 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
 #endif
 
 	arm_mm_memblock_reserve();
+	arm_dt_memblock_reserve();
 
 	/* reserve any platform specific memblock areas */
 	if (mdesc->reserve)
@@ -622,7 +641,8 @@ void __init mem_init(void)
 			"    modules : 0x%08lx - 0x%08lx   (%4ld MB)\n"
 			"      .init : 0x%p" " - 0x%p" "   (%4d kB)\n"
 			"      .text : 0x%p" " - 0x%p" "   (%4d kB)\n"
-			"      .data : 0x%p" " - 0x%p" "   (%4d kB)\n",
+			"      .data : 0x%p" " - 0x%p" "   (%4d kB)\n"
+			"       .bss : 0x%p" " - 0x%p" "   (%4d kB)\n",
 
 			MLK(UL(CONFIG_VECTORS_BASE), UL(CONFIG_VECTORS_BASE) +
 				(PAGE_SIZE)),
@@ -644,7 +664,8 @@ void __init mem_init(void)
 
 			MLK_ROUNDUP(__init_begin, __init_end),
 			MLK_ROUNDUP(_text, _etext),
-			MLK_ROUNDUP(_sdata, _edata));
+			MLK_ROUNDUP(_sdata, _edata),
+			MLK_ROUNDUP(__bss_start, __bss_stop));
 
 #undef MLK
 #undef MLM
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index d2384106af9c..5b3d7d543659 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -5,14 +5,9 @@ extern pmd_t *top_pmd;
 
 #define TOP_PTE(x)	pte_offset_kernel(top_pmd, x)
 
-static inline pmd_t *pmd_off(pgd_t *pgd, unsigned long virt)
-{
-	return pmd_offset(pud_offset(pgd, virt), virt);
-}
-
 static inline pmd_t *pmd_off_k(unsigned long virt)
 {
-	return pmd_off(pgd_offset_k(virt), virt);
+	return pmd_offset(pud_offset(pgd_offset_k(virt), virt), virt);
 }
 
 struct mem_type {
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 08a92368d9d3..9d9e736c2b4f 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -763,15 +763,12 @@ static void __init sanity_check_meminfo(void)
 {
 	int i, j, highmem = 0;
 
-	lowmem_limit = __pa(vmalloc_min - 1) + 1;
-	memblock_set_current_limit(lowmem_limit);
-
 	for (i = 0, j = 0; i < meminfo.nr_banks; i++) {
 		struct membank *bank = &meminfo.bank[j];
 		*bank = meminfo.bank[i];
 
 #ifdef CONFIG_HIGHMEM
-		if (__va(bank->start) > vmalloc_min ||
+		if (__va(bank->start) >= vmalloc_min ||
 		    __va(bank->start) < (void *)PAGE_OFFSET)
 			highmem = 1;
 
@@ -829,6 +826,9 @@ static void __init sanity_check_meminfo(void)
 			bank->size = newsize;
 		}
 #endif
+		if (!bank->highmem && bank->start + bank->size > lowmem_limit)
+			lowmem_limit = bank->start + bank->size;
+
 		j++;
 	}
 #ifdef CONFIG_HIGHMEM
@@ -852,6 +852,7 @@ static void __init sanity_check_meminfo(void)
 	}
 #endif
 	meminfo.nr_banks = j;
+	memblock_set_current_limit(lowmem_limit);
 }
 
 static inline void prepare_page_table(void)
diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S
index e4c165ca6696..537ffcb0646d 100644
--- a/arch/arm/mm/proc-arm7tdmi.S
+++ b/arch/arm/mm/proc-arm7tdmi.S
@@ -146,7 +146,7 @@ __arm7tdmi_proc_info:
 		.long	0
 		.long	0
 		.long	v4_cache_fns
-		.size	__arm7tdmi_proc_info, . - __arm7dmi_proc_info
+		.size	__arm7tdmi_proc_info, . - __arm7tdmi_proc_info
 
 		.type	__triscenda7_proc_info, #object
 __triscenda7_proc_info:
diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S
index 7b7ebd4d096d..546b54da1005 100644
--- a/arch/arm/mm/proc-arm9tdmi.S
+++ b/arch/arm/mm/proc-arm9tdmi.S
@@ -116,7 +116,7 @@ __arm9tdmi_proc_info:
 		.long	0
 		.long	0
 		.long	v4_cache_fns
-		.size	__arm9tdmi_proc_info, . - __arm9dmi_proc_info
+		.size	__arm9tdmi_proc_info, . - __arm9tdmi_proc_info
 
 		.type	__p2001_proc_info, #object
 __p2001_proc_info:
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index ab17cc0d3fa7..1d2b8451bf25 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -213,7 +213,9 @@ __v6_setup:
 	mcr	p15, 0, r0, c2, c0, 2		@ TTB control register
 	ALT_SMP(orr	r4, r4, #TTB_FLAGS_SMP)
 	ALT_UP(orr	r4, r4, #TTB_FLAGS_UP)
-	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
+	ALT_SMP(orr	r8, r8, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r8, r8, #TTB_FLAGS_UP)
+	mcr	p15, 0, r8, c2, c0, 1		@ load TTB1
 #endif /* CONFIG_MMU */
 	adr	r5, v6_crval
 	ldmia	r5, {r5, r6}
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index babfba09c89f..089c0b5e454f 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -210,19 +210,21 @@ cpu_v7_name:
 
 /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */
 .globl	cpu_v7_suspend_size
-.equ	cpu_v7_suspend_size, 4 * 8
+.equ	cpu_v7_suspend_size, 4 * 9
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_v7_do_suspend)
 	stmfd	sp!, {r4 - r11, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
 	mrc	p15, 0, r5, c13, c0, 1	@ Context ID
+	mrc	p15, 0, r6, c13, c0, 3	@ User r/o thread ID
+	stmia	r0!, {r4 - r6}
 	mrc	p15, 0, r6, c3, c0, 0	@ Domain ID
 	mrc	p15, 0, r7, c2, c0, 0	@ TTB 0
 	mrc	p15, 0, r8, c2, c0, 1	@ TTB 1
 	mrc	p15, 0, r9, c1, c0, 0	@ Control register
 	mrc	p15, 0, r10, c1, c0, 1	@ Auxiliary control register
 	mrc	p15, 0, r11, c1, c0, 2	@ Co-processor access control
-	stmia	r0, {r4 - r11}
+	stmia	r0, {r6 - r11}
 	ldmfd	sp!, {r4 - r11, pc}
 ENDPROC(cpu_v7_do_suspend)
 
@@ -230,9 +232,11 @@ ENTRY(cpu_v7_do_resume)
 	mov	ip, #0
 	mcr	p15, 0, ip, c8, c7, 0	@ invalidate TLBs
 	mcr	p15, 0, ip, c7, c5, 0	@ invalidate I cache
-	ldmia	r0, {r4 - r11}
+	ldmia	r0!, {r4 - r6}
 	mcr	p15, 0, r4, c13, c0, 0	@ FCSE/PID
 	mcr	p15, 0, r5, c13, c0, 1	@ Context ID
+	mcr	p15, 0, r6, c13, c0, 3	@ User r/o thread ID
+	ldmia	r0, {r6 - r11}
 	mcr	p15, 0, r6, c3, c0, 0	@ Domain ID
 	mcr	p15, 0, r7, c2, c0, 0	@ TTB 0
 	mcr	p15, 0, r8, c2, c0, 1	@ TTB 1
@@ -368,7 +372,9 @@ __v7_setup:
 	mcr	p15, 0, r10, c2, c0, 2		@ TTB control register
 	ALT_SMP(orr	r4, r4, #TTB_FLAGS_SMP)
 	ALT_UP(orr	r4, r4, #TTB_FLAGS_UP)
-	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
+	ALT_SMP(orr	r8, r8, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r8, r8, #TTB_FLAGS_UP)
+	mcr	p15, 0, r8, c2, c0, 1		@ load TTB1
 	ldr	r5, =PRRR			@ PRRR
 	ldr	r6, =NMRR			@ NMRR
 	mcr	p15, 0, r5, c10, c2, 0		@ write PRRR
@@ -416,9 +422,9 @@ ENTRY(v7_processor_functions)
 	.word	cpu_v7_dcache_clean_area
 	.word	cpu_v7_switch_mm
 	.word	cpu_v7_set_pte_ext
-	.word	0
-	.word	0
-	.word	0
+	.word	cpu_v7_suspend_size
+	.word	cpu_v7_do_suspend
+	.word	cpu_v7_do_resume
 	.size	v7_processor_functions, . - v7_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/plat-iop/cp6.c b/arch/arm/plat-iop/cp6.c
index 9612a87e2a88..bab73e2c79db 100644
--- a/arch/arm/plat-iop/cp6.c
+++ b/arch/arm/plat-iop/cp6.c
@@ -18,6 +18,7 @@
  */
 #include <linux/init.h>
 #include <asm/traps.h>
+#include <asm/ptrace.h>
 
 static int cp6_trap(struct pt_regs *regs, unsigned int instr)
 {
diff --git a/arch/arm/plat-mxc/devices/platform-imx-dma.c b/arch/arm/plat-mxc/devices/platform-imx-dma.c
index 3538b85ede91..b130f60ca6b7 100644
--- a/arch/arm/plat-mxc/devices/platform-imx-dma.c
+++ b/arch/arm/plat-mxc/devices/platform-imx-dma.c
@@ -139,7 +139,7 @@ static struct sdma_script_start_addrs addr_imx35_to2 = {
 #endif
 
 #ifdef CONFIG_SOC_IMX51
-static struct sdma_script_start_addrs addr_imx51_to1 = {
+static struct sdma_script_start_addrs addr_imx51 = {
 	.ap_2_ap_addr = 642,
 	.uart_2_mcu_addr = 817,
 	.mcu_2_app_addr = 747,
@@ -196,7 +196,9 @@ static int __init imxXX_add_imx_dma(void)
 
 #if defined(CONFIG_SOC_IMX51)
 	if (cpu_is_mx51()) {
-		imx51_imx_sdma_data.pdata.script_addrs = &addr_imx51_to1;
+		int to_version = mx51_revision() >> 4;
+		imx51_imx_sdma_data.pdata.to_version = to_version;
+		imx51_imx_sdma_data.pdata.script_addrs = &addr_imx51;
 		ret = imx_add_imx_sdma(&imx51_imx_sdma_data);
 	} else
 #endif
diff --git a/arch/arm/plat-nomadik/Kconfig b/arch/arm/plat-nomadik/Kconfig
index 18296ee68802..ce659015535e 100644
--- a/arch/arm/plat-nomadik/Kconfig
+++ b/arch/arm/plat-nomadik/Kconfig
@@ -21,9 +21,4 @@ config HAS_MTU
 	  to multiple interrupt generating programmable
 	  32-bit free running decrementing counters.
 
-config NOMADIK_GPIO
-	bool
-	help
-	  Support for the Nomadik GPIO controller.
-
 endif
diff --git a/arch/arm/plat-nomadik/Makefile b/arch/arm/plat-nomadik/Makefile
index c33547361bd7..37c7cdd0f8f0 100644
--- a/arch/arm/plat-nomadik/Makefile
+++ b/arch/arm/plat-nomadik/Makefile
@@ -3,4 +3,3 @@
 # Licensed under GPLv2
 
 obj-$(CONFIG_HAS_MTU)	+= timer.o
-obj-$(CONFIG_NOMADIK_GPIO)	+= gpio.o
diff --git a/arch/arm/plat-nomadik/include/plat/gpio.h b/arch/arm/plat-nomadik/include/plat/gpio.h
index 1b9f6f0843d1..d5d7e651269c 100644
--- a/arch/arm/plat-nomadik/include/plat/gpio.h
+++ b/arch/arm/plat-nomadik/include/plat/gpio.h
@@ -78,6 +78,8 @@ extern int nmk_gpio_get_mode(int gpio);
 extern void nmk_gpio_wakeups_suspend(void);
 extern void nmk_gpio_wakeups_resume(void);
 
+extern void nmk_gpio_read_pull(int gpio_bank, u32 *pull_up);
+
 /*
  * Platform data to register a block: only the initial gpio/irq number.
  */
@@ -88,6 +90,7 @@ struct nmk_gpio_platform_data {
 	int num_gpio;
 	u32 (*get_secondary_status)(unsigned int bank);
 	void (*set_ioforce)(bool enable);
+	bool supports_sleepmode;
 };
 
 #endif /* __ASM_PLAT_GPIO_H */
diff --git a/arch/arm/plat-omap/Makefile b/arch/arm/plat-omap/Makefile
index a4a12859fdd5..f0233e6abcdf 100644
--- a/arch/arm/plat-omap/Makefile
+++ b/arch/arm/plat-omap/Makefile
@@ -3,7 +3,7 @@
 #
 
 # Common support
-obj-y := common.o sram.o clock.o devices.o dma.o mux.o gpio.o \
+obj-y := common.o sram.o clock.o devices.o dma.o mux.o \
 	 usb.o fb.o io.o counter_32k.o
 obj-m :=
 obj-n :=
diff --git a/arch/arm/plat-omap/include/plat/flash.h b/arch/arm/plat-omap/include/plat/flash.h
index 3083195123ea..0d88499b79e9 100644
--- a/arch/arm/plat-omap/include/plat/flash.h
+++ b/arch/arm/plat-omap/include/plat/flash.h
@@ -11,6 +11,7 @@
 
 #include <linux/mtd/map.h>
 
+struct platform_device;
 extern void omap1_set_vpp(struct platform_device *pdev, int enable);
 
 #endif
diff --git a/arch/arm/plat-omap/include/plat/gpio.h b/arch/arm/plat-omap/include/plat/gpio.h
index cac2e8ac6968..ec97e00cb581 100644
--- a/arch/arm/plat-omap/include/plat/gpio.h
+++ b/arch/arm/plat-omap/include/plat/gpio.h
@@ -52,6 +52,109 @@
 
 #define OMAP34XX_NR_GPIOS		6
 
+/*
+ * OMAP1510 GPIO registers
+ */
+#define OMAP1510_GPIO_DATA_INPUT	0x00
+#define OMAP1510_GPIO_DATA_OUTPUT	0x04
+#define OMAP1510_GPIO_DIR_CONTROL	0x08
+#define OMAP1510_GPIO_INT_CONTROL	0x0c
+#define OMAP1510_GPIO_INT_MASK		0x10
+#define OMAP1510_GPIO_INT_STATUS	0x14
+#define OMAP1510_GPIO_PIN_CONTROL	0x18
+
+#define OMAP1510_IH_GPIO_BASE		64
+
+/*
+ * OMAP1610 specific GPIO registers
+ */
+#define OMAP1610_GPIO_REVISION		0x0000
+#define OMAP1610_GPIO_SYSCONFIG		0x0010
+#define OMAP1610_GPIO_SYSSTATUS		0x0014
+#define OMAP1610_GPIO_IRQSTATUS1	0x0018
+#define OMAP1610_GPIO_IRQENABLE1	0x001c
+#define OMAP1610_GPIO_WAKEUPENABLE	0x0028
+#define OMAP1610_GPIO_DATAIN		0x002c
+#define OMAP1610_GPIO_DATAOUT		0x0030
+#define OMAP1610_GPIO_DIRECTION		0x0034
+#define OMAP1610_GPIO_EDGE_CTRL1	0x0038
+#define OMAP1610_GPIO_EDGE_CTRL2	0x003c
+#define OMAP1610_GPIO_CLEAR_IRQENABLE1	0x009c
+#define OMAP1610_GPIO_CLEAR_WAKEUPENA	0x00a8
+#define OMAP1610_GPIO_CLEAR_DATAOUT	0x00b0
+#define OMAP1610_GPIO_SET_IRQENABLE1	0x00dc
+#define OMAP1610_GPIO_SET_WAKEUPENA	0x00e8
+#define OMAP1610_GPIO_SET_DATAOUT	0x00f0
+
+/*
+ * OMAP7XX specific GPIO registers
+ */
+#define OMAP7XX_GPIO_DATA_INPUT		0x00
+#define OMAP7XX_GPIO_DATA_OUTPUT	0x04
+#define OMAP7XX_GPIO_DIR_CONTROL	0x08
+#define OMAP7XX_GPIO_INT_CONTROL	0x0c
+#define OMAP7XX_GPIO_INT_MASK		0x10
+#define OMAP7XX_GPIO_INT_STATUS		0x14
+
+/*
+ * omap2+ specific GPIO registers
+ */
+#define OMAP24XX_GPIO_REVISION		0x0000
+#define OMAP24XX_GPIO_IRQSTATUS1	0x0018
+#define OMAP24XX_GPIO_IRQSTATUS2	0x0028
+#define OMAP24XX_GPIO_IRQENABLE2	0x002c
+#define OMAP24XX_GPIO_IRQENABLE1	0x001c
+#define OMAP24XX_GPIO_WAKE_EN		0x0020
+#define OMAP24XX_GPIO_CTRL		0x0030
+#define OMAP24XX_GPIO_OE		0x0034
+#define OMAP24XX_GPIO_DATAIN		0x0038
+#define OMAP24XX_GPIO_DATAOUT		0x003c
+#define OMAP24XX_GPIO_LEVELDETECT0	0x0040
+#define OMAP24XX_GPIO_LEVELDETECT1	0x0044
+#define OMAP24XX_GPIO_RISINGDETECT	0x0048
+#define OMAP24XX_GPIO_FALLINGDETECT	0x004c
+#define OMAP24XX_GPIO_DEBOUNCE_EN	0x0050
+#define OMAP24XX_GPIO_DEBOUNCE_VAL	0x0054
+#define OMAP24XX_GPIO_CLEARIRQENABLE1	0x0060
+#define OMAP24XX_GPIO_SETIRQENABLE1	0x0064
+#define OMAP24XX_GPIO_CLEARWKUENA	0x0080
+#define OMAP24XX_GPIO_SETWKUENA		0x0084
+#define OMAP24XX_GPIO_CLEARDATAOUT	0x0090
+#define OMAP24XX_GPIO_SETDATAOUT	0x0094
+
+#define OMAP4_GPIO_REVISION		0x0000
+#define OMAP4_GPIO_EOI			0x0020
+#define OMAP4_GPIO_IRQSTATUSRAW0	0x0024
+#define OMAP4_GPIO_IRQSTATUSRAW1	0x0028
+#define OMAP4_GPIO_IRQSTATUS0		0x002c
+#define OMAP4_GPIO_IRQSTATUS1		0x0030
+#define OMAP4_GPIO_IRQSTATUSSET0	0x0034
+#define OMAP4_GPIO_IRQSTATUSSET1	0x0038
+#define OMAP4_GPIO_IRQSTATUSCLR0	0x003c
+#define OMAP4_GPIO_IRQSTATUSCLR1	0x0040
+#define OMAP4_GPIO_IRQWAKEN0		0x0044
+#define OMAP4_GPIO_IRQWAKEN1		0x0048
+#define OMAP4_GPIO_IRQENABLE1		0x011c
+#define OMAP4_GPIO_WAKE_EN		0x0120
+#define OMAP4_GPIO_IRQSTATUS2		0x0128
+#define OMAP4_GPIO_IRQENABLE2		0x012c
+#define OMAP4_GPIO_CTRL			0x0130
+#define OMAP4_GPIO_OE			0x0134
+#define OMAP4_GPIO_DATAIN		0x0138
+#define OMAP4_GPIO_DATAOUT		0x013c
+#define OMAP4_GPIO_LEVELDETECT0		0x0140
+#define OMAP4_GPIO_LEVELDETECT1		0x0144
+#define OMAP4_GPIO_RISINGDETECT		0x0148
+#define OMAP4_GPIO_FALLINGDETECT	0x014c
+#define OMAP4_GPIO_DEBOUNCENABLE	0x0150
+#define OMAP4_GPIO_DEBOUNCINGTIME	0x0154
+#define OMAP4_GPIO_CLEARIRQENABLE1	0x0160
+#define OMAP4_GPIO_SETIRQENABLE1	0x0164
+#define OMAP4_GPIO_CLEARWKUENA		0x0180
+#define OMAP4_GPIO_SETWKUENA		0x0184
+#define OMAP4_GPIO_CLEARDATAOUT		0x0190
+#define OMAP4_GPIO_SETDATAOUT		0x0194
+
 #define OMAP_MPUIO(nr)		(OMAP_MAX_GPIO_LINES + (nr))
 #define OMAP_GPIO_IS_MPUIO(nr)	((nr) >= OMAP_MAX_GPIO_LINES)
 
diff --git a/arch/arm/plat-omap/include/plat/iovmm.h b/arch/arm/plat-omap/include/plat/iovmm.h
index 32a2f6c4d39e..e992b9655fbc 100644
--- a/arch/arm/plat-omap/include/plat/iovmm.h
+++ b/arch/arm/plat-omap/include/plat/iovmm.h
@@ -29,9 +29,6 @@ struct iovm_struct {
  * lower 16 bit is used for h/w and upper 16 bit is for s/w.
  */
 #define IOVMF_SW_SHIFT		16
-#define IOVMF_HW_SIZE		(1 << IOVMF_SW_SHIFT)
-#define IOVMF_HW_MASK		(IOVMF_HW_SIZE - 1)
-#define IOVMF_SW_MASK		(~IOVMF_HW_MASK)UL
 
 /*
  * iovma: h/w flags derived from cam and ram attribute
diff --git a/arch/arm/plat-omap/include/plat/mmc.h b/arch/arm/plat-omap/include/plat/mmc.h
index f38fef9f1310..c7b874186c27 100644
--- a/arch/arm/plat-omap/include/plat/mmc.h
+++ b/arch/arm/plat-omap/include/plat/mmc.h
@@ -101,6 +101,9 @@ struct omap_mmc_platform_data {
 		/* If using power_saving and the MMC power is not to go off */
 		unsigned no_off:1;
 
+		/* eMMC does not handle power off when not in sleep state */
+		unsigned no_regulator_off_init:1;
+
 		/* Regulator off remapped to sleep */
 		unsigned vcc_aux_disable_is_sleep:1;
 
diff --git a/arch/arm/plat-omap/iovmm.c b/arch/arm/plat-omap/iovmm.c
index 51ef43e8def6..83a37c54342f 100644
--- a/arch/arm/plat-omap/iovmm.c
+++ b/arch/arm/plat-omap/iovmm.c
@@ -648,7 +648,6 @@ u32 iommu_vmap(struct iommu *obj, u32 da, const struct sg_table *sgt,
 			return PTR_ERR(va);
 	}
 
-	flags &= IOVMF_HW_MASK;
 	flags |= IOVMF_DISCONT;
 	flags |= IOVMF_MMIO;
 
@@ -706,7 +705,6 @@ u32 iommu_vmalloc(struct iommu *obj, u32 da, size_t bytes, u32 flags)
 	if (!va)
 		return -ENOMEM;
 
-	flags &= IOVMF_HW_MASK;
 	flags |= IOVMF_DISCONT;
 	flags |= IOVMF_ALLOC;
 
@@ -795,7 +793,6 @@ u32 iommu_kmap(struct iommu *obj, u32 da, u32 pa, size_t bytes,
 	if (!va)
 		return -ENOMEM;
 
-	flags &= IOVMF_HW_MASK;
 	flags |= IOVMF_LINEAR;
 	flags |= IOVMF_MMIO;
 
@@ -853,7 +850,6 @@ u32 iommu_kmalloc(struct iommu *obj, u32 da, size_t bytes, u32 flags)
 		return -ENOMEM;
 	pa = virt_to_phys(va);
 
-	flags &= IOVMF_HW_MASK;
 	flags |= IOVMF_LINEAR;
 	flags |= IOVMF_ALLOC;
 
diff --git a/arch/arm/plat-omap/omap_device.c b/arch/arm/plat-omap/omap_device.c
index a37b8eb65b76..49fc0df0c21f 100644
--- a/arch/arm/plat-omap/omap_device.c
+++ b/arch/arm/plat-omap/omap_device.c
@@ -84,6 +84,7 @@
 #include <linux/io.h>
 #include <linux/clk.h>
 #include <linux/clkdev.h>
+#include <linux/pm_runtime.h>
 
 #include <plat/omap_device.h>
 #include <plat/omap_hwmod.h>
@@ -539,20 +540,34 @@ int omap_early_device_register(struct omap_device *od)
 static int _od_runtime_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
+	int ret;
+
+	ret = pm_generic_runtime_suspend(dev);
+
+	if (!ret)
+		omap_device_idle(pdev);
+
+	return ret;
+}
 
-	return omap_device_idle(pdev);
+static int _od_runtime_idle(struct device *dev)
+{
+	return pm_generic_runtime_idle(dev);
 }
 
 static int _od_runtime_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 
-	return omap_device_enable(pdev);
+	omap_device_enable(pdev);
+
+	return pm_generic_runtime_resume(dev);
 }
 
 static struct dev_power_domain omap_device_power_domain = {
 	.ops = {
 		.runtime_suspend = _od_runtime_suspend,
+		.runtime_idle = _od_runtime_idle,
 		.runtime_resume = _od_runtime_resume,
 		USE_PLATFORM_PM_SLEEP_OPS
 	}
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index a3f50b34a90d..6af3d0b1f8d0 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -166,7 +166,7 @@ static void __init omap_detect_sram(void)
 		else if (cpu_is_omap1611())
 			omap_sram_size = SZ_256K;
 		else {
-			printk(KERN_ERR "Could not detect SRAM size\n");
+			pr_err("Could not detect SRAM size\n");
 			omap_sram_size = 0x4000;
 		}
 	}
@@ -221,10 +221,10 @@ static void __init omap_map_sram(void)
 	omap_sram_io_desc[0].length = ROUND_DOWN(omap_sram_size, PAGE_SIZE);
 	iotable_init(omap_sram_io_desc, ARRAY_SIZE(omap_sram_io_desc));
 
-	printk(KERN_INFO "SRAM: Mapped pa 0x%08lx to va 0x%08lx size: 0x%lx\n",
-	__pfn_to_phys(omap_sram_io_desc[0].pfn),
-	omap_sram_io_desc[0].virtual,
-	       omap_sram_io_desc[0].length);
+	pr_info("SRAM: Mapped pa 0x%08llx to va 0x%08lx size: 0x%lx\n",
+		(long long) __pfn_to_phys(omap_sram_io_desc[0].pfn),
+		omap_sram_io_desc[0].virtual,
+		omap_sram_io_desc[0].length);
 
 	/*
 	 * Normally devicemaps_init() would flush caches and tlb after
@@ -252,7 +252,7 @@ static void __init omap_map_sram(void)
 void *omap_sram_push_address(unsigned long size)
 {
 	if (size > (omap_sram_ceil - (omap_sram_base + SRAM_BOOTLOADER_SZ))) {
-		printk(KERN_ERR "Not enough space in SRAM\n");
+		pr_err("Not enough space in SRAM\n");
 		return NULL;
 	}
 
diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c
index c10d10c56e2e..2abf9660bc6c 100644
--- a/arch/arm/plat-s3c24xx/dma.c
+++ b/arch/arm/plat-s3c24xx/dma.c
@@ -1199,7 +1199,7 @@ EXPORT_SYMBOL(s3c2410_dma_getposition);
 
 #ifdef CONFIG_PM
 
-static void s3c2410_dma_suspend_chan(s3c2410_dma_chan *cp)
+static void s3c2410_dma_suspend_chan(struct s3c2410_dma_chan *cp)
 {
 	printk(KERN_DEBUG "suspending dma channel %d\n", cp->number);
 
diff --git a/arch/arm/plat-s3c24xx/irq.c b/arch/arm/plat-s3c24xx/irq.c
index 9aee7e1668b1..fc8c5f89954d 100644
--- a/arch/arm/plat-s3c24xx/irq.c
+++ b/arch/arm/plat-s3c24xx/irq.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
 #include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/irq.h>
 #include <asm/mach/irq.h>
@@ -668,3 +669,8 @@ void __init s3c24xx_init_irq(void)
 
 	irqdbf("s3c2410: registered interrupt handlers\n");
 }
+
+struct syscore_ops s3c24xx_irq_syscore_ops = {
+	.suspend	= s3c24xx_irq_suspend,
+	.resume		= s3c24xx_irq_resume,
+};
diff --git a/arch/arm/plat-s5p/Kconfig b/arch/arm/plat-s5p/Kconfig
index 6751bcf7b888..e98f5c5c7879 100644
--- a/arch/arm/plat-s5p/Kconfig
+++ b/arch/arm/plat-s5p/Kconfig
@@ -7,7 +7,7 @@
 
 config PLAT_S5P
 	bool
-	depends on (ARCH_S5P64X0 || ARCH_S5P6442 || ARCH_S5PC100 || ARCH_S5PV210 || ARCH_EXYNOS4)
+	depends on (ARCH_S5P64X0 || ARCH_S5PC100 || ARCH_S5PV210 || ARCH_EXYNOS4)
 	default y
 	select ARM_VIC if !ARCH_EXYNOS4
 	select ARM_GIC if ARCH_EXYNOS4
diff --git a/arch/arm/plat-s5p/cpu.c b/arch/arm/plat-s5p/cpu.c
index 5cf5e721e6ca..bbc2aa7449ca 100644
--- a/arch/arm/plat-s5p/cpu.c
+++ b/arch/arm/plat-s5p/cpu.c
@@ -21,7 +21,6 @@
 
 #include <plat/cpu.h>
 #include <plat/s5p6440.h>
-#include <plat/s5p6442.h>
 #include <plat/s5p6450.h>
 #include <plat/s5pc100.h>
 #include <plat/s5pv210.h>
@@ -30,7 +29,6 @@
 /* table of supported CPUs */
 
 static const char name_s5p6440[] = "S5P6440";
-static const char name_s5p6442[] = "S5P6442";
 static const char name_s5p6450[] = "S5P6450";
 static const char name_s5pc100[] = "S5PC100";
 static const char name_s5pv210[] = "S5PV210/S5PC110";
@@ -46,14 +44,6 @@ static struct cpu_table cpu_ids[] __initdata = {
 		.init		= s5p64x0_init,
 		.name		= name_s5p6440,
 	}, {
-		.idcode		= 0x36442000,
-		.idmask		= 0xfffff000,
-		.map_io		= s5p6442_map_io,
-		.init_clocks	= s5p6442_init_clocks,
-		.init_uarts	= s5p6442_init_uarts,
-		.init		= s5p6442_init,
-		.name		= name_s5p6442,
-	}, {
 		.idcode		= 0x36450000,
 		.idmask		= 0xfffff000,
 		.map_io		= s5p6450_map_io,
diff --git a/arch/arm/plat-s5p/dev-onenand.c b/arch/arm/plat-s5p/dev-onenand.c
index 6db926202caa..20336c8f2479 100644
--- a/arch/arm/plat-s5p/dev-onenand.c
+++ b/arch/arm/plat-s5p/dev-onenand.c
@@ -15,8 +15,6 @@
 
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/onenand.h>
 
 #include <mach/irqs.h>
 #include <mach/map.h>
@@ -45,13 +43,3 @@ struct platform_device s5p_device_onenand = {
 	.num_resources	= ARRAY_SIZE(s5p_onenand_resources),
 	.resource	= s5p_onenand_resources,
 };
-
-void s5p_onenand_set_platdata(struct onenand_platform_data *pdata)
-{
-	struct onenand_platform_data *pd;
-
-	pd = kmemdup(pdata, sizeof(struct onenand_platform_data), GFP_KERNEL);
-	if (!pd)
-		printk(KERN_ERR "%s: no memory for platform data\n", __func__);
-	s5p_device_onenand.dev.platform_data = pd;
-}
diff --git a/arch/arm/plat-s5p/include/plat/map-s5p.h b/arch/arm/plat-s5p/include/plat/map-s5p.h
index a6c3d327ce72..d973d39666a3 100644
--- a/arch/arm/plat-s5p/include/plat/map-s5p.h
+++ b/arch/arm/plat-s5p/include/plat/map-s5p.h
@@ -39,7 +39,7 @@
 #define S5P_VA_TWD		S5P_VA_COREPERI(0x600)
 #define S5P_VA_GIC_DIST		S5P_VA_COREPERI(0x1000)
 
-#define S5P_VA_USB_HSPHY	S3C_ADDR(0x02900000)
+#define S3C_VA_USB_HSPHY	S3C_ADDR(0x02900000)
 
 #define VA_VIC(x)		(S3C_VA_IRQ + ((x) * 0x10000))
 #define VA_VIC0			VA_VIC(0)
diff --git a/arch/arm/plat-s5p/include/plat/s5p6442.h b/arch/arm/plat-s5p/include/plat/s5p6442.h
deleted file mode 100644
index 7b8801349c94..000000000000
--- a/arch/arm/plat-s5p/include/plat/s5p6442.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/* arch/arm/plat-s5p/include/plat/s5p6442.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * Header file for s5p6442 cpu support
- *
- * 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.
-*/
-
-/* Common init code for S5P6442 related SoCs */
-
-extern void s5p6442_common_init_uarts(struct s3c2410_uartcfg *cfg, int no);
-extern void s5p6442_register_clocks(void);
-extern void s5p6442_setup_clocks(void);
-
-#ifdef CONFIG_CPU_S5P6442
-
-extern  int s5p6442_init(void);
-extern void s5p6442_init_irq(void);
-extern void s5p6442_map_io(void);
-extern void s5p6442_init_clocks(int xtal);
-
-#define s5p6442_init_uarts s5p6442_common_init_uarts
-
-#else
-#define s5p6442_init_clocks NULL
-#define s5p6442_init_uarts NULL
-#define s5p6442_map_io NULL
-#define s5p6442_init NULL
-#endif
diff --git a/arch/arm/plat-samsung/Makefile b/arch/arm/plat-samsung/Makefile
index e9de58a2e294..53eb15b0a07d 100644
--- a/arch/arm/plat-samsung/Makefile
+++ b/arch/arm/plat-samsung/Makefile
@@ -19,7 +19,6 @@ obj-y				+= gpio.o
 obj-y				+= gpio-config.o
 obj-y				+= dev-asocdma.o
 
-obj-$(CONFIG_SAMSUNG_GPIOLIB_4BIT)	+= gpiolib.o
 obj-$(CONFIG_SAMSUNG_CLKSRC)	+= clock-clksrc.o
 
 obj-$(CONFIG_SAMSUNG_IRQ_UART)	+= irq-uart.o
diff --git a/arch/arm/plat-samsung/dev-onenand.c b/arch/arm/plat-samsung/dev-onenand.c
index 45ec73287d8c..f54ae71f0cd2 100644
--- a/arch/arm/plat-samsung/dev-onenand.c
+++ b/arch/arm/plat-samsung/dev-onenand.c
@@ -13,8 +13,6 @@
 
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/onenand.h>
 
 #include <mach/irqs.h>
 #include <mach/map.h>
@@ -43,13 +41,3 @@ struct platform_device s3c_device_onenand = {
 	.num_resources	= ARRAY_SIZE(s3c_onenand_resources),
 	.resource	= s3c_onenand_resources,
 };
-
-void s3c_onenand_set_platdata(struct onenand_platform_data *pdata)
-{
-	struct onenand_platform_data *pd;
-
-	pd = kmemdup(pdata, sizeof(struct onenand_platform_data), GFP_KERNEL);
-	if (!pd)
-		printk(KERN_ERR "%s: no memory for platform data\n", __func__);
-	s3c_device_onenand.dev.platform_data = pd;
-}
diff --git a/arch/arm/plat-samsung/include/plat/cpu.h b/arch/arm/plat-samsung/include/plat/cpu.h
index 3aedac0034ba..c0a5741b23e6 100644
--- a/arch/arm/plat-samsung/include/plat/cpu.h
+++ b/arch/arm/plat-samsung/include/plat/cpu.h
@@ -86,7 +86,6 @@ extern struct sysdev_class s3c2443_sysclass;
 extern struct sysdev_class s3c6410_sysclass;
 extern struct sysdev_class s3c64xx_sysclass;
 extern struct sysdev_class s5p64x0_sysclass;
-extern struct sysdev_class s5p6442_sysclass;
 extern struct sysdev_class s5pv210_sysclass;
 extern struct sysdev_class exynos4_sysclass;
 
diff --git a/arch/arm/plat-samsung/include/plat/debug-macro.S b/arch/arm/plat-samsung/include/plat/debug-macro.S
index dc6efd90e8ff..207e275362a8 100644
--- a/arch/arm/plat-samsung/include/plat/debug-macro.S
+++ b/arch/arm/plat-samsung/include/plat/debug-macro.S
@@ -11,7 +11,7 @@
 
 #include <plat/regs-serial.h>
 
-/* The S5PV210/S5PC110 and S5P6442 implementations are as belows. */
+/* The S5PV210/S5PC110 implementations are as belows. */
 
 	.macro fifo_level_s5pv210 rd, rx
 		ldr	\rd, [ \rx, # S3C2410_UFSTAT ]
diff --git a/arch/arm/plat-samsung/include/plat/devs.h b/arch/arm/plat-samsung/include/plat/devs.h
index 39818d8da420..4af108ff4112 100644
--- a/arch/arm/plat-samsung/include/plat/devs.h
+++ b/arch/arm/plat-samsung/include/plat/devs.h
@@ -75,10 +75,8 @@ extern struct platform_device s5pc100_device_spi1;
 extern struct platform_device s5pc100_device_spi2;
 extern struct platform_device s5pv210_device_spi0;
 extern struct platform_device s5pv210_device_spi1;
-extern struct platform_device s5p6440_device_spi0;
-extern struct platform_device s5p6440_device_spi1;
-extern struct platform_device s5p6450_device_spi0;
-extern struct platform_device s5p6450_device_spi1;
+extern struct platform_device s5p64x0_device_spi0;
+extern struct platform_device s5p64x0_device_spi1;
 
 extern struct platform_device s3c_device_hwmon;
 
@@ -111,12 +109,6 @@ extern struct platform_device exynos4_device_spdif;
 extern struct platform_device exynos4_device_pd[];
 extern struct platform_device exynos4_device_ahci;
 
-extern struct platform_device s5p6442_device_pcm0;
-extern struct platform_device s5p6442_device_pcm1;
-extern struct platform_device s5p6442_device_iis0;
-extern struct platform_device s5p6442_device_iis1;
-extern struct platform_device s5p6442_device_spi;
-
 extern struct platform_device s5p6440_device_pcm;
 extern struct platform_device s5p6440_device_iis;
 
diff --git a/arch/arm/plat-samsung/include/plat/regs-serial.h b/arch/arm/plat-samsung/include/plat/regs-serial.h
index 788837e99cb3..c151c5f94a87 100644
--- a/arch/arm/plat-samsung/include/plat/regs-serial.h
+++ b/arch/arm/plat-samsung/include/plat/regs-serial.h
@@ -194,7 +194,7 @@
 #define S3C64XX_UINTSP		0x34
 #define S3C64XX_UINTM		0x38
 
-/* Following are specific to S5PV210 and S5P6442 */
+/* Following are specific to S5PV210 */
 #define S5PV210_UCON_CLKMASK	(1<<10)
 #define S5PV210_UCON_PCLK	(0<<10)
 #define S5PV210_UCON_UCLK	(1<<10)
diff --git a/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h b/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h
index ff1a561b326e..0ffe34a21554 100644
--- a/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h
+++ b/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h
@@ -69,6 +69,5 @@ extern void s3c64xx_spi_set_info(int cntrlr, int src_clk_nr, int num_cs);
 extern void s5pc100_spi_set_info(int cntrlr, int src_clk_nr, int num_cs);
 extern void s5pv210_spi_set_info(int cntrlr, int src_clk_nr, int num_cs);
 extern void s5p64x0_spi_set_info(int cntrlr, int src_clk_nr, int num_cs);
-extern void s5p6442_spi_set_info(int cntrlr, int src_clk_nr, int num_cs);
 
 #endif /* __S3C64XX_PLAT_SPI_H */
diff --git a/arch/avr32/configs/atngw100_defconfig b/arch/avr32/configs/atngw100_defconfig
index 6f9ca56de1f6..a06bfccc2840 100644
--- a/arch/avr32/configs/atngw100_defconfig
+++ b/arch/avr32/configs/atngw100_defconfig
@@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/avr32/configs/atngw100_evklcd100_defconfig b/arch/avr32/configs/atngw100_evklcd100_defconfig
index 7eece0af34c9..d8f1fe80d210 100644
--- a/arch/avr32/configs/atngw100_evklcd100_defconfig
+++ b/arch/avr32/configs/atngw100_evklcd100_defconfig
@@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/avr32/configs/atngw100_evklcd101_defconfig b/arch/avr32/configs/atngw100_evklcd101_defconfig
index 387eb9d6e423..d4c5b19ec950 100644
--- a/arch/avr32/configs/atngw100_evklcd101_defconfig
+++ b/arch/avr32/configs/atngw100_evklcd101_defconfig
@@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/avr32/configs/atngw100_mrmt_defconfig b/arch/avr32/configs/atngw100_mrmt_defconfig
index 19f6ceeeff7b..77ca4f905d2c 100644
--- a/arch/avr32/configs/atngw100_mrmt_defconfig
+++ b/arch/avr32/configs/atngw100_mrmt_defconfig
@@ -7,6 +7,7 @@ CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_SLUB_DEBUG is not set
@@ -109,7 +110,7 @@ CONFIG_LEDS_GPIO=y
 CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_S35390A=m
 CONFIG_RTC_DRV_AT32AP700X=m
 CONFIG_DMADEVICES=y
diff --git a/arch/avr32/configs/atngw100mkii_defconfig b/arch/avr32/configs/atngw100mkii_defconfig
index f0fe237133a9..6e0dca4d3131 100644
--- a/arch/avr32/configs/atngw100mkii_defconfig
+++ b/arch/avr32/configs/atngw100mkii_defconfig
@@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/avr32/configs/atngw100mkii_evklcd100_defconfig b/arch/avr32/configs/atngw100mkii_evklcd100_defconfig
index e4a7c1dc8380..7f2a344a5fa8 100644
--- a/arch/avr32/configs/atngw100mkii_evklcd100_defconfig
+++ b/arch/avr32/configs/atngw100mkii_evklcd100_defconfig
@@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/avr32/configs/atngw100mkii_evklcd101_defconfig b/arch/avr32/configs/atngw100mkii_evklcd101_defconfig
index 6f37f70c2c37..085eeba88f67 100644
--- a/arch/avr32/configs/atngw100mkii_evklcd101_defconfig
+++ b/arch/avr32/configs/atngw100mkii_evklcd101_defconfig
@@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/avr32/configs/atstk1002_defconfig b/arch/avr32/configs/atstk1002_defconfig
index 4fb01f5ab42f..d1a887e64055 100644
--- a/arch/avr32/configs/atstk1002_defconfig
+++ b/arch/avr32/configs/atstk1002_defconfig
@@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/avr32/configs/atstk1003_defconfig b/arch/avr32/configs/atstk1003_defconfig
index 9faaf9b900f2..956f2819ad45 100644
--- a/arch/avr32/configs/atstk1003_defconfig
+++ b/arch/avr32/configs/atstk1003_defconfig
@@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/avr32/configs/atstk1004_defconfig b/arch/avr32/configs/atstk1004_defconfig
index 3d2a5d85f970..40c69f38c61a 100644
--- a/arch/avr32/configs/atstk1004_defconfig
+++ b/arch/avr32/configs/atstk1004_defconfig
@@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/avr32/configs/atstk1006_defconfig b/arch/avr32/configs/atstk1006_defconfig
index 1ed8f22d4fe2..511eb8af356d 100644
--- a/arch/avr32/configs/atstk1006_defconfig
+++ b/arch/avr32/configs/atstk1006_defconfig
@@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/avr32/configs/favr-32_defconfig b/arch/avr32/configs/favr-32_defconfig
index aeadc955db32..19973b06170c 100644
--- a/arch/avr32/configs/favr-32_defconfig
+++ b/arch/avr32/configs/favr-32_defconfig
@@ -6,6 +6,7 @@ CONFIG_LOG_BUF_SHIFT=14
 CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/avr32/configs/hammerhead_defconfig b/arch/avr32/configs/hammerhead_defconfig
index 1692beeb7ed3..6f45681196d1 100644
--- a/arch/avr32/configs/hammerhead_defconfig
+++ b/arch/avr32/configs/hammerhead_defconfig
@@ -7,6 +7,7 @@ CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/avr32/configs/merisc_defconfig b/arch/avr32/configs/merisc_defconfig
index 8b670a6530bf..3befab966827 100644
--- a/arch/avr32/configs/merisc_defconfig
+++ b/arch/avr32/configs/merisc_defconfig
@@ -7,6 +7,7 @@ CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 CONFIG_MODULES=y
diff --git a/arch/avr32/configs/mimc200_defconfig b/arch/avr32/configs/mimc200_defconfig
index 5a51f2e7ffb9..1bee51f22154 100644
--- a/arch/avr32/configs/mimc200_defconfig
+++ b/arch/avr32/configs/mimc200_defconfig
@@ -7,6 +7,7 @@ CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/avr32/include/asm/processor.h b/arch/avr32/include/asm/processor.h
index 49a88f5a9d2f..108502bc6770 100644
--- a/arch/avr32/include/asm/processor.h
+++ b/arch/avr32/include/asm/processor.h
@@ -131,7 +131,6 @@ struct thread_struct {
  */
 #define start_thread(regs, new_pc, new_sp)	 \
 	do {					 \
-		set_fs(USER_DS);		 \
 		memset(regs, 0, sizeof(*regs));	 \
 		regs->sr = MODE_USER;		 \
 		regs->pc = new_pc & ~1;		 \
diff --git a/arch/avr32/include/asm/unistd.h b/arch/avr32/include/asm/unistd.h
index 89861a27543e..f714544e5560 100644
--- a/arch/avr32/include/asm/unistd.h
+++ b/arch/avr32/include/asm/unistd.h
@@ -299,9 +299,10 @@
 #define __NR_signalfd		279
 /* 280 was __NR_timerfd */
 #define __NR_eventfd		281
+#define __NR_setns		283
 
 #ifdef __KERNEL__
-#define NR_syscalls		282
+#define NR_syscalls		284
 
 /* Old stuff */
 #define __IGNORE_uselib
diff --git a/arch/avr32/kernel/syscall_table.S b/arch/avr32/kernel/syscall_table.S
index e76bad16b0f0..c7fd394d28a4 100644
--- a/arch/avr32/kernel/syscall_table.S
+++ b/arch/avr32/kernel/syscall_table.S
@@ -296,4 +296,5 @@ sys_call_table:
 	.long	sys_ni_syscall		/* 280, was sys_timerfd */
 	.long	sys_eventfd
 	.long	sys_recvmmsg
+	.long	sys_setns
 	.long	sys_ni_syscall		/* r8 is saturated at nr_syscalls */
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index bfc9d071db9b..7fbf0dcb9afe 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -1014,6 +1014,7 @@ static struct platform_device *__initdata at32_usarts[4];
 void __init at32_map_usart(unsigned int hw_id, unsigned int line, int flags)
 {
 	struct platform_device *pdev;
+	struct atmel_uart_data *pdata;
 
 	switch (hw_id) {
 	case 0:
@@ -1043,6 +1044,8 @@ void __init at32_map_usart(unsigned int hw_id, unsigned int line, int flags)
 	}
 
 	pdev->id = line;
+	pdata = pdev->dev.platform_data;
+	pdata->num = line;
 	at32_usarts[line] = pdev;
 }
 
diff --git a/arch/avr32/mach-at32ap/include/mach/board.h b/arch/avr32/mach-at32ap/include/mach/board.h
index 61740201b311..679458d9a622 100644
--- a/arch/avr32/mach-at32ap/include/mach/board.h
+++ b/arch/avr32/mach-at32ap/include/mach/board.h
@@ -33,6 +33,7 @@ extern struct platform_device *atmel_default_console_device;
 #define	ATMEL_USART_CLK		0x04
 
 struct atmel_uart_data {
+	int		num;		/* port num */
 	short		use_dma_tx;	/* use transmit DMA? */
 	short		use_dma_rx;	/* use receive DMA? */
 	void __iomem	*regs;		/* virtual base address, if any */
diff --git a/arch/avr32/mach-at32ap/include/mach/cpu.h b/arch/avr32/mach-at32ap/include/mach/cpu.h
index 9c96a130f3a8..8181293115e4 100644
--- a/arch/avr32/mach-at32ap/include/mach/cpu.h
+++ b/arch/avr32/mach-at32ap/include/mach/cpu.h
@@ -31,8 +31,20 @@
 #define cpu_is_at91sam9263()	(0)
 #define cpu_is_at91sam9rl()	(0)
 #define cpu_is_at91cap9()	(0)
+#define cpu_is_at91cap9_revB()	(0)
+#define cpu_is_at91cap9_revC()	(0)
 #define cpu_is_at91sam9g10()	(0)
+#define cpu_is_at91sam9g20()	(0)
 #define cpu_is_at91sam9g45()	(0)
 #define cpu_is_at91sam9g45es()	(0)
+#define cpu_is_at91sam9m10()	(0)
+#define cpu_is_at91sam9g46()	(0)
+#define cpu_is_at91sam9m11()	(0)
+#define cpu_is_at91sam9x5()	(0)
+#define cpu_is_at91sam9g15()	(0)
+#define cpu_is_at91sam9g35()	(0)
+#define cpu_is_at91sam9x35()	(0)
+#define cpu_is_at91sam9g25()	(0)
+#define cpu_is_at91sam9x25()	(0)
 
 #endif /* __ASM_ARCH_CPU_H */
diff --git a/arch/avr32/mach-at32ap/intc.c b/arch/avr32/mach-at32ap/intc.c
index 3e3646186c9f..c9ac2f8e8f64 100644
--- a/arch/avr32/mach-at32ap/intc.c
+++ b/arch/avr32/mach-at32ap/intc.c
@@ -167,14 +167,12 @@ static int intc_suspend(void)
 	return 0;
 }
 
-static int intc_resume(void)
+static void intc_resume(void)
 {
 	int i;
 
 	for (i = 0; i < 64; i++)
 		intc_writel(&intc0, INTPR0 + 4 * i, intc0.saved_ipr[i]);
-
-	return 0;
 }
 #else
 #define intc_suspend	NULL
diff --git a/arch/blackfin/configs/CM-BF548_defconfig b/arch/blackfin/configs/CM-BF548_defconfig
index 31d954216c05..9f1d08401fca 100644
--- a/arch/blackfin/configs/CM-BF548_defconfig
+++ b/arch/blackfin/configs/CM-BF548_defconfig
@@ -112,7 +112,7 @@ CONFIG_USB_G_SERIAL=m
 CONFIG_USB_G_PRINTER=m
 CONFIG_MMC=m
 CONFIG_SDH_BFIN=m
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_BFIN=m
 CONFIG_EXT2_FS=m
 # CONFIG_DNOTIFY is not set
diff --git a/arch/blackfin/include/asm/bfin_serial.h b/arch/blackfin/include/asm/bfin_serial.h
index 7dbc664eab1e..7fd0ec7b5b0f 100644
--- a/arch/blackfin/include/asm/bfin_serial.h
+++ b/arch/blackfin/include/asm/bfin_serial.h
@@ -184,7 +184,7 @@ struct bfin_uart_regs {
 #undef __BFP
 
 #ifndef port_membase
-# define port_membase(p) (((struct bfin_serial_port *)(p))->port.membase)
+# define port_membase(p) 0
 #endif
 
 #define UART_GET_CHAR(p)      bfin_read16(port_membase(p) + OFFSET_RBR)
@@ -235,10 +235,10 @@ struct bfin_uart_regs {
 #define UART_SET_DLAB(p)      do { UART_PUT_LCR(p, UART_GET_LCR(p) | DLAB); SSYNC(); } while (0)
 
 #ifndef put_lsr_cache
-# define put_lsr_cache(p, v) (((struct bfin_serial_port *)(p))->lsr = (v))
+# define put_lsr_cache(p, v)
 #endif
 #ifndef get_lsr_cache
-# define get_lsr_cache(p)    (((struct bfin_serial_port *)(p))->lsr)
+# define get_lsr_cache(p) 0
 #endif
 
 /* The hardware clears the LSR bits upon read, so we need to cache
diff --git a/arch/blackfin/include/asm/gptimers.h b/arch/blackfin/include/asm/gptimers.h
index c722acdda0d3..38657dac1235 100644
--- a/arch/blackfin/include/asm/gptimers.h
+++ b/arch/blackfin/include/asm/gptimers.h
@@ -193,4 +193,22 @@ uint16_t get_enabled_gptimers(void);
 uint32_t get_gptimer_status(unsigned int group);
 void     set_gptimer_status(unsigned int group, uint32_t value);
 
+/*
+ * All Blackfin system MMRs are padded to 32bits even if the register
+ * itself is only 16bits.  So use a helper macro to streamline this.
+ */
+#define __BFP(m) u16 m; u16 __pad_##m
+
+/*
+ * bfin timer registers layout
+ */
+struct bfin_gptimer_regs {
+	__BFP(config);
+	u32 counter;
+	u32 period;
+	u32 width;
+};
+
+#undef __BFP
+
 #endif
diff --git a/arch/blackfin/include/asm/unistd.h b/arch/blackfin/include/asm/unistd.h
index ff9a9f35d50b..0ccba60b9ccf 100644
--- a/arch/blackfin/include/asm/unistd.h
+++ b/arch/blackfin/include/asm/unistd.h
@@ -397,8 +397,10 @@
 #define __NR_open_by_handle_at	376
 #define __NR_clock_adjtime	377
 #define __NR_syncfs		378
+#define __NR_setns		379
+#define __NR_sendmmsg		380
 
-#define __NR_syscall		379
+#define __NR_syscall		381
 #define NR_syscalls		__NR_syscall
 
 /* Old optional stuff no one actually uses */
diff --git a/arch/blackfin/kernel/debug-mmrs.c b/arch/blackfin/kernel/debug-mmrs.c
index 94b1d8a0256a..fce4807ceef9 100644
--- a/arch/blackfin/kernel/debug-mmrs.c
+++ b/arch/blackfin/kernel/debug-mmrs.c
@@ -13,6 +13,7 @@
 
 #include <asm/blackfin.h>
 #include <asm/gpio.h>
+#include <asm/gptimers.h>
 #include <asm/bfin_can.h>
 #include <asm/bfin_dma.h>
 #include <asm/bfin_ppi.h>
@@ -230,8 +231,8 @@ bfin_debug_mmrs_dma(struct dentry *parent, unsigned long base, int num, char mdm
 #define DMA(num)  _DMA(num, DMA##num##_NEXT_DESC_PTR, 0, "")
 #define _MDMA(num, x) \
 	do { \
-		_DMA(num, x##DMA_D##num##_CONFIG, 'D', #x); \
-		_DMA(num, x##DMA_S##num##_CONFIG, 'S', #x); \
+		_DMA(num, x##DMA_D##num##_NEXT_DESC_PTR, 'D', #x); \
+		_DMA(num, x##DMA_S##num##_NEXT_DESC_PTR, 'S', #x); \
 	} while (0)
 #define MDMA(num) _MDMA(num, M)
 #define IMDMA(num) _MDMA(num, IM)
@@ -264,20 +265,15 @@ bfin_debug_mmrs_eppi(struct dentry *parent, unsigned long base, int num)
 /*
  * General Purpose Timers
  */
-#define GPTIMER_OFF(mmr) (TIMER0_##mmr - TIMER0_CONFIG)
-#define __GPTIMER(name) \
-	do { \
-		strcpy(_buf, #name); \
-		debugfs_create_x16(buf, S_IRUSR|S_IWUSR, parent, (u16 *)(base + GPTIMER_OFF(name))); \
-	} while (0)
+#define __GPTIMER(uname, lname) __REGS(gptimer, #uname, lname)
 static void __init __maybe_unused
 bfin_debug_mmrs_gptimer(struct dentry *parent, unsigned long base, int num)
 {
 	char buf[32], *_buf = REGS_STR_PFX(buf, TIMER, num);
-	__GPTIMER(CONFIG);
-	__GPTIMER(COUNTER);
-	__GPTIMER(PERIOD);
-	__GPTIMER(WIDTH);
+	__GPTIMER(CONFIG, config);
+	__GPTIMER(COUNTER, counter);
+	__GPTIMER(PERIOD, period);
+	__GPTIMER(WIDTH, width);
 }
 #define GPTIMER(num) bfin_debug_mmrs_gptimer(parent, TIMER##num##_CONFIG, num)
 
@@ -355,7 +351,7 @@ bfin_debug_mmrs_ppi(struct dentry *parent, unsigned long base, int num)
 	__PPI(DELAY, delay);
 	__PPI(FRAME, frame);
 }
-#define PPI(num) bfin_debug_mmrs_ppi(parent, PPI##num##_STATUS, num)
+#define PPI(num) bfin_debug_mmrs_ppi(parent, PPI##num##_CONTROL, num)
 
 /*
  * SPI
@@ -1288,15 +1284,15 @@ static int __init bfin_debug_mmrs_init(void)
 	D16(VR_CTL);
 	D32(CHIPID);	/* it's part of this hardware block */
 
-#if defined(PPI_STATUS) || defined(PPI0_STATUS) || defined(PPI1_STATUS)
+#if defined(PPI_CONTROL) || defined(PPI0_CONTROL) || defined(PPI1_CONTROL)
 	parent = debugfs_create_dir("ppi", top);
-# ifdef PPI_STATUS
-	bfin_debug_mmrs_ppi(parent, PPI_STATUS, -1);
+# ifdef PPI_CONTROL
+	bfin_debug_mmrs_ppi(parent, PPI_CONTROL, -1);
 # endif
-# ifdef PPI0_STATUS
+# ifdef PPI0_CONTROL
 	PPI(0);
 # endif
-# ifdef PPI1_STATUS
+# ifdef PPI1_CONTROL
 	PPI(1);
 # endif
 #endif
@@ -1341,6 +1337,10 @@ static int __init bfin_debug_mmrs_init(void)
 	D16(RSI_PID1);
 	D16(RSI_PID2);
 	D16(RSI_PID3);
+	D16(RSI_PID4);
+	D16(RSI_PID5);
+	D16(RSI_PID6);
+	D16(RSI_PID7);
 	D16(RSI_PWR_CONTROL);
 	D16(RSI_RD_WAIT_EN);
 	D32(RSI_RESPONSE0);
diff --git a/arch/blackfin/lib/strncpy.S b/arch/blackfin/lib/strncpy.S
index f3931d50b4a7..2c07dddac995 100644
--- a/arch/blackfin/lib/strncpy.S
+++ b/arch/blackfin/lib/strncpy.S
@@ -25,7 +25,7 @@
 
 ENTRY(_strncpy)
 	CC = R2 == 0;
-	if CC JUMP 4f;
+	if CC JUMP 6f;
 
 	P2 = R2 ;       /* size */
 	P0 = R0 ;       /* dst*/
diff --git a/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index f6d924ac0c44..000000000000
--- a/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * Copyright 2008-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS)
-# define CONFIG_SERIAL_BFIN_CTSRTS
-
-# ifndef CONFIG_UART0_CTS_PIN
-#  define CONFIG_UART0_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART0_RTS_PIN
-#  define CONFIG_UART0_RTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_CTS_PIN
-#  define CONFIG_UART1_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_RTS_PIN
-#  define CONFIG_UART1_RTS_PIN -1
-# endif
-#endif
-
-struct bfin_serial_res {
-	unsigned long uart_base_addr;
-	int uart_irq;
-	int uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	unsigned int uart_tx_dma_channel;
-	unsigned int uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	int uart_cts_pin;
-	int uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-#ifdef CONFIG_SERIAL_BFIN_UART0
-	{
-	 0xFFC00400,
-	 IRQ_UART0_RX,
-	 IRQ_UART0_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	 CH_UART0_TX,
-	 CH_UART0_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	 CONFIG_UART0_CTS_PIN,
-	 CONFIG_UART0_RTS_PIN,
-#endif
-	 },
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART1
-	{
-	 0xFFC02000,
-	 IRQ_UART1_RX,
-	 IRQ_UART1_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	 CH_UART1_TX,
-	 CH_UART1_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	 CONFIG_UART1_CTS_PIN,
-	 CONFIG_UART1_RTS_PIN,
-#endif
-	 },
-#endif
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-bf518/include/mach/defBF514.h b/arch/blackfin/mach-bf518/include/mach/defBF514.h
index 98a51c479290..cfab428e577c 100644
--- a/arch/blackfin/mach-bf518/include/mach/defBF514.h
+++ b/arch/blackfin/mach-bf518/include/mach/defBF514.h
@@ -36,13 +36,13 @@
 #define RSI_EMASK                      0xFFC038C4 /* RSI Exception Mask Register */
 #define RSI_CONFIG                     0xFFC038C8 /* RSI Configuration Register */
 #define RSI_RD_WAIT_EN                 0xFFC038CC /* RSI Read Wait Enable Register */
-#define RSI_PID0                       0xFFC03FE0 /* RSI Peripheral ID Register 0 */
-#define RSI_PID1                       0xFFC03FE4 /* RSI Peripheral ID Register 1 */
-#define RSI_PID2                       0xFFC03FE8 /* RSI Peripheral ID Register 2 */
-#define RSI_PID3                       0xFFC03FEC /* RSI Peripheral ID Register 3 */
-#define RSI_PID4                       0xFFC03FF0 /* RSI Peripheral ID Register 4 */
-#define RSI_PID5                       0xFFC03FF4 /* RSI Peripheral ID Register 5 */
-#define RSI_PID6                       0xFFC03FF8 /* RSI Peripheral ID Register 6 */
-#define RSI_PID7                       0xFFC03FFC /* RSI Peripheral ID Register 7 */
+#define RSI_PID0                       0xFFC038D0 /* RSI Peripheral ID Register 0 */
+#define RSI_PID1                       0xFFC038D4 /* RSI Peripheral ID Register 1 */
+#define RSI_PID2                       0xFFC038D8 /* RSI Peripheral ID Register 2 */
+#define RSI_PID3                       0xFFC038DC /* RSI Peripheral ID Register 3 */
+#define RSI_PID4                       0xFFC038E0 /* RSI Peripheral ID Register 0 */
+#define RSI_PID5                       0xFFC038E4 /* RSI Peripheral ID Register 1 */
+#define RSI_PID6                       0xFFC038E8 /* RSI Peripheral ID Register 2 */
+#define RSI_PID7                       0xFFC038EC /* RSI Peripheral ID Register 3 */
 
 #endif /* _DEF_BF514_H */
diff --git a/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index 960e08919def..000000000000
--- a/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * Copyright 2007-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS)
-# define CONFIG_SERIAL_BFIN_CTSRTS
-
-# ifndef CONFIG_UART0_CTS_PIN
-#  define CONFIG_UART0_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART0_RTS_PIN
-#  define CONFIG_UART0_RTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_CTS_PIN
-#  define CONFIG_UART1_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_RTS_PIN
-#  define CONFIG_UART1_RTS_PIN -1
-# endif
-#endif
-
-struct bfin_serial_res {
-	unsigned long uart_base_addr;
-	int uart_irq;
-	int uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	unsigned int uart_tx_dma_channel;
-	unsigned int uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	int uart_cts_pin;
-	int uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-#ifdef CONFIG_SERIAL_BFIN_UART0
-	{
-	 0xFFC00400,
-	 IRQ_UART0_RX,
-	 IRQ_UART0_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	 CH_UART0_TX,
-	 CH_UART0_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	 CONFIG_UART0_CTS_PIN,
-	 CONFIG_UART0_RTS_PIN,
-#endif
-	 },
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART1
-	{
-	 0xFFC02000,
-	 IRQ_UART1_RX,
-	 IRQ_UART1_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	 CH_UART1_TX,
-	 CH_UART1_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	 CONFIG_UART1_CTS_PIN,
-	 CONFIG_UART1_RTS_PIN,
-#endif
-	 },
-#endif
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-bf527/include/mach/defBF525.h b/arch/blackfin/mach-bf527/include/mach/defBF525.h
index cc383adfdffa..aab80bb1a683 100644
--- a/arch/blackfin/mach-bf527/include/mach/defBF525.h
+++ b/arch/blackfin/mach-bf527/include/mach/defBF525.h
@@ -185,8 +185,8 @@
 #define                USB_EP_NI7_TXTYPE  0xffc03bd4   /* Sets the transaction protocol and peripheral endpoint number for the Host Tx endpoint7 */
 #define            USB_EP_NI7_TXINTERVAL  0xffc03bd8   /* Sets the NAK response timeout on Endpoint7 */
 #define                USB_EP_NI7_RXTYPE  0xffc03bdc   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint7 */
-#define            USB_EP_NI7_RXINTERVAL  0xffc03bf0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint7 */
-#define               USB_EP_NI7_TXCOUNT  0xffc03bf8   /* Number of bytes to be written to the endpoint7 Tx FIFO */
+#define            USB_EP_NI7_RXINTERVAL  0xffc03be0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint7 */
+#define               USB_EP_NI7_TXCOUNT  0xffc03be8   /* Number of bytes to be written to the endpoint7 Tx FIFO */
 
 #define                USB_DMA_INTERRUPT  0xffc03c00   /* Indicates pending interrupts for the DMA channels */
 
diff --git a/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index 45dcaa4f3e41..000000000000
--- a/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * Copyright 2006-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#ifdef CONFIG_BFIN_UART0_CTSRTS
-# define CONFIG_SERIAL_BFIN_CTSRTS
-# ifndef CONFIG_UART0_CTS_PIN
-#  define CONFIG_UART0_CTS_PIN -1
-# endif
-# ifndef CONFIG_UART0_RTS_PIN
-#  define CONFIG_UART0_RTS_PIN -1
-# endif
-#endif
-
-struct bfin_serial_res {
-	unsigned long	uart_base_addr;
-	int		uart_irq;
-	int		uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	unsigned int	uart_tx_dma_channel;
-	unsigned int	uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	int		uart_cts_pin;
-	int		uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-	{
-	0xFFC00400,
-	IRQ_UART0_RX,
-	IRQ_UART0_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	CH_UART0_TX,
-	CH_UART0_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	CONFIG_UART0_CTS_PIN,
-	CONFIG_UART0_RTS_PIN,
-#endif
-	}
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-bf537/boards/stamp.c b/arch/blackfin/mach-bf537/boards/stamp.c
index e16dc4560048..76db1d483173 100644
--- a/arch/blackfin/mach-bf537/boards/stamp.c
+++ b/arch/blackfin/mach-bf537/boards/stamp.c
@@ -382,7 +382,6 @@ static struct platform_device net2272_bfin_device = {
 #endif
 
 #if defined(CONFIG_MTD_NAND_PLATFORM) || defined(CONFIG_MTD_NAND_PLATFORM_MODULE)
-#ifdef CONFIG_MTD_PARTITIONS
 const char *part_probes[] = { "cmdlinepart", "RedBoot", NULL };
 
 static struct mtd_partition bfin_plat_nand_partitions[] = {
@@ -396,7 +395,6 @@ static struct mtd_partition bfin_plat_nand_partitions[] = {
 		.offset = MTDPART_OFS_APPEND,
 	},
 };
-#endif
 
 #define BFIN_NAND_PLAT_CLE 2
 #define BFIN_NAND_PLAT_ALE 1
@@ -423,11 +421,9 @@ static struct platform_nand_data bfin_plat_nand_data = {
 	.chip = {
 		.nr_chips = 1,
 		.chip_delay = 30,
-#ifdef CONFIG_MTD_PARTITIONS
 		.part_probe_types = part_probes,
 		.partitions = bfin_plat_nand_partitions,
 		.nr_partitions = ARRAY_SIZE(bfin_plat_nand_partitions),
-#endif
 	},
 	.ctrl = {
 		.cmd_ctrl  = bfin_plat_nand_cmd_ctrl,
diff --git a/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index 3e955dba8951..000000000000
--- a/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * Copyright 2006-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS)
-# define CONFIG_SERIAL_BFIN_CTSRTS
-
-# ifndef CONFIG_UART0_CTS_PIN
-#  define CONFIG_UART0_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART0_RTS_PIN
-#  define CONFIG_UART0_RTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_CTS_PIN
-#  define CONFIG_UART1_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_RTS_PIN
-#  define CONFIG_UART1_RTS_PIN -1
-# endif
-#endif
-
-struct bfin_serial_res {
-	unsigned long	uart_base_addr;
-	int		uart_irq;
-	int		uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	unsigned int	uart_tx_dma_channel;
-	unsigned int	uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	int	uart_cts_pin;
-	int	uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-#ifdef CONFIG_SERIAL_BFIN_UART0
-	{
-	0xFFC00400,
-	IRQ_UART0_RX,
-	IRQ_UART0_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	CH_UART0_TX,
-	CH_UART0_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	CONFIG_UART0_CTS_PIN,
-	CONFIG_UART0_RTS_PIN,
-#endif
-	},
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART1
-	{
-	0xFFC02000,
-	IRQ_UART1_RX,
-	IRQ_UART1_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	CH_UART1_TX,
-	CH_UART1_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	CONFIG_UART1_CTS_PIN,
-	CONFIG_UART1_RTS_PIN,
-#endif
-	},
-#endif
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index beb502e9cb33..000000000000
--- a/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,93 +0,0 @@
-/*
- * Copyright 2008-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later.
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS)
-# define CONFIG_SERIAL_BFIN_CTSRTS
-
-# ifndef CONFIG_UART0_CTS_PIN
-#  define CONFIG_UART0_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART0_RTS_PIN
-#  define CONFIG_UART0_RTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_CTS_PIN
-#  define CONFIG_UART1_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_RTS_PIN
-#  define CONFIG_UART1_RTS_PIN -1
-# endif
-#endif
-
-struct bfin_serial_res {
-	unsigned long	uart_base_addr;
-	int		uart_irq;
-	int		uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	unsigned int	uart_tx_dma_channel;
-	unsigned int	uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	int	uart_cts_pin;
-	int	uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-#ifdef CONFIG_SERIAL_BFIN_UART0
-	{
-	0xFFC00400,
-	IRQ_UART0_RX,
-	IRQ_UART0_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	CH_UART0_TX,
-	CH_UART0_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	CONFIG_UART0_CTS_PIN,
-	CONFIG_UART0_RTS_PIN,
-#endif
-	},
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART1
-	{
-	0xFFC02000,
-	IRQ_UART1_RX,
-	IRQ_UART1_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	CH_UART1_TX,
-	CH_UART1_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	CONFIG_UART1_CTS_PIN,
-	CONFIG_UART1_RTS_PIN,
-#endif
-	},
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART2
-	{
-	0xFFC02100,
-	IRQ_UART2_RX,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	CH_UART2_TX,
-	CH_UART2_RX,
-#endif
-#ifdef CONFIG_BFIN_UART2_CTSRTS
-	CONFIG_UART2_CTS_PIN,
-	CONFIG_UART2_RTS_PIN,
-#endif
-	},
-#endif
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index 0d94edaaaa2e..000000000000
--- a/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * Copyright 2007-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later.
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS) || \
-	defined(CONFIG_BFIN_UART2_CTSRTS) || defined(CONFIG_BFIN_UART3_CTSRTS)
-# define CONFIG_SERIAL_BFIN_HARD_CTSRTS
-#endif
-
-struct bfin_serial_res {
-	unsigned long	uart_base_addr;
-	int		uart_irq;
-	int		uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	unsigned int	uart_tx_dma_channel;
-	unsigned int	uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_HARD_CTSRTS
-	int		uart_cts_pin;
-	int		uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-#ifdef CONFIG_SERIAL_BFIN_UART0
-	{
-	0xFFC00400,
-	IRQ_UART0_RX,
-	IRQ_UART0_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	CH_UART0_TX,
-	CH_UART0_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_HARD_CTSRTS
-	0,
-	0,
-#endif
-	},
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART1
-	{
-	0xFFC02000,
-	IRQ_UART1_RX,
-	IRQ_UART1_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	CH_UART1_TX,
-	CH_UART1_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_HARD_CTSRTS
-	GPIO_PE10,
-	GPIO_PE9,
-#endif
-	},
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART2
-	{
-	0xFFC02100,
-	IRQ_UART2_RX,
-	IRQ_UART2_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	CH_UART2_TX,
-	CH_UART2_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_HARD_CTSRTS
-	0,
-	0,
-#endif
-	},
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART3
-	{
-	0xFFC03100,
-	IRQ_UART3_RX,
-	IRQ_UART3_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	CH_UART3_TX,
-	CH_UART3_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_HARD_CTSRTS
-	GPIO_PB3,
-	GPIO_PB2,
-#endif
-	},
-#endif
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-bf548/include/mach/defBF547.h b/arch/blackfin/mach-bf548/include/mach/defBF547.h
index 1cbba115f96f..1fa41ec03f31 100644
--- a/arch/blackfin/mach-bf548/include/mach/defBF547.h
+++ b/arch/blackfin/mach-bf548/include/mach/defBF547.h
@@ -271,10 +271,10 @@
 #define            USB_EP_NI0_TXINTERVAL  0xffc03e18   /* Sets the NAK response timeout on Endpoint 0 */
 #define                USB_EP_NI0_RXTYPE  0xffc03e1c   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint0 */
 #define            USB_EP_NI0_RXINTERVAL  0xffc03e20   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint0 */
+#define               USB_EP_NI0_TXCOUNT  0xffc03e28   /* Number of bytes to be written to the endpoint0 Tx FIFO */
 
 /* USB Endpoint 1 Control Registers */
 
-#define               USB_EP_NI0_TXCOUNT  0xffc03e28   /* Number of bytes to be written to the endpoint0 Tx FIFO */
 #define                USB_EP_NI1_TXMAXP  0xffc03e40   /* Maximum packet size for Host Tx endpoint1 */
 #define                 USB_EP_NI1_TXCSR  0xffc03e44   /* Control Status register for endpoint1 */
 #define                USB_EP_NI1_RXMAXP  0xffc03e48   /* Maximum packet size for Host Rx endpoint1 */
@@ -284,10 +284,10 @@
 #define            USB_EP_NI1_TXINTERVAL  0xffc03e58   /* Sets the NAK response timeout on Endpoint1 */
 #define                USB_EP_NI1_RXTYPE  0xffc03e5c   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint1 */
 #define            USB_EP_NI1_RXINTERVAL  0xffc03e60   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint1 */
+#define               USB_EP_NI1_TXCOUNT  0xffc03e68   /* Number of bytes to be written to the+H102 endpoint1 Tx FIFO */
 
 /* USB Endpoint 2 Control Registers */
 
-#define               USB_EP_NI1_TXCOUNT  0xffc03e68   /* Number of bytes to be written to the+H102 endpoint1 Tx FIFO */
 #define                USB_EP_NI2_TXMAXP  0xffc03e80   /* Maximum packet size for Host Tx endpoint2 */
 #define                 USB_EP_NI2_TXCSR  0xffc03e84   /* Control Status register for endpoint2 */
 #define                USB_EP_NI2_RXMAXP  0xffc03e88   /* Maximum packet size for Host Rx endpoint2 */
@@ -297,10 +297,10 @@
 #define            USB_EP_NI2_TXINTERVAL  0xffc03e98   /* Sets the NAK response timeout on Endpoint2 */
 #define                USB_EP_NI2_RXTYPE  0xffc03e9c   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint2 */
 #define            USB_EP_NI2_RXINTERVAL  0xffc03ea0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint2 */
+#define               USB_EP_NI2_TXCOUNT  0xffc03ea8   /* Number of bytes to be written to the endpoint2 Tx FIFO */
 
 /* USB Endpoint 3 Control Registers */
 
-#define               USB_EP_NI2_TXCOUNT  0xffc03ea8   /* Number of bytes to be written to the endpoint2 Tx FIFO */
 #define                USB_EP_NI3_TXMAXP  0xffc03ec0   /* Maximum packet size for Host Tx endpoint3 */
 #define                 USB_EP_NI3_TXCSR  0xffc03ec4   /* Control Status register for endpoint3 */
 #define                USB_EP_NI3_RXMAXP  0xffc03ec8   /* Maximum packet size for Host Rx endpoint3 */
@@ -310,10 +310,10 @@
 #define            USB_EP_NI3_TXINTERVAL  0xffc03ed8   /* Sets the NAK response timeout on Endpoint3 */
 #define                USB_EP_NI3_RXTYPE  0xffc03edc   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint3 */
 #define            USB_EP_NI3_RXINTERVAL  0xffc03ee0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint3 */
+#define               USB_EP_NI3_TXCOUNT  0xffc03ee8   /* Number of bytes to be written to the H124endpoint3 Tx FIFO */
 
 /* USB Endpoint 4 Control Registers */
 
-#define               USB_EP_NI3_TXCOUNT  0xffc03ee8   /* Number of bytes to be written to the H124endpoint3 Tx FIFO */
 #define                USB_EP_NI4_TXMAXP  0xffc03f00   /* Maximum packet size for Host Tx endpoint4 */
 #define                 USB_EP_NI4_TXCSR  0xffc03f04   /* Control Status register for endpoint4 */
 #define                USB_EP_NI4_RXMAXP  0xffc03f08   /* Maximum packet size for Host Rx endpoint4 */
@@ -323,10 +323,10 @@
 #define            USB_EP_NI4_TXINTERVAL  0xffc03f18   /* Sets the NAK response timeout on Endpoint4 */
 #define                USB_EP_NI4_RXTYPE  0xffc03f1c   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint4 */
 #define            USB_EP_NI4_RXINTERVAL  0xffc03f20   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint4 */
+#define               USB_EP_NI4_TXCOUNT  0xffc03f28   /* Number of bytes to be written to the endpoint4 Tx FIFO */
 
 /* USB Endpoint 5 Control Registers */
 
-#define               USB_EP_NI4_TXCOUNT  0xffc03f28   /* Number of bytes to be written to the endpoint4 Tx FIFO */
 #define                USB_EP_NI5_TXMAXP  0xffc03f40   /* Maximum packet size for Host Tx endpoint5 */
 #define                 USB_EP_NI5_TXCSR  0xffc03f44   /* Control Status register for endpoint5 */
 #define                USB_EP_NI5_RXMAXP  0xffc03f48   /* Maximum packet size for Host Rx endpoint5 */
@@ -336,10 +336,10 @@
 #define            USB_EP_NI5_TXINTERVAL  0xffc03f58   /* Sets the NAK response timeout on Endpoint5 */
 #define                USB_EP_NI5_RXTYPE  0xffc03f5c   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint5 */
 #define            USB_EP_NI5_RXINTERVAL  0xffc03f60   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint5 */
+#define               USB_EP_NI5_TXCOUNT  0xffc03f68   /* Number of bytes to be written to the H145endpoint5 Tx FIFO */
 
 /* USB Endpoint 6 Control Registers */
 
-#define               USB_EP_NI5_TXCOUNT  0xffc03f68   /* Number of bytes to be written to the H145endpoint5 Tx FIFO */
 #define                USB_EP_NI6_TXMAXP  0xffc03f80   /* Maximum packet size for Host Tx endpoint6 */
 #define                 USB_EP_NI6_TXCSR  0xffc03f84   /* Control Status register for endpoint6 */
 #define                USB_EP_NI6_RXMAXP  0xffc03f88   /* Maximum packet size for Host Rx endpoint6 */
@@ -349,10 +349,10 @@
 #define            USB_EP_NI6_TXINTERVAL  0xffc03f98   /* Sets the NAK response timeout on Endpoint6 */
 #define                USB_EP_NI6_RXTYPE  0xffc03f9c   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint6 */
 #define            USB_EP_NI6_RXINTERVAL  0xffc03fa0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint6 */
+#define               USB_EP_NI6_TXCOUNT  0xffc03fa8   /* Number of bytes to be written to the endpoint6 Tx FIFO */
 
 /* USB Endpoint 7 Control Registers */
 
-#define               USB_EP_NI6_TXCOUNT  0xffc03fa8   /* Number of bytes to be written to the endpoint6 Tx FIFO */
 #define                USB_EP_NI7_TXMAXP  0xffc03fc0   /* Maximum packet size for Host Tx endpoint7 */
 #define                 USB_EP_NI7_TXCSR  0xffc03fc4   /* Control Status register for endpoint7 */
 #define                USB_EP_NI7_RXMAXP  0xffc03fc8   /* Maximum packet size for Host Rx endpoint7 */
@@ -361,8 +361,9 @@
 #define                USB_EP_NI7_TXTYPE  0xffc03fd4   /* Sets the transaction protocol and peripheral endpoint number for the Host Tx endpoint7 */
 #define            USB_EP_NI7_TXINTERVAL  0xffc03fd8   /* Sets the NAK response timeout on Endpoint7 */
 #define                USB_EP_NI7_RXTYPE  0xffc03fdc   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint7 */
-#define            USB_EP_NI7_RXINTERVAL  0xffc03ff0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint7 */
-#define               USB_EP_NI7_TXCOUNT  0xffc03ff8   /* Number of bytes to be written to the endpoint7 Tx FIFO */
+#define            USB_EP_NI7_RXINTERVAL  0xffc03fe0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint7 */
+#define               USB_EP_NI7_TXCOUNT  0xffc03fe8   /* Number of bytes to be written to the endpoint7 Tx FIFO */
+
 #define                USB_DMA_INTERRUPT  0xffc04000   /* Indicates pending interrupts for the DMA channels */
 
 /* USB Channel 0 Config Registers */
diff --git a/arch/blackfin/mach-bf561/boards/acvilon.c b/arch/blackfin/mach-bf561/boards/acvilon.c
index 3926cd909b66..9231a942892b 100644
--- a/arch/blackfin/mach-bf561/boards/acvilon.c
+++ b/arch/blackfin/mach-bf561/boards/acvilon.c
@@ -243,7 +243,6 @@ static struct platform_device bfin_uart0_device = {
 
 #if defined(CONFIG_MTD_NAND_PLATFORM) || defined(CONFIG_MTD_NAND_PLATFORM_MODULE)
 
-#ifdef CONFIG_MTD_PARTITIONS
 const char *part_probes[] = { "cmdlinepart", NULL };
 
 static struct mtd_partition bfin_plat_nand_partitions[] = {
@@ -257,7 +256,6 @@ static struct mtd_partition bfin_plat_nand_partitions[] = {
 	     .offset = MTDPART_OFS_APPEND,
 	     },
 };
-#endif
 
 #define BFIN_NAND_PLAT_CLE 2
 #define BFIN_NAND_PLAT_ALE 3
@@ -286,11 +284,9 @@ static struct platform_nand_data bfin_plat_nand_data = {
 	.chip = {
 		 .nr_chips = 1,
 		 .chip_delay = 30,
-#ifdef CONFIG_MTD_PARTITIONS
 		 .part_probe_types = part_probes,
 		 .partitions = bfin_plat_nand_partitions,
 		 .nr_partitions = ARRAY_SIZE(bfin_plat_nand_partitions),
-#endif
 		 },
 	.ctrl = {
 		 .cmd_ctrl = bfin_plat_nand_cmd_ctrl,
diff --git a/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index 3a6947456cf1..000000000000
--- a/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * Copyright 2006-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later.
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#ifdef CONFIG_BFIN_UART0_CTSRTS
-# define CONFIG_SERIAL_BFIN_CTSRTS
-# ifndef CONFIG_UART0_CTS_PIN
-#  define CONFIG_UART0_CTS_PIN -1
-# endif
-# ifndef CONFIG_UART0_RTS_PIN
-#  define CONFIG_UART0_RTS_PIN -1
-# endif
-#endif
-
-struct bfin_serial_res {
-	unsigned long	uart_base_addr;
-	int		uart_irq;
-	int		uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	unsigned int	uart_tx_dma_channel;
-	unsigned int	uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	int		uart_cts_pin;
-	int		uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-	{
-	0xFFC00400,
-	IRQ_UART_RX,
-	IRQ_UART_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-	CH_UART_TX,
-	CH_UART_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	CONFIG_UART0_CTS_PIN,
-	CONFIG_UART0_RTS_PIN,
-#endif
-	}
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S
index f96933f48a7f..225d311c9701 100644
--- a/arch/blackfin/mach-common/entry.S
+++ b/arch/blackfin/mach-common/entry.S
@@ -1753,6 +1753,8 @@ ENTRY(_sys_call_table)
 	.long _sys_open_by_handle_at
 	.long _sys_clock_adjtime
 	.long _sys_syncfs
+	.long _sys_setns
+	.long _sys_sendmmsg		/* 380 */
 
 	.rept NR_syscalls-(.-_sys_call_table)/4
 	.long _sys_ni_syscall
diff --git a/arch/blackfin/mm/maccess.c b/arch/blackfin/mm/maccess.c
index b71cebc1f8a3..e2532114c5fd 100644
--- a/arch/blackfin/mm/maccess.c
+++ b/arch/blackfin/mm/maccess.c
@@ -16,7 +16,7 @@ static int validate_memory_access_address(unsigned long addr, int size)
 	return bfin_mem_access_type(addr, size);
 }
 
-long probe_kernel_read(void *dst, void *src, size_t size)
+long probe_kernel_read(void *dst, const void *src, size_t size)
 {
 	unsigned long lsrc = (unsigned long)src;
 	int mem_type;
@@ -55,7 +55,7 @@ long probe_kernel_read(void *dst, void *src, size_t size)
 	return -EFAULT;
 }
 
-long probe_kernel_write(void *dst, void *src, size_t size)
+long probe_kernel_write(void *dst, const void *src, size_t size)
 {
 	unsigned long ldst = (unsigned long)dst;
 	int mem_type;
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index b6b94a27d276..17addacb169e 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -270,7 +270,6 @@ config ETRAX_AXISFLASHMAP
 	select MTD_JEDECPROBE if ETRAX_ARCH_V32
 	select MTD_CHAR
 	select MTD_BLOCK
-	select MTD_PARTITIONS
 	select MTD_COMPLEX_MAPPINGS
 	help
 	  This option enables MTD mapping of flash devices.  Needed to use
diff --git a/arch/cris/arch-v10/drivers/axisflashmap.c b/arch/cris/arch-v10/drivers/axisflashmap.c
index ed708e19d09e..a4bbdfd37bd8 100644
--- a/arch/cris/arch-v10/drivers/axisflashmap.c
+++ b/arch/cris/arch-v10/drivers/axisflashmap.c
@@ -372,7 +372,7 @@ static int __init init_axis_flash(void)
 #ifdef CONFIG_ETRAX_AXISFLASHMAP_MTD0WHOLE
 	if (mymtd) {
 		main_partition.size = mymtd->size;
-		err = add_mtd_partitions(mymtd, &main_partition, 1);
+		err = mtd_device_register(mymtd, &main_partition, 1);
 		if (err)
 			panic("axisflashmap: Could not initialize "
 			      "partition for whole main mtd device!\n");
@@ -382,10 +382,12 @@ static int __init init_axis_flash(void)
         if (mymtd) {
 		if (use_default_ptable) {
 			printk(KERN_INFO " Using default partition table.\n");
-			err = add_mtd_partitions(mymtd, axis_default_partitions,
-						 NUM_DEFAULT_PARTITIONS);
+			err = mtd_device_register(mymtd,
+						  axis_default_partitions,
+						  NUM_DEFAULT_PARTITIONS);
 		} else {
-			err = add_mtd_partitions(mymtd, axis_partitions, pidx);
+			err = mtd_device_register(mymtd, axis_partitions,
+						  pidx);
 		}
 
 		if (err)
diff --git a/arch/cris/arch-v10/kernel/entry.S b/arch/cris/arch-v10/kernel/entry.S
index 0d6420d087fd..1161883eb582 100644
--- a/arch/cris/arch-v10/kernel/entry.S
+++ b/arch/cris/arch-v10/kernel/entry.S
@@ -937,6 +937,7 @@ sys_call_table:
 	.long sys_inotify_init1
 	.long sys_preadv
 	.long sys_pwritev
+	.long sys_setns			/* 335 */
 
         /*
          * NOTE!! This doesn't have to be exact - we just have
diff --git a/arch/cris/arch-v32/drivers/Kconfig b/arch/cris/arch-v32/drivers/Kconfig
index 1633b120aa81..41a2732e8b9c 100644
--- a/arch/cris/arch-v32/drivers/Kconfig
+++ b/arch/cris/arch-v32/drivers/Kconfig
@@ -405,7 +405,6 @@ config ETRAX_AXISFLASHMAP
 	select MTD_JEDECPROBE
 	select MTD_CHAR
 	select MTD_BLOCK
-	select MTD_PARTITIONS
 	select MTD_COMPLEX_MAPPINGS
 	help
 	  This option enables MTD mapping of flash devices.  Needed to use
diff --git a/arch/cris/arch-v32/drivers/axisflashmap.c b/arch/cris/arch-v32/drivers/axisflashmap.c
index 7b155f8203b8..a2bde3744622 100644
--- a/arch/cris/arch-v32/drivers/axisflashmap.c
+++ b/arch/cris/arch-v32/drivers/axisflashmap.c
@@ -561,7 +561,7 @@ static int __init init_axis_flash(void)
 #ifdef CONFIG_ETRAX_AXISFLASHMAP_MTD0WHOLE
 	if (main_mtd) {
 		main_partition.size = main_mtd->size;
-		err = add_mtd_partitions(main_mtd, &main_partition, 1);
+		err = mtd_device_register(main_mtd, &main_partition, 1);
 		if (err)
 			panic("axisflashmap: Could not initialize "
 			      "partition for whole main mtd device!\n");
@@ -597,7 +597,8 @@ static int __init init_axis_flash(void)
 			mtd_ram->erasesize = (main_mtd ? main_mtd->erasesize :
 				CONFIG_ETRAX_PTABLE_SECTOR);
 		} else {
-			err = add_mtd_partitions(main_mtd, &partition[part], 1);
+			err = mtd_device_register(main_mtd, &partition[part],
+						  1);
 			if (err)
 				panic("axisflashmap: Could not add mtd "
 					"partition %d\n", part);
@@ -633,7 +634,7 @@ static int __init init_axis_flash(void)
 #ifndef CONFIG_ETRAX_VCS_SIM
 	if (aux_mtd) {
 		aux_partition.size = aux_mtd->size;
-		err = add_mtd_partitions(aux_mtd, &aux_partition, 1);
+		err = mtd_device_register(aux_mtd, &aux_partition, 1);
 		if (err)
 			panic("axisflashmap: Could not initialize "
 			      "aux mtd device!\n");
diff --git a/arch/cris/arch-v32/kernel/entry.S b/arch/cris/arch-v32/kernel/entry.S
index 3abf12c23e5f..84fed7e91ada 100644
--- a/arch/cris/arch-v32/kernel/entry.S
+++ b/arch/cris/arch-v32/kernel/entry.S
@@ -880,6 +880,7 @@ sys_call_table:
 	.long sys_inotify_init1
 	.long sys_preadv
 	.long sys_pwritev
+	.long sys_setns			/* 335 */
 
         /*
          * NOTE!! This doesn't have to be exact - we just have
diff --git a/arch/cris/include/asm/unistd.h b/arch/cris/include/asm/unistd.h
index f6fad83b3a8c..f921b8b0f97e 100644
--- a/arch/cris/include/asm/unistd.h
+++ b/arch/cris/include/asm/unistd.h
@@ -339,10 +339,11 @@
 #define __NR_inotify_init1	332
 #define __NR_preadv		333
 #define __NR_pwritev		334
+#define __NR_setns		335
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 335
+#define NR_syscalls 336
 
 #include <arch/unistd.h>
 
diff --git a/arch/frv/include/asm/suspend.h b/arch/frv/include/asm/suspend.h
deleted file mode 100644
index 5fa7b5a6ee40..000000000000
--- a/arch/frv/include/asm/suspend.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* suspend.h: suspension stuff
- *
- * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@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 the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#ifndef _ASM_SUSPEND_H
-#define _ASM_SUSPEND_H
-
-static inline int arch_prepare_suspend(void)
-{
-	return 0;
-}
-
-#endif /* _ASM_SUSPEND_H */
diff --git a/arch/frv/include/asm/unistd.h b/arch/frv/include/asm/unistd.h
index b28da499e22a..a569dff7cd59 100644
--- a/arch/frv/include/asm/unistd.h
+++ b/arch/frv/include/asm/unistd.h
@@ -343,10 +343,11 @@
 #define __NR_pwritev		334
 #define __NR_rt_tgsigqueueinfo	335
 #define __NR_perf_event_open	336
+#define __NR_setns		337
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 337
+#define NR_syscalls 338
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 /* #define __ARCH_WANT_OLD_READDIR */
diff --git a/arch/frv/kernel/entry.S b/arch/frv/kernel/entry.S
index 63d579bf1c29..017d6d7b784f 100644
--- a/arch/frv/kernel/entry.S
+++ b/arch/frv/kernel/entry.S
@@ -1526,5 +1526,6 @@ sys_call_table:
 	.long sys_pwritev
 	.long sys_rt_tgsigqueueinfo	/* 335 */
 	.long sys_perf_event_open
+	.long sys_setns
 
 syscall_table_size = (. - sys_call_table)
diff --git a/arch/h8300/include/asm/unistd.h b/arch/h8300/include/asm/unistd.h
index 50f2c5a36591..2c3f8e60b1e0 100644
--- a/arch/h8300/include/asm/unistd.h
+++ b/arch/h8300/include/asm/unistd.h
@@ -325,10 +325,11 @@
 #define __NR_move_pages		317
 #define __NR_getcpu		318
 #define __NR_epoll_pwait	319
+#define __NR_setns		320
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 320
+#define NR_syscalls 321
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/h8300/kernel/syscalls.S b/arch/h8300/kernel/syscalls.S
index faefaff7d43d..f4b2e67bcc34 100644
--- a/arch/h8300/kernel/syscalls.S
+++ b/arch/h8300/kernel/syscalls.S
@@ -333,6 +333,7 @@ SYMBOL_NAME_LABEL(sys_call_table)
 	.long SYMBOL_NAME(sys_ni_syscall)	/* sys_move_pages */
 	.long SYMBOL_NAME(sys_getcpu)
 	.long SYMBOL_NAME(sys_ni_syscall)	/* sys_epoll_pwait */
+	.long SYMBOL_NAME(sys_setns)		/* 320 */
 
 	.macro	call_sp addr
 	mov.l	#SYMBOL_NAME(\addr),er6
diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h
index 404d037c5e10..7c928da35b17 100644
--- a/arch/ia64/include/asm/unistd.h
+++ b/arch/ia64/include/asm/unistd.h
@@ -319,11 +319,13 @@
 #define __NR_open_by_handle_at  	1327
 #define __NR_clock_adjtime		1328
 #define __NR_syncfs			1329
+#define __NR_setns			1330
+#define __NR_sendmmsg			1331
 
 #ifdef __KERNEL__
 
 
-#define NR_syscalls			306 /* length of syscall table */
+#define NR_syscalls			308 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 6de2e23b3636..97dd2abdeb1a 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1775,6 +1775,8 @@ sys_call_table:
 	data8 sys_open_by_handle_at
 	data8 sys_clock_adjtime
 	data8 sys_syncfs
+	data8 sys_setns				// 1330
+	data8 sys_sendmmsg
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
 #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
diff --git a/arch/m32r/include/asm/mmzone.h b/arch/m32r/include/asm/mmzone.h
index 9f3b5accda88..115ced33febd 100644
--- a/arch/m32r/include/asm/mmzone.h
+++ b/arch/m32r/include/asm/mmzone.h
@@ -14,12 +14,6 @@ extern struct pglist_data *node_data[];
 #define NODE_DATA(nid)		(node_data[nid])
 
 #define node_localnr(pfn, nid)	((pfn) - NODE_DATA(nid)->node_start_pfn)
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)						\
-({									\
-	pg_data_t *__pgdat = NODE_DATA(nid);				\
-	__pgdat->node_start_pfn + __pgdat->node_spanned_pages - 1;	\
-})
 
 #define pmd_page(pmd)		(pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
 /*
@@ -44,7 +38,7 @@ static __inline__ int pfn_to_nid(unsigned long pfn)
 	int node;
 
 	for (node = 0 ; node < MAX_NUMNODES ; node++)
-		if (pfn >= node_start_pfn(node) && pfn <= node_end_pfn(node))
+		if (pfn >= node_start_pfn(node) && pfn < node_end_pfn(node))
 			break;
 
 	return node;
diff --git a/arch/m32r/include/asm/unistd.h b/arch/m32r/include/asm/unistd.h
index c70545689da8..3e1db561aacc 100644
--- a/arch/m32r/include/asm/unistd.h
+++ b/arch/m32r/include/asm/unistd.h
@@ -330,10 +330,11 @@
 /* #define __NR_timerfd		322 removed */
 #define __NR_eventfd		323
 #define __NR_fallocate		324
+#define __NR_setns		325
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 325
+#define NR_syscalls 326
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_STAT64
diff --git a/arch/m32r/kernel/syscall_table.S b/arch/m32r/kernel/syscall_table.S
index 60536e271233..528f2e6ad064 100644
--- a/arch/m32r/kernel/syscall_table.S
+++ b/arch/m32r/kernel/syscall_table.S
@@ -324,3 +324,4 @@ ENTRY(sys_call_table)
 	.long sys_ni_syscall
 	.long sys_eventfd
 	.long sys_fallocate
+	.long sys_setns			/* 325 */
diff --git a/arch/m68k/Kconfig.nommu b/arch/m68k/Kconfig.nommu
index fc98f9b9d4d2..b004dc1b1710 100644
--- a/arch/m68k/Kconfig.nommu
+++ b/arch/m68k/Kconfig.nommu
@@ -14,6 +14,33 @@ config GENERIC_CLOCKEVENTS
 	bool
 	default n
 
+config M68000
+	bool
+	help
+	  The Freescale (was Motorola) 68000 CPU is the first generation of
+	  the well known M68K family of processors. The CPU core as well as
+	  being available as a stand alone CPU was also used in many
+	  System-On-Chip devices (eg 68328, 68302, etc). It does not contain
+	  a paging MMU.
+
+config MCPU32
+	bool
+	help
+	  The Freescale (was then Motorola) CPU32 is a CPU core that is
+	  based on the 68020 processor. For the most part it is used in
+	  System-On-Chip parts, and does not contain a paging MMU.
+
+config COLDFIRE
+	bool
+	select GENERIC_GPIO
+	select ARCH_REQUIRE_GPIOLIB
+	help
+	  The Freescale ColdFire family of processors is a modern derivitive
+	  of the 68000 processor family. They are mainly targeted at embedded
+	  applications, and are all System-On-Chip (SOC) devices, as opposed
+	  to stand alone CPUs. They implement a subset of the original 68000
+	  processor instruction set.
+
 config COLDFIRE_SW_A7
 	bool
 	default n
@@ -36,26 +63,31 @@ choice
 
 config M68328
 	bool "MC68328"
+	select M68000
 	help
 	  Motorola 68328 processor support.
 
 config M68EZ328
 	bool "MC68EZ328"
+	select M68000
 	help
 	  Motorola 68EX328 processor support.
 
 config M68VZ328
 	bool "MC68VZ328"
+	select M68000
 	help
 	  Motorola 68VZ328 processor support.
 
 config M68360
 	bool "MC68360"
+	select MCPU32
 	help
 	  Motorola 68360 processor support.
 
 config M5206
 	bool "MCF5206"
+	select COLDFIRE
 	select COLDFIRE_SW_A7
 	select HAVE_MBAR
 	help
@@ -63,6 +95,7 @@ config M5206
 
 config M5206e
 	bool "MCF5206e"
+	select COLDFIRE
 	select COLDFIRE_SW_A7
 	select HAVE_MBAR
 	help
@@ -70,6 +103,7 @@ config M5206e
 
 config M520x
 	bool "MCF520x"
+	select COLDFIRE
 	select GENERIC_CLOCKEVENTS
 	select HAVE_CACHE_SPLIT
 	help
@@ -77,6 +111,7 @@ config M520x
 
 config M523x
 	bool "MCF523x"
+	select COLDFIRE
 	select GENERIC_CLOCKEVENTS
 	select HAVE_CACHE_SPLIT
 	select HAVE_IPSBAR
@@ -85,6 +120,7 @@ config M523x
 
 config M5249
 	bool "MCF5249"
+	select COLDFIRE
 	select COLDFIRE_SW_A7
 	select HAVE_MBAR
 	help
@@ -92,6 +128,7 @@ config M5249
 
 config M5271
 	bool "MCF5271"
+	select COLDFIRE
 	select HAVE_CACHE_SPLIT
 	select HAVE_IPSBAR
 	help
@@ -99,6 +136,7 @@ config M5271
 
 config M5272
 	bool "MCF5272"
+	select COLDFIRE
 	select COLDFIRE_SW_A7
 	select HAVE_MBAR
 	help
@@ -106,6 +144,7 @@ config M5272
 
 config M5275
 	bool "MCF5275"
+	select COLDFIRE
 	select HAVE_CACHE_SPLIT
 	select HAVE_IPSBAR
 	help
@@ -113,6 +152,7 @@ config M5275
 
 config M528x
 	bool "MCF528x"
+	select COLDFIRE
 	select GENERIC_CLOCKEVENTS
 	select HAVE_CACHE_SPLIT
 	select HAVE_IPSBAR
@@ -121,6 +161,7 @@ config M528x
 
 config M5307
 	bool "MCF5307"
+	select COLDFIRE
 	select COLDFIRE_SW_A7
 	select HAVE_CACHE_CB
 	select HAVE_MBAR
@@ -129,12 +170,14 @@ config M5307
 
 config M532x
 	bool "MCF532x"
+	select COLDFIRE
 	select HAVE_CACHE_CB
 	help
 	  Freescale (Motorola) ColdFire 532x processor support.
 
 config M5407
 	bool "MCF5407"
+	select COLDFIRE
 	select COLDFIRE_SW_A7
 	select HAVE_CACHE_CB
 	select HAVE_MBAR
@@ -143,6 +186,7 @@ config M5407
 
 config M547x
 	bool "MCF547x"
+	select COLDFIRE
 	select HAVE_CACHE_CB
 	select HAVE_MBAR
 	help
@@ -150,6 +194,7 @@ config M547x
 
 config M548x
 	bool "MCF548x"
+	select COLDFIRE
 	select HAVE_CACHE_CB
 	select HAVE_MBAR
 	help
@@ -168,13 +213,6 @@ config M54xx
 	depends on (M548x || M547x)
 	default y
 
-config COLDFIRE
-	bool
-	depends on (M5206 || M5206e || M520x || M523x || M5249 || M527x || M5272 || M528x || M5307 || M532x || M5407 || M54xx)
-	select GENERIC_GPIO
-	select ARCH_REQUIRE_GPIOLIB
-	default y
-
 config CLOCK_SET
 	bool "Enable setting the CPU clock frequency"
 	default n
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index f3b649de2a1b..43f984e93970 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -349,10 +349,11 @@
 #define __NR_open_by_handle_at	341
 #define __NR_clock_adjtime	342
 #define __NR_syncfs		343
+#define __NR_setns		344
 
 #ifdef __KERNEL__
 
-#define NR_syscalls		344
+#define NR_syscalls		345
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/m68k/kernel/m68k_ksyms.c b/arch/m68k/kernel/m68k_ksyms.c
index 33f82769547c..1b7a14d1a000 100644
--- a/arch/m68k/kernel/m68k_ksyms.c
+++ b/arch/m68k/kernel/m68k_ksyms.c
@@ -14,8 +14,7 @@ EXPORT_SYMBOL(__ashrdi3);
 EXPORT_SYMBOL(__lshrdi3);
 EXPORT_SYMBOL(__muldi3);
 
-#if !defined(__mc68020__) && !defined(__mc68030__) && \
-    !defined(__mc68040__) && !defined(__mc68060__) && !defined(__mcpu32__)
+#if defined(CONFIG_M68000) || defined(CONFIG_COLDFIRE)
 /*
  * Simpler 68k and ColdFire parts also need a few other gcc functions.
  */
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 6f7b09122a00..00d1452f9571 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -364,4 +364,5 @@ ENTRY(sys_call_table)
 	.long sys_open_by_handle_at
 	.long sys_clock_adjtime
 	.long sys_syncfs
+	.long sys_setns
 
diff --git a/arch/m68k/kernel/vmlinux.lds_no.S b/arch/m68k/kernel/vmlinux.lds_no.S
index f4d715cdca0e..7dc4087a9545 100644
--- a/arch/m68k/kernel/vmlinux.lds_no.S
+++ b/arch/m68k/kernel/vmlinux.lds_no.S
@@ -84,52 +84,52 @@ SECTIONS {
 		/* Kernel symbol table: Normal symbols */
 		. = ALIGN(4);
 		__start___ksymtab = .;
-		*(__ksymtab)
+		*(SORT(___ksymtab+*))
 		__stop___ksymtab = .;
 
 		/* Kernel symbol table: GPL-only symbols */
 		__start___ksymtab_gpl = .;
-		*(__ksymtab_gpl)
+		*(SORT(___ksymtab_gpl+*))
 		__stop___ksymtab_gpl = .;
 
 		/* Kernel symbol table: Normal unused symbols */
 		__start___ksymtab_unused = .;
-		*(__ksymtab_unused)
+		*(SORT(___ksymtab_unused+*))
 		__stop___ksymtab_unused = .;
 
 		/* Kernel symbol table: GPL-only unused symbols */
 		__start___ksymtab_unused_gpl = .;
-		*(__ksymtab_unused_gpl)
+		*(SORT(___ksymtab_unused_gpl+*))
 		__stop___ksymtab_unused_gpl = .;
 
 		/* Kernel symbol table: GPL-future symbols */
 		__start___ksymtab_gpl_future = .;
-		*(__ksymtab_gpl_future)
+		*(SORT(___ksymtab_gpl_future+*))
 		__stop___ksymtab_gpl_future = .;
 
 		/* Kernel symbol table: Normal symbols */
 		__start___kcrctab = .;
-		*(__kcrctab)
+		*(SORT(___kcrctab+*))
 		__stop___kcrctab = .;
 
 		/* Kernel symbol table: GPL-only symbols */
 		__start___kcrctab_gpl = .;
-		*(__kcrctab_gpl)
+		*(SORT(___kcrctab_gpl+*))
 		__stop___kcrctab_gpl = .;
 
 		/* Kernel symbol table: Normal unused symbols */
 		__start___kcrctab_unused = .;
-		*(__kcrctab_unused)
+		*(SORT(___kcrctab_unused+*))
 		__stop___kcrctab_unused = .;
 
 		/* Kernel symbol table: GPL-only unused symbols */
 		__start___kcrctab_unused_gpl = .;
-		*(__kcrctab_unused_gpl)
+		*(SORT(___kcrctab_unused_gpl+*))
 		__stop___kcrctab_unused_gpl = .;
 
 		/* Kernel symbol table: GPL-future symbols */
 		__start___kcrctab_gpl_future = .;
-		*(__kcrctab_gpl_future)
+		*(SORT(___kcrctab_gpl_future+*))
 		__stop___kcrctab_gpl_future = .;
 
 		/* Kernel symbol table: strings */
diff --git a/arch/m68k/lib/memcpy.c b/arch/m68k/lib/memcpy.c
index 62182c81e91c..064889316974 100644
--- a/arch/m68k/lib/memcpy.c
+++ b/arch/m68k/lib/memcpy.c
@@ -34,8 +34,10 @@ void *memcpy(void *to, const void *from, size_t n)
 	if (temp) {
 		long *lto = to;
 		const long *lfrom = from;
-#if defined(__mc68020__) || defined(__mc68030__) || \
-    defined(__mc68040__) || defined(__mc68060__) || defined(__mcpu32__)
+#if defined(CONFIG_M68000) || defined(CONFIG_COLDFIRE)
+		for (; temp; temp--)
+			*lto++ = *lfrom++;
+#else
 		asm volatile (
 			"	movel %2,%3\n"
 			"	andw  #7,%3\n"
@@ -56,9 +58,6 @@ void *memcpy(void *to, const void *from, size_t n)
 			"	jpl   4b"
 			: "=a" (lfrom), "=a" (lto), "=d" (temp), "=&d" (temp1)
 			: "0" (lfrom), "1" (lto), "2" (temp));
-#else
-		for (; temp; temp--)
-			*lto++ = *lfrom++;
 #endif
 		to = lto;
 		from = lfrom;
diff --git a/arch/m68k/lib/memset.c b/arch/m68k/lib/memset.c
index f649e6a2e644..8a7639f0a2fe 100644
--- a/arch/m68k/lib/memset.c
+++ b/arch/m68k/lib/memset.c
@@ -32,8 +32,10 @@ void *memset(void *s, int c, size_t count)
 	temp = count >> 2;
 	if (temp) {
 		long *ls = s;
-#if defined(__mc68020__) || defined(__mc68030__) || \
-    defined(__mc68040__) || defined(__mc68060__) || defined(__mcpu32__)
+#if defined(CONFIG_M68000) || defined(CONFIG_COLDFIRE)
+		for (; temp; temp--)
+			*ls++ = c;
+#else
 		size_t temp1;
 		asm volatile (
 			"	movel %1,%2\n"
@@ -55,9 +57,6 @@ void *memset(void *s, int c, size_t count)
 			"	jpl   1b"
 			: "=a" (ls), "=d" (temp), "=&d" (temp1)
 			: "d" (c), "0" (ls), "1" (temp));
-#else
-		for (; temp; temp--)
-			*ls++ = c;
 #endif
 		s = ls;
 	}
diff --git a/arch/m68k/lib/muldi3.c b/arch/m68k/lib/muldi3.c
index 079bafca073e..79e928a525d0 100644
--- a/arch/m68k/lib/muldi3.c
+++ b/arch/m68k/lib/muldi3.c
@@ -19,17 +19,7 @@ along with GNU CC; see the file COPYING.  If not, write to
 the Free Software Foundation, 59 Temple Place - Suite 330,
 Boston, MA 02111-1307, USA.  */
 
-#if defined(__mc68020__) || defined(__mc68030__) || \
-    defined(__mc68040__) || defined(__mc68060__) || defined(__mcpu32__)
-
-#define umul_ppmm(w1, w0, u, v) \
-  __asm__ ("mulu%.l %3,%1:%0"						\
-           : "=d" ((USItype)(w0)),					\
-             "=d" ((USItype)(w1))					\
-           : "%0" ((USItype)(u)),					\
-             "dmi" ((USItype)(v)))
-
-#else
+#if defined(CONFIG_M68000) || defined(CONFIG_COLDFIRE)
 
 #define SI_TYPE_SIZE 32
 #define __BITS4 (SI_TYPE_SIZE / 4)
@@ -61,6 +51,15 @@ Boston, MA 02111-1307, USA.  */
     (w0) = __ll_lowpart (__x1) * __ll_B + __ll_lowpart (__x0);		\
   } while (0)
 
+#else
+
+#define umul_ppmm(w1, w0, u, v) \
+  __asm__ ("mulu%.l %3,%1:%0"						\
+           : "=d" ((USItype)(w0)),					\
+             "=d" ((USItype)(w1))					\
+           : "%0" ((USItype)(u)),					\
+             "dmi" ((USItype)(v)))
+
 #endif
 
 #define __umulsidi3(u, v) \
diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h
index 30edd61a6b8f..7d7092b917ac 100644
--- a/arch/microblaze/include/asm/unistd.h
+++ b/arch/microblaze/include/asm/unistd.h
@@ -390,8 +390,9 @@
 #define __NR_open_by_handle_at	372
 #define __NR_clock_adjtime	373
 #define __NR_syncfs		374
+#define __NR_setns		375
 
-#define __NR_syscalls		375
+#define __NR_syscalls		376
 
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c
index 00ee90f08343..b15cc219b1d9 100644
--- a/arch/microblaze/kernel/prom.c
+++ b/arch/microblaze/kernel/prom.c
@@ -130,7 +130,7 @@ void __init early_init_devtree(void *params)
 	 * device-tree, including the platform type, initrd location and
 	 * size, TCE reserve, and more ...
 	 */
-	of_scan_flat_dt(early_init_dt_scan_chosen, NULL);
+	of_scan_flat_dt(early_init_dt_scan_chosen, cmd_line);
 
 	/* Scan memory nodes and rebuild MEMBLOCKs */
 	memblock_init();
diff --git a/arch/microblaze/kernel/syscall_table.S b/arch/microblaze/kernel/syscall_table.S
index 85cea81d1ca1..d915a122c865 100644
--- a/arch/microblaze/kernel/syscall_table.S
+++ b/arch/microblaze/kernel/syscall_table.S
@@ -379,3 +379,4 @@ ENTRY(sys_call_table)
 	.long sys_open_by_handle_at
 	.long sys_clock_adjtime
 	.long sys_syncfs
+	.long sys_setns			/* 375 */
diff --git a/arch/mips/cavium-octeon/flash_setup.c b/arch/mips/cavium-octeon/flash_setup.c
index 008f657116eb..0ee02f5e51cc 100644
--- a/arch/mips/cavium-octeon/flash_setup.c
+++ b/arch/mips/cavium-octeon/flash_setup.c
@@ -16,7 +16,6 @@
 
 static struct map_info flash_map;
 static struct mtd_info *mymtd;
-#ifdef CONFIG_MTD_PARTITIONS
 static int nr_parts;
 static struct mtd_partition *parts;
 static const char *part_probe_types[] = {
@@ -26,7 +25,6 @@ static const char *part_probe_types[] = {
 #endif
 	NULL
 };
-#endif
 
 /**
  * Module/ driver initialization.
@@ -63,17 +61,10 @@ static int __init flash_init(void)
 		if (mymtd) {
 			mymtd->owner = THIS_MODULE;
 
-#ifdef CONFIG_MTD_PARTITIONS
 			nr_parts = parse_mtd_partitions(mymtd,
 							part_probe_types,
 							&parts, 0);
-			if (nr_parts > 0)
-				add_mtd_partitions(mymtd, parts, nr_parts);
-			else
-				add_mtd_device(mymtd);
-#else
-			add_mtd_device(mymtd);
-#endif
+			mtd_device_register(mymtd, parts, nr_parts);
 		} else {
 			pr_err("Failed to register MTD device for flash\n");
 		}
diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig
index 37862b2ce363..807c97eed8a8 100644
--- a/arch/mips/configs/mtx1_defconfig
+++ b/arch/mips/configs/mtx1_defconfig
@@ -678,7 +678,7 @@ CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_CLASS=y
 CONFIG_RTC_INTF_DEV_UIE_EMUL=y
 CONFIG_RTC_DRV_TEST=m
 CONFIG_RTC_DRV_DS1307=m
diff --git a/arch/mips/include/asm/prom.h b/arch/mips/include/asm/prom.h
index f29b862d9db3..857d9b7858ad 100644
--- a/arch/mips/include/asm/prom.h
+++ b/arch/mips/include/asm/prom.h
@@ -14,9 +14,6 @@
 #ifdef CONFIG_OF
 #include <asm/bootinfo.h>
 
-/* which is compatible with the flattened device tree (FDT) */
-#define cmd_line arcs_cmdline
-
 extern int early_init_dt_scan_memory_arch(unsigned long node,
 	const char *uname, int depth, void *data);
 
diff --git a/arch/mips/include/asm/suspend.h b/arch/mips/include/asm/suspend.h
index 294cdb66c5fc..3adac3b53d19 100644
--- a/arch/mips/include/asm/suspend.h
+++ b/arch/mips/include/asm/suspend.h
@@ -1,8 +1,6 @@
 #ifndef __ASM_SUSPEND_H
 #define __ASM_SUSPEND_H
 
-static inline int arch_prepare_suspend(void) { return 0; }
-
 /* References to section boundaries */
 extern const void __nosave_begin, __nosave_end;
 
diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h
index fa2e37ea2be1..6fcfc480e9d0 100644
--- a/arch/mips/include/asm/unistd.h
+++ b/arch/mips/include/asm/unistd.h
@@ -363,16 +363,17 @@
 #define __NR_open_by_handle_at		(__NR_Linux + 340)
 #define __NR_clock_adjtime		(__NR_Linux + 341)
 #define __NR_syncfs			(__NR_Linux + 342)
+#define __NR_setns			(__NR_Linux + 343)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		342
+#define __NR_Linux_syscalls		343
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		342
+#define __NR_O32_Linux_syscalls		343
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -682,16 +683,17 @@
 #define __NR_open_by_handle_at		(__NR_Linux + 299)
 #define __NR_clock_adjtime		(__NR_Linux + 300)
 #define __NR_syncfs			(__NR_Linux + 301)
+#define __NR_setns			(__NR_Linux + 302)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		301
+#define __NR_Linux_syscalls		302
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		301
+#define __NR_64_Linux_syscalls		302
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1006,16 +1008,17 @@
 #define __NR_open_by_handle_at		(__NR_Linux + 304)
 #define __NR_clock_adjtime		(__NR_Linux + 305)
 #define __NR_syncfs			(__NR_Linux + 306)
+#define __NR_setns			(__NR_Linux + 307)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		306
+#define __NR_Linux_syscalls		307
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		306
+#define __NR_N32_Linux_syscalls		307
 
 #ifdef __KERNEL__
 
diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index a19811e98a41..5b7eade41fa3 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -83,7 +83,8 @@ void __init early_init_devtree(void *params)
 	 * device-tree, including the platform type, initrd location and
 	 * size, and more ...
 	 */
-	of_scan_flat_dt(early_init_dt_scan_chosen, NULL);
+	of_scan_flat_dt(early_init_dt_scan_chosen, arcs_cmdline);
+
 
 	/* Scan memory nodes */
 	of_scan_flat_dt(early_init_dt_scan_root, NULL);
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 7a8e1dd7f6f2..99e656e425f3 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -589,6 +589,7 @@ einval:	li	v0, -ENOSYS
 	sys	sys_open_by_handle_at	3	/* 4340 */
 	sys	sys_clock_adjtime	2
 	sys	sys_syncfs		1
+	sys	sys_setns		2
 	.endm
 
 	/* We pre-compute the number of _instruction_ bytes needed to
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 2d31c83224f9..fb0575f47f3d 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -428,4 +428,5 @@ sys_call_table:
 	PTR	sys_open_by_handle_at
 	PTR	sys_clock_adjtime		/* 5300 */
 	PTR	sys_syncfs
+	PTR	sys_setns
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 38a0503b9a4a..4de0c5534e73 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -428,4 +428,5 @@ EXPORT(sysn32_call_table)
 	PTR	sys_open_by_handle_at
 	PTR	compat_sys_clock_adjtime	/* 6305 */
 	PTR	sys_syncfs
+	PTR	sys_setns
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 91ea5e4041dd..4a387de08bfa 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -546,4 +546,5 @@ sys_call_table:
 	PTR	compat_sys_open_by_handle_at	/* 4340 */
 	PTR	compat_sys_clock_adjtime
 	PTR	sys_syncfs
+	PTR	sys_setns
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 812816c45662..ec38e00b2559 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -639,7 +639,6 @@ void __init txx9_physmap_flash_init(int no, unsigned long addr,
 		.flags = IORESOURCE_MEM,
 	};
 	struct platform_device *pdev;
-#ifdef CONFIG_MTD_PARTITIONS
 	static struct mtd_partition parts[2];
 	struct physmap_flash_data pdata_part;
 
@@ -658,7 +657,7 @@ void __init txx9_physmap_flash_init(int no, unsigned long addr,
 		pdata_part.parts = parts;
 		pdata = &pdata_part;
 	}
-#endif
+
 	pdev = platform_device_alloc("physmap-flash", no);
 	if (!pdev ||
 	    platform_device_add_resources(pdev, &res, 1) ||
diff --git a/arch/mn10300/include/asm/uaccess.h b/arch/mn10300/include/asm/uaccess.h
index 3d6e60dad9d9..780560b330d9 100644
--- a/arch/mn10300/include/asm/uaccess.h
+++ b/arch/mn10300/include/asm/uaccess.h
@@ -15,6 +15,7 @@
  * User space memory access functions
  */
 #include <linux/thread_info.h>
+#include <linux/kernel.h>
 #include <asm/page.h>
 #include <asm/errno.h>
 
diff --git a/arch/mn10300/include/asm/unistd.h b/arch/mn10300/include/asm/unistd.h
index 9d056f515929..9051f921cbc7 100644
--- a/arch/mn10300/include/asm/unistd.h
+++ b/arch/mn10300/include/asm/unistd.h
@@ -349,10 +349,11 @@
 #define __NR_rt_tgsigqueueinfo	336
 #define __NR_perf_event_open	337
 #define __NR_recvmmsg		338
+#define __NR_setns		339
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 339
+#define NR_syscalls 340
 
 /*
  * specify the deprecated syscalls we want to support on this arch
diff --git a/arch/mn10300/kernel/entry.S b/arch/mn10300/kernel/entry.S
index fb93ad720b82..ae435e1d5669 100644
--- a/arch/mn10300/kernel/entry.S
+++ b/arch/mn10300/kernel/entry.S
@@ -759,6 +759,7 @@ ENTRY(sys_call_table)
 	.long sys_rt_tgsigqueueinfo
 	.long sys_perf_event_open
 	.long sys_recvmmsg
+	.long sys_setns
 
 
 nr_syscalls=(.-sys_call_table)/4
diff --git a/arch/mn10300/kernel/traps.c b/arch/mn10300/kernel/traps.c
index f03cb278828f..bd3e5e73826e 100644
--- a/arch/mn10300/kernel/traps.c
+++ b/arch/mn10300/kernel/traps.c
@@ -28,7 +28,7 @@
 #include <linux/irq.h>
 #include <asm/processor.h>
 #include <asm/system.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/atomic.h>
 #include <asm/smp.h>
@@ -156,7 +156,7 @@ int die_if_no_fixup(const char *str, struct pt_regs *regs,
 
 	case EXCEP_TRAP:
 	case EXCEP_UNIMPINS:
-		if (get_user(opcode, (uint8_t __user *)regs->pc) != 0)
+		if (probe_kernel_read(&opcode, (u8 *)regs->pc, 1) < 0)
 			break;
 		if (opcode == 0xff) {
 			if (notify_die(DIE_BREAKPOINT, str, regs, code, 0, 0))
diff --git a/arch/mn10300/kernel/vmlinux.lds.S b/arch/mn10300/kernel/vmlinux.lds.S
index 6f702a6ab395..13c4814c29f8 100644
--- a/arch/mn10300/kernel/vmlinux.lds.S
+++ b/arch/mn10300/kernel/vmlinux.lds.S
@@ -44,6 +44,7 @@ SECTIONS
   RO_DATA(PAGE_SIZE)
 
   /* writeable */
+  _sdata = .;     /* Start of rw data section */
   RW_DATA_SECTION(32, PAGE_SIZE, THREAD_SIZE)
   _edata = .;
 
diff --git a/arch/mn10300/mm/cache-dbg-flush-by-reg.S b/arch/mn10300/mm/cache-dbg-flush-by-reg.S
index 665919f2ab62..a775ea5d7cee 100644
--- a/arch/mn10300/mm/cache-dbg-flush-by-reg.S
+++ b/arch/mn10300/mm/cache-dbg-flush-by-reg.S
@@ -120,14 +120,14 @@ debugger_local_cache_flushinv_one:
 	# conditionally purge this line in all ways
 	mov	d1,(L1_CACHE_WAYDISP*0,a0)
 
-debugger_local_cache_flushinv_no_dcache:
+debugger_local_cache_flushinv_one_no_dcache:
 	#
 	# now try to flush the icache
 	#
 	mov	CHCTR,a0
 	movhu	(a0),d0
 	btst	CHCTR_ICEN,d0
-	beq	mn10300_local_icache_inv_range_reg_end
+	beq	debugger_local_cache_flushinv_one_end
 
 	LOCAL_CLI_SAVE(d1)
 
diff --git a/arch/parisc/include/asm/mmzone.h b/arch/parisc/include/asm/mmzone.h
index 9608d2cf214a..e67eb9c3d1bf 100644
--- a/arch/parisc/include/asm/mmzone.h
+++ b/arch/parisc/include/asm/mmzone.h
@@ -14,13 +14,6 @@ extern struct node_map_data node_data[];
 
 #define NODE_DATA(nid)          (&node_data[nid].pg_data)
 
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)						\
-({									\
-	pg_data_t *__pgdat = NODE_DATA(nid);				\
-	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;		\
-})
-
 /* We have these possible memory map layouts:
  * Astro: 0-3.75, 67.75-68, 4-64
  * zx1: 0-1, 257-260, 4-256
diff --git a/arch/parisc/include/asm/unistd.h b/arch/parisc/include/asm/unistd.h
index 9cbc2c3bf630..3392de3e7be0 100644
--- a/arch/parisc/include/asm/unistd.h
+++ b/arch/parisc/include/asm/unistd.h
@@ -820,8 +820,9 @@
 #define __NR_name_to_handle_at	(__NR_Linux + 325)
 #define __NR_open_by_handle_at	(__NR_Linux + 326)
 #define __NR_syncfs		(__NR_Linux + 327)
+#define __NR_setns		(__NR_Linux + 328)
 
-#define __NR_Linux_syscalls	(__NR_syncfs + 1)
+#define __NR_Linux_syscalls	(__NR_setns + 1)
 
 
 #define __IGNORE_select		/* newselect */
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index a5b02ce4d41e..34a4f5a2fffb 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -426,6 +426,7 @@
 	ENTRY_SAME(name_to_handle_at)	/* 325 */
 	ENTRY_COMP(open_by_handle_at)
 	ENTRY_SAME(syncfs)
+	ENTRY_SAME(setns)
 
 	/* Nothing yet */
 
diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore
index 3d80c3e9cf60..12da77ec0228 100644
--- a/arch/powerpc/boot/.gitignore
+++ b/arch/powerpc/boot/.gitignore
@@ -1,5 +1,4 @@
 addnote
-dtc
 empty.c
 hack-coff
 infblock.c
diff --git a/arch/powerpc/boot/dtc-src/.gitignore b/arch/powerpc/boot/dtc-src/.gitignore
deleted file mode 100644
index a7c3f94e5e75..000000000000
--- a/arch/powerpc/boot/dtc-src/.gitignore
+++ /dev/null
@@ -1,3 +0,0 @@
-dtc-lexer.lex.c
-dtc-parser.tab.c
-dtc-parser.tab.h
diff --git a/arch/powerpc/configs/52xx/pcm030_defconfig b/arch/powerpc/configs/52xx/pcm030_defconfig
index 7f7e4a878602..22e719575c60 100644
--- a/arch/powerpc/configs/52xx/pcm030_defconfig
+++ b/arch/powerpc/configs/52xx/pcm030_defconfig
@@ -85,7 +85,7 @@ CONFIG_USB_OHCI_HCD=m
 CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
 # CONFIG_USB_OHCI_HCD_PCI is not set
 CONFIG_USB_STORAGE=m
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_PCF8563=m
 CONFIG_EXT2_FS=m
 CONFIG_EXT3_FS=m
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index 6472322bf13b..185c292b0f1c 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -141,7 +141,7 @@ CONFIG_USB_EHCI_TT_NEWSCHED=y
 # CONFIG_USB_EHCI_HCD_PPC_OF is not set
 CONFIG_USB_OHCI_HCD=m
 CONFIG_USB_STORAGE=m
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_PS3=m
 CONFIG_EXT2_FS=m
 CONFIG_EXT3_FS=m
diff --git a/arch/powerpc/include/asm/fsl_lbc.h b/arch/powerpc/include/asm/fsl_lbc.h
index 5c1bf3466749..8a0b5ece8f76 100644
--- a/arch/powerpc/include/asm/fsl_lbc.h
+++ b/arch/powerpc/include/asm/fsl_lbc.h
@@ -157,6 +157,8 @@ struct fsl_lbc_regs {
 #define LBCR_EPAR_SHIFT    16
 #define LBCR_BMT   0x0000FF00
 #define LBCR_BMT_SHIFT      8
+#define LBCR_BMTPS 0x0000000F
+#define LBCR_BMTPS_SHIFT    0
 #define LBCR_INIT  0x00040000
 	__be32 lcrr;            /**< Clock Ratio Register */
 #define LCRR_DBYP    0x80000000
diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h
index fd3fd58bad84..7b589178be46 100644
--- a/arch/powerpc/include/asm/mmzone.h
+++ b/arch/powerpc/include/asm/mmzone.h
@@ -38,13 +38,6 @@ u64 memory_hotplug_max(void);
 #define memory_hotplug_max() memblock_end_of_DRAM()
 #endif
 
-/*
- * Following are macros that each numa implmentation must define.
- */
-
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)	(NODE_DATA(nid)->node_end_pfn)
-
 #else
 #define memory_hotplug_max() memblock_end_of_DRAM()
 #endif /* CONFIG_NEED_MULTIPLE_NODES */
diff --git a/arch/powerpc/include/asm/rio.h b/arch/powerpc/include/asm/rio.h
index 0018bf80cb25..b1d2deceeedb 100644
--- a/arch/powerpc/include/asm/rio.h
+++ b/arch/powerpc/include/asm/rio.h
@@ -14,5 +14,10 @@
 #define ASM_PPC_RIO_H
 
 extern void platform_rio_init(void);
+#ifdef CONFIG_FSL_RIO
+extern int fsl_rio_mcheck_exception(struct pt_regs *);
+#else
+static inline int fsl_rio_mcheck_exception(struct pt_regs *regs) {return 0; }
+#endif
 
 #endif				/* ASM_PPC_RIO_H */
diff --git a/arch/powerpc/include/asm/suspend.h b/arch/powerpc/include/asm/suspend.h
deleted file mode 100644
index c6efc3466aa6..000000000000
--- a/arch/powerpc/include/asm/suspend.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_POWERPC_SUSPEND_H
-#define __ASM_POWERPC_SUSPEND_H
-
-static inline int arch_prepare_suspend(void) { return 0; }
-
-#endif /* __ASM_POWERPC_SUSPEND_H */
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 8489d372077f..f6736b7da463 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -353,3 +353,4 @@ COMPAT_SYS_SPU(open_by_handle_at)
 COMPAT_SYS_SPU(clock_adjtime)
 SYSCALL_SPU(syncfs)
 COMPAT_SYS_SPU(sendmmsg)
+SYSCALL_SPU(setns)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 6d23c8193caa..b8b3f599362b 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -372,10 +372,11 @@
 #define __NR_clock_adjtime	347
 #define __NR_syncfs		348
 #define __NR_sendmmsg		349
+#define __NR_setns		350
 
 #ifdef __KERNEL__
 
-#define __NR_syscalls		350
+#define __NR_syscalls		351
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 34d2722b9451..9fb933248ab6 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -1979,7 +1979,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.pvr_value		= 0x80240000,
 		.cpu_name		= "e5500",
 		.cpu_features		= CPU_FTRS_E5500,
-		.cpu_user_features	= COMMON_USER_BOOKE,
+		.cpu_user_features	= COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
 		.mmu_features		= MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS |
 			MMU_FTR_USE_TLBILX,
 		.icache_bsize		= 64,
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 48aeb55faae9..8c3112a57cf2 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -82,11 +82,29 @@ static int __init early_parse_mem(char *p)
 }
 early_param("mem", early_parse_mem);
 
+/*
+ * overlaps_initrd - check for overlap with page aligned extension of
+ * initrd.
+ */
+static inline int overlaps_initrd(unsigned long start, unsigned long size)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+	if (!initrd_start)
+		return 0;
+
+	return	(start + size) > _ALIGN_DOWN(initrd_start, PAGE_SIZE) &&
+			start <= _ALIGN_UP(initrd_end, PAGE_SIZE);
+#else
+	return 0;
+#endif
+}
+
 /**
  * move_device_tree - move tree to an unused area, if needed.
  *
  * The device tree may be allocated beyond our memory limit, or inside the
- * crash kernel region for kdump. If so, move it out of the way.
+ * crash kernel region for kdump, or within the page aligned range of initrd.
+ * If so, move it out of the way.
  */
 static void __init move_device_tree(void)
 {
@@ -99,7 +117,8 @@ static void __init move_device_tree(void)
 	size = be32_to_cpu(initial_boot_params->totalsize);
 
 	if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) ||
-			overlaps_crashkernel(start, size)) {
+			overlaps_crashkernel(start, size) ||
+			overlaps_initrd(start, size)) {
 		p = __va(memblock_alloc(size, PAGE_SIZE));
 		memcpy(p, initial_boot_params, size);
 		initial_boot_params = (struct boot_param_header *)p;
@@ -555,7 +574,9 @@ static void __init early_reserve_mem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* then reserve the initrd, if any */
 	if (initrd_start && (initrd_end > initrd_start))
-		memblock_reserve(__pa(initrd_start), initrd_end - initrd_start);
+		memblock_reserve(_ALIGN_DOWN(__pa(initrd_start), PAGE_SIZE),
+			_ALIGN_UP(initrd_end, PAGE_SIZE) -
+			_ALIGN_DOWN(initrd_start, PAGE_SIZE));
 #endif /* CONFIG_BLK_DEV_INITRD */
 
 #ifdef CONFIG_PPC32
@@ -694,7 +715,7 @@ void __init early_init_devtree(void *params)
 	 * device-tree, including the platform type, initrd location and
 	 * size, TCE reserve, and more ...
 	 */
-	of_scan_flat_dt(early_init_dt_scan_chosen_ppc, NULL);
+	of_scan_flat_dt(early_init_dt_scan_chosen_ppc, cmd_line);
 
 	/* Scan memory nodes and rebuild MEMBLOCKs */
 	memblock_init();
diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c
index 560c96119501..aa17b76dd427 100644
--- a/arch/powerpc/kernel/swsusp.c
+++ b/arch/powerpc/kernel/swsusp.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/sched.h>
-#include <asm/suspend.h>
 #include <asm/system.h>
 #include <asm/current.h>
 #include <asm/mmu_context.h>
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index b13306b0d925..0ff4ab98d50c 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -55,6 +55,7 @@
 #endif
 #include <asm/kexec.h>
 #include <asm/ppc-opcode.h>
+#include <asm/rio.h>
 
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
 int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -424,6 +425,12 @@ int machine_check_e500mc(struct pt_regs *regs)
 	unsigned long reason = mcsr;
 	int recoverable = 1;
 
+	if (reason & MCSR_BUS_RBERR) {
+		recoverable = fsl_rio_mcheck_exception(regs);
+		if (recoverable == 1)
+			goto silent_out;
+	}
+
 	printk("Machine check in kernel mode.\n");
 	printk("Caused by (from MCSR=%lx): ", reason);
 
@@ -499,6 +506,7 @@ int machine_check_e500mc(struct pt_regs *regs)
 		       reason & MCSR_MEA ? "Effective" : "Physical", addr);
 	}
 
+silent_out:
 	mtspr(SPRN_MCSR, mcsr);
 	return mfspr(SPRN_MCSR) == 0 && recoverable;
 }
@@ -507,6 +515,11 @@ int machine_check_e500(struct pt_regs *regs)
 {
 	unsigned long reason = get_mc_reason(regs);
 
+	if (reason & MCSR_BUS_RBERR) {
+		if (fsl_rio_mcheck_exception(regs))
+			return 1;
+	}
+
 	printk("Machine check in kernel mode.\n");
 	printk("Caused by (from MCSR=%lx): ", reason);
 
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index d65b591e5556..5de0f254dbb5 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -223,21 +223,6 @@ void free_initmem(void)
 #undef FREESEC
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	if (start < end)
-		printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-	for (; start < end; start += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(start));
-		init_page_count(virt_to_page(start));
-		free_page(start);
-		totalram_pages++;
-	}
-}
-#endif
-
-
 #ifdef CONFIG_8xx /* No 8xx specific .c file to put that in ... */
 void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 				phys_addr_t first_memblock_size)
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 6374b2196a17..f6dbb4c20e64 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -99,20 +99,6 @@ void free_initmem(void)
 		((unsigned long)__init_end - (unsigned long)__init_begin) >> 10);
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	if (start < end)
-		printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-	for (; start < end; start += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(start));
-		init_page_count(virt_to_page(start));
-		free_page(start);
-		totalram_pages++;
-	}
-}
-#endif
-
 static void pgd_ctor(void *addr)
 {
 	memset(addr, 0, PGD_TABLE_SIZE);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 57e545b84bf1..29d4dde65c45 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -382,6 +382,25 @@ void __init mem_init(void)
 	mem_init_done = 1;
 }
 
+#ifdef CONFIG_BLK_DEV_INITRD
+void __init free_initrd_mem(unsigned long start, unsigned long end)
+{
+	if (start >= end)
+		return;
+
+	start = _ALIGN_DOWN(start, PAGE_SIZE);
+	end = _ALIGN_UP(end, PAGE_SIZE);
+	pr_info("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
+
+	for (; start < end; start += PAGE_SIZE) {
+		ClearPageReserved(virt_to_page(start));
+		init_page_count(virt_to_page(start));
+		free_page(start);
+		totalram_pages++;
+	}
+}
+#endif
+
 /*
  * This is called when a page has been modified by the kernel.
  * It just marks the page as not i-cache clean.  We do the i-cache
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 9089b0421191..7667db448aa7 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -715,7 +715,8 @@ static struct syscore_ops pmacpic_syscore_ops = {
 
 static int __init init_pmacpic_syscore(void)
 {
-	register_syscore_ops(&pmacpic_syscore_ops);
+	if (pmac_irq_hw[0])
+		register_syscore_ops(&pmacpic_syscore_ops);
 	return 0;
 }
 
diff --git a/arch/powerpc/sysdev/fsl_lbc.c b/arch/powerpc/sysdev/fsl_lbc.c
index 4fcb5a4e60dd..d917573cf1a8 100644
--- a/arch/powerpc/sysdev/fsl_lbc.c
+++ b/arch/powerpc/sysdev/fsl_lbc.c
@@ -184,7 +184,8 @@ int fsl_upm_run_pattern(struct fsl_upm *upm, void __iomem *io_base, u32 mar)
 }
 EXPORT_SYMBOL(fsl_upm_run_pattern);
 
-static int __devinit fsl_lbc_ctrl_init(struct fsl_lbc_ctrl *ctrl)
+static int __devinit fsl_lbc_ctrl_init(struct fsl_lbc_ctrl *ctrl,
+				       struct device_node *node)
 {
 	struct fsl_lbc_regs __iomem *lbc = ctrl->regs;
 
@@ -195,8 +196,9 @@ static int __devinit fsl_lbc_ctrl_init(struct fsl_lbc_ctrl *ctrl)
 	out_be32(&lbc->lteccr, LTECCR_CLEAR);
 	out_be32(&lbc->ltedr, LTEDR_ENABLE);
 
-	/* Enable interrupts for any detected events */
-	out_be32(&lbc->lteir, LTEIR_ENABLE);
+	/* Set the monitor timeout value to the maximum for erratum A001 */
+	if (of_device_is_compatible(node, "fsl,elbc"))
+		clrsetbits_be32(&lbc->lbcr, LBCR_BMT, LBCR_BMTPS);
 
 	return 0;
 }
@@ -304,7 +306,7 @@ static int __devinit fsl_lbc_ctrl_probe(struct platform_device *dev)
 
 	fsl_lbc_ctrl_dev->dev = &dev->dev;
 
-	ret = fsl_lbc_ctrl_init(fsl_lbc_ctrl_dev);
+	ret = fsl_lbc_ctrl_init(fsl_lbc_ctrl_dev, dev->dev.of_node);
 	if (ret < 0)
 		goto err;
 
@@ -317,6 +319,9 @@ static int __devinit fsl_lbc_ctrl_probe(struct platform_device *dev)
 		goto err;
 	}
 
+	/* Enable interrupts for any detected events */
+	out_be32(&fsl_lbc_ctrl_dev->regs->lteir, LTEIR_ENABLE);
+
 	return 0;
 
 err:
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index 49798532b477..5b206a2fe17c 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -10,7 +10,7 @@
  * - Added Port-Write message handling
  * - Added Machine Check exception handling
  *
- * Copyright (C) 2007, 2008 Freescale Semiconductor, Inc.
+ * Copyright (C) 2007, 2008, 2010 Freescale Semiconductor, Inc.
  * Zhang Wei <wei.zhang@freescale.com>
  *
  * Copyright 2005 MontaVista Software, Inc.
@@ -47,15 +47,33 @@
 #define IRQ_RIO_RX(m)		(((struct rio_priv *)(m->priv))->rxirq)
 #define IRQ_RIO_PW(m)		(((struct rio_priv *)(m->priv))->pwirq)
 
+#define IPWSR_CLEAR		0x98
+#define OMSR_CLEAR		0x1cb3
+#define IMSR_CLEAR		0x491
+#define IDSR_CLEAR		0x91
+#define ODSR_CLEAR		0x1c00
+#define LTLEECSR_ENABLE_ALL	0xFFC000FC
+#define ESCSR_CLEAR		0x07120204
+
+#define RIO_PORT1_EDCSR		0x0640
+#define RIO_PORT2_EDCSR		0x0680
+#define RIO_PORT1_IECSR		0x10130
+#define RIO_PORT2_IECSR		0x101B0
+#define RIO_IM0SR		0x13064
+#define RIO_IM1SR		0x13164
+#define RIO_OM0SR		0x13004
+#define RIO_OM1SR		0x13104
+
 #define RIO_ATMU_REGS_OFFSET	0x10c00
 #define RIO_P_MSG_REGS_OFFSET	0x11000
 #define RIO_S_MSG_REGS_OFFSET	0x13000
 #define RIO_GCCSR		0x13c
 #define RIO_ESCSR		0x158
+#define RIO_PORT2_ESCSR		0x178
 #define RIO_CCSR		0x15c
 #define RIO_LTLEDCSR		0x0608
-#define  RIO_LTLEDCSR_IER	0x80000000
-#define  RIO_LTLEDCSR_PRT	0x01000000
+#define RIO_LTLEDCSR_IER	0x80000000
+#define RIO_LTLEDCSR_PRT	0x01000000
 #define RIO_LTLEECSR		0x060c
 #define RIO_EPWISR		0x10010
 #define RIO_ISR_AACR		0x10120
@@ -88,7 +106,10 @@
 #define RIO_IPWSR_PWD		0x00000008
 #define RIO_IPWSR_PWB		0x00000004
 
-#define RIO_EPWISR_PINT		0x80000000
+/* EPWISR Error match value */
+#define RIO_EPWISR_PINT1	0x80000000
+#define RIO_EPWISR_PINT2	0x40000000
+#define RIO_EPWISR_MU		0x00000002
 #define RIO_EPWISR_PW		0x00000001
 
 #define RIO_MSG_DESC_SIZE	32
@@ -260,9 +281,7 @@ struct rio_priv {
 static void __iomem *rio_regs_win;
 
 #ifdef CONFIG_E500
-static int (*saved_mcheck_exception)(struct pt_regs *regs);
-
-static int fsl_rio_mcheck_exception(struct pt_regs *regs)
+int fsl_rio_mcheck_exception(struct pt_regs *regs)
 {
 	const struct exception_table_entry *entry = NULL;
 	unsigned long reason = mfspr(SPRN_MCSR);
@@ -284,11 +303,9 @@ static int fsl_rio_mcheck_exception(struct pt_regs *regs)
 		}
 	}
 
-	if (saved_mcheck_exception)
-		return saved_mcheck_exception(regs);
-	else
-		return cur_cpu_spec->machine_check(regs);
+	return 0;
 }
+EXPORT_SYMBOL_GPL(fsl_rio_mcheck_exception);
 #endif
 
 /**
@@ -1064,6 +1081,40 @@ static int fsl_rio_doorbell_init(struct rio_mport *mport)
 	return rc;
 }
 
+static void port_error_handler(struct rio_mport *port, int offset)
+{
+	/*XXX: Error recovery is not implemented, we just clear errors */
+	out_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR), 0);
+
+	if (offset == 0) {
+		out_be32((u32 *)(rio_regs_win + RIO_PORT1_EDCSR), 0);
+		out_be32((u32 *)(rio_regs_win + RIO_PORT1_IECSR), 0);
+		out_be32((u32 *)(rio_regs_win + RIO_ESCSR), ESCSR_CLEAR);
+	} else {
+		out_be32((u32 *)(rio_regs_win + RIO_PORT2_EDCSR), 0);
+		out_be32((u32 *)(rio_regs_win + RIO_PORT2_IECSR), 0);
+		out_be32((u32 *)(rio_regs_win + RIO_PORT2_ESCSR), ESCSR_CLEAR);
+	}
+}
+
+static void msg_unit_error_handler(struct rio_mport *port)
+{
+	struct rio_priv *priv = port->priv;
+
+	/*XXX: Error recovery is not implemented, we just clear errors */
+	out_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR), 0);
+
+	out_be32((u32 *)(rio_regs_win + RIO_IM0SR), IMSR_CLEAR);
+	out_be32((u32 *)(rio_regs_win + RIO_IM1SR), IMSR_CLEAR);
+	out_be32((u32 *)(rio_regs_win + RIO_OM0SR), OMSR_CLEAR);
+	out_be32((u32 *)(rio_regs_win + RIO_OM1SR), OMSR_CLEAR);
+
+	out_be32(&priv->msg_regs->odsr, ODSR_CLEAR);
+	out_be32(&priv->msg_regs->dsr, IDSR_CLEAR);
+
+	out_be32(&priv->msg_regs->pwsr, IPWSR_CLEAR);
+}
+
 /**
  * fsl_rio_port_write_handler - MPC85xx port write interrupt handler
  * @irq: Linux interrupt number
@@ -1144,10 +1195,22 @@ fsl_rio_port_write_handler(int irq, void *dev_instance)
 	}
 
 pw_done:
-	if (epwisr & RIO_EPWISR_PINT) {
+	if (epwisr & RIO_EPWISR_PINT1) {
+		tmp = in_be32(priv->regs_win + RIO_LTLEDCSR);
+		pr_debug("RIO_LTLEDCSR = 0x%x\n", tmp);
+		port_error_handler(port, 0);
+	}
+
+	if (epwisr & RIO_EPWISR_PINT2) {
 		tmp = in_be32(priv->regs_win + RIO_LTLEDCSR);
 		pr_debug("RIO_LTLEDCSR = 0x%x\n", tmp);
-		out_be32(priv->regs_win + RIO_LTLEDCSR, 0);
+		port_error_handler(port, 1);
+	}
+
+	if (epwisr & RIO_EPWISR_MU) {
+		tmp = in_be32(priv->regs_win + RIO_LTLEDCSR);
+		pr_debug("RIO_LTLEDCSR = 0x%x\n", tmp);
+		msg_unit_error_handler(port);
 	}
 
 	return IRQ_HANDLED;
@@ -1258,12 +1321,14 @@ static int fsl_rio_port_write_init(struct rio_mport *mport)
 
 
 	/* Hook up port-write handler */
-	rc = request_irq(IRQ_RIO_PW(mport), fsl_rio_port_write_handler, 0,
-			 "port-write", (void *)mport);
+	rc = request_irq(IRQ_RIO_PW(mport), fsl_rio_port_write_handler,
+			IRQF_SHARED, "port-write", (void *)mport);
 	if (rc < 0) {
 		pr_err("MPC85xx RIO: unable to request inbound doorbell irq");
 		goto err_out;
 	}
+	/* Enable Error Interrupt */
+	out_be32((u32 *)(rio_regs_win + RIO_LTLEECSR), LTLEECSR_ENABLE_ALL);
 
 	INIT_WORK(&priv->pw_work, fsl_pw_dpc);
 	spin_lock_init(&priv->pw_fifo_lock);
@@ -1538,11 +1603,6 @@ int fsl_rio_setup(struct platform_device *dev)
 	fsl_rio_doorbell_init(port);
 	fsl_rio_port_write_init(port);
 
-#ifdef CONFIG_E500
-	saved_mcheck_exception = ppc_md.machine_check_exception;
-	ppc_md.machine_check_exception = fsl_rio_mcheck_exception;
-#endif
-
 	return 0;
 err:
 	iounmap(priv->regs_win);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index ff2d2371b2e9..c03fef7a9c22 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -2,7 +2,7 @@ config MMU
 	def_bool y
 
 config ZONE_DMA
-	def_bool y if 64BIT
+	def_bool y
 
 config LOCKDEP_SUPPORT
 	def_bool y
@@ -89,6 +89,7 @@ config S390
 	select HAVE_GET_USER_PAGES_FAST
 	select HAVE_ARCH_MUTEX_CPU_RELAX
 	select HAVE_ARCH_JUMP_LABEL if !MARCH_G5
+	select HAVE_RCU_TABLE_FREE if SMP
 	select ARCH_INLINE_SPIN_TRYLOCK
 	select ARCH_INLINE_SPIN_TRYLOCK_BH
 	select ARCH_INLINE_SPIN_LOCK
@@ -578,6 +579,7 @@ config S390_GUEST
 	def_bool y
 	prompt "s390 guest support for KVM (EXPERIMENTAL)"
 	depends on 64BIT && EXPERIMENTAL
+	select VIRTUALIZATION
 	select VIRTIO
 	select VIRTIO_RING
 	select VIRTIO_CONSOLE
diff --git a/arch/s390/appldata/appldata_mem.c b/arch/s390/appldata/appldata_mem.c
index e43fe7537031..f7d3dc555bdb 100644
--- a/arch/s390/appldata/appldata_mem.c
+++ b/arch/s390/appldata/appldata_mem.c
@@ -92,9 +92,7 @@ static void appldata_get_mem_data(void *data)
 	mem_data->pswpin     = ev[PSWPIN];
 	mem_data->pswpout    = ev[PSWPOUT];
 	mem_data->pgalloc    = ev[PGALLOC_NORMAL];
-#ifdef CONFIG_ZONE_DMA
 	mem_data->pgalloc    += ev[PGALLOC_DMA];
-#endif
 	mem_data->pgfault    = ev[PGFAULT];
 	mem_data->pgmajfault = ev[PGMAJFAULT];
 
diff --git a/arch/s390/include/asm/delay.h b/arch/s390/include/asm/delay.h
index 8a096b83f51f..0e3b35f96be1 100644
--- a/arch/s390/include/asm/delay.h
+++ b/arch/s390/include/asm/delay.h
@@ -14,10 +14,12 @@
 #ifndef _S390_DELAY_H
 #define _S390_DELAY_H
 
-extern void __udelay(unsigned long long usecs);
-extern void udelay_simple(unsigned long long usecs);
-extern void __delay(unsigned long loops);
+void __ndelay(unsigned long long nsecs);
+void __udelay(unsigned long long usecs);
+void udelay_simple(unsigned long long usecs);
+void __delay(unsigned long loops);
 
+#define ndelay(n) __ndelay((unsigned long long) (n))
 #define udelay(n) __udelay((unsigned long long) (n))
 #define mdelay(n) __udelay((unsigned long long) (n) * 1000)
 
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index 1544b90bd6d6..ba7b01c726a3 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -2,6 +2,7 @@
 #define _ASM_IRQ_H
 
 #include <linux/hardirq.h>
+#include <linux/types.h>
 
 enum interruption_class {
 	EXTERNAL_INTERRUPT,
@@ -31,4 +32,11 @@ enum interruption_class {
 	NR_IRQS,
 };
 
+typedef void (*ext_int_handler_t)(unsigned int, unsigned int, unsigned long);
+
+int register_external_interrupt(u16 code, ext_int_handler_t handler);
+int unregister_external_interrupt(u16 code, ext_int_handler_t handler);
+void service_subclass_irq_register(void);
+void service_subclass_irq_unregister(void);
+
 #endif /* _ASM_IRQ_H */
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index f6314af3b354..38e71ebcd3c2 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -17,15 +17,15 @@
 #include <linux/gfp.h>
 #include <linux/mm.h>
 
-#define check_pgt_cache()	do {} while (0)
-
 unsigned long *crst_table_alloc(struct mm_struct *);
 void crst_table_free(struct mm_struct *, unsigned long *);
-void crst_table_free_rcu(struct mm_struct *, unsigned long *);
 
 unsigned long *page_table_alloc(struct mm_struct *);
 void page_table_free(struct mm_struct *, unsigned long *);
-void page_table_free_rcu(struct mm_struct *, unsigned long *);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+void page_table_free_rcu(struct mmu_gather *, unsigned long *);
+void __tlb_remove_table(void *_table);
+#endif
 
 static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
 {
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index c4773a2ef3d3..801fbe1d837d 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -293,19 +293,6 @@ extern unsigned long VMALLOC_START;
  * swap pte is 1011 and 0001, 0011, 0101, 0111 are invalid.
  */
 
-/* Page status table bits for virtualization */
-#define RCP_ACC_BITS	0xf000000000000000UL
-#define RCP_FP_BIT	0x0800000000000000UL
-#define RCP_PCL_BIT	0x0080000000000000UL
-#define RCP_HR_BIT	0x0040000000000000UL
-#define RCP_HC_BIT	0x0020000000000000UL
-#define RCP_GR_BIT	0x0004000000000000UL
-#define RCP_GC_BIT	0x0002000000000000UL
-
-/* User dirty / referenced bit for KVM's migration feature */
-#define KVM_UR_BIT	0x0000800000000000UL
-#define KVM_UC_BIT	0x0000400000000000UL
-
 #ifndef __s390x__
 
 /* Bits in the segment table address-space-control-element */
@@ -325,6 +312,19 @@ extern unsigned long VMALLOC_START;
 #define _SEGMENT_ENTRY		(_SEGMENT_ENTRY_PTL)
 #define _SEGMENT_ENTRY_EMPTY	(_SEGMENT_ENTRY_INV)
 
+/* Page status table bits for virtualization */
+#define RCP_ACC_BITS	0xf0000000UL
+#define RCP_FP_BIT	0x08000000UL
+#define RCP_PCL_BIT	0x00800000UL
+#define RCP_HR_BIT	0x00400000UL
+#define RCP_HC_BIT	0x00200000UL
+#define RCP_GR_BIT	0x00040000UL
+#define RCP_GC_BIT	0x00020000UL
+
+/* User dirty / referenced bit for KVM's migration feature */
+#define KVM_UR_BIT	0x00008000UL
+#define KVM_UC_BIT	0x00004000UL
+
 #else /* __s390x__ */
 
 /* Bits in the segment/region table address-space-control-element */
@@ -367,6 +367,19 @@ extern unsigned long VMALLOC_START;
 #define _SEGMENT_ENTRY_LARGE	0x400	/* STE-format control, large page   */
 #define _SEGMENT_ENTRY_CO	0x100	/* change-recording override   */
 
+/* Page status table bits for virtualization */
+#define RCP_ACC_BITS	0xf000000000000000UL
+#define RCP_FP_BIT	0x0800000000000000UL
+#define RCP_PCL_BIT	0x0080000000000000UL
+#define RCP_HR_BIT	0x0040000000000000UL
+#define RCP_HC_BIT	0x0020000000000000UL
+#define RCP_GR_BIT	0x0004000000000000UL
+#define RCP_GC_BIT	0x0002000000000000UL
+
+/* User dirty / referenced bit for KVM's migration feature */
+#define KVM_UR_BIT	0x0000800000000000UL
+#define KVM_UC_BIT	0x0000400000000000UL
+
 #endif /* __s390x__ */
 
 /*
@@ -577,16 +590,16 @@ static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
 static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
-	unsigned long pfn, bits;
+	unsigned long address, bits;
 	unsigned char skey;
 
-	pfn = pte_val(*ptep) >> PAGE_SHIFT;
-	skey = page_get_storage_key(pfn);
+	address = pte_val(*ptep) & PAGE_MASK;
+	skey = page_get_storage_key(address);
 	bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
 	/* Clear page changed & referenced bit in the storage key */
 	if (bits) {
 		skey ^= bits;
-		page_set_storage_key(pfn, skey, 1);
+		page_set_storage_key(address, skey, 1);
 	}
 	/* Transfer page changed & referenced bit to guest bits in pgste */
 	pgste_val(pgste) |= bits << 48;		/* RCP_GR_BIT & RCP_GC_BIT */
@@ -628,16 +641,16 @@ static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
 static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
-	unsigned long pfn;
+	unsigned long address;
 	unsigned long okey, nkey;
 
-	pfn = pte_val(*ptep) >> PAGE_SHIFT;
-	okey = nkey = page_get_storage_key(pfn);
+	address = pte_val(*ptep) & PAGE_MASK;
+	okey = nkey = page_get_storage_key(address);
 	nkey &= ~(_PAGE_ACC_BITS | _PAGE_FP_BIT);
 	/* Set page access key and fetch protection bit from pgste */
 	nkey |= (pgste_val(pgste) & (RCP_ACC_BITS | RCP_FP_BIT)) >> 56;
 	if (okey != nkey)
-		page_set_storage_key(pfn, nkey, 1);
+		page_set_storage_key(address, nkey, 1);
 #endif
 }
 
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index 350e7ee5952d..15c97625df8d 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -139,110 +139,47 @@ struct slib {
 	struct slibe slibe[QDIO_MAX_BUFFERS_PER_Q];
 } __attribute__ ((packed, aligned(2048)));
 
-/**
- * struct sbal_flags - storage block address list flags
- * @last: last entry
- * @cont: contiguous storage
- * @frag: fragmentation
- */
-struct sbal_flags {
-	u8	: 1;
-	u8 last : 1;
-	u8 cont : 1;
-	u8	: 1;
-	u8 frag : 2;
-	u8	: 2;
-} __attribute__ ((packed));
-
-#define SBAL_FLAGS_FIRST_FRAG		0x04000000UL
-#define SBAL_FLAGS_MIDDLE_FRAG		0x08000000UL
-#define SBAL_FLAGS_LAST_FRAG		0x0c000000UL
-#define SBAL_FLAGS_LAST_ENTRY		0x40000000UL
-#define SBAL_FLAGS_CONTIGUOUS		0x20000000UL
+#define SBAL_EFLAGS_LAST_ENTRY		0x40
+#define SBAL_EFLAGS_CONTIGUOUS		0x20
+#define SBAL_EFLAGS_FIRST_FRAG		0x04
+#define SBAL_EFLAGS_MIDDLE_FRAG		0x08
+#define SBAL_EFLAGS_LAST_FRAG		0x0c
+#define SBAL_EFLAGS_MASK		0x6f
 
-#define SBAL_FLAGS0_DATA_CONTINUATION	0x20UL
+#define SBAL_SFLAGS0_PCI_REQ		0x40
+#define SBAL_SFLAGS0_DATA_CONTINUATION	0x20
 
 /* Awesome OpenFCP extensions */
-#define SBAL_FLAGS0_TYPE_STATUS		0x00UL
-#define SBAL_FLAGS0_TYPE_WRITE		0x08UL
-#define SBAL_FLAGS0_TYPE_READ		0x10UL
-#define SBAL_FLAGS0_TYPE_WRITE_READ	0x18UL
-#define SBAL_FLAGS0_MORE_SBALS		0x04UL
-#define SBAL_FLAGS0_COMMAND		0x02UL
-#define SBAL_FLAGS0_LAST_SBAL		0x00UL
-#define SBAL_FLAGS0_ONLY_SBAL		SBAL_FLAGS0_COMMAND
-#define SBAL_FLAGS0_MIDDLE_SBAL		SBAL_FLAGS0_MORE_SBALS
-#define SBAL_FLAGS0_FIRST_SBAL SBAL_FLAGS0_MORE_SBALS | SBAL_FLAGS0_COMMAND
-#define SBAL_FLAGS0_PCI			0x40
-
-/**
- * struct sbal_sbalf_0 - sbal flags for sbale 0
- * @pci: PCI indicator
- * @cont: data continuation
- * @sbtype: storage-block type (FCP)
- */
-struct sbal_sbalf_0 {
-	u8	  : 1;
-	u8 pci	  : 1;
-	u8 cont   : 1;
-	u8 sbtype : 2;
-	u8	  : 3;
-} __attribute__ ((packed));
-
-/**
- * struct sbal_sbalf_1 - sbal flags for sbale 1
- * @key: storage key
- */
-struct sbal_sbalf_1 {
-	u8     : 4;
-	u8 key : 4;
-} __attribute__ ((packed));
-
-/**
- * struct sbal_sbalf_14 - sbal flags for sbale 14
- * @erridx: error index
- */
-struct sbal_sbalf_14 {
-	u8	  : 4;
-	u8 erridx : 4;
-} __attribute__ ((packed));
-
-/**
- * struct sbal_sbalf_15 - sbal flags for sbale 15
- * @reason: reason for error state
- */
-struct sbal_sbalf_15 {
-	u8 reason;
-} __attribute__ ((packed));
-
-/**
- * union sbal_sbalf - storage block address list flags
- * @i0: sbalf0
- * @i1: sbalf1
- * @i14: sbalf14
- * @i15: sblaf15
- * @value: raw value
- */
-union sbal_sbalf {
-	struct sbal_sbalf_0  i0;
-	struct sbal_sbalf_1  i1;
-	struct sbal_sbalf_14 i14;
-	struct sbal_sbalf_15 i15;
-	u8 value;
-};
+#define SBAL_SFLAGS0_TYPE_STATUS	0x00
+#define SBAL_SFLAGS0_TYPE_WRITE		0x08
+#define SBAL_SFLAGS0_TYPE_READ		0x10
+#define SBAL_SFLAGS0_TYPE_WRITE_READ	0x18
+#define SBAL_SFLAGS0_MORE_SBALS		0x04
+#define SBAL_SFLAGS0_COMMAND		0x02
+#define SBAL_SFLAGS0_LAST_SBAL		0x00
+#define SBAL_SFLAGS0_ONLY_SBAL		SBAL_SFLAGS0_COMMAND
+#define SBAL_SFLAGS0_MIDDLE_SBAL	SBAL_SFLAGS0_MORE_SBALS
+#define SBAL_SFLAGS0_FIRST_SBAL (SBAL_SFLAGS0_MORE_SBALS | SBAL_SFLAGS0_COMMAND)
 
 /**
  * struct qdio_buffer_element - SBAL entry
- * @flags: flags
+ * @eflags: SBAL entry flags
+ * @scount: SBAL count
+ * @sflags: whole SBAL flags
  * @length: length
  * @addr: address
 */
 struct qdio_buffer_element {
-	u32 flags;
+	u8 eflags;
+	/* private: */
+	u8 res1;
+	/* public: */
+	u8 scount;
+	u8 sflags;
 	u32 length;
 #ifdef CONFIG_32BIT
 	/* private: */
-	void *reserved;
+	void *res2;
 	/* public: */
 #endif
 	void *addr;
diff --git a/arch/s390/include/asm/s390_ext.h b/arch/s390/include/asm/s390_ext.h
deleted file mode 100644
index 080876d5f196..000000000000
--- a/arch/s390/include/asm/s390_ext.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- *    Copyright IBM Corp. 1999,2010
- *    Author(s): Holger Smolinski <Holger.Smolinski@de.ibm.com>,
- *		 Martin Schwidefsky <schwidefsky@de.ibm.com>,
- */
-
-#ifndef _S390_EXTINT_H
-#define _S390_EXTINT_H
-
-#include <linux/types.h>
-
-typedef void (*ext_int_handler_t)(unsigned int, unsigned int, unsigned long);
-
-int register_external_interrupt(__u16 code, ext_int_handler_t handler);
-int unregister_external_interrupt(__u16 code, ext_int_handler_t handler);
-
-#endif /* _S390_EXTINT_H */
diff --git a/arch/s390/include/asm/suspend.h b/arch/s390/include/asm/suspend.h
deleted file mode 100644
index dc75c616eafe..000000000000
--- a/arch/s390/include/asm/suspend.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __ASM_S390_SUSPEND_H
-#define __ASM_S390_SUSPEND_H
-
-static inline int arch_prepare_suspend(void)
-{
-	return 0;
-}
-
-#endif
-
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 77eee5477a52..c687a2c83462 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -26,67 +26,60 @@
 #include <linux/swap.h>
 #include <asm/processor.h>
 #include <asm/pgalloc.h>
-#include <asm/smp.h>
 #include <asm/tlbflush.h>
 
 struct mmu_gather {
 	struct mm_struct *mm;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	struct mmu_table_batch *batch;
+#endif
 	unsigned int fullmm;
-	unsigned int nr_ptes;
-	unsigned int nr_pxds;
-	unsigned int max;
-	void **array;
-	void *local[8];
+	unsigned int need_flush;
 };
 
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
-	unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+struct mmu_table_batch {
+	struct rcu_head		rcu;
+	unsigned int		nr;
+	void			*tables[0];
+};
 
-	if (addr) {
-		tlb->array = (void *) addr;
-		tlb->max = PAGE_SIZE / sizeof(void *);
-	}
-}
+#define MAX_TABLE_BATCH		\
+	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
+
+extern void tlb_table_flush(struct mmu_gather *tlb);
+extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
+#endif
 
 static inline void tlb_gather_mmu(struct mmu_gather *tlb,
 				  struct mm_struct *mm,
 				  unsigned int full_mm_flush)
 {
 	tlb->mm = mm;
-	tlb->max = ARRAY_SIZE(tlb->local);
-	tlb->array = tlb->local;
 	tlb->fullmm = full_mm_flush;
+	tlb->need_flush = 0;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb->batch = NULL;
+#endif
 	if (tlb->fullmm)
 		__tlb_flush_mm(mm);
-	else
-		__tlb_alloc_page(tlb);
-	tlb->nr_ptes = 0;
-	tlb->nr_pxds = tlb->max;
 }
 
 static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 {
-	if (!tlb->fullmm && (tlb->nr_ptes > 0 || tlb->nr_pxds < tlb->max))
-		__tlb_flush_mm(tlb->mm);
-	while (tlb->nr_ptes > 0)
-		page_table_free_rcu(tlb->mm, tlb->array[--tlb->nr_ptes]);
-	while (tlb->nr_pxds < tlb->max)
-		crst_table_free_rcu(tlb->mm, tlb->array[tlb->nr_pxds++]);
+	if (!tlb->need_flush)
+		return;
+	tlb->need_flush = 0;
+	__tlb_flush_mm(tlb->mm);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb_table_flush(tlb);
+#endif
 }
 
 static inline void tlb_finish_mmu(struct mmu_gather *tlb,
 				  unsigned long start, unsigned long end)
 {
 	tlb_flush_mmu(tlb);
-
-	rcu_table_freelist_finish();
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	if (tlb->array != tlb->local)
-		free_pages((unsigned long) tlb->array, 0);
 }
 
 /*
@@ -112,12 +105,11 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				unsigned long address)
 {
-	if (!tlb->fullmm) {
-		tlb->array[tlb->nr_ptes++] = pte;
-		if (tlb->nr_ptes >= tlb->nr_pxds)
-			tlb_flush_mmu(tlb);
-	} else
-		page_table_free(tlb->mm, (unsigned long *) pte);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	if (!tlb->fullmm)
+		return page_table_free_rcu(tlb, (unsigned long *) pte);
+#endif
+	page_table_free(tlb->mm, (unsigned long *) pte);
 }
 
 /*
@@ -133,12 +125,11 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 #ifdef __s390x__
 	if (tlb->mm->context.asce_limit <= (1UL << 31))
 		return;
-	if (!tlb->fullmm) {
-		tlb->array[--tlb->nr_pxds] = pmd;
-		if (tlb->nr_ptes >= tlb->nr_pxds)
-			tlb_flush_mmu(tlb);
-	} else
-		crst_table_free(tlb->mm, (unsigned long *) pmd);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	if (!tlb->fullmm)
+		return tlb_remove_table(tlb, pmd);
+#endif
+	crst_table_free(tlb->mm, (unsigned long *) pmd);
 #endif
 }
 
@@ -155,12 +146,11 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 #ifdef __s390x__
 	if (tlb->mm->context.asce_limit <= (1UL << 42))
 		return;
-	if (!tlb->fullmm) {
-		tlb->array[--tlb->nr_pxds] = pud;
-		if (tlb->nr_ptes >= tlb->nr_pxds)
-			tlb_flush_mmu(tlb);
-	} else
-		crst_table_free(tlb->mm, (unsigned long *) pud);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	if (!tlb->fullmm)
+		return tlb_remove_table(tlb, pud);
+#endif
+	crst_table_free(tlb->mm, (unsigned long *) pud);
 #endif
 }
 
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index c5338834ddbd..005d77d8ae2a 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -7,7 +7,7 @@
 extern unsigned char cpu_core_id[NR_CPUS];
 extern cpumask_t cpu_core_map[NR_CPUS];
 
-static inline const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+static inline const struct cpumask *cpu_coregroup_mask(int cpu)
 {
 	return &cpu_core_map[cpu];
 }
@@ -21,7 +21,7 @@ static inline const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
 extern unsigned char cpu_book_id[NR_CPUS];
 extern cpumask_t cpu_book_map[NR_CPUS];
 
-static inline const struct cpumask *cpu_book_mask(unsigned int cpu)
+static inline const struct cpumask *cpu_book_mask(int cpu)
 {
 	return &cpu_book_map[cpu];
 }
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 2d9ea11f919a..2b23885e81e9 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -49,12 +49,13 @@
 
 #define segment_eq(a,b) ((a).ar4 == (b).ar4)
 
+#define __access_ok(addr, size)	\
+({				\
+	__chk_user_ptr(addr);	\
+	1;			\
+})
 
-static inline int __access_ok(const void __user *addr, unsigned long size)
-{
-	return 1;
-}
-#define access_ok(type,addr,size) __access_ok(addr,size)
+#define access_ok(type, addr, size) __access_ok(addr, size)
 
 /*
  * The exception table consists of pairs of addresses: the first is the
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 9208e69245a0..404bdb9671b4 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -276,7 +276,8 @@
 #define __NR_open_by_handle_at	336
 #define __NR_clock_adjtime	337
 #define __NR_syncfs		338
-#define NR_syscalls 339
+#define __NR_setns		339
+#define NR_syscalls 340
 
 /* 
  * There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 5ff15dacb571..df3732249baa 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -20,10 +20,10 @@ CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w
 
-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 vtime.o sysinfo.o nmi.o sclp.o jump_label.o
+obj-y	:=  bitmap.o traps.o time.o process.o base.o early.o setup.o vtime.o \
+	    processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o \
+	    debug.o irq.o ipl.o dis.o diag.o mem_detect.o sclp.o vdso.o \
+	    sysinfo.o jump_label.o
 
 obj-y	+= $(if $(CONFIG_64BIT),entry64.o,entry.o)
 obj-y	+= $(if $(CONFIG_64BIT),reipl64.o,reipl.o)
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 1dc96ea08fa8..1f5eb789c3a7 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -1904,3 +1904,9 @@ compat_sys_clock_adjtime_wrapper:
 sys_syncfs_wrapper:
 	lgfr	%r2,%r2			# int
 	jg	sys_syncfs
+
+	.globl	sys_setns_wrapper
+sys_setns_wrapper:
+	lgfr	%r2,%r2			# int
+	lgfr	%r3,%r3			# int
+	jg	sys_setns
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 3d4a78fc1adc..1ca3d1d6a86c 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -30,9 +30,9 @@
 #include <asm/atomic.h>
 #include <asm/mathemu.h>
 #include <asm/cpcmd.h>
-#include <asm/s390_ext.h>
 #include <asm/lowcore.h>
 #include <asm/debug.h>
+#include <asm/irq.h>
 
 #ifndef CONFIG_64BIT
 #define ONELONG "%08lx: "
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index e204f9597aaf..e3264f6a9720 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -1,19 +1,28 @@
 /*
- *    Copyright IBM Corp. 2004,2010
- *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
- *		 Thomas Spatzier (tspat@de.ibm.com)
+ *    Copyright IBM Corp. 2004,2011
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ *		 Holger Smolinski <Holger.Smolinski@de.ibm.com>,
+ *		 Thomas Spatzier <tspat@de.ibm.com>,
  *
  * This file contains interrupt related functions.
  */
 
-#include <linux/module.h>
-#include <linux/kernel.h>
 #include <linux/kernel_stat.h>
 #include <linux/interrupt.h>
 #include <linux/seq_file.h>
-#include <linux/cpu.h>
 #include <linux/proc_fs.h>
 #include <linux/profile.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/ftrace.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <asm/irq_regs.h>
+#include <asm/cputime.h>
+#include <asm/lowcore.h>
+#include <asm/irq.h>
+#include "entry.h"
 
 struct irq_class {
 	char *name;
@@ -82,8 +91,7 @@ int show_interrupts(struct seq_file *p, void *v)
  * For compatibilty only. S/390 specific setup of interrupts et al. is done
  * much later in init_channel_subsystem().
  */
-void __init
-init_IRQ(void)
+void __init init_IRQ(void)
 {
 	/* nothing... */
 }
@@ -134,3 +142,116 @@ void init_irq_proc(void)
 	create_prof_cpu_mask(root_irq_dir);
 }
 #endif
+
+/*
+ * ext_int_hash[index] is the start of the list for all external interrupts
+ * that hash to this index. With the current set of external interrupts
+ * (0x1202 external call, 0x1004 cpu timer, 0x2401 hwc console, 0x4000
+ * iucv and 0x2603 pfault) this is always the first element.
+ */
+
+struct ext_int_info {
+	struct ext_int_info *next;
+	ext_int_handler_t handler;
+	u16 code;
+};
+
+static struct ext_int_info *ext_int_hash[256];
+
+static inline int ext_hash(u16 code)
+{
+	return (code + (code >> 9)) & 0xff;
+}
+
+int register_external_interrupt(u16 code, ext_int_handler_t handler)
+{
+	struct ext_int_info *p;
+	int index;
+
+	p = kmalloc(sizeof(*p), GFP_ATOMIC);
+	if (!p)
+		return -ENOMEM;
+	p->code = code;
+	p->handler = handler;
+	index = ext_hash(code);
+	p->next = ext_int_hash[index];
+	ext_int_hash[index] = p;
+	return 0;
+}
+EXPORT_SYMBOL(register_external_interrupt);
+
+int unregister_external_interrupt(u16 code, ext_int_handler_t handler)
+{
+	struct ext_int_info *p, *q;
+	int index;
+
+	index = ext_hash(code);
+	q = NULL;
+	p = ext_int_hash[index];
+	while (p) {
+		if (p->code == code && p->handler == handler)
+			break;
+		q = p;
+		p = p->next;
+	}
+	if (!p)
+		return -ENOENT;
+	if (q)
+		q->next = p->next;
+	else
+		ext_int_hash[index] = p->next;
+	kfree(p);
+	return 0;
+}
+EXPORT_SYMBOL(unregister_external_interrupt);
+
+void __irq_entry do_extint(struct pt_regs *regs, unsigned int ext_int_code,
+			   unsigned int param32, unsigned long param64)
+{
+	struct pt_regs *old_regs;
+	unsigned short code;
+	struct ext_int_info *p;
+	int index;
+
+	code = (unsigned short) ext_int_code;
+	old_regs = set_irq_regs(regs);
+	s390_idle_check(regs, S390_lowcore.int_clock,
+			S390_lowcore.async_enter_timer);
+	irq_enter();
+	if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator)
+		/* Serve timer interrupts first. */
+		clock_comparator_work();
+	kstat_cpu(smp_processor_id()).irqs[EXTERNAL_INTERRUPT]++;
+	if (code != 0x1004)
+		__get_cpu_var(s390_idle).nohz_delay = 1;
+	index = ext_hash(code);
+	for (p = ext_int_hash[index]; p; p = p->next) {
+		if (likely(p->code == code))
+			p->handler(ext_int_code, param32, param64);
+	}
+	irq_exit();
+	set_irq_regs(old_regs);
+}
+
+static DEFINE_SPINLOCK(sc_irq_lock);
+static int sc_irq_refcount;
+
+void service_subclass_irq_register(void)
+{
+	spin_lock(&sc_irq_lock);
+	if (!sc_irq_refcount)
+		ctl_set_bit(0, 9);
+	sc_irq_refcount++;
+	spin_unlock(&sc_irq_lock);
+}
+EXPORT_SYMBOL(service_subclass_irq_register);
+
+void service_subclass_irq_unregister(void)
+{
+	spin_lock(&sc_irq_lock);
+	sc_irq_refcount--;
+	if (!sc_irq_refcount)
+		ctl_clear_bit(0, 9);
+	spin_unlock(&sc_irq_lock);
+}
+EXPORT_SYMBOL(service_subclass_irq_unregister);
diff --git a/arch/s390/kernel/s390_ext.c b/arch/s390/kernel/s390_ext.c
deleted file mode 100644
index 185029919c4d..000000000000
--- a/arch/s390/kernel/s390_ext.c
+++ /dev/null
@@ -1,108 +0,0 @@
-/*
- *    Copyright IBM Corp. 1999,2010
- *    Author(s): Holger Smolinski <Holger.Smolinski@de.ibm.com>,
- *		 Martin Schwidefsky <schwidefsky@de.ibm.com>,
- */
-
-#include <linux/kernel_stat.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/ftrace.h>
-#include <linux/errno.h>
-#include <linux/slab.h>
-#include <asm/s390_ext.h>
-#include <asm/irq_regs.h>
-#include <asm/cputime.h>
-#include <asm/lowcore.h>
-#include <asm/irq.h>
-#include "entry.h"
-
-struct ext_int_info {
-	struct ext_int_info *next;
-	ext_int_handler_t handler;
-	__u16 code;
-};
-
-/*
- * ext_int_hash[index] is the start of the list for all external interrupts
- * that hash to this index. With the current set of external interrupts 
- * (0x1202 external call, 0x1004 cpu timer, 0x2401 hwc console, 0x4000
- * iucv and 0x2603 pfault) this is always the first element. 
- */
-static struct ext_int_info *ext_int_hash[256];
-
-static inline int ext_hash(__u16 code)
-{
-	return (code + (code >> 9)) & 0xff;
-}
-
-int register_external_interrupt(__u16 code, ext_int_handler_t handler)
-{
-	struct ext_int_info *p;
-	int index;
-
-	p = kmalloc(sizeof(*p), GFP_ATOMIC);
-	if (!p)
-		return -ENOMEM;
-	p->code = code;
-	p->handler = handler;
-	index = ext_hash(code);
-	p->next = ext_int_hash[index];
-	ext_int_hash[index] = p;
-	return 0;
-}
-EXPORT_SYMBOL(register_external_interrupt);
-
-int unregister_external_interrupt(__u16 code, ext_int_handler_t handler)
-{
-	struct ext_int_info *p, *q;
-	int index;
-
-	index = ext_hash(code);
-	q = NULL;
-	p = ext_int_hash[index];
-	while (p) {
-		if (p->code == code && p->handler == handler)
-			break;
-		q = p;
-		p = p->next;
-	}
-	if (!p)
-		return -ENOENT;
-	if (q)
-		q->next = p->next;
-	else
-		ext_int_hash[index] = p->next;
-	kfree(p);
-	return 0;
-}
-EXPORT_SYMBOL(unregister_external_interrupt);
-
-void __irq_entry do_extint(struct pt_regs *regs, unsigned int ext_int_code,
-			   unsigned int param32, unsigned long param64)
-{
-	struct pt_regs *old_regs;
-	unsigned short code;
-	struct ext_int_info *p;
-	int index;
-
-	code = (unsigned short) ext_int_code;
-	old_regs = set_irq_regs(regs);
-	s390_idle_check(regs, S390_lowcore.int_clock,
-			S390_lowcore.async_enter_timer);
-	irq_enter();
-	if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator)
-		/* Serve timer interrupts first. */
-		clock_comparator_work();
-	kstat_cpu(smp_processor_id()).irqs[EXTERNAL_INTERRUPT]++;
-	if (code != 0x1004)
-		__get_cpu_var(s390_idle).nohz_delay = 1;
-	index = ext_hash(code);
-	for (p = ext_int_hash[index]; p; p = p->next) {
-		if (likely(p->code == code))
-			p->handler(ext_int_code, param32, param64);
-	}
-	irq_exit();
-	set_irq_regs(old_regs);
-}
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index f8e85ecbc459..1d55c95f617c 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -44,7 +44,6 @@
 #include <asm/sigp.h>
 #include <asm/pgalloc.h>
 #include <asm/irq.h>
-#include <asm/s390_ext.h>
 #include <asm/cpcmd.h>
 #include <asm/tlbflush.h>
 #include <asm/timer.h>
@@ -263,7 +262,7 @@ void smp_ctl_set_bit(int cr, int bit)
 
 	memset(&parms.orvals, 0, sizeof(parms.orvals));
 	memset(&parms.andvals, 0xff, sizeof(parms.andvals));
-	parms.orvals[cr] = 1 << bit;
+	parms.orvals[cr] = 1UL << bit;
 	on_each_cpu(smp_ctl_bit_callback, &parms, 1);
 }
 EXPORT_SYMBOL(smp_ctl_set_bit);
@@ -277,7 +276,7 @@ void smp_ctl_clear_bit(int cr, int bit)
 
 	memset(&parms.orvals, 0, sizeof(parms.orvals));
 	memset(&parms.andvals, 0xff, sizeof(parms.andvals));
-	parms.andvals[cr] = ~(1L << bit);
+	parms.andvals[cr] = ~(1UL << bit);
 	on_each_cpu(smp_ctl_bit_callback, &parms, 1);
 }
 EXPORT_SYMBOL(smp_ctl_clear_bit);
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 9c65fd4ddce0..6ee39ef8fe4a 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -347,3 +347,4 @@ SYSCALL(sys_name_to_handle_at,sys_name_to_handle_at,sys_name_to_handle_at_wrappe
 SYSCALL(sys_open_by_handle_at,sys_open_by_handle_at,compat_sys_open_by_handle_at_wrapper)
 SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime_wrapper)
 SYSCALL(sys_syncfs,sys_syncfs,sys_syncfs_wrapper)
+SYSCALL(sys_setns,sys_setns,sys_setns_wrapper)
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index a59557f1fb5f..dff933065ab6 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -41,7 +41,6 @@
 #include <linux/kprobes.h>
 #include <asm/uaccess.h>
 #include <asm/delay.h>
-#include <asm/s390_ext.h>
 #include <asm/div64.h>
 #include <asm/vdso.h>
 #include <asm/irq.h>
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 2eafb8c7a746..0cd340b72632 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -17,7 +17,6 @@
 #include <linux/smp.h>
 #include <linux/cpuset.h>
 #include <asm/delay.h>
-#include <asm/s390_ext.h>
 
 #define PTF_HORIZONTAL	(0UL)
 #define PTF_VERTICAL	(1UL)
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index b5a4a739b477..a65d2e82f61d 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -39,7 +39,6 @@
 #include <asm/atomic.h>
 #include <asm/mathemu.h>
 #include <asm/cpcmd.h>
-#include <asm/s390_ext.h>
 #include <asm/lowcore.h>
 #include <asm/debug.h>
 #include "entry.h"
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 5e8ead4b4aba..2d6228f60cd6 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -22,10 +22,10 @@
 #include <linux/cpu.h>
 #include <linux/kprobes.h>
 
-#include <asm/s390_ext.h>
 #include <asm/timer.h>
 #include <asm/irq_regs.h>
 #include <asm/cputime.h>
+#include <asm/irq.h>
 
 static DEFINE_PER_CPU(struct vtimer_queue, virt_cpu_timer);
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 30ca85cce314..67345ae7ce8d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -731,6 +731,7 @@ static int __init kvm_s390_init(void)
 	}
 	memcpy(facilities, S390_lowcore.stfle_fac_list, 16);
 	facilities[0] &= 0xff00fff3f47c0000ULL;
+	facilities[1] &= 0x201c000000000000ULL;
 	return 0;
 }
 
diff --git a/arch/s390/kvm/sie64a.S b/arch/s390/kvm/sie64a.S
index ab0e041ac54c..5faa1b1b23fa 100644
--- a/arch/s390/kvm/sie64a.S
+++ b/arch/s390/kvm/sie64a.S
@@ -93,4 +93,6 @@ sie_err:
 
 	.section __ex_table,"a"
 	.quad	sie_inst,sie_err
+	.quad	sie_exit,sie_err
+	.quad	sie_reenter,sie_err
 	.previous
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index 0f53110e1d09..a65229d91c92 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/irqflags.h>
 #include <linux/interrupt.h>
+#include <asm/div64.h>
 
 void __delay(unsigned long loops)
 {
@@ -116,3 +117,17 @@ void udelay_simple(unsigned long long usecs)
 	while (get_clock() < end)
 		cpu_relax();
 }
+
+void __ndelay(unsigned long long nsecs)
+{
+	u64 end;
+
+	nsecs <<= 9;
+	do_div(nsecs, 125);
+	end = get_clock() + nsecs;
+	if (nsecs & ~0xfffUL)
+		__udelay(nsecs >> 12);
+	while (get_clock() < end)
+		barrier();
+}
+EXPORT_SYMBOL(__ndelay);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index a0f9e730f26a..fe103e891e7a 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -34,7 +34,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/system.h>
 #include <asm/pgtable.h>
-#include <asm/s390_ext.h>
+#include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/compat.h>
 #include "../kernel/entry.h"
@@ -245,9 +245,12 @@ static noinline void do_fault_error(struct pt_regs *regs, long int_code,
 		do_no_context(regs, int_code, trans_exc_code);
 		break;
 	default: /* fault & VM_FAULT_ERROR */
-		if (fault & VM_FAULT_OOM)
-			pagefault_out_of_memory();
-		else if (fault & VM_FAULT_SIGBUS) {
+		if (fault & VM_FAULT_OOM) {
+			if (!(regs->psw.mask & PSW_MASK_PSTATE))
+				do_no_context(regs, int_code, trans_exc_code);
+			else
+				pagefault_out_of_memory();
+		} else if (fault & VM_FAULT_SIGBUS) {
 			/* Kernel mode? Handle exceptions or die */
 			if (!(regs->psw.mask & PSW_MASK_PSTATE))
 				do_no_context(regs, int_code, trans_exc_code);
@@ -277,7 +280,8 @@ static inline int do_exception(struct pt_regs *regs, int access,
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
 	unsigned long address;
-	int fault, write;
+	unsigned int flags;
+	int fault;
 
 	if (notify_page_fault(regs))
 		return 0;
@@ -296,6 +300,10 @@ static inline int do_exception(struct pt_regs *regs, int access,
 
 	address = trans_exc_code & __FAIL_ADDR_MASK;
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+	flags = FAULT_FLAG_ALLOW_RETRY;
+	if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
+		flags |= FAULT_FLAG_WRITE;
+retry:
 	down_read(&mm->mmap_sem);
 
 	fault = VM_FAULT_BADMAP;
@@ -325,21 +333,31 @@ static inline int do_exception(struct pt_regs *regs, int access,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	write = (access == VM_WRITE ||
-		 (trans_exc_code & store_indication) == 0x400) ?
-		FAULT_FLAG_WRITE : 0;
-	fault = handle_mm_fault(mm, vma, address, write);
+	fault = handle_mm_fault(mm, vma, address, flags);
 	if (unlikely(fault & VM_FAULT_ERROR))
 		goto out_up;
 
-	if (fault & VM_FAULT_MAJOR) {
-		tsk->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
-				     regs, address);
-	} else {
-		tsk->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
-				     regs, address);
+	/*
+	 * Major/minor page fault accounting is only done on the
+	 * initial attempt. If we go through a retry, it is extremely
+	 * likely that the page will be found in page cache at that point.
+	 */
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR) {
+			tsk->maj_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+				      regs, address);
+		} else {
+			tsk->min_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+				      regs, address);
+		}
+		if (fault & VM_FAULT_RETRY) {
+			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
+			 * of starvation. */
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			goto retry;
+		}
 	}
 	/*
 	 * The instruction that caused the program check will
@@ -429,10 +447,9 @@ int __handle_fault(unsigned long uaddr, unsigned long pgm_int_code, int write)
 	access = write ? VM_WRITE : VM_READ;
 	fault = do_exception(&regs, access, uaddr | 2);
 	if (unlikely(fault)) {
-		if (fault & VM_FAULT_OOM) {
-			pagefault_out_of_memory();
-			fault = 0;
-		} else if (fault & VM_FAULT_SIGBUS)
+		if (fault & VM_FAULT_OOM)
+			return -EFAULT;
+		else if (fault & VM_FAULT_SIGBUS)
 			do_sigbus(&regs, pgm_int_code, uaddr);
 	}
 	return fault ? -EFAULT : 0;
@@ -485,7 +502,6 @@ int pfault_init(void)
 		"2:\n"
 		EX_TABLE(0b,1b)
 		: "=d" (rc) : "a" (&refbk), "m" (refbk) : "cc");
-        __ctl_set_bit(0, 9);
         return rc;
 }
 
@@ -500,7 +516,6 @@ void pfault_fini(void)
 
 	if (!MACHINE_IS_VM || pfault_disable)
 		return;
-	__ctl_clear_bit(0,9);
 	asm volatile(
 		"	diag	%0,0,0x258\n"
 		"0:\n"
@@ -615,6 +630,7 @@ static int __init pfault_irq_init(void)
 	rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP;
 	if (rc)
 		goto out_pfault;
+	service_subclass_irq_register();
 	hotcpu_notifier(pfault_cpu_notify, 0);
 	return 0;
 
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index dfefc2171691..59b663109d90 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -119,9 +119,7 @@ void __init paging_init(void)
 	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
 	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-#ifdef CONFIG_ZONE_DMA
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS);
-#endif
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 	free_area_init_nodes(max_zone_pfns);
 	fault_init();
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 71a4b0d34be0..51e5cd9b906a 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -19,7 +19,7 @@
  * using the stura instruction.
  * Returns the number of bytes copied or -EFAULT.
  */
-static long probe_kernel_write_odd(void *dst, void *src, size_t size)
+static long probe_kernel_write_odd(void *dst, const void *src, size_t size)
 {
 	unsigned long count, aligned;
 	int offset, mask;
@@ -45,7 +45,7 @@ static long probe_kernel_write_odd(void *dst, void *src, size_t size)
 	return rc ? rc : count;
 }
 
-long probe_kernel_write(void *dst, void *src, size_t size)
+long probe_kernel_write(void *dst, const void *src, size_t size)
 {
 	long copied = 0;
 
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 14c6fae6fe6b..37a23c223705 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -24,91 +24,12 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 
-struct rcu_table_freelist {
-	struct rcu_head rcu;
-	struct mm_struct *mm;
-	unsigned int pgt_index;
-	unsigned int crst_index;
-	unsigned long *table[0];
-};
-
-#define RCU_FREELIST_SIZE \
-	((PAGE_SIZE - sizeof(struct rcu_table_freelist)) \
-	  / sizeof(unsigned long))
-
-static DEFINE_PER_CPU(struct rcu_table_freelist *, rcu_table_freelist);
-
-static void __page_table_free(struct mm_struct *mm, unsigned long *table);
-
-static struct rcu_table_freelist *rcu_table_freelist_get(struct mm_struct *mm)
-{
-	struct rcu_table_freelist **batchp = &__get_cpu_var(rcu_table_freelist);
-	struct rcu_table_freelist *batch = *batchp;
-
-	if (batch)
-		return batch;
-	batch = (struct rcu_table_freelist *) __get_free_page(GFP_ATOMIC);
-	if (batch) {
-		batch->mm = mm;
-		batch->pgt_index = 0;
-		batch->crst_index = RCU_FREELIST_SIZE;
-		*batchp = batch;
-	}
-	return batch;
-}
-
-static void rcu_table_freelist_callback(struct rcu_head *head)
-{
-	struct rcu_table_freelist *batch =
-		container_of(head, struct rcu_table_freelist, rcu);
-
-	while (batch->pgt_index > 0)
-		__page_table_free(batch->mm, batch->table[--batch->pgt_index]);
-	while (batch->crst_index < RCU_FREELIST_SIZE)
-		crst_table_free(batch->mm, batch->table[batch->crst_index++]);
-	free_page((unsigned long) batch);
-}
-
-void rcu_table_freelist_finish(void)
-{
-	struct rcu_table_freelist *batch = __get_cpu_var(rcu_table_freelist);
-
-	if (!batch)
-		return;
-	call_rcu(&batch->rcu, rcu_table_freelist_callback);
-	__get_cpu_var(rcu_table_freelist) = NULL;
-}
-
-static void smp_sync(void *arg)
-{
-}
-
 #ifndef CONFIG_64BIT
 #define ALLOC_ORDER	1
-#define TABLES_PER_PAGE	4
-#define FRAG_MASK	15UL
-#define SECOND_HALVES	10UL
-
-void clear_table_pgstes(unsigned long *table)
-{
-	clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/4);
-	memset(table + 256, 0, PAGE_SIZE/4);
-	clear_table(table + 512, _PAGE_TYPE_EMPTY, PAGE_SIZE/4);
-	memset(table + 768, 0, PAGE_SIZE/4);
-}
-
+#define FRAG_MASK	0x0f
 #else
 #define ALLOC_ORDER	2
-#define TABLES_PER_PAGE	2
-#define FRAG_MASK	3UL
-#define SECOND_HALVES	2UL
-
-void clear_table_pgstes(unsigned long *table)
-{
-	clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2);
-	memset(table + 256, 0, PAGE_SIZE/2);
-}
-
+#define FRAG_MASK	0x03
 #endif
 
 unsigned long VMALLOC_START = VMALLOC_END - VMALLOC_SIZE;
@@ -137,26 +58,6 @@ void crst_table_free(struct mm_struct *mm, unsigned long *table)
 	free_pages((unsigned long) table, ALLOC_ORDER);
 }
 
-void crst_table_free_rcu(struct mm_struct *mm, unsigned long *table)
-{
-	struct rcu_table_freelist *batch;
-
-	if (atomic_read(&mm->mm_users) < 2 &&
-	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
-		crst_table_free(mm, table);
-		return;
-	}
-	batch = rcu_table_freelist_get(mm);
-	if (!batch) {
-		smp_call_function(smp_sync, NULL, 1);
-		crst_table_free(mm, table);
-		return;
-	}
-	batch->table[--batch->crst_index] = table;
-	if (batch->pgt_index >= batch->crst_index)
-		rcu_table_freelist_finish();
-}
-
 #ifdef CONFIG_64BIT
 int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
 {
@@ -232,121 +133,175 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
 }
 #endif
 
+static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits)
+{
+	unsigned int old, new;
+
+	do {
+		old = atomic_read(v);
+		new = old ^ bits;
+	} while (atomic_cmpxchg(v, old, new) != old);
+	return new;
+}
+
 /*
  * page table entry allocation/free routines.
  */
+#ifdef CONFIG_PGSTE
+static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm)
+{
+	struct page *page;
+	unsigned long *table;
+
+	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+	if (!page)
+		return NULL;
+	pgtable_page_ctor(page);
+	atomic_set(&page->_mapcount, 3);
+	table = (unsigned long *) page_to_phys(page);
+	clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2);
+	clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
+	return table;
+}
+
+static inline void page_table_free_pgste(unsigned long *table)
+{
+	struct page *page;
+
+	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+	pgtable_page_ctor(page);
+	atomic_set(&page->_mapcount, -1);
+	__free_page(page);
+}
+#endif
+
 unsigned long *page_table_alloc(struct mm_struct *mm)
 {
 	struct page *page;
 	unsigned long *table;
-	unsigned long bits;
+	unsigned int mask, bit;
 
-	bits = (mm->context.has_pgste) ? 3UL : 1UL;
+#ifdef CONFIG_PGSTE
+	if (mm_has_pgste(mm))
+		return page_table_alloc_pgste(mm);
+#endif
+	/* Allocate fragments of a 4K page as 1K/2K page table */
 	spin_lock_bh(&mm->context.list_lock);
-	page = NULL;
+	mask = FRAG_MASK;
 	if (!list_empty(&mm->context.pgtable_list)) {
 		page = list_first_entry(&mm->context.pgtable_list,
 					struct page, lru);
-		if ((page->flags & FRAG_MASK) == ((1UL << TABLES_PER_PAGE) - 1))
-			page = NULL;
+		table = (unsigned long *) page_to_phys(page);
+		mask = atomic_read(&page->_mapcount);
+		mask = mask | (mask >> 4);
 	}
-	if (!page) {
+	if ((mask & FRAG_MASK) == FRAG_MASK) {
 		spin_unlock_bh(&mm->context.list_lock);
 		page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
 		if (!page)
 			return NULL;
 		pgtable_page_ctor(page);
-		page->flags &= ~FRAG_MASK;
+		atomic_set(&page->_mapcount, 1);
 		table = (unsigned long *) page_to_phys(page);
-		if (mm->context.has_pgste)
-			clear_table_pgstes(table);
-		else
-			clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
+		clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
 		spin_lock_bh(&mm->context.list_lock);
 		list_add(&page->lru, &mm->context.pgtable_list);
+	} else {
+		for (bit = 1; mask & bit; bit <<= 1)
+			table += PTRS_PER_PTE;
+		mask = atomic_xor_bits(&page->_mapcount, bit);
+		if ((mask & FRAG_MASK) == FRAG_MASK)
+			list_del(&page->lru);
 	}
-	table = (unsigned long *) page_to_phys(page);
-	while (page->flags & bits) {
-		table += 256;
-		bits <<= 1;
-	}
-	page->flags |= bits;
-	if ((page->flags & FRAG_MASK) == ((1UL << TABLES_PER_PAGE) - 1))
-		list_move_tail(&page->lru, &mm->context.pgtable_list);
 	spin_unlock_bh(&mm->context.list_lock);
 	return table;
 }
 
-static void __page_table_free(struct mm_struct *mm, unsigned long *table)
+void page_table_free(struct mm_struct *mm, unsigned long *table)
 {
 	struct page *page;
-	unsigned long bits;
+	unsigned int bit, mask;
 
-	bits = ((unsigned long) table) & 15;
-	table = (unsigned long *)(((unsigned long) table) ^ bits);
+#ifdef CONFIG_PGSTE
+	if (mm_has_pgste(mm))
+		return page_table_free_pgste(table);
+#endif
+	/* Free 1K/2K page table fragment of a 4K page */
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
-	page->flags ^= bits;
-	if (!(page->flags & FRAG_MASK)) {
+	bit = 1 << ((__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t)));
+	spin_lock_bh(&mm->context.list_lock);
+	if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK)
+		list_del(&page->lru);
+	mask = atomic_xor_bits(&page->_mapcount, bit);
+	if (mask & FRAG_MASK)
+		list_add(&page->lru, &mm->context.pgtable_list);
+	spin_unlock_bh(&mm->context.list_lock);
+	if (mask == 0) {
 		pgtable_page_dtor(page);
+		atomic_set(&page->_mapcount, -1);
 		__free_page(page);
 	}
 }
 
-void page_table_free(struct mm_struct *mm, unsigned long *table)
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+
+static void __page_table_free_rcu(void *table, unsigned bit)
 {
 	struct page *page;
-	unsigned long bits;
 
-	bits = (mm->context.has_pgste) ? 3UL : 1UL;
-	bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
+#ifdef CONFIG_PGSTE
+	if (bit == FRAG_MASK)
+		return page_table_free_pgste(table);
+#endif
+	/* Free 1K/2K page table fragment of a 4K page */
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
-	spin_lock_bh(&mm->context.list_lock);
-	page->flags ^= bits;
-	if (page->flags & FRAG_MASK) {
-		/* Page now has some free pgtable fragments. */
-		if (!list_empty(&page->lru))
-			list_move(&page->lru, &mm->context.pgtable_list);
-		page = NULL;
-	} else
-		/* All fragments of the 4K page have been freed. */
-		list_del(&page->lru);
-	spin_unlock_bh(&mm->context.list_lock);
-	if (page) {
+	if (atomic_xor_bits(&page->_mapcount, bit) == 0) {
 		pgtable_page_dtor(page);
+		atomic_set(&page->_mapcount, -1);
 		__free_page(page);
 	}
 }
 
-void page_table_free_rcu(struct mm_struct *mm, unsigned long *table)
+void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table)
 {
-	struct rcu_table_freelist *batch;
+	struct mm_struct *mm;
 	struct page *page;
-	unsigned long bits;
+	unsigned int bit, mask;
 
-	if (atomic_read(&mm->mm_users) < 2 &&
-	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
-		page_table_free(mm, table);
-		return;
-	}
-	batch = rcu_table_freelist_get(mm);
-	if (!batch) {
-		smp_call_function(smp_sync, NULL, 1);
-		page_table_free(mm, table);
+	mm = tlb->mm;
+#ifdef CONFIG_PGSTE
+	if (mm_has_pgste(mm)) {
+		table = (unsigned long *) (__pa(table) | FRAG_MASK);
+		tlb_remove_table(tlb, table);
 		return;
 	}
-	bits = (mm->context.has_pgste) ? 3UL : 1UL;
-	bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
+#endif
+	bit = 1 << ((__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t)));
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	spin_lock_bh(&mm->context.list_lock);
-	/* Delayed freeing with rcu prevents reuse of pgtable fragments */
-	list_del_init(&page->lru);
+	if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK)
+		list_del(&page->lru);
+	mask = atomic_xor_bits(&page->_mapcount, bit | (bit << 4));
+	if (mask & FRAG_MASK)
+		list_add_tail(&page->lru, &mm->context.pgtable_list);
 	spin_unlock_bh(&mm->context.list_lock);
-	table = (unsigned long *)(((unsigned long) table) | bits);
-	batch->table[batch->pgt_index++] = table;
-	if (batch->pgt_index >= batch->crst_index)
-		rcu_table_freelist_finish();
+	table = (unsigned long *) (__pa(table) | (bit << 4));
+	tlb_remove_table(tlb, table);
 }
 
+void __tlb_remove_table(void *_table)
+{
+	void *table = (void *)((unsigned long) _table & PAGE_MASK);
+	unsigned type = (unsigned long) _table & ~PAGE_MASK;
+
+	if (type)
+		__page_table_free_rcu(table, type);
+	else
+		free_pages((unsigned long) table, ALLOC_ORDER);
+}
+
+#endif
+
 /*
  * switch on pgstes for its userspace process (for kvm)
  */
@@ -360,7 +315,7 @@ int s390_enable_sie(void)
 		return -EINVAL;
 
 	/* Do we have pgstes? if yes, we are done */
-	if (tsk->mm->context.has_pgste)
+	if (mm_has_pgste(tsk->mm))
 		return 0;
 
 	/* lets check if we are allowed to replace the mm */
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index 053caa0fd276..4552ce40c81a 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -19,7 +19,7 @@
 #include <linux/oprofile.h>
 
 #include <asm/lowcore.h>
-#include <asm/s390_ext.h>
+#include <asm/irq.h>
 
 #include "hwsampler.h"
 
@@ -580,7 +580,7 @@ static int hws_cpu_callback(struct notifier_block *nfb,
 {
 	/* We do not have sampler space available for all possible CPUs.
 	   All CPUs should be online when hw sampling is activated. */
-	return NOTIFY_BAD;
+	return (hws_state <= HWS_DEALLOCATED) ? NOTIFY_OK : NOTIFY_BAD;
 }
 
 static struct notifier_block hws_cpu_notifier = {
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 5995e9bc72d9..0e358c2cffeb 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -25,7 +25,7 @@ extern void s390_backtrace(struct pt_regs * const regs, unsigned int depth);
 
 #include "hwsampler.h"
 
-#define DEFAULT_INTERVAL	4096
+#define DEFAULT_INTERVAL	4127518
 
 #define DEFAULT_SDBT_BLOCKS	1
 #define DEFAULT_SDB_BLOCKS	511
@@ -151,6 +151,12 @@ static int oprofile_hwsampler_init(struct oprofile_operations *ops)
 	if (oprofile_max_interval == 0)
 		return -ENODEV;
 
+	/* The initial value should be sane */
+	if (oprofile_hw_interval < oprofile_min_interval)
+		oprofile_hw_interval = oprofile_min_interval;
+	if (oprofile_hw_interval > oprofile_max_interval)
+		oprofile_hw_interval = oprofile_max_interval;
+
 	if (oprofile_timer_init(ops))
 		return -ENODEV;
 
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 74495a5ea027..f03338c2f088 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -161,7 +161,7 @@ config ARCH_HAS_CPU_IDLE_WAIT
 
 config NO_IOPORT
 	def_bool !PCI
-	depends on !SH_CAYMAN && !SH_SH4202_MICRODEV
+	depends on !SH_CAYMAN && !SH_SH4202_MICRODEV && !SH_SHMIN
 
 config IO_TRAPPED
 	bool
diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c
index 618bd566cf53..969421f64a15 100644
--- a/arch/sh/boards/mach-ap325rxa/setup.c
+++ b/arch/sh/boards/mach-ap325rxa/setup.c
@@ -359,37 +359,31 @@ static struct soc_camera_link camera_link = {
 	.priv		= &camera_info,
 };
 
-static void dummy_release(struct device *dev)
+static struct platform_device *camera_device;
+
+static void ap325rxa_camera_release(struct device *dev)
 {
+	soc_camera_platform_release(&camera_device);
 }
 
-static struct platform_device camera_device = {
-	.name		= "soc_camera_platform",
-	.dev		= {
-		.platform_data	= &camera_info,
-		.release	= dummy_release,
-	},
-};
-
 static int ap325rxa_camera_add(struct soc_camera_link *icl,
 			       struct device *dev)
 {
-	if (icl != &camera_link || camera_probe() <= 0)
-		return -ENODEV;
+	int ret = soc_camera_platform_add(icl, dev, &camera_device, &camera_link,
+					  ap325rxa_camera_release, 0);
+	if (ret < 0)
+		return ret;
 
-	camera_info.dev = dev;
+	ret = camera_probe();
+	if (ret < 0)
+		soc_camera_platform_del(icl, camera_device, &camera_link);
 
-	return platform_device_register(&camera_device);
+	return ret;
 }
 
 static void ap325rxa_camera_del(struct soc_camera_link *icl)
 {
-	if (icl != &camera_link)
-		return;
-
-	platform_device_unregister(&camera_device);
-	memset(&camera_device.dev.kobj, 0,
-	       sizeof(camera_device.dev.kobj));
+	soc_camera_platform_del(icl, camera_device, &camera_link);
 }
 #endif /* CONFIG_I2C */
 
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index bb13d0e1b964..513cb1a2e6c8 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -20,6 +20,7 @@
 #include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/usb/r8a66597.h>
+#include <linux/usb/renesas_usbhs.h>
 #include <linux/i2c.h>
 #include <linux/i2c/tsc2007.h>
 #include <linux/spi/spi.h>
@@ -232,6 +233,52 @@ static struct platform_device usb1_common_device = {
 	.resource	= usb1_common_resources,
 };
 
+/*
+ * USBHS
+ */
+static int usbhs_get_id(struct platform_device *pdev)
+{
+	return gpio_get_value(GPIO_PTB3);
+}
+
+static struct renesas_usbhs_platform_info usbhs_info = {
+	.platform_callback = {
+		.get_id		= usbhs_get_id,
+	},
+	.driver_param = {
+		.buswait_bwait		= 4,
+		.detection_delay	= 5,
+	},
+};
+
+static struct resource usbhs_resources[] = {
+	[0] = {
+		.start	= 0xa4d90000,
+		.end	= 0xa4d90124 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 66,
+		.end	= 66,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device usbhs_device = {
+	.name	= "renesas_usbhs",
+	.id	= 1,
+	.dev = {
+		.dma_mask		= NULL,         /*  not use dma */
+		.coherent_dma_mask	= 0xffffffff,
+		.platform_data		= &usbhs_info,
+	},
+	.num_resources	= ARRAY_SIZE(usbhs_resources),
+	.resource	= usbhs_resources,
+	.archdata = {
+		.hwblk_id = HWBLK_USB1,
+	},
+};
+
 /* LCDC */
 const static struct fb_videomode ecovec_lcd_modes[] = {
 	{
@@ -885,6 +932,9 @@ static struct platform_device sh_mmcif_device = {
 	},
 	.num_resources	= ARRAY_SIZE(sh_mmcif_resources),
 	.resource	= sh_mmcif_resources,
+	.archdata = {
+		.hwblk_id = HWBLK_MMC,
+	},
 };
 #endif
 
@@ -894,6 +944,7 @@ static struct platform_device *ecovec_devices[] __initdata = {
 	&sh_eth_device,
 	&usb0_host_device,
 	&usb1_common_device,
+	&usbhs_device,
 	&lcdc_device,
 	&ceu0_device,
 	&ceu1_device,
diff --git a/arch/sh/boot/compressed/Makefile b/arch/sh/boot/compressed/Makefile
index 780e083e4d17..23bc849d9c64 100644
--- a/arch/sh/boot/compressed/Makefile
+++ b/arch/sh/boot/compressed/Makefile
@@ -27,8 +27,6 @@ IMAGE_OFFSET	:= $(shell /bin/bash -c 'printf "0x%08x" \
 			$(CONFIG_BOOT_LINK_OFFSET)]')
 endif
 
-LIBGCC	:= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
-
 ifeq ($(CONFIG_MCOUNT),y)
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
 KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
@@ -37,7 +35,25 @@ endif
 LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(IMAGE_OFFSET) -e startup \
 		   -T $(obj)/../../kernel/vmlinux.lds
 
-$(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o $(LIBGCC) FORCE
+#
+# Pull in the necessary libgcc bits from the in-kernel implementation.
+#
+lib1funcs-$(CONFIG_SUPERH32)	:= ashiftrt.S ashldi3.c ashrsi3.S ashlsi3.S \
+				   lshrsi3.S
+lib1funcs-obj			:= \
+	$(addsuffix .o, $(basename $(addprefix $(obj)/, $(lib1funcs-y))))
+
+lib1funcs-dir		:= $(srctree)/arch/$(SRCARCH)/lib
+ifeq ($(BITS),64)
+	lib1funcs-dir 	:= $(addsuffix $(BITS), $(lib1funcs-dir))
+endif
+
+KBUILD_CFLAGS += -I$(lib1funcs-dir)
+
+$(addprefix $(obj)/,$(lib1funcs-y)): $(obj)/%: $(lib1funcs-dir)/% FORCE
+	$(call cmd,shipped)
+
+$(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o $(lib1funcs-obj) FORCE
 	$(call if_changed,ld)
 	@:
 
diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig
index 0f558914e760..e2cbd92d520b 100644
--- a/arch/sh/configs/titan_defconfig
+++ b/arch/sh/configs/titan_defconfig
@@ -227,7 +227,7 @@ CONFIG_USB_SERIAL=m
 CONFIG_USB_SERIAL_GENERIC=y
 CONFIG_USB_SERIAL_ARK3116=m
 CONFIG_USB_SERIAL_PL2303=m
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_SH=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
diff --git a/arch/sh/include/asm/cmpxchg-grb.h b/arch/sh/include/asm/cmpxchg-grb.h
index 4676bf57693a..f848dec9e483 100644
--- a/arch/sh/include/asm/cmpxchg-grb.h
+++ b/arch/sh/include/asm/cmpxchg-grb.h
@@ -15,8 +15,9 @@ static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
 		"   mov.l   %2,   @%1     \n\t" /* store new value */
 		"1: mov     r1,   r15     \n\t" /* LOGOUT */
 		: "=&r" (retval),
-		  "+r"  (m)
-		: "r"   (val)
+		  "+r"  (m),
+		  "+r"  (val)		/* inhibit r15 overloading */
+		:
 		: "memory", "r0", "r1");
 
 	return retval;
@@ -36,8 +37,9 @@ static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
 		"   mov.b   %2,   @%1     \n\t" /* store new value */
 		"1: mov     r1,   r15     \n\t" /* LOGOUT */
 		: "=&r" (retval),
-		  "+r"  (m)
-		: "r"   (val)
+		  "+r"  (m),
+		  "+r"  (val)		/* inhibit r15 overloading */
+		:
 		: "memory" , "r0", "r1");
 
 	return retval;
@@ -54,13 +56,14 @@ static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old,
 		"   nop                   \n\t"
 		"   mov    r15,   r1      \n\t" /* r1 = saved sp */
 		"   mov    #-8,   r15     \n\t" /* LOGIN */
-		"   mov.l  @%1,   %0      \n\t" /* load  old value */
-		"   cmp/eq  %0,   %2      \n\t"
+		"   mov.l  @%3,   %0      \n\t" /* load  old value */
+		"   cmp/eq  %0,   %1      \n\t"
 		"   bf            1f      \n\t" /* if not equal */
-		"   mov.l   %3,   @%1     \n\t" /* store new value */
+		"   mov.l   %2,   @%3     \n\t" /* store new value */
 		"1: mov     r1,   r15     \n\t" /* LOGOUT */
-		: "=&r" (retval)
-		:  "r"  (m), "r"  (old), "r"  (new)
+		: "=&r" (retval),
+		  "+r"  (old), "+r"  (new) /* old or new can be r15 */
+		:  "r"  (m)
 		: "memory" , "r0", "r1", "t");
 
 	return retval;
diff --git a/arch/sh/include/asm/mmzone.h b/arch/sh/include/asm/mmzone.h
index 8887baff5eff..15a8496960e6 100644
--- a/arch/sh/include/asm/mmzone.h
+++ b/arch/sh/include/asm/mmzone.h
@@ -9,10 +9,6 @@
 extern struct pglist_data *node_data[];
 #define NODE_DATA(nid)		(node_data[nid])
 
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)	(NODE_DATA(nid)->node_start_pfn + \
-				 NODE_DATA(nid)->node_spanned_pages)
-
 static inline int pfn_to_nid(unsigned long pfn)
 {
 	int nid;
diff --git a/arch/sh/include/asm/pgtable.h b/arch/sh/include/asm/pgtable.h
index db85916b9e95..9210e93a92c3 100644
--- a/arch/sh/include/asm/pgtable.h
+++ b/arch/sh/include/asm/pgtable.h
@@ -18,6 +18,7 @@
 #include <asm/pgtable-2level.h>
 #endif
 #include <asm/page.h>
+#include <asm/mmu.h>
 
 #ifndef __ASSEMBLY__
 #include <asm/addrspace.h>
diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h
index 2a541ddb5a1b..e25c4c7d6b63 100644
--- a/arch/sh/include/asm/processor_64.h
+++ b/arch/sh/include/asm/processor_64.h
@@ -150,7 +150,6 @@ struct thread_struct {
 #define SR_USER (SR_MMU | SR_FD)
 
 #define start_thread(_regs, new_pc, new_sp)			\
-	set_fs(USER_DS);					\
 	_regs->sr = SR_USER;	/* User mode. */		\
 	_regs->pc = new_pc - 4;	/* Compensate syscall exit */	\
 	_regs->pc |= 1;		/* Set SHmedia ! */		\
diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h
index 40725b4a8018..88bd6be168a9 100644
--- a/arch/sh/include/asm/ptrace.h
+++ b/arch/sh/include/asm/ptrace.h
@@ -41,7 +41,9 @@
 
 #define user_mode(regs)			(((regs)->sr & 0x40000000)==0)
 #define kernel_stack_pointer(_regs)	((unsigned long)(_regs)->regs[15])
-#define GET_USP(regs) ((regs)->regs[15])
+
+#define GET_FP(regs)	((regs)->regs[14])
+#define GET_USP(regs)	((regs)->regs[15])
 
 extern void show_regs(struct pt_regs *);
 
@@ -131,7 +133,7 @@ extern void ptrace_triggered(struct perf_event *bp, int nmi,
 
 static inline unsigned long profile_pc(struct pt_regs *regs)
 {
-	unsigned long pc = instruction_pointer(regs);
+	unsigned long pc = regs->pc;
 
 	if (virt_addr_uncached(pc))
 		return CAC_ADDR(pc);
diff --git a/arch/sh/include/asm/suspend.h b/arch/sh/include/asm/suspend.h
index 64eb41a063e8..e14567a7e9a1 100644
--- a/arch/sh/include/asm/suspend.h
+++ b/arch/sh/include/asm/suspend.h
@@ -3,7 +3,6 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/notifier.h>
-static inline int arch_prepare_suspend(void) { return 0; }
 
 #include <asm/ptrace.h>
 
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 6c308d8b9a50..ec88bfcdf7ce 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -9,6 +9,7 @@
 #include <linux/pagemap.h>
 
 #ifdef CONFIG_MMU
+#include <linux/swap.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
diff --git a/arch/sh/include/asm/unistd_32.h b/arch/sh/include/asm/unistd_32.h
index bb7d2702c2c9..3432008d2888 100644
--- a/arch/sh/include/asm/unistd_32.h
+++ b/arch/sh/include/asm/unistd_32.h
@@ -374,8 +374,9 @@
 #define __NR_clock_adjtime	361
 #define __NR_syncfs		362
 #define __NR_sendmmsg		363
+#define __NR_setns		364
 
-#define NR_syscalls 364
+#define NR_syscalls 365
 
 #ifdef __KERNEL__
 
diff --git a/arch/sh/include/asm/unistd_64.h b/arch/sh/include/asm/unistd_64.h
index 46327cea1e5c..ec9898665f23 100644
--- a/arch/sh/include/asm/unistd_64.h
+++ b/arch/sh/include/asm/unistd_64.h
@@ -395,10 +395,11 @@
 #define __NR_clock_adjtime	372
 #define __NR_syncfs		373
 #define __NR_sendmmsg		374
+#define __NR_setns		375
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 375
+#define NR_syscalls 376
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7722.h b/arch/sh/include/cpu-sh4/cpu/sh7722.h
index 7a5b8a331b4a..bd0622788d64 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7722.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7722.h
@@ -236,6 +236,7 @@ enum {
 };
 
 enum {
+	SHDMA_SLAVE_INVALID,
 	SHDMA_SLAVE_SCIF0_TX,
 	SHDMA_SLAVE_SCIF0_RX,
 	SHDMA_SLAVE_SCIF1_TX,
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7724.h b/arch/sh/include/cpu-sh4/cpu/sh7724.h
index 7eb435999426..cbc47e6bcab5 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7724.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7724.h
@@ -285,6 +285,7 @@ enum {
 };
 
 enum {
+	SHDMA_SLAVE_INVALID,
 	SHDMA_SLAVE_SCIF0_TX,
 	SHDMA_SLAVE_SCIF0_RX,
 	SHDMA_SLAVE_SCIF1_TX,
@@ -297,6 +298,14 @@ enum {
 	SHDMA_SLAVE_SCIF4_RX,
 	SHDMA_SLAVE_SCIF5_TX,
 	SHDMA_SLAVE_SCIF5_RX,
+	SHDMA_SLAVE_USB0D0_TX,
+	SHDMA_SLAVE_USB0D0_RX,
+	SHDMA_SLAVE_USB0D1_TX,
+	SHDMA_SLAVE_USB0D1_RX,
+	SHDMA_SLAVE_USB1D0_TX,
+	SHDMA_SLAVE_USB1D0_RX,
+	SHDMA_SLAVE_USB1D1_TX,
+	SHDMA_SLAVE_USB1D1_RX,
 	SHDMA_SLAVE_SDHI0_TX,
 	SHDMA_SLAVE_SDHI0_RX,
 	SHDMA_SLAVE_SDHI1_TX,
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7757.h b/arch/sh/include/cpu-sh4/cpu/sh7757.h
index 05b8196c7753..41f9f8b9db73 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7757.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7757.h
@@ -252,6 +252,7 @@ enum {
 };
 
 enum {
+	SHDMA_SLAVE_INVALID,
 	SHDMA_SLAVE_SDHI_TX,
 	SHDMA_SLAVE_SDHI_RX,
 	SHDMA_SLAVE_MMCIF_TX,
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c
index 0333fe9e3881..134a397b1918 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c
@@ -93,6 +93,46 @@ static const struct sh_dmae_slave_config sh7724_dmae_slaves[] = {
 		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
 		.mid_rid	= 0x36,
 	}, {
+		.slave_id	= SHDMA_SLAVE_USB0D0_TX,
+		.addr		= 0xA4D80100,
+		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT),
+		.mid_rid	= 0x73,
+	}, {
+		.slave_id	= SHDMA_SLAVE_USB0D0_RX,
+		.addr		= 0xA4D80100,
+		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT),
+		.mid_rid	= 0x73,
+	}, {
+		.slave_id	= SHDMA_SLAVE_USB0D1_TX,
+		.addr		= 0xA4D80120,
+		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT),
+		.mid_rid	= 0x77,
+	}, {
+		.slave_id	= SHDMA_SLAVE_USB0D1_RX,
+		.addr		= 0xA4D80120,
+		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT),
+		.mid_rid	= 0x77,
+	}, {
+		.slave_id	= SHDMA_SLAVE_USB1D0_TX,
+		.addr		= 0xA4D90100,
+		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT),
+		.mid_rid	= 0xab,
+	}, {
+		.slave_id	= SHDMA_SLAVE_USB1D0_RX,
+		.addr		= 0xA4D90100,
+		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT),
+		.mid_rid	= 0xab,
+	}, {
+		.slave_id	= SHDMA_SLAVE_USB1D1_TX,
+		.addr		= 0xA4D90120,
+		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT),
+		.mid_rid	= 0xaf,
+	}, {
+		.slave_id	= SHDMA_SLAVE_USB1D1_RX,
+		.addr		= 0xA4D90120,
+		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT),
+		.mid_rid	= 0xaf,
+	}, {
 		.slave_id	= SHDMA_SLAVE_SDHI0_TX,
 		.addr		= 0x04ce0030,
 		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_16BIT),
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 762a13984bbd..aaf6d59c2012 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -21,6 +21,7 @@
 #include <linux/fs.h>
 #include <linux/ftrace.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/prefetch.h>
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/system.h>
@@ -101,8 +102,6 @@ EXPORT_SYMBOL(kernel_thread);
 void start_thread(struct pt_regs *regs, unsigned long new_pc,
 		  unsigned long new_sp)
 {
-	set_fs(USER_DS);
-
 	regs->pr = 0;
 	regs->sr = SR_FD;
 	regs->pc = new_pc;
diff --git a/arch/sh/kernel/syscalls_32.S b/arch/sh/kernel/syscalls_32.S
index 7c486f3e3a3c..39b051de4c7c 100644
--- a/arch/sh/kernel/syscalls_32.S
+++ b/arch/sh/kernel/syscalls_32.S
@@ -381,3 +381,4 @@ ENTRY(sys_call_table)
 	.long sys_clock_adjtime
 	.long sys_syncfs
 	.long sys_sendmmsg
+	.long sys_setns
diff --git a/arch/sh/kernel/syscalls_64.S b/arch/sh/kernel/syscalls_64.S
index ba1a737afe80..089c4d825d08 100644
--- a/arch/sh/kernel/syscalls_64.S
+++ b/arch/sh/kernel/syscalls_64.S
@@ -401,3 +401,4 @@ sys_call_table:
 	.long sys_clock_adjtime
 	.long sys_syncfs
 	.long sys_sendmmsg
+	.long sys_setns			/* 375 */
diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c
index 52411462c409..115725198038 100644
--- a/arch/sh/mm/cache-debugfs.c
+++ b/arch/sh/mm/cache-debugfs.c
@@ -26,9 +26,9 @@ static int cache_seq_show(struct seq_file *file, void *iter)
 {
 	unsigned int cache_type = (unsigned int)file->private;
 	struct cache_info *cache;
-	unsigned int waysize, way, cache_size;
-	unsigned long ccr, base;
-	static unsigned long addrstart = 0;
+	unsigned int waysize, way;
+	unsigned long ccr;
+	unsigned long addrstart = 0;
 
 	/*
 	 * Go uncached immediately so we don't skew the results any
@@ -45,28 +45,13 @@ static int cache_seq_show(struct seq_file *file, void *iter)
 	}
 
 	if (cache_type == CACHE_TYPE_DCACHE) {
-		base = CACHE_OC_ADDRESS_ARRAY;
+		addrstart = CACHE_OC_ADDRESS_ARRAY;
 		cache = &current_cpu_data.dcache;
 	} else {
-		base = CACHE_IC_ADDRESS_ARRAY;
+		addrstart = CACHE_IC_ADDRESS_ARRAY;
 		cache = &current_cpu_data.icache;
 	}
 
-	/*
-	 * Due to the amount of data written out (depending on the cache size),
-	 * we may be iterated over multiple times. In this case, keep track of
-	 * the entry position in addrstart, and rewind it when we've hit the
-	 * end of the cache.
-	 *
-	 * Likewise, the same code is used for multiple caches, so care must
-	 * be taken for bouncing addrstart back and forth so the appropriate
-	 * cache is hit.
-	 */
-	cache_size = cache->ways * cache->sets * cache->linesz;
-	if (((addrstart & 0xff000000) != base) ||
-	     (addrstart & 0x00ffffff) > cache_size)
-		addrstart = base;
-
 	waysize = cache->sets;
 
 	/*
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index 40733a952402..f251b5f27652 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -82,7 +82,7 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	void *addr;
 
 	addr = __in_29bit_mode() ?
-	       (void *)P1SEGADDR((unsigned long)vaddr) : vaddr;
+	       (void *)CAC_ADDR((unsigned long)vaddr) : vaddr;
 
 	switch (direction) {
 	case DMA_FROM_DEVICE:		/* invalidate only */
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index af32e17fa170..253986bd6bb6 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -26,7 +26,6 @@ config SPARC
 	select HAVE_DMA_API_DEBUG
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_GENERIC_HARDIRQS
-	select GENERIC_HARDIRQS_NO_DEPRECATED
 	select GENERIC_IRQ_SHOW
 	select USE_GENERIC_SMP_HELPERS if SMP
 
@@ -528,6 +527,23 @@ config PCI_DOMAINS
 config PCI_SYSCALL
 	def_bool PCI
 
+config PCIC_PCI
+	bool
+	depends on PCI && SPARC32 && !SPARC_LEON
+	default y
+
+config LEON_PCI
+	bool
+	depends on PCI && SPARC_LEON
+	default y
+
+config GRPCI2
+	bool "GRPCI2 Host Bridge Support"
+	depends on LEON_PCI
+	default y
+	help
+	  Say Y here to include the GRPCI2 Host Bridge Driver.
+
 source "drivers/pci/Kconfig"
 
 source "drivers/pcmcia/Kconfig"
diff --git a/arch/sparc/include/asm/floppy_32.h b/arch/sparc/include/asm/floppy_32.h
index 482c79e2a416..7440915e86d8 100644
--- a/arch/sparc/include/asm/floppy_32.h
+++ b/arch/sparc/include/asm/floppy_32.h
@@ -138,7 +138,7 @@ static unsigned char sun_82072_fd_inb(int port)
 		return sun_fdc->data_82072;
 	case 7: /* FD_DIR */
 		return sun_read_dir();
-	};
+	}
 	panic("sun_82072_fd_inb: How did I get here?");
 }
 
@@ -161,7 +161,7 @@ static void sun_82072_fd_outb(unsigned char value, int port)
 	case 4: /* FD_STATUS */
 		sun_fdc->status_82072 = value;
 		break;
-	};
+	}
 	return;
 }
 
@@ -186,7 +186,7 @@ static unsigned char sun_82077_fd_inb(int port)
 		return sun_fdc->data_82077;
 	case 7: /* FD_DIR */
 		return sun_read_dir();
-	};
+	}
 	panic("sun_82077_fd_inb: How did I get here?");
 }
 
@@ -212,7 +212,7 @@ static void sun_82077_fd_outb(unsigned char value, int port)
 	case 3: /* FD_TDR */
 		sun_fdc->tapectl_82077 = value;
 		break;
-	};
+	}
 	return;
 }
 
diff --git a/arch/sparc/include/asm/floppy_64.h b/arch/sparc/include/asm/floppy_64.h
index 6597ce874d78..bcef1f5a2a6d 100644
--- a/arch/sparc/include/asm/floppy_64.h
+++ b/arch/sparc/include/asm/floppy_64.h
@@ -111,7 +111,7 @@ static unsigned char sun_82077_fd_inb(unsigned long port)
 	case 7: /* FD_DIR */
 		/* XXX: Is DCL on 0x80 in sun4m? */
 		return sbus_readb(&sun_fdc->dir_82077);
-	};
+	}
 	panic("sun_82072_fd_inb: How did I get here?");
 }
 
@@ -135,7 +135,7 @@ static void sun_82077_fd_outb(unsigned char value, unsigned long port)
 	case 4: /* FD_STATUS */
 		sbus_writeb(value, &sun_fdc->status_82077);
 		break;
-	};
+	}
 	return;
 }
 
diff --git a/arch/sparc/include/asm/leon.h b/arch/sparc/include/asm/leon.h
index 6bdaf1e43d2a..a4e457f003ed 100644
--- a/arch/sparc/include/asm/leon.h
+++ b/arch/sparc/include/asm/leon.h
@@ -318,6 +318,9 @@ struct device_node;
 extern unsigned int leon_build_device_irq(unsigned int real_irq,
 					   irq_flow_handler_t flow_handler,
 					   const char *name, int do_ack);
+extern void leon_update_virq_handling(unsigned int virq,
+			      irq_flow_handler_t flow_handler,
+			      const char *name, int do_ack);
 extern void leon_clear_clock_irq(void);
 extern void leon_load_profile_irq(int cpu, unsigned int limit);
 extern void leon_init_timers(irq_handler_t counter_fn);
diff --git a/arch/sparc/include/asm/leon_pci.h b/arch/sparc/include/asm/leon_pci.h
new file mode 100644
index 000000000000..42b4b31a82fe
--- /dev/null
+++ b/arch/sparc/include/asm/leon_pci.h
@@ -0,0 +1,21 @@
+/*
+ * asm/leon_pci.h
+ *
+ * Copyright (C) 2011 Aeroflex Gaisler AB, Daniel Hellstrom
+ */
+
+#ifndef _ASM_LEON_PCI_H_
+#define _ASM_LEON_PCI_H_
+
+/* PCI related definitions */
+struct leon_pci_info {
+	struct pci_ops *ops;
+	struct resource	io_space;
+	struct resource	mem_space;
+	int (*map_irq)(struct pci_dev *dev, u8 slot, u8 pin);
+};
+
+extern void leon_pci_init(struct platform_device *ofdev,
+				struct leon_pci_info *info);
+
+#endif /* _ASM_LEON_PCI_H_ */
diff --git a/arch/sparc/include/asm/mmzone.h b/arch/sparc/include/asm/mmzone.h
index e8c648741ed4..99d9b9f577bf 100644
--- a/arch/sparc/include/asm/mmzone.h
+++ b/arch/sparc/include/asm/mmzone.h
@@ -8,8 +8,6 @@
 extern struct pglist_data *node_data[];
 
 #define NODE_DATA(nid)		(node_data[nid])
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)	(NODE_DATA(nid)->node_end_pfn)
 
 extern int numa_cpu_lookup_table[];
 extern cpumask_t numa_cpumask_lookup_table[];
diff --git a/arch/sparc/include/asm/pci_32.h b/arch/sparc/include/asm/pci_32.h
index 332ac9ab36bc..862e3ce92b15 100644
--- a/arch/sparc/include/asm/pci_32.h
+++ b/arch/sparc/include/asm/pci_32.h
@@ -47,7 +47,31 @@ extern struct device_node *pci_device_to_OF_node(struct pci_dev *pdev);
 
 #endif /* __KERNEL__ */
 
+#ifndef CONFIG_LEON_PCI
 /* generic pci stuff */
 #include <asm-generic/pci.h>
+#else
+/*
+ * On LEON PCI Memory space is mapped 1:1 with physical address space.
+ *
+ * I/O space is located at low 64Kbytes in PCI I/O space. The I/O addresses
+ * are converted into CPU addresses to virtual addresses that are mapped with
+ * MMU to the PCI Host PCI I/O space window which are translated to the low
+ * 64Kbytes by the Host controller.
+ */
+
+extern void
+pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
+			struct resource *res);
+
+extern void
+pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res,
+			struct pci_bus_region *region);
+
+static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
+{
+	return PCI_IRQ_NONE;
+}
+#endif
 
 #endif /* __SPARC_PCI_H */
diff --git a/arch/sparc/include/asm/pcic.h b/arch/sparc/include/asm/pcic.h
index 7eb5d78f5211..6676cbcc8b6a 100644
--- a/arch/sparc/include/asm/pcic.h
+++ b/arch/sparc/include/asm/pcic.h
@@ -29,7 +29,7 @@ struct linux_pcic {
 	int			pcic_imdim;
 };
 
-#ifdef CONFIG_PCI
+#ifdef CONFIG_PCIC_PCI
 extern int pcic_present(void);
 extern int pcic_probe(void);
 extern void pci_time_init(void);
diff --git a/arch/sparc/include/asm/system_32.h b/arch/sparc/include/asm/system_32.h
index 47a7e862474e..aba16092a81b 100644
--- a/arch/sparc/include/asm/system_32.h
+++ b/arch/sparc/include/asm/system_32.h
@@ -220,7 +220,7 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int
 	switch (size) {
 	case 4:
 		return xchg_u32(ptr, x);
-	};
+	}
 	__xchg_called_with_bad_pointer();
 	return x;
 }
diff --git a/arch/sparc/include/asm/system_64.h b/arch/sparc/include/asm/system_64.h
index 3c96d3bb9f15..10bcabce97b2 100644
--- a/arch/sparc/include/asm/system_64.h
+++ b/arch/sparc/include/asm/system_64.h
@@ -234,7 +234,7 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr,
 		return xchg32(ptr, x);
 	case 8:
 		return xchg64(ptr, x);
-	};
+	}
 	__xchg_called_with_bad_pointer();
 	return x;
 }
diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h
index c5387ed0add8..6260d5deeabc 100644
--- a/arch/sparc/include/asm/unistd.h
+++ b/arch/sparc/include/asm/unistd.h
@@ -405,8 +405,9 @@
 #define __NR_clock_adjtime	334
 #define __NR_syncfs		335
 #define __NR_sendmmsg		336
+#define __NR_setns		337
 
-#define NR_syscalls		337
+#define NR_syscalls		338
 
 #ifdef __32bit_syscall_numbers__
 /* Sparc 32-bit only has the "setresuid32", "getresuid32" variants,
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 9cff2709a96d..b90b4a1d070a 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -73,7 +73,9 @@ obj-$(CONFIG_SPARC64_SMP) += cpumap.o
 
 obj-y                     += dma.o
 
-obj-$(CONFIG_SPARC32_PCI) += pcic.o
+obj-$(CONFIG_PCIC_PCI)    += pcic.o
+obj-$(CONFIG_LEON_PCI)    += leon_pci.o
+obj-$(CONFIG_GRPCI2)      += leon_pci_grpci2.o
 
 obj-$(CONFIG_SMP)         += trampoline_$(BITS).o smp_$(BITS).o
 obj-$(CONFIG_SPARC32_SMP) += sun4m_smp.o sun4d_smp.o leon_smp.o
diff --git a/arch/sparc/kernel/apc.c b/arch/sparc/kernel/apc.c
index 1e34f29e58bb..caef9deb5866 100644
--- a/arch/sparc/kernel/apc.c
+++ b/arch/sparc/kernel/apc.c
@@ -123,7 +123,7 @@ static long apc_ioctl(struct file *f, unsigned int cmd, unsigned long __arg)
 
 	default:
 		return -EINVAL;
-	};
+	}
 
 	return 0;
 }
diff --git a/arch/sparc/kernel/auxio_32.c b/arch/sparc/kernel/auxio_32.c
index 8505e0ac78ba..acf5151f3c1d 100644
--- a/arch/sparc/kernel/auxio_32.c
+++ b/arch/sparc/kernel/auxio_32.c
@@ -101,7 +101,7 @@ void set_auxio(unsigned char bits_on, unsigned char bits_off)
 		break;
 	default:
 		panic("Can't set AUXIO register on this machine.");
-	};
+	}
 	spin_unlock_irqrestore(&auxio_lock, flags);
 }
 EXPORT_SYMBOL(set_auxio);
diff --git a/arch/sparc/kernel/chmc.c b/arch/sparc/kernel/chmc.c
index 668c7be5d365..5f450260981d 100644
--- a/arch/sparc/kernel/chmc.c
+++ b/arch/sparc/kernel/chmc.c
@@ -664,7 +664,7 @@ static void chmc_interpret_one_decode_reg(struct chmc *p, int which_bank, u64 va
 	case 0x0:
 		bp->interleave = 16;
 		break;
-	};
+	}
 
 	/* UK[10] is reserved, and UK[11] is not set for the SDRAM
 	 * bank size definition.
diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index 8341963f4c84..9fe08a1ea6c6 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -229,7 +229,7 @@ real_irq_entry:
 #ifdef CONFIG_SMP
 	.globl	patchme_maybe_smp_msg
 
-	cmp	%l7, 12
+	cmp	%l7, 11
 patchme_maybe_smp_msg:
 	bgu	maybe_smp4m_msg
 	 nop
@@ -293,7 +293,7 @@ maybe_smp4m_msg:
 	WRITE_PAUSE
 	wr	%l4, PSR_ET, %psr
 	WRITE_PAUSE
-	sll	%o2, 28, %o2		! shift for simpler checks below
+	sll	%o3, 28, %o2		! shift for simpler checks below
 maybe_smp4m_msg_check_single:
 	andcc	%o2, 0x1, %g0
 	beq,a	maybe_smp4m_msg_check_mask
@@ -1604,7 +1604,7 @@ restore_current:
 	retl
 	 nop
 
-#ifdef CONFIG_PCI
+#ifdef CONFIG_PCIC_PCI
 #include <asm/pcic.h>
 
 	.align	4
@@ -1650,7 +1650,7 @@ pcic_nmi_trap_patch:
 	 rd	%psr, %l0
 	.word	0
 
-#endif /* CONFIG_PCI */
+#endif /* CONFIG_PCIC_PCI */
 
 	.globl	flushw_all
 flushw_all:
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index 2f538ac2e139..d17255a2bbac 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -236,6 +236,21 @@ static unsigned int _leon_build_device_irq(struct platform_device *op,
 	return leon_build_device_irq(real_irq, handle_simple_irq, "edge", 0);
 }
 
+void leon_update_virq_handling(unsigned int virq,
+			      irq_flow_handler_t flow_handler,
+			      const char *name, int do_ack)
+{
+	unsigned long mask = (unsigned long)irq_get_chip_data(virq);
+
+	mask &= ~LEON_DO_ACK_HW;
+	if (do_ack)
+		mask |= LEON_DO_ACK_HW;
+
+	irq_set_chip_and_handler_name(virq, &leon_irq,
+				      flow_handler, name);
+	irq_set_chip_data(virq, (void *)mask);
+}
+
 void __init leon_init_timers(irq_handler_t counter_fn)
 {
 	int irq, eirq;
@@ -361,6 +376,22 @@ void __init leon_init_timers(irq_handler_t counter_fn)
 		prom_halt();
 	}
 
+#ifdef CONFIG_SMP
+	{
+		unsigned long flags;
+
+		/*
+		 * In SMP, sun4m adds a IPI handler to IRQ trap handler that
+		 * LEON never must take, sun4d and LEON overwrites the branch
+		 * with a NOP.
+		 */
+		local_irq_save(flags);
+		patchme_maybe_smp_msg[0] = 0x01000000; /* NOP out the branch */
+		local_flush_cache_all();
+		local_irq_restore(flags);
+	}
+#endif
+
 	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl,
 			      LEON3_GPTIMER_EN |
 			      LEON3_GPTIMER_RL |
diff --git a/arch/sparc/kernel/leon_pci.c b/arch/sparc/kernel/leon_pci.c
new file mode 100644
index 000000000000..a8a9a275037d
--- /dev/null
+++ b/arch/sparc/kernel/leon_pci.c
@@ -0,0 +1,253 @@
+/*
+ * leon_pci.c: LEON Host PCI support
+ *
+ * Copyright (C) 2011 Aeroflex Gaisler AB, Daniel Hellstrom
+ *
+ * Code is partially derived from pcic.c
+ */
+
+#include <linux/of_device.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <asm/leon.h>
+#include <asm/leon_pci.h>
+
+/* The LEON architecture does not rely on a BIOS or bootloader to setup
+ * PCI for us. The Linux generic routines are used to setup resources,
+ * reset values of confuration-space registers settings ae preseved.
+ */
+void leon_pci_init(struct platform_device *ofdev, struct leon_pci_info *info)
+{
+	struct pci_bus *root_bus;
+
+	root_bus = pci_scan_bus_parented(&ofdev->dev, 0, info->ops, info);
+	if (root_bus) {
+		root_bus->resource[0] = &info->io_space;
+		root_bus->resource[1] = &info->mem_space;
+		root_bus->resource[2] = NULL;
+
+		/* Init all PCI devices into PCI tree */
+		pci_bus_add_devices(root_bus);
+
+		/* Setup IRQs of all devices using custom routines */
+		pci_fixup_irqs(pci_common_swizzle, info->map_irq);
+
+		/* Assign devices with resources */
+		pci_assign_unassigned_resources();
+	}
+}
+
+/* PCI Memory and Prefetchable Memory is direct-mapped. However I/O Space is
+ * accessed through a Window which is translated to low 64KB in PCI space, the
+ * first 4KB is not used so 60KB is available.
+ *
+ * This function is used by generic code to translate resource addresses into
+ * PCI addresses.
+ */
+void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
+			     struct resource *res)
+{
+	struct leon_pci_info *info = dev->bus->sysdata;
+
+	region->start = res->start;
+	region->end = res->end;
+
+	if (res->flags & IORESOURCE_IO) {
+		region->start -= (info->io_space.start - 0x1000);
+		region->end -= (info->io_space.start - 0x1000);
+	}
+}
+EXPORT_SYMBOL(pcibios_resource_to_bus);
+
+/* see pcibios_resource_to_bus() comment */
+void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res,
+			     struct pci_bus_region *region)
+{
+	struct leon_pci_info *info = dev->bus->sysdata;
+
+	res->start = region->start;
+	res->end = region->end;
+
+	if (res->flags & IORESOURCE_IO) {
+		res->start += (info->io_space.start - 0x1000);
+		res->end += (info->io_space.start - 0x1000);
+	}
+}
+EXPORT_SYMBOL(pcibios_bus_to_resource);
+
+void __devinit pcibios_fixup_bus(struct pci_bus *pbus)
+{
+	struct leon_pci_info *info = pbus->sysdata;
+	struct pci_dev *dev;
+	int i, has_io, has_mem;
+	u16 cmd;
+
+	/* Generic PCI bus probing sets these to point at
+	 * &io{port,mem}_resouce which is wrong for us.
+	 */
+	if (pbus->self == NULL) {
+		pbus->resource[0] = &info->io_space;
+		pbus->resource[1] = &info->mem_space;
+		pbus->resource[2] = NULL;
+	}
+
+	list_for_each_entry(dev, &pbus->devices, bus_list) {
+		/*
+		 * We can not rely on that the bootloader has enabled I/O
+		 * or memory access to PCI devices. Instead we enable it here
+		 * if the device has BARs of respective type.
+		 */
+		has_io = has_mem = 0;
+		for (i = 0; i < PCI_ROM_RESOURCE; i++) {
+			unsigned long f = dev->resource[i].flags;
+			if (f & IORESOURCE_IO)
+				has_io = 1;
+			else if (f & IORESOURCE_MEM)
+				has_mem = 1;
+		}
+		/* ROM BARs are mapped into 32-bit memory space */
+		if (dev->resource[PCI_ROM_RESOURCE].end != 0) {
+			dev->resource[PCI_ROM_RESOURCE].flags |=
+							IORESOURCE_ROM_ENABLE;
+			has_mem = 1;
+		}
+		pci_bus_read_config_word(pbus, dev->devfn, PCI_COMMAND, &cmd);
+		if (has_io && !(cmd & PCI_COMMAND_IO)) {
+#ifdef CONFIG_PCI_DEBUG
+			printk(KERN_INFO "LEONPCI: Enabling I/O for dev %s\n",
+					 pci_name(dev));
+#endif
+			cmd |= PCI_COMMAND_IO;
+			pci_bus_write_config_word(pbus, dev->devfn, PCI_COMMAND,
+									cmd);
+		}
+		if (has_mem && !(cmd & PCI_COMMAND_MEMORY)) {
+#ifdef CONFIG_PCI_DEBUG
+			printk(KERN_INFO "LEONPCI: Enabling MEMORY for dev"
+					 "%s\n", pci_name(dev));
+#endif
+			cmd |= PCI_COMMAND_MEMORY;
+			pci_bus_write_config_word(pbus, dev->devfn, PCI_COMMAND,
+									cmd);
+		}
+	}
+}
+
+/*
+ * Other archs parse arguments here.
+ */
+char * __devinit pcibios_setup(char *str)
+{
+	return str;
+}
+
+resource_size_t pcibios_align_resource(void *data, const struct resource *res,
+				resource_size_t size, resource_size_t align)
+{
+	return res->start;
+}
+
+int pcibios_enable_device(struct pci_dev *dev, int mask)
+{
+	return pci_enable_resources(dev, mask);
+}
+
+struct device_node *pci_device_to_OF_node(struct pci_dev *pdev)
+{
+	/*
+	 * Currently the OpenBoot nodes are not connected with the PCI device,
+	 * this is because the LEON PROM does not create PCI nodes. Eventually
+	 * this will change and the same approach as pcic.c can be used to
+	 * match PROM nodes with pci devices.
+	 */
+	return NULL;
+}
+EXPORT_SYMBOL(pci_device_to_OF_node);
+
+void __devinit pcibios_update_irq(struct pci_dev *dev, int irq)
+{
+#ifdef CONFIG_PCI_DEBUG
+	printk(KERN_DEBUG "LEONPCI: Assigning IRQ %02d to %s\n", irq,
+		pci_name(dev));
+#endif
+	pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq);
+}
+
+/* in/out routines taken from pcic.c
+ *
+ * This probably belongs here rather than ioport.c because
+ * we do not want this crud linked into SBus kernels.
+ * Also, think for a moment about likes of floppy.c that
+ * include architecture specific parts. They may want to redefine ins/outs.
+ *
+ * We do not use horrible macros here because we want to
+ * advance pointer by sizeof(size).
+ */
+void outsb(unsigned long addr, const void *src, unsigned long count)
+{
+	while (count) {
+		count -= 1;
+		outb(*(const char *)src, addr);
+		src += 1;
+		/* addr += 1; */
+	}
+}
+EXPORT_SYMBOL(outsb);
+
+void outsw(unsigned long addr, const void *src, unsigned long count)
+{
+	while (count) {
+		count -= 2;
+		outw(*(const short *)src, addr);
+		src += 2;
+		/* addr += 2; */
+	}
+}
+EXPORT_SYMBOL(outsw);
+
+void outsl(unsigned long addr, const void *src, unsigned long count)
+{
+	while (count) {
+		count -= 4;
+		outl(*(const long *)src, addr);
+		src += 4;
+		/* addr += 4; */
+	}
+}
+EXPORT_SYMBOL(outsl);
+
+void insb(unsigned long addr, void *dst, unsigned long count)
+{
+	while (count) {
+		count -= 1;
+		*(unsigned char *)dst = inb(addr);
+		dst += 1;
+		/* addr += 1; */
+	}
+}
+EXPORT_SYMBOL(insb);
+
+void insw(unsigned long addr, void *dst, unsigned long count)
+{
+	while (count) {
+		count -= 2;
+		*(unsigned short *)dst = inw(addr);
+		dst += 2;
+		/* addr += 2; */
+	}
+}
+EXPORT_SYMBOL(insw);
+
+void insl(unsigned long addr, void *dst, unsigned long count)
+{
+	while (count) {
+		count -= 4;
+		/*
+		 * XXX I am sure we are in for an unaligned trap here.
+		 */
+		*(unsigned long *)dst = inl(addr);
+		dst += 4;
+		/* addr += 4; */
+	}
+}
+EXPORT_SYMBOL(insl);
diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c
new file mode 100644
index 000000000000..44dc093ee33a
--- /dev/null
+++ b/arch/sparc/kernel/leon_pci_grpci2.c
@@ -0,0 +1,897 @@
+/*
+ * leon_pci_grpci2.c: GRPCI2 Host PCI driver
+ *
+ * Copyright (C) 2011 Aeroflex Gaisler AB, Daniel Hellstrom
+ *
+ */
+
+#include <linux/of_device.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <asm/io.h>
+#include <asm/leon.h>
+#include <asm/vaddrs.h>
+#include <asm/sections.h>
+#include <asm/leon_pci.h>
+
+#include "irq.h"
+
+struct grpci2_barcfg {
+	unsigned long pciadr;	/* PCI Space Address */
+	unsigned long ahbadr;	/* PCI Base address mapped to this AHB addr */
+};
+
+/* Device Node Configuration options:
+ *  - barcfgs    : Custom Configuration of Host's 6 target BARs
+ *  - irq_mask   : Limit which PCI interrupts are enabled
+ *  - do_reset   : Force PCI Reset on startup
+ *
+ * barcfgs
+ * =======
+ *
+ * Optional custom Target BAR configuration (see struct grpci2_barcfg). All
+ * addresses are physical. Array always contains 6 elements (len=2*4*6 bytes)
+ *
+ * -1 means not configured (let host driver do default setup).
+ *
+ * [i*2+0] = PCI Address of BAR[i] on target interface
+ * [i*2+1] = Accessing PCI address of BAR[i] result in this AMBA address
+ *
+ *
+ * irq_mask
+ * ========
+ *
+ * Limit which PCI interrupts are enabled. 0=Disable, 1=Enable. By default
+ * all are enabled. Use this when PCI interrupt pins are floating on PCB.
+ * int, len=4.
+ *  bit0 = PCI INTA#
+ *  bit1 = PCI INTB#
+ *  bit2 = PCI INTC#
+ *  bit3 = PCI INTD#
+ *
+ *
+ * reset
+ * =====
+ *
+ * Force PCI reset on startup. int, len=4
+ */
+
+/* Enable Debugging Configuration Space Access */
+#undef GRPCI2_DEBUG_CFGACCESS
+
+/*
+ * GRPCI2 APB Register MAP
+ */
+struct grpci2_regs {
+	unsigned int ctrl;		/* 0x00 Control */
+	unsigned int sts_cap;		/* 0x04 Status / Capabilities */
+	int res1;			/* 0x08 */
+	unsigned int io_map;		/* 0x0C I/O Map address */
+	unsigned int dma_ctrl;		/* 0x10 DMA */
+	unsigned int dma_bdbase;	/* 0x14 DMA */
+	int res2[2];			/* 0x18 */
+	unsigned int bars[6];		/* 0x20 read-only PCI BARs */
+	int res3[2];			/* 0x38 */
+	unsigned int ahbmst_map[16];	/* 0x40 AHB->PCI Map per AHB Master */
+
+	/* PCI Trace Buffer Registers (OPTIONAL) */
+	unsigned int t_ctrl;		/* 0x80 */
+	unsigned int t_cnt;		/* 0x84 */
+	unsigned int t_adpat;		/* 0x88 */
+	unsigned int t_admask;		/* 0x8C */
+	unsigned int t_sigpat;		/* 0x90 */
+	unsigned int t_sigmask;		/* 0x94 */
+	unsigned int t_adstate;		/* 0x98 */
+	unsigned int t_sigstate;	/* 0x9C */
+};
+
+#define REGLOAD(a)	(be32_to_cpu(__raw_readl(&(a))))
+#define REGSTORE(a, v)	(__raw_writel(cpu_to_be32(v), &(a)))
+
+#define CTRL_BUS_BIT 16
+
+#define CTRL_RESET (1<<31)
+#define CTRL_SI (1<<27)
+#define CTRL_PE (1<<26)
+#define CTRL_EI (1<<25)
+#define CTRL_ER (1<<24)
+#define CTRL_BUS (0xff<<CTRL_BUS_BIT)
+#define CTRL_HOSTINT 0xf
+
+#define STS_HOST_BIT	31
+#define STS_MST_BIT	30
+#define STS_TAR_BIT	29
+#define STS_DMA_BIT	28
+#define STS_DI_BIT	27
+#define STS_HI_BIT	26
+#define STS_IRQMODE_BIT	24
+#define STS_TRACE_BIT	23
+#define STS_CFGERRVALID_BIT 20
+#define STS_CFGERR_BIT	19
+#define STS_INTTYPE_BIT	12
+#define STS_INTSTS_BIT	8
+#define STS_FDEPTH_BIT	2
+#define STS_FNUM_BIT	0
+
+#define STS_HOST	(1<<STS_HOST_BIT)
+#define STS_MST		(1<<STS_MST_BIT)
+#define STS_TAR		(1<<STS_TAR_BIT)
+#define STS_DMA		(1<<STS_DMA_BIT)
+#define STS_DI		(1<<STS_DI_BIT)
+#define STS_HI		(1<<STS_HI_BIT)
+#define STS_IRQMODE	(0x3<<STS_IRQMODE_BIT)
+#define STS_TRACE	(1<<STS_TRACE_BIT)
+#define STS_CFGERRVALID	(1<<STS_CFGERRVALID_BIT)
+#define STS_CFGERR	(1<<STS_CFGERR_BIT)
+#define STS_INTTYPE	(0x3f<<STS_INTTYPE_BIT)
+#define STS_INTSTS	(0xf<<STS_INTSTS_BIT)
+#define STS_FDEPTH	(0x7<<STS_FDEPTH_BIT)
+#define STS_FNUM	(0x3<<STS_FNUM_BIT)
+
+#define STS_ISYSERR	(1<<17)
+#define STS_IDMA	(1<<16)
+#define STS_IDMAERR	(1<<15)
+#define STS_IMSTABRT	(1<<14)
+#define STS_ITGTABRT	(1<<13)
+#define STS_IPARERR	(1<<12)
+
+#define STS_ERR_IRQ (STS_ISYSERR | STS_IMSTABRT | STS_ITGTABRT | STS_IPARERR)
+
+struct grpci2_bd_chan {
+	unsigned int ctrl;	/* 0x00 DMA Control */
+	unsigned int nchan;	/* 0x04 Next DMA Channel Address */
+	unsigned int nbd;	/* 0x08 Next Data Descriptor in chan */
+	unsigned int res;	/* 0x0C Reserved */
+};
+
+#define BD_CHAN_EN		0x80000000
+#define BD_CHAN_TYPE		0x00300000
+#define BD_CHAN_BDCNT		0x0000ffff
+#define BD_CHAN_EN_BIT		31
+#define BD_CHAN_TYPE_BIT	20
+#define BD_CHAN_BDCNT_BIT	0
+
+struct grpci2_bd_data {
+	unsigned int ctrl;	/* 0x00 DMA Data Control */
+	unsigned int pci_adr;	/* 0x04 PCI Start Address */
+	unsigned int ahb_adr;	/* 0x08 AHB Start address */
+	unsigned int next;	/* 0x0C Next Data Descriptor in chan */
+};
+
+#define BD_DATA_EN		0x80000000
+#define BD_DATA_IE		0x40000000
+#define BD_DATA_DR		0x20000000
+#define BD_DATA_TYPE		0x00300000
+#define BD_DATA_ER		0x00080000
+#define BD_DATA_LEN		0x0000ffff
+#define BD_DATA_EN_BIT		31
+#define BD_DATA_IE_BIT		30
+#define BD_DATA_DR_BIT		29
+#define BD_DATA_TYPE_BIT	20
+#define BD_DATA_ER_BIT		19
+#define BD_DATA_LEN_BIT		0
+
+/* GRPCI2 Capability */
+struct grpci2_cap_first {
+	unsigned int ctrl;
+	unsigned int pci2ahb_map[6];
+	unsigned int ext2ahb_map;
+	unsigned int io_map;
+	unsigned int pcibar_size[6];
+};
+#define CAP9_CTRL_OFS 0
+#define CAP9_BAR_OFS 0x4
+#define CAP9_IOMAP_OFS 0x20
+#define CAP9_BARSIZE_OFS 0x24
+
+struct grpci2_priv {
+	struct leon_pci_info	info; /* must be on top of this structure */
+	struct grpci2_regs	*regs;
+	char			irq;
+	char			irq_mode; /* IRQ Mode from CAPSTS REG */
+	char			bt_enabled;
+	char			do_reset;
+	char			irq_mask;
+	u32			pciid; /* PCI ID of Host */
+	unsigned char		irq_map[4];
+
+	/* Virtual IRQ numbers */
+	unsigned int		virq_err;
+	unsigned int		virq_dma;
+
+	/* AHB PCI Windows */
+	unsigned long		pci_area;	/* MEMORY */
+	unsigned long		pci_area_end;
+	unsigned long		pci_io;		/* I/O */
+	unsigned long		pci_conf;	/* CONFIGURATION */
+	unsigned long		pci_conf_end;
+	unsigned long		pci_io_va;
+
+	struct grpci2_barcfg	tgtbars[6];
+};
+
+DEFINE_SPINLOCK(grpci2_dev_lock);
+struct grpci2_priv *grpci2priv;
+
+int grpci2_map_irq(struct pci_dev *dev, u8 slot, u8 pin)
+{
+	struct grpci2_priv *priv = dev->bus->sysdata;
+	int irq_group;
+
+	/* Use default IRQ decoding on PCI BUS0 according slot numbering */
+	irq_group = slot & 0x3;
+	pin = ((pin - 1) + irq_group) & 0x3;
+
+	return priv->irq_map[pin];
+}
+
+static int grpci2_cfg_r32(struct grpci2_priv *priv, unsigned int bus,
+				unsigned int devfn, int where, u32 *val)
+{
+	unsigned int *pci_conf;
+	unsigned long flags;
+	u32 tmp;
+
+	if (where & 0x3)
+		return -EINVAL;
+
+	if (bus == 0 && PCI_SLOT(devfn) != 0)
+		devfn += (0x8 * 6);
+
+	/* Select bus */
+	spin_lock_irqsave(&grpci2_dev_lock, flags);
+	REGSTORE(priv->regs->ctrl, (REGLOAD(priv->regs->ctrl) & ~(0xff << 16)) |
+				   (bus << 16));
+	spin_unlock_irqrestore(&grpci2_dev_lock, flags);
+
+	/* clear old status */
+	REGSTORE(priv->regs->sts_cap, (STS_CFGERR | STS_CFGERRVALID));
+
+	pci_conf = (unsigned int *) (priv->pci_conf |
+						(devfn << 8) | (where & 0xfc));
+	tmp = LEON3_BYPASS_LOAD_PA(pci_conf);
+
+	/* Wait until GRPCI2 signals that CFG access is done, it should be
+	 * done instantaneously unless a DMA operation is ongoing...
+	 */
+	while ((REGLOAD(priv->regs->sts_cap) & STS_CFGERRVALID) == 0)
+		;
+
+	if (REGLOAD(priv->regs->sts_cap) & STS_CFGERR) {
+		*val = 0xffffffff;
+	} else {
+		/* Bus always little endian (unaffected by byte-swapping) */
+		*val = flip_dword(tmp);
+	}
+
+	return 0;
+}
+
+static int grpci2_cfg_r16(struct grpci2_priv *priv, unsigned int bus,
+				unsigned int devfn, int where, u32 *val)
+{
+	u32 v;
+	int ret;
+
+	if (where & 0x1)
+		return -EINVAL;
+	ret = grpci2_cfg_r32(priv, bus, devfn, where & ~0x3, &v);
+	*val = 0xffff & (v >> (8 * (where & 0x3)));
+	return ret;
+}
+
+static int grpci2_cfg_r8(struct grpci2_priv *priv, unsigned int bus,
+				unsigned int devfn, int where, u32 *val)
+{
+	u32 v;
+	int ret;
+
+	ret = grpci2_cfg_r32(priv, bus, devfn, where & ~0x3, &v);
+	*val = 0xff & (v >> (8 * (where & 3)));
+
+	return ret;
+}
+
+static int grpci2_cfg_w32(struct grpci2_priv *priv, unsigned int bus,
+				unsigned int devfn, int where, u32 val)
+{
+	unsigned int *pci_conf;
+	unsigned long flags;
+
+	if (where & 0x3)
+		return -EINVAL;
+
+	if (bus == 0 && PCI_SLOT(devfn) != 0)
+		devfn += (0x8 * 6);
+
+	/* Select bus */
+	spin_lock_irqsave(&grpci2_dev_lock, flags);
+	REGSTORE(priv->regs->ctrl, (REGLOAD(priv->regs->ctrl) & ~(0xff << 16)) |
+				   (bus << 16));
+	spin_unlock_irqrestore(&grpci2_dev_lock, flags);
+
+	/* clear old status */
+	REGSTORE(priv->regs->sts_cap, (STS_CFGERR | STS_CFGERRVALID));
+
+	pci_conf = (unsigned int *) (priv->pci_conf |
+						(devfn << 8) | (where & 0xfc));
+	LEON3_BYPASS_STORE_PA(pci_conf, flip_dword(val));
+
+	/* Wait until GRPCI2 signals that CFG access is done, it should be
+	 * done instantaneously unless a DMA operation is ongoing...
+	 */
+	while ((REGLOAD(priv->regs->sts_cap) & STS_CFGERRVALID) == 0)
+		;
+
+	return 0;
+}
+
+static int grpci2_cfg_w16(struct grpci2_priv *priv, unsigned int bus,
+				unsigned int devfn, int where, u32 val)
+{
+	int ret;
+	u32 v;
+
+	if (where & 0x1)
+		return -EINVAL;
+	ret = grpci2_cfg_r32(priv, bus, devfn, where&~3, &v);
+	if (ret)
+		return ret;
+	v = (v & ~(0xffff << (8 * (where & 0x3)))) |
+	    ((0xffff & val) << (8 * (where & 0x3)));
+	return grpci2_cfg_w32(priv, bus, devfn, where & ~0x3, v);
+}
+
+static int grpci2_cfg_w8(struct grpci2_priv *priv, unsigned int bus,
+				unsigned int devfn, int where, u32 val)
+{
+	int ret;
+	u32 v;
+
+	ret = grpci2_cfg_r32(priv, bus, devfn, where & ~0x3, &v);
+	if (ret != 0)
+		return ret;
+	v = (v & ~(0xff << (8 * (where & 0x3)))) |
+	    ((0xff & val) << (8 * (where & 0x3)));
+	return grpci2_cfg_w32(priv, bus, devfn, where & ~0x3, v);
+}
+
+/* Read from Configuration Space. When entering here the PCI layer has taken
+ * the pci_lock spinlock and IRQ is off.
+ */
+static int grpci2_read_config(struct pci_bus *bus, unsigned int devfn,
+			      int where, int size, u32 *val)
+{
+	struct grpci2_priv *priv = grpci2priv;
+	unsigned int busno = bus->number;
+	int ret;
+
+	if (PCI_SLOT(devfn) > 15 || (PCI_SLOT(devfn) == 0 && busno == 0)) {
+		*val = ~0;
+		return 0;
+	}
+
+	switch (size) {
+	case 1:
+		ret = grpci2_cfg_r8(priv, busno, devfn, where, val);
+		break;
+	case 2:
+		ret = grpci2_cfg_r16(priv, busno, devfn, where, val);
+		break;
+	case 4:
+		ret = grpci2_cfg_r32(priv, busno, devfn, where, val);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+#ifdef GRPCI2_DEBUG_CFGACCESS
+	printk(KERN_INFO "grpci2_read_config: [%02x:%02x:%x] ofs=%d val=%x "
+		"size=%d\n", busno, PCI_SLOT(devfn), PCI_FUNC(devfn), where,
+		*val, size);
+#endif
+
+	return ret;
+}
+
+/* Write to Configuration Space. When entering here the PCI layer has taken
+ * the pci_lock spinlock and IRQ is off.
+ */
+static int grpci2_write_config(struct pci_bus *bus, unsigned int devfn,
+			       int where, int size, u32 val)
+{
+	struct grpci2_priv *priv = grpci2priv;
+	unsigned int busno = bus->number;
+
+	if (PCI_SLOT(devfn) > 15 || (PCI_SLOT(devfn) == 0 && busno == 0))
+		return 0;
+
+#ifdef GRPCI2_DEBUG_CFGACCESS
+	printk(KERN_INFO "grpci2_write_config: [%02x:%02x:%x] ofs=%d size=%d "
+		"val=%x\n", busno, PCI_SLOT(devfn), PCI_FUNC(devfn),
+		where, size, val);
+#endif
+
+	switch (size) {
+	default:
+		return -EINVAL;
+	case 1:
+		return grpci2_cfg_w8(priv, busno, devfn, where, val);
+	case 2:
+		return grpci2_cfg_w16(priv, busno, devfn, where, val);
+	case 4:
+		return grpci2_cfg_w32(priv, busno, devfn, where, val);
+	}
+}
+
+static struct pci_ops grpci2_ops = {
+	.read =		grpci2_read_config,
+	.write =	grpci2_write_config,
+};
+
+/* GENIRQ IRQ chip implementation for GRPCI2 irqmode=0..2. In configuration
+ * 3 where all PCI Interrupts has a separate IRQ on the system IRQ controller
+ * this is not needed and the standard IRQ controller can be used.
+ */
+
+static void grpci2_mask_irq(struct irq_data *data)
+{
+	unsigned long flags;
+	unsigned int irqidx;
+	struct grpci2_priv *priv = grpci2priv;
+
+	irqidx = (unsigned int)data->chip_data - 1;
+	if (irqidx > 3) /* only mask PCI interrupts here */
+		return;
+
+	spin_lock_irqsave(&grpci2_dev_lock, flags);
+	REGSTORE(priv->regs->ctrl, REGLOAD(priv->regs->ctrl) & ~(1 << irqidx));
+	spin_unlock_irqrestore(&grpci2_dev_lock, flags);
+}
+
+static void grpci2_unmask_irq(struct irq_data *data)
+{
+	unsigned long flags;
+	unsigned int irqidx;
+	struct grpci2_priv *priv = grpci2priv;
+
+	irqidx = (unsigned int)data->chip_data - 1;
+	if (irqidx > 3) /* only unmask PCI interrupts here */
+		return;
+
+	spin_lock_irqsave(&grpci2_dev_lock, flags);
+	REGSTORE(priv->regs->ctrl, REGLOAD(priv->regs->ctrl) | (1 << irqidx));
+	spin_unlock_irqrestore(&grpci2_dev_lock, flags);
+}
+
+static unsigned int grpci2_startup_irq(struct irq_data *data)
+{
+	grpci2_unmask_irq(data);
+	return 0;
+}
+
+static void grpci2_shutdown_irq(struct irq_data *data)
+{
+	grpci2_mask_irq(data);
+}
+
+static struct irq_chip grpci2_irq = {
+	.name		= "grpci2",
+	.irq_startup	= grpci2_startup_irq,
+	.irq_shutdown	= grpci2_shutdown_irq,
+	.irq_mask	= grpci2_mask_irq,
+	.irq_unmask	= grpci2_unmask_irq,
+};
+
+/* Handle one or multiple IRQs from the PCI core */
+static void grpci2_pci_flow_irq(unsigned int irq, struct irq_desc *desc)
+{
+	struct grpci2_priv *priv = grpci2priv;
+	int i, ack = 0;
+	unsigned int ctrl, sts_cap, pci_ints;
+
+	ctrl = REGLOAD(priv->regs->ctrl);
+	sts_cap = REGLOAD(priv->regs->sts_cap);
+
+	/* Error Interrupt? */
+	if (sts_cap & STS_ERR_IRQ) {
+		generic_handle_irq(priv->virq_err);
+		ack = 1;
+	}
+
+	/* PCI Interrupt? */
+	pci_ints = ((~sts_cap) >> STS_INTSTS_BIT) & ctrl & CTRL_HOSTINT;
+	if (pci_ints) {
+		/* Call respective PCI Interrupt handler */
+		for (i = 0; i < 4; i++) {
+			if (pci_ints & (1 << i))
+				generic_handle_irq(priv->irq_map[i]);
+		}
+		ack = 1;
+	}
+
+	/*
+	 * Decode DMA Interrupt only when shared with Err and PCI INTX#, when
+	 * the DMA is a unique IRQ the DMA interrupts doesn't end up here, they
+	 * goes directly to DMA ISR.
+	 */
+	if ((priv->irq_mode == 0) && (sts_cap & (STS_IDMA | STS_IDMAERR))) {
+		generic_handle_irq(priv->virq_dma);
+		ack = 1;
+	}
+
+	/*
+	 * Call "first level" IRQ chip end-of-irq handler. It will ACK LEON IRQ
+	 * Controller, this must be done after IRQ sources have been handled to
+	 * avoid double IRQ generation
+	 */
+	if (ack)
+		desc->irq_data.chip->irq_eoi(&desc->irq_data);
+}
+
+/* Create a virtual IRQ */
+static unsigned int grpci2_build_device_irq(unsigned int irq)
+{
+	unsigned int virq = 0, pil;
+
+	pil = 1 << 8;
+	virq = irq_alloc(irq, pil);
+	if (virq == 0)
+		goto out;
+
+	irq_set_chip_and_handler_name(virq, &grpci2_irq, handle_simple_irq,
+				      "pcilvl");
+	irq_set_chip_data(virq, (void *)irq);
+
+out:
+	return virq;
+}
+
+void grpci2_hw_init(struct grpci2_priv *priv)
+{
+	u32 ahbadr, pciadr, bar_sz, capptr, io_map, data;
+	struct grpci2_regs *regs = priv->regs;
+	int i;
+	struct grpci2_barcfg *barcfg = priv->tgtbars;
+
+	/* Reset any earlier setup */
+	if (priv->do_reset) {
+		printk(KERN_INFO "GRPCI2: Resetting PCI bus\n");
+		REGSTORE(regs->ctrl, CTRL_RESET);
+		ssleep(1); /* Wait for boards to settle */
+	}
+	REGSTORE(regs->ctrl, 0);
+	REGSTORE(regs->sts_cap, ~0); /* Clear Status */
+	REGSTORE(regs->dma_ctrl, 0);
+	REGSTORE(regs->dma_bdbase, 0);
+
+	/* Translate I/O accesses to 0, I/O Space always @ PCI low 64Kbytes */
+	REGSTORE(regs->io_map, REGLOAD(regs->io_map) & 0x0000ffff);
+
+	/* set 1:1 mapping between AHB -> PCI memory space, for all Masters
+	 * Each AHB master has it's own mapping registers. Max 16 AHB masters.
+	 */
+	for (i = 0; i < 16; i++)
+		REGSTORE(regs->ahbmst_map[i], priv->pci_area);
+
+	/* Get the GRPCI2 Host PCI ID */
+	grpci2_cfg_r32(priv, 0, 0, PCI_VENDOR_ID, &priv->pciid);
+
+	/* Get address to first (always defined) capability structure */
+	grpci2_cfg_r8(priv, 0, 0, PCI_CAPABILITY_LIST, &capptr);
+
+	/* Enable/Disable Byte twisting */
+	grpci2_cfg_r32(priv, 0, 0, capptr+CAP9_IOMAP_OFS, &io_map);
+	io_map = (io_map & ~0x1) | (priv->bt_enabled ? 1 : 0);
+	grpci2_cfg_w32(priv, 0, 0, capptr+CAP9_IOMAP_OFS, io_map);
+
+	/* Setup the Host's PCI Target BARs for other peripherals to access,
+	 * and do DMA to the host's memory. The target BARs can be sized and
+	 * enabled individually.
+	 *
+	 * User may set custom target BARs, but default is:
+	 * The first BARs is used to map kernel low (DMA is part of normal
+	 * region on sparc which is SRMMU_MAXMEM big) main memory 1:1 to the
+	 * PCI bus, the other BARs are disabled. We assume that the first BAR
+	 * is always available.
+	 */
+	for (i = 0; i < 6; i++) {
+		if (barcfg[i].pciadr != ~0 && barcfg[i].ahbadr != ~0) {
+			/* Target BARs must have the proper alignment */
+			ahbadr = barcfg[i].ahbadr;
+			pciadr = barcfg[i].pciadr;
+			bar_sz = ((pciadr - 1) & ~pciadr) + 1;
+		} else {
+			if (i == 0) {
+				/* Map main memory */
+				bar_sz = 0xf0000008; /* 256MB prefetchable */
+				ahbadr = 0xf0000000 & (u32)__pa(PAGE_ALIGN(
+					(unsigned long) &_end));
+				pciadr = ahbadr;
+			} else {
+				bar_sz = 0;
+				ahbadr = 0;
+				pciadr = 0;
+			}
+		}
+		grpci2_cfg_w32(priv, 0, 0, capptr+CAP9_BARSIZE_OFS+i*4, bar_sz);
+		grpci2_cfg_w32(priv, 0, 0, PCI_BASE_ADDRESS_0+i*4, pciadr);
+		grpci2_cfg_w32(priv, 0, 0, capptr+CAP9_BAR_OFS+i*4, ahbadr);
+		printk(KERN_INFO "        TGT BAR[%d]: 0x%08x (PCI)-> 0x%08x\n",
+			i, pciadr, ahbadr);
+	}
+
+	/* set as bus master and enable pci memory responses */
+	grpci2_cfg_r32(priv, 0, 0, PCI_COMMAND, &data);
+	data |= (PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
+	grpci2_cfg_w32(priv, 0, 0, PCI_COMMAND, data);
+
+	/* Enable Error respone (CPU-TRAP) on illegal memory access. */
+	REGSTORE(regs->ctrl, CTRL_ER | CTRL_PE);
+}
+
+static irqreturn_t grpci2_jump_interrupt(int irq, void *arg)
+{
+	printk(KERN_ERR "GRPCI2: Jump IRQ happened\n");
+	return IRQ_NONE;
+}
+
+/* Handle GRPCI2 Error Interrupt */
+static irqreturn_t grpci2_err_interrupt(int irq, void *arg)
+{
+	struct grpci2_priv *priv = arg;
+	struct grpci2_regs *regs = priv->regs;
+	unsigned int status;
+
+	status = REGLOAD(regs->sts_cap);
+	if ((status & STS_ERR_IRQ) == 0)
+		return IRQ_NONE;
+
+	if (status & STS_IPARERR)
+		printk(KERN_ERR "GRPCI2: Parity Error\n");
+
+	if (status & STS_ITGTABRT)
+		printk(KERN_ERR "GRPCI2: Target Abort\n");
+
+	if (status & STS_IMSTABRT)
+		printk(KERN_ERR "GRPCI2: Master Abort\n");
+
+	if (status & STS_ISYSERR)
+		printk(KERN_ERR "GRPCI2: System Error\n");
+
+	/* Clear handled INT TYPE IRQs */
+	REGSTORE(regs->sts_cap, status & STS_ERR_IRQ);
+
+	return IRQ_HANDLED;
+}
+
+static int __devinit grpci2_of_probe(struct platform_device *ofdev)
+{
+	struct grpci2_regs *regs;
+	struct grpci2_priv *priv;
+	int err, i, len;
+	const int *tmp;
+	unsigned int capability;
+
+	if (grpci2priv) {
+		printk(KERN_ERR "GRPCI2: only one GRPCI2 core supported\n");
+		return -ENODEV;
+	}
+
+	if (ofdev->num_resources < 3) {
+		printk(KERN_ERR "GRPCI2: not enough APB/AHB resources\n");
+		return -EIO;
+	}
+
+	/* Find Device Address */
+	regs = of_ioremap(&ofdev->resource[0], 0,
+			  resource_size(&ofdev->resource[0]),
+			  "grlib-grpci2 regs");
+	if (regs == NULL) {
+		printk(KERN_ERR "GRPCI2: ioremap failed\n");
+		return -EIO;
+	}
+
+	/*
+	 * Check that we're in Host Slot and that we can act as a Host Bridge
+	 * and not only as target.
+	 */
+	capability = REGLOAD(regs->sts_cap);
+	if ((capability & STS_HOST) || !(capability & STS_MST)) {
+		printk(KERN_INFO "GRPCI2: not in host system slot\n");
+		err = -EIO;
+		goto err1;
+	}
+
+	priv = grpci2priv = kzalloc(sizeof(struct grpci2_priv), GFP_KERNEL);
+	if (grpci2priv == NULL) {
+		err = -ENOMEM;
+		goto err1;
+	}
+	memset(grpci2priv, 0, sizeof(*grpci2priv));
+	priv->regs = regs;
+	priv->irq = ofdev->archdata.irqs[0]; /* BASE IRQ */
+	priv->irq_mode = (capability & STS_IRQMODE) >> STS_IRQMODE_BIT;
+
+	printk(KERN_INFO "GRPCI2: host found at %p, irq%d\n", regs, priv->irq);
+
+	/* Byte twisting should be made configurable from kernel command line */
+	priv->bt_enabled = 1;
+
+	/* Let user do custom Target BAR assignment */
+	tmp = of_get_property(ofdev->dev.of_node, "barcfg", &len);
+	if (tmp && (len == 2*4*6))
+		memcpy(priv->tgtbars, tmp, 2*4*6);
+	else
+		memset(priv->tgtbars, -1, 2*4*6);
+
+	/* Limit IRQ unmasking in irq_mode 2 and 3 */
+	tmp = of_get_property(ofdev->dev.of_node, "irq_mask", &len);
+	if (tmp && (len == 4))
+		priv->do_reset = *tmp;
+	else
+		priv->irq_mask = 0xf;
+
+	/* Optional PCI reset. Force PCI reset on startup */
+	tmp = of_get_property(ofdev->dev.of_node, "reset", &len);
+	if (tmp && (len == 4))
+		priv->do_reset = *tmp;
+	else
+		priv->do_reset = 0;
+
+	/* Find PCI Memory, I/O and Configuration Space Windows */
+	priv->pci_area = ofdev->resource[1].start;
+	priv->pci_area_end = ofdev->resource[1].end+1;
+	priv->pci_io = ofdev->resource[2].start;
+	priv->pci_conf = ofdev->resource[2].start + 0x10000;
+	priv->pci_conf_end = priv->pci_conf + 0x10000;
+	priv->pci_io_va = (unsigned long)ioremap(priv->pci_io, 0x10000);
+	if (!priv->pci_io_va) {
+		err = -EIO;
+		goto err2;
+	}
+
+	printk(KERN_INFO
+		"GRPCI2: MEMORY SPACE [0x%08lx - 0x%08lx]\n"
+		"        I/O    SPACE [0x%08lx - 0x%08lx]\n"
+		"        CONFIG SPACE [0x%08lx - 0x%08lx]\n",
+		priv->pci_area, priv->pci_area_end-1,
+		priv->pci_io, priv->pci_conf-1,
+		priv->pci_conf, priv->pci_conf_end-1);
+
+	/*
+	 * I/O Space resources in I/O Window mapped into Virtual Adr Space
+	 * We never use low 4KB because some devices seem have problems using
+	 * address 0.
+	 */
+	memset(&priv->info.io_space, 0, sizeof(struct resource));
+	priv->info.io_space.name = "GRPCI2 PCI I/O Space";
+	priv->info.io_space.start = priv->pci_io_va + 0x1000;
+	priv->info.io_space.end = priv->pci_io_va + 0x10000 - 1;
+	priv->info.io_space.flags = IORESOURCE_IO;
+
+	/*
+	 * GRPCI2 has no prefetchable memory, map everything as
+	 * non-prefetchable memory
+	 */
+	memset(&priv->info.mem_space, 0, sizeof(struct resource));
+	priv->info.mem_space.name = "GRPCI2 PCI MEM Space";
+	priv->info.mem_space.start = priv->pci_area;
+	priv->info.mem_space.end = priv->pci_area_end - 1;
+	priv->info.mem_space.flags = IORESOURCE_MEM;
+
+	if (request_resource(&iomem_resource, &priv->info.mem_space) < 0)
+		goto err3;
+	if (request_resource(&ioport_resource, &priv->info.io_space) < 0)
+		goto err4;
+
+	grpci2_hw_init(priv);
+
+	/*
+	 * Get PCI Interrupt to System IRQ mapping and setup IRQ handling
+	 * Error IRQ always on PCI INTA.
+	 */
+	if (priv->irq_mode < 2) {
+		/* All PCI interrupts are shared using the same system IRQ */
+		leon_update_virq_handling(priv->irq, grpci2_pci_flow_irq,
+					 "pcilvl", 0);
+
+		priv->irq_map[0] = grpci2_build_device_irq(1);
+		priv->irq_map[1] = grpci2_build_device_irq(2);
+		priv->irq_map[2] = grpci2_build_device_irq(3);
+		priv->irq_map[3] = grpci2_build_device_irq(4);
+
+		priv->virq_err = grpci2_build_device_irq(5);
+		if (priv->irq_mode & 1)
+			priv->virq_dma = ofdev->archdata.irqs[1];
+		else
+			priv->virq_dma = grpci2_build_device_irq(6);
+
+		/* Enable IRQs on LEON IRQ controller */
+		err = request_irq(priv->irq, grpci2_jump_interrupt, 0,
+					"GRPCI2_JUMP", priv);
+		if (err)
+			printk(KERN_ERR "GRPCI2: ERR IRQ request failed\n");
+	} else {
+		/* All PCI interrupts have an unique IRQ interrupt */
+		for (i = 0; i < 4; i++) {
+			/* Make LEON IRQ layer handle level IRQ by acking */
+			leon_update_virq_handling(ofdev->archdata.irqs[i],
+						 handle_fasteoi_irq, "pcilvl",
+						 1);
+			priv->irq_map[i] = ofdev->archdata.irqs[i];
+		}
+		priv->virq_err = priv->irq_map[0];
+		if (priv->irq_mode & 1)
+			priv->virq_dma = ofdev->archdata.irqs[4];
+		else
+			priv->virq_dma = priv->irq_map[0];
+
+		/* Unmask all PCI interrupts, request_irq will not do that */
+		REGSTORE(regs->ctrl, REGLOAD(regs->ctrl)|(priv->irq_mask&0xf));
+	}
+
+	/* Setup IRQ handler for non-configuration space access errors */
+	err = request_irq(priv->virq_err, grpci2_err_interrupt, IRQF_SHARED,
+				"GRPCI2_ERR", priv);
+	if (err) {
+		printk(KERN_DEBUG "GRPCI2: ERR VIRQ request failed: %d\n", err);
+		goto err5;
+	}
+
+	/*
+	 * Enable Error Interrupts. PCI interrupts are unmasked once request_irq
+	 * is called by the PCI Device drivers
+	 */
+	REGSTORE(regs->ctrl, REGLOAD(regs->ctrl) | CTRL_EI | CTRL_SI);
+
+	/* Init common layer and scan buses */
+	priv->info.ops = &grpci2_ops;
+	priv->info.map_irq = grpci2_map_irq;
+	leon_pci_init(ofdev, &priv->info);
+
+	return 0;
+
+err5:
+	release_resource(&priv->info.io_space);
+err4:
+	release_resource(&priv->info.mem_space);
+err3:
+	err = -ENOMEM;
+	iounmap((void *)priv->pci_io_va);
+err2:
+	kfree(priv);
+err1:
+	of_iounmap(&ofdev->resource[0], regs,
+		resource_size(&ofdev->resource[0]));
+	return err;
+}
+
+static struct of_device_id grpci2_of_match[] = {
+	{
+	 .name = "GAISLER_GRPCI2",
+	 },
+	{
+	 .name = "01_07c",
+	 },
+	{},
+};
+
+static struct platform_driver grpci2_of_driver = {
+	.driver = {
+		.name = "grpci2",
+		.owner = THIS_MODULE,
+		.of_match_table = grpci2_of_match,
+	},
+	.probe = grpci2_of_probe,
+};
+
+static int __init grpci2_init(void)
+{
+	return platform_driver_register(&grpci2_of_driver);
+}
+
+subsys_initcall(grpci2_init);
diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c
index 8d348c474a2f..99ba5baa9497 100644
--- a/arch/sparc/kernel/module.c
+++ b/arch/sparc/kernel/module.c
@@ -214,7 +214,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs,
 			       me->name,
 			       (int) (ELF_R_TYPE(rel[i].r_info) & 0xff));
 			return -ENOEXEC;
-		};
+		}
 	}
 	return 0;
 }
diff --git a/arch/sparc/kernel/pci_common.c b/arch/sparc/kernel/pci_common.c
index 6e3874b64488..a6895987fb70 100644
--- a/arch/sparc/kernel/pci_common.c
+++ b/arch/sparc/kernel/pci_common.c
@@ -281,7 +281,7 @@ static int sun4v_read_pci_cfg(struct pci_bus *bus_dev, unsigned int devfn,
 	case 4:
 		*value = ret & 0xffffffff;
 		break;
-	};
+	}
 
 
 	return PCIBIOS_SUCCESSFUL;
@@ -456,7 +456,7 @@ void pci_determine_mem_io_space(struct pci_pbm_info *pbm)
 
 		default:
 			break;
-		};
+		}
 	}
 
 	if (!saw_io || !saw_mem) {
diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c
index 283fbc329a43..f030b02edddd 100644
--- a/arch/sparc/kernel/pci_schizo.c
+++ b/arch/sparc/kernel/pci_schizo.c
@@ -264,7 +264,7 @@ static void schizo_check_iommu_error_pbm(struct pci_pbm_info *pbm,
 		default:
 			type_string = "ECC Error";
 			break;
-		};
+		}
 		printk("%s: IOMMU Error, type[%s]\n",
 		       pbm->name, type_string);
 
@@ -319,7 +319,7 @@ static void schizo_check_iommu_error_pbm(struct pci_pbm_info *pbm,
 			default:
 				type_string = "ECC Error";
 				break;
-			};
+			}
 			printk("%s: IOMMU TAG(%d)[error(%s) ctx(%x) wr(%d) str(%d) "
 			       "sz(%dK) vpg(%08lx)]\n",
 			       pbm->name, i, type_string,
@@ -1328,7 +1328,7 @@ static int __devinit schizo_pbm_init(struct pci_pbm_info *pbm,
 	default:
 		chipset_name = "SCHIZO";
 		break;
-	};
+	}
 
 	/* For SCHIZO, three OBP regs:
 	 * 1) PBM controller regs
diff --git a/arch/sparc/kernel/prom_irqtrans.c b/arch/sparc/kernel/prom_irqtrans.c
index 570b98f6e897..40e4936bd479 100644
--- a/arch/sparc/kernel/prom_irqtrans.c
+++ b/arch/sparc/kernel/prom_irqtrans.c
@@ -694,7 +694,7 @@ static unsigned int sbus_of_build_irq(struct device_node *dp,
 		case 3:
 			iclr = reg_base + SYSIO_ICLR_SLOT3;
 			break;
-		};
+		}
 
 		iclr += ((unsigned long)sbus_level - 1UL) * 8UL;
 	}
diff --git a/arch/sparc/kernel/psycho_common.c b/arch/sparc/kernel/psycho_common.c
index fe2af66bb198..8db48e808ed4 100644
--- a/arch/sparc/kernel/psycho_common.c
+++ b/arch/sparc/kernel/psycho_common.c
@@ -228,7 +228,7 @@ void psycho_check_iommu_error(struct pci_pbm_info *pbm,
 		default:
 			type_str = "ECC Error";
 			break;
-		};
+		}
 		printk(KERN_ERR "%s: IOMMU Error, type[%s]\n",
 		       pbm->name, type_str);
 
diff --git a/arch/sparc/kernel/sbus.c b/arch/sparc/kernel/sbus.c
index 2ca32d13abcf..a161b9c77f05 100644
--- a/arch/sparc/kernel/sbus.c
+++ b/arch/sparc/kernel/sbus.c
@@ -97,7 +97,7 @@ void sbus_set_sbus64(struct device *dev, int bursts)
 
 	default:
 		return;
-	};
+	}
 
 	val = upa_readq(cfg_reg);
 	if (val & (1UL << 14UL)) {
@@ -244,7 +244,7 @@ static unsigned int sbus_build_irq(struct platform_device *op, unsigned int ino)
 		case 3:
 			iclr = reg_base + SYSIO_ICLR_SLOT3;
 			break;
-		};
+		}
 
 		iclr += ((unsigned long)sbus_level - 1UL) * 8UL;
 	}
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index 3249d3f3234d..d26e1f6c717a 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -267,7 +267,7 @@ void __init setup_arch(char **cmdline_p)
 	default:
 		printk("UNKNOWN!\n");
 		break;
-	};
+	}
 
 #ifdef CONFIG_DUMMY_CONSOLE
 	conswitchp = &dummy_con;
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index f3b6850cc8db..c4dd0999da86 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -209,7 +209,7 @@ void __init per_cpu_patch(void)
 		default:
 			prom_printf("Unknown cpu type, halting.\n");
 			prom_halt();
-		};
+		}
 
 		*(unsigned int *) (addr +  0) = insns[0];
 		wmb();
diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c
index d5b3958be0b4..21b125341bf7 100644
--- a/arch/sparc/kernel/smp_32.c
+++ b/arch/sparc/kernel/smp_32.c
@@ -114,7 +114,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 		printk("UNKNOWN!\n");
 		BUG();
 		break;
-	};
+	}
 }
 
 void cpu_panic(void)
@@ -374,7 +374,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		printk("UNKNOWN!\n");
 		BUG();
 		break;
-	};
+	}
 }
 
 /* Set this up early so that things like the scheduler can init
@@ -447,7 +447,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 		printk("UNKNOWN!\n");
 		BUG();
 		break;
-	};
+	}
 
 	if (!ret) {
 		cpumask_set_cpu(cpu, &smp_commenced_mask);
diff --git a/arch/sparc/kernel/sun4d_irq.c b/arch/sparc/kernel/sun4d_irq.c
index a9ea60eb2c10..1d13c5bda0b1 100644
--- a/arch/sparc/kernel/sun4d_irq.c
+++ b/arch/sparc/kernel/sun4d_irq.c
@@ -103,10 +103,9 @@ static void sun4d_sbus_handler_irq(int sbusl)
 
 	sbil = (sbusl << 2);
 	/* Loop for each pending SBI */
-	for (sbino = 0; bus_mask; sbino++) {
+	for (sbino = 0; bus_mask; sbino++, bus_mask >>= 1) {
 		unsigned int idx, mask;
 
-		bus_mask >>= 1;
 		if (!(bus_mask & 1))
 			continue;
 		/* XXX This seems to ACK the irq twice.  acquire_sbi()
@@ -118,19 +117,16 @@ static void sun4d_sbus_handler_irq(int sbusl)
 		mask &= (0xf << sbil);
 
 		/* Loop for each pending SBI slot */
-		idx = 0;
 		slot = (1 << sbil);
-		while (mask != 0) {
+		for (idx = 0; mask != 0; idx++, slot <<= 1) {
 			unsigned int pil;
 			struct irq_bucket *p;
 
-			idx++;
-			slot <<= 1;
 			if (!(mask & slot))
 				continue;
 
 			mask &= ~slot;
-			pil = sun4d_encode_irq(sbino, sbil, idx);
+			pil = sun4d_encode_irq(sbino, sbusl, idx);
 
 			p = irq_map[pil];
 			while (p) {
@@ -218,10 +214,10 @@ static void sun4d_unmask_irq(struct irq_data *data)
 
 #ifdef CONFIG_SMP
 	spin_lock_irqsave(&sun4d_imsk_lock, flags);
-	cc_set_imsk_other(cpuid, cc_get_imsk_other(cpuid) | ~(1 << real_irq));
+	cc_set_imsk_other(cpuid, cc_get_imsk_other(cpuid) & ~(1 << real_irq));
 	spin_unlock_irqrestore(&sun4d_imsk_lock, flags);
 #else
-	cc_set_imsk(cc_get_imsk() | ~(1 << real_irq));
+	cc_set_imsk(cc_get_imsk() & ~(1 << real_irq));
 #endif
 }
 
@@ -299,26 +295,68 @@ static void __init sun4d_load_profile_irqs(void)
 	}
 }
 
+unsigned int _sun4d_build_device_irq(unsigned int real_irq,
+                                     unsigned int pil,
+                                     unsigned int board)
+{
+	struct sun4d_handler_data *handler_data;
+	unsigned int irq;
+
+	irq = irq_alloc(real_irq, pil);
+	if (irq == 0) {
+		prom_printf("IRQ: allocate for %d %d %d failed\n",
+			real_irq, pil, board);
+		goto err_out;
+	}
+
+	handler_data = irq_get_handler_data(irq);
+	if (unlikely(handler_data))
+		goto err_out;
+
+	handler_data = kzalloc(sizeof(struct sun4d_handler_data), GFP_ATOMIC);
+	if (unlikely(!handler_data)) {
+		prom_printf("IRQ: kzalloc(sun4d_handler_data) failed.\n");
+		prom_halt();
+	}
+	handler_data->cpuid    = board_to_cpu[board];
+	handler_data->real_irq = real_irq;
+	irq_set_chip_and_handler_name(irq, &sun4d_irq,
+	                              handle_level_irq, "level");
+	irq_set_handler_data(irq, handler_data);
+
+err_out:
+	return irq;
+}
+
+
+
 unsigned int sun4d_build_device_irq(struct platform_device *op,
                                     unsigned int real_irq)
 {
 	struct device_node *dp = op->dev.of_node;
-	struct device_node *io_unit, *sbi = dp->parent;
+	struct device_node *board_parent, *bus = dp->parent;
+	char *bus_connection;
 	const struct linux_prom_registers *regs;
-	struct sun4d_handler_data *handler_data;
 	unsigned int pil;
 	unsigned int irq;
 	int board, slot;
 	int sbusl;
 
-	irq = 0;
-	while (sbi) {
-		if (!strcmp(sbi->name, "sbi"))
+	irq = real_irq;
+	while (bus) {
+		if (!strcmp(bus->name, "sbi")) {
+			bus_connection = "io-unit";
+			break;
+		}
+
+		if (!strcmp(bus->name, "bootbus")) {
+			bus_connection = "cpu-unit";
 			break;
+		}
 
-		sbi = sbi->parent;
+		bus = bus->parent;
 	}
-	if (!sbi)
+	if (!bus)
 		goto err_out;
 
 	regs = of_get_property(dp, "reg", NULL);
@@ -328,17 +366,19 @@ unsigned int sun4d_build_device_irq(struct platform_device *op,
 	slot = regs->which_io;
 
 	/*
-	 *  If SBI's parent is not io-unit or the io-unit lacks
-	 * a "board#" property, something is very wrong.
+	 * If Bus nodes parent is not io-unit/cpu-unit or the io-unit/cpu-unit
+	 * lacks a "board#" property, something is very wrong.
 	 */
-	if (!sbi->parent || strcmp(sbi->parent->name, "io-unit")) {
-		printk("%s: Error, parent is not io-unit.\n", sbi->full_name);
+	if (!bus->parent || strcmp(bus->parent->name, bus_connection)) {
+		printk(KERN_ERR "%s: Error, parent is not %s.\n",
+			bus->full_name, bus_connection);
 		goto err_out;
 	}
-	io_unit = sbi->parent;
-	board = of_getintprop_default(io_unit, "board#", -1);
+	board_parent = bus->parent;
+	board = of_getintprop_default(board_parent, "board#", -1);
 	if (board == -1) {
-		printk("%s: Error, lacks board# property.\n", io_unit->full_name);
+		printk(KERN_ERR "%s: Error, lacks board# property.\n",
+			board_parent->full_name);
 		goto err_out;
 	}
 
@@ -348,29 +388,17 @@ unsigned int sun4d_build_device_irq(struct platform_device *op,
 	else
 		pil = real_irq;
 
-	irq = irq_alloc(real_irq, pil);
-	if (irq == 0)
-		goto err_out;
-
-	handler_data = irq_get_handler_data(irq);
-	if (unlikely(handler_data))
-		goto err_out;
-
-	handler_data = kzalloc(sizeof(struct sun4d_handler_data), GFP_ATOMIC);
-	if (unlikely(!handler_data)) {
-		prom_printf("IRQ: kzalloc(sun4d_handler_data) failed.\n");
-		prom_halt();
-	}
-	handler_data->cpuid    = board_to_cpu[board];
-	handler_data->real_irq = real_irq;
-	irq_set_chip_and_handler_name(irq, &sun4d_irq,
-	                              handle_level_irq, "level");
-	irq_set_handler_data(irq, handler_data);
-
+	irq = _sun4d_build_device_irq(real_irq, pil, board);
 err_out:
-	return real_irq;
+	return irq;
 }
 
+unsigned int sun4d_build_timer_irq(unsigned int board, unsigned int real_irq)
+{
+	return _sun4d_build_device_irq(real_irq, real_irq, board);
+}
+
+
 static void __init sun4d_fixup_trap_table(void)
 {
 #ifdef CONFIG_SMP
@@ -402,6 +430,7 @@ static void __init sun4d_init_timers(irq_handler_t counter_fn)
 	unsigned int irq;
 	const u32 *reg;
 	int err;
+	int board;
 
 	dp = of_find_node_by_name(NULL, "cpu-unit");
 	if (!dp) {
@@ -414,12 +443,19 @@ 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();
 	}
 
+	board = of_getintprop_default(dp, "board#", -1);
+	if (board == -1) {
+		prom_printf("sun4d_init_timers: No board# property on cpu-unit\n");
+		prom_halt();
+	}
+
+	of_node_put(dp);
+
 	res.start = reg[1];
 	res.end = reg[2] - 1;
 	res.flags = reg[0] & 0xff;
@@ -434,7 +470,7 @@ static void __init sun4d_init_timers(irq_handler_t counter_fn)
 
 	master_l10_counter = &sun4d_timers->l10_cur_count;
 
-	irq = sun4d_build_device_irq(NULL, SUN4D_TIMER_IRQ);
+	irq = sun4d_build_timer_irq(board, SUN4D_TIMER_IRQ);
 	err = request_irq(irq, counter_fn, IRQF_TIMER, "timer", NULL);
 	if (err) {
 		prom_printf("sun4d_init_timers: request_irq() failed with %d\n",
diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c
index 6db18c6927fb..170cd8e8eb2a 100644
--- a/arch/sparc/kernel/sys_sparc32.c
+++ b/arch/sparc/kernel/sys_sparc32.c
@@ -109,7 +109,7 @@ asmlinkage long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compa
 
 	default:
 		return -ENOSYS;
-	};
+	}
 
 	return -ENOSYS;
 }
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 96082d30def0..908b47a5ee24 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -460,7 +460,7 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second
 		default:
 			err = -ENOSYS;
 			goto out;
-		};
+		}
 	}
 	if (call <= MSGCTL) {
 		switch (call) {
@@ -481,7 +481,7 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second
 		default:
 			err = -ENOSYS;
 			goto out;
-		};
+		}
 	}
 	if (call <= SHMCTL) {
 		switch (call) {
@@ -507,7 +507,7 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second
 		default:
 			err = -ENOSYS;
 			goto out;
-		};
+		}
 	} else {
 		err = -ENOSYS;
 	}
diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
index 332c83ff7701..6e492d59f6b1 100644
--- a/arch/sparc/kernel/systbls_32.S
+++ b/arch/sparc/kernel/systbls_32.S
@@ -84,4 +84,4 @@ sys_call_table:
 /*320*/	.long sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, sys_preadv
 /*325*/	.long sys_pwritev, sys_rt_tgsigqueueinfo, sys_perf_event_open, sys_recvmmsg, sys_fanotify_init
 /*330*/	.long sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime
-/*335*/	.long sys_syncfs, sys_sendmmsg
+/*335*/	.long sys_syncfs, sys_sendmmsg, sys_setns
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index 43887ca0be0e..f566518483b5 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -85,7 +85,7 @@ sys_call_table32:
 /*320*/	.word sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, compat_sys_preadv
 	.word compat_sys_pwritev, compat_sys_rt_tgsigqueueinfo, sys_perf_event_open, compat_sys_recvmmsg, sys_fanotify_init
 /*330*/	.word sys32_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, compat_sys_open_by_handle_at, compat_sys_clock_adjtime
-	.word sys_syncfs, compat_sys_sendmmsg
+	.word sys_syncfs, compat_sys_sendmmsg, sys_setns
 
 #endif /* CONFIG_COMPAT */
 
@@ -162,4 +162,4 @@ sys_call_table:
 /*320*/	.word sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, sys_preadv
 	.word sys_pwritev, sys_rt_tgsigqueueinfo, sys_perf_event_open, sys_recvmmsg, sys_fanotify_init
 /*330*/	.word sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime
-	.word sys_syncfs, sys_sendmmsg
+	.word sys_syncfs, sys_sendmmsg, sys_setns
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index 2b8d54b2d850..1db6b18964d2 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -708,7 +708,7 @@ static void sparc64_timer_setup(enum clock_event_mode mode,
 	case CLOCK_EVT_MODE_UNUSED:
 		WARN_ON(1);
 		break;
-	};
+	}
 }
 
 static struct clock_event_device sparc64_clockevent = {
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 1ed547bd850f..0cbdaa41cd1e 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -1804,7 +1804,7 @@ static const char *sun4v_err_type_to_str(u32 type)
 		return "warning resumable";
 	default:
 		return "unknown";
-	};
+	}
 }
 
 static void sun4v_log_error(struct pt_regs *regs, struct sun4v_error_entry *ent, int cpu, const char *pfx, atomic_t *ocnt)
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index c752c4c479bd..b2b019ea8caa 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -211,7 +211,7 @@ static inline int do_int_store(int reg_num, int size, unsigned long *dst_addr,
 		default:
 			BUG();
 			break;
-		};
+		}
 	}
 	return __do_int_store(dst_addr, size, src_val, asi);
 }
@@ -328,7 +328,7 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 		case ASI_SNFL:
 			asi &= ~0x08;
 			break;
-		};
+		}
 		switch (dir) {
 		case load:
 			reg_addr = fetch_reg_addr(((insn>>25)&0x1f), regs);
@@ -351,7 +351,7 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 				default:
 					BUG();
 					break;
-				};
+				}
 				*reg_addr = val_in;
 			}
 			break;
diff --git a/arch/sparc/kernel/us2e_cpufreq.c b/arch/sparc/kernel/us2e_cpufreq.c
index 531d54fc9829..489fc15f3194 100644
--- a/arch/sparc/kernel/us2e_cpufreq.c
+++ b/arch/sparc/kernel/us2e_cpufreq.c
@@ -176,7 +176,7 @@ static unsigned long index_to_estar_mode(unsigned int index)
 
 	default:
 		BUG();
-	};
+	}
 }
 
 static unsigned long index_to_divisor(unsigned int index)
@@ -199,7 +199,7 @@ static unsigned long index_to_divisor(unsigned int index)
 
 	default:
 		BUG();
-	};
+	}
 }
 
 static unsigned long estar_to_divisor(unsigned long estar)
@@ -224,7 +224,7 @@ static unsigned long estar_to_divisor(unsigned long estar)
 		break;
 	default:
 		BUG();
-	};
+	}
 
 	return ret;
 }
diff --git a/arch/sparc/kernel/us3_cpufreq.c b/arch/sparc/kernel/us3_cpufreq.c
index 9a8ceb700833..eb1624b931d9 100644
--- a/arch/sparc/kernel/us3_cpufreq.c
+++ b/arch/sparc/kernel/us3_cpufreq.c
@@ -71,7 +71,7 @@ static unsigned long get_current_freq(unsigned int cpu, unsigned long safari_cfg
 		break;
 	default:
 		BUG();
-	};
+	}
 
 	return ret;
 }
@@ -125,7 +125,7 @@ static void us3_set_cpu_divider_index(unsigned int cpu, unsigned int index)
 
 	default:
 		BUG();
-	};
+	}
 
 	reg = read_safari_cfg();
 
diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c
index aa6ac70d4fd5..29348ea139c3 100644
--- a/arch/sparc/kernel/viohs.c
+++ b/arch/sparc/kernel/viohs.c
@@ -363,7 +363,7 @@ static int process_ver(struct vio_driver_state *vio, struct vio_ver_info *pkt)
 
 	default:
 		return handshake_failure(vio);
-	};
+	}
 }
 
 static int process_attr(struct vio_driver_state *vio, void *pkt)
diff --git a/arch/sparc/kernel/visemul.c b/arch/sparc/kernel/visemul.c
index 9dfd2ebcb157..36357717d691 100644
--- a/arch/sparc/kernel/visemul.c
+++ b/arch/sparc/kernel/visemul.c
@@ -334,7 +334,7 @@ static void edge(struct pt_regs *regs, unsigned int insn, unsigned int opf)
 		left = edge32_tab_l[(rs1 >> 2) & 0x1].left;
 		right = edge32_tab_l[(rs2 >> 2) & 0x1].right;
 		break;
-	};
+	}
 
 	if ((rs1 & ~0x7UL) == (rs2 & ~0x7UL))
 		rd_val = right & left;
@@ -360,7 +360,7 @@ static void edge(struct pt_regs *regs, unsigned int insn, unsigned int opf)
 		tstate = regs->tstate & ~(TSTATE_XCC | TSTATE_ICC);
 		regs->tstate = tstate | (ccr << 32UL);
 	}
-	};
+	}
 }
 
 static void array(struct pt_regs *regs, unsigned int insn, unsigned int opf)
@@ -392,7 +392,7 @@ static void array(struct pt_regs *regs, unsigned int insn, unsigned int opf)
 
 	case ARRAY32_OPF:
 		rd_val <<= 2;
-	};
+	}
 
 	store_reg(regs, rd_val, RD(insn));
 }
@@ -577,7 +577,7 @@ static void pformat(struct pt_regs *regs, unsigned int insn, unsigned int opf)
 		*fpd_regaddr(f, RD(insn)) = rd_val;
 		break;
 	}
-	};
+	}
 }
 
 static void pmul(struct pt_regs *regs, unsigned int insn, unsigned int opf)
@@ -693,7 +693,7 @@ static void pmul(struct pt_regs *regs, unsigned int insn, unsigned int opf)
 		*fpd_regaddr(f, RD(insn)) = rd_val;
 		break;
 	}
-	};
+	}
 }
 
 static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf)
@@ -786,7 +786,7 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf)
 				rd_val |= 1 << i;
 		}
 		break;
-	};
+	}
 
 	maybe_flush_windows(0, 0, RD(insn), 0);
 	store_reg(regs, rd_val, RD(insn));
@@ -885,7 +885,7 @@ int vis_emul(struct pt_regs *regs, unsigned int insn)
 	case BSHUFFLE_OPF:
 		bshuffle(regs, insn);
 		break;
-	};
+	}
 
 	regs->tpc = regs->tnpc;
 	regs->tnpc += 4;
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index b10ac4d62378..7543ddbdadb2 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -135,7 +135,7 @@ asmlinkage int lookup_fault(unsigned long pc, unsigned long ret_pc,
 
 	default:
 		break;
-	};
+	}
 
 	memset(&regs, 0, sizeof (regs));
 	regs.pc = pc;
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index ca217327e8d2..7b00de61c5f1 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -340,7 +340,7 @@ void __init paging_init(void)
 		prom_printf("paging_init: sparc_cpu_model = %d\n", sparc_cpu_model);
 		prom_printf("paging_init: Halting...\n");
 		prom_halt();
-	};
+	}
 
 	/* Initialize the protection map with non-constant, MMU dependent values. */
 	protection_map[0] = PAGE_NONE;
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index e10cd03fab80..3fd8e18bed80 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1625,7 +1625,7 @@ static void __init sun4v_ktsb_init(void)
 		ktsb_descr[0].pgsz_idx = HV_PGSZ_IDX_4MB;
 		ktsb_descr[0].pgsz_mask = HV_PGSZ_MASK_4MB;
 		break;
-	};
+	}
 
 	ktsb_descr[0].assoc = 1;
 	ktsb_descr[0].num_ttes = KERNEL_TSB_NENTRIES;
@@ -2266,7 +2266,7 @@ unsigned long pte_sz_bits(unsigned long sz)
 			return _PAGE_SZ512K_4V;
 		case 4 * 1024 * 1024:
 			return _PAGE_SZ4MB_4V;
-		};
+		}
 	} else {
 		switch (sz) {
 		case 8 * 1024:
@@ -2278,7 +2278,7 @@ unsigned long pte_sz_bits(unsigned long sz)
 			return _PAGE_SZ512K_4U;
 		case 4 * 1024 * 1024:
 			return _PAGE_SZ4MB_4U;
-		};
+		}
 	}
 }
 
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index fe09fd8be695..cbef74e793b8 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -1665,7 +1665,7 @@ static void __init init_swift(void)
 	default:
 		srmmu_modtype = Swift_ok;
 		break;
-	};
+	}
 
 	BTFIXUPSET_CALL(flush_cache_all, swift_flush_cache_all, BTFIXUPCALL_NORM);
 	BTFIXUPSET_CALL(flush_cache_mm, swift_flush_cache_mm, BTFIXUPCALL_NORM);
@@ -2069,7 +2069,7 @@ static void __init get_srmmu_type(void)
 			/* Some other Cypress revision, assume a 605. */
 			init_cypress_605(mod_rev);
 			break;
-		};
+		}
 		return;
 	}
 	
diff --git a/arch/sparc/mm/sun4c.c b/arch/sparc/mm/sun4c.c
index a2350b5e68aa..1cf4f198709a 100644
--- a/arch/sparc/mm/sun4c.c
+++ b/arch/sparc/mm/sun4c.c
@@ -318,7 +318,7 @@ void __init sun4c_probe_vac(void)
 		prom_printf("probe_vac: Didn't expect vac-linesize of %d, halting\n",
 			    sun4c_vacinfo.linesize);
 		prom_halt();
-	};
+	}
 
 	sun4c_flush_all();
 	sun4c_enable_vac();
@@ -364,7 +364,7 @@ static void __init patch_kernel_fault_handler(void)
 			prom_printf("Unhandled number of segmaps: %d\n",
 				    num_segmaps);
 			prom_halt();
-	};
+	}
 	switch (num_contexts) {
 		case 8:
 			/* Default, nothing to do. */
@@ -377,7 +377,7 @@ static void __init patch_kernel_fault_handler(void)
 			prom_printf("Unhandled number of contexts: %d\n",
 				    num_contexts);
 			prom_halt();
-	};
+	}
 
 	if (sun4c_vacinfo.do_hwflushes != 0) {
 		PATCH_INSN(vac_hwflush_patch1_on, vac_hwflush_patch1);
@@ -394,7 +394,7 @@ static void __init patch_kernel_fault_handler(void)
 			prom_printf("Impossible VAC linesize %d, halting...\n",
 				    sun4c_vacinfo.linesize);
 			prom_halt();
-		};
+		}
 	}
 }
 
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 948461513499..a5f51b22fcbe 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -180,7 +180,7 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign
 		printk(KERN_ERR "TSB[%s:%d]: Impossible TSB size %lu, killing process.\n",
 		       current->comm, current->pid, tsb_bytes);
 		do_exit(SIGSEGV);
-	};
+	}
 	tte |= pte_sz_bits(page_sz);
 
 	if (tlb_type == cheetah_plus || tlb_type == hypervisor) {
@@ -215,7 +215,7 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign
 #endif
 		default:
 			BUG();
-		};
+		}
 		hp->assoc = 1;
 		hp->num_ttes = tsb_bytes / 16;
 		hp->ctx_idx = 0;
@@ -230,7 +230,7 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign
 #endif
 		default:
 			BUG();
-		};
+		}
 		hp->tsb_base = tsb_paddr;
 		hp->resv = 0;
 	}
diff --git a/arch/sparc/prom/console_32.c b/arch/sparc/prom/console_32.c
index b05e3db5fa63..a00f47b16c10 100644
--- a/arch/sparc/prom/console_32.c
+++ b/arch/sparc/prom/console_32.c
@@ -38,7 +38,7 @@ static int prom_nbputchar(const char *buf)
 		break;
 	default:
 		break;
-	};
+	}
 	restore_current();
 	spin_unlock_irqrestore(&prom_lock, flags);
 	return i; /* Ugh, we could spin forever on unsupported proms ;( */
diff --git a/arch/sparc/prom/init_32.c b/arch/sparc/prom/init_32.c
index 0a601b300639..26c64cea3c9c 100644
--- a/arch/sparc/prom/init_32.c
+++ b/arch/sparc/prom/init_32.c
@@ -53,7 +53,7 @@ void __init prom_init(struct linux_romvec *rp)
 			    romvec->pv_romvers);
 		prom_halt();
 		break;
-	};
+	}
 
 	prom_rev = romvec->pv_plugin_revision;
 	prom_prev = romvec->pv_printrev;
diff --git a/arch/sparc/prom/mp.c b/arch/sparc/prom/mp.c
index 97c44c9ddbc8..0da8256cf76f 100644
--- a/arch/sparc/prom/mp.c
+++ b/arch/sparc/prom/mp.c
@@ -35,7 +35,7 @@ prom_startcpu(int cpunode, struct linux_prom_registers *ctable_reg, int ctx, cha
 	case PROM_V3:
 		ret = (*(romvec->v3_cpustart))(cpunode, (int) ctable_reg, ctx, pc);
 		break;
-	};
+	}
 	restore_current();
 	spin_unlock_irqrestore(&prom_lock, flags);
 
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index e1e50101b3bb..0249b8b4db54 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -11,6 +11,7 @@ config TILE
 	select GENERIC_IRQ_PROBE
 	select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_IRQ_SHOW
+	select SYS_HYPERVISOR
 
 # FIXME: investigate whether we need/want these options.
 #	select HAVE_IOREMAP_PROT
diff --git a/arch/tile/include/asm/hardwall.h b/arch/tile/include/asm/hardwall.h
index 0bed3ec7b42c..2ac422848c7d 100644
--- a/arch/tile/include/asm/hardwall.h
+++ b/arch/tile/include/asm/hardwall.h
@@ -40,6 +40,10 @@
 #define HARDWALL_DEACTIVATE \
  _IO(HARDWALL_IOCTL_BASE, _HARDWALL_DEACTIVATE)
 
+#define _HARDWALL_GET_ID 4
+#define HARDWALL_GET_ID \
+ _IO(HARDWALL_IOCTL_BASE, _HARDWALL_GET_ID)
+
 #ifndef __KERNEL__
 
 /* This is the canonical name expected by userspace. */
@@ -47,9 +51,14 @@
 
 #else
 
-/* Hook for /proc/tile/hardwall. */
-struct seq_file;
-int proc_tile_hardwall_show(struct seq_file *sf, void *v);
+/* /proc hooks for hardwall. */
+struct proc_dir_entry;
+#ifdef CONFIG_HARDWALL
+void proc_tile_hardwall_init(struct proc_dir_entry *root);
+int proc_pid_hardwall(struct task_struct *task, char *buffer);
+#else
+static inline void proc_tile_hardwall_init(struct proc_dir_entry *root) {}
+#endif
 
 #endif
 
diff --git a/arch/tile/include/asm/mmzone.h b/arch/tile/include/asm/mmzone.h
index c6344c4f32ac..9d3dbce8f953 100644
--- a/arch/tile/include/asm/mmzone.h
+++ b/arch/tile/include/asm/mmzone.h
@@ -40,17 +40,6 @@ static inline int pfn_to_nid(unsigned long pfn)
 	return highbits_to_node[__pfn_to_highbits(pfn)];
 }
 
-/*
- * Following are macros that each numa implmentation must define.
- */
-
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)						\
-({									\
-	pg_data_t *__pgdat = NODE_DATA(nid);				\
-	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;		\
-})
-
 #define kern_addr_valid(kaddr)	virt_addr_valid((void *)kaddr)
 
 static inline int pfn_valid(int pfn)
diff --git a/arch/tile/kernel/Makefile b/arch/tile/kernel/Makefile
index b4c8e8ec45dc..b4dbc057baad 100644
--- a/arch/tile/kernel/Makefile
+++ b/arch/tile/kernel/Makefile
@@ -5,7 +5,7 @@
 extra-y := vmlinux.lds head_$(BITS).o
 obj-y := backtrace.o entry.o init_task.o irq.o messaging.o \
 	pci-dma.o proc.o process.o ptrace.o reboot.o \
-	setup.o signal.o single_step.o stack.o sys.o time.o traps.o \
+	setup.o signal.o single_step.o stack.o sys.o sysfs.o time.o traps.o \
 	intvec_$(BITS).o regs_$(BITS).o tile-desc_$(BITS).o
 
 obj-$(CONFIG_HARDWALL)		+= hardwall.o
diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c
index 3bddef710de4..8c41891aab34 100644
--- a/arch/tile/kernel/hardwall.c
+++ b/arch/tile/kernel/hardwall.c
@@ -40,16 +40,25 @@
 struct hardwall_info {
 	struct list_head list;             /* "rectangles" list */
 	struct list_head task_head;        /* head of tasks in this hardwall */
+	struct cpumask cpumask;            /* cpus in the rectangle */
 	int ulhc_x;                        /* upper left hand corner x coord */
 	int ulhc_y;                        /* upper left hand corner y coord */
 	int width;                         /* rectangle width */
 	int height;                        /* rectangle height */
+	int id;                            /* integer id for this hardwall */
 	int teardown_in_progress;          /* are we tearing this one down? */
 };
 
 /* Currently allocated hardwall rectangles */
 static LIST_HEAD(rectangles);
 
+/* /proc/tile/hardwall */
+static struct proc_dir_entry *hardwall_proc_dir;
+
+/* Functions to manage files in /proc/tile/hardwall. */
+static void hardwall_add_proc(struct hardwall_info *rect);
+static void hardwall_remove_proc(struct hardwall_info *rect);
+
 /*
  * Guard changes to the hardwall data structures.
  * This could be finer grained (e.g. one lock for the list of hardwall
@@ -105,6 +114,8 @@ static int setup_rectangle(struct hardwall_info *r, struct cpumask *mask)
 	r->ulhc_y = cpu_y(ulhc);
 	r->width = cpu_x(lrhc) - r->ulhc_x + 1;
 	r->height = cpu_y(lrhc) - r->ulhc_y + 1;
+	cpumask_copy(&r->cpumask, mask);
+	r->id = ulhc;   /* The ulhc cpu id can be the hardwall id. */
 
 	/* Width and height must be positive */
 	if (r->width <= 0 || r->height <= 0)
@@ -388,6 +399,9 @@ static struct hardwall_info *hardwall_create(
 	/* Set up appropriate hardwalling on all affected cpus. */
 	hardwall_setup(rect);
 
+	/* Create a /proc/tile/hardwall entry. */
+	hardwall_add_proc(rect);
+
 	return rect;
 }
 
@@ -645,6 +659,9 @@ static void hardwall_destroy(struct hardwall_info *rect)
 	/* Restart switch and disable firewall. */
 	on_each_cpu_mask(&mask, restart_udn_switch, NULL, 1);
 
+	/* Remove the /proc/tile/hardwall entry. */
+	hardwall_remove_proc(rect);
+
 	/* Now free the rectangle from the list. */
 	spin_lock_irqsave(&hardwall_lock, flags);
 	BUG_ON(!list_empty(&rect->task_head));
@@ -654,35 +671,57 @@ static void hardwall_destroy(struct hardwall_info *rect)
 }
 
 
-/*
- * Dump hardwall state via /proc; initialized in arch/tile/sys/proc.c.
- */
-int proc_tile_hardwall_show(struct seq_file *sf, void *v)
+static int hardwall_proc_show(struct seq_file *sf, void *v)
 {
-	struct hardwall_info *r;
+	struct hardwall_info *rect = sf->private;
+	char buf[256];
 
-	if (udn_disabled) {
-		seq_printf(sf, "%dx%d 0,0 pids:\n", smp_width, smp_height);
-		return 0;
-	}
-
-	spin_lock_irq(&hardwall_lock);
-	list_for_each_entry(r, &rectangles, list) {
-		struct task_struct *p;
-		seq_printf(sf, "%dx%d %d,%d pids:",
-			   r->width, r->height, r->ulhc_x, r->ulhc_y);
-		list_for_each_entry(p, &r->task_head, thread.hardwall_list) {
-			unsigned int cpu = cpumask_first(&p->cpus_allowed);
-			unsigned int x = cpu % smp_width;
-			unsigned int y = cpu / smp_width;
-			seq_printf(sf, " %d@%d,%d", p->pid, x, y);
-		}
-		seq_printf(sf, "\n");
-	}
-	spin_unlock_irq(&hardwall_lock);
+	int rc = cpulist_scnprintf(buf, sizeof(buf), &rect->cpumask);
+	buf[rc++] = '\n';
+	seq_write(sf, buf, rc);
 	return 0;
 }
 
+static int hardwall_proc_open(struct inode *inode,
+			      struct file *file)
+{
+	return single_open(file, hardwall_proc_show, PDE(inode)->data);
+}
+
+static const struct file_operations hardwall_proc_fops = {
+	.open		= hardwall_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void hardwall_add_proc(struct hardwall_info *rect)
+{
+	char buf[64];
+	snprintf(buf, sizeof(buf), "%d", rect->id);
+	proc_create_data(buf, 0444, hardwall_proc_dir,
+			 &hardwall_proc_fops, rect);
+}
+
+static void hardwall_remove_proc(struct hardwall_info *rect)
+{
+	char buf[64];
+	snprintf(buf, sizeof(buf), "%d", rect->id);
+	remove_proc_entry(buf, hardwall_proc_dir);
+}
+
+int proc_pid_hardwall(struct task_struct *task, char *buffer)
+{
+	struct hardwall_info *rect = task->thread.hardwall;
+	return rect ? sprintf(buffer, "%d\n", rect->id) : 0;
+}
+
+void proc_tile_hardwall_init(struct proc_dir_entry *root)
+{
+	if (!udn_disabled)
+		hardwall_proc_dir = proc_mkdir("hardwall", root);
+}
+
 
 /*
  * Character device support via ioctl/close.
@@ -716,6 +755,9 @@ static long hardwall_ioctl(struct file *file, unsigned int a, unsigned long b)
 			return -EINVAL;
 		return hardwall_deactivate(current);
 
+	case _HARDWALL_GET_ID:
+		return rect ? rect->id : -EINVAL;
+
 	default:
 		return -EINVAL;
 	}
diff --git a/arch/tile/kernel/proc.c b/arch/tile/kernel/proc.c
index 2e02c41ddf3b..62d820833c68 100644
--- a/arch/tile/kernel/proc.c
+++ b/arch/tile/kernel/proc.c
@@ -27,6 +27,7 @@
 #include <asm/processor.h>
 #include <asm/sections.h>
 #include <asm/homecache.h>
+#include <asm/hardwall.h>
 #include <arch/chip.h>
 
 
@@ -88,3 +89,75 @@ const struct seq_operations cpuinfo_op = {
 	.stop	= c_stop,
 	.show	= show_cpuinfo,
 };
+
+/*
+ * Support /proc/tile directory
+ */
+
+static int __init proc_tile_init(void)
+{
+	struct proc_dir_entry *root = proc_mkdir("tile", NULL);
+	if (root == NULL)
+		return 0;
+
+	proc_tile_hardwall_init(root);
+
+	return 0;
+}
+
+arch_initcall(proc_tile_init);
+
+/*
+ * Support /proc/sys/tile directory
+ */
+
+#ifndef __tilegx__  /* FIXME: GX: no support for unaligned access yet */
+static ctl_table unaligned_subtable[] = {
+	{
+		.procname	= "enabled",
+		.data		= &unaligned_fixup,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
+		.procname	= "printk",
+		.data		= &unaligned_printk,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
+		.procname	= "count",
+		.data		= &unaligned_fixup_count,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{}
+};
+
+static ctl_table unaligned_table[] = {
+	{
+		.procname	= "unaligned_fixup",
+		.mode		= 0555,
+		.child		= unaligned_subtable
+	},
+	{}
+};
+#endif
+
+static struct ctl_path tile_path[] = {
+	{ .procname = "tile" },
+	{ }
+};
+
+static int __init proc_sys_tile_init(void)
+{
+#ifndef __tilegx__  /* FIXME: GX: no support for unaligned access yet */
+	register_sysctl_paths(tile_path, unaligned_table);
+#endif
+	return 0;
+}
+
+arch_initcall(proc_sys_tile_init);
diff --git a/arch/tile/kernel/sysfs.c b/arch/tile/kernel/sysfs.c
new file mode 100644
index 000000000000..b671a86f4515
--- /dev/null
+++ b/arch/tile/kernel/sysfs.c
@@ -0,0 +1,185 @@
+/*
+ * Copyright 2011 Tilera Corporation. 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, version 2.
+ *
+ *   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.
+ *
+ * /sys entry support.
+ */
+
+#include <linux/sysdev.h>
+#include <linux/cpu.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <hv/hypervisor.h>
+
+/* Return a string queried from the hypervisor, truncated to page size. */
+static ssize_t get_hv_confstr(char *page, int query)
+{
+	ssize_t n = hv_confstr(query, (unsigned long)page, PAGE_SIZE - 1);
+	n = n < 0 ? 0 : min(n, (ssize_t)PAGE_SIZE - 1) - 1;
+	if (n)
+		page[n++] = '\n';
+	page[n] = '\0';
+	return n;
+}
+
+static ssize_t chip_width_show(struct sysdev_class *dev,
+			       struct sysdev_class_attribute *attr,
+			       char *page)
+{
+	return sprintf(page, "%u\n", smp_width);
+}
+static SYSDEV_CLASS_ATTR(chip_width, 0444, chip_width_show, NULL);
+
+static ssize_t chip_height_show(struct sysdev_class *dev,
+				struct sysdev_class_attribute *attr,
+				char *page)
+{
+	return sprintf(page, "%u\n", smp_height);
+}
+static SYSDEV_CLASS_ATTR(chip_height, 0444, chip_height_show, NULL);
+
+static ssize_t chip_serial_show(struct sysdev_class *dev,
+				struct sysdev_class_attribute *attr,
+				char *page)
+{
+	return get_hv_confstr(page, HV_CONFSTR_CHIP_SERIAL_NUM);
+}
+static SYSDEV_CLASS_ATTR(chip_serial, 0444, chip_serial_show, NULL);
+
+static ssize_t chip_revision_show(struct sysdev_class *dev,
+				  struct sysdev_class_attribute *attr,
+				  char *page)
+{
+	return get_hv_confstr(page, HV_CONFSTR_CHIP_REV);
+}
+static SYSDEV_CLASS_ATTR(chip_revision, 0444, chip_revision_show, NULL);
+
+
+static ssize_t type_show(struct sysdev_class *dev,
+			    struct sysdev_class_attribute *attr,
+			    char *page)
+{
+	return sprintf(page, "tilera\n");
+}
+static SYSDEV_CLASS_ATTR(type, 0444, type_show, NULL);
+
+#define HV_CONF_ATTR(name, conf)					\
+	static ssize_t name ## _show(struct sysdev_class *dev,		\
+				     struct sysdev_class_attribute *attr, \
+				     char *page)			\
+	{								\
+		return get_hv_confstr(page, conf);			\
+	}								\
+	static SYSDEV_CLASS_ATTR(name, 0444, name ## _show, NULL);
+
+HV_CONF_ATTR(version,		HV_CONFSTR_HV_SW_VER)
+HV_CONF_ATTR(config_version,	HV_CONFSTR_HV_CONFIG_VER)
+
+HV_CONF_ATTR(board_part,	HV_CONFSTR_BOARD_PART_NUM)
+HV_CONF_ATTR(board_serial,	HV_CONFSTR_BOARD_SERIAL_NUM)
+HV_CONF_ATTR(board_revision,	HV_CONFSTR_BOARD_REV)
+HV_CONF_ATTR(board_description,	HV_CONFSTR_BOARD_DESC)
+HV_CONF_ATTR(mezz_part,		HV_CONFSTR_MEZZ_PART_NUM)
+HV_CONF_ATTR(mezz_serial,	HV_CONFSTR_MEZZ_SERIAL_NUM)
+HV_CONF_ATTR(mezz_revision,	HV_CONFSTR_MEZZ_REV)
+HV_CONF_ATTR(mezz_description,	HV_CONFSTR_MEZZ_DESC)
+HV_CONF_ATTR(switch_control,	HV_CONFSTR_SWITCH_CONTROL)
+
+static struct attribute *board_attrs[] = {
+	&attr_board_part.attr,
+	&attr_board_serial.attr,
+	&attr_board_revision.attr,
+	&attr_board_description.attr,
+	&attr_mezz_part.attr,
+	&attr_mezz_serial.attr,
+	&attr_mezz_revision.attr,
+	&attr_mezz_description.attr,
+	&attr_switch_control.attr,
+	NULL
+};
+
+static struct attribute_group board_attr_group = {
+	.name   = "board",
+	.attrs  = board_attrs,
+};
+
+
+static struct bin_attribute hvconfig_bin;
+
+static ssize_t
+hvconfig_bin_read(struct file *filp, struct kobject *kobj,
+		  struct bin_attribute *bin_attr,
+		  char *buf, loff_t off, size_t count)
+{
+	static size_t size;
+
+	/* Lazily learn the true size (minus the trailing NUL). */
+	if (size == 0)
+		size = hv_confstr(HV_CONFSTR_HV_CONFIG, 0, 0) - 1;
+
+	/* Check and adjust input parameters. */
+	if (off > size)
+		return -EINVAL;
+	if (count > size - off)
+		count = size - off;
+
+	if (count) {
+		/* Get a copy of the hvc and copy out the relevant portion. */
+		char *hvc;
+
+		size = off + count;
+		hvc = kmalloc(size, GFP_KERNEL);
+		if (hvc == NULL)
+			return -ENOMEM;
+		hv_confstr(HV_CONFSTR_HV_CONFIG, (unsigned long)hvc, size);
+		memcpy(buf, hvc + off, count);
+		kfree(hvc);
+	}
+
+	return count;
+}
+
+static int __init create_sysfs_entries(void)
+{
+	struct sysdev_class *cls = &cpu_sysdev_class;
+	int err = 0;
+
+#define create_cpu_attr(name)						\
+	if (!err)							\
+		err = sysfs_create_file(&cls->kset.kobj, &attr_##name.attr);
+	create_cpu_attr(chip_width);
+	create_cpu_attr(chip_height);
+	create_cpu_attr(chip_serial);
+	create_cpu_attr(chip_revision);
+
+#define create_hv_attr(name)						\
+	if (!err)							\
+		err = sysfs_create_file(hypervisor_kobj, &attr_##name.attr);
+	create_hv_attr(type);
+	create_hv_attr(version);
+	create_hv_attr(config_version);
+
+	if (!err)
+		err = sysfs_create_group(hypervisor_kobj, &board_attr_group);
+
+	if (!err) {
+		sysfs_bin_attr_init(&hvconfig_bin);
+		hvconfig_bin.attr.name = "hvconfig";
+		hvconfig_bin.attr.mode = S_IRUGO;
+		hvconfig_bin.read = hvconfig_bin_read;
+		hvconfig_bin.size = PAGE_SIZE;
+		err = sysfs_create_bin_file(hypervisor_kobj, &hvconfig_bin);
+	}
+
+	return err;
+}
+subsys_initcall(create_sysfs_entries);
diff --git a/arch/um/include/asm/percpu.h b/arch/um/include/asm/percpu.h
new file mode 100644
index 000000000000..efe7508d8abd
--- /dev/null
+++ b/arch/um/include/asm/percpu.h
@@ -0,0 +1,6 @@
+#ifndef __UM_PERCPU_H
+#define __UM_PERCPU_H
+
+#include <asm-generic/percpu.h>
+
+#endif /* __UM_PERCPU_H */
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index d3a303246c9f..e57dcce9bfda 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -231,10 +231,6 @@ config PUV3_PWM
 	help
 	  Enable support for NB0916 PWM controllers
 
-config PUV3_RTC
-	tristate "PKUnity v3 RTC Support"
-	depends on !ARCH_FPGA
-
 if PUV3_NB0916
 
 menu "PKUnity NetBook-0916 Features"
diff --git a/arch/unicore32/Makefile b/arch/unicore32/Makefile
index 76a8beec7d03..6af4bc415f2b 100644
--- a/arch/unicore32/Makefile
+++ b/arch/unicore32/Makefile
@@ -40,42 +40,10 @@ core-y			+= arch/unicore32/mm/
 
 libs-y			+= arch/unicore32/lib/
 
-ASM_GENERATED_DIR	:= $(srctree)/arch/unicore32/include/generated
-LINUXINCLUDE		+= -I$(ASM_GENERATED_DIR)
-
-ASM_GENERIC_HEADERS	:= atomic.h auxvec.h
-ASM_GENERIC_HEADERS	+= bitsperlong.h bug.h bugs.h
-ASM_GENERIC_HEADERS	+= cputime.h current.h
-ASM_GENERIC_HEADERS	+= device.h div64.h
-ASM_GENERIC_HEADERS	+= emergency-restart.h errno.h
-ASM_GENERIC_HEADERS	+= fb.h fcntl.h ftrace.h futex.h
-ASM_GENERIC_HEADERS	+= hardirq.h hw_irq.h
-ASM_GENERIC_HEADERS	+= ioctl.h ioctls.h ipcbuf.h irq_regs.h
-ASM_GENERIC_HEADERS	+= kdebug.h kmap_types.h
-ASM_GENERIC_HEADERS	+= local.h
-ASM_GENERIC_HEADERS	+= mman.h module.h msgbuf.h
-ASM_GENERIC_HEADERS	+= param.h parport.h percpu.h poll.h posix_types.h
-ASM_GENERIC_HEADERS	+= resource.h
-ASM_GENERIC_HEADERS	+= scatterlist.h sections.h segment.h sembuf.h serial.h
-ASM_GENERIC_HEADERS	+= setup.h shmbuf.h shmparam.h
-ASM_GENERIC_HEADERS	+= siginfo.h signal.h sizes.h
-ASM_GENERIC_HEADERS	+= socket.h sockios.h stat.h statfs.h swab.h syscalls.h
-ASM_GENERIC_HEADERS	+= termbits.h termios.h topology.h types.h
-ASM_GENERIC_HEADERS	+= ucontext.h unaligned.h user.h
-ASM_GENERIC_HEADERS	+= vga.h
-ASM_GENERIC_HEADERS	+= xor.h
-
-archprepare:
-ifneq ($(ASM_GENERATED_DIR), $(wildcard $(ASM_GENERATED_DIR)))
-	$(Q)mkdir -p $(ASM_GENERATED_DIR)/asm
-	$(Q)$(foreach a, $(ASM_GENERIC_HEADERS),	\
-		echo '#include <asm-generic/$a>'	\
-			> $(ASM_GENERATED_DIR)/asm/$a; )
-endif
-
 boot			:= arch/unicore32/boot
 
-# Default target when executing plain make
+# Default defconfig and target when executing plain make
+KBUILD_DEFCONFIG	:= $(ARCH)_defconfig
 KBUILD_IMAGE		:= zImage
 
 all:	$(KBUILD_IMAGE)
@@ -83,8 +51,6 @@ all:	$(KBUILD_IMAGE)
 zImage Image uImage: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
-MRPROPER_DIRS		+= $(ASM_GENERATED_DIR)
-
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
 
diff --git a/arch/unicore32/boot/compressed/Makefile b/arch/unicore32/boot/compressed/Makefile
index 95373428cb3d..b0954a2d23cf 100644
--- a/arch/unicore32/boot/compressed/Makefile
+++ b/arch/unicore32/boot/compressed/Makefile
@@ -59,7 +59,7 @@ $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head.o $(obj)/piggy.o \
 # We now have a PIC decompressor implementation.  Decompressors running
 # from RAM should not define ZTEXTADDR.  Decompressors running directly
 # from ROM or Flash must define ZTEXTADDR (preferably via the config)
-ZTEXTADDR	:= 0
+ZTEXTADDR	:= 0x03000000
 ZBSSADDR	:= ALIGN(4)
 
 SEDFLAGS_lds	= s/TEXT_START/$(ZTEXTADDR)/;s/BSS_START/$(ZBSSADDR)/
diff --git a/arch/unicore32/configs/debug_defconfig b/arch/unicore32/configs/unicore32_defconfig
index b5fbde9f1cb2..c9dd3198b6f7 100644
--- a/arch/unicore32/configs/debug_defconfig
+++ b/arch/unicore32/configs/unicore32_defconfig
@@ -1,6 +1,6 @@
 ### General setup
 CONFIG_EXPERIMENTAL=y
-CONFIG_LOCALVERSION="-debug"
+CONFIG_LOCALVERSION="-unicore32"
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
@@ -64,7 +64,6 @@ CONFIG_I2C_BATTERY_BQ27200=n
 CONFIG_I2C_EEPROM_AT24=n
 CONFIG_LCD_BACKLIGHT=n
 
-CONFIG_PUV3_RTC=y
 CONFIG_PUV3_UMAL=y
 CONFIG_PUV3_MUSB=n
 CONFIG_PUV3_AC97=n
@@ -167,8 +166,9 @@ CONFIG_LEDS_TRIGGER_IDE_DISK=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 
 #	Real Time Clock
-CONFIG_RTC_LIB=m
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PUV3=y
 
 ### File systems
 CONFIG_EXT2_FS=m
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index b200fdaca44d..ca113d6999c5 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -1,2 +1,61 @@
 include include/asm-generic/Kbuild.asm
 
+generic-y += atomic.h
+generic-y += auxvec.h
+generic-y += bitsperlong.h
+generic-y += bug.h
+generic-y += bugs.h
+generic-y += cputime.h
+generic-y += current.h
+generic-y += device.h
+generic-y += div64.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += fb.h
+generic-y += fcntl.h
+generic-y += ftrace.h
+generic-y += futex.h
+generic-y += hardirq.h
+generic-y += hw_irq.h
+generic-y += ioctl.h
+generic-y += ioctls.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += kdebug.h
+generic-y += kmap_types.h
+generic-y += local.h
+generic-y += mman.h
+generic-y += module.h
+generic-y += msgbuf.h
+generic-y += param.h
+generic-y += parport.h
+generic-y += percpu.h
+generic-y += poll.h
+generic-y += posix_types.h
+generic-y += resource.h
+generic-y += scatterlist.h
+generic-y += sections.h
+generic-y += segment.h
+generic-y += sembuf.h
+generic-y += serial.h
+generic-y += setup.h
+generic-y += shmbuf.h
+generic-y += shmparam.h
+generic-y += siginfo.h
+generic-y += signal.h
+generic-y += sizes.h
+generic-y += socket.h
+generic-y += sockios.h
+generic-y += stat.h
+generic-y += statfs.h
+generic-y += swab.h
+generic-y += syscalls.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += topology.h
+generic-y += types.h
+generic-y += ucontext.h
+generic-y += unaligned.h
+generic-y += user.h
+generic-y += vga.h
+generic-y += xor.h
diff --git a/arch/unicore32/include/asm/suspend.h b/arch/unicore32/include/asm/suspend.h
index 88a9c0f32b21..65bad75c7e96 100644
--- a/arch/unicore32/include/asm/suspend.h
+++ b/arch/unicore32/include/asm/suspend.h
@@ -14,7 +14,6 @@
 #define __UNICORE_SUSPEND_H__
 
 #ifndef __ASSEMBLY__
-static inline int arch_prepare_suspend(void) { return 0; }
 
 #include <asm/ptrace.h>
 
diff --git a/arch/unicore32/kernel/Makefile b/arch/unicore32/kernel/Makefile
index ec23a2fb2f50..aeb0f181568e 100644
--- a/arch/unicore32/kernel/Makefile
+++ b/arch/unicore32/kernel/Makefile
@@ -16,7 +16,6 @@ obj-$(CONFIG_UNICORE_FPU_F64)	+= fpu-ucf64.o
 obj-$(CONFIG_ARCH_PUV3)		+= clock.o irq.o time.o
 
 obj-$(CONFIG_PUV3_GPIO)		+= gpio.o
-obj-$(CONFIG_PUV3_RTC)		+= rtc.o
 obj-$(CONFIG_PUV3_PWM)		+= pwm.o
 obj-$(CONFIG_PUV3_PM)		+= pm.o sleep.o
 obj-$(CONFIG_HIBERNATION)	+= hibernate.o hibernate_asm.o
diff --git a/arch/unicore32/kernel/vmlinux.lds.S b/arch/unicore32/kernel/vmlinux.lds.S
index 9bf7f7af52c5..77e407e49a63 100644
--- a/arch/unicore32/kernel/vmlinux.lds.S
+++ b/arch/unicore32/kernel/vmlinux.lds.S
@@ -30,7 +30,7 @@ SECTIONS
 	HEAD_TEXT_SECTION
 	INIT_TEXT_SECTION(PAGE_SIZE)
 	INIT_DATA_SECTION(16)
-	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 	__init_end = .;
 
 	_stext = .;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 95f5826be458..c1870dddd322 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -849,4 +849,5 @@ ia32_sys_call_table:
 	.quad compat_sys_clock_adjtime
 	.quad sys_syncfs
 	.quad compat_sys_sendmmsg	/* 345 */
+	.quad sys_setns
 ia32_syscall_end:
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 416d865eae39..610001d385dd 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -139,7 +139,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
 	    boot_cpu_data.x86_model <= 0x05 &&
 	    boot_cpu_data.x86_mask < 0x0A)
 		return 1;
-	else if (c1e_detected)
+	else if (amd_e400_c1e_detected)
 		return 1;
 	else
 		return max_cstate;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 5dc6acc98dbd..71cc3800712c 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -125,7 +125,7 @@
 #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_F16C	(4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRND	(4*32+30) /* The RDRAND instruction */
+#define X86_FEATURE_RDRAND	(4*32+30) /* The RDRAND instruction */
 #define X86_FEATURE_HYPERVISOR	(4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 617bd56b3070..7b439d9aea2a 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -4,30 +4,33 @@
 #include <asm/desc_defs.h>
 #include <asm/ldt.h>
 #include <asm/mmu.h>
+
 #include <linux/smp.h>
 
-static inline void fill_ldt(struct desc_struct *desc,
-			    const struct user_desc *info)
-{
-	desc->limit0 = info->limit & 0x0ffff;
-	desc->base0 = info->base_addr & 0x0000ffff;
-
-	desc->base1 = (info->base_addr & 0x00ff0000) >> 16;
-	desc->type = (info->read_exec_only ^ 1) << 1;
-	desc->type |= info->contents << 2;
-	desc->s = 1;
-	desc->dpl = 0x3;
-	desc->p = info->seg_not_present ^ 1;
-	desc->limit = (info->limit & 0xf0000) >> 16;
-	desc->avl = info->useable;
-	desc->d = info->seg_32bit;
-	desc->g = info->limit_in_pages;
-	desc->base2 = (info->base_addr & 0xff000000) >> 24;
+static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *info)
+{
+	desc->limit0		= info->limit & 0x0ffff;
+
+	desc->base0		= (info->base_addr & 0x0000ffff);
+	desc->base1		= (info->base_addr & 0x00ff0000) >> 16;
+
+	desc->type		= (info->read_exec_only ^ 1) << 1;
+	desc->type	       |= info->contents << 2;
+
+	desc->s			= 1;
+	desc->dpl		= 0x3;
+	desc->p			= info->seg_not_present ^ 1;
+	desc->limit		= (info->limit & 0xf0000) >> 16;
+	desc->avl		= info->useable;
+	desc->d			= info->seg_32bit;
+	desc->g			= info->limit_in_pages;
+
+	desc->base2		= (info->base_addr & 0xff000000) >> 24;
 	/*
 	 * Don't allow setting of the lm bit. It is useless anyway
 	 * because 64bit system calls require __USER_CS:
 	 */
-	desc->l = 0;
+	desc->l			= 0;
 }
 
 extern struct desc_ptr idt_descr;
@@ -36,6 +39,7 @@ extern gate_desc idt_table[];
 struct gdt_page {
 	struct desc_struct gdt[GDT_ENTRIES];
 } __attribute__((aligned(PAGE_SIZE)));
+
 DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
 
 static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
@@ -48,16 +52,16 @@ static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
 static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func,
 			     unsigned dpl, unsigned ist, unsigned seg)
 {
-	gate->offset_low = PTR_LOW(func);
-	gate->segment = __KERNEL_CS;
-	gate->ist = ist;
-	gate->p = 1;
-	gate->dpl = dpl;
-	gate->zero0 = 0;
-	gate->zero1 = 0;
-	gate->type = type;
-	gate->offset_middle = PTR_MIDDLE(func);
-	gate->offset_high = PTR_HIGH(func);
+	gate->offset_low	= PTR_LOW(func);
+	gate->segment		= __KERNEL_CS;
+	gate->ist		= ist;
+	gate->p			= 1;
+	gate->dpl		= dpl;
+	gate->zero0		= 0;
+	gate->zero1		= 0;
+	gate->type		= type;
+	gate->offset_middle	= PTR_MIDDLE(func);
+	gate->offset_high	= PTR_HIGH(func);
 }
 
 #else
@@ -66,8 +70,7 @@ static inline void pack_gate(gate_desc *gate, unsigned char type,
 			     unsigned short seg)
 {
 	gate->a = (seg << 16) | (base & 0xffff);
-	gate->b = (base & 0xffff0000) |
-		  (((0x80 | type | (dpl << 5)) & 0xff) << 8);
+	gate->b = (base & 0xffff0000) | (((0x80 | type | (dpl << 5)) & 0xff) << 8);
 }
 
 #endif
@@ -75,31 +78,29 @@ static inline void pack_gate(gate_desc *gate, unsigned char type,
 static inline int desc_empty(const void *ptr)
 {
 	const u32 *desc = ptr;
+
 	return !(desc[0] | desc[1]);
 }
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
-#define load_TR_desc() native_load_tr_desc()
-#define load_gdt(dtr) native_load_gdt(dtr)
-#define load_idt(dtr) native_load_idt(dtr)
-#define load_tr(tr) asm volatile("ltr %0"::"m" (tr))
-#define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt))
-
-#define store_gdt(dtr) native_store_gdt(dtr)
-#define store_idt(dtr) native_store_idt(dtr)
-#define store_tr(tr) (tr = native_store_tr())
-
-#define load_TLS(t, cpu) native_load_tls(t, cpu)
-#define set_ldt native_set_ldt
-
-#define write_ldt_entry(dt, entry, desc)	\
-	native_write_ldt_entry(dt, entry, desc)
-#define write_gdt_entry(dt, entry, desc, type)		\
-	native_write_gdt_entry(dt, entry, desc, type)
-#define write_idt_entry(dt, entry, g)		\
-	native_write_idt_entry(dt, entry, g)
+#define load_TR_desc()				native_load_tr_desc()
+#define load_gdt(dtr)				native_load_gdt(dtr)
+#define load_idt(dtr)				native_load_idt(dtr)
+#define load_tr(tr)				asm volatile("ltr %0"::"m" (tr))
+#define load_ldt(ldt)				asm volatile("lldt %0"::"m" (ldt))
+
+#define store_gdt(dtr)				native_store_gdt(dtr)
+#define store_idt(dtr)				native_store_idt(dtr)
+#define store_tr(tr)				(tr = native_store_tr())
+
+#define load_TLS(t, cpu)			native_load_tls(t, cpu)
+#define set_ldt					native_set_ldt
+
+#define write_ldt_entry(dt, entry, desc)	native_write_ldt_entry(dt, entry, desc)
+#define write_gdt_entry(dt, entry, desc, type)	native_write_gdt_entry(dt, entry, desc, type)
+#define write_idt_entry(dt, entry, g)		native_write_idt_entry(dt, entry, g)
 
 static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
 {
@@ -112,33 +113,27 @@ static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
 
 #define store_ldt(ldt) asm("sldt %0" : "=m"(ldt))
 
-static inline void native_write_idt_entry(gate_desc *idt, int entry,
-					  const gate_desc *gate)
+static inline void native_write_idt_entry(gate_desc *idt, int entry, const gate_desc *gate)
 {
 	memcpy(&idt[entry], gate, sizeof(*gate));
 }
 
-static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry,
-					  const void *desc)
+static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry, const void *desc)
 {
 	memcpy(&ldt[entry], desc, 8);
 }
 
-static inline void native_write_gdt_entry(struct desc_struct *gdt, int entry,
-					  const void *desc, int type)
+static inline void
+native_write_gdt_entry(struct desc_struct *gdt, int entry, const void *desc, int type)
 {
 	unsigned int size;
+
 	switch (type) {
-	case DESC_TSS:
-		size = sizeof(tss_desc);
-		break;
-	case DESC_LDT:
-		size = sizeof(ldt_desc);
-		break;
-	default:
-		size = sizeof(struct desc_struct);
-		break;
+	case DESC_TSS:	size = sizeof(tss_desc);	break;
+	case DESC_LDT:	size = sizeof(ldt_desc);	break;
+	default:	size = sizeof(*gdt);		break;
 	}
+
 	memcpy(&gdt[entry], desc, size);
 }
 
@@ -154,20 +149,21 @@ static inline void pack_descriptor(struct desc_struct *desc, unsigned long base,
 }
 
 
-static inline void set_tssldt_descriptor(void *d, unsigned long addr,
-					 unsigned type, unsigned size)
+static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned type, unsigned size)
 {
 #ifdef CONFIG_X86_64
 	struct ldttss_desc64 *desc = d;
+
 	memset(desc, 0, sizeof(*desc));
-	desc->limit0 = size & 0xFFFF;
-	desc->base0 = PTR_LOW(addr);
-	desc->base1 = PTR_MIDDLE(addr) & 0xFF;
-	desc->type = type;
-	desc->p = 1;
-	desc->limit1 = (size >> 16) & 0xF;
-	desc->base2 = (PTR_MIDDLE(addr) >> 8) & 0xFF;
-	desc->base3 = PTR_HIGH(addr);
+
+	desc->limit0		= size & 0xFFFF;
+	desc->base0		= PTR_LOW(addr);
+	desc->base1		= PTR_MIDDLE(addr) & 0xFF;
+	desc->type		= type;
+	desc->p			= 1;
+	desc->limit1		= (size >> 16) & 0xF;
+	desc->base2		= (PTR_MIDDLE(addr) >> 8) & 0xFF;
+	desc->base3		= PTR_HIGH(addr);
 #else
 	pack_descriptor((struct desc_struct *)d, addr, size, 0x80 | type, 0);
 #endif
@@ -237,14 +233,16 @@ static inline void native_store_idt(struct desc_ptr *dtr)
 static inline unsigned long native_store_tr(void)
 {
 	unsigned long tr;
+
 	asm volatile("str %0":"=r" (tr));
+
 	return tr;
 }
 
 static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
 {
-	unsigned int i;
 	struct desc_struct *gdt = get_cpu_gdt_table(cpu);
+	unsigned int i;
 
 	for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
 		gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
@@ -313,6 +311,7 @@ static inline void _set_gate(int gate, unsigned type, void *addr,
 			     unsigned dpl, unsigned ist, unsigned seg)
 {
 	gate_desc s;
+
 	pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg);
 	/*
 	 * does not need to be atomic because it is only done once at
@@ -343,8 +342,9 @@ static inline void alloc_system_vector(int vector)
 		set_bit(vector, used_vectors);
 		if (first_system_vector > vector)
 			first_system_vector = vector;
-	} else
+	} else {
 		BUG();
+	}
 }
 
 static inline void alloc_intr_gate(unsigned int n, void *addr)
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
index 38d87379e270..f49253d75710 100644
--- a/arch/x86/include/asm/idle.h
+++ b/arch/x86/include/asm/idle.h
@@ -16,6 +16,6 @@ static inline void enter_idle(void) { }
 static inline void exit_idle(void) { }
 #endif /* CONFIG_X86_64 */
 
-void c1e_remove_cpu(int cpu);
+void amd_e400_remove_cpu(int cpu);
 
 #endif /* _ASM_X86_IDLE_H */
diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h
index 19ae14ba6978..0cd3800f33b9 100644
--- a/arch/x86/include/asm/memblock.h
+++ b/arch/x86/include/asm/memblock.h
@@ -4,7 +4,6 @@
 #define ARCH_DISCARD_MEMBLOCK
 
 u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align);
-void memblock_x86_to_bootmem(u64 start, u64 end);
 
 void memblock_x86_reserve_range(u64 start, u64 end, char *name);
 void memblock_x86_free_range(u64 start, u64 end);
@@ -19,5 +18,6 @@ u64 memblock_x86_hole_size(u64 start, u64 end);
 u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align);
 u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit);
 u64 memblock_x86_memory_in_range(u64 addr, u64 limit);
+bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align);
 
 #endif
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index aeff3e89b222..5f55e6962769 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -11,14 +11,14 @@
 typedef struct {
 	void *ldt;
 	int size;
-	struct mutex lock;
-	void *vdso;
 
 #ifdef CONFIG_X86_64
 	/* True if mm supports a task running in 32 bit compatibility mode. */
 	unsigned short ia32_compat;
 #endif
 
+	struct mutex lock;
+	void *vdso;
 } mm_context_t;
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 5e83a416eca8..224e8c5eb307 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -48,17 +48,6 @@ static inline int pfn_to_nid(unsigned long pfn)
 #endif
 }
 
-/*
- * Following are macros that each numa implmentation must define.
- */
-
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)						\
-({									\
-	pg_data_t *__pgdat = NODE_DATA(nid);				\
-	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;		\
-})
-
 static inline int pfn_valid(int pfn)
 {
 	int nid = pfn_to_nid(pfn);
diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h
index b3f88d7867c7..129d9aa3ceb3 100644
--- a/arch/x86/include/asm/mmzone_64.h
+++ b/arch/x86/include/asm/mmzone_64.h
@@ -13,8 +13,5 @@ extern struct pglist_data *node_data[];
 
 #define NODE_DATA(nid)		(node_data[nid])
 
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)       (NODE_DATA(nid)->node_start_pfn +	\
-				 NODE_DATA(nid)->node_spanned_pages)
 #endif
 #endif /* _ASM_X86_MMZONE_64_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 4c25ab48257b..219371546afd 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -754,10 +754,10 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
 
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
-extern void init_c1e_mask(void);
+extern void init_amd_e400_c1e_mask(void);
 
 extern unsigned long		boot_option_idle_override;
-extern bool			c1e_detected;
+extern bool			amd_e400_c1e_detected;
 
 enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT,
 			 IDLE_POLL, IDLE_FORCE_MWAIT};
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 31d84acc1512..a518c0a45044 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -22,6 +22,8 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 	u64 product;
 #ifdef __i386__
 	u32 tmp1, tmp2;
+#else
+	ulong tmp;
 #endif
 
 	if (shift < 0)
@@ -42,8 +44,11 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
 #elif defined(__x86_64__)
 	__asm__ (
-		"mul %%rdx ; shrd $32,%%rdx,%%rax"
-		: "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
+		"mul %[mul_frac] ; shrd $32, %[hi], %[lo]"
+		: [lo]"=a"(product),
+		  [hi]"=d"(tmp)
+		: "0"(delta),
+		  [mul_frac]"rm"((u64)mul_frac));
 #else
 #error implement me!
 #endif
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index fd921c3a6841..487055c8c1aa 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -9,8 +9,6 @@
 #include <asm/desc.h>
 #include <asm/i387.h>
 
-static inline int arch_prepare_suspend(void) { return 0; }
-
 /* image of the saved processor state */
 struct saved_context {
 	u16 es, fs, gs, ss;
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 8d942afae681..09b0bf104156 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -9,11 +9,6 @@
 #include <asm/desc.h>
 #include <asm/i387.h>
 
-static inline int arch_prepare_suspend(void)
-{
-	return 0;
-}
-
 /*
  * Image of the saved processor state, used by the low level ACPI suspend to
  * RAM code and by the low level hibernation code.
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index fb6a625c99bf..593485b38ab3 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -351,10 +351,11 @@
 #define __NR_clock_adjtime	343
 #define __NR_syncfs             344
 #define __NR_sendmmsg		345
+#define __NR_setns		346
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 346
+#define NR_syscalls 347
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index 79f90eb15aad..705bf139288c 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -679,6 +679,8 @@ __SYSCALL(__NR_clock_adjtime, sys_clock_adjtime)
 __SYSCALL(__NR_syncfs, sys_syncfs)
 #define __NR_sendmmsg				307
 __SYSCALL(__NR_sendmmsg, sys_sendmmsg)
+#define __NR_setns				308
+__SYSCALL(__NR_setns, sys_setns)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 130f1eeee5fe..a291c40efd43 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -5,7 +5,7 @@
  *
  * SGI UV Broadcast Assist Unit definitions
  *
- * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2008-2011 Silicon Graphics, Inc. All rights reserved.
  */
 
 #ifndef _ASM_X86_UV_UV_BAU_H
@@ -35,17 +35,20 @@
 
 #define MAX_CPUS_PER_UVHUB		64
 #define MAX_CPUS_PER_SOCKET		32
-#define UV_ADP_SIZE			64 /* hardware-provided max. */
-#define UV_CPUS_PER_ACT_STATUS		32 /* hardware-provided max. */
-#define UV_ITEMS_PER_DESCRIPTOR		8
+#define ADP_SZ				64 /* hardware-provided max. */
+#define UV_CPUS_PER_AS			32 /* hardware-provided max. */
+#define ITEMS_PER_DESC			8
 /* the 'throttle' to prevent the hardware stay-busy bug */
 #define MAX_BAU_CONCURRENT		3
 #define UV_ACT_STATUS_MASK		0x3
 #define UV_ACT_STATUS_SIZE		2
 #define UV_DISTRIBUTION_SIZE		256
 #define UV_SW_ACK_NPENDING		8
-#define UV_NET_ENDPOINT_INTD		0x38
-#define UV_DESC_BASE_PNODE_SHIFT	49
+#define UV1_NET_ENDPOINT_INTD		0x38
+#define UV2_NET_ENDPOINT_INTD		0x28
+#define UV_NET_ENDPOINT_INTD		(is_uv1_hub() ?			\
+			UV1_NET_ENDPOINT_INTD : UV2_NET_ENDPOINT_INTD)
+#define UV_DESC_PSHIFT			49
 #define UV_PAYLOADQ_PNODE_SHIFT		49
 #define UV_PTC_BASENAME			"sgi_uv/ptc_statistics"
 #define UV_BAU_BASENAME			"sgi_uv/bau_tunables"
@@ -53,29 +56,64 @@
 #define UV_BAU_TUNABLES_FILE		"bau_tunables"
 #define WHITESPACE			" \t\n"
 #define uv_physnodeaddr(x)		((__pa((unsigned long)(x)) & uv_mmask))
-#define UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT 15
-#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT 16
-#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x0000000009UL
+#define cpubit_isset(cpu, bau_local_cpumask) \
+	test_bit((cpu), (bau_local_cpumask).bits)
+
 /* [19:16] SOFT_ACK timeout period  19: 1 is urgency 7  17:16 1 is multiplier */
-#define BAU_MISC_CONTROL_MULT_MASK 3
+/*
+ * UV2: Bit 19 selects between
+ *  (0): 10 microsecond timebase and
+ *  (1): 80 microseconds
+ *  we're using 655us, similar to UV1: 65 units of 10us
+ */
+#define UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD (9UL)
+#define UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD (65*10UL)
+
+#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD	(is_uv1_hub() ?			\
+		UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD :			\
+		UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD)
 
-#define UVH_AGING_PRESCALE_SEL 0x000000b000UL
+#define BAU_MISC_CONTROL_MULT_MASK	3
+
+#define UVH_AGING_PRESCALE_SEL		0x000000b000UL
 /* [30:28] URGENCY_7  an index into a table of times */
-#define BAU_URGENCY_7_SHIFT 28
-#define BAU_URGENCY_7_MASK 7
+#define BAU_URGENCY_7_SHIFT		28
+#define BAU_URGENCY_7_MASK		7
 
-#define UVH_TRANSACTION_TIMEOUT 0x000000b200UL
+#define UVH_TRANSACTION_TIMEOUT		0x000000b200UL
 /* [45:40] BAU - BAU transaction timeout select - a multiplier */
-#define BAU_TRANS_SHIFT 40
-#define BAU_TRANS_MASK 0x3f
+#define BAU_TRANS_SHIFT			40
+#define BAU_TRANS_MASK			0x3f
+
+/*
+ * shorten some awkward names
+ */
+#define AS_PUSH_SHIFT UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT
+#define SOFTACK_MSHIFT UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT
+#define SOFTACK_PSHIFT UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT
+#define SOFTACK_TIMEOUT_PERIOD UV_INTD_SOFT_ACK_TIMEOUT_PERIOD
+#define write_gmmr	uv_write_global_mmr64
+#define write_lmmr	uv_write_local_mmr
+#define read_lmmr	uv_read_local_mmr
+#define read_gmmr	uv_read_global_mmr64
 
 /*
  * bits in UVH_LB_BAU_SB_ACTIVATION_STATUS_0/1
  */
-#define DESC_STATUS_IDLE		0
-#define DESC_STATUS_ACTIVE		1
-#define DESC_STATUS_DESTINATION_TIMEOUT	2
-#define DESC_STATUS_SOURCE_TIMEOUT	3
+#define DS_IDLE				0
+#define DS_ACTIVE			1
+#define DS_DESTINATION_TIMEOUT		2
+#define DS_SOURCE_TIMEOUT		3
+/*
+ * bits put together from HRP_LB_BAU_SB_ACTIVATION_STATUS_0/1/2
+ * values 1 and 5 will not occur
+ */
+#define UV2H_DESC_IDLE			0
+#define UV2H_DESC_DEST_TIMEOUT		2
+#define UV2H_DESC_DEST_STRONG_NACK	3
+#define UV2H_DESC_BUSY			4
+#define UV2H_DESC_SOURCE_TIMEOUT	6
+#define UV2H_DESC_DEST_PUT_ERR		7
 
 /*
  * delay for 'plugged' timeout retries, in microseconds
@@ -86,15 +124,24 @@
  * threshholds at which to use IPI to free resources
  */
 /* after this # consecutive 'plugged' timeouts, use IPI to release resources */
-#define PLUGSB4RESET 100
+#define PLUGSB4RESET			100
 /* after this many consecutive timeouts, use IPI to release resources */
-#define TIMEOUTSB4RESET 1
+#define TIMEOUTSB4RESET			1
 /* at this number uses of IPI to release resources, giveup the request */
-#define IPI_RESET_LIMIT 1
+#define IPI_RESET_LIMIT			1
 /* after this # consecutive successes, bump up the throttle if it was lowered */
-#define COMPLETE_THRESHOLD 5
+#define COMPLETE_THRESHOLD		5
+
+#define UV_LB_SUBNODEID			0x10
 
-#define UV_LB_SUBNODEID 0x10
+/* these two are the same for UV1 and UV2: */
+#define UV_SA_SHFT UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT
+#define UV_SA_MASK UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK
+/* 4 bits of software ack period */
+#define UV2_ACK_MASK			0x7UL
+#define UV2_ACK_UNITS_SHFT		3
+#define UV2_LEG_SHFT UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT
+#define UV2_EXT_SHFT UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT
 
 /*
  * number of entries in the destination side payload queue
@@ -115,9 +162,16 @@
 /*
  * tuning the action when the numalink network is extremely delayed
  */
-#define CONGESTED_RESPONSE_US 1000 /* 'long' response time, in microseconds */
-#define CONGESTED_REPS 10 /* long delays averaged over this many broadcasts */
-#define CONGESTED_PERIOD 30 /* time for the bau to be disabled, in seconds */
+#define CONGESTED_RESPONSE_US		1000	/* 'long' response time, in
+						   microseconds */
+#define CONGESTED_REPS			10	/* long delays averaged over
+						   this many broadcasts */
+#define CONGESTED_PERIOD		30	/* time for the bau to be
+						   disabled, in seconds */
+/* see msg_type: */
+#define MSG_NOOP			0
+#define MSG_REGULAR			1
+#define MSG_RETRY			2
 
 /*
  * Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor)
@@ -129,8 +183,8 @@
  * 'base_dest_nasid' field of the header corresponds to the
  * destination nodeID associated with that specified bit.
  */
-struct bau_target_uvhubmask {
-	unsigned long bits[BITS_TO_LONGS(UV_DISTRIBUTION_SIZE)];
+struct bau_targ_hubmask {
+	unsigned long		bits[BITS_TO_LONGS(UV_DISTRIBUTION_SIZE)];
 };
 
 /*
@@ -139,7 +193,7 @@ struct bau_target_uvhubmask {
  *  enough bits for max. cpu's per uvhub)
  */
 struct bau_local_cpumask {
-	unsigned long bits;
+	unsigned long		bits;
 };
 
 /*
@@ -160,14 +214,14 @@ struct bau_local_cpumask {
  * The payload is software-defined for INTD transactions
  */
 struct bau_msg_payload {
-	unsigned long address;		/* signifies a page or all TLB's
-						of the cpu */
+	unsigned long	address;		/* signifies a page or all
+						   TLB's of the cpu */
 	/* 64 bits */
-	unsigned short sending_cpu;	/* filled in by sender */
+	unsigned short	sending_cpu;		/* filled in by sender */
 	/* 16 bits */
-	unsigned short acknowledge_count;/* filled in by destination */
+	unsigned short	acknowledge_count;	/* filled in by destination */
 	/* 16 bits */
-	unsigned int reserved1:32;	/* not usable */
+	unsigned int	reserved1:32;		/* not usable */
 };
 
 
@@ -176,93 +230,96 @@ struct bau_msg_payload {
  * see table 4.2.3.0.1 in broacast_assist spec.
  */
 struct bau_msg_header {
-	unsigned int dest_subnodeid:6;	/* must be 0x10, for the LB */
+	unsigned int	dest_subnodeid:6;	/* must be 0x10, for the LB */
 	/* bits 5:0 */
-	unsigned int base_dest_nasid:15; /* nasid of the */
-	/* bits 20:6 */			  /* first bit in uvhub map */
-	unsigned int command:8;	/* message type */
+	unsigned int	base_dest_nasid:15;	/* nasid of the first bit */
+	/* bits 20:6 */				/* in uvhub map */
+	unsigned int	command:8;		/* message type */
 	/* bits 28:21 */
-				/* 0x38: SN3net EndPoint Message */
-	unsigned int rsvd_1:3;	/* must be zero */
+	/* 0x38: SN3net EndPoint Message */
+	unsigned int	rsvd_1:3;		/* must be zero */
 	/* bits 31:29 */
-				/* int will align on 32 bits */
-	unsigned int rsvd_2:9;	/* must be zero */
+	/* int will align on 32 bits */
+	unsigned int	rsvd_2:9;		/* must be zero */
 	/* bits 40:32 */
-				/* Suppl_A is 56-41 */
-	unsigned int sequence:16;/* message sequence number */
-	/* bits 56:41 */	/* becomes bytes 16-17 of msg */
-				/* Address field (96:57) is never used as an
-				   address (these are address bits 42:3) */
-
-	unsigned int rsvd_3:1;	/* must be zero */
+	/* Suppl_A is 56-41 */
+	unsigned int	sequence:16;		/* message sequence number */
+	/* bits 56:41 */			/* becomes bytes 16-17 of msg */
+						/* Address field (96:57) is
+						   never used as an address
+						   (these are address bits
+						   42:3) */
+
+	unsigned int	rsvd_3:1;		/* must be zero */
 	/* bit 57 */
-				/* address bits 27:4 are payload */
+	/* address bits 27:4 are payload */
 	/* these next 24  (58-81) bits become bytes 12-14 of msg */
-
 	/* bits 65:58 land in byte 12 */
-	unsigned int replied_to:1;/* sent as 0 by the source to byte 12 */
+	unsigned int	replied_to:1;		/* sent as 0 by the source to
+						   byte 12 */
 	/* bit 58 */
-	unsigned int msg_type:3; /* software type of the message*/
+	unsigned int	msg_type:3;		/* software type of the
+						   message */
 	/* bits 61:59 */
-	unsigned int canceled:1; /* message canceled, resource to be freed*/
+	unsigned int	canceled:1;		/* message canceled, resource
+						   is to be freed*/
 	/* bit 62 */
-	unsigned int payload_1a:1;/* not currently used */
+	unsigned int	payload_1a:1;		/* not currently used */
 	/* bit 63 */
-	unsigned int payload_1b:2;/* not currently used */
+	unsigned int	payload_1b:2;		/* not currently used */
 	/* bits 65:64 */
 
 	/* bits 73:66 land in byte 13 */
-	unsigned int payload_1ca:6;/* not currently used */
+	unsigned int	payload_1ca:6;		/* not currently used */
 	/* bits 71:66 */
-	unsigned int payload_1c:2;/* not currently used */
+	unsigned int	payload_1c:2;		/* not currently used */
 	/* bits 73:72 */
 
 	/* bits 81:74 land in byte 14 */
-	unsigned int payload_1d:6;/* not currently used */
+	unsigned int	payload_1d:6;		/* not currently used */
 	/* bits 79:74 */
-	unsigned int payload_1e:2;/* not currently used */
+	unsigned int	payload_1e:2;		/* not currently used */
 	/* bits 81:80 */
 
-	unsigned int rsvd_4:7;	/* must be zero */
+	unsigned int	rsvd_4:7;		/* must be zero */
 	/* bits 88:82 */
-	unsigned int sw_ack_flag:1;/* software acknowledge flag */
+	unsigned int	swack_flag:1;		/* software acknowledge flag */
 	/* bit 89 */
-				/* INTD trasactions at destination are to
-				   wait for software acknowledge */
-	unsigned int rsvd_5:6;	/* must be zero */
+						/* INTD trasactions at
+						   destination are to wait for
+						   software acknowledge */
+	unsigned int	rsvd_5:6;		/* must be zero */
 	/* bits 95:90 */
-	unsigned int rsvd_6:5;	/* must be zero */
+	unsigned int	rsvd_6:5;		/* must be zero */
 	/* bits 100:96 */
-	unsigned int int_both:1;/* if 1, interrupt both sockets on the uvhub */
+	unsigned int	int_both:1;		/* if 1, interrupt both sockets
+						   on the uvhub */
 	/* bit 101*/
-	unsigned int fairness:3;/* usually zero */
+	unsigned int	fairness:3;		/* usually zero */
 	/* bits 104:102 */
-	unsigned int multilevel:1;	/* multi-level multicast format */
+	unsigned int	multilevel:1;		/* multi-level multicast
+						   format */
 	/* bit 105 */
-				/* 0 for TLB: endpoint multi-unicast messages */
-	unsigned int chaining:1;/* next descriptor is part of this activation*/
+	/* 0 for TLB: endpoint multi-unicast messages */
+	unsigned int	chaining:1;		/* next descriptor is part of
+						   this activation*/
 	/* bit 106 */
-	unsigned int rsvd_7:21;	/* must be zero */
+	unsigned int	rsvd_7:21;		/* must be zero */
 	/* bits 127:107 */
 };
 
-/* see msg_type: */
-#define MSG_NOOP 0
-#define MSG_REGULAR 1
-#define MSG_RETRY 2
-
 /*
  * The activation descriptor:
  * The format of the message to send, plus all accompanying control
  * Should be 64 bytes
  */
 struct bau_desc {
-	struct bau_target_uvhubmask distribution;
+	struct bau_targ_hubmask	distribution;
 	/*
 	 * message template, consisting of header and payload:
 	 */
-	struct bau_msg_header header;
-	struct bau_msg_payload payload;
+	struct bau_msg_header		header;
+	struct bau_msg_payload		payload;
 };
 /*
  *   -payload--    ---------header------
@@ -281,59 +338,51 @@ struct bau_desc {
  * are 32 bytes (2 micropackets) (256 bits) in length, but contain only 17
  * bytes of usable data, including the sw ack vector in byte 15 (bits 127:120)
  * (12 bytes come from bau_msg_payload, 3 from payload_1, 2 from
- *  sw_ack_vector and payload_2)
+ *  swack_vec and payload_2)
  * "Enabling Software Acknowledgment mode (see Section 4.3.3 Software
  *  Acknowledge Processing) also selects 32 byte (17 bytes usable) payload
  *  operation."
  */
-struct bau_payload_queue_entry {
-	unsigned long address;		/* signifies a page or all TLB's
-						of the cpu */
+struct bau_pq_entry {
+	unsigned long	address;	/* signifies a page or all TLB's
+					   of the cpu */
 	/* 64 bits, bytes 0-7 */
-
-	unsigned short sending_cpu;	/* cpu that sent the message */
+	unsigned short	sending_cpu;	/* cpu that sent the message */
 	/* 16 bits, bytes 8-9 */
-
-	unsigned short acknowledge_count; /* filled in by destination */
+	unsigned short	acknowledge_count; /* filled in by destination */
 	/* 16 bits, bytes 10-11 */
-
 	/* these next 3 bytes come from bits 58-81 of the message header */
-	unsigned short replied_to:1;    /* sent as 0 by the source */
-	unsigned short msg_type:3;      /* software message type */
-	unsigned short canceled:1;      /* sent as 0 by the source */
-	unsigned short unused1:3;       /* not currently using */
+	unsigned short	replied_to:1;	/* sent as 0 by the source */
+	unsigned short	msg_type:3;	/* software message type */
+	unsigned short	canceled:1;	/* sent as 0 by the source */
+	unsigned short	unused1:3;	/* not currently using */
 	/* byte 12 */
-
-	unsigned char unused2a;		/* not currently using */
+	unsigned char	unused2a;	/* not currently using */
 	/* byte 13 */
-	unsigned char unused2;		/* not currently using */
+	unsigned char	unused2;	/* not currently using */
 	/* byte 14 */
-
-	unsigned char sw_ack_vector;	/* filled in by the hardware */
+	unsigned char	swack_vec;	/* filled in by the hardware */
 	/* byte 15 (bits 127:120) */
-
-	unsigned short sequence;	/* message sequence number */
+	unsigned short	sequence;	/* message sequence number */
 	/* bytes 16-17 */
-	unsigned char unused4[2];	/* not currently using bytes 18-19 */
+	unsigned char	unused4[2];	/* not currently using bytes 18-19 */
 	/* bytes 18-19 */
-
-	int number_of_cpus;		/* filled in at destination */
+	int		number_of_cpus;	/* filled in at destination */
 	/* 32 bits, bytes 20-23 (aligned) */
-
-	unsigned char unused5[8];       /* not using */
+	unsigned char	unused5[8];	/* not using */
 	/* bytes 24-31 */
 };
 
 struct msg_desc {
-	struct bau_payload_queue_entry *msg;
-	int msg_slot;
-	int sw_ack_slot;
-	struct bau_payload_queue_entry *va_queue_first;
-	struct bau_payload_queue_entry *va_queue_last;
+	struct bau_pq_entry	*msg;
+	int			msg_slot;
+	int			swack_slot;
+	struct bau_pq_entry	*queue_first;
+	struct bau_pq_entry	*queue_last;
 };
 
 struct reset_args {
-	int sender;
+	int			sender;
 };
 
 /*
@@ -341,112 +390,226 @@ struct reset_args {
  */
 struct ptc_stats {
 	/* sender statistics */
-	unsigned long s_giveup; /* number of fall backs to IPI-style flushes */
-	unsigned long s_requestor; /* number of shootdown requests */
-	unsigned long s_stimeout; /* source side timeouts */
-	unsigned long s_dtimeout; /* destination side timeouts */
-	unsigned long s_time; /* time spent in sending side */
-	unsigned long s_retriesok; /* successful retries */
-	unsigned long s_ntargcpu; /* total number of cpu's targeted */
-	unsigned long s_ntargself; /* times the sending cpu was targeted */
-	unsigned long s_ntarglocals; /* targets of cpus on the local blade */
-	unsigned long s_ntargremotes; /* targets of cpus on remote blades */
-	unsigned long s_ntarglocaluvhub; /* targets of the local hub */
-	unsigned long s_ntargremoteuvhub; /* remotes hubs targeted */
-	unsigned long s_ntarguvhub; /* total number of uvhubs targeted */
-	unsigned long s_ntarguvhub16; /* number of times target hubs >= 16*/
-	unsigned long s_ntarguvhub8; /* number of times target hubs >= 8 */
-	unsigned long s_ntarguvhub4; /* number of times target hubs >= 4 */
-	unsigned long s_ntarguvhub2; /* number of times target hubs >= 2 */
-	unsigned long s_ntarguvhub1; /* number of times target hubs == 1 */
-	unsigned long s_resets_plug; /* ipi-style resets from plug state */
-	unsigned long s_resets_timeout; /* ipi-style resets from timeouts */
-	unsigned long s_busy; /* status stayed busy past s/w timer */
-	unsigned long s_throttles; /* waits in throttle */
-	unsigned long s_retry_messages; /* retry broadcasts */
-	unsigned long s_bau_reenabled; /* for bau enable/disable */
-	unsigned long s_bau_disabled; /* for bau enable/disable */
+	unsigned long	s_giveup;		/* number of fall backs to
+						   IPI-style flushes */
+	unsigned long	s_requestor;		/* number of shootdown
+						   requests */
+	unsigned long	s_stimeout;		/* source side timeouts */
+	unsigned long	s_dtimeout;		/* destination side timeouts */
+	unsigned long	s_time;			/* time spent in sending side */
+	unsigned long	s_retriesok;		/* successful retries */
+	unsigned long	s_ntargcpu;		/* total number of cpu's
+						   targeted */
+	unsigned long	s_ntargself;		/* times the sending cpu was
+						   targeted */
+	unsigned long	s_ntarglocals;		/* targets of cpus on the local
+						   blade */
+	unsigned long	s_ntargremotes;		/* targets of cpus on remote
+						   blades */
+	unsigned long	s_ntarglocaluvhub;	/* targets of the local hub */
+	unsigned long	s_ntargremoteuvhub;	/* remotes hubs targeted */
+	unsigned long	s_ntarguvhub;		/* total number of uvhubs
+						   targeted */
+	unsigned long	s_ntarguvhub16;		/* number of times target
+						   hubs >= 16*/
+	unsigned long	s_ntarguvhub8;		/* number of times target
+						   hubs >= 8 */
+	unsigned long	s_ntarguvhub4;		/* number of times target
+						   hubs >= 4 */
+	unsigned long	s_ntarguvhub2;		/* number of times target
+						   hubs >= 2 */
+	unsigned long	s_ntarguvhub1;		/* number of times target
+						   hubs == 1 */
+	unsigned long	s_resets_plug;		/* ipi-style resets from plug
+						   state */
+	unsigned long	s_resets_timeout;	/* ipi-style resets from
+						   timeouts */
+	unsigned long	s_busy;			/* status stayed busy past
+						   s/w timer */
+	unsigned long	s_throttles;		/* waits in throttle */
+	unsigned long	s_retry_messages;	/* retry broadcasts */
+	unsigned long	s_bau_reenabled;	/* for bau enable/disable */
+	unsigned long	s_bau_disabled;		/* for bau enable/disable */
 	/* destination statistics */
-	unsigned long d_alltlb; /* times all tlb's on this cpu were flushed */
-	unsigned long d_onetlb; /* times just one tlb on this cpu was flushed */
-	unsigned long d_multmsg; /* interrupts with multiple messages */
-	unsigned long d_nomsg; /* interrupts with no message */
-	unsigned long d_time; /* time spent on destination side */
-	unsigned long d_requestee; /* number of messages processed */
-	unsigned long d_retries; /* number of retry messages processed */
-	unsigned long d_canceled; /* number of messages canceled by retries */
-	unsigned long d_nocanceled; /* retries that found nothing to cancel */
-	unsigned long d_resets; /* number of ipi-style requests processed */
-	unsigned long d_rcanceled; /* number of messages canceled by resets */
+	unsigned long	d_alltlb;		/* times all tlb's on this
+						   cpu were flushed */
+	unsigned long	d_onetlb;		/* times just one tlb on this
+						   cpu was flushed */
+	unsigned long	d_multmsg;		/* interrupts with multiple
+						   messages */
+	unsigned long	d_nomsg;		/* interrupts with no message */
+	unsigned long	d_time;			/* time spent on destination
+						   side */
+	unsigned long	d_requestee;		/* number of messages
+						   processed */
+	unsigned long	d_retries;		/* number of retry messages
+						   processed */
+	unsigned long	d_canceled;		/* number of messages canceled
+						   by retries */
+	unsigned long	d_nocanceled;		/* retries that found nothing
+						   to cancel */
+	unsigned long	d_resets;		/* number of ipi-style requests
+						   processed */
+	unsigned long	d_rcanceled;		/* number of messages canceled
+						   by resets */
+};
+
+struct tunables {
+	int			*tunp;
+	int			deflt;
 };
 
 struct hub_and_pnode {
-	short uvhub;
-	short pnode;
+	short			uvhub;
+	short			pnode;
 };
+
+struct socket_desc {
+	short			num_cpus;
+	short			cpu_number[MAX_CPUS_PER_SOCKET];
+};
+
+struct uvhub_desc {
+	unsigned short		socket_mask;
+	short			num_cpus;
+	short			uvhub;
+	short			pnode;
+	struct socket_desc	socket[2];
+};
+
 /*
  * one per-cpu; to locate the software tables
  */
 struct bau_control {
-	struct bau_desc *descriptor_base;
-	struct bau_payload_queue_entry *va_queue_first;
-	struct bau_payload_queue_entry *va_queue_last;
-	struct bau_payload_queue_entry *bau_msg_head;
-	struct bau_control *uvhub_master;
-	struct bau_control *socket_master;
-	struct ptc_stats *statp;
-	unsigned long timeout_interval;
-	unsigned long set_bau_on_time;
-	atomic_t active_descriptor_count;
-	int plugged_tries;
-	int timeout_tries;
-	int ipi_attempts;
-	int conseccompletes;
-	int baudisabled;
-	int set_bau_off;
-	short cpu;
-	short osnode;
-	short uvhub_cpu;
-	short uvhub;
-	short cpus_in_socket;
-	short cpus_in_uvhub;
-	short partition_base_pnode;
-	unsigned short message_number;
-	unsigned short uvhub_quiesce;
-	short socket_acknowledge_count[DEST_Q_SIZE];
-	cycles_t send_message;
-	spinlock_t uvhub_lock;
-	spinlock_t queue_lock;
+	struct bau_desc		*descriptor_base;
+	struct bau_pq_entry	*queue_first;
+	struct bau_pq_entry	*queue_last;
+	struct bau_pq_entry	*bau_msg_head;
+	struct bau_control	*uvhub_master;
+	struct bau_control	*socket_master;
+	struct ptc_stats	*statp;
+	unsigned long		timeout_interval;
+	unsigned long		set_bau_on_time;
+	atomic_t		active_descriptor_count;
+	int			plugged_tries;
+	int			timeout_tries;
+	int			ipi_attempts;
+	int			conseccompletes;
+	int			baudisabled;
+	int			set_bau_off;
+	short			cpu;
+	short			osnode;
+	short			uvhub_cpu;
+	short			uvhub;
+	short			cpus_in_socket;
+	short			cpus_in_uvhub;
+	short			partition_base_pnode;
+	unsigned short		message_number;
+	unsigned short		uvhub_quiesce;
+	short			socket_acknowledge_count[DEST_Q_SIZE];
+	cycles_t		send_message;
+	spinlock_t		uvhub_lock;
+	spinlock_t		queue_lock;
 	/* tunables */
-	int max_bau_concurrent;
-	int max_bau_concurrent_constant;
-	int plugged_delay;
-	int plugsb4reset;
-	int timeoutsb4reset;
-	int ipi_reset_limit;
-	int complete_threshold;
-	int congested_response_us;
-	int congested_reps;
-	int congested_period;
-	cycles_t period_time;
-	long period_requests;
-	struct hub_and_pnode *target_hub_and_pnode;
+	int			max_concurr;
+	int			max_concurr_const;
+	int			plugged_delay;
+	int			plugsb4reset;
+	int			timeoutsb4reset;
+	int			ipi_reset_limit;
+	int			complete_threshold;
+	int			cong_response_us;
+	int			cong_reps;
+	int			cong_period;
+	cycles_t		period_time;
+	long			period_requests;
+	struct hub_and_pnode	*thp;
 };
 
-static inline int bau_uvhub_isset(int uvhub, struct bau_target_uvhubmask *dstp)
+static unsigned long read_mmr_uv2_status(void)
+{
+	return read_lmmr(UV2H_LB_BAU_SB_ACTIVATION_STATUS_2);
+}
+
+static void write_mmr_data_broadcast(int pnode, unsigned long mmr_image)
+{
+	write_gmmr(pnode, UVH_BAU_DATA_BROADCAST, mmr_image);
+}
+
+static void write_mmr_descriptor_base(int pnode, unsigned long mmr_image)
+{
+	write_gmmr(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE, mmr_image);
+}
+
+static void write_mmr_activation(unsigned long index)
+{
+	write_lmmr(UVH_LB_BAU_SB_ACTIVATION_CONTROL, index);
+}
+
+static void write_gmmr_activation(int pnode, unsigned long mmr_image)
+{
+	write_gmmr(pnode, UVH_LB_BAU_SB_ACTIVATION_CONTROL, mmr_image);
+}
+
+static void write_mmr_payload_first(int pnode, unsigned long mmr_image)
+{
+	write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST, mmr_image);
+}
+
+static void write_mmr_payload_tail(int pnode, unsigned long mmr_image)
+{
+	write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL, mmr_image);
+}
+
+static void write_mmr_payload_last(int pnode, unsigned long mmr_image)
+{
+	write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST, mmr_image);
+}
+
+static void write_mmr_misc_control(int pnode, unsigned long mmr_image)
+{
+	write_gmmr(pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
+}
+
+static unsigned long read_mmr_misc_control(int pnode)
+{
+	return read_gmmr(pnode, UVH_LB_BAU_MISC_CONTROL);
+}
+
+static void write_mmr_sw_ack(unsigned long mr)
+{
+	uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr);
+}
+
+static unsigned long read_mmr_sw_ack(void)
+{
+	return read_lmmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
+}
+
+static unsigned long read_gmmr_sw_ack(int pnode)
+{
+	return read_gmmr(pnode, UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
+}
+
+static void write_mmr_data_config(int pnode, unsigned long mr)
+{
+	uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, mr);
+}
+
+static inline int bau_uvhub_isset(int uvhub, struct bau_targ_hubmask *dstp)
 {
 	return constant_test_bit(uvhub, &dstp->bits[0]);
 }
-static inline void bau_uvhub_set(int pnode, struct bau_target_uvhubmask *dstp)
+static inline void bau_uvhub_set(int pnode, struct bau_targ_hubmask *dstp)
 {
 	__set_bit(pnode, &dstp->bits[0]);
 }
-static inline void bau_uvhubs_clear(struct bau_target_uvhubmask *dstp,
+static inline void bau_uvhubs_clear(struct bau_targ_hubmask *dstp,
 				    int nbits)
 {
 	bitmap_zero(&dstp->bits[0], nbits);
 }
-static inline int bau_uvhub_weight(struct bau_target_uvhubmask *dstp)
+static inline int bau_uvhub_weight(struct bau_targ_hubmask *dstp)
 {
 	return bitmap_weight((unsigned long *)&dstp->bits[0],
 				UV_DISTRIBUTION_SIZE);
@@ -457,9 +620,6 @@ static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits)
 	bitmap_zero(&dstp->bits, nbits);
 }
 
-#define cpubit_isset(cpu, bau_local_cpumask) \
-	test_bit((cpu), (bau_local_cpumask).bits)
-
 extern void uv_bau_message_intr1(void);
 extern void uv_bau_timeout_intr1(void);
 
@@ -467,7 +627,7 @@ struct atomic_short {
 	short counter;
 };
 
-/**
+/*
  * atomic_read_short - read a short atomic variable
  * @v: pointer of type atomic_short
  *
@@ -478,14 +638,14 @@ static inline int atomic_read_short(const struct atomic_short *v)
 	return v->counter;
 }
 
-/**
- * atomic_add_short_return - add and return a short int
+/*
+ * atom_asr - add and return a short int
  * @i: short value to add
  * @v: pointer of type atomic_short
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static inline int atomic_add_short_return(short i, struct atomic_short *v)
+static inline int atom_asr(short i, struct atomic_short *v)
 {
 	short __i = i;
 	asm volatile(LOCK_PREFIX "xaddw %0, %1"
@@ -494,4 +654,26 @@ static inline int atomic_add_short_return(short i, struct atomic_short *v)
 	return i + __i;
 }
 
+/*
+ * conditionally add 1 to *v, unless *v is >= u
+ * return 0 if we cannot add 1 to *v because it is >= u
+ * return 1 if we can add 1 to *v because it is < u
+ * the add is atomic
+ *
+ * This is close to atomic_add_unless(), but this allows the 'u' value
+ * to be lowered below the current 'v'.  atomic_add_unless can only stop
+ * on equal.
+ */
+static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u)
+{
+	spin_lock(lock);
+	if (atomic_read(v) >= u) {
+		spin_unlock(lock);
+		return 0;
+	}
+	atomic_inc(v);
+	spin_unlock(lock);
+	return 1;
+}
+
 #endif /* _ASM_X86_UV_UV_BAU_H */
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 4298002d0c83..f26544a15214 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -77,8 +77,9 @@
  *
  *		1111110000000000
  *		5432109876543210
- *		pppppppppplc0cch	Nehalem-EX
- *		ppppppppplcc0cch	Westmere-EX
+ *		pppppppppplc0cch	Nehalem-EX (12 bits in hdw reg)
+ *		ppppppppplcc0cch	Westmere-EX (12 bits in hdw reg)
+ *		pppppppppppcccch	SandyBridge (15 bits in hdw reg)
  *		sssssssssss
  *
  *			p  = pnode bits
@@ -87,7 +88,7 @@
  *			h  = hyperthread
  *			s  = bits that are in the SOCKET_ID CSR
  *
- *	Note: Processor only supports 12 bits in the APICID register. The ACPI
+ *	Note: Processor may support fewer bits in the APICID register. The ACPI
  *	      tables hold all 16 bits. Software needs to be aware of this.
  *
  *	      Unless otherwise specified, all references to APICID refer to
@@ -138,6 +139,8 @@ struct uv_hub_info_s {
 	unsigned long		global_mmr_base;
 	unsigned long		gpa_mask;
 	unsigned int		gnode_extra;
+	unsigned char		hub_revision;
+	unsigned char		apic_pnode_shift;
 	unsigned long		gnode_upper;
 	unsigned long		lowmem_remap_top;
 	unsigned long		lowmem_remap_base;
@@ -149,13 +152,31 @@ struct uv_hub_info_s {
 	unsigned char		m_val;
 	unsigned char		n_val;
 	struct uv_scir_s	scir;
-	unsigned char		apic_pnode_shift;
 };
 
 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))
 
+/*
+ * Hub revisions less than UV2_HUB_REVISION_BASE are UV1 hubs. All UV2
+ * hubs have revision numbers greater than or equal to UV2_HUB_REVISION_BASE.
+ * This is a software convention - NOT the hardware revision numbers in
+ * the hub chip.
+ */
+#define UV1_HUB_REVISION_BASE		1
+#define UV2_HUB_REVISION_BASE		3
+
+static inline int is_uv1_hub(void)
+{
+	return uv_hub_info->hub_revision < UV2_HUB_REVISION_BASE;
+}
+
+static inline int is_uv2_hub(void)
+{
+	return uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE;
+}
+
 union uvh_apicid {
     unsigned long       v;
     struct uvh_apicid_s {
@@ -180,11 +201,25 @@ union uvh_apicid {
 #define UV_PNODE_TO_GNODE(p)		((p) |uv_hub_info->gnode_extra)
 #define UV_PNODE_TO_NASID(p)		(UV_PNODE_TO_GNODE(p) << 1)
 
-#define UV_LOCAL_MMR_BASE		0xf4000000UL
-#define UV_GLOBAL_MMR32_BASE		0xf8000000UL
+#define UV1_LOCAL_MMR_BASE		0xf4000000UL
+#define UV1_GLOBAL_MMR32_BASE		0xf8000000UL
+#define UV1_LOCAL_MMR_SIZE		(64UL * 1024 * 1024)
+#define UV1_GLOBAL_MMR32_SIZE		(64UL * 1024 * 1024)
+
+#define UV2_LOCAL_MMR_BASE		0xfa000000UL
+#define UV2_GLOBAL_MMR32_BASE		0xfc000000UL
+#define UV2_LOCAL_MMR_SIZE		(32UL * 1024 * 1024)
+#define UV2_GLOBAL_MMR32_SIZE		(32UL * 1024 * 1024)
+
+#define UV_LOCAL_MMR_BASE		(is_uv1_hub() ? UV1_LOCAL_MMR_BASE     \
+						: UV2_LOCAL_MMR_BASE)
+#define UV_GLOBAL_MMR32_BASE		(is_uv1_hub() ? UV1_GLOBAL_MMR32_BASE  \
+						: UV2_GLOBAL_MMR32_BASE)
+#define UV_LOCAL_MMR_SIZE		(is_uv1_hub() ? UV1_LOCAL_MMR_SIZE :   \
+						UV2_LOCAL_MMR_SIZE)
+#define UV_GLOBAL_MMR32_SIZE		(is_uv1_hub() ? UV1_GLOBAL_MMR32_SIZE :\
+						UV2_GLOBAL_MMR32_SIZE)
 #define UV_GLOBAL_MMR64_BASE		(uv_hub_info->global_mmr_base)
-#define UV_LOCAL_MMR_SIZE		(64UL * 1024 * 1024)
-#define UV_GLOBAL_MMR32_SIZE		(64UL * 1024 * 1024)
 
 #define UV_GLOBAL_GRU_MMR_BASE		0x4000000
 
@@ -301,6 +336,17 @@ static inline int uv_apicid_to_pnode(int apicid)
 }
 
 /*
+ * Convert an apicid to the socket number on the blade
+ */
+static inline int uv_apicid_to_socket(int apicid)
+{
+	if (is_uv1_hub())
+		return (apicid >> (uv_hub_info->apic_pnode_shift - 1)) & 1;
+	else
+		return 0;
+}
+
+/*
  * Access global MMRs using the low memory MMR32 space. This region supports
  * faster MMR access but not all MMRs are accessible in this space.
  */
@@ -519,14 +565,13 @@ static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
 
 /*
  * Get the minimum revision number of the hub chips within the partition.
- *     1 - initial rev 1.0 silicon
- *     2 - rev 2.0 production silicon
+ *     1 - UV1 rev 1.0 initial silicon
+ *     2 - UV1 rev 2.0 production silicon
+ *     3 - UV2 rev 1.0 initial silicon
  */
 static inline int uv_get_min_hub_revision_id(void)
 {
-	extern int uv_min_hub_revision_id;
-
-	return uv_min_hub_revision_id;
+	return uv_hub_info->hub_revision;
 }
 
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index f5bb64a823d7..4be52c863448 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -11,13 +11,64 @@
 #ifndef _ASM_X86_UV_UV_MMRS_H
 #define _ASM_X86_UV_UV_MMRS_H
 
+/*
+ * This file contains MMR definitions for both UV1 & UV2 hubs.
+ *
+ * In general, MMR addresses and structures are identical on both hubs.
+ * These MMRs are identified as:
+ *	#define UVH_xxx		<address>
+ *	union uvh_xxx {
+ *		unsigned long       v;
+ *		struct uvh_int_cmpd_s {
+ *		} s;
+ *	};
+ *
+ * If the MMR exists on both hub type but has different addresses or
+ * contents, the MMR definition is similar to:
+ *	#define UV1H_xxx	<uv1 address>
+ *	#define UV2H_xxx	<uv2address>
+ *	#define UVH_xxx		(is_uv1_hub() ? UV1H_xxx : UV2H_xxx)
+ *	union uvh_xxx {
+ *		unsigned long       v;
+ *		struct uv1h_int_cmpd_s {	 (Common fields only)
+ *		} s;
+ *		struct uv1h_int_cmpd_s {	 (Full UV1 definition)
+ *		} s1;
+ *		struct uv2h_int_cmpd_s {	 (Full UV2 definition)
+ *		} s2;
+ *	};
+ *
+ * Only essential difference are enumerated. For example, if the address is
+ * the same for both UV1 & UV2, only a single #define is generated. Likewise,
+ * if the contents is the same for both hubs, only the "s" structure is
+ * generated.
+ *
+ * If the MMR exists on ONLY 1 type of hub, no generic definition is
+ * generated:
+ *	#define UVnH_xxx	<uvn address>
+ *	union uvnh_xxx {
+ *		unsigned long       v;
+ *		struct uvh_int_cmpd_s {
+ *		} sn;
+ *	};
+ */
+
 #define UV_MMR_ENABLE		(1UL << 63)
 
+#define UV1_HUB_PART_NUMBER	0x88a5
+#define UV2_HUB_PART_NUMBER	0x8eb8
+
+/* Compat: if this #define is present, UV headers support UV2 */
+#define UV2_HUB_IS_SUPPORTED	1
+
+/* KABI compat: if this #define is present, KABI hacks are present */
+#define UV2_HUB_KABI_HACKS	1
+
 /* ========================================================================= */
 /*                          UVH_BAU_DATA_BROADCAST                           */
 /* ========================================================================= */
 #define UVH_BAU_DATA_BROADCAST 0x61688UL
-#define UVH_BAU_DATA_BROADCAST_32 0x0440
+#define UVH_BAU_DATA_BROADCAST_32 0x440
 
 #define UVH_BAU_DATA_BROADCAST_ENABLE_SHFT 0
 #define UVH_BAU_DATA_BROADCAST_ENABLE_MASK 0x0000000000000001UL
@@ -34,7 +85,7 @@ union uvh_bau_data_broadcast_u {
 /*                           UVH_BAU_DATA_CONFIG                             */
 /* ========================================================================= */
 #define UVH_BAU_DATA_CONFIG 0x61680UL
-#define UVH_BAU_DATA_CONFIG_32 0x0438
+#define UVH_BAU_DATA_CONFIG_32 0x438
 
 #define UVH_BAU_DATA_CONFIG_VECTOR_SHFT 0
 #define UVH_BAU_DATA_CONFIG_VECTOR_MASK 0x00000000000000ffUL
@@ -73,125 +124,245 @@ union uvh_bau_data_config_u {
 /*                           UVH_EVENT_OCCURRED0                             */
 /* ========================================================================= */
 #define UVH_EVENT_OCCURRED0 0x70000UL
-#define UVH_EVENT_OCCURRED0_32 0x005e8
-
-#define UVH_EVENT_OCCURRED0_LB_HCERR_SHFT 0
-#define UVH_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL
-#define UVH_EVENT_OCCURRED0_GR0_HCERR_SHFT 1
-#define UVH_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000002UL
-#define UVH_EVENT_OCCURRED0_GR1_HCERR_SHFT 2
-#define UVH_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000004UL
-#define UVH_EVENT_OCCURRED0_LH_HCERR_SHFT 3
-#define UVH_EVENT_OCCURRED0_LH_HCERR_MASK 0x0000000000000008UL
-#define UVH_EVENT_OCCURRED0_RH_HCERR_SHFT 4
-#define UVH_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000010UL
-#define UVH_EVENT_OCCURRED0_XN_HCERR_SHFT 5
-#define UVH_EVENT_OCCURRED0_XN_HCERR_MASK 0x0000000000000020UL
-#define UVH_EVENT_OCCURRED0_SI_HCERR_SHFT 6
-#define UVH_EVENT_OCCURRED0_SI_HCERR_MASK 0x0000000000000040UL
-#define UVH_EVENT_OCCURRED0_LB_AOERR0_SHFT 7
-#define UVH_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000080UL
-#define UVH_EVENT_OCCURRED0_GR0_AOERR0_SHFT 8
-#define UVH_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000000100UL
-#define UVH_EVENT_OCCURRED0_GR1_AOERR0_SHFT 9
-#define UVH_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000000200UL
-#define UVH_EVENT_OCCURRED0_LH_AOERR0_SHFT 10
-#define UVH_EVENT_OCCURRED0_LH_AOERR0_MASK 0x0000000000000400UL
-#define UVH_EVENT_OCCURRED0_RH_AOERR0_SHFT 11
-#define UVH_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL
-#define UVH_EVENT_OCCURRED0_XN_AOERR0_SHFT 12
-#define UVH_EVENT_OCCURRED0_XN_AOERR0_MASK 0x0000000000001000UL
-#define UVH_EVENT_OCCURRED0_SI_AOERR0_SHFT 13
-#define UVH_EVENT_OCCURRED0_SI_AOERR0_MASK 0x0000000000002000UL
-#define UVH_EVENT_OCCURRED0_LB_AOERR1_SHFT 14
-#define UVH_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000004000UL
-#define UVH_EVENT_OCCURRED0_GR0_AOERR1_SHFT 15
-#define UVH_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000000008000UL
-#define UVH_EVENT_OCCURRED0_GR1_AOERR1_SHFT 16
-#define UVH_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000000010000UL
-#define UVH_EVENT_OCCURRED0_LH_AOERR1_SHFT 17
-#define UVH_EVENT_OCCURRED0_LH_AOERR1_MASK 0x0000000000020000UL
-#define UVH_EVENT_OCCURRED0_RH_AOERR1_SHFT 18
-#define UVH_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000040000UL
-#define UVH_EVENT_OCCURRED0_XN_AOERR1_SHFT 19
-#define UVH_EVENT_OCCURRED0_XN_AOERR1_MASK 0x0000000000080000UL
-#define UVH_EVENT_OCCURRED0_SI_AOERR1_SHFT 20
-#define UVH_EVENT_OCCURRED0_SI_AOERR1_MASK 0x0000000000100000UL
-#define UVH_EVENT_OCCURRED0_RH_VPI_INT_SHFT 21
-#define UVH_EVENT_OCCURRED0_RH_VPI_INT_MASK 0x0000000000200000UL
-#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 22
-#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 23
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000000800000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 24
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000001000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 25
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000002000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 26
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000004000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 27
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000000008000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 28
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000000010000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 29
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000000020000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 30
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000000040000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 31
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000000080000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 32
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000000100000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 33
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000000200000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 34
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000000400000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 35
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000000800000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 36
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000001000000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 37
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000002000000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 38
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000004000000000UL
-#define UVH_EVENT_OCCURRED0_L1_NMI_INT_SHFT 39
-#define UVH_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0000008000000000UL
-#define UVH_EVENT_OCCURRED0_STOP_CLOCK_SHFT 40
-#define UVH_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0000010000000000UL
-#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 41
-#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0000020000000000UL
-#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 42
-#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0000040000000000UL
-#define UVH_EVENT_OCCURRED0_LTC_INT_SHFT 43
-#define UVH_EVENT_OCCURRED0_LTC_INT_MASK 0x0000080000000000UL
-#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 44
-#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
-#define UVH_EVENT_OCCURRED0_IPI_INT_SHFT 45
-#define UVH_EVENT_OCCURRED0_IPI_INT_MASK 0x0000200000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT 46
-#define UVH_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0000400000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT1_SHFT 47
-#define UVH_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0000800000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT2_SHFT 48
-#define UVH_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0001000000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT3_SHFT 49
-#define UVH_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0002000000000000UL
-#define UVH_EVENT_OCCURRED0_PROFILE_INT_SHFT 50
-#define UVH_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0004000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC0_SHFT 51
-#define UVH_EVENT_OCCURRED0_RTC0_MASK 0x0008000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC1_SHFT 52
-#define UVH_EVENT_OCCURRED0_RTC1_MASK 0x0010000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC2_SHFT 53
-#define UVH_EVENT_OCCURRED0_RTC2_MASK 0x0020000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC3_SHFT 54
-#define UVH_EVENT_OCCURRED0_RTC3_MASK 0x0040000000000000UL
-#define UVH_EVENT_OCCURRED0_BAU_DATA_SHFT 55
-#define UVH_EVENT_OCCURRED0_BAU_DATA_MASK 0x0080000000000000UL
-#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_SHFT 56
-#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK 0x0100000000000000UL
+#define UVH_EVENT_OCCURRED0_32 0x5e8
+
+#define UV1H_EVENT_OCCURRED0_LB_HCERR_SHFT 0
+#define UV1H_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL
+#define UV1H_EVENT_OCCURRED0_GR0_HCERR_SHFT 1
+#define UV1H_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000002UL
+#define UV1H_EVENT_OCCURRED0_GR1_HCERR_SHFT 2
+#define UV1H_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000004UL
+#define UV1H_EVENT_OCCURRED0_LH_HCERR_SHFT 3
+#define UV1H_EVENT_OCCURRED0_LH_HCERR_MASK 0x0000000000000008UL
+#define UV1H_EVENT_OCCURRED0_RH_HCERR_SHFT 4
+#define UV1H_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000010UL
+#define UV1H_EVENT_OCCURRED0_XN_HCERR_SHFT 5
+#define UV1H_EVENT_OCCURRED0_XN_HCERR_MASK 0x0000000000000020UL
+#define UV1H_EVENT_OCCURRED0_SI_HCERR_SHFT 6
+#define UV1H_EVENT_OCCURRED0_SI_HCERR_MASK 0x0000000000000040UL
+#define UV1H_EVENT_OCCURRED0_LB_AOERR0_SHFT 7
+#define UV1H_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000080UL
+#define UV1H_EVENT_OCCURRED0_GR0_AOERR0_SHFT 8
+#define UV1H_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000000100UL
+#define UV1H_EVENT_OCCURRED0_GR1_AOERR0_SHFT 9
+#define UV1H_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000000200UL
+#define UV1H_EVENT_OCCURRED0_LH_AOERR0_SHFT 10
+#define UV1H_EVENT_OCCURRED0_LH_AOERR0_MASK 0x0000000000000400UL
+#define UV1H_EVENT_OCCURRED0_RH_AOERR0_SHFT 11
+#define UV1H_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL
+#define UV1H_EVENT_OCCURRED0_XN_AOERR0_SHFT 12
+#define UV1H_EVENT_OCCURRED0_XN_AOERR0_MASK 0x0000000000001000UL
+#define UV1H_EVENT_OCCURRED0_SI_AOERR0_SHFT 13
+#define UV1H_EVENT_OCCURRED0_SI_AOERR0_MASK 0x0000000000002000UL
+#define UV1H_EVENT_OCCURRED0_LB_AOERR1_SHFT 14
+#define UV1H_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000004000UL
+#define UV1H_EVENT_OCCURRED0_GR0_AOERR1_SHFT 15
+#define UV1H_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000000008000UL
+#define UV1H_EVENT_OCCURRED0_GR1_AOERR1_SHFT 16
+#define UV1H_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000000010000UL
+#define UV1H_EVENT_OCCURRED0_LH_AOERR1_SHFT 17
+#define UV1H_EVENT_OCCURRED0_LH_AOERR1_MASK 0x0000000000020000UL
+#define UV1H_EVENT_OCCURRED0_RH_AOERR1_SHFT 18
+#define UV1H_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000040000UL
+#define UV1H_EVENT_OCCURRED0_XN_AOERR1_SHFT 19
+#define UV1H_EVENT_OCCURRED0_XN_AOERR1_MASK 0x0000000000080000UL
+#define UV1H_EVENT_OCCURRED0_SI_AOERR1_SHFT 20
+#define UV1H_EVENT_OCCURRED0_SI_AOERR1_MASK 0x0000000000100000UL
+#define UV1H_EVENT_OCCURRED0_RH_VPI_INT_SHFT 21
+#define UV1H_EVENT_OCCURRED0_RH_VPI_INT_MASK 0x0000000000200000UL
+#define UV1H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 22
+#define UV1H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 23
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000000800000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 24
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000001000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 25
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000002000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 26
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000004000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 27
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000000008000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 28
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000000010000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 29
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000000020000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 30
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000000040000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 31
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000000080000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 32
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000000100000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 33
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000000200000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 34
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000000400000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 35
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000000800000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 36
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000001000000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 37
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000002000000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 38
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000004000000000UL
+#define UV1H_EVENT_OCCURRED0_L1_NMI_INT_SHFT 39
+#define UV1H_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0000008000000000UL
+#define UV1H_EVENT_OCCURRED0_STOP_CLOCK_SHFT 40
+#define UV1H_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0000010000000000UL
+#define UV1H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 41
+#define UV1H_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0000020000000000UL
+#define UV1H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 42
+#define UV1H_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0000040000000000UL
+#define UV1H_EVENT_OCCURRED0_LTC_INT_SHFT 43
+#define UV1H_EVENT_OCCURRED0_LTC_INT_MASK 0x0000080000000000UL
+#define UV1H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 44
+#define UV1H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
+#define UV1H_EVENT_OCCURRED0_IPI_INT_SHFT 45
+#define UV1H_EVENT_OCCURRED0_IPI_INT_MASK 0x0000200000000000UL
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT0_SHFT 46
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0000400000000000UL
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT1_SHFT 47
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0000800000000000UL
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT2_SHFT 48
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0001000000000000UL
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT3_SHFT 49
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0002000000000000UL
+#define UV1H_EVENT_OCCURRED0_PROFILE_INT_SHFT 50
+#define UV1H_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0004000000000000UL
+#define UV1H_EVENT_OCCURRED0_RTC0_SHFT 51
+#define UV1H_EVENT_OCCURRED0_RTC0_MASK 0x0008000000000000UL
+#define UV1H_EVENT_OCCURRED0_RTC1_SHFT 52
+#define UV1H_EVENT_OCCURRED0_RTC1_MASK 0x0010000000000000UL
+#define UV1H_EVENT_OCCURRED0_RTC2_SHFT 53
+#define UV1H_EVENT_OCCURRED0_RTC2_MASK 0x0020000000000000UL
+#define UV1H_EVENT_OCCURRED0_RTC3_SHFT 54
+#define UV1H_EVENT_OCCURRED0_RTC3_MASK 0x0040000000000000UL
+#define UV1H_EVENT_OCCURRED0_BAU_DATA_SHFT 55
+#define UV1H_EVENT_OCCURRED0_BAU_DATA_MASK 0x0080000000000000UL
+#define UV1H_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_SHFT 56
+#define UV1H_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK 0x0100000000000000UL
+
+#define UV2H_EVENT_OCCURRED0_LB_HCERR_SHFT 0
+#define UV2H_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL
+#define UV2H_EVENT_OCCURRED0_QP_HCERR_SHFT 1
+#define UV2H_EVENT_OCCURRED0_QP_HCERR_MASK 0x0000000000000002UL
+#define UV2H_EVENT_OCCURRED0_RH_HCERR_SHFT 2
+#define UV2H_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000004UL
+#define UV2H_EVENT_OCCURRED0_LH0_HCERR_SHFT 3
+#define UV2H_EVENT_OCCURRED0_LH0_HCERR_MASK 0x0000000000000008UL
+#define UV2H_EVENT_OCCURRED0_LH1_HCERR_SHFT 4
+#define UV2H_EVENT_OCCURRED0_LH1_HCERR_MASK 0x0000000000000010UL
+#define UV2H_EVENT_OCCURRED0_GR0_HCERR_SHFT 5
+#define UV2H_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000020UL
+#define UV2H_EVENT_OCCURRED0_GR1_HCERR_SHFT 6
+#define UV2H_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000040UL
+#define UV2H_EVENT_OCCURRED0_NI0_HCERR_SHFT 7
+#define UV2H_EVENT_OCCURRED0_NI0_HCERR_MASK 0x0000000000000080UL
+#define UV2H_EVENT_OCCURRED0_NI1_HCERR_SHFT 8
+#define UV2H_EVENT_OCCURRED0_NI1_HCERR_MASK 0x0000000000000100UL
+#define UV2H_EVENT_OCCURRED0_LB_AOERR0_SHFT 9
+#define UV2H_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000200UL
+#define UV2H_EVENT_OCCURRED0_QP_AOERR0_SHFT 10
+#define UV2H_EVENT_OCCURRED0_QP_AOERR0_MASK 0x0000000000000400UL
+#define UV2H_EVENT_OCCURRED0_RH_AOERR0_SHFT 11
+#define UV2H_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR0_SHFT 12
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR0_MASK 0x0000000000001000UL
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR0_SHFT 13
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR0_MASK 0x0000000000002000UL
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR0_SHFT 14
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000004000UL
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR0_SHFT 15
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000008000UL
+#define UV2H_EVENT_OCCURRED0_XB_AOERR0_SHFT 16
+#define UV2H_EVENT_OCCURRED0_XB_AOERR0_MASK 0x0000000000010000UL
+#define UV2H_EVENT_OCCURRED0_RT_AOERR0_SHFT 17
+#define UV2H_EVENT_OCCURRED0_RT_AOERR0_MASK 0x0000000000020000UL
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_SHFT 18
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_MASK 0x0000000000040000UL
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_SHFT 19
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_MASK 0x0000000000080000UL
+#define UV2H_EVENT_OCCURRED0_LB_AOERR1_SHFT 20
+#define UV2H_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000100000UL
+#define UV2H_EVENT_OCCURRED0_QP_AOERR1_SHFT 21
+#define UV2H_EVENT_OCCURRED0_QP_AOERR1_MASK 0x0000000000200000UL
+#define UV2H_EVENT_OCCURRED0_RH_AOERR1_SHFT 22
+#define UV2H_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000400000UL
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_SHFT 23
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_MASK 0x0000000000800000UL
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_SHFT 24
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_MASK 0x0000000001000000UL
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_SHFT 25
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000002000000UL
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_SHFT 26
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000004000000UL
+#define UV2H_EVENT_OCCURRED0_XB_AOERR1_SHFT 27
+#define UV2H_EVENT_OCCURRED0_XB_AOERR1_MASK 0x0000000008000000UL
+#define UV2H_EVENT_OCCURRED0_RT_AOERR1_SHFT 28
+#define UV2H_EVENT_OCCURRED0_RT_AOERR1_MASK 0x0000000010000000UL
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_SHFT 29
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_MASK 0x0000000020000000UL
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_SHFT 30
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_MASK 0x0000000040000000UL
+#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 31
+#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000080000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 32
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000100000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 33
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000200000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 34
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000400000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 35
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000800000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 36
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000001000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 37
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000002000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 38
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000004000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 39
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000008000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 40
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000010000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 41
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000020000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 42
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000040000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 43
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000080000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 44
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000100000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 45
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000200000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 46
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000400000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 47
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000800000000000UL
+#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_SHFT 48
+#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0001000000000000UL
+#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_SHFT 49
+#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0002000000000000UL
+#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 50
+#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0004000000000000UL
+#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 51
+#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0008000000000000UL
+#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 52
+#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0010000000000000UL
+#define UV2H_EVENT_OCCURRED0_IPI_INT_SHFT 53
+#define UV2H_EVENT_OCCURRED0_IPI_INT_MASK 0x0020000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_SHFT 54
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0040000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_SHFT 55
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0080000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_SHFT 56
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0100000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_SHFT 57
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0200000000000000UL
+#define UV2H_EVENT_OCCURRED0_PROFILE_INT_SHFT 58
+#define UV2H_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0400000000000000UL
+
 union uvh_event_occurred0_u {
     unsigned long	v;
-    struct uvh_event_occurred0_s {
+    struct uv1h_event_occurred0_s {
 	unsigned long	lb_hcerr             :  1;  /* RW, W1C */
 	unsigned long	gr0_hcerr            :  1;  /* RW, W1C */
 	unsigned long	gr1_hcerr            :  1;  /* RW, W1C */
@@ -250,14 +421,76 @@ union uvh_event_occurred0_u {
 	unsigned long	bau_data             :  1;  /* RW, W1C */
 	unsigned long	power_management_req :  1;  /* RW, W1C */
 	unsigned long	rsvd_57_63           :  7;  /*    */
-    } s;
+    } s1;
+    struct uv2h_event_occurred0_s {
+	unsigned long	lb_hcerr            :  1;  /* RW */
+	unsigned long	qp_hcerr            :  1;  /* RW */
+	unsigned long	rh_hcerr            :  1;  /* RW */
+	unsigned long	lh0_hcerr           :  1;  /* RW */
+	unsigned long	lh1_hcerr           :  1;  /* RW */
+	unsigned long	gr0_hcerr           :  1;  /* RW */
+	unsigned long	gr1_hcerr           :  1;  /* RW */
+	unsigned long	ni0_hcerr           :  1;  /* RW */
+	unsigned long	ni1_hcerr           :  1;  /* RW */
+	unsigned long	lb_aoerr0           :  1;  /* RW */
+	unsigned long	qp_aoerr0           :  1;  /* RW */
+	unsigned long	rh_aoerr0           :  1;  /* RW */
+	unsigned long	lh0_aoerr0          :  1;  /* RW */
+	unsigned long	lh1_aoerr0          :  1;  /* RW */
+	unsigned long	gr0_aoerr0          :  1;  /* RW */
+	unsigned long	gr1_aoerr0          :  1;  /* RW */
+	unsigned long	xb_aoerr0           :  1;  /* RW */
+	unsigned long	rt_aoerr0           :  1;  /* RW */
+	unsigned long	ni0_aoerr0          :  1;  /* RW */
+	unsigned long	ni1_aoerr0          :  1;  /* RW */
+	unsigned long	lb_aoerr1           :  1;  /* RW */
+	unsigned long	qp_aoerr1           :  1;  /* RW */
+	unsigned long	rh_aoerr1           :  1;  /* RW */
+	unsigned long	lh0_aoerr1          :  1;  /* RW */
+	unsigned long	lh1_aoerr1          :  1;  /* RW */
+	unsigned long	gr0_aoerr1          :  1;  /* RW */
+	unsigned long	gr1_aoerr1          :  1;  /* RW */
+	unsigned long	xb_aoerr1           :  1;  /* RW */
+	unsigned long	rt_aoerr1           :  1;  /* RW */
+	unsigned long	ni0_aoerr1          :  1;  /* RW */
+	unsigned long	ni1_aoerr1          :  1;  /* RW */
+	unsigned long	system_shutdown_int :  1;  /* RW */
+	unsigned long	lb_irq_int_0        :  1;  /* RW */
+	unsigned long	lb_irq_int_1        :  1;  /* RW */
+	unsigned long	lb_irq_int_2        :  1;  /* RW */
+	unsigned long	lb_irq_int_3        :  1;  /* RW */
+	unsigned long	lb_irq_int_4        :  1;  /* RW */
+	unsigned long	lb_irq_int_5        :  1;  /* RW */
+	unsigned long	lb_irq_int_6        :  1;  /* RW */
+	unsigned long	lb_irq_int_7        :  1;  /* RW */
+	unsigned long	lb_irq_int_8        :  1;  /* RW */
+	unsigned long	lb_irq_int_9        :  1;  /* RW */
+	unsigned long	lb_irq_int_10       :  1;  /* RW */
+	unsigned long	lb_irq_int_11       :  1;  /* RW */
+	unsigned long	lb_irq_int_12       :  1;  /* RW */
+	unsigned long	lb_irq_int_13       :  1;  /* RW */
+	unsigned long	lb_irq_int_14       :  1;  /* RW */
+	unsigned long	lb_irq_int_15       :  1;  /* RW */
+	unsigned long	l1_nmi_int          :  1;  /* RW */
+	unsigned long	stop_clock          :  1;  /* RW */
+	unsigned long	asic_to_l1          :  1;  /* RW */
+	unsigned long	l1_to_asic          :  1;  /* RW */
+	unsigned long	la_seq_trigger      :  1;  /* RW */
+	unsigned long	ipi_int             :  1;  /* RW */
+	unsigned long	extio_int0          :  1;  /* RW */
+	unsigned long	extio_int1          :  1;  /* RW */
+	unsigned long	extio_int2          :  1;  /* RW */
+	unsigned long	extio_int3          :  1;  /* RW */
+	unsigned long	profile_int         :  1;  /* RW */
+	unsigned long	rsvd_59_63          :  5;  /*    */
+    } s2;
 };
 
 /* ========================================================================= */
 /*                        UVH_EVENT_OCCURRED0_ALIAS                          */
 /* ========================================================================= */
 #define UVH_EVENT_OCCURRED0_ALIAS 0x0000000000070008UL
-#define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0
+#define UVH_EVENT_OCCURRED0_ALIAS_32 0x5f0
 
 /* ========================================================================= */
 /*                         UVH_GR0_TLB_INT0_CONFIG                           */
@@ -432,8 +665,16 @@ union uvh_int_cmpb_u {
 /* ========================================================================= */
 #define UVH_INT_CMPC 0x22100UL
 
-#define UVH_INT_CMPC_REAL_TIME_CMPC_SHFT 0
-#define UVH_INT_CMPC_REAL_TIME_CMPC_MASK 0x00ffffffffffffffUL
+#define UV1H_INT_CMPC_REAL_TIME_CMPC_SHFT	0
+#define UV2H_INT_CMPC_REAL_TIME_CMPC_SHFT	0
+#define UVH_INT_CMPC_REAL_TIME_CMPC_SHFT	(is_uv1_hub() ?		\
+			UV1H_INT_CMPC_REAL_TIME_CMPC_SHFT :	\
+			UV2H_INT_CMPC_REAL_TIME_CMPC_SHFT)
+#define UV1H_INT_CMPC_REAL_TIME_CMPC_MASK	0xffffffffffffffUL
+#define UV2H_INT_CMPC_REAL_TIME_CMPC_MASK	0xffffffffffffffUL
+#define UVH_INT_CMPC_REAL_TIME_CMPC_MASK	(is_uv1_hub() ?		\
+			UV1H_INT_CMPC_REAL_TIME_CMPC_MASK :	\
+			UV2H_INT_CMPC_REAL_TIME_CMPC_MASK)
 
 union uvh_int_cmpc_u {
     unsigned long	v;
@@ -448,8 +689,16 @@ union uvh_int_cmpc_u {
 /* ========================================================================= */
 #define UVH_INT_CMPD 0x22180UL
 
-#define UVH_INT_CMPD_REAL_TIME_CMPD_SHFT 0
-#define UVH_INT_CMPD_REAL_TIME_CMPD_MASK 0x00ffffffffffffffUL
+#define UV1H_INT_CMPD_REAL_TIME_CMPD_SHFT	0
+#define UV2H_INT_CMPD_REAL_TIME_CMPD_SHFT	0
+#define UVH_INT_CMPD_REAL_TIME_CMPD_SHFT	(is_uv1_hub() ?		\
+			UV1H_INT_CMPD_REAL_TIME_CMPD_SHFT :	\
+			UV2H_INT_CMPD_REAL_TIME_CMPD_SHFT)
+#define UV1H_INT_CMPD_REAL_TIME_CMPD_MASK	0xffffffffffffffUL
+#define UV2H_INT_CMPD_REAL_TIME_CMPD_MASK	0xffffffffffffffUL
+#define UVH_INT_CMPD_REAL_TIME_CMPD_MASK	(is_uv1_hub() ?		\
+			UV1H_INT_CMPD_REAL_TIME_CMPD_MASK :	\
+			UV2H_INT_CMPD_REAL_TIME_CMPD_MASK)
 
 union uvh_int_cmpd_u {
     unsigned long	v;
@@ -463,7 +712,7 @@ union uvh_int_cmpd_u {
 /*                               UVH_IPI_INT                                 */
 /* ========================================================================= */
 #define UVH_IPI_INT 0x60500UL
-#define UVH_IPI_INT_32 0x0348
+#define UVH_IPI_INT_32 0x348
 
 #define UVH_IPI_INT_VECTOR_SHFT 0
 #define UVH_IPI_INT_VECTOR_MASK 0x00000000000000ffUL
@@ -493,7 +742,7 @@ union uvh_ipi_int_u {
 /*                   UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x009c0
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x9c0
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_MASK 0x000007fffffffff0UL
@@ -515,7 +764,7 @@ union uvh_lb_bau_intd_payload_queue_first_u {
 /*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x009c8
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x9c8
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_MASK 0x000007fffffffff0UL
@@ -533,7 +782,7 @@ union uvh_lb_bau_intd_payload_queue_last_u {
 /*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x009d0
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x9d0
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_MASK 0x000007fffffffff0UL
@@ -551,7 +800,7 @@ union uvh_lb_bau_intd_payload_queue_tail_u {
 /*                   UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE                    */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0x0a68
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0xa68
 
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_SHFT 0
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_MASK 0x0000000000000001UL
@@ -585,6 +834,7 @@ union uvh_lb_bau_intd_payload_queue_tail_u {
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_MASK 0x0000000000004000UL
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_SHFT 15
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_MASK 0x0000000000008000UL
+
 union uvh_lb_bau_intd_software_acknowledge_u {
     unsigned long	v;
     struct uvh_lb_bau_intd_software_acknowledge_s {
@@ -612,13 +862,13 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 /*                UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS                 */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x0000000000320088UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0x0a70
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0xa70
 
 /* ========================================================================= */
 /*                         UVH_LB_BAU_MISC_CONTROL                           */
 /* ========================================================================= */
 #define UVH_LB_BAU_MISC_CONTROL 0x320170UL
-#define UVH_LB_BAU_MISC_CONTROL_32 0x00a10
+#define UVH_LB_BAU_MISC_CONTROL_32 0xa10
 
 #define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0
 #define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL
@@ -628,8 +878,8 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 #define UVH_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL
 #define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10
 #define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL
-#define UVH_LB_BAU_MISC_CONTROL_CSI_AGENT_PRESENCE_VECTOR_SHFT 11
-#define UVH_LB_BAU_MISC_CONTROL_CSI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
+#define UVH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11
+#define UVH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
 #define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14
 #define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL
 #define UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15
@@ -650,8 +900,86 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 #define UVH_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL
 #define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28
 #define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL
-#define UVH_LB_BAU_MISC_CONTROL_FUN_SHFT 48
-#define UVH_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL
+
+#define UV1H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0
+#define UV1H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL
+#define UV1H_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8
+#define UV1H_LB_BAU_MISC_CONTROL_APIC_MODE_MASK 0x0000000000000100UL
+#define UV1H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT 9
+#define UV1H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL
+#define UV1H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10
+#define UV1H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL
+#define UV1H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11
+#define UV1H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
+#define UV1H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14
+#define UV1H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL
+#define UV1H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16
+#define UV1H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL
+#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21
+#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL
+#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22
+#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL
+#define UV1H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_SHFT 23
+#define UV1H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_MASK 0x0000000000800000UL
+#define UV1H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24
+#define UV1H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL
+#define UV1H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27
+#define UV1H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL
+#define UV1H_LB_BAU_MISC_CONTROL_FUN_SHFT 48
+#define UV1H_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL
+
+#define UV2H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0
+#define UV2H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL
+#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8
+#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_MASK 0x0000000000000100UL
+#define UV2H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT 9
+#define UV2H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL
+#define UV2H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10
+#define UV2H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL
+#define UV2H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11
+#define UV2H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
+#define UV2H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14
+#define UV2H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL
+#define UV2H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16
+#define UV2H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL
+#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21
+#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL
+#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22
+#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_SHFT 23
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_MASK 0x0000000000800000UL
+#define UV2H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24
+#define UV2H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27
+#define UV2H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_SHFT 29
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_MASK 0x0000000020000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_SHFT 30
+#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_MASK 0x0000000040000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_SHFT 31
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_MASK 0x0000000080000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_SHFT 32
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_MASK 0x0000000100000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT 33
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_MASK 0x0000000200000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_SHFT 34
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_MASK 0x0000000400000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT 35
+#define UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_MASK 0x0000000800000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_FUN_SHFT 48
+#define UV2H_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL
 
 union uvh_lb_bau_misc_control_u {
     unsigned long	v;
@@ -660,7 +988,25 @@ union uvh_lb_bau_misc_control_u {
 	unsigned long	apic_mode                          :  1;  /* RW */
 	unsigned long	force_broadcast                    :  1;  /* RW */
 	unsigned long	force_lock_nop                     :  1;  /* RW */
-	unsigned long	csi_agent_presence_vector          :  3;  /* RW */
+	unsigned long	qpi_agent_presence_vector          :  3;  /* RW */
+	unsigned long	descriptor_fetch_mode              :  1;  /* RW */
+	unsigned long	enable_intd_soft_ack_mode          :  1;  /* RW */
+	unsigned long	intd_soft_ack_timeout_period       :  4;  /* RW */
+	unsigned long	enable_dual_mapping_mode           :  1;  /* RW */
+	unsigned long	vga_io_port_decode_enable          :  1;  /* RW */
+	unsigned long	vga_io_port_16_bit_decode          :  1;  /* RW */
+	unsigned long	suppress_dest_registration         :  1;  /* RW */
+	unsigned long	programmed_initial_priority        :  3;  /* RW */
+	unsigned long	use_incoming_priority              :  1;  /* RW */
+	unsigned long	enable_programmed_initial_priority :  1;  /* RW */
+	unsigned long	rsvd_29_63    : 35;
+    } s;
+    struct uv1h_lb_bau_misc_control_s {
+	unsigned long	rejection_delay                    :  8;  /* RW */
+	unsigned long	apic_mode                          :  1;  /* RW */
+	unsigned long	force_broadcast                    :  1;  /* RW */
+	unsigned long	force_lock_nop                     :  1;  /* RW */
+	unsigned long	qpi_agent_presence_vector          :  3;  /* RW */
 	unsigned long	descriptor_fetch_mode              :  1;  /* RW */
 	unsigned long	enable_intd_soft_ack_mode          :  1;  /* RW */
 	unsigned long	intd_soft_ack_timeout_period       :  4;  /* RW */
@@ -673,14 +1019,40 @@ union uvh_lb_bau_misc_control_u {
 	unsigned long	enable_programmed_initial_priority :  1;  /* RW */
 	unsigned long	rsvd_29_47                         : 19;  /*    */
 	unsigned long	fun                                : 16;  /* RW */
-    } s;
+    } s1;
+    struct uv2h_lb_bau_misc_control_s {
+	unsigned long	rejection_delay                      :  8;  /* RW */
+	unsigned long	apic_mode                            :  1;  /* RW */
+	unsigned long	force_broadcast                      :  1;  /* RW */
+	unsigned long	force_lock_nop                       :  1;  /* RW */
+	unsigned long	qpi_agent_presence_vector            :  3;  /* RW */
+	unsigned long	descriptor_fetch_mode                :  1;  /* RW */
+	unsigned long	enable_intd_soft_ack_mode            :  1;  /* RW */
+	unsigned long	intd_soft_ack_timeout_period         :  4;  /* RW */
+	unsigned long	enable_dual_mapping_mode             :  1;  /* RW */
+	unsigned long	vga_io_port_decode_enable            :  1;  /* RW */
+	unsigned long	vga_io_port_16_bit_decode            :  1;  /* RW */
+	unsigned long	suppress_dest_registration           :  1;  /* RW */
+	unsigned long	programmed_initial_priority          :  3;  /* RW */
+	unsigned long	use_incoming_priority                :  1;  /* RW */
+	unsigned long	enable_programmed_initial_priority   :  1;  /* RW */
+	unsigned long	enable_automatic_apic_mode_selection :  1;  /* RW */
+	unsigned long	apic_mode_status                     :  1;  /* RO */
+	unsigned long	suppress_interrupts_to_self          :  1;  /* RW */
+	unsigned long	enable_lock_based_system_flush       :  1;  /* RW */
+	unsigned long	enable_extended_sb_status            :  1;  /* RW */
+	unsigned long	suppress_int_prio_udt_to_self        :  1;  /* RW */
+	unsigned long	use_legacy_descriptor_formats        :  1;  /* RW */
+	unsigned long	rsvd_36_47                           : 12;  /*    */
+	unsigned long	fun                                  : 16;  /* RW */
+    } s2;
 };
 
 /* ========================================================================= */
 /*                     UVH_LB_BAU_SB_ACTIVATION_CONTROL                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x009a8
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x9a8
 
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_MASK 0x000000000000003fUL
@@ -703,7 +1075,7 @@ union uvh_lb_bau_sb_activation_control_u {
 /*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_0                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x009b0
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x9b0
 
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_MASK 0xffffffffffffffffUL
@@ -719,7 +1091,7 @@ union uvh_lb_bau_sb_activation_status_0_u {
 /*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_1                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x009b8
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x9b8
 
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_MASK 0xffffffffffffffffUL
@@ -735,7 +1107,7 @@ union uvh_lb_bau_sb_activation_status_1_u {
 /*                      UVH_LB_BAU_SB_DESCRIPTOR_BASE                        */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x009a0
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x9a0
 
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_SHFT 12
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
@@ -754,23 +1126,6 @@ union uvh_lb_bau_sb_descriptor_base_u {
 };
 
 /* ========================================================================= */
-/*                   UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK                     */
-/* ========================================================================= */
-#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK 0x320130UL
-#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_32 0x009f0
-
-#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_SHFT 0
-#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_MASK 0x00000000ffffffffUL
-
-union uvh_lb_target_physical_apic_id_mask_u {
-	unsigned long v;
-	struct uvh_lb_target_physical_apic_id_mask_s {
-		unsigned long bit_enables : 32;  /* RW */
-		unsigned long rsvd_32_63  : 32;  /*    */
-	} s;
-};
-
-/* ========================================================================= */
 /*                               UVH_NODE_ID                                 */
 /* ========================================================================= */
 #define UVH_NODE_ID 0x0UL
@@ -785,10 +1140,36 @@ union uvh_lb_target_physical_apic_id_mask_u {
 #define UVH_NODE_ID_REVISION_MASK 0x00000000f0000000UL
 #define UVH_NODE_ID_NODE_ID_SHFT 32
 #define UVH_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL
-#define UVH_NODE_ID_NODES_PER_BIT_SHFT 48
-#define UVH_NODE_ID_NODES_PER_BIT_MASK 0x007f000000000000UL
-#define UVH_NODE_ID_NI_PORT_SHFT 56
-#define UVH_NODE_ID_NI_PORT_MASK 0x0f00000000000000UL
+
+#define UV1H_NODE_ID_FORCE1_SHFT 0
+#define UV1H_NODE_ID_FORCE1_MASK 0x0000000000000001UL
+#define UV1H_NODE_ID_MANUFACTURER_SHFT 1
+#define UV1H_NODE_ID_MANUFACTURER_MASK 0x0000000000000ffeUL
+#define UV1H_NODE_ID_PART_NUMBER_SHFT 12
+#define UV1H_NODE_ID_PART_NUMBER_MASK 0x000000000ffff000UL
+#define UV1H_NODE_ID_REVISION_SHFT 28
+#define UV1H_NODE_ID_REVISION_MASK 0x00000000f0000000UL
+#define UV1H_NODE_ID_NODE_ID_SHFT 32
+#define UV1H_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL
+#define UV1H_NODE_ID_NODES_PER_BIT_SHFT 48
+#define UV1H_NODE_ID_NODES_PER_BIT_MASK 0x007f000000000000UL
+#define UV1H_NODE_ID_NI_PORT_SHFT 56
+#define UV1H_NODE_ID_NI_PORT_MASK 0x0f00000000000000UL
+
+#define UV2H_NODE_ID_FORCE1_SHFT 0
+#define UV2H_NODE_ID_FORCE1_MASK 0x0000000000000001UL
+#define UV2H_NODE_ID_MANUFACTURER_SHFT 1
+#define UV2H_NODE_ID_MANUFACTURER_MASK 0x0000000000000ffeUL
+#define UV2H_NODE_ID_PART_NUMBER_SHFT 12
+#define UV2H_NODE_ID_PART_NUMBER_MASK 0x000000000ffff000UL
+#define UV2H_NODE_ID_REVISION_SHFT 28
+#define UV2H_NODE_ID_REVISION_MASK 0x00000000f0000000UL
+#define UV2H_NODE_ID_NODE_ID_SHFT 32
+#define UV2H_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL
+#define UV2H_NODE_ID_NODES_PER_BIT_SHFT 50
+#define UV2H_NODE_ID_NODES_PER_BIT_MASK 0x01fc000000000000UL
+#define UV2H_NODE_ID_NI_PORT_SHFT 57
+#define UV2H_NODE_ID_NI_PORT_MASK 0x3e00000000000000UL
 
 union uvh_node_id_u {
     unsigned long	v;
@@ -798,12 +1179,31 @@ union uvh_node_id_u {
 	unsigned long	part_number   : 16;  /* RO */
 	unsigned long	revision      :  4;  /* RO */
 	unsigned long	node_id       : 15;  /* RW */
+	unsigned long	rsvd_47_63    : 17;
+    } s;
+    struct uv1h_node_id_s {
+	unsigned long	force1        :  1;  /* RO */
+	unsigned long	manufacturer  : 11;  /* RO */
+	unsigned long	part_number   : 16;  /* RO */
+	unsigned long	revision      :  4;  /* RO */
+	unsigned long	node_id       : 15;  /* RW */
 	unsigned long	rsvd_47       :  1;  /*    */
 	unsigned long	nodes_per_bit :  7;  /* RW */
 	unsigned long	rsvd_55       :  1;  /*    */
 	unsigned long	ni_port       :  4;  /* RO */
 	unsigned long	rsvd_60_63    :  4;  /*    */
-    } s;
+    } s1;
+    struct uv2h_node_id_s {
+	unsigned long	force1        :  1;  /* RO */
+	unsigned long	manufacturer  : 11;  /* RO */
+	unsigned long	part_number   : 16;  /* RO */
+	unsigned long	revision      :  4;  /* RO */
+	unsigned long	node_id       : 15;  /* RW */
+	unsigned long	rsvd_47_49    :  3;  /*    */
+	unsigned long	nodes_per_bit :  7;  /* RO */
+	unsigned long	ni_port       :  5;  /* RO */
+	unsigned long	rsvd_62_63    :  2;  /*    */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -954,18 +1354,38 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
 #define UVH_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL
 #define UVH_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6
 #define UVH_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL
-#define UVH_RH_GAM_CONFIG_MMR_MMIOL_CFG_SHFT 12
-#define UVH_RH_GAM_CONFIG_MMR_MMIOL_CFG_MASK 0x0000000000001000UL
+
+#define UV1H_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0
+#define UV1H_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL
+#define UV1H_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6
+#define UV1H_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL
+#define UV1H_RH_GAM_CONFIG_MMR_MMIOL_CFG_SHFT 12
+#define UV1H_RH_GAM_CONFIG_MMR_MMIOL_CFG_MASK 0x0000000000001000UL
+
+#define UV2H_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0
+#define UV2H_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL
+#define UV2H_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6
+#define UV2H_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL
 
 union uvh_rh_gam_config_mmr_u {
     unsigned long	v;
     struct uvh_rh_gam_config_mmr_s {
 	unsigned long	m_skt     :  6;  /* RW */
 	unsigned long	n_skt     :  4;  /* RW */
+	unsigned long	rsvd_10_63    : 54;
+    } s;
+    struct uv1h_rh_gam_config_mmr_s {
+	unsigned long	m_skt     :  6;  /* RW */
+	unsigned long	n_skt     :  4;  /* RW */
 	unsigned long	rsvd_10_11:  2;  /*    */
 	unsigned long	mmiol_cfg :  1;  /* RW */
 	unsigned long	rsvd_13_63: 51;  /*    */
-    } s;
+    } s1;
+    struct uv2h_rh_gam_config_mmr_s {
+	unsigned long	m_skt :  6;  /* RW */
+	unsigned long	n_skt :  4;  /* RW */
+	unsigned long	rsvd_10_63: 54;  /*    */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -975,25 +1395,49 @@ union uvh_rh_gam_config_mmr_u {
 
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 48
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0001000000000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 48
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0001000000000000UL
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
 
 union uvh_rh_gam_gru_overlay_config_mmr_u {
     unsigned long	v;
     struct uvh_rh_gam_gru_overlay_config_mmr_s {
 	unsigned long	rsvd_0_27: 28;  /*    */
 	unsigned long	base   : 18;  /* RW */
+	unsigned long	rsvd_46_62    : 17;
+	unsigned long	enable :  1;  /* RW */
+    } s;
+    struct uv1h_rh_gam_gru_overlay_config_mmr_s {
+	unsigned long	rsvd_0_27: 28;  /*    */
+	unsigned long	base   : 18;  /* RW */
 	unsigned long	rsvd_46_47:  2;  /*    */
 	unsigned long	gr4    :  1;  /* RW */
 	unsigned long	rsvd_49_51:  3;  /*    */
 	unsigned long	n_gru  :  4;  /* RW */
 	unsigned long	rsvd_56_62:  7;  /*    */
 	unsigned long	enable :  1;  /* RW */
-    } s;
+    } s1;
+    struct uv2h_rh_gam_gru_overlay_config_mmr_s {
+	unsigned long	rsvd_0_27: 28;  /*    */
+	unsigned long	base   : 18;  /* RW */
+	unsigned long	rsvd_46_51:  6;  /*    */
+	unsigned long	n_gru  :  4;  /* RW */
+	unsigned long	rsvd_56_62:  7;  /*    */
+	unsigned long	enable :  1;  /* RW */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -1001,25 +1445,42 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
 /* ========================================================================= */
 #define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL
 
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 30
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003fffc0000000UL
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 30
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003fffc0000000UL
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 27
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff8000000UL
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
 
 union uvh_rh_gam_mmioh_overlay_config_mmr_u {
     unsigned long	v;
-    struct uvh_rh_gam_mmioh_overlay_config_mmr_s {
+    struct uv1h_rh_gam_mmioh_overlay_config_mmr_s {
 	unsigned long	rsvd_0_29: 30;  /*    */
 	unsigned long	base   : 16;  /* RW */
 	unsigned long	m_io   :  6;  /* RW */
 	unsigned long	n_io   :  4;  /* RW */
 	unsigned long	rsvd_56_62:  7;  /*    */
 	unsigned long	enable :  1;  /* RW */
-    } s;
+    } s1;
+    struct uv2h_rh_gam_mmioh_overlay_config_mmr_s {
+	unsigned long	rsvd_0_26: 27;  /*    */
+	unsigned long	base   : 19;  /* RW */
+	unsigned long	m_io   :  6;  /* RW */
+	unsigned long	n_io   :  4;  /* RW */
+	unsigned long	rsvd_56_62:  7;  /*    */
+	unsigned long	enable :  1;  /* RW */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -1029,20 +1490,40 @@ union uvh_rh_gam_mmioh_overlay_config_mmr_u {
 
 #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26
 #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_SHFT 46
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_MASK 0x0000400000000000UL
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_SHFT 46
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_MASK 0x0000400000000000UL
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26
+#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
 
 union uvh_rh_gam_mmr_overlay_config_mmr_u {
     unsigned long	v;
     struct uvh_rh_gam_mmr_overlay_config_mmr_s {
 	unsigned long	rsvd_0_25: 26;  /*    */
 	unsigned long	base     : 20;  /* RW */
+	unsigned long	rsvd_46_62    : 17;
+	unsigned long	enable   :  1;  /* RW */
+    } s;
+    struct uv1h_rh_gam_mmr_overlay_config_mmr_s {
+	unsigned long	rsvd_0_25: 26;  /*    */
+	unsigned long	base     : 20;  /* RW */
 	unsigned long	dual_hub :  1;  /* RW */
 	unsigned long	rsvd_47_62: 16;  /*    */
 	unsigned long	enable   :  1;  /* RW */
-    } s;
+    } s1;
+    struct uv2h_rh_gam_mmr_overlay_config_mmr_s {
+	unsigned long	rsvd_0_25: 26;  /*    */
+	unsigned long	base   : 20;  /* RW */
+	unsigned long	rsvd_46_62: 17;  /*    */
+	unsigned long	enable :  1;  /* RW */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -1103,10 +1584,11 @@ union uvh_rtc1_int_config_u {
 /*                               UVH_SCRATCH5                                */
 /* ========================================================================= */
 #define UVH_SCRATCH5 0x2d0200UL
-#define UVH_SCRATCH5_32 0x00778
+#define UVH_SCRATCH5_32 0x778
 
 #define UVH_SCRATCH5_SCRATCH5_SHFT 0
 #define UVH_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL
+
 union uvh_scratch5_u {
     unsigned long	v;
     struct uvh_scratch5_s {
@@ -1114,4 +1596,154 @@ union uvh_scratch5_u {
     } s;
 };
 
+/* ========================================================================= */
+/*                           UV2H_EVENT_OCCURRED2                            */
+/* ========================================================================= */
+#define UV2H_EVENT_OCCURRED2 0x70100UL
+#define UV2H_EVENT_OCCURRED2_32 0xb68
+
+#define UV2H_EVENT_OCCURRED2_RTC_0_SHFT 0
+#define UV2H_EVENT_OCCURRED2_RTC_0_MASK 0x0000000000000001UL
+#define UV2H_EVENT_OCCURRED2_RTC_1_SHFT 1
+#define UV2H_EVENT_OCCURRED2_RTC_1_MASK 0x0000000000000002UL
+#define UV2H_EVENT_OCCURRED2_RTC_2_SHFT 2
+#define UV2H_EVENT_OCCURRED2_RTC_2_MASK 0x0000000000000004UL
+#define UV2H_EVENT_OCCURRED2_RTC_3_SHFT 3
+#define UV2H_EVENT_OCCURRED2_RTC_3_MASK 0x0000000000000008UL
+#define UV2H_EVENT_OCCURRED2_RTC_4_SHFT 4
+#define UV2H_EVENT_OCCURRED2_RTC_4_MASK 0x0000000000000010UL
+#define UV2H_EVENT_OCCURRED2_RTC_5_SHFT 5
+#define UV2H_EVENT_OCCURRED2_RTC_5_MASK 0x0000000000000020UL
+#define UV2H_EVENT_OCCURRED2_RTC_6_SHFT 6
+#define UV2H_EVENT_OCCURRED2_RTC_6_MASK 0x0000000000000040UL
+#define UV2H_EVENT_OCCURRED2_RTC_7_SHFT 7
+#define UV2H_EVENT_OCCURRED2_RTC_7_MASK 0x0000000000000080UL
+#define UV2H_EVENT_OCCURRED2_RTC_8_SHFT 8
+#define UV2H_EVENT_OCCURRED2_RTC_8_MASK 0x0000000000000100UL
+#define UV2H_EVENT_OCCURRED2_RTC_9_SHFT 9
+#define UV2H_EVENT_OCCURRED2_RTC_9_MASK 0x0000000000000200UL
+#define UV2H_EVENT_OCCURRED2_RTC_10_SHFT 10
+#define UV2H_EVENT_OCCURRED2_RTC_10_MASK 0x0000000000000400UL
+#define UV2H_EVENT_OCCURRED2_RTC_11_SHFT 11
+#define UV2H_EVENT_OCCURRED2_RTC_11_MASK 0x0000000000000800UL
+#define UV2H_EVENT_OCCURRED2_RTC_12_SHFT 12
+#define UV2H_EVENT_OCCURRED2_RTC_12_MASK 0x0000000000001000UL
+#define UV2H_EVENT_OCCURRED2_RTC_13_SHFT 13
+#define UV2H_EVENT_OCCURRED2_RTC_13_MASK 0x0000000000002000UL
+#define UV2H_EVENT_OCCURRED2_RTC_14_SHFT 14
+#define UV2H_EVENT_OCCURRED2_RTC_14_MASK 0x0000000000004000UL
+#define UV2H_EVENT_OCCURRED2_RTC_15_SHFT 15
+#define UV2H_EVENT_OCCURRED2_RTC_15_MASK 0x0000000000008000UL
+#define UV2H_EVENT_OCCURRED2_RTC_16_SHFT 16
+#define UV2H_EVENT_OCCURRED2_RTC_16_MASK 0x0000000000010000UL
+#define UV2H_EVENT_OCCURRED2_RTC_17_SHFT 17
+#define UV2H_EVENT_OCCURRED2_RTC_17_MASK 0x0000000000020000UL
+#define UV2H_EVENT_OCCURRED2_RTC_18_SHFT 18
+#define UV2H_EVENT_OCCURRED2_RTC_18_MASK 0x0000000000040000UL
+#define UV2H_EVENT_OCCURRED2_RTC_19_SHFT 19
+#define UV2H_EVENT_OCCURRED2_RTC_19_MASK 0x0000000000080000UL
+#define UV2H_EVENT_OCCURRED2_RTC_20_SHFT 20
+#define UV2H_EVENT_OCCURRED2_RTC_20_MASK 0x0000000000100000UL
+#define UV2H_EVENT_OCCURRED2_RTC_21_SHFT 21
+#define UV2H_EVENT_OCCURRED2_RTC_21_MASK 0x0000000000200000UL
+#define UV2H_EVENT_OCCURRED2_RTC_22_SHFT 22
+#define UV2H_EVENT_OCCURRED2_RTC_22_MASK 0x0000000000400000UL
+#define UV2H_EVENT_OCCURRED2_RTC_23_SHFT 23
+#define UV2H_EVENT_OCCURRED2_RTC_23_MASK 0x0000000000800000UL
+#define UV2H_EVENT_OCCURRED2_RTC_24_SHFT 24
+#define UV2H_EVENT_OCCURRED2_RTC_24_MASK 0x0000000001000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_25_SHFT 25
+#define UV2H_EVENT_OCCURRED2_RTC_25_MASK 0x0000000002000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_26_SHFT 26
+#define UV2H_EVENT_OCCURRED2_RTC_26_MASK 0x0000000004000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_27_SHFT 27
+#define UV2H_EVENT_OCCURRED2_RTC_27_MASK 0x0000000008000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_28_SHFT 28
+#define UV2H_EVENT_OCCURRED2_RTC_28_MASK 0x0000000010000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_29_SHFT 29
+#define UV2H_EVENT_OCCURRED2_RTC_29_MASK 0x0000000020000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_30_SHFT 30
+#define UV2H_EVENT_OCCURRED2_RTC_30_MASK 0x0000000040000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_31_SHFT 31
+#define UV2H_EVENT_OCCURRED2_RTC_31_MASK 0x0000000080000000UL
+
+union uv2h_event_occurred2_u {
+    unsigned long	v;
+    struct uv2h_event_occurred2_s {
+	unsigned long	rtc_0  :  1;  /* RW */
+	unsigned long	rtc_1  :  1;  /* RW */
+	unsigned long	rtc_2  :  1;  /* RW */
+	unsigned long	rtc_3  :  1;  /* RW */
+	unsigned long	rtc_4  :  1;  /* RW */
+	unsigned long	rtc_5  :  1;  /* RW */
+	unsigned long	rtc_6  :  1;  /* RW */
+	unsigned long	rtc_7  :  1;  /* RW */
+	unsigned long	rtc_8  :  1;  /* RW */
+	unsigned long	rtc_9  :  1;  /* RW */
+	unsigned long	rtc_10 :  1;  /* RW */
+	unsigned long	rtc_11 :  1;  /* RW */
+	unsigned long	rtc_12 :  1;  /* RW */
+	unsigned long	rtc_13 :  1;  /* RW */
+	unsigned long	rtc_14 :  1;  /* RW */
+	unsigned long	rtc_15 :  1;  /* RW */
+	unsigned long	rtc_16 :  1;  /* RW */
+	unsigned long	rtc_17 :  1;  /* RW */
+	unsigned long	rtc_18 :  1;  /* RW */
+	unsigned long	rtc_19 :  1;  /* RW */
+	unsigned long	rtc_20 :  1;  /* RW */
+	unsigned long	rtc_21 :  1;  /* RW */
+	unsigned long	rtc_22 :  1;  /* RW */
+	unsigned long	rtc_23 :  1;  /* RW */
+	unsigned long	rtc_24 :  1;  /* RW */
+	unsigned long	rtc_25 :  1;  /* RW */
+	unsigned long	rtc_26 :  1;  /* RW */
+	unsigned long	rtc_27 :  1;  /* RW */
+	unsigned long	rtc_28 :  1;  /* RW */
+	unsigned long	rtc_29 :  1;  /* RW */
+	unsigned long	rtc_30 :  1;  /* RW */
+	unsigned long	rtc_31 :  1;  /* RW */
+	unsigned long	rsvd_32_63: 32;  /*    */
+    } s1;
+};
+
+/* ========================================================================= */
+/*                        UV2H_EVENT_OCCURRED2_ALIAS                         */
+/* ========================================================================= */
+#define UV2H_EVENT_OCCURRED2_ALIAS 0x70108UL
+#define UV2H_EVENT_OCCURRED2_ALIAS_32 0xb70
+
+/* ========================================================================= */
+/*                    UV2H_LB_BAU_SB_ACTIVATION_STATUS_2                     */
+/* ========================================================================= */
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2 0x320130UL
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_32 0x9f0
+
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_SHFT 0
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_MASK 0xffffffffffffffffUL
+
+union uv2h_lb_bau_sb_activation_status_2_u {
+    unsigned long	v;
+    struct uv2h_lb_bau_sb_activation_status_2_s {
+	unsigned long	aux_error : 64;  /* RW */
+    } s1;
+};
+
+/* ========================================================================= */
+/*                   UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK                    */
+/* ========================================================================= */
+#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK 0x320130UL
+#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK_32 0x9f0
+
+#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_SHFT 0
+#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_MASK 0x00000000ffffffffUL
+
+union uv1h_lb_target_physical_apic_id_mask_u {
+    unsigned long	v;
+    struct uv1h_lb_target_physical_apic_id_mask_s {
+	unsigned long	bit_enables : 32;  /* RW */
+	unsigned long	rsvd_32_63  : 32;  /*    */
+    } s1;
+};
+
+
 #endif /* __ASM_UV_MMRS_X86_H__ */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index f5abe3a245b8..90b06d4daee2 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -8,6 +8,7 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not profile debug and lowlevel utilities
+CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 CFLAGS_REMOVE_pvclock.o = -pg
@@ -28,6 +29,7 @@ CFLAGS_paravirt.o	:= $(nostackp)
 GCOV_PROFILE_vsyscall_64.o	:= n
 GCOV_PROFILE_hpet.o		:= n
 GCOV_PROFILE_tsc.o		:= n
+GCOV_PROFILE_vread_tsc_64.o	:= n
 GCOV_PROFILE_paravirt.o		:= n
 
 # vread_tsc_64 is hot and should be fully optimized:
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index cd8cbeb5fa34..7c3a95e54ec5 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -30,6 +30,7 @@
 #include <asm/proto.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
+#include <asm/dma.h>
 #include <asm/amd_iommu_proto.h>
 #include <asm/amd_iommu_types.h>
 #include <asm/amd_iommu.h>
@@ -154,6 +155,10 @@ static int iommu_init_device(struct device *dev)
 	pdev = pci_get_bus_and_slot(PCI_BUS(alias), alias & 0xff);
 	if (pdev)
 		dev_data->alias = &pdev->dev;
+	else {
+		kfree(dev_data);
+		return -ENOTSUPP;
+	}
 
 	atomic_set(&dev_data->bind, 0);
 
@@ -163,6 +168,20 @@ static int iommu_init_device(struct device *dev)
 	return 0;
 }
 
+static void iommu_ignore_device(struct device *dev)
+{
+	u16 devid, alias;
+
+	devid = get_device_id(dev);
+	alias = amd_iommu_alias_table[devid];
+
+	memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry));
+	memset(&amd_iommu_dev_table[alias], 0, sizeof(struct dev_table_entry));
+
+	amd_iommu_rlookup_table[devid] = NULL;
+	amd_iommu_rlookup_table[alias] = NULL;
+}
+
 static void iommu_uninit_device(struct device *dev)
 {
 	kfree(dev->archdata.iommu);
@@ -192,7 +211,9 @@ int __init amd_iommu_init_devices(void)
 			continue;
 
 		ret = iommu_init_device(&pdev->dev);
-		if (ret)
+		if (ret == -ENOTSUPP)
+			iommu_ignore_device(&pdev->dev);
+		else if (ret)
 			goto out_free;
 	}
 
@@ -2383,6 +2404,23 @@ static struct dma_map_ops amd_iommu_dma_ops = {
 	.dma_supported = amd_iommu_dma_supported,
 };
 
+static unsigned device_dma_ops_init(void)
+{
+	struct pci_dev *pdev = NULL;
+	unsigned unhandled = 0;
+
+	for_each_pci_dev(pdev) {
+		if (!check_device(&pdev->dev)) {
+			unhandled += 1;
+			continue;
+		}
+
+		pdev->dev.archdata.dma_ops = &amd_iommu_dma_ops;
+	}
+
+	return unhandled;
+}
+
 /*
  * The function which clues the AMD IOMMU driver into dma_ops.
  */
@@ -2395,7 +2433,7 @@ void __init amd_iommu_init_api(void)
 int __init amd_iommu_init_dma_ops(void)
 {
 	struct amd_iommu *iommu;
-	int ret;
+	int ret, unhandled;
 
 	/*
 	 * first allocate a default protection domain for every IOMMU we
@@ -2421,7 +2459,11 @@ int __init amd_iommu_init_dma_ops(void)
 	swiotlb = 0;
 
 	/* Make the driver finally visible to the drivers */
-	dma_ops = &amd_iommu_dma_ops;
+	unhandled = device_dma_ops_init();
+	if (unhandled && max_pfn > MAX_DMA32_PFN) {
+		/* There are unhandled devices - initialize swiotlb for them */
+		swiotlb = 1;
+	}
 
 	amd_iommu_stats_init();
 
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 9179c21120a8..bfc8453bd98d 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -731,8 +731,8 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 {
 	u8 *p = (u8 *)h;
 	u8 *end = p, flags = 0;
-	u16 dev_i, devid = 0, devid_start = 0, devid_to = 0;
-	u32 ext_flags = 0;
+	u16 devid = 0, devid_start = 0, devid_to = 0;
+	u32 dev_i, ext_flags = 0;
 	bool alias = false;
 	struct ivhd_entry *e;
 
@@ -887,7 +887,7 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 /* Initializes the device->iommu mapping for the driver */
 static int __init init_iommu_devices(struct amd_iommu *iommu)
 {
-	u16 i;
+	u32 i;
 
 	for (i = iommu->first_device; i <= iommu->last_device; ++i)
 		set_iommu_for_device(iommu, i);
@@ -1177,7 +1177,7 @@ static int __init init_memory_definitions(struct acpi_table_header *table)
  */
 static void init_device_table(void)
 {
-	u16 devid;
+	u32 devid;
 
 	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
 		set_dev_entry_bit(devid, DEV_ENTRY_VALID);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b961af86bfea..b9338b8cf420 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -390,7 +390,8 @@ static unsigned int reserve_eilvt_offset(int offset, unsigned int new)
 
 /*
  * If mask=1, the LVT entry does not generate interrupts while mask=0
- * enables the vector. See also the BKDGs.
+ * enables the vector. See also the BKDGs. Must be called with
+ * preemption disabled.
  */
 
 int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index f450b683dfcf..adc66c3a1fef 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -91,6 +91,10 @@ static int __init early_get_pnodeid(void)
 	m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_CONFIG_MMR);
 	uv_min_hub_revision_id = node_id.s.revision;
 
+	if (node_id.s.part_number == UV2_HUB_PART_NUMBER)
+		uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1;
+
+	uv_hub_info->hub_revision = uv_min_hub_revision_id;
 	pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1);
 	return pnode;
 }
@@ -112,17 +116,25 @@ static void __init early_get_apic_pnode_shift(void)
  */
 static void __init uv_set_apicid_hibit(void)
 {
-	union uvh_lb_target_physical_apic_id_mask_u apicid_mask;
+	union uv1h_lb_target_physical_apic_id_mask_u apicid_mask;
 
-	apicid_mask.v = uv_early_read_mmr(UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK);
-	uv_apicid_hibits = apicid_mask.s.bit_enables & UV_APICID_HIBIT_MASK;
+	if (is_uv1_hub()) {
+		apicid_mask.v =
+			uv_early_read_mmr(UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK);
+		uv_apicid_hibits =
+			apicid_mask.s1.bit_enables & UV_APICID_HIBIT_MASK;
+	}
 }
 
 static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
-	int pnodeid;
+	int pnodeid, is_uv1, is_uv2;
 
-	if (!strcmp(oem_id, "SGI")) {
+	is_uv1 = !strcmp(oem_id, "SGI");
+	is_uv2 = !strcmp(oem_id, "SGI2");
+	if (is_uv1 || is_uv2) {
+		uv_hub_info->hub_revision =
+			is_uv1 ? UV1_HUB_REVISION_BASE : UV2_HUB_REVISION_BASE;
 		pnodeid = early_get_pnodeid();
 		early_get_apic_pnode_shift();
 		x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
@@ -484,12 +496,19 @@ static __init void map_mmr_high(int max_pnode)
 static __init void map_mmioh_high(int max_pnode)
 {
 	union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh;
-	int shift = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+	int shift;
 
 	mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR);
-	if (mmioh.s.enable)
-		map_high("MMIOH", mmioh.s.base, shift, mmioh.s.m_io,
+	if (is_uv1_hub() && mmioh.s1.enable) {
+		shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+		map_high("MMIOH", mmioh.s1.base, shift, mmioh.s1.m_io,
+			max_pnode, map_uc);
+	}
+	if (is_uv2_hub() && mmioh.s2.enable) {
+		shift = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+		map_high("MMIOH", mmioh.s2.base, shift, mmioh.s2.m_io,
 			max_pnode, map_uc);
+	}
 }
 
 static __init void map_low_mmrs(void)
@@ -613,14 +632,14 @@ late_initcall(uv_init_heartbeat);
 
 /* Direct Legacy VGA I/O traffic to designated IOH */
 int uv_set_vga_state(struct pci_dev *pdev, bool decode,
-		      unsigned int command_bits, bool change_bridge)
+		      unsigned int command_bits, u32 flags)
 {
 	int domain, bus, rc;
 
-	PR_DEVEL("devfn %x decode %d cmd %x chg_brdg %d\n",
-			pdev->devfn, decode, command_bits, change_bridge);
+	PR_DEVEL("devfn %x decode %d cmd %x flags %d\n",
+			pdev->devfn, decode, command_bits, flags);
 
-	if (!change_bridge)
+	if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE))
 		return 0;
 
 	if ((command_bits & PCI_COMMAND_IO) == 0)
@@ -736,13 +755,14 @@ void __init uv_system_init(void)
 	unsigned long mmr_base, present, paddr;
 	unsigned short pnode_mask, pnode_io_mask;
 
+	printk(KERN_INFO "UV: Found %s hub\n", is_uv1_hub() ? "UV1" : "UV2");
 	map_low_mmrs();
 
 	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
 	m_val = m_n_config.s.m_skt;
 	n_val = m_n_config.s.n_skt;
 	mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR);
-	n_io = mmioh.s.n_io;
+	n_io = is_uv1_hub() ? mmioh.s1.n_io : mmioh.s2.n_io;
 	mmr_base =
 	    uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
 	    ~UV_MMR_ENABLE;
@@ -811,6 +831,8 @@ void __init uv_system_init(void)
 		 */
 		uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
 		uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift;
+		uv_cpu_hub_info(cpu)->hub_revision = uv_hub_info->hub_revision;
+
 		pnode = uv_apicid_to_pnode(apicid);
 		blade = boot_pnode_to_blade(pnode);
 		lcpu = uv_blade_info[blade].nr_possible_cpus;
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 3bfa02235965..965a7666c283 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -361,6 +361,7 @@ struct apm_user {
  * idle percentage above which bios idle calls are done
  */
 #ifdef CONFIG_APM_CPU_IDLE
+#warning deprecated CONFIG_APM_CPU_IDLE will be deleted in 2012
 #define DEFAULT_IDLE_THRESHOLD	95
 #else
 #define DEFAULT_IDLE_THRESHOLD	100
@@ -904,6 +905,7 @@ static void apm_cpu_idle(void)
 	unsigned int jiffies_since_last_check = jiffies - last_jiffies;
 	unsigned int bucket;
 
+	WARN_ONCE(1, "deprecated apm_cpu_idle will be deleted in 2012");
 recalc:
 	if (jiffies_since_last_check > IDLE_CALC_LIMIT) {
 		use_apm_idle = 0;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 8f5cabb3c5b0..b13ed393dfce 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -612,8 +612,11 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	}
 #endif
 
-	/* As a rule processors have APIC timer running in deep C states */
-	if (c->x86 > 0xf && !cpu_has_amd_erratum(amd_erratum_400))
+	/*
+	 * Family 0x12 and above processors have APIC timer
+	 * running in deep C states.
+	 */
+	if (c->x86 > 0x11)
 		set_cpu_cap(c, X86_FEATURE_ARAT);
 
 	/*
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c39576cb3018..525514cf33c3 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -19,6 +19,7 @@
 
 static int __init no_halt(char *s)
 {
+	WARN_ONCE(1, "\"no-hlt\" is deprecated, please use \"idle=poll\"\n");
 	boot_cpu_data.hlt_works_ok = 0;
 	return 1;
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c8b41623377f..22a073d7fbff 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -477,13 +477,6 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c)
 	if (smp_num_siblings <= 1)
 		goto out;
 
-	if (smp_num_siblings > nr_cpu_ids) {
-		pr_warning("CPU: Unsupported number of siblings %d",
-			   smp_num_siblings);
-		smp_num_siblings = 1;
-		return;
-	}
-
 	index_msb = get_count_order(smp_num_siblings);
 	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
 
@@ -909,7 +902,7 @@ static void vgetcpu_set_mode(void)
 void __init identify_boot_cpu(void)
 {
 	identify_cpu(&boot_cpu_data);
-	init_c1e_mask();
+	init_amd_e400_c1e_mask();
 #ifdef CONFIG_X86_32
 	sysenter_setup();
 	enable_sep_cpu();
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 690bc8461835..9aeb78a23de4 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/pci.h>
 #include <linux/of_pci.h>
+#include <linux/initrd.h>
 
 #include <asm/hpet.h>
 #include <asm/irq_controller.h>
@@ -98,6 +99,16 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 	return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS));
 }
 
+#ifdef CONFIG_BLK_DEV_INITRD
+void __init early_init_dt_setup_initrd_arch(unsigned long start,
+					    unsigned long end)
+{
+	initrd_start = (unsigned long)__va(start);
+	initrd_end = (unsigned long)__va(end);
+	initrd_below_start_ok = 1;
+}
+#endif
+
 void __init add_dtb(u64 data)
 {
 	initial_dtb = data + offsetof(struct setup_data, data);
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 0ba15a6cc57e..c9a281f272fd 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -123,7 +123,7 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 static atomic_t nmi_running = ATOMIC_INIT(0);
 static int mod_code_status;		/* holds return value of text 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 const 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);
@@ -225,7 +225,7 @@ within(unsigned long addr, unsigned long start, unsigned long end)
 }
 
 static int
-do_ftrace_mod_code(unsigned long ip, void *new_code)
+do_ftrace_mod_code(unsigned long ip, const void *new_code)
 {
 	/*
 	 * On x86_64, kernel text mappings are mapped read-only with
@@ -266,8 +266,8 @@ static const unsigned char *ftrace_nop_replace(void)
 }
 
 static int
-ftrace_modify_code(unsigned long ip, unsigned char *old_code,
-		   unsigned char *new_code)
+ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
+		   unsigned const char *new_code)
 {
 	unsigned char replaced[MCOUNT_INSN_SIZE];
 
@@ -301,7 +301,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 int ftrace_make_nop(struct module *mod,
 		    struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned char *new, *old;
+	unsigned const char *new, *old;
 	unsigned long ip = rec->ip;
 
 	old = ftrace_call_replace(ip, addr);
@@ -312,7 +312,7 @@ int ftrace_make_nop(struct module *mod,
 
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned char *new, *old;
+	unsigned const char *new, *old;
 	unsigned long ip = rec->ip;
 
 	old = ftrace_nop_replace();
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 88a90a977f8e..e1ba8cb24e4e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -337,7 +337,9 @@ EXPORT_SYMBOL(boot_option_idle_override);
  * Powermanagement idle function, if any..
  */
 void (*pm_idle)(void);
+#ifdef CONFIG_APM_MODULE
 EXPORT_SYMBOL(pm_idle);
+#endif
 
 #ifdef CONFIG_X86_32
 /*
@@ -535,45 +537,45 @@ int mwait_usable(const struct cpuinfo_x86 *c)
 	return (edx & MWAIT_EDX_C1);
 }
 
-bool c1e_detected;
-EXPORT_SYMBOL(c1e_detected);
+bool amd_e400_c1e_detected;
+EXPORT_SYMBOL(amd_e400_c1e_detected);
 
-static cpumask_var_t c1e_mask;
+static cpumask_var_t amd_e400_c1e_mask;
 
-void c1e_remove_cpu(int cpu)
+void amd_e400_remove_cpu(int cpu)
 {
-	if (c1e_mask != NULL)
-		cpumask_clear_cpu(cpu, c1e_mask);
+	if (amd_e400_c1e_mask != NULL)
+		cpumask_clear_cpu(cpu, amd_e400_c1e_mask);
 }
 
 /*
- * C1E aware idle routine. We check for C1E active in the interrupt
+ * AMD Erratum 400 aware idle routine. We check for C1E active in the interrupt
  * pending message MSR. If we detect C1E, then we handle it the same
  * way as C3 power states (local apic timer and TSC stop)
  */
-static void c1e_idle(void)
+static void amd_e400_idle(void)
 {
 	if (need_resched())
 		return;
 
-	if (!c1e_detected) {
+	if (!amd_e400_c1e_detected) {
 		u32 lo, hi;
 
 		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
 
 		if (lo & K8_INTP_C1E_ACTIVE_MASK) {
-			c1e_detected = true;
+			amd_e400_c1e_detected = true;
 			if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 				mark_tsc_unstable("TSC halt in AMD C1E");
 			printk(KERN_INFO "System has AMD C1E enabled\n");
 		}
 	}
 
-	if (c1e_detected) {
+	if (amd_e400_c1e_detected) {
 		int cpu = smp_processor_id();
 
-		if (!cpumask_test_cpu(cpu, c1e_mask)) {
-			cpumask_set_cpu(cpu, c1e_mask);
+		if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) {
+			cpumask_set_cpu(cpu, amd_e400_c1e_mask);
 			/*
 			 * Force broadcast so ACPI can not interfere.
 			 */
@@ -616,17 +618,17 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 		pm_idle = mwait_idle;
 	} else if (cpu_has_amd_erratum(amd_erratum_400)) {
 		/* E400: APIC timer interrupt does not wake up CPU from C1e */
-		printk(KERN_INFO "using C1E aware idle routine\n");
-		pm_idle = c1e_idle;
+		printk(KERN_INFO "using AMD E400 aware idle routine\n");
+		pm_idle = amd_e400_idle;
 	} else
 		pm_idle = default_idle;
 }
 
-void __init init_c1e_mask(void)
+void __init init_amd_e400_c1e_mask(void)
 {
-	/* If we're using c1e_idle, we need to allocate c1e_mask. */
-	if (pm_idle == c1e_idle)
-		zalloc_cpumask_var(&c1e_mask, GFP_KERNEL);
+	/* If we're using amd_e400_idle, we need to allocate amd_e400_c1e_mask. */
+	if (pm_idle == amd_e400_idle)
+		zalloc_cpumask_var(&amd_e400_c1e_mask, GFP_KERNEL);
 }
 
 static int __init idle_setup(char *str)
@@ -640,6 +642,7 @@ static int __init idle_setup(char *str)
 		boot_option_idle_override = IDLE_POLL;
 	} else if (!strcmp(str, "mwait")) {
 		boot_option_idle_override = IDLE_FORCE_MWAIT;
+		WARN_ONCE(1, "\"idle=mwait\" will be removed in 2012\n");
 	} else if (!strcmp(str, "halt")) {
 		/*
 		 * When the boot option of idle=halt is added, halt is
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 8d128783af47..a3d0dc59067b 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -245,7 +245,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 {
 	set_user_gs(regs, 0);
 	regs->fs		= 0;
-	set_fs(USER_DS);
 	regs->ds		= __USER_DS;
 	regs->es		= __USER_DS;
 	regs->ss		= __USER_DS;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 6c9dd922ac0d..ca6f7ab8df33 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -338,7 +338,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
 	regs->cs		= _cs;
 	regs->ss		= _ss;
 	regs->flags		= X86_EFLAGS_IF;
-	set_fs(USER_DS);
 	/*
 	 * Free the old FP and other extended state
 	 */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index a3e5948670c2..afaf38447ef5 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -910,6 +910,13 @@ void __init setup_arch(char **cmdline_p)
 	memblock.current_limit = get_max_mapped();
 	memblock_x86_fill();
 
+	/*
+	 * The EFI specification says that boot service code won't be called
+	 * after ExitBootServices(). This is, in fact, a lie.
+	 */
+	if (efi_enabled)
+		efi_reserve_boot_services();
+
 	/* preallocate 4k for mptable mpc */
 	early_reserve_e820_mpc_new();
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a3c430bdfb60..9fd3137230d4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -285,6 +285,19 @@ notrace static void __cpuinit start_secondary(void *unused)
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
 	x86_platform.nmi_init();
 
+	/*
+	 * Wait until the cpu which brought this one up marked it
+	 * online before enabling interrupts. If we don't do that then
+	 * we can end up waking up the softirq thread before this cpu
+	 * reached the active state, which makes the scheduler unhappy
+	 * and schedule the softirq thread on the wrong cpu. This is
+	 * only observable with forced threaded interrupts, but in
+	 * theory it could also happen w/o them. It's just way harder
+	 * to achieve.
+	 */
+	while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask))
+		cpu_relax();
+
 	/* enable local interrupts */
 	local_irq_enable();
 
@@ -1307,7 +1320,7 @@ void play_dead_common(void)
 {
 	idle_task_exit();
 	reset_lazy_tlbstate();
-	c1e_remove_cpu(raw_smp_processor_id());
+	amd_e400_remove_cpu(raw_smp_processor_id());
 
 	mb();
 	/* Ack it */
@@ -1332,7 +1345,7 @@ static inline void mwait_play_dead(void)
 	void *mwait_ptr;
 	struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info);
 
-	if (!this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c))
+	if (!(this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c)))
 		return;
 	if (!this_cpu_has(X86_FEATURE_CLFLSH))
 		return;
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index 32cbffb0c494..fbb0a045a1a2 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -345,3 +345,4 @@ ENTRY(sys_call_table)
 	.long sys_clock_adjtime
 	.long sys_syncfs
 	.long sys_sendmmsg		/* 345 */
+	.long sys_setns
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index d6e2477feb18..6df88c7885c0 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -47,38 +47,40 @@
 #define DstDI       (5<<1)	/* Destination is in ES:(E)DI */
 #define DstMem64    (6<<1)	/* 64bit memory operand */
 #define DstImmUByte (7<<1)	/* 8-bit unsigned immediate operand */
-#define DstMask     (7<<1)
+#define DstDX       (8<<1)	/* Destination is in DX register */
+#define DstMask     (0xf<<1)
 /* Source operand type. */
-#define SrcNone     (0<<4)	/* No source operand. */
-#define SrcReg      (1<<4)	/* Register operand. */
-#define SrcMem      (2<<4)	/* Memory operand. */
-#define SrcMem16    (3<<4)	/* Memory operand (16-bit). */
-#define SrcMem32    (4<<4)	/* Memory operand (32-bit). */
-#define SrcImm      (5<<4)	/* Immediate operand. */
-#define SrcImmByte  (6<<4)	/* 8-bit sign-extended immediate operand. */
-#define SrcOne      (7<<4)	/* Implied '1' */
-#define SrcImmUByte (8<<4)      /* 8-bit unsigned immediate operand. */
-#define SrcImmU     (9<<4)      /* Immediate operand, unsigned */
-#define SrcSI       (0xa<<4)	/* Source is in the DS:RSI */
-#define SrcImmFAddr (0xb<<4)	/* Source is immediate far address */
-#define SrcMemFAddr (0xc<<4)	/* Source is far address in memory */
-#define SrcAcc      (0xd<<4)	/* Source Accumulator */
-#define SrcImmU16   (0xe<<4)    /* Immediate operand, unsigned, 16 bits */
-#define SrcMask     (0xf<<4)
+#define SrcNone     (0<<5)	/* No source operand. */
+#define SrcReg      (1<<5)	/* Register operand. */
+#define SrcMem      (2<<5)	/* Memory operand. */
+#define SrcMem16    (3<<5)	/* Memory operand (16-bit). */
+#define SrcMem32    (4<<5)	/* Memory operand (32-bit). */
+#define SrcImm      (5<<5)	/* Immediate operand. */
+#define SrcImmByte  (6<<5)	/* 8-bit sign-extended immediate operand. */
+#define SrcOne      (7<<5)	/* Implied '1' */
+#define SrcImmUByte (8<<5)      /* 8-bit unsigned immediate operand. */
+#define SrcImmU     (9<<5)      /* Immediate operand, unsigned */
+#define SrcSI       (0xa<<5)	/* Source is in the DS:RSI */
+#define SrcImmFAddr (0xb<<5)	/* Source is immediate far address */
+#define SrcMemFAddr (0xc<<5)	/* Source is far address in memory */
+#define SrcAcc      (0xd<<5)	/* Source Accumulator */
+#define SrcImmU16   (0xe<<5)    /* Immediate operand, unsigned, 16 bits */
+#define SrcDX       (0xf<<5)	/* Source is in DX register */
+#define SrcMask     (0xf<<5)
 /* Generic ModRM decode. */
-#define ModRM       (1<<8)
+#define ModRM       (1<<9)
 /* Destination is only written; never read. */
-#define Mov         (1<<9)
-#define BitOp       (1<<10)
-#define MemAbs      (1<<11)      /* Memory operand is absolute displacement */
-#define String      (1<<12)     /* String instruction (rep capable) */
-#define Stack       (1<<13)     /* Stack instruction (push/pop) */
-#define GroupMask   (7<<14)     /* Opcode uses one of the group mechanisms */
-#define Group       (1<<14)     /* Bits 3:5 of modrm byte extend opcode */
-#define GroupDual   (2<<14)     /* Alternate decoding of mod == 3 */
-#define Prefix      (3<<14)     /* Instruction varies with 66/f2/f3 prefix */
-#define RMExt       (4<<14)     /* Opcode extension in ModRM r/m if mod == 3 */
-#define Sse         (1<<17)     /* SSE Vector instruction */
+#define Mov         (1<<10)
+#define BitOp       (1<<11)
+#define MemAbs      (1<<12)      /* Memory operand is absolute displacement */
+#define String      (1<<13)     /* String instruction (rep capable) */
+#define Stack       (1<<14)     /* Stack instruction (push/pop) */
+#define GroupMask   (7<<15)     /* Opcode uses one of the group mechanisms */
+#define Group       (1<<15)     /* Bits 3:5 of modrm byte extend opcode */
+#define GroupDual   (2<<15)     /* Alternate decoding of mod == 3 */
+#define Prefix      (3<<15)     /* Instruction varies with 66/f2/f3 prefix */
+#define RMExt       (4<<15)     /* Opcode extension in ModRM r/m if mod == 3 */
+#define Sse         (1<<18)     /* SSE Vector instruction */
 /* Misc flags */
 #define Prot        (1<<21) /* instruction generates #UD if not in prot-mode */
 #define VendorSpecific (1<<22) /* Vendor specific instruction */
@@ -3154,8 +3156,8 @@ static struct opcode opcode_table[256] = {
 	I(DstReg | SrcMem | ModRM | Src2Imm, em_imul_3op),
 	I(SrcImmByte | Mov | Stack, em_push),
 	I(DstReg | SrcMem | ModRM | Src2ImmByte, em_imul_3op),
-	D2bvIP(DstDI | Mov | String, ins, check_perm_in), /* insb, insw/insd */
-	D2bvIP(SrcSI | ImplicitOps | String, outs, check_perm_out), /* outsb, outsw/outsd */
+	D2bvIP(DstDI | SrcDX | Mov | String, ins, check_perm_in), /* insb, insw/insd */
+	D2bvIP(SrcSI | DstDX | String, outs, check_perm_out), /* outsb, outsw/outsd */
 	/* 0x70 - 0x7F */
 	X16(D(SrcImmByte)),
 	/* 0x80 - 0x87 */
@@ -3212,8 +3214,8 @@ static struct opcode opcode_table[256] = {
 	/* 0xE8 - 0xEF */
 	D(SrcImm | Stack), D(SrcImm | ImplicitOps),
 	D(SrcImmFAddr | No64), D(SrcImmByte | ImplicitOps),
-	D2bvIP(SrcNone | DstAcc,     in,  check_perm_in),
-	D2bvIP(SrcAcc | ImplicitOps, out, check_perm_out),
+	D2bvIP(SrcDX | DstAcc, in,  check_perm_in),
+	D2bvIP(SrcAcc | DstDX, out, check_perm_out),
 	/* 0xF0 - 0xF7 */
 	N, DI(ImplicitOps, icebp), N, N,
 	DI(ImplicitOps | Priv, hlt), D(ImplicitOps),
@@ -3613,6 +3615,12 @@ done_prefixes:
 		memop.bytes = c->op_bytes + 2;
 		goto srcmem_common;
 		break;
+	case SrcDX:
+		c->src.type = OP_REG;
+		c->src.bytes = 2;
+		c->src.addr.reg = &c->regs[VCPU_REGS_RDX];
+		fetch_register_operand(&c->src);
+		break;
 	}
 
 	if (rc != X86EMUL_CONTINUE)
@@ -3682,6 +3690,12 @@ done_prefixes:
 		c->dst.addr.mem.seg = VCPU_SREG_ES;
 		c->dst.val = 0;
 		break;
+	case DstDX:
+		c->dst.type = OP_REG;
+		c->dst.bytes = 2;
+		c->dst.addr.reg = &c->regs[VCPU_REGS_RDX];
+		fetch_register_operand(&c->dst);
+		break;
 	case ImplicitOps:
 		/* Special instructions do their own operand decoding. */
 	default:
@@ -4027,7 +4041,6 @@ special_insn:
 		break;
 	case 0xec: /* in al,dx */
 	case 0xed: /* in (e/r)ax,dx */
-		c->src.val = c->regs[VCPU_REGS_RDX];
 	do_io_in:
 		if (!pio_in_emulated(ctxt, ops, c->dst.bytes, c->src.val,
 				     &c->dst.val))
@@ -4035,7 +4048,6 @@ special_insn:
 		break;
 	case 0xee: /* out dx,al */
 	case 0xef: /* out dx,(e/r)ax */
-		c->dst.val = c->regs[VCPU_REGS_RDX];
 	do_io_out:
 		ops->pio_out_emulated(ctxt, c->src.bytes, c->dst.val,
 				      &c->src.val, 1);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index bd14bb4c8594..aee38623b768 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -565,7 +565,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
 
 static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn)
 {
-	return gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true);
+	return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true);
 }
 
 static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 6c4dc010c4cb..9d03ad4dd5ec 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -121,7 +121,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 				    gva_t addr, u32 access)
 {
 	pt_element_t pte;
-	pt_element_t __user *ptep_user;
+	pt_element_t __user *uninitialized_var(ptep_user);
 	gfn_t table_gfn;
 	unsigned index, pt_access, uninitialized_var(pte_access);
 	gpa_t pte_gpa;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4c3fa0f67469..d48ec60ea421 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2047,7 +2047,8 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
 					unsigned long cr0,
 					struct kvm_vcpu *vcpu)
 {
-	vmx_decache_cr3(vcpu);
+	if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
+		vmx_decache_cr3(vcpu);
 	if (!(cr0 & X86_CR0_PG)) {
 		/* From paging/starting to nonpaging */
 		vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index e191c096ab90..db832fd65ecb 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -993,6 +993,7 @@ static void lguest_time_irq(unsigned int irq, struct irq_desc *desc)
 static void lguest_time_init(void)
 {
 	/* Set up the timer interrupt (0) to go to our simple timer routine */
+	lguest_setup_irq(0);
 	irq_set_handler(0, lguest_time_irq);
 
 	clocksource_register_hz(&lguest_clock, NSEC_PER_SEC);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f7a2a054a3c0..2dbf6bf4c7e5 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -823,16 +823,30 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 	force_sig_info_fault(SIGBUS, code, address, tsk, fault);
 }
 
-static noinline void
+static noinline int
 mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	       unsigned long address, unsigned int fault)
 {
+	/*
+	 * Pagefault was interrupted by SIGKILL. We have no reason to
+	 * continue pagefault.
+	 */
+	if (fatal_signal_pending(current)) {
+		if (!(fault & VM_FAULT_RETRY))
+			up_read(&current->mm->mmap_sem);
+		if (!(error_code & PF_USER))
+			no_context(regs, error_code, address);
+		return 1;
+	}
+	if (!(fault & VM_FAULT_ERROR))
+		return 0;
+
 	if (fault & VM_FAULT_OOM) {
 		/* Kernel mode? Handle exceptions or die: */
 		if (!(error_code & PF_USER)) {
 			up_read(&current->mm->mmap_sem);
 			no_context(regs, error_code, address);
-			return;
+			return 1;
 		}
 
 		out_of_memory(regs, error_code, address);
@@ -843,6 +857,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 		else
 			BUG();
 	}
+	return 1;
 }
 
 static int spurious_fault_check(unsigned long error_code, pte_t *pte)
@@ -1133,19 +1148,9 @@ good_area:
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);
 
-	if (unlikely(fault & VM_FAULT_ERROR)) {
-		mm_fault_error(regs, error_code, address, fault);
-		return;
-	}
-
-	/*
-	 * Pagefault was interrupted by SIGKILL. We have no reason to
-	 * continue pagefault.
-	 */
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
-		if (!(error_code & PF_USER))
-			no_context(regs, error_code, address);
-		return;
+	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
+		if (mm_fault_error(regs, error_code, address, fault))
+			return;
 	}
 
 	/*
diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c
index aa1169392b83..992da5ec5a64 100644
--- a/arch/x86/mm/memblock.c
+++ b/arch/x86/mm/memblock.c
@@ -8,7 +8,7 @@
 #include <linux/range.h>
 
 /* Check for already reserved areas */
-static bool __init check_with_memblock_reserved_size(u64 *addrp, u64 *sizep, u64 align)
+bool __init memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align)
 {
 	struct memblock_region *r;
 	u64 addr = *addrp, last;
@@ -59,7 +59,7 @@ u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align)
 		if (addr >= ei_last)
 			continue;
 		*sizep = ei_last - addr;
-		while (check_with_memblock_reserved_size(&addr, sizep, align))
+		while (memblock_x86_check_reserved_size(&addr, sizep, align))
 			;
 
 		if (*sizep)
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index c3b8e24f2b16..9cbb710dc94b 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -316,16 +316,23 @@ static void op_amd_stop_ibs(void)
 		wrmsrl(MSR_AMD64_IBSOPCTL, 0);
 }
 
-static inline int eilvt_is_available(int offset)
+static inline int get_eilvt(int offset)
 {
-	/* check if we may assign a vector */
 	return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1);
 }
 
+static inline int put_eilvt(int offset)
+{
+	return !setup_APIC_eilvt(offset, 0, 0, 1);
+}
+
 static inline int ibs_eilvt_valid(void)
 {
 	int offset;
 	u64 val;
+	int valid = 0;
+
+	preempt_disable();
 
 	rdmsrl(MSR_AMD64_IBSCTL, val);
 	offset = val & IBSCTL_LVT_OFFSET_MASK;
@@ -333,16 +340,20 @@ static inline int ibs_eilvt_valid(void)
 	if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
 		pr_err(FW_BUG "cpu %d, invalid IBS interrupt offset %d (MSR%08X=0x%016llx)\n",
 		       smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
-		return 0;
+		goto out;
 	}
 
-	if (!eilvt_is_available(offset)) {
+	if (!get_eilvt(offset)) {
 		pr_err(FW_BUG "cpu %d, IBS interrupt offset %d not available (MSR%08X=0x%016llx)\n",
 		       smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
-		return 0;
+		goto out;
 	}
 
-	return 1;
+	valid = 1;
+out:
+	preempt_enable();
+
+	return valid;
 }
 
 static inline int get_ibs_offset(void)
@@ -598,69 +609,76 @@ static int setup_ibs_ctl(int ibs_eilvt_off)
 	return 0;
 }
 
+/*
+ * This runs only on the current cpu. We try to find an LVT offset and
+ * setup the local APIC. For this we must disable preemption. On
+ * success we initialize all nodes with this offset. This updates then
+ * the offset in the IBS_CTL per-node msr. The per-core APIC setup of
+ * the IBS interrupt vector is called from op_amd_setup_ctrs()/op_-
+ * amd_cpu_shutdown() using the new offset.
+ */
 static int force_ibs_eilvt_setup(void)
 {
-	int i;
+	int offset;
 	int ret;
 
-	/* find the next free available EILVT entry */
-	for (i = 1; i < 4; i++) {
-		if (!eilvt_is_available(i))
-			continue;
-		ret = setup_ibs_ctl(i);
-		if (ret)
-			return ret;
-		pr_err(FW_BUG "using offset %d for IBS interrupts\n", i);
-		return 0;
+	preempt_disable();
+	/* find the next free available EILVT entry, skip offset 0 */
+	for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) {
+		if (get_eilvt(offset))
+			break;
 	}
+	preempt_enable();
 
-	printk(KERN_DEBUG "No EILVT entry available\n");
-
-	return -EBUSY;
-}
-
-static int __init_ibs_nmi(void)
-{
-	int ret;
-
-	if (ibs_eilvt_valid())
-		return 0;
+	if (offset == APIC_EILVT_NR_MAX) {
+		printk(KERN_DEBUG "No EILVT entry available\n");
+		return -EBUSY;
+	}
 
-	ret = force_ibs_eilvt_setup();
+	ret = setup_ibs_ctl(offset);
 	if (ret)
-		return ret;
+		goto out;
 
-	if (!ibs_eilvt_valid())
-		return -EFAULT;
+	if (!ibs_eilvt_valid()) {
+		ret = -EFAULT;
+		goto out;
+	}
 
+	pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
 	pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
 
 	return 0;
+out:
+	preempt_disable();
+	put_eilvt(offset);
+	preempt_enable();
+	return ret;
 }
 
 /*
  * check and reserve APIC extended interrupt LVT offset for IBS if
  * available
- *
- * init_ibs() preforms implicitly cpu-local operations, so pin this
- * thread to its current CPU
  */
 
 static void init_ibs(void)
 {
-	preempt_disable();
-
 	ibs_caps = get_ibs_caps();
+
 	if (!ibs_caps)
+		return;
+
+	if (ibs_eilvt_valid())
 		goto out;
 
-	if (__init_ibs_nmi() < 0)
-		ibs_caps = 0;
-	else
-		printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
+	if (!force_ibs_eilvt_setup())
+		goto out;
+
+	/* Failed to setup ibs */
+	ibs_caps = 0;
+	return;
 
 out:
-	preempt_enable();
+	printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
 }
 
 static int (*create_arch_files)(struct super_block *sb, struct dentry *root);
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 0972315c3860..68c3c1395202 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -188,7 +188,7 @@ static bool resource_contains(struct resource *res, resource_size_t point)
 	return false;
 }
 
-static void coalesce_windows(struct pci_root_info *info, int type)
+static void coalesce_windows(struct pci_root_info *info, unsigned long type)
 {
 	int i, j;
 	struct resource *res1, *res2;
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index b30aa26a8df2..474356b98ede 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -304,6 +304,61 @@ static void __init print_efi_memmap(void)
 }
 #endif  /*  EFI_DEBUG  */
 
+void __init efi_reserve_boot_services(void)
+{
+	void *p;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		efi_memory_desc_t *md = p;
+		u64 start = md->phys_addr;
+		u64 size = md->num_pages << EFI_PAGE_SHIFT;
+
+		if (md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA)
+			continue;
+		/* Only reserve where possible:
+		 * - Not within any already allocated areas
+		 * - Not over any memory area (really needed, if above?)
+		 * - Not within any part of the kernel
+		 * - Not the bios reserved area
+		*/
+		if ((start+size >= virt_to_phys(_text)
+				&& start <= virt_to_phys(_end)) ||
+			!e820_all_mapped(start, start+size, E820_RAM) ||
+			memblock_x86_check_reserved_size(&start, &size,
+							1<<EFI_PAGE_SHIFT)) {
+			/* Could not reserve, skip it */
+			md->num_pages = 0;
+			memblock_dbg(PFX "Could not reserve boot range "
+					"[0x%010llx-0x%010llx]\n",
+						start, start+size-1);
+		} else
+			memblock_x86_reserve_range(start, start+size,
+							"EFI Boot");
+	}
+}
+
+static void __init efi_free_boot_services(void)
+{
+	void *p;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		efi_memory_desc_t *md = p;
+		unsigned long long start = md->phys_addr;
+		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+
+		if (md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA)
+			continue;
+
+		/* Could not reserve boot area */
+		if (!size)
+			continue;
+
+		free_bootmem_late(start, size);
+	}
+}
+
 void __init efi_init(void)
 {
 	efi_config_table_t *config_tables;
@@ -536,7 +591,9 @@ void __init efi_enter_virtual_mode(void)
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
-		if (!(md->attribute & EFI_MEMORY_RUNTIME))
+		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
+		    md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA)
 			continue;
 
 		size = md->num_pages << EFI_PAGE_SHIFT;
@@ -593,6 +650,13 @@ void __init efi_enter_virtual_mode(void)
 	}
 
 	/*
+	 * Thankfully, it does seem that no runtime services other than
+	 * SetVirtualAddressMap() will touch boot services code, so we can
+	 * get rid of it all at this point
+	 */
+	efi_free_boot_services();
+
+	/*
 	 * Now that EFI is in virtual mode, update the function
 	 * pointers in the runtime service table to the new virtual addresses.
 	 *
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 2649426a7905..ac3aa54e2654 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -49,10 +49,11 @@ static void __init early_code_mapping_set_exec(int executable)
 	if (!(__supported_pte_mask & _PAGE_NX))
 		return;
 
-	/* Make EFI runtime service code area executable */
+	/* Make EFI service code area executable */
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
-		if (md->type == EFI_RUNTIME_SERVICES_CODE)
+		if (md->type == EFI_RUNTIME_SERVICES_CODE ||
+		    md->type == EFI_BOOT_SERVICES_CODE)
 			efi_set_executable(md, executable);
 	}
 }
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index c58e0ea39ef5..68e467f69fec 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1,7 +1,7 @@
 /*
  *	SGI UltraViolet TLB flush routines.
  *
- *	(c) 2008-2010 Cliff Wickman <cpw@sgi.com>, SGI.
+ *	(c) 2008-2011 Cliff Wickman <cpw@sgi.com>, SGI.
  *
  *	This code is released under the GNU General Public License version 2 or
  *	later.
@@ -35,6 +35,7 @@ static int timeout_base_ns[] = {
 		5242880,
 		167772160
 };
+
 static int timeout_us;
 static int nobau;
 static int baudisabled;
@@ -42,20 +43,70 @@ static spinlock_t disable_lock;
 static cycles_t congested_cycles;
 
 /* tunables: */
-static int max_bau_concurrent = MAX_BAU_CONCURRENT;
-static int max_bau_concurrent_constant = MAX_BAU_CONCURRENT;
-static int plugged_delay = PLUGGED_DELAY;
-static int plugsb4reset = PLUGSB4RESET;
-static int timeoutsb4reset = TIMEOUTSB4RESET;
-static int ipi_reset_limit = IPI_RESET_LIMIT;
-static int complete_threshold = COMPLETE_THRESHOLD;
-static int congested_response_us = CONGESTED_RESPONSE_US;
-static int congested_reps = CONGESTED_REPS;
-static int congested_period = CONGESTED_PERIOD;
+static int max_concurr		= MAX_BAU_CONCURRENT;
+static int max_concurr_const	= MAX_BAU_CONCURRENT;
+static int plugged_delay	= PLUGGED_DELAY;
+static int plugsb4reset		= PLUGSB4RESET;
+static int timeoutsb4reset	= TIMEOUTSB4RESET;
+static int ipi_reset_limit	= IPI_RESET_LIMIT;
+static int complete_threshold	= COMPLETE_THRESHOLD;
+static int congested_respns_us	= CONGESTED_RESPONSE_US;
+static int congested_reps	= CONGESTED_REPS;
+static int congested_period	= CONGESTED_PERIOD;
+
+static struct tunables tunables[] = {
+	{&max_concurr, MAX_BAU_CONCURRENT}, /* must be [0] */
+	{&plugged_delay, PLUGGED_DELAY},
+	{&plugsb4reset, PLUGSB4RESET},
+	{&timeoutsb4reset, TIMEOUTSB4RESET},
+	{&ipi_reset_limit, IPI_RESET_LIMIT},
+	{&complete_threshold, COMPLETE_THRESHOLD},
+	{&congested_respns_us, CONGESTED_RESPONSE_US},
+	{&congested_reps, CONGESTED_REPS},
+	{&congested_period, CONGESTED_PERIOD}
+};
+
 static struct dentry *tunables_dir;
 static struct dentry *tunables_file;
 
-static int __init setup_nobau(char *arg)
+/* these correspond to the statistics printed by ptc_seq_show() */
+static char *stat_description[] = {
+	"sent:     number of shootdown messages sent",
+	"stime:    time spent sending messages",
+	"numuvhubs: number of hubs targeted with shootdown",
+	"numuvhubs16: number times 16 or more hubs targeted",
+	"numuvhubs8: number times 8 or more hubs targeted",
+	"numuvhubs4: number times 4 or more hubs targeted",
+	"numuvhubs2: number times 2 or more hubs targeted",
+	"numuvhubs1: number times 1 hub targeted",
+	"numcpus:  number of cpus targeted with shootdown",
+	"dto:      number of destination timeouts",
+	"retries:  destination timeout retries sent",
+	"rok:   :  destination timeouts successfully retried",
+	"resetp:   ipi-style resource resets for plugs",
+	"resett:   ipi-style resource resets for timeouts",
+	"giveup:   fall-backs to ipi-style shootdowns",
+	"sto:      number of source timeouts",
+	"bz:       number of stay-busy's",
+	"throt:    number times spun in throttle",
+	"swack:   image of UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE",
+	"recv:     shootdown messages received",
+	"rtime:    time spent processing messages",
+	"all:      shootdown all-tlb messages",
+	"one:      shootdown one-tlb messages",
+	"mult:     interrupts that found multiple messages",
+	"none:     interrupts that found no messages",
+	"retry:    number of retry messages processed",
+	"canc:     number messages canceled by retries",
+	"nocan:    number retries that found nothing to cancel",
+	"reset:    number of ipi-style reset requests processed",
+	"rcan:     number messages canceled by reset requests",
+	"disable:  number times use of the BAU was disabled",
+	"enable:   number times use of the BAU was re-enabled"
+};
+
+static int __init
+setup_nobau(char *arg)
 {
 	nobau = 1;
 	return 0;
@@ -63,7 +114,7 @@ static int __init setup_nobau(char *arg)
 early_param("nobau", setup_nobau);
 
 /* base pnode in this partition */
-static int uv_partition_base_pnode __read_mostly;
+static int uv_base_pnode __read_mostly;
 /* position of pnode (which is nasid>>1): */
 static int uv_nshift __read_mostly;
 static unsigned long uv_mmask __read_mostly;
@@ -109,60 +160,52 @@ static int __init uvhub_to_first_apicid(int uvhub)
  * clear of the Timeout bit (as well) will free the resource. No reply will
  * be sent (the hardware will only do one reply per message).
  */
-static inline void uv_reply_to_message(struct msg_desc *mdp,
-				       struct bau_control *bcp)
+static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp)
 {
 	unsigned long dw;
-	struct bau_payload_queue_entry *msg;
+	struct bau_pq_entry *msg;
 
 	msg = mdp->msg;
 	if (!msg->canceled) {
-		dw = (msg->sw_ack_vector << UV_SW_ACK_NPENDING) |
-						msg->sw_ack_vector;
-		uv_write_local_mmr(
-				UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, dw);
+		dw = (msg->swack_vec << UV_SW_ACK_NPENDING) | msg->swack_vec;
+		write_mmr_sw_ack(dw);
 	}
 	msg->replied_to = 1;
-	msg->sw_ack_vector = 0;
+	msg->swack_vec = 0;
 }
 
 /*
  * Process the receipt of a RETRY message
  */
-static inline void uv_bau_process_retry_msg(struct msg_desc *mdp,
-					    struct bau_control *bcp)
+static void bau_process_retry_msg(struct msg_desc *mdp,
+					struct bau_control *bcp)
 {
 	int i;
 	int cancel_count = 0;
-	int slot2;
 	unsigned long msg_res;
 	unsigned long mmr = 0;
-	struct bau_payload_queue_entry *msg;
-	struct bau_payload_queue_entry *msg2;
-	struct ptc_stats *stat;
+	struct bau_pq_entry *msg = mdp->msg;
+	struct bau_pq_entry *msg2;
+	struct ptc_stats *stat = bcp->statp;
 
-	msg = mdp->msg;
-	stat = bcp->statp;
 	stat->d_retries++;
 	/*
 	 * cancel any message from msg+1 to the retry itself
 	 */
 	for (msg2 = msg+1, i = 0; i < DEST_Q_SIZE; msg2++, i++) {
-		if (msg2 > mdp->va_queue_last)
-			msg2 = mdp->va_queue_first;
+		if (msg2 > mdp->queue_last)
+			msg2 = mdp->queue_first;
 		if (msg2 == msg)
 			break;
 
-		/* same conditions for cancellation as uv_do_reset */
+		/* same conditions for cancellation as do_reset */
 		if ((msg2->replied_to == 0) && (msg2->canceled == 0) &&
-		    (msg2->sw_ack_vector) && ((msg2->sw_ack_vector &
-			msg->sw_ack_vector) == 0) &&
+		    (msg2->swack_vec) && ((msg2->swack_vec &
+			msg->swack_vec) == 0) &&
 		    (msg2->sending_cpu == msg->sending_cpu) &&
 		    (msg2->msg_type != MSG_NOOP)) {
-			slot2 = msg2 - mdp->va_queue_first;
-			mmr = uv_read_local_mmr
-				(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
-			msg_res = msg2->sw_ack_vector;
+			mmr = read_mmr_sw_ack();
+			msg_res = msg2->swack_vec;
 			/*
 			 * This is a message retry; clear the resources held
 			 * by the previous message only if they timed out.
@@ -170,6 +213,7 @@ static inline void uv_bau_process_retry_msg(struct msg_desc *mdp,
 			 * situation to report.
 			 */
 			if (mmr & (msg_res << UV_SW_ACK_NPENDING)) {
+				unsigned long mr;
 				/*
 				 * is the resource timed out?
 				 * make everyone ignore the cancelled message.
@@ -177,10 +221,8 @@ static inline void uv_bau_process_retry_msg(struct msg_desc *mdp,
 				msg2->canceled = 1;
 				stat->d_canceled++;
 				cancel_count++;
-				uv_write_local_mmr(
-				    UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS,
-					(msg_res << UV_SW_ACK_NPENDING) |
-					 msg_res);
+				mr = (msg_res << UV_SW_ACK_NPENDING) | msg_res;
+				write_mmr_sw_ack(mr);
 			}
 		}
 	}
@@ -192,20 +234,19 @@ static inline void uv_bau_process_retry_msg(struct msg_desc *mdp,
  * Do all the things a cpu should do for a TLB shootdown message.
  * Other cpu's may come here at the same time for this message.
  */
-static void uv_bau_process_message(struct msg_desc *mdp,
-				   struct bau_control *bcp)
+static void bau_process_message(struct msg_desc *mdp,
+					struct bau_control *bcp)
 {
-	int msg_ack_count;
 	short socket_ack_count = 0;
-	struct ptc_stats *stat;
-	struct bau_payload_queue_entry *msg;
+	short *sp;
+	struct atomic_short *asp;
+	struct ptc_stats *stat = bcp->statp;
+	struct bau_pq_entry *msg = mdp->msg;
 	struct bau_control *smaster = bcp->socket_master;
 
 	/*
 	 * This must be a normal message, or retry of a normal message
 	 */
-	msg = mdp->msg;
-	stat = bcp->statp;
 	if (msg->address == TLB_FLUSH_ALL) {
 		local_flush_tlb();
 		stat->d_alltlb++;
@@ -222,30 +263,32 @@ static void uv_bau_process_message(struct msg_desc *mdp,
 	 * cpu number.
 	 */
 	if (msg->msg_type == MSG_RETRY && bcp == bcp->uvhub_master)
-		uv_bau_process_retry_msg(mdp, bcp);
+		bau_process_retry_msg(mdp, bcp);
 
 	/*
-	 * This is a sw_ack message, so we have to reply to it.
+	 * This is a swack message, so we have to reply to it.
 	 * Count each responding cpu on the socket. This avoids
 	 * pinging the count's cache line back and forth between
 	 * the sockets.
 	 */
-	socket_ack_count = atomic_add_short_return(1, (struct atomic_short *)
-			&smaster->socket_acknowledge_count[mdp->msg_slot]);
+	sp = &smaster->socket_acknowledge_count[mdp->msg_slot];
+	asp = (struct atomic_short *)sp;
+	socket_ack_count = atom_asr(1, asp);
 	if (socket_ack_count == bcp->cpus_in_socket) {
+		int msg_ack_count;
 		/*
 		 * Both sockets dump their completed count total into
 		 * the message's count.
 		 */
 		smaster->socket_acknowledge_count[mdp->msg_slot] = 0;
-		msg_ack_count = atomic_add_short_return(socket_ack_count,
-				(struct atomic_short *)&msg->acknowledge_count);
+		asp = (struct atomic_short *)&msg->acknowledge_count;
+		msg_ack_count = atom_asr(socket_ack_count, asp);
 
 		if (msg_ack_count == bcp->cpus_in_uvhub) {
 			/*
 			 * All cpus in uvhub saw it; reply
 			 */
-			uv_reply_to_message(mdp, bcp);
+			reply_to_message(mdp, bcp);
 		}
 	}
 
@@ -268,62 +311,51 @@ static int uvhub_to_first_cpu(int uvhub)
  * Last resort when we get a large number of destination timeouts is
  * to clear resources held by a given cpu.
  * Do this with IPI so that all messages in the BAU message queue
- * can be identified by their nonzero sw_ack_vector field.
+ * can be identified by their nonzero swack_vec field.
  *
  * This is entered for a single cpu on the uvhub.
  * The sender want's this uvhub to free a specific message's
- * sw_ack resources.
+ * swack resources.
  */
-static void
-uv_do_reset(void *ptr)
+static void do_reset(void *ptr)
 {
 	int i;
-	int slot;
-	int count = 0;
-	unsigned long mmr;
-	unsigned long msg_res;
-	struct bau_control *bcp;
-	struct reset_args *rap;
-	struct bau_payload_queue_entry *msg;
-	struct ptc_stats *stat;
+	struct bau_control *bcp = &per_cpu(bau_control, smp_processor_id());
+	struct reset_args *rap = (struct reset_args *)ptr;
+	struct bau_pq_entry *msg;
+	struct ptc_stats *stat = bcp->statp;
 
-	bcp = &per_cpu(bau_control, smp_processor_id());
-	rap = (struct reset_args *)ptr;
-	stat = bcp->statp;
 	stat->d_resets++;
-
 	/*
 	 * We're looking for the given sender, and
-	 * will free its sw_ack resource.
+	 * will free its swack resource.
 	 * If all cpu's finally responded after the timeout, its
 	 * message 'replied_to' was set.
 	 */
-	for (msg = bcp->va_queue_first, i = 0; i < DEST_Q_SIZE; msg++, i++) {
-		/* uv_do_reset: same conditions for cancellation as
-		   uv_bau_process_retry_msg() */
+	for (msg = bcp->queue_first, i = 0; i < DEST_Q_SIZE; msg++, i++) {
+		unsigned long msg_res;
+		/* do_reset: same conditions for cancellation as
+		   bau_process_retry_msg() */
 		if ((msg->replied_to == 0) &&
 		    (msg->canceled == 0) &&
 		    (msg->sending_cpu == rap->sender) &&
-		    (msg->sw_ack_vector) &&
+		    (msg->swack_vec) &&
 		    (msg->msg_type != MSG_NOOP)) {
+			unsigned long mmr;
+			unsigned long mr;
 			/*
 			 * make everyone else ignore this message
 			 */
 			msg->canceled = 1;
-			slot = msg - bcp->va_queue_first;
-			count++;
 			/*
 			 * only reset the resource if it is still pending
 			 */
-			mmr = uv_read_local_mmr
-					(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
-			msg_res = msg->sw_ack_vector;
+			mmr = read_mmr_sw_ack();
+			msg_res = msg->swack_vec;
+			mr = (msg_res << UV_SW_ACK_NPENDING) | msg_res;
 			if (mmr & msg_res) {
 				stat->d_rcanceled++;
-				uv_write_local_mmr(
-				    UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS,
-					(msg_res << UV_SW_ACK_NPENDING) |
-					 msg_res);
+				write_mmr_sw_ack(mr);
 			}
 		}
 	}
@@ -334,39 +366,38 @@ uv_do_reset(void *ptr)
  * Use IPI to get all target uvhubs to release resources held by
  * a given sending cpu number.
  */
-static void uv_reset_with_ipi(struct bau_target_uvhubmask *distribution,
-			      int sender)
+static void reset_with_ipi(struct bau_targ_hubmask *distribution, int sender)
 {
 	int uvhub;
-	int cpu;
+	int maskbits;
 	cpumask_t mask;
 	struct reset_args reset_args;
 
 	reset_args.sender = sender;
-
 	cpus_clear(mask);
 	/* find a single cpu for each uvhub in this distribution mask */
-	for (uvhub = 0;
-		    uvhub < sizeof(struct bau_target_uvhubmask) * BITSPERBYTE;
-		    uvhub++) {
+	maskbits = sizeof(struct bau_targ_hubmask) * BITSPERBYTE;
+	for (uvhub = 0; uvhub < maskbits; uvhub++) {
+		int cpu;
 		if (!bau_uvhub_isset(uvhub, distribution))
 			continue;
 		/* find a cpu for this uvhub */
 		cpu = uvhub_to_first_cpu(uvhub);
 		cpu_set(cpu, mask);
 	}
-	/* IPI all cpus; Preemption is already disabled */
-	smp_call_function_many(&mask, uv_do_reset, (void *)&reset_args, 1);
+
+	/* IPI all cpus; preemption is already disabled */
+	smp_call_function_many(&mask, do_reset, (void *)&reset_args, 1);
 	return;
 }
 
-static inline unsigned long
-cycles_2_us(unsigned long long cyc)
+static inline unsigned long cycles_2_us(unsigned long long cyc)
 {
 	unsigned long long ns;
 	unsigned long us;
-	ns =  (cyc * per_cpu(cyc2ns, smp_processor_id()))
-						>> CYC2NS_SCALE_FACTOR;
+	int cpu = smp_processor_id();
+
+	ns =  (cyc * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR;
 	us = ns / 1000;
 	return us;
 }
@@ -376,56 +407,56 @@ cycles_2_us(unsigned long long cyc)
  * leaves uvhub_quiesce set so that no new broadcasts are started by
  * bau_flush_send_and_wait()
  */
-static inline void
-quiesce_local_uvhub(struct bau_control *hmaster)
+static inline void quiesce_local_uvhub(struct bau_control *hmaster)
 {
-	atomic_add_short_return(1, (struct atomic_short *)
-		 &hmaster->uvhub_quiesce);
+	atom_asr(1, (struct atomic_short *)&hmaster->uvhub_quiesce);
 }
 
 /*
  * mark this quiet-requestor as done
  */
-static inline void
-end_uvhub_quiesce(struct bau_control *hmaster)
+static inline void end_uvhub_quiesce(struct bau_control *hmaster)
 {
-	atomic_add_short_return(-1, (struct atomic_short *)
-		&hmaster->uvhub_quiesce);
+	atom_asr(-1, (struct atomic_short *)&hmaster->uvhub_quiesce);
+}
+
+static unsigned long uv1_read_status(unsigned long mmr_offset, int right_shift)
+{
+	unsigned long descriptor_status;
+
+	descriptor_status = uv_read_local_mmr(mmr_offset);
+	descriptor_status >>= right_shift;
+	descriptor_status &= UV_ACT_STATUS_MASK;
+	return descriptor_status;
 }
 
 /*
  * Wait for completion of a broadcast software ack message
  * return COMPLETE, RETRY(PLUGGED or TIMEOUT) or GIVEUP
  */
-static int uv_wait_completion(struct bau_desc *bau_desc,
-	unsigned long mmr_offset, int right_shift, int this_cpu,
-	struct bau_control *bcp, struct bau_control *smaster, long try)
+static int uv1_wait_completion(struct bau_desc *bau_desc,
+				unsigned long mmr_offset, int right_shift,
+				struct bau_control *bcp, long try)
 {
 	unsigned long descriptor_status;
-	cycles_t ttime;
+	cycles_t ttm;
 	struct ptc_stats *stat = bcp->statp;
-	struct bau_control *hmaster;
-
-	hmaster = bcp->uvhub_master;
 
+	descriptor_status = uv1_read_status(mmr_offset, right_shift);
 	/* spin on the status MMR, waiting for it to go idle */
-	while ((descriptor_status = (((unsigned long)
-		uv_read_local_mmr(mmr_offset) >>
-			right_shift) & UV_ACT_STATUS_MASK)) !=
-			DESC_STATUS_IDLE) {
+	while ((descriptor_status != DS_IDLE)) {
 		/*
-		 * Our software ack messages may be blocked because there are
-		 * no swack resources available.  As long as none of them
-		 * has timed out hardware will NACK our message and its
-		 * state will stay IDLE.
+		 * Our software ack messages may be blocked because
+		 * there are no swack resources available.  As long
+		 * as none of them has timed out hardware will NACK
+		 * our message and its state will stay IDLE.
 		 */
-		if (descriptor_status == DESC_STATUS_SOURCE_TIMEOUT) {
+		if (descriptor_status == DS_SOURCE_TIMEOUT) {
 			stat->s_stimeout++;
 			return FLUSH_GIVEUP;
-		} else if (descriptor_status ==
-					DESC_STATUS_DESTINATION_TIMEOUT) {
+		} else if (descriptor_status == DS_DESTINATION_TIMEOUT) {
 			stat->s_dtimeout++;
-			ttime = get_cycles();
+			ttm = get_cycles();
 
 			/*
 			 * Our retries may be blocked by all destination
@@ -433,8 +464,7 @@ static int uv_wait_completion(struct bau_desc *bau_desc,
 			 * pending.  In that case hardware returns the
 			 * ERROR that looks like a destination timeout.
 			 */
-			if (cycles_2_us(ttime - bcp->send_message) <
-							timeout_us) {
+			if (cycles_2_us(ttm - bcp->send_message) < timeout_us) {
 				bcp->conseccompletes = 0;
 				return FLUSH_RETRY_PLUGGED;
 			}
@@ -447,80 +477,160 @@ static int uv_wait_completion(struct bau_desc *bau_desc,
 			 */
 			cpu_relax();
 		}
+		descriptor_status = uv1_read_status(mmr_offset, right_shift);
 	}
 	bcp->conseccompletes++;
 	return FLUSH_COMPLETE;
 }
 
-static inline cycles_t
-sec_2_cycles(unsigned long sec)
+/*
+ * UV2 has an extra bit of status in the ACTIVATION_STATUS_2 register.
+ */
+static unsigned long uv2_read_status(unsigned long offset, int rshft, int cpu)
 {
-	unsigned long ns;
-	cycles_t cyc;
+	unsigned long descriptor_status;
+	unsigned long descriptor_status2;
 
-	ns = sec * 1000000000;
-	cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id()));
-	return cyc;
+	descriptor_status = ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK);
+	descriptor_status2 = (read_mmr_uv2_status() >> cpu) & 0x1UL;
+	descriptor_status = (descriptor_status << 1) | descriptor_status2;
+	return descriptor_status;
+}
+
+static int uv2_wait_completion(struct bau_desc *bau_desc,
+				unsigned long mmr_offset, int right_shift,
+				struct bau_control *bcp, long try)
+{
+	unsigned long descriptor_stat;
+	cycles_t ttm;
+	int cpu = bcp->uvhub_cpu;
+	struct ptc_stats *stat = bcp->statp;
+
+	descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu);
+
+	/* spin on the status MMR, waiting for it to go idle */
+	while (descriptor_stat != UV2H_DESC_IDLE) {
+		/*
+		 * Our software ack messages may be blocked because
+		 * there are no swack resources available.  As long
+		 * as none of them has timed out hardware will NACK
+		 * our message and its state will stay IDLE.
+		 */
+		if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT) ||
+		    (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) ||
+		    (descriptor_stat == UV2H_DESC_DEST_PUT_ERR)) {
+			stat->s_stimeout++;
+			return FLUSH_GIVEUP;
+		} else if (descriptor_stat == UV2H_DESC_DEST_TIMEOUT) {
+			stat->s_dtimeout++;
+			ttm = get_cycles();
+			/*
+			 * Our retries may be blocked by all destination
+			 * swack resources being consumed, and a timeout
+			 * pending.  In that case hardware returns the
+			 * ERROR that looks like a destination timeout.
+			 */
+			if (cycles_2_us(ttm - bcp->send_message) < timeout_us) {
+				bcp->conseccompletes = 0;
+				return FLUSH_RETRY_PLUGGED;
+			}
+			bcp->conseccompletes = 0;
+			return FLUSH_RETRY_TIMEOUT;
+		} else {
+			/*
+			 * descriptor_stat is still BUSY
+			 */
+			cpu_relax();
+		}
+		descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu);
+	}
+	bcp->conseccompletes++;
+	return FLUSH_COMPLETE;
 }
 
 /*
- * conditionally add 1 to *v, unless *v is >= u
- * return 0 if we cannot add 1 to *v because it is >= u
- * return 1 if we can add 1 to *v because it is < u
- * the add is atomic
- *
- * This is close to atomic_add_unless(), but this allows the 'u' value
- * to be lowered below the current 'v'.  atomic_add_unless can only stop
- * on equal.
+ * There are 2 status registers; each and array[32] of 2 bits. Set up for
+ * which register to read and position in that register based on cpu in
+ * current hub.
  */
-static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u)
+static int wait_completion(struct bau_desc *bau_desc,
+				struct bau_control *bcp, long try)
 {
-	spin_lock(lock);
-	if (atomic_read(v) >= u) {
-		spin_unlock(lock);
-		return 0;
+	int right_shift;
+	unsigned long mmr_offset;
+	int cpu = bcp->uvhub_cpu;
+
+	if (cpu < UV_CPUS_PER_AS) {
+		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
+		right_shift = cpu * UV_ACT_STATUS_SIZE;
+	} else {
+		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
+		right_shift = ((cpu - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE);
 	}
-	atomic_inc(v);
-	spin_unlock(lock);
-	return 1;
+
+	if (is_uv1_hub())
+		return uv1_wait_completion(bau_desc, mmr_offset, right_shift,
+								bcp, try);
+	else
+		return uv2_wait_completion(bau_desc, mmr_offset, right_shift,
+								bcp, try);
+}
+
+static inline cycles_t sec_2_cycles(unsigned long sec)
+{
+	unsigned long ns;
+	cycles_t cyc;
+
+	ns = sec * 1000000000;
+	cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id()));
+	return cyc;
 }
 
 /*
- * Our retries are blocked by all destination swack resources being
+ * Our retries are blocked by all destination sw ack resources being
  * in use, and a timeout is pending. In that case hardware immediately
  * returns the ERROR that looks like a destination timeout.
  */
-static void
-destination_plugged(struct bau_desc *bau_desc, struct bau_control *bcp,
+static void destination_plugged(struct bau_desc *bau_desc,
+			struct bau_control *bcp,
 			struct bau_control *hmaster, struct ptc_stats *stat)
 {
 	udelay(bcp->plugged_delay);
 	bcp->plugged_tries++;
+
 	if (bcp->plugged_tries >= bcp->plugsb4reset) {
 		bcp->plugged_tries = 0;
+
 		quiesce_local_uvhub(hmaster);
+
 		spin_lock(&hmaster->queue_lock);
-		uv_reset_with_ipi(&bau_desc->distribution, bcp->cpu);
+		reset_with_ipi(&bau_desc->distribution, bcp->cpu);
 		spin_unlock(&hmaster->queue_lock);
+
 		end_uvhub_quiesce(hmaster);
+
 		bcp->ipi_attempts++;
 		stat->s_resets_plug++;
 	}
 }
 
-static void
-destination_timeout(struct bau_desc *bau_desc, struct bau_control *bcp,
-			struct bau_control *hmaster, struct ptc_stats *stat)
+static void destination_timeout(struct bau_desc *bau_desc,
+			struct bau_control *bcp, struct bau_control *hmaster,
+			struct ptc_stats *stat)
 {
-	hmaster->max_bau_concurrent = 1;
+	hmaster->max_concurr = 1;
 	bcp->timeout_tries++;
 	if (bcp->timeout_tries >= bcp->timeoutsb4reset) {
 		bcp->timeout_tries = 0;
+
 		quiesce_local_uvhub(hmaster);
+
 		spin_lock(&hmaster->queue_lock);
-		uv_reset_with_ipi(&bau_desc->distribution, bcp->cpu);
+		reset_with_ipi(&bau_desc->distribution, bcp->cpu);
 		spin_unlock(&hmaster->queue_lock);
+
 		end_uvhub_quiesce(hmaster);
+
 		bcp->ipi_attempts++;
 		stat->s_resets_timeout++;
 	}
@@ -530,34 +640,104 @@ destination_timeout(struct bau_desc *bau_desc, struct bau_control *bcp,
  * Completions are taking a very long time due to a congested numalink
  * network.
  */
-static void
-disable_for_congestion(struct bau_control *bcp, struct ptc_stats *stat)
+static void disable_for_congestion(struct bau_control *bcp,
+					struct ptc_stats *stat)
 {
-	int tcpu;
-	struct bau_control *tbcp;
-
 	/* let only one cpu do this disabling */
 	spin_lock(&disable_lock);
+
 	if (!baudisabled && bcp->period_requests &&
 	    ((bcp->period_time / bcp->period_requests) > congested_cycles)) {
+		int tcpu;
+		struct bau_control *tbcp;
 		/* it becomes this cpu's job to turn on the use of the
 		   BAU again */
 		baudisabled = 1;
 		bcp->set_bau_off = 1;
-		bcp->set_bau_on_time = get_cycles() +
-			sec_2_cycles(bcp->congested_period);
+		bcp->set_bau_on_time = get_cycles();
+		bcp->set_bau_on_time += sec_2_cycles(bcp->cong_period);
 		stat->s_bau_disabled++;
 		for_each_present_cpu(tcpu) {
 			tbcp = &per_cpu(bau_control, tcpu);
-				tbcp->baudisabled = 1;
+			tbcp->baudisabled = 1;
 		}
 	}
+
 	spin_unlock(&disable_lock);
 }
 
-/**
- * uv_flush_send_and_wait
- *
+static void count_max_concurr(int stat, struct bau_control *bcp,
+				struct bau_control *hmaster)
+{
+	bcp->plugged_tries = 0;
+	bcp->timeout_tries = 0;
+	if (stat != FLUSH_COMPLETE)
+		return;
+	if (bcp->conseccompletes <= bcp->complete_threshold)
+		return;
+	if (hmaster->max_concurr >= hmaster->max_concurr_const)
+		return;
+	hmaster->max_concurr++;
+}
+
+static void record_send_stats(cycles_t time1, cycles_t time2,
+		struct bau_control *bcp, struct ptc_stats *stat,
+		int completion_status, int try)
+{
+	cycles_t elapsed;
+
+	if (time2 > time1) {
+		elapsed = time2 - time1;
+		stat->s_time += elapsed;
+
+		if ((completion_status == FLUSH_COMPLETE) && (try == 1)) {
+			bcp->period_requests++;
+			bcp->period_time += elapsed;
+			if ((elapsed > congested_cycles) &&
+			    (bcp->period_requests > bcp->cong_reps))
+				disable_for_congestion(bcp, stat);
+		}
+	} else
+		stat->s_requestor--;
+
+	if (completion_status == FLUSH_COMPLETE && try > 1)
+		stat->s_retriesok++;
+	else if (completion_status == FLUSH_GIVEUP)
+		stat->s_giveup++;
+}
+
+/*
+ * Because of a uv1 hardware bug only a limited number of concurrent
+ * requests can be made.
+ */
+static void uv1_throttle(struct bau_control *hmaster, struct ptc_stats *stat)
+{
+	spinlock_t *lock = &hmaster->uvhub_lock;
+	atomic_t *v;
+
+	v = &hmaster->active_descriptor_count;
+	if (!atomic_inc_unless_ge(lock, v, hmaster->max_concurr)) {
+		stat->s_throttles++;
+		do {
+			cpu_relax();
+		} while (!atomic_inc_unless_ge(lock, v, hmaster->max_concurr));
+	}
+}
+
+/*
+ * Handle the completion status of a message send.
+ */
+static void handle_cmplt(int completion_status, struct bau_desc *bau_desc,
+			struct bau_control *bcp, struct bau_control *hmaster,
+			struct ptc_stats *stat)
+{
+	if (completion_status == FLUSH_RETRY_PLUGGED)
+		destination_plugged(bau_desc, bcp, hmaster, stat);
+	else if (completion_status == FLUSH_RETRY_TIMEOUT)
+		destination_timeout(bau_desc, bcp, hmaster, stat);
+}
+
+/*
  * Send a broadcast and wait for it to complete.
  *
  * The flush_mask contains the cpus the broadcast is to be sent to including
@@ -568,44 +748,23 @@ disable_for_congestion(struct bau_control *bcp, struct ptc_stats *stat)
  * returned to the kernel.
  */
 int uv_flush_send_and_wait(struct bau_desc *bau_desc,
-			   struct cpumask *flush_mask, struct bau_control *bcp)
+			struct cpumask *flush_mask, struct bau_control *bcp)
 {
-	int right_shift;
-	int completion_status = 0;
 	int seq_number = 0;
+	int completion_stat = 0;
 	long try = 0;
-	int cpu = bcp->uvhub_cpu;
-	int this_cpu = bcp->cpu;
-	unsigned long mmr_offset;
 	unsigned long index;
 	cycles_t time1;
 	cycles_t time2;
-	cycles_t elapsed;
 	struct ptc_stats *stat = bcp->statp;
-	struct bau_control *smaster = bcp->socket_master;
 	struct bau_control *hmaster = bcp->uvhub_master;
 
-	if (!atomic_inc_unless_ge(&hmaster->uvhub_lock,
-			&hmaster->active_descriptor_count,
-			hmaster->max_bau_concurrent)) {
-		stat->s_throttles++;
-		do {
-			cpu_relax();
-		} while (!atomic_inc_unless_ge(&hmaster->uvhub_lock,
-			&hmaster->active_descriptor_count,
-			hmaster->max_bau_concurrent));
-	}
+	if (is_uv1_hub())
+		uv1_throttle(hmaster, stat);
+
 	while (hmaster->uvhub_quiesce)
 		cpu_relax();
 
-	if (cpu < UV_CPUS_PER_ACT_STATUS) {
-		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
-		right_shift = cpu * UV_ACT_STATUS_SIZE;
-	} else {
-		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
-		right_shift =
-		    ((cpu - UV_CPUS_PER_ACT_STATUS) * UV_ACT_STATUS_SIZE);
-	}
 	time1 = get_cycles();
 	do {
 		if (try == 0) {
@@ -615,64 +774,134 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
 			bau_desc->header.msg_type = MSG_RETRY;
 			stat->s_retry_messages++;
 		}
+
 		bau_desc->header.sequence = seq_number;
-		index = (1UL << UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT) |
-			bcp->uvhub_cpu;
+		index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu;
 		bcp->send_message = get_cycles();
-		uv_write_local_mmr(UVH_LB_BAU_SB_ACTIVATION_CONTROL, index);
+
+		write_mmr_activation(index);
+
 		try++;
-		completion_status = uv_wait_completion(bau_desc, mmr_offset,
-			right_shift, this_cpu, bcp, smaster, try);
+		completion_stat = wait_completion(bau_desc, bcp, try);
+
+		handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat);
 
-		if (completion_status == FLUSH_RETRY_PLUGGED) {
-			destination_plugged(bau_desc, bcp, hmaster, stat);
-		} else if (completion_status == FLUSH_RETRY_TIMEOUT) {
-			destination_timeout(bau_desc, bcp, hmaster, stat);
-		}
 		if (bcp->ipi_attempts >= bcp->ipi_reset_limit) {
 			bcp->ipi_attempts = 0;
-			completion_status = FLUSH_GIVEUP;
+			completion_stat = FLUSH_GIVEUP;
 			break;
 		}
 		cpu_relax();
-	} while ((completion_status == FLUSH_RETRY_PLUGGED) ||
-		 (completion_status == FLUSH_RETRY_TIMEOUT));
+	} while ((completion_stat == FLUSH_RETRY_PLUGGED) ||
+		 (completion_stat == FLUSH_RETRY_TIMEOUT));
+
 	time2 = get_cycles();
-	bcp->plugged_tries = 0;
-	bcp->timeout_tries = 0;
-	if ((completion_status == FLUSH_COMPLETE) &&
-	    (bcp->conseccompletes > bcp->complete_threshold) &&
-	    (hmaster->max_bau_concurrent <
-					hmaster->max_bau_concurrent_constant))
-			hmaster->max_bau_concurrent++;
+
+	count_max_concurr(completion_stat, bcp, hmaster);
+
 	while (hmaster->uvhub_quiesce)
 		cpu_relax();
+
 	atomic_dec(&hmaster->active_descriptor_count);
-	if (time2 > time1) {
-		elapsed = time2 - time1;
-		stat->s_time += elapsed;
-		if ((completion_status == FLUSH_COMPLETE) && (try == 1)) {
-			bcp->period_requests++;
-			bcp->period_time += elapsed;
-			if ((elapsed > congested_cycles) &&
-			    (bcp->period_requests > bcp->congested_reps)) {
-				disable_for_congestion(bcp, stat);
+
+	record_send_stats(time1, time2, bcp, stat, completion_stat, try);
+
+	if (completion_stat == FLUSH_GIVEUP)
+		return 1;
+	return 0;
+}
+
+/*
+ * The BAU is disabled. When the disabled time period has expired, the cpu
+ * that disabled it must re-enable it.
+ * Return 0 if it is re-enabled for all cpus.
+ */
+static int check_enable(struct bau_control *bcp, struct ptc_stats *stat)
+{
+	int tcpu;
+	struct bau_control *tbcp;
+
+	if (bcp->set_bau_off) {
+		if (get_cycles() >= bcp->set_bau_on_time) {
+			stat->s_bau_reenabled++;
+			baudisabled = 0;
+			for_each_present_cpu(tcpu) {
+				tbcp = &per_cpu(bau_control, tcpu);
+				tbcp->baudisabled = 0;
+				tbcp->period_requests = 0;
+				tbcp->period_time = 0;
 			}
+			return 0;
 		}
+	}
+	return -1;
+}
+
+static void record_send_statistics(struct ptc_stats *stat, int locals, int hubs,
+				int remotes, struct bau_desc *bau_desc)
+{
+	stat->s_requestor++;
+	stat->s_ntargcpu += remotes + locals;
+	stat->s_ntargremotes += remotes;
+	stat->s_ntarglocals += locals;
+
+	/* uvhub statistics */
+	hubs = bau_uvhub_weight(&bau_desc->distribution);
+	if (locals) {
+		stat->s_ntarglocaluvhub++;
+		stat->s_ntargremoteuvhub += (hubs - 1);
 	} else
-		stat->s_requestor--;
-	if (completion_status == FLUSH_COMPLETE && try > 1)
-		stat->s_retriesok++;
-	else if (completion_status == FLUSH_GIVEUP) {
-		stat->s_giveup++;
-		return 1;
+		stat->s_ntargremoteuvhub += hubs;
+
+	stat->s_ntarguvhub += hubs;
+
+	if (hubs >= 16)
+		stat->s_ntarguvhub16++;
+	else if (hubs >= 8)
+		stat->s_ntarguvhub8++;
+	else if (hubs >= 4)
+		stat->s_ntarguvhub4++;
+	else if (hubs >= 2)
+		stat->s_ntarguvhub2++;
+	else
+		stat->s_ntarguvhub1++;
+}
+
+/*
+ * Translate a cpu mask to the uvhub distribution mask in the BAU
+ * activation descriptor.
+ */
+static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp,
+			struct bau_desc *bau_desc, int *localsp, int *remotesp)
+{
+	int cpu;
+	int pnode;
+	int cnt = 0;
+	struct hub_and_pnode *hpp;
+
+	for_each_cpu(cpu, flush_mask) {
+		/*
+		 * The distribution vector is a bit map of pnodes, relative
+		 * to the partition base pnode (and the partition base nasid
+		 * in the header).
+		 * Translate cpu to pnode and hub using a local memory array.
+		 */
+		hpp = &bcp->socket_master->thp[cpu];
+		pnode = hpp->pnode - bcp->partition_base_pnode;
+		bau_uvhub_set(pnode, &bau_desc->distribution);
+		cnt++;
+		if (hpp->uvhub == bcp->uvhub)
+			(*localsp)++;
+		else
+			(*remotesp)++;
 	}
+	if (!cnt)
+		return 1;
 	return 0;
 }
 
-/**
- * uv_flush_tlb_others - globally purge translation cache of a virtual
- * address or all TLB's
+/*
+ * globally purge translation cache of a virtual address or all TLB's
  * @cpumask: mask of all cpu's in which the address is to be removed
  * @mm: mm_struct containing virtual address range
  * @va: virtual address to be removed (or TLB_FLUSH_ALL for all TLB's on cpu)
@@ -696,20 +925,16 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
  * done.  The returned pointer is valid till preemption is re-enabled.
  */
 const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
-					  struct mm_struct *mm,
-					  unsigned long va, unsigned int cpu)
+				struct mm_struct *mm, unsigned long va,
+				unsigned int cpu)
 {
 	int locals = 0;
 	int remotes = 0;
 	int hubs = 0;
-	int tcpu;
-	int tpnode;
 	struct bau_desc *bau_desc;
 	struct cpumask *flush_mask;
 	struct ptc_stats *stat;
 	struct bau_control *bcp;
-	struct bau_control *tbcp;
-	struct hub_and_pnode *hpp;
 
 	/* kernel was booted 'nobau' */
 	if (nobau)
@@ -720,20 +945,8 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 
 	/* bau was disabled due to slow response */
 	if (bcp->baudisabled) {
-		/* the cpu that disabled it must re-enable it */
-		if (bcp->set_bau_off) {
-			if (get_cycles() >= bcp->set_bau_on_time) {
-				stat->s_bau_reenabled++;
-				baudisabled = 0;
-				for_each_present_cpu(tcpu) {
-					tbcp = &per_cpu(bau_control, tcpu);
-					tbcp->baudisabled = 0;
-					tbcp->period_requests = 0;
-					tbcp->period_time = 0;
-				}
-			}
-		}
-		return cpumask;
+		if (check_enable(bcp, stat))
+			return cpumask;
 	}
 
 	/*
@@ -744,59 +957,20 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 	flush_mask = (struct cpumask *)per_cpu(uv_flush_tlb_mask, cpu);
 	/* don't actually do a shootdown of the local cpu */
 	cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu));
+
 	if (cpu_isset(cpu, *cpumask))
 		stat->s_ntargself++;
 
 	bau_desc = bcp->descriptor_base;
-	bau_desc += UV_ITEMS_PER_DESCRIPTOR * bcp->uvhub_cpu;
+	bau_desc += ITEMS_PER_DESC * bcp->uvhub_cpu;
 	bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
-
-	for_each_cpu(tcpu, flush_mask) {
-		/*
-		 * The distribution vector is a bit map of pnodes, relative
-		 * to the partition base pnode (and the partition base nasid
-		 * in the header).
-		 * Translate cpu to pnode and hub using an array stored
-		 * in local memory.
-		 */
-		hpp = &bcp->socket_master->target_hub_and_pnode[tcpu];
-		tpnode = hpp->pnode - bcp->partition_base_pnode;
-		bau_uvhub_set(tpnode, &bau_desc->distribution);
-		if (hpp->uvhub == bcp->uvhub)
-			locals++;
-		else
-			remotes++;
-	}
-	if ((locals + remotes) == 0)
+	if (set_distrib_bits(flush_mask, bcp, bau_desc, &locals, &remotes))
 		return NULL;
-	stat->s_requestor++;
-	stat->s_ntargcpu += remotes + locals;
-	stat->s_ntargremotes += remotes;
-	stat->s_ntarglocals += locals;
-	remotes = bau_uvhub_weight(&bau_desc->distribution);
 
-	/* uvhub statistics */
-	hubs = bau_uvhub_weight(&bau_desc->distribution);
-	if (locals) {
-		stat->s_ntarglocaluvhub++;
-		stat->s_ntargremoteuvhub += (hubs - 1);
-	} else
-		stat->s_ntargremoteuvhub += hubs;
-	stat->s_ntarguvhub += hubs;
-	if (hubs >= 16)
-		stat->s_ntarguvhub16++;
-	else if (hubs >= 8)
-		stat->s_ntarguvhub8++;
-	else if (hubs >= 4)
-		stat->s_ntarguvhub4++;
-	else if (hubs >= 2)
-		stat->s_ntarguvhub2++;
-	else
-		stat->s_ntarguvhub1++;
+	record_send_statistics(stat, locals, hubs, remotes, bau_desc);
 
 	bau_desc->payload.address = va;
 	bau_desc->payload.sending_cpu = cpu;
-
 	/*
 	 * uv_flush_send_and_wait returns 0 if all cpu's were messaged,
 	 * or 1 if it gave up and the original cpumask should be returned.
@@ -825,26 +999,31 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
 {
 	int count = 0;
 	cycles_t time_start;
-	struct bau_payload_queue_entry *msg;
+	struct bau_pq_entry *msg;
 	struct bau_control *bcp;
 	struct ptc_stats *stat;
 	struct msg_desc msgdesc;
 
 	time_start = get_cycles();
+
 	bcp = &per_cpu(bau_control, smp_processor_id());
 	stat = bcp->statp;
-	msgdesc.va_queue_first = bcp->va_queue_first;
-	msgdesc.va_queue_last = bcp->va_queue_last;
+
+	msgdesc.queue_first = bcp->queue_first;
+	msgdesc.queue_last = bcp->queue_last;
+
 	msg = bcp->bau_msg_head;
-	while (msg->sw_ack_vector) {
+	while (msg->swack_vec) {
 		count++;
-		msgdesc.msg_slot = msg - msgdesc.va_queue_first;
-		msgdesc.sw_ack_slot = ffs(msg->sw_ack_vector) - 1;
+
+		msgdesc.msg_slot = msg - msgdesc.queue_first;
+		msgdesc.swack_slot = ffs(msg->swack_vec) - 1;
 		msgdesc.msg = msg;
-		uv_bau_process_message(&msgdesc, bcp);
+		bau_process_message(&msgdesc, bcp);
+
 		msg++;
-		if (msg > msgdesc.va_queue_last)
-			msg = msgdesc.va_queue_first;
+		if (msg > msgdesc.queue_last)
+			msg = msgdesc.queue_first;
 		bcp->bau_msg_head = msg;
 	}
 	stat->d_time += (get_cycles() - time_start);
@@ -852,18 +1031,17 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
 		stat->d_nomsg++;
 	else if (count > 1)
 		stat->d_multmsg++;
+
 	ack_APIC_irq();
 }
 
 /*
- * uv_enable_timeouts
- *
- * Each target uvhub (i.e. a uvhub that has no cpu's) needs to have
+ * Each target uvhub (i.e. a uvhub that has cpu's) needs to have
  * shootdown message timeouts enabled.  The timeout does not cause
  * an interrupt, but causes an error message to be returned to
  * the sender.
  */
-static void __init uv_enable_timeouts(void)
+static void __init enable_timeouts(void)
 {
 	int uvhub;
 	int nuvhubs;
@@ -877,47 +1055,44 @@ static void __init uv_enable_timeouts(void)
 			continue;
 
 		pnode = uv_blade_to_pnode(uvhub);
-		mmr_image =
-		    uv_read_global_mmr64(pnode, UVH_LB_BAU_MISC_CONTROL);
+		mmr_image = read_mmr_misc_control(pnode);
 		/*
 		 * Set the timeout period and then lock it in, in three
 		 * steps; captures and locks in the period.
 		 *
 		 * To program the period, the SOFT_ACK_MODE must be off.
 		 */
-		mmr_image &= ~((unsigned long)1 <<
-		    UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT);
-		uv_write_global_mmr64
-		    (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
+		mmr_image &= ~(1L << SOFTACK_MSHIFT);
+		write_mmr_misc_control(pnode, mmr_image);
 		/*
 		 * Set the 4-bit period.
 		 */
-		mmr_image &= ~((unsigned long)0xf <<
-		     UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT);
-		mmr_image |= (UV_INTD_SOFT_ACK_TIMEOUT_PERIOD <<
-		     UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT);
-		uv_write_global_mmr64
-		    (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
+		mmr_image &= ~((unsigned long)0xf << SOFTACK_PSHIFT);
+		mmr_image |= (SOFTACK_TIMEOUT_PERIOD << SOFTACK_PSHIFT);
+		write_mmr_misc_control(pnode, mmr_image);
 		/*
+		 * UV1:
 		 * Subsequent reversals of the timebase bit (3) cause an
 		 * immediate timeout of one or all INTD resources as
 		 * indicated in bits 2:0 (7 causes all of them to timeout).
 		 */
-		mmr_image |= ((unsigned long)1 <<
-		    UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT);
-		uv_write_global_mmr64
-		    (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
+		mmr_image |= (1L << SOFTACK_MSHIFT);
+		if (is_uv2_hub()) {
+			mmr_image |= (1L << UV2_LEG_SHFT);
+			mmr_image |= (1L << UV2_EXT_SHFT);
+		}
+		write_mmr_misc_control(pnode, mmr_image);
 	}
 }
 
-static void *uv_ptc_seq_start(struct seq_file *file, loff_t *offset)
+static void *ptc_seq_start(struct seq_file *file, loff_t *offset)
 {
 	if (*offset < num_possible_cpus())
 		return offset;
 	return NULL;
 }
 
-static void *uv_ptc_seq_next(struct seq_file *file, void *data, loff_t *offset)
+static void *ptc_seq_next(struct seq_file *file, void *data, loff_t *offset)
 {
 	(*offset)++;
 	if (*offset < num_possible_cpus())
@@ -925,12 +1100,11 @@ static void *uv_ptc_seq_next(struct seq_file *file, void *data, loff_t *offset)
 	return NULL;
 }
 
-static void uv_ptc_seq_stop(struct seq_file *file, void *data)
+static void ptc_seq_stop(struct seq_file *file, void *data)
 {
 }
 
-static inline unsigned long long
-microsec_2_cycles(unsigned long microsec)
+static inline unsigned long long usec_2_cycles(unsigned long microsec)
 {
 	unsigned long ns;
 	unsigned long long cyc;
@@ -941,29 +1115,27 @@ microsec_2_cycles(unsigned long microsec)
 }
 
 /*
- * Display the statistics thru /proc.
+ * Display the statistics thru /proc/sgi_uv/ptc_statistics
  * 'data' points to the cpu number
+ * Note: see the descriptions in stat_description[].
  */
-static int uv_ptc_seq_show(struct seq_file *file, void *data)
+static int ptc_seq_show(struct seq_file *file, void *data)
 {
 	struct ptc_stats *stat;
 	int cpu;
 
 	cpu = *(loff_t *)data;
-
 	if (!cpu) {
 		seq_printf(file,
 			"# cpu sent stime self locals remotes ncpus localhub ");
 		seq_printf(file,
 			"remotehub numuvhubs numuvhubs16 numuvhubs8 ");
 		seq_printf(file,
-			"numuvhubs4 numuvhubs2 numuvhubs1 dto ");
-		seq_printf(file,
-			"retries rok resetp resett giveup sto bz throt ");
+			"numuvhubs4 numuvhubs2 numuvhubs1 dto retries rok ");
 		seq_printf(file,
-			"sw_ack recv rtime all ");
+			"resetp resett giveup sto bz throt swack recv rtime ");
 		seq_printf(file,
-			"one mult none retry canc nocan reset rcan ");
+			"all one mult none retry canc nocan reset rcan ");
 		seq_printf(file,
 			"disable enable\n");
 	}
@@ -990,8 +1162,7 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data)
 		/* destination side statistics */
 		seq_printf(file,
 			   "%lx %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ",
-			   uv_read_global_mmr64(uv_cpu_to_pnode(cpu),
-					UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE),
+			   read_gmmr_sw_ack(uv_cpu_to_pnode(cpu)),
 			   stat->d_requestee, cycles_2_us(stat->d_time),
 			   stat->d_alltlb, stat->d_onetlb, stat->d_multmsg,
 			   stat->d_nomsg, stat->d_retries, stat->d_canceled,
@@ -1000,7 +1171,6 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data)
 		seq_printf(file, "%ld %ld\n",
 			stat->s_bau_disabled, stat->s_bau_reenabled);
 	}
-
 	return 0;
 }
 
@@ -1008,18 +1178,18 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data)
  * Display the tunables thru debugfs
  */
 static ssize_t tunables_read(struct file *file, char __user *userbuf,
-						size_t count, loff_t *ppos)
+				size_t count, loff_t *ppos)
 {
 	char *buf;
 	int ret;
 
 	buf = kasprintf(GFP_KERNEL, "%s %s %s\n%d %d %d %d %d %d %d %d %d\n",
-		"max_bau_concurrent plugged_delay plugsb4reset",
+		"max_concur plugged_delay plugsb4reset",
 		"timeoutsb4reset ipi_reset_limit complete_threshold",
 		"congested_response_us congested_reps congested_period",
-		max_bau_concurrent, plugged_delay, plugsb4reset,
+		max_concurr, plugged_delay, plugsb4reset,
 		timeoutsb4reset, ipi_reset_limit, complete_threshold,
-		congested_response_us, congested_reps, congested_period);
+		congested_respns_us, congested_reps, congested_period);
 
 	if (!buf)
 		return -ENOMEM;
@@ -1030,13 +1200,16 @@ static ssize_t tunables_read(struct file *file, char __user *userbuf,
 }
 
 /*
- * -1: resetf the statistics
+ * handle a write to /proc/sgi_uv/ptc_statistics
+ * -1: reset the statistics
  *  0: display meaning of the statistics
  */
-static ssize_t uv_ptc_proc_write(struct file *file, const char __user *user,
-				 size_t count, loff_t *data)
+static ssize_t ptc_proc_write(struct file *file, const char __user *user,
+				size_t count, loff_t *data)
 {
 	int cpu;
+	int i;
+	int elements;
 	long input_arg;
 	char optstr[64];
 	struct ptc_stats *stat;
@@ -1046,79 +1219,18 @@ static ssize_t uv_ptc_proc_write(struct file *file, const char __user *user,
 	if (copy_from_user(optstr, user, count))
 		return -EFAULT;
 	optstr[count - 1] = '\0';
+
 	if (strict_strtol(optstr, 10, &input_arg) < 0) {
 		printk(KERN_DEBUG "%s is invalid\n", optstr);
 		return -EINVAL;
 	}
 
 	if (input_arg == 0) {
+		elements = sizeof(stat_description)/sizeof(*stat_description);
 		printk(KERN_DEBUG "# cpu:      cpu number\n");
 		printk(KERN_DEBUG "Sender statistics:\n");
-		printk(KERN_DEBUG
-		"sent:     number of shootdown messages sent\n");
-		printk(KERN_DEBUG
-		"stime:    time spent sending messages\n");
-		printk(KERN_DEBUG
-		"numuvhubs: number of hubs targeted with shootdown\n");
-		printk(KERN_DEBUG
-		"numuvhubs16: number times 16 or more hubs targeted\n");
-		printk(KERN_DEBUG
-		"numuvhubs8: number times 8 or more hubs targeted\n");
-		printk(KERN_DEBUG
-		"numuvhubs4: number times 4 or more hubs targeted\n");
-		printk(KERN_DEBUG
-		"numuvhubs2: number times 2 or more hubs targeted\n");
-		printk(KERN_DEBUG
-		"numuvhubs1: number times 1 hub targeted\n");
-		printk(KERN_DEBUG
-		"numcpus:  number of cpus targeted with shootdown\n");
-		printk(KERN_DEBUG
-		"dto:      number of destination timeouts\n");
-		printk(KERN_DEBUG
-		"retries:  destination timeout retries sent\n");
-		printk(KERN_DEBUG
-		"rok:   :  destination timeouts successfully retried\n");
-		printk(KERN_DEBUG
-		"resetp:   ipi-style resource resets for plugs\n");
-		printk(KERN_DEBUG
-		"resett:   ipi-style resource resets for timeouts\n");
-		printk(KERN_DEBUG
-		"giveup:   fall-backs to ipi-style shootdowns\n");
-		printk(KERN_DEBUG
-		"sto:      number of source timeouts\n");
-		printk(KERN_DEBUG
-		"bz:       number of stay-busy's\n");
-		printk(KERN_DEBUG
-		"throt:    number times spun in throttle\n");
-		printk(KERN_DEBUG "Destination side statistics:\n");
-		printk(KERN_DEBUG
-		"sw_ack:   image of UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE\n");
-		printk(KERN_DEBUG
-		"recv:     shootdown messages received\n");
-		printk(KERN_DEBUG
-		"rtime:    time spent processing messages\n");
-		printk(KERN_DEBUG
-		"all:      shootdown all-tlb messages\n");
-		printk(KERN_DEBUG
-		"one:      shootdown one-tlb messages\n");
-		printk(KERN_DEBUG
-		"mult:     interrupts that found multiple messages\n");
-		printk(KERN_DEBUG
-		"none:     interrupts that found no messages\n");
-		printk(KERN_DEBUG
-		"retry:    number of retry messages processed\n");
-		printk(KERN_DEBUG
-		"canc:     number messages canceled by retries\n");
-		printk(KERN_DEBUG
-		"nocan:    number retries that found nothing to cancel\n");
-		printk(KERN_DEBUG
-		"reset:    number of ipi-style reset requests processed\n");
-		printk(KERN_DEBUG
-		"rcan:     number messages canceled by reset requests\n");
-		printk(KERN_DEBUG
-		"disable:  number times use of the BAU was disabled\n");
-		printk(KERN_DEBUG
-		"enable:   number times use of the BAU was re-enabled\n");
+		for (i = 0; i < elements; i++)
+			printk(KERN_DEBUG "%s\n", stat_description[i]);
 	} else if (input_arg == -1) {
 		for_each_present_cpu(cpu) {
 			stat = &per_cpu(ptcstats, cpu);
@@ -1145,27 +1257,18 @@ static int local_atoi(const char *name)
 }
 
 /*
- * set the tunables
- * 0 values reset them to defaults
+ * Parse the values written to /sys/kernel/debug/sgi_uv/bau_tunables.
+ * Zero values reset them to defaults.
  */
-static ssize_t tunables_write(struct file *file, const char __user *user,
-				 size_t count, loff_t *data)
+static int parse_tunables_write(struct bau_control *bcp, char *instr,
+				int count)
 {
-	int cpu;
-	int cnt = 0;
-	int val;
 	char *p;
 	char *q;
-	char instr[64];
-	struct bau_control *bcp;
-
-	if (count == 0 || count > sizeof(instr)-1)
-		return -EINVAL;
-	if (copy_from_user(instr, user, count))
-		return -EFAULT;
+	int cnt = 0;
+	int val;
+	int e = sizeof(tunables) / sizeof(*tunables);
 
-	instr[count] = '\0';
-	/* count the fields */
 	p = instr + strspn(instr, WHITESPACE);
 	q = p;
 	for (; *p; p = q + strspn(q, WHITESPACE)) {
@@ -1174,8 +1277,8 @@ static ssize_t tunables_write(struct file *file, const char __user *user,
 		if (q == p)
 			break;
 	}
-	if (cnt != 9) {
-		printk(KERN_INFO "bau tunable error: should be 9 numbers\n");
+	if (cnt != e) {
+		printk(KERN_INFO "bau tunable error: should be %d values\n", e);
 		return -EINVAL;
 	}
 
@@ -1187,97 +1290,80 @@ static ssize_t tunables_write(struct file *file, const char __user *user,
 		switch (cnt) {
 		case 0:
 			if (val == 0) {
-				max_bau_concurrent = MAX_BAU_CONCURRENT;
-				max_bau_concurrent_constant =
-							MAX_BAU_CONCURRENT;
+				max_concurr = MAX_BAU_CONCURRENT;
+				max_concurr_const = MAX_BAU_CONCURRENT;
 				continue;
 			}
-			bcp = &per_cpu(bau_control, smp_processor_id());
 			if (val < 1 || val > bcp->cpus_in_uvhub) {
 				printk(KERN_DEBUG
 				"Error: BAU max concurrent %d is invalid\n",
 				val);
 				return -EINVAL;
 			}
-			max_bau_concurrent = val;
-			max_bau_concurrent_constant = val;
-			continue;
-		case 1:
-			if (val == 0)
-				plugged_delay = PLUGGED_DELAY;
-			else
-				plugged_delay = val;
-			continue;
-		case 2:
-			if (val == 0)
-				plugsb4reset = PLUGSB4RESET;
-			else
-				plugsb4reset = val;
-			continue;
-		case 3:
-			if (val == 0)
-				timeoutsb4reset = TIMEOUTSB4RESET;
-			else
-				timeoutsb4reset = val;
-			continue;
-		case 4:
-			if (val == 0)
-				ipi_reset_limit = IPI_RESET_LIMIT;
-			else
-				ipi_reset_limit = val;
-			continue;
-		case 5:
-			if (val == 0)
-				complete_threshold = COMPLETE_THRESHOLD;
-			else
-				complete_threshold = val;
-			continue;
-		case 6:
-			if (val == 0)
-				congested_response_us = CONGESTED_RESPONSE_US;
-			else
-				congested_response_us = val;
-			continue;
-		case 7:
-			if (val == 0)
-				congested_reps = CONGESTED_REPS;
-			else
-				congested_reps = val;
+			max_concurr = val;
+			max_concurr_const = val;
 			continue;
-		case 8:
+		default:
 			if (val == 0)
-				congested_period = CONGESTED_PERIOD;
+				*tunables[cnt].tunp = tunables[cnt].deflt;
 			else
-				congested_period = val;
+				*tunables[cnt].tunp = val;
 			continue;
 		}
 		if (q == p)
 			break;
 	}
+	return 0;
+}
+
+/*
+ * Handle a write to debugfs. (/sys/kernel/debug/sgi_uv/bau_tunables)
+ */
+static ssize_t tunables_write(struct file *file, const char __user *user,
+				size_t count, loff_t *data)
+{
+	int cpu;
+	int ret;
+	char instr[100];
+	struct bau_control *bcp;
+
+	if (count == 0 || count > sizeof(instr)-1)
+		return -EINVAL;
+	if (copy_from_user(instr, user, count))
+		return -EFAULT;
+
+	instr[count] = '\0';
+
+	bcp = &per_cpu(bau_control, smp_processor_id());
+
+	ret = parse_tunables_write(bcp, instr, count);
+	if (ret)
+		return ret;
+
 	for_each_present_cpu(cpu) {
 		bcp = &per_cpu(bau_control, cpu);
-		bcp->max_bau_concurrent = max_bau_concurrent;
-		bcp->max_bau_concurrent_constant = max_bau_concurrent;
-		bcp->plugged_delay = plugged_delay;
-		bcp->plugsb4reset = plugsb4reset;
-		bcp->timeoutsb4reset = timeoutsb4reset;
-		bcp->ipi_reset_limit = ipi_reset_limit;
-		bcp->complete_threshold = complete_threshold;
-		bcp->congested_response_us = congested_response_us;
-		bcp->congested_reps = congested_reps;
-		bcp->congested_period = congested_period;
+		bcp->max_concurr =		max_concurr;
+		bcp->max_concurr_const =	max_concurr;
+		bcp->plugged_delay =		plugged_delay;
+		bcp->plugsb4reset =		plugsb4reset;
+		bcp->timeoutsb4reset =		timeoutsb4reset;
+		bcp->ipi_reset_limit =		ipi_reset_limit;
+		bcp->complete_threshold =	complete_threshold;
+		bcp->cong_response_us =		congested_respns_us;
+		bcp->cong_reps =		congested_reps;
+		bcp->cong_period =		congested_period;
 	}
 	return count;
 }
 
 static const struct seq_operations uv_ptc_seq_ops = {
-	.start		= uv_ptc_seq_start,
-	.next		= uv_ptc_seq_next,
-	.stop		= uv_ptc_seq_stop,
-	.show		= uv_ptc_seq_show
+	.start		= ptc_seq_start,
+	.next		= ptc_seq_next,
+	.stop		= ptc_seq_stop,
+	.show		= ptc_seq_show
 };
 
-static int uv_ptc_proc_open(struct inode *inode, struct file *file)
+static int ptc_proc_open(struct inode *inode, struct file *file)
 {
 	return seq_open(file, &uv_ptc_seq_ops);
 }
@@ -1288,9 +1374,9 @@ static int tunables_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations proc_uv_ptc_operations = {
-	.open		= uv_ptc_proc_open,
+	.open		= ptc_proc_open,
 	.read		= seq_read,
-	.write		= uv_ptc_proc_write,
+	.write		= ptc_proc_write,
 	.llseek		= seq_lseek,
 	.release	= seq_release,
 };
@@ -1324,7 +1410,7 @@ static int __init uv_ptc_init(void)
 		return -EINVAL;
 	}
 	tunables_file = debugfs_create_file(UV_BAU_TUNABLES_FILE, 0600,
-			tunables_dir, NULL, &tunables_fops);
+					tunables_dir, NULL, &tunables_fops);
 	if (!tunables_file) {
 		printk(KERN_ERR "unable to create debugfs file %s\n",
 		       UV_BAU_TUNABLES_FILE);
@@ -1336,24 +1422,24 @@ static int __init uv_ptc_init(void)
 /*
  * Initialize the sending side's sending buffers.
  */
-static void
-uv_activation_descriptor_init(int node, int pnode, int base_pnode)
+static void activation_descriptor_init(int node, int pnode, int base_pnode)
 {
 	int i;
 	int cpu;
 	unsigned long pa;
 	unsigned long m;
 	unsigned long n;
+	size_t dsize;
 	struct bau_desc *bau_desc;
 	struct bau_desc *bd2;
 	struct bau_control *bcp;
 
 	/*
-	 * each bau_desc is 64 bytes; there are 8 (UV_ITEMS_PER_DESCRIPTOR)
-	 * per cpu; and one per cpu on the uvhub (UV_ADP_SIZE)
+	 * each bau_desc is 64 bytes; there are 8 (ITEMS_PER_DESC)
+	 * per cpu; and one per cpu on the uvhub (ADP_SZ)
 	 */
-	bau_desc = kmalloc_node(sizeof(struct bau_desc) * UV_ADP_SIZE
-				* UV_ITEMS_PER_DESCRIPTOR, GFP_KERNEL, node);
+	dsize = sizeof(struct bau_desc) * ADP_SZ * ITEMS_PER_DESC;
+	bau_desc = kmalloc_node(dsize, GFP_KERNEL, node);
 	BUG_ON(!bau_desc);
 
 	pa = uv_gpa(bau_desc); /* need the real nasid*/
@@ -1361,27 +1447,25 @@ uv_activation_descriptor_init(int node, int pnode, int base_pnode)
 	m = pa & uv_mmask;
 
 	/* the 14-bit pnode */
-	uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE,
-			      (n << UV_DESC_BASE_PNODE_SHIFT | m));
+	write_mmr_descriptor_base(pnode, (n << UV_DESC_PSHIFT | m));
 	/*
-	 * Initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each
+	 * Initializing all 8 (ITEMS_PER_DESC) descriptors for each
 	 * cpu even though we only use the first one; one descriptor can
 	 * describe a broadcast to 256 uv hubs.
 	 */
-	for (i = 0, bd2 = bau_desc; i < (UV_ADP_SIZE*UV_ITEMS_PER_DESCRIPTOR);
-		i++, bd2++) {
+	for (i = 0, bd2 = bau_desc; i < (ADP_SZ * ITEMS_PER_DESC); i++, bd2++) {
 		memset(bd2, 0, sizeof(struct bau_desc));
-		bd2->header.sw_ack_flag = 1;
+		bd2->header.swack_flag =	1;
 		/*
 		 * The base_dest_nasid set in the message header is the nasid
 		 * of the first uvhub in the partition. The bit map will
 		 * indicate destination pnode numbers relative to that base.
 		 * They may not be consecutive if nasid striding is being used.
 		 */
-		bd2->header.base_dest_nasid = UV_PNODE_TO_NASID(base_pnode);
-		bd2->header.dest_subnodeid = UV_LB_SUBNODEID;
-		bd2->header.command = UV_NET_ENDPOINT_INTD;
-		bd2->header.int_both = 1;
+		bd2->header.base_dest_nasid =	UV_PNODE_TO_NASID(base_pnode);
+		bd2->header.dest_subnodeid =	UV_LB_SUBNODEID;
+		bd2->header.command =		UV_NET_ENDPOINT_INTD;
+		bd2->header.int_both =		1;
 		/*
 		 * all others need to be set to zero:
 		 *   fairness chaining multilevel count replied_to
@@ -1401,57 +1485,55 @@ uv_activation_descriptor_init(int node, int pnode, int base_pnode)
  * - node is first node (kernel memory notion) on the uvhub
  * - pnode is the uvhub's physical identifier
  */
-static void
-uv_payload_queue_init(int node, int pnode)
+static void pq_init(int node, int pnode)
 {
-	int pn;
 	int cpu;
+	size_t plsize;
 	char *cp;
-	unsigned long pa;
-	struct bau_payload_queue_entry *pqp;
-	struct bau_payload_queue_entry *pqp_malloc;
+	void *vp;
+	unsigned long pn;
+	unsigned long first;
+	unsigned long pn_first;
+	unsigned long last;
+	struct bau_pq_entry *pqp;
 	struct bau_control *bcp;
 
-	pqp = kmalloc_node((DEST_Q_SIZE + 1)
-			   * sizeof(struct bau_payload_queue_entry),
-			   GFP_KERNEL, node);
+	plsize = (DEST_Q_SIZE + 1) * sizeof(struct bau_pq_entry);
+	vp = kmalloc_node(plsize, GFP_KERNEL, node);
+	pqp = (struct bau_pq_entry *)vp;
 	BUG_ON(!pqp);
-	pqp_malloc = pqp;
 
 	cp = (char *)pqp + 31;
-	pqp = (struct bau_payload_queue_entry *)(((unsigned long)cp >> 5) << 5);
+	pqp = (struct bau_pq_entry *)(((unsigned long)cp >> 5) << 5);
 
 	for_each_present_cpu(cpu) {
 		if (pnode != uv_cpu_to_pnode(cpu))
 			continue;
 		/* for every cpu on this pnode: */
 		bcp = &per_cpu(bau_control, cpu);
-		bcp->va_queue_first = pqp;
-		bcp->bau_msg_head = pqp;
-		bcp->va_queue_last = pqp + (DEST_Q_SIZE - 1);
+		bcp->queue_first	= pqp;
+		bcp->bau_msg_head	= pqp;
+		bcp->queue_last		= pqp + (DEST_Q_SIZE - 1);
 	}
 	/*
 	 * need the pnode of where the memory was really allocated
 	 */
-	pa = uv_gpa(pqp);
-	pn = pa >> uv_nshift;
-	uv_write_global_mmr64(pnode,
-			      UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST,
-			      ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) |
-			      uv_physnodeaddr(pqp));
-	uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL,
-			      uv_physnodeaddr(pqp));
-	uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST,
-			      (unsigned long)
-			      uv_physnodeaddr(pqp + (DEST_Q_SIZE - 1)));
+	pn = uv_gpa(pqp) >> uv_nshift;
+	first = uv_physnodeaddr(pqp);
+	pn_first = ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) | first;
+	last = uv_physnodeaddr(pqp + (DEST_Q_SIZE - 1));
+	write_mmr_payload_first(pnode, pn_first);
+	write_mmr_payload_tail(pnode, first);
+	write_mmr_payload_last(pnode, last);
+
 	/* in effect, all msg_type's are set to MSG_NOOP */
-	memset(pqp, 0, sizeof(struct bau_payload_queue_entry) * DEST_Q_SIZE);
+	memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE);
 }
 
 /*
  * Initialization of each UV hub's structures
  */
-static void __init uv_init_uvhub(int uvhub, int vector, int base_pnode)
+static void __init init_uvhub(int uvhub, int vector, int base_pnode)
 {
 	int node;
 	int pnode;
@@ -1459,24 +1541,24 @@ static void __init uv_init_uvhub(int uvhub, int vector, int base_pnode)
 
 	node = uvhub_to_first_node(uvhub);
 	pnode = uv_blade_to_pnode(uvhub);
-	uv_activation_descriptor_init(node, pnode, base_pnode);
-	uv_payload_queue_init(node, pnode);
+
+	activation_descriptor_init(node, pnode, base_pnode);
+
+	pq_init(node, pnode);
 	/*
 	 * The below initialization can't be in firmware because the
 	 * messaging IRQ will be determined by the OS.
 	 */
 	apicid = uvhub_to_first_apicid(uvhub) | uv_apicid_hibits;
-	uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG,
-				      ((apicid << 32) | vector));
+	write_mmr_data_config(pnode, ((apicid << 32) | vector));
 }
 
 /*
  * We will set BAU_MISC_CONTROL with a timeout period.
  * But the BIOS has set UVH_AGING_PRESCALE_SEL and UVH_TRANSACTION_TIMEOUT.
- * So the destination timeout period has be be calculated from them.
+ * So the destination timeout period has to be calculated from them.
  */
-static int
-calculate_destination_timeout(void)
+static int calculate_destination_timeout(void)
 {
 	unsigned long mmr_image;
 	int mult1;
@@ -1486,73 +1568,92 @@ calculate_destination_timeout(void)
 	int ret;
 	unsigned long ts_ns;
 
-	mult1 = UV_INTD_SOFT_ACK_TIMEOUT_PERIOD & BAU_MISC_CONTROL_MULT_MASK;
-	mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL);
-	index = (mmr_image >> BAU_URGENCY_7_SHIFT) & BAU_URGENCY_7_MASK;
-	mmr_image = uv_read_local_mmr(UVH_TRANSACTION_TIMEOUT);
-	mult2 = (mmr_image >> BAU_TRANS_SHIFT) & BAU_TRANS_MASK;
-	base = timeout_base_ns[index];
-	ts_ns = base * mult1 * mult2;
-	ret = ts_ns / 1000;
+	if (is_uv1_hub()) {
+		mult1 = SOFTACK_TIMEOUT_PERIOD & BAU_MISC_CONTROL_MULT_MASK;
+		mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL);
+		index = (mmr_image >> BAU_URGENCY_7_SHIFT) & BAU_URGENCY_7_MASK;
+		mmr_image = uv_read_local_mmr(UVH_TRANSACTION_TIMEOUT);
+		mult2 = (mmr_image >> BAU_TRANS_SHIFT) & BAU_TRANS_MASK;
+		base = timeout_base_ns[index];
+		ts_ns = base * mult1 * mult2;
+		ret = ts_ns / 1000;
+	} else {
+		/* 4 bits  0/1 for 10/80us, 3 bits of multiplier */
+		mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL);
+		mmr_image = (mmr_image & UV_SA_MASK) >> UV_SA_SHFT;
+		if (mmr_image & (1L << UV2_ACK_UNITS_SHFT))
+			mult1 = 80;
+		else
+			mult1 = 10;
+		base = mmr_image & UV2_ACK_MASK;
+		ret = mult1 * base;
+	}
 	return ret;
 }
 
+static void __init init_per_cpu_tunables(void)
+{
+	int cpu;
+	struct bau_control *bcp;
+
+	for_each_present_cpu(cpu) {
+		bcp = &per_cpu(bau_control, cpu);
+		bcp->baudisabled		= 0;
+		bcp->statp			= &per_cpu(ptcstats, cpu);
+		/* time interval to catch a hardware stay-busy bug */
+		bcp->timeout_interval		= usec_2_cycles(2*timeout_us);
+		bcp->max_concurr		= max_concurr;
+		bcp->max_concurr_const		= max_concurr;
+		bcp->plugged_delay		= plugged_delay;
+		bcp->plugsb4reset		= plugsb4reset;
+		bcp->timeoutsb4reset		= timeoutsb4reset;
+		bcp->ipi_reset_limit		= ipi_reset_limit;
+		bcp->complete_threshold		= complete_threshold;
+		bcp->cong_response_us		= congested_respns_us;
+		bcp->cong_reps			= congested_reps;
+		bcp->cong_period		= congested_period;
+	}
+}
+
 /*
- * initialize the bau_control structure for each cpu
+ * Scan all cpus to collect blade and socket summaries.
  */
-static int __init uv_init_per_cpu(int nuvhubs, int base_part_pnode)
+static int __init get_cpu_topology(int base_pnode,
+					struct uvhub_desc *uvhub_descs,
+					unsigned char *uvhub_mask)
 {
-	int i;
 	int cpu;
-	int tcpu;
 	int pnode;
 	int uvhub;
-	int have_hmaster;
-	short socket = 0;
-	unsigned short socket_mask;
-	unsigned char *uvhub_mask;
+	int socket;
 	struct bau_control *bcp;
 	struct uvhub_desc *bdp;
 	struct socket_desc *sdp;
-	struct bau_control *hmaster = NULL;
-	struct bau_control *smaster = NULL;
-	struct socket_desc {
-		short num_cpus;
-		short cpu_number[MAX_CPUS_PER_SOCKET];
-	};
-	struct uvhub_desc {
-		unsigned short socket_mask;
-		short num_cpus;
-		short uvhub;
-		short pnode;
-		struct socket_desc socket[2];
-	};
-	struct uvhub_desc *uvhub_descs;
-
-	timeout_us = calculate_destination_timeout();
 
-	uvhub_descs = kmalloc(nuvhubs * sizeof(struct uvhub_desc), GFP_KERNEL);
-	memset(uvhub_descs, 0, nuvhubs * sizeof(struct uvhub_desc));
-	uvhub_mask = kzalloc((nuvhubs+7)/8, GFP_KERNEL);
 	for_each_present_cpu(cpu) {
 		bcp = &per_cpu(bau_control, cpu);
+
 		memset(bcp, 0, sizeof(struct bau_control));
+
 		pnode = uv_cpu_hub_info(cpu)->pnode;
-		if ((pnode - base_part_pnode) >= UV_DISTRIBUTION_SIZE) {
+		if ((pnode - base_pnode) >= UV_DISTRIBUTION_SIZE) {
 			printk(KERN_EMERG
 				"cpu %d pnode %d-%d beyond %d; BAU disabled\n",
-				cpu, pnode, base_part_pnode,
-				UV_DISTRIBUTION_SIZE);
+				cpu, pnode, base_pnode, UV_DISTRIBUTION_SIZE);
 			return 1;
 		}
+
 		bcp->osnode = cpu_to_node(cpu);
-		bcp->partition_base_pnode = uv_partition_base_pnode;
+		bcp->partition_base_pnode = base_pnode;
+
 		uvhub = uv_cpu_hub_info(cpu)->numa_blade_id;
 		*(uvhub_mask + (uvhub/8)) |= (1 << (uvhub%8));
 		bdp = &uvhub_descs[uvhub];
+
 		bdp->num_cpus++;
 		bdp->uvhub = uvhub;
 		bdp->pnode = pnode;
+
 		/* kludge: 'assuming' one node per socket, and assuming that
 		   disabling a socket just leaves a gap in node numbers */
 		socket = bcp->osnode & 1;
@@ -1561,84 +1662,129 @@ static int __init uv_init_per_cpu(int nuvhubs, int base_part_pnode)
 		sdp->cpu_number[sdp->num_cpus] = cpu;
 		sdp->num_cpus++;
 		if (sdp->num_cpus > MAX_CPUS_PER_SOCKET) {
-			printk(KERN_EMERG "%d cpus per socket invalid\n", sdp->num_cpus);
+			printk(KERN_EMERG "%d cpus per socket invalid\n",
+				sdp->num_cpus);
 			return 1;
 		}
 	}
+	return 0;
+}
+
+/*
+ * Each socket is to get a local array of pnodes/hubs.
+ */
+static void make_per_cpu_thp(struct bau_control *smaster)
+{
+	int cpu;
+	size_t hpsz = sizeof(struct hub_and_pnode) * num_possible_cpus();
+
+	smaster->thp = kmalloc_node(hpsz, GFP_KERNEL, smaster->osnode);
+	memset(smaster->thp, 0, hpsz);
+	for_each_present_cpu(cpu) {
+		smaster->thp[cpu].pnode = uv_cpu_hub_info(cpu)->pnode;
+		smaster->thp[cpu].uvhub = uv_cpu_hub_info(cpu)->numa_blade_id;
+	}
+}
+
+/*
+ * Initialize all the per_cpu information for the cpu's on a given socket,
+ * given what has been gathered into the socket_desc struct.
+ * And reports the chosen hub and socket masters back to the caller.
+ */
+static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp,
+			struct bau_control **smasterp,
+			struct bau_control **hmasterp)
+{
+	int i;
+	int cpu;
+	struct bau_control *bcp;
+
+	for (i = 0; i < sdp->num_cpus; i++) {
+		cpu = sdp->cpu_number[i];
+		bcp = &per_cpu(bau_control, cpu);
+		bcp->cpu = cpu;
+		if (i == 0) {
+			*smasterp = bcp;
+			if (!(*hmasterp))
+				*hmasterp = bcp;
+		}
+		bcp->cpus_in_uvhub = bdp->num_cpus;
+		bcp->cpus_in_socket = sdp->num_cpus;
+		bcp->socket_master = *smasterp;
+		bcp->uvhub = bdp->uvhub;
+		bcp->uvhub_master = *hmasterp;
+		bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->blade_processor_id;
+		if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
+			printk(KERN_EMERG "%d cpus per uvhub invalid\n",
+				bcp->uvhub_cpu);
+			return 1;
+		}
+	}
+	return 0;
+}
+
+/*
+ * Summarize the blade and socket topology into the per_cpu structures.
+ */
+static int __init summarize_uvhub_sockets(int nuvhubs,
+			struct uvhub_desc *uvhub_descs,
+			unsigned char *uvhub_mask)
+{
+	int socket;
+	int uvhub;
+	unsigned short socket_mask;
+
 	for (uvhub = 0; uvhub < nuvhubs; uvhub++) {
+		struct uvhub_desc *bdp;
+		struct bau_control *smaster = NULL;
+		struct bau_control *hmaster = NULL;
+
 		if (!(*(uvhub_mask + (uvhub/8)) & (1 << (uvhub%8))))
 			continue;
-		have_hmaster = 0;
+
 		bdp = &uvhub_descs[uvhub];
 		socket_mask = bdp->socket_mask;
 		socket = 0;
 		while (socket_mask) {
-			if (!(socket_mask & 1))
-				goto nextsocket;
-			sdp = &bdp->socket[socket];
-			for (i = 0; i < sdp->num_cpus; i++) {
-				cpu = sdp->cpu_number[i];
-				bcp = &per_cpu(bau_control, cpu);
-				bcp->cpu = cpu;
-				if (i == 0) {
-					smaster = bcp;
-					if (!have_hmaster) {
-						have_hmaster++;
-						hmaster = bcp;
-					}
-				}
-				bcp->cpus_in_uvhub = bdp->num_cpus;
-				bcp->cpus_in_socket = sdp->num_cpus;
-				bcp->socket_master = smaster;
-				bcp->uvhub = bdp->uvhub;
-				bcp->uvhub_master = hmaster;
-				bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->
-						blade_processor_id;
-				if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
-					printk(KERN_EMERG
-						"%d cpus per uvhub invalid\n",
-						bcp->uvhub_cpu);
+			struct socket_desc *sdp;
+			if ((socket_mask & 1)) {
+				sdp = &bdp->socket[socket];
+				if (scan_sock(sdp, bdp, &smaster, &hmaster))
 					return 1;
-				}
 			}
-nextsocket:
 			socket++;
 			socket_mask = (socket_mask >> 1);
-			/* each socket gets a local array of pnodes/hubs */
-			bcp = smaster;
-			bcp->target_hub_and_pnode = kmalloc_node(
-				sizeof(struct hub_and_pnode) *
-				num_possible_cpus(), GFP_KERNEL, bcp->osnode);
-			memset(bcp->target_hub_and_pnode, 0,
-				sizeof(struct hub_and_pnode) *
-				num_possible_cpus());
-			for_each_present_cpu(tcpu) {
-				bcp->target_hub_and_pnode[tcpu].pnode =
-					uv_cpu_hub_info(tcpu)->pnode;
-				bcp->target_hub_and_pnode[tcpu].uvhub =
-					uv_cpu_hub_info(tcpu)->numa_blade_id;
-			}
+			make_per_cpu_thp(smaster);
 		}
 	}
+	return 0;
+}
+
+/*
+ * initialize the bau_control structure for each cpu
+ */
+static int __init init_per_cpu(int nuvhubs, int base_part_pnode)
+{
+	unsigned char *uvhub_mask;
+	void *vp;
+	struct uvhub_desc *uvhub_descs;
+
+	timeout_us = calculate_destination_timeout();
+
+	vp = kmalloc(nuvhubs * sizeof(struct uvhub_desc), GFP_KERNEL);
+	uvhub_descs = (struct uvhub_desc *)vp;
+	memset(uvhub_descs, 0, nuvhubs * sizeof(struct uvhub_desc));
+	uvhub_mask = kzalloc((nuvhubs+7)/8, GFP_KERNEL);
+
+	if (get_cpu_topology(base_part_pnode, uvhub_descs, uvhub_mask))
+		return 1;
+
+	if (summarize_uvhub_sockets(nuvhubs, uvhub_descs, uvhub_mask))
+		return 1;
+
 	kfree(uvhub_descs);
 	kfree(uvhub_mask);
-	for_each_present_cpu(cpu) {
-		bcp = &per_cpu(bau_control, cpu);
-		bcp->baudisabled = 0;
-		bcp->statp = &per_cpu(ptcstats, cpu);
-		/* time interval to catch a hardware stay-busy bug */
-		bcp->timeout_interval = microsec_2_cycles(2*timeout_us);
-		bcp->max_bau_concurrent = max_bau_concurrent;
-		bcp->max_bau_concurrent_constant = max_bau_concurrent;
-		bcp->plugged_delay = plugged_delay;
-		bcp->plugsb4reset = plugsb4reset;
-		bcp->timeoutsb4reset = timeoutsb4reset;
-		bcp->ipi_reset_limit = ipi_reset_limit;
-		bcp->complete_threshold = complete_threshold;
-		bcp->congested_response_us = congested_response_us;
-		bcp->congested_reps = congested_reps;
-		bcp->congested_period = congested_period;
-	}
+	init_per_cpu_tunables();
 	return 0;
 }
 
@@ -1651,8 +1797,9 @@ static int __init uv_bau_init(void)
 	int pnode;
 	int nuvhubs;
 	int cur_cpu;
+	int cpus;
 	int vector;
-	unsigned long mmr;
+	cpumask_var_t *mask;
 
 	if (!is_uv_system())
 		return 0;
@@ -1660,24 +1807,25 @@ static int __init uv_bau_init(void)
 	if (nobau)
 		return 0;
 
-	for_each_possible_cpu(cur_cpu)
-		zalloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu),
-				       GFP_KERNEL, cpu_to_node(cur_cpu));
+	for_each_possible_cpu(cur_cpu) {
+		mask = &per_cpu(uv_flush_tlb_mask, cur_cpu);
+		zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cur_cpu));
+	}
 
 	uv_nshift = uv_hub_info->m_val;
 	uv_mmask = (1UL << uv_hub_info->m_val) - 1;
 	nuvhubs = uv_num_possible_blades();
 	spin_lock_init(&disable_lock);
-	congested_cycles = microsec_2_cycles(congested_response_us);
+	congested_cycles = usec_2_cycles(congested_respns_us);
 
-	uv_partition_base_pnode = 0x7fffffff;
+	uv_base_pnode = 0x7fffffff;
 	for (uvhub = 0; uvhub < nuvhubs; uvhub++) {
-		if (uv_blade_nr_possible_cpus(uvhub) &&
-			(uv_blade_to_pnode(uvhub) < uv_partition_base_pnode))
-			uv_partition_base_pnode = uv_blade_to_pnode(uvhub);
+		cpus = uv_blade_nr_possible_cpus(uvhub);
+		if (cpus && (uv_blade_to_pnode(uvhub) < uv_base_pnode))
+			uv_base_pnode = uv_blade_to_pnode(uvhub);
 	}
 
-	if (uv_init_per_cpu(nuvhubs, uv_partition_base_pnode)) {
+	if (init_per_cpu(nuvhubs, uv_base_pnode)) {
 		nobau = 1;
 		return 0;
 	}
@@ -1685,21 +1833,21 @@ static int __init uv_bau_init(void)
 	vector = UV_BAU_MESSAGE;
 	for_each_possible_blade(uvhub)
 		if (uv_blade_nr_possible_cpus(uvhub))
-			uv_init_uvhub(uvhub, vector, uv_partition_base_pnode);
+			init_uvhub(uvhub, vector, uv_base_pnode);
 
-	uv_enable_timeouts();
+	enable_timeouts();
 	alloc_intr_gate(vector, uv_bau_message_intr1);
 
 	for_each_possible_blade(uvhub) {
 		if (uv_blade_nr_possible_cpus(uvhub)) {
+			unsigned long val;
+			unsigned long mmr;
 			pnode = uv_blade_to_pnode(uvhub);
 			/* INIT the bau */
-			uv_write_global_mmr64(pnode,
-					UVH_LB_BAU_SB_ACTIVATION_CONTROL,
-					((unsigned long)1 << 63));
+			val = 1L << 63;
+			write_gmmr_activation(pnode, val);
 			mmr = 1; /* should be 1 to broadcast to both sockets */
-			uv_write_global_mmr64(pnode, UVH_BAU_DATA_BROADCAST,
-						mmr);
+			write_mmr_data_broadcast(pnode, mmr);
 		}
 	}
 
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 0eb90184515f..9f29a01ee1b3 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -99,8 +99,12 @@ static void uv_rtc_send_IPI(int cpu)
 /* Check for an RTC interrupt pending */
 static int uv_intr_pending(int pnode)
 {
-	return uv_read_global_mmr64(pnode, UVH_EVENT_OCCURRED0) &
-		UVH_EVENT_OCCURRED0_RTC1_MASK;
+	if (is_uv1_hub())
+		return uv_read_global_mmr64(pnode, UVH_EVENT_OCCURRED0) &
+			UV1H_EVENT_OCCURRED0_RTC1_MASK;
+	else
+		return uv_read_global_mmr64(pnode, UV2H_EVENT_OCCURRED2) &
+			UV2H_EVENT_OCCURRED2_RTC_1_MASK;
 }
 
 /* Setup interrupt and return non-zero if early expiration occurred. */
@@ -114,8 +118,12 @@ static int uv_setup_intr(int cpu, u64 expires)
 		UVH_RTC1_INT_CONFIG_M_MASK);
 	uv_write_global_mmr64(pnode, UVH_INT_CMPB, -1L);
 
-	uv_write_global_mmr64(pnode, UVH_EVENT_OCCURRED0_ALIAS,
-		UVH_EVENT_OCCURRED0_RTC1_MASK);
+	if (is_uv1_hub())
+		uv_write_global_mmr64(pnode, UVH_EVENT_OCCURRED0_ALIAS,
+				UV1H_EVENT_OCCURRED0_RTC1_MASK);
+	else
+		uv_write_global_mmr64(pnode, UV2H_EVENT_OCCURRED2_ALIAS,
+				UV2H_EVENT_OCCURRED2_RTC_1_MASK);
 
 	val = (X86_PLATFORM_IPI_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) |
 		((u64)apicid << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index dd7b88f2ec7a..5525163a0398 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1033,6 +1033,13 @@ static void xen_machine_halt(void)
 	xen_reboot(SHUTDOWN_poweroff);
 }
 
+static void xen_machine_power_off(void)
+{
+	if (pm_power_off)
+		pm_power_off();
+	xen_reboot(SHUTDOWN_poweroff);
+}
+
 static void xen_crash_shutdown(struct pt_regs *regs)
 {
 	xen_reboot(SHUTDOWN_crash);
@@ -1058,7 +1065,7 @@ int xen_panic_handler_init(void)
 static const struct machine_ops xen_machine_ops __initconst = {
 	.restart = xen_restart,
 	.halt = xen_machine_halt,
-	.power_off = xen_machine_halt,
+	.power_off = xen_machine_power_off,
 	.shutdown = xen_machine_halt,
 	.crash_shutdown = xen_crash_shutdown,
 	.emergency_restart = xen_emergency_restart,
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index dc708dcc62f1..673e968df3cf 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -59,6 +59,7 @@
 #include <asm/page.h>
 #include <asm/init.h>
 #include <asm/pat.h>
+#include <asm/smp.h>
 
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
@@ -1231,7 +1232,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 {
 	struct {
 		struct mmuext_op op;
-		DECLARE_BITMAP(mask, NR_CPUS);
+		DECLARE_BITMAP(mask, num_processors);
 	} *args;
 	struct multicall_space mcs;
 
@@ -1599,6 +1600,11 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 		for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
 			pte_t pte;
 
+#ifdef CONFIG_X86_32
+			if (pfn > max_pfn_mapped)
+				max_pfn_mapped = pfn;
+#endif
+
 			if (!pte_none(pte_page[pteidx]))
 				continue;
 
@@ -1766,7 +1772,9 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 	initial_kernel_pmd =
 		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
 
-	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
+	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
+				  xen_start_info->nr_pt_frames * PAGE_SIZE +
+				  512*1024);
 
 	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
 	memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 8bff7e7c290b..1b2b73ff0a6e 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -189,10 +189,10 @@ struct multicall_space __xen_mc_entry(size_t args)
 	unsigned argidx = roundup(b->argidx, sizeof(u64));
 
 	BUG_ON(preemptible());
-	BUG_ON(b->argidx > MC_ARGS);
+	BUG_ON(b->argidx >= MC_ARGS);
 
 	if (b->mcidx == MC_BATCH ||
-	    (argidx + args) > MC_ARGS) {
+	    (argidx + args) >= MC_ARGS) {
 		mc_stats_flush(b->mcidx == MC_BATCH ? FL_SLOTS : FL_ARGS);
 		xen_mc_flush();
 		argidx = roundup(b->argidx, sizeof(u64));
@@ -206,7 +206,7 @@ struct multicall_space __xen_mc_entry(size_t args)
 	ret.args = &b->args[argidx];
 	b->argidx = argidx + args;
 
-	BUG_ON(b->argidx > MC_ARGS);
+	BUG_ON(b->argidx >= MC_ARGS);
 	return ret;
 }
 
@@ -216,7 +216,7 @@ struct multicall_space xen_mc_extend_args(unsigned long op, size_t size)
 	struct multicall_space ret = { NULL, NULL };
 
 	BUG_ON(preemptible());
-	BUG_ON(b->argidx > MC_ARGS);
+	BUG_ON(b->argidx >= MC_ARGS);
 
 	if (b->mcidx == 0)
 		return ret;
@@ -224,14 +224,14 @@ struct multicall_space xen_mc_extend_args(unsigned long op, size_t size)
 	if (b->entries[b->mcidx - 1].op != op)
 		return ret;
 
-	if ((b->argidx + size) > MC_ARGS)
+	if ((b->argidx + size) >= MC_ARGS)
 		return ret;
 
 	ret.mc = &b->entries[b->mcidx - 1];
 	ret.args = &b->args[b->argidx];
 	b->argidx += size;
 
-	BUG_ON(b->argidx > MC_ARGS);
+	BUG_ON(b->argidx >= MC_ARGS);
 	return ret;
 }
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index be1a464f6d66..60aeeb56948f 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -227,11 +227,7 @@ char * __init xen_memory_setup(void)
 
 	memcpy(map_raw, map, sizeof(map));
 	e820.nr_map = 0;
-#ifdef CONFIG_X86_32
 	xen_extra_mem_start = mem_end;
-#else
-	xen_extra_mem_start = max((1ULL << 32), mem_end);
-#endif
 	for (i = 0; i < memmap.nr_entries; i++) {
 		unsigned long long end;
 
@@ -266,6 +262,12 @@ char * __init xen_memory_setup(void)
 		if (map[i].size > 0)
 			e820_add_region(map[i].addr, map[i].size, map[i].type);
 	}
+	/* Align the balloon area so that max_low_pfn does not get set
+	 * to be at the _end_ of the PCI gap at the far end (fee01000).
+	 * Note that xen_extra_mem_start gets set in the loop above to be
+	 * past the last E820 region. */
+	if (xen_initial_domain() && (xen_extra_mem_start < (1ULL<<32)))
+		xen_extra_mem_start = (1ULL<<32);
 
 	/*
 	 * In domU, the ISA region is normal, usable memory, but we
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 41038c01de40..b4533a86d7e4 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -205,11 +205,18 @@ static void __init xen_smp_prepare_boot_cpu(void)
 static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned cpu;
+	unsigned int i;
 
 	xen_init_lock_cpu(0);
 
 	smp_store_cpu_info(0);
 	cpu_data(0).x86_max_cores = 1;
+
+	for_each_possible_cpu(i) {
+		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
+	}
 	set_cpu_sibling_map(0);
 
 	if (xen_smp_intr_init(0))
diff --git a/arch/xtensa/include/asm/unistd.h b/arch/xtensa/include/asm/unistd.h
index 528042c2951e..a6f934f37f1a 100644
--- a/arch/xtensa/include/asm/unistd.h
+++ b/arch/xtensa/include/asm/unistd.h
@@ -683,8 +683,10 @@ __SYSCALL(305, sys_ni_syscall, 0)
 __SYSCALL(306, sys_eventfd, 1)
 #define __NR_recvmmsg				307
 __SYSCALL(307, sys_recvmmsg, 5)
+#define __NR_setns				308
+__SYSCALL(308, sys_setns, 2)
 
-#define __NR_syscall_count			308
+#define __NR_syscall_count			309
 
 /*
  * sysxtensa syscall handler
diff --git a/block/blk-core.c b/block/blk-core.c
index c8303e9d919d..d2f8f4049abd 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -345,6 +345,7 @@ void blk_put_queue(struct request_queue *q)
 {
 	kobject_put(&q->kobj);
 }
+EXPORT_SYMBOL(blk_put_queue);
 
 /*
  * Note: If a driver supplied the queue lock, it should not zap that lock
@@ -566,6 +567,7 @@ int blk_get_queue(struct request_queue *q)
 
 	return 1;
 }
+EXPORT_SYMBOL(blk_get_queue);
 
 static inline void blk_free_request(struct request_queue *q, struct request *rq)
 {
@@ -1130,7 +1132,6 @@ static bool bio_attempt_front_merge(struct request_queue *q,
 				    struct request *req, struct bio *bio)
 {
 	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
-	sector_t sector;
 
 	if (!ll_front_merge_fn(q, req, bio))
 		return false;
@@ -1140,8 +1141,6 @@ static bool bio_attempt_front_merge(struct request_queue *q,
 	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
 		blk_rq_set_mixed_merge(req);
 
-	sector = bio->bi_sector;
-
 	bio->bi_next = req->bio;
 	req->bio = bio;
 
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index c898049dafd5..342eae9b0d3c 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -21,7 +21,7 @@ static void cfq_dtor(struct io_context *ioc)
 	if (!hlist_empty(&ioc->cic_list)) {
 		struct cfq_io_context *cic;
 
-		cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+		cic = hlist_entry(ioc->cic_list.first, struct cfq_io_context,
 								cic_list);
 		cic->dtor(ioc);
 	}
@@ -57,7 +57,7 @@ static void cfq_exit(struct io_context *ioc)
 	if (!hlist_empty(&ioc->cic_list)) {
 		struct cfq_io_context *cic;
 
-		cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+		cic = hlist_entry(ioc->cic_list.first, struct cfq_io_context,
 								cic_list);
 		cic->exit(ioc);
 	}
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index a62be8d0dc1b..3689f833afdc 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -927,7 +927,7 @@ static int throtl_dispatch(struct request_queue *q)
 
 	bio_list_init(&bio_list_on_stack);
 
-	throtl_log(td, "dispatch nr_queued=%lu read=%u write=%u",
+	throtl_log(td, "dispatch nr_queued=%d read=%u write=%u",
 			total_nr_queued(td), td->nr_queued[READ],
 			td->nr_queued[WRITE]);
 
@@ -1204,7 +1204,7 @@ int blk_throtl_bio(struct request_queue *q, struct bio **biop)
 	}
 
 queue_bio:
-	throtl_log_tg(td, tg, "[%c] bio. bdisp=%u sz=%u bps=%llu"
+	throtl_log_tg(td, tg, "[%c] bio. bdisp=%llu sz=%u bps=%llu"
 			" iodisp=%u iops=%u queued=%d/%d",
 			rw == READ ? 'R' : 'W',
 			tg->bytes_disp[rw], bio->bi_size, tg->bps[rw],
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 7c52d6888924..f3799432676d 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -185,7 +185,7 @@ struct cfq_group {
 	int nr_cfqq;
 
 	/*
-	 * Per group busy queus average. Useful for workload slice calc. We
+	 * Per group busy queues average. Useful for workload slice calc. We
 	 * create the array for each prio class but at run time it is used
 	 * only for RT and BE class and slot for IDLE class remains unused.
 	 * This is primarily done to avoid confusion and a gcc warning.
@@ -369,16 +369,16 @@ CFQ_CFQQ_FNS(wait_busy);
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \
 			cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \
-			blkg_path(&(cfqq)->cfqg->blkg), ##args);
+			blkg_path(&(cfqq)->cfqg->blkg), ##args)
 
 #define cfq_log_cfqg(cfqd, cfqg, fmt, args...)				\
 	blk_add_trace_msg((cfqd)->queue, "%s " fmt,			\
-				blkg_path(&(cfqg)->blkg), ##args);      \
+				blkg_path(&(cfqg)->blkg), ##args)       \
 
 #else
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
-#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0);
+#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0)
 #endif
 #define cfq_log(cfqd, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
@@ -988,9 +988,10 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 
 	cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
 					st->min_vdisktime);
-	cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u disp=%u charge=%u iops=%u"
-			" sect=%u", used_sl, cfqq->slice_dispatch, charge,
-			iops_mode(cfqd), cfqq->nr_sectors);
+	cfq_log_cfqq(cfqq->cfqd, cfqq,
+		     "sl_used=%u disp=%u charge=%u iops=%u sect=%lu",
+		     used_sl, cfqq->slice_dispatch, charge,
+		     iops_mode(cfqd), cfqq->nr_sectors);
 	cfq_blkiocg_update_timeslice_used(&cfqg->blkg, used_sl,
 					  unaccounted_sl);
 	cfq_blkiocg_set_start_empty_time(&cfqg->blkg);
@@ -2023,8 +2024,8 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	 */
 	if (sample_valid(cic->ttime_samples) &&
 	    (cfqq->slice_end - jiffies < cic->ttime_mean)) {
-		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%d",
-				cic->ttime_mean);
+		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%lu",
+			     cic->ttime_mean);
 		return;
 	}
 
@@ -2772,8 +2773,11 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
 	smp_wmb();
 	cic->key = cfqd_dead_key(cfqd);
 
-	if (ioc->ioc_data == cic)
+	if (rcu_dereference(ioc->ioc_data) == cic) {
+		spin_lock(&ioc->lock);
 		rcu_assign_pointer(ioc->ioc_data, NULL);
+		spin_unlock(&ioc->lock);
+	}
 
 	if (cic->cfqq[BLK_RW_ASYNC]) {
 		cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]);
@@ -3786,9 +3790,6 @@ new_queue:
 	return 0;
 
 queue_fail:
-	if (cic)
-		put_io_context(cic->ioc);
-
 	cfq_schedule_dispatch(cfqd);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 	cfq_log(cfqd, "set_request fail");
diff --git a/block/genhd.c b/block/genhd.c
index 2dd988723d73..3608289c8ecd 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1371,6 +1371,7 @@ struct disk_events {
 	struct gendisk		*disk;		/* the associated disk */
 	spinlock_t		lock;
 
+	struct mutex		block_mutex;	/* protects blocking */
 	int			block;		/* event blocking depth */
 	unsigned int		pending;	/* events already sent out */
 	unsigned int		clearing;	/* events being cleared */
@@ -1414,22 +1415,44 @@ static unsigned long disk_events_poll_jiffies(struct gendisk *disk)
 	return msecs_to_jiffies(intv_msecs);
 }
 
-static void __disk_block_events(struct gendisk *disk, bool sync)
+/**
+ * disk_block_events - block and flush disk event checking
+ * @disk: disk to block events for
+ *
+ * On return from this function, it is guaranteed that event checking
+ * isn't in progress and won't happen until unblocked by
+ * disk_unblock_events().  Events blocking is counted and the actual
+ * unblocking happens after the matching number of unblocks are done.
+ *
+ * Note that this intentionally does not block event checking from
+ * disk_clear_events().
+ *
+ * CONTEXT:
+ * Might sleep.
+ */
+void disk_block_events(struct gendisk *disk)
 {
 	struct disk_events *ev = disk->ev;
 	unsigned long flags;
 	bool cancel;
 
+	if (!ev)
+		return;
+
+	/*
+	 * Outer mutex ensures that the first blocker completes canceling
+	 * the event work before further blockers are allowed to finish.
+	 */
+	mutex_lock(&ev->block_mutex);
+
 	spin_lock_irqsave(&ev->lock, flags);
 	cancel = !ev->block++;
 	spin_unlock_irqrestore(&ev->lock, flags);
 
-	if (cancel) {
-		if (sync)
-			cancel_delayed_work_sync(&disk->ev->dwork);
-		else
-			cancel_delayed_work(&disk->ev->dwork);
-	}
+	if (cancel)
+		cancel_delayed_work_sync(&disk->ev->dwork);
+
+	mutex_unlock(&ev->block_mutex);
 }
 
 static void __disk_unblock_events(struct gendisk *disk, bool check_now)
@@ -1461,27 +1484,6 @@ out_unlock:
 }
 
 /**
- * disk_block_events - block and flush disk event checking
- * @disk: disk to block events for
- *
- * On return from this function, it is guaranteed that event checking
- * isn't in progress and won't happen until unblocked by
- * disk_unblock_events().  Events blocking is counted and the actual
- * unblocking happens after the matching number of unblocks are done.
- *
- * Note that this intentionally does not block event checking from
- * disk_clear_events().
- *
- * CONTEXT:
- * Might sleep.
- */
-void disk_block_events(struct gendisk *disk)
-{
-	if (disk->ev)
-		__disk_block_events(disk, true);
-}
-
-/**
  * disk_unblock_events - unblock disk event checking
  * @disk: disk to unblock events for
  *
@@ -1508,10 +1510,18 @@ void disk_unblock_events(struct gendisk *disk)
  */
 void disk_check_events(struct gendisk *disk)
 {
-	if (disk->ev) {
-		__disk_block_events(disk, false);
-		__disk_unblock_events(disk, true);
+	struct disk_events *ev = disk->ev;
+	unsigned long flags;
+
+	if (!ev)
+		return;
+
+	spin_lock_irqsave(&ev->lock, flags);
+	if (!ev->block) {
+		cancel_delayed_work(&ev->dwork);
+		queue_delayed_work(system_nrt_wq, &ev->dwork, 0);
 	}
+	spin_unlock_irqrestore(&ev->lock, flags);
 }
 EXPORT_SYMBOL_GPL(disk_check_events);
 
@@ -1546,7 +1556,7 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
 	spin_unlock_irq(&ev->lock);
 
 	/* uncondtionally schedule event check and wait for it to finish */
-	__disk_block_events(disk, true);
+	disk_block_events(disk);
 	queue_delayed_work(system_nrt_wq, &ev->dwork, 0);
 	flush_delayed_work(&ev->dwork);
 	__disk_unblock_events(disk, false);
@@ -1664,7 +1674,7 @@ static ssize_t disk_events_poll_msecs_store(struct device *dev,
 	if (intv < 0 && intv != -1)
 		return -EINVAL;
 
-	__disk_block_events(disk, true);
+	disk_block_events(disk);
 	disk->ev->poll_msecs = intv;
 	__disk_unblock_events(disk, true);
 
@@ -1728,7 +1738,7 @@ static void disk_add_events(struct gendisk *disk)
 {
 	struct disk_events *ev;
 
-	if (!disk->fops->check_events || !(disk->events | disk->async_events))
+	if (!disk->fops->check_events)
 		return;
 
 	ev = kzalloc(sizeof(*ev), GFP_KERNEL);
@@ -1750,6 +1760,7 @@ static void disk_add_events(struct gendisk *disk)
 	INIT_LIST_HEAD(&ev->node);
 	ev->disk = disk;
 	spin_lock_init(&ev->lock);
+	mutex_init(&ev->block_mutex);
 	ev->block = 1;
 	ev->poll_msecs = -1;
 	INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn);
@@ -1770,7 +1781,7 @@ static void disk_del_events(struct gendisk *disk)
 	if (!disk->ev)
 		return;
 
-	__disk_block_events(disk, true);
+	disk_block_events(disk);
 
 	mutex_lock(&disk_events_mutex);
 	list_del_init(&disk->ev->node);
diff --git a/drivers/Makefile b/drivers/Makefile
index 6b17f5864340..09f3232bcdcd 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -17,6 +17,9 @@ obj-$(CONFIG_SFI)		+= sfi/
 # was used and do nothing if so
 obj-$(CONFIG_PNP)		+= pnp/
 obj-$(CONFIG_ARM_AMBA)		+= amba/
+# Many drivers will want to use DMA so this has to be made available
+# really early.
+obj-$(CONFIG_DMA_ENGINE)	+= dma/
 
 obj-$(CONFIG_VIRTIO)		+= virtio/
 obj-$(CONFIG_XEN)		+= xen/
@@ -92,7 +95,6 @@ obj-$(CONFIG_EISA)		+= eisa/
 obj-y				+= lguest/
 obj-$(CONFIG_CPU_FREQ)		+= cpufreq/
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle/
-obj-$(CONFIG_DMA_ENGINE)	+= dma/
 obj-$(CONFIG_MMC)		+= mmc/
 obj-$(CONFIG_MEMSTICK)		+= memstick/
 obj-y				+= leds/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index bc2218db5ba9..de0e3df76776 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -369,6 +369,21 @@ config ACPI_HED
 	  which is used to report some hardware errors notified via
 	  SCI, mainly the corrected errors.
 
+config ACPI_CUSTOM_METHOD
+	tristate "Allow ACPI methods to be inserted/replaced at run time"
+	depends on DEBUG_FS
+	default n
+	help
+	  This debug facility allows ACPI AML methods to me inserted and/or
+	  replaced without rebooting the system. For details refer to:
+	  Documentation/acpi/method-customizing.txt.
+
+	  NOTE: This option is security sensitive, because it allows arbitrary
+	  kernel memory to be written to by root (uid=0) users, allowing them
+	  to bypass certain security measures (e.g. if root is not allowed to
+	  load additional kernel modules after boot, this feature may be used
+	  to override that restriction).
+
 source "drivers/acpi/apei/Kconfig"
 
 endif	# ACPI
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index b66fbb2fc85f..ecb26b4f29a0 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -61,6 +61,7 @@ obj-$(CONFIG_ACPI_SBS)		+= sbshc.o
 obj-$(CONFIG_ACPI_SBS)		+= sbs.o
 obj-$(CONFIG_ACPI_HED)		+= hed.o
 obj-$(CONFIG_ACPI_EC_DEBUGFS)	+= ec_sys.o
+obj-$(CONFIG_ACPI_CUSTOM_METHOD)+= custom_method.o
 
 # processor has its own "processor." module_param namespace
 processor-y			:= processor_driver.o processor_throttling.o
diff --git a/drivers/acpi/acpica/Makefile b/drivers/acpi/acpica/Makefile
index a1224712fd0c..301bd2d388ad 100644
--- a/drivers/acpi/acpica/Makefile
+++ b/drivers/acpi/acpica/Makefile
@@ -14,7 +14,7 @@ acpi-y := dsfield.o   dsmthdat.o  dsopcode.o  dswexec.o  dswscope.o \
 
 acpi-y += evevent.o  evregion.o  evsci.o    evxfevnt.o \
 	 evmisc.o   evrgnini.o  evxface.o  evxfregn.o \
-	 evgpe.o    evgpeblk.o evgpeinit.o  evgpeutil.o evxfgpe.o
+	 evgpe.o    evgpeblk.o evgpeinit.o  evgpeutil.o evxfgpe.o evglock.o
 
 acpi-y += exconfig.o  exfield.o  exnames.o   exoparg6.o  exresolv.o  exstorob.o\
 	 exconvrt.o  exfldio.o  exoparg1.o  exprep.o    exresop.o   exsystem.o\
diff --git a/drivers/acpi/acpica/acconfig.h b/drivers/acpi/acpica/acconfig.h
index ab87396c2c07..bc533dde16c4 100644
--- a/drivers/acpi/acpica/acconfig.h
+++ b/drivers/acpi/acpica/acconfig.h
@@ -187,7 +187,6 @@
 
 /* Operation regions */
 
-#define ACPI_NUM_PREDEFINED_REGIONS     9
 #define ACPI_USER_REGION_BEGIN          0x80
 
 /* Maximum space_ids for Operation Regions */
diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h
index 41d247daf461..bea3b4899183 100644
--- a/drivers/acpi/acpica/acevents.h
+++ b/drivers/acpi/acpica/acevents.h
@@ -58,12 +58,6 @@ u32 acpi_ev_fixed_event_detect(void);
  */
 u8 acpi_ev_is_notify_object(struct acpi_namespace_node *node);
 
-acpi_status acpi_ev_acquire_global_lock(u16 timeout);
-
-acpi_status acpi_ev_release_global_lock(void);
-
-acpi_status acpi_ev_init_global_lock_handler(void);
-
 u32 acpi_ev_get_gpe_number_index(u32 gpe_number);
 
 acpi_status
@@ -71,6 +65,17 @@ acpi_ev_queue_notify_request(struct acpi_namespace_node *node,
 			     u32 notify_value);
 
 /*
+ * evglock - Global Lock support
+ */
+acpi_status acpi_ev_init_global_lock_handler(void);
+
+acpi_status acpi_ev_acquire_global_lock(u16 timeout);
+
+acpi_status acpi_ev_release_global_lock(void);
+
+acpi_status acpi_ev_remove_global_lock_handler(void);
+
+/*
  * evgpe - Low-level GPE support
  */
 u32 acpi_ev_gpe_detect(struct acpi_gpe_xrupt_info *gpe_xrupt_list);
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index d69750b83b36..73863d86f022 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -214,24 +214,23 @@ ACPI_EXTERN struct acpi_mutex_info acpi_gbl_mutex_info[ACPI_NUM_MUTEX];
 
 /*
  * Global lock mutex is an actual AML mutex object
- * Global lock semaphore works in conjunction with the HW global lock
+ * Global lock semaphore works in conjunction with the actual global lock
+ * Global lock spinlock is used for "pending" handshake
  */
 ACPI_EXTERN union acpi_operand_object *acpi_gbl_global_lock_mutex;
 ACPI_EXTERN acpi_semaphore acpi_gbl_global_lock_semaphore;
+ACPI_EXTERN acpi_spinlock acpi_gbl_global_lock_pending_lock;
 ACPI_EXTERN u16 acpi_gbl_global_lock_handle;
 ACPI_EXTERN u8 acpi_gbl_global_lock_acquired;
 ACPI_EXTERN u8 acpi_gbl_global_lock_present;
+ACPI_EXTERN u8 acpi_gbl_global_lock_pending;
 
 /*
  * Spinlocks are used for interfaces that can be possibly called at
  * interrupt level
  */
-ACPI_EXTERN spinlock_t _acpi_gbl_gpe_lock;	/* For GPE data structs and registers */
-ACPI_EXTERN spinlock_t _acpi_gbl_hardware_lock;	/* For ACPI H/W except GPE registers */
-ACPI_EXTERN spinlock_t _acpi_ev_global_lock_pending_lock; /* For global lock */
-#define acpi_gbl_gpe_lock	&_acpi_gbl_gpe_lock
-#define acpi_gbl_hardware_lock	&_acpi_gbl_hardware_lock
-#define acpi_ev_global_lock_pending_lock &_acpi_ev_global_lock_pending_lock
+ACPI_EXTERN acpi_spinlock acpi_gbl_gpe_lock;	/* For GPE data structs and registers */
+ACPI_EXTERN acpi_spinlock acpi_gbl_hardware_lock;	/* For ACPI H/W except GPE registers */
 
 /*****************************************************************************
  *
diff --git a/drivers/acpi/acpica/amlcode.h b/drivers/acpi/acpica/amlcode.h
index f4f0998d3967..1077f17859ed 100644
--- a/drivers/acpi/acpica/amlcode.h
+++ b/drivers/acpi/acpica/amlcode.h
@@ -394,21 +394,6 @@
 #define AML_CLASS_METHOD_CALL       0x09
 #define AML_CLASS_UNKNOWN           0x0A
 
-/* Predefined Operation Region space_iDs */
-
-typedef enum {
-	REGION_MEMORY = 0,
-	REGION_IO,
-	REGION_PCI_CONFIG,
-	REGION_EC,
-	REGION_SMBUS,
-	REGION_CMOS,
-	REGION_PCI_BAR,
-	REGION_IPMI,
-	REGION_DATA_TABLE,	/* Internal use only */
-	REGION_FIXED_HW = 0x7F
-} AML_REGION_TYPES;
-
 /* Comparison operation codes for match_op operator */
 
 typedef enum {
diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c
index 23a3b1ab20c1..324acec1179a 100644
--- a/drivers/acpi/acpica/dswload.c
+++ b/drivers/acpi/acpica/dswload.c
@@ -450,7 +450,7 @@ acpi_status acpi_ds_load1_end_op(struct acpi_walk_state *walk_state)
 			status =
 			    acpi_ex_create_region(op->named.data,
 						  op->named.length,
-						  REGION_DATA_TABLE,
+						  ACPI_ADR_SPACE_DATA_TABLE,
 						  walk_state);
 			if (ACPI_FAILURE(status)) {
 				return_ACPI_STATUS(status);
diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c
index 4be4e921dfe1..976318138c56 100644
--- a/drivers/acpi/acpica/dswload2.c
+++ b/drivers/acpi/acpica/dswload2.c
@@ -562,7 +562,7 @@ acpi_status acpi_ds_load2_end_op(struct acpi_walk_state *walk_state)
 				    ((op->common.value.arg)->common.value.
 				     integer);
 			} else {
-				region_space = REGION_DATA_TABLE;
+				region_space = ACPI_ADR_SPACE_DATA_TABLE;
 			}
 
 			/*
diff --git a/drivers/acpi/acpica/evglock.c b/drivers/acpi/acpica/evglock.c
new file mode 100644
index 000000000000..56a562a1e5d7
--- /dev/null
+++ b/drivers/acpi/acpica/evglock.c
@@ -0,0 +1,335 @@
+/******************************************************************************
+ *
+ * Module Name: evglock - Global Lock support
+ *
+ *****************************************************************************/
+
+/*
+ * Copyright (C) 2000 - 2011, Intel Corp.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions, and the following disclaimer,
+ *    without modification.
+ * 2. Redistributions in binary form must reproduce at minimum a disclaimer
+ *    substantially similar to the "NO WARRANTY" disclaimer below
+ *    ("Disclaimer") and any redistribution must be conditioned upon
+ *    including a substantially similar Disclaimer requirement for further
+ *    binary redistribution.
+ * 3. Neither the names of the above-listed copyright holders nor the names
+ *    of any contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * NO WARRANTY
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+ * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGES.
+ */
+
+#include <acpi/acpi.h>
+#include "accommon.h"
+#include "acevents.h"
+#include "acinterp.h"
+
+#define _COMPONENT          ACPI_EVENTS
+ACPI_MODULE_NAME("evglock")
+
+/* Local prototypes */
+static u32 acpi_ev_global_lock_handler(void *context);
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ev_init_global_lock_handler
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Install a handler for the global lock release event
+ *
+ ******************************************************************************/
+
+acpi_status acpi_ev_init_global_lock_handler(void)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(ev_init_global_lock_handler);
+
+	/* Attempt installation of the global lock handler */
+
+	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.
+	 */
+	acpi_gbl_global_lock_present = FALSE;
+	if (status == AE_NO_HARDWARE_RESPONSE) {
+		ACPI_ERROR((AE_INFO,
+			    "No response from Global Lock hardware, disabling lock"));
+
+		return_ACPI_STATUS(AE_OK);
+	}
+
+	status = acpi_os_create_lock(&acpi_gbl_global_lock_pending_lock);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	acpi_gbl_global_lock_pending = FALSE;
+	acpi_gbl_global_lock_present = TRUE;
+	return_ACPI_STATUS(status);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ev_remove_global_lock_handler
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Remove the handler for the Global Lock
+ *
+ ******************************************************************************/
+
+acpi_status acpi_ev_remove_global_lock_handler(void)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(ev_remove_global_lock_handler);
+
+	acpi_gbl_global_lock_present = FALSE;
+	status = acpi_remove_fixed_event_handler(ACPI_EVENT_GLOBAL,
+						 acpi_ev_global_lock_handler);
+
+	return_ACPI_STATUS(status);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ev_global_lock_handler
+ *
+ * PARAMETERS:  Context         - From thread interface, not used
+ *
+ * RETURN:      ACPI_INTERRUPT_HANDLED
+ *
+ * DESCRIPTION: Invoked directly from the SCI handler when a global lock
+ *              release interrupt occurs. If there is actually a pending
+ *              request for the lock, signal the waiting thread.
+ *
+ ******************************************************************************/
+
+static u32 acpi_ev_global_lock_handler(void *context)
+{
+	acpi_status status;
+	acpi_cpu_flags flags;
+
+	flags = acpi_os_acquire_lock(acpi_gbl_global_lock_pending_lock);
+
+	/*
+	 * If a request for the global lock is not actually pending,
+	 * we are done. This handles "spurious" global lock interrupts
+	 * which are possible (and have been seen) with bad BIOSs.
+	 */
+	if (!acpi_gbl_global_lock_pending) {
+		goto cleanup_and_exit;
+	}
+
+	/*
+	 * Send a unit to the global lock semaphore. The actual acquisition
+	 * of the global lock will be performed by the waiting thread.
+	 */
+	status = acpi_os_signal_semaphore(acpi_gbl_global_lock_semaphore, 1);
+	if (ACPI_FAILURE(status)) {
+		ACPI_ERROR((AE_INFO, "Could not signal Global Lock semaphore"));
+	}
+
+	acpi_gbl_global_lock_pending = FALSE;
+
+      cleanup_and_exit:
+
+	acpi_os_release_lock(acpi_gbl_global_lock_pending_lock, flags);
+	return (ACPI_INTERRUPT_HANDLED);
+}
+
+/******************************************************************************
+ *
+ * FUNCTION:    acpi_ev_acquire_global_lock
+ *
+ * PARAMETERS:  Timeout         - Max time to wait for the lock, in millisec.
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Attempt to gain ownership of the Global Lock.
+ *
+ * MUTEX:       Interpreter must be locked
+ *
+ * Note: The original implementation allowed multiple threads to "acquire" the
+ * Global Lock, and the OS would hold the lock until the last thread had
+ * released it. However, this could potentially starve the BIOS out of the
+ * lock, especially in the case where there is a tight handshake between the
+ * Embedded Controller driver and the BIOS. Therefore, this implementation
+ * allows only one thread to acquire the HW Global Lock at a time, and makes
+ * the global lock appear as a standard mutex on the OS side.
+ *
+ *****************************************************************************/
+
+acpi_status acpi_ev_acquire_global_lock(u16 timeout)
+{
+	acpi_cpu_flags flags;
+	acpi_status status;
+	u8 acquired = FALSE;
+
+	ACPI_FUNCTION_TRACE(ev_acquire_global_lock);
+
+	/*
+	 * Only one thread can acquire the GL at a time, the global_lock_mutex
+	 * enforces this. This interface releases the interpreter if we must wait.
+	 */
+	status =
+	    acpi_ex_system_wait_mutex(acpi_gbl_global_lock_mutex->mutex.
+				      os_mutex, timeout);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/*
+	 * Update the global lock handle and check for wraparound. The handle is
+	 * only used for the external global lock interfaces, but it is updated
+	 * here to properly handle the case where a single thread may acquire the
+	 * lock via both the AML and the acpi_acquire_global_lock interfaces. The
+	 * handle is therefore updated on the first acquire from a given thread
+	 * regardless of where the acquisition request originated.
+	 */
+	acpi_gbl_global_lock_handle++;
+	if (acpi_gbl_global_lock_handle == 0) {
+		acpi_gbl_global_lock_handle = 1;
+	}
+
+	/*
+	 * 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;
+		return_ACPI_STATUS(AE_OK);
+	}
+
+	flags = acpi_os_acquire_lock(acpi_gbl_global_lock_pending_lock);
+
+	do {
+
+		/* Attempt to acquire the actual hardware lock */
+
+		ACPI_ACQUIRE_GLOBAL_LOCK(acpi_gbl_FACS, acquired);
+		if (acquired) {
+			acpi_gbl_global_lock_acquired = TRUE;
+			ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+					  "Acquired hardware Global Lock\n"));
+			break;
+		}
+
+		/*
+		 * Did not get the lock. The pending bit was set above, and
+		 * we must now wait until we receive the global lock
+		 * released interrupt.
+		 */
+		acpi_gbl_global_lock_pending = TRUE;
+		acpi_os_release_lock(acpi_gbl_global_lock_pending_lock, flags);
+
+		ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+				  "Waiting for hardware Global Lock\n"));
+
+		/*
+		 * Wait for handshake with the global lock interrupt handler.
+		 * This interface releases the interpreter if we must wait.
+		 */
+		status =
+		    acpi_ex_system_wait_semaphore
+		    (acpi_gbl_global_lock_semaphore, ACPI_WAIT_FOREVER);
+
+		flags = acpi_os_acquire_lock(acpi_gbl_global_lock_pending_lock);
+
+	} while (ACPI_SUCCESS(status));
+
+	acpi_gbl_global_lock_pending = FALSE;
+	acpi_os_release_lock(acpi_gbl_global_lock_pending_lock, flags);
+
+	return_ACPI_STATUS(status);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ev_release_global_lock
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Releases ownership of the Global Lock.
+ *
+ ******************************************************************************/
+
+acpi_status acpi_ev_release_global_lock(void)
+{
+	u8 pending = FALSE;
+	acpi_status status = AE_OK;
+
+	ACPI_FUNCTION_TRACE(ev_release_global_lock);
+
+	/* Lock must be already acquired */
+
+	if (!acpi_gbl_global_lock_acquired) {
+		ACPI_WARNING((AE_INFO,
+			      "Cannot release the ACPI Global Lock, it has not been acquired"));
+		return_ACPI_STATUS(AE_NOT_ACQUIRED);
+	}
+
+	if (acpi_gbl_global_lock_present) {
+
+		/* Allow any thread to release the lock */
+
+		ACPI_RELEASE_GLOBAL_LOCK(acpi_gbl_FACS, pending);
+
+		/*
+		 * If the pending bit was set, we must write GBL_RLS to the control
+		 * register
+		 */
+		if (pending) {
+			status =
+			    acpi_write_bit_register
+			    (ACPI_BITREG_GLOBAL_LOCK_RELEASE,
+			     ACPI_ENABLE_EVENT);
+		}
+
+		ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+				  "Released hardware Global Lock\n"));
+	}
+
+	acpi_gbl_global_lock_acquired = FALSE;
+
+	/* Release the local GL mutex */
+
+	acpi_os_release_mutex(acpi_gbl_global_lock_mutex->mutex.os_mutex);
+	return_ACPI_STATUS(status);
+}
diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c
index 7dc80946f7bd..d0b331844427 100644
--- a/drivers/acpi/acpica/evmisc.c
+++ b/drivers/acpi/acpica/evmisc.c
@@ -45,7 +45,6 @@
 #include "accommon.h"
 #include "acevents.h"
 #include "acnamesp.h"
-#include "acinterp.h"
 
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evmisc")
@@ -53,10 +52,6 @@ ACPI_MODULE_NAME("evmisc")
 /* Local prototypes */
 static void ACPI_SYSTEM_XFACE acpi_ev_notify_dispatch(void *context);
 
-static u32 acpi_ev_global_lock_handler(void *context);
-
-static acpi_status acpi_ev_remove_global_lock_handler(void);
-
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ev_is_notify_object
@@ -275,304 +270,6 @@ static void ACPI_SYSTEM_XFACE acpi_ev_notify_dispatch(void *context)
 	acpi_ut_delete_generic_state(notify_info);
 }
 
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ev_global_lock_handler
- *
- * PARAMETERS:  Context         - From thread interface, not used
- *
- * RETURN:      ACPI_INTERRUPT_HANDLED
- *
- * DESCRIPTION: Invoked directly from the SCI handler when a global lock
- *              release interrupt occurs.  If there's a thread waiting for
- *              the global lock, signal it.
- *
- * NOTE: Assumes that the semaphore can be signaled from interrupt level. If
- * this is not possible for some reason, a separate thread will have to be
- * scheduled to do this.
- *
- ******************************************************************************/
-static u8 acpi_ev_global_lock_pending;
-
-static u32 acpi_ev_global_lock_handler(void *context)
-{
-	acpi_status status;
-	acpi_cpu_flags flags;
-
-	flags = acpi_os_acquire_lock(acpi_ev_global_lock_pending_lock);
-
-	if (!acpi_ev_global_lock_pending) {
-		goto out;
-	}
-
-	/* Send a unit to the semaphore */
-
-	status = acpi_os_signal_semaphore(acpi_gbl_global_lock_semaphore, 1);
-	if (ACPI_FAILURE(status)) {
-		ACPI_ERROR((AE_INFO, "Could not signal Global Lock semaphore"));
-	}
-
-	acpi_ev_global_lock_pending = FALSE;
-
- out:
-	acpi_os_release_lock(acpi_ev_global_lock_pending_lock, flags);
-
-	return (ACPI_INTERRUPT_HANDLED);
-}
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ev_init_global_lock_handler
- *
- * PARAMETERS:  None
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Install a handler for the global lock release event
- *
- ******************************************************************************/
-
-acpi_status acpi_ev_init_global_lock_handler(void)
-{
-	acpi_status status;
-
-	ACPI_FUNCTION_TRACE(ev_init_global_lock_handler);
-
-	/* Attempt installation of the global lock handler */
-
-	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 (status == AE_NO_HARDWARE_RESPONSE) {
-		ACPI_ERROR((AE_INFO,
-			    "No response from Global Lock hardware, disabling lock"));
-
-		acpi_gbl_global_lock_present = FALSE;
-		return_ACPI_STATUS(AE_OK);
-	}
-
-	acpi_gbl_global_lock_present = TRUE;
-	return_ACPI_STATUS(status);
-}
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ev_remove_global_lock_handler
- *
- * PARAMETERS:  None
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Remove the handler for the Global Lock
- *
- ******************************************************************************/
-
-static acpi_status acpi_ev_remove_global_lock_handler(void)
-{
-	acpi_status status;
-
-	ACPI_FUNCTION_TRACE(ev_remove_global_lock_handler);
-
-	acpi_gbl_global_lock_present = FALSE;
-	status = acpi_remove_fixed_event_handler(ACPI_EVENT_GLOBAL,
-						 acpi_ev_global_lock_handler);
-
-	return_ACPI_STATUS(status);
-}
-
-/******************************************************************************
- *
- * FUNCTION:    acpi_ev_acquire_global_lock
- *
- * PARAMETERS:  Timeout         - Max time to wait for the lock, in millisec.
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Attempt to gain ownership of the Global Lock.
- *
- * MUTEX:       Interpreter must be locked
- *
- * Note: The original implementation allowed multiple threads to "acquire" the
- * Global Lock, and the OS would hold the lock until the last thread had
- * released it. However, this could potentially starve the BIOS out of the
- * lock, especially in the case where there is a tight handshake between the
- * Embedded Controller driver and the BIOS. Therefore, this implementation
- * allows only one thread to acquire the HW Global Lock at a time, and makes
- * the global lock appear as a standard mutex on the OS side.
- *
- *****************************************************************************/
-static acpi_thread_id acpi_ev_global_lock_thread_id;
-static int acpi_ev_global_lock_acquired;
-
-acpi_status acpi_ev_acquire_global_lock(u16 timeout)
-{
-	acpi_cpu_flags flags;
-	acpi_status status = AE_OK;
-	u8 acquired = FALSE;
-
-	ACPI_FUNCTION_TRACE(ev_acquire_global_lock);
-
-	/*
-	 * Only one thread can acquire the GL at a time, the global_lock_mutex
-	 * enforces this. This interface releases the interpreter if we must wait.
-	 */
-	status = acpi_ex_system_wait_mutex(
-			acpi_gbl_global_lock_mutex->mutex.os_mutex, 0);
-	if (status == AE_TIME) {
-		if (acpi_ev_global_lock_thread_id == acpi_os_get_thread_id()) {
-			acpi_ev_global_lock_acquired++;
-			return AE_OK;
-		}
-	}
-
-	if (ACPI_FAILURE(status)) {
-		status = acpi_ex_system_wait_mutex(
-				acpi_gbl_global_lock_mutex->mutex.os_mutex,
-				timeout);
-	}
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
-
-	acpi_ev_global_lock_thread_id = acpi_os_get_thread_id();
-	acpi_ev_global_lock_acquired++;
-
-	/*
-	 * Update the global lock handle and check for wraparound. The handle is
-	 * only used for the external global lock interfaces, but it is updated
-	 * here to properly handle the case where a single thread may acquire the
-	 * lock via both the AML and the acpi_acquire_global_lock interfaces. The
-	 * handle is therefore updated on the first acquire from a given thread
-	 * regardless of where the acquisition request originated.
-	 */
-	acpi_gbl_global_lock_handle++;
-	if (acpi_gbl_global_lock_handle == 0) {
-		acpi_gbl_global_lock_handle = 1;
-	}
-
-	/*
-	 * 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;
-		return_ACPI_STATUS(AE_OK);
-	}
-
-	flags = acpi_os_acquire_lock(acpi_ev_global_lock_pending_lock);
-
-	do {
-
-		/* Attempt to acquire the actual hardware lock */
-
-		ACPI_ACQUIRE_GLOBAL_LOCK(acpi_gbl_FACS, acquired);
-		if (acquired) {
-			acpi_gbl_global_lock_acquired = TRUE;
-
-			ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
-					  "Acquired hardware Global Lock\n"));
-			break;
-		}
-
-		acpi_ev_global_lock_pending = TRUE;
-
-		acpi_os_release_lock(acpi_ev_global_lock_pending_lock, flags);
-
-		/*
-		 * Did not get the lock. The pending bit was set above, and we
-		 * must wait until we get the global lock released interrupt.
-		 */
-		ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
-				  "Waiting for hardware Global Lock\n"));
-
-		/*
-		 * Wait for handshake with the global lock interrupt handler.
-		 * This interface releases the interpreter if we must wait.
-		 */
-		status = acpi_ex_system_wait_semaphore(
-						acpi_gbl_global_lock_semaphore,
-						ACPI_WAIT_FOREVER);
-
-		flags = acpi_os_acquire_lock(acpi_ev_global_lock_pending_lock);
-
-	} while (ACPI_SUCCESS(status));
-
-	acpi_ev_global_lock_pending = FALSE;
-
-	acpi_os_release_lock(acpi_ev_global_lock_pending_lock, flags);
-
-	return_ACPI_STATUS(status);
-}
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ev_release_global_lock
- *
- * PARAMETERS:  None
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Releases ownership of the Global Lock.
- *
- ******************************************************************************/
-
-acpi_status acpi_ev_release_global_lock(void)
-{
-	u8 pending = FALSE;
-	acpi_status status = AE_OK;
-
-	ACPI_FUNCTION_TRACE(ev_release_global_lock);
-
-	/* Lock must be already acquired */
-
-	if (!acpi_gbl_global_lock_acquired) {
-		ACPI_WARNING((AE_INFO,
-			      "Cannot release the ACPI Global Lock, it has not been acquired"));
-		return_ACPI_STATUS(AE_NOT_ACQUIRED);
-	}
-
-	acpi_ev_global_lock_acquired--;
-	if (acpi_ev_global_lock_acquired > 0) {
-		return AE_OK;
-	}
-
-	if (acpi_gbl_global_lock_present) {
-
-		/* Allow any thread to release the lock */
-
-		ACPI_RELEASE_GLOBAL_LOCK(acpi_gbl_FACS, pending);
-
-		/*
-		 * If the pending bit was set, we must write GBL_RLS to the control
-		 * register
-		 */
-		if (pending) {
-			status =
-			    acpi_write_bit_register
-			    (ACPI_BITREG_GLOBAL_LOCK_RELEASE,
-			     ACPI_ENABLE_EVENT);
-		}
-
-		ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
-				  "Released hardware Global Lock\n"));
-	}
-
-	acpi_gbl_global_lock_acquired = FALSE;
-
-	/* Release the local GL mutex */
-	acpi_ev_global_lock_thread_id = 0;
-	acpi_ev_global_lock_acquired = 0;
-	acpi_os_release_mutex(acpi_gbl_global_lock_mutex->mutex.os_mutex);
-	return_ACPI_STATUS(status);
-}
-
 /******************************************************************************
  *
  * FUNCTION:    acpi_ev_terminate
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index bea7223d7a71..f0edf5c43c03 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -55,6 +55,8 @@ static u8
 acpi_ev_has_default_handler(struct acpi_namespace_node *node,
 			    acpi_adr_space_type space_id);
 
+static void acpi_ev_orphan_ec_reg_method(void);
+
 static acpi_status
 acpi_ev_reg_run(acpi_handle obj_handle,
 		u32 level, void *context, void **return_value);
@@ -561,7 +563,9 @@ acpi_ev_detach_region(union acpi_operand_object *region_obj,
 
 			/* Now stop region accesses by executing the _REG method */
 
-			status = acpi_ev_execute_reg_method(region_obj, 0);
+			status =
+			    acpi_ev_execute_reg_method(region_obj,
+						       ACPI_REG_DISCONNECT);
 			if (ACPI_FAILURE(status)) {
 				ACPI_EXCEPTION((AE_INFO, status,
 						"from region _REG, [%s]",
@@ -1062,6 +1066,12 @@ acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
 					ACPI_NS_WALK_UNLOCK, acpi_ev_reg_run,
 					NULL, &space_id, NULL);
 
+	/* Special case for EC: handle "orphan" _REG methods with no region */
+
+	if (space_id == ACPI_ADR_SPACE_EC) {
+		acpi_ev_orphan_ec_reg_method();
+	}
+
 	return_ACPI_STATUS(status);
 }
 
@@ -1120,6 +1130,113 @@ acpi_ev_reg_run(acpi_handle obj_handle,
 		return (AE_OK);
 	}
 
-	status = acpi_ev_execute_reg_method(obj_desc, 1);
+	status = acpi_ev_execute_reg_method(obj_desc, ACPI_REG_CONNECT);
 	return (status);
 }
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ev_orphan_ec_reg_method
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Execute an "orphan" _REG method that appears under the EC
+ *              device. This is a _REG method that has no corresponding region
+ *              within the EC device scope. The orphan _REG method appears to
+ *              have been enabled by the description of the ECDT in the ACPI
+ *              specification: "The availability of the region space can be
+ *              detected by providing a _REG method object underneath the
+ *              Embedded Controller device."
+ *
+ *              To quickly access the EC device, we use the EC_ID that appears
+ *              within the ECDT. Otherwise, we would need to perform a time-
+ *              consuming namespace walk, executing _HID methods to find the
+ *              EC device.
+ *
+ ******************************************************************************/
+
+static void acpi_ev_orphan_ec_reg_method(void)
+{
+	struct acpi_table_ecdt *table;
+	acpi_status status;
+	struct acpi_object_list args;
+	union acpi_object objects[2];
+	struct acpi_namespace_node *ec_device_node;
+	struct acpi_namespace_node *reg_method;
+	struct acpi_namespace_node *next_node;
+
+	ACPI_FUNCTION_TRACE(ev_orphan_ec_reg_method);
+
+	/* Get the ECDT (if present in system) */
+
+	status = acpi_get_table(ACPI_SIG_ECDT, 0,
+				ACPI_CAST_INDIRECT_PTR(struct acpi_table_header,
+						       &table));
+	if (ACPI_FAILURE(status)) {
+		return_VOID;
+	}
+
+	/* We need a valid EC_ID string */
+
+	if (!(*table->id)) {
+		return_VOID;
+	}
+
+	/* Namespace is currently locked, must release */
+
+	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
+
+	/* Get a handle to the EC device referenced in the ECDT */
+
+	status = acpi_get_handle(NULL,
+				 ACPI_CAST_PTR(char, table->id),
+				 ACPI_CAST_PTR(acpi_handle, &ec_device_node));
+	if (ACPI_FAILURE(status)) {
+		goto exit;
+	}
+
+	/* Get a handle to a _REG method immediately under the EC device */
+
+	status = acpi_get_handle(ec_device_node,
+				 METHOD_NAME__REG, ACPI_CAST_PTR(acpi_handle,
+								 &reg_method));
+	if (ACPI_FAILURE(status)) {
+		goto exit;
+	}
+
+	/*
+	 * Execute the _REG method only if there is no Operation Region in
+	 * this scope with the Embedded Controller space ID. Otherwise, it
+	 * will already have been executed. Note, this allows for Regions
+	 * with other space IDs to be present; but the code below will then
+	 * execute the _REG method with the EC space ID argument.
+	 */
+	next_node = acpi_ns_get_next_node(ec_device_node, NULL);
+	while (next_node) {
+		if ((next_node->type == ACPI_TYPE_REGION) &&
+		    (next_node->object) &&
+		    (next_node->object->region.space_id == ACPI_ADR_SPACE_EC)) {
+			goto exit;	/* Do not execute _REG */
+		}
+		next_node = acpi_ns_get_next_node(ec_device_node, next_node);
+	}
+
+	/* Evaluate the _REG(EC,Connect) method */
+
+	args.count = 2;
+	args.pointer = objects;
+	objects[0].type = ACPI_TYPE_INTEGER;
+	objects[0].integer.value = ACPI_ADR_SPACE_EC;
+	objects[1].type = ACPI_TYPE_INTEGER;
+	objects[1].integer.value = ACPI_REG_CONNECT;
+
+	status = acpi_evaluate_object(reg_method, NULL, &args, NULL);
+
+      exit:
+	/* We ignore all errors from above, don't care */
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
+	return_VOID;
+}
diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c
index 9659cee6093e..55a5d35ef34a 100644
--- a/drivers/acpi/acpica/evrgnini.c
+++ b/drivers/acpi/acpica/evrgnini.c
@@ -637,7 +637,7 @@ acpi_ev_initialize_region(union acpi_operand_object *region_obj,
 
 					status =
 					    acpi_ev_execute_reg_method
-					    (region_obj, 1);
+					    (region_obj, ACPI_REG_CONNECT);
 
 					if (acpi_ns_locked) {
 						status =
diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c
index c85c8c45599d..00cd95692a91 100644
--- a/drivers/acpi/acpica/evxfregn.c
+++ b/drivers/acpi/acpica/evxfregn.c
@@ -130,20 +130,21 @@ acpi_install_address_space_handler(acpi_handle device,
 	case ACPI_ADR_SPACE_PCI_CONFIG:
 	case ACPI_ADR_SPACE_DATA_TABLE:
 
-		if (acpi_gbl_reg_methods_executed) {
+		if (!acpi_gbl_reg_methods_executed) {
 
-			/* Run all _REG methods for this address space */
-
-			status = acpi_ev_execute_reg_methods(node, space_id);
+			/* We will defer execution of the _REG methods for this space */
+			goto unlock_and_exit;
 		}
 		break;
 
 	default:
-
-		status = acpi_ev_execute_reg_methods(node, space_id);
 		break;
 	}
 
+	/* Run all _REG methods for this address space */
+
+	status = acpi_ev_execute_reg_methods(node, space_id);
+
       unlock_and_exit:
 	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
 	return_ACPI_STATUS(status);
diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c
index e7b372d17667..110711afada8 100644
--- a/drivers/acpi/acpica/excreate.c
+++ b/drivers/acpi/acpica/excreate.c
@@ -305,7 +305,8 @@ acpi_ex_create_region(u8 * aml_start,
 	 * range
 	 */
 	if ((region_space >= ACPI_NUM_PREDEFINED_REGIONS) &&
-	    (region_space < ACPI_USER_REGION_BEGIN)) {
+	    (region_space < ACPI_USER_REGION_BEGIN) &&
+	    (region_space != ACPI_ADR_SPACE_DATA_TABLE)) {
 		ACPI_ERROR((AE_INFO, "Invalid AddressSpace type 0x%X",
 			    region_space));
 		return_ACPI_STATUS(AE_AML_INVALID_SPACE_ID);
diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c
index 1d76ac85b5e7..ac7b854b0bd7 100644
--- a/drivers/acpi/acpica/nsrepair.c
+++ b/drivers/acpi/acpica/nsrepair.c
@@ -74,7 +74,6 @@ ACPI_MODULE_NAME("nsrepair")
  *
  * Additional possible repairs:
  *
- * Optional/unnecessary NULL package elements removed
  * Required package elements that are NULL replaced by Integer/String/Buffer
  * Incorrect standalone package wrapped with required outer package
  *
@@ -623,16 +622,12 @@ acpi_ns_remove_null_elements(struct acpi_predefined_data *data,
 	ACPI_FUNCTION_NAME(ns_remove_null_elements);
 
 	/*
-	 * PTYPE1 packages contain no subpackages.
-	 * PTYPE2 packages contain a variable number of sub-packages. We can
-	 * safely remove all NULL elements from the PTYPE2 packages.
+	 * We can safely remove all NULL elements from these package types:
+	 * PTYPE1_VAR packages contain a variable number of simple data types.
+	 * PTYPE2 packages contain a variable number of sub-packages.
 	 */
 	switch (package_type) {
-	case ACPI_PTYPE1_FIXED:
 	case ACPI_PTYPE1_VAR:
-	case ACPI_PTYPE1_OPTION:
-		return;
-
 	case ACPI_PTYPE2:
 	case ACPI_PTYPE2_COUNT:
 	case ACPI_PTYPE2_PKG_COUNT:
@@ -642,6 +637,8 @@ acpi_ns_remove_null_elements(struct acpi_predefined_data *data,
 		break;
 
 	default:
+	case ACPI_PTYPE1_FIXED:
+	case ACPI_PTYPE1_OPTION:
 		return;
 	}
 
diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c
index 136a814cec69..97cb36f85ce9 100644
--- a/drivers/acpi/acpica/utdecode.c
+++ b/drivers/acpi/acpica/utdecode.c
@@ -170,8 +170,7 @@ const char *acpi_gbl_region_types[ACPI_NUM_PREDEFINED_REGIONS] = {
 	"SMBus",
 	"SystemCMOS",
 	"PCIBARTarget",
-	"IPMI",
-	"DataTable"
+	"IPMI"
 };
 
 char *acpi_ut_get_region_name(u8 space_id)
@@ -179,6 +178,8 @@ char *acpi_ut_get_region_name(u8 space_id)
 
 	if (space_id >= ACPI_USER_REGION_BEGIN) {
 		return ("UserDefinedRegion");
+	} else if (space_id == ACPI_ADR_SPACE_DATA_TABLE) {
+		return ("DataTable");
 	} else if (space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) {
 		return ("FunctionalFixedHW");
 	} else if (space_id >= ACPI_NUM_PREDEFINED_REGIONS) {
diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c
index a946c689f03b..7d797e2baecd 100644
--- a/drivers/acpi/acpica/utmutex.c
+++ b/drivers/acpi/acpica/utmutex.c
@@ -83,9 +83,15 @@ acpi_status acpi_ut_mutex_initialize(void)
 
 	/* Create the spinlocks for use at interrupt level */
 
-	spin_lock_init(acpi_gbl_gpe_lock);
-	spin_lock_init(acpi_gbl_hardware_lock);
-	spin_lock_init(acpi_ev_global_lock_pending_lock);
+	status = acpi_os_create_lock (&acpi_gbl_gpe_lock);
+	if (ACPI_FAILURE (status)) {
+		return_ACPI_STATUS (status);
+	}
+
+	status = acpi_os_create_lock (&acpi_gbl_hardware_lock);
+	if (ACPI_FAILURE (status)) {
+		return_ACPI_STATUS (status);
+	}
 
 	/* Mutex for _OSI support */
 	status = acpi_os_create_mutex(&acpi_gbl_osi_mutex);
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 9749980ca6ca..d1e06c182cdb 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -227,7 +227,7 @@ static int __acpi_bus_set_power(struct acpi_device *device, int state)
 	acpi_status status = AE_OK;
 	char object_name[5] = { '_', 'P', 'S', '0' + state, '\0' };
 
-	if (!device || (state < ACPI_STATE_D0) || (state > ACPI_STATE_D3))
+	if (!device || (state < ACPI_STATE_D0) || (state > ACPI_STATE_D3_COLD))
 		return -EINVAL;
 
 	/* Make sure this is a valid target state */
diff --git a/drivers/acpi/custom_method.c b/drivers/acpi/custom_method.c
new file mode 100644
index 000000000000..5d42c2414ae5
--- /dev/null
+++ b/drivers/acpi/custom_method.c
@@ -0,0 +1,100 @@
+/*
+ * debugfs.c - ACPI debugfs interface to userspace.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <acpi/acpi_drivers.h>
+
+#include "internal.h"
+
+#define _COMPONENT		ACPI_SYSTEM_COMPONENT
+ACPI_MODULE_NAME("custom_method");
+MODULE_LICENSE("GPL");
+
+static struct dentry *cm_dentry;
+
+/* /sys/kernel/debug/acpi/custom_method */
+
+static ssize_t cm_write(struct file *file, const char __user * user_buf,
+			size_t count, loff_t *ppos)
+{
+	static char *buf;
+	static u32 max_size;
+	static u32 uncopied_bytes;
+
+	struct acpi_table_header table;
+	acpi_status status;
+
+	if (!(*ppos)) {
+		/* parse the table header to get the table length */
+		if (count <= sizeof(struct acpi_table_header))
+			return -EINVAL;
+		if (copy_from_user(&table, user_buf,
+				   sizeof(struct acpi_table_header)))
+			return -EFAULT;
+		uncopied_bytes = max_size = table.length;
+		buf = kzalloc(max_size, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+	}
+
+	if (buf == NULL)
+		return -EINVAL;
+
+	if ((*ppos > max_size) ||
+	    (*ppos + count > max_size) ||
+	    (*ppos + count < count) ||
+	    (count > uncopied_bytes))
+		return -EINVAL;
+
+	if (copy_from_user(buf + (*ppos), user_buf, count)) {
+		kfree(buf);
+		buf = NULL;
+		return -EFAULT;
+	}
+
+	uncopied_bytes -= count;
+	*ppos += count;
+
+	if (!uncopied_bytes) {
+		status = acpi_install_method(buf);
+		kfree(buf);
+		buf = NULL;
+		if (ACPI_FAILURE(status))
+			return -EINVAL;
+		add_taint(TAINT_OVERRIDDEN_ACPI_TABLE);
+	}
+
+	return count;
+}
+
+static const struct file_operations cm_fops = {
+	.write = cm_write,
+	.llseek = default_llseek,
+};
+
+static int __init acpi_custom_method_init(void)
+{
+	if (acpi_debugfs_dir == NULL)
+		return -ENOENT;
+
+	cm_dentry = debugfs_create_file("custom_method", S_IWUSR,
+					acpi_debugfs_dir, NULL, &cm_fops);
+	if (cm_dentry == NULL)
+		return -ENODEV;
+
+	return 0;
+}
+
+static void __exit acpi_custom_method_exit(void)
+{
+	if (cm_dentry)
+		debugfs_remove(cm_dentry);
+ }
+
+module_init(acpi_custom_method_init);
+module_exit(acpi_custom_method_exit);
diff --git a/drivers/acpi/debugfs.c b/drivers/acpi/debugfs.c
index 384f7abcff77..182a9fc36355 100644
--- a/drivers/acpi/debugfs.c
+++ b/drivers/acpi/debugfs.c
@@ -3,100 +3,16 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/uaccess.h>
 #include <linux/debugfs.h>
 #include <acpi/acpi_drivers.h>
 
 #define _COMPONENT		ACPI_SYSTEM_COMPONENT
 ACPI_MODULE_NAME("debugfs");
 
+struct dentry *acpi_debugfs_dir;
+EXPORT_SYMBOL_GPL(acpi_debugfs_dir);
 
-/* /sys/modules/acpi/parameters/aml_debug_output */
-
-module_param_named(aml_debug_output, acpi_gbl_enable_aml_debug_object,
-		   bool, 0644);
-MODULE_PARM_DESC(aml_debug_output,
-		 "To enable/disable the ACPI Debug Object output.");
-
-/* /sys/kernel/debug/acpi/custom_method */
-
-static ssize_t cm_write(struct file *file, const char __user * user_buf,
-			size_t count, loff_t *ppos)
+void __init acpi_debugfs_init(void)
 {
-	static char *buf;
-	static u32 max_size;
-	static u32 uncopied_bytes;
-
-	struct acpi_table_header table;
-	acpi_status status;
-
-	if (!(*ppos)) {
-		/* parse the table header to get the table length */
-		if (count <= sizeof(struct acpi_table_header))
-			return -EINVAL;
-		if (copy_from_user(&table, user_buf,
-				   sizeof(struct acpi_table_header)))
-			return -EFAULT;
-		uncopied_bytes = max_size = table.length;
-		buf = kzalloc(max_size, GFP_KERNEL);
-		if (!buf)
-			return -ENOMEM;
-	}
-
-	if (buf == NULL)
-		return -EINVAL;
-
-	if ((*ppos > max_size) ||
-	    (*ppos + count > max_size) ||
-	    (*ppos + count < count) ||
-	    (count > uncopied_bytes))
-		return -EINVAL;
-
-	if (copy_from_user(buf + (*ppos), user_buf, count)) {
-		kfree(buf);
-		buf = NULL;
-		return -EFAULT;
-	}
-
-	uncopied_bytes -= count;
-	*ppos += count;
-
-	if (!uncopied_bytes) {
-		status = acpi_install_method(buf);
-		kfree(buf);
-		buf = NULL;
-		if (ACPI_FAILURE(status))
-			return -EINVAL;
-		add_taint(TAINT_OVERRIDDEN_ACPI_TABLE);
-	}
-
-	return count;
-}
-
-static const struct file_operations cm_fops = {
-	.write = cm_write,
-	.llseek = default_llseek,
-};
-
-int __init acpi_debugfs_init(void)
-{
-	struct dentry *acpi_dir, *cm_dentry;
-
-	acpi_dir = debugfs_create_dir("acpi", NULL);
-	if (!acpi_dir)
-		goto err;
-
-	cm_dentry = debugfs_create_file("custom_method", S_IWUSR,
-					acpi_dir, NULL, &cm_fops);
-	if (!cm_dentry)
-		goto err;
-
-	return 0;
-
-err:
-	if (acpi_dir)
-		debugfs_remove(acpi_dir);
-	return -EINVAL;
+	acpi_debugfs_dir = debugfs_create_dir("acpi", NULL);
 }
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index fa848c4116a8..b19a18dd994f 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -69,7 +69,6 @@ enum ec_command {
 
 #define ACPI_EC_DELAY		500	/* Wait 500ms max. during EC ops */
 #define ACPI_EC_UDELAY_GLK	1000	/* Wait 1ms max. to get global lock */
-#define ACPI_EC_CDELAY		10	/* Wait 10us before polling EC */
 #define ACPI_EC_MSI_UDELAY	550	/* Wait 550us for MSI EC */
 
 #define ACPI_EC_STORM_THRESHOLD 8	/* number of false interrupts
@@ -433,8 +432,7 @@ EXPORT_SYMBOL(ec_write);
 
 int ec_transaction(u8 command,
 		   const u8 * wdata, unsigned wdata_len,
-		   u8 * rdata, unsigned rdata_len,
-		   int force_poll)
+		   u8 * rdata, unsigned rdata_len)
 {
 	struct transaction t = {.command = command,
 				.wdata = wdata, .rdata = rdata,
@@ -592,8 +590,6 @@ static void acpi_ec_gpe_query(void *ec_cxt)
 	mutex_unlock(&ec->lock);
 }
 
-static void acpi_ec_gpe_query(void *ec_cxt);
-
 static int ec_check_sci(struct acpi_ec *ec, u8 state)
 {
 	if (state & ACPI_EC_FLAG_SCI) {
@@ -808,8 +804,6 @@ static int acpi_ec_add(struct acpi_device *device)
 			return -EINVAL;
 	}
 
-	ec->handle = device->handle;
-
 	/* Find and register all query methods */
 	acpi_walk_namespace(ACPI_TYPE_METHOD, ec->handle, 1,
 			    acpi_ec_register_query_methods, NULL, ec, NULL);
@@ -938,8 +932,19 @@ static struct dmi_system_id __initdata ec_dmi_table[] = {
 	ec_flag_msi, "MSI hardware", {
 	DMI_MATCH(DMI_CHASSIS_VENDOR, "MICRO-STAR")}, NULL},
 	{
+	ec_flag_msi, "Quanta hardware", {
+	DMI_MATCH(DMI_SYS_VENDOR, "Quanta"),
+	DMI_MATCH(DMI_PRODUCT_NAME, "TW8/SW8/DW8"),}, NULL},
+	{
+	ec_flag_msi, "Quanta hardware", {
+	DMI_MATCH(DMI_SYS_VENDOR, "Quanta"),
+	DMI_MATCH(DMI_PRODUCT_NAME, "TW9/SW9"),}, NULL},
+	{
 	ec_validate_ecdt, "ASUS hardware", {
 	DMI_MATCH(DMI_BIOS_VENDOR, "ASUS") }, NULL},
+	{
+	ec_validate_ecdt, "ASUS hardware", {
+	DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer Inc.") }, NULL},
 	{},
 };
 
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 4bfb759deb10..ca75b9ce0489 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -28,9 +28,10 @@ int acpi_scan_init(void);
 int acpi_sysfs_init(void);
 
 #ifdef CONFIG_DEBUG_FS
+extern struct dentry *acpi_debugfs_dir;
 int acpi_debugfs_init(void);
 #else
-static inline int acpi_debugfs_init(void) { return 0; }
+static inline void acpi_debugfs_init(void) { return; }
 #endif
 
 /* --------------------------------------------------------------------------
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 45ad4ffef533..52ca9649d769 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -902,14 +902,6 @@ void acpi_os_wait_events_complete(void *context)
 
 EXPORT_SYMBOL(acpi_os_wait_events_complete);
 
-/*
- * Deallocate the memory for a spinlock.
- */
-void acpi_os_delete_lock(acpi_spinlock handle)
-{
-	return;
-}
-
 acpi_status
 acpi_os_create_semaphore(u32 max_units, u32 initial_units, acpi_handle * handle)
 {
@@ -1341,6 +1333,31 @@ int acpi_resources_are_enforced(void)
 EXPORT_SYMBOL(acpi_resources_are_enforced);
 
 /*
+ * Create and initialize a spinlock.
+ */
+acpi_status
+acpi_os_create_lock(acpi_spinlock *out_handle)
+{
+	spinlock_t *lock;
+
+	lock = ACPI_ALLOCATE(sizeof(spinlock_t));
+	if (!lock)
+		return AE_NO_MEMORY;
+	spin_lock_init(lock);
+	*out_handle = lock;
+
+	return AE_OK;
+}
+
+/*
+ * Deallocate the memory for a spinlock.
+ */
+void acpi_os_delete_lock(acpi_spinlock handle)
+{
+	ACPI_FREE(handle);
+}
+
+/*
  * Acquire a spinlock.
  *
  * handle is a pointer to the spinlock_t.
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index 25bf17da69fd..02d2a4c9084d 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -37,7 +37,6 @@ static struct dmi_system_id __initdata processor_idle_dmi_table[] = {
 	{},
 };
 
-#ifdef CONFIG_SMP
 static int map_lapic_id(struct acpi_subtable_header *entry,
 		 u32 acpi_id, int *apic_id)
 {
@@ -165,7 +164,9 @@ exit:
 
 int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
 {
+#ifdef CONFIG_SMP
 	int i;
+#endif
 	int apic_id = -1;
 
 	apic_id = map_mat_entry(handle, type, acpi_id);
@@ -174,14 +175,19 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
 	if (apic_id == -1)
 		return apic_id;
 
+#ifdef CONFIG_SMP
 	for_each_possible_cpu(i) {
 		if (cpu_physical_id(i) == apic_id)
 			return i;
 	}
+#else
+	/* In UP kernel, only processor 0 is valid */
+	if (apic_id == 0)
+		return apic_id;
+#endif
 	return -1;
 }
 EXPORT_SYMBOL_GPL(acpi_get_cpuid);
-#endif
 
 static bool __init processor_physically_present(acpi_handle handle)
 {
@@ -217,7 +223,7 @@ static bool __init processor_physically_present(acpi_handle handle)
 	type = (acpi_type == ACPI_TYPE_DEVICE) ? 1 : 0;
 	cpuid = acpi_get_cpuid(handle, type, acpi_id);
 
-	if ((cpuid == -1) && (num_possible_cpus() > 1))
+	if (cpuid == -1)
 		return false;
 
 	return true;
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index d615b7d69bca..431ab11c8c1b 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -161,7 +161,7 @@ static void lapic_timer_check_state(int state, struct acpi_processor *pr,
 	if (cpu_has(&cpu_data(pr->id), X86_FEATURE_ARAT))
 		return;
 
-	if (c1e_detected)
+	if (amd_e400_c1e_detected)
 		type = ACPI_STATE_C1;
 
 	/*
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 61891e75583d..77255f250dbb 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -220,6 +220,14 @@ module_param_call(trace_state, param_set_trace_state, param_get_trace_state,
 		  NULL, 0644);
 #endif /* CONFIG_ACPI_DEBUG */
 
+
+/* /sys/modules/acpi/parameters/aml_debug_output */
+
+module_param_named(aml_debug_output, acpi_gbl_enable_aml_debug_object,
+		   bool, 0644);
+MODULE_PARM_DESC(aml_debug_output,
+		 "To enable/disable the ACPI Debug Object output.");
+
 /* /sys/module/acpi/parameters/acpica_version */
 static int param_get_acpica_version(char *buffer, struct kernel_param *kp)
 {
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 7025593a58c8..d74926e0939e 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -603,6 +603,10 @@ int amba_device_register(struct amba_device *dev, struct resource *parent)
 	if (ret)
 		goto err_out;
 
+	/* Hard-coded primecell ID instead of plug-n-play */
+	if (dev->periphid != 0)
+		goto skip_probe;
+
 	/*
 	 * Dynamically calculate the size of the resource
 	 * and use this for iomap
@@ -643,6 +647,7 @@ int amba_device_register(struct amba_device *dev, struct resource *parent)
 	if (ret)
 		goto err_release;
 
+ skip_probe:
 	ret = device_add(&dev->dev);
 	if (ret)
 		goto err_release;
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 736bee5dafeb..000d03ae6653 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4143,9 +4143,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	 * Devices which choke on SETXFER.  Applies only if both the
 	 * device and controller are SATA.
 	 */
-	{ "PIONEER DVD-RW  DVRTD08",	"1.00",	ATA_HORKAGE_NOSETXFER },
-	{ "PIONEER DVD-RW  DVR-212D",	"1.28", ATA_HORKAGE_NOSETXFER },
-	{ "PIONEER DVD-RW  DVR-216D",	"1.08", ATA_HORKAGE_NOSETXFER },
+	{ "PIONEER DVD-RW  DVRTD08",	NULL,	ATA_HORKAGE_NOSETXFER },
+	{ "PIONEER DVD-RW  DVR-212D",	NULL,	ATA_HORKAGE_NOSETXFER },
+	{ "PIONEER DVD-RW  DVR-216D",	NULL,	ATA_HORKAGE_NOSETXFER },
 
 	/* End Marker */
 	{ }
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index dfb6e9d3d759..7f099d6e4e0b 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -2802,10 +2802,11 @@ int ata_eh_reset(struct ata_link *link, int classify,
 	}
 
 	/*
-	 * Some controllers can't be frozen very well and may set
-	 * spuruious error conditions during reset.  Clear accumulated
-	 * error information.  As reset is the final recovery action,
-	 * nothing is lost by doing this.
+	 * Some controllers can't be frozen very well and may set spurious
+	 * error conditions during reset.  Clear accumulated error
+	 * information and re-thaw the port if frozen.  As reset is the
+	 * final recovery action and we cross check link onlineness against
+	 * device classification later, no hotplug event is lost by this.
 	 */
 	spin_lock_irqsave(link->ap->lock, flags);
 	memset(&link->eh_info, 0, sizeof(link->eh_info));
@@ -2814,6 +2815,9 @@ int ata_eh_reset(struct ata_link *link, int classify,
 	ap->pflags &= ~ATA_PFLAG_EH_PENDING;
 	spin_unlock_irqrestore(link->ap->lock, flags);
 
+	if (ap->pflags & ATA_PFLAG_FROZEN)
+		ata_eh_thaw_port(ap);
+
 	/*
 	 * Make sure onlineness and classification result correspond.
 	 * Hotplug could have happened during reset and some
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index d51f9795c064..927f968e99d9 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3797,6 +3797,12 @@ EXPORT_SYMBOL_GPL(ata_sas_port_alloc);
  */
 int ata_sas_port_start(struct ata_port *ap)
 {
+	/*
+	 * the port is marked as frozen at allocation time, but if we don't
+	 * have new eh, we won't thaw it
+	 */
+	if (!ap->ops->error_handler)
+		ap->pflags &= ~ATA_PFLAG_FROZEN;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ata_sas_port_start);
diff --git a/drivers/ata/pata_marvell.c b/drivers/ata/pata_marvell.c
index 75a6a0c0094f..5d7f58a7e34d 100644
--- a/drivers/ata/pata_marvell.c
+++ b/drivers/ata/pata_marvell.c
@@ -161,6 +161,9 @@ static const struct pci_device_id marvell_pci_tbl[] = {
 	{ PCI_DEVICE(0x11AB, 0x6121), },
 	{ PCI_DEVICE(0x11AB, 0x6123), },
 	{ PCI_DEVICE(0x11AB, 0x6145), },
+	{ PCI_DEVICE(0x1B4B, 0x91A0), },
+	{ PCI_DEVICE(0x1B4B, 0x91A4), },
+
 	{ }	/* terminate list */
 };
 
diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c
index 1c4b3aa4c7c4..dc88a39e7db8 100644
--- a/drivers/ata/sata_dwc_460ex.c
+++ b/drivers/ata/sata_dwc_460ex.c
@@ -389,7 +389,7 @@ static void sata_dwc_tf_dump(struct ata_taskfile *tf)
 /*
  * Function: get_burst_length_encode
  * arguments: datalength: length in bytes of data
- * returns value to be programmed in register corrresponding to data length
+ * returns value to be programmed in register corresponding to data length
  * This value is effectively the log(base 2) of the length
  */
 static  int get_burst_length_encode(int datalength)
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index c0dd09df7be8..ad367c4139b1 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -291,7 +291,7 @@ static int pm_runtime_clk_notify(struct notifier_block *nb,
 {
 	struct pm_clk_notifier_block *clknb;
 	struct device *dev = data;
-	char *con_id;
+	char **con_id;
 	int error;
 
 	dev_dbg(dev, "%s() %ld\n", __func__, action);
@@ -309,8 +309,8 @@ static int pm_runtime_clk_notify(struct notifier_block *nb,
 
 		dev->pwr_domain = clknb->pwr_domain;
 		if (clknb->con_ids[0]) {
-			for (con_id = clknb->con_ids[0]; *con_id; con_id++)
-				pm_runtime_clk_add(dev, con_id);
+			for (con_id = clknb->con_ids; *con_id; con_id++)
+				pm_runtime_clk_add(dev, *con_id);
 		} else {
 			pm_runtime_clk_add(dev, NULL);
 		}
@@ -380,25 +380,25 @@ static int pm_runtime_clk_notify(struct notifier_block *nb,
 {
 	struct pm_clk_notifier_block *clknb;
 	struct device *dev = data;
-	char *con_id;
+	char **con_id;
 
 	dev_dbg(dev, "%s() %ld\n", __func__, action);
 
 	clknb = container_of(nb, struct pm_clk_notifier_block, nb);
 
 	switch (action) {
-	case BUS_NOTIFY_ADD_DEVICE:
+	case BUS_NOTIFY_BIND_DRIVER:
 		if (clknb->con_ids[0]) {
-			for (con_id = clknb->con_ids[0]; *con_id; con_id++)
-				enable_clock(dev, con_id);
+			for (con_id = clknb->con_ids; *con_id; con_id++)
+				enable_clock(dev, *con_id);
 		} else {
 			enable_clock(dev, NULL);
 		}
 		break;
-	case BUS_NOTIFY_DEL_DEVICE:
+	case BUS_NOTIFY_UNBOUND_DRIVER:
 		if (clknb->con_ids[0]) {
-			for (con_id = clknb->con_ids[0]; *con_id; con_id++)
-				disable_clock(dev, con_id);
+			for (con_id = clknb->con_ids; *con_id; con_id++)
+				disable_clock(dev, *con_id);
 		} else {
 			disable_clock(dev, NULL);
 		}
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index aa6320207745..06f09bf89cb2 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -57,7 +57,8 @@ static int async_error;
  */
 void device_pm_init(struct device *dev)
 {
-	dev->power.in_suspend = false;
+	dev->power.is_prepared = false;
+	dev->power.is_suspended = false;
 	init_completion(&dev->power.completion);
 	complete_all(&dev->power.completion);
 	dev->power.wakeup = NULL;
@@ -91,7 +92,7 @@ void device_pm_add(struct device *dev)
 	pr_debug("PM: Adding info for %s:%s\n",
 		 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
 	mutex_lock(&dpm_list_mtx);
-	if (dev->parent && dev->parent->power.in_suspend)
+	if (dev->parent && dev->parent->power.is_prepared)
 		dev_warn(dev, "parent %s should not be sleeping\n",
 			dev_name(dev->parent));
 	list_add_tail(&dev->power.entry, &dpm_list);
@@ -511,7 +512,14 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)
 	dpm_wait(dev->parent, async);
 	device_lock(dev);
 
-	dev->power.in_suspend = false;
+	/*
+	 * This is a fib.  But we'll allow new children to be added below
+	 * a resumed device, even if the device hasn't been completed yet.
+	 */
+	dev->power.is_prepared = false;
+
+	if (!dev->power.is_suspended)
+		goto Unlock;
 
 	if (dev->pwr_domain) {
 		pm_dev_dbg(dev, state, "power domain ");
@@ -548,6 +556,9 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)
 	}
 
  End:
+	dev->power.is_suspended = false;
+
+ Unlock:
 	device_unlock(dev);
 	complete_all(&dev->power.completion);
 
@@ -670,7 +681,7 @@ void dpm_complete(pm_message_t state)
 		struct device *dev = to_device(dpm_prepared_list.prev);
 
 		get_device(dev);
-		dev->power.in_suspend = false;
+		dev->power.is_prepared = false;
 		list_move(&dev->power.entry, &list);
 		mutex_unlock(&dpm_list_mtx);
 
@@ -835,11 +846,11 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	device_lock(dev);
 
 	if (async_error)
-		goto End;
+		goto Unlock;
 
 	if (pm_wakeup_pending()) {
 		async_error = -EBUSY;
-		goto End;
+		goto Unlock;
 	}
 
 	if (dev->pwr_domain) {
@@ -877,6 +888,9 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	}
 
  End:
+	dev->power.is_suspended = !error;
+
+ Unlock:
 	device_unlock(dev);
 	complete_all(&dev->power.completion);
 
@@ -1042,7 +1056,7 @@ int dpm_prepare(pm_message_t state)
 			put_device(dev);
 			break;
 		}
-		dev->power.in_suspend = true;
+		dev->power.is_prepared = true;
 		if (!list_empty(&dev->power.entry))
 			list_move_tail(&dev->power.entry, &dpm_prepared_list);
 		put_device(dev);
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index b7f51e4594f8..dba1c32e1ddf 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -35,10 +35,6 @@
  */
 struct brd_device {
 	int		brd_number;
-	int		brd_refcnt;
-	loff_t		brd_offset;
-	loff_t		brd_sizelimit;
-	unsigned	brd_blocksize;
 
 	struct request_queue	*brd_queue;
 	struct gendisk		*brd_disk;
@@ -440,11 +436,11 @@ static int rd_nr;
 int rd_size = CONFIG_BLK_DEV_RAM_SIZE;
 static int max_part;
 static int part_shift;
-module_param(rd_nr, int, 0);
+module_param(rd_nr, int, S_IRUGO);
 MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices");
-module_param(rd_size, int, 0);
+module_param(rd_size, int, S_IRUGO);
 MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");
-module_param(max_part, int, 0);
+module_param(max_part, int, S_IRUGO);
 MODULE_PARM_DESC(max_part, "Maximum number of partitions per RAM disk");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR);
@@ -552,7 +548,7 @@ static struct kobject *brd_probe(dev_t dev, int *part, void *data)
 	struct kobject *kobj;
 
 	mutex_lock(&brd_devices_mutex);
-	brd = brd_init_one(dev & MINORMASK);
+	brd = brd_init_one(MINOR(dev) >> part_shift);
 	kobj = brd ? get_disk(brd->brd_disk) : ERR_PTR(-ENOMEM);
 	mutex_unlock(&brd_devices_mutex);
 
@@ -575,25 +571,39 @@ static int __init brd_init(void)
 	 *
 	 * (1) if rd_nr is specified, create that many upfront, and this
 	 *     also becomes a hard limit.
-	 * (2) if rd_nr is not specified, create 1 rd device on module
-	 *     load, user can further extend brd device by create dev node
-	 *     themselves and have kernel automatically instantiate actual
-	 *     device on-demand.
+	 * (2) if rd_nr is not specified, create CONFIG_BLK_DEV_RAM_COUNT
+	 *     (default 16) rd device on module load, user can further
+	 *     extend brd device by create dev node themselves and have
+	 *     kernel automatically instantiate actual device on-demand.
 	 */
 
 	part_shift = 0;
-	if (max_part > 0)
+	if (max_part > 0) {
 		part_shift = fls(max_part);
 
+		/*
+		 * Adjust max_part according to part_shift as it is exported
+		 * to user space so that user can decide correct minor number
+		 * if [s]he want to create more devices.
+		 *
+		 * Note that -1 is required because partition 0 is reserved
+		 * for the whole disk.
+		 */
+		max_part = (1UL << part_shift) - 1;
+	}
+
+	if ((1UL << part_shift) > DISK_MAX_PARTS)
+		return -EINVAL;
+
 	if (rd_nr > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
 
 	if (rd_nr) {
 		nr = rd_nr;
-		range = rd_nr;
+		range = rd_nr << part_shift;
 	} else {
 		nr = CONFIG_BLK_DEV_RAM_COUNT;
-		range = 1UL << (MINORBITS - part_shift);
+		range = 1UL << MINORBITS;
 	}
 
 	if (register_blkdev(RAMDISK_MAJOR, "ramdisk"))
@@ -632,7 +642,7 @@ static void __exit brd_exit(void)
 	unsigned long range;
 	struct brd_device *brd, *next;
 
-	range = rd_nr ? rd_nr :  1UL << (MINORBITS - part_shift);
+	range = rd_nr ? rd_nr << part_shift : 1UL << MINORBITS;
 
 	list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
 		brd_del_one(brd);
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index db8f88586c8d..98de8f418676 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -1038,6 +1038,7 @@ static void floppy_disable_hlt(void)
 {
 	unsigned long flags;
 
+	WARN_ONCE(1, "floppy_disable_hlt() scheduled for removal in 2012");
 	spin_lock_irqsave(&floppy_hlt_lock, flags);
 	if (!hlt_disabled) {
 		hlt_disabled = 1;
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index c59a672a3de0..76c8da78212b 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1540,9 +1540,9 @@ static const struct block_device_operations lo_fops = {
  * And now the modules code and kernel interface.
  */
 static int max_loop;
-module_param(max_loop, int, 0);
+module_param(max_loop, int, S_IRUGO);
 MODULE_PARM_DESC(max_loop, "Maximum number of loop devices");
-module_param(max_part, int, 0);
+module_param(max_part, int, S_IRUGO);
 MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);
@@ -1688,9 +1688,20 @@ static int __init loop_init(void)
 	 */
 
 	part_shift = 0;
-	if (max_part > 0)
+	if (max_part > 0) {
 		part_shift = fls(max_part);
 
+		/*
+		 * Adjust max_part according to part_shift as it is exported
+		 * to user space so that user can decide correct minor number
+		 * if [s]he want to create more devices.
+		 *
+		 * Note that -1 is required because partition 0 is reserved
+		 * for the whole disk.
+		 */
+		max_part = (1UL << part_shift) - 1;
+	}
+
 	if ((1UL << part_shift) > DISK_MAX_PARTS)
 		return -EINVAL;
 
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index e6fc716aca45..f533f3375e24 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -192,7 +192,8 @@ static int sock_xmit(struct nbd_device *lo, int send, void *buf, int size,
 			if (lo->xmit_timeout)
 				del_timer_sync(&ti);
 		} else
-			result = kernel_recvmsg(sock, &msg, &iov, 1, size, 0);
+			result = kernel_recvmsg(sock, &msg, &iov, 1, size,
+						msg.msg_flags);
 
 		if (signal_pending(current)) {
 			siginfo_t info;
@@ -753,9 +754,26 @@ static int __init nbd_init(void)
 		return -ENOMEM;
 
 	part_shift = 0;
-	if (max_part > 0)
+	if (max_part > 0) {
 		part_shift = fls(max_part);
 
+		/*
+		 * Adjust max_part according to part_shift as it is exported
+		 * to user space so that user can know the max number of
+		 * partition kernel should be able to manage.
+		 *
+		 * Note that -1 is required because partition 0 is reserved
+		 * for the whole disk.
+		 */
+		max_part = (1UL << part_shift) - 1;
+	}
+
+	if ((1UL << part_shift) > DISK_MAX_PARTS)
+		return -EINVAL;
+
+	if (nbds_max > 1UL << (MINORBITS - part_shift))
+		return -EINVAL;
+
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = alloc_disk(1 << part_shift);
 		if (!disk)
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index a0aabd904a51..46b8136c31bb 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -321,7 +321,6 @@ static void pcd_init_units(void)
 		strcpy(disk->disk_name, cd->name);	/* umm... */
 		disk->fops = &pcd_bdops;
 		disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-		disk->events = DISK_EVENT_MEDIA_CHANGE;
 	}
 }
 
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 6ecf89cdf006..079c08808d8a 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -6,10 +6,13 @@
 #include <linux/virtio.h>
 #include <linux/virtio_blk.h>
 #include <linux/scatterlist.h>
+#include <linux/string_helpers.h>
+#include <scsi/scsi_cmnd.h>
 
 #define PART_BITS 4
 
 static int major, index;
+struct workqueue_struct *virtblk_wq;
 
 struct virtio_blk
 {
@@ -26,6 +29,9 @@ struct virtio_blk
 
 	mempool_t *pool;
 
+	/* Process context for config space updates */
+	struct work_struct config_work;
+
 	/* What host tells us, plus 2 for header & tailer. */
 	unsigned int sg_elems;
 
@@ -141,7 +147,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 	num = blk_rq_map_sg(q, vbr->req, vblk->sg + out);
 
 	if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC) {
-		sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, 96);
+		sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
 		sg_set_buf(&vblk->sg[num + out + in++], &vbr->in_hdr,
 			   sizeof(vbr->in_hdr));
 	}
@@ -291,6 +297,46 @@ static ssize_t virtblk_serial_show(struct device *dev,
 }
 DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
 
+static void virtblk_config_changed_work(struct work_struct *work)
+{
+	struct virtio_blk *vblk =
+		container_of(work, struct virtio_blk, config_work);
+	struct virtio_device *vdev = vblk->vdev;
+	struct request_queue *q = vblk->disk->queue;
+	char cap_str_2[10], cap_str_10[10];
+	u64 capacity, size;
+
+	/* Host must always specify the capacity. */
+	vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity),
+			  &capacity, sizeof(capacity));
+
+	/* If capacity is too big, truncate with warning. */
+	if ((sector_t)capacity != capacity) {
+		dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n",
+			 (unsigned long long)capacity);
+		capacity = (sector_t)-1;
+	}
+
+	size = capacity * queue_logical_block_size(q);
+	string_get_size(size, STRING_UNITS_2, cap_str_2, sizeof(cap_str_2));
+	string_get_size(size, STRING_UNITS_10, cap_str_10, sizeof(cap_str_10));
+
+	dev_notice(&vdev->dev,
+		  "new size: %llu %d-byte logical blocks (%s/%s)\n",
+		  (unsigned long long)capacity,
+		  queue_logical_block_size(q),
+		  cap_str_10, cap_str_2);
+
+	set_capacity(vblk->disk, capacity);
+}
+
+static void virtblk_config_changed(struct virtio_device *vdev)
+{
+	struct virtio_blk *vblk = vdev->priv;
+
+	queue_work(virtblk_wq, &vblk->config_work);
+}
+
 static int __devinit virtblk_probe(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk;
@@ -327,6 +373,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 	vblk->vdev = vdev;
 	vblk->sg_elems = sg_elems;
 	sg_init_table(vblk->sg, vblk->sg_elems);
+	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
 
 	/* We expect one virtqueue, for output. */
 	vblk->vq = virtio_find_single_vq(vdev, blk_done, "requests");
@@ -477,6 +524,8 @@ static void __devexit virtblk_remove(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
 
+	flush_work(&vblk->config_work);
+
 	/* Nothing should be pending. */
 	BUG_ON(!list_empty(&vblk->reqs));
 
@@ -508,27 +557,47 @@ static unsigned int features[] = {
  * Use __refdata to avoid this warning.
  */
 static struct virtio_driver __refdata virtio_blk = {
-	.feature_table = features,
-	.feature_table_size = ARRAY_SIZE(features),
-	.driver.name =	KBUILD_MODNAME,
-	.driver.owner =	THIS_MODULE,
-	.id_table =	id_table,
-	.probe =	virtblk_probe,
-	.remove =	__devexit_p(virtblk_remove),
+	.feature_table		= features,
+	.feature_table_size	= ARRAY_SIZE(features),
+	.driver.name		= KBUILD_MODNAME,
+	.driver.owner		= THIS_MODULE,
+	.id_table		= id_table,
+	.probe			= virtblk_probe,
+	.remove			= __devexit_p(virtblk_remove),
+	.config_changed		= virtblk_config_changed,
 };
 
 static int __init init(void)
 {
+	int error;
+
+	virtblk_wq = alloc_workqueue("virtio-blk", 0, 0);
+	if (!virtblk_wq)
+		return -ENOMEM;
+
 	major = register_blkdev(0, "virtblk");
-	if (major < 0)
-		return major;
-	return register_virtio_driver(&virtio_blk);
+	if (major < 0) {
+		error = major;
+		goto out_destroy_workqueue;
+	}
+
+	error = register_virtio_driver(&virtio_blk);
+	if (error)
+		goto out_unregister_blkdev;
+	return 0;
+
+out_unregister_blkdev:
+	unregister_blkdev(major, "virtblk");
+out_destroy_workqueue:
+	destroy_workqueue(virtblk_wq);
+	return error;
 }
 
 static void __exit fini(void)
 {
 	unregister_blkdev(major, "virtblk");
 	unregister_virtio_driver(&virtio_blk);
+	destroy_workqueue(virtblk_wq);
 }
 module_init(init);
 module_exit(fini);
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index c73910cc28c9..5cf2993a8338 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -809,11 +809,13 @@ static int __init xen_blkif_init(void)
  failed_init:
 	kfree(blkbk->pending_reqs);
 	kfree(blkbk->pending_grant_handles);
-	for (i = 0; i < mmap_pages; i++) {
-		if (blkbk->pending_pages[i])
-			__free_page(blkbk->pending_pages[i]);
+	if (blkbk->pending_pages) {
+		for (i = 0; i < mmap_pages; i++) {
+			if (blkbk->pending_pages[i])
+				__free_page(blkbk->pending_pages[i]);
+		}
+		kfree(blkbk->pending_pages);
 	}
-	kfree(blkbk->pending_pages);
 	kfree(blkbk);
 	blkbk = NULL;
 	return rc;
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 34570823355b..6cc0db1bf522 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -357,14 +357,13 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 	}
 
 	vbd->bdev = bdev;
-	vbd->size = vbd_sz(vbd);
-
 	if (vbd->bdev->bd_disk == NULL) {
 		DPRINTK("xen_vbd_create: device %08x doesn't exist.\n",
 			vbd->pdevice);
 		xen_vbd_free(vbd);
 		return -ENOENT;
 	}
+	vbd->size = vbd_sz(vbd);
 
 	if (vbd->bdev->bd_disk->flags & GENHD_FL_CD || cdrom)
 		vbd->type |= VDISK_CDROM;
diff --git a/drivers/bluetooth/btmrvl_debugfs.c b/drivers/bluetooth/btmrvl_debugfs.c
index fd6305bf953e..8ecf4c6c2874 100644
--- a/drivers/bluetooth/btmrvl_debugfs.c
+++ b/drivers/bluetooth/btmrvl_debugfs.c
@@ -64,6 +64,8 @@ static ssize_t btmrvl_hscfgcmd_write(struct file *file,
 		return -EFAULT;
 
 	ret = strict_strtol(buf, 10, &result);
+	if (ret)
+		return ret;
 
 	priv->btmrvl_dev.hscfgcmd = result;
 
@@ -108,6 +110,8 @@ static ssize_t btmrvl_psmode_write(struct file *file, const char __user *ubuf,
 		return -EFAULT;
 
 	ret = strict_strtol(buf, 10, &result);
+	if (ret)
+		return ret;
 
 	priv->btmrvl_dev.psmode = result;
 
@@ -147,6 +151,8 @@ static ssize_t btmrvl_pscmd_write(struct file *file, const char __user *ubuf,
 		return -EFAULT;
 
 	ret = strict_strtol(buf, 10, &result);
+	if (ret)
+		return ret;
 
 	priv->btmrvl_dev.pscmd = result;
 
@@ -191,6 +197,8 @@ static ssize_t btmrvl_gpiogap_write(struct file *file, const char __user *ubuf,
 		return -EFAULT;
 
 	ret = strict_strtol(buf, 16, &result);
+	if (ret)
+		return ret;
 
 	priv->btmrvl_dev.gpio_gap = result;
 
@@ -230,6 +238,8 @@ static ssize_t btmrvl_hscmd_write(struct file *file, const char __user *ubuf,
 		return -EFAULT;
 
 	ret = strict_strtol(buf, 10, &result);
+	if (ret)
+		return ret;
 
 	priv->btmrvl_dev.hscmd = result;
 	if (priv->btmrvl_dev.hscmd) {
@@ -272,6 +282,8 @@ static ssize_t btmrvl_hsmode_write(struct file *file, const char __user *ubuf,
 		return -EFAULT;
 
 	ret = strict_strtol(buf, 10, &result);
+	if (ret)
+		return ret;
 
 	priv->btmrvl_dev.hsmode = result;
 
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index b3f01996318f..48ad2a7ab080 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -355,29 +355,24 @@ static void hci_uart_tty_wakeup(struct tty_struct *tty)
  *             flags        pointer to flags for data
  *             count        count of received data in bytes
  *     
- * Return Value:    Number of bytes received
+ * Return Value:    None
  */
-static unsigned int hci_uart_tty_receive(struct tty_struct *tty,
-		const u8 *data, char *flags, int count)
+static void hci_uart_tty_receive(struct tty_struct *tty, const u8 *data, char *flags, int count)
 {
 	struct hci_uart *hu = (void *)tty->disc_data;
-	int received;
 
 	if (!hu || tty != hu->tty)
-		return -ENODEV;
+		return;
 
 	if (!test_bit(HCI_UART_PROTO_SET, &hu->flags))
-		return -EINVAL;
+		return;
 
 	spin_lock(&hu->rx_lock);
-	received = hu->proto->recv(hu, (void *) data, count);
-	if (received > 0)
-		hu->hdev->stat.byte_rx += received;
+	hu->proto->recv(hu, (void *) data, count);
+	hu->hdev->stat.byte_rx += count;
 	spin_unlock(&hu->rx_lock);
 
 	tty_unthrottle(tty);
-
-	return received;
 }
 
 static int hci_uart_register_dev(struct hci_uart *hu)
diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c
index ae15a4ddaa9b..7878da89d29e 100644
--- a/drivers/cdrom/viocd.c
+++ b/drivers/cdrom/viocd.c
@@ -627,7 +627,6 @@ static int viocd_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	gendisk->fops = &viocd_fops;
 	gendisk->flags = GENHD_FL_CD | GENHD_FL_REMOVABLE |
 			 GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-	gendisk->events = DISK_EVENT_MEDIA_CHANGE;
 	set_capacity(gendisk, 0);
 	gendisk->private_data = d;
 	d->viocd_disk = gendisk;
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 051474c65b78..34d6a1cab8de 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -163,11 +163,32 @@ static irqreturn_t hpet_interrupt(int irq, void *data)
 	 * This has the effect of treating non-periodic like periodic.
 	 */
 	if ((devp->hd_flags & (HPET_IE | HPET_PERIODIC)) == HPET_IE) {
-		unsigned long m, t;
+		unsigned long m, t, mc, base, k;
+		struct hpet __iomem *hpet = devp->hd_hpet;
+		struct hpets *hpetp = devp->hd_hpets;
 
 		t = devp->hd_ireqfreq;
 		m = read_counter(&devp->hd_timer->hpet_compare);
-		write_counter(t + m, &devp->hd_timer->hpet_compare);
+		mc = read_counter(&hpet->hpet_mc);
+		/* The time for the next interrupt would logically be t + m,
+		 * however, if we are very unlucky and the interrupt is delayed
+		 * for longer than t then we will completely miss the next
+		 * interrupt if we set t + m and an application will hang.
+		 * Therefore we need to make a more complex computation assuming
+		 * that there exists a k for which the following is true:
+		 * k * t + base < mc + delta
+		 * (k + 1) * t + base > mc + delta
+		 * where t is the interval in hpet ticks for the given freq,
+		 * base is the theoretical start value 0 < base < t,
+		 * mc is the main counter value at the time of the interrupt,
+		 * delta is the time it takes to write the a value to the
+		 * comparator.
+		 * k may then be computed as (mc - base + delta) / t .
+		 */
+		base = mc % t;
+		k = (mc - base + hpetp->hp_delta) / t;
+		write_counter(t * (k + 1) + base,
+			      &devp->hd_timer->hpet_compare);
 	}
 
 	if (devp->hd_flags & HPET_SHARED_IRQ)
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 838568a7dbf5..fb68b1295373 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1677,17 +1677,12 @@ static int __devinit virtcons_probe(struct virtio_device *vdev)
 	portdev->config.max_nr_ports = 1;
 	if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_MULTIPORT)) {
 		multiport = true;
-		vdev->features[0] |= 1 << VIRTIO_CONSOLE_F_MULTIPORT;
-
 		vdev->config->get(vdev, offsetof(struct virtio_console_config,
 						 max_nr_ports),
 				  &portdev->config.max_nr_ports,
 				  sizeof(portdev->config.max_nr_ports));
 	}
 
-	/* Let the Host know we support multiple ports.*/
-	vdev->config->finalize_features(vdev);
-
 	err = init_vqs(portdev);
 	if (err < 0) {
 		dev_err(&vdev->dev, "Error %d initializing vqs\n", err);
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index 036e5865eb40..dc7c033ef587 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -24,7 +24,6 @@
 #include <linux/ioport.h>
 #include <linux/io.h>
 #include <linux/clk.h>
-#include <linux/pm_runtime.h>
 #include <linux/irq.h>
 #include <linux/err.h>
 #include <linux/clocksource.h>
@@ -153,12 +152,10 @@ static int sh_cmt_enable(struct sh_cmt_priv *p, unsigned long *rate)
 {
 	int ret;
 
-	/* wake up device and enable clock */
-	pm_runtime_get_sync(&p->pdev->dev);
+	/* enable clock */
 	ret = clk_enable(p->clk);
 	if (ret) {
 		dev_err(&p->pdev->dev, "cannot enable clock\n");
-		pm_runtime_put_sync(&p->pdev->dev);
 		return ret;
 	}
 
@@ -190,9 +187,8 @@ static void sh_cmt_disable(struct sh_cmt_priv *p)
 	/* disable interrupts in CMT block */
 	sh_cmt_write(p, CMCSR, 0);
 
-	/* stop clock and mark device as idle */
+	/* stop clock */
 	clk_disable(p->clk);
-	pm_runtime_put_sync(&p->pdev->dev);
 }
 
 /* private flags */
@@ -664,7 +660,6 @@ static int __devinit sh_cmt_probe(struct platform_device *pdev)
 
 	if (p) {
 		dev_info(&pdev->dev, "kept as earlytimer\n");
-		pm_runtime_enable(&pdev->dev);
 		return 0;
 	}
 
@@ -679,9 +674,6 @@ static int __devinit sh_cmt_probe(struct platform_device *pdev)
 		kfree(p);
 		platform_set_drvdata(pdev, NULL);
 	}
-
-	if (!is_early_platform_device(pdev))
-		pm_runtime_enable(&pdev->dev);
 	return ret;
 }
 
diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c
index 17296288a205..808135768617 100644
--- a/drivers/clocksource/sh_tmu.c
+++ b/drivers/clocksource/sh_tmu.c
@@ -25,7 +25,6 @@
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/clk.h>
-#include <linux/pm_runtime.h>
 #include <linux/irq.h>
 #include <linux/err.h>
 #include <linux/clocksource.h>
@@ -110,12 +109,10 @@ static int sh_tmu_enable(struct sh_tmu_priv *p)
 {
 	int ret;
 
-	/* wake up device and enable clock */
-	pm_runtime_get_sync(&p->pdev->dev);
+	/* enable clock */
 	ret = clk_enable(p->clk);
 	if (ret) {
 		dev_err(&p->pdev->dev, "cannot enable clock\n");
-		pm_runtime_put_sync(&p->pdev->dev);
 		return ret;
 	}
 
@@ -144,9 +141,8 @@ static void sh_tmu_disable(struct sh_tmu_priv *p)
 	/* disable interrupts in TMU block */
 	sh_tmu_write(p, TCR, 0x0000);
 
-	/* stop clock and mark device as idle */
+	/* stop clock */
 	clk_disable(p->clk);
-	pm_runtime_put_sync(&p->pdev->dev);
 }
 
 static void sh_tmu_set_next(struct sh_tmu_priv *p, unsigned long delta,
@@ -415,7 +411,6 @@ static int __devinit sh_tmu_probe(struct platform_device *pdev)
 
 	if (p) {
 		dev_info(&pdev->dev, "kept as earlytimer\n");
-		pm_runtime_enable(&pdev->dev);
 		return 0;
 	}
 
@@ -430,9 +425,6 @@ static int __devinit sh_tmu_probe(struct platform_device *pdev)
 		kfree(p);
 		platform_set_drvdata(pdev, NULL);
 	}
-
-	if (!is_early_platform_device(pdev))
-		pm_runtime_enable(&pdev->dev);
 	return ret;
 }
 
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index b60a4c263686..faf7c5217848 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -298,11 +298,13 @@ static int cpufreq_stat_notifier_trans(struct notifier_block *nb,
 	old_index = stat->last_index;
 	new_index = freq_table_get_index(stat, freq->new);
 
-	cpufreq_stats_update(freq->cpu);
-	if (old_index == new_index)
+	/* We can't do stat->time_in_state[-1]= .. */
+	if (old_index == -1 || new_index == -1)
 		return 0;
 
-	if (old_index == -1 || new_index == -1)
+	cpufreq_stats_update(freq->cpu);
+
+	if (old_index == new_index)
 		return 0;
 
 	spin_lock(&cpufreq_stats_lock);
@@ -387,6 +389,7 @@ static void __exit cpufreq_stats_exit(void)
 	unregister_hotcpu_notifier(&cpufreq_stat_cpu_notifier);
 	for_each_online_cpu(cpu) {
 		cpufreq_stats_free_table(cpu);
+		cpufreq_stats_free_sysfs(cpu);
 	}
 }
 
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index 83479b6fb9a1..bce576d7478e 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1079,6 +1079,9 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data,
 	}
 
 	res = transition_fid_vid(data, fid, vid);
+	if (res)
+		return res;
+
 	freqs.new = find_khz_freq_from_fid(data->currfid);
 
 	for_each_cpu(i, data->available_cores) {
@@ -1101,7 +1104,8 @@ static int transition_frequency_pstate(struct powernow_k8_data *data,
 	/* get MSR index for hardware pstate transition */
 	pstate = index & HW_PSTATE_MASK;
 	if (pstate > data->max_hw_pstate)
-		return 0;
+		return -EINVAL;
+
 	freqs.old = find_khz_freq_from_pstate(data->powernow_table,
 			data->currpstate);
 	freqs.new = find_khz_freq_from_pstate(data->powernow_table, pstate);
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index f508690eb958..c47f3d09c1ee 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -237,6 +237,7 @@ static int menu_select(struct cpuidle_device *dev)
 	unsigned int power_usage = -1;
 	int i;
 	int multiplier;
+	struct timespec t;
 
 	if (data->needs_update) {
 		menu_update(dev);
@@ -251,8 +252,9 @@ static int menu_select(struct cpuidle_device *dev)
 		return 0;
 
 	/* determine the expected residency time, round up */
+	t = ktime_to_timespec(tick_nohz_get_sleep_length());
 	data->expected_us =
-	    DIV_ROUND_UP((u32)ktime_to_ns(tick_nohz_get_sleep_length()), 1000);
+		t.tv_sec * USEC_PER_SEC + t.tv_nsec / NSEC_PER_USEC;
 
 
 	data->bucket = which_bucket(data->expected_us);
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index a572600e44eb..25cf327cd1cb 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -200,16 +200,18 @@ config PL330_DMA
 	  platform_data for a dma-pl330 device.
 
 config PCH_DMA
-	tristate "Intel EG20T PCH / OKI SEMICONDUCTOR ML7213 IOH DMA support"
+	tristate "Intel EG20T PCH / OKI Semi IOH(ML7213/ML7223) DMA support"
 	depends on PCI && X86
 	select DMA_ENGINE
 	help
 	  Enable support for Intel EG20T PCH DMA engine.
 
-	  This driver also can be used for OKI SEMICONDUCTOR ML7213 IOH(Input/
-	  Output Hub) which is for IVI(In-Vehicle Infotainment) use.
-	  ML7213 is companion chip for Intel Atom E6xx series.
-	  ML7213 is completely compatible for Intel EG20T PCH.
+	  This driver also can be used for OKI SEMICONDUCTOR IOH(Input/
+	  Output Hub), ML7213 and ML7223.
+	  ML7213 IOH is for IVI(In-Vehicle Infotainment) use and ML7223 IOH is
+	  for MP(Media Phone) use.
+	  ML7213/ML7223 is companion chip for Intel Atom E6xx series.
+	  ML7213/ML7223 is completely compatible for Intel EG20T PCH.
 
 config IMX_SDMA
 	tristate "i.MX SDMA support"
diff --git a/drivers/dma/TODO b/drivers/dma/TODO
new file mode 100644
index 000000000000..a4af8589330c
--- /dev/null
+++ b/drivers/dma/TODO
@@ -0,0 +1,14 @@
+TODO for slave dma
+
+1. Move remaining drivers to use new slave interface
+2. Remove old slave pointer machansim
+3. Make issue_pending to start the transaction in below drivers
+	- mpc512x_dma
+	- imx-dma
+	- imx-sdma
+	- mxs-dma.c
+	- dw_dmac
+	- intel_mid_dma
+	- ste_dma40
+4. Check other subsystems for dma drivers and merge/move to dmaengine
+5. Remove dma_slave_config's dma direction.
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 235f53bf494e..36144f88d718 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -37,8 +37,8 @@
 
 #define	ATC_DEFAULT_CFG		(ATC_FIFOCFG_HALFFIFO)
 #define	ATC_DEFAULT_CTRLA	(0)
-#define	ATC_DEFAULT_CTRLB	(ATC_SIF(0)	\
-				|ATC_DIF(1))
+#define	ATC_DEFAULT_CTRLB	(ATC_SIF(AT_DMA_MEM_IF) \
+				|ATC_DIF(AT_DMA_MEM_IF))
 
 /*
  * Initial number of descriptors to allocate for each channel. This could
@@ -165,6 +165,29 @@ static void atc_desc_put(struct at_dma_chan *atchan, struct at_desc *desc)
 }
 
 /**
+ * atc_desc_chain - build chain adding a descripor
+ * @first: address of first descripor of the chain
+ * @prev: address of previous descripor of the chain
+ * @desc: descriptor to queue
+ *
+ * Called from prep_* functions
+ */
+static void atc_desc_chain(struct at_desc **first, struct at_desc **prev,
+			   struct at_desc *desc)
+{
+	if (!(*first)) {
+		*first = desc;
+	} else {
+		/* inform the HW lli about chaining */
+		(*prev)->lli.dscr = desc->txd.phys;
+		/* insert the link descriptor to the LD ring */
+		list_add_tail(&desc->desc_node,
+				&(*first)->tx_list);
+	}
+	*prev = desc;
+}
+
+/**
  * atc_assign_cookie - compute and assign new cookie
  * @atchan: channel we work on
  * @desc: descriptor to assign cookie for
@@ -237,16 +260,12 @@ static void atc_dostart(struct at_dma_chan *atchan, struct at_desc *first)
 static void
 atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 {
-	dma_async_tx_callback		callback;
-	void				*param;
 	struct dma_async_tx_descriptor	*txd = &desc->txd;
 
 	dev_vdbg(chan2dev(&atchan->chan_common),
 		"descriptor %u complete\n", txd->cookie);
 
 	atchan->completed_cookie = txd->cookie;
-	callback = txd->callback;
-	param = txd->callback_param;
 
 	/* move children to free_list */
 	list_splice_init(&desc->tx_list, &atchan->free_list);
@@ -278,12 +297,19 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 		}
 	}
 
-	/*
-	 * The API requires that no submissions are done from a
-	 * callback, so we don't need to drop the lock here
-	 */
-	if (callback)
-		callback(param);
+	/* for cyclic transfers,
+	 * no need to replay callback function while stopping */
+	if (!test_bit(ATC_IS_CYCLIC, &atchan->status)) {
+		dma_async_tx_callback	callback = txd->callback;
+		void			*param = txd->callback_param;
+
+		/*
+		 * The API requires that no submissions are done from a
+		 * callback, so we don't need to drop the lock here
+		 */
+		if (callback)
+			callback(param);
+	}
 
 	dma_run_dependencies(txd);
 }
@@ -419,6 +445,26 @@ static void atc_handle_error(struct at_dma_chan *atchan)
 	atc_chain_complete(atchan, bad_desc);
 }
 
+/**
+ * atc_handle_cyclic - at the end of a period, run callback function
+ * @atchan: channel used for cyclic operations
+ *
+ * Called with atchan->lock held and bh disabled
+ */
+static void atc_handle_cyclic(struct at_dma_chan *atchan)
+{
+	struct at_desc			*first = atc_first_active(atchan);
+	struct dma_async_tx_descriptor	*txd = &first->txd;
+	dma_async_tx_callback		callback = txd->callback;
+	void				*param = txd->callback_param;
+
+	dev_vdbg(chan2dev(&atchan->chan_common),
+			"new cyclic period llp 0x%08x\n",
+			channel_readl(atchan, DSCR));
+
+	if (callback)
+		callback(param);
+}
 
 /*--  IRQ & Tasklet  ---------------------------------------------------*/
 
@@ -426,16 +472,11 @@ static void atc_tasklet(unsigned long data)
 {
 	struct at_dma_chan *atchan = (struct at_dma_chan *)data;
 
-	/* Channel cannot be enabled here */
-	if (atc_chan_is_enabled(atchan)) {
-		dev_err(chan2dev(&atchan->chan_common),
-			"BUG: channel enabled in tasklet\n");
-		return;
-	}
-
 	spin_lock(&atchan->lock);
-	if (test_and_clear_bit(0, &atchan->error_status))
+	if (test_and_clear_bit(ATC_IS_ERROR, &atchan->status))
 		atc_handle_error(atchan);
+	else if (test_bit(ATC_IS_CYCLIC, &atchan->status))
+		atc_handle_cyclic(atchan);
 	else
 		atc_advance_work(atchan);
 
@@ -464,12 +505,13 @@ static irqreturn_t at_dma_interrupt(int irq, void *dev_id)
 
 		for (i = 0; i < atdma->dma_common.chancnt; i++) {
 			atchan = &atdma->chan[i];
-			if (pending & (AT_DMA_CBTC(i) | AT_DMA_ERR(i))) {
+			if (pending & (AT_DMA_BTC(i) | AT_DMA_ERR(i))) {
 				if (pending & AT_DMA_ERR(i)) {
 					/* Disable channel on AHB error */
-					dma_writel(atdma, CHDR, atchan->mask);
+					dma_writel(atdma, CHDR,
+						AT_DMA_RES(i) | atchan->mask);
 					/* Give information to tasklet */
-					set_bit(0, &atchan->error_status);
+					set_bit(ATC_IS_ERROR, &atchan->status);
 				}
 				tasklet_schedule(&atchan->tasklet);
 				ret = IRQ_HANDLED;
@@ -549,7 +591,7 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	}
 
 	ctrla =   ATC_DEFAULT_CTRLA;
-	ctrlb =   ATC_DEFAULT_CTRLB
+	ctrlb =   ATC_DEFAULT_CTRLB | ATC_IEN
 		| ATC_SRC_ADDR_MODE_INCR
 		| ATC_DST_ADDR_MODE_INCR
 		| ATC_FC_MEM2MEM;
@@ -584,16 +626,7 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 
 		desc->txd.cookie = 0;
 
-		if (!first) {
-			first = desc;
-		} else {
-			/* inform the HW lli about chaining */
-			prev->lli.dscr = desc->txd.phys;
-			/* insert the link descriptor to the LD ring */
-			list_add_tail(&desc->desc_node,
-					&first->tx_list);
-		}
-		prev = desc;
+		atc_desc_chain(&first, &prev, desc);
 	}
 
 	/* First descriptor of the chain embedds additional information */
@@ -639,7 +672,8 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	struct scatterlist	*sg;
 	size_t			total_len = 0;
 
-	dev_vdbg(chan2dev(chan), "prep_slave_sg: %s f0x%lx\n",
+	dev_vdbg(chan2dev(chan), "prep_slave_sg (%d): %s f0x%lx\n",
+			sg_len,
 			direction == DMA_TO_DEVICE ? "TO DEVICE" : "FROM DEVICE",
 			flags);
 
@@ -651,14 +685,15 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	reg_width = atslave->reg_width;
 
 	ctrla = ATC_DEFAULT_CTRLA | atslave->ctrla;
-	ctrlb = ATC_DEFAULT_CTRLB | ATC_IEN;
+	ctrlb = ATC_IEN;
 
 	switch (direction) {
 	case DMA_TO_DEVICE:
 		ctrla |=  ATC_DST_WIDTH(reg_width);
 		ctrlb |=  ATC_DST_ADDR_MODE_FIXED
 			| ATC_SRC_ADDR_MODE_INCR
-			| ATC_FC_MEM2PER;
+			| ATC_FC_MEM2PER
+			| ATC_SIF(AT_DMA_MEM_IF) | ATC_DIF(AT_DMA_PER_IF);
 		reg = atslave->tx_reg;
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct at_desc	*desc;
@@ -682,16 +717,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 					| len >> mem_width;
 			desc->lli.ctrlb = ctrlb;
 
-			if (!first) {
-				first = desc;
-			} else {
-				/* inform the HW lli about chaining */
-				prev->lli.dscr = desc->txd.phys;
-				/* insert the link descriptor to the LD ring */
-				list_add_tail(&desc->desc_node,
-						&first->tx_list);
-			}
-			prev = desc;
+			atc_desc_chain(&first, &prev, desc);
 			total_len += len;
 		}
 		break;
@@ -699,7 +725,8 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		ctrla |=  ATC_SRC_WIDTH(reg_width);
 		ctrlb |=  ATC_DST_ADDR_MODE_INCR
 			| ATC_SRC_ADDR_MODE_FIXED
-			| ATC_FC_PER2MEM;
+			| ATC_FC_PER2MEM
+			| ATC_SIF(AT_DMA_PER_IF) | ATC_DIF(AT_DMA_MEM_IF);
 
 		reg = atslave->rx_reg;
 		for_each_sg(sgl, sg, sg_len, i) {
@@ -724,16 +751,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 					| len >> reg_width;
 			desc->lli.ctrlb = ctrlb;
 
-			if (!first) {
-				first = desc;
-			} else {
-				/* inform the HW lli about chaining */
-				prev->lli.dscr = desc->txd.phys;
-				/* insert the link descriptor to the LD ring */
-				list_add_tail(&desc->desc_node,
-						&first->tx_list);
-			}
-			prev = desc;
+			atc_desc_chain(&first, &prev, desc);
 			total_len += len;
 		}
 		break;
@@ -759,41 +777,211 @@ err_desc_get:
 	return NULL;
 }
 
+/**
+ * atc_dma_cyclic_check_values
+ * Check for too big/unaligned periods and unaligned DMA buffer
+ */
+static int
+atc_dma_cyclic_check_values(unsigned int reg_width, dma_addr_t buf_addr,
+		size_t period_len, enum dma_data_direction direction)
+{
+	if (period_len > (ATC_BTSIZE_MAX << reg_width))
+		goto err_out;
+	if (unlikely(period_len & ((1 << reg_width) - 1)))
+		goto err_out;
+	if (unlikely(buf_addr & ((1 << reg_width) - 1)))
+		goto err_out;
+	if (unlikely(!(direction & (DMA_TO_DEVICE | DMA_FROM_DEVICE))))
+		goto err_out;
+
+	return 0;
+
+err_out:
+	return -EINVAL;
+}
+
+/**
+ * atc_dma_cyclic_fill_desc - Fill one period decriptor
+ */
+static int
+atc_dma_cyclic_fill_desc(struct at_dma_slave *atslave, struct at_desc *desc,
+		unsigned int period_index, dma_addr_t buf_addr,
+		size_t period_len, enum dma_data_direction direction)
+{
+	u32		ctrla;
+	unsigned int	reg_width = atslave->reg_width;
+
+	/* prepare common CRTLA value */
+	ctrla =   ATC_DEFAULT_CTRLA | atslave->ctrla
+		| ATC_DST_WIDTH(reg_width)
+		| ATC_SRC_WIDTH(reg_width)
+		| period_len >> reg_width;
+
+	switch (direction) {
+	case DMA_TO_DEVICE:
+		desc->lli.saddr = buf_addr + (period_len * period_index);
+		desc->lli.daddr = atslave->tx_reg;
+		desc->lli.ctrla = ctrla;
+		desc->lli.ctrlb = ATC_DST_ADDR_MODE_FIXED
+				| ATC_SRC_ADDR_MODE_INCR
+				| ATC_FC_MEM2PER
+				| ATC_SIF(AT_DMA_MEM_IF)
+				| ATC_DIF(AT_DMA_PER_IF);
+		break;
+
+	case DMA_FROM_DEVICE:
+		desc->lli.saddr = atslave->rx_reg;
+		desc->lli.daddr = buf_addr + (period_len * period_index);
+		desc->lli.ctrla = ctrla;
+		desc->lli.ctrlb = ATC_DST_ADDR_MODE_INCR
+				| ATC_SRC_ADDR_MODE_FIXED
+				| ATC_FC_PER2MEM
+				| ATC_SIF(AT_DMA_PER_IF)
+				| ATC_DIF(AT_DMA_MEM_IF);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * atc_prep_dma_cyclic - prepare the cyclic DMA transfer
+ * @chan: the DMA channel to prepare
+ * @buf_addr: physical DMA address where the buffer starts
+ * @buf_len: total number of bytes for the entire buffer
+ * @period_len: number of bytes for each period
+ * @direction: transfer direction, to or from device
+ */
+static struct dma_async_tx_descriptor *
+atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+		size_t period_len, enum dma_data_direction direction)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_dma_slave	*atslave = chan->private;
+	struct at_desc		*first = NULL;
+	struct at_desc		*prev = NULL;
+	unsigned long		was_cyclic;
+	unsigned int		periods = buf_len / period_len;
+	unsigned int		i;
+
+	dev_vdbg(chan2dev(chan), "prep_dma_cyclic: %s buf@0x%08x - %d (%d/%d)\n",
+			direction == DMA_TO_DEVICE ? "TO DEVICE" : "FROM DEVICE",
+			buf_addr,
+			periods, buf_len, period_len);
+
+	if (unlikely(!atslave || !buf_len || !period_len)) {
+		dev_dbg(chan2dev(chan), "prep_dma_cyclic: length is zero!\n");
+		return NULL;
+	}
+
+	was_cyclic = test_and_set_bit(ATC_IS_CYCLIC, &atchan->status);
+	if (was_cyclic) {
+		dev_dbg(chan2dev(chan), "prep_dma_cyclic: channel in use!\n");
+		return NULL;
+	}
+
+	/* Check for too big/unaligned periods and unaligned DMA buffer */
+	if (atc_dma_cyclic_check_values(atslave->reg_width, buf_addr,
+					period_len, direction))
+		goto err_out;
+
+	/* build cyclic linked list */
+	for (i = 0; i < periods; i++) {
+		struct at_desc	*desc;
+
+		desc = atc_desc_get(atchan);
+		if (!desc)
+			goto err_desc_get;
+
+		if (atc_dma_cyclic_fill_desc(atslave, desc, i, buf_addr,
+						period_len, direction))
+			goto err_desc_get;
+
+		atc_desc_chain(&first, &prev, desc);
+	}
+
+	/* lets make a cyclic list */
+	prev->lli.dscr = first->txd.phys;
+
+	/* First descriptor of the chain embedds additional information */
+	first->txd.cookie = -EBUSY;
+	first->len = buf_len;
+
+	return &first->txd;
+
+err_desc_get:
+	dev_err(chan2dev(chan), "not enough descriptors available\n");
+	atc_desc_put(atchan, first);
+err_out:
+	clear_bit(ATC_IS_CYCLIC, &atchan->status);
+	return NULL;
+}
+
+
 static int atc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		       unsigned long arg)
 {
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
 	struct at_dma		*atdma = to_at_dma(chan->device);
-	struct at_desc		*desc, *_desc;
+	int			chan_id = atchan->chan_common.chan_id;
+
 	LIST_HEAD(list);
 
-	/* Only supports DMA_TERMINATE_ALL */
-	if (cmd != DMA_TERMINATE_ALL)
-		return -ENXIO;
+	dev_vdbg(chan2dev(chan), "atc_control (%d)\n", cmd);
 
-	/*
-	 * This is only called when something went wrong elsewhere, so
-	 * we don't really care about the data. Just disable the
-	 * channel. We still have to poll the channel enable bit due
-	 * to AHB/HSB limitations.
-	 */
-	spin_lock_bh(&atchan->lock);
+	if (cmd == DMA_PAUSE) {
+		spin_lock_bh(&atchan->lock);
 
-	dma_writel(atdma, CHDR, atchan->mask);
+		dma_writel(atdma, CHER, AT_DMA_SUSP(chan_id));
+		set_bit(ATC_IS_PAUSED, &atchan->status);
 
-	/* confirm that this channel is disabled */
-	while (dma_readl(atdma, CHSR) & atchan->mask)
-		cpu_relax();
+		spin_unlock_bh(&atchan->lock);
+	} else if (cmd == DMA_RESUME) {
+		if (!test_bit(ATC_IS_PAUSED, &atchan->status))
+			return 0;
 
-	/* active_list entries will end up before queued entries */
-	list_splice_init(&atchan->queue, &list);
-	list_splice_init(&atchan->active_list, &list);
+		spin_lock_bh(&atchan->lock);
 
-	/* Flush all pending and queued descriptors */
-	list_for_each_entry_safe(desc, _desc, &list, desc_node)
-		atc_chain_complete(atchan, desc);
+		dma_writel(atdma, CHDR, AT_DMA_RES(chan_id));
+		clear_bit(ATC_IS_PAUSED, &atchan->status);
 
-	spin_unlock_bh(&atchan->lock);
+		spin_unlock_bh(&atchan->lock);
+	} else if (cmd == DMA_TERMINATE_ALL) {
+		struct at_desc	*desc, *_desc;
+		/*
+		 * This is only called when something went wrong elsewhere, so
+		 * we don't really care about the data. Just disable the
+		 * channel. We still have to poll the channel enable bit due
+		 * to AHB/HSB limitations.
+		 */
+		spin_lock_bh(&atchan->lock);
+
+		/* disabling channel: must also remove suspend state */
+		dma_writel(atdma, CHDR, AT_DMA_RES(chan_id) | atchan->mask);
+
+		/* confirm that this channel is disabled */
+		while (dma_readl(atdma, CHSR) & atchan->mask)
+			cpu_relax();
+
+		/* active_list entries will end up before queued entries */
+		list_splice_init(&atchan->queue, &list);
+		list_splice_init(&atchan->active_list, &list);
+
+		/* Flush all pending and queued descriptors */
+		list_for_each_entry_safe(desc, _desc, &list, desc_node)
+			atc_chain_complete(atchan, desc);
+
+		clear_bit(ATC_IS_PAUSED, &atchan->status);
+		/* if channel dedicated to cyclic operations, free it */
+		clear_bit(ATC_IS_CYCLIC, &atchan->status);
+
+		spin_unlock_bh(&atchan->lock);
+	} else {
+		return -ENXIO;
+	}
 
 	return 0;
 }
@@ -835,9 +1023,17 @@ atc_tx_status(struct dma_chan *chan,
 
 	spin_unlock_bh(&atchan->lock);
 
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-	dev_vdbg(chan2dev(chan), "tx_status: %d (d%d, u%d)\n",
-		 cookie, last_complete ? last_complete : 0,
+	if (ret != DMA_SUCCESS)
+		dma_set_tx_state(txstate, last_complete, last_used,
+			atc_first_active(atchan)->len);
+	else
+		dma_set_tx_state(txstate, last_complete, last_used, 0);
+
+	if (test_bit(ATC_IS_PAUSED, &atchan->status))
+		ret = DMA_PAUSED;
+
+	dev_vdbg(chan2dev(chan), "tx_status %d: cookie = %d (d%d, u%d)\n",
+		 ret, cookie, last_complete ? last_complete : 0,
 		 last_used ? last_used : 0);
 
 	return ret;
@@ -853,6 +1049,10 @@ static void atc_issue_pending(struct dma_chan *chan)
 
 	dev_vdbg(chan2dev(chan), "issue_pending\n");
 
+	/* Not needed for cyclic transfers */
+	if (test_bit(ATC_IS_CYCLIC, &atchan->status))
+		return;
+
 	spin_lock_bh(&atchan->lock);
 	if (!atc_chan_is_enabled(atchan)) {
 		atc_advance_work(atchan);
@@ -959,6 +1159,7 @@ static void atc_free_chan_resources(struct dma_chan *chan)
 	}
 	list_splice_init(&atchan->free_list, &list);
 	atchan->descs_allocated = 0;
+	atchan->status = 0;
 
 	dev_vdbg(chan2dev(chan), "free_chan_resources: done\n");
 }
@@ -1092,10 +1293,15 @@ static int __init at_dma_probe(struct platform_device *pdev)
 	if (dma_has_cap(DMA_MEMCPY, atdma->dma_common.cap_mask))
 		atdma->dma_common.device_prep_dma_memcpy = atc_prep_dma_memcpy;
 
-	if (dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask)) {
+	if (dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask))
 		atdma->dma_common.device_prep_slave_sg = atc_prep_slave_sg;
+
+	if (dma_has_cap(DMA_CYCLIC, atdma->dma_common.cap_mask))
+		atdma->dma_common.device_prep_dma_cyclic = atc_prep_dma_cyclic;
+
+	if (dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask) ||
+	    dma_has_cap(DMA_CYCLIC, atdma->dma_common.cap_mask))
 		atdma->dma_common.device_control = atc_control;
-	}
 
 	dma_writel(atdma, EN, AT_DMA_ENABLE);
 
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index 495457e3dc4b..087dbf1dd39c 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -103,6 +103,10 @@
 /* Bitfields in CTRLB */
 #define	ATC_SIF(i)		(0x3 & (i))	/* Src tx done via AHB-Lite Interface i */
 #define	ATC_DIF(i)		((0x3 & (i)) <<  4)	/* Dst tx done via AHB-Lite Interface i */
+				  /* Specify AHB interfaces */
+#define AT_DMA_MEM_IF		0 /* interface 0 as memory interface */
+#define AT_DMA_PER_IF		1 /* interface 1 as peripheral interface */
+
 #define	ATC_SRC_PIP		(0x1 <<  8)	/* Source Picture-in-Picture enabled */
 #define	ATC_DST_PIP		(0x1 << 12)	/* Destination Picture-in-Picture enabled */
 #define	ATC_SRC_DSCR_DIS	(0x1 << 16)	/* Src Descriptor fetch disable */
@@ -181,12 +185,23 @@ txd_to_at_desc(struct dma_async_tx_descriptor *txd)
 /*--  Channels  --------------------------------------------------------*/
 
 /**
+ * atc_status - information bits stored in channel status flag
+ *
+ * Manipulated with atomic operations.
+ */
+enum atc_status {
+	ATC_IS_ERROR = 0,
+	ATC_IS_PAUSED = 1,
+	ATC_IS_CYCLIC = 24,
+};
+
+/**
  * struct at_dma_chan - internal representation of an Atmel HDMAC channel
  * @chan_common: common dmaengine channel object members
  * @device: parent device
  * @ch_regs: memory mapped register base
  * @mask: channel index in a mask
- * @error_status: transmit error status information from irq handler
+ * @status: transmit status information from irq/prep* functions
  *                to tasklet (use atomic operations)
  * @tasklet: bottom half to finish transaction work
  * @lock: serializes enqueue/dequeue operations to descriptors lists
@@ -201,7 +216,7 @@ struct at_dma_chan {
 	struct at_dma		*device;
 	void __iomem		*ch_regs;
 	u8			mask;
-	unsigned long		error_status;
+	unsigned long		status;
 	struct tasklet_struct	tasklet;
 
 	spinlock_t		lock;
@@ -309,8 +324,8 @@ static void atc_setup_irq(struct at_dma_chan *atchan, int on)
 	struct at_dma	*atdma = to_at_dma(atchan->chan_common.device);
 	u32		ebci;
 
-	/* enable interrupts on buffer chain completion & error */
-	ebci =    AT_DMA_CBTC(atchan->chan_common.chan_id)
+	/* enable interrupts on buffer transfer completion & error */
+	ebci =    AT_DMA_BTC(atchan->chan_common.chan_id)
 		| AT_DMA_ERR(atchan->chan_common.chan_id);
 	if (on)
 		dma_writel(atdma, EBCIER, ebci);
@@ -347,7 +362,12 @@ static inline int atc_chan_is_enabled(struct at_dma_chan *atchan)
  */
 static void set_desc_eol(struct at_desc *desc)
 {
-	desc->lli.ctrlb |= ATC_SRC_DSCR_DIS | ATC_DST_DSCR_DIS;
+	u32 ctrlb = desc->lli.ctrlb;
+
+	ctrlb &= ~ATC_IEN;
+	ctrlb |= ATC_SRC_DSCR_DIS | ATC_DST_DSCR_DIS;
+
+	desc->lli.ctrlb = ctrlb;
 	desc->lli.dscr = 0;
 }
 
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index f48e54006518..af8c0b5ed70f 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -1610,7 +1610,7 @@ int __init coh901318_init(void)
 {
 	return platform_driver_probe(&coh901318_driver, coh901318_probe);
 }
-arch_initcall(coh901318_init);
+subsys_initcall(coh901318_init);
 
 void __exit coh901318_exit(void)
 {
diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c
index 2a2e2fa00e91..4d180ca9a1d8 100644
--- a/drivers/dma/dw_dmac.c
+++ b/drivers/dma/dw_dmac.c
@@ -3,6 +3,7 @@
  * AVR32 systems.)
  *
  * Copyright (C) 2007-2008 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
  *
  * 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
@@ -93,8 +94,9 @@ static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
 	struct dw_desc *desc, *_desc;
 	struct dw_desc *ret = NULL;
 	unsigned int i = 0;
+	unsigned long flags;
 
-	spin_lock_bh(&dwc->lock);
+	spin_lock_irqsave(&dwc->lock, flags);
 	list_for_each_entry_safe(desc, _desc, &dwc->free_list, desc_node) {
 		if (async_tx_test_ack(&desc->txd)) {
 			list_del(&desc->desc_node);
@@ -104,7 +106,7 @@ static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
 		dev_dbg(chan2dev(&dwc->chan), "desc %p not ACKed\n", desc);
 		i++;
 	}
-	spin_unlock_bh(&dwc->lock);
+	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	dev_vdbg(chan2dev(&dwc->chan), "scanned %u descriptors on freelist\n", i);
 
@@ -130,12 +132,14 @@ static void dwc_sync_desc_for_cpu(struct dw_dma_chan *dwc, struct dw_desc *desc)
  */
 static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 {
+	unsigned long flags;
+
 	if (desc) {
 		struct dw_desc *child;
 
 		dwc_sync_desc_for_cpu(dwc, desc);
 
-		spin_lock_bh(&dwc->lock);
+		spin_lock_irqsave(&dwc->lock, flags);
 		list_for_each_entry(child, &desc->tx_list, desc_node)
 			dev_vdbg(chan2dev(&dwc->chan),
 					"moving child desc %p to freelist\n",
@@ -143,7 +147,7 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 		list_splice_init(&desc->tx_list, &dwc->free_list);
 		dev_vdbg(chan2dev(&dwc->chan), "moving desc %p to freelist\n", desc);
 		list_add(&desc->desc_node, &dwc->free_list);
-		spin_unlock_bh(&dwc->lock);
+		spin_unlock_irqrestore(&dwc->lock, flags);
 	}
 }
 
@@ -195,18 +199,23 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
 /*----------------------------------------------------------------------*/
 
 static void
-dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
+dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc,
+		bool callback_required)
 {
-	dma_async_tx_callback		callback;
-	void				*param;
+	dma_async_tx_callback		callback = NULL;
+	void				*param = NULL;
 	struct dma_async_tx_descriptor	*txd = &desc->txd;
 	struct dw_desc			*child;
+	unsigned long			flags;
 
 	dev_vdbg(chan2dev(&dwc->chan), "descriptor %u complete\n", txd->cookie);
 
+	spin_lock_irqsave(&dwc->lock, flags);
 	dwc->completed = txd->cookie;
-	callback = txd->callback;
-	param = txd->callback_param;
+	if (callback_required) {
+		callback = txd->callback;
+		param = txd->callback_param;
+	}
 
 	dwc_sync_desc_for_cpu(dwc, desc);
 
@@ -238,11 +247,9 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
 		}
 	}
 
-	/*
-	 * The API requires that no submissions are done from a
-	 * callback, so we don't need to drop the lock here
-	 */
-	if (callback)
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
+	if (callback_required && callback)
 		callback(param);
 }
 
@@ -250,7 +257,9 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
 {
 	struct dw_desc *desc, *_desc;
 	LIST_HEAD(list);
+	unsigned long flags;
 
+	spin_lock_irqsave(&dwc->lock, flags);
 	if (dma_readl(dw, CH_EN) & dwc->mask) {
 		dev_err(chan2dev(&dwc->chan),
 			"BUG: XFER bit set, but channel not idle!\n");
@@ -271,8 +280,10 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		dwc_dostart(dwc, dwc_first_active(dwc));
 	}
 
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
 	list_for_each_entry_safe(desc, _desc, &list, desc_node)
-		dwc_descriptor_complete(dwc, desc);
+		dwc_descriptor_complete(dwc, desc, true);
 }
 
 static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
@@ -281,7 +292,9 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	struct dw_desc *desc, *_desc;
 	struct dw_desc *child;
 	u32 status_xfer;
+	unsigned long flags;
 
+	spin_lock_irqsave(&dwc->lock, flags);
 	/*
 	 * Clear block interrupt flag before scanning so that we don't
 	 * miss any, and read LLP before RAW_XFER to ensure it is
@@ -294,30 +307,47 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	if (status_xfer & dwc->mask) {
 		/* Everything we've submitted is done */
 		dma_writel(dw, CLEAR.XFER, dwc->mask);
+		spin_unlock_irqrestore(&dwc->lock, flags);
+
 		dwc_complete_all(dw, dwc);
 		return;
 	}
 
-	if (list_empty(&dwc->active_list))
+	if (list_empty(&dwc->active_list)) {
+		spin_unlock_irqrestore(&dwc->lock, flags);
 		return;
+	}
 
 	dev_vdbg(chan2dev(&dwc->chan), "scan_descriptors: llp=0x%x\n", llp);
 
 	list_for_each_entry_safe(desc, _desc, &dwc->active_list, desc_node) {
-		if (desc->lli.llp == llp)
+		/* check first descriptors addr */
+		if (desc->txd.phys == llp) {
+			spin_unlock_irqrestore(&dwc->lock, flags);
+			return;
+		}
+
+		/* check first descriptors llp */
+		if (desc->lli.llp == llp) {
 			/* This one is currently in progress */
+			spin_unlock_irqrestore(&dwc->lock, flags);
 			return;
+		}
 
 		list_for_each_entry(child, &desc->tx_list, desc_node)
-			if (child->lli.llp == llp)
+			if (child->lli.llp == llp) {
 				/* Currently in progress */
+				spin_unlock_irqrestore(&dwc->lock, flags);
 				return;
+			}
 
 		/*
 		 * No descriptors so far seem to be in progress, i.e.
 		 * this one must be done.
 		 */
-		dwc_descriptor_complete(dwc, desc);
+		spin_unlock_irqrestore(&dwc->lock, flags);
+		dwc_descriptor_complete(dwc, desc, true);
+		spin_lock_irqsave(&dwc->lock, flags);
 	}
 
 	dev_err(chan2dev(&dwc->chan),
@@ -332,6 +362,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		list_move(dwc->queue.next, &dwc->active_list);
 		dwc_dostart(dwc, dwc_first_active(dwc));
 	}
+	spin_unlock_irqrestore(&dwc->lock, flags);
 }
 
 static void dwc_dump_lli(struct dw_dma_chan *dwc, struct dw_lli *lli)
@@ -346,9 +377,12 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 {
 	struct dw_desc *bad_desc;
 	struct dw_desc *child;
+	unsigned long flags;
 
 	dwc_scan_descriptors(dw, dwc);
 
+	spin_lock_irqsave(&dwc->lock, flags);
+
 	/*
 	 * The descriptor currently at the head of the active list is
 	 * borked. Since we don't have any way to report errors, we'll
@@ -378,8 +412,10 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	list_for_each_entry(child, &bad_desc->tx_list, desc_node)
 		dwc_dump_lli(dwc, &child->lli);
 
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
 	/* Pretend the descriptor completed successfully */
-	dwc_descriptor_complete(dwc, bad_desc);
+	dwc_descriptor_complete(dwc, bad_desc, true);
 }
 
 /* --------------------- Cyclic DMA API extensions -------------------- */
@@ -402,6 +438,8 @@ EXPORT_SYMBOL(dw_dma_get_dst_addr);
 static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
 		u32 status_block, u32 status_err, u32 status_xfer)
 {
+	unsigned long flags;
+
 	if (status_block & dwc->mask) {
 		void (*callback)(void *param);
 		void *callback_param;
@@ -412,11 +450,9 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
 
 		callback = dwc->cdesc->period_callback;
 		callback_param = dwc->cdesc->period_callback_param;
-		if (callback) {
-			spin_unlock(&dwc->lock);
+
+		if (callback)
 			callback(callback_param);
-			spin_lock(&dwc->lock);
-		}
 	}
 
 	/*
@@ -430,6 +466,9 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
 		dev_err(chan2dev(&dwc->chan), "cyclic DMA unexpected %s "
 				"interrupt, stopping DMA transfer\n",
 				status_xfer ? "xfer" : "error");
+
+		spin_lock_irqsave(&dwc->lock, flags);
+
 		dev_err(chan2dev(&dwc->chan),
 			"  SAR: 0x%x DAR: 0x%x LLP: 0x%x CTL: 0x%x:%08x\n",
 			channel_readl(dwc, SAR),
@@ -453,6 +492,8 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
 
 		for (i = 0; i < dwc->cdesc->periods; i++)
 			dwc_dump_lli(dwc, &dwc->cdesc->desc[i]->lli);
+
+		spin_unlock_irqrestore(&dwc->lock, flags);
 	}
 }
 
@@ -476,7 +517,6 @@ static void dw_dma_tasklet(unsigned long data)
 
 	for (i = 0; i < dw->dma.chancnt; i++) {
 		dwc = &dw->chan[i];
-		spin_lock(&dwc->lock);
 		if (test_bit(DW_DMA_IS_CYCLIC, &dwc->flags))
 			dwc_handle_cyclic(dw, dwc, status_block, status_err,
 					status_xfer);
@@ -484,7 +524,6 @@ static void dw_dma_tasklet(unsigned long data)
 			dwc_handle_error(dw, dwc);
 		else if ((status_block | status_xfer) & (1 << i))
 			dwc_scan_descriptors(dw, dwc);
-		spin_unlock(&dwc->lock);
 	}
 
 	/*
@@ -539,8 +578,9 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
 	struct dw_desc		*desc = txd_to_dw_desc(tx);
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(tx->chan);
 	dma_cookie_t		cookie;
+	unsigned long		flags;
 
-	spin_lock_bh(&dwc->lock);
+	spin_lock_irqsave(&dwc->lock, flags);
 	cookie = dwc_assign_cookie(dwc, desc);
 
 	/*
@@ -560,7 +600,7 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
 		list_add_tail(&desc->desc_node, &dwc->queue);
 	}
 
-	spin_unlock_bh(&dwc->lock);
+	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	return cookie;
 }
@@ -689,9 +729,15 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		reg = dws->tx_reg;
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
-			u32		len;
-			u32		mem;
+			u32		len, dlen, mem;
+
+			mem = sg_phys(sg);
+			len = sg_dma_len(sg);
+			mem_width = 2;
+			if (unlikely(mem & 3 || len & 3))
+				mem_width = 0;
 
+slave_sg_todev_fill_desc:
 			desc = dwc_desc_get(dwc);
 			if (!desc) {
 				dev_err(chan2dev(chan),
@@ -699,16 +745,19 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 				goto err_desc_get;
 			}
 
-			mem = sg_phys(sg);
-			len = sg_dma_len(sg);
-			mem_width = 2;
-			if (unlikely(mem & 3 || len & 3))
-				mem_width = 0;
-
 			desc->lli.sar = mem;
 			desc->lli.dar = reg;
 			desc->lli.ctllo = ctllo | DWC_CTLL_SRC_WIDTH(mem_width);
-			desc->lli.ctlhi = len >> mem_width;
+			if ((len >> mem_width) > DWC_MAX_COUNT) {
+				dlen = DWC_MAX_COUNT << mem_width;
+				mem += dlen;
+				len -= dlen;
+			} else {
+				dlen = len;
+				len = 0;
+			}
+
+			desc->lli.ctlhi = dlen >> mem_width;
 
 			if (!first) {
 				first = desc;
@@ -722,7 +771,10 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 						&first->tx_list);
 			}
 			prev = desc;
-			total_len += len;
+			total_len += dlen;
+
+			if (len)
+				goto slave_sg_todev_fill_desc;
 		}
 		break;
 	case DMA_FROM_DEVICE:
@@ -735,15 +787,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		reg = dws->rx_reg;
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
-			u32		len;
-			u32		mem;
-
-			desc = dwc_desc_get(dwc);
-			if (!desc) {
-				dev_err(chan2dev(chan),
-					"not enough descriptors available\n");
-				goto err_desc_get;
-			}
+			u32		len, dlen, mem;
 
 			mem = sg_phys(sg);
 			len = sg_dma_len(sg);
@@ -751,10 +795,26 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			if (unlikely(mem & 3 || len & 3))
 				mem_width = 0;
 
+slave_sg_fromdev_fill_desc:
+			desc = dwc_desc_get(dwc);
+			if (!desc) {
+				dev_err(chan2dev(chan),
+						"not enough descriptors available\n");
+				goto err_desc_get;
+			}
+
 			desc->lli.sar = reg;
 			desc->lli.dar = mem;
 			desc->lli.ctllo = ctllo | DWC_CTLL_DST_WIDTH(mem_width);
-			desc->lli.ctlhi = len >> reg_width;
+			if ((len >> reg_width) > DWC_MAX_COUNT) {
+				dlen = DWC_MAX_COUNT << reg_width;
+				mem += dlen;
+				len -= dlen;
+			} else {
+				dlen = len;
+				len = 0;
+			}
+			desc->lli.ctlhi = dlen >> reg_width;
 
 			if (!first) {
 				first = desc;
@@ -768,7 +828,10 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 						&first->tx_list);
 			}
 			prev = desc;
-			total_len += len;
+			total_len += dlen;
+
+			if (len)
+				goto slave_sg_fromdev_fill_desc;
 		}
 		break;
 	default:
@@ -799,34 +862,51 @@ static int dwc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
 	struct dw_dma		*dw = to_dw_dma(chan->device);
 	struct dw_desc		*desc, *_desc;
+	unsigned long		flags;
+	u32			cfglo;
 	LIST_HEAD(list);
 
-	/* Only supports DMA_TERMINATE_ALL */
-	if (cmd != DMA_TERMINATE_ALL)
-		return -ENXIO;
+	if (cmd == DMA_PAUSE) {
+		spin_lock_irqsave(&dwc->lock, flags);
 
-	/*
-	 * This is only called when something went wrong elsewhere, so
-	 * we don't really care about the data. Just disable the
-	 * channel. We still have to poll the channel enable bit due
-	 * to AHB/HSB limitations.
-	 */
-	spin_lock_bh(&dwc->lock);
+		cfglo = channel_readl(dwc, CFG_LO);
+		channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP);
+		while (!(channel_readl(dwc, CFG_LO) & DWC_CFGL_FIFO_EMPTY))
+			cpu_relax();
 
-	channel_clear_bit(dw, CH_EN, dwc->mask);
+		dwc->paused = true;
+		spin_unlock_irqrestore(&dwc->lock, flags);
+	} else if (cmd == DMA_RESUME) {
+		if (!dwc->paused)
+			return 0;
 
-	while (dma_readl(dw, CH_EN) & dwc->mask)
-		cpu_relax();
+		spin_lock_irqsave(&dwc->lock, flags);
 
-	/* active_list entries will end up before queued entries */
-	list_splice_init(&dwc->queue, &list);
-	list_splice_init(&dwc->active_list, &list);
+		cfglo = channel_readl(dwc, CFG_LO);
+		channel_writel(dwc, CFG_LO, cfglo & ~DWC_CFGL_CH_SUSP);
+		dwc->paused = false;
 
-	spin_unlock_bh(&dwc->lock);
+		spin_unlock_irqrestore(&dwc->lock, flags);
+	} else if (cmd == DMA_TERMINATE_ALL) {
+		spin_lock_irqsave(&dwc->lock, flags);
 
-	/* Flush all pending and queued descriptors */
-	list_for_each_entry_safe(desc, _desc, &list, desc_node)
-		dwc_descriptor_complete(dwc, desc);
+		channel_clear_bit(dw, CH_EN, dwc->mask);
+		while (dma_readl(dw, CH_EN) & dwc->mask)
+			cpu_relax();
+
+		dwc->paused = false;
+
+		/* active_list entries will end up before queued entries */
+		list_splice_init(&dwc->queue, &list);
+		list_splice_init(&dwc->active_list, &list);
+
+		spin_unlock_irqrestore(&dwc->lock, flags);
+
+		/* Flush all pending and queued descriptors */
+		list_for_each_entry_safe(desc, _desc, &list, desc_node)
+			dwc_descriptor_complete(dwc, desc, false);
+	} else
+		return -ENXIO;
 
 	return 0;
 }
@@ -846,9 +926,7 @@ dwc_tx_status(struct dma_chan *chan,
 
 	ret = dma_async_is_complete(cookie, last_complete, last_used);
 	if (ret != DMA_SUCCESS) {
-		spin_lock_bh(&dwc->lock);
 		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
-		spin_unlock_bh(&dwc->lock);
 
 		last_complete = dwc->completed;
 		last_used = chan->cookie;
@@ -856,7 +934,14 @@ dwc_tx_status(struct dma_chan *chan,
 		ret = dma_async_is_complete(cookie, last_complete, last_used);
 	}
 
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
+	if (ret != DMA_SUCCESS)
+		dma_set_tx_state(txstate, last_complete, last_used,
+				dwc_first_active(dwc)->len);
+	else
+		dma_set_tx_state(txstate, last_complete, last_used, 0);
+
+	if (dwc->paused)
+		return DMA_PAUSED;
 
 	return ret;
 }
@@ -865,10 +950,8 @@ static void dwc_issue_pending(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
 
-	spin_lock_bh(&dwc->lock);
 	if (!list_empty(&dwc->queue))
 		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
-	spin_unlock_bh(&dwc->lock);
 }
 
 static int dwc_alloc_chan_resources(struct dma_chan *chan)
@@ -880,6 +963,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 	int			i;
 	u32			cfghi;
 	u32			cfglo;
+	unsigned long		flags;
 
 	dev_vdbg(chan2dev(chan), "alloc_chan_resources\n");
 
@@ -917,16 +1001,16 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 	 * doesn't mean what you think it means), and status writeback.
 	 */
 
-	spin_lock_bh(&dwc->lock);
+	spin_lock_irqsave(&dwc->lock, flags);
 	i = dwc->descs_allocated;
 	while (dwc->descs_allocated < NR_DESCS_PER_CHANNEL) {
-		spin_unlock_bh(&dwc->lock);
+		spin_unlock_irqrestore(&dwc->lock, flags);
 
 		desc = kzalloc(sizeof(struct dw_desc), GFP_KERNEL);
 		if (!desc) {
 			dev_info(chan2dev(chan),
 				"only allocated %d descriptors\n", i);
-			spin_lock_bh(&dwc->lock);
+			spin_lock_irqsave(&dwc->lock, flags);
 			break;
 		}
 
@@ -938,7 +1022,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 				sizeof(desc->lli), DMA_TO_DEVICE);
 		dwc_desc_put(dwc, desc);
 
-		spin_lock_bh(&dwc->lock);
+		spin_lock_irqsave(&dwc->lock, flags);
 		i = ++dwc->descs_allocated;
 	}
 
@@ -947,7 +1031,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 	channel_set_bit(dw, MASK.BLOCK, dwc->mask);
 	channel_set_bit(dw, MASK.ERROR, dwc->mask);
 
-	spin_unlock_bh(&dwc->lock);
+	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	dev_dbg(chan2dev(chan),
 		"alloc_chan_resources allocated %d descriptors\n", i);
@@ -960,6 +1044,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
 	struct dw_dma		*dw = to_dw_dma(chan->device);
 	struct dw_desc		*desc, *_desc;
+	unsigned long		flags;
 	LIST_HEAD(list);
 
 	dev_dbg(chan2dev(chan), "free_chan_resources (descs allocated=%u)\n",
@@ -970,7 +1055,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	BUG_ON(!list_empty(&dwc->queue));
 	BUG_ON(dma_readl(to_dw_dma(chan->device), CH_EN) & dwc->mask);
 
-	spin_lock_bh(&dwc->lock);
+	spin_lock_irqsave(&dwc->lock, flags);
 	list_splice_init(&dwc->free_list, &list);
 	dwc->descs_allocated = 0;
 
@@ -979,7 +1064,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	channel_clear_bit(dw, MASK.BLOCK, dwc->mask);
 	channel_clear_bit(dw, MASK.ERROR, dwc->mask);
 
-	spin_unlock_bh(&dwc->lock);
+	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	list_for_each_entry_safe(desc, _desc, &list, desc_node) {
 		dev_vdbg(chan2dev(chan), "  freeing descriptor %p\n", desc);
@@ -1004,13 +1089,14 @@ int dw_dma_cyclic_start(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
 	struct dw_dma		*dw = to_dw_dma(dwc->chan.device);
+	unsigned long		flags;
 
 	if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) {
 		dev_err(chan2dev(&dwc->chan), "missing prep for cyclic DMA\n");
 		return -ENODEV;
 	}
 
-	spin_lock(&dwc->lock);
+	spin_lock_irqsave(&dwc->lock, flags);
 
 	/* assert channel is idle */
 	if (dma_readl(dw, CH_EN) & dwc->mask) {
@@ -1023,7 +1109,7 @@ int dw_dma_cyclic_start(struct dma_chan *chan)
 			channel_readl(dwc, LLP),
 			channel_readl(dwc, CTL_HI),
 			channel_readl(dwc, CTL_LO));
-		spin_unlock(&dwc->lock);
+		spin_unlock_irqrestore(&dwc->lock, flags);
 		return -EBUSY;
 	}
 
@@ -1038,7 +1124,7 @@ int dw_dma_cyclic_start(struct dma_chan *chan)
 
 	channel_set_bit(dw, CH_EN, dwc->mask);
 
-	spin_unlock(&dwc->lock);
+	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	return 0;
 }
@@ -1054,14 +1140,15 @@ void dw_dma_cyclic_stop(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
 	struct dw_dma		*dw = to_dw_dma(dwc->chan.device);
+	unsigned long		flags;
 
-	spin_lock(&dwc->lock);
+	spin_lock_irqsave(&dwc->lock, flags);
 
 	channel_clear_bit(dw, CH_EN, dwc->mask);
 	while (dma_readl(dw, CH_EN) & dwc->mask)
 		cpu_relax();
 
-	spin_unlock(&dwc->lock);
+	spin_unlock_irqrestore(&dwc->lock, flags);
 }
 EXPORT_SYMBOL(dw_dma_cyclic_stop);
 
@@ -1090,17 +1177,18 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 	unsigned int			reg_width;
 	unsigned int			periods;
 	unsigned int			i;
+	unsigned long			flags;
 
-	spin_lock_bh(&dwc->lock);
+	spin_lock_irqsave(&dwc->lock, flags);
 	if (!list_empty(&dwc->queue) || !list_empty(&dwc->active_list)) {
-		spin_unlock_bh(&dwc->lock);
+		spin_unlock_irqrestore(&dwc->lock, flags);
 		dev_dbg(chan2dev(&dwc->chan),
 				"queue and/or active list are not empty\n");
 		return ERR_PTR(-EBUSY);
 	}
 
 	was_cyclic = test_and_set_bit(DW_DMA_IS_CYCLIC, &dwc->flags);
-	spin_unlock_bh(&dwc->lock);
+	spin_unlock_irqrestore(&dwc->lock, flags);
 	if (was_cyclic) {
 		dev_dbg(chan2dev(&dwc->chan),
 				"channel already prepared for cyclic DMA\n");
@@ -1214,13 +1302,14 @@ void dw_dma_cyclic_free(struct dma_chan *chan)
 	struct dw_dma		*dw = to_dw_dma(dwc->chan.device);
 	struct dw_cyclic_desc	*cdesc = dwc->cdesc;
 	int			i;
+	unsigned long		flags;
 
 	dev_dbg(chan2dev(&dwc->chan), "cyclic free\n");
 
 	if (!cdesc)
 		return;
 
-	spin_lock_bh(&dwc->lock);
+	spin_lock_irqsave(&dwc->lock, flags);
 
 	channel_clear_bit(dw, CH_EN, dwc->mask);
 	while (dma_readl(dw, CH_EN) & dwc->mask)
@@ -1230,7 +1319,7 @@ void dw_dma_cyclic_free(struct dma_chan *chan)
 	dma_writel(dw, CLEAR.ERROR, dwc->mask);
 	dma_writel(dw, CLEAR.XFER, dwc->mask);
 
-	spin_unlock_bh(&dwc->lock);
+	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	for (i = 0; i < cdesc->periods; i++)
 		dwc_desc_put(dwc, cdesc->desc[i]);
@@ -1487,3 +1576,4 @@ module_exit(dw_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller driver");
 MODULE_AUTHOR("Haavard Skinnemoen (Atmel)");
+MODULE_AUTHOR("Viresh Kumar <viresh.kumar@st.com>");
diff --git a/drivers/dma/dw_dmac_regs.h b/drivers/dma/dw_dmac_regs.h
index 720f821527f8..c3419518d701 100644
--- a/drivers/dma/dw_dmac_regs.h
+++ b/drivers/dma/dw_dmac_regs.h
@@ -2,6 +2,7 @@
  * Driver for the Synopsys DesignWare AHB DMA Controller
  *
  * Copyright (C) 2005-2007 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
  *
  * 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
@@ -138,6 +139,7 @@ struct dw_dma_chan {
 	void __iomem		*ch_regs;
 	u8			mask;
 	u8			priority;
+	bool			paused;
 
 	spinlock_t		lock;
 
diff --git a/drivers/dma/intel_mid_dma.c b/drivers/dma/intel_mid_dma.c
index 3d4ec38b9b62..f653517ef744 100644
--- a/drivers/dma/intel_mid_dma.c
+++ b/drivers/dma/intel_mid_dma.c
@@ -1292,8 +1292,7 @@ static int __devinit intel_mid_dma_probe(struct pci_dev *pdev,
 	if (err)
 		goto err_dma;
 
-	pm_runtime_set_active(&pdev->dev);
-	pm_runtime_enable(&pdev->dev);
+	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_allow(&pdev->dev);
 	return 0;
 
@@ -1322,6 +1321,9 @@ err_enable_device:
 static void __devexit intel_mid_dma_remove(struct pci_dev *pdev)
 {
 	struct middma_device *device = pci_get_drvdata(pdev);
+
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_forbid(&pdev->dev);
 	middma_shutdown(pdev);
 	pci_dev_put(pdev);
 	kfree(device);
@@ -1385,13 +1387,20 @@ int dma_resume(struct pci_dev *pci)
 static int dma_runtime_suspend(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
-	return dma_suspend(pci_dev, PMSG_SUSPEND);
+	struct middma_device *device = pci_get_drvdata(pci_dev);
+
+	device->state = SUSPENDED;
+	return 0;
 }
 
 static int dma_runtime_resume(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
-	return dma_resume(pci_dev);
+	struct middma_device *device = pci_get_drvdata(pci_dev);
+
+	device->state = RUNNING;
+	iowrite32(REG_BIT0, device->dma_base + DMA_CFG);
+	return 0;
 }
 
 static int dma_runtime_idle(struct device *dev)
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index f4a51d4d0349..5d65f8377971 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -508,6 +508,7 @@ int ioat2_alloc_chan_resources(struct dma_chan *c)
 	struct ioat_ring_ent **ring;
 	u64 status;
 	int order;
+	int i = 0;
 
 	/* have we already been set up? */
 	if (ioat->ring)
@@ -548,8 +549,11 @@ int ioat2_alloc_chan_resources(struct dma_chan *c)
 	ioat2_start_null_desc(ioat);
 
 	/* check that we got off the ground */
-	udelay(5);
-	status = ioat_chansts(chan);
+	do {
+		udelay(1);
+		status = ioat_chansts(chan);
+	} while (i++ < 20 && !is_ioat_active(status) && !is_ioat_idle(status));
+
 	if (is_ioat_active(status) || is_ioat_idle(status)) {
 		set_bit(IOAT_RUN, &chan->state);
 		return 1 << ioat->alloc_order;
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index c6b01f535b29..e03f811a83dd 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -619,7 +619,7 @@ iop_adma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dma_dest,
 
 	if (unlikely(!len))
 		return NULL;
-	BUG_ON(unlikely(len > IOP_ADMA_MAX_BYTE_COUNT));
+	BUG_ON(len > IOP_ADMA_MAX_BYTE_COUNT);
 
 	dev_dbg(iop_chan->device->common.dev, "%s len: %u\n",
 		__func__, len);
@@ -652,7 +652,7 @@ iop_adma_prep_dma_memset(struct dma_chan *chan, dma_addr_t dma_dest,
 
 	if (unlikely(!len))
 		return NULL;
-	BUG_ON(unlikely(len > IOP_ADMA_MAX_BYTE_COUNT));
+	BUG_ON(len > IOP_ADMA_MAX_BYTE_COUNT);
 
 	dev_dbg(iop_chan->device->common.dev, "%s len: %u\n",
 		__func__, len);
@@ -686,7 +686,7 @@ iop_adma_prep_dma_xor(struct dma_chan *chan, dma_addr_t dma_dest,
 
 	if (unlikely(!len))
 		return NULL;
-	BUG_ON(unlikely(len > IOP_ADMA_XOR_MAX_BYTE_COUNT));
+	BUG_ON(len > IOP_ADMA_XOR_MAX_BYTE_COUNT);
 
 	dev_dbg(iop_chan->device->common.dev,
 		"%s src_cnt: %d len: %u flags: %lx\n",
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index a25f5f61e0e0..954e334e01bb 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -671,7 +671,7 @@ mv_xor_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	if (unlikely(len < MV_XOR_MIN_BYTE_COUNT))
 		return NULL;
 
-	BUG_ON(unlikely(len > MV_XOR_MAX_BYTE_COUNT));
+	BUG_ON(len > MV_XOR_MAX_BYTE_COUNT);
 
 	spin_lock_bh(&mv_chan->lock);
 	slot_cnt = mv_chan_memcpy_slot_count(len);
@@ -710,7 +710,7 @@ mv_xor_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value,
 	if (unlikely(len < MV_XOR_MIN_BYTE_COUNT))
 		return NULL;
 
-	BUG_ON(unlikely(len > MV_XOR_MAX_BYTE_COUNT));
+	BUG_ON(len > MV_XOR_MAX_BYTE_COUNT);
 
 	spin_lock_bh(&mv_chan->lock);
 	slot_cnt = mv_chan_memset_slot_count(len);
@@ -744,7 +744,7 @@ mv_xor_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
 	if (unlikely(len < MV_XOR_MIN_BYTE_COUNT))
 		return NULL;
 
-	BUG_ON(unlikely(len > MV_XOR_MAX_BYTE_COUNT));
+	BUG_ON(len > MV_XOR_MAX_BYTE_COUNT);
 
 	dev_dbg(mv_chan->device->common.dev,
 		"%s src_cnt: %d len: dest %x %u flags: %ld\n",
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 8d8fef1480a9..ff5b38f9d45b 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -77,10 +77,10 @@ struct pch_dma_regs {
 	u32	dma_ctl0;
 	u32	dma_ctl1;
 	u32	dma_ctl2;
-	u32	reserved1;
+	u32	dma_ctl3;
 	u32	dma_sts0;
 	u32	dma_sts1;
-	u32	reserved2;
+	u32	dma_sts2;
 	u32	reserved3;
 	struct pch_dma_desc_regs desc[MAX_CHAN_NR];
 };
@@ -130,6 +130,7 @@ struct pch_dma {
 #define PCH_DMA_CTL0	0x00
 #define PCH_DMA_CTL1	0x04
 #define PCH_DMA_CTL2	0x08
+#define PCH_DMA_CTL3	0x0C
 #define PCH_DMA_STS0	0x10
 #define PCH_DMA_STS1	0x14
 
@@ -138,7 +139,8 @@ struct pch_dma {
 #define dma_writel(pd, name, val) \
 	writel((val), (pd)->membase + PCH_DMA_##name)
 
-static inline struct pch_dma_desc *to_pd_desc(struct dma_async_tx_descriptor *txd)
+static inline
+struct pch_dma_desc *to_pd_desc(struct dma_async_tx_descriptor *txd)
 {
 	return container_of(txd, struct pch_dma_desc, txd);
 }
@@ -163,13 +165,15 @@ static inline struct device *chan2parent(struct dma_chan *chan)
 	return chan->dev->device.parent;
 }
 
-static inline struct pch_dma_desc *pdc_first_active(struct pch_dma_chan *pd_chan)
+static inline
+struct pch_dma_desc *pdc_first_active(struct pch_dma_chan *pd_chan)
 {
 	return list_first_entry(&pd_chan->active_list,
 				struct pch_dma_desc, desc_node);
 }
 
-static inline struct pch_dma_desc *pdc_first_queued(struct pch_dma_chan *pd_chan)
+static inline
+struct pch_dma_desc *pdc_first_queued(struct pch_dma_chan *pd_chan)
 {
 	return list_first_entry(&pd_chan->queue,
 				struct pch_dma_desc, desc_node);
@@ -199,16 +203,30 @@ static void pdc_set_dir(struct dma_chan *chan)
 	struct pch_dma *pd = to_pd(chan->device);
 	u32 val;
 
-	val = dma_readl(pd, CTL0);
+	if (chan->chan_id < 8) {
+		val = dma_readl(pd, CTL0);
 
-	if (pd_chan->dir == DMA_TO_DEVICE)
-		val |= 0x1 << (DMA_CTL0_BITS_PER_CH * chan->chan_id +
-			       DMA_CTL0_DIR_SHIFT_BITS);
-	else
-		val &= ~(0x1 << (DMA_CTL0_BITS_PER_CH * chan->chan_id +
-				 DMA_CTL0_DIR_SHIFT_BITS));
+		if (pd_chan->dir == DMA_TO_DEVICE)
+			val |= 0x1 << (DMA_CTL0_BITS_PER_CH * chan->chan_id +
+				       DMA_CTL0_DIR_SHIFT_BITS);
+		else
+			val &= ~(0x1 << (DMA_CTL0_BITS_PER_CH * chan->chan_id +
+					 DMA_CTL0_DIR_SHIFT_BITS));
+
+		dma_writel(pd, CTL0, val);
+	} else {
+		int ch = chan->chan_id - 8; /* ch8-->0 ch9-->1 ... ch11->3 */
+		val = dma_readl(pd, CTL3);
 
-	dma_writel(pd, CTL0, val);
+		if (pd_chan->dir == DMA_TO_DEVICE)
+			val |= 0x1 << (DMA_CTL0_BITS_PER_CH * ch +
+				       DMA_CTL0_DIR_SHIFT_BITS);
+		else
+			val &= ~(0x1 << (DMA_CTL0_BITS_PER_CH * ch +
+					 DMA_CTL0_DIR_SHIFT_BITS));
+
+		dma_writel(pd, CTL3, val);
+	}
 
 	dev_dbg(chan2dev(chan), "pdc_set_dir: chan %d -> %x\n",
 		chan->chan_id, val);
@@ -219,13 +237,26 @@ static void pdc_set_mode(struct dma_chan *chan, u32 mode)
 	struct pch_dma *pd = to_pd(chan->device);
 	u32 val;
 
-	val = dma_readl(pd, CTL0);
+	if (chan->chan_id < 8) {
+		val = dma_readl(pd, CTL0);
+
+		val &= ~(DMA_CTL0_MODE_MASK_BITS <<
+			(DMA_CTL0_BITS_PER_CH * chan->chan_id));
+		val |= mode << (DMA_CTL0_BITS_PER_CH * chan->chan_id);
 
-	val &= ~(DMA_CTL0_MODE_MASK_BITS <<
-		(DMA_CTL0_BITS_PER_CH * chan->chan_id));
-	val |= mode << (DMA_CTL0_BITS_PER_CH * chan->chan_id);
+		dma_writel(pd, CTL0, val);
+	} else {
+		int ch = chan->chan_id - 8; /* ch8-->0 ch9-->1 ... ch11->3 */
+
+		val = dma_readl(pd, CTL3);
+
+		val &= ~(DMA_CTL0_MODE_MASK_BITS <<
+			(DMA_CTL0_BITS_PER_CH * ch));
+		val |= mode << (DMA_CTL0_BITS_PER_CH * ch);
 
-	dma_writel(pd, CTL0, val);
+		dma_writel(pd, CTL3, val);
+
+	}
 
 	dev_dbg(chan2dev(chan), "pdc_set_mode: chan %d -> %x\n",
 		chan->chan_id, val);
@@ -251,9 +282,6 @@ static bool pdc_is_idle(struct pch_dma_chan *pd_chan)
 
 static void pdc_dostart(struct pch_dma_chan *pd_chan, struct pch_dma_desc* desc)
 {
-	struct pch_dma *pd = to_pd(pd_chan->chan.device);
-	u32 val;
-
 	if (!pdc_is_idle(pd_chan)) {
 		dev_err(chan2dev(&pd_chan->chan),
 			"BUG: Attempt to start non-idle channel\n");
@@ -279,10 +307,6 @@ static void pdc_dostart(struct pch_dma_chan *pd_chan, struct pch_dma_desc* desc)
 		channel_writel(pd_chan, NEXT, desc->txd.phys);
 		pdc_set_mode(&pd_chan->chan, DMA_CTL0_SG);
 	}
-
-	val = dma_readl(pd, CTL2);
-	val |= 1 << (DMA_CTL2_START_SHIFT_BITS + pd_chan->chan.chan_id);
-	dma_writel(pd, CTL2, val);
 }
 
 static void pdc_chain_complete(struct pch_dma_chan *pd_chan,
@@ -403,7 +427,7 @@ static struct pch_dma_desc *pdc_desc_get(struct pch_dma_chan *pd_chan)
 {
 	struct pch_dma_desc *desc, *_d;
 	struct pch_dma_desc *ret = NULL;
-	int i;
+	int i = 0;
 
 	spin_lock(&pd_chan->lock);
 	list_for_each_entry_safe(desc, _d, &pd_chan->free_list, desc_node) {
@@ -478,7 +502,6 @@ static int pd_alloc_chan_resources(struct dma_chan *chan)
 	spin_unlock_bh(&pd_chan->lock);
 
 	pdc_enable_irq(chan, 1);
-	pdc_set_dir(chan);
 
 	return pd_chan->descs_allocated;
 }
@@ -561,6 +584,9 @@ static struct dma_async_tx_descriptor *pd_prep_slave_sg(struct dma_chan *chan,
 	else
 		return NULL;
 
+	pd_chan->dir = direction;
+	pdc_set_dir(chan);
+
 	for_each_sg(sgl, sg, sg_len, i) {
 		desc = pdc_desc_get(pd_chan);
 
@@ -703,6 +729,7 @@ static void pch_dma_save_regs(struct pch_dma *pd)
 	pd->regs.dma_ctl0 = dma_readl(pd, CTL0);
 	pd->regs.dma_ctl1 = dma_readl(pd, CTL1);
 	pd->regs.dma_ctl2 = dma_readl(pd, CTL2);
+	pd->regs.dma_ctl3 = dma_readl(pd, CTL3);
 
 	list_for_each_entry_safe(chan, _c, &pd->dma.channels, device_node) {
 		pd_chan = to_pd_chan(chan);
@@ -725,6 +752,7 @@ static void pch_dma_restore_regs(struct pch_dma *pd)
 	dma_writel(pd, CTL0, pd->regs.dma_ctl0);
 	dma_writel(pd, CTL1, pd->regs.dma_ctl1);
 	dma_writel(pd, CTL2, pd->regs.dma_ctl2);
+	dma_writel(pd, CTL3, pd->regs.dma_ctl3);
 
 	list_for_each_entry_safe(chan, _c, &pd->dma.channels, device_node) {
 		pd_chan = to_pd_chan(chan);
@@ -850,8 +878,6 @@ static int __devinit pch_dma_probe(struct pci_dev *pdev,
 
 		pd_chan->membase = &regs->desc[i];
 
-		pd_chan->dir = (i % 2) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
-
 		spin_lock_init(&pd_chan->lock);
 
 		INIT_LIST_HEAD(&pd_chan->active_list);
@@ -929,13 +955,23 @@ static void __devexit pch_dma_remove(struct pci_dev *pdev)
 #define PCI_DEVICE_ID_ML7213_DMA1_8CH	0x8026
 #define PCI_DEVICE_ID_ML7213_DMA2_8CH	0x802B
 #define PCI_DEVICE_ID_ML7213_DMA3_4CH	0x8034
+#define PCI_DEVICE_ID_ML7213_DMA4_12CH	0x8032
+#define PCI_DEVICE_ID_ML7223_DMA1_4CH	0x800B
+#define PCI_DEVICE_ID_ML7223_DMA2_4CH	0x800E
+#define PCI_DEVICE_ID_ML7223_DMA3_4CH	0x8017
+#define PCI_DEVICE_ID_ML7223_DMA4_4CH	0x803B
 
-static const struct pci_device_id pch_dma_id_table[] = {
+DEFINE_PCI_DEVICE_TABLE(pch_dma_id_table) = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_EG20T_PCH_DMA_8CH), 8 },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_EG20T_PCH_DMA_4CH), 4 },
 	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7213_DMA1_8CH), 8}, /* UART Video */
 	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7213_DMA2_8CH), 8}, /* PCMIF SPI */
 	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7213_DMA3_4CH), 4}, /* FPGA */
+	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7213_DMA4_12CH), 12}, /* I2S */
+	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7223_DMA1_4CH), 4}, /* UART */
+	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7223_DMA2_4CH), 4}, /* Video SPI */
+	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7223_DMA3_4CH), 4}, /* Security */
+	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7223_DMA4_4CH), 4}, /* FPGA */
 	{ 0, },
 };
 
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index 3b0247e74cc4..fc457a7e8832 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -2313,7 +2313,7 @@ static struct dma_async_tx_descriptor *ppc440spe_adma_prep_dma_memcpy(
 	if (unlikely(!len))
 		return NULL;
 
-	BUG_ON(unlikely(len > PPC440SPE_ADMA_DMA_MAX_BYTE_COUNT));
+	BUG_ON(len > PPC440SPE_ADMA_DMA_MAX_BYTE_COUNT);
 
 	spin_lock_bh(&ppc440spe_chan->lock);
 
@@ -2354,7 +2354,7 @@ static struct dma_async_tx_descriptor *ppc440spe_adma_prep_dma_memset(
 	if (unlikely(!len))
 		return NULL;
 
-	BUG_ON(unlikely(len > PPC440SPE_ADMA_DMA_MAX_BYTE_COUNT));
+	BUG_ON(len > PPC440SPE_ADMA_DMA_MAX_BYTE_COUNT);
 
 	spin_lock_bh(&ppc440spe_chan->lock);
 
@@ -2397,7 +2397,7 @@ static struct dma_async_tx_descriptor *ppc440spe_adma_prep_dma_xor(
 				     dma_dest, dma_src, src_cnt));
 	if (unlikely(!len))
 		return NULL;
-	BUG_ON(unlikely(len > PPC440SPE_ADMA_XOR_MAX_BYTE_COUNT));
+	BUG_ON(len > PPC440SPE_ADMA_XOR_MAX_BYTE_COUNT);
 
 	dev_dbg(ppc440spe_chan->device->common.dev,
 		"ppc440spe adma%d: %s src_cnt: %d len: %u int_en: %d\n",
@@ -2887,7 +2887,7 @@ static struct dma_async_tx_descriptor *ppc440spe_adma_prep_dma_pq(
 	ADMA_LL_DBG(prep_dma_pq_dbg(ppc440spe_chan->device->id,
 				    dst, src, src_cnt));
 	BUG_ON(!len);
-	BUG_ON(unlikely(len > PPC440SPE_ADMA_XOR_MAX_BYTE_COUNT));
+	BUG_ON(len > PPC440SPE_ADMA_XOR_MAX_BYTE_COUNT);
 	BUG_ON(!src_cnt);
 
 	if (src_cnt == 1 && dst[1] == src[0]) {
diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c
index 636e40925b16..028330044201 100644
--- a/drivers/dma/shdma.c
+++ b/drivers/dma/shdma.c
@@ -343,7 +343,7 @@ static int sh_dmae_alloc_chan_resources(struct dma_chan *chan)
 
 		dmae_set_dmars(sh_chan, cfg->mid_rid);
 		dmae_set_chcr(sh_chan, cfg->chcr);
-	} else if ((sh_dmae_readl(sh_chan, CHCR) & 0xf00) != 0x400) {
+	} else {
 		dmae_init(sh_chan);
 	}
 
@@ -1144,6 +1144,8 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
 	/* platform data */
 	shdev->pdata = pdata;
 
+	platform_set_drvdata(pdev, shdev);
+
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_get_sync(&pdev->dev);
 
@@ -1219,6 +1221,11 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
 	} else {
 		do {
 			for (i = chanirq_res->start; i <= chanirq_res->end; i++) {
+				if (irq_cnt >= SH_DMAC_MAX_CHANNELS) {
+					irq_cap = 1;
+					break;
+				}
+
 				if ((errirq_res->flags & IORESOURCE_BITS) ==
 				    IORESOURCE_IRQ_SHAREABLE)
 					chan_flag[irq_cnt] = IRQF_SHARED;
@@ -1228,15 +1235,11 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
 					"Found IRQ %d for channel %d\n",
 					i, irq_cnt);
 				chan_irq[irq_cnt++] = i;
-
-				if (irq_cnt >= SH_DMAC_MAX_CHANNELS)
-					break;
 			}
 
-			if (irq_cnt >= SH_DMAC_MAX_CHANNELS) {
-				irq_cap = 1;
+			if (irq_cnt >= SH_DMAC_MAX_CHANNELS)
 				break;
-			}
+
 			chanirq_res = platform_get_resource(pdev,
 						IORESOURCE_IRQ, ++irqres);
 		} while (irq_cnt < pdata->channel_num && chanirq_res);
@@ -1256,7 +1259,6 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
 
 	pm_runtime_put(&pdev->dev);
 
-	platform_set_drvdata(pdev, shdev);
 	dma_async_device_register(&shdev->common);
 
 	return err;
@@ -1278,6 +1280,8 @@ rst_err:
 
 	if (dmars)
 		iounmap(shdev->dmars);
+
+	platform_set_drvdata(pdev, NULL);
 emapdmars:
 	iounmap(shdev->chan_reg);
 	synchronize_rcu();
@@ -1316,6 +1320,8 @@ static int __exit sh_dmae_remove(struct platform_device *pdev)
 		iounmap(shdev->dmars);
 	iounmap(shdev->chan_reg);
 
+	platform_set_drvdata(pdev, NULL);
+
 	synchronize_rcu();
 	kfree(shdev);
 
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 94ee15dd3aed..8f222d4db7de 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -1829,7 +1829,7 @@ d40_get_dev_addr(struct d40_chan *chan, enum dma_data_direction direction)
 {
 	struct stedma40_platform_data *plat = chan->base->plat_data;
 	struct stedma40_chan_cfg *cfg = &chan->dma_cfg;
-	dma_addr_t addr;
+	dma_addr_t addr = 0;
 
 	if (chan->runtime_addr)
 		return chan->runtime_addr;
@@ -2962,4 +2962,4 @@ static int __init stedma40_init(void)
 {
 	return platform_driver_probe(&d40_driver, d40_probe);
 }
-arch_initcall(stedma40_init);
+subsys_initcall(stedma40_init);
diff --git a/drivers/firmware/iscsi_ibft_find.c b/drivers/firmware/iscsi_ibft_find.c
index f032e446fc11..bfe723266fd8 100644
--- a/drivers/firmware/iscsi_ibft_find.c
+++ b/drivers/firmware/iscsi_ibft_find.c
@@ -108,7 +108,9 @@ done:
  */
 unsigned long __init find_ibft_region(unsigned long *sizep)
 {
+#ifdef CONFIG_ACPI
 	int i;
+#endif
 	ibft_addr = NULL;
 
 #ifdef CONFIG_ACPI
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index b57ec09af891..2967002a9f82 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -86,6 +86,22 @@ config GPIO_IT8761E
 	help
 	  Say yes here to support GPIO functionality of IT8761E super I/O chip.
 
+config GPIO_EXYNOS4
+	def_bool y
+	depends on CPU_EXYNOS4210
+
+config GPIO_PLAT_SAMSUNG
+	def_bool y
+	depends on SAMSUNG_GPIOLIB_4BIT
+
+config GPIO_S5PC100
+	def_bool y
+	depends on CPU_S5PC100
+
+config GPIO_S5PV210
+	def_bool y
+	depends on CPU_S5PV210
+
 config GPIO_PL061
 	bool "PrimeCell PL061 GPIO support"
 	depends on ARM_AMBA
@@ -303,7 +319,7 @@ comment "PCI GPIO expanders:"
 
 config GPIO_CS5535
 	tristate "AMD CS5535/CS5536 GPIO support"
-	depends on PCI && X86 && !CS5535_GPIO
+	depends on PCI && X86 && !CS5535_GPIO && MFD_CS5535
 	help
 	  The AMD CS5535 and CS5536 southbridges support 28 GPIO pins that
 	  can be used for quite a number of things.  The CS5535/6 is found on
@@ -334,13 +350,19 @@ config GPIO_LANGWELL
 	  Say Y here to support Intel Langwell/Penwell GPIO.
 
 config GPIO_PCH
-	tristate "PCH GPIO of Intel Topcliff"
+	tristate "Intel EG20T PCH / OKI SEMICONDUCTOR ML7223 IOH GPIO"
 	depends on PCI && X86
 	help
 	  This driver is for PCH(Platform controller Hub) GPIO of Intel Topcliff
 	  which is an IOH(Input/Output Hub) for x86 embedded processor.
 	  This driver can access PCH GPIO device.
 
+	  This driver also can be used for OKI SEMICONDUCTOR IOH(Input/
+	  Output Hub), ML7223.
+	  ML7223 IOH is for MP(Media Phone) use.
+	  ML7223 is companion chip for Intel Atom E6xx series.
+	  ML7223 is completely compatible for Intel EG20T PCH.
+
 config GPIO_ML_IOH
 	tristate "OKI SEMICONDUCTOR ML7213 IOH GPIO support"
 	depends on PCI
@@ -424,4 +446,11 @@ config AB8500_GPIO
 	depends on AB8500_CORE && BROKEN
 	help
 	  Select this to enable the AB8500 IC GPIO driver
+
+config GPIO_TPS65910
+	bool "TPS65910 GPIO"
+	depends on MFD_TPS65910
+	help
+	  Select this option to enable GPIO driver for the TPS65910
+	  chip family.
 endif
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index d92ce3a62ae5..b605f8ec6fbe 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -8,6 +8,10 @@ obj-$(CONFIG_GPIO_ADP5520)	+= adp5520-gpio.o
 obj-$(CONFIG_GPIO_ADP5588)	+= adp5588-gpio.o
 obj-$(CONFIG_GPIO_BASIC_MMIO_CORE)	+= basic_mmio_gpio.o
 obj-$(CONFIG_GPIO_BASIC_MMIO)	+= basic_mmio_gpio.o
+obj-$(CONFIG_GPIO_EXYNOS4)	+= gpio-exynos4.o
+obj-$(CONFIG_GPIO_PLAT_SAMSUNG)	+= gpio-plat-samsung.o
+obj-$(CONFIG_GPIO_S5PC100)	+= gpio-s5pc100.o
+obj-$(CONFIG_GPIO_S5PV210)	+= gpio-s5pv210.o
 obj-$(CONFIG_GPIO_LANGWELL)	+= langwell_gpio.o
 obj-$(CONFIG_GPIO_MAX730X)	+= max730x.o
 obj-$(CONFIG_GPIO_MAX7300)	+= max7300.o
@@ -16,6 +20,7 @@ obj-$(CONFIG_GPIO_MAX732X)	+= max732x.o
 obj-$(CONFIG_GPIO_MC33880)	+= mc33880.o
 obj-$(CONFIG_GPIO_MCP23S08)	+= mcp23s08.o
 obj-$(CONFIG_GPIO_74X164)	+= 74x164.o
+obj-$(CONFIG_ARCH_OMAP)         += gpio-omap.o
 obj-$(CONFIG_GPIO_PCA953X)	+= pca953x.o
 obj-$(CONFIG_GPIO_PCF857X)	+= pcf857x.o
 obj-$(CONFIG_GPIO_PCH)		+= pch_gpio.o
@@ -34,9 +39,12 @@ obj-$(CONFIG_GPIO_WM831X)	+= wm831x-gpio.o
 obj-$(CONFIG_GPIO_WM8350)	+= wm8350-gpiolib.o
 obj-$(CONFIG_GPIO_WM8994)	+= wm8994-gpio.o
 obj-$(CONFIG_GPIO_SCH)		+= sch_gpio.o
+obj-$(CONFIG_MACH_U300)		+= gpio-u300.o
+obj-$(CONFIG_PLAT_NOMADIK)	+= gpio-nomadik.o
 obj-$(CONFIG_GPIO_RDC321X)	+= rdc321x-gpio.o
 obj-$(CONFIG_GPIO_JANZ_TTL)	+= janz-ttl.o
 obj-$(CONFIG_GPIO_SX150X)	+= sx150x.o
 obj-$(CONFIG_GPIO_VX855)	+= vx855_gpio.o
 obj-$(CONFIG_GPIO_ML_IOH)	+= ml_ioh_gpio.o
 obj-$(CONFIG_AB8500_GPIO)       += ab8500-gpio.o
+obj-$(CONFIG_GPIO_TPS65910)	+= tps65910-gpio.o
diff --git a/arch/arm/mach-exynos4/gpiolib.c b/drivers/gpio/gpio-exynos4.c
index d54ca6adb660..9029835112e7 100644
--- a/arch/arm/mach-exynos4/gpiolib.c
+++ b/drivers/gpio/gpio-exynos4.c
@@ -21,16 +21,37 @@
 #include <plat/gpio-cfg.h>
 #include <plat/gpio-cfg-helpers.h>
 
+int s3c_gpio_setpull_exynos4(struct s3c_gpio_chip *chip,
+				unsigned int off, s3c_gpio_pull_t pull)
+{
+	if (pull == S3C_GPIO_PULL_UP)
+		pull = 3;
+
+	return s3c_gpio_setpull_updown(chip, off, pull);
+}
+
+s3c_gpio_pull_t s3c_gpio_getpull_exynos4(struct s3c_gpio_chip *chip,
+						unsigned int off)
+{
+	s3c_gpio_pull_t pull;
+
+	pull = s3c_gpio_getpull_updown(chip, off);
+	if (pull == 3)
+		pull = S3C_GPIO_PULL_UP;
+
+	return pull;
+}
+
 static struct s3c_gpio_cfg gpio_cfg = {
 	.set_config	= s3c_gpio_setcfg_s3c64xx_4bit,
-	.set_pull	= s3c_gpio_setpull_updown,
-	.get_pull	= s3c_gpio_getpull_updown,
+	.set_pull	= s3c_gpio_setpull_exynos4,
+	.get_pull	= s3c_gpio_getpull_exynos4,
 };
 
 static struct s3c_gpio_cfg gpio_cfg_noint = {
 	.set_config	= s3c_gpio_setcfg_s3c64xx_4bit,
-	.set_pull	= s3c_gpio_setpull_updown,
-	.get_pull	= s3c_gpio_getpull_updown,
+	.set_pull	= s3c_gpio_setpull_exynos4,
+	.get_pull	= s3c_gpio_getpull_exynos4,
 };
 
 /*
diff --git a/arch/arm/plat-nomadik/gpio.c b/drivers/gpio/gpio-nomadik.c
index 307b8131aa8c..2c212c732d76 100644
--- a/arch/arm/plat-nomadik/gpio.c
+++ b/drivers/gpio/gpio-nomadik.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2008,2009 STMicroelectronics
  * Copyright (C) 2009 Alessandro Rubini <rubini@unipv.it>
  *   Rewritten based on work by Prafulla WADASKAR <prafulla.wadaskar@st.com>
+ * Copyright (C) 2011 Linus Walleij <linus.walleij@linaro.org>
  *
  * 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
@@ -49,6 +50,7 @@ struct nmk_gpio_chip {
 	u32 (*get_secondary_status)(unsigned int bank);
 	void (*set_ioforce)(bool enable);
 	spinlock_t lock;
+	bool sleepmode;
 	/* Keep track of configured edges */
 	u32 edge_rising;
 	u32 edge_falling;
@@ -57,6 +59,7 @@ struct nmk_gpio_chip {
 	u32 fwimsc;
 	u32 slpm;
 	u32 enabled;
+	u32 pull_up;
 };
 
 static struct nmk_gpio_chip *
@@ -103,16 +106,22 @@ static void __nmk_gpio_set_pull(struct nmk_gpio_chip *nmk_chip,
 	u32 pdis;
 
 	pdis = readl(nmk_chip->addr + NMK_GPIO_PDIS);
-	if (pull == NMK_GPIO_PULL_NONE)
+	if (pull == NMK_GPIO_PULL_NONE) {
 		pdis |= bit;
-	else
+		nmk_chip->pull_up &= ~bit;
+	} else {
 		pdis &= ~bit;
+	}
+
 	writel(pdis, nmk_chip->addr + NMK_GPIO_PDIS);
 
-	if (pull == NMK_GPIO_PULL_UP)
+	if (pull == NMK_GPIO_PULL_UP) {
+		nmk_chip->pull_up |= bit;
 		writel(bit, nmk_chip->addr + NMK_GPIO_DATS);
-	else if (pull == NMK_GPIO_PULL_DOWN)
+	} else if (pull == NMK_GPIO_PULL_DOWN) {
+		nmk_chip->pull_up &= ~bit;
 		writel(bit, nmk_chip->addr + NMK_GPIO_DATC);
+	}
 }
 
 static void __nmk_gpio_make_input(struct nmk_gpio_chip *nmk_chip,
@@ -386,14 +395,25 @@ EXPORT_SYMBOL(nmk_config_pins_sleep);
  * @gpio: pin number
  * @mode: NMK_GPIO_SLPM_INPUT or NMK_GPIO_SLPM_NOCHANGE,
  *
- * Sets the sleep mode of a pin.  If @mode is NMK_GPIO_SLPM_INPUT, the pin is
- * changed to an input (with pullup/down enabled) in sleep and deep sleep.  If
- * @mode is NMK_GPIO_SLPM_NOCHANGE, the pin remains in the state it was
- * configured even when in sleep and deep sleep.
+ * This register is actually in the pinmux layer, not the GPIO block itself.
+ * The GPIO1B_SLPM register defines the GPIO mode when SLEEP/DEEP-SLEEP
+ * mode is entered (i.e. when signal IOFORCE is HIGH by the platform code).
+ * Each GPIO can be configured to be forced into GPIO mode when IOFORCE is
+ * HIGH, overriding the normal setting defined by GPIO_AFSELx registers.
+ * When IOFORCE returns LOW (by software, after SLEEP/DEEP-SLEEP exit),
+ * the GPIOs return to the normal setting defined by GPIO_AFSELx registers.
+ *
+ * If @mode is NMK_GPIO_SLPM_INPUT, the corresponding GPIO is switched to GPIO
+ * mode when signal IOFORCE is HIGH (i.e. when SLEEP/DEEP-SLEEP mode is
+ * entered) regardless of the altfunction selected. Also wake-up detection is
+ * ENABLED.
+ *
+ * If @mode is NMK_GPIO_SLPM_NOCHANGE, the corresponding GPIO remains
+ * controlled by NMK_GPIO_DATC, NMK_GPIO_DATS, NMK_GPIO_DIR, NMK_GPIO_PDIS
+ * (for altfunction GPIO) or respective on-chip peripherals (for other
+ * altfuncs) when IOFORCE is HIGH. Also wake-up detection DISABLED.
  *
- * On DB8500v2 onwards, this setting loses the previous meaning and instead
- * indicates if wakeup detection is enabled on the pin.  Note that
- * enable_irq_wake() will automatically enable wakeup detection.
+ * Note that enable_irq_wake() will automatically enable wakeup detection.
  */
 int nmk_gpio_set_slpm(int gpio, enum nmk_gpio_slpm mode)
 {
@@ -544,6 +564,12 @@ static void __nmk_gpio_irq_modify(struct nmk_gpio_chip *nmk_chip,
 static void __nmk_gpio_set_wake(struct nmk_gpio_chip *nmk_chip,
 				int gpio, bool on)
 {
+	if (nmk_chip->sleepmode) {
+		__nmk_gpio_set_slpm(nmk_chip, gpio - nmk_chip->chip.base,
+				    on ? NMK_GPIO_SLPM_WAKEUP_ENABLE
+				    : NMK_GPIO_SLPM_WAKEUP_DISABLE);
+	}
+
 	__nmk_gpio_irq_modify(nmk_chip, gpio, WAKE, on);
 }
 
@@ -811,20 +837,43 @@ static void nmk_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 		bool pull;
 		u32 bit = 1 << i;
 
-		if (!label)
-			continue;
-
 		is_out = readl(nmk_chip->addr + NMK_GPIO_DIR) & bit;
 		pull = !(readl(nmk_chip->addr + NMK_GPIO_PDIS) & bit);
 		mode = nmk_gpio_get_mode(gpio);
 		seq_printf(s, " gpio-%-3d (%-20.20s) %s %s %s %s",
-			gpio, label,
+			gpio, label ?: "(none)",
 			is_out ? "out" : "in ",
 			chip->get
 				? (chip->get(chip, i) ? "hi" : "lo")
 				: "?  ",
 			(mode < 0) ? "unknown" : modes[mode],
 			pull ? "pull" : "none");
+
+		if (label && !is_out) {
+			int		irq = gpio_to_irq(gpio);
+			struct irq_desc	*desc = irq_to_desc(irq);
+
+			/* This races with request_irq(), set_irq_type(),
+			 * and set_irq_wake() ... but those are "rare".
+			 */
+			if (irq >= 0 && desc->action) {
+				char *trigger;
+				u32 bitmask = nmk_gpio_get_bitmask(gpio);
+
+				if (nmk_chip->edge_rising & bitmask)
+					trigger = "edge-rising";
+				else if (nmk_chip->edge_falling & bitmask)
+					trigger = "edge-falling";
+				else
+					trigger = "edge-undefined";
+
+				seq_printf(s, " irq-%d %s%s",
+					irq, trigger,
+					irqd_is_wakeup_set(&desc->irq_data)
+						? " wakeup" : "");
+			}
+		}
+
 		seq_printf(s, "\n");
 	}
 }
@@ -871,7 +920,7 @@ void nmk_gpio_wakeups_suspend(void)
 		writel(chip->fwimsc & chip->real_wake,
 		       chip->addr + NMK_GPIO_FWIMSC);
 
-		if (cpu_is_u8500v2()) {
+		if (chip->sleepmode) {
 			chip->slpm = readl(chip->addr + NMK_GPIO_SLPC);
 
 			/* 0 -> wakeup enable */
@@ -893,11 +942,30 @@ void nmk_gpio_wakeups_resume(void)
 		writel(chip->rwimsc, chip->addr + NMK_GPIO_RWIMSC);
 		writel(chip->fwimsc, chip->addr + NMK_GPIO_FWIMSC);
 
-		if (cpu_is_u8500v2())
+		if (chip->sleepmode)
 			writel(chip->slpm, chip->addr + NMK_GPIO_SLPC);
 	}
 }
 
+/*
+ * Read the pull up/pull down status.
+ * A bit set in 'pull_up' means that pull up
+ * is selected if pull is enabled in PDIS register.
+ * Note: only pull up/down set via this driver can
+ * be detected due to HW limitations.
+ */
+void nmk_gpio_read_pull(int gpio_bank, u32 *pull_up)
+{
+	if (gpio_bank < NUM_BANKS) {
+		struct nmk_gpio_chip *chip = nmk_gpio_chips[gpio_bank];
+
+		if (!chip)
+			return;
+
+		*pull_up = chip->pull_up;
+	}
+}
+
 static int __devinit nmk_gpio_probe(struct platform_device *dev)
 {
 	struct nmk_gpio_platform_data *pdata = dev->dev.platform_data;
@@ -961,6 +1029,7 @@ static int __devinit nmk_gpio_probe(struct platform_device *dev)
 	nmk_chip->secondary_parent_irq = secondary_irq;
 	nmk_chip->get_secondary_status = pdata->get_secondary_status;
 	nmk_chip->set_ioforce = pdata->set_ioforce;
+	nmk_chip->sleepmode = pdata->supports_sleepmode;
 	spin_lock_init(&nmk_chip->lock);
 
 	chip = &nmk_chip->chip;
@@ -1016,5 +1085,3 @@ core_initcall(nmk_gpio_init);
 MODULE_AUTHOR("Prafulla WADASKAR and Alessandro Rubini");
 MODULE_DESCRIPTION("Nomadik GPIO Driver");
 MODULE_LICENSE("GPL");
-
-
diff --git a/arch/arm/plat-omap/gpio.c b/drivers/gpio/gpio-omap.c
index efb869390199..35bebde23e83 100644
--- a/arch/arm/plat-omap/gpio.c
+++ b/drivers/gpio/gpio-omap.c
@@ -1,6 +1,4 @@
 /*
- *  linux/arch/arm/plat-omap/gpio.c
- *
  * Support functions for OMAP GPIO
  *
  * Copyright (C) 2003-2005 Nokia Corporation
@@ -30,109 +28,6 @@
 #include <mach/gpio.h>
 #include <asm/mach/irq.h>
 
-/*
- * OMAP1510 GPIO registers
- */
-#define OMAP1510_GPIO_DATA_INPUT	0x00
-#define OMAP1510_GPIO_DATA_OUTPUT	0x04
-#define OMAP1510_GPIO_DIR_CONTROL	0x08
-#define OMAP1510_GPIO_INT_CONTROL	0x0c
-#define OMAP1510_GPIO_INT_MASK		0x10
-#define OMAP1510_GPIO_INT_STATUS	0x14
-#define OMAP1510_GPIO_PIN_CONTROL	0x18
-
-#define OMAP1510_IH_GPIO_BASE		64
-
-/*
- * OMAP1610 specific GPIO registers
- */
-#define OMAP1610_GPIO_REVISION		0x0000
-#define OMAP1610_GPIO_SYSCONFIG		0x0010
-#define OMAP1610_GPIO_SYSSTATUS		0x0014
-#define OMAP1610_GPIO_IRQSTATUS1	0x0018
-#define OMAP1610_GPIO_IRQENABLE1	0x001c
-#define OMAP1610_GPIO_WAKEUPENABLE	0x0028
-#define OMAP1610_GPIO_DATAIN		0x002c
-#define OMAP1610_GPIO_DATAOUT		0x0030
-#define OMAP1610_GPIO_DIRECTION		0x0034
-#define OMAP1610_GPIO_EDGE_CTRL1	0x0038
-#define OMAP1610_GPIO_EDGE_CTRL2	0x003c
-#define OMAP1610_GPIO_CLEAR_IRQENABLE1	0x009c
-#define OMAP1610_GPIO_CLEAR_WAKEUPENA	0x00a8
-#define OMAP1610_GPIO_CLEAR_DATAOUT	0x00b0
-#define OMAP1610_GPIO_SET_IRQENABLE1	0x00dc
-#define OMAP1610_GPIO_SET_WAKEUPENA	0x00e8
-#define OMAP1610_GPIO_SET_DATAOUT	0x00f0
-
-/*
- * OMAP7XX specific GPIO registers
- */
-#define OMAP7XX_GPIO_DATA_INPUT		0x00
-#define OMAP7XX_GPIO_DATA_OUTPUT	0x04
-#define OMAP7XX_GPIO_DIR_CONTROL	0x08
-#define OMAP7XX_GPIO_INT_CONTROL	0x0c
-#define OMAP7XX_GPIO_INT_MASK		0x10
-#define OMAP7XX_GPIO_INT_STATUS		0x14
-
-/*
- * omap2+ specific GPIO registers
- */
-#define OMAP24XX_GPIO_REVISION		0x0000
-#define OMAP24XX_GPIO_IRQSTATUS1	0x0018
-#define OMAP24XX_GPIO_IRQSTATUS2	0x0028
-#define OMAP24XX_GPIO_IRQENABLE2	0x002c
-#define OMAP24XX_GPIO_IRQENABLE1	0x001c
-#define OMAP24XX_GPIO_WAKE_EN		0x0020
-#define OMAP24XX_GPIO_CTRL		0x0030
-#define OMAP24XX_GPIO_OE		0x0034
-#define OMAP24XX_GPIO_DATAIN		0x0038
-#define OMAP24XX_GPIO_DATAOUT		0x003c
-#define OMAP24XX_GPIO_LEVELDETECT0	0x0040
-#define OMAP24XX_GPIO_LEVELDETECT1	0x0044
-#define OMAP24XX_GPIO_RISINGDETECT	0x0048
-#define OMAP24XX_GPIO_FALLINGDETECT	0x004c
-#define OMAP24XX_GPIO_DEBOUNCE_EN	0x0050
-#define OMAP24XX_GPIO_DEBOUNCE_VAL	0x0054
-#define OMAP24XX_GPIO_CLEARIRQENABLE1	0x0060
-#define OMAP24XX_GPIO_SETIRQENABLE1	0x0064
-#define OMAP24XX_GPIO_CLEARWKUENA	0x0080
-#define OMAP24XX_GPIO_SETWKUENA		0x0084
-#define OMAP24XX_GPIO_CLEARDATAOUT	0x0090
-#define OMAP24XX_GPIO_SETDATAOUT	0x0094
-
-#define OMAP4_GPIO_REVISION		0x0000
-#define OMAP4_GPIO_EOI			0x0020
-#define OMAP4_GPIO_IRQSTATUSRAW0	0x0024
-#define OMAP4_GPIO_IRQSTATUSRAW1	0x0028
-#define OMAP4_GPIO_IRQSTATUS0		0x002c
-#define OMAP4_GPIO_IRQSTATUS1		0x0030
-#define OMAP4_GPIO_IRQSTATUSSET0	0x0034
-#define OMAP4_GPIO_IRQSTATUSSET1	0x0038
-#define OMAP4_GPIO_IRQSTATUSCLR0	0x003c
-#define OMAP4_GPIO_IRQSTATUSCLR1	0x0040
-#define OMAP4_GPIO_IRQWAKEN0		0x0044
-#define OMAP4_GPIO_IRQWAKEN1		0x0048
-#define OMAP4_GPIO_IRQENABLE1		0x011c
-#define OMAP4_GPIO_WAKE_EN		0x0120
-#define OMAP4_GPIO_IRQSTATUS2		0x0128
-#define OMAP4_GPIO_IRQENABLE2		0x012c
-#define OMAP4_GPIO_CTRL			0x0130
-#define OMAP4_GPIO_OE			0x0134
-#define OMAP4_GPIO_DATAIN		0x0138
-#define OMAP4_GPIO_DATAOUT		0x013c
-#define OMAP4_GPIO_LEVELDETECT0		0x0140
-#define OMAP4_GPIO_LEVELDETECT1		0x0144
-#define OMAP4_GPIO_RISINGDETECT		0x0148
-#define OMAP4_GPIO_FALLINGDETECT	0x014c
-#define OMAP4_GPIO_DEBOUNCENABLE	0x0150
-#define OMAP4_GPIO_DEBOUNCINGTIME	0x0154
-#define OMAP4_GPIO_CLEARIRQENABLE1	0x0160
-#define OMAP4_GPIO_SETIRQENABLE1	0x0164
-#define OMAP4_GPIO_CLEARWKUENA		0x0180
-#define OMAP4_GPIO_SETWKUENA		0x0184
-#define OMAP4_GPIO_CLEARDATAOUT		0x0190
-#define OMAP4_GPIO_SETDATAOUT		0x0194
-
 struct gpio_bank {
 	unsigned long pbase;
 	void __iomem *base;
@@ -537,7 +432,6 @@ static inline void set_24xx_gpio_triggering(struct gpio_bank *bank, int gpio,
 {
 	void __iomem *base = bank->base;
 	u32 gpio_bit = 1 << gpio;
-	u32 val;
 
 	if (cpu_is_omap44xx()) {
 		MOD_REG_BIT(OMAP4_GPIO_LEVELDETECT0, gpio_bit,
@@ -560,15 +454,8 @@ static inline void set_24xx_gpio_triggering(struct gpio_bank *bank, int gpio,
 	}
 	if (likely(!(bank->non_wakeup_gpios & gpio_bit))) {
 		if (cpu_is_omap44xx()) {
-			if (trigger != 0)
-				__raw_writel(1 << gpio, bank->base+
-						OMAP4_GPIO_IRQWAKEN0);
-			else {
-				val = __raw_readl(bank->base +
-							OMAP4_GPIO_IRQWAKEN0);
-				__raw_writel(val & (~(1 << gpio)), bank->base +
-							 OMAP4_GPIO_IRQWAKEN0);
-			}
+			MOD_REG_BIT(OMAP4_GPIO_IRQWAKEN0, gpio_bit,
+				trigger != 0);
 		} else {
 			/*
 			 * GPIO wakeup request can only be generated on edge
@@ -582,8 +469,9 @@ static inline void set_24xx_gpio_triggering(struct gpio_bank *bank, int gpio,
 					+ OMAP24XX_GPIO_CLEARWKUENA);
 		}
 	}
-	/* This part needs to be executed always for OMAP34xx */
-	if (cpu_is_omap34xx() || (bank->non_wakeup_gpios & gpio_bit)) {
+	/* This part needs to be executed always for OMAP{34xx, 44xx} */
+	if (cpu_is_omap34xx() || cpu_is_omap44xx() ||
+			(bank->non_wakeup_gpios & gpio_bit)) {
 		/*
 		 * Log the edge gpio and manually trigger the IRQ
 		 * after resume if the input level changes
@@ -1239,8 +1127,11 @@ static void gpio_irq_shutdown(struct irq_data *d)
 {
 	unsigned int gpio = d->irq - IH_GPIO_BASE;
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
+	unsigned long flags;
 
+	spin_lock_irqsave(&bank->lock, flags);
 	_reset_gpio(bank, gpio);
+	spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static void gpio_ack_irq(struct irq_data *d)
@@ -1255,9 +1146,12 @@ static void gpio_mask_irq(struct irq_data *d)
 {
 	unsigned int gpio = d->irq - IH_GPIO_BASE;
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
+	unsigned long flags;
 
+	spin_lock_irqsave(&bank->lock, flags);
 	_set_gpio_irqenable(bank, gpio, 0);
 	_set_gpio_triggering(bank, get_gpio_index(gpio), IRQ_TYPE_NONE);
+	spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static void gpio_unmask_irq(struct irq_data *d)
@@ -1266,7 +1160,9 @@ static void gpio_unmask_irq(struct irq_data *d)
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
 	unsigned int irq_mask = 1 << get_gpio_index(gpio);
 	u32 trigger = irqd_get_trigger_type(d);
+	unsigned long flags;
 
+	spin_lock_irqsave(&bank->lock, flags);
 	if (trigger)
 		_set_gpio_triggering(bank, get_gpio_index(gpio), trigger);
 
@@ -1278,6 +1174,7 @@ static void gpio_unmask_irq(struct irq_data *d)
 	}
 
 	_set_gpio_irqenable(bank, gpio, 1);
+	spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static struct irq_chip gpio_irq_chip = {
@@ -1629,7 +1526,7 @@ static void omap_gpio_mod_init(struct gpio_bank *bank, int id)
 	}
 }
 
-static void __init omap_gpio_chip_init(struct gpio_bank *bank)
+static void __devinit omap_gpio_chip_init(struct gpio_bank *bank)
 {
 	int j;
 	static int gpio;
diff --git a/arch/arm/plat-samsung/gpiolib.c b/drivers/gpio/gpio-plat-samsung.c
index ea37c0461788..ea37c0461788 100644
--- a/arch/arm/plat-samsung/gpiolib.c
+++ b/drivers/gpio/gpio-plat-samsung.c
diff --git a/arch/arm/mach-s5pc100/gpiolib.c b/drivers/gpio/gpio-s5pc100.c
index 2842394b28b5..2842394b28b5 100644
--- a/arch/arm/mach-s5pc100/gpiolib.c
+++ b/drivers/gpio/gpio-s5pc100.c
diff --git a/arch/arm/mach-s5pv210/gpiolib.c b/drivers/gpio/gpio-s5pv210.c
index 1ba20a703e05..1ba20a703e05 100644
--- a/arch/arm/mach-s5pv210/gpiolib.c
+++ b/drivers/gpio/gpio-s5pv210.c
diff --git a/arch/arm/mach-u300/gpio.c b/drivers/gpio/gpio-u300.c
index d92790140fe5..d92790140fe5 100644
--- a/arch/arm/mach-u300/gpio.c
+++ b/drivers/gpio/gpio-u300.c
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 137a8ca67822..a971e3d043ba 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1296,7 +1296,7 @@ EXPORT_SYMBOL_GPL(gpio_request_one);
  * @array:	array of the 'struct gpio'
  * @num:	how many GPIOs in the array
  */
-int gpio_request_array(struct gpio *array, size_t num)
+int gpio_request_array(const struct gpio *array, size_t num)
 {
 	int i, err;
 
@@ -1319,7 +1319,7 @@ EXPORT_SYMBOL_GPL(gpio_request_array);
  * @array:	array of the 'struct gpio'
  * @num:	how many GPIOs in the array
  */
-void gpio_free_array(struct gpio *array, size_t num)
+void gpio_free_array(const struct gpio *array, size_t num)
 {
 	while (num--)
 		gpio_free((array++)->gpio);
diff --git a/drivers/gpio/langwell_gpio.c b/drivers/gpio/langwell_gpio.c
index 1b06f67e1f69..bd6571e0097a 100644
--- a/drivers/gpio/langwell_gpio.c
+++ b/drivers/gpio/langwell_gpio.c
@@ -33,6 +33,7 @@
 #include <linux/io.h>
 #include <linux/gpio.h>
 #include <linux/slab.h>
+#include <linux/pm_runtime.h>
 
 /*
  * Langwell chip has 64 pins and thus there are 2 32bit registers to control
@@ -63,6 +64,7 @@ struct lnw_gpio {
 	void				*reg_base;
 	spinlock_t			lock;
 	unsigned			irq_base;
+	struct pci_dev			*pdev;
 };
 
 static void __iomem *gpio_reg(struct gpio_chip *chip, unsigned offset,
@@ -104,11 +106,18 @@ static int lnw_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 	u32 value;
 	unsigned long flags;
 
+	if (lnw->pdev)
+		pm_runtime_get(&lnw->pdev->dev);
+
 	spin_lock_irqsave(&lnw->lock, flags);
 	value = readl(gpdr);
 	value &= ~BIT(offset % 32);
 	writel(value, gpdr);
 	spin_unlock_irqrestore(&lnw->lock, flags);
+
+	if (lnw->pdev)
+		pm_runtime_put(&lnw->pdev->dev);
+
 	return 0;
 }
 
@@ -120,11 +129,19 @@ static int lnw_gpio_direction_output(struct gpio_chip *chip,
 	unsigned long flags;
 
 	lnw_gpio_set(chip, offset, value);
+
+	if (lnw->pdev)
+		pm_runtime_get(&lnw->pdev->dev);
+
 	spin_lock_irqsave(&lnw->lock, flags);
 	value = readl(gpdr);
 	value |= BIT(offset % 32);
 	writel(value, gpdr);
 	spin_unlock_irqrestore(&lnw->lock, flags);
+
+	if (lnw->pdev)
+		pm_runtime_put(&lnw->pdev->dev);
+
 	return 0;
 }
 
@@ -145,6 +162,10 @@ static int lnw_irq_type(struct irq_data *d, unsigned type)
 
 	if (gpio >= lnw->chip.ngpio)
 		return -EINVAL;
+
+	if (lnw->pdev)
+		pm_runtime_get(&lnw->pdev->dev);
+
 	spin_lock_irqsave(&lnw->lock, flags);
 	if (type & IRQ_TYPE_EDGE_RISING)
 		value = readl(grer) | BIT(gpio % 32);
@@ -159,6 +180,9 @@ static int lnw_irq_type(struct irq_data *d, unsigned type)
 	writel(value, gfer);
 	spin_unlock_irqrestore(&lnw->lock, flags);
 
+	if (lnw->pdev)
+		pm_runtime_put(&lnw->pdev->dev);
+
 	return 0;
 }
 
@@ -211,6 +235,39 @@ static void lnw_irq_handler(unsigned irq, struct irq_desc *desc)
 	chip->irq_eoi(data);
 }
 
+#ifdef CONFIG_PM
+static int lnw_gpio_runtime_resume(struct device *dev)
+{
+	return 0;
+}
+
+static int lnw_gpio_runtime_suspend(struct device *dev)
+{
+	return 0;
+}
+
+static int lnw_gpio_runtime_idle(struct device *dev)
+{
+	int err = pm_schedule_suspend(dev, 500);
+
+	if (!err)
+		return 0;
+
+	return -EBUSY;
+}
+
+#else
+#define lnw_gpio_runtime_suspend	NULL
+#define lnw_gpio_runtime_resume		NULL
+#define lnw_gpio_runtime_idle		NULL
+#endif
+
+static const struct dev_pm_ops lnw_gpio_pm_ops = {
+	.runtime_suspend = lnw_gpio_runtime_suspend,
+	.runtime_resume = lnw_gpio_runtime_resume,
+	.runtime_idle = lnw_gpio_runtime_idle,
+};
+
 static int __devinit lnw_gpio_probe(struct pci_dev *pdev,
 			const struct pci_device_id *id)
 {
@@ -270,6 +327,7 @@ static int __devinit lnw_gpio_probe(struct pci_dev *pdev,
 	lnw->chip.base = gpio_base;
 	lnw->chip.ngpio = id->driver_data;
 	lnw->chip.can_sleep = 0;
+	lnw->pdev = pdev;
 	pci_set_drvdata(pdev, lnw);
 	retval = gpiochip_add(&lnw->chip);
 	if (retval) {
@@ -285,6 +343,10 @@ static int __devinit lnw_gpio_probe(struct pci_dev *pdev,
 	}
 
 	spin_lock_init(&lnw->lock);
+
+	pm_runtime_put_noidle(&pdev->dev);
+	pm_runtime_allow(&pdev->dev);
+
 	goto done;
 err5:
 	kfree(lnw);
@@ -302,6 +364,9 @@ static struct pci_driver lnw_gpio_driver = {
 	.name		= "langwell_gpio",
 	.id_table	= lnw_gpio_ids,
 	.probe		= lnw_gpio_probe,
+	.driver		= {
+		.pm	= &lnw_gpio_pm_ops,
+	},
 };
 
 
diff --git a/drivers/gpio/pca953x.c b/drivers/gpio/pca953x.c
index 78a843947d82..0451d7ac94ac 100644
--- a/drivers/gpio/pca953x.c
+++ b/drivers/gpio/pca953x.c
@@ -24,33 +24,46 @@
 #include <linux/of_gpio.h>
 #endif
 
-#define PCA953X_INPUT          0
-#define PCA953X_OUTPUT         1
-#define PCA953X_INVERT         2
-#define PCA953X_DIRECTION      3
-
-#define PCA953X_GPIOS	       0x00FF
-#define PCA953X_INT	       0x0100
+#define PCA953X_INPUT		0
+#define PCA953X_OUTPUT		1
+#define PCA953X_INVERT		2
+#define PCA953X_DIRECTION	3
+
+#define PCA957X_IN		0
+#define PCA957X_INVRT		1
+#define PCA957X_BKEN		2
+#define PCA957X_PUPD		3
+#define PCA957X_CFG		4
+#define PCA957X_OUT		5
+#define PCA957X_MSK		6
+#define PCA957X_INTS		7
+
+#define PCA_GPIO_MASK		0x00FF
+#define PCA_INT			0x0100
+#define PCA953X_TYPE		0x1000
+#define PCA957X_TYPE		0x2000
 
 static const struct i2c_device_id pca953x_id[] = {
-	{ "pca9534", 8  | PCA953X_INT, },
-	{ "pca9535", 16 | PCA953X_INT, },
-	{ "pca9536", 4, },
-	{ "pca9537", 4  | PCA953X_INT, },
-	{ "pca9538", 8  | PCA953X_INT, },
-	{ "pca9539", 16 | PCA953X_INT, },
-	{ "pca9554", 8  | PCA953X_INT, },
-	{ "pca9555", 16 | PCA953X_INT, },
-	{ "pca9556", 8, },
-	{ "pca9557", 8, },
-
-	{ "max7310", 8, },
-	{ "max7312", 16 | PCA953X_INT, },
-	{ "max7313", 16 | PCA953X_INT, },
-	{ "max7315", 8  | PCA953X_INT, },
-	{ "pca6107", 8  | PCA953X_INT, },
-	{ "tca6408", 8  | PCA953X_INT, },
-	{ "tca6416", 16 | PCA953X_INT, },
+	{ "pca9534", 8  | PCA953X_TYPE | PCA_INT, },
+	{ "pca9535", 16 | PCA953X_TYPE | PCA_INT, },
+	{ "pca9536", 4  | PCA953X_TYPE, },
+	{ "pca9537", 4  | PCA953X_TYPE | PCA_INT, },
+	{ "pca9538", 8  | PCA953X_TYPE | PCA_INT, },
+	{ "pca9539", 16 | PCA953X_TYPE | PCA_INT, },
+	{ "pca9554", 8  | PCA953X_TYPE | PCA_INT, },
+	{ "pca9555", 16 | PCA953X_TYPE | PCA_INT, },
+	{ "pca9556", 8  | PCA953X_TYPE, },
+	{ "pca9557", 8  | PCA953X_TYPE, },
+	{ "pca9574", 8  | PCA957X_TYPE | PCA_INT, },
+	{ "pca9575", 16 | PCA957X_TYPE | PCA_INT, },
+
+	{ "max7310", 8  | PCA953X_TYPE, },
+	{ "max7312", 16 | PCA953X_TYPE | PCA_INT, },
+	{ "max7313", 16 | PCA953X_TYPE | PCA_INT, },
+	{ "max7315", 8  | PCA953X_TYPE | PCA_INT, },
+	{ "pca6107", 8  | PCA953X_TYPE | PCA_INT, },
+	{ "tca6408", 8  | PCA953X_TYPE | PCA_INT, },
+	{ "tca6416", 16 | PCA953X_TYPE | PCA_INT, },
 	/* NYET:  { "tca6424", 24, }, */
 	{ }
 };
@@ -75,16 +88,32 @@ struct pca953x_chip {
 	struct pca953x_platform_data *dyn_pdata;
 	struct gpio_chip gpio_chip;
 	const char *const *names;
+	int	chip_type;
 };
 
 static int pca953x_write_reg(struct pca953x_chip *chip, int reg, uint16_t val)
 {
-	int ret;
+	int ret = 0;
 
 	if (chip->gpio_chip.ngpio <= 8)
 		ret = i2c_smbus_write_byte_data(chip->client, reg, val);
-	else
-		ret = i2c_smbus_write_word_data(chip->client, reg << 1, val);
+	else {
+		switch (chip->chip_type) {
+		case PCA953X_TYPE:
+			ret = i2c_smbus_write_word_data(chip->client,
+							reg << 1, val);
+			break;
+		case PCA957X_TYPE:
+			ret = i2c_smbus_write_byte_data(chip->client, reg << 1,
+							val & 0xff);
+			if (ret < 0)
+				break;
+			ret = i2c_smbus_write_byte_data(chip->client,
+							(reg << 1) + 1,
+							(val & 0xff00) >> 8);
+			break;
+		}
+	}
 
 	if (ret < 0) {
 		dev_err(&chip->client->dev, "failed writing register\n");
@@ -116,13 +145,22 @@ static int pca953x_gpio_direction_input(struct gpio_chip *gc, unsigned off)
 {
 	struct pca953x_chip *chip;
 	uint16_t reg_val;
-	int ret;
+	int ret, offset = 0;
 
 	chip = container_of(gc, struct pca953x_chip, gpio_chip);
 
 	mutex_lock(&chip->i2c_lock);
 	reg_val = chip->reg_direction | (1u << off);
-	ret = pca953x_write_reg(chip, PCA953X_DIRECTION, reg_val);
+
+	switch (chip->chip_type) {
+	case PCA953X_TYPE:
+		offset = PCA953X_DIRECTION;
+		break;
+	case PCA957X_TYPE:
+		offset = PCA957X_CFG;
+		break;
+	}
+	ret = pca953x_write_reg(chip, offset, reg_val);
 	if (ret)
 		goto exit;
 
@@ -138,7 +176,7 @@ static int pca953x_gpio_direction_output(struct gpio_chip *gc,
 {
 	struct pca953x_chip *chip;
 	uint16_t reg_val;
-	int ret;
+	int ret, offset = 0;
 
 	chip = container_of(gc, struct pca953x_chip, gpio_chip);
 
@@ -149,7 +187,15 @@ static int pca953x_gpio_direction_output(struct gpio_chip *gc,
 	else
 		reg_val = chip->reg_output & ~(1u << off);
 
-	ret = pca953x_write_reg(chip, PCA953X_OUTPUT, reg_val);
+	switch (chip->chip_type) {
+	case PCA953X_TYPE:
+		offset = PCA953X_OUTPUT;
+		break;
+	case PCA957X_TYPE:
+		offset = PCA957X_OUT;
+		break;
+	}
+	ret = pca953x_write_reg(chip, offset, reg_val);
 	if (ret)
 		goto exit;
 
@@ -157,7 +203,15 @@ static int pca953x_gpio_direction_output(struct gpio_chip *gc,
 
 	/* then direction */
 	reg_val = chip->reg_direction & ~(1u << off);
-	ret = pca953x_write_reg(chip, PCA953X_DIRECTION, reg_val);
+	switch (chip->chip_type) {
+	case PCA953X_TYPE:
+		offset = PCA953X_DIRECTION;
+		break;
+	case PCA957X_TYPE:
+		offset = PCA957X_CFG;
+		break;
+	}
+	ret = pca953x_write_reg(chip, offset, reg_val);
 	if (ret)
 		goto exit;
 
@@ -172,12 +226,20 @@ static int pca953x_gpio_get_value(struct gpio_chip *gc, unsigned off)
 {
 	struct pca953x_chip *chip;
 	uint16_t reg_val;
-	int ret;
+	int ret, offset = 0;
 
 	chip = container_of(gc, struct pca953x_chip, gpio_chip);
 
 	mutex_lock(&chip->i2c_lock);
-	ret = pca953x_read_reg(chip, PCA953X_INPUT, &reg_val);
+	switch (chip->chip_type) {
+	case PCA953X_TYPE:
+		offset = PCA953X_INPUT;
+		break;
+	case PCA957X_TYPE:
+		offset = PCA957X_IN;
+		break;
+	}
+	ret = pca953x_read_reg(chip, offset, &reg_val);
 	mutex_unlock(&chip->i2c_lock);
 	if (ret < 0) {
 		/* NOTE:  diagnostic already emitted; that's all we should
@@ -194,7 +256,7 @@ static void pca953x_gpio_set_value(struct gpio_chip *gc, unsigned off, int val)
 {
 	struct pca953x_chip *chip;
 	uint16_t reg_val;
-	int ret;
+	int ret, offset = 0;
 
 	chip = container_of(gc, struct pca953x_chip, gpio_chip);
 
@@ -204,7 +266,15 @@ static void pca953x_gpio_set_value(struct gpio_chip *gc, unsigned off, int val)
 	else
 		reg_val = chip->reg_output & ~(1u << off);
 
-	ret = pca953x_write_reg(chip, PCA953X_OUTPUT, reg_val);
+	switch (chip->chip_type) {
+	case PCA953X_TYPE:
+		offset = PCA953X_OUTPUT;
+		break;
+	case PCA957X_TYPE:
+		offset = PCA957X_OUT;
+		break;
+	}
+	ret = pca953x_write_reg(chip, offset, reg_val);
 	if (ret)
 		goto exit;
 
@@ -322,9 +392,17 @@ static uint16_t pca953x_irq_pending(struct pca953x_chip *chip)
 	uint16_t old_stat;
 	uint16_t pending;
 	uint16_t trigger;
-	int ret;
-
-	ret = pca953x_read_reg(chip, PCA953X_INPUT, &cur_stat);
+	int ret, offset = 0;
+
+	switch (chip->chip_type) {
+	case PCA953X_TYPE:
+		offset = PCA953X_INPUT;
+		break;
+	case PCA957X_TYPE:
+		offset = PCA957X_IN;
+		break;
+	}
+	ret = pca953x_read_reg(chip, offset, &cur_stat);
 	if (ret)
 		return 0;
 
@@ -372,14 +450,21 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 {
 	struct i2c_client *client = chip->client;
 	struct pca953x_platform_data *pdata = client->dev.platform_data;
-	int ret;
+	int ret, offset = 0;
 
 	if (pdata->irq_base != -1
-			&& (id->driver_data & PCA953X_INT)) {
+			&& (id->driver_data & PCA_INT)) {
 		int lvl;
 
-		ret = pca953x_read_reg(chip, PCA953X_INPUT,
-				       &chip->irq_stat);
+		switch (chip->chip_type) {
+		case PCA953X_TYPE:
+			offset = PCA953X_INPUT;
+			break;
+		case PCA957X_TYPE:
+			offset = PCA957X_IN;
+			break;
+		}
+		ret = pca953x_read_reg(chip, offset, &chip->irq_stat);
 		if (ret)
 			goto out_failed;
 
@@ -439,7 +524,7 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 	struct i2c_client *client = chip->client;
 	struct pca953x_platform_data *pdata = client->dev.platform_data;
 
-	if (pdata->irq_base != -1 && (id->driver_data & PCA953X_INT))
+	if (pdata->irq_base != -1 && (id->driver_data & PCA_INT))
 		dev_warn(&client->dev, "interrupt support not compiled in\n");
 
 	return 0;
@@ -499,12 +584,65 @@ pca953x_get_alt_pdata(struct i2c_client *client)
 }
 #endif
 
+static int __devinit device_pca953x_init(struct pca953x_chip *chip, int invert)
+{
+	int ret;
+
+	ret = pca953x_read_reg(chip, PCA953X_OUTPUT, &chip->reg_output);
+	if (ret)
+		goto out;
+
+	ret = pca953x_read_reg(chip, PCA953X_DIRECTION,
+			       &chip->reg_direction);
+	if (ret)
+		goto out;
+
+	/* set platform specific polarity inversion */
+	ret = pca953x_write_reg(chip, PCA953X_INVERT, invert);
+	if (ret)
+		goto out;
+	return 0;
+out:
+	return ret;
+}
+
+static int __devinit device_pca957x_init(struct pca953x_chip *chip, int invert)
+{
+	int ret;
+	uint16_t val = 0;
+
+	/* Let every port in proper state, that could save power */
+	pca953x_write_reg(chip, PCA957X_PUPD, 0x0);
+	pca953x_write_reg(chip, PCA957X_CFG, 0xffff);
+	pca953x_write_reg(chip, PCA957X_OUT, 0x0);
+
+	ret = pca953x_read_reg(chip, PCA957X_IN, &val);
+	if (ret)
+		goto out;
+	ret = pca953x_read_reg(chip, PCA957X_OUT, &chip->reg_output);
+	if (ret)
+		goto out;
+	ret = pca953x_read_reg(chip, PCA957X_CFG, &chip->reg_direction);
+	if (ret)
+		goto out;
+
+	/* set platform specific polarity inversion */
+	pca953x_write_reg(chip, PCA957X_INVRT, invert);
+
+	/* To enable register 6, 7 to controll pull up and pull down */
+	pca953x_write_reg(chip, PCA957X_BKEN, 0x202);
+
+	return 0;
+out:
+	return ret;
+}
+
 static int __devinit pca953x_probe(struct i2c_client *client,
 				   const struct i2c_device_id *id)
 {
 	struct pca953x_platform_data *pdata;
 	struct pca953x_chip *chip;
-	int ret;
+	int ret = 0;
 
 	chip = kzalloc(sizeof(struct pca953x_chip), GFP_KERNEL);
 	if (chip == NULL)
@@ -531,25 +669,20 @@ static int __devinit pca953x_probe(struct i2c_client *client,
 	chip->gpio_start = pdata->gpio_base;
 
 	chip->names = pdata->names;
+	chip->chip_type = id->driver_data & (PCA953X_TYPE | PCA957X_TYPE);
 
 	mutex_init(&chip->i2c_lock);
 
 	/* initialize cached registers from their original values.
 	 * we can't share this chip with another i2c master.
 	 */
-	pca953x_setup_gpio(chip, id->driver_data & PCA953X_GPIOS);
+	pca953x_setup_gpio(chip, id->driver_data & PCA_GPIO_MASK);
 
-	ret = pca953x_read_reg(chip, PCA953X_OUTPUT, &chip->reg_output);
-	if (ret)
-		goto out_failed;
-
-	ret = pca953x_read_reg(chip, PCA953X_DIRECTION, &chip->reg_direction);
-	if (ret)
-		goto out_failed;
-
-	/* set platform specific polarity inversion */
-	ret = pca953x_write_reg(chip, PCA953X_INVERT, pdata->invert);
-	if (ret)
+	if (chip->chip_type == PCA953X_TYPE)
+		device_pca953x_init(chip, pdata->invert);
+	else if (chip->chip_type == PCA957X_TYPE)
+		device_pca957x_init(chip, pdata->invert);
+	else
 		goto out_failed;
 
 	ret = pca953x_irq_setup(chip, id);
diff --git a/drivers/gpio/pch_gpio.c b/drivers/gpio/pch_gpio.c
index f970a5f3585e..36919e77c495 100644
--- a/drivers/gpio/pch_gpio.c
+++ b/drivers/gpio/pch_gpio.c
@@ -283,8 +283,10 @@ static int pch_gpio_resume(struct pci_dev *pdev)
 #define pch_gpio_resume NULL
 #endif
 
+#define PCI_VENDOR_ID_ROHM             0x10DB
 static DEFINE_PCI_DEVICE_TABLE(pch_gpio_pcidev_id) = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x8803) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_ROHM, 0x8014) },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, pch_gpio_pcidev_id);
diff --git a/drivers/gpio/tps65910-gpio.c b/drivers/gpio/tps65910-gpio.c
new file mode 100644
index 000000000000..8d1ddfdd63eb
--- /dev/null
+++ b/drivers/gpio/tps65910-gpio.c
@@ -0,0 +1,100 @@
+/*
+ * tps65910-gpio.c  --  TI TPS6591x
+ *
+ * Copyright 2010 Texas Instruments Inc.
+ *
+ * Author: Graeme Gregory <gg@slimlogic.co.uk>
+ * Author: Jorge Eduardo Candelaria jedu@slimlogic.co.uk>
+ *
+ *  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/gpio.h>
+#include <linux/i2c.h>
+#include <linux/mfd/tps65910.h>
+
+static int tps65910_gpio_get(struct gpio_chip *gc, unsigned offset)
+{
+	struct tps65910 *tps65910 = container_of(gc, struct tps65910, gpio);
+	uint8_t val;
+
+	tps65910->read(tps65910, TPS65910_GPIO0 + offset, 1, &val);
+
+	if (val & GPIO_STS_MASK)
+		return 1;
+
+	return 0;
+}
+
+static void tps65910_gpio_set(struct gpio_chip *gc, unsigned offset,
+			      int value)
+{
+	struct tps65910 *tps65910 = container_of(gc, struct tps65910, gpio);
+
+	if (value)
+		tps65910_set_bits(tps65910, TPS65910_GPIO0 + offset,
+						GPIO_SET_MASK);
+	else
+		tps65910_clear_bits(tps65910, TPS65910_GPIO0 + offset,
+						GPIO_SET_MASK);
+}
+
+static int tps65910_gpio_output(struct gpio_chip *gc, unsigned offset,
+				int value)
+{
+	struct tps65910 *tps65910 = container_of(gc, struct tps65910, gpio);
+
+	/* Set the initial value */
+	tps65910_gpio_set(gc, 0, value);
+
+	return tps65910_set_bits(tps65910, TPS65910_GPIO0 + offset,
+						GPIO_CFG_MASK);
+}
+
+static int tps65910_gpio_input(struct gpio_chip *gc, unsigned offset)
+{
+	struct tps65910 *tps65910 = container_of(gc, struct tps65910, gpio);
+
+	return tps65910_clear_bits(tps65910, TPS65910_GPIO0 + offset,
+						GPIO_CFG_MASK);
+}
+
+void tps65910_gpio_init(struct tps65910 *tps65910, int gpio_base)
+{
+	int ret;
+
+	if (!gpio_base)
+		return;
+
+	tps65910->gpio.owner		= THIS_MODULE;
+	tps65910->gpio.label		= tps65910->i2c_client->name;
+	tps65910->gpio.dev		= tps65910->dev;
+	tps65910->gpio.base		= gpio_base;
+
+	switch(tps65910_chip_id(tps65910)) {
+	case TPS65910:
+		tps65910->gpio.ngpio	= 6;
+	case TPS65911:
+		tps65910->gpio.ngpio	= 9;
+	default:
+		return;
+	}
+	tps65910->gpio.can_sleep	= 1;
+
+	tps65910->gpio.direction_input	= tps65910_gpio_input;
+	tps65910->gpio.direction_output	= tps65910_gpio_output;
+	tps65910->gpio.set		= tps65910_gpio_set;
+	tps65910->gpio.get		= tps65910_gpio_get;
+
+	ret = gpiochip_add(&tps65910->gpio);
+
+	if (ret)
+		dev_warn(tps65910->dev, "GPIO registration failed: %d\n", ret);
+}
diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index 3e257a50bf56..61e1ef90d4e5 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -46,10 +46,11 @@ static struct drm_map_list *drm_find_matching_map(struct drm_device *dev,
 	list_for_each_entry(entry, &dev->maplist, head) {
 		/*
 		 * Because the kernel-userspace ABI is fixed at a 32-bit offset
-		 * while PCI resources may live above that, we ignore the map
-		 * offset for maps of type _DRM_FRAMEBUFFER or _DRM_REGISTERS.
-		 * It is assumed that each driver will have only one resource of
-		 * each type.
+		 * while PCI resources may live above that, we only compare the
+		 * lower 32 bits of the map offset for maps of type
+		 * _DRM_FRAMEBUFFER or _DRM_REGISTERS.
+		 * It is assumed that if a driver have more than one resource
+		 * of each type, the lower 32 bits are different.
 		 */
 		if (!entry->map ||
 		    map->type != entry->map->type ||
@@ -59,9 +60,12 @@ static struct drm_map_list *drm_find_matching_map(struct drm_device *dev,
 		case _DRM_SHM:
 			if (map->flags != _DRM_CONTAINS_LOCK)
 				break;
+			return entry;
 		case _DRM_REGISTERS:
 		case _DRM_FRAME_BUFFER:
-			return entry;
+			if ((entry->map->offset & 0xffffffff) ==
+			    (map->offset & 0xffffffff))
+				return entry;
 		default: /* Make gcc happy */
 			;
 		}
@@ -183,9 +187,6 @@ static int drm_addmap_core(struct drm_device * dev, resource_size_t offset,
 			return -EINVAL;
 		}
 #endif
-#ifdef __alpha__
-		map->offset += dev->hose->mem_space->start;
-#endif
 		/* Some drivers preinitialize some maps, without the X Server
 		 * needing to be aware of it.  Therefore, we just return success
 		 * when the server tries to create a duplicate map.
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 872747c5a544..21058e6ad2b8 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -1113,7 +1113,7 @@ int drm_mode_getresources(struct drm_device *dev, void *data,
 	if (card_res->count_fbs >= fb_count) {
 		copied = 0;
 		fb_id = (uint32_t __user *)(unsigned long)card_res->fb_id_ptr;
-		list_for_each_entry(fb, &file_priv->fbs, head) {
+		list_for_each_entry(fb, &file_priv->fbs, filp_head) {
 			if (put_user(fb->base.id, fb_id + copied)) {
 				ret = -EFAULT;
 				goto out;
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 0a9357c66ff8..09292193dafe 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -184,9 +184,9 @@ drm_edid_block_valid(u8 *raw_edid)
 
 bad:
 	if (raw_edid) {
-		DRM_ERROR("Raw EDID:\n");
+		printk(KERN_ERR "Raw EDID:\n");
 		print_hex_dump_bytes(KERN_ERR, DUMP_PREFIX_NONE, raw_edid, EDID_LENGTH);
-		printk("\n");
+		printk(KERN_ERR "\n");
 	}
 	return 0;
 }
@@ -258,6 +258,17 @@ drm_do_probe_ddc_edid(struct i2c_adapter *adapter, unsigned char *buf,
 	return ret == 2 ? 0 : -1;
 }
 
+static bool drm_edid_is_zero(u8 *in_edid, int length)
+{
+	int i;
+	u32 *raw_edid = (u32 *)in_edid;
+
+	for (i = 0; i < length / 4; i++)
+		if (*(raw_edid + i) != 0)
+			return false;
+	return true;
+}
+
 static u8 *
 drm_do_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter)
 {
@@ -273,6 +284,10 @@ drm_do_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter)
 			goto out;
 		if (drm_edid_block_valid(block))
 			break;
+		if (i == 0 && drm_edid_is_zero(block, EDID_LENGTH)) {
+			connector->null_edid_counter++;
+			goto carp;
+		}
 	}
 	if (i == 4)
 		goto carp;
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 74e4ff578017..4012fe423460 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -34,6 +34,7 @@
 #include <linux/module.h>
 #include <linux/mman.h>
 #include <linux/pagemap.h>
+#include <linux/shmem_fs.h>
 #include "drmP.h"
 
 /** @file drm_gem.c
diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c
index d61d185cf040..4a058c7af6c0 100644
--- a/drivers/gpu/drm/drm_ioc32.c
+++ b/drivers/gpu/drm/drm_ioc32.c
@@ -28,6 +28,7 @@
  * IN THE SOFTWARE.
  */
 #include <linux/compat.h>
+#include <linux/ratelimit.h>
 
 #include "drmP.h"
 #include "drm_core.h"
@@ -253,10 +254,10 @@ static int compat_drm_addmap(struct file *file, unsigned int cmd,
 		return -EFAULT;
 
 	m32.handle = (unsigned long)handle;
-	if (m32.handle != (unsigned long)handle && printk_ratelimit())
-		printk(KERN_ERR "compat_drm_addmap truncated handle"
-		       " %p for type %d offset %x\n",
-		       handle, m32.type, m32.offset);
+	if (m32.handle != (unsigned long)handle)
+		printk_ratelimited(KERN_ERR "compat_drm_addmap truncated handle"
+				   " %p for type %d offset %x\n",
+				   handle, m32.type, m32.offset);
 
 	if (copy_to_user(argp, &m32, sizeof(m32)))
 		return -EFAULT;
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index e1aee4f6a7c6..b6a19cb07caf 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -251,7 +251,7 @@ err:
 }
 
 
-int drm_pci_irq_by_busid(struct drm_device *dev, struct drm_irq_busid *p)
+static int drm_pci_irq_by_busid(struct drm_device *dev, struct drm_irq_busid *p)
 {
 	if ((p->busnum >> 8) != drm_get_pci_domain(dev) ||
 	    (p->busnum & 0xff) != dev->pdev->bus->number ||
@@ -292,6 +292,7 @@ static struct drm_bus drm_pci_bus = {
 	.get_name = drm_pci_get_name,
 	.set_busid = drm_pci_set_busid,
 	.set_unique = drm_pci_set_unique,
+	.irq_by_busid = drm_pci_irq_by_busid,
 	.agp_init = drm_pci_agp_init,
 };
 
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index 2c3fcbdfd8ff..5db96d45fc71 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -526,7 +526,7 @@ static int drm_mmap_dma(struct file *filp, struct vm_area_struct *vma)
 static resource_size_t drm_core_get_reg_ofs(struct drm_device *dev)
 {
 #ifdef __alpha__
-	return dev->hose->dense_mem_base - dev->hose->mem_space->start;
+	return dev->hose->dense_mem_base;
 #else
 	return 0;
 #endif
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 51c2257b11e6..4d46441cbe2d 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -776,7 +776,7 @@ static int i915_error_state(struct seq_file *m, void *unused)
 	seq_printf(m, "  INSTPM: 0x%08x\n", error->instpm);
 	seq_printf(m, "  seqno: 0x%08x\n", error->seqno);
 
-	for (i = 0; i < 16; i++)
+	for (i = 0; i < dev_priv->num_fence_regs; i++)
 		seq_printf(m, "  fence[%d] = %08llx\n", i, error->fence[i]);
 
 	if (error->active_bo)
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 0239e9974bf2..2b79588541e7 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -2182,9 +2182,8 @@ int i915_driver_unload(struct drm_device *dev)
 		/* Flush any outstanding unpin_work. */
 		flush_workqueue(dev_priv->wq);
 
-		i915_gem_free_all_phys_object(dev);
-
 		mutex_lock(&dev->struct_mutex);
+		i915_gem_free_all_phys_object(dev);
 		i915_gem_cleanup_ringbuffer(dev);
 		mutex_unlock(&dev->struct_mutex);
 		if (I915_HAS_FBC(dev) && i915_powersave)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ee660355ae68..f63ee162f124 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -716,6 +716,7 @@ typedef struct drm_i915_private {
 	struct intel_fbdev *fbdev;
 
 	struct drm_property *broadcast_rgb_property;
+	struct drm_property *force_audio_property;
 
 	atomic_t forcewake_count;
 } drm_i915_private_t;
@@ -909,13 +910,6 @@ struct drm_i915_file_private {
 	} mm;
 };
 
-enum intel_chip_family {
-	CHIP_I8XX = 0x01,
-	CHIP_I9XX = 0x02,
-	CHIP_I915 = 0x04,
-	CHIP_I965 = 0x08,
-};
-
 #define INTEL_INFO(dev)	(((struct drm_i915_private *) (dev)->dev_private)->info)
 
 #define IS_I830(dev)		((dev)->pci_device == 0x3577)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0b2e167d2bce..85f713746a1f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -31,6 +31,7 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 #include "intel_drv.h"
+#include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/pci.h>
@@ -354,13 +355,12 @@ i915_gem_shmem_pread_fast(struct drm_device *dev,
 		 * page_offset = offset within page
 		 * page_length = bytes to copy for this page
 		 */
-		page_offset = offset & (PAGE_SIZE-1);
+		page_offset = offset_in_page(offset);
 		page_length = remain;
 		if ((page_offset + remain) > PAGE_SIZE)
 			page_length = PAGE_SIZE - page_offset;
 
-		page = read_cache_page_gfp(mapping, offset >> PAGE_SHIFT,
-					   GFP_HIGHUSER | __GFP_RECLAIMABLE);
+		page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT);
 		if (IS_ERR(page))
 			return PTR_ERR(page);
 
@@ -453,9 +453,9 @@ i915_gem_shmem_pread_slow(struct drm_device *dev,
 		 * data_page_offset = offset with data_page_index page.
 		 * page_length = bytes to copy for this page
 		 */
-		shmem_page_offset = offset & ~PAGE_MASK;
+		shmem_page_offset = offset_in_page(offset);
 		data_page_index = data_ptr / PAGE_SIZE - first_data_page;
-		data_page_offset = data_ptr & ~PAGE_MASK;
+		data_page_offset = offset_in_page(data_ptr);
 
 		page_length = remain;
 		if ((shmem_page_offset + page_length) > PAGE_SIZE)
@@ -463,10 +463,11 @@ i915_gem_shmem_pread_slow(struct drm_device *dev,
 		if ((data_page_offset + page_length) > PAGE_SIZE)
 			page_length = PAGE_SIZE - data_page_offset;
 
-		page = read_cache_page_gfp(mapping, offset >> PAGE_SHIFT,
-					   GFP_HIGHUSER | __GFP_RECLAIMABLE);
-		if (IS_ERR(page))
-			return PTR_ERR(page);
+		page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT);
+		if (IS_ERR(page)) {
+			ret = PTR_ERR(page);
+			goto out;
+		}
 
 		if (do_bit17_swizzling) {
 			slow_shmem_bit17_copy(page,
@@ -638,8 +639,8 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 		 * page_offset = offset within page
 		 * page_length = bytes to copy for this page
 		 */
-		page_base = (offset & ~(PAGE_SIZE-1));
-		page_offset = offset & (PAGE_SIZE-1);
+		page_base = offset & PAGE_MASK;
+		page_offset = offset_in_page(offset);
 		page_length = remain;
 		if ((page_offset + remain) > PAGE_SIZE)
 			page_length = PAGE_SIZE - page_offset;
@@ -650,7 +651,6 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 		 */
 		if (fast_user_write(dev_priv->mm.gtt_mapping, page_base,
 				    page_offset, user_data, page_length))
-
 			return -EFAULT;
 
 		remain -= page_length;
@@ -730,9 +730,9 @@ i915_gem_gtt_pwrite_slow(struct drm_device *dev,
 		 * page_length = bytes to copy for this page
 		 */
 		gtt_page_base = offset & PAGE_MASK;
-		gtt_page_offset = offset & ~PAGE_MASK;
+		gtt_page_offset = offset_in_page(offset);
 		data_page_index = data_ptr / PAGE_SIZE - first_data_page;
-		data_page_offset = data_ptr & ~PAGE_MASK;
+		data_page_offset = offset_in_page(data_ptr);
 
 		page_length = remain;
 		if ((gtt_page_offset + page_length) > PAGE_SIZE)
@@ -791,13 +791,12 @@ i915_gem_shmem_pwrite_fast(struct drm_device *dev,
 		 * page_offset = offset within page
 		 * page_length = bytes to copy for this page
 		 */
-		page_offset = offset & (PAGE_SIZE-1);
+		page_offset = offset_in_page(offset);
 		page_length = remain;
 		if ((page_offset + remain) > PAGE_SIZE)
 			page_length = PAGE_SIZE - page_offset;
 
-		page = read_cache_page_gfp(mapping, offset >> PAGE_SHIFT,
-					   GFP_HIGHUSER | __GFP_RECLAIMABLE);
+		page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT);
 		if (IS_ERR(page))
 			return PTR_ERR(page);
 
@@ -896,9 +895,9 @@ i915_gem_shmem_pwrite_slow(struct drm_device *dev,
 		 * data_page_offset = offset with data_page_index page.
 		 * page_length = bytes to copy for this page
 		 */
-		shmem_page_offset = offset & ~PAGE_MASK;
+		shmem_page_offset = offset_in_page(offset);
 		data_page_index = data_ptr / PAGE_SIZE - first_data_page;
-		data_page_offset = data_ptr & ~PAGE_MASK;
+		data_page_offset = offset_in_page(data_ptr);
 
 		page_length = remain;
 		if ((shmem_page_offset + page_length) > PAGE_SIZE)
@@ -906,8 +905,7 @@ i915_gem_shmem_pwrite_slow(struct drm_device *dev,
 		if ((data_page_offset + page_length) > PAGE_SIZE)
 			page_length = PAGE_SIZE - data_page_offset;
 
-		page = read_cache_page_gfp(mapping, offset >> PAGE_SHIFT,
-					   GFP_HIGHUSER | __GFP_RECLAIMABLE);
+		page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT);
 		if (IS_ERR(page)) {
 			ret = PTR_ERR(page);
 			goto out;
@@ -1218,11 +1216,11 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		ret = i915_gem_object_bind_to_gtt(obj, 0, true);
 		if (ret)
 			goto unlock;
-	}
 
-	ret = i915_gem_object_set_to_gtt_domain(obj, write);
-	if (ret)
-		goto unlock;
+		ret = i915_gem_object_set_to_gtt_domain(obj, write);
+		if (ret)
+			goto unlock;
+	}
 
 	if (obj->tiling_mode == I915_TILING_NONE)
 		ret = i915_gem_object_put_fence(obj);
@@ -1450,8 +1448,9 @@ i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj)
 	 * edge of an even tile row (where tile rows are counted as if the bo is
 	 * placed in a fenced gtt region).
 	 */
-	if (IS_GEN2(dev) ||
-	    (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev)))
+	if (IS_GEN2(dev))
+		tile_height = 16;
+	else if (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev))
 		tile_height = 32;
 	else
 		tile_height = 8;
@@ -1556,12 +1555,10 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj,
 
 	inode = obj->base.filp->f_path.dentry->d_inode;
 	mapping = inode->i_mapping;
+	gfpmask |= mapping_gfp_mask(mapping);
+
 	for (i = 0; i < page_count; i++) {
-		page = read_cache_page_gfp(mapping, i,
-					   GFP_HIGHUSER |
-					   __GFP_COLD |
-					   __GFP_RECLAIMABLE |
-					   gfpmask);
+		page = shmem_read_mapping_page_gfp(mapping, i, gfpmask);
 		if (IS_ERR(page))
 			goto err_pages;
 
@@ -1699,13 +1696,10 @@ i915_gem_object_truncate(struct drm_i915_gem_object *obj)
 	/* Our goal here is to return as much of the memory as
 	 * is possible back to the system as we are called from OOM.
 	 * To do this we must instruct the shmfs to drop all of its
-	 * backing pages, *now*. Here we mirror the actions taken
-	 * when by shmem_delete_inode() to release the backing store.
+	 * backing pages, *now*.
 	 */
 	inode = obj->base.filp->f_path.dentry->d_inode;
-	truncate_inode_pages(inode->i_mapping, 0);
-	if (inode->i_op->truncate_range)
-		inode->i_op->truncate_range(inode, 0, (loff_t)-1);
+	shmem_truncate_range(inode, 0, (loff_t)-1);
 
 	obj->madv = __I915_MADV_PURGED;
 }
@@ -2924,8 +2918,6 @@ i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj)
 	 */
 	wmb();
 
-	i915_gem_release_mmap(obj);
-
 	old_write_domain = obj->base.write_domain;
 	obj->base.write_domain = 0;
 
@@ -3565,6 +3557,7 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj;
+	struct address_space *mapping;
 
 	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
 	if (obj == NULL)
@@ -3575,6 +3568,9 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
 		return NULL;
 	}
 
+	mapping = obj->base.filp->f_path.dentry->d_inode->i_mapping;
+	mapping_set_gfp_mask(mapping, GFP_HIGHUSER | __GFP_RECLAIMABLE);
+
 	i915_gem_info_add_obj(dev_priv, size);
 
 	obj->base.write_domain = I915_GEM_DOMAIN_CPU;
@@ -3950,8 +3946,7 @@ void i915_gem_detach_phys_object(struct drm_device *dev,
 
 	page_count = obj->base.size / PAGE_SIZE;
 	for (i = 0; i < page_count; i++) {
-		struct page *page = read_cache_page_gfp(mapping, i,
-							GFP_HIGHUSER | __GFP_RECLAIMABLE);
+		struct page *page = shmem_read_mapping_page(mapping, i);
 		if (!IS_ERR(page)) {
 			char *dst = kmap_atomic(page);
 			memcpy(dst, vaddr + i*PAGE_SIZE, PAGE_SIZE);
@@ -4012,8 +4007,7 @@ i915_gem_attach_phys_object(struct drm_device *dev,
 		struct page *page;
 		char *dst, *src;
 
-		page = read_cache_page_gfp(mapping, i,
-					   GFP_HIGHUSER | __GFP_RECLAIMABLE);
+		page = shmem_read_mapping_page(mapping, i);
 		if (IS_ERR(page))
 			return PTR_ERR(page);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 20a4cc5b818f..4934cf84c320 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -187,10 +187,6 @@ i915_gem_object_set_to_gpu_domain(struct drm_i915_gem_object *obj,
 	if ((flush_domains | invalidate_domains) & I915_GEM_DOMAIN_CPU)
 		i915_gem_clflush_object(obj);
 
-	/* blow away mappings if mapped through GTT */
-	if ((flush_domains | invalidate_domains) & I915_GEM_DOMAIN_GTT)
-		i915_gem_release_mmap(obj);
-
 	if (obj->base.pending_write_domain)
 		cd->flips |= atomic_read(&obj->pending_flip);
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index b79619a7b788..ae2b49969b99 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -517,7 +517,7 @@ irqreturn_t ivybridge_irq_handler(DRM_IRQ_ARGS)
 	if (de_iir & DE_PIPEA_VBLANK_IVB)
 		drm_handle_vblank(dev, 0);
 
-	if (de_iir & DE_PIPEB_VBLANK_IVB);
+	if (de_iir & DE_PIPEB_VBLANK_IVB)
 		drm_handle_vblank(dev, 1);
 
 	/* check event from PCH */
@@ -1740,6 +1740,17 @@ void ironlake_irq_preinstall(struct drm_device *dev)
 		INIT_WORK(&dev_priv->rps_work, gen6_pm_rps_work);
 
 	I915_WRITE(HWSTAM, 0xeffe);
+	if (IS_GEN6(dev)) {
+		/* Workaround stalls observed on Sandy Bridge GPUs by
+		 * making the blitter command streamer generate a
+		 * write to the Hardware Status Page for
+		 * MI_USER_INTERRUPT.  This appears to serialize the
+		 * previous seqno write out before the interrupt
+		 * happens.
+		 */
+		I915_WRITE(GEN6_BLITTER_HWSTAM, ~GEN6_BLITTER_USER_INTERRUPT);
+		I915_WRITE(GEN6_BSD_HWSTAM, ~GEN6_BSD_USER_INTERRUPT);
+	}
 
 	/* XXX hotplug from PCH */
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 2f967af8e62e..5d5def756c9e 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -531,6 +531,7 @@
 #define   GEN6_BSD_SLEEP_PSMI_CONTROL_RC_ILDL_MESSAGE_ENABLE		0
 #define   GEN6_BSD_SLEEP_PSMI_CONTROL_IDLE_INDICATOR			(1 << 3)
 
+#define GEN6_BSD_HWSTAM			0x12098
 #define GEN6_BSD_IMR			0x120a8
 #define   GEN6_BSD_USER_INTERRUPT	(1 << 12)
 
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index 60a94d2b5264..e8152d23d5b6 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -678,6 +678,7 @@ void i915_save_display(struct drm_device *dev)
 	}
 
 	/* VGA state */
+	mutex_lock(&dev->struct_mutex);
 	dev_priv->saveVGA0 = I915_READ(VGA0);
 	dev_priv->saveVGA1 = I915_READ(VGA1);
 	dev_priv->saveVGA_PD = I915_READ(VGA_PD);
@@ -687,6 +688,7 @@ void i915_save_display(struct drm_device *dev)
 		dev_priv->saveVGACNTRL = I915_READ(VGACNTRL);
 
 	i915_save_vga(dev);
+	mutex_unlock(&dev->struct_mutex);
 }
 
 void i915_restore_display(struct drm_device *dev)
@@ -780,6 +782,8 @@ void i915_restore_display(struct drm_device *dev)
 		I915_WRITE(CPU_VGACNTRL, dev_priv->saveVGACNTRL);
 	else
 		I915_WRITE(VGACNTRL, dev_priv->saveVGACNTRL);
+
+	mutex_lock(&dev->struct_mutex);
 	I915_WRITE(VGA0, dev_priv->saveVGA0);
 	I915_WRITE(VGA1, dev_priv->saveVGA1);
 	I915_WRITE(VGA_PD, dev_priv->saveVGA_PD);
@@ -787,6 +791,7 @@ void i915_restore_display(struct drm_device *dev)
 	udelay(150);
 
 	i915_restore_vga(dev);
+	mutex_unlock(&dev->struct_mutex);
 }
 
 int i915_save_state(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index e93f93cc7e78..0979d8877880 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -288,6 +288,8 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 		 * This may be a DVI-I connector with a shared DDC
 		 * link between analog and digital outputs, so we
 		 * have to check the EDID input spec of the attached device.
+		 *
+		 * On the other hand, what should we do if it is a broken EDID?
 		 */
 		if (edid != NULL) {
 			is_digital = edid->input & DRM_EDID_INPUT_DIGITAL;
@@ -298,6 +300,8 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 		if (!is_digital) {
 			DRM_DEBUG_KMS("CRT detected via DDC:0x50 [EDID]\n");
 			return true;
+		} else {
+			DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n");
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index f553ddfdc168..aa43e7be6053 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3983,54 +3983,6 @@ static void i830_update_wm(struct drm_device *dev)
 #define ILK_LP0_PLANE_LATENCY		700
 #define ILK_LP0_CURSOR_LATENCY		1300
 
-static bool ironlake_compute_wm0(struct drm_device *dev,
-				 int pipe,
-				 const struct intel_watermark_params *display,
-				 int display_latency_ns,
-				 const struct intel_watermark_params *cursor,
-				 int cursor_latency_ns,
-				 int *plane_wm,
-				 int *cursor_wm)
-{
-	struct drm_crtc *crtc;
-	int htotal, hdisplay, clock, pixel_size;
-	int line_time_us, line_count;
-	int entries, tlb_miss;
-
-	crtc = intel_get_crtc_for_pipe(dev, pipe);
-	if (crtc->fb == NULL || !crtc->enabled)
-		return false;
-
-	htotal = crtc->mode.htotal;
-	hdisplay = crtc->mode.hdisplay;
-	clock = crtc->mode.clock;
-	pixel_size = crtc->fb->bits_per_pixel / 8;
-
-	/* Use the small buffer method to calculate plane watermark */
-	entries = ((clock * pixel_size / 1000) * display_latency_ns) / 1000;
-	tlb_miss = display->fifo_size*display->cacheline_size - hdisplay * 8;
-	if (tlb_miss > 0)
-		entries += tlb_miss;
-	entries = DIV_ROUND_UP(entries, display->cacheline_size);
-	*plane_wm = entries + display->guard_size;
-	if (*plane_wm > (int)display->max_wm)
-		*plane_wm = display->max_wm;
-
-	/* Use the large buffer method to calculate cursor watermark */
-	line_time_us = ((htotal * 1000) / clock);
-	line_count = (cursor_latency_ns / line_time_us + 1000) / 1000;
-	entries = line_count * 64 * pixel_size;
-	tlb_miss = cursor->fifo_size*cursor->cacheline_size - hdisplay * 8;
-	if (tlb_miss > 0)
-		entries += tlb_miss;
-	entries = DIV_ROUND_UP(entries, cursor->cacheline_size);
-	*cursor_wm = entries + cursor->guard_size;
-	if (*cursor_wm > (int)cursor->max_wm)
-		*cursor_wm = (int)cursor->max_wm;
-
-	return true;
-}
-
 /*
  * Check the wm result.
  *
@@ -4139,12 +4091,12 @@ static void ironlake_update_wm(struct drm_device *dev)
 	unsigned int enabled;
 
 	enabled = 0;
-	if (ironlake_compute_wm0(dev, 0,
-				 &ironlake_display_wm_info,
-				 ILK_LP0_PLANE_LATENCY,
-				 &ironlake_cursor_wm_info,
-				 ILK_LP0_CURSOR_LATENCY,
-				 &plane_wm, &cursor_wm)) {
+	if (g4x_compute_wm0(dev, 0,
+			    &ironlake_display_wm_info,
+			    ILK_LP0_PLANE_LATENCY,
+			    &ironlake_cursor_wm_info,
+			    ILK_LP0_CURSOR_LATENCY,
+			    &plane_wm, &cursor_wm)) {
 		I915_WRITE(WM0_PIPEA_ILK,
 			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
 		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
@@ -4153,12 +4105,12 @@ static void ironlake_update_wm(struct drm_device *dev)
 		enabled |= 1;
 	}
 
-	if (ironlake_compute_wm0(dev, 1,
-				 &ironlake_display_wm_info,
-				 ILK_LP0_PLANE_LATENCY,
-				 &ironlake_cursor_wm_info,
-				 ILK_LP0_CURSOR_LATENCY,
-				 &plane_wm, &cursor_wm)) {
+	if (g4x_compute_wm0(dev, 1,
+			    &ironlake_display_wm_info,
+			    ILK_LP0_PLANE_LATENCY,
+			    &ironlake_cursor_wm_info,
+			    ILK_LP0_CURSOR_LATENCY,
+			    &plane_wm, &cursor_wm)) {
 		I915_WRITE(WM0_PIPEB_ILK,
 			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
 		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
@@ -4223,10 +4175,10 @@ static void sandybridge_update_wm(struct drm_device *dev)
 	unsigned int enabled;
 
 	enabled = 0;
-	if (ironlake_compute_wm0(dev, 0,
-				 &sandybridge_display_wm_info, latency,
-				 &sandybridge_cursor_wm_info, latency,
-				 &plane_wm, &cursor_wm)) {
+	if (g4x_compute_wm0(dev, 0,
+			    &sandybridge_display_wm_info, latency,
+			    &sandybridge_cursor_wm_info, latency,
+			    &plane_wm, &cursor_wm)) {
 		I915_WRITE(WM0_PIPEA_ILK,
 			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
 		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
@@ -4235,10 +4187,10 @@ static void sandybridge_update_wm(struct drm_device *dev)
 		enabled |= 1;
 	}
 
-	if (ironlake_compute_wm0(dev, 1,
-				 &sandybridge_display_wm_info, latency,
-				 &sandybridge_cursor_wm_info, latency,
-				 &plane_wm, &cursor_wm)) {
+	if (g4x_compute_wm0(dev, 1,
+			    &sandybridge_display_wm_info, latency,
+			    &sandybridge_cursor_wm_info, latency,
+			    &plane_wm, &cursor_wm)) {
 		I915_WRITE(WM0_PIPEB_ILK,
 			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
 		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
@@ -4735,6 +4687,7 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc,
 
 	I915_WRITE(DSPCNTR(plane), dspcntr);
 	POSTING_READ(DSPCNTR(plane));
+	intel_enable_plane(dev_priv, plane, pipe);
 
 	ret = intel_pipe_set_base(crtc, x, y, old_fb);
 
@@ -5265,8 +5218,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 
 	I915_WRITE(DSPCNTR(plane), dspcntr);
 	POSTING_READ(DSPCNTR(plane));
-	if (!HAS_PCH_SPLIT(dev))
-		intel_enable_plane(dev_priv, plane, pipe);
 
 	ret = intel_pipe_set_base(crtc, x, y, old_fb);
 
@@ -7675,6 +7626,7 @@ static void intel_init_display(struct drm_device *dev)
 			dev_priv->display.update_wm = NULL;
 		} else
 			dev_priv->display.update_wm = pineview_update_wm;
+		dev_priv->display.init_clock_gating = gen3_init_clock_gating;
 	} else if (IS_G4X(dev)) {
 		dev_priv->display.update_wm = g4x_update_wm;
 		dev_priv->display.init_clock_gating = g4x_init_clock_gating;
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index a4d80314e7f8..391b55f1cc74 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -59,8 +59,6 @@ struct intel_dp {
 	bool is_pch_edp;
 	uint8_t	train_set[4];
 	uint8_t link_status[DP_LINK_STATUS_SIZE];
-
-	struct drm_property *force_audio_property;
 };
 
 /**
@@ -1702,7 +1700,7 @@ intel_dp_set_property(struct drm_connector *connector,
 	if (ret)
 		return ret;
 
-	if (property == intel_dp->force_audio_property) {
+	if (property == dev_priv->force_audio_property) {
 		int i = val;
 		bool has_audio;
 
@@ -1841,16 +1839,7 @@ bool intel_dpd_is_edp(struct drm_device *dev)
 static void
 intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connector)
 {
-	struct drm_device *dev = connector->dev;
-
-	intel_dp->force_audio_property =
-		drm_property_create(dev, DRM_MODE_PROP_RANGE, "force_audio", 2);
-	if (intel_dp->force_audio_property) {
-		intel_dp->force_audio_property->values[0] = -1;
-		intel_dp->force_audio_property->values[1] = 1;
-		drm_connector_attach_property(connector, intel_dp->force_audio_property, 0);
-	}
-
+	intel_attach_force_audio_property(connector);
 	intel_attach_broadcast_rgb_property(connector);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 831d7a4a0d18..9ffa61eb4d7e 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -236,6 +236,7 @@ struct intel_unpin_work {
 int intel_ddc_get_modes(struct drm_connector *c, struct i2c_adapter *adapter);
 extern bool intel_ddc_probe(struct intel_encoder *intel_encoder, int ddc_bus);
 
+extern void intel_attach_force_audio_property(struct drm_connector *connector);
 extern void intel_attach_broadcast_rgb_property(struct drm_connector *connector);
 
 extern void intel_crt_init(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index f289b8642976..aa0a8e83142e 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -45,7 +45,6 @@ struct intel_hdmi {
 	bool has_hdmi_sink;
 	bool has_audio;
 	int force_audio;
-	struct drm_property *force_audio_property;
 };
 
 static struct intel_hdmi *enc_to_intel_hdmi(struct drm_encoder *encoder)
@@ -194,7 +193,7 @@ static int intel_hdmi_mode_valid(struct drm_connector *connector,
 	if (mode->clock > 165000)
 		return MODE_CLOCK_HIGH;
 	if (mode->clock < 20000)
-		return MODE_CLOCK_HIGH;
+		return MODE_CLOCK_LOW;
 
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
@@ -287,7 +286,7 @@ intel_hdmi_set_property(struct drm_connector *connector,
 	if (ret)
 		return ret;
 
-	if (property == intel_hdmi->force_audio_property) {
+	if (property == dev_priv->force_audio_property) {
 		int i = val;
 		bool has_audio;
 
@@ -365,16 +364,7 @@ static const struct drm_encoder_funcs intel_hdmi_enc_funcs = {
 static void
 intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *connector)
 {
-	struct drm_device *dev = connector->dev;
-
-	intel_hdmi->force_audio_property =
-		drm_property_create(dev, DRM_MODE_PROP_RANGE, "force_audio", 2);
-	if (intel_hdmi->force_audio_property) {
-		intel_hdmi->force_audio_property->values[0] = -1;
-		intel_hdmi->force_audio_property->values[1] = 1;
-		drm_connector_attach_property(connector, intel_hdmi->force_audio_property, 0);
-	}
-
+	intel_attach_force_audio_property(connector);
 	intel_attach_broadcast_rgb_property(connector);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index d3b903bce7c5..d98cee60b602 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -401,8 +401,7 @@ int intel_setup_gmbus(struct drm_device *dev)
 		bus->reg0 = i | GMBUS_RATE_100KHZ;
 
 		/* XXX force bit banging until GMBUS is fully debugged */
-		if (IS_GEN2(dev))
-			bus->force_bit = intel_gpio_create(dev_priv, i);
+		bus->force_bit = intel_gpio_create(dev_priv, i);
 	}
 
 	intel_i2c_reset(dev_priv->dev);
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 67cb076d271b..b28f7bd9f88a 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -727,6 +727,14 @@ static const struct dmi_system_id intel_no_lvds[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "U800"),
 		},
 	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+		.ident = "Asus EeeBox PC EB1007",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "EB1007"),
+		},
+	},
 
 	{ }	/* terminating entry */
 };
diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c
index 9034dd8f33c7..3b26a3ba02dd 100644
--- a/drivers/gpu/drm/i915/intel_modes.c
+++ b/drivers/gpu/drm/i915/intel_modes.c
@@ -81,6 +81,36 @@ int intel_ddc_get_modes(struct drm_connector *connector,
 	return ret;
 }
 
+static const char *force_audio_names[] = {
+	"off",
+	"auto",
+	"on",
+};
+
+void
+intel_attach_force_audio_property(struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_property *prop;
+	int i;
+
+	prop = dev_priv->force_audio_property;
+	if (prop == NULL) {
+		prop = drm_property_create(dev, DRM_MODE_PROP_ENUM,
+					   "audio",
+					   ARRAY_SIZE(force_audio_names));
+		if (prop == NULL)
+			return;
+
+		for (i = 0; i < ARRAY_SIZE(force_audio_names); i++)
+			drm_property_add_enum(prop, i, i-1, force_audio_names[i]);
+
+		dev_priv->force_audio_property = prop;
+	}
+	drm_connector_attach_property(connector, prop, 0);
+}
+
 static const char *broadcast_rgb_names[] = {
 	"Full",
 	"Limited 16:235",
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index a670c006982e..56a8e2aea19c 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -1416,6 +1416,8 @@ void intel_setup_overlay(struct drm_device *dev)
 		goto out_free;
 	overlay->reg_bo = reg_bo;
 
+	mutex_lock(&dev->struct_mutex);
+
 	if (OVERLAY_NEEDS_PHYSICAL(dev)) {
 		ret = i915_gem_attach_phys_object(dev, reg_bo,
 						  I915_GEM_PHYS_OVERLAY_REGS,
@@ -1440,6 +1442,8 @@ void intel_setup_overlay(struct drm_device *dev)
                 }
 	}
 
+	mutex_unlock(&dev->struct_mutex);
+
 	/* init all values */
 	overlay->color_key = 0x0101fe;
 	overlay->brightness = -19;
@@ -1464,6 +1468,7 @@ out_unpin_bo:
 	i915_gem_object_unpin(reg_bo);
 out_free_bo:
 	drm_gem_object_unreference(&reg_bo->base);
+	mutex_unlock(&dev->struct_mutex);
 out_free:
 	kfree(overlay);
 	return;
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 754086f83941..30fe554d8936 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -148,8 +148,6 @@ struct intel_sdvo_connector {
 	int   format_supported_num;
 	struct drm_property *tv_format;
 
-	struct drm_property *force_audio_property;
-
 	/* add the property for the SDVO-TV */
 	struct drm_property *left;
 	struct drm_property *right;
@@ -1712,7 +1710,7 @@ intel_sdvo_set_property(struct drm_connector *connector,
 	if (ret)
 		return ret;
 
-	if (property == intel_sdvo_connector->force_audio_property) {
+	if (property == dev_priv->force_audio_property) {
 		int i = val;
 		bool has_audio;
 
@@ -2037,15 +2035,7 @@ intel_sdvo_add_hdmi_properties(struct intel_sdvo_connector *connector)
 {
 	struct drm_device *dev = connector->base.base.dev;
 
-	connector->force_audio_property =
-		drm_property_create(dev, DRM_MODE_PROP_RANGE, "force_audio", 2);
-	if (connector->force_audio_property) {
-		connector->force_audio_property->values[0] = -1;
-		connector->force_audio_property->values[1] = 1;
-		drm_connector_attach_property(&connector->base.base,
-					      connector->force_audio_property, 0);
-	}
-
+	intel_attach_force_audio_property(&connector->base.base);
 	if (INTEL_INFO(dev)->gen >= 4 && IS_MOBILE(dev))
 		intel_attach_broadcast_rgb_property(&connector->base.base);
 }
diff --git a/drivers/gpu/drm/mga/mga_drv.h b/drivers/gpu/drm/mga/mga_drv.h
index 1084fa4d261b..54558a01969a 100644
--- a/drivers/gpu/drm/mga/mga_drv.h
+++ b/drivers/gpu/drm/mga/mga_drv.h
@@ -195,29 +195,10 @@ extern long mga_compat_ioctl(struct file *filp, unsigned int cmd,
 
 #define mga_flush_write_combine()	DRM_WRITEMEMORYBARRIER()
 
-#if defined(__linux__) && defined(__alpha__)
-#define MGA_BASE(reg)		((unsigned long)(dev_priv->mmio->handle))
-#define MGA_ADDR(reg)		(MGA_BASE(reg) + reg)
-
-#define MGA_DEREF(reg)		(*(volatile u32 *)MGA_ADDR(reg))
-#define MGA_DEREF8(reg)		(*(volatile u8 *)MGA_ADDR(reg))
-
-#define MGA_READ(reg)		(_MGA_READ((u32 *)MGA_ADDR(reg)))
-#define MGA_READ8(reg)		(_MGA_READ((u8 *)MGA_ADDR(reg)))
-#define MGA_WRITE(reg, val)	do { DRM_WRITEMEMORYBARRIER(); MGA_DEREF(reg) = val; } while (0)
-#define MGA_WRITE8(reg, val)	do { DRM_WRITEMEMORYBARRIER(); MGA_DEREF8(reg) = val; } while (0)
-
-static inline u32 _MGA_READ(u32 *addr)
-{
-	DRM_MEMORYBARRIER();
-	return *(volatile u32 *)addr;
-}
-#else
 #define MGA_READ8(reg)		DRM_READ8(dev_priv->mmio, (reg))
 #define MGA_READ(reg)		DRM_READ32(dev_priv->mmio, (reg))
 #define MGA_WRITE8(reg, val)	DRM_WRITE8(dev_priv->mmio, (reg), (val))
 #define MGA_WRITE(reg, val)	DRM_WRITE32(dev_priv->mmio, (reg), (val))
-#endif
 
 #define DWGREG0		0x1c00
 #define DWGREG0_END	0x1dff
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index f0d459bb46e4..525744d593c1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -262,7 +262,6 @@ static bool nouveau_dsm_detect(void)
 		vga_count++;
 
 		retval = nouveau_dsm_pci_probe(pdev);
-		printk("ret val is %d\n", retval);
 		if (retval & NOUVEAU_DSM_HAS_MUX)
 			has_dsm |= 1;
 		if (retval & NOUVEAU_DSM_HAS_OPT)
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 4b9f4493c9f9..7347075ca5b8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -339,11 +339,12 @@ semaphore_acquire(struct nouveau_channel *chan, struct nouveau_semaphore *sema)
 	int ret;
 
 	if (dev_priv->chipset < 0x84) {
-		ret = RING_SPACE(chan, 3);
+		ret = RING_SPACE(chan, 4);
 		if (ret)
 			return ret;
 
-		BEGIN_RING(chan, NvSubSw, NV_SW_SEMAPHORE_OFFSET, 2);
+		BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 3);
+		OUT_RING  (chan, NvSema);
 		OUT_RING  (chan, sema->mem->start);
 		OUT_RING  (chan, 1);
 	} else
@@ -351,10 +352,12 @@ semaphore_acquire(struct nouveau_channel *chan, struct nouveau_semaphore *sema)
 		struct nouveau_vma *vma = &dev_priv->fence.bo->vma;
 		u64 offset = vma->offset + sema->mem->start;
 
-		ret = RING_SPACE(chan, 5);
+		ret = RING_SPACE(chan, 7);
 		if (ret)
 			return ret;
 
+		BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 1);
+		OUT_RING  (chan, chan->vram_handle);
 		BEGIN_RING(chan, NvSubSw, 0x0010, 4);
 		OUT_RING  (chan, upper_32_bits(offset));
 		OUT_RING  (chan, lower_32_bits(offset));
@@ -394,11 +397,12 @@ semaphore_release(struct nouveau_channel *chan, struct nouveau_semaphore *sema)
 	int ret;
 
 	if (dev_priv->chipset < 0x84) {
-		ret = RING_SPACE(chan, 4);
+		ret = RING_SPACE(chan, 5);
 		if (ret)
 			return ret;
 
-		BEGIN_RING(chan, NvSubSw, NV_SW_SEMAPHORE_OFFSET, 1);
+		BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 2);
+		OUT_RING  (chan, NvSema);
 		OUT_RING  (chan, sema->mem->start);
 		BEGIN_RING(chan, NvSubSw, NV_SW_SEMAPHORE_RELEASE, 1);
 		OUT_RING  (chan, 1);
@@ -407,10 +411,12 @@ semaphore_release(struct nouveau_channel *chan, struct nouveau_semaphore *sema)
 		struct nouveau_vma *vma = &dev_priv->fence.bo->vma;
 		u64 offset = vma->offset + sema->mem->start;
 
-		ret = RING_SPACE(chan, 5);
+		ret = RING_SPACE(chan, 7);
 		if (ret)
 			return ret;
 
+		BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 1);
+		OUT_RING  (chan, chan->vram_handle);
 		BEGIN_RING(chan, NvSubSw, 0x0010, 4);
 		OUT_RING  (chan, upper_32_bits(offset));
 		OUT_RING  (chan, lower_32_bits(offset));
@@ -504,22 +510,22 @@ nouveau_fence_channel_init(struct nouveau_channel *chan)
 	struct nouveau_gpuobj *obj = NULL;
 	int ret;
 
-	if (dev_priv->card_type >= NV_C0)
-		goto out_initialised;
+	if (dev_priv->card_type < NV_C0) {
+		/* Create an NV_SW object for various sync purposes */
+		ret = nouveau_gpuobj_gr_new(chan, NvSw, NV_SW);
+		if (ret)
+			return ret;
 
-	/* Create an NV_SW object for various sync purposes */
-	ret = nouveau_gpuobj_gr_new(chan, NvSw, NV_SW);
-	if (ret)
-		return ret;
+		ret = RING_SPACE(chan, 2);
+		if (ret)
+			return ret;
 
-	/* we leave subchannel empty for nvc0 */
-	ret = RING_SPACE(chan, 2);
-	if (ret)
-		return ret;
-	BEGIN_RING(chan, NvSubSw, 0, 1);
-	OUT_RING(chan, NvSw);
+		BEGIN_RING(chan, NvSubSw, 0, 1);
+		OUT_RING  (chan, NvSw);
+		FIRE_RING (chan);
+	}
 
-	/* Create a DMA object for the shared cross-channel sync area. */
+	/* Setup area of memory shared between all channels for x-chan sync */
 	if (USE_SEMA(dev) && dev_priv->chipset < 0x84) {
 		struct ttm_mem_reg *mem = &dev_priv->fence.bo->bo.mem;
 
@@ -534,23 +540,8 @@ nouveau_fence_channel_init(struct nouveau_channel *chan)
 		nouveau_gpuobj_ref(NULL, &obj);
 		if (ret)
 			return ret;
-
-		ret = RING_SPACE(chan, 2);
-		if (ret)
-			return ret;
-		BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 1);
-		OUT_RING(chan, NvSema);
-	} else {
-		ret = RING_SPACE(chan, 2);
-		if (ret)
-			return ret;
-		BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 1);
-		OUT_RING  (chan, chan->vram_handle); /* whole VM */
 	}
 
-	FIRE_RING(chan);
-
-out_initialised:
 	INIT_LIST_HEAD(&chan->fence.pending);
 	spin_lock_init(&chan->fence.lock);
 	atomic_set(&chan->fence.last_sequence_irq, 0);
diff --git a/drivers/gpu/drm/nouveau/nouveau_hw.c b/drivers/gpu/drm/nouveau/nouveau_hw.c
index 053edf9d2f67..ba896e54b799 100644
--- a/drivers/gpu/drm/nouveau/nouveau_hw.c
+++ b/drivers/gpu/drm/nouveau/nouveau_hw.c
@@ -900,6 +900,7 @@ nv_save_state_ext(struct drm_device *dev, int head,
 	}
 	/* NV11 and NV20 don't have this, they stop at 0x52. */
 	if (nv_gf4_disp_arch(dev)) {
+		rd_cio_state(dev, head, regp, NV_CIO_CRE_42);
 		rd_cio_state(dev, head, regp, NV_CIO_CRE_53);
 		rd_cio_state(dev, head, regp, NV_CIO_CRE_54);
 
@@ -1003,6 +1004,7 @@ nv_load_state_ext(struct drm_device *dev, int head,
 			nouveau_wait_eq(dev, 650000000, NV_PRMCIO_INP0__COLOR, 0x8, 0x0);
 		}
 
+		wr_cio_state(dev, head, regp, NV_CIO_CRE_42);
 		wr_cio_state(dev, head, regp, NV_CIO_CRE_53);
 		wr_cio_state(dev, head, regp, NV_CIO_CRE_54);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c
index 2960f583dc38..5ee14d216ce8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_mem.c
@@ -397,7 +397,7 @@ nouveau_mem_vram_init(struct drm_device *dev)
 		if (pci_dma_supported(dev->pdev, DMA_BIT_MASK(40)))
 			dma_bits = 40;
 	} else
-	if (drm_pci_device_is_pcie(dev) &&
+	if (0 && drm_pci_device_is_pcie(dev) &&
 	    dev_priv->chipset  > 0x40 &&
 	    dev_priv->chipset != 0x45) {
 		if (pci_dma_supported(dev->pdev, DMA_BIT_MASK(39)))
@@ -868,7 +868,9 @@ nouveau_gart_manager_del(struct ttm_mem_type_manager *man,
 		nouveau_vm_unmap(&node->tmp_vma);
 		nouveau_vm_put(&node->tmp_vma);
 	}
+
 	mem->mm_node = NULL;
+	kfree(node);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_perf.c b/drivers/gpu/drm/nouveau/nouveau_perf.c
index 922fb6b664ed..ef9dec0e6f8b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_perf.c
+++ b/drivers/gpu/drm/nouveau/nouveau_perf.c
@@ -182,6 +182,11 @@ nouveau_perf_init(struct drm_device *dev)
 		entries   = perf[2];
 	}
 
+	if (entries > NOUVEAU_PM_MAX_LEVEL) {
+		NV_DEBUG(dev, "perf table has too many entries - buggy vbios?\n");
+		entries = NOUVEAU_PM_MAX_LEVEL;
+	}
+
 	entry = perf + headerlen;
 	for (i = 0; i < entries; i++) {
 		struct nouveau_pm_level *perflvl = &pm->perflvl[pm->nr_perflvl];
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index c77111eca6ac..82fad914e648 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -458,7 +458,7 @@ nouveau_sgdma_init(struct drm_device *dev)
 		dev_priv->gart_info.type = NOUVEAU_GART_HW;
 		dev_priv->gart_info.func = &nv50_sgdma_backend;
 	} else
-	if (drm_pci_device_is_pcie(dev) &&
+	if (0 && drm_pci_device_is_pcie(dev) &&
 	    dev_priv->chipset > 0x40 && dev_priv->chipset != 0x45) {
 		if (nv44_graph_class(dev)) {
 			dev_priv->gart_info.func = &nv44_sgdma_backend;
diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c
index 38ea662568c1..144f79a350ae 100644
--- a/drivers/gpu/drm/nouveau/nouveau_state.c
+++ b/drivers/gpu/drm/nouveau/nouveau_state.c
@@ -371,6 +371,7 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev)
 		engine->vram.flags_valid	= nv50_vram_flags_valid;
 		break;
 	case 0xC0:
+	case 0xD0:
 		engine->instmem.init		= nvc0_instmem_init;
 		engine->instmem.takedown	= nvc0_instmem_takedown;
 		engine->instmem.suspend		= nvc0_instmem_suspend;
@@ -563,68 +564,68 @@ nouveau_card_init(struct drm_device *dev)
 	if (ret)
 		goto out_timer;
 
-	switch (dev_priv->card_type) {
-	case NV_04:
-		nv04_graph_create(dev);
-		break;
-	case NV_10:
-		nv10_graph_create(dev);
-		break;
-	case NV_20:
-	case NV_30:
-		nv20_graph_create(dev);
-		break;
-	case NV_40:
-		nv40_graph_create(dev);
-		break;
-	case NV_50:
-		nv50_graph_create(dev);
-		break;
-	case NV_C0:
-		nvc0_graph_create(dev);
-		break;
-	default:
-		break;
-	}
-
-	switch (dev_priv->chipset) {
-	case 0x84:
-	case 0x86:
-	case 0x92:
-	case 0x94:
-	case 0x96:
-	case 0xa0:
-		nv84_crypt_create(dev);
-		break;
-	}
+	if (!nouveau_noaccel) {
+		switch (dev_priv->card_type) {
+		case NV_04:
+			nv04_graph_create(dev);
+			break;
+		case NV_10:
+			nv10_graph_create(dev);
+			break;
+		case NV_20:
+		case NV_30:
+			nv20_graph_create(dev);
+			break;
+		case NV_40:
+			nv40_graph_create(dev);
+			break;
+		case NV_50:
+			nv50_graph_create(dev);
+			break;
+		case NV_C0:
+			nvc0_graph_create(dev);
+			break;
+		default:
+			break;
+		}
 
-	switch (dev_priv->card_type) {
-	case NV_50:
 		switch (dev_priv->chipset) {
-		case 0xa3:
-		case 0xa5:
-		case 0xa8:
-		case 0xaf:
-			nva3_copy_create(dev);
+		case 0x84:
+		case 0x86:
+		case 0x92:
+		case 0x94:
+		case 0x96:
+		case 0xa0:
+			nv84_crypt_create(dev);
 			break;
 		}
-		break;
-	case NV_C0:
-		nvc0_copy_create(dev, 0);
-		nvc0_copy_create(dev, 1);
-		break;
-	default:
-		break;
-	}
 
-	if (dev_priv->card_type == NV_40)
-		nv40_mpeg_create(dev);
-	else
-	if (dev_priv->card_type == NV_50 &&
-	    (dev_priv->chipset < 0x98 || dev_priv->chipset == 0xa0))
-		nv50_mpeg_create(dev);
+		switch (dev_priv->card_type) {
+		case NV_50:
+			switch (dev_priv->chipset) {
+			case 0xa3:
+			case 0xa5:
+			case 0xa8:
+			case 0xaf:
+				nva3_copy_create(dev);
+				break;
+			}
+			break;
+		case NV_C0:
+			nvc0_copy_create(dev, 0);
+			nvc0_copy_create(dev, 1);
+			break;
+		default:
+			break;
+		}
+
+		if (dev_priv->card_type == NV_40)
+			nv40_mpeg_create(dev);
+		else
+		if (dev_priv->card_type == NV_50 &&
+		    (dev_priv->chipset < 0x98 || dev_priv->chipset == 0xa0))
+			nv50_mpeg_create(dev);
 
-	if (!nouveau_noaccel) {
 		for (e = 0; e < NVOBJ_ENGINE_NR; e++) {
 			if (dev_priv->eng[e]) {
 				ret = dev_priv->eng[e]->init(dev, e);
@@ -880,8 +881,8 @@ int nouveau_load(struct drm_device *dev, unsigned long flags)
 
 #ifdef __BIG_ENDIAN
 	/* Put the card in BE mode if it's not */
-	if (nv_rd32(dev, NV03_PMC_BOOT_1))
-		nv_wr32(dev, NV03_PMC_BOOT_1, 0x00000001);
+	if (nv_rd32(dev, NV03_PMC_BOOT_1) != 0x01000001)
+		nv_wr32(dev, NV03_PMC_BOOT_1, 0x01000001);
 
 	DRM_MEMORYBARRIER();
 #endif
@@ -922,6 +923,7 @@ int nouveau_load(struct drm_device *dev, unsigned long flags)
 		dev_priv->card_type = NV_50;
 		break;
 	case 0xc0:
+	case 0xd0:
 		dev_priv->card_type = NV_C0;
 		break;
 	default:
diff --git a/drivers/gpu/drm/nouveau/nouveau_vm.c b/drivers/gpu/drm/nouveau/nouveau_vm.c
index 0059e6f58a8b..519a6b4bba46 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vm.c
@@ -58,6 +58,7 @@ nouveau_vm_map_at(struct nouveau_vma *vma, u64 delta, struct nouveau_mem *node)
 			num -= len;
 			pte += len;
 			if (unlikely(end >= max)) {
+				phys += len << (bits + 12);
 				pde++;
 				pte = 0;
 			}
diff --git a/drivers/gpu/drm/nouveau/nv04_crtc.c b/drivers/gpu/drm/nouveau/nv04_crtc.c
index 3c78bc81357e..f1a3ae491995 100644
--- a/drivers/gpu/drm/nouveau/nv04_crtc.c
+++ b/drivers/gpu/drm/nouveau/nv04_crtc.c
@@ -376,7 +376,10 @@ nv_crtc_mode_set_vga(struct drm_crtc *crtc, struct drm_display_mode *mode)
 	 */
 
 	/* framebuffer can be larger than crtc scanout area. */
-	regp->CRTC[NV_CIO_CRE_RPC0_INDEX] = XLATE(fb->pitch / 8, 8, NV_CIO_CRE_RPC0_OFFSET_10_8);
+	regp->CRTC[NV_CIO_CRE_RPC0_INDEX] =
+		XLATE(fb->pitch / 8, 8, NV_CIO_CRE_RPC0_OFFSET_10_8);
+	regp->CRTC[NV_CIO_CRE_42] =
+		XLATE(fb->pitch / 8, 11, NV_CIO_CRE_42_OFFSET_11);
 	regp->CRTC[NV_CIO_CRE_RPC1_INDEX] = mode->crtc_hdisplay < 1280 ?
 					    MASK(NV_CIO_CRE_RPC1_LARGE) : 0x00;
 	regp->CRTC[NV_CIO_CRE_LSR_INDEX] = XLATE(horizBlankEnd, 6, NV_CIO_CRE_LSR_HBE_6) |
@@ -824,8 +827,11 @@ nv04_crtc_do_mode_set_base(struct drm_crtc *crtc,
 	regp->CRTC[NV_CIO_CR_OFFSET_INDEX] = drm_fb->pitch >> 3;
 	regp->CRTC[NV_CIO_CRE_RPC0_INDEX] =
 		XLATE(drm_fb->pitch >> 3, 8, NV_CIO_CRE_RPC0_OFFSET_10_8);
+	regp->CRTC[NV_CIO_CRE_42] =
+		XLATE(drm_fb->pitch / 8, 11, NV_CIO_CRE_42_OFFSET_11);
 	crtc_wr_cio_state(crtc, regp, NV_CIO_CRE_RPC0_INDEX);
 	crtc_wr_cio_state(crtc, regp, NV_CIO_CR_OFFSET_INDEX);
+	crtc_wr_cio_state(crtc, regp, NV_CIO_CRE_42);
 
 	/* Update the framebuffer location. */
 	regp->fb_start = nv_crtc->fb.offset & ~3;
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 74a3f6872701..08da478ba544 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -409,7 +409,7 @@ nv50_display_flip_next(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	struct nouveau_channel *evo = dispc->sync;
 	int ret;
 
-	ret = RING_SPACE(evo, 24);
+	ret = RING_SPACE(evo, chan ? 25 : 27);
 	if (unlikely(ret))
 		return ret;
 
@@ -458,8 +458,19 @@ nv50_display_flip_next(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	/* queue the flip on the crtc's "display sync" channel */
 	BEGIN_RING(evo, 0, 0x0100, 1);
 	OUT_RING  (evo, 0xfffe0000);
-	BEGIN_RING(evo, 0, 0x0084, 5);
-	OUT_RING  (evo, chan ? 0x00000100 : 0x00000010);
+	if (chan) {
+		BEGIN_RING(evo, 0, 0x0084, 1);
+		OUT_RING  (evo, 0x00000100);
+	} else {
+		BEGIN_RING(evo, 0, 0x0084, 1);
+		OUT_RING  (evo, 0x00000010);
+		/* allows gamma somehow, PDISP will bitch at you if
+		 * you don't wait for vblank before changing this..
+		 */
+		BEGIN_RING(evo, 0, 0x00e0, 1);
+		OUT_RING  (evo, 0x40000000);
+	}
+	BEGIN_RING(evo, 0, 0x0088, 4);
 	OUT_RING  (evo, dispc->sem.offset);
 	OUT_RING  (evo, 0xf00d0000 | dispc->sem.value);
 	OUT_RING  (evo, 0x74b1e000);
diff --git a/drivers/gpu/drm/nouveau/nvreg.h b/drivers/gpu/drm/nouveau/nvreg.h
index fe0f253089ac..bbfb1a68fb11 100644
--- a/drivers/gpu/drm/nouveau/nvreg.h
+++ b/drivers/gpu/drm/nouveau/nvreg.h
@@ -277,6 +277,8 @@
 #		define NV_CIO_CRE_EBR_VDE_11		2:2
 #		define NV_CIO_CRE_EBR_VRS_11		4:4
 #		define NV_CIO_CRE_EBR_VBS_11		6:6
+#	define NV_CIO_CRE_42			0x42
+#		define NV_CIO_CRE_42_OFFSET_11		6:6
 #	define NV_CIO_CRE_43			0x43
 #	define NV_CIO_CRE_44			0x44	/* head control */
 #	define NV_CIO_CRE_CSB			0x45	/* colour saturation boost */
diff --git a/drivers/gpu/drm/radeon/Kconfig b/drivers/gpu/drm/radeon/Kconfig
index 9746fee59f56..ea92bbe3ed37 100644
--- a/drivers/gpu/drm/radeon/Kconfig
+++ b/drivers/gpu/drm/radeon/Kconfig
@@ -28,11 +28,4 @@ config DRM_RADEON_KMS
 	  The kernel will also perform security check on command stream
 	  provided by the user, we want to catch and forbid any illegal use
 	  of the GPU such as DMA into random system memory or into memory
-	  not owned by the process supplying the command stream. This part
-	  of the code is still incomplete and this why we propose that patch
-	  as a staging driver addition, future security might forbid current
-	  experimental userspace to run.
-
-	  This code support the following hardware : R1XX,R2XX,R3XX,R4XX,R5XX
-	  (radeon up to X1950). Works is underway to provide support for R6XX,
-	  R7XX and newer hardware (radeon from HD2XXX to HD4XXX).
+	  not owned by the process supplying the command stream.
diff --git a/drivers/gpu/drm/radeon/atombios.h b/drivers/gpu/drm/radeon/atombios.h
index 49611e2365d9..1b50ad8919d5 100644
--- a/drivers/gpu/drm/radeon/atombios.h
+++ b/drivers/gpu/drm/radeon/atombios.h
@@ -1200,6 +1200,7 @@ typedef struct _EXTERNAL_ENCODER_CONTROL_PARAMETERS_V3
 #define EXTERNAL_ENCODER_ACTION_V3_ENCODER_BLANKING_OFF   0x10
 #define EXTERNAL_ENCODER_ACTION_V3_ENCODER_BLANKING       0x11
 #define EXTERNAL_ENCODER_ACTION_V3_DACLOAD_DETECTION      0x12
+#define EXTERNAL_ENCODER_ACTION_V3_DDC_SETUP              0x14
 
 // ucConfig
 #define EXTERNAL_ENCODER_CONFIG_V3_DPLINKRATE_MASK				0x03
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index ec848787d7d9..9541995e4b21 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -671,6 +671,13 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 								DISPPLL_CONFIG_DUAL_LINK;
 					}
 				}
+				if (radeon_encoder_is_dp_bridge(encoder)) {
+					struct drm_encoder *ext_encoder = radeon_atom_get_external_encoder(encoder);
+					struct radeon_encoder *ext_radeon_encoder = to_radeon_encoder(ext_encoder);
+					args.v3.sInput.ucExtTransmitterID = ext_radeon_encoder->encoder_id;
+				} else
+					args.v3.sInput.ucExtTransmitterID = 0;
+
 				atom_execute_table(rdev->mode_info.atom_context,
 						   index, (uint32_t *)&args);
 				adjusted_clock = le32_to_cpu(args.v3.sOutput.ulDispPllFreq) * 10;
@@ -1045,7 +1052,7 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	uint64_t fb_location;
 	uint32_t fb_format, fb_pitch_pixels, tiling_flags;
 	u32 fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_NONE);
-	u32 tmp;
+	u32 tmp, viewport_w, viewport_h;
 	int r;
 
 	/* no fb bound */
@@ -1171,8 +1178,10 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	y &= ~1;
 	WREG32(EVERGREEN_VIEWPORT_START + radeon_crtc->crtc_offset,
 	       (x << 16) | y);
+	viewport_w = crtc->mode.hdisplay;
+	viewport_h = (crtc->mode.vdisplay + 1) & ~1;
 	WREG32(EVERGREEN_VIEWPORT_SIZE + radeon_crtc->crtc_offset,
-	       (crtc->mode.hdisplay << 16) | crtc->mode.vdisplay);
+	       (viewport_w << 16) | viewport_h);
 
 	/* pageflip setup */
 	/* make sure flip is at vb rather than hb */
@@ -1213,7 +1222,7 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 	uint64_t fb_location;
 	uint32_t fb_format, fb_pitch_pixels, tiling_flags;
 	u32 fb_swap = R600_D1GRPH_SWAP_ENDIAN_NONE;
-	u32 tmp;
+	u32 tmp, viewport_w, viewport_h;
 	int r;
 
 	/* no fb bound */
@@ -1338,8 +1347,10 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 	y &= ~1;
 	WREG32(AVIVO_D1MODE_VIEWPORT_START + radeon_crtc->crtc_offset,
 	       (x << 16) | y);
+	viewport_w = crtc->mode.hdisplay;
+	viewport_h = (crtc->mode.vdisplay + 1) & ~1;
 	WREG32(AVIVO_D1MODE_VIEWPORT_SIZE + radeon_crtc->crtc_offset,
-	       (crtc->mode.hdisplay << 16) | crtc->mode.vdisplay);
+	       (viewport_w << 16) | viewport_h);
 
 	/* pageflip setup */
 	/* make sure flip is at vb rather than hb */
diff --git a/drivers/gpu/drm/radeon/cayman_blit_shaders.c b/drivers/gpu/drm/radeon/cayman_blit_shaders.c
index e148ab04b80b..7b4eeb7b4a8c 100644
--- a/drivers/gpu/drm/radeon/cayman_blit_shaders.c
+++ b/drivers/gpu/drm/radeon/cayman_blit_shaders.c
@@ -39,17 +39,335 @@
 
 const u32 cayman_default_state[] =
 {
-	/* XXX fill in additional blit state */
+	0xc0066900,
+	0x00000000,
+	0x00000060, /* DB_RENDER_CONTROL */
+	0x00000000, /* DB_COUNT_CONTROL */
+	0x00000000, /* DB_DEPTH_VIEW */
+	0x0000002a, /* DB_RENDER_OVERRIDE */
+	0x00000000, /* DB_RENDER_OVERRIDE2 */
+	0x00000000, /* DB_HTILE_DATA_BASE */
 
 	0xc0026900,
-	0x00000316,
-	0x0000000e, /* VGT_VERTEX_REUSE_BLOCK_CNTL */
-	0x00000010, /*  */
+	0x0000000a,
+	0x00000000, /* DB_STENCIL_CLEAR */
+	0x00000000, /* DB_DEPTH_CLEAR */
+
+	0xc0036900,
+	0x0000000f,
+	0x00000000, /* DB_DEPTH_INFO */
+	0x00000000, /* DB_Z_INFO */
+	0x00000000, /* DB_STENCIL_INFO */
+
+	0xc0016900,
+	0x00000080,
+	0x00000000, /* PA_SC_WINDOW_OFFSET */
+
+	0xc00d6900,
+	0x00000083,
+	0x0000ffff, /* PA_SC_CLIPRECT_RULE */
+	0x00000000, /* PA_SC_CLIPRECT_0_TL */
+	0x20002000, /* PA_SC_CLIPRECT_0_BR */
+	0x00000000,
+	0x20002000,
+	0x00000000,
+	0x20002000,
+	0x00000000,
+	0x20002000,
+	0xaaaaaaaa, /* PA_SC_EDGERULE */
+	0x00000000, /* PA_SU_HARDWARE_SCREEN_OFFSET */
+	0x0000000f, /* CB_TARGET_MASK */
+	0x0000000f, /* CB_SHADER_MASK */
+
+	0xc0226900,
+	0x00000094,
+	0x80000000, /* PA_SC_VPORT_SCISSOR_0_TL */
+	0x20002000, /* PA_SC_VPORT_SCISSOR_0_BR */
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x00000000, /* PA_SC_VPORT_ZMIN_0 */
+	0x3f800000, /* PA_SC_VPORT_ZMAX_0 */
+
+	0xc0016900,
+	0x000000d4,
+	0x00000000, /* SX_MISC */
 
 	0xc0026900,
 	0x000000d9,
 	0x00000000, /* CP_RINGID */
 	0x00000000, /* CP_VMID */
+
+	0xc0096900,
+	0x00000100,
+	0x00ffffff, /* VGT_MAX_VTX_INDX */
+	0x00000000, /* VGT_MIN_VTX_INDX */
+	0x00000000, /* VGT_INDX_OFFSET */
+	0x00000000, /* VGT_MULTI_PRIM_IB_RESET_INDX */
+	0x00000000, /* SX_ALPHA_TEST_CONTROL */
+	0x00000000, /* CB_BLEND_RED */
+	0x00000000, /* CB_BLEND_GREEN */
+	0x00000000, /* CB_BLEND_BLUE */
+	0x00000000, /* CB_BLEND_ALPHA */
+
+	0xc0016900,
+	0x00000187,
+	0x00000100, /* SPI_VS_OUT_ID_0 */
+
+	0xc0026900,
+	0x00000191,
+	0x00000100, /* SPI_PS_INPUT_CNTL_0 */
+	0x00000101, /* SPI_PS_INPUT_CNTL_1 */
+
+	0xc0016900,
+	0x000001b1,
+	0x00000000, /* SPI_VS_OUT_CONFIG */
+
+	0xc0106900,
+	0x000001b3,
+	0x20000001, /* SPI_PS_IN_CONTROL_0 */
+	0x00000000, /* SPI_PS_IN_CONTROL_1 */
+	0x00000000, /* SPI_INTERP_CONTROL_0 */
+	0x00000000, /* SPI_INPUT_Z */
+	0x00000000, /* SPI_FOG_CNTL */
+	0x00100000, /* SPI_BARYC_CNTL */
+	0x00000000, /* SPI_PS_IN_CONTROL_2 */
+	0x00000000, /* SPI_COMPUTE_INPUT_CNTL */
+	0x00000000, /* SPI_COMPUTE_NUM_THREAD_X */
+	0x00000000, /* SPI_COMPUTE_NUM_THREAD_Y */
+	0x00000000, /* SPI_COMPUTE_NUM_THREAD_Z */
+	0x00000000, /* SPI_GPR_MGMT */
+	0x00000000, /* SPI_LDS_MGMT */
+	0x00000000, /* SPI_STACK_MGMT */
+	0x00000000, /* SPI_WAVE_MGMT_1 */
+	0x00000000, /* SPI_WAVE_MGMT_2 */
+
+	0xc0016900,
+	0x000001e0,
+	0x00000000, /* CB_BLEND0_CONTROL */
+
+	0xc00e6900,
+	0x00000200,
+	0x00000000, /* DB_DEPTH_CONTROL */
+	0x00000000, /* DB_EQAA */
+	0x00cc0010, /* CB_COLOR_CONTROL */
+	0x00000210, /* DB_SHADER_CONTROL */
+	0x00010000, /* PA_CL_CLIP_CNTL */
+	0x00000004, /* PA_SU_SC_MODE_CNTL */
+	0x00000100, /* PA_CL_VTE_CNTL */
+	0x00000000, /* PA_CL_VS_OUT_CNTL */
+	0x00000000, /* PA_CL_NANINF_CNTL */
+	0x00000000, /* PA_SU_LINE_STIPPLE_CNTL */
+	0x00000000, /* PA_SU_LINE_STIPPLE_SCALE */
+	0x00000000, /* PA_SU_PRIM_FILTER_CNTL */
+	0x00000000, /*  */
+	0x00000000, /*  */
+
+	0xc0026900,
+	0x00000229,
+	0x00000000, /* SQ_PGM_START_FS */
+	0x00000000,
+
+	0xc0016900,
+	0x0000023b,
+	0x00000000, /* SQ_LDS_ALLOC_PS */
+
+	0xc0066900,
+	0x00000240,
+	0x00000000, /* SQ_ESGS_RING_ITEMSIZE */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+
+	0xc0046900,
+	0x00000247,
+	0x00000000, /* SQ_GS_VERT_ITEMSIZE */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+
+	0xc0116900,
+	0x00000280,
+	0x00000000, /* PA_SU_POINT_SIZE */
+	0x00000000, /* PA_SU_POINT_MINMAX */
+	0x00000008, /* PA_SU_LINE_CNTL */
+	0x00000000, /* PA_SC_LINE_STIPPLE */
+	0x00000000, /* VGT_OUTPUT_PATH_CNTL */
+	0x00000000, /* VGT_HOS_CNTL */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000, /* VGT_GS_MODE */
+
+	0xc0026900,
+	0x00000292,
+	0x00000000, /* PA_SC_MODE_CNTL_0 */
+	0x00000000, /* PA_SC_MODE_CNTL_1 */
+
+	0xc0016900,
+	0x000002a1,
+	0x00000000, /* VGT_PRIMITIVEID_EN */
+
+	0xc0016900,
+	0x000002a5,
+	0x00000000, /* VGT_MULTI_PRIM_IB_RESET_EN */
+
+	0xc0026900,
+	0x000002a8,
+	0x00000000, /* VGT_INSTANCE_STEP_RATE_0 */
+	0x00000000,
+
+	0xc0026900,
+	0x000002ad,
+	0x00000000, /* VGT_REUSE_OFF */
+	0x00000000,
+
+	0xc0016900,
+	0x000002d5,
+	0x00000000, /* VGT_SHADER_STAGES_EN */
+
+	0xc0016900,
+	0x000002dc,
+	0x0000aa00, /* DB_ALPHA_TO_MASK */
+
+	0xc0066900,
+	0x000002de,
+	0x00000000, /* PA_SU_POLY_OFFSET_DB_FMT_CNTL */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+
+	0xc0026900,
+	0x000002e5,
+	0x00000000, /* VGT_STRMOUT_CONFIG */
+	0x00000000,
+
+	0xc01b6900,
+	0x000002f5,
+	0x76543210, /* PA_SC_CENTROID_PRIORITY_0 */
+	0xfedcba98, /* PA_SC_CENTROID_PRIORITY_1 */
+	0x00000000, /* PA_SC_LINE_CNTL */
+	0x00000000, /* PA_SC_AA_CONFIG */
+	0x00000005, /* PA_SU_VTX_CNTL */
+	0x3f800000, /* PA_CL_GB_VERT_CLIP_ADJ */
+	0x3f800000, /* PA_CL_GB_VERT_DISC_ADJ */
+	0x3f800000, /* PA_CL_GB_HORZ_CLIP_ADJ */
+	0x3f800000, /* PA_CL_GB_HORZ_DISC_ADJ */
+	0x00000000, /* PA_SC_AA_SAMPLE_LOCS_PIXEL_X0Y0_0 */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0xffffffff, /* PA_SC_AA_MASK_X0Y0_X1Y0 */
+	0xffffffff,
+
+	0xc0026900,
+	0x00000316,
+	0x0000000e, /* VGT_VERTEX_REUSE_BLOCK_CNTL */
+	0x00000010, /*  */
+};
+
+const u32 cayman_vs[] =
+{
+	0x00000004,
+	0x80400400,
+	0x0000a03c,
+	0x95000688,
+	0x00004000,
+	0x15000688,
+	0x00000000,
+	0x88000000,
+	0x04000000,
+	0x67961001,
+#ifdef __BIG_ENDIAN
+	0x00020000,
+#else
+	0x00000000,
+#endif
+	0x00000000,
+	0x04000000,
+	0x67961000,
+#ifdef __BIG_ENDIAN
+	0x00020008,
+#else
+	0x00000008,
+#endif
+	0x00000000,
+};
+
+const u32 cayman_ps[] =
+{
+	0x00000004,
+	0xa00c0000,
+	0x00000008,
+	0x80400000,
+	0x00000000,
+	0x95000688,
+	0x00000000,
+	0x88000000,
+	0x00380400,
+	0x00146b10,
+	0x00380000,
+	0x20146b10,
+	0x00380400,
+	0x40146b00,
+	0x80380000,
+	0x60146b00,
+	0x00000010,
+	0x000d1000,
+	0xb0800000,
+	0x00000000,
 };
 
+const u32 cayman_ps_size = ARRAY_SIZE(cayman_ps);
+const u32 cayman_vs_size = ARRAY_SIZE(cayman_vs);
 const u32 cayman_default_size = ARRAY_SIZE(cayman_default_state);
diff --git a/drivers/gpu/drm/radeon/cayman_blit_shaders.h b/drivers/gpu/drm/radeon/cayman_blit_shaders.h
index 33b75e5d0fa4..f5d0e9a60267 100644
--- a/drivers/gpu/drm/radeon/cayman_blit_shaders.h
+++ b/drivers/gpu/drm/radeon/cayman_blit_shaders.h
@@ -25,8 +25,11 @@
 #ifndef CAYMAN_BLIT_SHADERS_H
 #define CAYMAN_BLIT_SHADERS_H
 
+extern const u32 cayman_ps[];
+extern const u32 cayman_vs[];
 extern const u32 cayman_default_state[];
 
+extern const u32 cayman_ps_size, cayman_vs_size;
 extern const u32 cayman_default_size;
 
 #endif
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 7c37638095f7..12d2fdc52414 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -88,21 +88,40 @@ u32 evergreen_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 /* get temperature in millidegrees */
 int evergreen_get_temp(struct radeon_device *rdev)
 {
-	u32 temp = (RREG32(CG_MULT_THERMAL_STATUS) & ASIC_T_MASK) >>
-		ASIC_T_SHIFT;
-	u32 actual_temp = 0;
-
-	if (temp & 0x400)
-		actual_temp = -256;
-	else if (temp & 0x200)
-		actual_temp = 255;
-	else if (temp & 0x100) {
-		actual_temp = temp & 0x1ff;
-		actual_temp |= ~0x1ff;
-	} else
-		actual_temp = temp & 0xff;
+	u32 temp, toffset;
+	int actual_temp = 0;
+
+	if (rdev->family == CHIP_JUNIPER) {
+		toffset = (RREG32(CG_THERMAL_CTRL) & TOFFSET_MASK) >>
+			TOFFSET_SHIFT;
+		temp = (RREG32(CG_TS0_STATUS) & TS0_ADC_DOUT_MASK) >>
+			TS0_ADC_DOUT_SHIFT;
+
+		if (toffset & 0x100)
+			actual_temp = temp / 2 - (0x200 - toffset);
+		else
+			actual_temp = temp / 2 + toffset;
+
+		actual_temp = actual_temp * 1000;
+
+	} else {
+		temp = (RREG32(CG_MULT_THERMAL_STATUS) & ASIC_T_MASK) >>
+			ASIC_T_SHIFT;
+
+		if (temp & 0x400)
+			actual_temp = -256;
+		else if (temp & 0x200)
+			actual_temp = 255;
+		else if (temp & 0x100) {
+			actual_temp = temp & 0x1ff;
+			actual_temp |= ~0x1ff;
+		} else
+			actual_temp = temp & 0xff;
 
-	return (actual_temp * 1000) / 2;
+		actual_temp = (actual_temp * 1000) / 2;
+	}
+
+	return actual_temp;
 }
 
 int sumo_get_temp(struct radeon_device *rdev)
@@ -121,11 +140,17 @@ void evergreen_pm_misc(struct radeon_device *rdev)
 	struct radeon_voltage *voltage = &ps->clock_info[req_cm_idx].voltage;
 
 	if (voltage->type == VOLTAGE_SW) {
+		/* 0xff01 is a flag rather then an actual voltage */
+		if (voltage->voltage == 0xff01)
+			return;
 		if (voltage->voltage && (voltage->voltage != rdev->pm.current_vddc)) {
 			radeon_atom_set_voltage(rdev, voltage->voltage, SET_VOLTAGE_TYPE_ASIC_VDDC);
 			rdev->pm.current_vddc = voltage->voltage;
 			DRM_DEBUG("Setting: vddc: %d\n", voltage->voltage);
 		}
+		/* 0xff01 is a flag rather then an actual voltage */
+		if (voltage->vddci == 0xff01)
+			return;
 		if (voltage->vddci && (voltage->vddci != rdev->pm.current_vddci)) {
 			radeon_atom_set_voltage(rdev, voltage->vddci, SET_VOLTAGE_TYPE_ASIC_VDDCI);
 			rdev->pm.current_vddci = voltage->vddci;
@@ -1415,6 +1440,8 @@ static u32 evergreen_get_tile_pipe_to_backend_map(struct radeon_device *rdev,
 	case CHIP_CEDAR:
 	case CHIP_REDWOOD:
 	case CHIP_PALM:
+	case CHIP_SUMO:
+	case CHIP_SUMO2:
 	case CHIP_TURKS:
 	case CHIP_CAICOS:
 		force_no_swizzle = false;
@@ -1544,6 +1571,8 @@ static void evergreen_program_channel_remap(struct radeon_device *rdev)
 	case CHIP_REDWOOD:
 	case CHIP_CEDAR:
 	case CHIP_PALM:
+	case CHIP_SUMO:
+	case CHIP_SUMO2:
 	case CHIP_TURKS:
 	case CHIP_CAICOS:
 	default:
@@ -1689,6 +1718,54 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 		rdev->config.evergreen.sc_hiz_tile_fifo_size = 0x30;
 		rdev->config.evergreen.sc_earlyz_tile_fifo_size = 0x130;
 		break;
+	case CHIP_SUMO:
+		rdev->config.evergreen.num_ses = 1;
+		rdev->config.evergreen.max_pipes = 4;
+		rdev->config.evergreen.max_tile_pipes = 2;
+		if (rdev->pdev->device == 0x9648)
+			rdev->config.evergreen.max_simds = 3;
+		else if ((rdev->pdev->device == 0x9647) ||
+			 (rdev->pdev->device == 0x964a))
+			rdev->config.evergreen.max_simds = 4;
+		else
+			rdev->config.evergreen.max_simds = 5;
+		rdev->config.evergreen.max_backends = 2 * rdev->config.evergreen.num_ses;
+		rdev->config.evergreen.max_gprs = 256;
+		rdev->config.evergreen.max_threads = 248;
+		rdev->config.evergreen.max_gs_threads = 32;
+		rdev->config.evergreen.max_stack_entries = 256;
+		rdev->config.evergreen.sx_num_of_sets = 4;
+		rdev->config.evergreen.sx_max_export_size = 256;
+		rdev->config.evergreen.sx_max_export_pos_size = 64;
+		rdev->config.evergreen.sx_max_export_smx_size = 192;
+		rdev->config.evergreen.max_hw_contexts = 8;
+		rdev->config.evergreen.sq_num_cf_insts = 2;
+
+		rdev->config.evergreen.sc_prim_fifo_size = 0x40;
+		rdev->config.evergreen.sc_hiz_tile_fifo_size = 0x30;
+		rdev->config.evergreen.sc_earlyz_tile_fifo_size = 0x130;
+		break;
+	case CHIP_SUMO2:
+		rdev->config.evergreen.num_ses = 1;
+		rdev->config.evergreen.max_pipes = 4;
+		rdev->config.evergreen.max_tile_pipes = 4;
+		rdev->config.evergreen.max_simds = 2;
+		rdev->config.evergreen.max_backends = 1 * rdev->config.evergreen.num_ses;
+		rdev->config.evergreen.max_gprs = 256;
+		rdev->config.evergreen.max_threads = 248;
+		rdev->config.evergreen.max_gs_threads = 32;
+		rdev->config.evergreen.max_stack_entries = 512;
+		rdev->config.evergreen.sx_num_of_sets = 4;
+		rdev->config.evergreen.sx_max_export_size = 256;
+		rdev->config.evergreen.sx_max_export_pos_size = 64;
+		rdev->config.evergreen.sx_max_export_smx_size = 192;
+		rdev->config.evergreen.max_hw_contexts = 8;
+		rdev->config.evergreen.sq_num_cf_insts = 2;
+
+		rdev->config.evergreen.sc_prim_fifo_size = 0x40;
+		rdev->config.evergreen.sc_hiz_tile_fifo_size = 0x30;
+		rdev->config.evergreen.sc_earlyz_tile_fifo_size = 0x130;
+		break;
 	case CHIP_BARTS:
 		rdev->config.evergreen.num_ses = 2;
 		rdev->config.evergreen.max_pipes = 4;
@@ -1936,9 +2013,9 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 		rdev->config.evergreen.tile_config |= (3 << 0);
 		break;
 	}
-	/* num banks is 8 on all fusion asics */
+	/* num banks is 8 on all fusion asics. 0 = 4, 1 = 8, 2 = 16 */
 	if (rdev->flags & RADEON_IS_IGP)
-		rdev->config.evergreen.tile_config |= 8 << 4;
+		rdev->config.evergreen.tile_config |= 1 << 4;
 	else
 		rdev->config.evergreen.tile_config |=
 			((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) << 4;
@@ -2039,6 +2116,8 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 	switch (rdev->family) {
 	case CHIP_CEDAR:
 	case CHIP_PALM:
+	case CHIP_SUMO:
+	case CHIP_SUMO2:
 	case CHIP_CAICOS:
 		/* no vertex cache */
 		sq_config &= ~VC_ENABLE;
@@ -2060,6 +2139,8 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 	switch (rdev->family) {
 	case CHIP_CEDAR:
 	case CHIP_PALM:
+	case CHIP_SUMO:
+	case CHIP_SUMO2:
 		ps_thread_count = 96;
 		break;
 	default:
@@ -2099,6 +2180,8 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 	switch (rdev->family) {
 	case CHIP_CEDAR:
 	case CHIP_PALM:
+	case CHIP_SUMO:
+	case CHIP_SUMO2:
 	case CHIP_CAICOS:
 		vgt_cache_invalidation = CACHE_INVALIDATION(TC_ONLY);
 		break;
@@ -2618,28 +2701,25 @@ static inline u32 evergreen_get_ih_wptr(struct radeon_device *rdev)
 
 int evergreen_irq_process(struct radeon_device *rdev)
 {
-	u32 wptr = evergreen_get_ih_wptr(rdev);
-	u32 rptr = rdev->ih.rptr;
+	u32 wptr;
+	u32 rptr;
 	u32 src_id, src_data;
 	u32 ring_index;
 	unsigned long flags;
 	bool queue_hotplug = false;
 
-	DRM_DEBUG("r600_irq_process start: rptr %d, wptr %d\n", rptr, wptr);
-	if (!rdev->ih.enabled)
+	if (!rdev->ih.enabled || rdev->shutdown)
 		return IRQ_NONE;
 
-	spin_lock_irqsave(&rdev->ih.lock, flags);
+	wptr = evergreen_get_ih_wptr(rdev);
+	rptr = rdev->ih.rptr;
+	DRM_DEBUG("r600_irq_process start: rptr %d, wptr %d\n", rptr, wptr);
 
+	spin_lock_irqsave(&rdev->ih.lock, flags);
 	if (rptr == wptr) {
 		spin_unlock_irqrestore(&rdev->ih.lock, flags);
 		return IRQ_NONE;
 	}
-	if (rdev->shutdown) {
-		spin_unlock_irqrestore(&rdev->ih.lock, flags);
-		return IRQ_NONE;
-	}
-
 restart_ih:
 	/* display interrupts */
 	evergreen_irq_ack(rdev);
@@ -2868,7 +2948,7 @@ restart_ih:
 			radeon_fence_process(rdev);
 			break;
 		case 233: /* GUI IDLE */
-			DRM_DEBUG("IH: CP EOP\n");
+			DRM_DEBUG("IH: GUI idle\n");
 			rdev->pm.gui_idle = true;
 			wake_up(&rdev->irq.idle_queue);
 			break;
diff --git a/drivers/gpu/drm/radeon/evergreen_blit_kms.c b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
index ba06a69c6de8..57f3bc17b87e 100644
--- a/drivers/gpu/drm/radeon/evergreen_blit_kms.c
+++ b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
@@ -31,6 +31,7 @@
 
 #include "evergreend.h"
 #include "evergreen_blit_shaders.h"
+#include "cayman_blit_shaders.h"
 
 #define DI_PT_RECTLIST        0x11
 #define DI_INDEX_SIZE_16_BIT  0x0
@@ -152,6 +153,8 @@ set_vtx_resource(struct radeon_device *rdev, u64 gpu_addr)
 
 	if ((rdev->family == CHIP_CEDAR) ||
 	    (rdev->family == CHIP_PALM) ||
+	    (rdev->family == CHIP_SUMO) ||
+	    (rdev->family == CHIP_SUMO2) ||
 	    (rdev->family == CHIP_CAICOS))
 		cp_set_surface_sync(rdev,
 				    PACKET3_TC_ACTION_ENA, 48, gpu_addr);
@@ -199,6 +202,16 @@ static void
 set_scissors(struct radeon_device *rdev, int x1, int y1,
 	     int x2, int y2)
 {
+	/* workaround some hw bugs */
+	if (x2 == 0)
+		x1 = 1;
+	if (y2 == 0)
+		y1 = 1;
+	if (rdev->family == CHIP_CAYMAN) {
+		if ((x2 == 1) && (y2 == 1))
+			x2 = 2;
+	}
+
 	radeon_ring_write(rdev, PACKET3(PACKET3_SET_CONTEXT_REG, 2));
 	radeon_ring_write(rdev, (PA_SC_SCREEN_SCISSOR_TL - PACKET3_SET_CONTEXT_REG_START) >> 2);
 	radeon_ring_write(rdev, (x1 << 0) | (y1 << 16));
@@ -255,238 +268,284 @@ set_default_state(struct radeon_device *rdev)
 	u64 gpu_addr;
 	int dwords;
 
-	switch (rdev->family) {
-	case CHIP_CEDAR:
-	default:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 96;
-		num_vs_threads = 16;
-		num_gs_threads = 16;
-		num_es_threads = 16;
-		num_hs_threads = 16;
-		num_ls_threads = 16;
-		num_ps_stack_entries = 42;
-		num_vs_stack_entries = 42;
-		num_gs_stack_entries = 42;
-		num_es_stack_entries = 42;
-		num_hs_stack_entries = 42;
-		num_ls_stack_entries = 42;
-		break;
-	case CHIP_REDWOOD:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 128;
-		num_vs_threads = 20;
-		num_gs_threads = 20;
-		num_es_threads = 20;
-		num_hs_threads = 20;
-		num_ls_threads = 20;
-		num_ps_stack_entries = 42;
-		num_vs_stack_entries = 42;
-		num_gs_stack_entries = 42;
-		num_es_stack_entries = 42;
-		num_hs_stack_entries = 42;
-		num_ls_stack_entries = 42;
-		break;
-	case CHIP_JUNIPER:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 128;
-		num_vs_threads = 20;
-		num_gs_threads = 20;
-		num_es_threads = 20;
-		num_hs_threads = 20;
-		num_ls_threads = 20;
-		num_ps_stack_entries = 85;
-		num_vs_stack_entries = 85;
-		num_gs_stack_entries = 85;
-		num_es_stack_entries = 85;
-		num_hs_stack_entries = 85;
-		num_ls_stack_entries = 85;
-		break;
-	case CHIP_CYPRESS:
-	case CHIP_HEMLOCK:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 128;
-		num_vs_threads = 20;
-		num_gs_threads = 20;
-		num_es_threads = 20;
-		num_hs_threads = 20;
-		num_ls_threads = 20;
-		num_ps_stack_entries = 85;
-		num_vs_stack_entries = 85;
-		num_gs_stack_entries = 85;
-		num_es_stack_entries = 85;
-		num_hs_stack_entries = 85;
-		num_ls_stack_entries = 85;
-		break;
-	case CHIP_PALM:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 96;
-		num_vs_threads = 16;
-		num_gs_threads = 16;
-		num_es_threads = 16;
-		num_hs_threads = 16;
-		num_ls_threads = 16;
-		num_ps_stack_entries = 42;
-		num_vs_stack_entries = 42;
-		num_gs_stack_entries = 42;
-		num_es_stack_entries = 42;
-		num_hs_stack_entries = 42;
-		num_ls_stack_entries = 42;
-		break;
-	case CHIP_BARTS:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 128;
-		num_vs_threads = 20;
-		num_gs_threads = 20;
-		num_es_threads = 20;
-		num_hs_threads = 20;
-		num_ls_threads = 20;
-		num_ps_stack_entries = 85;
-		num_vs_stack_entries = 85;
-		num_gs_stack_entries = 85;
-		num_es_stack_entries = 85;
-		num_hs_stack_entries = 85;
-		num_ls_stack_entries = 85;
-		break;
-	case CHIP_TURKS:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 128;
-		num_vs_threads = 20;
-		num_gs_threads = 20;
-		num_es_threads = 20;
-		num_hs_threads = 20;
-		num_ls_threads = 20;
-		num_ps_stack_entries = 42;
-		num_vs_stack_entries = 42;
-		num_gs_stack_entries = 42;
-		num_es_stack_entries = 42;
-		num_hs_stack_entries = 42;
-		num_ls_stack_entries = 42;
-		break;
-	case CHIP_CAICOS:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 128;
-		num_vs_threads = 10;
-		num_gs_threads = 10;
-		num_es_threads = 10;
-		num_hs_threads = 10;
-		num_ls_threads = 10;
-		num_ps_stack_entries = 42;
-		num_vs_stack_entries = 42;
-		num_gs_stack_entries = 42;
-		num_es_stack_entries = 42;
-		num_hs_stack_entries = 42;
-		num_ls_stack_entries = 42;
-		break;
-	}
-
-	if ((rdev->family == CHIP_CEDAR) ||
-	    (rdev->family == CHIP_PALM) ||
-	    (rdev->family == CHIP_CAICOS))
-		sq_config = 0;
-	else
-		sq_config = VC_ENABLE;
-
-	sq_config |= (EXPORT_SRC_C |
-		      CS_PRIO(0) |
-		      LS_PRIO(0) |
-		      HS_PRIO(0) |
-		      PS_PRIO(0) |
-		      VS_PRIO(1) |
-		      GS_PRIO(2) |
-		      ES_PRIO(3));
-
-	sq_gpr_resource_mgmt_1 = (NUM_PS_GPRS(num_ps_gprs) |
-				  NUM_VS_GPRS(num_vs_gprs) |
-				  NUM_CLAUSE_TEMP_GPRS(num_temp_gprs));
-	sq_gpr_resource_mgmt_2 = (NUM_GS_GPRS(num_gs_gprs) |
-				  NUM_ES_GPRS(num_es_gprs));
-	sq_gpr_resource_mgmt_3 = (NUM_HS_GPRS(num_hs_gprs) |
-				  NUM_LS_GPRS(num_ls_gprs));
-	sq_thread_resource_mgmt = (NUM_PS_THREADS(num_ps_threads) |
-				   NUM_VS_THREADS(num_vs_threads) |
-				   NUM_GS_THREADS(num_gs_threads) |
-				   NUM_ES_THREADS(num_es_threads));
-	sq_thread_resource_mgmt_2 = (NUM_HS_THREADS(num_hs_threads) |
-				     NUM_LS_THREADS(num_ls_threads));
-	sq_stack_resource_mgmt_1 = (NUM_PS_STACK_ENTRIES(num_ps_stack_entries) |
-				    NUM_VS_STACK_ENTRIES(num_vs_stack_entries));
-	sq_stack_resource_mgmt_2 = (NUM_GS_STACK_ENTRIES(num_gs_stack_entries) |
-				    NUM_ES_STACK_ENTRIES(num_es_stack_entries));
-	sq_stack_resource_mgmt_3 = (NUM_HS_STACK_ENTRIES(num_hs_stack_entries) |
-				    NUM_LS_STACK_ENTRIES(num_ls_stack_entries));
-
 	/* set clear context state */
 	radeon_ring_write(rdev, PACKET3(PACKET3_CLEAR_STATE, 0));
 	radeon_ring_write(rdev, 0);
 
-	/* disable dyn gprs */
-	radeon_ring_write(rdev, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-	radeon_ring_write(rdev, (SQ_DYN_GPR_CNTL_PS_FLUSH_REQ - PACKET3_SET_CONFIG_REG_START) >> 2);
-	radeon_ring_write(rdev, 0);
+	if (rdev->family < CHIP_CAYMAN) {
+		switch (rdev->family) {
+		case CHIP_CEDAR:
+		default:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 96;
+			num_vs_threads = 16;
+			num_gs_threads = 16;
+			num_es_threads = 16;
+			num_hs_threads = 16;
+			num_ls_threads = 16;
+			num_ps_stack_entries = 42;
+			num_vs_stack_entries = 42;
+			num_gs_stack_entries = 42;
+			num_es_stack_entries = 42;
+			num_hs_stack_entries = 42;
+			num_ls_stack_entries = 42;
+			break;
+		case CHIP_REDWOOD:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 128;
+			num_vs_threads = 20;
+			num_gs_threads = 20;
+			num_es_threads = 20;
+			num_hs_threads = 20;
+			num_ls_threads = 20;
+			num_ps_stack_entries = 42;
+			num_vs_stack_entries = 42;
+			num_gs_stack_entries = 42;
+			num_es_stack_entries = 42;
+			num_hs_stack_entries = 42;
+			num_ls_stack_entries = 42;
+			break;
+		case CHIP_JUNIPER:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 128;
+			num_vs_threads = 20;
+			num_gs_threads = 20;
+			num_es_threads = 20;
+			num_hs_threads = 20;
+			num_ls_threads = 20;
+			num_ps_stack_entries = 85;
+			num_vs_stack_entries = 85;
+			num_gs_stack_entries = 85;
+			num_es_stack_entries = 85;
+			num_hs_stack_entries = 85;
+			num_ls_stack_entries = 85;
+			break;
+		case CHIP_CYPRESS:
+		case CHIP_HEMLOCK:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 128;
+			num_vs_threads = 20;
+			num_gs_threads = 20;
+			num_es_threads = 20;
+			num_hs_threads = 20;
+			num_ls_threads = 20;
+			num_ps_stack_entries = 85;
+			num_vs_stack_entries = 85;
+			num_gs_stack_entries = 85;
+			num_es_stack_entries = 85;
+			num_hs_stack_entries = 85;
+			num_ls_stack_entries = 85;
+			break;
+		case CHIP_PALM:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 96;
+			num_vs_threads = 16;
+			num_gs_threads = 16;
+			num_es_threads = 16;
+			num_hs_threads = 16;
+			num_ls_threads = 16;
+			num_ps_stack_entries = 42;
+			num_vs_stack_entries = 42;
+			num_gs_stack_entries = 42;
+			num_es_stack_entries = 42;
+			num_hs_stack_entries = 42;
+			num_ls_stack_entries = 42;
+			break;
+		case CHIP_SUMO:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 96;
+			num_vs_threads = 25;
+			num_gs_threads = 25;
+			num_es_threads = 25;
+			num_hs_threads = 25;
+			num_ls_threads = 25;
+			num_ps_stack_entries = 42;
+			num_vs_stack_entries = 42;
+			num_gs_stack_entries = 42;
+			num_es_stack_entries = 42;
+			num_hs_stack_entries = 42;
+			num_ls_stack_entries = 42;
+			break;
+		case CHIP_SUMO2:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 96;
+			num_vs_threads = 25;
+			num_gs_threads = 25;
+			num_es_threads = 25;
+			num_hs_threads = 25;
+			num_ls_threads = 25;
+			num_ps_stack_entries = 85;
+			num_vs_stack_entries = 85;
+			num_gs_stack_entries = 85;
+			num_es_stack_entries = 85;
+			num_hs_stack_entries = 85;
+			num_ls_stack_entries = 85;
+			break;
+		case CHIP_BARTS:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 128;
+			num_vs_threads = 20;
+			num_gs_threads = 20;
+			num_es_threads = 20;
+			num_hs_threads = 20;
+			num_ls_threads = 20;
+			num_ps_stack_entries = 85;
+			num_vs_stack_entries = 85;
+			num_gs_stack_entries = 85;
+			num_es_stack_entries = 85;
+			num_hs_stack_entries = 85;
+			num_ls_stack_entries = 85;
+			break;
+		case CHIP_TURKS:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 128;
+			num_vs_threads = 20;
+			num_gs_threads = 20;
+			num_es_threads = 20;
+			num_hs_threads = 20;
+			num_ls_threads = 20;
+			num_ps_stack_entries = 42;
+			num_vs_stack_entries = 42;
+			num_gs_stack_entries = 42;
+			num_es_stack_entries = 42;
+			num_hs_stack_entries = 42;
+			num_ls_stack_entries = 42;
+			break;
+		case CHIP_CAICOS:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 128;
+			num_vs_threads = 10;
+			num_gs_threads = 10;
+			num_es_threads = 10;
+			num_hs_threads = 10;
+			num_ls_threads = 10;
+			num_ps_stack_entries = 42;
+			num_vs_stack_entries = 42;
+			num_gs_stack_entries = 42;
+			num_es_stack_entries = 42;
+			num_hs_stack_entries = 42;
+			num_ls_stack_entries = 42;
+			break;
+		}
 
-	/* SQ config */
-	radeon_ring_write(rdev, PACKET3(PACKET3_SET_CONFIG_REG, 11));
-	radeon_ring_write(rdev, (SQ_CONFIG - PACKET3_SET_CONFIG_REG_START) >> 2);
-	radeon_ring_write(rdev, sq_config);
-	radeon_ring_write(rdev, sq_gpr_resource_mgmt_1);
-	radeon_ring_write(rdev, sq_gpr_resource_mgmt_2);
-	radeon_ring_write(rdev, sq_gpr_resource_mgmt_3);
-	radeon_ring_write(rdev, 0);
-	radeon_ring_write(rdev, 0);
-	radeon_ring_write(rdev, sq_thread_resource_mgmt);
-	radeon_ring_write(rdev, sq_thread_resource_mgmt_2);
-	radeon_ring_write(rdev, sq_stack_resource_mgmt_1);
-	radeon_ring_write(rdev, sq_stack_resource_mgmt_2);
-	radeon_ring_write(rdev, sq_stack_resource_mgmt_3);
+		if ((rdev->family == CHIP_CEDAR) ||
+		    (rdev->family == CHIP_PALM) ||
+		    (rdev->family == CHIP_SUMO) ||
+		    (rdev->family == CHIP_SUMO2) ||
+		    (rdev->family == CHIP_CAICOS))
+			sq_config = 0;
+		else
+			sq_config = VC_ENABLE;
+
+		sq_config |= (EXPORT_SRC_C |
+			      CS_PRIO(0) |
+			      LS_PRIO(0) |
+			      HS_PRIO(0) |
+			      PS_PRIO(0) |
+			      VS_PRIO(1) |
+			      GS_PRIO(2) |
+			      ES_PRIO(3));
+
+		sq_gpr_resource_mgmt_1 = (NUM_PS_GPRS(num_ps_gprs) |
+					  NUM_VS_GPRS(num_vs_gprs) |
+					  NUM_CLAUSE_TEMP_GPRS(num_temp_gprs));
+		sq_gpr_resource_mgmt_2 = (NUM_GS_GPRS(num_gs_gprs) |
+					  NUM_ES_GPRS(num_es_gprs));
+		sq_gpr_resource_mgmt_3 = (NUM_HS_GPRS(num_hs_gprs) |
+					  NUM_LS_GPRS(num_ls_gprs));
+		sq_thread_resource_mgmt = (NUM_PS_THREADS(num_ps_threads) |
+					   NUM_VS_THREADS(num_vs_threads) |
+					   NUM_GS_THREADS(num_gs_threads) |
+					   NUM_ES_THREADS(num_es_threads));
+		sq_thread_resource_mgmt_2 = (NUM_HS_THREADS(num_hs_threads) |
+					     NUM_LS_THREADS(num_ls_threads));
+		sq_stack_resource_mgmt_1 = (NUM_PS_STACK_ENTRIES(num_ps_stack_entries) |
+					    NUM_VS_STACK_ENTRIES(num_vs_stack_entries));
+		sq_stack_resource_mgmt_2 = (NUM_GS_STACK_ENTRIES(num_gs_stack_entries) |
+					    NUM_ES_STACK_ENTRIES(num_es_stack_entries));
+		sq_stack_resource_mgmt_3 = (NUM_HS_STACK_ENTRIES(num_hs_stack_entries) |
+					    NUM_LS_STACK_ENTRIES(num_ls_stack_entries));
+
+		/* disable dyn gprs */
+		radeon_ring_write(rdev, PACKET3(PACKET3_SET_CONFIG_REG, 1));
+		radeon_ring_write(rdev, (SQ_DYN_GPR_CNTL_PS_FLUSH_REQ - PACKET3_SET_CONFIG_REG_START) >> 2);
+		radeon_ring_write(rdev, 0);
+
+		/* SQ config */
+		radeon_ring_write(rdev, PACKET3(PACKET3_SET_CONFIG_REG, 11));
+		radeon_ring_write(rdev, (SQ_CONFIG - PACKET3_SET_CONFIG_REG_START) >> 2);
+		radeon_ring_write(rdev, sq_config);
+		radeon_ring_write(rdev, sq_gpr_resource_mgmt_1);
+		radeon_ring_write(rdev, sq_gpr_resource_mgmt_2);
+		radeon_ring_write(rdev, sq_gpr_resource_mgmt_3);
+		radeon_ring_write(rdev, 0);
+		radeon_ring_write(rdev, 0);
+		radeon_ring_write(rdev, sq_thread_resource_mgmt);
+		radeon_ring_write(rdev, sq_thread_resource_mgmt_2);
+		radeon_ring_write(rdev, sq_stack_resource_mgmt_1);
+		radeon_ring_write(rdev, sq_stack_resource_mgmt_2);
+		radeon_ring_write(rdev, sq_stack_resource_mgmt_3);
+	}
 
 	/* CONTEXT_CONTROL */
 	radeon_ring_write(rdev, 0xc0012800);
@@ -560,7 +619,10 @@ int evergreen_blit_init(struct radeon_device *rdev)
 	mutex_init(&rdev->r600_blit.mutex);
 	rdev->r600_blit.state_offset = 0;
 
-	rdev->r600_blit.state_len = evergreen_default_size;
+	if (rdev->family < CHIP_CAYMAN)
+		rdev->r600_blit.state_len = evergreen_default_size;
+	else
+		rdev->r600_blit.state_len = cayman_default_size;
 
 	dwords = rdev->r600_blit.state_len;
 	while (dwords & 0xf) {
@@ -572,11 +634,17 @@ int evergreen_blit_init(struct radeon_device *rdev)
 	obj_size = ALIGN(obj_size, 256);
 
 	rdev->r600_blit.vs_offset = obj_size;
-	obj_size += evergreen_vs_size * 4;
+	if (rdev->family < CHIP_CAYMAN)
+		obj_size += evergreen_vs_size * 4;
+	else
+		obj_size += cayman_vs_size * 4;
 	obj_size = ALIGN(obj_size, 256);
 
 	rdev->r600_blit.ps_offset = obj_size;
-	obj_size += evergreen_ps_size * 4;
+	if (rdev->family < CHIP_CAYMAN)
+		obj_size += evergreen_ps_size * 4;
+	else
+		obj_size += cayman_ps_size * 4;
 	obj_size = ALIGN(obj_size, 256);
 
 	r = radeon_bo_create(rdev, obj_size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
@@ -599,16 +667,29 @@ int evergreen_blit_init(struct radeon_device *rdev)
 		return r;
 	}
 
-	memcpy_toio(ptr + rdev->r600_blit.state_offset,
-		    evergreen_default_state, rdev->r600_blit.state_len * 4);
-
-	if (num_packet2s)
-		memcpy_toio(ptr + rdev->r600_blit.state_offset + (rdev->r600_blit.state_len * 4),
-			    packet2s, num_packet2s * 4);
-	for (i = 0; i < evergreen_vs_size; i++)
-		*(u32 *)((unsigned long)ptr + rdev->r600_blit.vs_offset + i * 4) = cpu_to_le32(evergreen_vs[i]);
-	for (i = 0; i < evergreen_ps_size; i++)
-		*(u32 *)((unsigned long)ptr + rdev->r600_blit.ps_offset + i * 4) = cpu_to_le32(evergreen_ps[i]);
+	if (rdev->family < CHIP_CAYMAN) {
+		memcpy_toio(ptr + rdev->r600_blit.state_offset,
+			    evergreen_default_state, rdev->r600_blit.state_len * 4);
+
+		if (num_packet2s)
+			memcpy_toio(ptr + rdev->r600_blit.state_offset + (rdev->r600_blit.state_len * 4),
+				    packet2s, num_packet2s * 4);
+		for (i = 0; i < evergreen_vs_size; i++)
+			*(u32 *)((unsigned long)ptr + rdev->r600_blit.vs_offset + i * 4) = cpu_to_le32(evergreen_vs[i]);
+		for (i = 0; i < evergreen_ps_size; i++)
+			*(u32 *)((unsigned long)ptr + rdev->r600_blit.ps_offset + i * 4) = cpu_to_le32(evergreen_ps[i]);
+	} else {
+		memcpy_toio(ptr + rdev->r600_blit.state_offset,
+			    cayman_default_state, rdev->r600_blit.state_len * 4);
+
+		if (num_packet2s)
+			memcpy_toio(ptr + rdev->r600_blit.state_offset + (rdev->r600_blit.state_len * 4),
+				    packet2s, num_packet2s * 4);
+		for (i = 0; i < cayman_vs_size; i++)
+			*(u32 *)((unsigned long)ptr + rdev->r600_blit.vs_offset + i * 4) = cpu_to_le32(cayman_vs[i]);
+		for (i = 0; i < cayman_ps_size; i++)
+			*(u32 *)((unsigned long)ptr + rdev->r600_blit.ps_offset + i * 4) = cpu_to_le32(cayman_ps[i]);
+	}
 	radeon_bo_kunmap(rdev->r600_blit.shader_obj);
 	radeon_bo_unreserve(rdev->r600_blit.shader_obj);
 
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index f37e91ee8a11..1636e3449825 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -168,10 +168,16 @@
 #define		SE_DB_BUSY					(1 << 30)
 #define		SE_CB_BUSY					(1 << 31)
 /* evergreen */
+#define	CG_THERMAL_CTRL					0x72c
+#define		TOFFSET_MASK			        0x00003FE0
+#define		TOFFSET_SHIFT			        5
 #define	CG_MULT_THERMAL_STATUS				0x740
 #define		ASIC_T(x)			        ((x) << 16)
-#define		ASIC_T_MASK			        0x7FF0000
+#define		ASIC_T_MASK			        0x07FF0000
 #define		ASIC_T_SHIFT			        16
+#define	CG_TS0_STATUS					0x760
+#define		TS0_ADC_DOUT_MASK			0x000003FF
+#define		TS0_ADC_DOUT_SHIFT			0
 /* APU */
 #define	CG_THERMAL_STATUS			        0x678
 
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index b205ba1cdd8f..16caafeadf5e 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1387,14 +1387,12 @@ static int cayman_startup(struct radeon_device *rdev)
 		return r;
 	cayman_gpu_init(rdev);
 
-#if 0
-	r = cayman_blit_init(rdev);
+	r = evergreen_blit_init(rdev);
 	if (r) {
-		cayman_blit_fini(rdev);
+		evergreen_blit_fini(rdev);
 		rdev->asic->copy = NULL;
 		dev_warn(rdev->dev, "failed blitter (%d) falling back to memcpy\n", r);
 	}
-#endif
 
 	/* allocate wb buffer */
 	r = radeon_wb_init(rdev);
@@ -1452,7 +1450,7 @@ int cayman_resume(struct radeon_device *rdev)
 
 int cayman_suspend(struct radeon_device *rdev)
 {
-	/* int r; */
+	int r;
 
 	/* FIXME: we should wait for ring to be empty */
 	cayman_cp_enable(rdev, false);
@@ -1461,14 +1459,13 @@ int cayman_suspend(struct radeon_device *rdev)
 	radeon_wb_disable(rdev);
 	cayman_pcie_gart_disable(rdev);
 
-#if 0
 	/* unpin shaders bo */
 	r = radeon_bo_reserve(rdev->r600_blit.shader_obj, false);
 	if (likely(r == 0)) {
 		radeon_bo_unpin(rdev->r600_blit.shader_obj);
 		radeon_bo_unreserve(rdev->r600_blit.shader_obj);
 	}
-#endif
+
 	return 0;
 }
 
@@ -1580,7 +1577,7 @@ int cayman_init(struct radeon_device *rdev)
 
 void cayman_fini(struct radeon_device *rdev)
 {
-	/* cayman_blit_fini(rdev); */
+	evergreen_blit_fini(rdev);
 	cayman_cp_fini(rdev);
 	r600_irq_fini(rdev);
 	radeon_wb_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/r100_track.h b/drivers/gpu/drm/radeon/r100_track.h
index 2fef9de7f363..686f9dc5d4bd 100644
--- a/drivers/gpu/drm/radeon/r100_track.h
+++ b/drivers/gpu/drm/radeon/r100_track.h
@@ -63,7 +63,7 @@ struct r100_cs_track {
 	unsigned			num_arrays;
 	unsigned			max_indx;
 	unsigned			color_channel_mask;
-	struct r100_cs_track_array	arrays[11];
+	struct r100_cs_track_array	arrays[16];
 	struct r100_cs_track_cb 	cb[R300_MAX_CB];
 	struct r100_cs_track_cb 	zb;
 	struct r100_cs_track_cb 	aa;
@@ -146,6 +146,12 @@ static inline int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
 	ib = p->ib->ptr;
 	track = (struct r100_cs_track *)p->track;
 	c = radeon_get_ib_value(p, idx++) & 0x1F;
+	if (c > 16) {
+	    DRM_ERROR("Only 16 vertex buffers are allowed %d\n",
+		      pkt->opcode);
+	    r100_cs_dump_packet(p, pkt);
+	    return -EINVAL;
+	}
 	track->num_arrays = c;
 	for (i = 0; i < (c - 1); i+=2, idx+=3) {
 		r = r100_cs_packet_next_reloc(p, &reloc);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 6f27593901c7..f79d2ccb6755 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -87,6 +87,10 @@ MODULE_FIRMWARE("radeon/CYPRESS_rlc.bin");
 MODULE_FIRMWARE("radeon/PALM_pfp.bin");
 MODULE_FIRMWARE("radeon/PALM_me.bin");
 MODULE_FIRMWARE("radeon/SUMO_rlc.bin");
+MODULE_FIRMWARE("radeon/SUMO_pfp.bin");
+MODULE_FIRMWARE("radeon/SUMO_me.bin");
+MODULE_FIRMWARE("radeon/SUMO2_pfp.bin");
+MODULE_FIRMWARE("radeon/SUMO2_me.bin");
 
 int r600_debugfs_mc_info_init(struct radeon_device *rdev);
 
@@ -586,6 +590,9 @@ void r600_pm_misc(struct radeon_device *rdev)
 	struct radeon_voltage *voltage = &ps->clock_info[req_cm_idx].voltage;
 
 	if ((voltage->type == VOLTAGE_SW) && voltage->voltage) {
+		/* 0xff01 is a flag rather then an actual voltage */
+		if (voltage->voltage == 0xff01)
+			return;
 		if (voltage->voltage != rdev->pm.current_vddc) {
 			radeon_atom_set_voltage(rdev, voltage->voltage, SET_VOLTAGE_TYPE_ASIC_VDDC);
 			rdev->pm.current_vddc = voltage->voltage;
@@ -2024,6 +2031,14 @@ int r600_init_microcode(struct radeon_device *rdev)
 		chip_name = "PALM";
 		rlc_chip_name = "SUMO";
 		break;
+	case CHIP_SUMO:
+		chip_name = "SUMO";
+		rlc_chip_name = "SUMO";
+		break;
+	case CHIP_SUMO2:
+		chip_name = "SUMO2";
+		rlc_chip_name = "SUMO";
+		break;
 	default: BUG();
 	}
 
@@ -3282,27 +3297,26 @@ static inline u32 r600_get_ih_wptr(struct radeon_device *rdev)
 
 int r600_irq_process(struct radeon_device *rdev)
 {
-	u32 wptr = r600_get_ih_wptr(rdev);
-	u32 rptr = rdev->ih.rptr;
+	u32 wptr;
+	u32 rptr;
 	u32 src_id, src_data;
 	u32 ring_index;
 	unsigned long flags;
 	bool queue_hotplug = false;
 
-	DRM_DEBUG("r600_irq_process start: rptr %d, wptr %d\n", rptr, wptr);
-	if (!rdev->ih.enabled)
+	if (!rdev->ih.enabled || rdev->shutdown)
 		return IRQ_NONE;
 
+	wptr = r600_get_ih_wptr(rdev);
+	rptr = rdev->ih.rptr;
+	DRM_DEBUG("r600_irq_process start: rptr %d, wptr %d\n", rptr, wptr);
+
 	spin_lock_irqsave(&rdev->ih.lock, flags);
 
 	if (rptr == wptr) {
 		spin_unlock_irqrestore(&rdev->ih.lock, flags);
 		return IRQ_NONE;
 	}
-	if (rdev->shutdown) {
-		spin_unlock_irqrestore(&rdev->ih.lock, flags);
-		return IRQ_NONE;
-	}
 
 restart_ih:
 	/* display interrupts */
@@ -3432,7 +3446,7 @@ restart_ih:
 			radeon_fence_process(rdev);
 			break;
 		case 233: /* GUI IDLE */
-			DRM_DEBUG("IH: CP EOP\n");
+			DRM_DEBUG("IH: GUI idle\n");
 			rdev->pm.gui_idle = true;
 			wake_up(&rdev->irq.idle_queue);
 			break;
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index fd18be9871ab..909bda8dd550 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -71,20 +71,21 @@ struct r600_cs_track {
 	u64			db_bo_mc;
 };
 
-#define FMT_8_BIT(fmt, vc) [fmt] = { 1, 1, 1, vc }
-#define FMT_16_BIT(fmt, vc) [fmt] = { 1, 1, 2, vc }
-#define FMT_24_BIT(fmt) [fmt] = { 1, 1, 3, 0 }
-#define FMT_32_BIT(fmt, vc) [fmt] = { 1, 1, 4, vc }
-#define FMT_48_BIT(fmt) [fmt] = { 1, 1, 6, 0 }
-#define FMT_64_BIT(fmt, vc) [fmt] = { 1, 1, 8, vc }
-#define FMT_96_BIT(fmt) [fmt] = { 1, 1, 12, 0 }
-#define FMT_128_BIT(fmt, vc) [fmt] = { 1, 1, 16, vc }
+#define FMT_8_BIT(fmt, vc)   [fmt] = { 1, 1, 1, vc, CHIP_R600 }
+#define FMT_16_BIT(fmt, vc)  [fmt] = { 1, 1, 2, vc, CHIP_R600 }
+#define FMT_24_BIT(fmt)      [fmt] = { 1, 1, 3,  0, CHIP_R600 }
+#define FMT_32_BIT(fmt, vc)  [fmt] = { 1, 1, 4, vc, CHIP_R600 }
+#define FMT_48_BIT(fmt)      [fmt] = { 1, 1, 6,  0, CHIP_R600 }
+#define FMT_64_BIT(fmt, vc)  [fmt] = { 1, 1, 8, vc, CHIP_R600 }
+#define FMT_96_BIT(fmt)      [fmt] = { 1, 1, 12, 0, CHIP_R600 }
+#define FMT_128_BIT(fmt, vc) [fmt] = { 1, 1, 16,vc, CHIP_R600 }
 
 struct gpu_formats {
 	unsigned blockwidth;
 	unsigned blockheight;
 	unsigned blocksize;
 	unsigned valid_color;
+	enum radeon_family min_family;
 };
 
 static const struct gpu_formats color_formats_table[] = {
@@ -154,7 +155,11 @@ static const struct gpu_formats color_formats_table[] = {
 	[V_038004_FMT_BC3] = { 4, 4, 16, 0 },
 	[V_038004_FMT_BC4] = { 4, 4, 8, 0 },
 	[V_038004_FMT_BC5] = { 4, 4, 16, 0},
+	[V_038004_FMT_BC6] = { 4, 4, 16, 0, CHIP_CEDAR}, /* Evergreen-only */
+	[V_038004_FMT_BC7] = { 4, 4, 16, 0, CHIP_CEDAR}, /* Evergreen-only */
 
+	/* The other Evergreen formats */
+	[V_038004_FMT_32_AS_32_32_32_32] = { 1, 1, 4, 0, CHIP_CEDAR},
 };
 
 static inline bool fmt_is_valid_color(u32 format)
@@ -168,11 +173,14 @@ static inline bool fmt_is_valid_color(u32 format)
 	return false;
 }
 
-static inline bool fmt_is_valid_texture(u32 format)
+static inline bool fmt_is_valid_texture(u32 format, enum radeon_family family)
 {
 	if (format >= ARRAY_SIZE(color_formats_table))
 		return false;
 	
+	if (family < color_formats_table[format].min_family)
+		return false;
+
 	if (color_formats_table[format].blockwidth > 0)
 		return true;
 
@@ -1325,7 +1333,7 @@ static inline int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 i
 		return -EINVAL;
 	}
 	format = G_038004_DATA_FORMAT(word1);
-	if (!fmt_is_valid_texture(format)) {
+	if (!fmt_is_valid_texture(format, p->family)) {
 		dev_warn(p->dev, "%s:%d texture invalid format %d\n",
 			 __func__, __LINE__, format);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index b2b944bcd05a..f140a0d5cb54 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1309,6 +1309,9 @@
 #define     V_038004_FMT_BC3                           0x00000033
 #define     V_038004_FMT_BC4                           0x00000034
 #define     V_038004_FMT_BC5                           0x00000035
+#define     V_038004_FMT_BC6                           0x00000036
+#define     V_038004_FMT_BC7                           0x00000037
+#define     V_038004_FMT_32_AS_32_32_32_32             0x00000038
 #define R_038010_SQ_TEX_RESOURCE_WORD4_0             0x038010
 #define   S_038010_FORMAT_COMP_X(x)                    (((x) & 0x3) << 0)
 #define   G_038010_FORMAT_COMP_X(x)                    (((x) >> 0) & 0x3)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index ba643b576054..ef0e0e016914 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -165,6 +165,7 @@ struct radeon_clock {
 	uint32_t default_sclk;
 	uint32_t default_dispclk;
 	uint32_t dp_extclk;
+	uint32_t max_pixel_clock;
 };
 
 /*
@@ -178,6 +179,7 @@ void radeon_pm_resume(struct radeon_device *rdev);
 void radeon_combios_get_power_modes(struct radeon_device *rdev);
 void radeon_atombios_get_power_modes(struct radeon_device *rdev);
 void radeon_atom_set_voltage(struct radeon_device *rdev, u16 voltage_level, u8 voltage_type);
+int radeon_atom_get_max_vddc(struct radeon_device *rdev, u16 *voltage);
 void rs690_pm_info(struct radeon_device *rdev);
 extern int rv6xx_get_temp(struct radeon_device *rdev);
 extern int rv770_get_temp(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index d948265db87e..b2449629537d 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -906,9 +906,9 @@ static struct radeon_asic cayman_asic = {
 	.get_vblank_counter = &evergreen_get_vblank_counter,
 	.fence_ring_emit = &r600_fence_ring_emit,
 	.cs_parse = &evergreen_cs_parse,
-	.copy_blit = NULL,
-	.copy_dma = NULL,
-	.copy = NULL,
+	.copy_blit = &evergreen_copy_blit,
+	.copy_dma = &evergreen_copy_blit,
+	.copy = &evergreen_copy_blit,
 	.get_engine_clock = &radeon_atom_get_engine_clock,
 	.set_engine_clock = &radeon_atom_set_engine_clock,
 	.get_memory_clock = &radeon_atom_get_memory_clock,
@@ -938,6 +938,13 @@ static struct radeon_asic cayman_asic = {
 int radeon_asic_init(struct radeon_device *rdev)
 {
 	radeon_register_accessor_init(rdev);
+
+	/* set the number of crtcs */
+	if (rdev->flags & RADEON_SINGLE_CRTC)
+		rdev->num_crtc = 1;
+	else
+		rdev->num_crtc = 2;
+
 	switch (rdev->family) {
 	case CHIP_R100:
 	case CHIP_RV100:
@@ -1017,18 +1024,32 @@ int radeon_asic_init(struct radeon_device *rdev)
 	case CHIP_JUNIPER:
 	case CHIP_CYPRESS:
 	case CHIP_HEMLOCK:
+		/* set num crtcs */
+		if (rdev->family == CHIP_CEDAR)
+			rdev->num_crtc = 4;
+		else
+			rdev->num_crtc = 6;
 		rdev->asic = &evergreen_asic;
 		break;
 	case CHIP_PALM:
+	case CHIP_SUMO:
+	case CHIP_SUMO2:
 		rdev->asic = &sumo_asic;
 		break;
 	case CHIP_BARTS:
 	case CHIP_TURKS:
 	case CHIP_CAICOS:
+		/* set num crtcs */
+		if (rdev->family == CHIP_CAICOS)
+			rdev->num_crtc = 4;
+		else
+			rdev->num_crtc = 6;
 		rdev->asic = &btc_asic;
 		break;
 	case CHIP_CAYMAN:
 		rdev->asic = &cayman_asic;
+		/* set num crtcs */
+		rdev->num_crtc = 6;
 		break;
 	default:
 		/* FIXME: not supported yet */
@@ -1040,18 +1061,6 @@ int radeon_asic_init(struct radeon_device *rdev)
 		rdev->asic->set_memory_clock = NULL;
 	}
 
-	/* set the number of crtcs */
-	if (rdev->flags & RADEON_SINGLE_CRTC)
-		rdev->num_crtc = 1;
-	else {
-		if (ASIC_IS_DCE41(rdev))
-			rdev->num_crtc = 2;
-		else if (ASIC_IS_DCE4(rdev))
-			rdev->num_crtc = 6;
-		else
-			rdev->num_crtc = 2;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index 90dfb2b8cf03..bf2b61584cdb 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -1246,6 +1246,10 @@ bool radeon_atom_get_clock_info(struct drm_device *dev)
 		}
 		*dcpll = *p1pll;
 
+		rdev->clock.max_pixel_clock = le16_to_cpu(firmware_info->info.usMaxPixelClock);
+		if (rdev->clock.max_pixel_clock == 0)
+			rdev->clock.max_pixel_clock = 40000;
+
 		return true;
 	}
 
@@ -2316,6 +2320,14 @@ static bool radeon_atombios_parse_pplib_clock_info(struct radeon_device *rdev,
 			le16_to_cpu(clock_info->r600.usVDDC);
 	}
 
+	/* patch up vddc if necessary */
+	if (rdev->pm.power_state[state_index].clock_info[mode_index].voltage.voltage == 0xff01) {
+		u16 vddc;
+
+		if (radeon_atom_get_max_vddc(rdev, &vddc) == 0)
+			rdev->pm.power_state[state_index].clock_info[mode_index].voltage.voltage = vddc;
+	}
+
 	if (rdev->flags & RADEON_IS_IGP) {
 		/* skip invalid modes */
 		if (rdev->pm.power_state[state_index].clock_info[mode_index].sclk == 0)
@@ -2603,6 +2615,10 @@ void radeon_atom_set_voltage(struct radeon_device *rdev, u16 voltage_level, u8 v
 	if (!atom_parse_cmd_header(rdev->mode_info.atom_context, index, &frev, &crev))
 		return;
 
+	/* 0xff01 is a flag rather then an actual voltage */
+	if (voltage_level == 0xff01)
+		return;
+
 	switch (crev) {
 	case 1:
 		args.v1.ucVoltageType = voltage_type;
@@ -2622,7 +2638,35 @@ void radeon_atom_set_voltage(struct radeon_device *rdev, u16 voltage_level, u8 v
 	atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
 }
 
+int radeon_atom_get_max_vddc(struct radeon_device *rdev,
+			     u16 *voltage)
+{
+	union set_voltage args;
+	int index = GetIndexIntoMasterTable(COMMAND, SetVoltage);
+	u8 frev, crev;
+
+	if (!atom_parse_cmd_header(rdev->mode_info.atom_context, index, &frev, &crev))
+		return -EINVAL;
 
+	switch (crev) {
+	case 1:
+		return -EINVAL;
+	case 2:
+		args.v2.ucVoltageType = SET_VOLTAGE_GET_MAX_VOLTAGE;
+		args.v2.ucVoltageMode = 0;
+		args.v2.usVoltageLevel = 0;
+
+		atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+
+		*voltage = le16_to_cpu(args.v2.usVoltageLevel);
+		break;
+	default:
+		DRM_ERROR("Unknown table version %d, %d\n", frev, crev);
+		return -EINVAL;
+	}
+
+	return 0;
+}
 
 void radeon_atom_initialize_bios_scratch_regs(struct drm_device *dev)
 {
diff --git a/drivers/gpu/drm/radeon/radeon_clocks.c b/drivers/gpu/drm/radeon/radeon_clocks.c
index 5249af8931e6..2d48e7a1474b 100644
--- a/drivers/gpu/drm/radeon/radeon_clocks.c
+++ b/drivers/gpu/drm/radeon/radeon_clocks.c
@@ -117,7 +117,7 @@ static bool __devinit radeon_read_clocks_OF(struct drm_device *dev)
 	p1pll->reference_div = RREG32_PLL(RADEON_PPLL_REF_DIV) & 0x3ff;
 	if (p1pll->reference_div < 2)
 		p1pll->reference_div = 12;
-	p2pll->reference_div = p1pll->reference_div;	
+	p2pll->reference_div = p1pll->reference_div;
 
 	/* These aren't in the device-tree */
 	if (rdev->family >= CHIP_R420) {
@@ -139,6 +139,8 @@ static bool __devinit radeon_read_clocks_OF(struct drm_device *dev)
 		p2pll->pll_out_min = 12500;
 		p2pll->pll_out_max = 35000;
 	}
+	/* not sure what the max should be in all cases */
+	rdev->clock.max_pixel_clock = 35000;
 
 	spll->reference_freq = mpll->reference_freq = p1pll->reference_freq;
 	spll->reference_div = mpll->reference_div =
@@ -151,7 +153,7 @@ static bool __devinit radeon_read_clocks_OF(struct drm_device *dev)
 	else
 		rdev->clock.default_sclk =
 			radeon_legacy_get_engine_clock(rdev);
-			
+
 	val = of_get_property(dp, "ATY,MCLK", NULL);
 	if (val && *val)
 		rdev->clock.default_mclk = (*val) / 10;
@@ -160,7 +162,7 @@ static bool __devinit radeon_read_clocks_OF(struct drm_device *dev)
 			radeon_legacy_get_memory_clock(rdev);
 
 	DRM_INFO("Using device-tree clock info\n");
-	
+
 	return true;
 }
 #else
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 5b991f7c6e2a..e4594676a07c 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -866,6 +866,11 @@ bool radeon_combios_get_clock_info(struct drm_device *dev)
 		rdev->clock.default_sclk = sclk;
 		rdev->clock.default_mclk = mclk;
 
+		if (RBIOS32(pll_info + 0x16))
+			rdev->clock.max_pixel_clock = RBIOS32(pll_info + 0x16);
+		else
+			rdev->clock.max_pixel_clock = 35000; /* might need something asic specific */
+
 		return true;
 	}
 	return false;
@@ -1548,10 +1553,12 @@ bool radeon_get_legacy_connector_info_from_table(struct drm_device *dev)
 			   (rdev->pdev->subsystem_device == 0x4a48)) {
 			/* Mac X800 */
 			rdev->mode_info.connector_table = CT_MAC_X800;
-		} else if ((rdev->pdev->device == 0x4150) &&
+		} else if ((of_machine_is_compatible("PowerMac7,2") ||
+			    of_machine_is_compatible("PowerMac7,3")) &&
+			   (rdev->pdev->device == 0x4150) &&
 			   (rdev->pdev->subsystem_vendor == 0x1002) &&
 			   (rdev->pdev->subsystem_device == 0x4150)) {
-			/* Mac G5 9600 */
+			/* Mac G5 tower 9600 */
 			rdev->mode_info.connector_table = CT_MAC_G5_9600;
 		} else
 #endif /* CONFIG_PPC_PMAC */
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index ee1dccb3fec9..cbfca3a24fdf 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -44,6 +44,8 @@ extern void
 radeon_legacy_backlight_init(struct radeon_encoder *radeon_encoder,
 			     struct drm_connector *drm_connector);
 
+bool radeon_connector_encoder_is_dp_bridge(struct drm_connector *connector);
+
 void radeon_connector_hotplug(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
@@ -626,8 +628,14 @@ static int radeon_vga_get_modes(struct drm_connector *connector)
 static int radeon_vga_mode_valid(struct drm_connector *connector,
 				  struct drm_display_mode *mode)
 {
+	struct drm_device *dev = connector->dev;
+	struct radeon_device *rdev = dev->dev_private;
+
 	/* XXX check mode bandwidth */
-	/* XXX verify against max DAC output frequency */
+
+	if ((mode->clock / 10) > rdev->clock.max_pixel_clock)
+		return MODE_CLOCK_HIGH;
+
 	return MODE_OK;
 }
 
@@ -830,6 +838,13 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 		if (!radeon_connector->edid) {
 			DRM_ERROR("%s: probed a monitor but no|invalid EDID\n",
 					drm_get_connector_name(connector));
+			/* rs690 seems to have a problem with connectors not existing and always
+			 * return a block of 0's. If we see this just stop polling on this output */
+			if ((rdev->family == CHIP_RS690 || rdev->family == CHIP_RS740) && radeon_connector->base.null_edid_counter) {
+				ret = connector_status_disconnected;
+				DRM_ERROR("%s: detected RS690 floating bus bug, stopping ddc detect\n", drm_get_connector_name(connector));
+				radeon_connector->ddc_bus = NULL;
+			}
 		} else {
 			radeon_connector->use_digital = !!(radeon_connector->edid->input & DRM_EDID_INPUT_DIGITAL);
 
@@ -1015,6 +1030,11 @@ static int radeon_dvi_mode_valid(struct drm_connector *connector,
 		} else
 			return MODE_CLOCK_HIGH;
 	}
+
+	/* check against the max pixel clock */
+	if ((mode->clock / 10) > rdev->clock.max_pixel_clock)
+		return MODE_CLOCK_HIGH;
+
 	return MODE_OK;
 }
 
@@ -1052,10 +1072,11 @@ static int radeon_dp_get_modes(struct drm_connector *connector)
 {
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct radeon_connector_atom_dig *radeon_dig_connector = radeon_connector->con_priv;
+	struct drm_encoder *encoder = radeon_best_single_encoder(connector);
 	int ret;
 
-	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
-		struct drm_encoder *encoder;
+	if ((connector->connector_type == DRM_MODE_CONNECTOR_eDP) ||
+	    (connector->connector_type == DRM_MODE_CONNECTOR_LVDS)) {
 		struct drm_display_mode *mode;
 
 		if (!radeon_dig_connector->edp_on)
@@ -1067,7 +1088,6 @@ static int radeon_dp_get_modes(struct drm_connector *connector)
 						     ATOM_TRANSMITTER_ACTION_POWER_OFF);
 
 		if (ret > 0) {
-			encoder = radeon_best_single_encoder(connector);
 			if (encoder) {
 				radeon_fixup_lvds_native_mode(encoder, connector);
 				/* add scaled modes */
@@ -1091,8 +1111,14 @@ static int radeon_dp_get_modes(struct drm_connector *connector)
 			/* add scaled modes */
 			radeon_add_common_modes(encoder, connector);
 		}
-	} else
+	} else {
+		/* need to setup ddc on the bridge */
+		if (radeon_connector_encoder_is_dp_bridge(connector)) {
+			if (encoder)
+				radeon_atom_ext_encoder_setup_ddc(encoder);
+		}
 		ret = radeon_ddc_get_modes(radeon_connector);
+	}
 
 	return ret;
 }
@@ -1176,14 +1202,15 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	enum drm_connector_status ret = connector_status_disconnected;
 	struct radeon_connector_atom_dig *radeon_dig_connector = radeon_connector->con_priv;
+	struct drm_encoder *encoder = radeon_best_single_encoder(connector);
 
 	if (radeon_connector->edid) {
 		kfree(radeon_connector->edid);
 		radeon_connector->edid = NULL;
 	}
 
-	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
-		struct drm_encoder *encoder = radeon_best_single_encoder(connector);
+	if ((connector->connector_type == DRM_MODE_CONNECTOR_eDP) ||
+	    (connector->connector_type == DRM_MODE_CONNECTOR_LVDS)) {
 		if (encoder) {
 			struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 			struct drm_display_mode *native_mode = &radeon_encoder->native_mode;
@@ -1203,6 +1230,11 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 			atombios_set_edp_panel_power(connector,
 						     ATOM_TRANSMITTER_ACTION_POWER_OFF);
 	} else {
+		/* need to setup ddc on the bridge */
+		if (radeon_connector_encoder_is_dp_bridge(connector)) {
+			if (encoder)
+				radeon_atom_ext_encoder_setup_ddc(encoder);
+		}
 		radeon_dig_connector->dp_sink_type = radeon_dp_getsinktype(radeon_connector);
 		if (radeon_hpd_sense(rdev, radeon_connector->hpd.hpd)) {
 			ret = connector_status_connected;
@@ -1217,6 +1249,16 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 					ret = connector_status_connected;
 			}
 		}
+
+		if ((ret == connector_status_disconnected) &&
+		    radeon_connector->dac_load_detect) {
+			struct drm_encoder *encoder = radeon_best_single_encoder(connector);
+			struct drm_encoder_helper_funcs *encoder_funcs;
+			if (encoder) {
+				encoder_funcs = encoder->helper_private;
+				ret = encoder_funcs->detect(encoder, connector);
+			}
+		}
 	}
 
 	radeon_connector_update_scratch_regs(connector, ret);
@@ -1231,7 +1273,8 @@ static int radeon_dp_mode_valid(struct drm_connector *connector,
 
 	/* XXX check mode bandwidth */
 
-	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
+	if ((connector->connector_type == DRM_MODE_CONNECTOR_eDP) ||
+	    (connector->connector_type == DRM_MODE_CONNECTOR_LVDS)) {
 		struct drm_encoder *encoder = radeon_best_single_encoder(connector);
 
 		if ((mode->hdisplay < 320) || (mode->vdisplay < 240))
@@ -1241,7 +1284,7 @@ static int radeon_dp_mode_valid(struct drm_connector *connector,
 			struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 			struct drm_display_mode *native_mode = &radeon_encoder->native_mode;
 
-		/* AVIVO hardware supports downscaling modes larger than the panel
+			/* AVIVO hardware supports downscaling modes larger than the panel
 			 * to the panel size, but I'm not sure this is desirable.
 			 */
 			if ((mode->hdisplay > native_mode->hdisplay) ||
@@ -1390,6 +1433,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 		default:
 			connector->interlace_allowed = true;
 			connector->doublescan_allowed = true;
+			radeon_connector->dac_load_detect = true;
+			drm_connector_attach_property(&radeon_connector->base,
+						      rdev->mode_info.load_detect_property,
+						      1);
 			break;
 		case DRM_MODE_CONNECTOR_DVII:
 		case DRM_MODE_CONNECTOR_DVID:
@@ -1411,6 +1458,12 @@ radeon_add_atom_connector(struct drm_device *dev,
 				connector->doublescan_allowed = true;
 			else
 				connector->doublescan_allowed = false;
+			if (connector_type == DRM_MODE_CONNECTOR_DVII) {
+				radeon_connector->dac_load_detect = true;
+				drm_connector_attach_property(&radeon_connector->base,
+							      rdev->mode_info.load_detect_property,
+							      1);
+			}
 			break;
 		case DRM_MODE_CONNECTOR_LVDS:
 		case DRM_MODE_CONNECTOR_eDP:
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 8c1916941871..fae00c0d75aa 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -228,6 +228,7 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	parser.filp = filp;
 	parser.rdev = rdev;
 	parser.dev = rdev->dev;
+	parser.family = rdev->family;
 	r = radeon_cs_parser_init(&parser, data);
 	if (r) {
 		DRM_ERROR("Failed to initialize parser !\n");
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 5b61364e31f4..7cfaa7e2f3b5 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -82,6 +82,8 @@ static const char radeon_family_name[][16] = {
 	"CYPRESS",
 	"HEMLOCK",
 	"PALM",
+	"SUMO",
+	"SUMO2",
 	"BARTS",
 	"TURKS",
 	"CAICOS",
@@ -213,6 +215,8 @@ int radeon_wb_init(struct radeon_device *rdev)
 		return r;
 	}
 
+	/* clear wb memory */
+	memset((char *)rdev->wb.wb, 0, RADEON_GPU_PAGE_SIZE);
 	/* disable event_write fences */
 	rdev->wb.use_event = false;
 	/* disabled via module param */
@@ -752,6 +756,7 @@ int radeon_device_init(struct radeon_device *rdev,
 	dma_bits = rdev->need_dma32 ? 32 : 40;
 	r = pci_set_dma_mask(rdev->pdev, DMA_BIT_MASK(dma_bits));
 	if (r) {
+		rdev->need_dma32 = true;
 		printk(KERN_WARNING "radeon: No suitable DMA available.\n");
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index ae247eec87c0..292f73f0ddbd 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -264,6 +264,8 @@ static void radeon_unpin_work_func(struct work_struct *__work)
 		radeon_bo_unreserve(work->old_rbo);
 	} else
 		DRM_ERROR("failed to reserve buffer after flip\n");
+
+	drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
 	kfree(work);
 }
 
@@ -371,6 +373,8 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 	new_radeon_fb = to_radeon_framebuffer(fb);
 	/* schedule unpin of the old buffer */
 	obj = old_radeon_fb->obj;
+	/* take a reference to the old object */
+	drm_gem_object_reference(obj);
 	rbo = gem_to_radeon_bo(obj);
 	work->old_rbo = rbo;
 	INIT_WORK(&work->work, radeon_unpin_work_func);
@@ -378,12 +382,9 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 	/* We borrow the event spin lock for protecting unpin_work */
 	spin_lock_irqsave(&dev->event_lock, flags);
 	if (radeon_crtc->unpin_work) {
-		spin_unlock_irqrestore(&dev->event_lock, flags);
-		kfree(work);
-		radeon_fence_unref(&fence);
-
 		DRM_DEBUG_DRIVER("flip queue: crtc already busy\n");
-		return -EBUSY;
+		r = -EBUSY;
+		goto unlock_free;
 	}
 	radeon_crtc->unpin_work = work;
 	radeon_crtc->deferred_flip_completion = 0;
@@ -497,6 +498,8 @@ pflip_cleanup1:
 pflip_cleanup:
 	spin_lock_irqsave(&dev->event_lock, flags);
 	radeon_crtc->unpin_work = NULL;
+unlock_free:
+	drm_gem_object_unreference_unlocked(old_radeon_fb->obj);
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 	radeon_fence_unref(&fence);
 	kfree(work);
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 1d330606292f..73dfbe8e5f9e 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -113,7 +113,7 @@ int radeon_benchmarking = 0;
 int radeon_testing = 0;
 int radeon_connector_table = 0;
 int radeon_tv = 1;
-int radeon_audio = 1;
+int radeon_audio = 0;
 int radeon_disp_priority = 0;
 int radeon_hw_i2c = 0;
 int radeon_pcie_gen2 = 0;
@@ -151,7 +151,7 @@ module_param_named(connector_table, radeon_connector_table, int, 0444);
 MODULE_PARM_DESC(tv, "TV enable (0 = disable)");
 module_param_named(tv, radeon_tv, int, 0444);
 
-MODULE_PARM_DESC(audio, "Audio enable (0 = disable)");
+MODULE_PARM_DESC(audio, "Audio enable (1 = enable)");
 module_param_named(audio, radeon_audio, int, 0444);
 
 MODULE_PARM_DESC(disp_priority, "Display Priority (0 = auto, 1 = normal, 2 = high)");
diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index 1b557554696e..b293487e5aa3 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -367,7 +367,8 @@ static bool radeon_atom_mode_fixup(struct drm_encoder *encoder,
 	}
 
 	if (ASIC_IS_DCE3(rdev) &&
-	    (radeon_encoder->active_device & (ATOM_DEVICE_DFP_SUPPORT | ATOM_DEVICE_LCD_SUPPORT))) {
+	    ((radeon_encoder->active_device & (ATOM_DEVICE_DFP_SUPPORT | ATOM_DEVICE_LCD_SUPPORT)) ||
+	     radeon_encoder_is_dp_bridge(encoder))) {
 		struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 		radeon_dp_set_link_config(connector, mode);
 	}
@@ -660,21 +661,16 @@ atombios_get_encoder_mode(struct drm_encoder *encoder)
 	if (radeon_encoder_is_dp_bridge(encoder))
 		return ATOM_ENCODER_MODE_DP;
 
+	/* DVO is always DVO */
+	if (radeon_encoder->encoder_id == ATOM_ENCODER_MODE_DVO)
+		return ATOM_ENCODER_MODE_DVO;
+
 	connector = radeon_get_connector_for_encoder(encoder);
-	if (!connector) {
-		switch (radeon_encoder->encoder_id) {
-		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
-		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
-		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
-		case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA:
-		case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1:
-			return ATOM_ENCODER_MODE_DVI;
-		case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC1:
-		case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC2:
-		default:
-			return ATOM_ENCODER_MODE_CRT;
-		}
-	}
+	/* if we don't have an active device yet, just use one of
+	 * the connectors tied to the encoder.
+	 */
+	if (!connector)
+		connector = radeon_get_connector_for_encoder_init(encoder);
 	radeon_connector = to_radeon_connector(connector);
 
 	switch (connector->connector_type) {
@@ -954,10 +950,15 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 	int dp_lane_count = 0;
 	int connector_object_id = 0;
 	int igp_lane_info = 0;
+	int dig_encoder = dig->dig_encoder;
 
-	if (action == ATOM_TRANSMITTER_ACTION_INIT)
+	if (action == ATOM_TRANSMITTER_ACTION_INIT) {
 		connector = radeon_get_connector_for_encoder_init(encoder);
-	else
+		/* just needed to avoid bailing in the encoder check.  the encoder
+		 * isn't used for init
+		 */
+		dig_encoder = 0;
+	} else
 		connector = radeon_get_connector_for_encoder(encoder);
 
 	if (connector) {
@@ -973,7 +974,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 	}
 
 	/* no dig encoder assigned */
-	if (dig->dig_encoder == -1)
+	if (dig_encoder == -1)
 		return;
 
 	if (atombios_get_encoder_mode(encoder) == ATOM_ENCODER_MODE_DP)
@@ -1023,7 +1024,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 
 		if (dig->linkb)
 			args.v3.acConfig.ucLinkSel = 1;
-		if (dig->dig_encoder & 1)
+		if (dig_encoder & 1)
 			args.v3.acConfig.ucEncoderSel = 1;
 
 		/* Select the PLL for the PHY
@@ -1073,7 +1074,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 				args.v3.acConfig.fDualLinkConnector = 1;
 		}
 	} else if (ASIC_IS_DCE32(rdev)) {
-		args.v2.acConfig.ucEncoderSel = dig->dig_encoder;
+		args.v2.acConfig.ucEncoderSel = dig_encoder;
 		if (dig->linkb)
 			args.v2.acConfig.ucLinkSel = 1;
 
@@ -1089,9 +1090,10 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 			break;
 		}
 
-		if (is_dp)
+		if (is_dp) {
 			args.v2.acConfig.fCoherentMode = 1;
-		else if (radeon_encoder->devices & (ATOM_DEVICE_DFP_SUPPORT)) {
+			args.v2.acConfig.fDPConnector = 1;
+		} else if (radeon_encoder->devices & (ATOM_DEVICE_DFP_SUPPORT)) {
 			if (dig->coherent_mode)
 				args.v2.acConfig.fCoherentMode = 1;
 			if (radeon_encoder->pixel_clock > 165000)
@@ -1100,7 +1102,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 	} else {
 		args.v1.ucConfig = ATOM_TRANSMITTER_CONFIG_CLKSRC_PPLL;
 
-		if (dig->dig_encoder)
+		if (dig_encoder)
 			args.v1.ucConfig |= ATOM_TRANSMITTER_CONFIG_DIG2_ENCODER;
 		else
 			args.v1.ucConfig |= ATOM_TRANSMITTER_CONFIG_DIG1_ENCODER;
@@ -1430,7 +1432,11 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode)
 	if (is_dig) {
 		switch (mode) {
 		case DRM_MODE_DPMS_ON:
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
+			/* some early dce3.2 boards have a bug in their transmitter control table */
+			if ((rdev->family == CHIP_RV710) || (rdev->family == CHIP_RV730))
+				atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
+			else
+				atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
 			if (atombios_get_encoder_mode(encoder) == ATOM_ENCODER_MODE_DP) {
 				struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 
@@ -1521,26 +1527,29 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode)
 	}
 
 	if (ext_encoder) {
-		int action;
-
 		switch (mode) {
 		case DRM_MODE_DPMS_ON:
 		default:
-			if (ASIC_IS_DCE41(rdev))
-				action = EXTERNAL_ENCODER_ACTION_V3_ENABLE_OUTPUT;
-			else
-				action = ATOM_ENABLE;
+			if (ASIC_IS_DCE41(rdev)) {
+				atombios_external_encoder_setup(encoder, ext_encoder,
+								EXTERNAL_ENCODER_ACTION_V3_ENABLE_OUTPUT);
+				atombios_external_encoder_setup(encoder, ext_encoder,
+								EXTERNAL_ENCODER_ACTION_V3_ENCODER_BLANKING_OFF);
+			} else
+				atombios_external_encoder_setup(encoder, ext_encoder, ATOM_ENABLE);
 			break;
 		case DRM_MODE_DPMS_STANDBY:
 		case DRM_MODE_DPMS_SUSPEND:
 		case DRM_MODE_DPMS_OFF:
-			if (ASIC_IS_DCE41(rdev))
-				action = EXTERNAL_ENCODER_ACTION_V3_DISABLE_OUTPUT;
-			else
-				action = ATOM_DISABLE;
+			if (ASIC_IS_DCE41(rdev)) {
+				atombios_external_encoder_setup(encoder, ext_encoder,
+								EXTERNAL_ENCODER_ACTION_V3_ENCODER_BLANKING);
+				atombios_external_encoder_setup(encoder, ext_encoder,
+								EXTERNAL_ENCODER_ACTION_V3_DISABLE_OUTPUT);
+			} else
+				atombios_external_encoder_setup(encoder, ext_encoder, ATOM_DISABLE);
 			break;
 		}
-		atombios_external_encoder_setup(encoder, ext_encoder, action);
 	}
 
 	radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false);
@@ -1999,6 +2008,65 @@ radeon_atom_dac_detect(struct drm_encoder *encoder, struct drm_connector *connec
 	return connector_status_disconnected;
 }
 
+static enum drm_connector_status
+radeon_atom_dig_detect(struct drm_encoder *encoder, struct drm_connector *connector)
+{
+	struct drm_device *dev = encoder->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+	struct drm_encoder *ext_encoder = radeon_atom_get_external_encoder(encoder);
+	u32 bios_0_scratch;
+
+	if (!ASIC_IS_DCE4(rdev))
+		return connector_status_unknown;
+
+	if (!ext_encoder)
+		return connector_status_unknown;
+
+	if ((radeon_connector->devices & ATOM_DEVICE_CRT_SUPPORT) == 0)
+		return connector_status_unknown;
+
+	/* load detect on the dp bridge */
+	atombios_external_encoder_setup(encoder, ext_encoder,
+					EXTERNAL_ENCODER_ACTION_V3_DACLOAD_DETECTION);
+
+	bios_0_scratch = RREG32(R600_BIOS_0_SCRATCH);
+
+	DRM_DEBUG_KMS("Bios 0 scratch %x %08x\n", bios_0_scratch, radeon_encoder->devices);
+	if (radeon_connector->devices & ATOM_DEVICE_CRT1_SUPPORT) {
+		if (bios_0_scratch & ATOM_S0_CRT1_MASK)
+			return connector_status_connected;
+	}
+	if (radeon_connector->devices & ATOM_DEVICE_CRT2_SUPPORT) {
+		if (bios_0_scratch & ATOM_S0_CRT2_MASK)
+			return connector_status_connected;
+	}
+	if (radeon_connector->devices & ATOM_DEVICE_CV_SUPPORT) {
+		if (bios_0_scratch & (ATOM_S0_CV_MASK|ATOM_S0_CV_MASK_A))
+			return connector_status_connected;
+	}
+	if (radeon_connector->devices & ATOM_DEVICE_TV1_SUPPORT) {
+		if (bios_0_scratch & (ATOM_S0_TV1_COMPOSITE | ATOM_S0_TV1_COMPOSITE_A))
+			return connector_status_connected; /* CTV */
+		else if (bios_0_scratch & (ATOM_S0_TV1_SVIDEO | ATOM_S0_TV1_SVIDEO_A))
+			return connector_status_connected; /* STV */
+	}
+	return connector_status_disconnected;
+}
+
+void
+radeon_atom_ext_encoder_setup_ddc(struct drm_encoder *encoder)
+{
+	struct drm_encoder *ext_encoder = radeon_atom_get_external_encoder(encoder);
+
+	if (ext_encoder)
+		/* ddc_setup on the dp bridge */
+		atombios_external_encoder_setup(encoder, ext_encoder,
+						EXTERNAL_ENCODER_ACTION_V3_DDC_SETUP);
+
+}
+
 static void radeon_atom_encoder_prepare(struct drm_encoder *encoder)
 {
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
@@ -2162,7 +2230,7 @@ static const struct drm_encoder_helper_funcs radeon_atom_dig_helper_funcs = {
 	.mode_set = radeon_atom_encoder_mode_set,
 	.commit = radeon_atom_encoder_commit,
 	.disable = radeon_atom_encoder_disable,
-	/* no detect for TMDS/LVDS yet */
+	.detect = radeon_atom_dig_detect,
 };
 
 static const struct drm_encoder_helper_funcs radeon_atom_dac_helper_funcs = {
diff --git a/drivers/gpu/drm/radeon/radeon_family.h b/drivers/gpu/drm/radeon/radeon_family.h
index 6f1d9e563e77..ec2f1ea84f81 100644
--- a/drivers/gpu/drm/radeon/radeon_family.h
+++ b/drivers/gpu/drm/radeon/radeon_family.h
@@ -81,6 +81,8 @@ enum radeon_family {
 	CHIP_CYPRESS,
 	CHIP_HEMLOCK,
 	CHIP_PALM,
+	CHIP_SUMO,
+	CHIP_SUMO2,
 	CHIP_BARTS,
 	CHIP_TURKS,
 	CHIP_CAICOS,
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 1f8229436570..021d2b6b556f 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -40,6 +40,35 @@
 #include "radeon.h"
 #include "radeon_trace.h"
 
+static void radeon_fence_write(struct radeon_device *rdev, u32 seq)
+{
+	if (rdev->wb.enabled) {
+		u32 scratch_index;
+		if (rdev->wb.use_event)
+			scratch_index = R600_WB_EVENT_OFFSET + rdev->fence_drv.scratch_reg - rdev->scratch.reg_base;
+		else
+			scratch_index = RADEON_WB_SCRATCH_OFFSET + rdev->fence_drv.scratch_reg - rdev->scratch.reg_base;
+		rdev->wb.wb[scratch_index/4] = cpu_to_le32(seq);;
+	} else
+		WREG32(rdev->fence_drv.scratch_reg, seq);
+}
+
+static u32 radeon_fence_read(struct radeon_device *rdev)
+{
+	u32 seq;
+
+	if (rdev->wb.enabled) {
+		u32 scratch_index;
+		if (rdev->wb.use_event)
+			scratch_index = R600_WB_EVENT_OFFSET + rdev->fence_drv.scratch_reg - rdev->scratch.reg_base;
+		else
+			scratch_index = RADEON_WB_SCRATCH_OFFSET + rdev->fence_drv.scratch_reg - rdev->scratch.reg_base;
+		seq = le32_to_cpu(rdev->wb.wb[scratch_index/4]);
+	} else
+		seq = RREG32(rdev->fence_drv.scratch_reg);
+	return seq;
+}
+
 int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence)
 {
 	unsigned long irq_flags;
@@ -50,12 +79,12 @@ int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence)
 		return 0;
 	}
 	fence->seq = atomic_add_return(1, &rdev->fence_drv.seq);
-	if (!rdev->cp.ready) {
+	if (!rdev->cp.ready)
 		/* FIXME: cp is not running assume everythings is done right
 		 * away
 		 */
-		WREG32(rdev->fence_drv.scratch_reg, fence->seq);
-	} else
+		radeon_fence_write(rdev, fence->seq);
+	else
 		radeon_fence_ring_emit(rdev, fence);
 
 	trace_radeon_fence_emit(rdev->ddev, fence->seq);
@@ -73,15 +102,7 @@ static bool radeon_fence_poll_locked(struct radeon_device *rdev)
 	bool wake = false;
 	unsigned long cjiffies;
 
-	if (rdev->wb.enabled) {
-		u32 scratch_index;
-		if (rdev->wb.use_event)
-			scratch_index = R600_WB_EVENT_OFFSET + rdev->fence_drv.scratch_reg - rdev->scratch.reg_base;
-		else
-			scratch_index = RADEON_WB_SCRATCH_OFFSET + rdev->fence_drv.scratch_reg - rdev->scratch.reg_base;
-		seq = le32_to_cpu(rdev->wb.wb[scratch_index/4]);
-	} else
-		seq = RREG32(rdev->fence_drv.scratch_reg);
+	seq = radeon_fence_read(rdev);
 	if (seq != rdev->fence_drv.last_seq) {
 		rdev->fence_drv.last_seq = seq;
 		rdev->fence_drv.last_jiffies = jiffies;
@@ -251,7 +272,7 @@ retry:
 			r = radeon_gpu_reset(rdev);
 			if (r)
 				return r;
-			WREG32(rdev->fence_drv.scratch_reg, fence->seq);
+			radeon_fence_write(rdev, fence->seq);
 			rdev->gpu_lockup = false;
 		}
 		timeout = RADEON_FENCE_JIFFIES_TIMEOUT;
@@ -351,7 +372,7 @@ int radeon_fence_driver_init(struct radeon_device *rdev)
 		write_unlock_irqrestore(&rdev->fence_drv.lock, irq_flags);
 		return r;
 	}
-	WREG32(rdev->fence_drv.scratch_reg, 0);
+	radeon_fence_write(rdev, 0);
 	atomic_set(&rdev->fence_drv.seq, 0);
 	INIT_LIST_HEAD(&rdev->fence_drv.created);
 	INIT_LIST_HEAD(&rdev->fence_drv.emited);
@@ -391,7 +412,7 @@ static int radeon_debugfs_fence_info(struct seq_file *m, void *data)
 	struct radeon_fence *fence;
 
 	seq_printf(m, "Last signaled fence 0x%08X\n",
-		   RREG32(rdev->fence_drv.scratch_reg));
+		   radeon_fence_read(rdev));
 	if (!list_empty(&rdev->fence_drv.emited)) {
 		   fence = list_entry(rdev->fence_drv.emited.prev,
 				      struct radeon_fence, list);
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 977a341266b6..6df4e3cec0c2 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -483,6 +483,8 @@ extern void radeon_atom_encoder_init(struct radeon_device *rdev);
 extern void atombios_dig_transmitter_setup(struct drm_encoder *encoder,
 					   int action, uint8_t lane_num,
 					   uint8_t lane_set);
+extern void radeon_atom_ext_encoder_setup_ddc(struct drm_encoder *encoder);
+extern struct drm_encoder *radeon_atom_get_external_encoder(struct drm_encoder *encoder);
 extern int radeon_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
 				u8 write_byte, u8 *read_byte);
 
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 86eda1ea94df..aaa19dc418a0 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -487,6 +487,7 @@ static int radeon_hwmon_init(struct radeon_device *rdev)
 	case THERMAL_TYPE_RV6XX:
 	case THERMAL_TYPE_RV770:
 	case THERMAL_TYPE_EVERGREEN:
+	case THERMAL_TYPE_NI:
 	case THERMAL_TYPE_SUMO:
 		rdev->pm.int_hwmon_dev = hwmon_device_register(rdev->dev);
 		if (IS_ERR(rdev->pm.int_hwmon_dev)) {
diff --git a/drivers/gpu/drm/radeon/reg_srcs/r600 b/drivers/gpu/drm/radeon/reg_srcs/r600
index 92f1900dc7ca..ea49752ee99c 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/r600
+++ b/drivers/gpu/drm/radeon/reg_srcs/r600
@@ -758,6 +758,5 @@ r600 0x9400
 0x00009714 VC_ENHANCE
 0x00009830 DB_DEBUG
 0x00009838 DB_WATERMARKS
-0x00028D28 DB_SRESULTS_COMPARE_STATE0
 0x00028D44 DB_ALPHA_TO_MASK
 0x00009700 VC_CNTL
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index ef8a5babe9f7..6f508ffd1035 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -105,6 +105,9 @@ void rv770_pm_misc(struct radeon_device *rdev)
 	struct radeon_voltage *voltage = &ps->clock_info[req_cm_idx].voltage;
 
 	if ((voltage->type == VOLTAGE_SW) && voltage->voltage) {
+		/* 0xff01 is a flag rather then an actual voltage */
+		if (voltage->voltage == 0xff01)
+			return;
 		if (voltage->voltage != rdev->pm.current_vddc) {
 			radeon_atom_set_voltage(rdev, voltage->voltage, SET_VOLTAGE_TYPE_ASIC_VDDC);
 			rdev->pm.current_vddc = voltage->voltage;
diff --git a/drivers/gpu/drm/savage/savage_bci.c b/drivers/gpu/drm/savage/savage_bci.c
index bf5f83ea14fe..cb1ee4e0050a 100644
--- a/drivers/gpu/drm/savage/savage_bci.c
+++ b/drivers/gpu/drm/savage/savage_bci.c
@@ -647,9 +647,6 @@ int savage_driver_firstopen(struct drm_device *dev)
 	ret = drm_addmap(dev, aperture_base, SAVAGE_APERTURE_SIZE,
 			 _DRM_FRAME_BUFFER, _DRM_WRITE_COMBINING,
 			 &dev_priv->aperture);
-	if (ret)
-		return ret;
-
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 90e23e0bfadb..58c271ebc0f7 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -31,6 +31,7 @@
 #include <linux/sched.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
+#include <linux/shmem_fs.h>
 #include <linux/file.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
@@ -484,7 +485,7 @@ static int ttm_tt_swapin(struct ttm_tt *ttm)
 	swap_space = swap_storage->f_path.dentry->d_inode->i_mapping;
 
 	for (i = 0; i < ttm->num_pages; ++i) {
-		from_page = read_mapping_page(swap_space, i, NULL);
+		from_page = shmem_read_mapping_page(swap_space, i);
 		if (IS_ERR(from_page)) {
 			ret = PTR_ERR(from_page);
 			goto out_err;
@@ -557,7 +558,7 @@ int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage)
 		from_page = ttm->pages[i];
 		if (unlikely(from_page == NULL))
 			continue;
-		to_page = read_mapping_page(swap_space, i, NULL);
+		to_page = shmem_read_mapping_page(swap_space, i);
 		if (unlikely(IS_ERR(to_page))) {
 			ret = PTR_ERR(to_page);
 			goto out_err;
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 67d2a7585934..36ca465c00ce 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -305,6 +305,7 @@ config HID_MULTITOUCH
 	  - 3M PCT touch screens
 	  - ActionStar dual touch panels
 	  - Cando dual touch panels
+	  - Chunghwa panels
 	  - CVTouch panels
 	  - Cypress TrueTouch panels
 	  - Elo TouchSystems IntelliTouch Plus panels
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index c957c4b4fe70..6f3289a57888 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1359,6 +1359,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_CYMOTION_SOLAR) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_TACTICAL_PAD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_WIRELESS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CHUNGHWAT, USB_DEVICE_ID_CHUNGHWAT_MULTITOUCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CREATIVELABS, USB_DEVICE_ID_PRODIKEYS_PCMIDI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CVTOUCH, USB_DEVICE_ID_CVTOUCH_SCREEN) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_1) },
@@ -1422,6 +1423,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_SPACETRAVELLER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_SPACENAVIGATOR) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LUMIO, USB_DEVICE_ID_CRYSTALTOUCH) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LUMIO, USB_DEVICE_ID_CRYSTALTOUCH_DUAL) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICOLCD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICOLCD_BOOTLOADER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_SIDEWINDER_GV) },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 0b374a6d6db0..a756ee6c7df5 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -173,6 +173,9 @@
 #define USB_DEVICE_ID_CHICONY_MULTI_TOUCH	0xb19d
 #define USB_DEVICE_ID_CHICONY_WIRELESS	0x0618
 
+#define USB_VENDOR_ID_CHUNGHWAT		0x2247
+#define USB_DEVICE_ID_CHUNGHWAT_MULTITOUCH	0x0001
+
 #define USB_VENDOR_ID_CIDC		0x1677
 
 #define USB_VENDOR_ID_CMEDIA		0x0d8c
@@ -446,6 +449,7 @@
 
 #define USB_VENDOR_ID_LUMIO		0x202e
 #define USB_DEVICE_ID_CRYSTALTOUCH	0x0006
+#define USB_DEVICE_ID_CRYSTALTOUCH_DUAL	0x0007
 
 #define USB_VENDOR_ID_MCC		0x09db
 #define USB_DEVICE_ID_MCC_PMD1024LS	0x0076
@@ -622,6 +626,7 @@
 #define USB_VENDOR_ID_UCLOGIC		0x5543
 #define USB_DEVICE_ID_UCLOGIC_TABLET_PF1209	0x0042
 #define USB_DEVICE_ID_UCLOGIC_TABLET_KNA5	0x6001
+#define USB_DEVICE_ID_UCLOGIC_TABLET_TWA60	0x0064
 #define USB_DEVICE_ID_UCLOGIC_TABLET_WP4030U	0x0003
 #define USB_DEVICE_ID_UCLOGIC_TABLET_WP5540U	0x0004
 #define USB_DEVICE_ID_UCLOGIC_TABLET_WP8060U	0x0005
diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index a5eda4c8127a..0ec91c18a421 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -501,17 +501,9 @@ static int magicmouse_probe(struct hid_device *hdev,
 	}
 	report->size = 6;
 
-	/*
-	 * The device reponds with 'invalid report id' when feature
-	 * report switching it into multitouch mode is sent to it.
-	 *
-	 * This results in -EIO from the _raw low-level transport callback,
-	 * but there seems to be no other way of switching the mode.
-	 * Thus the super-ugly hacky success check below.
-	 */
 	ret = hdev->hid_output_raw_report(hdev, feature, sizeof(feature),
 			HID_FEATURE_REPORT);
-	if (ret != -EIO) {
+	if (ret != sizeof(feature)) {
 		hid_err(hdev, "unable to request touch data (%d)\n", ret);
 		goto err_stop_hw;
 	}
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index ecd4d2db9e80..62cac4dc3b62 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -64,6 +64,7 @@ struct mt_device {
 	struct mt_class *mtclass;	/* our mt device class */
 	unsigned last_field_index;	/* last field index of the report */
 	unsigned last_slot_field;	/* the last field of a slot */
+	int last_mt_collection;	/* last known mt-related collection */
 	__s8 inputmode;		/* InputMode HID feature, -1 if non-existent */
 	__u8 num_received;	/* how many contacts we received */
 	__u8 num_expected;	/* expected last contact index */
@@ -225,8 +226,10 @@ static int mt_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 				cls->sn_move);
 			/* touchscreen emulation */
 			set_abs(hi->input, ABS_X, field, cls->sn_move);
-			td->last_slot_field = usage->hid;
-			td->last_field_index = field->index;
+			if (td->last_mt_collection == usage->collection_index) {
+				td->last_slot_field = usage->hid;
+				td->last_field_index = field->index;
+			}
 			return 1;
 		case HID_GD_Y:
 			if (quirks & MT_QUIRK_EGALAX_XYZ_FIXUP)
@@ -237,8 +240,10 @@ static int mt_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 				cls->sn_move);
 			/* touchscreen emulation */
 			set_abs(hi->input, ABS_Y, field, cls->sn_move);
-			td->last_slot_field = usage->hid;
-			td->last_field_index = field->index;
+			if (td->last_mt_collection == usage->collection_index) {
+				td->last_slot_field = usage->hid;
+				td->last_field_index = field->index;
+			}
 			return 1;
 		}
 		return 0;
@@ -246,31 +251,42 @@ static int mt_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 	case HID_UP_DIGITIZER:
 		switch (usage->hid) {
 		case HID_DG_INRANGE:
-			td->last_slot_field = usage->hid;
-			td->last_field_index = field->index;
+			if (td->last_mt_collection == usage->collection_index) {
+				td->last_slot_field = usage->hid;
+				td->last_field_index = field->index;
+			}
 			return 1;
 		case HID_DG_CONFIDENCE:
-			td->last_slot_field = usage->hid;
-			td->last_field_index = field->index;
+			if (td->last_mt_collection == usage->collection_index) {
+				td->last_slot_field = usage->hid;
+				td->last_field_index = field->index;
+			}
 			return 1;
 		case HID_DG_TIPSWITCH:
 			hid_map_usage(hi, usage, bit, max, EV_KEY, BTN_TOUCH);
 			input_set_capability(hi->input, EV_KEY, BTN_TOUCH);
-			td->last_slot_field = usage->hid;
-			td->last_field_index = field->index;
+			if (td->last_mt_collection == usage->collection_index) {
+				td->last_slot_field = usage->hid;
+				td->last_field_index = field->index;
+			}
 			return 1;
 		case HID_DG_CONTACTID:
+			if (!td->maxcontacts)
+				td->maxcontacts = MT_DEFAULT_MAXCONTACT;
 			input_mt_init_slots(hi->input, td->maxcontacts);
 			td->last_slot_field = usage->hid;
 			td->last_field_index = field->index;
+			td->last_mt_collection = usage->collection_index;
 			return 1;
 		case HID_DG_WIDTH:
 			hid_map_usage(hi, usage, bit, max,
 					EV_ABS, ABS_MT_TOUCH_MAJOR);
 			set_abs(hi->input, ABS_MT_TOUCH_MAJOR, field,
 				cls->sn_width);
-			td->last_slot_field = usage->hid;
-			td->last_field_index = field->index;
+			if (td->last_mt_collection == usage->collection_index) {
+				td->last_slot_field = usage->hid;
+				td->last_field_index = field->index;
+			}
 			return 1;
 		case HID_DG_HEIGHT:
 			hid_map_usage(hi, usage, bit, max,
@@ -279,8 +295,10 @@ static int mt_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 				cls->sn_height);
 			input_set_abs_params(hi->input,
 					ABS_MT_ORIENTATION, 0, 1, 0, 0);
-			td->last_slot_field = usage->hid;
-			td->last_field_index = field->index;
+			if (td->last_mt_collection == usage->collection_index) {
+				td->last_slot_field = usage->hid;
+				td->last_field_index = field->index;
+			}
 			return 1;
 		case HID_DG_TIPPRESSURE:
 			if (quirks & MT_QUIRK_EGALAX_XYZ_FIXUP)
@@ -292,16 +310,20 @@ static int mt_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 			/* touchscreen emulation */
 			set_abs(hi->input, ABS_PRESSURE, field,
 				cls->sn_pressure);
-			td->last_slot_field = usage->hid;
-			td->last_field_index = field->index;
+			if (td->last_mt_collection == usage->collection_index) {
+				td->last_slot_field = usage->hid;
+				td->last_field_index = field->index;
+			}
 			return 1;
 		case HID_DG_CONTACTCOUNT:
-			td->last_field_index = field->index;
+			if (td->last_mt_collection == usage->collection_index)
+				td->last_field_index = field->index;
 			return 1;
 		case HID_DG_CONTACTMAX:
 			/* we don't set td->last_slot_field as contactcount and
 			 * contact max are global to the report */
-			td->last_field_index = field->index;
+			if (td->last_mt_collection == usage->collection_index)
+				td->last_field_index = field->index;
 			return -1;
 		}
 		/* let hid-input decide for the others */
@@ -516,6 +538,7 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	}
 	td->mtclass = mtclass;
 	td->inputmode = -1;
+	td->last_mt_collection = -1;
 	hid_set_drvdata(hdev, td);
 
 	ret = hid_parse(hdev);
@@ -526,9 +549,6 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	if (ret)
 		goto fail;
 
-	if (!td->maxcontacts)
-		td->maxcontacts = MT_DEFAULT_MAXCONTACT;
-
 	td->slots = kzalloc(td->maxcontacts * sizeof(struct mt_slot),
 				GFP_KERNEL);
 	if (!td->slots) {
@@ -593,6 +613,11 @@ static const struct hid_device_id mt_devices[] = {
 		HID_USB_DEVICE(USB_VENDOR_ID_CANDO,
 			USB_DEVICE_ID_CANDO_MULTI_TOUCH_15_6) },
 
+	/* Chunghwa Telecom touch panels */
+	{  .driver_data = MT_CLS_DEFAULT,
+		HID_USB_DEVICE(USB_VENDOR_ID_CHUNGHWAT,
+			USB_DEVICE_ID_CHUNGHWAT_MULTITOUCH) },
+
 	/* CVTouch panels */
 	{ .driver_data = MT_CLS_DEFAULT,
 		HID_USB_DEVICE(USB_VENDOR_ID_CVTOUCH,
@@ -651,6 +676,9 @@ static const struct hid_device_id mt_devices[] = {
 	{ .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE,
 		HID_USB_DEVICE(USB_VENDOR_ID_LUMIO,
 			USB_DEVICE_ID_CRYSTALTOUCH) },
+	{ .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE,
+		HID_USB_DEVICE(USB_VENDOR_ID_LUMIO,
+			USB_DEVICE_ID_CRYSTALTOUCH_DUAL) },
 
 	/* MosArt panels */
 	{ .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE,
@@ -681,10 +709,10 @@ static const struct hid_device_id mt_devices[] = {
 		HID_USB_DEVICE(USB_VENDOR_ID_STANTUM,
 			USB_DEVICE_ID_MTP)},
 	{ .driver_data = MT_CLS_CONFIDENCE,
-		HID_USB_DEVICE(USB_VENDOR_ID_STANTUM,
+		HID_USB_DEVICE(USB_VENDOR_ID_STANTUM_STM,
 			USB_DEVICE_ID_MTP_STM)},
 	{ .driver_data = MT_CLS_CONFIDENCE,
-		HID_USB_DEVICE(USB_VENDOR_ID_STANTUM,
+		HID_USB_DEVICE(USB_VENDOR_ID_STANTUM_SITRONIX,
 			USB_DEVICE_ID_MTP_SITRONIX)},
 
 	/* Touch International panels */
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 0e30b140edca..621959d5cc42 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -74,6 +74,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_PF1209, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_WP4030U, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_KNA5, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_TWA60, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_WP5540U, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_WP8060U, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_MEDIA_TABLET_10_6_INCH, HID_QUIRK_MULTI_INPUT },
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index ff3c644888b1..7c1188b53c3e 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -248,12 +248,15 @@ static int hiddev_release(struct inode * inode, struct file * file)
 			usbhid_close(list->hiddev->hid);
 			usbhid_put_power(list->hiddev->hid);
 		} else {
+			mutex_unlock(&list->hiddev->existancelock);
 			kfree(list->hiddev);
+			kfree(list);
+			return 0;
 		}
 	}
 
-	kfree(list);
 	mutex_unlock(&list->hiddev->existancelock);
+	kfree(list);
 
 	return 0;
 }
@@ -923,10 +926,11 @@ void hiddev_disconnect(struct hid_device *hid)
 	usb_deregister_dev(usbhid->intf, &hiddev_class);
 
 	if (hiddev->open) {
+		mutex_unlock(&hiddev->existancelock);
 		usbhid_close(hiddev->hid);
 		wake_up_interruptible(&hiddev->wait);
 	} else {
+		mutex_unlock(&hiddev->existancelock);
 		kfree(hiddev);
 	}
-	mutex_unlock(&hiddev->existancelock);
 }
diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c
index b5e892017e0c..dcb78a7a8047 100644
--- a/drivers/hwmon/asus_atk0110.c
+++ b/drivers/hwmon/asus_atk0110.c
@@ -268,6 +268,7 @@ static struct device_attribute atk_name_attr =
 static void atk_init_attribute(struct device_attribute *attr, char *name,
 		sysfs_show_func show)
 {
+	sysfs_attr_init(&attr->attr);
 	attr->attr.name = name;
 	attr->attr.mode = 0444;
 	attr->show = show;
@@ -1188,19 +1189,15 @@ static int atk_create_files(struct atk_data *data)
 	int err;
 
 	list_for_each_entry(s, &data->sensor_list, list) {
-		sysfs_attr_init(&s->input_attr.attr);
 		err = device_create_file(data->hwmon_dev, &s->input_attr);
 		if (err)
 			return err;
-		sysfs_attr_init(&s->label_attr.attr);
 		err = device_create_file(data->hwmon_dev, &s->label_attr);
 		if (err)
 			return err;
-		sysfs_attr_init(&s->limit1_attr.attr);
 		err = device_create_file(data->hwmon_dev, &s->limit1_attr);
 		if (err)
 			return err;
-		sysfs_attr_init(&s->limit2_attr.attr);
 		err = device_create_file(data->hwmon_dev, &s->limit2_attr);
 		if (err)
 			return err;
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 9577c432e77f..0070d5476dd0 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -97,9 +97,7 @@ struct platform_data {
 struct pdev_entry {
 	struct list_head list;
 	struct platform_device *pdev;
-	unsigned int cpu;
 	u16 phys_proc_id;
-	u16 cpu_core_id;
 };
 
 static LIST_HEAD(pdev_list);
@@ -296,7 +294,7 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 		 * If the TjMax is not plausible, an assumption
 		 * will be used
 		 */
-		if (val > 80 && val < 120) {
+		if (val) {
 			dev_info(dev, "TjMax is %d C.\n", val);
 			return val * 1000;
 		}
@@ -304,24 +302,9 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 
 	/*
 	 * An assumption is made for early CPUs and unreadable MSR.
-	 * NOTE: the given value may not be correct.
+	 * NOTE: the calculated value may not be correct.
 	 */
-
-	switch (c->x86_model) {
-	case 0xe:
-	case 0xf:
-	case 0x16:
-	case 0x1a:
-		dev_warn(dev, "TjMax is assumed as 100 C!\n");
-		return 100000;
-	case 0x17:
-	case 0x1c:		/* Atom CPUs */
-		return adjust_tjmax(c, id, dev);
-	default:
-		dev_warn(dev, "CPU (model=0x%x) is not supported yet,"
-			" using default TjMax of 100C.\n", c->x86_model);
-		return 100000;
-	}
+	return adjust_tjmax(c, id, dev);
 }
 
 static void __devinit get_ucode_rev_on_cpu(void *edx)
@@ -341,7 +324,7 @@ static int get_pkg_tjmax(unsigned int cpu, struct device *dev)
 	err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
 	if (!err) {
 		val = (eax >> 16) & 0xff;
-		if (val > 80 && val < 120)
+		if (val)
 			return val * 1000;
 	}
 	dev_warn(dev, "Unable to read Pkg-TjMax from CPU:%u\n", cpu);
@@ -350,6 +333,7 @@ static int get_pkg_tjmax(unsigned int cpu, struct device *dev)
 
 static int create_name_attr(struct platform_data *pdata, struct device *dev)
 {
+	sysfs_attr_init(&pdata->name_attr.attr);
 	pdata->name_attr.attr.name = "name";
 	pdata->name_attr.attr.mode = S_IRUGO;
 	pdata->name_attr.show = show_name;
@@ -372,6 +356,7 @@ static int create_core_attrs(struct temp_data *tdata, struct device *dev,
 	for (i = 0; i < MAX_ATTRS; i++) {
 		snprintf(tdata->attr_name[i], CORETEMP_NAME_LENGTH, names[i],
 			attr_no);
+		sysfs_attr_init(&tdata->sd_attrs[i].dev_attr.attr);
 		tdata->sd_attrs[i].dev_attr.attr.name = tdata->attr_name[i];
 		tdata->sd_attrs[i].dev_attr.attr.mode = S_IRUGO;
 		tdata->sd_attrs[i].dev_attr.show = rd_ptr[i];
@@ -422,7 +407,7 @@ static void update_ttarget(__u8 cpu_model, struct temp_data *tdata,
 	}
 }
 
-static int chk_ucode_version(struct platform_device *pdev)
+static int __devinit chk_ucode_version(struct platform_device *pdev)
 {
 	struct cpuinfo_x86 *c = &cpu_data(pdev->id);
 	int err;
@@ -509,8 +494,8 @@ static int create_core_data(struct platform_data *pdata,
 	/*
 	 * Provide a single set of attributes for all HT siblings of a core
 	 * to avoid duplicate sensors (the processor ID and core ID of all
-	 * HT siblings of a core is the same).
-	 * Skip if a HT sibling of this core is already online.
+	 * HT siblings of a core are the same).
+	 * Skip if a HT sibling of this core is already registered.
 	 * This is not an error.
 	 */
 	if (pdata->core_data[attr_no] != NULL)
@@ -666,9 +651,7 @@ static int __cpuinit coretemp_device_add(unsigned int cpu)
 	}
 
 	pdev_entry->pdev = pdev;
-	pdev_entry->cpu = cpu;
 	pdev_entry->phys_proc_id = TO_PHYS_ID(cpu);
-	pdev_entry->cpu_core_id = TO_CORE_ID(cpu);
 
 	list_add_tail(&pdev_entry->list, &pdev_list);
 	mutex_unlock(&pdev_list_mutex);
@@ -770,10 +753,10 @@ static void __cpuinit put_core_offline(unsigned int cpu)
 		coretemp_remove_core(pdata, &pdev->dev, indx);
 
 	/*
-	 * If a core is taken offline, but a HT sibling of the same core is
-	 * still online, register the alternate sibling. This ensures that
-	 * exactly one set of attributes is provided as long as at least one
-	 * HT sibling of a core is online.
+	 * If a HT sibling of a core is taken offline, but another HT sibling
+	 * of the same core is still online, register the alternate sibling.
+	 * This ensures that exactly one set of attributes is provided as long
+	 * as at least one HT sibling of a core is online.
 	 */
 	for_each_sibling(i, cpu) {
 		if (i != cpu) {
diff --git a/drivers/hwmon/ibmaem.c b/drivers/hwmon/ibmaem.c
index 537409d07ee7..1a409c5bc9bc 100644
--- a/drivers/hwmon/ibmaem.c
+++ b/drivers/hwmon/ibmaem.c
@@ -947,6 +947,7 @@ static int aem_register_sensors(struct aem_data *data,
 
 	/* Set up read-only sensors */
 	while (ro->label) {
+		sysfs_attr_init(&sensors->dev_attr.attr);
 		sensors->dev_attr.attr.name = ro->label;
 		sensors->dev_attr.attr.mode = S_IRUGO;
 		sensors->dev_attr.show = ro->show;
@@ -963,6 +964,7 @@ static int aem_register_sensors(struct aem_data *data,
 
 	/* Set up read-write sensors */
 	while (rw->label) {
+		sysfs_attr_init(&sensors->dev_attr.attr);
 		sensors->dev_attr.attr.name = rw->label;
 		sensors->dev_attr.attr.mode = S_IRUGO | S_IWUSR;
 		sensors->dev_attr.show = rw->show;
diff --git a/drivers/hwmon/ibmpex.c b/drivers/hwmon/ibmpex.c
index 06d4eafcf76b..41dbf8161ed7 100644
--- a/drivers/hwmon/ibmpex.c
+++ b/drivers/hwmon/ibmpex.c
@@ -358,6 +358,7 @@ static int create_sensor(struct ibmpex_bmc_data *data, int type,
 	else if (type == POWER_SENSOR)
 		sprintf(n, power_sensor_name_templates[func], "power", counter);
 
+	sysfs_attr_init(&data->sensors[sensor].attr[func].dev_attr.attr);
 	data->sensors[sensor].attr[func].dev_attr.attr.name = n;
 	data->sensors[sensor].attr[func].dev_attr.attr.mode = S_IRUGO;
 	data->sensors[sensor].attr[func].dev_attr.show = ibmpex_show_sensor;
diff --git a/drivers/hwmon/max6642.c b/drivers/hwmon/max6642.c
index 0f9fc40379cd..e855d3b0bd1f 100644
--- a/drivers/hwmon/max6642.c
+++ b/drivers/hwmon/max6642.c
@@ -136,15 +136,29 @@ static int max6642_detect(struct i2c_client *client,
 	if (man_id != 0x4D)
 		return -ENODEV;
 
+	/* sanity check */
+	if (i2c_smbus_read_byte_data(client, 0x04) != 0x4D
+	    || i2c_smbus_read_byte_data(client, 0x06) != 0x4D
+	    || i2c_smbus_read_byte_data(client, 0xff) != 0x4D)
+		return -ENODEV;
+
 	/*
 	 * We read the config and status register, the 4 lower bits in the
 	 * config register should be zero and bit 5, 3, 1 and 0 should be
 	 * zero in the status register.
 	 */
 	reg_config = i2c_smbus_read_byte_data(client, MAX6642_REG_R_CONFIG);
+	if ((reg_config & 0x0f) != 0x00)
+		return -ENODEV;
+
+	/* in between, another round of sanity checks */
+	if (i2c_smbus_read_byte_data(client, 0x04) != reg_config
+	    || i2c_smbus_read_byte_data(client, 0x06) != reg_config
+	    || i2c_smbus_read_byte_data(client, 0xff) != reg_config)
+		return -ENODEV;
+
 	reg_status = i2c_smbus_read_byte_data(client, MAX6642_REG_R_STATUS);
-	if (((reg_config & 0x0f) != 0x00) ||
-	    ((reg_status & 0x2b) != 0x00))
+	if ((reg_status & 0x2b) != 0x00)
 		return -ENODEV;
 
 	strlcpy(info->type, "max6642", I2C_NAME_SIZE);
@@ -246,7 +260,7 @@ static SENSOR_DEVICE_ATTR_2(temp1_max, S_IWUSR | S_IRUGO, show_temp_max,
 			    set_temp_max, 0, MAX6642_REG_W_LOCAL_HIGH);
 static SENSOR_DEVICE_ATTR_2(temp2_max, S_IWUSR | S_IRUGO, show_temp_max,
 			    set_temp_max, 1, MAX6642_REG_W_REMOTE_HIGH);
-static SENSOR_DEVICE_ATTR(temp_fault, S_IRUGO, show_alarm, NULL, 2);
+static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 2);
 static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, show_alarm, NULL, 6);
 static SENSOR_DEVICE_ATTR(temp2_max_alarm, S_IRUGO, show_alarm, NULL, 4);
 
@@ -256,7 +270,7 @@ static struct attribute *max6642_attributes[] = {
 	&sensor_dev_attr_temp1_max.dev_attr.attr,
 	&sensor_dev_attr_temp2_max.dev_attr.attr,
 
-	&sensor_dev_attr_temp_fault.dev_attr.attr,
+	&sensor_dev_attr_temp2_fault.dev_attr.attr,
 	&sensor_dev_attr_temp1_max_alarm.dev_attr.attr,
 	&sensor_dev_attr_temp2_max_alarm.dev_attr.attr,
 	NULL
diff --git a/drivers/hwmon/pmbus_core.c b/drivers/hwmon/pmbus_core.c
index 98799bab69ce..354770ed3186 100644
--- a/drivers/hwmon/pmbus_core.c
+++ b/drivers/hwmon/pmbus_core.c
@@ -707,6 +707,7 @@ do {									\
 	struct sensor_device_attribute *a				\
 	    = &data->_type##s[data->num_##_type##s].attribute;		\
 	BUG_ON(data->num_attributes >= data->max_attributes);		\
+	sysfs_attr_init(&a->dev_attr.attr);				\
 	a->dev_attr.attr.name = _name;					\
 	a->dev_attr.attr.mode = _mode;					\
 	a->dev_attr.show = _show;					\
diff --git a/drivers/hwmon/s3c-hwmon.c b/drivers/hwmon/s3c-hwmon.c
index 92b42db43bcf..b39f52e2752a 100644
--- a/drivers/hwmon/s3c-hwmon.c
+++ b/drivers/hwmon/s3c-hwmon.c
@@ -232,6 +232,7 @@ static int s3c_hwmon_create_attr(struct device *dev,
 
 	attr = &attrs->in;
 	attr->index = channel;
+	sysfs_attr_init(&attr->dev_attr.attr);
 	attr->dev_attr.attr.name  = attrs->in_name;
 	attr->dev_attr.attr.mode  = S_IRUGO;
 	attr->dev_attr.show = s3c_hwmon_ch_show;
@@ -249,6 +250,7 @@ static int s3c_hwmon_create_attr(struct device *dev,
 
 		attr = &attrs->label;
 		attr->index = channel;
+		sysfs_attr_init(&attr->dev_attr.attr);
 		attr->dev_attr.attr.name  = attrs->label_name;
 		attr->dev_attr.attr.mode  = S_IRUGO;
 		attr->dev_attr.show = s3c_hwmon_label_show;
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 6e5123b1d341..04b09564bfa9 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -778,7 +778,8 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq,
 					sector_t block)
 {
 	struct ide_cmd cmd;
-	int uptodate = 0, nsectors;
+	int uptodate = 0;
+	unsigned int nsectors;
 
 	ide_debug_log(IDE_DBG_RQ, "cmd: 0x%x, block: %llu",
 				  rq->cmd[0], (unsigned long long)block);
@@ -1782,7 +1783,6 @@ static int ide_cd_probe(ide_drive_t *drive)
 	ide_cd_read_toc(drive, &sense);
 	g->fops = &idecd_ops;
 	g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-	g->events = DISK_EVENT_MEDIA_CHANGE;
 	add_disk(g);
 	return 0;
 
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index f660cd04ec2f..31fb44085c9b 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1463,9 +1463,9 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 	struct c4iw_qp_attributes attrs;
 	int disconnect = 1;
 	int release = 0;
-	int abort = 0;
 	struct tid_info *t = dev->rdev.lldi.tids;
 	unsigned int tid = GET_TID(hdr);
+	int ret;
 
 	ep = lookup_tid(t, tid);
 	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
@@ -1501,10 +1501,12 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 		start_ep_timer(ep);
 		__state_set(&ep->com, CLOSING);
 		attrs.next_state = C4IW_QP_STATE_CLOSING;
-		abort = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
+		ret = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
 				       C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
-		peer_close_upcall(ep);
-		disconnect = 1;
+		if (ret != -ECONNRESET) {
+			peer_close_upcall(ep);
+			disconnect = 1;
+		}
 		break;
 	case ABORTING:
 		disconnect = 0;
@@ -2109,15 +2111,16 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp)
 		break;
 	}
 
-	mutex_unlock(&ep->com.mutex);
 	if (close) {
-		if (abrupt)
-			ret = abort_connection(ep, NULL, gfp);
-		else
+		if (abrupt) {
+			close_complete_upcall(ep);
+			ret = send_abort(ep, NULL, gfp);
+		} else
 			ret = send_halfclose(ep, gfp);
 		if (ret)
 			fatal = 1;
 	}
+	mutex_unlock(&ep->com.mutex);
 	if (fatal)
 		release_ep_resources(ep);
 	return ret;
@@ -2301,6 +2304,31 @@ static int fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb)
 	return 0;
 }
 
+static int peer_abort_intr(struct c4iw_dev *dev, struct sk_buff *skb)
+{
+	struct cpl_abort_req_rss *req = cplhdr(skb);
+	struct c4iw_ep *ep;
+	struct tid_info *t = dev->rdev.lldi.tids;
+	unsigned int tid = GET_TID(req);
+
+	ep = lookup_tid(t, tid);
+	if (is_neg_adv_abort(req->status)) {
+		PDBG("%s neg_adv_abort ep %p tid %u\n", __func__, ep,
+		     ep->hwtid);
+		kfree_skb(skb);
+		return 0;
+	}
+	PDBG("%s ep %p tid %u state %u\n", __func__, ep, ep->hwtid,
+	     ep->com.state);
+
+	/*
+	 * Wake up any threads in rdma_init() or rdma_fini().
+	 */
+	c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET);
+	sched(dev, skb);
+	return 0;
+}
+
 /*
  * Most upcalls from the T4 Core go to sched() to
  * schedule the processing on a work queue.
@@ -2317,7 +2345,7 @@ c4iw_handler_func c4iw_handlers[NUM_CPL_CMDS] = {
 	[CPL_PASS_ESTABLISH] = sched,
 	[CPL_PEER_CLOSE] = sched,
 	[CPL_CLOSE_CON_RPL] = sched,
-	[CPL_ABORT_REQ_RSS] = sched,
+	[CPL_ABORT_REQ_RSS] = peer_abort_intr,
 	[CPL_RDMA_TERMINATE] = sched,
 	[CPL_FW4_ACK] = sched,
 	[CPL_SET_TCB_RPL] = set_tcb_rpl,
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index 8d8f8add6fcd..1720dc790d13 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -801,6 +801,10 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
 	if (ucontext) {
 		memsize = roundup(memsize, PAGE_SIZE);
 		hwentries = memsize / sizeof *chp->cq.queue;
+		while (hwentries > T4_MAX_IQ_SIZE) {
+			memsize -= PAGE_SIZE;
+			hwentries = memsize / sizeof *chp->cq.queue;
+		}
 	}
 	chp->cq.size = hwentries;
 	chp->cq.memsize = memsize;
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 273ffe49525a..0347eed4a167 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -625,7 +625,7 @@ pbl_done:
 	mhp->attr.perms = c4iw_ib_to_tpt_access(acc);
 	mhp->attr.va_fbo = virt;
 	mhp->attr.page_size = shift - 12;
-	mhp->attr.len = (u32) length;
+	mhp->attr.len = length;
 
 	err = register_mem(rhp, php, mhp, shift);
 	if (err)
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 3b773b05a898..a41578e48c7b 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1207,11 +1207,8 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 				c4iw_get_ep(&qhp->ep->com);
 			}
 			ret = rdma_fini(rhp, qhp, ep);
-			if (ret) {
-				if (internal)
-					c4iw_get_ep(&qhp->ep->com);
+			if (ret)
 				goto err;
-			}
 			break;
 		case C4IW_QP_STATE_TERMINATE:
 			set_state(qhp, C4IW_QP_STATE_TERMINATE);
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 9f53e68a096a..8ec5237031a0 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -469,6 +469,8 @@ static u8 ib_rate_to_delay[IB_RATE_120_GBPS + 1] = {
 #define IB_7322_LT_STATE_RECOVERIDLE     0x0f
 #define IB_7322_LT_STATE_CFGENH          0x10
 #define IB_7322_LT_STATE_CFGTEST         0x11
+#define IB_7322_LT_STATE_CFGWAITRMTTEST  0x12
+#define IB_7322_LT_STATE_CFGWAITENH      0x13
 
 /* link state machine states from IBC */
 #define IB_7322_L_STATE_DOWN             0x0
@@ -498,8 +500,10 @@ static const u8 qib_7322_physportstate[0x20] = {
 		IB_PHYSPORTSTATE_LINK_ERR_RECOVER,
 	[IB_7322_LT_STATE_CFGENH] = IB_PHYSPORTSTATE_CFG_ENH,
 	[IB_7322_LT_STATE_CFGTEST] = IB_PHYSPORTSTATE_CFG_TRAIN,
-	[0x12] = IB_PHYSPORTSTATE_CFG_TRAIN,
-	[0x13] = IB_PHYSPORTSTATE_CFG_WAIT_ENH,
+	[IB_7322_LT_STATE_CFGWAITRMTTEST] =
+		IB_PHYSPORTSTATE_CFG_TRAIN,
+	[IB_7322_LT_STATE_CFGWAITENH] =
+		IB_PHYSPORTSTATE_CFG_WAIT_ENH,
 	[0x14] = IB_PHYSPORTSTATE_CFG_TRAIN,
 	[0x15] = IB_PHYSPORTSTATE_CFG_TRAIN,
 	[0x16] = IB_PHYSPORTSTATE_CFG_TRAIN,
@@ -1692,7 +1696,9 @@ static void handle_serdes_issues(struct qib_pportdata *ppd, u64 ibcst)
 		break;
 	}
 
-	if (ibclt == IB_7322_LT_STATE_CFGTEST &&
+	if (((ibclt >= IB_7322_LT_STATE_CFGTEST &&
+	      ibclt <= IB_7322_LT_STATE_CFGWAITENH) ||
+	     ibclt == IB_7322_LT_STATE_LINKUP) &&
 	    (ibcst & SYM_MASK(IBCStatusA_0, LinkSpeedQDR))) {
 		force_h1(ppd);
 		ppd->cpspec->qdr_reforce = 1;
@@ -7301,12 +7307,17 @@ static void ibsd_wr_allchans(struct qib_pportdata *ppd, int addr, unsigned data,
 static void serdes_7322_los_enable(struct qib_pportdata *ppd, int enable)
 {
 	u64 data = qib_read_kreg_port(ppd, krp_serdesctrl);
-	printk(KERN_INFO QIB_DRV_NAME " IB%u:%u Turning LOS %s\n",
-		ppd->dd->unit, ppd->port, (enable ? "on" : "off"));
-	if (enable)
+	u8 state = SYM_FIELD(data, IBSerdesCtrl_0, RXLOSEN);
+
+	if (enable && !state) {
+		printk(KERN_INFO QIB_DRV_NAME " IB%u:%u Turning LOS on\n",
+			ppd->dd->unit, ppd->port);
 		data |= SYM_MASK(IBSerdesCtrl_0, RXLOSEN);
-	else
+	} else if (!enable && state) {
+		printk(KERN_INFO QIB_DRV_NAME " IB%u:%u Turning LOS off\n",
+			ppd->dd->unit, ppd->port);
 		data &= ~SYM_MASK(IBSerdesCtrl_0, RXLOSEN);
+	}
 	qib_write_kreg_port(ppd, krp_serdesctrl, data);
 }
 
diff --git a/drivers/infiniband/hw/qib/qib_intr.c b/drivers/infiniband/hw/qib/qib_intr.c
index a693c56ec8a6..6ae57d23004a 100644
--- a/drivers/infiniband/hw/qib/qib_intr.c
+++ b/drivers/infiniband/hw/qib/qib_intr.c
@@ -96,8 +96,12 @@ void qib_handle_e_ibstatuschanged(struct qib_pportdata *ppd, u64 ibcs)
 	 * states, or if it transitions from any of the up (INIT or better)
 	 * states into any of the down states (except link recovery), then
 	 * call the chip-specific code to take appropriate actions.
+	 *
+	 * ppd->lflags could be 0 if this is the first time the interrupt
+	 * handlers has been called but the link is already up.
 	 */
-	if (lstate >= IB_PORT_INIT && (ppd->lflags & QIBL_LINKDOWN) &&
+	if (lstate >= IB_PORT_INIT &&
+	    (!ppd->lflags || (ppd->lflags & QIBL_LINKDOWN)) &&
 	    ltstate == IB_PHYSPORTSTATE_LINKUP) {
 		/* transitioned to UP */
 		if (dd->f_ib_updown(ppd, 1, ibcs))
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index be0921ef6b52..4cf25347b015 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -111,7 +111,8 @@ static void evdev_event(struct input_handle *handle,
 
 	rcu_read_unlock();
 
-	wake_up_interruptible(&evdev->wait);
+	if (type == EV_SYN && code == SYN_REPORT)
+		wake_up_interruptible(&evdev->wait);
 }
 
 static int evdev_fasync(int fd, struct file *file, int on)
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 75e11c7b70fd..da38d97a51b1 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -1756,7 +1756,7 @@ static unsigned int input_estimate_events_per_packet(struct input_dev *dev)
 	} else if (test_bit(ABS_MT_TRACKING_ID, dev->absbit)) {
 		mt_slots = dev->absinfo[ABS_MT_TRACKING_ID].maximum -
 			   dev->absinfo[ABS_MT_TRACKING_ID].minimum + 1,
-		clamp(mt_slots, 2, 32);
+		mt_slots = clamp(mt_slots, 2, 32);
 	} else if (test_bit(ABS_MT_POSITION_X, dev->absbit)) {
 		mt_slots = 2;
 	} else {
diff --git a/drivers/input/keyboard/omap-keypad.c b/drivers/input/keyboard/omap-keypad.c
index f23a743817db..33d0bdc837c0 100644
--- a/drivers/input/keyboard/omap-keypad.c
+++ b/drivers/input/keyboard/omap-keypad.c
@@ -209,6 +209,7 @@ static void omap_kp_tasklet(unsigned long data)
 #endif
 		}
 	}
+	input_sync(omap_kp_data->input);
 	memcpy(keypad_state, new_state, sizeof(keypad_state));
 
 	if (key_down) {
diff --git a/drivers/input/keyboard/sh_keysc.c b/drivers/input/keyboard/sh_keysc.c
index 834cf98e7efb..6876700a4469 100644
--- a/drivers/input/keyboard/sh_keysc.c
+++ b/drivers/input/keyboard/sh_keysc.c
@@ -32,7 +32,7 @@ static const struct {
 	[SH_KEYSC_MODE_3] = { 2, 4, 7 },
 	[SH_KEYSC_MODE_4] = { 3, 6, 6 },
 	[SH_KEYSC_MODE_5] = { 4, 6, 7 },
-	[SH_KEYSC_MODE_6] = { 5, 7, 7 },
+	[SH_KEYSC_MODE_6] = { 5, 8, 8 },
 };
 
 struct sh_keysc_priv {
diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c
index 257e033986e4..0110b5a3a167 100644
--- a/drivers/input/mousedev.c
+++ b/drivers/input/mousedev.c
@@ -187,7 +187,7 @@ static void mousedev_abs_event(struct input_dev *dev, struct mousedev *mousedev,
 		if (size == 0)
 			size = xres ? : 1;
 
-		clamp(value, min, max);
+		value = clamp(value, min, max);
 
 		mousedev->packet.x = ((value - min) * xres) / size;
 		mousedev->packet.abs_event = 1;
@@ -201,7 +201,7 @@ static void mousedev_abs_event(struct input_dev *dev, struct mousedev *mousedev,
 		if (size == 0)
 			size = yres ? : 1;
 
-		clamp(value, min, max);
+		value = clamp(value, min, max);
 
 		mousedev->packet.y = yres - ((value - min) * yres) / size;
 		mousedev->packet.abs_event = 1;
diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c
index f3698967edf6..8755f5f3ad37 100644
--- a/drivers/input/serio/serport.c
+++ b/drivers/input/serio/serport.c
@@ -120,21 +120,17 @@ static void serport_ldisc_close(struct tty_struct *tty)
  * 'interrupt' routine.
  */
 
-static unsigned int serport_ldisc_receive(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void serport_ldisc_receive(struct tty_struct *tty, const unsigned char *cp, char *fp, int count)
 {
 	struct serport *serport = (struct serport*) tty->disc_data;
 	unsigned long flags;
 	unsigned int ch_flags;
-	int ret = 0;
 	int i;
 
 	spin_lock_irqsave(&serport->lock, flags);
 
-	if (!test_bit(SERPORT_ACTIVE, &serport->flags)) {
-		ret = -EINVAL;
+	if (!test_bit(SERPORT_ACTIVE, &serport->flags))
 		goto out;
-	}
 
 	for (i = 0; i < count; i++) {
 		switch (fp[i]) {
@@ -156,8 +152,6 @@ static unsigned int serport_ldisc_receive(struct tty_struct *tty,
 
 out:
 	spin_unlock_irqrestore(&serport->lock, flags);
-
-	return ret == 0 ? count : ret;
 }
 
 /*
diff --git a/drivers/isdn/gigaset/interface.c b/drivers/isdn/gigaset/interface.c
index 59de638225fe..e35058bcd7b9 100644
--- a/drivers/isdn/gigaset/interface.c
+++ b/drivers/isdn/gigaset/interface.c
@@ -156,8 +156,10 @@ static int if_open(struct tty_struct *tty, struct file *filp)
 	if (!cs || !try_module_get(cs->driver->owner))
 		return -ENODEV;
 
-	if (mutex_lock_interruptible(&cs->mutex))
+	if (mutex_lock_interruptible(&cs->mutex)) {
+		module_put(cs->driver->owner);
 		return -ERESTARTSYS;
+	}
 	tty->driver_data = cs;
 
 	++cs->open_count;
diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c
index 1d44d470897c..86a5c4f7775e 100644
--- a/drivers/isdn/gigaset/ser-gigaset.c
+++ b/drivers/isdn/gigaset/ser-gigaset.c
@@ -674,7 +674,7 @@ gigaset_tty_ioctl(struct tty_struct *tty, struct file *file,
  *	cflags	buffer containing error flags for received characters (ignored)
  *	count	number of received characters
  */
-static unsigned int
+static void
 gigaset_tty_receive(struct tty_struct *tty, const unsigned char *buf,
 		    char *cflags, int count)
 {
@@ -683,12 +683,12 @@ gigaset_tty_receive(struct tty_struct *tty, const unsigned char *buf,
 	struct inbuf_t *inbuf;
 
 	if (!cs)
-		return -ENODEV;
+		return;
 	inbuf = cs->inbuf;
 	if (!inbuf) {
 		dev_err(cs->dev, "%s: no inbuf\n", __func__);
 		cs_put(cs);
-		return -EINVAL;
+		return;
 	}
 
 	tail = inbuf->tail;
@@ -725,8 +725,6 @@ gigaset_tty_receive(struct tty_struct *tty, const unsigned char *buf,
 	gig_dbg(DEBUG_INTR, "%s-->BH", __func__);
 	gigaset_schedule_event(cs);
 	cs_put(cs);
-
-	return count;
 }
 
 /*
diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c
index 3ccbff13eaf2..71a8eb6ef71e 100644
--- a/drivers/isdn/hardware/mISDN/hfcsusb.c
+++ b/drivers/isdn/hardware/mISDN/hfcsusb.c
@@ -283,6 +283,7 @@ hfcsusb_ph_info(struct hfcsusb *hw)
 	_queue_data(&dch->dev.D, MPH_INFORMATION_IND, MISDN_ID_ANY,
 		sizeof(struct ph_info_dch) + dch->dev.nrbchan *
 		sizeof(struct ph_info_ch), phi, GFP_ATOMIC);
+	kfree(phi);
 }
 
 /*
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 23f0d5e99f35..713d43b4e563 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -1,3 +1,10 @@
+config LEDS_GPIO_REGISTER
+	bool
+	help
+	  This option provides the function gpio_led_register_device.
+	  As this function is used by arch code it must not be compiled as a
+	  module.
+
 menuconfig NEW_LEDS
 	bool "LED Support"
 	help
@@ -7,22 +14,14 @@ menuconfig NEW_LEDS
 	  This is not related to standard keyboard LEDs which are controlled
 	  via the input system.
 
+if NEW_LEDS
+
 config LEDS_CLASS
 	bool "LED Class Support"
-	depends on NEW_LEDS
 	help
 	  This option enables the led sysfs class in /sys/class/leds.  You'll
 	  need this to do anything useful with LEDs.  If unsure, say N.
 
-config LEDS_GPIO_REGISTER
-	bool
-	help
-	  This option provides the function gpio_led_register_device.
-	  As this function is used by arch code it must not be compiled as a
-	  module.
-
-if NEW_LEDS
-
 comment "LED drivers"
 
 config LEDS_88PM860X
@@ -391,6 +390,7 @@ config LEDS_NETXBIG
 
 config LEDS_ASIC3
 	bool "LED support for the HTC ASIC3"
+	depends on LEDS_CLASS
 	depends on MFD_ASIC3
 	default y
 	help
diff --git a/drivers/leds/leds-lp5521.c b/drivers/leds/leds-lp5521.c
index c0cff64a1ae6..cc1dc4817fac 100644
--- a/drivers/leds/leds-lp5521.c
+++ b/drivers/leds/leds-lp5521.c
@@ -593,7 +593,7 @@ static void lp5521_unregister_sysfs(struct i2c_client *client)
 				&lp5521_led_attribute_group);
 }
 
-static int __init lp5521_init_led(struct lp5521_led *led,
+static int __devinit lp5521_init_led(struct lp5521_led *led,
 				struct i2c_client *client,
 				int chan, struct lp5521_platform_data *pdata)
 {
@@ -637,7 +637,7 @@ static int __init lp5521_init_led(struct lp5521_led *led,
 	return 0;
 }
 
-static int lp5521_probe(struct i2c_client *client,
+static int __devinit lp5521_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
 	struct lp5521_chip		*chip;
diff --git a/drivers/leds/leds-lp5523.c b/drivers/leds/leds-lp5523.c
index e19fed25f137..5971e309b234 100644
--- a/drivers/leds/leds-lp5523.c
+++ b/drivers/leds/leds-lp5523.c
@@ -826,7 +826,7 @@ static int __init lp5523_init_engine(struct lp5523_engine *engine, int id)
 	return 0;
 }
 
-static int __init lp5523_init_led(struct lp5523_led *led, struct device *dev,
+static int __devinit lp5523_init_led(struct lp5523_led *led, struct device *dev,
 			   int chan, struct lp5523_platform_data *pdata)
 {
 	char name[32];
@@ -872,7 +872,7 @@ static int __init lp5523_init_led(struct lp5523_led *led, struct device *dev,
 
 static struct i2c_driver lp5523_driver;
 
-static int lp5523_probe(struct i2c_client *client,
+static int __devinit lp5523_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
 	struct lp5523_chip		*chip;
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 70bd738b8b99..574b09afedd3 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -534,6 +534,82 @@ void bitmap_print_sb(struct bitmap *bitmap)
 	kunmap_atomic(sb, KM_USER0);
 }
 
+/*
+ * bitmap_new_disk_sb
+ * @bitmap
+ *
+ * This function is somewhat the reverse of bitmap_read_sb.  bitmap_read_sb
+ * reads and verifies the on-disk bitmap superblock and populates bitmap_info.
+ * This function verifies 'bitmap_info' and populates the on-disk bitmap
+ * structure, which is to be written to disk.
+ *
+ * Returns: 0 on success, -Exxx on error
+ */
+static int bitmap_new_disk_sb(struct bitmap *bitmap)
+{
+	bitmap_super_t *sb;
+	unsigned long chunksize, daemon_sleep, write_behind;
+	int err = -EINVAL;
+
+	bitmap->sb_page = alloc_page(GFP_KERNEL);
+	if (IS_ERR(bitmap->sb_page)) {
+		err = PTR_ERR(bitmap->sb_page);
+		bitmap->sb_page = NULL;
+		return err;
+	}
+	bitmap->sb_page->index = 0;
+
+	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
+
+	sb->magic = cpu_to_le32(BITMAP_MAGIC);
+	sb->version = cpu_to_le32(BITMAP_MAJOR_HI);
+
+	chunksize = bitmap->mddev->bitmap_info.chunksize;
+	BUG_ON(!chunksize);
+	if (!is_power_of_2(chunksize)) {
+		kunmap_atomic(sb, KM_USER0);
+		printk(KERN_ERR "bitmap chunksize not a power of 2\n");
+		return -EINVAL;
+	}
+	sb->chunksize = cpu_to_le32(chunksize);
+
+	daemon_sleep = bitmap->mddev->bitmap_info.daemon_sleep;
+	if (!daemon_sleep ||
+	    (daemon_sleep < 1) || (daemon_sleep > MAX_SCHEDULE_TIMEOUT)) {
+		printk(KERN_INFO "Choosing daemon_sleep default (5 sec)\n");
+		daemon_sleep = 5 * HZ;
+	}
+	sb->daemon_sleep = cpu_to_le32(daemon_sleep);
+	bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
+
+	/*
+	 * FIXME: write_behind for RAID1.  If not specified, what
+	 * is a good choice?  We choose COUNTER_MAX / 2 arbitrarily.
+	 */
+	write_behind = bitmap->mddev->bitmap_info.max_write_behind;
+	if (write_behind > COUNTER_MAX)
+		write_behind = COUNTER_MAX / 2;
+	sb->write_behind = cpu_to_le32(write_behind);
+	bitmap->mddev->bitmap_info.max_write_behind = write_behind;
+
+	/* keep the array size field of the bitmap superblock up to date */
+	sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);
+
+	memcpy(sb->uuid, bitmap->mddev->uuid, 16);
+
+	bitmap->flags |= BITMAP_STALE;
+	sb->state |= cpu_to_le32(BITMAP_STALE);
+	bitmap->events_cleared = bitmap->mddev->events;
+	sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
+
+	bitmap->flags |= BITMAP_HOSTENDIAN;
+	sb->version = cpu_to_le32(BITMAP_MAJOR_HOSTENDIAN);
+
+	kunmap_atomic(sb, KM_USER0);
+
+	return 0;
+}
+
 /* read the superblock from the bitmap file and initialize some bitmap fields */
 static int bitmap_read_sb(struct bitmap *bitmap)
 {
@@ -575,7 +651,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 		reason = "unrecognized superblock version";
 	else if (chunksize < 512)
 		reason = "bitmap chunksize too small";
-	else if ((1 << ffz(~chunksize)) != chunksize)
+	else if (!is_power_of_2(chunksize))
 		reason = "bitmap chunksize not a power of 2";
 	else if (daemon_sleep < 1 || daemon_sleep > MAX_SCHEDULE_TIMEOUT)
 		reason = "daemon sleep period out of range";
@@ -1076,8 +1152,8 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 	}
 
 	printk(KERN_INFO "%s: bitmap initialized from disk: "
-		"read %lu/%lu pages, set %lu bits\n",
-		bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt);
+	       "read %lu/%lu pages, set %lu of %lu bits\n",
+	       bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt, chunks);
 
 	return 0;
 
@@ -1332,7 +1408,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
 			return 0;
 		}
 
-		if (unlikely((*bmc & COUNTER_MAX) == COUNTER_MAX)) {
+		if (unlikely(COUNTER(*bmc) == COUNTER_MAX)) {
 			DEFINE_WAIT(__wait);
 			/* note that it is safe to do the prepare_to_wait
 			 * after the test as long as we do it before dropping
@@ -1404,10 +1480,10 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
 			sysfs_notify_dirent_safe(bitmap->sysfs_can_clear);
 		}
 
-		if (!success && ! (*bmc & NEEDED_MASK))
+		if (!success && !NEEDED(*bmc))
 			*bmc |= NEEDED_MASK;
 
-		if ((*bmc & COUNTER_MAX) == COUNTER_MAX)
+		if (COUNTER(*bmc) == COUNTER_MAX)
 			wake_up(&bitmap->overflow_wait);
 
 		(*bmc)--;
@@ -1728,9 +1804,16 @@ int bitmap_create(mddev_t *mddev)
 		vfs_fsync(file, 1);
 	}
 	/* read superblock from bitmap file (this sets mddev->bitmap_info.chunksize) */
-	if (!mddev->bitmap_info.external)
-		err = bitmap_read_sb(bitmap);
-	else {
+	if (!mddev->bitmap_info.external) {
+		/*
+		 * If 'MD_ARRAY_FIRST_USE' is set, then device-mapper is
+		 * instructing us to create a new on-disk bitmap instance.
+		 */
+		if (test_and_clear_bit(MD_ARRAY_FIRST_USE, &mddev->flags))
+			err = bitmap_new_disk_sb(bitmap);
+		else
+			err = bitmap_read_sb(bitmap);
+	} else {
 		err = 0;
 		if (mddev->bitmap_info.chunksize == 0 ||
 		    mddev->bitmap_info.daemon_sleep == 0)
@@ -1754,9 +1837,6 @@ int bitmap_create(mddev_t *mddev)
 	bitmap->chunks = chunks;
 	bitmap->pages = pages;
 	bitmap->missing_pages = pages;
-	bitmap->counter_bits = COUNTER_BITS;
-
-	bitmap->syncchunk = ~0UL;
 
 #ifdef INJECT_FATAL_FAULT_1
 	bitmap->bp = NULL;
diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
index d0aeaf46d932..b2a127e891ac 100644
--- a/drivers/md/bitmap.h
+++ b/drivers/md/bitmap.h
@@ -85,7 +85,6 @@
 typedef __u16 bitmap_counter_t;
 #define COUNTER_BITS 16
 #define COUNTER_BIT_SHIFT 4
-#define COUNTER_BYTE_RATIO (COUNTER_BITS / 8)
 #define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3)
 
 #define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1)))
@@ -196,19 +195,10 @@ struct bitmap {
 
 	mddev_t *mddev; /* the md device that the bitmap is for */
 
-	int counter_bits; /* how many bits per block counter */
-
 	/* bitmap chunksize -- how much data does each bit represent? */
 	unsigned long chunkshift; /* chunksize = 2^chunkshift (for bitops) */
 	unsigned long chunks; /* total number of data chunks for the array */
 
-	/* We hold a count on the chunk currently being synced, and drop
-	 * it when the last block is started.  If the resync is aborted
-	 * midway, we need to be able to drop that count, so we remember
-	 * the counted chunk..
-	 */
-	unsigned long syncchunk;
-
 	__u64	events_cleared;
 	int need_sync;
 
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 76a5af00a26b..2067288f61f9 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -19,6 +19,8 @@
 #define DM_MSG_PREFIX "io"
 
 #define DM_IO_MAX_REGIONS	BITS_PER_LONG
+#define MIN_IOS		16
+#define MIN_BIOS	16
 
 struct dm_io_client {
 	mempool_t *pool;
@@ -41,33 +43,21 @@ struct io {
 static struct kmem_cache *_dm_io_cache;
 
 /*
- * io contexts are only dynamically allocated for asynchronous
- * io.  Since async io is likely to be the majority of io we'll
- * have the same number of io contexts as bios! (FIXME: must reduce this).
- */
-
-static unsigned int pages_to_ios(unsigned int pages)
-{
-	return 4 * pages;	/* too many ? */
-}
-
-/*
  * Create a client with mempool and bioset.
  */
-struct dm_io_client *dm_io_client_create(unsigned num_pages)
+struct dm_io_client *dm_io_client_create(void)
 {
-	unsigned ios = pages_to_ios(num_pages);
 	struct dm_io_client *client;
 
 	client = kmalloc(sizeof(*client), GFP_KERNEL);
 	if (!client)
 		return ERR_PTR(-ENOMEM);
 
-	client->pool = mempool_create_slab_pool(ios, _dm_io_cache);
+	client->pool = mempool_create_slab_pool(MIN_IOS, _dm_io_cache);
 	if (!client->pool)
 		goto bad;
 
-	client->bios = bioset_create(16, 0);
+	client->bios = bioset_create(MIN_BIOS, 0);
 	if (!client->bios)
 		goto bad;
 
@@ -81,13 +71,6 @@ struct dm_io_client *dm_io_client_create(unsigned num_pages)
 }
 EXPORT_SYMBOL(dm_io_client_create);
 
-int dm_io_client_resize(unsigned num_pages, struct dm_io_client *client)
-{
-	return mempool_resize(client->pool, pages_to_ios(num_pages),
-			      GFP_KERNEL);
-}
-EXPORT_SYMBOL(dm_io_client_resize);
-
 void dm_io_client_destroy(struct dm_io_client *client)
 {
 	mempool_destroy(client->pool);
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 1bb73a13ca40..819e37eaaeba 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -27,15 +27,19 @@
 
 #include "dm.h"
 
+#define SUB_JOB_SIZE	128
+#define SPLIT_COUNT	8
+#define MIN_JOBS	8
+#define RESERVE_PAGES	(DIV_ROUND_UP(SUB_JOB_SIZE << SECTOR_SHIFT, PAGE_SIZE))
+
 /*-----------------------------------------------------------------
  * Each kcopyd client has its own little pool of preallocated
  * pages for kcopyd io.
  *---------------------------------------------------------------*/
 struct dm_kcopyd_client {
-	spinlock_t lock;
 	struct page_list *pages;
-	unsigned int nr_pages;
-	unsigned int nr_free_pages;
+	unsigned nr_reserved_pages;
+	unsigned nr_free_pages;
 
 	struct dm_io_client *io_client;
 
@@ -67,15 +71,18 @@ static void wake(struct dm_kcopyd_client *kc)
 	queue_work(kc->kcopyd_wq, &kc->kcopyd_work);
 }
 
-static struct page_list *alloc_pl(void)
+/*
+ * Obtain one page for the use of kcopyd.
+ */
+static struct page_list *alloc_pl(gfp_t gfp)
 {
 	struct page_list *pl;
 
-	pl = kmalloc(sizeof(*pl), GFP_KERNEL);
+	pl = kmalloc(sizeof(*pl), gfp);
 	if (!pl)
 		return NULL;
 
-	pl->page = alloc_page(GFP_KERNEL);
+	pl->page = alloc_page(gfp);
 	if (!pl->page) {
 		kfree(pl);
 		return NULL;
@@ -90,41 +97,56 @@ static void free_pl(struct page_list *pl)
 	kfree(pl);
 }
 
-static int kcopyd_get_pages(struct dm_kcopyd_client *kc,
-			    unsigned int nr, struct page_list **pages)
+/*
+ * Add the provided pages to a client's free page list, releasing
+ * back to the system any beyond the reserved_pages limit.
+ */
+static void kcopyd_put_pages(struct dm_kcopyd_client *kc, struct page_list *pl)
 {
-	struct page_list *pl;
-
-	spin_lock(&kc->lock);
-	if (kc->nr_free_pages < nr) {
-		spin_unlock(&kc->lock);
-		return -ENOMEM;
-	}
-
-	kc->nr_free_pages -= nr;
-	for (*pages = pl = kc->pages; --nr; pl = pl->next)
-		;
+	struct page_list *next;
 
-	kc->pages = pl->next;
-	pl->next = NULL;
+	do {
+		next = pl->next;
 
-	spin_unlock(&kc->lock);
+		if (kc->nr_free_pages >= kc->nr_reserved_pages)
+			free_pl(pl);
+		else {
+			pl->next = kc->pages;
+			kc->pages = pl;
+			kc->nr_free_pages++;
+		}
 
-	return 0;
+		pl = next;
+	} while (pl);
 }
 
-static void kcopyd_put_pages(struct dm_kcopyd_client *kc, struct page_list *pl)
+static int kcopyd_get_pages(struct dm_kcopyd_client *kc,
+			    unsigned int nr, struct page_list **pages)
 {
-	struct page_list *cursor;
+	struct page_list *pl;
+
+	*pages = NULL;
+
+	do {
+		pl = alloc_pl(__GFP_NOWARN | __GFP_NORETRY);
+		if (unlikely(!pl)) {
+			/* Use reserved pages */
+			pl = kc->pages;
+			if (unlikely(!pl))
+				goto out_of_memory;
+			kc->pages = pl->next;
+			kc->nr_free_pages--;
+		}
+		pl->next = *pages;
+		*pages = pl;
+	} while (--nr);
 
-	spin_lock(&kc->lock);
-	for (cursor = pl; cursor->next; cursor = cursor->next)
-		kc->nr_free_pages++;
+	return 0;
 
-	kc->nr_free_pages++;
-	cursor->next = kc->pages;
-	kc->pages = pl;
-	spin_unlock(&kc->lock);
+out_of_memory:
+	if (*pages)
+		kcopyd_put_pages(kc, *pages);
+	return -ENOMEM;
 }
 
 /*
@@ -141,13 +163,16 @@ static void drop_pages(struct page_list *pl)
 	}
 }
 
-static int client_alloc_pages(struct dm_kcopyd_client *kc, unsigned int nr)
+/*
+ * Allocate and reserve nr_pages for the use of a specific client.
+ */
+static int client_reserve_pages(struct dm_kcopyd_client *kc, unsigned nr_pages)
 {
-	unsigned int i;
+	unsigned i;
 	struct page_list *pl = NULL, *next;
 
-	for (i = 0; i < nr; i++) {
-		next = alloc_pl();
+	for (i = 0; i < nr_pages; i++) {
+		next = alloc_pl(GFP_KERNEL);
 		if (!next) {
 			if (pl)
 				drop_pages(pl);
@@ -157,17 +182,18 @@ static int client_alloc_pages(struct dm_kcopyd_client *kc, unsigned int nr)
 		pl = next;
 	}
 
+	kc->nr_reserved_pages += nr_pages;
 	kcopyd_put_pages(kc, pl);
-	kc->nr_pages += nr;
+
 	return 0;
 }
 
 static void client_free_pages(struct dm_kcopyd_client *kc)
 {
-	BUG_ON(kc->nr_free_pages != kc->nr_pages);
+	BUG_ON(kc->nr_free_pages != kc->nr_reserved_pages);
 	drop_pages(kc->pages);
 	kc->pages = NULL;
-	kc->nr_free_pages = kc->nr_pages = 0;
+	kc->nr_free_pages = kc->nr_reserved_pages = 0;
 }
 
 /*-----------------------------------------------------------------
@@ -216,16 +242,17 @@ struct kcopyd_job {
 	struct mutex lock;
 	atomic_t sub_jobs;
 	sector_t progress;
-};
 
-/* FIXME: this should scale with the number of pages */
-#define MIN_JOBS 512
+	struct kcopyd_job *master_job;
+};
 
 static struct kmem_cache *_job_cache;
 
 int __init dm_kcopyd_init(void)
 {
-	_job_cache = KMEM_CACHE(kcopyd_job, 0);
+	_job_cache = kmem_cache_create("kcopyd_job",
+				sizeof(struct kcopyd_job) * (SPLIT_COUNT + 1),
+				__alignof__(struct kcopyd_job), 0, NULL);
 	if (!_job_cache)
 		return -ENOMEM;
 
@@ -299,7 +326,12 @@ static int run_complete_job(struct kcopyd_job *job)
 
 	if (job->pages)
 		kcopyd_put_pages(kc, job->pages);
-	mempool_free(job, kc->job_pool);
+	/*
+	 * If this is the master job, the sub jobs have already
+	 * completed so we can free everything.
+	 */
+	if (job->master_job == job)
+		mempool_free(job, kc->job_pool);
 	fn(read_err, write_err, context);
 
 	if (atomic_dec_and_test(&kc->nr_jobs))
@@ -460,14 +492,14 @@ static void dispatch_job(struct kcopyd_job *job)
 	wake(kc);
 }
 
-#define SUB_JOB_SIZE 128
 static void segment_complete(int read_err, unsigned long write_err,
 			     void *context)
 {
 	/* FIXME: tidy this function */
 	sector_t progress = 0;
 	sector_t count = 0;
-	struct kcopyd_job *job = (struct kcopyd_job *) context;
+	struct kcopyd_job *sub_job = (struct kcopyd_job *) context;
+	struct kcopyd_job *job = sub_job->master_job;
 	struct dm_kcopyd_client *kc = job->kc;
 
 	mutex_lock(&job->lock);
@@ -498,8 +530,6 @@ static void segment_complete(int read_err, unsigned long write_err,
 
 	if (count) {
 		int i;
-		struct kcopyd_job *sub_job = mempool_alloc(kc->job_pool,
-							   GFP_NOIO);
 
 		*sub_job = *job;
 		sub_job->source.sector += progress;
@@ -511,7 +541,7 @@ static void segment_complete(int read_err, unsigned long write_err,
 		}
 
 		sub_job->fn = segment_complete;
-		sub_job->context = job;
+		sub_job->context = sub_job;
 		dispatch_job(sub_job);
 
 	} else if (atomic_dec_and_test(&job->sub_jobs)) {
@@ -531,19 +561,19 @@ static void segment_complete(int read_err, unsigned long write_err,
 }
 
 /*
- * Create some little jobs that will do the move between
- * them.
+ * Create some sub jobs to share the work between them.
  */
-#define SPLIT_COUNT 8
-static void split_job(struct kcopyd_job *job)
+static void split_job(struct kcopyd_job *master_job)
 {
 	int i;
 
-	atomic_inc(&job->kc->nr_jobs);
+	atomic_inc(&master_job->kc->nr_jobs);
 
-	atomic_set(&job->sub_jobs, SPLIT_COUNT);
-	for (i = 0; i < SPLIT_COUNT; i++)
-		segment_complete(0, 0u, job);
+	atomic_set(&master_job->sub_jobs, SPLIT_COUNT);
+	for (i = 0; i < SPLIT_COUNT; i++) {
+		master_job[i + 1].master_job = master_job;
+		segment_complete(0, 0u, &master_job[i + 1]);
+	}
 }
 
 int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
@@ -553,7 +583,8 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
 	struct kcopyd_job *job;
 
 	/*
-	 * Allocate a new job.
+	 * Allocate an array of jobs consisting of one master job
+	 * followed by SPLIT_COUNT sub jobs.
 	 */
 	job = mempool_alloc(kc->job_pool, GFP_NOIO);
 
@@ -577,10 +608,10 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
 
 	job->fn = fn;
 	job->context = context;
+	job->master_job = job;
 
-	if (job->source.count < SUB_JOB_SIZE)
+	if (job->source.count <= SUB_JOB_SIZE)
 		dispatch_job(job);
-
 	else {
 		mutex_init(&job->lock);
 		job->progress = 0;
@@ -606,17 +637,15 @@ int kcopyd_cancel(struct kcopyd_job *job, int block)
 /*-----------------------------------------------------------------
  * Client setup
  *---------------------------------------------------------------*/
-int dm_kcopyd_client_create(unsigned int nr_pages,
-			    struct dm_kcopyd_client **result)
+struct dm_kcopyd_client *dm_kcopyd_client_create(void)
 {
 	int r = -ENOMEM;
 	struct dm_kcopyd_client *kc;
 
 	kc = kmalloc(sizeof(*kc), GFP_KERNEL);
 	if (!kc)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
-	spin_lock_init(&kc->lock);
 	spin_lock_init(&kc->job_lock);
 	INIT_LIST_HEAD(&kc->complete_jobs);
 	INIT_LIST_HEAD(&kc->io_jobs);
@@ -633,12 +662,12 @@ int dm_kcopyd_client_create(unsigned int nr_pages,
 		goto bad_workqueue;
 
 	kc->pages = NULL;
-	kc->nr_pages = kc->nr_free_pages = 0;
-	r = client_alloc_pages(kc, nr_pages);
+	kc->nr_reserved_pages = kc->nr_free_pages = 0;
+	r = client_reserve_pages(kc, RESERVE_PAGES);
 	if (r)
 		goto bad_client_pages;
 
-	kc->io_client = dm_io_client_create(nr_pages);
+	kc->io_client = dm_io_client_create();
 	if (IS_ERR(kc->io_client)) {
 		r = PTR_ERR(kc->io_client);
 		goto bad_io_client;
@@ -647,8 +676,7 @@ int dm_kcopyd_client_create(unsigned int nr_pages,
 	init_waitqueue_head(&kc->destroyq);
 	atomic_set(&kc->nr_jobs, 0);
 
-	*result = kc;
-	return 0;
+	return kc;
 
 bad_io_client:
 	client_free_pages(kc);
@@ -659,7 +687,7 @@ bad_workqueue:
 bad_slab:
 	kfree(kc);
 
-	return r;
+	return ERR_PTR(r);
 }
 EXPORT_SYMBOL(dm_kcopyd_client_create);
 
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index a1f321889676..948e3f4925bf 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -449,8 +449,7 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 
 		lc->io_req.mem.type = DM_IO_VMA;
 		lc->io_req.notify.fn = NULL;
-		lc->io_req.client = dm_io_client_create(dm_div_up(buf_size,
-								   PAGE_SIZE));
+		lc->io_req.client = dm_io_client_create();
 		if (IS_ERR(lc->io_req.client)) {
 			r = PTR_ERR(lc->io_req.client);
 			DMWARN("couldn't allocate disk io client");
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index a550a057d991..aa4e570c2cb5 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1290,7 +1290,7 @@ static int do_end_io(struct multipath *m, struct request *clone,
 	if (!error && !clone->errors)
 		return 0;	/* I/O complete */
 
-	if (error == -EOPNOTSUPP || error == -EREMOTEIO)
+	if (error == -EOPNOTSUPP || error == -EREMOTEIO || error == -EILSEQ)
 		return error;
 
 	if (mpio->pgpath)
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 976ad4688afc..9bfd057be686 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -22,8 +22,6 @@
 #define DM_MSG_PREFIX "raid1"
 
 #define MAX_RECOVERY 1	/* Maximum number of regions recovered in parallel. */
-#define DM_IO_PAGES 64
-#define DM_KCOPYD_PAGES 64
 
 #define DM_RAID1_HANDLE_ERRORS 0x01
 #define errors_handled(p)	((p)->features & DM_RAID1_HANDLE_ERRORS)
@@ -887,7 +885,7 @@ static struct mirror_set *alloc_context(unsigned int nr_mirrors,
 		return NULL;
 	}
 
-	ms->io_client = dm_io_client_create(DM_IO_PAGES);
+	ms->io_client = dm_io_client_create();
 	if (IS_ERR(ms->io_client)) {
 		ti->error = "Error creating dm_io client";
 		mempool_destroy(ms->read_record_pool);
@@ -1117,9 +1115,11 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto err_destroy_wq;
 	}
 
-	r = dm_kcopyd_client_create(DM_KCOPYD_PAGES, &ms->kcopyd_client);
-	if (r)
+	ms->kcopyd_client = dm_kcopyd_client_create();
+	if (IS_ERR(ms->kcopyd_client)) {
+		r = PTR_ERR(ms->kcopyd_client);
 		goto err_destroy_wq;
+	}
 
 	wakeup_mirrord(ms);
 	return 0;
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 95891dfcbca0..135c2f1fdbfc 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -154,11 +154,6 @@ struct pstore {
 	struct workqueue_struct *metadata_wq;
 };
 
-static unsigned sectors_to_pages(unsigned sectors)
-{
-	return DIV_ROUND_UP(sectors, PAGE_SIZE >> 9);
-}
-
 static int alloc_area(struct pstore *ps)
 {
 	int r = -ENOMEM;
@@ -318,8 +313,7 @@ static int read_header(struct pstore *ps, int *new_snapshot)
 		chunk_size_supplied = 0;
 	}
 
-	ps->io_client = dm_io_client_create(sectors_to_pages(ps->store->
-							     chunk_size));
+	ps->io_client = dm_io_client_create();
 	if (IS_ERR(ps->io_client))
 		return PTR_ERR(ps->io_client);
 
@@ -368,11 +362,6 @@ static int read_header(struct pstore *ps, int *new_snapshot)
 		return r;
 	}
 
-	r = dm_io_client_resize(sectors_to_pages(ps->store->chunk_size),
-				ps->io_client);
-	if (r)
-		return r;
-
 	r = alloc_area(ps);
 	return r;
 
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index a2d330942cb2..9ecff5f3023a 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -40,11 +40,6 @@ static const char dm_snapshot_merge_target_name[] = "snapshot-merge";
 #define SNAPSHOT_COPY_PRIORITY 2
 
 /*
- * Reserve 1MB for each snapshot initially (with minimum of 1 page).
- */
-#define SNAPSHOT_PAGES (((1UL << 20) >> PAGE_SHIFT) ? : 1)
-
-/*
  * The size of the mempool used to track chunks in use.
  */
 #define MIN_IOS 256
@@ -1116,8 +1111,9 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad_hash_tables;
 	}
 
-	r = dm_kcopyd_client_create(SNAPSHOT_PAGES, &s->kcopyd_client);
-	if (r) {
+	s->kcopyd_client = dm_kcopyd_client_create();
+	if (IS_ERR(s->kcopyd_client)) {
+		r = PTR_ERR(s->kcopyd_client);
 		ti->error = "Could not create kcopyd client";
 		goto bad_kcopyd;
 	}
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index cb8380c9767f..451c3bb176d2 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -362,6 +362,7 @@ static void close_dev(struct dm_dev_internal *d, struct mapped_device *md)
 static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
 				  sector_t start, sector_t len, void *data)
 {
+	struct request_queue *q;
 	struct queue_limits *limits = data;
 	struct block_device *bdev = dev->bdev;
 	sector_t dev_size =
@@ -370,6 +371,22 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
 		limits->logical_block_size >> SECTOR_SHIFT;
 	char b[BDEVNAME_SIZE];
 
+	/*
+	 * Some devices exist without request functions,
+	 * such as loop devices not yet bound to backing files.
+	 * Forbid the use of such devices.
+	 */
+	q = bdev_get_queue(bdev);
+	if (!q || !q->make_request_fn) {
+		DMWARN("%s: %s is not yet initialised: "
+		       "start=%llu, len=%llu, dev_size=%llu",
+		       dm_device_name(ti->table->md), bdevname(bdev, b),
+		       (unsigned long long)start,
+		       (unsigned long long)len,
+		       (unsigned long long)dev_size);
+		return 1;
+	}
+
 	if (!dev_size)
 		return 0;
 
@@ -1346,7 +1363,8 @@ bool dm_table_supports_discards(struct dm_table *t)
 		return 0;
 
 	/*
-	 * Ensure that at least one underlying device supports discards.
+	 * Unless any target used by the table set discards_supported,
+	 * require at least one underlying device to support discards.
 	 * t->devices includes internal dm devices such as mirror logs
 	 * so we need to use iterate_devices here, which targets
 	 * supporting discard must provide.
@@ -1354,6 +1372,9 @@ bool dm_table_supports_discards(struct dm_table *t)
 	while (i < dm_table_get_num_targets(t)) {
 		ti = dm_table_get_target(t, i++);
 
+		if (ti->discards_supported)
+			return 1;
+
 		if (ti->type->iterate_devices &&
 		    ti->type->iterate_devices(ti, device_discard_capable, NULL))
 			return 1;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index aa640a85bb21..4332fc2f25d4 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -351,6 +351,9 @@ void mddev_resume(mddev_t *mddev)
 	mddev->suspended = 0;
 	wake_up(&mddev->sb_wait);
 	mddev->pers->quiesce(mddev, 0);
+
+	md_wakeup_thread(mddev->thread);
+	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 }
 EXPORT_SYMBOL_GPL(mddev_resume);
 
@@ -1750,6 +1753,18 @@ static struct super_type super_types[] = {
 	},
 };
 
+static void sync_super(mddev_t *mddev, mdk_rdev_t *rdev)
+{
+	if (mddev->sync_super) {
+		mddev->sync_super(mddev, rdev);
+		return;
+	}
+
+	BUG_ON(mddev->major_version >= ARRAY_SIZE(super_types));
+
+	super_types[mddev->major_version].sync_super(mddev, rdev);
+}
+
 static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2)
 {
 	mdk_rdev_t *rdev, *rdev2;
@@ -1781,8 +1796,8 @@ int md_integrity_register(mddev_t *mddev)
 
 	if (list_empty(&mddev->disks))
 		return 0; /* nothing to do */
-	if (blk_get_integrity(mddev->gendisk))
-		return 0; /* already registered */
+	if (!mddev->gendisk || blk_get_integrity(mddev->gendisk))
+		return 0; /* shouldn't register, or already is */
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
 		/* skip spares and non-functional disks */
 		if (test_bit(Faulty, &rdev->flags))
@@ -2168,8 +2183,7 @@ static void sync_sbs(mddev_t * mddev, int nospares)
 			/* Don't update this superblock */
 			rdev->sb_loaded = 2;
 		} else {
-			super_types[mddev->major_version].
-				sync_super(mddev, rdev);
+			sync_super(mddev, rdev);
 			rdev->sb_loaded = 1;
 		}
 	}
@@ -2462,7 +2476,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 		if (rdev->raid_disk == -1)
 			return -EEXIST;
 		/* personality does all needed checks */
-		if (rdev->mddev->pers->hot_add_disk == NULL)
+		if (rdev->mddev->pers->hot_remove_disk == NULL)
 			return -EINVAL;
 		err = rdev->mddev->pers->
 			hot_remove_disk(rdev->mddev, rdev->raid_disk);
@@ -4619,9 +4633,6 @@ int md_run(mddev_t *mddev)
 	if (mddev->flags)
 		md_update_sb(mddev, 0);
 
-	md_wakeup_thread(mddev->thread);
-	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
-
 	md_new_event(mddev);
 	sysfs_notify_dirent_safe(mddev->sysfs_state);
 	sysfs_notify_dirent_safe(mddev->sysfs_action);
@@ -4642,6 +4653,10 @@ static int do_md_run(mddev_t *mddev)
 		bitmap_destroy(mddev);
 		goto out;
 	}
+
+	md_wakeup_thread(mddev->thread);
+	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
+
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	revalidate_disk(mddev->gendisk);
 	mddev->changed = 1;
@@ -5259,6 +5274,8 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
 		if (mddev->degraded)
 			set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+		if (!err)
+			md_new_event(mddev);
 		md_wakeup_thread(mddev->thread);
 		return err;
 	}
@@ -6866,8 +6883,8 @@ void md_do_sync(mddev_t *mddev)
 	 * Tune reconstruction:
 	 */
 	window = 32*(PAGE_SIZE/512);
-	printk(KERN_INFO "md: using %dk window, over a total of %llu blocks.\n",
-		window/2,(unsigned long long) max_sectors/2);
+	printk(KERN_INFO "md: using %dk window, over a total of %lluk.\n",
+		window/2, (unsigned long long)max_sectors/2);
 
 	atomic_set(&mddev->recovery_active, 0);
 	last_check = 0;
@@ -7045,7 +7062,6 @@ void md_do_sync(mddev_t *mddev)
 }
 EXPORT_SYMBOL_GPL(md_do_sync);
 
-
 static int remove_and_add_spares(mddev_t *mddev)
 {
 	mdk_rdev_t *rdev;
@@ -7157,6 +7173,9 @@ static void reap_sync_thread(mddev_t *mddev)
  */
 void md_check_recovery(mddev_t *mddev)
 {
+	if (mddev->suspended)
+		return;
+
 	if (mddev->bitmap)
 		bitmap_daemon_work(mddev);
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 0b1fd3f1d85b..1c26c7a08ae6 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -124,6 +124,7 @@ struct mddev_s
 #define MD_CHANGE_DEVS	0	/* Some device status has changed */
 #define MD_CHANGE_CLEAN 1	/* transition to or from 'clean' */
 #define MD_CHANGE_PENDING 2	/* switch from 'clean' to 'active' in progress */
+#define MD_ARRAY_FIRST_USE 3    /* First use of array, needs initialization */
 
 	int				suspended;
 	atomic_t			active_io;
@@ -330,6 +331,7 @@ struct mddev_s
 	atomic_t flush_pending;
 	struct work_struct flush_work;
 	struct work_struct event_work;	/* used by dm to report failure event */
+	void (*sync_super)(mddev_t *mddev, mdk_rdev_t *rdev);
 };
 
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 5d096096f958..f7431b6d8447 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -497,21 +497,19 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
 	return best_disk;
 }
 
-static int raid1_congested(void *data, int bits)
+int md_raid1_congested(mddev_t *mddev, int bits)
 {
-	mddev_t *mddev = data;
 	conf_t *conf = mddev->private;
 	int i, ret = 0;
 
-	if (mddev_congested(mddev, bits))
-		return 1;
-
 	rcu_read_lock();
 	for (i = 0; i < mddev->raid_disks; i++) {
 		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
 		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			struct request_queue *q = bdev_get_queue(rdev->bdev);
 
+			BUG_ON(!q);
+
 			/* Note the '|| 1' - when read_balance prefers
 			 * non-congested targets, it can be removed
 			 */
@@ -524,7 +522,15 @@ static int raid1_congested(void *data, int bits)
 	rcu_read_unlock();
 	return ret;
 }
+EXPORT_SYMBOL_GPL(md_raid1_congested);
 
+static int raid1_congested(void *data, int bits)
+{
+	mddev_t *mddev = data;
+
+	return mddev_congested(mddev, bits) ||
+		md_raid1_congested(mddev, bits);
+}
 
 static void flush_pending_writes(conf_t *conf)
 {
@@ -1972,6 +1978,8 @@ static int run(mddev_t *mddev)
 		return PTR_ERR(conf);
 
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
+		if (!mddev->gendisk)
+			continue;
 		disk_stack_limits(mddev->gendisk, rdev->bdev,
 				  rdev->data_offset << 9);
 		/* as we don't honour merge_bvec_fn, we must never risk
@@ -2013,8 +2021,10 @@ static int run(mddev_t *mddev)
 
 	md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
 
-	mddev->queue->backing_dev_info.congested_fn = raid1_congested;
-	mddev->queue->backing_dev_info.congested_data = mddev;
+	if (mddev->queue) {
+		mddev->queue->backing_dev_info.congested_fn = raid1_congested;
+		mddev->queue->backing_dev_info.congested_data = mddev;
+	}
 	return md_integrity_register(mddev);
 }
 
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 5fc4ca1af863..e743a64fac4f 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -126,4 +126,6 @@ struct r1bio_s {
  */
 #define	R1BIO_Returned 6
 
+extern int md_raid1_congested(mddev_t *mddev, int bits);
+
 #endif
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 346e69bfdab3..b72edf35ec54 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -129,7 +129,7 @@ static inline int raid5_dec_bi_hw_segments(struct bio *bio)
 
 static inline void raid5_set_bi_hw_segments(struct bio *bio, unsigned int cnt)
 {
-	bio->bi_phys_segments = raid5_bi_phys_segments(bio) || (cnt << 16);
+	bio->bi_phys_segments = raid5_bi_phys_segments(bio) | (cnt << 16);
 }
 
 /* Find first data disk in a raid6 stripe */
@@ -514,7 +514,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 		bi = &sh->dev[i].req;
 
 		bi->bi_rw = rw;
-		if (rw == WRITE)
+		if (rw & WRITE)
 			bi->bi_end_io = raid5_end_write_request;
 		else
 			bi->bi_end_io = raid5_end_read_request;
@@ -548,13 +548,13 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			bi->bi_io_vec[0].bv_offset = 0;
 			bi->bi_size = STRIPE_SIZE;
 			bi->bi_next = NULL;
-			if (rw == WRITE &&
+			if ((rw & WRITE) &&
 			    test_bit(R5_ReWrite, &sh->dev[i].flags))
 				atomic_add(STRIPE_SECTORS,
 					&rdev->corrected_errors);
 			generic_make_request(bi);
 		} else {
-			if (rw == WRITE)
+			if (rw & WRITE)
 				set_bit(STRIPE_DEGRADED, &sh->state);
 			pr_debug("skip op %ld on disc %d for sector %llu\n",
 				bi->bi_rw, i, (unsigned long long)sh->sector);
@@ -585,7 +585,7 @@ async_copy_data(int frombio, struct bio *bio, struct page *page,
 	init_async_submit(&submit, flags, tx, NULL, NULL, NULL);
 
 	bio_for_each_segment(bvl, bio, i) {
-		int len = bio_iovec_idx(bio, i)->bv_len;
+		int len = bvl->bv_len;
 		int clen;
 		int b_offset = 0;
 
@@ -601,8 +601,8 @@ async_copy_data(int frombio, struct bio *bio, struct page *page,
 			clen = len;
 
 		if (clen > 0) {
-			b_offset += bio_iovec_idx(bio, i)->bv_offset;
-			bio_page = bio_iovec_idx(bio, i)->bv_page;
+			b_offset += bvl->bv_offset;
+			bio_page = bvl->bv_page;
 			if (frombio)
 				tx = async_memcpy(page, bio_page, page_offset,
 						  b_offset, clen, &submit);
@@ -4858,7 +4858,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 			printk(KERN_INFO "md/raid:%s: device %s operational as raid"
 			       " disk %d\n",
 			       mdname(mddev), bdevname(rdev->bdev, b), raid_disk);
-		} else
+		} else if (rdev->saved_raid_disk != raid_disk)
 			/* Cannot rely on bitmap to complete recovery */
 			conf->fullsync = 1;
 	}
diff --git a/drivers/media/dvb/dm1105/dm1105.c b/drivers/media/dvb/dm1105/dm1105.c
index 2d8b4044be36..b2b0c45f32a9 100644
--- a/drivers/media/dvb/dm1105/dm1105.c
+++ b/drivers/media/dvb/dm1105/dm1105.c
@@ -20,6 +20,7 @@
  */
 
 #include <linux/i2c.h>
+#include <linux/i2c-algo-bit.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -49,11 +50,12 @@
 
 #define UNSET (-1U)
 
-#define DM1105_BOARD_NOAUTO		UNSET
-#define DM1105_BOARD_UNKNOWN		0
-#define DM1105_BOARD_DVBWORLD_2002	1
-#define DM1105_BOARD_DVBWORLD_2004	2
-#define DM1105_BOARD_AXESS_DM05		3
+#define DM1105_BOARD_NOAUTO			UNSET
+#define DM1105_BOARD_UNKNOWN			0
+#define DM1105_BOARD_DVBWORLD_2002		1
+#define DM1105_BOARD_DVBWORLD_2004		2
+#define DM1105_BOARD_AXESS_DM05			3
+#define DM1105_BOARD_UNBRANDED_I2C_ON_GPIO	4
 
 /* ----------------------------------------------- */
 /*
@@ -157,22 +159,38 @@
 #define DM1105_MAX				0x04
 
 #define DRIVER_NAME				"dm1105"
+#define DM1105_I2C_GPIO_NAME			"dm1105-gpio"
 
 #define DM1105_DMA_PACKETS			47
 #define DM1105_DMA_PACKET_LENGTH		(128*4)
 #define DM1105_DMA_BYTES			(128 * 4 * DM1105_DMA_PACKETS)
 
+/*  */
+#define GPIO08					(1 << 8)
+#define GPIO13					(1 << 13)
+#define GPIO14					(1 << 14)
+#define GPIO15					(1 << 15)
+#define GPIO16					(1 << 16)
+#define GPIO17					(1 << 17)
+#define GPIO_ALL				0x03ffff
+
 /* GPIO's for LNB power control */
-#define DM1105_LNB_MASK				0x00000000
-#define DM1105_LNB_OFF				0x00020000
-#define DM1105_LNB_13V				0x00010100
-#define DM1105_LNB_18V				0x00000100
+#define DM1105_LNB_MASK				(GPIO_ALL & ~(GPIO14 | GPIO13))
+#define DM1105_LNB_OFF				GPIO17
+#define DM1105_LNB_13V				(GPIO16 | GPIO08)
+#define DM1105_LNB_18V				GPIO08
 
 /* GPIO's for LNB power control for Axess DM05 */
-#define DM05_LNB_MASK				0x00000000
-#define DM05_LNB_OFF				0x00020000/* actually 13v */
-#define DM05_LNB_13V				0x00020000
-#define DM05_LNB_18V				0x00030000
+#define DM05_LNB_MASK				(GPIO_ALL & ~(GPIO14 | GPIO13))
+#define DM05_LNB_OFF				GPIO17/* actually 13v */
+#define DM05_LNB_13V				GPIO17
+#define DM05_LNB_18V				(GPIO17 | GPIO16)
+
+/* GPIO's for LNB power control for unbranded with I2C on GPIO */
+#define UNBR_LNB_MASK				(GPIO17 | GPIO16)
+#define UNBR_LNB_OFF				0
+#define UNBR_LNB_13V				GPIO17
+#define UNBR_LNB_18V				(GPIO17 | GPIO16)
 
 static unsigned int card[]  = {[0 ... 3] = UNSET };
 module_param_array(card,  int, NULL, 0444);
@@ -187,7 +205,11 @@ static unsigned int dm1105_devcount;
 DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
 struct dm1105_board {
-	char                    *name;
+	char	*name;
+	struct	{
+		u32	mask, off, v13, v18;
+	} lnb;
+	u32	gpio_scl, gpio_sda;
 };
 
 struct dm1105_subid {
@@ -199,15 +221,50 @@ struct dm1105_subid {
 static const struct dm1105_board dm1105_boards[] = {
 	[DM1105_BOARD_UNKNOWN] = {
 		.name		= "UNKNOWN/GENERIC",
+		.lnb = {
+			.mask = DM1105_LNB_MASK,
+			.off = DM1105_LNB_OFF,
+			.v13 = DM1105_LNB_13V,
+			.v18 = DM1105_LNB_18V,
+		},
 	},
 	[DM1105_BOARD_DVBWORLD_2002] = {
 		.name		= "DVBWorld PCI 2002",
+		.lnb = {
+			.mask = DM1105_LNB_MASK,
+			.off = DM1105_LNB_OFF,
+			.v13 = DM1105_LNB_13V,
+			.v18 = DM1105_LNB_18V,
+		},
 	},
 	[DM1105_BOARD_DVBWORLD_2004] = {
 		.name		= "DVBWorld PCI 2004",
+		.lnb = {
+			.mask = DM1105_LNB_MASK,
+			.off = DM1105_LNB_OFF,
+			.v13 = DM1105_LNB_13V,
+			.v18 = DM1105_LNB_18V,
+		},
 	},
 	[DM1105_BOARD_AXESS_DM05] = {
 		.name		= "Axess/EasyTv DM05",
+		.lnb = {
+			.mask = DM05_LNB_MASK,
+			.off = DM05_LNB_OFF,
+			.v13 = DM05_LNB_13V,
+			.v18 = DM05_LNB_18V,
+		},
+	},
+	[DM1105_BOARD_UNBRANDED_I2C_ON_GPIO] = {
+		.name		= "Unbranded DM1105 with i2c on GPIOs",
+		.lnb = {
+			.mask = UNBR_LNB_MASK,
+			.off = UNBR_LNB_OFF,
+			.v13 = UNBR_LNB_13V,
+			.v18 = UNBR_LNB_18V,
+		},
+		.gpio_scl	= GPIO14,
+		.gpio_sda	= GPIO13,
 	},
 };
 
@@ -293,6 +350,8 @@ struct dm1105_dev {
 
 	/* i2c */
 	struct i2c_adapter i2c_adap;
+	struct i2c_adapter i2c_bb_adap;
+	struct i2c_algo_bit_data i2c_bit;
 
 	/* irq */
 	struct work_struct work;
@@ -328,6 +387,103 @@ struct dm1105_dev {
 #define dm_setl(reg, bit)	dm_andorl((reg), (bit), (bit))
 #define dm_clearl(reg, bit)	dm_andorl((reg), (bit), 0)
 
+/* The chip has 18 GPIOs. In HOST mode GPIO's used as 15 bit address lines,
+ so we can use only 3 GPIO's from GPIO15 to GPIO17.
+ Here I don't check whether HOST is enebled as it is not implemented yet.
+ */
+static void dm1105_gpio_set(struct dm1105_dev *dev, u32 mask)
+{
+	if (mask & 0xfffc0000)
+		printk(KERN_ERR "%s: Only 18 GPIO's are allowed\n", __func__);
+
+	if (mask & 0x0003ffff)
+		dm_setl(DM1105_GPIOVAL, mask & 0x0003ffff);
+
+}
+
+static void dm1105_gpio_clear(struct dm1105_dev *dev, u32 mask)
+{
+	if (mask & 0xfffc0000)
+		printk(KERN_ERR "%s: Only 18 GPIO's are allowed\n", __func__);
+
+	if (mask & 0x0003ffff)
+		dm_clearl(DM1105_GPIOVAL, mask & 0x0003ffff);
+
+}
+
+static void dm1105_gpio_andor(struct dm1105_dev *dev, u32 mask, u32 val)
+{
+	if (mask & 0xfffc0000)
+		printk(KERN_ERR "%s: Only 18 GPIO's are allowed\n", __func__);
+
+	if (mask & 0x0003ffff)
+		dm_andorl(DM1105_GPIOVAL, mask & 0x0003ffff, val);
+
+}
+
+static u32 dm1105_gpio_get(struct dm1105_dev *dev, u32 mask)
+{
+	if (mask & 0xfffc0000)
+		printk(KERN_ERR "%s: Only 18 GPIO's are allowed\n", __func__);
+
+	if (mask & 0x0003ffff)
+		return dm_readl(DM1105_GPIOVAL) & mask & 0x0003ffff;
+
+	return 0;
+}
+
+static void dm1105_gpio_enable(struct dm1105_dev *dev, u32 mask, int asoutput)
+{
+	if (mask & 0xfffc0000)
+		printk(KERN_ERR "%s: Only 18 GPIO's are allowed\n", __func__);
+
+	if ((mask & 0x0003ffff) && asoutput)
+		dm_clearl(DM1105_GPIOCTR, mask & 0x0003ffff);
+	else if ((mask & 0x0003ffff) && !asoutput)
+		dm_setl(DM1105_GPIOCTR, mask & 0x0003ffff);
+
+}
+
+static void dm1105_setline(struct dm1105_dev *dev, u32 line, int state)
+{
+	if (state)
+		dm1105_gpio_enable(dev, line, 0);
+	else {
+		dm1105_gpio_enable(dev, line, 1);
+		dm1105_gpio_clear(dev, line);
+	}
+}
+
+static void dm1105_setsda(void *data, int state)
+{
+	struct dm1105_dev *dev = data;
+
+	dm1105_setline(dev, dm1105_boards[dev->boardnr].gpio_sda, state);
+}
+
+static void dm1105_setscl(void *data, int state)
+{
+	struct dm1105_dev *dev = data;
+
+	dm1105_setline(dev, dm1105_boards[dev->boardnr].gpio_scl, state);
+}
+
+static int dm1105_getsda(void *data)
+{
+	struct dm1105_dev *dev = data;
+
+	return dm1105_gpio_get(dev, dm1105_boards[dev->boardnr].gpio_sda)
+									? 1 : 0;
+}
+
+static int dm1105_getscl(void *data)
+{
+	struct dm1105_dev *dev = data;
+
+	return dm1105_gpio_get(dev, dm1105_boards[dev->boardnr].gpio_scl)
+									? 1 : 0;
+}
+
 static int dm1105_i2c_xfer(struct i2c_adapter *i2c_adap,
 			    struct i2c_msg *msgs, int num)
 {
@@ -436,31 +592,20 @@ static inline struct dm1105_dev *frontend_to_dm1105_dev(struct dvb_frontend *fe)
 static int dm1105_set_voltage(struct dvb_frontend *fe, fe_sec_voltage_t voltage)
 {
 	struct dm1105_dev *dev = frontend_to_dm1105_dev(fe);
-	u32 lnb_mask, lnb_13v, lnb_18v, lnb_off;
 
-	switch (dev->boardnr) {
-	case DM1105_BOARD_AXESS_DM05:
-		lnb_mask = DM05_LNB_MASK;
-		lnb_off = DM05_LNB_OFF;
-		lnb_13v = DM05_LNB_13V;
-		lnb_18v = DM05_LNB_18V;
-		break;
-	case DM1105_BOARD_DVBWORLD_2002:
-	case DM1105_BOARD_DVBWORLD_2004:
-	default:
-		lnb_mask = DM1105_LNB_MASK;
-		lnb_off = DM1105_LNB_OFF;
-		lnb_13v = DM1105_LNB_13V;
-		lnb_18v = DM1105_LNB_18V;
-	}
-
-	dm_writel(DM1105_GPIOCTR, lnb_mask);
+	dm1105_gpio_enable(dev, dm1105_boards[dev->boardnr].lnb.mask, 1);
 	if (voltage == SEC_VOLTAGE_18)
-		dm_writel(DM1105_GPIOVAL, lnb_18v);
+		dm1105_gpio_andor(dev,
+				dm1105_boards[dev->boardnr].lnb.mask,
+				dm1105_boards[dev->boardnr].lnb.v18);
 	else if (voltage == SEC_VOLTAGE_13)
-		dm_writel(DM1105_GPIOVAL, lnb_13v);
+		dm1105_gpio_andor(dev,
+				dm1105_boards[dev->boardnr].lnb.mask,
+				dm1105_boards[dev->boardnr].lnb.v13);
 	else
-		dm_writel(DM1105_GPIOVAL, lnb_off);
+		dm1105_gpio_andor(dev,
+				dm1105_boards[dev->boardnr].lnb.mask,
+				dm1105_boards[dev->boardnr].lnb.off);
 
 	return 0;
 }
@@ -708,6 +853,38 @@ static int __devinit frontend_init(struct dm1105_dev *dev)
 	int ret;
 
 	switch (dev->boardnr) {
+	case DM1105_BOARD_UNBRANDED_I2C_ON_GPIO:
+		dm1105_gpio_enable(dev, GPIO15, 1);
+		dm1105_gpio_clear(dev, GPIO15);
+		msleep(100);
+		dm1105_gpio_set(dev, GPIO15);
+		msleep(200);
+		dev->fe = dvb_attach(
+			stv0299_attach, &sharp_z0194a_config,
+			&dev->i2c_bb_adap);
+		if (dev->fe) {
+			dev->fe->ops.set_voltage = dm1105_set_voltage;
+			dvb_attach(dvb_pll_attach, dev->fe, 0x60,
+					&dev->i2c_bb_adap, DVB_PLL_OPERA1);
+			break;
+		}
+
+		dev->fe = dvb_attach(
+			stv0288_attach, &earda_config,
+			&dev->i2c_bb_adap);
+		if (dev->fe) {
+			dev->fe->ops.set_voltage = dm1105_set_voltage;
+			dvb_attach(stb6000_attach, dev->fe, 0x61,
+					&dev->i2c_bb_adap);
+			break;
+		}
+
+		dev->fe = dvb_attach(
+			si21xx_attach, &serit_config,
+			&dev->i2c_bb_adap);
+		if (dev->fe)
+			dev->fe->ops.set_voltage = dm1105_set_voltage;
+		break;
 	case DM1105_BOARD_DVBWORLD_2004:
 		dev->fe = dvb_attach(
 			cx24116_attach, &serit_sp2633_config,
@@ -870,11 +1047,32 @@ static int __devinit dm1105_probe(struct pci_dev *pdev,
 	if (ret < 0)
 		goto err_dm1105_hw_exit;
 
+	i2c_set_adapdata(&dev->i2c_bb_adap, dev);
+	strcpy(dev->i2c_bb_adap.name, DM1105_I2C_GPIO_NAME);
+	dev->i2c_bb_adap.owner = THIS_MODULE;
+	dev->i2c_bb_adap.dev.parent = &pdev->dev;
+	dev->i2c_bb_adap.algo_data = &dev->i2c_bit;
+	dev->i2c_bit.data = dev;
+	dev->i2c_bit.setsda = dm1105_setsda;
+	dev->i2c_bit.setscl = dm1105_setscl;
+	dev->i2c_bit.getsda = dm1105_getsda;
+	dev->i2c_bit.getscl = dm1105_getscl;
+	dev->i2c_bit.udelay = 10;
+	dev->i2c_bit.timeout = 10;
+
+	/* Raise SCL and SDA */
+	dm1105_setsda(dev, 1);
+	dm1105_setscl(dev, 1);
+
+	ret = i2c_bit_add_bus(&dev->i2c_bb_adap);
+	if (ret < 0)
+		goto err_i2c_del_adapter;
+
 	/* dvb */
 	ret = dvb_register_adapter(&dev->dvb_adapter, DRIVER_NAME,
 					THIS_MODULE, &pdev->dev, adapter_nr);
 	if (ret < 0)
-		goto err_i2c_del_adapter;
+		goto err_i2c_del_adapters;
 
 	dvb_adapter = &dev->dvb_adapter;
 
@@ -952,6 +1150,8 @@ err_dvb_dmx_release:
 	dvb_dmx_release(dvbdemux);
 err_dvb_unregister_adapter:
 	dvb_unregister_adapter(dvb_adapter);
+err_i2c_del_adapters:
+	i2c_del_adapter(&dev->i2c_bb_adap);
 err_i2c_del_adapter:
 	i2c_del_adapter(&dev->i2c_adap);
 err_dm1105_hw_exit:
diff --git a/drivers/media/dvb/dvb-usb/anysee.c b/drivers/media/dvb/dvb-usb/anysee.c
index 4dc1ca333236..7c327b54308e 100644
--- a/drivers/media/dvb/dvb-usb/anysee.c
+++ b/drivers/media/dvb/dvb-usb/anysee.c
@@ -60,8 +60,6 @@ static int anysee_ctrl_msg(struct dvb_usb_device *d, u8 *sbuf, u8 slen,
 	int act_len, ret;
 	u8 buf[64];
 
-	if (slen > sizeof(buf))
-		slen = sizeof(buf);
 	memcpy(&buf[0], sbuf, slen);
 	buf[60] = state->seq++;
 
@@ -180,30 +178,37 @@ static int anysee_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msg,
 {
 	struct dvb_usb_device *d = i2c_get_adapdata(adap);
 	int ret = 0, inc, i = 0;
+	u8 buf[52]; /* 4 + 48 (I2C WR USB command header + I2C WR max) */
 
 	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
 		return -EAGAIN;
 
 	while (i < num) {
 		if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) {
-			u8 buf[6];
+			if (msg[i].len > 2 || msg[i+1].len > 60) {
+				ret = -EOPNOTSUPP;
+				break;
+			}
 			buf[0] = CMD_I2C_READ;
 			buf[1] = (msg[i].addr << 1) | 0x01;
 			buf[2] = msg[i].buf[0];
 			buf[3] = msg[i].buf[1];
 			buf[4] = msg[i].len-1;
 			buf[5] = msg[i+1].len;
-			ret = anysee_ctrl_msg(d, buf, sizeof(buf), msg[i+1].buf,
+			ret = anysee_ctrl_msg(d, buf, 6, msg[i+1].buf,
 				msg[i+1].len);
 			inc = 2;
 		} else {
-			u8 buf[4+msg[i].len];
+			if (msg[i].len > 48) {
+				ret = -EOPNOTSUPP;
+				break;
+			}
 			buf[0] = CMD_I2C_WRITE;
 			buf[1] = (msg[i].addr << 1);
 			buf[2] = msg[i].len;
 			buf[3] = 0x01;
 			memcpy(&buf[4], msg[i].buf, msg[i].len);
-			ret = anysee_ctrl_msg(d, buf, sizeof(buf), NULL, 0);
+			ret = anysee_ctrl_msg(d, buf, 4 + msg[i].len, NULL, 0);
 			inc = 1;
 		}
 		if (ret)
diff --git a/drivers/media/dvb/dvb-usb/lmedm04.c b/drivers/media/dvb/dvb-usb/lmedm04.c
index f36f471deae2..37b146961ae2 100644
--- a/drivers/media/dvb/dvb-usb/lmedm04.c
+++ b/drivers/media/dvb/dvb-usb/lmedm04.c
@@ -207,17 +207,6 @@ static int lme2510_stream_restart(struct dvb_usb_device *d)
 			rbuff, sizeof(rbuff));
 	return ret;
 }
-static int lme2510_remote_keypress(struct dvb_usb_adapter *adap, u32 keypress)
-{
-	struct dvb_usb_device *d = adap->dev;
-
-	deb_info(1, "INT Key Keypress =%04x", keypress);
-
-	if (keypress > 0)
-		rc_keydown(d->rc_dev, keypress, 0);
-
-	return 0;
-}
 
 static int lme2510_enable_pid(struct dvb_usb_device *d, u8 index, u16 pid_out)
 {
@@ -256,6 +245,7 @@ static void lme2510_int_response(struct urb *lme_urb)
 	struct lme2510_state *st = adap->dev->priv;
 	static u8 *ibuf, *rbuf;
 	int i = 0, offset;
+	u32 key;
 
 	switch (lme_urb->status) {
 	case 0:
@@ -282,10 +272,16 @@ static void lme2510_int_response(struct urb *lme_urb)
 
 		switch (ibuf[0]) {
 		case 0xaa:
-			debug_data_snipet(1, "INT Remote data snipet in", ibuf);
-			lme2510_remote_keypress(adap,
-				(u32)(ibuf[2] << 24) + (ibuf[3] << 16) +
-				(ibuf[4] << 8) + ibuf[5]);
+			debug_data_snipet(1, "INT Remote data snipet", ibuf);
+			if ((ibuf[4] + ibuf[5]) == 0xff) {
+				key = ibuf[5];
+				key += (ibuf[3] > 0)
+					? (ibuf[3] ^ 0xff) << 8 : 0;
+				key += (ibuf[2] ^ 0xff) << 16;
+				deb_info(1, "INT Key =%08x", key);
+				if (adap->dev->rc_dev != NULL)
+					rc_keydown(adap->dev->rc_dev, key, 0);
+			}
 			break;
 		case 0xbb:
 			switch (st->tuner_config) {
@@ -691,45 +687,6 @@ static int lme2510_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff)
 	return (ret < 0) ? -ENODEV : 0;
 }
 
-static int lme2510_int_service(struct dvb_usb_adapter *adap)
-{
-	struct dvb_usb_device *d = adap->dev;
-	struct rc_dev *rc;
-	int ret;
-
-	info("STA Configuring Remote");
-
-	rc = rc_allocate_device();
-	if (!rc)
-		return -ENOMEM;
-
-	usb_make_path(d->udev, d->rc_phys, sizeof(d->rc_phys));
-	strlcat(d->rc_phys, "/ir0", sizeof(d->rc_phys));
-
-	rc->input_name = "LME2510 Remote Control";
-	rc->input_phys = d->rc_phys;
-	rc->map_name = RC_MAP_LME2510;
-	rc->driver_name = "LME 2510";
-	usb_to_input_id(d->udev, &rc->input_id);
-
-	ret = rc_register_device(rc);
-	if (ret) {
-		rc_free_device(rc);
-		return ret;
-	}
-	d->rc_dev = rc;
-
-	/* Start the Interrupt */
-	ret = lme2510_int_read(adap);
-	if (ret < 0) {
-		rc_unregister_device(rc);
-		info("INT Unable to start Interrupt Service");
-		return -ENODEV;
-	}
-
-	return 0;
-}
-
 static u8 check_sum(u8 *p, u8 len)
 {
 	u8 sum = 0;
@@ -831,7 +788,7 @@ static int lme_firmware_switch(struct usb_device *udev, int cold)
 
 	cold_fw = !cold;
 
-	if (udev->descriptor.idProduct == 0x1122) {
+	if (le16_to_cpu(udev->descriptor.idProduct) == 0x1122) {
 		switch (dvb_usb_lme2510_firmware) {
 		default:
 			dvb_usb_lme2510_firmware = TUNER_S0194;
@@ -1053,8 +1010,11 @@ static int dm04_lme2510_frontend_attach(struct dvb_usb_adapter *adap)
 
 
 end:	if (ret) {
-		kfree(adap->fe);
-		adap->fe = NULL;
+		if (adap->fe) {
+			dvb_frontend_detach(adap->fe);
+			adap->fe = NULL;
+		}
+		adap->dev->props.rc.core.rc_codes = NULL;
 		return -ENODEV;
 	}
 
@@ -1097,8 +1057,12 @@ static int dm04_lme2510_tuner(struct dvb_usb_adapter *adap)
 		return -ENODEV;
 	}
 
-	/* Start the Interrupt & Remote*/
-	ret = lme2510_int_service(adap);
+	/* Start the Interrupt*/
+	ret = lme2510_int_read(adap);
+	if (ret < 0) {
+		info("INT Unable to start Interrupt Service");
+		return -ENODEV;
+	}
 
 	return ret;
 }
@@ -1204,6 +1168,12 @@ static struct dvb_usb_device_properties lme2510_properties = {
 			}
 		}
 	},
+	.rc.core = {
+		.protocol	= RC_TYPE_NEC,
+		.module_name	= "LME2510 Remote Control",
+		.allowed_protos	= RC_TYPE_NEC,
+		.rc_codes	= RC_MAP_LME2510,
+	},
 	.power_ctrl       = lme2510_powerup,
 	.identify_state   = lme2510_identify_state,
 	.i2c_algo         = &lme2510_i2c_algo,
@@ -1246,6 +1216,12 @@ static struct dvb_usb_device_properties lme2510c_properties = {
 			}
 		}
 	},
+	.rc.core = {
+		.protocol	= RC_TYPE_NEC,
+		.module_name	= "LME2510 Remote Control",
+		.allowed_protos	= RC_TYPE_NEC,
+		.rc_codes	= RC_MAP_LME2510,
+	},
 	.power_ctrl       = lme2510_powerup,
 	.identify_state   = lme2510_identify_state,
 	.i2c_algo         = &lme2510_i2c_algo,
@@ -1269,19 +1245,21 @@ static void *lme2510_exit_int(struct dvb_usb_device *d)
 		adap->feedcount = 0;
 	}
 
-	if (st->lme_urb != NULL) {
+	if (st->usb_buffer != NULL) {
 		st->i2c_talk_onoff = 1;
 		st->signal_lock = 0;
 		st->signal_level = 0;
 		st->signal_sn = 0;
 		buffer = st->usb_buffer;
+	}
+
+	if (st->lme_urb != NULL) {
 		usb_kill_urb(st->lme_urb);
 		usb_free_coherent(d->udev, 5000, st->buffer,
 				  st->lme_urb->transfer_dma);
 		info("Interrupt Service Stopped");
-		rc_unregister_device(d->rc_dev);
-		info("Remote Stopped");
 	}
+
 	return buffer;
 }
 
@@ -1293,7 +1271,8 @@ static void lme2510_exit(struct usb_interface *intf)
 	if (d != NULL) {
 		usb_buffer = lme2510_exit_int(d);
 		dvb_usb_device_exit(intf);
-		kfree(usb_buffer);
+		if (usb_buffer != NULL)
+			kfree(usb_buffer);
 	}
 }
 
@@ -1327,5 +1306,5 @@ module_exit(lme2510_module_exit);
 
 MODULE_AUTHOR("Malcolm Priestley <tvboxspy@gmail.com>");
 MODULE_DESCRIPTION("LME2510(C) DVB-S USB2.0");
-MODULE_VERSION("1.86");
+MODULE_VERSION("1.88");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb/frontends/stb0899_algo.c b/drivers/media/dvb/frontends/stb0899_algo.c
index 2da55ec20392..d70eee00f33a 100644
--- a/drivers/media/dvb/frontends/stb0899_algo.c
+++ b/drivers/media/dvb/frontends/stb0899_algo.c
@@ -23,7 +23,7 @@
 #include "stb0899_priv.h"
 #include "stb0899_reg.h"
 
-inline u32 stb0899_do_div(u64 n, u32 d)
+static inline u32 stb0899_do_div(u64 n, u32 d)
 {
 	/* wrap do_div() for ease of use */
 
diff --git a/drivers/media/dvb/frontends/tda8261.c b/drivers/media/dvb/frontends/tda8261.c
index 1742056a34e8..53c7d8f1df28 100644
--- a/drivers/media/dvb/frontends/tda8261.c
+++ b/drivers/media/dvb/frontends/tda8261.c
@@ -224,7 +224,6 @@ exit:
 }
 
 EXPORT_SYMBOL(tda8261_attach);
-MODULE_PARM_DESC(verbose, "Set verbosity level");
 
 MODULE_AUTHOR("Manu Abraham");
 MODULE_DESCRIPTION("TDA8261 8PSK/QPSK Tuner");
diff --git a/drivers/media/media-devnode.c b/drivers/media/media-devnode.c
index af5263c6625a..7b42ace419d9 100644
--- a/drivers/media/media-devnode.c
+++ b/drivers/media/media-devnode.c
@@ -213,14 +213,14 @@ int __must_check media_devnode_register(struct media_devnode *mdev)
 
 	/* Part 1: Find a free minor number */
 	mutex_lock(&media_devnode_lock);
-	minor = find_next_zero_bit(media_devnode_nums, 0, MEDIA_NUM_DEVICES);
+	minor = find_next_zero_bit(media_devnode_nums, MEDIA_NUM_DEVICES, 0);
 	if (minor == MEDIA_NUM_DEVICES) {
 		mutex_unlock(&media_devnode_lock);
 		printk(KERN_ERR "could not get a free minor\n");
 		return -ENFILE;
 	}
 
-	set_bit(mdev->minor, media_devnode_nums);
+	set_bit(minor, media_devnode_nums);
 	mutex_unlock(&media_devnode_lock);
 
 	mdev->minor = minor;
diff --git a/drivers/media/radio/radio-wl1273.c b/drivers/media/radio/radio-wl1273.c
index 46cacf845049..459f7272d326 100644
--- a/drivers/media/radio/radio-wl1273.c
+++ b/drivers/media/radio/radio-wl1273.c
@@ -1382,7 +1382,7 @@ static int wl1273_fm_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 
 	switch (ctrl->id) {
 	case  V4L2_CID_TUNE_ANTENNA_CAPACITOR:
-		ctrl->val = wl1273_fm_get_tx_ctune(radio);
+		ctrl->cur.val = wl1273_fm_get_tx_ctune(radio);
 		break;
 
 	default:
diff --git a/drivers/media/radio/wl128x/fmdrv_v4l2.c b/drivers/media/radio/wl128x/fmdrv_v4l2.c
index d50e5ac75ab6..87010724f914 100644
--- a/drivers/media/radio/wl128x/fmdrv_v4l2.c
+++ b/drivers/media/radio/wl128x/fmdrv_v4l2.c
@@ -191,7 +191,7 @@ static int fm_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 
 	switch (ctrl->id) {
 	case  V4L2_CID_TUNE_ANTENNA_CAPACITOR:
-		ctrl->val = fm_tx_get_tune_cap_val(fmdev);
+		ctrl->cur.val = fm_tx_get_tune_cap_val(fmdev);
 		break;
 	default:
 		fmwarn("%s: Unknown IOCTL: %d\n", __func__, ctrl->id);
diff --git a/drivers/media/rc/Kconfig b/drivers/media/rc/Kconfig
index 154c337f00fd..7d4bbc226d06 100644
--- a/drivers/media/rc/Kconfig
+++ b/drivers/media/rc/Kconfig
@@ -148,6 +148,18 @@ config IR_ITE_CIR
 	   To compile this driver as a module, choose M here: the
 	   module will be called ite-cir.
 
+config IR_FINTEK
+	tristate "Fintek Consumer Infrared Transceiver"
+	depends on PNP
+	depends on RC_CORE
+	---help---
+	   Say Y here to enable support for integrated infrared receiver
+	   /transciever made by Fintek. This chip is found on assorted
+	   Jetway motherboards (and of course, possibly others).
+
+	   To compile this driver as a module, choose M here: the
+	   module will be called fintek-cir.
+
 config IR_NUVOTON
 	tristate "Nuvoton w836x7hg Consumer Infrared Transceiver"
 	depends on PNP
diff --git a/drivers/media/rc/Makefile b/drivers/media/rc/Makefile
index 1f90a219a162..52830e5f4eaa 100644
--- a/drivers/media/rc/Makefile
+++ b/drivers/media/rc/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_IR_LIRC_CODEC) += ir-lirc-codec.o
 obj-$(CONFIG_IR_IMON) += imon.o
 obj-$(CONFIG_IR_ITE_CIR) += ite-cir.o
 obj-$(CONFIG_IR_MCEUSB) += mceusb.o
+obj-$(CONFIG_IR_FINTEK) += fintek-cir.o
 obj-$(CONFIG_IR_NUVOTON) += nuvoton-cir.o
 obj-$(CONFIG_IR_ENE) += ene_ir.o
 obj-$(CONFIG_IR_REDRAT3) += redrat3.o
diff --git a/drivers/media/rc/fintek-cir.c b/drivers/media/rc/fintek-cir.c
new file mode 100644
index 000000000000..8fa539dde1b4
--- /dev/null
+++ b/drivers/media/rc/fintek-cir.c
@@ -0,0 +1,684 @@
+/*
+ * Driver for Feature Integration Technology Inc. (aka Fintek) LPC CIR
+ *
+ * Copyright (C) 2011 Jarod Wilson <jarod@redhat.com>
+ *
+ * Special thanks to Fintek for providing hardware and spec sheets.
+ * This driver is based upon the nuvoton, ite and ene drivers for
+ * similar hardware.
+ *
+ * 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/kernel.h>
+#include <linux/module.h>
+#include <linux/pnp.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <media/rc-core.h>
+#include <linux/pci_ids.h>
+
+#include "fintek-cir.h"
+
+/* write val to config reg */
+static inline void fintek_cr_write(struct fintek_dev *fintek, u8 val, u8 reg)
+{
+	fit_dbg("%s: reg 0x%02x, val 0x%02x  (ip/dp: %02x/%02x)",
+		__func__, reg, val, fintek->cr_ip, fintek->cr_dp);
+	outb(reg, fintek->cr_ip);
+	outb(val, fintek->cr_dp);
+}
+
+/* read val from config reg */
+static inline u8 fintek_cr_read(struct fintek_dev *fintek, u8 reg)
+{
+	u8 val;
+
+	outb(reg, fintek->cr_ip);
+	val = inb(fintek->cr_dp);
+
+	fit_dbg("%s: reg 0x%02x, val 0x%02x  (ip/dp: %02x/%02x)",
+		__func__, reg, val, fintek->cr_ip, fintek->cr_dp);
+	return val;
+}
+
+/* update config register bit without changing other bits */
+static inline void fintek_set_reg_bit(struct fintek_dev *fintek, u8 val, u8 reg)
+{
+	u8 tmp = fintek_cr_read(fintek, reg) | val;
+	fintek_cr_write(fintek, tmp, reg);
+}
+
+/* clear config register bit without changing other bits */
+static inline void fintek_clear_reg_bit(struct fintek_dev *fintek, u8 val, u8 reg)
+{
+	u8 tmp = fintek_cr_read(fintek, reg) & ~val;
+	fintek_cr_write(fintek, tmp, reg);
+}
+
+/* enter config mode */
+static inline void fintek_config_mode_enable(struct fintek_dev *fintek)
+{
+	/* Enabling Config Mode explicitly requires writing 2x */
+	outb(CONFIG_REG_ENABLE, fintek->cr_ip);
+	outb(CONFIG_REG_ENABLE, fintek->cr_ip);
+}
+
+/* exit config mode */
+static inline void fintek_config_mode_disable(struct fintek_dev *fintek)
+{
+	outb(CONFIG_REG_DISABLE, fintek->cr_ip);
+}
+
+/*
+ * When you want to address a specific logical device, write its logical
+ * device number to GCR_LOGICAL_DEV_NO
+ */
+static inline void fintek_select_logical_dev(struct fintek_dev *fintek, u8 ldev)
+{
+	fintek_cr_write(fintek, ldev, GCR_LOGICAL_DEV_NO);
+}
+
+/* write val to cir config register */
+static inline void fintek_cir_reg_write(struct fintek_dev *fintek, u8 val, u8 offset)
+{
+	outb(val, fintek->cir_addr + offset);
+}
+
+/* read val from cir config register */
+static u8 fintek_cir_reg_read(struct fintek_dev *fintek, u8 offset)
+{
+	u8 val;
+
+	val = inb(fintek->cir_addr + offset);
+
+	return val;
+}
+
+#define pr_reg(text, ...) \
+	printk(KERN_INFO KBUILD_MODNAME ": " text, ## __VA_ARGS__)
+
+/* dump current cir register contents */
+static void cir_dump_regs(struct fintek_dev *fintek)
+{
+	fintek_config_mode_enable(fintek);
+	fintek_select_logical_dev(fintek, LOGICAL_DEV_CIR);
+
+	pr_reg("%s: Dump CIR logical device registers:\n", FINTEK_DRIVER_NAME);
+	pr_reg(" * CR CIR BASE ADDR: 0x%x\n",
+	       (fintek_cr_read(fintek, CIR_CR_BASE_ADDR_HI) << 8) |
+		fintek_cr_read(fintek, CIR_CR_BASE_ADDR_LO));
+	pr_reg(" * CR CIR IRQ NUM:   0x%x\n",
+	       fintek_cr_read(fintek, CIR_CR_IRQ_SEL));
+
+	fintek_config_mode_disable(fintek);
+
+	pr_reg("%s: Dump CIR registers:\n", FINTEK_DRIVER_NAME);
+	pr_reg(" * STATUS:     0x%x\n", fintek_cir_reg_read(fintek, CIR_STATUS));
+	pr_reg(" * CONTROL:    0x%x\n", fintek_cir_reg_read(fintek, CIR_CONTROL));
+	pr_reg(" * RX_DATA:    0x%x\n", fintek_cir_reg_read(fintek, CIR_RX_DATA));
+	pr_reg(" * TX_CONTROL: 0x%x\n", fintek_cir_reg_read(fintek, CIR_TX_CONTROL));
+	pr_reg(" * TX_DATA:    0x%x\n", fintek_cir_reg_read(fintek, CIR_TX_DATA));
+}
+
+/* detect hardware features */
+static int fintek_hw_detect(struct fintek_dev *fintek)
+{
+	unsigned long flags;
+	u8 chip_major, chip_minor;
+	u8 vendor_major, vendor_minor;
+	u8 portsel, ir_class;
+	u16 vendor;
+	int ret = 0;
+
+	fintek_config_mode_enable(fintek);
+
+	/* Check if we're using config port 0x4e or 0x2e */
+	portsel = fintek_cr_read(fintek, GCR_CONFIG_PORT_SEL);
+	if (portsel == 0xff) {
+		fit_pr(KERN_INFO, "first portsel read was bunk, trying alt");
+		fintek_config_mode_disable(fintek);
+		fintek->cr_ip = CR_INDEX_PORT2;
+		fintek->cr_dp = CR_DATA_PORT2;
+		fintek_config_mode_enable(fintek);
+		portsel = fintek_cr_read(fintek, GCR_CONFIG_PORT_SEL);
+	}
+	fit_dbg("portsel reg: 0x%02x", portsel);
+
+	ir_class = fintek_cir_reg_read(fintek, CIR_CR_CLASS);
+	fit_dbg("ir_class reg: 0x%02x", ir_class);
+
+	switch (ir_class) {
+	case CLASS_RX_2TX:
+	case CLASS_RX_1TX:
+		fintek->hw_tx_capable = true;
+		break;
+	case CLASS_RX_ONLY:
+	default:
+		fintek->hw_tx_capable = false;
+		break;
+	}
+
+	chip_major = fintek_cr_read(fintek, GCR_CHIP_ID_HI);
+	chip_minor = fintek_cr_read(fintek, GCR_CHIP_ID_LO);
+
+	vendor_major = fintek_cr_read(fintek, GCR_VENDOR_ID_HI);
+	vendor_minor = fintek_cr_read(fintek, GCR_VENDOR_ID_LO);
+	vendor = vendor_major << 8 | vendor_minor;
+
+	if (vendor != VENDOR_ID_FINTEK)
+		fit_pr(KERN_WARNING, "Unknown vendor ID: 0x%04x", vendor);
+	else
+		fit_dbg("Read Fintek vendor ID from chip");
+
+	fintek_config_mode_disable(fintek);
+
+	spin_lock_irqsave(&fintek->fintek_lock, flags);
+	fintek->chip_major  = chip_major;
+	fintek->chip_minor  = chip_minor;
+	fintek->chip_vendor = vendor;
+	spin_unlock_irqrestore(&fintek->fintek_lock, flags);
+
+	return ret;
+}
+
+static void fintek_cir_ldev_init(struct fintek_dev *fintek)
+{
+	/* Select CIR logical device and enable */
+	fintek_select_logical_dev(fintek, LOGICAL_DEV_CIR);
+	fintek_cr_write(fintek, LOGICAL_DEV_ENABLE, CIR_CR_DEV_EN);
+
+	/* Write allocated CIR address and IRQ information to hardware */
+	fintek_cr_write(fintek, fintek->cir_addr >> 8, CIR_CR_BASE_ADDR_HI);
+	fintek_cr_write(fintek, fintek->cir_addr & 0xff, CIR_CR_BASE_ADDR_LO);
+
+	fintek_cr_write(fintek, fintek->cir_irq, CIR_CR_IRQ_SEL);
+
+	fit_dbg("CIR initialized, base io address: 0x%lx, irq: %d (len: %d)",
+		fintek->cir_addr, fintek->cir_irq, fintek->cir_port_len);
+}
+
+/* enable CIR interrupts */
+static void fintek_enable_cir_irq(struct fintek_dev *fintek)
+{
+	fintek_cir_reg_write(fintek, CIR_STATUS_IRQ_EN, CIR_STATUS);
+}
+
+static void fintek_cir_regs_init(struct fintek_dev *fintek)
+{
+	/* clear any and all stray interrupts */
+	fintek_cir_reg_write(fintek, CIR_STATUS_IRQ_MASK, CIR_STATUS);
+
+	/* and finally, enable interrupts */
+	fintek_enable_cir_irq(fintek);
+}
+
+static void fintek_enable_wake(struct fintek_dev *fintek)
+{
+	fintek_config_mode_enable(fintek);
+	fintek_select_logical_dev(fintek, LOGICAL_DEV_ACPI);
+
+	/* Allow CIR PME's to wake system */
+	fintek_set_reg_bit(fintek, ACPI_WAKE_EN_CIR_BIT, LDEV_ACPI_WAKE_EN_REG);
+	/* Enable CIR PME's */
+	fintek_set_reg_bit(fintek, ACPI_PME_CIR_BIT, LDEV_ACPI_PME_EN_REG);
+	/* Clear CIR PME status register */
+	fintek_set_reg_bit(fintek, ACPI_PME_CIR_BIT, LDEV_ACPI_PME_CLR_REG);
+	/* Save state */
+	fintek_set_reg_bit(fintek, ACPI_STATE_CIR_BIT, LDEV_ACPI_STATE_REG);
+
+	fintek_config_mode_disable(fintek);
+}
+
+static int fintek_cmdsize(u8 cmd, u8 subcmd)
+{
+	int datasize = 0;
+
+	switch (cmd) {
+	case BUF_COMMAND_NULL:
+		if (subcmd == BUF_HW_CMD_HEADER)
+			datasize = 1;
+		break;
+	case BUF_HW_CMD_HEADER:
+		if (subcmd == BUF_CMD_G_REVISION)
+			datasize = 2;
+		break;
+	case BUF_COMMAND_HEADER:
+		switch (subcmd) {
+		case BUF_CMD_S_CARRIER:
+		case BUF_CMD_S_TIMEOUT:
+		case BUF_RSP_PULSE_COUNT:
+			datasize = 2;
+			break;
+		case BUF_CMD_SIG_END:
+		case BUF_CMD_S_TXMASK:
+		case BUF_CMD_S_RXSENSOR:
+			datasize = 1;
+			break;
+		}
+	}
+
+	return datasize;
+}
+
+/* process ir data stored in driver buffer */
+static void fintek_process_rx_ir_data(struct fintek_dev *fintek)
+{
+	DEFINE_IR_RAW_EVENT(rawir);
+	u8 sample;
+	int i;
+
+	for (i = 0; i < fintek->pkts; i++) {
+		sample = fintek->buf[i];
+		switch (fintek->parser_state) {
+		case CMD_HEADER:
+			fintek->cmd = sample;
+			if ((fintek->cmd == BUF_COMMAND_HEADER) ||
+			    ((fintek->cmd & BUF_COMMAND_MASK) !=
+			     BUF_PULSE_BIT)) {
+				fintek->parser_state = SUBCMD;
+				continue;
+			}
+			fintek->rem = (fintek->cmd & BUF_LEN_MASK);
+			fit_dbg("%s: rem: 0x%02x", __func__, fintek->rem);
+			if (fintek->rem)
+				fintek->parser_state = PARSE_IRDATA;
+			else
+				ir_raw_event_reset(fintek->rdev);
+			break;
+		case SUBCMD:
+			fintek->rem = fintek_cmdsize(fintek->cmd, sample);
+			fintek->parser_state = CMD_DATA;
+			break;
+		case CMD_DATA:
+			fintek->rem--;
+			break;
+		case PARSE_IRDATA:
+			fintek->rem--;
+			init_ir_raw_event(&rawir);
+			rawir.pulse = ((sample & BUF_PULSE_BIT) != 0);
+			rawir.duration = US_TO_NS((sample & BUF_SAMPLE_MASK)
+					  * CIR_SAMPLE_PERIOD);
+
+			fit_dbg("Storing %s with duration %d",
+				rawir.pulse ? "pulse" : "space",
+				rawir.duration);
+			ir_raw_event_store_with_filter(fintek->rdev, &rawir);
+			break;
+		}
+
+		if ((fintek->parser_state != CMD_HEADER) && !fintek->rem)
+			fintek->parser_state = CMD_HEADER;
+	}
+
+	fintek->pkts = 0;
+
+	fit_dbg("Calling ir_raw_event_handle");
+	ir_raw_event_handle(fintek->rdev);
+}
+
+/* copy data from hardware rx register into driver buffer */
+static void fintek_get_rx_ir_data(struct fintek_dev *fintek, u8 rx_irqs)
+{
+	unsigned long flags;
+	u8 sample, status;
+
+	spin_lock_irqsave(&fintek->fintek_lock, flags);
+
+	/*
+	 * We must read data from CIR_RX_DATA until the hardware IR buffer
+	 * is empty and clears the RX_TIMEOUT and/or RX_RECEIVE flags in
+	 * the CIR_STATUS register
+	 */
+	do {
+		sample = fintek_cir_reg_read(fintek, CIR_RX_DATA);
+		fit_dbg("%s: sample: 0x%02x", __func__, sample);
+
+		fintek->buf[fintek->pkts] = sample;
+		fintek->pkts++;
+
+		status = fintek_cir_reg_read(fintek, CIR_STATUS);
+		if (!(status & CIR_STATUS_IRQ_EN))
+			break;
+	} while (status & rx_irqs);
+
+	fintek_process_rx_ir_data(fintek);
+
+	spin_unlock_irqrestore(&fintek->fintek_lock, flags);
+}
+
+static void fintek_cir_log_irqs(u8 status)
+{
+	fit_pr(KERN_INFO, "IRQ 0x%02x:%s%s%s%s%s", status,
+		status & CIR_STATUS_IRQ_EN	? " IRQEN"	: "",
+		status & CIR_STATUS_TX_FINISH	? " TXF"	: "",
+		status & CIR_STATUS_TX_UNDERRUN	? " TXU"	: "",
+		status & CIR_STATUS_RX_TIMEOUT	? " RXTO"	: "",
+		status & CIR_STATUS_RX_RECEIVE	? " RXOK"	: "");
+}
+
+/* interrupt service routine for incoming and outgoing CIR data */
+static irqreturn_t fintek_cir_isr(int irq, void *data)
+{
+	struct fintek_dev *fintek = data;
+	u8 status, rx_irqs;
+
+	fit_dbg_verbose("%s firing", __func__);
+
+	fintek_config_mode_enable(fintek);
+	fintek_select_logical_dev(fintek, LOGICAL_DEV_CIR);
+	fintek_config_mode_disable(fintek);
+
+	/*
+	 * Get IR Status register contents. Write 1 to ack/clear
+	 *
+	 * bit: reg name    - description
+	 *   3: TX_FINISH   - TX is finished
+	 *   2: TX_UNDERRUN - TX underrun
+	 *   1: RX_TIMEOUT  - RX data timeout
+	 *   0: RX_RECEIVE  - RX data received
+	 */
+	status = fintek_cir_reg_read(fintek, CIR_STATUS);
+	if (!(status & CIR_STATUS_IRQ_MASK) || status == 0xff) {
+		fit_dbg_verbose("%s exiting, IRSTS 0x%02x", __func__, status);
+		fintek_cir_reg_write(fintek, CIR_STATUS_IRQ_MASK, CIR_STATUS);
+		return IRQ_RETVAL(IRQ_NONE);
+	}
+
+	if (debug)
+		fintek_cir_log_irqs(status);
+
+	rx_irqs = status & (CIR_STATUS_RX_RECEIVE | CIR_STATUS_RX_TIMEOUT);
+	if (rx_irqs)
+		fintek_get_rx_ir_data(fintek, rx_irqs);
+
+	/* ack/clear all irq flags we've got */
+	fintek_cir_reg_write(fintek, status, CIR_STATUS);
+
+	fit_dbg_verbose("%s done", __func__);
+	return IRQ_RETVAL(IRQ_HANDLED);
+}
+
+static void fintek_enable_cir(struct fintek_dev *fintek)
+{
+	/* set IRQ enabled */
+	fintek_cir_reg_write(fintek, CIR_STATUS_IRQ_EN, CIR_STATUS);
+
+	fintek_config_mode_enable(fintek);
+
+	/* enable the CIR logical device */
+	fintek_select_logical_dev(fintek, LOGICAL_DEV_CIR);
+	fintek_cr_write(fintek, LOGICAL_DEV_ENABLE, CIR_CR_DEV_EN);
+
+	fintek_config_mode_disable(fintek);
+
+	/* clear all pending interrupts */
+	fintek_cir_reg_write(fintek, CIR_STATUS_IRQ_MASK, CIR_STATUS);
+
+	/* enable interrupts */
+	fintek_enable_cir_irq(fintek);
+}
+
+static void fintek_disable_cir(struct fintek_dev *fintek)
+{
+	fintek_config_mode_enable(fintek);
+
+	/* disable the CIR logical device */
+	fintek_select_logical_dev(fintek, LOGICAL_DEV_CIR);
+	fintek_cr_write(fintek, LOGICAL_DEV_DISABLE, CIR_CR_DEV_EN);
+
+	fintek_config_mode_disable(fintek);
+}
+
+static int fintek_open(struct rc_dev *dev)
+{
+	struct fintek_dev *fintek = dev->priv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&fintek->fintek_lock, flags);
+	fintek_enable_cir(fintek);
+	spin_unlock_irqrestore(&fintek->fintek_lock, flags);
+
+	return 0;
+}
+
+static void fintek_close(struct rc_dev *dev)
+{
+	struct fintek_dev *fintek = dev->priv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&fintek->fintek_lock, flags);
+	fintek_disable_cir(fintek);
+	spin_unlock_irqrestore(&fintek->fintek_lock, flags);
+}
+
+/* Allocate memory, probe hardware, and initialize everything */
+static int fintek_probe(struct pnp_dev *pdev, const struct pnp_device_id *dev_id)
+{
+	struct fintek_dev *fintek;
+	struct rc_dev *rdev;
+	int ret = -ENOMEM;
+
+	fintek = kzalloc(sizeof(struct fintek_dev), GFP_KERNEL);
+	if (!fintek)
+		return ret;
+
+	/* input device for IR remote (and tx) */
+	rdev = rc_allocate_device();
+	if (!rdev)
+		goto failure;
+
+	ret = -ENODEV;
+	/* validate pnp resources */
+	if (!pnp_port_valid(pdev, 0)) {
+		dev_err(&pdev->dev, "IR PNP Port not valid!\n");
+		goto failure;
+	}
+
+	if (!pnp_irq_valid(pdev, 0)) {
+		dev_err(&pdev->dev, "IR PNP IRQ not valid!\n");
+		goto failure;
+	}
+
+	fintek->cir_addr = pnp_port_start(pdev, 0);
+	fintek->cir_irq  = pnp_irq(pdev, 0);
+	fintek->cir_port_len = pnp_port_len(pdev, 0);
+
+	fintek->cr_ip = CR_INDEX_PORT;
+	fintek->cr_dp = CR_DATA_PORT;
+
+	spin_lock_init(&fintek->fintek_lock);
+
+	ret = -EBUSY;
+	/* now claim resources */
+	if (!request_region(fintek->cir_addr,
+			    fintek->cir_port_len, FINTEK_DRIVER_NAME))
+		goto failure;
+
+	if (request_irq(fintek->cir_irq, fintek_cir_isr, IRQF_SHARED,
+			FINTEK_DRIVER_NAME, (void *)fintek))
+		goto failure;
+
+	pnp_set_drvdata(pdev, fintek);
+	fintek->pdev = pdev;
+
+	ret = fintek_hw_detect(fintek);
+	if (ret)
+		goto failure;
+
+	/* Initialize CIR & CIR Wake Logical Devices */
+	fintek_config_mode_enable(fintek);
+	fintek_cir_ldev_init(fintek);
+	fintek_config_mode_disable(fintek);
+
+	/* Initialize CIR & CIR Wake Config Registers */
+	fintek_cir_regs_init(fintek);
+
+	/* Set up the rc device */
+	rdev->priv = fintek;
+	rdev->driver_type = RC_DRIVER_IR_RAW;
+	rdev->allowed_protos = RC_TYPE_ALL;
+	rdev->open = fintek_open;
+	rdev->close = fintek_close;
+	rdev->input_name = FINTEK_DESCRIPTION;
+	rdev->input_phys = "fintek/cir0";
+	rdev->input_id.bustype = BUS_HOST;
+	rdev->input_id.vendor = VENDOR_ID_FINTEK;
+	rdev->input_id.product = fintek->chip_major;
+	rdev->input_id.version = fintek->chip_minor;
+	rdev->dev.parent = &pdev->dev;
+	rdev->driver_name = FINTEK_DRIVER_NAME;
+	rdev->map_name = RC_MAP_RC6_MCE;
+	rdev->timeout = US_TO_NS(1000);
+	/* rx resolution is hardwired to 50us atm, 1, 25, 100 also possible */
+	rdev->rx_resolution = US_TO_NS(CIR_SAMPLE_PERIOD);
+
+	ret = rc_register_device(rdev);
+	if (ret)
+		goto failure;
+
+	device_init_wakeup(&pdev->dev, true);
+	fintek->rdev = rdev;
+	fit_pr(KERN_NOTICE, "driver has been successfully loaded\n");
+	if (debug)
+		cir_dump_regs(fintek);
+
+	return 0;
+
+failure:
+	if (fintek->cir_irq)
+		free_irq(fintek->cir_irq, fintek);
+	if (fintek->cir_addr)
+		release_region(fintek->cir_addr, fintek->cir_port_len);
+
+	rc_free_device(rdev);
+	kfree(fintek);
+
+	return ret;
+}
+
+static void __devexit fintek_remove(struct pnp_dev *pdev)
+{
+	struct fintek_dev *fintek = pnp_get_drvdata(pdev);
+	unsigned long flags;
+
+	spin_lock_irqsave(&fintek->fintek_lock, flags);
+	/* disable CIR */
+	fintek_disable_cir(fintek);
+	fintek_cir_reg_write(fintek, CIR_STATUS_IRQ_MASK, CIR_STATUS);
+	/* enable CIR Wake (for IR power-on) */
+	fintek_enable_wake(fintek);
+	spin_unlock_irqrestore(&fintek->fintek_lock, flags);
+
+	/* free resources */
+	free_irq(fintek->cir_irq, fintek);
+	release_region(fintek->cir_addr, fintek->cir_port_len);
+
+	rc_unregister_device(fintek->rdev);
+
+	kfree(fintek);
+}
+
+static int fintek_suspend(struct pnp_dev *pdev, pm_message_t state)
+{
+	struct fintek_dev *fintek = pnp_get_drvdata(pdev);
+
+	fit_dbg("%s called", __func__);
+
+	/* disable all CIR interrupts */
+	fintek_cir_reg_write(fintek, CIR_STATUS_IRQ_MASK, CIR_STATUS);
+
+	fintek_config_mode_enable(fintek);
+
+	/* disable cir logical dev */
+	fintek_select_logical_dev(fintek, LOGICAL_DEV_CIR);
+	fintek_cr_write(fintek, LOGICAL_DEV_DISABLE, CIR_CR_DEV_EN);
+
+	fintek_config_mode_disable(fintek);
+
+	/* make sure wake is enabled */
+	fintek_enable_wake(fintek);
+
+	return 0;
+}
+
+static int fintek_resume(struct pnp_dev *pdev)
+{
+	int ret = 0;
+	struct fintek_dev *fintek = pnp_get_drvdata(pdev);
+
+	fit_dbg("%s called", __func__);
+
+	/* open interrupt */
+	fintek_enable_cir_irq(fintek);
+
+	/* Enable CIR logical device */
+	fintek_config_mode_enable(fintek);
+	fintek_select_logical_dev(fintek, LOGICAL_DEV_CIR);
+	fintek_cr_write(fintek, LOGICAL_DEV_ENABLE, CIR_CR_DEV_EN);
+
+	fintek_config_mode_disable(fintek);
+
+	fintek_cir_regs_init(fintek);
+
+	return ret;
+}
+
+static void fintek_shutdown(struct pnp_dev *pdev)
+{
+	struct fintek_dev *fintek = pnp_get_drvdata(pdev);
+	fintek_enable_wake(fintek);
+}
+
+static const struct pnp_device_id fintek_ids[] = {
+	{ "FIT0002", 0 },   /* CIR */
+	{ "", 0 },
+};
+
+static struct pnp_driver fintek_driver = {
+	.name		= FINTEK_DRIVER_NAME,
+	.id_table	= fintek_ids,
+	.flags		= PNP_DRIVER_RES_DO_NOT_CHANGE,
+	.probe		= fintek_probe,
+	.remove		= __devexit_p(fintek_remove),
+	.suspend	= fintek_suspend,
+	.resume		= fintek_resume,
+	.shutdown	= fintek_shutdown,
+};
+
+int fintek_init(void)
+{
+	return pnp_register_driver(&fintek_driver);
+}
+
+void fintek_exit(void)
+{
+	pnp_unregister_driver(&fintek_driver);
+}
+
+module_param(debug, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(debug, "Enable debugging output");
+
+MODULE_DEVICE_TABLE(pnp, fintek_ids);
+MODULE_DESCRIPTION(FINTEK_DESCRIPTION " driver");
+
+MODULE_AUTHOR("Jarod Wilson <jarod@redhat.com>");
+MODULE_LICENSE("GPL");
+
+module_init(fintek_init);
+module_exit(fintek_exit);
diff --git a/drivers/media/rc/fintek-cir.h b/drivers/media/rc/fintek-cir.h
new file mode 100644
index 000000000000..1b10b2011f5e
--- /dev/null
+++ b/drivers/media/rc/fintek-cir.h
@@ -0,0 +1,243 @@
+/*
+ * Driver for Feature Integration Technology Inc. (aka Fintek) LPC CIR
+ *
+ * Copyright (C) 2011 Jarod Wilson <jarod@redhat.com>
+ *
+ * Special thanks to Fintek for providing hardware and spec sheets.
+ * This driver is based upon the nuvoton, ite and ene drivers for
+ * similar hardware.
+ *
+ * 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/spinlock.h>
+#include <linux/ioctl.h>
+
+/* platform driver name to register */
+#define FINTEK_DRIVER_NAME	"fintek-cir"
+#define FINTEK_DESCRIPTION	"Fintek LPC SuperIO Consumer IR Transceiver"
+#define VENDOR_ID_FINTEK	0x1934
+
+
+/* debugging module parameter */
+static int debug;
+
+#define fit_pr(level, text, ...) \
+	printk(level KBUILD_MODNAME ": " text, ## __VA_ARGS__)
+
+#define fit_dbg(text, ...) \
+	if (debug) \
+		printk(KERN_DEBUG \
+			KBUILD_MODNAME ": " text "\n" , ## __VA_ARGS__)
+
+#define fit_dbg_verbose(text, ...) \
+	if (debug > 1) \
+		printk(KERN_DEBUG \
+			KBUILD_MODNAME ": " text "\n" , ## __VA_ARGS__)
+
+#define fit_dbg_wake(text, ...) \
+	if (debug > 2) \
+		printk(KERN_DEBUG \
+			KBUILD_MODNAME ": " text "\n" , ## __VA_ARGS__)
+
+
+#define TX_BUF_LEN 256
+#define RX_BUF_LEN 32
+
+struct fintek_dev {
+	struct pnp_dev *pdev;
+	struct rc_dev *rdev;
+
+	spinlock_t fintek_lock;
+
+	/* for rx */
+	u8 buf[RX_BUF_LEN];
+	unsigned int pkts;
+
+	struct {
+		spinlock_t lock;
+		u8 buf[TX_BUF_LEN];
+		unsigned int buf_count;
+		unsigned int cur_buf_num;
+		wait_queue_head_t queue;
+	} tx;
+
+	/* Config register index/data port pair */
+	u8 cr_ip;
+	u8 cr_dp;
+
+	/* hardware I/O settings */
+	unsigned long cir_addr;
+	int cir_irq;
+	int cir_port_len;
+
+	/* hardware id */
+	u8 chip_major;
+	u8 chip_minor;
+	u16 chip_vendor;
+
+	/* hardware features */
+	bool hw_learning_capable;
+	bool hw_tx_capable;
+
+	/* rx settings */
+	bool learning_enabled;
+	bool carrier_detect_enabled;
+
+	enum {
+		CMD_HEADER = 0,
+		SUBCMD,
+		CMD_DATA,
+		PARSE_IRDATA,
+	} parser_state;
+
+	u8 cmd, rem;
+
+	/* carrier period = 1 / frequency */
+	u32 carrier;
+};
+
+/* buffer packet constants, largely identical to mceusb.c */
+#define BUF_PULSE_BIT		0x80
+#define BUF_LEN_MASK		0x1f
+#define BUF_SAMPLE_MASK		0x7f
+
+#define BUF_COMMAND_HEADER	0x9f
+#define BUF_COMMAND_MASK	0xe0
+#define BUF_COMMAND_NULL	0x00
+#define BUF_HW_CMD_HEADER	0xff
+#define BUF_CMD_G_REVISION	0x0b
+#define BUF_CMD_S_CARRIER	0x06
+#define BUF_CMD_S_TIMEOUT	0x0c
+#define BUF_CMD_SIG_END		0x01
+#define BUF_CMD_S_TXMASK	0x08
+#define BUF_CMD_S_RXSENSOR	0x14
+#define BUF_RSP_PULSE_COUNT	0x15
+
+#define CIR_SAMPLE_PERIOD	50
+
+/*
+ * Configuration Register:
+ *  Index Port
+ *  Data Port
+ */
+#define CR_INDEX_PORT		0x2e
+#define CR_DATA_PORT		0x2f
+
+/* Possible alternate values, depends on how the chip is wired */
+#define CR_INDEX_PORT2		0x4e
+#define CR_DATA_PORT2		0x4f
+
+/*
+ * GCR_CONFIG_PORT_SEL bit 4 specifies which Index Port value is
+ * active. 1 = 0x4e, 0 = 0x2e
+ */
+#define PORT_SEL_PORT_4E_EN	0x10
+
+/* Extended Function Mode enable/disable magic values */
+#define CONFIG_REG_ENABLE	0x87
+#define CONFIG_REG_DISABLE	0xaa
+
+/* Chip IDs found in CR_CHIP_ID_{HI,LO} */
+#define CHIP_ID_HIGH_F71809U	0x04
+#define CHIP_ID_LOW_F71809U	0x08
+
+/*
+ * Global control regs we need to care about:
+ *      Global Control                  def.
+ *      Register name           addr    val. */
+#define GCR_SOFTWARE_RESET	0x02 /* 0x00 */
+#define GCR_LOGICAL_DEV_NO	0x07 /* 0x00 */
+#define GCR_CHIP_ID_HI		0x20 /* 0x04 */
+#define GCR_CHIP_ID_LO		0x21 /* 0x08 */
+#define GCR_VENDOR_ID_HI	0x23 /* 0x19 */
+#define GCR_VENDOR_ID_LO	0x24 /* 0x34 */
+#define GCR_CONFIG_PORT_SEL	0x25 /* 0x01 */
+#define GCR_KBMOUSE_WAKEUP	0x27
+
+#define LOGICAL_DEV_DISABLE	0x00
+#define LOGICAL_DEV_ENABLE	0x01
+
+/* Logical device number of the CIR function */
+#define LOGICAL_DEV_CIR		0x05
+
+/* CIR Logical Device (LDN 0x08) config registers */
+#define CIR_CR_COMMAND_INDEX	0x04
+#define CIR_CR_IRCS		0x05 /* Before host writes command to IR, host
+					must set to 1. When host finshes write
+					command to IR, host must clear to 0. */
+#define CIR_CR_COMMAND_DATA	0x06 /* Host read or write comand data */
+#define CIR_CR_CLASS		0x07 /* 0xff = rx-only, 0x66 = rx + 2 tx,
+					0x33 = rx + 1 tx */
+#define CIR_CR_DEV_EN		0x30 /* bit0 = 1 enables CIR */
+#define CIR_CR_BASE_ADDR_HI	0x60 /* MSB of CIR IO base addr */
+#define CIR_CR_BASE_ADDR_LO	0x61 /* LSB of CIR IO base addr */
+#define CIR_CR_IRQ_SEL		0x70 /* bits3-0 store CIR IRQ */
+#define CIR_CR_PSOUT_STATUS	0xf1
+#define CIR_CR_WAKE_KEY3_ADDR	0xf8
+#define CIR_CR_WAKE_KEY3_CODE	0xf9
+#define CIR_CR_WAKE_KEY3_DC	0xfa
+#define CIR_CR_WAKE_CONTROL	0xfb
+#define CIR_CR_WAKE_KEY12_ADDR	0xfc
+#define CIR_CR_WAKE_KEY4_ADDR	0xfd
+#define CIR_CR_WAKE_KEY5_ADDR	0xfe
+
+#define CLASS_RX_ONLY		0xff
+#define CLASS_RX_2TX		0x66
+#define CLASS_RX_1TX		0x33
+
+/* CIR device registers */
+#define CIR_STATUS		0x00
+#define CIR_RX_DATA		0x01
+#define CIR_TX_CONTROL		0x02
+#define CIR_TX_DATA		0x03
+#define CIR_CONTROL		0x04
+
+/* Bits to enable CIR wake */
+#define LOGICAL_DEV_ACPI	0x01
+#define LDEV_ACPI_WAKE_EN_REG	0xe8
+#define ACPI_WAKE_EN_CIR_BIT	0x04
+
+#define LDEV_ACPI_PME_EN_REG	0xf0
+#define LDEV_ACPI_PME_CLR_REG	0xf1
+#define ACPI_PME_CIR_BIT	0x02
+
+#define LDEV_ACPI_STATE_REG	0xf4
+#define ACPI_STATE_CIR_BIT	0x20
+
+/*
+ * CIR status register (0x00):
+ *   7 - CIR_IRQ_EN (1 = enable CIR IRQ, 0 = disable)
+ *   3 - TX_FINISH (1 when TX finished, write 1 to clear)
+ *   2 - TX_UNDERRUN (1 on TX underrun, write 1 to clear)
+ *   1 - RX_TIMEOUT (1 on RX timeout, write 1 to clear)
+ *   0 - RX_RECEIVE (1 on RX receive, write 1 to clear)
+ */
+#define CIR_STATUS_IRQ_EN	0x80
+#define CIR_STATUS_TX_FINISH	0x08
+#define CIR_STATUS_TX_UNDERRUN	0x04
+#define CIR_STATUS_RX_TIMEOUT	0x02
+#define CIR_STATUS_RX_RECEIVE	0x01
+#define CIR_STATUS_IRQ_MASK	0x0f
+
+/*
+ * CIR TX control register (0x02):
+ *   7 - TX_START (1 to indicate TX start, auto-cleared when done)
+ *   6 - TX_END (1 to indicate TX data written to TX fifo)
+ */
+#define CIR_TX_CONTROL_TX_START	0x80
+#define CIR_TX_CONTROL_TX_END	0x40
+
diff --git a/drivers/media/rc/keymaps/rc-lme2510.c b/drivers/media/rc/keymaps/rc-lme2510.c
index afae14fd152e..129d3f9a461d 100644
--- a/drivers/media/rc/keymaps/rc-lme2510.c
+++ b/drivers/media/rc/keymaps/rc-lme2510.c
@@ -14,81 +14,81 @@
 
 static struct rc_map_table lme2510_rc[] = {
 	/* Type 1 - 26 buttons */
-	{ 0xef12ba45, KEY_0 },
-	{ 0xef12a05f, KEY_1 },
-	{ 0xef12af50, KEY_2 },
-	{ 0xef12a25d, KEY_3 },
-	{ 0xef12be41, KEY_4 },
-	{ 0xef12f50a, KEY_5 },
-	{ 0xef12bd42, KEY_6 },
-	{ 0xef12b847, KEY_7 },
-	{ 0xef12b649, KEY_8 },
-	{ 0xef12fa05, KEY_9 },
-	{ 0xef12bc43, KEY_POWER },
-	{ 0xef12b946, KEY_SUBTITLE },
-	{ 0xef12f906, KEY_PAUSE },
-	{ 0xef12fc03, KEY_MEDIA_REPEAT},
-	{ 0xef12fd02, KEY_PAUSE },
-	{ 0xef12a15e, KEY_VOLUMEUP },
-	{ 0xef12a35c, KEY_VOLUMEDOWN },
-	{ 0xef12f609, KEY_CHANNELUP },
-	{ 0xef12e51a, KEY_CHANNELDOWN },
-	{ 0xef12e11e, KEY_PLAY },
-	{ 0xef12e41b, KEY_ZOOM },
-	{ 0xef12a659, KEY_MUTE },
-	{ 0xef12a55a, KEY_TV },
-	{ 0xef12e718, KEY_RECORD },
-	{ 0xef12f807, KEY_EPG },
-	{ 0xef12fe01, KEY_STOP },
+	{ 0x10ed45, KEY_0 },
+	{ 0x10ed5f, KEY_1 },
+	{ 0x10ed50, KEY_2 },
+	{ 0x10ed5d, KEY_3 },
+	{ 0x10ed41, KEY_4 },
+	{ 0x10ed0a, KEY_5 },
+	{ 0x10ed42, KEY_6 },
+	{ 0x10ed47, KEY_7 },
+	{ 0x10ed49, KEY_8 },
+	{ 0x10ed05, KEY_9 },
+	{ 0x10ed43, KEY_POWER },
+	{ 0x10ed46, KEY_SUBTITLE },
+	{ 0x10ed06, KEY_PAUSE },
+	{ 0x10ed03, KEY_MEDIA_REPEAT},
+	{ 0x10ed02, KEY_PAUSE },
+	{ 0x10ed5e, KEY_VOLUMEUP },
+	{ 0x10ed5c, KEY_VOLUMEDOWN },
+	{ 0x10ed09, KEY_CHANNELUP },
+	{ 0x10ed1a, KEY_CHANNELDOWN },
+	{ 0x10ed1e, KEY_PLAY },
+	{ 0x10ed1b, KEY_ZOOM },
+	{ 0x10ed59, KEY_MUTE },
+	{ 0x10ed5a, KEY_TV },
+	{ 0x10ed18, KEY_RECORD },
+	{ 0x10ed07, KEY_EPG },
+	{ 0x10ed01, KEY_STOP },
 	/* Type 2 - 20 buttons */
-	{ 0xff40ea15, KEY_0 },
-	{ 0xff40f708, KEY_1 },
-	{ 0xff40f609, KEY_2 },
-	{ 0xff40f50a, KEY_3 },
-	{ 0xff40f30c, KEY_4 },
-	{ 0xff40f20d, KEY_5 },
-	{ 0xff40f10e, KEY_6 },
-	{ 0xff40ef10, KEY_7 },
-	{ 0xff40ee11, KEY_8 },
-	{ 0xff40ed12, KEY_9 },
-	{ 0xff40ff00, KEY_POWER },
-	{ 0xff40fb04, KEY_MEDIA_REPEAT}, /* Recall */
-	{ 0xff40e51a, KEY_PAUSE }, /* Timeshift */
-	{ 0xff40fd02, KEY_VOLUMEUP }, /* 2 x -/+ Keys not marked */
-	{ 0xff40f906, KEY_VOLUMEDOWN }, /* Volume defined as right hand*/
-	{ 0xff40fe01, KEY_CHANNELUP },
-	{ 0xff40fa05, KEY_CHANNELDOWN },
-	{ 0xff40eb14, KEY_ZOOM },
-	{ 0xff40e718, KEY_RECORD },
-	{ 0xff40e916, KEY_STOP },
+	{ 0xbf15, KEY_0 },
+	{ 0xbf08, KEY_1 },
+	{ 0xbf09, KEY_2 },
+	{ 0xbf0a, KEY_3 },
+	{ 0xbf0c, KEY_4 },
+	{ 0xbf0d, KEY_5 },
+	{ 0xbf0e, KEY_6 },
+	{ 0xbf10, KEY_7 },
+	{ 0xbf11, KEY_8 },
+	{ 0xbf12, KEY_9 },
+	{ 0xbf00, KEY_POWER },
+	{ 0xbf04, KEY_MEDIA_REPEAT}, /* Recall */
+	{ 0xbf1a, KEY_PAUSE }, /* Timeshift */
+	{ 0xbf02, KEY_VOLUMEUP }, /* 2 x -/+ Keys not marked */
+	{ 0xbf06, KEY_VOLUMEDOWN }, /* Volume defined as right hand*/
+	{ 0xbf01, KEY_CHANNELUP },
+	{ 0xbf05, KEY_CHANNELDOWN },
+	{ 0xbf14, KEY_ZOOM },
+	{ 0xbf18, KEY_RECORD },
+	{ 0xbf16, KEY_STOP },
 	/* Type 3 - 20 buttons */
-	{ 0xff00e31c, KEY_0 },
-	{ 0xff00f807, KEY_1 },
-	{ 0xff00ea15, KEY_2 },
-	{ 0xff00f609, KEY_3 },
-	{ 0xff00e916, KEY_4 },
-	{ 0xff00e619, KEY_5 },
-	{ 0xff00f20d, KEY_6 },
-	{ 0xff00f30c, KEY_7 },
-	{ 0xff00e718, KEY_8 },
-	{ 0xff00a15e, KEY_9 },
-	{ 0xff00ba45, KEY_POWER },
-	{ 0xff00bb44, KEY_MEDIA_REPEAT}, /* Recall */
-	{ 0xff00b54a, KEY_PAUSE }, /* Timeshift */
-	{ 0xff00b847, KEY_VOLUMEUP }, /* 2 x -/+ Keys not marked */
-	{ 0xff00bc43, KEY_VOLUMEDOWN }, /* Volume defined as right hand*/
-	{ 0xff00b946, KEY_CHANNELUP },
-	{ 0xff00bf40, KEY_CHANNELDOWN },
-	{ 0xff00f708, KEY_ZOOM },
-	{ 0xff00bd42, KEY_RECORD },
-	{ 0xff00a55a, KEY_STOP },
+	{ 0x1c, KEY_0 },
+	{ 0x07, KEY_1 },
+	{ 0x15, KEY_2 },
+	{ 0x09, KEY_3 },
+	{ 0x16, KEY_4 },
+	{ 0x19, KEY_5 },
+	{ 0x0d, KEY_6 },
+	{ 0x0c, KEY_7 },
+	{ 0x18, KEY_8 },
+	{ 0x5e, KEY_9 },
+	{ 0x45, KEY_POWER },
+	{ 0x44, KEY_MEDIA_REPEAT}, /* Recall */
+	{ 0x4a, KEY_PAUSE }, /* Timeshift */
+	{ 0x47, KEY_VOLUMEUP }, /* 2 x -/+ Keys not marked */
+	{ 0x43, KEY_VOLUMEDOWN }, /* Volume defined as right hand*/
+	{ 0x46, KEY_CHANNELUP },
+	{ 0x40, KEY_CHANNELDOWN },
+	{ 0x08, KEY_ZOOM },
+	{ 0x42, KEY_RECORD },
+	{ 0x5a, KEY_STOP },
 };
 
 static struct rc_map_list lme2510_map = {
 	.map = {
 		.scan    = lme2510_rc,
 		.size    = ARRAY_SIZE(lme2510_rc),
-		.rc_type = RC_TYPE_UNKNOWN,
+		.rc_type = RC_TYPE_NEC,
 		.name    = RC_MAP_LME2510,
 	}
 };
diff --git a/drivers/media/video/Kconfig b/drivers/media/video/Kconfig
index 3be180b3ba27..bb53de7fe408 100644
--- a/drivers/media/video/Kconfig
+++ b/drivers/media/video/Kconfig
@@ -687,7 +687,7 @@ config VIDEO_HEXIUM_GEMINI
 
 config VIDEO_TIMBERDALE
 	tristate "Support for timberdale Video In/LogiWIN"
-	depends on VIDEO_V4L2 && I2C
+	depends on VIDEO_V4L2 && I2C && DMADEVICES
 	select DMA_ENGINE
 	select TIMB_DMA
 	select VIDEO_ADV7180
@@ -757,6 +757,8 @@ config VIDEO_NOON010PC30
 	---help---
 	  This driver supports NOON010PC30 CIF camera from Siliconfile
 
+source "drivers/media/video/m5mols/Kconfig"
+
 config VIDEO_OMAP3
 	tristate "OMAP 3 Camera support (EXPERIMENTAL)"
 	select OMAP_IOMMU
@@ -952,7 +954,7 @@ config  VIDEO_SAMSUNG_S5P_FIMC
 
 config VIDEO_S5P_MIPI_CSIS
 	tristate "Samsung S5P and EXYNOS4 MIPI CSI receiver driver"
-	depends on VIDEO_V4L2 && PM_RUNTIME && VIDEO_V4L2_SUBDEV_API
+	depends on VIDEO_V4L2 && PM_RUNTIME && PLAT_S5P && VIDEO_V4L2_SUBDEV_API
 	---help---
 	  This is a v4l2 driver for Samsung S5P/EXYNOS4 MIPI-CSI receiver.
 
diff --git a/drivers/media/video/Makefile b/drivers/media/video/Makefile
index 9519160c2e01..f0fecd6f6a33 100644
--- a/drivers/media/video/Makefile
+++ b/drivers/media/video/Makefile
@@ -69,6 +69,7 @@ obj-$(CONFIG_VIDEO_MT9V011) += mt9v011.o
 obj-$(CONFIG_VIDEO_MT9V032) += mt9v032.o
 obj-$(CONFIG_VIDEO_SR030PC30)	+= sr030pc30.o
 obj-$(CONFIG_VIDEO_NOON010PC30)	+= noon010pc30.o
+obj-$(CONFIG_VIDEO_M5MOLS)	+= m5mols/
 
 obj-$(CONFIG_SOC_CAMERA_IMX074)		+= imx074.o
 obj-$(CONFIG_SOC_CAMERA_MT9M001)	+= mt9m001.o
diff --git a/drivers/media/video/cpia2/cpia2_v4l.c b/drivers/media/video/cpia2/cpia2_v4l.c
index 0073a8c55336..40eb6326e48a 100644
--- a/drivers/media/video/cpia2/cpia2_v4l.c
+++ b/drivers/media/video/cpia2/cpia2_v4l.c
@@ -438,7 +438,7 @@ static int cpia2_querycap(struct file *file, void *fh, struct v4l2_capability *v
 		strcat(vc->card, " (676/");
 		break;
 	default:
-		strcat(vc->card, " (???/");
+		strcat(vc->card, " (XXX/");
 		break;
 	}
 	switch (cam->params.version.sensor_flags) {
@@ -458,7 +458,7 @@ static int cpia2_querycap(struct file *file, void *fh, struct v4l2_capability *v
 		strcat(vc->card, "500)");
 		break;
 	default:
-		strcat(vc->card, "???)");
+		strcat(vc->card, "XXX)");
 		break;
 	}
 
diff --git a/drivers/media/video/cx23885/cx23885-cards.c b/drivers/media/video/cx23885/cx23885-cards.c
index 2354336862cf..934185cca758 100644
--- a/drivers/media/video/cx23885/cx23885-cards.c
+++ b/drivers/media/video/cx23885/cx23885-cards.c
@@ -25,8 +25,8 @@
 #include <linux/delay.h>
 #include <media/cx25840.h>
 #include <linux/firmware.h>
-#include <staging/altera.h>
 
+#include "../../../staging/altera-stapl/altera.h"
 #include "cx23885.h"
 #include "tuner-xc2028.h"
 #include "netup-init.h"
diff --git a/drivers/media/video/gspca/coarse_expo_autogain.h b/drivers/media/video/gspca/coarse_expo_autogain.h
deleted file mode 100644
index 1cb9d941eaf6..000000000000
--- a/drivers/media/video/gspca/coarse_expo_autogain.h
+++ /dev/null
@@ -1,116 +0,0 @@
-/*
- * Auto gain algorithm for camera's with a coarse exposure control
- *
- * Copyright (C) 2010 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
- * 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
- */
-
-/* Autogain + exposure algorithm for cameras with a coarse exposure control
-   (usually this means we can only control the clockdiv to change exposure)
-   As changing the clockdiv so that the fps drops from 30 to 15 fps for
-   example, will lead to a huge exposure change (it effectively doubles),
-   this algorithm normally tries to only adjust the gain (between 40 and
-   80 %) and if that does not help, only then changes exposure. This leads
-   to a much more stable image then using the knee algorithm which at
-   certain points of the knee graph will only try to adjust exposure,
-   which leads to oscilating as one exposure step is huge.
-
-   Note this assumes that the sd struct for the cam in question has
-   exp_too_high_cnt and exp_too_high_cnt int members for use by this function.
-
-   Returns 0 if no changes were made, 1 if the gain and or exposure settings
-   where changed. */
-static int gspca_coarse_grained_expo_autogain(struct gspca_dev *gspca_dev,
-	int avg_lum, int desired_avg_lum, int deadzone)
-{
-	int i, steps, gain, orig_gain, exposure, orig_exposure;
-	int gain_low, gain_high;
-	const struct ctrl *gain_ctrl = NULL;
-	const struct ctrl *exposure_ctrl = NULL;
-	struct sd *sd = (struct sd *) gspca_dev;
-	int retval = 0;
-
-	for (i = 0; i < gspca_dev->sd_desc->nctrls; i++) {
-		if (gspca_dev->ctrl_dis & (1 << i))
-			continue;
-		if (gspca_dev->sd_desc->ctrls[i].qctrl.id == V4L2_CID_GAIN)
-			gain_ctrl = &gspca_dev->sd_desc->ctrls[i];
-		if (gspca_dev->sd_desc->ctrls[i].qctrl.id == V4L2_CID_EXPOSURE)
-			exposure_ctrl = &gspca_dev->sd_desc->ctrls[i];
-	}
-	if (!gain_ctrl || !exposure_ctrl) {
-		PDEBUG(D_ERR, "Error: gspca_coarse_grained_expo_autogain "
-			"called on cam without gain or exposure");
-		return 0;
-	}
-
-	if (gain_ctrl->get(gspca_dev, &gain) ||
-	    exposure_ctrl->get(gspca_dev, &exposure))
-		return 0;
-
-	orig_gain = gain;
-	orig_exposure = exposure;
-	gain_low =
-		(gain_ctrl->qctrl.maximum - gain_ctrl->qctrl.minimum) / 5 * 2;
-	gain_low += gain_ctrl->qctrl.minimum;
-	gain_high =
-		(gain_ctrl->qctrl.maximum - gain_ctrl->qctrl.minimum) / 5 * 4;
-	gain_high += gain_ctrl->qctrl.minimum;
-
-	/* If we are of a multiple of deadzone, do multiple steps to reach the
-	   desired lumination fast (with the risc of a slight overshoot) */
-	steps = (desired_avg_lum - avg_lum) / deadzone;
-
-	PDEBUG(D_FRAM, "autogain: lum: %d, desired: %d, steps: %d",
-		avg_lum, desired_avg_lum, steps);
-
-	if ((gain + steps) > gain_high &&
-	    sd->exposure < exposure_ctrl->qctrl.maximum) {
-		gain = gain_high;
-		sd->exp_too_low_cnt++;
-	} else if ((gain + steps) < gain_low &&
-		   sd->exposure > exposure_ctrl->qctrl.minimum) {
-		gain = gain_low;
-		sd->exp_too_high_cnt++;
-	} else {
-		gain += steps;
-		if (gain > gain_ctrl->qctrl.maximum)
-			gain = gain_ctrl->qctrl.maximum;
-		else if (gain < gain_ctrl->qctrl.minimum)
-			gain = gain_ctrl->qctrl.minimum;
-		sd->exp_too_high_cnt = 0;
-		sd->exp_too_low_cnt = 0;
-	}
-
-	if (sd->exp_too_high_cnt > 3) {
-		exposure--;
-		sd->exp_too_high_cnt = 0;
-	} else if (sd->exp_too_low_cnt > 3) {
-		exposure++;
-		sd->exp_too_low_cnt = 0;
-	}
-
-	if (gain != orig_gain) {
-		gain_ctrl->set(gspca_dev, gain);
-		retval = 1;
-	}
-	if (exposure != orig_exposure) {
-		exposure_ctrl->set(gspca_dev, exposure);
-		retval = 1;
-	}
-
-	return retval;
-}
diff --git a/drivers/media/video/gspca/kinect.c b/drivers/media/video/gspca/kinect.c
index 66671a4092e4..26fc206f095e 100644
--- a/drivers/media/video/gspca/kinect.c
+++ b/drivers/media/video/gspca/kinect.c
@@ -34,7 +34,7 @@ MODULE_AUTHOR("Antonio Ospite <ospite@studenti.unina.it>");
 MODULE_DESCRIPTION("GSPCA/Kinect Sensor Device USB Camera Driver");
 MODULE_LICENSE("GPL");
 
-#ifdef DEBUG
+#ifdef GSPCA_DEBUG
 int gspca_debug = D_ERR | D_PROBE | D_CONF | D_STREAM | D_FRAM | D_PACK |
 	D_USBI | D_USBO | D_V4L2;
 #endif
diff --git a/drivers/media/video/gspca/ov519.c b/drivers/media/video/gspca/ov519.c
index 36a46fc78734..057e287b9152 100644
--- a/drivers/media/video/gspca/ov519.c
+++ b/drivers/media/video/gspca/ov519.c
@@ -609,7 +609,7 @@ static const struct v4l2_pix_format ovfx2_ov3610_mode[] = {
  * buffers, there are some pretty strict real time constraints for
  * isochronous transfer for larger frame sizes).
  */
-/*jfm: this value works well for 1600x1200, but not 800x600 - see isoc_init */
+/*jfm: this value does not work for 800x600 - see isoc_init */
 #define OVFX2_BULK_SIZE (13 * 4096)
 
 /* I2C registers */
@@ -3307,6 +3307,7 @@ static int sd_config(struct gspca_dev *gspca_dev,
 
 	gspca_dev->cam.ctrls = sd->ctrls;
 	sd->quality = QUALITY_DEF;
+	sd->frame_rate = 15;
 
 	return 0;
 }
@@ -3469,7 +3470,6 @@ static int sd_init(struct gspca_dev *gspca_dev)
 				ARRAY_SIZE(init_519_ov7660));
 		write_i2c_regvals(sd, norm_7660, ARRAY_SIZE(norm_7660));
 		sd->gspca_dev.curr_mode = 1;	/* 640x480 */
-		sd->frame_rate = 15;
 		ov519_set_mode(sd);
 		ov519_set_fr(sd);
 		sd->ctrls[COLORS].max = 4;	/* 0..4 */
@@ -3511,7 +3511,7 @@ static int sd_isoc_init(struct gspca_dev *gspca_dev)
 
 	switch (sd->bridge) {
 	case BRIDGE_OVFX2:
-		if (gspca_dev->width == 1600)
+		if (gspca_dev->width != 800)
 			gspca_dev->cam.bulk_size = OVFX2_BULK_SIZE;
 		else
 			gspca_dev->cam.bulk_size = 7 * 4096;
@@ -4478,7 +4478,7 @@ static void ovfx2_pkt_scan(struct gspca_dev *gspca_dev,
 	gspca_frame_add(gspca_dev, INTER_PACKET, data, len);
 
 	/* A short read signals EOF */
-	if (len < OVFX2_BULK_SIZE) {
+	if (len < gspca_dev->cam.bulk_size) {
 		/* If the frame is short, and it is one of the first ones
 		   the sensor and bridge are still syncing, so drop it. */
 		if (sd->first_frame) {
diff --git a/drivers/media/video/gspca/sonixj.c b/drivers/media/video/gspca/sonixj.c
index 6415aff5cbd1..81b8a600783b 100644
--- a/drivers/media/video/gspca/sonixj.c
+++ b/drivers/media/video/gspca/sonixj.c
@@ -60,7 +60,7 @@ struct sd {
 
 	u32 pktsz;			/* (used by pkt_scan) */
 	u16 npkt;
-	u8 nchg;
+	s8 nchg;
 	s8 short_mark;
 
 	u8 quality;			/* image quality */
diff --git a/drivers/media/video/gspca/stv06xx/stv06xx_hdcs.h b/drivers/media/video/gspca/stv06xx/stv06xx_hdcs.h
index b538dce96f78..a14a84a5079b 100644
--- a/drivers/media/video/gspca/stv06xx/stv06xx_hdcs.h
+++ b/drivers/media/video/gspca/stv06xx/stv06xx_hdcs.h
@@ -125,7 +125,7 @@
 #define HDCS_SLEEP_MODE		(1 << 1)
 
 #define HDCS_DEFAULT_EXPOSURE	48
-#define HDCS_DEFAULT_GAIN	128
+#define HDCS_DEFAULT_GAIN	50
 
 static int hdcs_probe_1x00(struct sd *sd);
 static int hdcs_probe_1020(struct sd *sd);
diff --git a/drivers/media/video/ivtv/ivtv-driver.c b/drivers/media/video/ivtv/ivtv-driver.c
index a4e4dfdbc2f2..0fb75524484d 100644
--- a/drivers/media/video/ivtv/ivtv-driver.c
+++ b/drivers/media/video/ivtv/ivtv-driver.c
@@ -1328,6 +1328,8 @@ int ivtv_init_on_first_open(struct ivtv *itv)
 	if (!itv->has_cx23415)
 		write_reg_sync(0x03, IVTV_REG_DMACONTROL);
 
+	ivtv_s_std_enc(itv, &itv->tuner_std);
+
 	/* Default interrupts enabled. For the PVR350 this includes the
 	   decoder VSYNC interrupt, which is always on. It is not only used
 	   during decoding but also by the OSD.
@@ -1336,12 +1338,10 @@ int ivtv_init_on_first_open(struct ivtv *itv)
 	if (itv->v4l2_cap & V4L2_CAP_VIDEO_OUTPUT) {
 		ivtv_clear_irq_mask(itv, IVTV_IRQ_MASK_INIT | IVTV_IRQ_DEC_VSYNC);
 		ivtv_set_osd_alpha(itv);
-	}
-	else
+		ivtv_s_std_dec(itv, &itv->tuner_std);
+	} else {
 		ivtv_clear_irq_mask(itv, IVTV_IRQ_MASK_INIT);
-
-	/* For cards with video out, this call needs interrupts enabled */
-	ivtv_s_std(NULL, &fh, &itv->tuner_std);
+	}
 
 	/* Setup initial controls */
 	cx2341x_handler_setup(&itv->cxhdl);
diff --git a/drivers/media/video/ivtv/ivtv-firmware.c b/drivers/media/video/ivtv/ivtv-firmware.c
index 14a1cea1d70d..02c5adebf517 100644
--- a/drivers/media/video/ivtv/ivtv-firmware.c
+++ b/drivers/media/video/ivtv/ivtv-firmware.c
@@ -280,8 +280,6 @@ int ivtv_firmware_restart(struct ivtv *itv)
 {
 	int rc = 0;
 	v4l2_std_id std;
-	struct ivtv_open_id fh;
-	fh.itv = itv;
 
 	if (itv->v4l2_cap & V4L2_CAP_VIDEO_OUTPUT)
 		/* Display test image during restart */
@@ -301,14 +299,19 @@ int ivtv_firmware_restart(struct ivtv *itv)
 	/* Allow settings to reload */
 	ivtv_mailbox_cache_invalidate(itv);
 
-	/* Restore video standard */
+	/* Restore encoder video standard */
 	std = itv->std;
 	itv->std = 0;
-	ivtv_s_std(NULL, &fh, &std);
+	ivtv_s_std_enc(itv, &std);
 
 	if (itv->v4l2_cap & V4L2_CAP_VIDEO_OUTPUT) {
 		ivtv_init_mpeg_decoder(itv);
 
+		/* Restore decoder video standard */
+		std = itv->std_out;
+		itv->std_out = 0;
+		ivtv_s_std_dec(itv, &std);
+
 		/* Restore framebuffer if active */
 		if (itv->ivtvfb_restore)
 			itv->ivtvfb_restore(itv);
diff --git a/drivers/media/video/ivtv/ivtv-ioctl.c b/drivers/media/video/ivtv/ivtv-ioctl.c
index 1689783cd19a..f9e347dae739 100644
--- a/drivers/media/video/ivtv/ivtv-ioctl.c
+++ b/drivers/media/video/ivtv/ivtv-ioctl.c
@@ -1071,28 +1071,8 @@ static int ivtv_g_std(struct file *file, void *fh, v4l2_std_id *std)
 	return 0;
 }
 
-int ivtv_s_std(struct file *file, void *fh, v4l2_std_id *std)
+void ivtv_s_std_enc(struct ivtv *itv, v4l2_std_id *std)
 {
-	DEFINE_WAIT(wait);
-	struct ivtv *itv = fh2id(fh)->itv;
-	struct yuv_playback_info *yi = &itv->yuv_info;
-	int f;
-
-	if ((*std & V4L2_STD_ALL) == 0)
-		return -EINVAL;
-
-	if (*std == itv->std)
-		return 0;
-
-	if (test_bit(IVTV_F_I_RADIO_USER, &itv->i_flags) ||
-	    atomic_read(&itv->capturing) > 0 ||
-	    atomic_read(&itv->decoding) > 0) {
-		/* Switching standard would turn off the radio or mess
-		   with already running streams, prevent that by
-		   returning EBUSY. */
-		return -EBUSY;
-	}
-
 	itv->std = *std;
 	itv->is_60hz = (*std & V4L2_STD_525_60) ? 1 : 0;
 	itv->is_50hz = !itv->is_60hz;
@@ -1106,48 +1086,79 @@ int ivtv_s_std(struct file *file, void *fh, v4l2_std_id *std)
 	if (itv->hw_flags & IVTV_HW_CX25840)
 		itv->vbi.sliced_decoder_line_size = itv->is_60hz ? 272 : 284;
 
-	IVTV_DEBUG_INFO("Switching standard to %llx.\n", (unsigned long long)itv->std);
-
 	/* Tuner */
 	ivtv_call_all(itv, core, s_std, itv->std);
+}
 
-	if (itv->v4l2_cap & V4L2_CAP_VIDEO_OUTPUT) {
-		/* set display standard */
-		itv->std_out = *std;
-		itv->is_out_60hz = itv->is_60hz;
-		itv->is_out_50hz = itv->is_50hz;
-		ivtv_call_all(itv, video, s_std_output, itv->std_out);
-
-		/*
-		 * The next firmware call is time sensitive. Time it to
-		 * avoid risk of a hard lock, by trying to ensure the call
-		 * happens within the first 100 lines of the top field.
-		 * Make 4 attempts to sync to the decoder before giving up.
-		 */
-		for (f = 0; f < 4; f++) {
-			prepare_to_wait(&itv->vsync_waitq, &wait,
-					TASK_UNINTERRUPTIBLE);
-			if ((read_reg(IVTV_REG_DEC_LINE_FIELD) >> 16) < 100)
-				break;
-			schedule_timeout(msecs_to_jiffies(25));
-		}
-		finish_wait(&itv->vsync_waitq, &wait);
-
-		if (f == 4)
-			IVTV_WARN("Mode change failed to sync to decoder\n");
-
-		ivtv_vapi(itv, CX2341X_DEC_SET_STANDARD, 1, itv->is_out_50hz);
-		itv->main_rect.left = itv->main_rect.top = 0;
-		itv->main_rect.width = 720;
-		itv->main_rect.height = itv->cxhdl.height;
-		ivtv_vapi(itv, CX2341X_OSD_SET_FRAMEBUFFER_WINDOW, 4,
-			720, itv->main_rect.height, 0, 0);
-		yi->main_rect = itv->main_rect;
-		if (!itv->osd_info) {
-			yi->osd_full_w = 720;
-			yi->osd_full_h = itv->is_out_50hz ? 576 : 480;
-		}
+void ivtv_s_std_dec(struct ivtv *itv, v4l2_std_id *std)
+{
+	struct yuv_playback_info *yi = &itv->yuv_info;
+	DEFINE_WAIT(wait);
+	int f;
+
+	/* set display standard */
+	itv->std_out = *std;
+	itv->is_out_60hz = (*std & V4L2_STD_525_60) ? 1 : 0;
+	itv->is_out_50hz = !itv->is_out_60hz;
+	ivtv_call_all(itv, video, s_std_output, itv->std_out);
+
+	/*
+	 * The next firmware call is time sensitive. Time it to
+	 * avoid risk of a hard lock, by trying to ensure the call
+	 * happens within the first 100 lines of the top field.
+	 * Make 4 attempts to sync to the decoder before giving up.
+	 */
+	for (f = 0; f < 4; f++) {
+		prepare_to_wait(&itv->vsync_waitq, &wait,
+				TASK_UNINTERRUPTIBLE);
+		if ((read_reg(IVTV_REG_DEC_LINE_FIELD) >> 16) < 100)
+			break;
+		schedule_timeout(msecs_to_jiffies(25));
 	}
+	finish_wait(&itv->vsync_waitq, &wait);
+
+	if (f == 4)
+		IVTV_WARN("Mode change failed to sync to decoder\n");
+
+	ivtv_vapi(itv, CX2341X_DEC_SET_STANDARD, 1, itv->is_out_50hz);
+	itv->main_rect.left = 0;
+	itv->main_rect.top = 0;
+	itv->main_rect.width = 720;
+	itv->main_rect.height = itv->is_out_50hz ? 576 : 480;
+	ivtv_vapi(itv, CX2341X_OSD_SET_FRAMEBUFFER_WINDOW, 4,
+		720, itv->main_rect.height, 0, 0);
+	yi->main_rect = itv->main_rect;
+	if (!itv->osd_info) {
+		yi->osd_full_w = 720;
+		yi->osd_full_h = itv->is_out_50hz ? 576 : 480;
+	}
+}
+
+int ivtv_s_std(struct file *file, void *fh, v4l2_std_id *std)
+{
+	struct ivtv *itv = fh2id(fh)->itv;
+
+	if ((*std & V4L2_STD_ALL) == 0)
+		return -EINVAL;
+
+	if (*std == itv->std)
+		return 0;
+
+	if (test_bit(IVTV_F_I_RADIO_USER, &itv->i_flags) ||
+	    atomic_read(&itv->capturing) > 0 ||
+	    atomic_read(&itv->decoding) > 0) {
+		/* Switching standard would mess with already running
+		   streams, prevent that by returning EBUSY. */
+		return -EBUSY;
+	}
+
+	IVTV_DEBUG_INFO("Switching standard to %llx.\n",
+		(unsigned long long)itv->std);
+
+	ivtv_s_std_enc(itv, std);
+	if (itv->v4l2_cap & V4L2_CAP_VIDEO_OUTPUT)
+		ivtv_s_std_dec(itv, std);
+
 	return 0;
 }
 
diff --git a/drivers/media/video/ivtv/ivtv-ioctl.h b/drivers/media/video/ivtv/ivtv-ioctl.h
index 58f003412afd..89185caeafae 100644
--- a/drivers/media/video/ivtv/ivtv-ioctl.h
+++ b/drivers/media/video/ivtv/ivtv-ioctl.h
@@ -27,7 +27,8 @@ u16 ivtv_get_service_set(struct v4l2_sliced_vbi_format *fmt);
 void ivtv_set_osd_alpha(struct ivtv *itv);
 int ivtv_set_speed(struct ivtv *itv, int speed);
 void ivtv_set_funcs(struct video_device *vdev);
-int ivtv_s_std(struct file *file, void *fh, v4l2_std_id *std);
+void ivtv_s_std_enc(struct ivtv *itv, v4l2_std_id *std);
+void ivtv_s_std_dec(struct ivtv *itv, v4l2_std_id *std);
 int ivtv_s_frequency(struct file *file, void *fh, struct v4l2_frequency *vf);
 int ivtv_s_input(struct file *file, void *fh, unsigned int inp);
 long ivtv_v4l2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
diff --git a/drivers/media/video/ivtv/ivtv-streams.c b/drivers/media/video/ivtv/ivtv-streams.c
index 942683336555..e7794dc1330e 100644
--- a/drivers/media/video/ivtv/ivtv-streams.c
+++ b/drivers/media/video/ivtv/ivtv-streams.c
@@ -589,7 +589,7 @@ int ivtv_start_v4l2_encode_stream(struct ivtv_stream *s)
 		v4l2_subdev_call(itv->sd_audio, audio, s_stream, 1);
 		/* Avoid unpredictable PCI bus hang - disable video clocks */
 		v4l2_subdev_call(itv->sd_video, video, s_stream, 0);
-		ivtv_msleep_timeout(300, 1);
+		ivtv_msleep_timeout(300, 0);
 		ivtv_vapi(itv, CX2341X_ENC_INITIALIZE_INPUT, 0);
 		v4l2_subdev_call(itv->sd_video, video, s_stream, 1);
 	}
@@ -834,7 +834,7 @@ int ivtv_stop_v4l2_encode_stream(struct ivtv_stream *s, int gop_end)
 		}
 
 		/* Handle any pending interrupts */
-		ivtv_msleep_timeout(100, 1);
+		ivtv_msleep_timeout(100, 0);
 	}
 
 	atomic_dec(&itv->capturing);
diff --git a/drivers/media/video/ivtv/ivtv-vbi.c b/drivers/media/video/ivtv/ivtv-vbi.c
index b6eb51ce7735..293db806d936 100644
--- a/drivers/media/video/ivtv/ivtv-vbi.c
+++ b/drivers/media/video/ivtv/ivtv-vbi.c
@@ -71,7 +71,7 @@ static void ivtv_set_wss(struct ivtv *itv, int enabled, int mode)
 	   Turning this signal on and off can confuse certain
 	   TVs. As far as I can tell there is no reason not to
 	   transmit this signal. */
-	if ((itv->std & V4L2_STD_625_50) && !enabled) {
+	if ((itv->std_out & V4L2_STD_625_50) && !enabled) {
 		enabled = 1;
 		mode = 0x08;  /* 4x3 full format */
 	}
diff --git a/drivers/media/video/ivtv/ivtvfb.c b/drivers/media/video/ivtv/ivtvfb.c
index 17247451c693..6b7c9c823330 100644
--- a/drivers/media/video/ivtv/ivtvfb.c
+++ b/drivers/media/video/ivtv/ivtvfb.c
@@ -247,7 +247,7 @@ static int ivtvfb_set_osd_coords(struct ivtv *itv, const struct ivtv_osd_coords
 
 static int ivtvfb_set_display_window(struct ivtv *itv, struct v4l2_rect *ivtv_window)
 {
-	int osd_height_limit = itv->is_50hz ? 576 : 480;
+	int osd_height_limit = itv->is_out_50hz ? 576 : 480;
 
 	/* Only fail if resolution too high, otherwise fudge the start coords. */
 	if ((ivtv_window->height > osd_height_limit) || (ivtv_window->width > IVTV_OSD_MAX_WIDTH))
@@ -471,9 +471,9 @@ static int ivtvfb_ioctl(struct fb_info *info, unsigned int cmd, unsigned long ar
 			vblank.flags = FB_VBLANK_HAVE_COUNT |FB_VBLANK_HAVE_VCOUNT |
 					FB_VBLANK_HAVE_VSYNC;
 			trace = read_reg(IVTV_REG_DEC_LINE_FIELD) >> 16;
-			if (itv->is_50hz && trace > 312)
+			if (itv->is_out_50hz && trace > 312)
 				trace -= 312;
-			else if (itv->is_60hz && trace > 262)
+			else if (itv->is_out_60hz && trace > 262)
 				trace -= 262;
 			if (trace == 1)
 				vblank.flags |= FB_VBLANK_VSYNCING;
@@ -656,7 +656,7 @@ static int _ivtvfb_check_var(struct fb_var_screeninfo *var, struct ivtv *itv)
 	IVTVFB_DEBUG_INFO("ivtvfb_check_var\n");
 
 	/* Set base references for mode calcs. */
-	if (itv->is_50hz) {
+	if (itv->is_out_50hz) {
 		pixclock = 84316;
 		hlimit = 776;
 		vlimit = 591;
@@ -784,12 +784,12 @@ static int _ivtvfb_check_var(struct fb_var_screeninfo *var, struct ivtv *itv)
 	   If the margins are too large, just center the screen
 	   (enforcing margins causes too many problems) */
 
-	if (var->left_margin + var->xres > IVTV_OSD_MAX_WIDTH + 1) {
+	if (var->left_margin + var->xres > IVTV_OSD_MAX_WIDTH + 1)
 		var->left_margin = 1 + ((IVTV_OSD_MAX_WIDTH - var->xres) / 2);
-	}
-	if (var->upper_margin + var->yres > (itv->is_50hz ? 577 : 481)) {
-		var->upper_margin = 1 + (((itv->is_50hz ? 576 : 480) - var->yres) / 2);
-	}
+
+	if (var->upper_margin + var->yres > (itv->is_out_50hz ? 577 : 481))
+		var->upper_margin = 1 + (((itv->is_out_50hz ? 576 : 480) -
+			var->yres) / 2);
 
 	/* Maintain overall 'size' for a constant refresh rate */
 	var->right_margin = hlimit - var->left_margin - var->xres;
@@ -836,7 +836,12 @@ static int ivtvfb_pan_display(struct fb_var_screeninfo *var, struct fb_info *inf
 	u32 osd_pan_index;
 	struct ivtv *itv = (struct ivtv *) info->par;
 
-	osd_pan_index = (var->xoffset + (var->yoffset * var->xres_virtual))*var->bits_per_pixel/8;
+	if (var->yoffset + info->var.yres > info->var.yres_virtual ||
+	    var->xoffset + info->var.xres > info->var.xres_virtual)
+		return -EINVAL;
+
+	osd_pan_index = var->yoffset * info->fix.line_length
+		      + var->xoffset * info->var.bits_per_pixel / 8;
 	write_reg(osd_pan_index, 0x02A0C);
 
 	/* Pass this info back the yuv handler */
@@ -1003,19 +1008,21 @@ static int ivtvfb_init_vidmode(struct ivtv *itv)
 	/* Hardware coords start at 0, user coords start at 1. */
 	osd_left--;
 
-	start_window.left = osd_left >= 0 ? osd_left : ((IVTV_OSD_MAX_WIDTH - start_window.width) / 2);
+	start_window.left = osd_left >= 0 ?
+		 osd_left : ((IVTV_OSD_MAX_WIDTH - start_window.width) / 2);
 
 	oi->display_byte_stride =
 			start_window.width * oi->bytes_per_pixel;
 
 	/* Vertical size & position */
 
-	max_height = itv->is_50hz ? 576 : 480;
+	max_height = itv->is_out_50hz ? 576 : 480;
 
 	if (osd_yres > max_height)
 		osd_yres = max_height;
 
-	start_window.height = osd_yres ? osd_yres : itv->is_50hz ? 480 : 400;
+	start_window.height = osd_yres ?
+		osd_yres : itv->is_out_50hz ? 480 : 400;
 
 	/* Check vertical start (osd_upper). */
 	if (osd_upper + start_window.height > max_height + 1) {
diff --git a/drivers/media/video/m5mols/Kconfig b/drivers/media/video/m5mols/Kconfig
new file mode 100644
index 000000000000..302dc3d70193
--- /dev/null
+++ b/drivers/media/video/m5mols/Kconfig
@@ -0,0 +1,5 @@
+config VIDEO_M5MOLS
+	tristate "Fujitsu M-5MOLS 8MP sensor support"
+	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
+	---help---
+	  This driver supports Fujitsu M-5MOLS camera sensor with ISP
diff --git a/drivers/media/video/m5mols/Makefile b/drivers/media/video/m5mols/Makefile
new file mode 100644
index 000000000000..0a44e028edc7
--- /dev/null
+++ b/drivers/media/video/m5mols/Makefile
@@ -0,0 +1,3 @@
+m5mols-objs	:= m5mols_core.o m5mols_controls.o m5mols_capture.o
+
+obj-$(CONFIG_VIDEO_M5MOLS)		+= m5mols.o
diff --git a/drivers/media/video/m5mols/m5mols.h b/drivers/media/video/m5mols/m5mols.h
new file mode 100644
index 000000000000..10b55c854487
--- /dev/null
+++ b/drivers/media/video/m5mols/m5mols.h
@@ -0,0 +1,296 @@
+/*
+ * Header for M-5MOLS 8M Pixel camera sensor with ISP
+ *
+ * Copyright (C) 2011 Samsung Electronics Co., Ltd.
+ * Author: HeungJun Kim, riverful.kim@samsung.com
+ *
+ * Copyright (C) 2009 Samsung Electronics Co., Ltd.
+ * Author: Dongsoo Nathaniel Kim, dongsoo45.kim@samsung.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.
+ */
+
+#ifndef M5MOLS_H
+#define M5MOLS_H
+
+#include <media/v4l2-subdev.h>
+#include "m5mols_reg.h"
+
+extern int m5mols_debug;
+
+#define to_m5mols(__sd)	container_of(__sd, struct m5mols_info, sd)
+
+#define to_sd(__ctrl) \
+	(&container_of(__ctrl->handler, struct m5mols_info, handle)->sd)
+
+enum m5mols_restype {
+	M5MOLS_RESTYPE_MONITOR,
+	M5MOLS_RESTYPE_CAPTURE,
+	M5MOLS_RESTYPE_MAX,
+};
+
+/**
+ * struct m5mols_resolution - structure for the resolution
+ * @type: resolution type according to the pixel code
+ * @width: width of the resolution
+ * @height: height of the resolution
+ * @reg: resolution preset register value
+ */
+struct m5mols_resolution {
+	u8 reg;
+	enum m5mols_restype type;
+	u16 width;
+	u16 height;
+};
+
+/**
+ * struct m5mols_exif - structure for the EXIF information of M-5MOLS
+ * @exposure_time: exposure time register value
+ * @shutter_speed: speed of the shutter register value
+ * @aperture: aperture register value
+ * @exposure_bias: it calls also EV bias
+ * @iso_speed: ISO register value
+ * @flash: status register value of the flash
+ * @sdr: status register value of the Subject Distance Range
+ * @qval: not written exact meaning in document
+ */
+struct m5mols_exif {
+	u32 exposure_time;
+	u32 shutter_speed;
+	u32 aperture;
+	u32 brightness;
+	u32 exposure_bias;
+	u16 iso_speed;
+	u16 flash;
+	u16 sdr;
+	u16 qval;
+};
+
+/**
+ * struct m5mols_capture - Structure for the capture capability
+ * @exif: EXIF information
+ * @main: size in bytes of the main image
+ * @thumb: size in bytes of the thumb image, if it was accompanied
+ * @total: total size in bytes of the produced image
+ */
+struct m5mols_capture {
+	struct m5mols_exif exif;
+	u32 main;
+	u32 thumb;
+	u32 total;
+};
+
+/**
+ * struct m5mols_scenemode - structure for the scenemode capability
+ * @metering: metering light register value
+ * @ev_bias: EV bias register value
+ * @wb_mode: mode which means the WhiteBalance is Auto or Manual
+ * @wb_preset: whitebalance preset register value in the Manual mode
+ * @chroma_en: register value whether the Chroma capability is enabled or not
+ * @chroma_lvl: chroma's level register value
+ * @edge_en: register value Whether the Edge capability is enabled or not
+ * @edge_lvl: edge's level register value
+ * @af_range: Auto Focus's range
+ * @fd_mode: Face Detection mode
+ * @mcc: Multi-axis Color Conversion which means emotion color
+ * @light: status of the Light
+ * @flash: status of the Flash
+ * @tone: Tone color which means Contrast
+ * @iso: ISO register value
+ * @capt_mode: Mode of the Image Stabilization while the camera capturing
+ * @wdr: Wide Dynamic Range register value
+ *
+ * The each value according to each scenemode is recommended in the documents.
+ */
+struct m5mols_scenemode {
+	u32 metering;
+	u32 ev_bias;
+	u32 wb_mode;
+	u32 wb_preset;
+	u32 chroma_en;
+	u32 chroma_lvl;
+	u32 edge_en;
+	u32 edge_lvl;
+	u32 af_range;
+	u32 fd_mode;
+	u32 mcc;
+	u32 light;
+	u32 flash;
+	u32 tone;
+	u32 iso;
+	u32 capt_mode;
+	u32 wdr;
+};
+
+/**
+ * struct m5mols_version - firmware version information
+ * @customer:	customer information
+ * @project:	version of project information according to customer
+ * @fw:		firmware revision
+ * @hw:		hardware revision
+ * @param:	version of the parameter
+ * @awb:	Auto WhiteBalance algorithm version
+ * @str:	information about manufacturer and packaging vendor
+ * @af:		Auto Focus version
+ *
+ * The register offset starts the customer version at 0x0, and it ends
+ * the awb version at 0x09. The customer, project information occupies 1 bytes
+ * each. And also the fw, hw, param, awb each requires 2 bytes. The str is
+ * unique string associated with firmware's version. It includes information
+ * about manufacturer and the vendor of the sensor's packaging. The least
+ * significant 2 bytes of the string indicate packaging manufacturer.
+ */
+#define VERSION_STRING_SIZE	22
+struct m5mols_version {
+	u8	customer;
+	u8	project;
+	u16	fw;
+	u16	hw;
+	u16	param;
+	u16	awb;
+	u8	str[VERSION_STRING_SIZE];
+	u8	af;
+};
+#define VERSION_SIZE sizeof(struct m5mols_version)
+
+/**
+ * struct m5mols_info - M-5MOLS driver data structure
+ * @pdata: platform data
+ * @sd: v4l-subdev instance
+ * @pad: media pad
+ * @ffmt: current fmt according to resolution type
+ * @res_type: current resolution type
+ * @code: current code
+ * @irq_waitq: waitqueue for the capture
+ * @work_irq: workqueue for the IRQ
+ * @flags: state variable for the interrupt handler
+ * @handle: control handler
+ * @autoexposure: Auto Exposure control
+ * @exposure: Exposure control
+ * @autowb: Auto White Balance control
+ * @colorfx: Color effect control
+ * @saturation:	Saturation control
+ * @zoom: Zoom control
+ * @ver: information of the version
+ * @cap: the capture mode attributes
+ * @power: current sensor's power status
+ * @ctrl_sync: true means all controls of the sensor are initialized
+ * @int_capture: true means the capture interrupt is issued once
+ * @lock_ae: true means the Auto Exposure is locked
+ * @lock_awb: true means the Aut WhiteBalance is locked
+ * @resolution:	register value for current resolution
+ * @interrupt: register value for current interrupt status
+ * @mode: register value for current operation mode
+ * @mode_save: register value for current operation mode for saving
+ * @set_power: optional power callback to the board code
+ */
+struct m5mols_info {
+	const struct m5mols_platform_data *pdata;
+	struct v4l2_subdev sd;
+	struct media_pad pad;
+	struct v4l2_mbus_framefmt ffmt[M5MOLS_RESTYPE_MAX];
+	int res_type;
+	enum v4l2_mbus_pixelcode code;
+	wait_queue_head_t irq_waitq;
+	struct work_struct work_irq;
+	unsigned long flags;
+
+	struct v4l2_ctrl_handler handle;
+	/* Autoexposure/exposure control cluster */
+	struct {
+		struct v4l2_ctrl *autoexposure;
+		struct v4l2_ctrl *exposure;
+	};
+	struct v4l2_ctrl *autowb;
+	struct v4l2_ctrl *colorfx;
+	struct v4l2_ctrl *saturation;
+	struct v4l2_ctrl *zoom;
+
+	struct m5mols_version ver;
+	struct m5mols_capture cap;
+	bool power;
+	bool ctrl_sync;
+	bool lock_ae;
+	bool lock_awb;
+	u8 resolution;
+	u32 interrupt;
+	u32 mode;
+	u32 mode_save;
+	int (*set_power)(struct device *dev, int on);
+};
+
+#define ST_CAPT_IRQ 0
+
+#define is_powered(__info) (__info->power)
+#define is_ctrl_synced(__info) (__info->ctrl_sync)
+#define is_available_af(__info)	(__info->ver.af)
+#define is_code(__code, __type) (__code == m5mols_default_ffmt[__type].code)
+#define is_manufacturer(__info, __manufacturer)	\
+				(__info->ver.str[0] == __manufacturer[0] && \
+				 __info->ver.str[1] == __manufacturer[1])
+/*
+ * I2C operation of the M-5MOLS
+ *
+ * The I2C read operation of the M-5MOLS requires 2 messages. The first
+ * message sends the information about the command, command category, and total
+ * message size. The second message is used to retrieve the data specifed in
+ * the first message
+ *
+ *   1st message                                2nd message
+ *   +-------+---+----------+-----+-------+     +------+------+------+------+
+ *   | size1 | R | category | cmd | size2 |     | d[0] | d[1] | d[2] | d[3] |
+ *   +-------+---+----------+-----+-------+     +------+------+------+------+
+ *   - size1: message data size(5 in this case)
+ *   - size2: desired buffer size of the 2nd message
+ *   - d[0..3]: according to size2
+ *
+ * The I2C write operation needs just one message. The message includes
+ * category, command, total size, and desired data.
+ *
+ *   1st message
+ *   +-------+---+----------+-----+------+------+------+------+
+ *   | size1 | W | category | cmd | d[0] | d[1] | d[2] | d[3] |
+ *   +-------+---+----------+-----+------+------+------+------+
+ *   - d[0..3]: according to size1
+ */
+int m5mols_read(struct v4l2_subdev *sd, u32 reg_comb, u32 *val);
+int m5mols_write(struct v4l2_subdev *sd, u32 reg_comb, u32 val);
+int m5mols_busy(struct v4l2_subdev *sd, u8 category, u8 cmd, u32 value);
+
+/*
+ * Mode operation of the M-5MOLS
+ *
+ * Changing the mode of the M-5MOLS is needed right executing order.
+ * There are three modes(PARAMETER, MONITOR, CAPTURE) which can be changed
+ * by user. There are various categories associated with each mode.
+ *
+ * +============================================================+
+ * | mode	| category					|
+ * +============================================================+
+ * | FLASH	| FLASH(only after Stand-by or Power-on)	|
+ * | SYSTEM	| SYSTEM(only after sensor arm-booting)		|
+ * | PARAMETER	| PARAMETER					|
+ * | MONITOR	| MONITOR(preview), Auto Focus, Face Detection	|
+ * | CAPTURE	| Single CAPTURE, Preview(recording)		|
+ * +============================================================+
+ *
+ * The available executing order between each modes are as follows:
+ *   PARAMETER <---> MONITOR <---> CAPTURE
+ */
+int m5mols_mode(struct m5mols_info *info, u32 mode);
+
+int m5mols_enable_interrupt(struct v4l2_subdev *sd, u32 reg);
+int m5mols_sync_controls(struct m5mols_info *info);
+int m5mols_start_capture(struct m5mols_info *info);
+int m5mols_do_scenemode(struct m5mols_info *info, u32 mode);
+int m5mols_lock_3a(struct m5mols_info *info, bool lock);
+int m5mols_set_ctrl(struct v4l2_ctrl *ctrl);
+
+/* The firmware function */
+int m5mols_update_fw(struct v4l2_subdev *sd,
+		     int (*set_power)(struct m5mols_info *, bool));
+
+#endif	/* M5MOLS_H */
diff --git a/drivers/media/video/m5mols/m5mols_capture.c b/drivers/media/video/m5mols/m5mols_capture.c
new file mode 100644
index 000000000000..d71a3903b60f
--- /dev/null
+++ b/drivers/media/video/m5mols/m5mols_capture.c
@@ -0,0 +1,191 @@
+/*
+ * The Capture code for Fujitsu M-5MOLS ISP
+ *
+ * Copyright (C) 2011 Samsung Electronics Co., Ltd.
+ * Author: HeungJun Kim, riverful.kim@samsung.com
+ *
+ * Copyright (C) 2009 Samsung Electronics Co., Ltd.
+ * Author: Dongsoo Nathaniel Kim, dongsoo45.kim@samsung.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/i2c.h>
+#include <linux/slab.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/version.h>
+#include <linux/gpio.h>
+#include <linux/regulator/consumer.h>
+#include <linux/videodev2.h>
+#include <linux/version.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-subdev.h>
+#include <media/m5mols.h>
+
+#include "m5mols.h"
+#include "m5mols_reg.h"
+
+static int m5mols_capture_error_handler(struct m5mols_info *info,
+					int timeout)
+{
+	int ret;
+
+	/* Disable all interrupts and clear relevant interrupt staus bits */
+	ret = m5mols_write(&info->sd, SYSTEM_INT_ENABLE,
+			   info->interrupt & ~(REG_INT_CAPTURE));
+	if (ret)
+		return ret;
+
+	if (timeout == 0)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+/**
+ * m5mols_read_rational - I2C read of a rational number
+ *
+ * Read numerator and denominator from registers @addr_num and @addr_den
+ * respectively and return the division result in @val.
+ */
+static int m5mols_read_rational(struct v4l2_subdev *sd, u32 addr_num,
+				u32 addr_den, u32 *val)
+{
+	u32 num, den;
+
+	int ret = m5mols_read(sd, addr_num, &num);
+	if (!ret)
+		ret = m5mols_read(sd, addr_den, &den);
+	if (ret)
+		return ret;
+	*val = den == 0 ? 0 : num / den;
+	return ret;
+}
+
+/**
+ * m5mols_capture_info - Gather captured image information
+ *
+ * For now it gathers only EXIF information and file size.
+ */
+static int m5mols_capture_info(struct m5mols_info *info)
+{
+	struct m5mols_exif *exif = &info->cap.exif;
+	struct v4l2_subdev *sd = &info->sd;
+	int ret;
+
+	ret = m5mols_read_rational(sd, EXIF_INFO_EXPTIME_NU,
+				   EXIF_INFO_EXPTIME_DE, &exif->exposure_time);
+	if (ret)
+		return ret;
+	ret = m5mols_read_rational(sd, EXIF_INFO_TV_NU, EXIF_INFO_TV_DE,
+				   &exif->shutter_speed);
+	if (ret)
+		return ret;
+	ret = m5mols_read_rational(sd, EXIF_INFO_AV_NU, EXIF_INFO_AV_DE,
+				   &exif->aperture);
+	if (ret)
+		return ret;
+	ret = m5mols_read_rational(sd, EXIF_INFO_BV_NU, EXIF_INFO_BV_DE,
+				   &exif->brightness);
+	if (ret)
+		return ret;
+	ret = m5mols_read_rational(sd, EXIF_INFO_EBV_NU, EXIF_INFO_EBV_DE,
+				   &exif->exposure_bias);
+	if (ret)
+		return ret;
+
+	ret = m5mols_read(sd, EXIF_INFO_ISO, (u32 *)&exif->iso_speed);
+	if (!ret)
+		ret = m5mols_read(sd, EXIF_INFO_FLASH, (u32 *)&exif->flash);
+	if (!ret)
+		ret = m5mols_read(sd, EXIF_INFO_SDR, (u32 *)&exif->sdr);
+	if (!ret)
+		ret = m5mols_read(sd, EXIF_INFO_QVAL, (u32 *)&exif->qval);
+	if (ret)
+		return ret;
+
+	if (!ret)
+		ret = m5mols_read(sd, CAPC_IMAGE_SIZE, &info->cap.main);
+	if (!ret)
+		ret = m5mols_read(sd, CAPC_THUMB_SIZE, &info->cap.thumb);
+	if (!ret)
+		info->cap.total = info->cap.main + info->cap.thumb;
+
+	return ret;
+}
+
+int m5mols_start_capture(struct m5mols_info *info)
+{
+	struct v4l2_subdev *sd = &info->sd;
+	u32 resolution = info->resolution;
+	int timeout;
+	int ret;
+
+	/*
+	 * Preparing capture. Setting control & interrupt before entering
+	 * capture mode
+	 *
+	 * 1) change to MONITOR mode for operating control & interrupt
+	 * 2) set controls (considering v4l2_control value & lock 3A)
+	 * 3) set interrupt
+	 * 4) change to CAPTURE mode
+	 */
+	ret = m5mols_mode(info, REG_MONITOR);
+	if (!ret)
+		ret = m5mols_sync_controls(info);
+	if (!ret)
+		ret = m5mols_lock_3a(info, true);
+	if (!ret)
+		ret = m5mols_enable_interrupt(sd, REG_INT_CAPTURE);
+	if (!ret)
+		ret = m5mols_mode(info, REG_CAPTURE);
+	if (!ret) {
+		/* Wait for capture interrupt, after changing capture mode */
+		timeout = wait_event_interruptible_timeout(info->irq_waitq,
+					   test_bit(ST_CAPT_IRQ, &info->flags),
+					   msecs_to_jiffies(2000));
+		if (test_and_clear_bit(ST_CAPT_IRQ, &info->flags))
+			ret = m5mols_capture_error_handler(info, timeout);
+	}
+	if (!ret)
+		ret = m5mols_lock_3a(info, false);
+	if (ret)
+		return ret;
+	/*
+	 * Starting capture. Setting capture frame count and resolution and
+	 * the format(available format: JPEG, Bayer RAW, YUV).
+	 *
+	 * 1) select single or multi(enable to 25), format, size
+	 * 2) set interrupt
+	 * 3) start capture(for main image, now)
+	 * 4) get information
+	 * 5) notify file size to v4l2 device(e.g, to s5p-fimc v4l2 device)
+	 */
+	ret = m5mols_write(sd, CAPC_SEL_FRAME, 1);
+	if (!ret)
+		ret = m5mols_write(sd, CAPP_YUVOUT_MAIN, REG_JPEG);
+	if (!ret)
+		ret = m5mols_write(sd, CAPP_MAIN_IMAGE_SIZE, resolution);
+	if (!ret)
+		ret = m5mols_enable_interrupt(sd, REG_INT_CAPTURE);
+	if (!ret)
+		ret = m5mols_write(sd, CAPC_START, REG_CAP_START_MAIN);
+	if (!ret) {
+		/* Wait for the capture completion interrupt */
+		timeout = wait_event_interruptible_timeout(info->irq_waitq,
+					   test_bit(ST_CAPT_IRQ, &info->flags),
+					   msecs_to_jiffies(2000));
+		if (test_and_clear_bit(ST_CAPT_IRQ, &info->flags)) {
+			ret = m5mols_capture_info(info);
+			if (!ret)
+				v4l2_subdev_notify(sd, 0, &info->cap.total);
+		}
+	}
+
+	return m5mols_capture_error_handler(info, timeout);
+}
diff --git a/drivers/media/video/m5mols/m5mols_controls.c b/drivers/media/video/m5mols/m5mols_controls.c
new file mode 100644
index 000000000000..817c16fec368
--- /dev/null
+++ b/drivers/media/video/m5mols/m5mols_controls.c
@@ -0,0 +1,299 @@
+/*
+ * Controls for M-5MOLS 8M Pixel camera sensor with ISP
+ *
+ * Copyright (C) 2011 Samsung Electronics Co., Ltd.
+ * Author: HeungJun Kim, riverful.kim@samsung.com
+ *
+ * Copyright (C) 2009 Samsung Electronics Co., Ltd.
+ * Author: Dongsoo Nathaniel Kim, dongsoo45.kim@samsung.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/i2c.h>
+#include <linux/delay.h>
+#include <linux/videodev2.h>
+#include <media/v4l2-ctrls.h>
+
+#include "m5mols.h"
+#include "m5mols_reg.h"
+
+static struct m5mols_scenemode m5mols_default_scenemode[] = {
+	[REG_SCENE_NORMAL] = {
+		REG_AE_CENTER, REG_AE_INDEX_00, REG_AWB_AUTO, 0,
+		REG_CHROMA_ON, 3, REG_EDGE_ON, 5,
+		REG_AF_NORMAL, REG_FD_OFF,
+		REG_MCC_NORMAL, REG_LIGHT_OFF, REG_FLASH_OFF,
+		5, REG_ISO_AUTO, REG_CAP_NONE, REG_WDR_OFF,
+	},
+	[REG_SCENE_PORTRAIT] = {
+		REG_AE_CENTER, REG_AE_INDEX_00, REG_AWB_AUTO, 0,
+		REG_CHROMA_ON, 3, REG_EDGE_ON, 4,
+		REG_AF_NORMAL, BIT_FD_EN | BIT_FD_DRAW_FACE_FRAME,
+		REG_MCC_OFF, REG_LIGHT_OFF, REG_FLASH_OFF,
+		6, REG_ISO_AUTO, REG_CAP_NONE, REG_WDR_OFF,
+	},
+	[REG_SCENE_LANDSCAPE] = {
+		REG_AE_ALL, REG_AE_INDEX_00, REG_AWB_AUTO, 0,
+		REG_CHROMA_ON, 4, REG_EDGE_ON, 6,
+		REG_AF_NORMAL, REG_FD_OFF,
+		REG_MCC_OFF, REG_LIGHT_OFF, REG_FLASH_OFF,
+		6, REG_ISO_AUTO, REG_CAP_NONE, REG_WDR_OFF,
+	},
+	[REG_SCENE_SPORTS] = {
+		REG_AE_CENTER, REG_AE_INDEX_00, REG_AWB_AUTO, 0,
+		REG_CHROMA_ON, 3, REG_EDGE_ON, 5,
+		REG_AF_NORMAL, REG_FD_OFF,
+		REG_MCC_OFF, REG_LIGHT_OFF, REG_FLASH_OFF,
+		6, REG_ISO_AUTO, REG_CAP_NONE, REG_WDR_OFF,
+	},
+	[REG_SCENE_PARTY_INDOOR] = {
+		REG_AE_CENTER, REG_AE_INDEX_00, REG_AWB_AUTO, 0,
+		REG_CHROMA_ON, 4, REG_EDGE_ON, 5,
+		REG_AF_NORMAL, REG_FD_OFF,
+		REG_MCC_OFF, REG_LIGHT_OFF, REG_FLASH_OFF,
+		6, REG_ISO_200, REG_CAP_NONE, REG_WDR_OFF,
+	},
+	[REG_SCENE_BEACH_SNOW] = {
+		REG_AE_CENTER, REG_AE_INDEX_10_POS, REG_AWB_AUTO, 0,
+		REG_CHROMA_ON, 4, REG_EDGE_ON, 5,
+		REG_AF_NORMAL, REG_FD_OFF,
+		REG_MCC_OFF, REG_LIGHT_OFF, REG_FLASH_OFF,
+		6, REG_ISO_50, REG_CAP_NONE, REG_WDR_OFF,
+	},
+	[REG_SCENE_SUNSET] = {
+		REG_AE_CENTER, REG_AE_INDEX_00, REG_AWB_PRESET,
+		REG_AWB_DAYLIGHT,
+		REG_CHROMA_ON, 3, REG_EDGE_ON, 5,
+		REG_AF_NORMAL, REG_FD_OFF,
+		REG_MCC_OFF, REG_LIGHT_OFF, REG_FLASH_OFF,
+		6, REG_ISO_AUTO, REG_CAP_NONE, REG_WDR_OFF,
+	},
+	[REG_SCENE_DAWN_DUSK] = {
+		REG_AE_CENTER, REG_AE_INDEX_00, REG_AWB_PRESET,
+		REG_AWB_FLUORESCENT_1,
+		REG_CHROMA_ON, 3, REG_EDGE_ON, 5,
+		REG_AF_NORMAL, REG_FD_OFF,
+		REG_MCC_OFF, REG_LIGHT_OFF, REG_FLASH_OFF,
+		6, REG_ISO_AUTO, REG_CAP_NONE, REG_WDR_OFF,
+	},
+	[REG_SCENE_FALL] = {
+		REG_AE_CENTER, REG_AE_INDEX_00, REG_AWB_AUTO, 0,
+		REG_CHROMA_ON, 5, REG_EDGE_ON, 5,
+		REG_AF_NORMAL, REG_FD_OFF,
+		REG_MCC_OFF, REG_LIGHT_OFF, REG_FLASH_OFF,
+		6, REG_ISO_AUTO, REG_CAP_NONE, REG_WDR_OFF,
+	},
+	[REG_SCENE_NIGHT] = {
+		REG_AE_CENTER, REG_AE_INDEX_00, REG_AWB_AUTO, 0,
+		REG_CHROMA_ON, 3, REG_EDGE_ON, 5,
+		REG_AF_NORMAL, REG_FD_OFF,
+		REG_MCC_OFF, REG_LIGHT_OFF, REG_FLASH_OFF,
+		6, REG_ISO_AUTO, REG_CAP_NONE, REG_WDR_OFF,
+	},
+	[REG_SCENE_AGAINST_LIGHT] = {
+		REG_AE_CENTER, REG_AE_INDEX_00, REG_AWB_AUTO, 0,
+		REG_CHROMA_ON, 3, REG_EDGE_ON, 5,
+		REG_AF_NORMAL, REG_FD_OFF,
+		REG_MCC_OFF, REG_LIGHT_OFF, REG_FLASH_OFF,
+		6, REG_ISO_AUTO, REG_CAP_NONE, REG_WDR_OFF,
+	},
+	[REG_SCENE_FIRE] = {
+		REG_AE_CENTER, REG_AE_INDEX_00, REG_AWB_AUTO, 0,
+		REG_CHROMA_ON, 3, REG_EDGE_ON, 5,
+		REG_AF_NORMAL, REG_FD_OFF,
+		REG_MCC_OFF, REG_LIGHT_OFF, REG_FLASH_OFF,
+		6, REG_ISO_50, REG_CAP_NONE, REG_WDR_OFF,
+	},
+	[REG_SCENE_TEXT] = {
+		REG_AE_CENTER, REG_AE_INDEX_00, REG_AWB_AUTO, 0,
+		REG_CHROMA_ON, 3, REG_EDGE_ON, 7,
+		REG_AF_MACRO, REG_FD_OFF,
+		REG_MCC_OFF, REG_LIGHT_OFF, REG_FLASH_OFF,
+		6, REG_ISO_AUTO, REG_CAP_ANTI_SHAKE, REG_WDR_ON,
+	},
+	[REG_SCENE_CANDLE] = {
+		REG_AE_CENTER, REG_AE_INDEX_00, REG_AWB_AUTO, 0,
+		REG_CHROMA_ON, 3, REG_EDGE_ON, 5,
+		REG_AF_NORMAL, REG_FD_OFF,
+		REG_MCC_OFF, REG_LIGHT_OFF, REG_FLASH_OFF,
+		6, REG_ISO_AUTO, REG_CAP_NONE, REG_WDR_OFF,
+	},
+};
+
+/**
+ * m5mols_do_scenemode() - Change current scenemode
+ * @mode:	Desired mode of the scenemode
+ *
+ * WARNING: The execution order is important. Do not change the order.
+ */
+int m5mols_do_scenemode(struct m5mols_info *info, u32 mode)
+{
+	struct v4l2_subdev *sd = &info->sd;
+	struct m5mols_scenemode scenemode = m5mols_default_scenemode[mode];
+	int ret;
+
+	if (mode > REG_SCENE_CANDLE)
+		return -EINVAL;
+
+	ret = m5mols_lock_3a(info, false);
+	if (!ret)
+		ret = m5mols_write(sd, AE_EV_PRESET_MONITOR, mode);
+	if (!ret)
+		ret = m5mols_write(sd, AE_EV_PRESET_CAPTURE, mode);
+	if (!ret)
+		ret = m5mols_write(sd, AE_MODE, scenemode.metering);
+	if (!ret)
+		ret = m5mols_write(sd, AE_INDEX, scenemode.ev_bias);
+	if (!ret)
+		ret = m5mols_write(sd, AWB_MODE, scenemode.wb_mode);
+	if (!ret)
+		ret = m5mols_write(sd, AWB_MANUAL, scenemode.wb_preset);
+	if (!ret)
+		ret = m5mols_write(sd, MON_CHROMA_EN, scenemode.chroma_en);
+	if (!ret)
+		ret = m5mols_write(sd, MON_CHROMA_LVL, scenemode.chroma_lvl);
+	if (!ret)
+		ret = m5mols_write(sd, MON_EDGE_EN, scenemode.edge_en);
+	if (!ret)
+		ret = m5mols_write(sd, MON_EDGE_LVL, scenemode.edge_lvl);
+	if (!ret && is_available_af(info))
+		ret = m5mols_write(sd, AF_MODE, scenemode.af_range);
+	if (!ret && is_available_af(info))
+		ret = m5mols_write(sd, FD_CTL, scenemode.fd_mode);
+	if (!ret)
+		ret = m5mols_write(sd, MON_TONE_CTL, scenemode.tone);
+	if (!ret)
+		ret = m5mols_write(sd, AE_ISO, scenemode.iso);
+	if (!ret)
+		ret = m5mols_mode(info, REG_CAPTURE);
+	if (!ret)
+		ret = m5mols_write(sd, CAPP_WDR_EN, scenemode.wdr);
+	if (!ret)
+		ret = m5mols_write(sd, CAPP_MCC_MODE, scenemode.mcc);
+	if (!ret)
+		ret = m5mols_write(sd, CAPP_LIGHT_CTRL, scenemode.light);
+	if (!ret)
+		ret = m5mols_write(sd, CAPP_FLASH_CTRL, scenemode.flash);
+	if (!ret)
+		ret = m5mols_write(sd, CAPC_MODE, scenemode.capt_mode);
+	if (!ret)
+		ret = m5mols_mode(info, REG_MONITOR);
+
+	return ret;
+}
+
+static int m5mols_lock_ae(struct m5mols_info *info, bool lock)
+{
+	int ret = 0;
+
+	if (info->lock_ae != lock)
+		ret = m5mols_write(&info->sd, AE_LOCK,
+				lock ? REG_AE_LOCK : REG_AE_UNLOCK);
+	if (!ret)
+		info->lock_ae = lock;
+
+	return ret;
+}
+
+static int m5mols_lock_awb(struct m5mols_info *info, bool lock)
+{
+	int ret = 0;
+
+	if (info->lock_awb != lock)
+		ret = m5mols_write(&info->sd, AWB_LOCK,
+				lock ? REG_AWB_LOCK : REG_AWB_UNLOCK);
+	if (!ret)
+		info->lock_awb = lock;
+
+	return ret;
+}
+
+/* m5mols_lock_3a() - Lock 3A(Auto Exposure, Auto Whitebalance, Auto Focus) */
+int m5mols_lock_3a(struct m5mols_info *info, bool lock)
+{
+	int ret;
+
+	ret = m5mols_lock_ae(info, lock);
+	if (!ret)
+		ret = m5mols_lock_awb(info, lock);
+	/* Don't need to handle unlocking AF */
+	if (!ret && is_available_af(info) && lock)
+		ret = m5mols_write(&info->sd, AF_EXECUTE, REG_AF_STOP);
+
+	return ret;
+}
+
+/* m5mols_set_ctrl() - The main s_ctrl function called by m5mols_set_ctrl() */
+int m5mols_set_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct v4l2_subdev *sd = to_sd(ctrl);
+	struct m5mols_info *info = to_m5mols(sd);
+	int ret;
+
+	switch (ctrl->id) {
+	case V4L2_CID_ZOOM_ABSOLUTE:
+		return m5mols_write(sd, MON_ZOOM, ctrl->val);
+
+	case V4L2_CID_EXPOSURE_AUTO:
+		ret = m5mols_lock_ae(info,
+			ctrl->val == V4L2_EXPOSURE_AUTO ? false : true);
+		if (!ret && ctrl->val == V4L2_EXPOSURE_AUTO)
+			ret = m5mols_write(sd, AE_MODE, REG_AE_ALL);
+		if (!ret && ctrl->val == V4L2_EXPOSURE_MANUAL) {
+			int val = info->exposure->val;
+			ret = m5mols_write(sd, AE_MODE, REG_AE_OFF);
+			if (!ret)
+				ret = m5mols_write(sd, AE_MAN_GAIN_MON, val);
+			if (!ret)
+				ret = m5mols_write(sd, AE_MAN_GAIN_CAP, val);
+		}
+		return ret;
+
+	case V4L2_CID_AUTO_WHITE_BALANCE:
+		ret = m5mols_lock_awb(info, ctrl->val ? false : true);
+		if (!ret)
+			ret = m5mols_write(sd, AWB_MODE, ctrl->val ?
+				REG_AWB_AUTO : REG_AWB_PRESET);
+		return ret;
+
+	case V4L2_CID_SATURATION:
+		ret = m5mols_write(sd, MON_CHROMA_LVL, ctrl->val);
+		if (!ret)
+			ret = m5mols_write(sd, MON_CHROMA_EN, REG_CHROMA_ON);
+		return ret;
+
+	case V4L2_CID_COLORFX:
+		/*
+		 * This control uses two kinds of registers: normal & color.
+		 * The normal effect belongs to category 1, while the color
+		 * one belongs to category 2.
+		 *
+		 * The normal effect uses one register: CAT1_EFFECT.
+		 * The color effect uses three registers:
+		 * CAT2_COLOR_EFFECT, CAT2_CFIXR, CAT2_CFIXB.
+		 */
+		ret = m5mols_write(sd, PARM_EFFECT,
+			ctrl->val == V4L2_COLORFX_NEGATIVE ? REG_EFFECT_NEGA :
+			ctrl->val == V4L2_COLORFX_EMBOSS ? REG_EFFECT_EMBOSS :
+			REG_EFFECT_OFF);
+		if (!ret)
+			ret = m5mols_write(sd, MON_EFFECT,
+				ctrl->val == V4L2_COLORFX_SEPIA ?
+				REG_COLOR_EFFECT_ON : REG_COLOR_EFFECT_OFF);
+		if (!ret)
+			ret = m5mols_write(sd, MON_CFIXR,
+				ctrl->val == V4L2_COLORFX_SEPIA ?
+				REG_CFIXR_SEPIA : 0);
+		if (!ret)
+			ret = m5mols_write(sd, MON_CFIXB,
+				ctrl->val == V4L2_COLORFX_SEPIA ?
+				REG_CFIXB_SEPIA : 0);
+		return ret;
+	}
+
+	return -EINVAL;
+}
diff --git a/drivers/media/video/m5mols/m5mols_core.c b/drivers/media/video/m5mols/m5mols_core.c
new file mode 100644
index 000000000000..76eac26e84ae
--- /dev/null
+++ b/drivers/media/video/m5mols/m5mols_core.c
@@ -0,0 +1,1004 @@
+/*
+ * Driver for M-5MOLS 8M Pixel camera sensor with ISP
+ *
+ * Copyright (C) 2011 Samsung Electronics Co., Ltd.
+ * Author: HeungJun Kim, riverful.kim@samsung.com
+ *
+ * Copyright (C) 2009 Samsung Electronics Co., Ltd.
+ * Author: Dongsoo Nathaniel Kim, dongsoo45.kim@samsung.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/i2c.h>
+#include <linux/slab.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/version.h>
+#include <linux/gpio.h>
+#include <linux/regulator/consumer.h>
+#include <linux/videodev2.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-subdev.h>
+#include <media/m5mols.h>
+
+#include "m5mols.h"
+#include "m5mols_reg.h"
+
+int m5mols_debug;
+module_param(m5mols_debug, int, 0644);
+
+#define MODULE_NAME		"M5MOLS"
+#define M5MOLS_I2C_CHECK_RETRY	500
+
+/* The regulator consumer names for external voltage regulators */
+static struct regulator_bulk_data supplies[] = {
+	{
+		.supply = "core",	/* ARM core power, 1.2V */
+	}, {
+		.supply	= "dig_18",	/* digital power 1, 1.8V */
+	}, {
+		.supply	= "d_sensor",	/* sensor power 1, 1.8V */
+	}, {
+		.supply	= "dig_28",	/* digital power 2, 2.8V */
+	}, {
+		.supply	= "a_sensor",	/* analog power */
+	}, {
+		.supply	= "dig_12",	/* digital power 3, 1.2V */
+	},
+};
+
+static struct v4l2_mbus_framefmt m5mols_default_ffmt[M5MOLS_RESTYPE_MAX] = {
+	[M5MOLS_RESTYPE_MONITOR] = {
+		.width		= 1920,
+		.height		= 1080,
+		.code		= V4L2_MBUS_FMT_VYUY8_2X8,
+		.field		= V4L2_FIELD_NONE,
+		.colorspace	= V4L2_COLORSPACE_JPEG,
+	},
+	[M5MOLS_RESTYPE_CAPTURE] = {
+		.width		= 1920,
+		.height		= 1080,
+		.code		= V4L2_MBUS_FMT_JPEG_1X8,
+		.field		= V4L2_FIELD_NONE,
+		.colorspace	= V4L2_COLORSPACE_JPEG,
+	},
+};
+#define SIZE_DEFAULT_FFMT	ARRAY_SIZE(m5mols_default_ffmt)
+
+static const struct m5mols_resolution m5mols_reg_res[] = {
+	{ 0x01, M5MOLS_RESTYPE_MONITOR, 128, 96 },	/* SUB-QCIF */
+	{ 0x03, M5MOLS_RESTYPE_MONITOR, 160, 120 },	/* QQVGA */
+	{ 0x05, M5MOLS_RESTYPE_MONITOR, 176, 144 },	/* QCIF */
+	{ 0x06, M5MOLS_RESTYPE_MONITOR, 176, 176 },
+	{ 0x08, M5MOLS_RESTYPE_MONITOR, 240, 320 },	/* QVGA */
+	{ 0x09, M5MOLS_RESTYPE_MONITOR, 320, 240 },	/* QVGA */
+	{ 0x0c, M5MOLS_RESTYPE_MONITOR, 240, 400 },	/* WQVGA */
+	{ 0x0d, M5MOLS_RESTYPE_MONITOR, 400, 240 },	/* WQVGA */
+	{ 0x0e, M5MOLS_RESTYPE_MONITOR, 352, 288 },	/* CIF */
+	{ 0x13, M5MOLS_RESTYPE_MONITOR, 480, 360 },
+	{ 0x15, M5MOLS_RESTYPE_MONITOR, 640, 360 },	/* qHD */
+	{ 0x17, M5MOLS_RESTYPE_MONITOR, 640, 480 },	/* VGA */
+	{ 0x18, M5MOLS_RESTYPE_MONITOR, 720, 480 },
+	{ 0x1a, M5MOLS_RESTYPE_MONITOR, 800, 480 },	/* WVGA */
+	{ 0x1f, M5MOLS_RESTYPE_MONITOR, 800, 600 },	/* SVGA */
+	{ 0x21, M5MOLS_RESTYPE_MONITOR, 1280, 720 },	/* HD */
+	{ 0x25, M5MOLS_RESTYPE_MONITOR, 1920, 1080 },	/* 1080p */
+	{ 0x29, M5MOLS_RESTYPE_MONITOR, 3264, 2448 },	/* 2.63fps 8M */
+	{ 0x39, M5MOLS_RESTYPE_MONITOR, 800, 602 },	/* AHS_MON debug */
+
+	{ 0x02, M5MOLS_RESTYPE_CAPTURE, 320, 240 },	/* QVGA */
+	{ 0x04, M5MOLS_RESTYPE_CAPTURE, 400, 240 },	/* WQVGA */
+	{ 0x07, M5MOLS_RESTYPE_CAPTURE, 480, 360 },
+	{ 0x08, M5MOLS_RESTYPE_CAPTURE, 640, 360 },	/* qHD */
+	{ 0x09, M5MOLS_RESTYPE_CAPTURE, 640, 480 },	/* VGA */
+	{ 0x0a, M5MOLS_RESTYPE_CAPTURE, 800, 480 },	/* WVGA */
+	{ 0x10, M5MOLS_RESTYPE_CAPTURE, 1280, 720 },	/* HD */
+	{ 0x14, M5MOLS_RESTYPE_CAPTURE, 1280, 960 },	/* 1M */
+	{ 0x17, M5MOLS_RESTYPE_CAPTURE, 1600, 1200 },	/* 2M */
+	{ 0x19, M5MOLS_RESTYPE_CAPTURE, 1920, 1080 },	/* Full-HD */
+	{ 0x1a, M5MOLS_RESTYPE_CAPTURE, 2048, 1152 },	/* 3Mega */
+	{ 0x1b, M5MOLS_RESTYPE_CAPTURE, 2048, 1536 },
+	{ 0x1c, M5MOLS_RESTYPE_CAPTURE, 2560, 1440 },	/* 4Mega */
+	{ 0x1d, M5MOLS_RESTYPE_CAPTURE, 2560, 1536 },
+	{ 0x1f, M5MOLS_RESTYPE_CAPTURE, 2560, 1920 },	/* 5Mega */
+	{ 0x21, M5MOLS_RESTYPE_CAPTURE, 3264, 1836 },	/* 6Mega */
+	{ 0x22, M5MOLS_RESTYPE_CAPTURE, 3264, 1960 },
+	{ 0x25, M5MOLS_RESTYPE_CAPTURE, 3264, 2448 },	/* 8Mega */
+};
+
+/**
+ * m5mols_swap_byte - an byte array to integer conversion function
+ * @size: size in bytes of I2C packet defined in the M-5MOLS datasheet
+ *
+ * Convert I2C data byte array with performing any required byte
+ * reordering to assure proper values for each data type, regardless
+ * of the architecture endianness.
+ */
+static u32 m5mols_swap_byte(u8 *data, u8 length)
+{
+	if (length == 1)
+		return *data;
+	else if (length == 2)
+		return be16_to_cpu(*((u16 *)data));
+	else
+		return be32_to_cpu(*((u32 *)data));
+}
+
+/**
+ * m5mols_read -  I2C read function
+ * @reg: combination of size, category and command for the I2C packet
+ * @val: read value
+ */
+int m5mols_read(struct v4l2_subdev *sd, u32 reg, u32 *val)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	u8 rbuf[M5MOLS_I2C_MAX_SIZE + 1];
+	u8 size = I2C_SIZE(reg);
+	u8 category = I2C_CATEGORY(reg);
+	u8 cmd = I2C_COMMAND(reg);
+	struct i2c_msg msg[2];
+	u8 wbuf[5];
+	int ret;
+
+	if (!client->adapter)
+		return -ENODEV;
+
+	if (size != 1 && size != 2 && size != 4) {
+		v4l2_err(sd, "Wrong data size\n");
+		return -EINVAL;
+	}
+
+	msg[0].addr = client->addr;
+	msg[0].flags = 0;
+	msg[0].len = 5;
+	msg[0].buf = wbuf;
+	wbuf[0] = 5;
+	wbuf[1] = M5MOLS_BYTE_READ;
+	wbuf[2] = category;
+	wbuf[3] = cmd;
+	wbuf[4] = size;
+
+	msg[1].addr = client->addr;
+	msg[1].flags = I2C_M_RD;
+	msg[1].len = size + 1;
+	msg[1].buf = rbuf;
+
+	/* minimum stabilization time */
+	usleep_range(200, 200);
+
+	ret = i2c_transfer(client->adapter, msg, 2);
+	if (ret < 0) {
+		v4l2_err(sd, "read failed: size:%d cat:%02x cmd:%02x. %d\n",
+			 size, category, cmd, ret);
+		return ret;
+	}
+
+	*val = m5mols_swap_byte(&rbuf[1], size);
+
+	return 0;
+}
+
+/**
+ * m5mols_write - I2C command write function
+ * @reg: combination of size, category and command for the I2C packet
+ * @val: value to write
+ */
+int m5mols_write(struct v4l2_subdev *sd, u32 reg, u32 val)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	u8 wbuf[M5MOLS_I2C_MAX_SIZE + 4];
+	u8 category = I2C_CATEGORY(reg);
+	u8 cmd = I2C_COMMAND(reg);
+	u8 size	= I2C_SIZE(reg);
+	u32 *buf = (u32 *)&wbuf[4];
+	struct i2c_msg msg[1];
+	int ret;
+
+	if (!client->adapter)
+		return -ENODEV;
+
+	if (size != 1 && size != 2 && size != 4) {
+		v4l2_err(sd, "Wrong data size\n");
+		return -EINVAL;
+	}
+
+	msg->addr = client->addr;
+	msg->flags = 0;
+	msg->len = (u16)size + 4;
+	msg->buf = wbuf;
+	wbuf[0] = size + 4;
+	wbuf[1] = M5MOLS_BYTE_WRITE;
+	wbuf[2] = category;
+	wbuf[3] = cmd;
+
+	*buf = m5mols_swap_byte((u8 *)&val, size);
+
+	usleep_range(200, 200);
+
+	ret = i2c_transfer(client->adapter, msg, 1);
+	if (ret < 0) {
+		v4l2_err(sd, "write failed: size:%d cat:%02x cmd:%02x. %d\n",
+			size, category, cmd, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int m5mols_busy(struct v4l2_subdev *sd, u8 category, u8 cmd, u32 mask)
+{
+	u32 busy, i;
+	int ret;
+
+	for (i = 0; i < M5MOLS_I2C_CHECK_RETRY; i++) {
+		ret = m5mols_read(sd, I2C_REG(category, cmd, 1), &busy);
+		if (ret < 0)
+			return ret;
+		if ((busy & mask) == mask)
+			return 0;
+	}
+	return -EBUSY;
+}
+
+/**
+ * m5mols_enable_interrupt - Clear interrupt pending bits and unmask interrupts
+ *
+ * Before writing desired interrupt value the INT_FACTOR register should
+ * be read to clear pending interrupts.
+ */
+int m5mols_enable_interrupt(struct v4l2_subdev *sd, u32 reg)
+{
+	struct m5mols_info *info = to_m5mols(sd);
+	u32 mask = is_available_af(info) ? REG_INT_AF : 0;
+	u32 dummy;
+	int ret;
+
+	ret = m5mols_read(sd, SYSTEM_INT_FACTOR, &dummy);
+	if (!ret)
+		ret = m5mols_write(sd, SYSTEM_INT_ENABLE, reg & ~mask);
+	return ret;
+}
+
+/**
+ * m5mols_reg_mode - Write the mode and check busy status
+ *
+ * It always accompanies a little delay changing the M-5MOLS mode, so it is
+ * needed checking current busy status to guarantee right mode.
+ */
+static int m5mols_reg_mode(struct v4l2_subdev *sd, u32 mode)
+{
+	int ret = m5mols_write(sd, SYSTEM_SYSMODE, mode);
+
+	return ret ? ret : m5mols_busy(sd, CAT_SYSTEM, CAT0_SYSMODE, mode);
+}
+
+/**
+ * m5mols_mode - manage the M-5MOLS's mode
+ * @mode: the required operation mode
+ *
+ * The commands of M-5MOLS are grouped into specific modes. Each functionality
+ * can be guaranteed only when the sensor is operating in mode which which
+ * a command belongs to.
+ */
+int m5mols_mode(struct m5mols_info *info, u32 mode)
+{
+	struct v4l2_subdev *sd = &info->sd;
+	int ret = -EINVAL;
+	u32 reg;
+
+	if (mode < REG_PARAMETER && mode > REG_CAPTURE)
+		return ret;
+
+	ret = m5mols_read(sd, SYSTEM_SYSMODE, &reg);
+	if ((!ret && reg == mode) || ret)
+		return ret;
+
+	switch (reg) {
+	case REG_PARAMETER:
+		ret = m5mols_reg_mode(sd, REG_MONITOR);
+		if (!ret && mode == REG_MONITOR)
+			break;
+		if (!ret)
+			ret = m5mols_reg_mode(sd, REG_CAPTURE);
+		break;
+
+	case REG_MONITOR:
+		if (mode == REG_PARAMETER) {
+			ret = m5mols_reg_mode(sd, REG_PARAMETER);
+			break;
+		}
+
+		ret = m5mols_reg_mode(sd, REG_CAPTURE);
+		break;
+
+	case REG_CAPTURE:
+		ret = m5mols_reg_mode(sd, REG_MONITOR);
+		if (!ret && mode == REG_MONITOR)
+			break;
+		if (!ret)
+			ret = m5mols_reg_mode(sd, REG_PARAMETER);
+		break;
+
+	default:
+		v4l2_warn(sd, "Wrong mode: %d\n", mode);
+	}
+
+	if (!ret)
+		info->mode = mode;
+
+	return ret;
+}
+
+/**
+ * m5mols_get_version - retrieve full revisions information of M-5MOLS
+ *
+ * The version information includes revisions of hardware and firmware,
+ * AutoFocus alghorithm version and the version string.
+ */
+static int m5mols_get_version(struct v4l2_subdev *sd)
+{
+	struct m5mols_info *info = to_m5mols(sd);
+	union {
+		struct m5mols_version ver;
+		u8 bytes[VERSION_SIZE];
+	} version;
+	u32 *value;
+	u8 cmd = CAT0_VER_CUSTOMER;
+	int ret;
+
+	do {
+		value = (u32 *)&version.bytes[cmd];
+		ret = m5mols_read(sd, SYSTEM_CMD(cmd), value);
+		if (ret)
+			return ret;
+	} while (cmd++ != CAT0_VER_AWB);
+
+	do {
+		value = (u32 *)&version.bytes[cmd];
+		ret = m5mols_read(sd, SYSTEM_VER_STRING, value);
+		if (ret)
+			return ret;
+		if (cmd >= VERSION_SIZE - 1)
+			return -EINVAL;
+	} while (version.bytes[cmd++]);
+
+	value = (u32 *)&version.bytes[cmd];
+	ret = m5mols_read(sd, AF_VERSION, value);
+	if (ret)
+		return ret;
+
+	/* store version information swapped for being readable */
+	info->ver	= version.ver;
+	info->ver.fw	= be16_to_cpu(info->ver.fw);
+	info->ver.hw	= be16_to_cpu(info->ver.hw);
+	info->ver.param	= be16_to_cpu(info->ver.param);
+	info->ver.awb	= be16_to_cpu(info->ver.awb);
+
+	v4l2_info(sd, "Manufacturer\t[%s]\n",
+			is_manufacturer(info, REG_SAMSUNG_ELECTRO) ?
+			"Samsung Electro-Machanics" :
+			is_manufacturer(info, REG_SAMSUNG_OPTICS) ?
+			"Samsung Fiber-Optics" :
+			is_manufacturer(info, REG_SAMSUNG_TECHWIN) ?
+			"Samsung Techwin" : "None");
+	v4l2_info(sd, "Customer/Project\t[0x%02x/0x%02x]\n",
+			info->ver.customer, info->ver.project);
+
+	if (!is_available_af(info))
+		v4l2_info(sd, "No support Auto Focus on this firmware\n");
+
+	return ret;
+}
+
+/**
+ * __find_restype - Lookup M-5MOLS resolution type according to pixel code
+ * @code: pixel code
+ */
+static enum m5mols_restype __find_restype(enum v4l2_mbus_pixelcode code)
+{
+	enum m5mols_restype type = M5MOLS_RESTYPE_MONITOR;
+
+	do {
+		if (code == m5mols_default_ffmt[type].code)
+			return type;
+	} while (type++ != SIZE_DEFAULT_FFMT);
+
+	return 0;
+}
+
+/**
+ * __find_resolution - Lookup preset and type of M-5MOLS's resolution
+ * @mf: pixel format to find/negotiate the resolution preset for
+ * @type: M-5MOLS resolution type
+ * @resolution:	M-5MOLS resolution preset register value
+ *
+ * Find nearest resolution matching resolution preset and adjust mf
+ * to supported values.
+ */
+static int __find_resolution(struct v4l2_subdev *sd,
+			     struct v4l2_mbus_framefmt *mf,
+			     enum m5mols_restype *type,
+			     u32 *resolution)
+{
+	const struct m5mols_resolution *fsize = &m5mols_reg_res[0];
+	const struct m5mols_resolution *match = NULL;
+	enum m5mols_restype stype = __find_restype(mf->code);
+	int i = ARRAY_SIZE(m5mols_reg_res);
+	unsigned int min_err = ~0;
+
+	while (i--) {
+		int err;
+		if (stype == fsize->type) {
+			err = abs(fsize->width - mf->width)
+				+ abs(fsize->height - mf->height);
+
+			if (err < min_err) {
+				min_err = err;
+				match = fsize;
+			}
+		}
+		fsize++;
+	}
+	if (match) {
+		mf->width  = match->width;
+		mf->height = match->height;
+		*resolution = match->reg;
+		*type = stype;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static struct v4l2_mbus_framefmt *__find_format(struct m5mols_info *info,
+				struct v4l2_subdev_fh *fh,
+				enum v4l2_subdev_format_whence which,
+				enum m5mols_restype type)
+{
+	if (which == V4L2_SUBDEV_FORMAT_TRY)
+		return fh ? v4l2_subdev_get_try_format(fh, 0) : NULL;
+
+	return &info->ffmt[type];
+}
+
+static int m5mols_get_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh,
+			  struct v4l2_subdev_format *fmt)
+{
+	struct m5mols_info *info = to_m5mols(sd);
+	struct v4l2_mbus_framefmt *format;
+
+	if (fmt->pad != 0)
+		return -EINVAL;
+
+	format = __find_format(info, fh, fmt->which, info->res_type);
+	if (!format)
+		return -EINVAL;
+
+	fmt->format = *format;
+	return 0;
+}
+
+static int m5mols_set_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh,
+			  struct v4l2_subdev_format *fmt)
+{
+	struct m5mols_info *info = to_m5mols(sd);
+	struct v4l2_mbus_framefmt *format = &fmt->format;
+	struct v4l2_mbus_framefmt *sfmt;
+	enum m5mols_restype type;
+	u32 resolution = 0;
+	int ret;
+
+	if (fmt->pad != 0)
+		return -EINVAL;
+
+	ret = __find_resolution(sd, format, &type, &resolution);
+	if (ret < 0)
+		return ret;
+
+	sfmt = __find_format(info, fh, fmt->which, type);
+	if (!sfmt)
+		return 0;
+
+	*sfmt		= m5mols_default_ffmt[type];
+	sfmt->width	= format->width;
+	sfmt->height	= format->height;
+
+	if (fmt->which == V4L2_SUBDEV_FORMAT_ACTIVE) {
+		info->resolution = resolution;
+		info->code = format->code;
+		info->res_type = type;
+	}
+
+	return 0;
+}
+
+static int m5mols_enum_mbus_code(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_fh *fh,
+				 struct v4l2_subdev_mbus_code_enum *code)
+{
+	if (!code || code->index >= SIZE_DEFAULT_FFMT)
+		return -EINVAL;
+
+	code->code = m5mols_default_ffmt[code->index].code;
+
+	return 0;
+}
+
+static struct v4l2_subdev_pad_ops m5mols_pad_ops = {
+	.enum_mbus_code	= m5mols_enum_mbus_code,
+	.get_fmt	= m5mols_get_fmt,
+	.set_fmt	= m5mols_set_fmt,
+};
+
+/**
+ * m5mols_sync_controls - Apply default scene mode and the current controls
+ *
+ * This is used only streaming for syncing between v4l2_ctrl framework and
+ * m5mols's controls. First, do the scenemode to the sensor, then call
+ * v4l2_ctrl_handler_setup. It can be same between some commands and
+ * the scenemode's in the default v4l2_ctrls. But, such commands of control
+ * should be prior to the scenemode's one.
+ */
+int m5mols_sync_controls(struct m5mols_info *info)
+{
+	int ret = -EINVAL;
+
+	if (!is_ctrl_synced(info)) {
+		ret = m5mols_do_scenemode(info, REG_SCENE_NORMAL);
+		if (ret)
+			return ret;
+
+		v4l2_ctrl_handler_setup(&info->handle);
+		info->ctrl_sync = true;
+	}
+
+	return ret;
+}
+
+/**
+ * m5mols_start_monitor - Start the monitor mode
+ *
+ * Before applying the controls setup the resolution and frame rate
+ * in PARAMETER mode, and then switch over to MONITOR mode.
+ */
+static int m5mols_start_monitor(struct m5mols_info *info)
+{
+	struct v4l2_subdev *sd = &info->sd;
+	int ret;
+
+	ret = m5mols_mode(info, REG_PARAMETER);
+	if (!ret)
+		ret = m5mols_write(sd, PARM_MON_SIZE, info->resolution);
+	if (!ret)
+		ret = m5mols_write(sd, PARM_MON_FPS, REG_FPS_30);
+	if (!ret)
+		ret = m5mols_mode(info, REG_MONITOR);
+	if (!ret)
+		ret = m5mols_sync_controls(info);
+
+	return ret;
+}
+
+static int m5mols_s_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct m5mols_info *info = to_m5mols(sd);
+
+	if (enable) {
+		int ret = -EINVAL;
+
+		if (is_code(info->code, M5MOLS_RESTYPE_MONITOR))
+			ret = m5mols_start_monitor(info);
+		if (is_code(info->code, M5MOLS_RESTYPE_CAPTURE))
+			ret = m5mols_start_capture(info);
+
+		return ret;
+	}
+
+	return m5mols_mode(info, REG_PARAMETER);
+}
+
+static const struct v4l2_subdev_video_ops m5mols_video_ops = {
+	.s_stream	= m5mols_s_stream,
+};
+
+static int m5mols_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct v4l2_subdev *sd = to_sd(ctrl);
+	struct m5mols_info *info = to_m5mols(sd);
+	int ret;
+
+	info->mode_save = info->mode;
+
+	ret = m5mols_mode(info, REG_PARAMETER);
+	if (!ret)
+		ret = m5mols_set_ctrl(ctrl);
+	if (!ret)
+		ret = m5mols_mode(info, info->mode_save);
+
+	return ret;
+}
+
+static const struct v4l2_ctrl_ops m5mols_ctrl_ops = {
+	.s_ctrl	= m5mols_s_ctrl,
+};
+
+static int m5mols_sensor_power(struct m5mols_info *info, bool enable)
+{
+	struct v4l2_subdev *sd = &info->sd;
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	const struct m5mols_platform_data *pdata = info->pdata;
+	int ret;
+
+	if (enable) {
+		if (is_powered(info))
+			return 0;
+
+		if (info->set_power) {
+			ret = info->set_power(&client->dev, 1);
+			if (ret)
+				return ret;
+		}
+
+		ret = regulator_bulk_enable(ARRAY_SIZE(supplies), supplies);
+		if (ret) {
+			info->set_power(&client->dev, 0);
+			return ret;
+		}
+
+		gpio_set_value(pdata->gpio_reset, !pdata->reset_polarity);
+		usleep_range(1000, 1000);
+		info->power = true;
+
+		return ret;
+	}
+
+	if (!is_powered(info))
+		return 0;
+
+	ret = regulator_bulk_disable(ARRAY_SIZE(supplies), supplies);
+	if (ret)
+		return ret;
+
+	if (info->set_power)
+		info->set_power(&client->dev, 0);
+
+	gpio_set_value(pdata->gpio_reset, pdata->reset_polarity);
+	usleep_range(1000, 1000);
+	info->power = false;
+
+	return ret;
+}
+
+/* m5mols_update_fw - optional firmware update routine */
+int __attribute__ ((weak)) m5mols_update_fw(struct v4l2_subdev *sd,
+		int (*set_power)(struct m5mols_info *, bool))
+{
+	return 0;
+}
+
+/**
+ * m5mols_sensor_armboot - Booting M-5MOLS internal ARM core.
+ *
+ * Booting internal ARM core makes the M-5MOLS is ready for getting commands
+ * with I2C. It's the first thing to be done after it powered up. It must wait
+ * at least 520ms recommended by M-5MOLS datasheet, after executing arm booting.
+ */
+static int m5mols_sensor_armboot(struct v4l2_subdev *sd)
+{
+	int ret;
+
+	ret = m5mols_write(sd, FLASH_CAM_START, REG_START_ARM_BOOT);
+	if (ret < 0)
+		return ret;
+
+	msleep(520);
+
+	ret = m5mols_get_version(sd);
+	if (!ret)
+		ret = m5mols_update_fw(sd, m5mols_sensor_power);
+	if (ret)
+		return ret;
+
+	v4l2_dbg(1, m5mols_debug, sd, "Success ARM Booting\n");
+
+	ret = m5mols_write(sd, PARM_INTERFACE, REG_INTERFACE_MIPI);
+	if (!ret)
+		ret = m5mols_enable_interrupt(sd, REG_INT_AF);
+
+	return ret;
+}
+
+static int m5mols_init_controls(struct m5mols_info *info)
+{
+	struct v4l2_subdev *sd = &info->sd;
+	u16 max_exposure;
+	u16 step_zoom;
+	int ret;
+
+	/* Determine value's range & step of controls for various FW version */
+	ret = m5mols_read(sd, AE_MAX_GAIN_MON, (u32 *)&max_exposure);
+	if (!ret)
+		step_zoom = is_manufacturer(info, REG_SAMSUNG_OPTICS) ? 31 : 1;
+	if (ret)
+		return ret;
+
+	v4l2_ctrl_handler_init(&info->handle, 6);
+	info->autowb = v4l2_ctrl_new_std(&info->handle,
+			&m5mols_ctrl_ops, V4L2_CID_AUTO_WHITE_BALANCE,
+			0, 1, 1, 0);
+	info->saturation = v4l2_ctrl_new_std(&info->handle,
+			&m5mols_ctrl_ops, V4L2_CID_SATURATION,
+			1, 5, 1, 3);
+	info->zoom = v4l2_ctrl_new_std(&info->handle,
+			&m5mols_ctrl_ops, V4L2_CID_ZOOM_ABSOLUTE,
+			1, 70, step_zoom, 1);
+	info->exposure = v4l2_ctrl_new_std(&info->handle,
+			&m5mols_ctrl_ops, V4L2_CID_EXPOSURE,
+			0, max_exposure, 1, (int)max_exposure/2);
+	info->colorfx = v4l2_ctrl_new_std_menu(&info->handle,
+			&m5mols_ctrl_ops, V4L2_CID_COLORFX,
+			4, (1 << V4L2_COLORFX_BW), V4L2_COLORFX_NONE);
+	info->autoexposure = v4l2_ctrl_new_std_menu(&info->handle,
+			&m5mols_ctrl_ops, V4L2_CID_EXPOSURE_AUTO,
+			1, 0, V4L2_EXPOSURE_MANUAL);
+
+	sd->ctrl_handler = &info->handle;
+	if (info->handle.error) {
+		v4l2_err(sd, "Failed to initialize controls: %d\n", ret);
+		v4l2_ctrl_handler_free(&info->handle);
+		return info->handle.error;
+	}
+
+	v4l2_ctrl_cluster(2, &info->autoexposure);
+
+	return 0;
+}
+
+/**
+ * m5mols_s_power - Main sensor power control function
+ *
+ * To prevent breaking the lens when the sensor is powered off the Soft-Landing
+ * algorithm is called where available. The Soft-Landing algorithm availability
+ * dependends on the firmware provider.
+ */
+static int m5mols_s_power(struct v4l2_subdev *sd, int on)
+{
+	struct m5mols_info *info = to_m5mols(sd);
+	int ret;
+
+	if (on) {
+		ret = m5mols_sensor_power(info, true);
+		if (!ret)
+			ret = m5mols_sensor_armboot(sd);
+		if (!ret)
+			ret = m5mols_init_controls(info);
+		if (ret)
+			return ret;
+
+		info->ffmt[M5MOLS_RESTYPE_MONITOR] =
+			m5mols_default_ffmt[M5MOLS_RESTYPE_MONITOR];
+		info->ffmt[M5MOLS_RESTYPE_CAPTURE] =
+			m5mols_default_ffmt[M5MOLS_RESTYPE_CAPTURE];
+		return ret;
+	}
+
+	if (is_manufacturer(info, REG_SAMSUNG_TECHWIN)) {
+		ret = m5mols_mode(info, REG_MONITOR);
+		if (!ret)
+			ret = m5mols_write(sd, AF_EXECUTE, REG_AF_STOP);
+		if (!ret)
+			ret = m5mols_write(sd, AF_MODE, REG_AF_POWEROFF);
+		if (!ret)
+			ret = m5mols_busy(sd, CAT_SYSTEM, CAT0_STATUS,
+					REG_AF_IDLE);
+		if (!ret)
+			v4l2_info(sd, "Success soft-landing lens\n");
+	}
+
+	ret = m5mols_sensor_power(info, false);
+	if (!ret) {
+		v4l2_ctrl_handler_free(&info->handle);
+		info->ctrl_sync = false;
+	}
+
+	return ret;
+}
+
+static int m5mols_log_status(struct v4l2_subdev *sd)
+{
+	struct m5mols_info *info = to_m5mols(sd);
+
+	v4l2_ctrl_handler_log_status(&info->handle, sd->name);
+
+	return 0;
+}
+
+static const struct v4l2_subdev_core_ops m5mols_core_ops = {
+	.s_power	= m5mols_s_power,
+	.g_ctrl		= v4l2_subdev_g_ctrl,
+	.s_ctrl		= v4l2_subdev_s_ctrl,
+	.queryctrl	= v4l2_subdev_queryctrl,
+	.querymenu	= v4l2_subdev_querymenu,
+	.g_ext_ctrls	= v4l2_subdev_g_ext_ctrls,
+	.try_ext_ctrls	= v4l2_subdev_try_ext_ctrls,
+	.s_ext_ctrls	= v4l2_subdev_s_ext_ctrls,
+	.log_status	= m5mols_log_status,
+};
+
+static const struct v4l2_subdev_ops m5mols_ops = {
+	.core		= &m5mols_core_ops,
+	.pad		= &m5mols_pad_ops,
+	.video		= &m5mols_video_ops,
+};
+
+static void m5mols_irq_work(struct work_struct *work)
+{
+	struct m5mols_info *info =
+		container_of(work, struct m5mols_info, work_irq);
+	struct v4l2_subdev *sd = &info->sd;
+	u32 reg;
+	int ret;
+
+	if (!is_powered(info) ||
+			m5mols_read(sd, SYSTEM_INT_FACTOR, &info->interrupt))
+		return;
+
+	switch (info->interrupt & REG_INT_MASK) {
+	case REG_INT_AF:
+		if (!is_available_af(info))
+			break;
+		ret = m5mols_read(sd, AF_STATUS, &reg);
+		v4l2_dbg(2, m5mols_debug, sd, "AF %s\n",
+			 reg == REG_AF_FAIL ? "Failed" :
+			 reg == REG_AF_SUCCESS ? "Success" :
+			 reg == REG_AF_IDLE ? "Idle" : "Busy");
+		break;
+	case REG_INT_CAPTURE:
+		if (!test_and_set_bit(ST_CAPT_IRQ, &info->flags))
+			wake_up_interruptible(&info->irq_waitq);
+
+		v4l2_dbg(2, m5mols_debug, sd, "CAPTURE\n");
+		break;
+	default:
+		v4l2_dbg(2, m5mols_debug, sd, "Undefined: %02x\n", reg);
+		break;
+	};
+}
+
+static irqreturn_t m5mols_irq_handler(int irq, void *data)
+{
+	struct v4l2_subdev *sd = data;
+	struct m5mols_info *info = to_m5mols(sd);
+
+	schedule_work(&info->work_irq);
+
+	return IRQ_HANDLED;
+}
+
+static int __devinit m5mols_probe(struct i2c_client *client,
+				  const struct i2c_device_id *id)
+{
+	const struct m5mols_platform_data *pdata = client->dev.platform_data;
+	struct m5mols_info *info;
+	struct v4l2_subdev *sd;
+	int ret;
+
+	if (pdata == NULL) {
+		dev_err(&client->dev, "No platform data\n");
+		return -EINVAL;
+	}
+
+	if (!gpio_is_valid(pdata->gpio_reset)) {
+		dev_err(&client->dev, "No valid RESET GPIO specified\n");
+		return -EINVAL;
+	}
+
+	if (!pdata->irq) {
+		dev_err(&client->dev, "Interrupt not assigned\n");
+		return -EINVAL;
+	}
+
+	info = kzalloc(sizeof(struct m5mols_info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->pdata = pdata;
+	info->set_power	= pdata->set_power;
+
+	ret = gpio_request(pdata->gpio_reset, "M5MOLS_NRST");
+	if (ret) {
+		dev_err(&client->dev, "Failed to request gpio: %d\n", ret);
+		goto out_free;
+	}
+	gpio_direction_output(pdata->gpio_reset, pdata->reset_polarity);
+
+	ret = regulator_bulk_get(&client->dev, ARRAY_SIZE(supplies), supplies);
+	if (ret) {
+		dev_err(&client->dev, "Failed to get regulators: %d\n", ret);
+		goto out_gpio;
+	}
+
+	sd = &info->sd;
+	strlcpy(sd->name, MODULE_NAME, sizeof(sd->name));
+	v4l2_i2c_subdev_init(sd, client, &m5mols_ops);
+
+	info->pad.flags = MEDIA_PAD_FL_SOURCE;
+	ret = media_entity_init(&sd->entity, 1, &info->pad, 0);
+	if (ret < 0)
+		goto out_reg;
+	sd->entity.type = MEDIA_ENT_T_V4L2_SUBDEV_SENSOR;
+
+	init_waitqueue_head(&info->irq_waitq);
+	INIT_WORK(&info->work_irq, m5mols_irq_work);
+	ret = request_irq(pdata->irq, m5mols_irq_handler,
+			  IRQF_TRIGGER_RISING, MODULE_NAME, sd);
+	if (ret) {
+		dev_err(&client->dev, "Interrupt request failed: %d\n", ret);
+		goto out_me;
+	}
+	info->res_type = M5MOLS_RESTYPE_MONITOR;
+	return 0;
+out_me:
+	media_entity_cleanup(&sd->entity);
+out_reg:
+	regulator_bulk_free(ARRAY_SIZE(supplies), supplies);
+out_gpio:
+	gpio_free(pdata->gpio_reset);
+out_free:
+	kfree(info);
+	return ret;
+}
+
+static int __devexit m5mols_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct m5mols_info *info = to_m5mols(sd);
+
+	v4l2_device_unregister_subdev(sd);
+	free_irq(info->pdata->irq, sd);
+
+	regulator_bulk_free(ARRAY_SIZE(supplies), supplies);
+	gpio_free(info->pdata->gpio_reset);
+	media_entity_cleanup(&sd->entity);
+	kfree(info);
+	return 0;
+}
+
+static const struct i2c_device_id m5mols_id[] = {
+	{ MODULE_NAME, 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(i2c, m5mols_id);
+
+static struct i2c_driver m5mols_i2c_driver = {
+	.driver = {
+		.name	= MODULE_NAME,
+	},
+	.probe		= m5mols_probe,
+	.remove		= __devexit_p(m5mols_remove),
+	.id_table	= m5mols_id,
+};
+
+static int __init m5mols_mod_init(void)
+{
+	return i2c_add_driver(&m5mols_i2c_driver);
+}
+
+static void __exit m5mols_mod_exit(void)
+{
+	i2c_del_driver(&m5mols_i2c_driver);
+}
+
+module_init(m5mols_mod_init);
+module_exit(m5mols_mod_exit);
+
+MODULE_AUTHOR("HeungJun Kim <riverful.kim@samsung.com>");
+MODULE_AUTHOR("Dongsoo Kim <dongsoo45.kim@samsung.com>");
+MODULE_DESCRIPTION("Fujitsu M-5MOLS 8M Pixel camera driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/video/m5mols/m5mols_reg.h b/drivers/media/video/m5mols/m5mols_reg.h
new file mode 100644
index 000000000000..b83e36fc6ac6
--- /dev/null
+++ b/drivers/media/video/m5mols/m5mols_reg.h
@@ -0,0 +1,399 @@
+/*
+ * Register map for M-5MOLS 8M Pixel camera sensor with ISP
+ *
+ * Copyright (C) 2011 Samsung Electronics Co., Ltd.
+ * Author: HeungJun Kim, riverful.kim@samsung.com
+ *
+ * Copyright (C) 2009 Samsung Electronics Co., Ltd.
+ * Author: Dongsoo Nathaniel Kim, dongsoo45.kim@samsung.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.
+ */
+
+#ifndef M5MOLS_REG_H
+#define M5MOLS_REG_H
+
+#define M5MOLS_I2C_MAX_SIZE	4
+#define M5MOLS_BYTE_READ	0x01
+#define M5MOLS_BYTE_WRITE	0x02
+
+#define I2C_CATEGORY(__cat)		((__cat >> 16) & 0xff)
+#define I2C_COMMAND(__comm)		((__comm >> 8) & 0xff)
+#define I2C_SIZE(__reg_s)		((__reg_s) & 0xff)
+#define I2C_REG(__cat, __cmd, __reg_s)	((__cat << 16) | (__cmd << 8) | __reg_s)
+
+/*
+ * Category section register
+ *
+ * The category means set including relevant command of M-5MOLS.
+ */
+#define CAT_SYSTEM		0x00
+#define CAT_PARAM		0x01
+#define CAT_MONITOR		0x02
+#define CAT_AE			0x03
+#define CAT_WB			0x06
+#define CAT_EXIF		0x07
+#define CAT_FD			0x09
+#define CAT_LENS		0x0a
+#define CAT_CAPT_PARM		0x0b
+#define CAT_CAPT_CTRL		0x0c
+#define CAT_FLASH		0x0f	/* related to FW, revisions, booting */
+
+/*
+ * Category 0 - SYSTEM mode
+ *
+ * The SYSTEM mode in the M-5MOLS means area available to handle with the whole
+ * & all-round system of sensor. It deals with version/interrupt/setting mode &
+ * even sensor's status. Especially, the M-5MOLS sensor with ISP varies by
+ * packaging & manufacturer, even the customer and project code. And the
+ * function details may vary among them. The version information helps to
+ * determine what methods shall be used in the driver.
+ *
+ * There is many registers between customer version address and awb one. For
+ * more specific contents, see definition if file m5mols.h.
+ */
+#define CAT0_VER_CUSTOMER	0x00	/* customer version */
+#define CAT0_VER_AWB		0x09	/* Auto WB version */
+#define CAT0_VER_STRING		0x0a	/* string including M-5MOLS */
+#define CAT0_SYSMODE		0x0b	/* SYSTEM mode register */
+#define CAT0_STATUS		0x0c	/* SYSTEM mode status register */
+#define CAT0_INT_FACTOR		0x10	/* interrupt pending register */
+#define CAT0_INT_ENABLE		0x11	/* interrupt enable register */
+
+#define SYSTEM_SYSMODE		I2C_REG(CAT_SYSTEM, CAT0_SYSMODE, 1)
+#define REG_SYSINIT		0x00	/* SYSTEM mode */
+#define REG_PARAMETER		0x01	/* PARAMETER mode */
+#define REG_MONITOR		0x02	/* MONITOR mode */
+#define REG_CAPTURE		0x03	/* CAPTURE mode */
+
+#define SYSTEM_CMD(__cmd)	I2C_REG(CAT_SYSTEM, cmd, 1)
+#define SYSTEM_VER_STRING	I2C_REG(CAT_SYSTEM, CAT0_VER_STRING, 1)
+#define REG_SAMSUNG_ELECTRO	"SE"	/* Samsung Electro-Mechanics */
+#define REG_SAMSUNG_OPTICS	"OP"	/* Samsung Fiber-Optics */
+#define REG_SAMSUNG_TECHWIN	"TB"	/* Samsung Techwin */
+
+#define SYSTEM_INT_FACTOR	I2C_REG(CAT_SYSTEM, CAT0_INT_FACTOR, 1)
+#define SYSTEM_INT_ENABLE	I2C_REG(CAT_SYSTEM, CAT0_INT_ENABLE, 1)
+#define REG_INT_MODE		(1 << 0)
+#define REG_INT_AF		(1 << 1)
+#define REG_INT_ZOOM		(1 << 2)
+#define REG_INT_CAPTURE		(1 << 3)
+#define REG_INT_FRAMESYNC	(1 << 4)
+#define REG_INT_FD		(1 << 5)
+#define REG_INT_LENS_INIT	(1 << 6)
+#define REG_INT_SOUND		(1 << 7)
+#define REG_INT_MASK		0x0f
+
+/*
+ * category 1 - PARAMETER mode
+ *
+ * This category supports function of camera features of M-5MOLS. It means we
+ * can handle with preview(MONITOR) resolution size/frame per second/interface
+ * between the sensor and the Application Processor/even the image effect.
+ */
+#define CAT1_DATA_INTERFACE	0x00	/* interface between sensor and AP */
+#define CAT1_MONITOR_SIZE	0x01	/* resolution at the MONITOR mode */
+#define CAT1_MONITOR_FPS	0x02	/* frame per second at this mode */
+#define CAT1_EFFECT		0x0b	/* image effects */
+
+#define PARM_MON_SIZE		I2C_REG(CAT_PARAM, CAT1_MONITOR_SIZE, 1)
+
+#define PARM_MON_FPS		I2C_REG(CAT_PARAM, CAT1_MONITOR_FPS, 1)
+#define REG_FPS_30		0x02
+
+#define PARM_INTERFACE		I2C_REG(CAT_PARAM, CAT1_DATA_INTERFACE, 1)
+#define REG_INTERFACE_MIPI	0x02
+
+#define PARM_EFFECT		I2C_REG(CAT_PARAM, CAT1_EFFECT, 1)
+#define REG_EFFECT_OFF		0x00
+#define REG_EFFECT_NEGA		0x01
+#define REG_EFFECT_EMBOSS	0x06
+#define REG_EFFECT_OUTLINE	0x07
+#define REG_EFFECT_WATERCOLOR	0x08
+
+/*
+ * Category 2 - MONITOR mode
+ *
+ * The MONITOR mode is same as preview mode as we said. The M-5MOLS has another
+ * mode named "Preview", but this preview mode is used at the case specific
+ * vider-recording mode. This mmode supports only YUYV format. On the other
+ * hand, the JPEG & RAW formats is supports by CAPTURE mode. And, there are
+ * another options like zoom/color effect(different with effect in PARAMETER
+ * mode)/anti hand shaking algorithm.
+ */
+#define CAT2_ZOOM		0x01	/* set the zoom position & execute */
+#define CAT2_ZOOM_STEP		0x03	/* set the zoom step */
+#define CAT2_CFIXB		0x09	/* CB value for color effect */
+#define CAT2_CFIXR		0x0a	/* CR value for color effect */
+#define CAT2_COLOR_EFFECT	0x0b	/* set on/off of color effect */
+#define CAT2_CHROMA_LVL		0x0f	/* set chroma level */
+#define CAT2_CHROMA_EN		0x10	/* set on/off of choroma */
+#define CAT2_EDGE_LVL		0x11	/* set sharpness level */
+#define CAT2_EDGE_EN		0x12	/* set on/off sharpness */
+#define CAT2_TONE_CTL		0x25	/* set tone color(contrast) */
+
+#define MON_ZOOM		I2C_REG(CAT_MONITOR, CAT2_ZOOM, 1)
+
+#define MON_CFIXR		I2C_REG(CAT_MONITOR, CAT2_CFIXR, 1)
+#define MON_CFIXB		I2C_REG(CAT_MONITOR, CAT2_CFIXB, 1)
+#define REG_CFIXB_SEPIA		0xd8
+#define REG_CFIXR_SEPIA		0x18
+
+#define MON_EFFECT		I2C_REG(CAT_MONITOR, CAT2_COLOR_EFFECT, 1)
+#define REG_COLOR_EFFECT_OFF	0x00
+#define REG_COLOR_EFFECT_ON	0x01
+
+#define MON_CHROMA_EN		I2C_REG(CAT_MONITOR, CAT2_CHROMA_EN, 1)
+#define MON_CHROMA_LVL		I2C_REG(CAT_MONITOR, CAT2_CHROMA_LVL, 1)
+#define REG_CHROMA_OFF		0x00
+#define REG_CHROMA_ON		0x01
+
+#define MON_EDGE_EN		I2C_REG(CAT_MONITOR, CAT2_EDGE_EN, 1)
+#define MON_EDGE_LVL		I2C_REG(CAT_MONITOR, CAT2_EDGE_LVL, 1)
+#define REG_EDGE_OFF		0x00
+#define REG_EDGE_ON		0x01
+
+#define MON_TONE_CTL		I2C_REG(CAT_MONITOR, CAT2_TONE_CTL, 1)
+
+/*
+ * Category 3 - Auto Exposure
+ *
+ * The M-5MOLS exposure capbility is detailed as which is similar to digital
+ * camera. This category supports AE locking/various AE mode(range of exposure)
+ * /ISO/flickering/EV bias/shutter/meteoring, and anything else. And the
+ * maximum/minimum exposure gain value depending on M-5MOLS firmware, may be
+ * different. So, this category also provide getting the max/min values. And,
+ * each MONITOR and CAPTURE mode has each gain/shutter/max exposure values.
+ */
+#define CAT3_AE_LOCK		0x00	/* locking Auto exposure */
+#define CAT3_AE_MODE		0x01	/* set AE mode, mode means range */
+#define CAT3_ISO		0x05	/* set ISO */
+#define CAT3_EV_PRESET_MONITOR	0x0a	/* EV(scenemode) preset for MONITOR */
+#define CAT3_EV_PRESET_CAPTURE	0x0b	/* EV(scenemode) preset for CAPTURE */
+#define CAT3_MANUAL_GAIN_MON	0x12	/* meteoring value for the MONITOR */
+#define CAT3_MAX_GAIN_MON	0x1a	/* max gain value for the MONITOR */
+#define CAT3_MANUAL_GAIN_CAP	0x26	/* meteoring value for the CAPTURE */
+#define CAT3_AE_INDEX		0x38	/* AE index */
+
+#define AE_LOCK			I2C_REG(CAT_AE, CAT3_AE_LOCK, 1)
+#define REG_AE_UNLOCK		0x00
+#define REG_AE_LOCK		0x01
+
+#define AE_MODE			I2C_REG(CAT_AE, CAT3_AE_MODE, 1)
+#define REG_AE_OFF		0x00	/* AE off */
+#define REG_AE_ALL		0x01	/* calc AE in all block integral */
+#define REG_AE_CENTER		0x03	/* calc AE in center weighted */
+#define REG_AE_SPOT		0x06	/* calc AE in specific spot */
+
+#define AE_ISO			I2C_REG(CAT_AE, CAT3_ISO, 1)
+#define REG_ISO_AUTO		0x00
+#define REG_ISO_50		0x01
+#define REG_ISO_100		0x02
+#define REG_ISO_200		0x03
+#define REG_ISO_400		0x04
+#define REG_ISO_800		0x05
+
+#define AE_EV_PRESET_MONITOR	I2C_REG(CAT_AE, CAT3_EV_PRESET_MONITOR, 1)
+#define AE_EV_PRESET_CAPTURE	I2C_REG(CAT_AE, CAT3_EV_PRESET_CAPTURE, 1)
+#define REG_SCENE_NORMAL	0x00
+#define REG_SCENE_PORTRAIT	0x01
+#define REG_SCENE_LANDSCAPE	0x02
+#define REG_SCENE_SPORTS	0x03
+#define REG_SCENE_PARTY_INDOOR	0x04
+#define REG_SCENE_BEACH_SNOW	0x05
+#define REG_SCENE_SUNSET	0x06
+#define REG_SCENE_DAWN_DUSK	0x07
+#define REG_SCENE_FALL		0x08
+#define REG_SCENE_NIGHT		0x09
+#define REG_SCENE_AGAINST_LIGHT	0x0a
+#define REG_SCENE_FIRE		0x0b
+#define REG_SCENE_TEXT		0x0c
+#define REG_SCENE_CANDLE	0x0d
+
+#define AE_MAN_GAIN_MON		I2C_REG(CAT_AE, CAT3_MANUAL_GAIN_MON, 2)
+#define AE_MAX_GAIN_MON		I2C_REG(CAT_AE, CAT3_MAX_GAIN_MON, 2)
+#define AE_MAN_GAIN_CAP		I2C_REG(CAT_AE, CAT3_MANUAL_GAIN_CAP, 2)
+
+#define AE_INDEX		I2C_REG(CAT_AE, CAT3_AE_INDEX, 1)
+#define REG_AE_INDEX_20_NEG	0x00
+#define REG_AE_INDEX_15_NEG	0x01
+#define REG_AE_INDEX_10_NEG	0x02
+#define REG_AE_INDEX_05_NEG	0x03
+#define REG_AE_INDEX_00		0x04
+#define REG_AE_INDEX_05_POS	0x05
+#define REG_AE_INDEX_10_POS	0x06
+#define REG_AE_INDEX_15_POS	0x07
+#define REG_AE_INDEX_20_POS	0x08
+
+/*
+ * Category 6 - White Balance
+ *
+ * This category provide AWB locking/mode/preset/speed/gain bias, etc.
+ */
+#define CAT6_AWB_LOCK		0x00	/* locking Auto Whitebalance */
+#define CAT6_AWB_MODE		0x02	/* set Auto or Manual */
+#define CAT6_AWB_MANUAL		0x03	/* set Manual(preset) value */
+
+#define AWB_LOCK		I2C_REG(CAT_WB, CAT6_AWB_LOCK, 1)
+#define REG_AWB_UNLOCK		0x00
+#define REG_AWB_LOCK		0x01
+
+#define AWB_MODE		I2C_REG(CAT_WB, CAT6_AWB_MODE, 1)
+#define REG_AWB_AUTO		0x01	/* AWB off */
+#define REG_AWB_PRESET		0x02	/* AWB preset */
+
+#define AWB_MANUAL		I2C_REG(CAT_WB, CAT6_AWB_MANUAL, 1)
+#define REG_AWB_INCANDESCENT	0x01
+#define REG_AWB_FLUORESCENT_1	0x02
+#define REG_AWB_FLUORESCENT_2	0x03
+#define REG_AWB_DAYLIGHT	0x04
+#define REG_AWB_CLOUDY		0x05
+#define REG_AWB_SHADE		0x06
+#define REG_AWB_HORIZON		0x07
+#define REG_AWB_LEDLIGHT	0x09
+
+/*
+ * Category 7 - EXIF information
+ */
+#define CAT7_INFO_EXPTIME_NU	0x00
+#define CAT7_INFO_EXPTIME_DE	0x04
+#define CAT7_INFO_TV_NU		0x08
+#define CAT7_INFO_TV_DE		0x0c
+#define CAT7_INFO_AV_NU		0x10
+#define CAT7_INFO_AV_DE		0x14
+#define CAT7_INFO_BV_NU		0x18
+#define CAT7_INFO_BV_DE		0x1c
+#define CAT7_INFO_EBV_NU	0x20
+#define CAT7_INFO_EBV_DE	0x24
+#define CAT7_INFO_ISO		0x28
+#define CAT7_INFO_FLASH		0x2a
+#define CAT7_INFO_SDR		0x2c
+#define CAT7_INFO_QVAL		0x2e
+
+#define EXIF_INFO_EXPTIME_NU	I2C_REG(CAT_EXIF, CAT7_INFO_EXPTIME_NU, 4)
+#define EXIF_INFO_EXPTIME_DE	I2C_REG(CAT_EXIF, CAT7_INFO_EXPTIME_DE, 4)
+#define EXIF_INFO_TV_NU		I2C_REG(CAT_EXIF, CAT7_INFO_TV_NU, 4)
+#define EXIF_INFO_TV_DE		I2C_REG(CAT_EXIF, CAT7_INFO_TV_DE, 4)
+#define EXIF_INFO_AV_NU		I2C_REG(CAT_EXIF, CAT7_INFO_AV_NU, 4)
+#define EXIF_INFO_AV_DE		I2C_REG(CAT_EXIF, CAT7_INFO_AV_DE, 4)
+#define EXIF_INFO_BV_NU		I2C_REG(CAT_EXIF, CAT7_INFO_BV_NU, 4)
+#define EXIF_INFO_BV_DE		I2C_REG(CAT_EXIF, CAT7_INFO_BV_DE, 4)
+#define EXIF_INFO_EBV_NU	I2C_REG(CAT_EXIF, CAT7_INFO_EBV_NU, 4)
+#define EXIF_INFO_EBV_DE	I2C_REG(CAT_EXIF, CAT7_INFO_EBV_DE, 4)
+#define EXIF_INFO_ISO		I2C_REG(CAT_EXIF, CAT7_INFO_ISO, 2)
+#define EXIF_INFO_FLASH		I2C_REG(CAT_EXIF, CAT7_INFO_FLASH, 2)
+#define EXIF_INFO_SDR		I2C_REG(CAT_EXIF, CAT7_INFO_SDR, 2)
+#define EXIF_INFO_QVAL		I2C_REG(CAT_EXIF, CAT7_INFO_QVAL, 2)
+
+/*
+ * Category 9 - Face Detection
+ */
+#define CAT9_FD_CTL		0x00
+
+#define FD_CTL			I2C_REG(CAT_FD, CAT9_FD_CTL, 1)
+#define BIT_FD_EN		0
+#define BIT_FD_DRAW_FACE_FRAME	4
+#define BIT_FD_DRAW_SMILE_LVL	6
+#define REG_FD(shift)		(1 << shift)
+#define REG_FD_OFF		0x0
+
+/*
+ * Category A - Lens Parameter
+ */
+#define CATA_AF_MODE		0x01
+#define CATA_AF_EXECUTE		0x02
+#define CATA_AF_STATUS		0x03
+#define CATA_AF_VERSION		0x0a
+
+#define AF_MODE			I2C_REG(CAT_LENS, CATA_AF_MODE, 1)
+#define REG_AF_NORMAL		0x00	/* Normal AF, one time */
+#define REG_AF_MACRO		0x01	/* Macro AF, one time */
+#define REG_AF_POWEROFF		0x07
+
+#define AF_EXECUTE		I2C_REG(CAT_LENS, CATA_AF_EXECUTE, 1)
+#define REG_AF_STOP		0x00
+#define REG_AF_EXE_AUTO		0x01
+#define REG_AF_EXE_CAF		0x02
+
+#define AF_STATUS		I2C_REG(CAT_LENS, CATA_AF_STATUS, 1)
+#define REG_AF_FAIL		0x00
+#define REG_AF_SUCCESS		0x02
+#define REG_AF_IDLE		0x04
+#define REG_AF_BUSY		0x05
+
+#define AF_VERSION		I2C_REG(CAT_LENS, CATA_AF_VERSION, 1)
+
+/*
+ * Category B - CAPTURE Parameter
+ */
+#define CATB_YUVOUT_MAIN	0x00
+#define CATB_MAIN_IMAGE_SIZE	0x01
+#define CATB_MCC_MODE		0x1d
+#define CATB_WDR_EN		0x2c
+#define CATB_LIGHT_CTRL		0x40
+#define CATB_FLASH_CTRL		0x41
+
+#define CAPP_YUVOUT_MAIN	I2C_REG(CAT_CAPT_PARM, CATB_YUVOUT_MAIN, 1)
+#define REG_YUV422		0x00
+#define REG_BAYER10		0x05
+#define REG_BAYER8		0x06
+#define REG_JPEG		0x10
+
+#define CAPP_MAIN_IMAGE_SIZE	I2C_REG(CAT_CAPT_PARM, CATB_MAIN_IMAGE_SIZE, 1)
+
+#define CAPP_MCC_MODE		I2C_REG(CAT_CAPT_PARM, CATB_MCC_MODE, 1)
+#define REG_MCC_OFF		0x00
+#define REG_MCC_NORMAL		0x01
+
+#define CAPP_WDR_EN		I2C_REG(CAT_CAPT_PARM, CATB_WDR_EN, 1)
+#define REG_WDR_OFF		0x00
+#define REG_WDR_ON		0x01
+#define REG_WDR_AUTO		0x02
+
+#define CAPP_LIGHT_CTRL		I2C_REG(CAT_CAPT_PARM, CATB_LIGHT_CTRL, 1)
+#define REG_LIGHT_OFF		0x00
+#define REG_LIGHT_ON		0x01
+#define REG_LIGHT_AUTO		0x02
+
+#define CAPP_FLASH_CTRL		I2C_REG(CAT_CAPT_PARM, CATB_FLASH_CTRL, 1)
+#define REG_FLASH_OFF		0x00
+#define REG_FLASH_ON		0x01
+#define REG_FLASH_AUTO		0x02
+
+/*
+ * Category C - CAPTURE Control
+ */
+#define CATC_CAP_MODE		0x00
+#define CATC_CAP_SEL_FRAME	0x06	/* It determines Single or Multi */
+#define CATC_CAP_START		0x09
+#define CATC_CAP_IMAGE_SIZE	0x0d
+#define CATC_CAP_THUMB_SIZE	0x11
+
+#define CAPC_MODE		I2C_REG(CAT_CAPT_CTRL, CATC_CAP_MODE, 1)
+#define REG_CAP_NONE		0x00
+#define REG_CAP_ANTI_SHAKE	0x02
+
+#define CAPC_SEL_FRAME		I2C_REG(CAT_CAPT_CTRL, CATC_CAP_SEL_FRAME, 1)
+
+#define CAPC_START		I2C_REG(CAT_CAPT_CTRL, CATC_CAP_START, 1)
+#define REG_CAP_START_MAIN	0x01
+#define REG_CAP_START_THUMB	0x03
+
+#define CAPC_IMAGE_SIZE		I2C_REG(CAT_CAPT_CTRL, CATC_CAP_IMAGE_SIZE, 1)
+#define CAPC_THUMB_SIZE		I2C_REG(CAT_CAPT_CTRL, CATC_CAP_THUMB_SIZE, 1)
+
+/*
+ * Category F - Flash
+ *
+ * This mode provides functions about internal flash stuff and system startup.
+ */
+#define CATF_CAM_START		0x12	/* It starts internal ARM core booting
+					 * after power-up */
+
+#define FLASH_CAM_START		I2C_REG(CAT_FLASH, CATF_CAM_START, 1)
+#define REG_START_ARM_BOOT	0x01
+
+#endif	/* M5MOLS_REG_H */
diff --git a/drivers/media/video/omap3isp/isp.c b/drivers/media/video/omap3isp/isp.c
index 472a69359e60..c9fd04ee70a8 100644
--- a/drivers/media/video/omap3isp/isp.c
+++ b/drivers/media/video/omap3isp/isp.c
@@ -391,7 +391,7 @@ static inline void isp_isr_dbg(struct isp_device *isp, u32 irqstatus)
 	};
 	int i;
 
-	dev_dbg(isp->dev, "");
+	dev_dbg(isp->dev, "ISP IRQ: ");
 
 	for (i = 0; i < ARRAY_SIZE(name); i++) {
 		if ((1 << i) & irqstatus)
diff --git a/drivers/media/video/soc_camera.c b/drivers/media/video/soc_camera.c
index 398864370267..4e4d4122d9a6 100644
--- a/drivers/media/video/soc_camera.c
+++ b/drivers/media/video/soc_camera.c
@@ -1512,7 +1512,7 @@ static int video_dev_create(struct soc_camera_device *icd)
  */
 static int soc_camera_video_start(struct soc_camera_device *icd)
 {
-	struct device_type *type = icd->vdev->dev.type;
+	const struct device_type *type = icd->vdev->dev.type;
 	int ret;
 
 	if (!icd->dev.parent)
diff --git a/drivers/media/video/uvc/Makefile b/drivers/media/video/uvc/Makefile
index 968c1994eda0..2071ca8a2f03 100644
--- a/drivers/media/video/uvc/Makefile
+++ b/drivers/media/video/uvc/Makefile
@@ -1,3 +1,6 @@
 uvcvideo-objs  := uvc_driver.o uvc_queue.o uvc_v4l2.o uvc_video.o uvc_ctrl.o \
 		  uvc_status.o uvc_isight.o
+ifeq ($(CONFIG_MEDIA_CONTROLLER),y)
+uvcvideo-objs  += uvc_entity.o
+endif
 obj-$(CONFIG_USB_VIDEO_CLASS) += uvcvideo.o
diff --git a/drivers/media/video/uvc/uvc_driver.c b/drivers/media/video/uvc/uvc_driver.c
index 823f4b389745..b6eae48d7fb8 100644
--- a/drivers/media/video/uvc/uvc_driver.c
+++ b/drivers/media/video/uvc/uvc_driver.c
@@ -248,7 +248,7 @@ uint32_t uvc_fraction_to_interval(uint32_t numerator, uint32_t denominator)
  * Terminal and unit management
  */
 
-static struct uvc_entity *uvc_entity_by_id(struct uvc_device *dev, int id)
+struct uvc_entity *uvc_entity_by_id(struct uvc_device *dev, int id)
 {
 	struct uvc_entity *entity;
 
@@ -795,9 +795,12 @@ static struct uvc_entity *uvc_alloc_entity(u16 type, u8 id,
 	struct uvc_entity *entity;
 	unsigned int num_inputs;
 	unsigned int size;
+	unsigned int i;
 
+	extra_size = ALIGN(extra_size, sizeof(*entity->pads));
 	num_inputs = (type & UVC_TERM_OUTPUT) ? num_pads : num_pads - 1;
-	size = sizeof(*entity) + extra_size + num_inputs;
+	size = sizeof(*entity) + extra_size + sizeof(*entity->pads) * num_pads
+	     + num_inputs;
 	entity = kzalloc(size, GFP_KERNEL);
 	if (entity == NULL)
 		return NULL;
@@ -805,8 +808,17 @@ static struct uvc_entity *uvc_alloc_entity(u16 type, u8 id,
 	entity->id = id;
 	entity->type = type;
 
+	entity->num_links = 0;
+	entity->num_pads = num_pads;
+	entity->pads = ((void *)(entity + 1)) + extra_size;
+
+	for (i = 0; i < num_inputs; ++i)
+		entity->pads[i].flags = MEDIA_PAD_FL_SINK;
+	if (!UVC_ENTITY_IS_OTERM(entity))
+		entity->pads[num_pads-1].flags = MEDIA_PAD_FL_SOURCE;
+
 	entity->bNrInPins = num_inputs;
-	entity->baSourceID = ((__u8 *)entity) + sizeof(*entity) + extra_size;
+	entity->baSourceID = (__u8 *)(&entity->pads[num_pads]);
 
 	return entity;
 }
@@ -1585,6 +1597,13 @@ static void uvc_delete(struct uvc_device *dev)
 	uvc_status_cleanup(dev);
 	uvc_ctrl_cleanup_device(dev);
 
+	if (dev->vdev.dev)
+		v4l2_device_unregister(&dev->vdev);
+#ifdef CONFIG_MEDIA_CONTROLLER
+	if (media_devnode_is_registered(&dev->mdev.devnode))
+		media_device_unregister(&dev->mdev);
+#endif
+
 	list_for_each_safe(p, n, &dev->chains) {
 		struct uvc_video_chain *chain;
 		chain = list_entry(p, struct uvc_video_chain, list);
@@ -1594,6 +1613,13 @@ static void uvc_delete(struct uvc_device *dev)
 	list_for_each_safe(p, n, &dev->entities) {
 		struct uvc_entity *entity;
 		entity = list_entry(p, struct uvc_entity, list);
+#ifdef CONFIG_MEDIA_CONTROLLER
+		uvc_mc_cleanup_entity(entity);
+#endif
+		if (entity->vdev) {
+			video_device_release(entity->vdev);
+			entity->vdev = NULL;
+		}
 		kfree(entity);
 	}
 
@@ -1616,8 +1642,6 @@ static void uvc_release(struct video_device *vdev)
 	struct uvc_streaming *stream = video_get_drvdata(vdev);
 	struct uvc_device *dev = stream->dev;
 
-	video_device_release(vdev);
-
 	/* Decrement the registered streams count and delete the device when it
 	 * reaches zero.
 	 */
@@ -1682,7 +1706,7 @@ static int uvc_register_video(struct uvc_device *dev,
 	 * unregistered before the reference is released, so we don't need to
 	 * get another one.
 	 */
-	vdev->parent = &dev->intf->dev;
+	vdev->v4l2_dev = &dev->vdev;
 	vdev->fops = &uvc_fops;
 	vdev->release = uvc_release;
 	strlcpy(vdev->name, dev->name, sizeof vdev->name);
@@ -1731,6 +1755,8 @@ static int uvc_register_terms(struct uvc_device *dev,
 		ret = uvc_register_video(dev, stream);
 		if (ret < 0)
 			return ret;
+
+		term->vdev = stream->vdev;
 	}
 
 	return 0;
@@ -1745,6 +1771,14 @@ static int uvc_register_chains(struct uvc_device *dev)
 		ret = uvc_register_terms(dev, chain);
 		if (ret < 0)
 			return ret;
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+		ret = uvc_mc_register_entities(chain);
+		if (ret < 0) {
+			uvc_printk(KERN_INFO, "Failed to register entites "
+				"(%d).\n", ret);
+		}
+#endif
 	}
 
 	return 0;
@@ -1814,6 +1848,24 @@ static int uvc_probe(struct usb_interface *intf,
 			"linux-uvc-devel mailing list.\n");
 	}
 
+	/* Register the media and V4L2 devices. */
+#ifdef CONFIG_MEDIA_CONTROLLER
+	dev->mdev.dev = &intf->dev;
+	strlcpy(dev->mdev.model, dev->name, sizeof(dev->mdev.model));
+	if (udev->serial)
+		strlcpy(dev->mdev.serial, udev->serial,
+			sizeof(dev->mdev.serial));
+	strcpy(dev->mdev.bus_info, udev->devpath);
+	dev->mdev.hw_revision = le16_to_cpu(udev->descriptor.bcdDevice);
+	dev->mdev.driver_version = DRIVER_VERSION_NUMBER;
+	if (media_device_register(&dev->mdev) < 0)
+		goto error;
+
+	dev->vdev.mdev = &dev->mdev;
+#endif
+	if (v4l2_device_register(&intf->dev, &dev->vdev) < 0)
+		goto error;
+
 	/* Initialize controls. */
 	if (uvc_ctrl_init_device(dev) < 0)
 		goto error;
@@ -1822,7 +1874,7 @@ static int uvc_probe(struct usb_interface *intf,
 	if (uvc_scan_device(dev) < 0)
 		goto error;
 
-	/* Register video devices. */
+	/* Register video device nodes. */
 	if (uvc_register_chains(dev) < 0)
 		goto error;
 
diff --git a/drivers/media/video/uvc/uvc_entity.c b/drivers/media/video/uvc/uvc_entity.c
new file mode 100644
index 000000000000..c3ab0c813be2
--- /dev/null
+++ b/drivers/media/video/uvc/uvc_entity.c
@@ -0,0 +1,118 @@
+/*
+ *      uvc_entity.c  --  USB Video Class driver
+ *
+ *      Copyright (C) 2005-2011
+ *          Laurent Pinchart (laurent.pinchart@ideasonboard.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/list.h>
+#include <linux/videodev2.h>
+
+#include <media/v4l2-common.h>
+
+#include "uvcvideo.h"
+
+/* ------------------------------------------------------------------------
+ * Video subdevices registration and unregistration
+ */
+
+static int uvc_mc_register_entity(struct uvc_video_chain *chain,
+	struct uvc_entity *entity)
+{
+	const u32 flags = MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE;
+	struct uvc_entity *remote;
+	unsigned int i;
+	u8 remote_pad;
+	int ret = 0;
+
+	for (i = 0; i < entity->num_pads; ++i) {
+		struct media_entity *source;
+		struct media_entity *sink;
+
+		if (!(entity->pads[i].flags & MEDIA_PAD_FL_SINK))
+			continue;
+
+		remote = uvc_entity_by_id(chain->dev, entity->baSourceID[i]);
+		if (remote == NULL)
+			return -EINVAL;
+
+		source = (UVC_ENTITY_TYPE(remote) == UVC_TT_STREAMING)
+		       ? &remote->vdev->entity : &remote->subdev.entity;
+		sink = (UVC_ENTITY_TYPE(entity) == UVC_TT_STREAMING)
+		     ? &entity->vdev->entity : &entity->subdev.entity;
+
+		remote_pad = remote->num_pads - 1;
+		ret = media_entity_create_link(source, remote_pad,
+					       sink, i, flags);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (UVC_ENTITY_TYPE(entity) != UVC_TT_STREAMING)
+		ret = v4l2_device_register_subdev(&chain->dev->vdev,
+						  &entity->subdev);
+
+	return ret;
+}
+
+static struct v4l2_subdev_ops uvc_subdev_ops = {
+};
+
+void uvc_mc_cleanup_entity(struct uvc_entity *entity)
+{
+	if (UVC_ENTITY_TYPE(entity) != UVC_TT_STREAMING)
+		media_entity_cleanup(&entity->subdev.entity);
+	else if (entity->vdev != NULL)
+		media_entity_cleanup(&entity->vdev->entity);
+}
+
+static int uvc_mc_init_entity(struct uvc_entity *entity)
+{
+	int ret;
+
+	if (UVC_ENTITY_TYPE(entity) != UVC_TT_STREAMING) {
+		v4l2_subdev_init(&entity->subdev, &uvc_subdev_ops);
+		strlcpy(entity->subdev.name, entity->name,
+			sizeof(entity->subdev.name));
+
+		ret = media_entity_init(&entity->subdev.entity,
+					entity->num_pads, entity->pads, 0);
+	} else
+		ret = media_entity_init(&entity->vdev->entity,
+					entity->num_pads, entity->pads, 0);
+
+	return ret;
+}
+
+int uvc_mc_register_entities(struct uvc_video_chain *chain)
+{
+	struct uvc_entity *entity;
+	int ret;
+
+	list_for_each_entry(entity, &chain->entities, chain) {
+		ret = uvc_mc_init_entity(entity);
+		if (ret < 0) {
+			uvc_printk(KERN_INFO, "Failed to initialize entity for "
+				   "entity %u\n", entity->id);
+			return ret;
+		}
+	}
+
+	list_for_each_entry(entity, &chain->entities, chain) {
+		ret = uvc_mc_register_entity(chain, entity);
+		if (ret < 0) {
+			uvc_printk(KERN_INFO, "Failed to register entity for "
+				   "entity %u\n", entity->id);
+			return ret;
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/media/video/uvc/uvcvideo.h b/drivers/media/video/uvc/uvcvideo.h
index 7cf224bae2e5..20107fd3574d 100644
--- a/drivers/media/video/uvc/uvcvideo.h
+++ b/drivers/media/video/uvc/uvcvideo.h
@@ -98,8 +98,11 @@ struct uvc_xu_control {
 #ifdef __KERNEL__
 
 #include <linux/poll.h>
+#include <linux/usb.h>
 #include <linux/usb/video.h>
 #include <linux/uvcvideo.h>
+#include <media/media-device.h>
+#include <media/v4l2-device.h>
 
 /* --------------------------------------------------------------------------
  * UVC constants
@@ -301,6 +304,13 @@ struct uvc_entity {
 	__u16 type;
 	char name[64];
 
+	/* Media controller-related fields. */
+	struct video_device *vdev;
+	struct v4l2_subdev subdev;
+	unsigned int num_pads;
+	unsigned int num_links;
+	struct media_pad *pads;
+
 	union {
 		struct {
 			__u16 wObjectiveFocalLengthMin;
@@ -504,6 +514,10 @@ struct uvc_device {
 	atomic_t nmappings;
 
 	/* Video control interface */
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_device mdev;
+#endif
+	struct v4l2_device vdev;
 	__u16 uvc_version;
 	__u32 clock_frequency;
 
@@ -583,6 +597,8 @@ extern unsigned int uvc_timeout_param;
 /* Core driver */
 extern struct uvc_driver uvc_driver;
 
+extern struct uvc_entity *uvc_entity_by_id(struct uvc_device *dev, int id);
+
 /* Video buffers queue management. */
 extern void uvc_queue_init(struct uvc_video_queue *queue,
 		enum v4l2_buf_type type, int drop_corrupted);
@@ -616,6 +632,10 @@ static inline int uvc_queue_streaming(struct uvc_video_queue *queue)
 /* V4L2 interface */
 extern const struct v4l2_file_operations uvc_fops;
 
+/* Media controller */
+extern int uvc_mc_register_entities(struct uvc_video_chain *chain);
+extern void uvc_mc_cleanup_entity(struct uvc_entity *entity);
+
 /* Video */
 extern int uvc_video_init(struct uvc_streaming *stream);
 extern int uvc_video_suspend(struct uvc_streaming *stream);
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 8344fc0ab858..0f09c057e796 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -719,6 +719,15 @@ config MFD_PM8XXX_IRQ
 	  This is required to use certain other PM 8xxx features, such as GPIO
 	  and MPP.
 
+config MFD_TPS65910
+	bool "TPS65910 Power Management chip"
+	depends on I2C=y && GPIOLIB
+	select MFD_CORE
+	select GPIO_TPS65910
+	help
+	  if you say yes here you get support for the TPS65910 series of
+	  Power Management chips.
+
 endif # MFD_SUPPORT
 
 menu "Multimedia Capabilities Port drivers"
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 1acb8f29a96c..efe3cc33ed92 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -93,3 +93,4 @@ obj-$(CONFIG_MFD_CS5535)	+= cs5535-mfd.o
 obj-$(CONFIG_MFD_OMAP_USB_HOST)	+= omap-usb-host.o
 obj-$(CONFIG_MFD_PM8921_CORE) 	+= pm8921-core.o
 obj-$(CONFIG_MFD_PM8XXX_IRQ) 	+= pm8xxx-irq.o
+obj-$(CONFIG_MFD_TPS65910)	+= tps65910.o tps65910-irq.o
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index e63782107e2f..02a15d7cb3b0 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -2005,7 +2005,8 @@ static struct regulator_init_data db8500_regulators[DB8500_NUM_REGULATORS] = {
 static struct mfd_cell db8500_prcmu_devs[] = {
 	{
 		.name = "db8500-prcmu-regulators",
-		.mfd_data = &db8500_regulators,
+		.platform_data = &db8500_regulators,
+		.pdata_size = sizeof(db8500_regulators),
 	},
 	{
 		.name = "cpufreq-u8500",
diff --git a/drivers/mfd/tps65910-irq.c b/drivers/mfd/tps65910-irq.c
new file mode 100644
index 000000000000..2bfad5c86cc7
--- /dev/null
+++ b/drivers/mfd/tps65910-irq.c
@@ -0,0 +1,218 @@
+/*
+ * tps65910-irq.c  --  TI TPS6591x
+ *
+ * Copyright 2010 Texas Instruments Inc.
+ *
+ * Author: Graeme Gregory <gg@slimlogic.co.uk>
+ * Author: Jorge Eduardo Candelaria <jedu@slimlogic.co.uk>
+ *
+ *  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/init.h>
+#include <linux/bug.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/gpio.h>
+#include <linux/mfd/tps65910.h>
+
+static inline int irq_to_tps65910_irq(struct tps65910 *tps65910,
+							int irq)
+{
+	return (irq - tps65910->irq_base);
+}
+
+/*
+ * This is a threaded IRQ handler so can access I2C/SPI.  Since all
+ * interrupts are clear on read the IRQ line will be reasserted and
+ * the physical IRQ will be handled again if another interrupt is
+ * asserted while we run - in the normal course of events this is a
+ * rare occurrence so we save I2C/SPI reads.  We're also assuming that
+ * it's rare to get lots of interrupts firing simultaneously so try to
+ * minimise I/O.
+ */
+static irqreturn_t tps65910_irq(int irq, void *irq_data)
+{
+	struct tps65910 *tps65910 = irq_data;
+	u32 irq_sts;
+	u32 irq_mask;
+	u8 reg;
+	int i;
+
+	tps65910->read(tps65910, TPS65910_INT_STS, 1, &reg);
+	irq_sts = reg;
+	tps65910->read(tps65910, TPS65910_INT_STS2, 1, &reg);
+	irq_sts |= reg << 8;
+	switch (tps65910_chip_id(tps65910)) {
+	case TPS65911:
+		tps65910->read(tps65910, TPS65910_INT_STS3, 1, &reg);
+		irq_sts |= reg << 16;
+	}
+
+	tps65910->read(tps65910, TPS65910_INT_MSK, 1, &reg);
+	irq_mask = reg;
+	tps65910->read(tps65910, TPS65910_INT_MSK2, 1, &reg);
+	irq_mask |= reg << 8;
+	switch (tps65910_chip_id(tps65910)) {
+	case TPS65911:
+		tps65910->read(tps65910, TPS65910_INT_MSK3, 1, &reg);
+		irq_mask |= reg << 16;
+	}
+
+	irq_sts &= ~irq_mask;
+
+	if (!irq_sts)
+		return IRQ_NONE;
+
+	for (i = 0; i < tps65910->irq_num; i++) {
+
+		if (!(irq_sts & (1 << i)))
+			continue;
+
+		handle_nested_irq(tps65910->irq_base + i);
+	}
+
+	/* Write the STS register back to clear IRQs we handled */
+	reg = irq_sts & 0xFF;
+	irq_sts >>= 8;
+	tps65910->write(tps65910, TPS65910_INT_STS, 1, &reg);
+	reg = irq_sts & 0xFF;
+	tps65910->write(tps65910, TPS65910_INT_STS2, 1, &reg);
+	switch (tps65910_chip_id(tps65910)) {
+	case TPS65911:
+		reg = irq_sts >> 8;
+		tps65910->write(tps65910, TPS65910_INT_STS3, 1, &reg);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void tps65910_irq_lock(struct irq_data *data)
+{
+	struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data);
+
+	mutex_lock(&tps65910->irq_lock);
+}
+
+static void tps65910_irq_sync_unlock(struct irq_data *data)
+{
+	struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data);
+	u32 reg_mask;
+	u8 reg;
+
+	tps65910->read(tps65910, TPS65910_INT_MSK, 1, &reg);
+	reg_mask = reg;
+	tps65910->read(tps65910, TPS65910_INT_MSK2, 1, &reg);
+	reg_mask |= reg << 8;
+	switch (tps65910_chip_id(tps65910)) {
+	case TPS65911:
+		tps65910->read(tps65910, TPS65910_INT_MSK3, 1, &reg);
+		reg_mask |= reg << 16;
+	}
+
+	if (tps65910->irq_mask != reg_mask) {
+		reg = tps65910->irq_mask & 0xFF;
+		tps65910->write(tps65910, TPS65910_INT_MSK, 1, &reg);
+		reg = tps65910->irq_mask >> 8 & 0xFF;
+		tps65910->write(tps65910, TPS65910_INT_MSK2, 1, &reg);
+		switch (tps65910_chip_id(tps65910)) {
+		case TPS65911:
+			reg = tps65910->irq_mask >> 16;
+			tps65910->write(tps65910, TPS65910_INT_MSK3, 1, &reg);
+		}
+	}
+	mutex_unlock(&tps65910->irq_lock);
+}
+
+static void tps65910_irq_enable(struct irq_data *data)
+{
+	struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data);
+
+	tps65910->irq_mask &= ~( 1 << irq_to_tps65910_irq(tps65910, data->irq));
+}
+
+static void tps65910_irq_disable(struct irq_data *data)
+{
+	struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data);
+
+	tps65910->irq_mask |= ( 1 << irq_to_tps65910_irq(tps65910, data->irq));
+}
+
+static struct irq_chip tps65910_irq_chip = {
+	.name = "tps65910",
+	.irq_bus_lock = tps65910_irq_lock,
+	.irq_bus_sync_unlock = tps65910_irq_sync_unlock,
+	.irq_disable = tps65910_irq_disable,
+	.irq_enable = tps65910_irq_enable,
+};
+
+int tps65910_irq_init(struct tps65910 *tps65910, int irq,
+		    struct tps65910_platform_data *pdata)
+{
+	int ret, cur_irq;
+	int flags = IRQF_ONESHOT;
+
+	if (!irq) {
+		dev_warn(tps65910->dev, "No interrupt support, no core IRQ\n");
+		return -EINVAL;
+	}
+
+	if (!pdata || !pdata->irq_base) {
+		dev_warn(tps65910->dev, "No interrupt support, no IRQ base\n");
+		return -EINVAL;
+	}
+
+	tps65910->irq_mask = 0xFFFFFF;
+
+	mutex_init(&tps65910->irq_lock);
+	tps65910->chip_irq = irq;
+	tps65910->irq_base = pdata->irq_base;
+
+	switch (tps65910_chip_id(tps65910)) {
+	case TPS65910:
+		tps65910->irq_num = TPS65910_NUM_IRQ;
+	case TPS65911:
+		tps65910->irq_num = TPS65911_NUM_IRQ;
+	}
+
+	/* Register with genirq */
+	for (cur_irq = tps65910->irq_base;
+	     cur_irq < tps65910->irq_num + tps65910->irq_base;
+	     cur_irq++) {
+		irq_set_chip_data(cur_irq, tps65910);
+		irq_set_chip_and_handler(cur_irq, &tps65910_irq_chip,
+					 handle_edge_irq);
+		irq_set_nested_thread(cur_irq, 1);
+
+		/* ARM needs us to explicitly flag the IRQ as valid
+		 * and will set them noprobe when we do so. */
+#ifdef CONFIG_ARM
+		set_irq_flags(cur_irq, IRQF_VALID);
+#else
+		irq_set_noprobe(cur_irq);
+#endif
+	}
+
+	ret = request_threaded_irq(irq, NULL, tps65910_irq, flags,
+				   "tps65910", tps65910);
+
+	irq_set_irq_type(irq, IRQ_TYPE_LEVEL_LOW);
+
+	if (ret != 0)
+		dev_err(tps65910->dev, "Failed to request IRQ: %d\n", ret);
+
+	return ret;
+}
+
+int tps65910_irq_exit(struct tps65910 *tps65910)
+{
+	free_irq(tps65910->chip_irq, tps65910);
+	return 0;
+}
diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c
new file mode 100644
index 000000000000..2229e66d80db
--- /dev/null
+++ b/drivers/mfd/tps65910.c
@@ -0,0 +1,229 @@
+/*
+ * tps65910.c  --  TI TPS6591x
+ *
+ * Copyright 2010 Texas Instruments Inc.
+ *
+ * Author: Graeme Gregory <gg@slimlogic.co.uk>
+ * Author: Jorge Eduardo Candelaria <jedu@slimlogic.co.uk>
+ *
+ *  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/module.h>
+#include <linux/moduleparam.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/tps65910.h>
+
+static struct mfd_cell tps65910s[] = {
+	{
+		.name = "tps65910-pmic",
+	},
+	{
+		.name = "tps65910-rtc",
+	},
+	{
+		.name = "tps65910-power",
+	},
+};
+
+
+static int tps65910_i2c_read(struct tps65910 *tps65910, u8 reg,
+				  int bytes, void *dest)
+{
+	struct i2c_client *i2c = tps65910->i2c_client;
+	struct i2c_msg xfer[2];
+	int ret;
+
+	/* Write register */
+	xfer[0].addr = i2c->addr;
+	xfer[0].flags = 0;
+	xfer[0].len = 1;
+	xfer[0].buf = &reg;
+
+	/* Read data */
+	xfer[1].addr = i2c->addr;
+	xfer[1].flags = I2C_M_RD;
+	xfer[1].len = bytes;
+	xfer[1].buf = dest;
+
+	ret = i2c_transfer(i2c->adapter, xfer, 2);
+	if (ret == 2)
+		ret = 0;
+	else if (ret >= 0)
+		ret = -EIO;
+
+	return ret;
+}
+
+static int tps65910_i2c_write(struct tps65910 *tps65910, u8 reg,
+				   int bytes, void *src)
+{
+	struct i2c_client *i2c = tps65910->i2c_client;
+	/* we add 1 byte for device register */
+	u8 msg[TPS65910_MAX_REGISTER + 1];
+	int ret;
+
+	if (bytes > TPS65910_MAX_REGISTER)
+		return -EINVAL;
+
+	msg[0] = reg;
+	memcpy(&msg[1], src, bytes);
+
+	ret = i2c_master_send(i2c, msg, bytes + 1);
+	if (ret < 0)
+		return ret;
+	if (ret != bytes + 1)
+		return -EIO;
+	return 0;
+}
+
+int tps65910_set_bits(struct tps65910 *tps65910, u8 reg, u8 mask)
+{
+	u8 data;
+	int err;
+
+	mutex_lock(&tps65910->io_mutex);
+	err = tps65910_i2c_read(tps65910, reg, 1, &data);
+	if (err) {
+		dev_err(tps65910->dev, "read from reg %x failed\n", reg);
+		goto out;
+	}
+
+	data |= mask;
+	err = tps65910_i2c_write(tps65910, reg, 1, &data);
+	if (err)
+		dev_err(tps65910->dev, "write to reg %x failed\n", reg);
+
+out:
+	mutex_unlock(&tps65910->io_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(tps65910_set_bits);
+
+int tps65910_clear_bits(struct tps65910 *tps65910, u8 reg, u8 mask)
+{
+	u8 data;
+	int err;
+
+	mutex_lock(&tps65910->io_mutex);
+	err = tps65910_i2c_read(tps65910, reg, 1, &data);
+	if (err) {
+		dev_err(tps65910->dev, "read from reg %x failed\n", reg);
+		goto out;
+	}
+
+	data &= mask;
+	err = tps65910_i2c_write(tps65910, reg, 1, &data);
+	if (err)
+		dev_err(tps65910->dev, "write to reg %x failed\n", reg);
+
+out:
+	mutex_unlock(&tps65910->io_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(tps65910_clear_bits);
+
+static int tps65910_i2c_probe(struct i2c_client *i2c,
+			    const struct i2c_device_id *id)
+{
+	struct tps65910 *tps65910;
+	struct tps65910_board *pmic_plat_data;
+	struct tps65910_platform_data *init_data;
+	int ret = 0;
+
+	pmic_plat_data = dev_get_platdata(&i2c->dev);
+	if (!pmic_plat_data)
+		return -EINVAL;
+
+	init_data = kzalloc(sizeof(struct tps65910_platform_data), GFP_KERNEL);
+	if (init_data == NULL)
+		return -ENOMEM;
+
+	init_data->irq = pmic_plat_data->irq;
+	init_data->irq_base = pmic_plat_data->irq;
+
+	tps65910 = kzalloc(sizeof(struct tps65910), GFP_KERNEL);
+	if (tps65910 == NULL)
+		return -ENOMEM;
+
+	i2c_set_clientdata(i2c, tps65910);
+	tps65910->dev = &i2c->dev;
+	tps65910->i2c_client = i2c;
+	tps65910->id = id->driver_data;
+	tps65910->read = tps65910_i2c_read;
+	tps65910->write = tps65910_i2c_write;
+	mutex_init(&tps65910->io_mutex);
+
+	ret = mfd_add_devices(tps65910->dev, -1,
+			      tps65910s, ARRAY_SIZE(tps65910s),
+			      NULL, 0);
+	if (ret < 0)
+		goto err;
+
+	tps65910_gpio_init(tps65910, pmic_plat_data->gpio_base);
+
+	ret = tps65910_irq_init(tps65910, init_data->irq, init_data);
+	if (ret < 0)
+		goto err;
+
+	return ret;
+
+err:
+	mfd_remove_devices(tps65910->dev);
+	kfree(tps65910);
+	return ret;
+}
+
+static int tps65910_i2c_remove(struct i2c_client *i2c)
+{
+	struct tps65910 *tps65910 = i2c_get_clientdata(i2c);
+
+	mfd_remove_devices(tps65910->dev);
+	kfree(tps65910);
+
+	return 0;
+}
+
+static const struct i2c_device_id tps65910_i2c_id[] = {
+       { "tps65910", TPS65910 },
+       { "tps65911", TPS65911 },
+       { }
+};
+MODULE_DEVICE_TABLE(i2c, tps65910_i2c_id);
+
+
+static struct i2c_driver tps65910_i2c_driver = {
+	.driver = {
+		   .name = "tps65910",
+		   .owner = THIS_MODULE,
+	},
+	.probe = tps65910_i2c_probe,
+	.remove = tps65910_i2c_remove,
+	.id_table = tps65910_i2c_id,
+};
+
+static int __init tps65910_i2c_init(void)
+{
+	return i2c_add_driver(&tps65910_i2c_driver);
+}
+/* init early so consumer devices can complete system boot */
+subsys_initcall(tps65910_i2c_init);
+
+static void __exit tps65910_i2c_exit(void)
+{
+	i2c_del_driver(&tps65910_i2c_driver);
+}
+module_exit(tps65910_i2c_exit);
+
+MODULE_AUTHOR("Graeme Gregory <gg@slimlogic.co.uk>");
+MODULE_AUTHOR("Jorge Eduardo Candelaria <jedu@slimlogic.co.uk>");
+MODULE_DESCRIPTION("TPS6591x chip family multi-function driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/tps65911-comparator.c b/drivers/mfd/tps65911-comparator.c
new file mode 100644
index 000000000000..3d2dc56a3d40
--- /dev/null
+++ b/drivers/mfd/tps65911-comparator.c
@@ -0,0 +1,188 @@
+/*
+ * tps65910.c  --  TI TPS6591x
+ *
+ * Copyright 2010 Texas Instruments Inc.
+ *
+ * Author: Jorge Eduardo Candelaria <jedu@slimlogic.co.uk>
+ *
+ *  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/init.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/debugfs.h>
+#include <linux/gpio.h>
+#include <linux/mfd/tps65910.h>
+
+#define COMP					0
+#define COMP1					1
+#define COMP2					2
+
+/* Comparator 1 voltage selection table in milivolts */
+static const u16 COMP_VSEL_TABLE[] = {
+	0, 2500, 2500, 2500, 2500, 2550, 2600, 2650,
+	2700, 2750, 2800, 2850, 2900, 2950, 3000, 3050,
+	3100, 3150, 3200, 3250, 3300, 3350, 3400, 3450,
+	3500,
+};
+
+struct comparator {
+	const char *name;
+	int reg;
+	int uV_max;
+	const u16 *vsel_table;
+};
+
+static struct comparator tps_comparators[] = {
+	{
+		.name = "COMP1",
+		.reg = TPS65911_VMBCH,
+		.uV_max = 3500,
+		.vsel_table = COMP_VSEL_TABLE,
+	},
+	{
+		.name = "COMP2",
+		.reg = TPS65911_VMBCH2,
+		.uV_max = 3500,
+		.vsel_table = COMP_VSEL_TABLE,
+	},
+};
+
+static int comp_threshold_set(struct tps65910 *tps65910, int id, int voltage)
+{
+	struct comparator tps_comp = tps_comparators[id];
+	int curr_voltage = 0;
+	int ret;
+	u8 index = 0, val;
+
+	if (id == COMP)
+		return 0;
+
+	while (curr_voltage < tps_comp.uV_max) {
+		curr_voltage = tps_comp.vsel_table[index];
+		if (curr_voltage >= voltage)
+			break;
+		else if (curr_voltage < voltage)
+			index ++;
+	}
+
+	if (curr_voltage > tps_comp.uV_max)
+		return -EINVAL;
+
+	val = index << 1;
+	ret = tps65910->write(tps65910, tps_comp.reg, 1, &val);
+
+	return ret;
+}
+
+static int comp_threshold_get(struct tps65910 *tps65910, int id)
+{
+	struct comparator tps_comp = tps_comparators[id];
+	int ret;
+	u8 val;
+
+	if (id == COMP)
+		return 0;
+
+	ret = tps65910->read(tps65910, tps_comp.reg, 1, &val);
+	if (ret < 0)
+		return ret;
+
+	val >>= 1;
+	return tps_comp.vsel_table[val];
+}
+
+static ssize_t comp_threshold_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct tps65910 *tps65910 = dev_get_drvdata(dev->parent);
+	struct attribute comp_attr = attr->attr;
+	int id, uVolt;
+
+	if (!strcmp(comp_attr.name, "comp1_threshold"))
+		id = COMP1;
+	else if (!strcmp(comp_attr.name, "comp2_threshold"))
+		id = COMP2;
+	else
+		return -EINVAL;
+
+	uVolt = comp_threshold_get(tps65910, id);
+
+	return sprintf(buf, "%d\n", uVolt);
+}
+
+static DEVICE_ATTR(comp1_threshold, S_IRUGO, comp_threshold_show, NULL);
+static DEVICE_ATTR(comp2_threshold, S_IRUGO, comp_threshold_show, NULL);
+
+static __devinit int tps65911_comparator_probe(struct platform_device *pdev)
+{
+	struct tps65910 *tps65910 = dev_get_drvdata(pdev->dev.parent);
+	struct tps65910_platform_data *pdata = dev_get_platdata(tps65910->dev);
+	int ret;
+
+	ret = comp_threshold_set(tps65910, COMP1,  pdata->vmbch_threshold);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "cannot set COMP1 threshold\n");
+		return ret;
+	}
+
+	ret = comp_threshold_set(tps65910, COMP2, pdata->vmbch2_threshold);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "cannot set COMP2 theshold\n");
+		return ret;
+	}
+
+	/* Create sysfs entry */
+	ret = device_create_file(&pdev->dev, &dev_attr_comp1_threshold);
+	if (ret < 0)
+		dev_err(&pdev->dev, "failed to add COMP1 sysfs file\n");
+
+	ret = device_create_file(&pdev->dev, &dev_attr_comp2_threshold);
+	if (ret < 0)
+		dev_err(&pdev->dev, "failed to add COMP2 sysfs file\n");
+
+	return ret;
+}
+
+static __devexit int tps65911_comparator_remove(struct platform_device *pdev)
+{
+	struct tps65910 *tps65910;
+
+	tps65910 = dev_get_drvdata(pdev->dev.parent);
+
+	return 0;
+}
+
+static struct platform_driver tps65911_comparator_driver = {
+	.driver = {
+		.name = "tps65911-comparator",
+		.owner = THIS_MODULE,
+	},
+	.probe = tps65911_comparator_probe,
+	.remove = __devexit_p(tps65911_comparator_remove),
+};
+
+static int __init tps65911_comparator_init(void)
+{
+	return platform_driver_register(&tps65911_comparator_driver);
+}
+subsys_initcall(tps65911_comparator_init);
+
+static void __exit tps65911_comparator_exit(void)
+{
+	platform_driver_unregister(&tps65911_comparator_driver);
+}
+module_exit(tps65911_comparator_exit);
+
+MODULE_AUTHOR("Jorge Eduardo Candelaria <jedu@slimlogic.co.uk>");
+MODULE_DESCRIPTION("TPS65911 comparator driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:tps65911-comparator");
diff --git a/drivers/misc/apds990x.c b/drivers/misc/apds990x.c
index 200311fea369..e2a52e5cf449 100644
--- a/drivers/misc/apds990x.c
+++ b/drivers/misc/apds990x.c
@@ -609,6 +609,7 @@ static int apds990x_detect(struct apds990x_chip *chip)
 	return ret;
 }
 
+#if defined(CONFIG_PM) || defined(CONFIG_PM_RUNTIME)
 static int apds990x_chip_on(struct apds990x_chip *chip)
 {
 	int err	 = regulator_bulk_enable(ARRAY_SIZE(chip->regs),
@@ -624,6 +625,7 @@ static int apds990x_chip_on(struct apds990x_chip *chip)
 	apds990x_mode_on(chip);
 	return 0;
 }
+#endif
 
 static int apds990x_chip_off(struct apds990x_chip *chip)
 {
diff --git a/drivers/misc/cb710/sgbuf2.c b/drivers/misc/cb710/sgbuf2.c
index d019746551f3..2a40d0efdff5 100644
--- a/drivers/misc/cb710/sgbuf2.c
+++ b/drivers/misc/cb710/sgbuf2.c
@@ -47,7 +47,7 @@ static uint32_t sg_dwiter_read_buffer(struct sg_mapping_iter *miter)
 
 static inline bool needs_unaligned_copy(const void *ptr)
 {
-#ifdef HAVE_EFFICIENT_UNALIGNED_ACCESS
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 	return false;
 #else
 	return ((ptr - NULL) & 3) != 0;
diff --git a/drivers/misc/cs5535-mfgpt.c b/drivers/misc/cs5535-mfgpt.c
index e01e08c8c88b..bc685bfc4c33 100644
--- a/drivers/misc/cs5535-mfgpt.c
+++ b/drivers/misc/cs5535-mfgpt.c
@@ -174,7 +174,7 @@ struct cs5535_mfgpt_timer *cs5535_mfgpt_alloc_timer(int timer_nr, int domain)
 		timer_nr = t < max ? (int) t : -1;
 	} else {
 		/* check if the requested timer's available */
-		if (test_bit(timer_nr, mfgpt->avail))
+		if (!test_bit(timer_nr, mfgpt->avail))
 			timer_nr = -1;
 	}
 
diff --git a/drivers/misc/ioc4.c b/drivers/misc/ioc4.c
index 668d41e594a9..df03dd3bd0e2 100644
--- a/drivers/misc/ioc4.c
+++ b/drivers/misc/ioc4.c
@@ -270,7 +270,7 @@ ioc4_variant(struct ioc4_driver_data *idd)
 	return IOC4_VARIANT_PCI_RT;
 }
 
-static void __devinit
+static void
 ioc4_load_modules(struct work_struct *work)
 {
 	request_module("sgiioc4");
diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c
index b0c56313dbbb..8cebec5e85ee 100644
--- a/drivers/misc/kgdbts.c
+++ b/drivers/misc/kgdbts.c
@@ -304,7 +304,10 @@ static int check_and_rewind_pc(char *put_str, char *arg)
 		return 1;
 	}
 	/* Readjust the instruction pointer if needed */
-	instruction_pointer_set(&kgdbts_regs, ip + offset);
+	ip += offset;
+#ifdef GDB_ADJUSTS_BREAK_OFFSET
+	instruction_pointer_set(&kgdbts_regs, ip);
+#endif
 	return 0;
 }
 
diff --git a/drivers/misc/lkdtm.c b/drivers/misc/lkdtm.c
index 81d7fa4ec0db..150cd7061b80 100644
--- a/drivers/misc/lkdtm.c
+++ b/drivers/misc/lkdtm.c
@@ -120,6 +120,7 @@ static int recur_count = REC_NUM_DEFAULT;
 static enum cname cpoint = CN_INVALID;
 static enum ctype cptype = CT_NONE;
 static int count = DEFAULT_COUNT;
+static DEFINE_SPINLOCK(count_lock);
 
 module_param(recur_count, int, 0644);
 MODULE_PARM_DESC(recur_count, " Recursion level for the stack overflow test, "\
@@ -230,11 +231,14 @@ static const char *cp_name_to_str(enum cname name)
 static int lkdtm_parse_commandline(void)
 {
 	int i;
+	unsigned long flags;
 
 	if (cpoint_count < 1 || recur_count < 1)
 		return -EINVAL;
 
+	spin_lock_irqsave(&count_lock, flags);
 	count = cpoint_count;
+	spin_unlock_irqrestore(&count_lock, flags);
 
 	/* No special parameters */
 	if (!cpoint_type && !cpoint_name)
@@ -349,6 +353,9 @@ static void lkdtm_do_action(enum ctype which)
 
 static void lkdtm_handler(void)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&count_lock, flags);
 	count--;
 	printk(KERN_INFO "lkdtm: Crash point %s of type %s hit, trigger in %d rounds\n",
 			cp_name_to_str(cpoint), cp_type_to_str(cptype), count);
@@ -357,6 +364,7 @@ static void lkdtm_handler(void)
 		lkdtm_do_action(cptype);
 		count = cpoint_count;
 	}
+	spin_unlock_irqrestore(&count_lock, flags);
 }
 
 static int lkdtm_register_cpoint(enum cname which)
diff --git a/drivers/misc/sgi-xp/xpnet.c b/drivers/misc/sgi-xp/xpnet.c
index ee5109a3cd98..42f067347bc7 100644
--- a/drivers/misc/sgi-xp/xpnet.c
+++ b/drivers/misc/sgi-xp/xpnet.c
@@ -495,14 +495,14 @@ xpnet_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += skb->len;
+
 	if (atomic_dec_return(&queued_msg->use_count) == 0) {
 		dev_kfree_skb(skb);
 		kfree(queued_msg);
 	}
 
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
-
 	return NETDEV_TX_OK;
 }
 
diff --git a/drivers/misc/spear13xx_pcie_gadget.c b/drivers/misc/spear13xx_pcie_gadget.c
index 7aded90f9daa..cfbddbef11de 100644
--- a/drivers/misc/spear13xx_pcie_gadget.c
+++ b/drivers/misc/spear13xx_pcie_gadget.c
@@ -845,7 +845,7 @@ err_iounmap:
 err_iounmap_app:
 	iounmap(config->va_app_base);
 err_kzalloc:
-	kfree(config);
+	kfree(target);
 err_rel_res:
 	release_mem_region(res1->start, resource_size(res1));
 err_rel_res0:
diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c
index 1a05fe08e2cb..f91f82eabda7 100644
--- a/drivers/misc/ti-st/st_core.c
+++ b/drivers/misc/ti-st/st_core.c
@@ -747,8 +747,8 @@ static void st_tty_close(struct tty_struct *tty)
 	pr_debug("%s: done ", __func__);
 }
 
-static unsigned int st_tty_receive(struct tty_struct *tty,
-		const unsigned char *data, char *tty_flags, int count)
+static void st_tty_receive(struct tty_struct *tty, const unsigned char *data,
+			   char *tty_flags, int count)
 {
 #ifdef VERBOSE
 	print_hex_dump(KERN_DEBUG, ">in>", DUMP_PREFIX_NONE,
@@ -761,8 +761,6 @@ static unsigned int st_tty_receive(struct tty_struct *tty,
 	 */
 	st_recv(tty->disc_data, data, count);
 	pr_debug("done %s", __func__);
-
-	return count;
 }
 
 /* wake-up function called in from the TTY layer
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 71da5641e258..f85e42224559 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -1024,7 +1024,7 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 	INIT_LIST_HEAD(&md->part);
 	md->usage = 1;
 
-	ret = mmc_init_queue(&md->queue, card, &md->lock);
+	ret = mmc_init_queue(&md->queue, card, &md->lock, subname);
 	if (ret)
 		goto err_putdisk;
 
@@ -1297,6 +1297,9 @@ static void mmc_blk_remove(struct mmc_card *card)
 	struct mmc_blk_data *md = mmc_get_drvdata(card);
 
 	mmc_blk_remove_parts(card, md);
+	mmc_claim_host(card->host);
+	mmc_blk_part_switch(card, md);
+	mmc_release_host(card->host);
 	mmc_blk_remove_req(md);
 	mmc_set_drvdata(card, NULL);
 }
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index c07322c2658c..6413afa318d2 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -106,10 +106,12 @@ static void mmc_request(struct request_queue *q)
  * @mq: mmc queue
  * @card: mmc card to attach this queue
  * @lock: queue lock
+ * @subname: partition subname
  *
  * Initialise a MMC card request queue.
  */
-int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock)
+int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
+		   spinlock_t *lock, const char *subname)
 {
 	struct mmc_host *host = card->host;
 	u64 limit = BLK_BOUNCE_HIGH;
@@ -133,12 +135,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock
 		mq->queue->limits.max_discard_sectors = UINT_MAX;
 		if (card->erased_byte == 0)
 			mq->queue->limits.discard_zeroes_data = 1;
-		if (!mmc_can_trim(card) && is_power_of_2(card->erase_size)) {
-			mq->queue->limits.discard_granularity =
-							card->erase_size << 9;
-			mq->queue->limits.discard_alignment =
-							card->erase_size << 9;
-		}
+		mq->queue->limits.discard_granularity = card->pref_erase << 9;
 		if (mmc_can_secure_erase_trim(card))
 			queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD,
 						mq->queue);
@@ -209,8 +206,8 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock
 
 	sema_init(&mq->thread_sem, 1);
 
-	mq->thread = kthread_run(mmc_queue_thread, mq, "mmcqd/%d",
-		host->index);
+	mq->thread = kthread_run(mmc_queue_thread, mq, "mmcqd/%d%s",
+		host->index, subname ? subname : "");
 
 	if (IS_ERR(mq->thread)) {
 		ret = PTR_ERR(mq->thread);
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index 64e66e0d4994..6223ef8dc9cd 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -19,7 +19,8 @@ struct mmc_queue {
 	unsigned int		bounce_sg_len;
 };
 
-extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *);
+extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *,
+			  const char *);
 extern void mmc_cleanup_queue(struct mmc_queue *);
 extern void mmc_queue_suspend(struct mmc_queue *);
 extern void mmc_queue_resume(struct mmc_queue *);
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 68091dda3f31..7843efe22359 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -1245,7 +1245,7 @@ static unsigned int mmc_mmc_erase_timeout(struct mmc_card *card,
 		 */
 		timeout_clks <<= 1;
 		timeout_us += (timeout_clks * 1000) /
-			      (card->host->ios.clock / 1000);
+			      (mmc_host_clk_rate(card->host) / 1000);
 
 		erase_timeout = timeout_us / 1000;
 
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index 4d0c15bfa514..262fff019177 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -691,15 +691,54 @@ static int mmc_sdio_resume(struct mmc_host *host)
 static int mmc_sdio_power_restore(struct mmc_host *host)
 {
 	int ret;
+	u32 ocr;
 
 	BUG_ON(!host);
 	BUG_ON(!host->card);
 
 	mmc_claim_host(host);
+
+	/*
+	 * Reset the card by performing the same steps that are taken by
+	 * mmc_rescan_try_freq() and mmc_attach_sdio() during a "normal" probe.
+	 *
+	 * sdio_reset() is technically not needed. Having just powered up the
+	 * hardware, it should already be in reset state. However, some
+	 * platforms (such as SD8686 on OLPC) do not instantly cut power,
+	 * meaning that a reset is required when restoring power soon after
+	 * powering off. It is harmless in other cases.
+	 *
+	 * The CMD5 reset (mmc_send_io_op_cond()), according to the SDIO spec,
+	 * is not necessary for non-removable cards. However, it is required
+	 * for OLPC SD8686 (which expects a [CMD5,5,3,7] init sequence), and
+	 * harmless in other situations.
+	 *
+	 * With these steps taken, mmc_select_voltage() is also required to
+	 * restore the correct voltage setting of the card.
+	 */
+	sdio_reset(host);
+	mmc_go_idle(host);
+	mmc_send_if_cond(host, host->ocr_avail);
+
+	ret = mmc_send_io_op_cond(host, 0, &ocr);
+	if (ret)
+		goto out;
+
+	if (host->ocr_avail_sdio)
+		host->ocr_avail = host->ocr_avail_sdio;
+
+	host->ocr = mmc_select_voltage(host, ocr & ~0x7F);
+	if (!host->ocr) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	ret = mmc_sdio_init_card(host, host->ocr, host->card,
 				mmc_card_keep_power(host));
 	if (!ret && host->sdio_irqs)
 		mmc_signal_sdio_irq(host);
+
+out:
 	mmc_release_host(host);
 
 	return ret;
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index d29b9c36919a..d2565df8a7fb 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -189,7 +189,7 @@ static int sdio_bus_remove(struct device *dev)
 
 	/* Then undo the runtime PM settings in sdio_bus_probe() */
 	if (func->card->host->caps & MMC_CAP_POWER_OFF_CARD)
-		pm_runtime_put_noidle(dev);
+		pm_runtime_put_sync(dev);
 
 out:
 	return ret;
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 4941e06fe2e1..7721de942c69 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -51,6 +51,7 @@ static unsigned int fmax = 515633;
  *		  is asserted (likewise for RX)
  * @sdio: variant supports SDIO
  * @st_clkdiv: true if using a ST-specific clock divider algorithm
+ * @blksz_datactrl16: true if Block size is at b16..b30 position in datactrl register
  */
 struct variant_data {
 	unsigned int		clkreg;
@@ -60,6 +61,7 @@ struct variant_data {
 	unsigned int		fifohalfsize;
 	bool			sdio;
 	bool			st_clkdiv;
+	bool			blksz_datactrl16;
 };
 
 static struct variant_data variant_arm = {
@@ -92,6 +94,17 @@ static struct variant_data variant_ux500 = {
 	.st_clkdiv		= true,
 };
 
+static struct variant_data variant_ux500v2 = {
+	.fifosize		= 30 * 4,
+	.fifohalfsize		= 8 * 4,
+	.clkreg			= MCI_CLK_ENABLE,
+	.clkreg_enable		= MCI_ST_UX500_HWFCEN,
+	.datalength_bits	= 24,
+	.sdio			= true,
+	.st_clkdiv		= true,
+	.blksz_datactrl16	= true,
+};
+
 /*
  * This must be called with host->lock held
  */
@@ -465,7 +478,10 @@ static void mmci_start_data(struct mmci_host *host, struct mmc_data *data)
 	blksz_bits = ffs(data->blksz) - 1;
 	BUG_ON(1 << blksz_bits != data->blksz);
 
-	datactrl = MCI_DPSM_ENABLE | blksz_bits << 4;
+	if (variant->blksz_datactrl16)
+		datactrl = MCI_DPSM_ENABLE | (data->blksz << 16);
+	else
+		datactrl = MCI_DPSM_ENABLE | blksz_bits << 4;
 
 	if (data->flags & MMC_DATA_READ)
 		datactrl |= MCI_DPSM_DIRECTION;
@@ -1128,9 +1144,17 @@ static int __devinit mmci_probe(struct amba_device *dev,
 		else if (ret != -ENOSYS)
 			goto err_gpio_cd;
 
+		/*
+		 * A gpio pin that will detect cards when inserted and removed
+		 * will most likely want to trigger on the edges if it is
+		 * 0 when ejected and 1 when inserted (or mutatis mutandis
+		 * for the inverted case) so we request triggers on both
+		 * edges.
+		 */
 		ret = request_any_context_irq(gpio_to_irq(plat->gpio_cd),
-					      mmci_cd_irq, 0,
-					      DRIVER_NAME " (cd)", host);
+				mmci_cd_irq,
+				IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
+				DRIVER_NAME " (cd)", host);
 		if (ret >= 0)
 			host->gpio_cd_irq = gpio_to_irq(plat->gpio_cd);
 	}
@@ -1311,9 +1335,14 @@ static struct amba_id mmci_ids[] = {
 	},
 	{
 		.id     = 0x00480180,
-		.mask   = 0x00ffffff,
+		.mask   = 0xf0ffffff,
 		.data	= &variant_ux500,
 	},
+	{
+		.id     = 0x10480180,
+		.mask   = 0xf0ffffff,
+		.data	= &variant_ux500v2,
+	},
 	{ 0, 0 },
 };
 
diff --git a/drivers/mmc/host/of_mmc_spi.c b/drivers/mmc/host/of_mmc_spi.c
index e2aecb7f1d5c..ab66f2454dc4 100644
--- a/drivers/mmc/host/of_mmc_spi.c
+++ b/drivers/mmc/host/of_mmc_spi.c
@@ -25,6 +25,11 @@
 #include <linux/mmc/core.h>
 #include <linux/mmc/host.h>
 
+/* For archs that don't support NO_IRQ (such as mips), provide a dummy value */
+#ifndef NO_IRQ
+#define NO_IRQ 0
+#endif
+
 MODULE_LICENSE("GPL");
 
 enum {
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 259ece047afc..dedf3dab8a3b 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -429,12 +429,14 @@ static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host)
 				return -EINVAL;
 			}
 		}
-		mmc_slot(host).ocr_mask = mmc_regulator_get_ocrmask(reg);
 
 		/* Allow an aux regulator */
 		reg = regulator_get(host->dev, "vmmc_aux");
 		host->vcc_aux = IS_ERR(reg) ? NULL : reg;
 
+		/* For eMMC do not power off when not in sleep state */
+		if (mmc_slot(host).no_regulator_off_init)
+			return 0;
 		/*
 		* UGLY HACK:  workaround regulator framework bugs.
 		* When the bootloader leaves a supply active, it's
@@ -959,7 +961,8 @@ static void omap_hsmmc_dma_cleanup(struct omap_hsmmc_host *host, int errno)
 	spin_unlock(&host->irq_lock);
 
 	if (host->use_dma && dma_ch != -1) {
-		dma_unmap_sg(mmc_dev(host->mmc), host->data->sg, host->dma_len,
+		dma_unmap_sg(mmc_dev(host->mmc), host->data->sg,
+			host->data->sg_len,
 			omap_hsmmc_get_dma_dir(host, host->data));
 		omap_free_dma(dma_ch);
 	}
@@ -1343,7 +1346,7 @@ static void omap_hsmmc_dma_cb(int lch, u16 ch_status, void *cb_data)
 		return;
 	}
 
-	dma_unmap_sg(mmc_dev(host->mmc), data->sg, host->dma_len,
+	dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
 		omap_hsmmc_get_dma_dir(host, data));
 
 	req_in_progress = host->req_in_progress;
diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index b3654293017b..ce500f03df85 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -92,7 +92,7 @@ static int __devinit sh_mobile_sdhi_probe(struct platform_device *pdev)
 		mmc_data->ocr_mask = p->tmio_ocr_mask;
 		mmc_data->capabilities |= p->tmio_caps;
 
-		if (p->dma_slave_tx >= 0 && p->dma_slave_rx >= 0) {
+		if (p->dma_slave_tx > 0 && p->dma_slave_rx > 0) {
 			priv->param_tx.slave_id = p->dma_slave_tx;
 			priv->param_rx.slave_id = p->dma_slave_rx;
 			priv->dma_priv.chan_priv_tx = &priv->param_tx;
@@ -165,13 +165,14 @@ static int sh_mobile_sdhi_remove(struct platform_device *pdev)
 
 	p->pdata = NULL;
 
+	tmio_mmc_host_remove(host);
+
 	for (i = 0; i < 3; i++) {
 		irq = platform_get_irq(pdev, i);
 		if (irq >= 0)
 			free_irq(irq, host);
 	}
 
-	tmio_mmc_host_remove(host);
 	clk_disable(priv->clk);
 	clk_put(priv->clk);
 	kfree(priv);
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index ad6347bb02dd..0b09e8239aa0 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -824,8 +824,8 @@ static int tmio_mmc_get_ro(struct mmc_host *mmc)
 	struct tmio_mmc_host *host = mmc_priv(mmc);
 	struct tmio_mmc_data *pdata = host->pdata;
 
-	return ((pdata->flags & TMIO_MMC_WRPROTECT_DISABLE) ||
-		!(sd_ctrl_read32(host, CTL_STATUS) & TMIO_STAT_WRPROTECT));
+	return !((pdata->flags & TMIO_MMC_WRPROTECT_DISABLE) ||
+		 (sd_ctrl_read32(host, CTL_STATUS) & TMIO_STAT_WRPROTECT));
 }
 
 static int tmio_mmc_get_cd(struct mmc_host *mmc)
diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c
index cbb03305b77b..d4455ffbefd8 100644
--- a/drivers/mmc/host/vub300.c
+++ b/drivers/mmc/host/vub300.c
@@ -2096,7 +2096,7 @@ static struct mmc_host_ops vub300_mmc_ops = {
 static int vub300_probe(struct usb_interface *interface,
 			const struct usb_device_id *id)
 {				/* NOT irq */
-	struct vub300_mmc_host *vub300 = NULL;
+	struct vub300_mmc_host *vub300;
 	struct usb_host_interface *iface_desc;
 	struct usb_device *udev = usb_get_dev(interface_to_usbdev(interface));
 	int i;
@@ -2118,23 +2118,20 @@ static int vub300_probe(struct usb_interface *interface,
 	command_out_urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!command_out_urb) {
 		retval = -ENOMEM;
-		dev_err(&vub300->udev->dev,
-			"not enough memory for the command_out_urb\n");
+		dev_err(&udev->dev, "not enough memory for command_out_urb\n");
 		goto error0;
 	}
 	command_res_urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!command_res_urb) {
 		retval = -ENOMEM;
-		dev_err(&vub300->udev->dev,
-			"not enough memory for the command_res_urb\n");
+		dev_err(&udev->dev, "not enough memory for command_res_urb\n");
 		goto error1;
 	}
 	/* this also allocates memory for our VUB300 mmc host device */
 	mmc = mmc_alloc_host(sizeof(struct vub300_mmc_host), &udev->dev);
 	if (!mmc) {
 		retval = -ENOMEM;
-		dev_err(&vub300->udev->dev,
-			"not enough memory for the mmc_host\n");
+		dev_err(&udev->dev, "not enough memory for the mmc_host\n");
 		goto error4;
 	}
 	/* MMC core transfer sizes tunable parameters */
diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig
index bc50d5ea5534..4be8373d43e5 100644
--- a/drivers/mtd/Kconfig
+++ b/drivers/mtd/Kconfig
@@ -33,20 +33,6 @@ config MTD_TESTS
 	  should normally be compiled as kernel modules. The modules perform
 	  various checks and verifications when loaded.
 
-config MTD_PARTITIONS
-	bool "MTD partitioning support"
-	help
-	  If you have a device which needs to divide its flash chip(s) up
-	  into multiple 'partitions', each of which appears to the user as
-	  a separate MTD device, you require this option to be enabled. If
-	  unsure, say 'Y'.
-
-	  Note, however, that you don't need this option for the DiskOnChip
-	  devices. Partitioning on NFTL 'devices' is a different - that's the
-	  'normal' form of partitioning used on a block device.
-
-if MTD_PARTITIONS
-
 config MTD_REDBOOT_PARTS
 	tristate "RedBoot partition table parsing"
 	---help---
@@ -99,7 +85,7 @@ endif # MTD_REDBOOT_PARTS
 
 config MTD_CMDLINE_PARTS
 	bool "Command line partition table parsing"
-	depends on MTD_PARTITIONS = "y" && MTD = "y"
+	depends on MTD = "y"
 	---help---
 	  Allow generic configuration of the MTD partition tables via the kernel
 	  command line. Multiple flash resources are supported for hardware where
@@ -163,8 +149,6 @@ config MTD_AR7_PARTS
 	---help---
 	  TI AR7 partitioning support
 
-endif # MTD_PARTITIONS
-
 comment "User Modules And Translation Layers"
 
 config MTD_CHAR
diff --git a/drivers/mtd/Makefile b/drivers/mtd/Makefile
index d578095fb255..39664c4229ff 100644
--- a/drivers/mtd/Makefile
+++ b/drivers/mtd/Makefile
@@ -4,8 +4,7 @@
 
 # Core functionality.
 obj-$(CONFIG_MTD)		+= mtd.o
-mtd-y				:= mtdcore.o mtdsuper.o mtdconcat.o
-mtd-$(CONFIG_MTD_PARTITIONS)	+= mtdpart.o
+mtd-y				:= mtdcore.o mtdsuper.o mtdconcat.o mtdpart.o
 mtd-$(CONFIG_MTD_OF_PARTS)	+= ofpart.o
 
 obj-$(CONFIG_MTD_REDBOOT_PARTS) += redboot.o
diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c
index 09cb7c8d93b4..e1e122f2f929 100644
--- a/drivers/mtd/chips/cfi_cmdset_0001.c
+++ b/drivers/mtd/chips/cfi_cmdset_0001.c
@@ -812,12 +812,9 @@ static int chip_ready (struct map_info *map, struct flchip *chip, unsigned long
 			        break;
 
 			if (time_after(jiffies, timeo)) {
-				/* Urgh. Resume and pretend we weren't here.  */
-				map_write(map, CMD(0xd0), adr);
-				/* Make sure we're in 'read status' mode if it had finished */
-				map_write(map, CMD(0x70), adr);
-				chip->state = FL_ERASING;
-				chip->oldstate = FL_READY;
+				/* Urgh. Resume and pretend we weren't here.
+				 * Make sure we're in 'read status' mode if it had finished */
+				put_chip(map, chip, adr);
 				printk(KERN_ERR "%s: Chip not ready after erase "
 				       "suspended: status = 0x%lx\n", map->name, status.x[0]);
 				return -EIO;
@@ -997,7 +994,6 @@ static void put_chip(struct map_info *map, struct flchip *chip, unsigned long ad
 
 	switch(chip->oldstate) {
 	case FL_ERASING:
-		chip->state = chip->oldstate;
 		/* What if one interleaved chip has finished and the
 		   other hasn't? The old code would leave the finished
 		   one in READY mode. That's bad, and caused -EROFS
diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index 0b49266840b9..23175edd5634 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -462,13 +462,14 @@ struct mtd_info *cfi_cmdset_0002(struct map_info *map, int primary)
 			cfi_fixup_major_minor(cfi, extp);
 
 			/*
-			 * Valid primary extension versions are: 1.0, 1.1, 1.2, 1.3, 1.4
+			 * Valid primary extension versions are: 1.0, 1.1, 1.2, 1.3, 1.4, 1.5
 			 * see: http://cs.ozerki.net/zap/pub/axim-x5/docs/cfi_r20.pdf, page 19 
 			 *      http://www.spansion.com/Support/AppNotes/cfi_100_20011201.pdf
 			 *      http://www.spansion.com/Support/Datasheets/s29ws-p_00_a12_e.pdf
+			 *      http://www.spansion.com/Support/Datasheets/S29GL_128S_01GS_00_02_e.pdf
 			 */
 			if (extp->MajorVersion != '1' ||
-			    (extp->MajorVersion == '1' && (extp->MinorVersion < '0' || extp->MinorVersion > '4'))) {
+			    (extp->MajorVersion == '1' && (extp->MinorVersion < '0' || extp->MinorVersion > '5'))) {
 				printk(KERN_ERR "  Unknown Amd/Fujitsu Extended Query "
 				       "version %c.%c (%#02x/%#02x).\n",
 				       extp->MajorVersion, extp->MinorVersion,
@@ -710,9 +711,7 @@ static int get_chip(struct map_info *map, struct flchip *chip, unsigned long adr
 				 * there was an error (so leave the erase
 				 * routine to recover from it) or we trying to
 				 * use the erase-in-progress sector. */
-				map_write(map, cfi->sector_erase_cmd, chip->in_progress_block_addr);
-				chip->state = FL_ERASING;
-				chip->oldstate = FL_READY;
+				put_chip(map, chip, adr);
 				printk(KERN_ERR "MTD %s(): chip not ready after erase suspend\n", __func__);
 				return -EIO;
 			}
@@ -762,7 +761,6 @@ static void put_chip(struct map_info *map, struct flchip *chip, unsigned long ad
 
 	switch(chip->oldstate) {
 	case FL_ERASING:
-		chip->state = chip->oldstate;
 		map_write(map, cfi->sector_erase_cmd, chip->in_progress_block_addr);
 		chip->oldstate = FL_READY;
 		chip->state = FL_ERASING;
diff --git a/drivers/mtd/chips/cfi_cmdset_0020.c b/drivers/mtd/chips/cfi_cmdset_0020.c
index ed56ad3884fb..179814a95f3a 100644
--- a/drivers/mtd/chips/cfi_cmdset_0020.c
+++ b/drivers/mtd/chips/cfi_cmdset_0020.c
@@ -296,6 +296,7 @@ static inline int do_read_onechip(struct map_info *map, struct flchip *chip, lof
 				/* make sure we're in 'read status' mode */
 				map_write(map, CMD(0x70), cmd_addr);
 				chip->state = FL_ERASING;
+				wake_up(&chip->wq);
 				mutex_unlock(&chip->mutex);
 				printk(KERN_ERR "Chip not ready after erase "
 				       "suspended: status = 0x%lx\n", status.x[0]);
diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c
index 97183c8c9e33..b78f23169d4e 100644
--- a/drivers/mtd/devices/block2mtd.c
+++ b/drivers/mtd/devices/block2mtd.c
@@ -294,7 +294,7 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size)
 	dev->mtd.priv = dev;
 	dev->mtd.owner = THIS_MODULE;
 
-	if (add_mtd_device(&dev->mtd)) {
+	if (mtd_device_register(&dev->mtd, NULL, 0)) {
 		/* Device didn't get added, so free the entry */
 		goto devinit_err;
 	}
@@ -465,7 +465,7 @@ static void __devexit block2mtd_exit(void)
 	list_for_each_safe(pos, next, &blkmtd_device_list) {
 		struct block2mtd_dev *dev = list_entry(pos, typeof(*dev), list);
 		block2mtd_sync(&dev->mtd);
-		del_mtd_device(&dev->mtd);
+		mtd_device_unregister(&dev->mtd);
 		INFO("mtd%d: [%s] removed", dev->mtd.index,
 				dev->mtd.name + strlen("block2mtd: "));
 		list_del(&dev->list);
diff --git a/drivers/mtd/devices/doc2000.c b/drivers/mtd/devices/doc2000.c
index 5bf5f460e132..f7fbf6025ef2 100644
--- a/drivers/mtd/devices/doc2000.c
+++ b/drivers/mtd/devices/doc2000.c
@@ -597,7 +597,7 @@ void DoC2k_init(struct mtd_info *mtd)
 		doc2klist = mtd;
 		mtd->size = this->totlen;
 		mtd->erasesize = this->erasesize;
-		add_mtd_device(mtd);
+		mtd_device_register(mtd, NULL, 0);
 		return;
 	}
 }
@@ -1185,7 +1185,7 @@ static void __exit cleanup_doc2000(void)
 		this = mtd->priv;
 		doc2klist = this->nextdoc;
 
-		del_mtd_device(mtd);
+		mtd_device_unregister(mtd);
 
 		iounmap(this->virtadr);
 		kfree(this->chips);
diff --git a/drivers/mtd/devices/doc2001.c b/drivers/mtd/devices/doc2001.c
index 0990f7803628..241192f05bc8 100644
--- a/drivers/mtd/devices/doc2001.c
+++ b/drivers/mtd/devices/doc2001.c
@@ -376,7 +376,7 @@ void DoCMil_init(struct mtd_info *mtd)
 		this->nextdoc = docmillist;
 		docmillist = mtd;
 		mtd->size  = this->totlen;
-		add_mtd_device(mtd);
+		mtd_device_register(mtd, NULL, 0);
 		return;
 	}
 }
@@ -826,7 +826,7 @@ static void __exit cleanup_doc2001(void)
 		this = mtd->priv;
 		docmillist = this->nextdoc;
 
-		del_mtd_device(mtd);
+		mtd_device_unregister(mtd);
 
 		iounmap(this->virtadr);
 		kfree(this->chips);
diff --git a/drivers/mtd/devices/doc2001plus.c b/drivers/mtd/devices/doc2001plus.c
index 8b36fa77a195..09ae0adc3ad0 100644
--- a/drivers/mtd/devices/doc2001plus.c
+++ b/drivers/mtd/devices/doc2001plus.c
@@ -499,7 +499,7 @@ void DoCMilPlus_init(struct mtd_info *mtd)
 		docmilpluslist = mtd;
 		mtd->size  = this->totlen;
 		mtd->erasesize = this->erasesize;
-		add_mtd_device(mtd);
+		mtd_device_register(mtd, NULL, 0);
 		return;
 	}
 }
@@ -1091,7 +1091,7 @@ static void __exit cleanup_doc2001plus(void)
 		this = mtd->priv;
 		docmilpluslist = this->nextdoc;
 
-		del_mtd_device(mtd);
+		mtd_device_unregister(mtd);
 
 		iounmap(this->virtadr);
 		kfree(this->chips);
diff --git a/drivers/mtd/devices/lart.c b/drivers/mtd/devices/lart.c
index 4b829f97d56c..772a0ff89e0f 100644
--- a/drivers/mtd/devices/lart.c
+++ b/drivers/mtd/devices/lart.c
@@ -684,9 +684,10 @@ static int __init lart_flash_init (void)
 #endif
 
 #ifndef HAVE_PARTITIONS
-   result = add_mtd_device (&mtd);
+   result = mtd_device_register(&mtd, NULL, 0);
 #else
-   result = add_mtd_partitions (&mtd,lart_partitions, ARRAY_SIZE(lart_partitions));
+   result = mtd_device_register(&mtd, lart_partitions,
+                                ARRAY_SIZE(lart_partitions));
 #endif
 
    return (result);
@@ -695,9 +696,9 @@ static int __init lart_flash_init (void)
 static void __exit lart_flash_exit (void)
 {
 #ifndef HAVE_PARTITIONS
-   del_mtd_device (&mtd);
+   mtd_device_unregister(&mtd);
 #else
-   del_mtd_partitions (&mtd);
+   mtd_device_unregister(&mtd);
 #endif
 }
 
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index 3fb981d4bb51..35180e475c4c 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -27,6 +27,7 @@
 #include <linux/sched.h>
 #include <linux/mod_devicetable.h>
 
+#include <linux/mtd/cfi.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 
@@ -55,6 +56,9 @@
 #define	OPCODE_EN4B		0xb7	/* Enter 4-byte mode */
 #define	OPCODE_EX4B		0xe9	/* Exit 4-byte mode */
 
+/* Used for Spansion flashes only. */
+#define	OPCODE_BRWR		0x17	/* Bank register write */
+
 /* Status Register bits. */
 #define	SR_WIP			1	/* Write in progress */
 #define	SR_WEL			2	/* Write enable latch */
@@ -76,6 +80,8 @@
 #define FAST_READ_DUMMY_BYTE 0
 #endif
 
+#define JEDEC_MFR(_jedec_id)	((_jedec_id) >> 16)
+
 /****************************************************************************/
 
 struct m25p {
@@ -158,11 +164,18 @@ static inline int write_disable(struct m25p *flash)
 /*
  * Enable/disable 4-byte addressing mode.
  */
-static inline int set_4byte(struct m25p *flash, int enable)
+static inline int set_4byte(struct m25p *flash, u32 jedec_id, int enable)
 {
-	u8	code = enable ? OPCODE_EN4B : OPCODE_EX4B;
-
-	return spi_write_then_read(flash->spi, &code, 1, NULL, 0);
+	switch (JEDEC_MFR(jedec_id)) {
+	case CFI_MFR_MACRONIX:
+		flash->command[0] = enable ? OPCODE_EN4B : OPCODE_EX4B;
+		return spi_write(flash->spi, flash->command, 1);
+	default:
+		/* Spansion style */
+		flash->command[0] = OPCODE_BRWR;
+		flash->command[1] = enable << 7;
+		return spi_write(flash->spi, flash->command, 2);
+	}
 }
 
 /*
@@ -668,6 +681,7 @@ static const struct spi_device_id m25p_ids[] = {
 	/* Macronix */
 	{ "mx25l4005a",  INFO(0xc22013, 0, 64 * 1024,   8, SECT_4K) },
 	{ "mx25l8005",   INFO(0xc22014, 0, 64 * 1024,  16, 0) },
+	{ "mx25l1606e",  INFO(0xc22015, 0, 64 * 1024,  32, SECT_4K) },
 	{ "mx25l3205d",  INFO(0xc22016, 0, 64 * 1024,  64, 0) },
 	{ "mx25l6405d",  INFO(0xc22017, 0, 64 * 1024, 128, 0) },
 	{ "mx25l12805d", INFO(0xc22018, 0, 64 * 1024, 256, 0) },
@@ -684,6 +698,10 @@ static const struct spi_device_id m25p_ids[] = {
 	{ "s25sl032a",  INFO(0x010215,      0,  64 * 1024,  64, 0) },
 	{ "s25sl032p",  INFO(0x010215, 0x4d00,  64 * 1024,  64, SECT_4K) },
 	{ "s25sl064a",  INFO(0x010216,      0,  64 * 1024, 128, 0) },
+	{ "s25fl256s0", INFO(0x010219, 0x4d00, 256 * 1024, 128, 0) },
+	{ "s25fl256s1", INFO(0x010219, 0x4d01,  64 * 1024, 512, 0) },
+	{ "s25fl512s",  INFO(0x010220, 0x4d00, 256 * 1024, 256, 0) },
+	{ "s70fl01gs",  INFO(0x010221, 0x4d00, 256 * 1024, 256, 0) },
 	{ "s25sl12800", INFO(0x012018, 0x0300, 256 * 1024,  64, 0) },
 	{ "s25sl12801", INFO(0x012018, 0x0301,  64 * 1024, 256, 0) },
 	{ "s25fl129p0", INFO(0x012018, 0x4d00, 256 * 1024,  64, 0) },
@@ -729,7 +747,10 @@ static const struct spi_device_id m25p_ids[] = {
 	{ "m25pe80", INFO(0x208014,  0, 64 * 1024, 16,       0) },
 	{ "m25pe16", INFO(0x208015,  0, 64 * 1024, 32, SECT_4K) },
 
-	{ "m25px64", INFO(0x207117,  0, 64 * 1024, 128, 0) },
+	{ "m25px32",    INFO(0x207116,  0, 64 * 1024, 64, SECT_4K) },
+	{ "m25px32-s0", INFO(0x207316,  0, 64 * 1024, 64, SECT_4K) },
+	{ "m25px32-s1", INFO(0x206316,  0, 64 * 1024, 64, SECT_4K) },
+	{ "m25px64",    INFO(0x207117,  0, 64 * 1024, 128, 0) },
 
 	/* Winbond -- w25x "blocks" are 64K, "sectors" are 4KiB */
 	{ "w25x10", INFO(0xef3011, 0, 64 * 1024,  2,  SECT_4K) },
@@ -804,6 +825,8 @@ static int __devinit m25p_probe(struct spi_device *spi)
 	struct m25p			*flash;
 	struct flash_info		*info;
 	unsigned			i;
+	struct mtd_partition		*parts = NULL;
+	int				nr_parts = 0;
 
 	/* Platform data helps sort out which chip type we have, as
 	 * well as how this board partitions it.  If we don't have
@@ -868,9 +891,9 @@ static int __devinit m25p_probe(struct spi_device *spi)
 	 * up with the software protection bits set
 	 */
 
-	if (info->jedec_id >> 16 == 0x1f ||
-	    info->jedec_id >> 16 == 0x89 ||
-	    info->jedec_id >> 16 == 0xbf) {
+	if (JEDEC_MFR(info->jedec_id) == CFI_MFR_ATMEL ||
+	    JEDEC_MFR(info->jedec_id) == CFI_MFR_INTEL ||
+	    JEDEC_MFR(info->jedec_id) == CFI_MFR_SST) {
 		write_enable(flash);
 		write_sr(flash, 0);
 	}
@@ -888,7 +911,7 @@ static int __devinit m25p_probe(struct spi_device *spi)
 	flash->mtd.read = m25p80_read;
 
 	/* sst flash chips use AAI word program */
-	if (info->jedec_id >> 16 == 0xbf)
+	if (JEDEC_MFR(info->jedec_id) == CFI_MFR_SST)
 		flash->mtd.write = sst_write;
 	else
 		flash->mtd.write = m25p80_write;
@@ -914,7 +937,7 @@ static int __devinit m25p_probe(struct spi_device *spi)
 		/* enable 4-byte addressing if the device exceeds 16MiB */
 		if (flash->mtd.size > 0x1000000) {
 			flash->addr_width = 4;
-			set_4byte(flash, 1);
+			set_4byte(flash, info->jedec_id, 1);
 		} else
 			flash->addr_width = 3;
 	}
@@ -945,48 +968,41 @@ static int __devinit m25p_probe(struct spi_device *spi)
 	/* partitions should match sector boundaries; and it may be good to
 	 * use readonly partitions for writeprotected sectors (BP2..BP0).
 	 */
-	if (mtd_has_partitions()) {
-		struct mtd_partition	*parts = NULL;
-		int			nr_parts = 0;
-
-		if (mtd_has_cmdlinepart()) {
-			static const char *part_probes[]
-					= { "cmdlinepart", NULL, };
+	if (mtd_has_cmdlinepart()) {
+		static const char *part_probes[]
+			= { "cmdlinepart", NULL, };
 
-			nr_parts = parse_mtd_partitions(&flash->mtd,
-					part_probes, &parts, 0);
-		}
+		nr_parts = parse_mtd_partitions(&flash->mtd,
+						part_probes, &parts, 0);
+	}
 
-		if (nr_parts <= 0 && data && data->parts) {
-			parts = data->parts;
-			nr_parts = data->nr_parts;
-		}
+	if (nr_parts <= 0 && data && data->parts) {
+		parts = data->parts;
+		nr_parts = data->nr_parts;
+	}
 
 #ifdef CONFIG_MTD_OF_PARTS
-		if (nr_parts <= 0 && spi->dev.of_node) {
-			nr_parts = of_mtd_parse_partitions(&spi->dev,
-					spi->dev.of_node, &parts);
-		}
+	if (nr_parts <= 0 && spi->dev.of_node) {
+		nr_parts = of_mtd_parse_partitions(&spi->dev,
+						   spi->dev.of_node, &parts);
+	}
 #endif
 
-		if (nr_parts > 0) {
-			for (i = 0; i < nr_parts; i++) {
-				DEBUG(MTD_DEBUG_LEVEL2, "partitions[%d] = "
-					"{.name = %s, .offset = 0x%llx, "
-						".size = 0x%llx (%lldKiB) }\n",
-					i, parts[i].name,
-					(long long)parts[i].offset,
-					(long long)parts[i].size,
-					(long long)(parts[i].size >> 10));
-			}
-			flash->partitioned = 1;
-			return add_mtd_partitions(&flash->mtd, parts, nr_parts);
+	if (nr_parts > 0) {
+		for (i = 0; i < nr_parts; i++) {
+			DEBUG(MTD_DEBUG_LEVEL2, "partitions[%d] = "
+			      "{.name = %s, .offset = 0x%llx, "
+			      ".size = 0x%llx (%lldKiB) }\n",
+			      i, parts[i].name,
+			      (long long)parts[i].offset,
+			      (long long)parts[i].size,
+			      (long long)(parts[i].size >> 10));
 		}
-	} else if (data && data->nr_parts)
-		dev_warn(&spi->dev, "ignoring %d default partitions on %s\n",
-				data->nr_parts, data->name);
+		flash->partitioned = 1;
+	}
 
-	return add_mtd_device(&flash->mtd) == 1 ? -ENODEV : 0;
+	return mtd_device_register(&flash->mtd, parts, nr_parts) == 1 ?
+		-ENODEV : 0;
 }
 
 
@@ -996,10 +1012,7 @@ static int __devexit m25p_remove(struct spi_device *spi)
 	int		status;
 
 	/* Clean up MTD stuff. */
-	if (mtd_has_partitions() && flash->partitioned)
-		status = del_mtd_partitions(&flash->mtd);
-	else
-		status = del_mtd_device(&flash->mtd);
+	status = mtd_device_unregister(&flash->mtd);
 	if (status == 0) {
 		kfree(flash->command);
 		kfree(flash);
diff --git a/drivers/mtd/devices/ms02-nv.c b/drivers/mtd/devices/ms02-nv.c
index 6a9a24a80a6d..8423fb6d4f26 100644
--- a/drivers/mtd/devices/ms02-nv.c
+++ b/drivers/mtd/devices/ms02-nv.c
@@ -220,7 +220,7 @@ static int __init ms02nv_init_one(ulong addr)
 	mtd->writesize = 1;
 
 	ret = -EIO;
-	if (add_mtd_device(mtd)) {
+	if (mtd_device_register(mtd, NULL, 0)) {
 		printk(KERN_ERR
 			"ms02-nv: Unable to register MTD device, aborting!\n");
 		goto err_out_csr_res;
@@ -262,7 +262,7 @@ static void __exit ms02nv_remove_one(void)
 
 	root_ms02nv_mtd = mp->next;
 
-	del_mtd_device(mtd);
+	mtd_device_unregister(mtd);
 
 	release_resource(mp->resource.csr);
 	kfree(mp->resource.csr);
diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c
index c5015cc721d5..13749d458a31 100644
--- a/drivers/mtd/devices/mtd_dataflash.c
+++ b/drivers/mtd/devices/mtd_dataflash.c
@@ -637,6 +637,8 @@ add_dataflash_otp(struct spi_device *spi, char *name,
 	struct flash_platform_data	*pdata = spi->dev.platform_data;
 	char				*otp_tag = "";
 	int				err = 0;
+	struct mtd_partition		*parts;
+	int				nr_parts = 0;
 
 	priv = kzalloc(sizeof *priv, GFP_KERNEL);
 	if (!priv)
@@ -675,33 +677,25 @@ add_dataflash_otp(struct spi_device *spi, char *name,
 			pagesize, otp_tag);
 	dev_set_drvdata(&spi->dev, priv);
 
-	if (mtd_has_partitions()) {
-		struct mtd_partition	*parts;
-		int			nr_parts = 0;
+	if (mtd_has_cmdlinepart()) {
+		static const char *part_probes[] = { "cmdlinepart", NULL, };
 
-		if (mtd_has_cmdlinepart()) {
-			static const char *part_probes[]
-					= { "cmdlinepart", NULL, };
-
-			nr_parts = parse_mtd_partitions(device,
-					part_probes, &parts, 0);
-		}
+		nr_parts = parse_mtd_partitions(device, part_probes, &parts,
+						0);
+	}
 
-		if (nr_parts <= 0 && pdata && pdata->parts) {
-			parts = pdata->parts;
-			nr_parts = pdata->nr_parts;
-		}
+	if (nr_parts <= 0 && pdata && pdata->parts) {
+		parts = pdata->parts;
+		nr_parts = pdata->nr_parts;
+	}
 
-		if (nr_parts > 0) {
-			priv->partitioned = 1;
-			err = add_mtd_partitions(device, parts, nr_parts);
-			goto out;
-		}
-	} else if (pdata && pdata->nr_parts)
-		dev_warn(&spi->dev, "ignoring %d default partitions on %s\n",
-				pdata->nr_parts, device->name);
+	if (nr_parts > 0) {
+		priv->partitioned = 1;
+		err = mtd_device_register(device, parts, nr_parts);
+		goto out;
+	}
 
-	if (add_mtd_device(device) == 1)
+	if (mtd_device_register(device, NULL, 0) == 1)
 		err = -ENODEV;
 
 out:
@@ -939,10 +933,7 @@ static int __devexit dataflash_remove(struct spi_device *spi)
 
 	DEBUG(MTD_DEBUG_LEVEL1, "%s: remove\n", dev_name(&spi->dev));
 
-	if (mtd_has_partitions() && flash->partitioned)
-		status = del_mtd_partitions(&flash->mtd);
-	else
-		status = del_mtd_device(&flash->mtd);
+	status = mtd_device_unregister(&flash->mtd);
 	if (status == 0) {
 		dev_set_drvdata(&spi->dev, NULL);
 		kfree(flash);
diff --git a/drivers/mtd/devices/mtdram.c b/drivers/mtd/devices/mtdram.c
index 1483e18971ce..2562689ba6b4 100644
--- a/drivers/mtd/devices/mtdram.c
+++ b/drivers/mtd/devices/mtdram.c
@@ -104,7 +104,7 @@ static int ram_write(struct mtd_info *mtd, loff_t to, size_t len,
 static void __exit cleanup_mtdram(void)
 {
 	if (mtd_info) {
-		del_mtd_device(mtd_info);
+		mtd_device_unregister(mtd_info);
 		vfree(mtd_info->priv);
 		kfree(mtd_info);
 	}
@@ -133,9 +133,8 @@ int mtdram_init_device(struct mtd_info *mtd, void *mapped_address,
 	mtd->read = ram_read;
 	mtd->write = ram_write;
 
-	if (add_mtd_device(mtd)) {
+	if (mtd_device_register(mtd, NULL, 0))
 		return -EIO;
-	}
 
 	return 0;
 }
diff --git a/drivers/mtd/devices/phram.c b/drivers/mtd/devices/phram.c
index 8d28fa02a5a2..23423bd00b06 100644
--- a/drivers/mtd/devices/phram.c
+++ b/drivers/mtd/devices/phram.c
@@ -115,7 +115,7 @@ static void unregister_devices(void)
 	struct phram_mtd_list *this, *safe;
 
 	list_for_each_entry_safe(this, safe, &phram_list, list) {
-		del_mtd_device(&this->mtd);
+		mtd_device_unregister(&this->mtd);
 		iounmap(this->mtd.priv);
 		kfree(this->mtd.name);
 		kfree(this);
@@ -153,7 +153,7 @@ static int register_device(char *name, unsigned long start, unsigned long len)
 	new->mtd.writesize = 1;
 
 	ret = -EAGAIN;
-	if (add_mtd_device(&new->mtd)) {
+	if (mtd_device_register(&new->mtd, NULL, 0)) {
 		pr_err("Failed to register new device\n");
 		goto out2;
 	}
diff --git a/drivers/mtd/devices/pmc551.c b/drivers/mtd/devices/pmc551.c
index 41b8cdcc64cb..ecff765579dd 100644
--- a/drivers/mtd/devices/pmc551.c
+++ b/drivers/mtd/devices/pmc551.c
@@ -798,7 +798,7 @@ static int __init init_pmc551(void)
 		mtd->writesize = 1;
 		mtd->owner = THIS_MODULE;
 
-		if (add_mtd_device(mtd)) {
+		if (mtd_device_register(mtd, NULL, 0)) {
 			printk(KERN_NOTICE "pmc551: Failed to register new device\n");
 			pci_iounmap(PCI_Device, priv->start);
 			kfree(mtd->priv);
@@ -806,7 +806,7 @@ static int __init init_pmc551(void)
 			break;
 		}
 
-		/* Keep a reference as the add_mtd_device worked */
+		/* Keep a reference as the mtd_device_register worked */
 		pci_dev_get(PCI_Device);
 
 		printk(KERN_NOTICE "Registered pmc551 memory device.\n");
@@ -856,7 +856,7 @@ static void __exit cleanup_pmc551(void)
 		pci_dev_put(priv->dev);
 
 		kfree(mtd->priv);
-		del_mtd_device(mtd);
+		mtd_device_unregister(mtd);
 		kfree(mtd);
 		found++;
 	}
diff --git a/drivers/mtd/devices/slram.c b/drivers/mtd/devices/slram.c
index 592016a0668f..e585263161b9 100644
--- a/drivers/mtd/devices/slram.c
+++ b/drivers/mtd/devices/slram.c
@@ -210,7 +210,7 @@ static int register_device(char *name, unsigned long start, unsigned long length
 	(*curmtd)->mtdinfo->erasesize = SLRAM_BLK_SZ;
 	(*curmtd)->mtdinfo->writesize = 1;
 
-	if (add_mtd_device((*curmtd)->mtdinfo))	{
+	if (mtd_device_register((*curmtd)->mtdinfo, NULL, 0))	{
 		E("slram: Failed to register new device\n");
 		iounmap(((slram_priv_t *)(*curmtd)->mtdinfo->priv)->start);
 		kfree((*curmtd)->mtdinfo->priv);
@@ -231,7 +231,7 @@ static void unregister_devices(void)
 
 	while (slram_mtdlist) {
 		nextitem = slram_mtdlist->next;
-		del_mtd_device(slram_mtdlist->mtdinfo);
+		mtd_device_unregister(slram_mtdlist->mtdinfo);
 		iounmap(((slram_priv_t *)slram_mtdlist->mtdinfo->priv)->start);
 		kfree(slram_mtdlist->mtdinfo->priv);
 		kfree(slram_mtdlist->mtdinfo);
diff --git a/drivers/mtd/devices/sst25l.c b/drivers/mtd/devices/sst25l.c
index c163e619abc9..1e2c430aaad2 100644
--- a/drivers/mtd/devices/sst25l.c
+++ b/drivers/mtd/devices/sst25l.c
@@ -66,7 +66,7 @@ struct flash_info {
 
 #define to_sst25l_flash(x) container_of(x, struct sst25l_flash, mtd)
 
-static struct flash_info __initdata sst25l_flash_info[] = {
+static struct flash_info __devinitdata sst25l_flash_info[] = {
 	{"sst25lf020a", 0xbf43, 256, 1024, 4096},
 	{"sst25lf040a",	0xbf44,	256, 2048, 4096},
 };
@@ -381,6 +381,8 @@ static int __devinit sst25l_probe(struct spi_device *spi)
 	struct sst25l_flash *flash;
 	struct flash_platform_data *data;
 	int ret, i;
+	struct mtd_partition *parts = NULL;
+	int nr_parts = 0;
 
 	flash_info = sst25l_match_device(spi);
 	if (!flash_info)
@@ -420,46 +422,37 @@ static int __devinit sst25l_probe(struct spi_device *spi)
 	      flash->mtd.erasesize, flash->mtd.erasesize / 1024,
 	      flash->mtd.numeraseregions);
 
-	if (mtd_has_partitions()) {
-		struct mtd_partition *parts = NULL;
-		int nr_parts = 0;
 
-		if (mtd_has_cmdlinepart()) {
-			static const char *part_probes[] =
-				{"cmdlinepart", NULL};
+	if (mtd_has_cmdlinepart()) {
+		static const char *part_probes[] = {"cmdlinepart", NULL};
 
-			nr_parts = parse_mtd_partitions(&flash->mtd,
-							part_probes,
-							&parts, 0);
-		}
+		nr_parts = parse_mtd_partitions(&flash->mtd,
+						part_probes,
+						&parts, 0);
+	}
 
-		if (nr_parts <= 0 && data && data->parts) {
-			parts = data->parts;
-			nr_parts = data->nr_parts;
-		}
+	if (nr_parts <= 0 && data && data->parts) {
+		parts = data->parts;
+		nr_parts = data->nr_parts;
+	}
 
-		if (nr_parts > 0) {
-			for (i = 0; i < nr_parts; i++) {
-				DEBUG(MTD_DEBUG_LEVEL2, "partitions[%d] = "
-				      "{.name = %s, .offset = 0x%llx, "
-				      ".size = 0x%llx (%lldKiB) }\n",
-				      i, parts[i].name,
-				      (long long)parts[i].offset,
-				      (long long)parts[i].size,
-				      (long long)(parts[i].size >> 10));
-			}
-
-			flash->partitioned = 1;
-			return add_mtd_partitions(&flash->mtd,
-						  parts, nr_parts);
+	if (nr_parts > 0) {
+		for (i = 0; i < nr_parts; i++) {
+			DEBUG(MTD_DEBUG_LEVEL2, "partitions[%d] = "
+			      "{.name = %s, .offset = 0x%llx, "
+			      ".size = 0x%llx (%lldKiB) }\n",
+			      i, parts[i].name,
+			      (long long)parts[i].offset,
+			      (long long)parts[i].size,
+			      (long long)(parts[i].size >> 10));
 		}
 
-	} else if (data && data->nr_parts) {
-		dev_warn(&spi->dev, "ignoring %d default partitions on %s\n",
-			 data->nr_parts, data->name);
+		flash->partitioned = 1;
+		return mtd_device_register(&flash->mtd, parts,
+					   nr_parts);
 	}
 
-	ret = add_mtd_device(&flash->mtd);
+	ret = mtd_device_register(&flash->mtd, NULL, 0);
 	if (ret == 1) {
 		kfree(flash);
 		dev_set_drvdata(&spi->dev, NULL);
@@ -469,15 +462,12 @@ static int __devinit sst25l_probe(struct spi_device *spi)
 	return 0;
 }
 
-static int __exit sst25l_remove(struct spi_device *spi)
+static int __devexit sst25l_remove(struct spi_device *spi)
 {
 	struct sst25l_flash *flash = dev_get_drvdata(&spi->dev);
 	int ret;
 
-	if (mtd_has_partitions() && flash->partitioned)
-		ret = del_mtd_partitions(&flash->mtd);
-	else
-		ret = del_mtd_device(&flash->mtd);
+	ret = mtd_device_unregister(&flash->mtd);
 	if (ret == 0)
 		kfree(flash);
 	return ret;
@@ -490,7 +480,7 @@ static struct spi_driver sst25l_driver = {
 		.owner	= THIS_MODULE,
 	},
 	.probe		= sst25l_probe,
-	.remove		= __exit_p(sst25l_remove),
+	.remove		= __devexit_p(sst25l_remove),
 };
 
 static int __init sst25l_init(void)
diff --git a/drivers/mtd/lpddr/lpddr_cmds.c b/drivers/mtd/lpddr/lpddr_cmds.c
index 12679925b420..65655dd59e1f 100644
--- a/drivers/mtd/lpddr/lpddr_cmds.c
+++ b/drivers/mtd/lpddr/lpddr_cmds.c
@@ -313,12 +313,7 @@ static int chip_ready(struct map_info *map, struct flchip *chip, int mode)
 		if (ret) {
 			/* Oops. something got wrong. */
 			/* Resume and pretend we weren't here.  */
-			map_write(map, CMD(LPDDR_RESUME),
-				map->pfow_base + PFOW_COMMAND_CODE);
-			map_write(map, CMD(LPDDR_START_EXECUTION),
-				map->pfow_base + PFOW_COMMAND_EXECUTE);
-			chip->state = FL_ERASING;
-			chip->oldstate = FL_READY;
+			put_chip(map, chip);
 			printk(KERN_ERR "%s: suspend operation failed."
 					"State may be wrong \n", map->name);
 			return -EIO;
@@ -383,7 +378,6 @@ static void put_chip(struct map_info *map, struct flchip *chip)
 
 	switch (chip->oldstate) {
 	case FL_ERASING:
-		chip->state = chip->oldstate;
 		map_write(map, CMD(LPDDR_RESUME),
 				map->pfow_base + PFOW_COMMAND_CODE);
 		map_write(map, CMD(LPDDR_START_EXECUTION),
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index 5069111c81cc..c0c328c5b133 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -82,7 +82,6 @@ config MTD_PHYSMAP_OF
 config MTD_PMC_MSP_EVM
 	tristate "CFI Flash device mapped on PMC-Sierra MSP"
 	depends on PMC_MSP && MTD_CFI
-	select MTD_PARTITIONS
 	help
 	  This provides a 'mapping' driver which supports the way
 	  in which user-programmable flash chips are connected on the
@@ -122,7 +121,7 @@ config MTD_SC520CDP
 
 config MTD_NETSC520
 	tristate "CFI Flash device mapped on AMD NetSc520"
-	depends on X86 && MTD_CFI && MTD_PARTITIONS
+	depends on X86 && MTD_CFI
 	help
 	  This enables access routines for the flash chips on the AMD NetSc520
 	  demonstration board. If you have one of these boards and would like
@@ -131,7 +130,6 @@ config MTD_NETSC520
 config MTD_TS5500
 	tristate "JEDEC Flash device mapped on Technologic Systems TS-5500"
 	depends on X86
-	select MTD_PARTITIONS
 	select MTD_JEDECPROBE
 	select MTD_CFI_AMDSTD
 	help
@@ -149,7 +147,7 @@ config MTD_TS5500
 
 config MTD_SBC_GXX
 	tristate "CFI Flash device mapped on Arcom SBC-GXx boards"
-	depends on X86 && MTD_CFI_INTELEXT && MTD_PARTITIONS && MTD_COMPLEX_MAPPINGS
+	depends on X86 && MTD_CFI_INTELEXT && MTD_COMPLEX_MAPPINGS
 	help
 	  This provides a driver for the on-board flash of Arcom Control
 	  Systems' SBC-GXn family of boards, formerly known as SBC-MediaGX.
@@ -161,7 +159,6 @@ config MTD_SBC_GXX
 config MTD_PXA2XX
 	tristate "CFI Flash device mapped on Intel XScale PXA2xx based boards"
 	depends on (PXA25x || PXA27x) && MTD_CFI_INTELEXT
-	select MTD_PARTITIONS
 	help
 	  This provides a driver for the NOR flash attached to a PXA2xx chip.
 
@@ -185,7 +182,7 @@ config MTD_VMAX
 
 config MTD_SCx200_DOCFLASH
 	tristate "Flash device mapped with DOCCS on NatSemi SCx200"
-	depends on SCx200 && MTD_CFI && MTD_PARTITIONS
+	depends on SCx200 && MTD_CFI
 	help
 	  Enable support for a flash chip mapped using the DOCCS signal on a
 	  National Semiconductor SCx200 processor.
@@ -247,7 +244,7 @@ config MTD_TSUNAMI
 
 config MTD_NETtel
 	tristate "CFI flash device on SnapGear/SecureEdge"
-	depends on X86 && MTD_PARTITIONS && MTD_JEDECPROBE
+	depends on X86 && MTD_JEDECPROBE
 	help
 	  Support for flash chips on NETtel/SecureEdge/SnapGear boards.
 
@@ -269,7 +266,7 @@ config MTD_LANTIQ
 
 config MTD_DILNETPC
 	tristate "CFI Flash device mapped on DIL/Net PC"
-	depends on X86 && MTD_PARTITIONS && MTD_CFI_INTELEXT && BROKEN
+	depends on X86 && MTD_CFI_INTELEXT && BROKEN
 	help
 	  MTD map driver for SSV DIL/Net PC Boards "DNP" and "ADNP".
 	  For details, see <http://www.ssv-embedded.de/ssv/pc104/p169.htm>
@@ -355,7 +352,7 @@ config MTD_CDB89712
 
 config MTD_SA1100
 	tristate "CFI Flash device mapped on StrongARM SA11x0"
-	depends on MTD_CFI && ARCH_SA1100 && MTD_PARTITIONS
+	depends on MTD_CFI && ARCH_SA1100
 	help
 	  This enables access to the flash chips on most platforms based on
 	  the SA1100 and SA1110, including the Assabet and the Compaq iPAQ.
@@ -389,7 +386,7 @@ config MTD_IXP2000
 
 config MTD_FORTUNET
 	tristate "CFI Flash device mapped on the FortuNet board"
-	depends on MTD_CFI && MTD_PARTITIONS && SA1100_FORTUNET
+	depends on MTD_CFI && SA1100_FORTUNET
 	help
 	  This enables access to the Flash on the FortuNet board.  If you
 	  have such a board, say 'Y'.
@@ -461,7 +458,6 @@ config MTD_PCMCIA_ANONYMOUS
 config MTD_BFIN_ASYNC
 	tristate "Blackfin BF533-STAMP Flash Chip Support"
 	depends on BFIN533_STAMP && MTD_CFI && MTD_COMPLEX_MAPPINGS
-	select MTD_PARTITIONS
 	default y
 	help
 	  Map driver which allows for simultaneous utilization of
@@ -473,7 +469,6 @@ config MTD_GPIO_ADDR
 	tristate "GPIO-assisted Flash Chip Support"
 	depends on GENERIC_GPIO || GPIOLIB
 	depends on MTD_COMPLEX_MAPPINGS
-	select MTD_PARTITIONS
 	help
 	  Map driver which allows flashes to be partially physically addressed
 	  and assisted by GPIOs.
@@ -482,14 +477,13 @@ config MTD_GPIO_ADDR
 
 config MTD_UCLINUX
 	bool "Generic uClinux RAM/ROM filesystem support"
-	depends on MTD_PARTITIONS && MTD_RAM=y && !MMU
+	depends on MTD_RAM=y && !MMU
 	help
 	  Map driver to support image based filesystems for uClinux.
 
 config MTD_WRSBC8260
 	tristate "Map driver for WindRiver PowerQUICC II MPC82xx board"
 	depends on (SBC82xx || SBC8560)
-	select MTD_PARTITIONS
 	select MTD_MAP_BANK_WIDTH_4
 	select MTD_MAP_BANK_WIDTH_1
 	select MTD_CFI_I1
@@ -502,7 +496,6 @@ config MTD_WRSBC8260
 config MTD_DMV182
         tristate "Map driver for Dy-4 SVME/DMV-182 board."
         depends on DMV182
-        select MTD_PARTITIONS
 	select MTD_MAP_BANK_WIDTH_32
 	select MTD_CFI_I8
 	select MTD_CFI_AMDSTD
diff --git a/drivers/mtd/maps/amd76xrom.c b/drivers/mtd/maps/amd76xrom.c
index 92de7e3a49a5..e2875d6fe129 100644
--- a/drivers/mtd/maps/amd76xrom.c
+++ b/drivers/mtd/maps/amd76xrom.c
@@ -82,7 +82,7 @@ static void amd76xrom_cleanup(struct amd76xrom_window *window)
 		if (map->rsrc.parent) {
 			release_resource(&map->rsrc);
 		}
-		del_mtd_device(map->mtd);
+		mtd_device_unregister(map->mtd);
 		map_destroy(map->mtd);
 		list_del(&map->list);
 		kfree(map);
@@ -262,7 +262,7 @@ static int __devinit amd76xrom_init_one (struct pci_dev *pdev,
 
 		/* Now that the mtd devices is complete claim and export it */
 		map->mtd->owner = THIS_MODULE;
-		if (add_mtd_device(map->mtd)) {
+		if (mtd_device_register(map->mtd, NULL, 0)) {
 			map_destroy(map->mtd);
 			map->mtd = NULL;
 			goto out;
diff --git a/drivers/mtd/maps/autcpu12-nvram.c b/drivers/mtd/maps/autcpu12-nvram.c
index 53664188fc47..e5bfd0e093bb 100644
--- a/drivers/mtd/maps/autcpu12-nvram.c
+++ b/drivers/mtd/maps/autcpu12-nvram.c
@@ -88,7 +88,7 @@ map:
 	sram_mtd->owner = THIS_MODULE;
 	sram_mtd->erasesize = 16;
 
-	if (add_mtd_device(sram_mtd)) {
+	if (mtd_device_register(sram_mtd, NULL, 0)) {
 		printk("NV-RAM device addition failed\n");
 		err = -ENOMEM;
 		goto out_probe;
@@ -111,7 +111,7 @@ out:
 static void __exit cleanup_autcpu12_maps(void)
 {
 	if (sram_mtd) {
-		del_mtd_device(sram_mtd);
+		mtd_device_unregister(sram_mtd);
 		map_destroy(sram_mtd);
 		iounmap((void *)autcpu12_sram_map.virt);
 	}
diff --git a/drivers/mtd/maps/bcm963xx-flash.c b/drivers/mtd/maps/bcm963xx-flash.c
index 1f3049590d9e..608967fe74c6 100644
--- a/drivers/mtd/maps/bcm963xx-flash.c
+++ b/drivers/mtd/maps/bcm963xx-flash.c
@@ -224,8 +224,8 @@ probe_ok:
 		goto err_probe;
 	}
 
-	return add_mtd_partitions(bcm963xx_mtd_info, parsed_parts,
-						parsed_nr_parts);
+	return mtd_device_register(bcm963xx_mtd_info, parsed_parts,
+				   parsed_nr_parts);
 
 err_probe:
 	iounmap(bcm963xx_map.virt);
@@ -235,7 +235,7 @@ err_probe:
 static int bcm963xx_remove(struct platform_device *pdev)
 {
 	if (bcm963xx_mtd_info) {
-		del_mtd_partitions(bcm963xx_mtd_info);
+		mtd_device_unregister(bcm963xx_mtd_info);
 		map_destroy(bcm963xx_mtd_info);
 	}
 
diff --git a/drivers/mtd/maps/bfin-async-flash.c b/drivers/mtd/maps/bfin-async-flash.c
index 85dd18193cf2..d4297a97e100 100644
--- a/drivers/mtd/maps/bfin-async-flash.c
+++ b/drivers/mtd/maps/bfin-async-flash.c
@@ -41,9 +41,7 @@ struct async_state {
 	uint32_t flash_ambctl0, flash_ambctl1;
 	uint32_t save_ambctl0, save_ambctl1;
 	unsigned long irq_flags;
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *parts;
-#endif
 };
 
 static void switch_to_flash(struct async_state *state)
@@ -124,9 +122,7 @@ static void bfin_flash_copy_to(struct map_info *map, unsigned long to, const voi
 	switch_back(state);
 }
 
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *part_probe_types[] = { "cmdlinepart", "RedBoot", NULL };
-#endif
 
 static int __devinit bfin_flash_probe(struct platform_device *pdev)
 {
@@ -169,22 +165,17 @@ static int __devinit bfin_flash_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-#ifdef CONFIG_MTD_PARTITIONS
 	ret = parse_mtd_partitions(state->mtd, part_probe_types, &pdata->parts, 0);
 	if (ret > 0) {
 		pr_devinit(KERN_NOTICE DRIVER_NAME ": Using commandline partition definition\n");
-		add_mtd_partitions(state->mtd, pdata->parts, ret);
+		mtd_device_register(state->mtd, pdata->parts, ret);
 		state->parts = pdata->parts;
-
 	} else if (pdata->nr_parts) {
 		pr_devinit(KERN_NOTICE DRIVER_NAME ": Using board partition definition\n");
-		add_mtd_partitions(state->mtd, pdata->parts, pdata->nr_parts);
-
-	} else
-#endif
-	{
+		mtd_device_register(state->mtd, pdata->parts, pdata->nr_parts);
+	} else {
 		pr_devinit(KERN_NOTICE DRIVER_NAME ": no partition info available, registering whole flash at once\n");
-		add_mtd_device(state->mtd);
+		mtd_device_register(state->mtd, NULL, 0);
 	}
 
 	platform_set_drvdata(pdev, state);
@@ -196,10 +187,8 @@ static int __devexit bfin_flash_remove(struct platform_device *pdev)
 {
 	struct async_state *state = platform_get_drvdata(pdev);
 	gpio_free(state->enet_flash_pin);
-#ifdef CONFIG_MTD_PARTITIONS
-	del_mtd_partitions(state->mtd);
+	mtd_device_unregister(state->mtd);
 	kfree(state->parts);
-#endif
 	map_destroy(state->mtd);
 	kfree(state);
 	return 0;
diff --git a/drivers/mtd/maps/cdb89712.c b/drivers/mtd/maps/cdb89712.c
index 8d92d8db9a98..c29cbf87ea0c 100644
--- a/drivers/mtd/maps/cdb89712.c
+++ b/drivers/mtd/maps/cdb89712.c
@@ -75,7 +75,7 @@ static int __init init_cdb89712_flash (void)
 
 	flash_mtd->owner = THIS_MODULE;
 
-	if (add_mtd_device(flash_mtd)) {
+	if (mtd_device_register(flash_mtd, NULL, 0)) {
 		printk("FLASH device addition failed\n");
 		err = -ENOMEM;
 		goto out_probe;
@@ -141,7 +141,7 @@ static int __init init_cdb89712_sram (void)
 	sram_mtd->owner = THIS_MODULE;
 	sram_mtd->erasesize = 16;
 
-	if (add_mtd_device(sram_mtd)) {
+	if (mtd_device_register(sram_mtd, NULL, 0)) {
 		printk("SRAM device addition failed\n");
 		err = -ENOMEM;
 		goto out_probe;
@@ -209,7 +209,7 @@ static int __init init_cdb89712_bootrom (void)
 	bootrom_mtd->owner = THIS_MODULE;
 	bootrom_mtd->erasesize = 0x10000;
 
-	if (add_mtd_device(bootrom_mtd)) {
+	if (mtd_device_register(bootrom_mtd, NULL, 0)) {
 		printk("BootROM device addition failed\n");
 		err = -ENOMEM;
 		goto out_probe;
@@ -249,21 +249,21 @@ static int __init init_cdb89712_maps(void)
 static void __exit cleanup_cdb89712_maps(void)
 {
 	if (sram_mtd) {
-		del_mtd_device(sram_mtd);
+		mtd_device_unregister(sram_mtd);
 		map_destroy(sram_mtd);
 		iounmap((void *)cdb89712_sram_map.virt);
 		release_resource (&cdb89712_sram_resource);
 	}
 
 	if (flash_mtd) {
-		del_mtd_device(flash_mtd);
+		mtd_device_unregister(flash_mtd);
 		map_destroy(flash_mtd);
 		iounmap((void *)cdb89712_flash_map.virt);
 		release_resource (&cdb89712_flash_resource);
 	}
 
 	if (bootrom_mtd) {
-		del_mtd_device(bootrom_mtd);
+		mtd_device_unregister(bootrom_mtd);
 		map_destroy(bootrom_mtd);
 		iounmap((void *)cdb89712_bootrom_map.virt);
 		release_resource (&cdb89712_bootrom_resource);
diff --git a/drivers/mtd/maps/ceiva.c b/drivers/mtd/maps/ceiva.c
index 23f551dc8ca8..06f9c9815720 100644
--- a/drivers/mtd/maps/ceiva.c
+++ b/drivers/mtd/maps/ceiva.c
@@ -224,7 +224,7 @@ static void __exit clps_destroy_mtd(struct clps_info *clps, struct mtd_info *mtd
 {
 	int i;
 
-	del_mtd_partitions(mtd);
+	mtd_device_unregister(mtd);
 
 	if (mtd != clps[0].mtd)
 		mtd_concat_destroy(mtd);
@@ -292,11 +292,11 @@ static void __init clps_locate_partitions(struct mtd_info *mtd)
 	if (nr_parts == 0) {
 		printk(KERN_NOTICE "clps flash: no partition info "
 			"available, registering whole flash\n");
-		add_mtd_device(mtd);
+		mtd_device_register(mtd, NULL, 0);
 	} else {
 		printk(KERN_NOTICE "clps flash: using %s partition "
 			"definition\n", part_type);
-		add_mtd_partitions(mtd, parsed_parts, nr_parts);
+		mtd_device_register(mtd, parsed_parts, nr_parts);
 	}
 
 	/* Always succeeds. */
diff --git a/drivers/mtd/maps/cfi_flagadm.c b/drivers/mtd/maps/cfi_flagadm.c
index f71343cd77cc..d16fc9d3b8cd 100644
--- a/drivers/mtd/maps/cfi_flagadm.c
+++ b/drivers/mtd/maps/cfi_flagadm.c
@@ -107,7 +107,7 @@ static int __init init_flagadm(void)
 	mymtd = do_map_probe("cfi_probe", &flagadm_map);
 	if (mymtd) {
 		mymtd->owner = THIS_MODULE;
-		add_mtd_partitions(mymtd, flagadm_parts, PARTITION_COUNT);
+		mtd_device_register(mymtd, flagadm_parts, PARTITION_COUNT);
 		printk(KERN_NOTICE "FlagaDM flash device initialized\n");
 		return 0;
 	}
@@ -119,7 +119,7 @@ static int __init init_flagadm(void)
 static void __exit cleanup_flagadm(void)
 {
 	if (mymtd) {
-		del_mtd_partitions(mymtd);
+		mtd_device_unregister(mymtd);
 		map_destroy(mymtd);
 	}
 	if (flagadm_map.virt) {
diff --git a/drivers/mtd/maps/ck804xrom.c b/drivers/mtd/maps/ck804xrom.c
index 5fdb7b26cea3..3d0e762fa5f2 100644
--- a/drivers/mtd/maps/ck804xrom.c
+++ b/drivers/mtd/maps/ck804xrom.c
@@ -94,7 +94,7 @@ static void ck804xrom_cleanup(struct ck804xrom_window *window)
 		if (map->rsrc.parent)
 			release_resource(&map->rsrc);
 
-		del_mtd_device(map->mtd);
+		mtd_device_unregister(map->mtd);
 		map_destroy(map->mtd);
 		list_del(&map->list);
 		kfree(map);
@@ -291,7 +291,7 @@ static int __devinit ck804xrom_init_one (struct pci_dev *pdev,
 
 		/* Now that the mtd devices is complete claim and export it */
 		map->mtd->owner = THIS_MODULE;
-		if (add_mtd_device(map->mtd)) {
+		if (mtd_device_register(map->mtd, NULL, 0)) {
 			map_destroy(map->mtd);
 			map->mtd = NULL;
 			goto out;
diff --git a/drivers/mtd/maps/dbox2-flash.c b/drivers/mtd/maps/dbox2-flash.c
index cfacfa6f45dd..85bdece6ab3f 100644
--- a/drivers/mtd/maps/dbox2-flash.c
+++ b/drivers/mtd/maps/dbox2-flash.c
@@ -93,7 +93,7 @@ static int __init init_dbox2_flash(void)
 		mymtd->owner = THIS_MODULE;
 
                 /* Create MTD devices for each partition. */
-	        add_mtd_partitions(mymtd, partition_info, NUM_PARTITIONS);
+		mtd_device_register(mymtd, partition_info, NUM_PARTITIONS);
 
 		return 0;
 	}
@@ -105,7 +105,7 @@ static int __init init_dbox2_flash(void)
 static void __exit cleanup_dbox2_flash(void)
 {
 	if (mymtd) {
-		del_mtd_partitions(mymtd);
+		mtd_device_unregister(mymtd);
 		map_destroy(mymtd);
 	}
 	if (dbox2_flash_map.virt) {
diff --git a/drivers/mtd/maps/dc21285.c b/drivers/mtd/maps/dc21285.c
index b3cb3a183809..7a9e1989c977 100644
--- a/drivers/mtd/maps/dc21285.c
+++ b/drivers/mtd/maps/dc21285.c
@@ -145,17 +145,13 @@ static struct map_info dc21285_map = {
 
 
 /* Partition stuff */
-#ifdef CONFIG_MTD_PARTITIONS
 static struct mtd_partition *dc21285_parts;
 static const char *probes[] = { "RedBoot", "cmdlinepart", NULL };
-#endif
 
 static int __init init_dc21285(void)
 {
 
-#ifdef CONFIG_MTD_PARTITIONS
 	int nrparts;
-#endif
 
 	/* Determine bankwidth */
 	switch (*CSR_SA110_CNTL & (3<<14)) {
@@ -204,13 +200,8 @@ static int __init init_dc21285(void)
 
 	dc21285_mtd->owner = THIS_MODULE;
 
-#ifdef CONFIG_MTD_PARTITIONS
 	nrparts = parse_mtd_partitions(dc21285_mtd, probes, &dc21285_parts, 0);
-	if (nrparts > 0)
-		add_mtd_partitions(dc21285_mtd, dc21285_parts, nrparts);
-	else
-#endif
-		add_mtd_device(dc21285_mtd);
+	mtd_device_register(dc21285_mtd, dc21285_parts, nrparts);
 
 	if(machine_is_ebsa285()) {
 		/*
@@ -232,14 +223,9 @@ static int __init init_dc21285(void)
 
 static void __exit cleanup_dc21285(void)
 {
-#ifdef CONFIG_MTD_PARTITIONS
-	if (dc21285_parts) {
-		del_mtd_partitions(dc21285_mtd);
+	mtd_device_unregister(dc21285_mtd);
+	if (dc21285_parts)
 		kfree(dc21285_parts);
-	} else
-#endif
-		del_mtd_device(dc21285_mtd);
-
 	map_destroy(dc21285_mtd);
 	iounmap(dc21285_map.virt);
 }
diff --git a/drivers/mtd/maps/dilnetpc.c b/drivers/mtd/maps/dilnetpc.c
index 0713e3a5a22c..3e393f0da823 100644
--- a/drivers/mtd/maps/dilnetpc.c
+++ b/drivers/mtd/maps/dilnetpc.c
@@ -450,7 +450,7 @@ static int __init init_dnpc(void)
 	partition_info[2].mtdp = &lowlvl_parts[1];
 	partition_info[3].mtdp = &lowlvl_parts[3];
 
-	add_mtd_partitions(mymtd, partition_info, NUM_PARTITIONS);
+	mtd_device_register(mymtd, partition_info, NUM_PARTITIONS);
 
 	/*
 	** now create a virtual MTD device by concatenating the for partitions
@@ -463,7 +463,8 @@ static int __init init_dnpc(void)
 		** we do not supply mtd pointers in higlvl_partition_info, so
 		** add_mtd_partitions() will register the devices.
 		*/
-		add_mtd_partitions(merged_mtd, higlvl_partition_info, NUM_HIGHLVL_PARTITIONS);
+		mtd_device_register(merged_mtd, higlvl_partition_info,
+				    NUM_HIGHLVL_PARTITIONS);
 	}
 
 	return 0;
@@ -472,12 +473,12 @@ static int __init init_dnpc(void)
 static void __exit cleanup_dnpc(void)
 {
 	if(merged_mtd) {
-		del_mtd_partitions(merged_mtd);
+		mtd_device_unregister(merged_mtd);
 		mtd_concat_destroy(merged_mtd);
 	}
 
 	if (mymtd) {
-		del_mtd_partitions(mymtd);
+		mtd_device_unregister(mymtd);
 		map_destroy(mymtd);
 	}
 	if (dnpc_map.virt) {
diff --git a/drivers/mtd/maps/dmv182.c b/drivers/mtd/maps/dmv182.c
index d171674eb2ed..6538ac675e00 100644
--- a/drivers/mtd/maps/dmv182.c
+++ b/drivers/mtd/maps/dmv182.c
@@ -120,7 +120,7 @@ static int __init init_svme182(void)
 		   this_mtd->size >> 20, FLASH_BASE_ADDR);
 
 	this_mtd->owner = THIS_MODULE;
-	add_mtd_partitions(this_mtd, partitions, num_parts);
+	mtd_device_register(this_mtd, partitions, num_parts);
 
 	return 0;
 }
@@ -129,7 +129,7 @@ static void __exit cleanup_svme182(void)
 {
 	if (this_mtd)
 	{
-		del_mtd_partitions(this_mtd);
+		mtd_device_unregister(this_mtd);
 		map_destroy(this_mtd);
 	}
 
diff --git a/drivers/mtd/maps/edb7312.c b/drivers/mtd/maps/edb7312.c
index be9e90b44587..fe42a212bb3e 100644
--- a/drivers/mtd/maps/edb7312.c
+++ b/drivers/mtd/maps/edb7312.c
@@ -15,10 +15,7 @@
 #include <asm/io.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/map.h>
-
-#ifdef CONFIG_MTD_PARTITIONS
 #include <linux/mtd/partitions.h>
-#endif
 
 #define WINDOW_ADDR 0x00000000      /* physical properties of flash */
 #define WINDOW_SIZE 0x01000000
@@ -40,8 +37,6 @@ struct map_info edb7312nor_map = {
 	.phys = WINDOW_ADDR,
 };
 
-#ifdef CONFIG_MTD_PARTITIONS
-
 /*
  * MTD partitioning stuff
  */
@@ -66,8 +61,6 @@ static struct mtd_partition static_partitions[3] =
 
 static const char *probes[] = { "RedBoot", "cmdlinepart", NULL };
 
-#endif
-
 static int                   mtd_parts_nb = 0;
 static struct mtd_partition *mtd_parts    = 0;
 
@@ -96,27 +89,24 @@ static int __init init_edb7312nor(void)
 	if (mymtd) {
 		mymtd->owner = THIS_MODULE;
 
-#ifdef CONFIG_MTD_PARTITIONS
 		mtd_parts_nb = parse_mtd_partitions(mymtd, probes, &mtd_parts, MTDID);
 		if (mtd_parts_nb > 0)
-		  part_type = "detected";
+			part_type = "detected";
 
-		if (mtd_parts_nb == 0)
-		{
+		if (mtd_parts_nb == 0) {
 			mtd_parts = static_partitions;
 			mtd_parts_nb = ARRAY_SIZE(static_partitions);
 			part_type = "static";
 		}
-#endif
-		add_mtd_device(mymtd);
+
 		if (mtd_parts_nb == 0)
-		  printk(KERN_NOTICE MSG_PREFIX "no partition info available\n");
+			printk(KERN_NOTICE MSG_PREFIX "no partition info available\n");
 		else
-		{
 			printk(KERN_NOTICE MSG_PREFIX
 			       "using %s partition definition\n", part_type);
-			add_mtd_partitions(mymtd, mtd_parts, mtd_parts_nb);
-		}
+		/* Register the whole device first. */
+		mtd_device_register(mymtd, NULL, 0);
+		mtd_device_register(mymtd, mtd_parts, mtd_parts_nb);
 		return 0;
 	}
 
@@ -127,7 +117,7 @@ static int __init init_edb7312nor(void)
 static void __exit cleanup_edb7312nor(void)
 {
 	if (mymtd) {
-		del_mtd_device(mymtd);
+		mtd_device_unregister(mymtd);
 		map_destroy(mymtd);
 	}
 	if (edb7312nor_map.virt) {
diff --git a/drivers/mtd/maps/esb2rom.c b/drivers/mtd/maps/esb2rom.c
index 4feb7507ab7c..08322b1c3e81 100644
--- a/drivers/mtd/maps/esb2rom.c
+++ b/drivers/mtd/maps/esb2rom.c
@@ -128,7 +128,7 @@ static void esb2rom_cleanup(struct esb2rom_window *window)
 	list_for_each_entry_safe(map, scratch, &window->maps, list) {
 		if (map->rsrc.parent)
 			release_resource(&map->rsrc);
-		del_mtd_device(map->mtd);
+		mtd_device_unregister(map->mtd);
 		map_destroy(map->mtd);
 		list_del(&map->list);
 		kfree(map);
@@ -352,7 +352,7 @@ static int __devinit esb2rom_init_one(struct pci_dev *pdev,
 
 		/* Now that the mtd devices is complete claim and export it */
 		map->mtd->owner = THIS_MODULE;
-		if (add_mtd_device(map->mtd)) {
+		if (mtd_device_register(map->mtd, NULL, 0)) {
 			map_destroy(map->mtd);
 			map->mtd = NULL;
 			goto out;
diff --git a/drivers/mtd/maps/fortunet.c b/drivers/mtd/maps/fortunet.c
index 1e43124d498b..956e2e4f30ea 100644
--- a/drivers/mtd/maps/fortunet.c
+++ b/drivers/mtd/maps/fortunet.c
@@ -243,8 +243,9 @@ static int __init init_fortunet(void)
 					&map_regions[ix].map_info);
 			}
 			map_regions[ix].mymtd->owner = THIS_MODULE;
-			add_mtd_partitions(map_regions[ix].mymtd,
-				map_regions[ix].parts,map_regions_parts[ix]);
+			mtd_device_register(map_regions[ix].mymtd,
+					    map_regions[ix].parts,
+					    map_regions_parts[ix]);
 		}
 	}
 	if(iy)
@@ -261,7 +262,7 @@ static void __exit cleanup_fortunet(void)
 		{
 			if( map_regions[ix].mymtd )
 			{
-				del_mtd_partitions( map_regions[ix].mymtd );
+				mtd_device_unregister(map_regions[ix].mymtd);
 				map_destroy( map_regions[ix].mymtd );
 			}
 			iounmap((void *)map_regions[ix].map_info.virt);
diff --git a/drivers/mtd/maps/gpio-addr-flash.c b/drivers/mtd/maps/gpio-addr-flash.c
index af5707a80205..7568c5f8b8ae 100644
--- a/drivers/mtd/maps/gpio-addr-flash.c
+++ b/drivers/mtd/maps/gpio-addr-flash.c
@@ -155,9 +155,7 @@ static void gf_copy_to(struct map_info *map, unsigned long to, const void *from,
 	memcpy_toio(map->virt + (to % state->win_size), from, len);
 }
 
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *part_probe_types[] = { "cmdlinepart", "RedBoot", NULL };
-#endif
 
 /**
  * gpio_flash_probe() - setup a mapping for a GPIO assisted flash
@@ -189,7 +187,7 @@ static const char *part_probe_types[] = { "cmdlinepart", "RedBoot", NULL };
  */
 static int __devinit gpio_flash_probe(struct platform_device *pdev)
 {
-	int ret;
+	int nr_parts;
 	size_t i, arr_size;
 	struct physmap_flash_data *pdata;
 	struct resource *memory;
@@ -254,24 +252,21 @@ static int __devinit gpio_flash_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-#ifdef CONFIG_MTD_PARTITIONS
-	ret = parse_mtd_partitions(state->mtd, part_probe_types, &pdata->parts, 0);
-	if (ret > 0) {
+	nr_parts = parse_mtd_partitions(state->mtd, part_probe_types,
+					&pdata->parts, 0);
+	if (nr_parts > 0) {
 		pr_devinit(KERN_NOTICE PFX "Using commandline partition definition\n");
-		add_mtd_partitions(state->mtd, pdata->parts, ret);
 		kfree(pdata->parts);
-
 	} else if (pdata->nr_parts) {
 		pr_devinit(KERN_NOTICE PFX "Using board partition definition\n");
-		add_mtd_partitions(state->mtd, pdata->parts, pdata->nr_parts);
-
-	} else
-#endif
-	{
+		nr_parts = pdata->nr_parts;
+	} else {
 		pr_devinit(KERN_NOTICE PFX "no partition info available, registering whole flash at once\n");
-		add_mtd_device(state->mtd);
+		nr_parts = 0;
 	}
 
+	mtd_device_register(state->mtd, pdata->parts, nr_parts);
+
 	return 0;
 }
 
@@ -282,9 +277,7 @@ static int __devexit gpio_flash_remove(struct platform_device *pdev)
 	do {
 		gpio_free(state->gpio_addrs[i]);
 	} while (++i < state->gpio_count);
-#ifdef CONFIG_MTD_PARTITIONS
-	del_mtd_partitions(state->mtd);
-#endif
+	mtd_device_unregister(state->mtd);
 	map_destroy(state->mtd);
 	kfree(state);
 	return 0;
diff --git a/drivers/mtd/maps/h720x-flash.c b/drivers/mtd/maps/h720x-flash.c
index 72c724fa8c27..7f035860a36b 100644
--- a/drivers/mtd/maps/h720x-flash.c
+++ b/drivers/mtd/maps/h720x-flash.c
@@ -92,18 +92,16 @@ static int __init h720x_mtd_init(void)
 	if (mymtd) {
 		mymtd->owner = THIS_MODULE;
 
-#ifdef CONFIG_MTD_PARTITIONS
 		nr_mtd_parts = parse_mtd_partitions(mymtd, probes, &mtd_parts, 0);
 		if (nr_mtd_parts > 0)
 			part_type = "command line";
-#endif
 		if (nr_mtd_parts <= 0) {
 			mtd_parts = h720x_partitions;
 			nr_mtd_parts = NUM_PARTITIONS;
 			part_type = "builtin";
 		}
 		printk(KERN_INFO "Using %s partition table\n", part_type);
-		add_mtd_partitions(mymtd, mtd_parts, nr_mtd_parts);
+		mtd_device_register(mymtd, mtd_parts, nr_mtd_parts);
 		return 0;
 	}
 
@@ -118,7 +116,7 @@ static void __exit h720x_mtd_cleanup(void)
 {
 
 	if (mymtd) {
-		del_mtd_partitions(mymtd);
+		mtd_device_unregister(mymtd);
 		map_destroy(mymtd);
 	}
 
diff --git a/drivers/mtd/maps/ichxrom.c b/drivers/mtd/maps/ichxrom.c
index 1337a4191a0c..6689dcb3124d 100644
--- a/drivers/mtd/maps/ichxrom.c
+++ b/drivers/mtd/maps/ichxrom.c
@@ -67,7 +67,7 @@ static void ichxrom_cleanup(struct ichxrom_window *window)
 	list_for_each_entry_safe(map, scratch, &window->maps, list) {
 		if (map->rsrc.parent)
 			release_resource(&map->rsrc);
-		del_mtd_device(map->mtd);
+		mtd_device_unregister(map->mtd);
 		map_destroy(map->mtd);
 		list_del(&map->list);
 		kfree(map);
@@ -287,7 +287,7 @@ static int __devinit ichxrom_init_one (struct pci_dev *pdev,
 
 		/* Now that the mtd devices is complete claim and export it */
 		map->mtd->owner = THIS_MODULE;
-		if (add_mtd_device(map->mtd)) {
+		if (mtd_device_register(map->mtd, NULL, 0)) {
 			map_destroy(map->mtd);
 			map->mtd = NULL;
 			goto out;
diff --git a/drivers/mtd/maps/impa7.c b/drivers/mtd/maps/impa7.c
index 998a27da97f3..404a50cbafa0 100644
--- a/drivers/mtd/maps/impa7.c
+++ b/drivers/mtd/maps/impa7.c
@@ -15,10 +15,7 @@
 #include <asm/io.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/map.h>
-
-#ifdef CONFIG_MTD_PARTITIONS
 #include <linux/mtd/partitions.h>
-#endif
 
 #define WINDOW_ADDR0 0x00000000      /* physical properties of flash */
 #define WINDOW_SIZE0 0x00800000
@@ -49,8 +46,6 @@ static struct map_info impa7_map[NUM_FLASHBANKS] = {
 	},
 };
 
-#ifdef CONFIG_MTD_PARTITIONS
-
 /*
  * MTD partitioning stuff
  */
@@ -66,8 +61,6 @@ static struct mtd_partition static_partitions[] =
 static int mtd_parts_nb[NUM_FLASHBANKS];
 static struct mtd_partition *mtd_parts[NUM_FLASHBANKS];
 
-#endif
-
 static const char *probes[] = { "cmdlinepart", NULL };
 
 static int __init init_impa7(void)
@@ -104,7 +97,6 @@ static int __init init_impa7(void)
 		if (impa7_mtd[i]) {
 			impa7_mtd[i]->owner = THIS_MODULE;
 			devicesfound++;
-#ifdef CONFIG_MTD_PARTITIONS
 			mtd_parts_nb[i] = parse_mtd_partitions(impa7_mtd[i],
 							       probes,
 							       &mtd_parts[i],
@@ -120,12 +112,8 @@ static int __init init_impa7(void)
 			printk(KERN_NOTICE MSG_PREFIX
 			       "using %s partition definition\n",
 			       part_type);
-			add_mtd_partitions(impa7_mtd[i],
-					   mtd_parts[i], mtd_parts_nb[i]);
-#else
-			add_mtd_device(impa7_mtd[i]);
-
-#endif
+			mtd_device_register(impa7_mtd[i],
+					    mtd_parts[i], mtd_parts_nb[i]);
 		}
 		else
 			iounmap((void *)impa7_map[i].virt);
@@ -138,11 +126,7 @@ static void __exit cleanup_impa7(void)
 	int i;
 	for (i=0; i<NUM_FLASHBANKS; i++) {
 		if (impa7_mtd[i]) {
-#ifdef CONFIG_MTD_PARTITIONS
-			del_mtd_partitions(impa7_mtd[i]);
-#else
-			del_mtd_device(impa7_mtd[i]);
-#endif
+			mtd_device_unregister(impa7_mtd[i]);
 			map_destroy(impa7_mtd[i]);
 			iounmap((void *)impa7_map[i].virt);
 			impa7_map[i].virt = 0;
diff --git a/drivers/mtd/maps/intel_vr_nor.c b/drivers/mtd/maps/intel_vr_nor.c
index fc1998512eb4..d2f47be8754b 100644
--- a/drivers/mtd/maps/intel_vr_nor.c
+++ b/drivers/mtd/maps/intel_vr_nor.c
@@ -66,33 +66,18 @@ struct vr_nor_mtd {
 
 static void __devexit vr_nor_destroy_partitions(struct vr_nor_mtd *p)
 {
-	if (p->nr_parts > 0) {
-#if defined(CONFIG_MTD_PARTITIONS) || defined(CONFIG_MTD_PARTITIONS_MODULE)
-		del_mtd_partitions(p->info);
-#endif
-	} else
-		del_mtd_device(p->info);
+	mtd_device_unregister(p->info);
 }
 
 static int __devinit vr_nor_init_partitions(struct vr_nor_mtd *p)
 {
-	int err = 0;
-#if defined(CONFIG_MTD_PARTITIONS) || defined(CONFIG_MTD_PARTITIONS_MODULE)
 	struct mtd_partition *parts;
 	static const char *part_probes[] = { "cmdlinepart", NULL };
-#endif
 
 	/* register the flash bank */
-#if defined(CONFIG_MTD_PARTITIONS) || defined(CONFIG_MTD_PARTITIONS_MODULE)
 	/* partition the flash bank */
 	p->nr_parts = parse_mtd_partitions(p->info, part_probes, &parts, 0);
-	if (p->nr_parts > 0)
-		err = add_mtd_partitions(p->info, parts, p->nr_parts);
-#endif
-	if (p->nr_parts <= 0)
-		err = add_mtd_device(p->info);
-
-	return err;
+	return mtd_device_register(p->info, parts, p->nr_parts);
 }
 
 static void __devexit vr_nor_destroy_mtd_setup(struct vr_nor_mtd *p)
diff --git a/drivers/mtd/maps/ixp2000.c b/drivers/mtd/maps/ixp2000.c
index 9639d83a9d6c..c00b9175ba9e 100644
--- a/drivers/mtd/maps/ixp2000.c
+++ b/drivers/mtd/maps/ixp2000.c
@@ -119,7 +119,7 @@ static int ixp2000_flash_remove(struct platform_device *dev)
 		return 0;
 
 	if (info->mtd) {
-		del_mtd_partitions(info->mtd);
+		mtd_device_unregister(info->mtd);
 		map_destroy(info->mtd);
 	}
 	if (info->map.map_priv_1)
@@ -230,7 +230,7 @@ static int ixp2000_flash_probe(struct platform_device *dev)
 
 	err = parse_mtd_partitions(info->mtd, probes, &info->partitions, 0);
 	if (err > 0) {
-		err = add_mtd_partitions(info->mtd, info->partitions, err);
+		err = mtd_device_register(info->mtd, info->partitions, err);
 		if(err)
 			dev_err(&dev->dev, "Could not parse partitions\n");
 	}
diff --git a/drivers/mtd/maps/ixp4xx.c b/drivers/mtd/maps/ixp4xx.c
index 1f9fde0dad35..155b21942f47 100644
--- a/drivers/mtd/maps/ixp4xx.c
+++ b/drivers/mtd/maps/ixp4xx.c
@@ -162,7 +162,7 @@ static int ixp4xx_flash_remove(struct platform_device *dev)
 		return 0;
 
 	if (info->mtd) {
-		del_mtd_partitions(info->mtd);
+		mtd_device_unregister(info->mtd);
 		map_destroy(info->mtd);
 	}
 	if (info->map.virt)
@@ -252,10 +252,8 @@ static int ixp4xx_flash_probe(struct platform_device *dev)
 	/* Use the fast version */
 	info->map.write = ixp4xx_write16;
 
-#ifdef CONFIG_MTD_PARTITIONS
 	nr_parts = parse_mtd_partitions(info->mtd, probes, &info->partitions,
 					dev->resource->start);
-#endif
 	if (nr_parts > 0) {
 		part_type = "dynamic";
 	} else {
@@ -263,18 +261,16 @@ static int ixp4xx_flash_probe(struct platform_device *dev)
 		nr_parts = plat->nr_parts;
 		part_type = "static";
 	}
-	if (nr_parts == 0) {
+	if (nr_parts == 0)
 		printk(KERN_NOTICE "IXP4xx flash: no partition info "
 			"available, registering whole flash\n");
-		err = add_mtd_device(info->mtd);
-	} else {
+	else
 		printk(KERN_NOTICE "IXP4xx flash: using %s partition "
 			"definition\n", part_type);
-		err = add_mtd_partitions(info->mtd, info->partitions, nr_parts);
 
-		if(err)
-			printk(KERN_ERR "Could not parse partitions\n");
-	}
+	err = mtd_device_register(info->mtd, info->partitions, nr_parts);
+	if (err)
+		printk(KERN_ERR "Could not parse partitions\n");
 
 	if (err)
 		goto Error;
diff --git a/drivers/mtd/maps/l440gx.c b/drivers/mtd/maps/l440gx.c
index 9e054503c4cf..dd0360ba2412 100644
--- a/drivers/mtd/maps/l440gx.c
+++ b/drivers/mtd/maps/l440gx.c
@@ -138,7 +138,7 @@ static int __init init_l440gx(void)
 	if (mymtd) {
 		mymtd->owner = THIS_MODULE;
 
-		add_mtd_device(mymtd);
+		mtd_device_register(mymtd, NULL, 0);
 		return 0;
 	}
 
@@ -148,7 +148,7 @@ static int __init init_l440gx(void)
 
 static void __exit cleanup_l440gx(void)
 {
-	del_mtd_device(mymtd);
+	mtd_device_unregister(mymtd);
 	map_destroy(mymtd);
 
 	iounmap(l440gx_map.virt);
diff --git a/drivers/mtd/maps/latch-addr-flash.c b/drivers/mtd/maps/latch-addr-flash.c
index ee2548085334..5936c466e901 100644
--- a/drivers/mtd/maps/latch-addr-flash.c
+++ b/drivers/mtd/maps/latch-addr-flash.c
@@ -112,18 +112,9 @@ static int latch_addr_flash_remove(struct platform_device *dev)
 	latch_addr_data = dev->dev.platform_data;
 
 	if (info->mtd != NULL) {
-		if (mtd_has_partitions()) {
-			if (info->nr_parts) {
-				del_mtd_partitions(info->mtd);
-				kfree(info->parts);
-			} else if (latch_addr_data->nr_parts) {
-				del_mtd_partitions(info->mtd);
-			} else {
-				del_mtd_device(info->mtd);
-			}
-		} else {
-			del_mtd_device(info->mtd);
-		}
+		if (info->nr_parts)
+			kfree(info->parts);
+		mtd_device_unregister(info->mtd);
 		map_destroy(info->mtd);
 	}
 
@@ -215,23 +206,21 @@ static int __devinit latch_addr_flash_probe(struct platform_device *dev)
 	}
 	info->mtd->owner = THIS_MODULE;
 
-	if (mtd_has_partitions()) {
-
-		err = parse_mtd_partitions(info->mtd,
-					   (const char **)part_probe_types,
-					   &info->parts, 0);
-		if (err > 0) {
-			add_mtd_partitions(info->mtd, info->parts, err);
-			return 0;
-		}
-		if (latch_addr_data->nr_parts) {
-			pr_notice("Using latch-addr-flash partition information\n");
-			add_mtd_partitions(info->mtd, latch_addr_data->parts,
-					latch_addr_data->nr_parts);
-			return 0;
-		}
+	err = parse_mtd_partitions(info->mtd, (const char **)part_probe_types,
+				   &info->parts, 0);
+	if (err > 0) {
+		mtd_device_register(info->mtd, info->parts, err);
+		return 0;
+	}
+	if (latch_addr_data->nr_parts) {
+		pr_notice("Using latch-addr-flash partition information\n");
+		mtd_device_register(info->mtd,
+				    latch_addr_data->parts,
+				    latch_addr_data->nr_parts);
+		return 0;
 	}
-	add_mtd_device(info->mtd);
+
+	mtd_device_register(info->mtd, NULL, 0);
 	return 0;
 
 iounmap:
diff --git a/drivers/mtd/maps/mbx860.c b/drivers/mtd/maps/mbx860.c
index 0eb5a7c85380..93fa56c33003 100644
--- a/drivers/mtd/maps/mbx860.c
+++ b/drivers/mtd/maps/mbx860.c
@@ -69,8 +69,8 @@ static int __init init_mbx(void)
 	mymtd = do_map_probe("jedec_probe", &mbx_map);
 	if (mymtd) {
 		mymtd->owner = THIS_MODULE;
-		add_mtd_device(mymtd);
-                add_mtd_partitions(mymtd, partition_info, NUM_PARTITIONS);
+		mtd_device_register(mymtd, NULL, 0);
+		mtd_device_register(mymtd, partition_info, NUM_PARTITIONS);
 		return 0;
 	}
 
@@ -81,7 +81,7 @@ static int __init init_mbx(void)
 static void __exit cleanup_mbx(void)
 {
 	if (mymtd) {
-		del_mtd_device(mymtd);
+		mtd_device_unregister(mymtd);
 		map_destroy(mymtd);
 	}
 	if (mbx_map.virt) {
diff --git a/drivers/mtd/maps/netsc520.c b/drivers/mtd/maps/netsc520.c
index c0cb319b2b70..81dc2598bc0a 100644
--- a/drivers/mtd/maps/netsc520.c
+++ b/drivers/mtd/maps/netsc520.c
@@ -116,14 +116,14 @@ static int __init init_netsc520(void)
 	}
 
 	mymtd->owner = THIS_MODULE;
-	add_mtd_partitions( mymtd, partition_info, NUM_PARTITIONS );
+	mtd_device_register(mymtd, partition_info, NUM_PARTITIONS);
 	return 0;
 }
 
 static void __exit cleanup_netsc520(void)
 {
 	if (mymtd) {
-		del_mtd_partitions(mymtd);
+		mtd_device_unregister(mymtd);
 		map_destroy(mymtd);
 	}
 	if (netsc520_map.virt) {
diff --git a/drivers/mtd/maps/nettel.c b/drivers/mtd/maps/nettel.c
index a97133eb9d70..eadcfffc4f9c 100644
--- a/drivers/mtd/maps/nettel.c
+++ b/drivers/mtd/maps/nettel.c
@@ -383,13 +383,13 @@ static int __init nettel_init(void)
 		/* No BIOS regions when AMD boot */
 		num_intel_partitions -= 2;
 	}
-	rc = add_mtd_partitions(intel_mtd, nettel_intel_partitions,
-		num_intel_partitions);
+	rc = mtd_device_register(intel_mtd, nettel_intel_partitions,
+				 num_intel_partitions);
 #endif
 
 	if (amd_mtd) {
-		rc = add_mtd_partitions(amd_mtd, nettel_amd_partitions,
-			num_amd_partitions);
+		rc = mtd_device_register(amd_mtd, nettel_amd_partitions,
+					 num_amd_partitions);
 	}
 
 #ifdef CONFIG_MTD_CFI_INTELEXT
@@ -419,7 +419,7 @@ static void __exit nettel_cleanup(void)
 	unregister_reboot_notifier(&nettel_notifier_block);
 #endif
 	if (amd_mtd) {
-		del_mtd_partitions(amd_mtd);
+		mtd_device_unregister(amd_mtd);
 		map_destroy(amd_mtd);
 	}
 	if (nettel_mmcrp) {
@@ -432,7 +432,7 @@ static void __exit nettel_cleanup(void)
 	}
 #ifdef CONFIG_MTD_CFI_INTELEXT
 	if (intel_mtd) {
-		del_mtd_partitions(intel_mtd);
+		mtd_device_unregister(intel_mtd);
 		map_destroy(intel_mtd);
 	}
 	if (nettel_intel_map.virt) {
diff --git a/drivers/mtd/maps/octagon-5066.c b/drivers/mtd/maps/octagon-5066.c
index 23fe1786770f..807ac2a2e686 100644
--- a/drivers/mtd/maps/octagon-5066.c
+++ b/drivers/mtd/maps/octagon-5066.c
@@ -175,7 +175,7 @@ void cleanup_oct5066(void)
 	int i;
 	for (i=0; i<2; i++) {
 		if (oct5066_mtd[i]) {
-			del_mtd_device(oct5066_mtd[i]);
+			mtd_device_unregister(oct5066_mtd[i]);
 			map_destroy(oct5066_mtd[i]);
 		}
 	}
@@ -220,7 +220,7 @@ static int __init init_oct5066(void)
 			oct5066_mtd[i] = do_map_probe("map_rom", &oct5066_map[i]);
 		if (oct5066_mtd[i]) {
 			oct5066_mtd[i]->owner = THIS_MODULE;
-			add_mtd_device(oct5066_mtd[i]);
+			mtd_device_register(oct5066_mtd[i], NULL, 0);
 		}
 	}
 
diff --git a/drivers/mtd/maps/pci.c b/drivers/mtd/maps/pci.c
index 48f4cf5cb9d1..1d005a3e9b41 100644
--- a/drivers/mtd/maps/pci.c
+++ b/drivers/mtd/maps/pci.c
@@ -313,7 +313,7 @@ mtd_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		goto release;
 
 	mtd->owner = THIS_MODULE;
-	add_mtd_device(mtd);
+	mtd_device_register(mtd, NULL, 0);
 
 	pci_set_drvdata(dev, mtd);
 
@@ -336,7 +336,7 @@ mtd_pci_remove(struct pci_dev *dev)
 	struct mtd_info *mtd = pci_get_drvdata(dev);
 	struct map_pci_info *map = mtd->priv;
 
-	del_mtd_device(mtd);
+	mtd_device_unregister(mtd);
 	map_destroy(mtd);
 	map->exit(dev, map);
 	kfree(map);
diff --git a/drivers/mtd/maps/pcmciamtd.c b/drivers/mtd/maps/pcmciamtd.c
index 33dc2829b01b..bbe168b65c26 100644
--- a/drivers/mtd/maps/pcmciamtd.c
+++ b/drivers/mtd/maps/pcmciamtd.c
@@ -630,7 +630,7 @@ static int pcmciamtd_config(struct pcmcia_device *link)
 		dev->pcmcia_map.copy_to = pcmcia_copy_to;
 	}
 
-	if(add_mtd_device(mtd)) {
+	if (mtd_device_register(mtd, NULL, 0)) {
 		map_destroy(mtd);
 		dev->mtd_info = NULL;
 		dev_err(&dev->p_dev->dev,
@@ -669,7 +669,7 @@ static void pcmciamtd_detach(struct pcmcia_device *link)
 	DEBUG(3, "link=0x%p", link);
 
 	if(dev->mtd_info) {
-		del_mtd_device(dev->mtd_info);
+		mtd_device_unregister(dev->mtd_info);
 		dev_info(&dev->p_dev->dev, "mtd%d: Removing\n",
 			 dev->mtd_info->index);
 		map_destroy(dev->mtd_info);
diff --git a/drivers/mtd/maps/physmap.c b/drivers/mtd/maps/physmap.c
index 1a9b94f0ee54..f64cee4a3bfb 100644
--- a/drivers/mtd/maps/physmap.c
+++ b/drivers/mtd/maps/physmap.c
@@ -27,10 +27,8 @@ struct physmap_flash_info {
 	struct mtd_info		*mtd[MAX_RESOURCES];
 	struct mtd_info		*cmtd;
 	struct map_info		map[MAX_RESOURCES];
-#ifdef CONFIG_MTD_PARTITIONS
 	int			nr_parts;
 	struct mtd_partition	*parts;
-#endif
 };
 
 static int physmap_flash_remove(struct platform_device *dev)
@@ -47,18 +45,9 @@ static int physmap_flash_remove(struct platform_device *dev)
 	physmap_data = dev->dev.platform_data;
 
 	if (info->cmtd) {
-#ifdef CONFIG_MTD_PARTITIONS
-		if (info->nr_parts || physmap_data->nr_parts) {
-			del_mtd_partitions(info->cmtd);
-
-			if (info->nr_parts)
-				kfree(info->parts);
-		} else {
-			del_mtd_device(info->cmtd);
-		}
-#else
-		del_mtd_device(info->cmtd);
-#endif
+		mtd_device_unregister(info->cmtd);
+		if (info->nr_parts)
+			kfree(info->parts);
 		if (info->cmtd != info->mtd[0])
 			mtd_concat_destroy(info->cmtd);
 	}
@@ -92,10 +81,8 @@ static const char *rom_probe_types[] = {
 					"qinfo_probe",
 					"map_rom",
 					NULL };
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *part_probe_types[] = { "cmdlinepart", "RedBoot", "afs",
 					  NULL };
-#endif
 
 static int physmap_flash_probe(struct platform_device *dev)
 {
@@ -188,24 +175,23 @@ static int physmap_flash_probe(struct platform_device *dev)
 	if (err)
 		goto err_out;
 
-#ifdef CONFIG_MTD_PARTITIONS
 	err = parse_mtd_partitions(info->cmtd, part_probe_types,
-				&info->parts, 0);
+				   &info->parts, 0);
 	if (err > 0) {
-		add_mtd_partitions(info->cmtd, info->parts, err);
+		mtd_device_register(info->cmtd, info->parts, err);
 		info->nr_parts = err;
 		return 0;
 	}
 
 	if (physmap_data->nr_parts) {
 		printk(KERN_NOTICE "Using physmap partition information\n");
-		add_mtd_partitions(info->cmtd, physmap_data->parts,
-				   physmap_data->nr_parts);
+		mtd_device_register(info->cmtd, physmap_data->parts,
+				    physmap_data->nr_parts);
 		return 0;
 	}
-#endif
 
-	add_mtd_device(info->cmtd);
+	mtd_device_register(info->cmtd, NULL, 0);
+
 	return 0;
 
 err_out:
@@ -269,14 +255,12 @@ void physmap_configure(unsigned long addr, unsigned long size,
 	physmap_flash_data.set_vpp = set_vpp;
 }
 
-#ifdef CONFIG_MTD_PARTITIONS
 void physmap_set_partitions(struct mtd_partition *parts, int num_parts)
 {
 	physmap_flash_data.nr_parts = num_parts;
 	physmap_flash_data.parts = parts;
 }
 #endif
-#endif
 
 static int __init physmap_init(void)
 {
diff --git a/drivers/mtd/maps/physmap_of.c b/drivers/mtd/maps/physmap_of.c
index c1d33464aee8..d251d1db129b 100644
--- a/drivers/mtd/maps/physmap_of.c
+++ b/drivers/mtd/maps/physmap_of.c
@@ -34,16 +34,12 @@ struct of_flash_list {
 
 struct of_flash {
 	struct mtd_info		*cmtd;
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition	*parts;
-#endif
 	int list_size; /* number of elements in of_flash_list */
 	struct of_flash_list	list[0];
 };
 
-#ifdef CONFIG_MTD_PARTITIONS
 #define OF_FLASH_PARTS(info)	((info)->parts)
-
 static int parse_obsolete_partitions(struct platform_device *dev,
 				     struct of_flash *info,
 				     struct device_node *dp)
@@ -89,10 +85,6 @@ static int parse_obsolete_partitions(struct platform_device *dev,
 
 	return nr_parts;
 }
-#else /* MTD_PARTITIONS */
-#define	OF_FLASH_PARTS(info)		(0)
-#define parse_partitions(info, dev)	(0)
-#endif /* MTD_PARTITIONS */
 
 static int of_flash_remove(struct platform_device *dev)
 {
@@ -105,17 +97,14 @@ static int of_flash_remove(struct platform_device *dev)
 	dev_set_drvdata(&dev->dev, NULL);
 
 	if (info->cmtd != info->list[0].mtd) {
-		del_mtd_device(info->cmtd);
+		mtd_device_unregister(info->cmtd);
 		mtd_concat_destroy(info->cmtd);
 	}
 
 	if (info->cmtd) {
-		if (OF_FLASH_PARTS(info)) {
-			del_mtd_partitions(info->cmtd);
+		if (OF_FLASH_PARTS(info))
 			kfree(OF_FLASH_PARTS(info));
-		} else {
-			del_mtd_device(info->cmtd);
-		}
+		mtd_device_unregister(info->cmtd);
 	}
 
 	for (i = 0; i < info->list_size; i++) {
@@ -172,7 +161,6 @@ static struct mtd_info * __devinit obsolete_probe(struct platform_device *dev,
 	}
 }
 
-#ifdef CONFIG_MTD_PARTITIONS
 /* When partitions are set we look for a linux,part-probe property which
    specifies the list of partition probers to use. If none is given then the
    default is use. These take precedence over other device tree
@@ -212,14 +200,11 @@ static void __devinit of_free_probes(const char **probes)
 	if (probes != part_probe_types_def)
 		kfree(probes);
 }
-#endif
 
 static struct of_device_id of_flash_match[];
 static int __devinit of_flash_probe(struct platform_device *dev)
 {
-#ifdef CONFIG_MTD_PARTITIONS
 	const char **part_probe_types;
-#endif
 	const struct of_device_id *match;
 	struct device_node *dp = dev->dev.of_node;
 	struct resource res;
@@ -346,7 +331,6 @@ static int __devinit of_flash_probe(struct platform_device *dev)
 	if (err)
 		goto err_out;
 
-#ifdef CONFIG_MTD_PARTITIONS
 	part_probe_types = of_get_probes(dp);
 	err = parse_mtd_partitions(info->cmtd, part_probe_types,
 				   &info->parts, 0);
@@ -356,13 +340,11 @@ static int __devinit of_flash_probe(struct platform_device *dev)
 	}
 	of_free_probes(part_probe_types);
 
-#ifdef CONFIG_MTD_OF_PARTS
 	if (err == 0) {
 		err = of_mtd_parse_partitions(&dev->dev, dp, &info->parts);
 		if (err < 0)
 			goto err_out;
 	}
-#endif
 
 	if (err == 0) {
 		err = parse_obsolete_partitions(dev, info, dp);
@@ -370,11 +352,7 @@ static int __devinit of_flash_probe(struct platform_device *dev)
 			goto err_out;
 	}
 
-	if (err > 0)
-		add_mtd_partitions(info->cmtd, info->parts, err);
-	else
-#endif
-		add_mtd_device(info->cmtd);
+	mtd_device_register(info->cmtd, info->parts, err);
 
 	kfree(mtd_list);
 
diff --git a/drivers/mtd/maps/plat-ram.c b/drivers/mtd/maps/plat-ram.c
index 76a76be5a7bd..9ca1eccba4bc 100644
--- a/drivers/mtd/maps/plat-ram.c
+++ b/drivers/mtd/maps/plat-ram.c
@@ -94,14 +94,11 @@ static int platram_remove(struct platform_device *pdev)
 		return 0;
 
 	if (info->mtd) {
-#ifdef CONFIG_MTD_PARTITIONS
+		mtd_device_unregister(info->mtd);
 		if (info->partitions) {
-			del_mtd_partitions(info->mtd);
 			if (info->free_partitions)
 				kfree(info->partitions);
 		}
-#endif
-		del_mtd_device(info->mtd);
 		map_destroy(info->mtd);
 	}
 
@@ -231,7 +228,6 @@ static int platram_probe(struct platform_device *pdev)
 	/* check to see if there are any available partitions, or wether
 	 * to add this device whole */
 
-#ifdef CONFIG_MTD_PARTITIONS
 	if (!pdata->nr_partitions) {
 		/* try to probe using the supplied probe type */
 		if (pdata->probes) {
@@ -239,24 +235,22 @@ static int platram_probe(struct platform_device *pdev)
 					   &info->partitions, 0);
 			info->free_partitions = 1;
 			if (err > 0)
-				err = add_mtd_partitions(info->mtd,
+				err = mtd_device_register(info->mtd,
 					info->partitions, err);
 		}
 	}
 	/* use the static mapping */
 	else
-		err = add_mtd_partitions(info->mtd, pdata->partitions,
-				pdata->nr_partitions);
-#endif /* CONFIG_MTD_PARTITIONS */
-
-	if (add_mtd_device(info->mtd)) {
-		dev_err(&pdev->dev, "add_mtd_device() failed\n");
-		err = -ENOMEM;
-	}
-
+		err = mtd_device_register(info->mtd, pdata->partitions,
+					  pdata->nr_partitions);
 	if (!err)
 		dev_info(&pdev->dev, "registered mtd device\n");
 
+	/* add the whole device. */
+	err = mtd_device_register(info->mtd, NULL, 0);
+	if (err)
+		dev_err(&pdev->dev, "failed to register the entire device\n");
+
 	return err;
 
  exit_free:
diff --git a/drivers/mtd/maps/pmcmsp-flash.c b/drivers/mtd/maps/pmcmsp-flash.c
index 64aea6acd48e..744ca5cacc9b 100644
--- a/drivers/mtd/maps/pmcmsp-flash.c
+++ b/drivers/mtd/maps/pmcmsp-flash.c
@@ -173,7 +173,7 @@ static int __init init_msp_flash(void)
 		msp_flash[i] = do_map_probe("cfi_probe", &msp_maps[i]);
 		if (msp_flash[i]) {
 			msp_flash[i]->owner = THIS_MODULE;
-			add_mtd_partitions(msp_flash[i], msp_parts[i], pcnt);
+			mtd_device_register(msp_flash[i], msp_parts[i], pcnt);
 		} else {
 			printk(KERN_ERR "map probe failed for flash\n");
 			ret = -ENXIO;
@@ -188,7 +188,7 @@ static int __init init_msp_flash(void)
 
 cleanup_loop:
 	while (i--) {
-		del_mtd_partitions(msp_flash[i]);
+		mtd_device_unregister(msp_flash[i]);
 		map_destroy(msp_flash[i]);
 		kfree(msp_maps[i].name);
 		iounmap(msp_maps[i].virt);
@@ -207,7 +207,7 @@ static void __exit cleanup_msp_flash(void)
 	int i;
 
 	for (i = 0; i < fcnt; i++) {
-		del_mtd_partitions(msp_flash[i]);
+		mtd_device_unregister(msp_flash[i]);
 		map_destroy(msp_flash[i]);
 		iounmap((void *)msp_maps[i].virt);
 
diff --git a/drivers/mtd/maps/pxa2xx-flash.c b/drivers/mtd/maps/pxa2xx-flash.c
index d8ae634d347e..f59d62f74d44 100644
--- a/drivers/mtd/maps/pxa2xx-flash.c
+++ b/drivers/mtd/maps/pxa2xx-flash.c
@@ -104,23 +104,18 @@ static int __devinit pxa2xx_flash_probe(struct platform_device *pdev)
 	}
 	info->mtd->owner = THIS_MODULE;
 
-#ifdef CONFIG_MTD_PARTITIONS
 	ret = parse_mtd_partitions(info->mtd, probes, &parts, 0);
 
 	if (ret > 0) {
 		info->nr_parts = ret;
 		info->parts = parts;
 	}
-#endif
 
-	if (info->nr_parts) {
-		add_mtd_partitions(info->mtd, info->parts,
-				   info->nr_parts);
-	} else {
+	if (!info->nr_parts)
 		printk("Registering %s as whole device\n",
 		       info->map.name);
-		add_mtd_device(info->mtd);
-	}
+
+	mtd_device_register(info->mtd, info->parts, info->nr_parts);
 
 	platform_set_drvdata(pdev, info);
 	return 0;
@@ -132,12 +127,7 @@ static int __devexit pxa2xx_flash_remove(struct platform_device *dev)
 
 	platform_set_drvdata(dev, NULL);
 
-#ifdef CONFIG_MTD_PARTITIONS
-	if (info->nr_parts)
-		del_mtd_partitions(info->mtd);
-	else
-#endif
-		del_mtd_device(info->mtd);
+	mtd_device_unregister(info->mtd);
 
 	map_destroy(info->mtd);
 	iounmap(info->map.virt);
diff --git a/drivers/mtd/maps/rbtx4939-flash.c b/drivers/mtd/maps/rbtx4939-flash.c
index 83ed64512c5e..761fb459d2c7 100644
--- a/drivers/mtd/maps/rbtx4939-flash.c
+++ b/drivers/mtd/maps/rbtx4939-flash.c
@@ -25,10 +25,8 @@
 struct rbtx4939_flash_info {
 	struct mtd_info *mtd;
 	struct map_info map;
-#ifdef CONFIG_MTD_PARTITIONS
 	int nr_parts;
 	struct mtd_partition *parts;
-#endif
 };
 
 static int rbtx4939_flash_remove(struct platform_device *dev)
@@ -41,28 +39,18 @@ static int rbtx4939_flash_remove(struct platform_device *dev)
 	platform_set_drvdata(dev, NULL);
 
 	if (info->mtd) {
-#ifdef CONFIG_MTD_PARTITIONS
 		struct rbtx4939_flash_data *pdata = dev->dev.platform_data;
 
-		if (info->nr_parts) {
-			del_mtd_partitions(info->mtd);
+		if (info->nr_parts)
 			kfree(info->parts);
-		} else if (pdata->nr_parts)
-			del_mtd_partitions(info->mtd);
-		else
-			del_mtd_device(info->mtd);
-#else
-		del_mtd_device(info->mtd);
-#endif
+		mtd_device_unregister(info->mtd);
 		map_destroy(info->mtd);
 	}
 	return 0;
 }
 
 static const char *rom_probe_types[] = { "cfi_probe", "jedec_probe", NULL };
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *part_probe_types[] = { "cmdlinepart", NULL };
-#endif
 
 static int rbtx4939_flash_probe(struct platform_device *dev)
 {
@@ -120,23 +108,21 @@ static int rbtx4939_flash_probe(struct platform_device *dev)
 	if (err)
 		goto err_out;
 
-#ifdef CONFIG_MTD_PARTITIONS
 	err = parse_mtd_partitions(info->mtd, part_probe_types,
 				&info->parts, 0);
 	if (err > 0) {
-		add_mtd_partitions(info->mtd, info->parts, err);
+		mtd_device_register(info->mtd, info->parts, err);
 		info->nr_parts = err;
 		return 0;
 	}
 
 	if (pdata->nr_parts) {
 		pr_notice("Using rbtx4939 partition information\n");
-		add_mtd_partitions(info->mtd, pdata->parts, pdata->nr_parts);
+		mtd_device_register(info->mtd, pdata->parts, pdata->nr_parts);
 		return 0;
 	}
-#endif
 
-	add_mtd_device(info->mtd);
+	mtd_device_register(info->mtd, NULL, 0);
 	return 0;
 
 err_out:
diff --git a/drivers/mtd/maps/rpxlite.c b/drivers/mtd/maps/rpxlite.c
index 3e3ef53d4fd4..ed88225bf667 100644
--- a/drivers/mtd/maps/rpxlite.c
+++ b/drivers/mtd/maps/rpxlite.c
@@ -36,7 +36,7 @@ static int __init init_rpxlite(void)
 	mymtd = do_map_probe("cfi_probe", &rpxlite_map);
 	if (mymtd) {
 		mymtd->owner = THIS_MODULE;
-		add_mtd_device(mymtd);
+		mtd_device_register(mymtd, NULL, 0);
 		return 0;
 	}
 
@@ -47,7 +47,7 @@ static int __init init_rpxlite(void)
 static void __exit cleanup_rpxlite(void)
 {
 	if (mymtd) {
-		del_mtd_device(mymtd);
+		mtd_device_unregister(mymtd);
 		map_destroy(mymtd);
 	}
 	if (rpxlite_map.virt) {
diff --git a/drivers/mtd/maps/sa1100-flash.c b/drivers/mtd/maps/sa1100-flash.c
index da875908ea8e..a9b5e0e5c4c5 100644
--- a/drivers/mtd/maps/sa1100-flash.c
+++ b/drivers/mtd/maps/sa1100-flash.c
@@ -226,12 +226,7 @@ static void sa1100_destroy(struct sa_info *info, struct flash_platform_data *pla
 	int i;
 
 	if (info->mtd) {
-		if (info->nr_parts == 0)
-			del_mtd_device(info->mtd);
-#ifdef CONFIG_MTD_PARTITIONS
-		else
-			del_mtd_partitions(info->mtd);
-#endif
+		mtd_device_unregister(info->mtd);
 		if (info->mtd != info->subdev[0].mtd)
 			mtd_concat_destroy(info->mtd);
 	}
@@ -363,28 +358,24 @@ static int __devinit sa1100_mtd_probe(struct platform_device *pdev)
 	/*
 	 * Partition selection stuff.
 	 */
-#ifdef CONFIG_MTD_PARTITIONS
 	nr_parts = parse_mtd_partitions(info->mtd, part_probes, &parts, 0);
 	if (nr_parts > 0) {
 		info->parts = parts;
 		part_type = "dynamic";
-	} else
-#endif
-	{
+	} else {
 		parts = plat->parts;
 		nr_parts = plat->nr_parts;
 		part_type = "static";
 	}
 
-	if (nr_parts == 0) {
+	if (nr_parts == 0)
 		printk(KERN_NOTICE "SA1100 flash: no partition info "
 			"available, registering whole flash\n");
-		add_mtd_device(info->mtd);
-	} else {
+	else
 		printk(KERN_NOTICE "SA1100 flash: using %s partition "
 			"definition\n", part_type);
-		add_mtd_partitions(info->mtd, parts, nr_parts);
-	}
+
+	mtd_device_register(info->mtd, parts, nr_parts);
 
 	info->nr_parts = nr_parts;
 
diff --git a/drivers/mtd/maps/sbc_gxx.c b/drivers/mtd/maps/sbc_gxx.c
index 04b2781fc627..556a2dfe94c5 100644
--- a/drivers/mtd/maps/sbc_gxx.c
+++ b/drivers/mtd/maps/sbc_gxx.c
@@ -182,7 +182,7 @@ static struct mtd_info *all_mtd;
 static void cleanup_sbc_gxx(void)
 {
 	if( all_mtd ) {
-		del_mtd_partitions( all_mtd );
+		mtd_device_unregister(all_mtd);
 		map_destroy( all_mtd );
 	}
 
@@ -223,7 +223,7 @@ static int __init init_sbc_gxx(void)
 	all_mtd->owner = THIS_MODULE;
 
 	/* Create MTD devices for each partition. */
-	add_mtd_partitions(all_mtd, partition_info, NUM_PARTITIONS );
+	mtd_device_register(all_mtd, partition_info, NUM_PARTITIONS);
 
 	return 0;
 }
diff --git a/drivers/mtd/maps/sc520cdp.c b/drivers/mtd/maps/sc520cdp.c
index 4d8aaaf4bb76..8fead8e46bce 100644
--- a/drivers/mtd/maps/sc520cdp.c
+++ b/drivers/mtd/maps/sc520cdp.c
@@ -266,10 +266,10 @@ static int __init init_sc520cdp(void)
 		/* Combine the two flash banks into a single MTD device & register it: */
 		merged_mtd = mtd_concat_create(mymtd, 2, "SC520CDP Flash Banks #0 and #1");
 		if(merged_mtd)
-			add_mtd_device(merged_mtd);
+			mtd_device_register(merged_mtd, NULL, 0);
 	}
 	if(devices_found == 3) /* register the third (DIL-Flash) device */
-		add_mtd_device(mymtd[2]);
+		mtd_device_register(mymtd[2], NULL, 0);
 	return(devices_found ? 0 : -ENXIO);
 }
 
@@ -278,11 +278,11 @@ static void __exit cleanup_sc520cdp(void)
 	int i;
 
 	if (merged_mtd) {
-		del_mtd_device(merged_mtd);
+		mtd_device_unregister(merged_mtd);
 		mtd_concat_destroy(merged_mtd);
 	}
 	if (mymtd[2])
-		del_mtd_device(mymtd[2]);
+		mtd_device_unregister(mymtd[2]);
 
 	for (i = 0; i < NUM_FLASH_BANKS; i++) {
 		if (mymtd[i])
diff --git a/drivers/mtd/maps/scb2_flash.c b/drivers/mtd/maps/scb2_flash.c
index 7e329f09a548..d88c8426bb0f 100644
--- a/drivers/mtd/maps/scb2_flash.c
+++ b/drivers/mtd/maps/scb2_flash.c
@@ -180,7 +180,7 @@ scb2_flash_probe(struct pci_dev *dev, const struct pci_device_id *ent)
 
 	scb2_mtd->owner = THIS_MODULE;
 	if (scb2_fixup_mtd(scb2_mtd) < 0) {
-		del_mtd_device(scb2_mtd);
+		mtd_device_unregister(scb2_mtd);
 		map_destroy(scb2_mtd);
 		iounmap(scb2_ioaddr);
 		if (!region_fail)
@@ -192,7 +192,7 @@ scb2_flash_probe(struct pci_dev *dev, const struct pci_device_id *ent)
 	       (unsigned long long)scb2_mtd->size,
 	       (unsigned long long)(SCB2_WINDOW - scb2_mtd->size));
 
-	add_mtd_device(scb2_mtd);
+	mtd_device_register(scb2_mtd, NULL, 0);
 
 	return 0;
 }
@@ -207,7 +207,7 @@ scb2_flash_remove(struct pci_dev *dev)
 	if (scb2_mtd->lock)
 		scb2_mtd->lock(scb2_mtd, 0, scb2_mtd->size);
 
-	del_mtd_device(scb2_mtd);
+	mtd_device_unregister(scb2_mtd);
 	map_destroy(scb2_mtd);
 
 	iounmap(scb2_ioaddr);
diff --git a/drivers/mtd/maps/scx200_docflash.c b/drivers/mtd/maps/scx200_docflash.c
index 027e628a4f1d..f1c1f737d0d7 100644
--- a/drivers/mtd/maps/scx200_docflash.c
+++ b/drivers/mtd/maps/scx200_docflash.c
@@ -44,7 +44,6 @@ static struct resource docmem = {
 
 static struct mtd_info *mymtd;
 
-#ifdef CONFIG_MTD_PARTITIONS
 static struct mtd_partition partition_info[] = {
 	{
 		.name   = "DOCCS Boot kernel",
@@ -68,8 +67,6 @@ static struct mtd_partition partition_info[] = {
 	},
 };
 #define NUM_PARTITIONS ARRAY_SIZE(partition_info)
-#endif
-
 
 static struct map_info scx200_docflash_map = {
 	.name      = "NatSemi SCx200 DOCCS Flash",
@@ -198,24 +195,17 @@ static int __init init_scx200_docflash(void)
 
 	mymtd->owner = THIS_MODULE;
 
-#ifdef CONFIG_MTD_PARTITIONS
 	partition_info[3].offset = mymtd->size-partition_info[3].size;
 	partition_info[2].size = partition_info[3].offset-partition_info[2].offset;
-	add_mtd_partitions(mymtd, partition_info, NUM_PARTITIONS);
-#else
-	add_mtd_device(mymtd);
-#endif
+	mtd_device_register(mymtd, partition_info, NUM_PARTITIONS);
+
 	return 0;
 }
 
 static void __exit cleanup_scx200_docflash(void)
 {
 	if (mymtd) {
-#ifdef CONFIG_MTD_PARTITIONS
-		del_mtd_partitions(mymtd);
-#else
-		del_mtd_device(mymtd);
-#endif
+		mtd_device_unregister(mymtd);
 		map_destroy(mymtd);
 	}
 	if (scx200_docflash_map.virt) {
diff --git a/drivers/mtd/maps/solutionengine.c b/drivers/mtd/maps/solutionengine.c
index 0eb41d9c6786..cbf6bade9354 100644
--- a/drivers/mtd/maps/solutionengine.c
+++ b/drivers/mtd/maps/solutionengine.c
@@ -89,7 +89,7 @@ static int __init init_soleng_maps(void)
 	eprom_mtd = do_map_probe("map_rom", &soleng_eprom_map);
 	if (eprom_mtd) {
 		eprom_mtd->owner = THIS_MODULE;
-		add_mtd_device(eprom_mtd);
+		mtd_device_register(eprom_mtd, NULL, 0);
 	}
 
 	nr_parts = parse_mtd_partitions(flash_mtd, probes, &parsed_parts, 0);
@@ -104,9 +104,9 @@ static int __init init_soleng_maps(void)
 #endif /* CONFIG_MTD_SUPERH_RESERVE */
 
 	if (nr_parts > 0)
-		add_mtd_partitions(flash_mtd, parsed_parts, nr_parts);
+		mtd_device_register(flash_mtd, parsed_parts, nr_parts);
 	else
-		add_mtd_device(flash_mtd);
+		mtd_device_register(flash_mtd, NULL, 0);
 
 	return 0;
 }
@@ -114,14 +114,14 @@ static int __init init_soleng_maps(void)
 static void __exit cleanup_soleng_maps(void)
 {
 	if (eprom_mtd) {
-		del_mtd_device(eprom_mtd);
+		mtd_device_unregister(eprom_mtd);
 		map_destroy(eprom_mtd);
 	}
 
 	if (parsed_parts)
-		del_mtd_partitions(flash_mtd);
+		mtd_device_unregister(flash_mtd);
 	else
-		del_mtd_device(flash_mtd);
+		mtd_device_unregister(flash_mtd);
 	map_destroy(flash_mtd);
 }
 
diff --git a/drivers/mtd/maps/sun_uflash.c b/drivers/mtd/maps/sun_uflash.c
index 3f1cb328a574..2d66234f57cb 100644
--- a/drivers/mtd/maps/sun_uflash.c
+++ b/drivers/mtd/maps/sun_uflash.c
@@ -101,7 +101,7 @@ int uflash_devinit(struct platform_device *op, struct device_node *dp)
 
 	up->mtd->owner = THIS_MODULE;
 
-	add_mtd_device(up->mtd);
+	mtd_device_register(up->mtd, NULL, 0);
 
 	dev_set_drvdata(&op->dev, up);
 
@@ -126,7 +126,7 @@ static int __devexit uflash_remove(struct platform_device *op)
 	struct uflash_dev *up = dev_get_drvdata(&op->dev);
 
 	if (up->mtd) {
-		del_mtd_device(up->mtd);
+		mtd_device_unregister(up->mtd);
 		map_destroy(up->mtd);
 	}
 	if (up->map.virt) {
diff --git a/drivers/mtd/maps/tqm8xxl.c b/drivers/mtd/maps/tqm8xxl.c
index 0718dfb3ee64..d78587990e7e 100644
--- a/drivers/mtd/maps/tqm8xxl.c
+++ b/drivers/mtd/maps/tqm8xxl.c
@@ -62,7 +62,6 @@ static void __iomem *start_scan_addr;
  * "struct map_desc *_io_desc" for the corresponding machine.
  */
 
-#ifdef CONFIG_MTD_PARTITIONS
 /* Currently, TQM8xxL has up to 8MiB flash */
 static unsigned long tqm8xxl_max_flash_size = 0x00800000;
 
@@ -107,7 +106,6 @@ static struct mtd_partition tqm8xxl_fs_partitions[] = {
 	  //.size = MTDPART_SIZ_FULL,
 	}
 };
-#endif
 
 static int __init init_tqm_mtd(void)
 {
@@ -188,7 +186,6 @@ static int __init init_tqm_mtd(void)
 		goto error_mem;
 	}
 
-#ifdef CONFIG_MTD_PARTITIONS
 	/*
 	 * Select Static partition definitions
 	 */
@@ -201,21 +198,14 @@ static int __init init_tqm_mtd(void)
 	part_banks[1].nums = ARRAY_SIZE(tqm8xxl_fs_partitions);
 
 	for(idx = 0; idx < num_banks ; idx++) {
-		if (part_banks[idx].nums == 0) {
+		if (part_banks[idx].nums == 0)
 			printk(KERN_NOTICE "TQM flash%d: no partition info available, registering whole flash at once\n", idx);
-			add_mtd_device(mtd_banks[idx]);
-		} else {
+		else
 			printk(KERN_NOTICE "TQM flash%d: Using %s partition definition\n",
 					idx, part_banks[idx].type);
-			add_mtd_partitions(mtd_banks[idx], part_banks[idx].mtd_part,
-								part_banks[idx].nums);
-		}
+		mtd_device_register(mtd_banks[idx], part_banks[idx].mtd_part,
+		part_banks[idx].nums);
 	}
-#else
-	printk(KERN_NOTICE "TQM flash: registering %d whole flash banks at once\n", num_banks);
-	for(idx = 0 ; idx < num_banks ; idx++)
-		add_mtd_device(mtd_banks[idx]);
-#endif
 	return 0;
 error_mem:
 	for(idx = 0 ; idx < FLASH_BANK_MAX ; idx++) {
@@ -237,7 +227,7 @@ static void __exit cleanup_tqm_mtd(void)
 	for(idx = 0 ; idx < num_banks ; idx++) {
 		/* destroy mtd_info previously allocated */
 		if (mtd_banks[idx]) {
-			del_mtd_partitions(mtd_banks[idx]);
+			mtd_device_unregister(mtd_banks[idx]);
 			map_destroy(mtd_banks[idx]);
 		}
 		/* release map_info not used anymore */
diff --git a/drivers/mtd/maps/ts5500_flash.c b/drivers/mtd/maps/ts5500_flash.c
index e02dfa9d4ddd..d1d671daf235 100644
--- a/drivers/mtd/maps/ts5500_flash.c
+++ b/drivers/mtd/maps/ts5500_flash.c
@@ -89,7 +89,7 @@ static int __init init_ts5500_map(void)
 	}
 
 	mymtd->owner = THIS_MODULE;
-	add_mtd_partitions(mymtd, ts5500_partitions, NUM_PARTITIONS);
+	mtd_device_register(mymtd, ts5500_partitions, NUM_PARTITIONS);
 
 	return 0;
 
@@ -102,7 +102,7 @@ err2:
 static void __exit cleanup_ts5500_map(void)
 {
 	if (mymtd) {
-		del_mtd_partitions(mymtd);
+		mtd_device_unregister(mymtd);
 		map_destroy(mymtd);
 	}
 
diff --git a/drivers/mtd/maps/tsunami_flash.c b/drivers/mtd/maps/tsunami_flash.c
index 77a8bfc02577..1de390e1c2fb 100644
--- a/drivers/mtd/maps/tsunami_flash.c
+++ b/drivers/mtd/maps/tsunami_flash.c
@@ -76,7 +76,7 @@ static void __exit  cleanup_tsunami_flash(void)
 	struct mtd_info *mtd;
 	mtd = tsunami_flash_mtd;
 	if (mtd) {
-		del_mtd_device(mtd);
+		mtd_device_unregister(mtd);
 		map_destroy(mtd);
 	}
 	tsunami_flash_mtd = 0;
@@ -97,7 +97,7 @@ static int __init init_tsunami_flash(void)
 	}
 	if (tsunami_flash_mtd) {
 		tsunami_flash_mtd->owner = THIS_MODULE;
-		add_mtd_device(tsunami_flash_mtd);
+		mtd_device_register(tsunami_flash_mtd, NULL, 0);
 		return 0;
 	}
 	return -ENXIO;
diff --git a/drivers/mtd/maps/uclinux.c b/drivers/mtd/maps/uclinux.c
index 35009294b435..6793074f3f40 100644
--- a/drivers/mtd/maps/uclinux.c
+++ b/drivers/mtd/maps/uclinux.c
@@ -89,11 +89,7 @@ static int __init uclinux_mtd_init(void)
 	mtd->priv = mapp;
 
 	uclinux_ram_mtdinfo = mtd;
-#ifdef CONFIG_MTD_PARTITIONS
-	add_mtd_partitions(mtd, uclinux_romfs, NUM_PARTITIONS);
-#else
-	add_mtd_device(mtd);
-#endif
+	mtd_device_register(mtd, uclinux_romfs, NUM_PARTITIONS);
 
 	return(0);
 }
@@ -103,11 +99,7 @@ static int __init uclinux_mtd_init(void)
 static void __exit uclinux_mtd_cleanup(void)
 {
 	if (uclinux_ram_mtdinfo) {
-#ifdef CONFIG_MTD_PARTITIONS
-		del_mtd_partitions(uclinux_ram_mtdinfo);
-#else
-		del_mtd_device(uclinux_ram_mtdinfo);
-#endif
+		mtd_device_unregister(uclinux_ram_mtdinfo);
 		map_destroy(uclinux_ram_mtdinfo);
 		uclinux_ram_mtdinfo = NULL;
 	}
diff --git a/drivers/mtd/maps/vmax301.c b/drivers/mtd/maps/vmax301.c
index 6adaa6acc193..5e68de73eabc 100644
--- a/drivers/mtd/maps/vmax301.c
+++ b/drivers/mtd/maps/vmax301.c
@@ -138,7 +138,7 @@ static void __exit cleanup_vmax301(void)
 
 	for (i=0; i<2; i++) {
 		if (vmax_mtd[i]) {
-			del_mtd_device(vmax_mtd[i]);
+			mtd_device_unregister(vmax_mtd[i]);
 			map_destroy(vmax_mtd[i]);
 		}
 	}
@@ -176,7 +176,7 @@ static int __init init_vmax301(void)
 			vmax_mtd[i] = do_map_probe("map_rom", &vmax_map[i]);
 		if (vmax_mtd[i]) {
 			vmax_mtd[i]->owner = THIS_MODULE;
-			add_mtd_device(vmax_mtd[i]);
+			mtd_device_register(vmax_mtd[i], NULL, 0);
 		}
 	}
 
diff --git a/drivers/mtd/maps/vmu-flash.c b/drivers/mtd/maps/vmu-flash.c
index 4afc167731ef..3a04b078576a 100644
--- a/drivers/mtd/maps/vmu-flash.c
+++ b/drivers/mtd/maps/vmu-flash.c
@@ -563,7 +563,7 @@ static void vmu_queryblocks(struct mapleq *mq)
 		goto fail_cache_create;
 	part_cur->pcache = pcache;
 
-	error = add_mtd_device(mtd_cur);
+	error = mtd_device_register(mtd_cur, NULL, 0);
 	if (error)
 		goto fail_mtd_register;
 
@@ -709,7 +709,7 @@ static void __devexit vmu_disconnect(struct maple_device *mdev)
 	for (x = 0; x < card->partitions; x++) {
 		mpart = ((card->mtd)[x]).priv;
 		mpart->mdev = NULL;
-		del_mtd_device(&((card->mtd)[x]));
+		mtd_device_unregister(&((card->mtd)[x]));
 		kfree(((card->parts)[x]).name);
 	}
 	kfree(card->parts);
diff --git a/drivers/mtd/maps/wr_sbc82xx_flash.c b/drivers/mtd/maps/wr_sbc82xx_flash.c
index 933a2b6598b4..901ce968efae 100644
--- a/drivers/mtd/maps/wr_sbc82xx_flash.c
+++ b/drivers/mtd/maps/wr_sbc82xx_flash.c
@@ -132,17 +132,20 @@ static int __init init_sbc82xx_flash(void)
 		nr_parts = parse_mtd_partitions(sbcmtd[i], part_probes,
 						&sbcmtd_parts[i], 0);
 		if (nr_parts > 0) {
-			add_mtd_partitions (sbcmtd[i], sbcmtd_parts[i], nr_parts);
+			mtd_device_register(sbcmtd[i], sbcmtd_parts[i],
+					    nr_parts);
 			continue;
 		}
 
 		/* No partitioning detected. Use default */
 		if (i == 2) {
-			add_mtd_device(sbcmtd[i]);
+			mtd_device_register(sbcmtd[i], NULL, 0);
 		} else if (i == bigflash) {
-			add_mtd_partitions (sbcmtd[i], bigflash_parts, ARRAY_SIZE(bigflash_parts));
+			mtd_device_register(sbcmtd[i], bigflash_parts,
+					    ARRAY_SIZE(bigflash_parts));
 		} else {
-			add_mtd_partitions (sbcmtd[i], smallflash_parts, ARRAY_SIZE(smallflash_parts));
+			mtd_device_register(sbcmtd[i], smallflash_parts,
+					    ARRAY_SIZE(smallflash_parts));
 		}
 	}
 	return 0;
@@ -157,9 +160,9 @@ static void __exit cleanup_sbc82xx_flash(void)
 			continue;
 
 		if (i<2 || sbcmtd_parts[i])
-			del_mtd_partitions(sbcmtd[i]);
+			mtd_device_unregister(sbcmtd[i]);
 		else
-			del_mtd_device(sbcmtd[i]);
+			mtd_device_unregister(sbcmtd[i]);
 
 		kfree(sbcmtd_parts[i]);
 		map_destroy(sbcmtd[i]);
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index a534e1f0c348..ca385697446e 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -221,15 +221,33 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode)
 	kref_get(&dev->ref);
 	__module_get(dev->tr->owner);
 
-	if (dev->mtd) {
-		ret = dev->tr->open ? dev->tr->open(dev) : 0;
-		__get_mtd_device(dev->mtd);
+	if (!dev->mtd)
+		goto unlock;
+
+	if (dev->tr->open) {
+		ret = dev->tr->open(dev);
+		if (ret)
+			goto error_put;
 	}
 
+	ret = __get_mtd_device(dev->mtd);
+	if (ret)
+		goto error_release;
+
 unlock:
 	mutex_unlock(&dev->lock);
 	blktrans_dev_put(dev);
 	return ret;
+
+error_release:
+	if (dev->tr->release)
+		dev->tr->release(dev);
+error_put:
+	module_put(dev->tr->owner);
+	kref_put(&dev->ref, blktrans_dev_release);
+	mutex_unlock(&dev->lock);
+	blktrans_dev_put(dev);
+	return ret;
 }
 
 static int blktrans_release(struct gendisk *disk, fmode_t mode)
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 4c36ef66a46b..3f92731a5b9e 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -166,10 +166,23 @@ static int mtd_close(struct inode *inode, struct file *file)
 	return 0;
 } /* mtd_close */
 
-/* FIXME: This _really_ needs to die. In 2.5, we should lock the
-   userspace buffer down and use it directly with readv/writev.
-*/
-#define MAX_KMALLOC_SIZE 0x20000
+/* Back in June 2001, dwmw2 wrote:
+ *
+ *   FIXME: This _really_ needs to die. In 2.5, we should lock the
+ *   userspace buffer down and use it directly with readv/writev.
+ *
+ * The implementation below, using mtd_kmalloc_up_to, mitigates
+ * allocation failures when the system is under low-memory situations
+ * or if memory is highly fragmented at the cost of reducing the
+ * performance of the requested transfer due to a smaller buffer size.
+ *
+ * A more complex but more memory-efficient implementation based on
+ * get_user_pages and iovecs to cover extents of those pages is a
+ * longer-term goal, as intimated by dwmw2 above. However, for the
+ * write case, this requires yet more complex head and tail transfer
+ * handling when those head and tail offsets and sizes are such that
+ * alignment requirements are not met in the NAND subdriver.
+ */
 
 static ssize_t mtd_read(struct file *file, char __user *buf, size_t count,loff_t *ppos)
 {
@@ -179,6 +192,7 @@ static ssize_t mtd_read(struct file *file, char __user *buf, size_t count,loff_t
 	size_t total_retlen=0;
 	int ret=0;
 	int len;
+	size_t size = count;
 	char *kbuf;
 
 	DEBUG(MTD_DEBUG_LEVEL0,"MTD_read\n");
@@ -189,23 +203,12 @@ static ssize_t mtd_read(struct file *file, char __user *buf, size_t count,loff_t
 	if (!count)
 		return 0;
 
-	/* FIXME: Use kiovec in 2.5 to lock down the user's buffers
-	   and pass them directly to the MTD functions */
-
-	if (count > MAX_KMALLOC_SIZE)
-		kbuf=kmalloc(MAX_KMALLOC_SIZE, GFP_KERNEL);
-	else
-		kbuf=kmalloc(count, GFP_KERNEL);
-
+	kbuf = mtd_kmalloc_up_to(mtd, &size);
 	if (!kbuf)
 		return -ENOMEM;
 
 	while (count) {
-
-		if (count > MAX_KMALLOC_SIZE)
-			len = MAX_KMALLOC_SIZE;
-		else
-			len = count;
+		len = min_t(size_t, count, size);
 
 		switch (mfi->mode) {
 		case MTD_MODE_OTP_FACTORY:
@@ -268,6 +271,7 @@ static ssize_t mtd_write(struct file *file, const char __user *buf, size_t count
 {
 	struct mtd_file_info *mfi = file->private_data;
 	struct mtd_info *mtd = mfi->mtd;
+	size_t size = count;
 	char *kbuf;
 	size_t retlen;
 	size_t total_retlen=0;
@@ -285,20 +289,12 @@ static ssize_t mtd_write(struct file *file, const char __user *buf, size_t count
 	if (!count)
 		return 0;
 
-	if (count > MAX_KMALLOC_SIZE)
-		kbuf=kmalloc(MAX_KMALLOC_SIZE, GFP_KERNEL);
-	else
-		kbuf=kmalloc(count, GFP_KERNEL);
-
+	kbuf = mtd_kmalloc_up_to(mtd, &size);
 	if (!kbuf)
 		return -ENOMEM;
 
 	while (count) {
-
-		if (count > MAX_KMALLOC_SIZE)
-			len = MAX_KMALLOC_SIZE;
-		else
-			len = count;
+		len = min_t(size_t, count, size);
 
 		if (copy_from_user(kbuf, buf, len)) {
 			kfree(kbuf);
@@ -512,7 +508,6 @@ static int shrink_ecclayout(const struct nand_ecclayout *from,
 	return 0;
 }
 
-#ifdef CONFIG_MTD_PARTITIONS
 static int mtd_blkpg_ioctl(struct mtd_info *mtd,
 			   struct blkpg_ioctl_arg __user *arg)
 {
@@ -548,8 +543,6 @@ static int mtd_blkpg_ioctl(struct mtd_info *mtd,
 		return -EINVAL;
 	}
 }
-#endif
-
 
 static int mtd_ioctl(struct file *file, u_int cmd, u_long arg)
 {
@@ -941,7 +934,6 @@ static int mtd_ioctl(struct file *file, u_int cmd, u_long arg)
 		break;
 	}
 
-#ifdef CONFIG_MTD_PARTITIONS
 	case BLKPG:
 	{
 		ret = mtd_blkpg_ioctl(mtd,
@@ -955,7 +947,6 @@ static int mtd_ioctl(struct file *file, u_int cmd, u_long arg)
 		ret = 0;
 		break;
 	}
-#endif
 
 	default:
 		ret = -ENOTTY;
diff --git a/drivers/mtd/mtdconcat.c b/drivers/mtd/mtdconcat.c
index 5060e608ea5d..e601672a5305 100644
--- a/drivers/mtd/mtdconcat.c
+++ b/drivers/mtd/mtdconcat.c
@@ -319,7 +319,7 @@ concat_write_oob(struct mtd_info *mtd, loff_t to, struct mtd_oob_ops *ops)
 	if (!(mtd->flags & MTD_WRITEABLE))
 		return -EROFS;
 
-	ops->retlen = 0;
+	ops->retlen = ops->oobretlen = 0;
 
 	for (i = 0; i < concat->num_subdev; i++) {
 		struct mtd_info *subdev = concat->subdev[i];
@@ -334,7 +334,7 @@ concat_write_oob(struct mtd_info *mtd, loff_t to, struct mtd_oob_ops *ops)
 			devops.len = subdev->size - to;
 
 		err = subdev->write_oob(subdev, to, &devops);
-		ops->retlen += devops.retlen;
+		ops->retlen += devops.oobretlen;
 		if (err)
 			return err;
 
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index da69bc8a5a7d..c510aff289a8 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/ptrace.h>
+#include <linux/seq_file.h>
 #include <linux/string.h>
 #include <linux/timer.h>
 #include <linux/major.h>
@@ -37,6 +38,7 @@
 #include <linux/gfp.h>
 
 #include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
 
 #include "mtdcore.h"
 /*
@@ -391,7 +393,7 @@ fail_locked:
  *	if the requested device does not appear to be present in the list.
  */
 
-int del_mtd_device (struct mtd_info *mtd)
+int del_mtd_device(struct mtd_info *mtd)
 {
 	int ret;
 	struct mtd_notifier *not;
@@ -427,6 +429,50 @@ out_error:
 }
 
 /**
+ * mtd_device_register - register an MTD device.
+ *
+ * @master: the MTD device to register
+ * @parts: the partitions to register - only valid if nr_parts > 0
+ * @nr_parts: the number of partitions in parts.  If zero then the full MTD
+ *            device is registered
+ *
+ * Register an MTD device with the system and optionally, a number of
+ * partitions.  If nr_parts is 0 then the whole device is registered, otherwise
+ * only the partitions are registered.  To register both the full device *and*
+ * the partitions, call mtd_device_register() twice, once with nr_parts == 0
+ * and once equal to the number of partitions.
+ */
+int mtd_device_register(struct mtd_info *master,
+			const struct mtd_partition *parts,
+			int nr_parts)
+{
+	return parts ? add_mtd_partitions(master, parts, nr_parts) :
+		add_mtd_device(master);
+}
+EXPORT_SYMBOL_GPL(mtd_device_register);
+
+/**
+ * mtd_device_unregister - unregister an existing MTD device.
+ *
+ * @master: the MTD device to unregister.  This will unregister both the master
+ *          and any partitions if registered.
+ */
+int mtd_device_unregister(struct mtd_info *master)
+{
+	int err;
+
+	err = del_mtd_partitions(master);
+	if (err)
+		return err;
+
+	if (!device_is_registered(&master->dev))
+		return 0;
+
+	return del_mtd_device(master);
+}
+EXPORT_SYMBOL_GPL(mtd_device_unregister);
+
+/**
  *	register_mtd_user - register a 'user' of MTD devices.
  *	@new: pointer to notifier info structure
  *
@@ -443,7 +489,7 @@ void register_mtd_user (struct mtd_notifier *new)
 
 	list_add(&new->list, &mtd_notifiers);
 
- 	__module_get(THIS_MODULE);
+	__module_get(THIS_MODULE);
 
 	mtd_for_each_device(mtd)
 		new->add(mtd);
@@ -532,7 +578,6 @@ int __get_mtd_device(struct mtd_info *mtd)
 		return -ENODEV;
 
 	if (mtd->get_device) {
-
 		err = mtd->get_device(mtd);
 
 		if (err) {
@@ -570,21 +615,13 @@ struct mtd_info *get_mtd_device_nm(const char *name)
 	if (!mtd)
 		goto out_unlock;
 
-	if (!try_module_get(mtd->owner))
+	err = __get_mtd_device(mtd);
+	if (err)
 		goto out_unlock;
 
-	if (mtd->get_device) {
-		err = mtd->get_device(mtd);
-		if (err)
-			goto out_put;
-	}
-
-	mtd->usecount++;
 	mutex_unlock(&mtd_table_mutex);
 	return mtd;
 
-out_put:
-	module_put(mtd->owner);
 out_unlock:
 	mutex_unlock(&mtd_table_mutex);
 	return ERR_PTR(err);
@@ -638,8 +675,54 @@ int default_mtd_writev(struct mtd_info *mtd, const struct kvec *vecs,
 	return ret;
 }
 
-EXPORT_SYMBOL_GPL(add_mtd_device);
-EXPORT_SYMBOL_GPL(del_mtd_device);
+/**
+ * mtd_kmalloc_up_to - allocate a contiguous buffer up to the specified size
+ * @size: A pointer to the ideal or maximum size of the allocation. Points
+ *        to the actual allocation size on success.
+ *
+ * This routine attempts to allocate a contiguous kernel buffer up to
+ * the specified size, backing off the size of the request exponentially
+ * until the request succeeds or until the allocation size falls below
+ * the system page size. This attempts to make sure it does not adversely
+ * impact system performance, so when allocating more than one page, we
+ * ask the memory allocator to avoid re-trying, swapping, writing back
+ * or performing I/O.
+ *
+ * Note, this function also makes sure that the allocated buffer is aligned to
+ * the MTD device's min. I/O unit, i.e. the "mtd->writesize" value.
+ *
+ * This is called, for example by mtd_{read,write} and jffs2_scan_medium,
+ * to handle smaller (i.e. degraded) buffer allocations under low- or
+ * fragmented-memory situations where such reduced allocations, from a
+ * requested ideal, are allowed.
+ *
+ * Returns a pointer to the allocated buffer on success; otherwise, NULL.
+ */
+void *mtd_kmalloc_up_to(const struct mtd_info *mtd, size_t *size)
+{
+	gfp_t flags = __GFP_NOWARN | __GFP_WAIT |
+		       __GFP_NORETRY | __GFP_NO_KSWAPD;
+	size_t min_alloc = max_t(size_t, mtd->writesize, PAGE_SIZE);
+	void *kbuf;
+
+	*size = min_t(size_t, *size, KMALLOC_MAX_SIZE);
+
+	while (*size > min_alloc) {
+		kbuf = kmalloc(*size, flags);
+		if (kbuf)
+			return kbuf;
+
+		*size >>= 1;
+		*size = ALIGN(*size, mtd->writesize);
+	}
+
+	/*
+	 * For the last resort allocation allow 'kmalloc()' to do all sorts of
+	 * things (write-back, dropping caches, etc) by using GFP_KERNEL.
+	 */
+	return kmalloc(*size, GFP_KERNEL);
+}
+
 EXPORT_SYMBOL_GPL(get_mtd_device);
 EXPORT_SYMBOL_GPL(get_mtd_device_nm);
 EXPORT_SYMBOL_GPL(__get_mtd_device);
@@ -648,6 +731,7 @@ EXPORT_SYMBOL_GPL(__put_mtd_device);
 EXPORT_SYMBOL_GPL(register_mtd_user);
 EXPORT_SYMBOL_GPL(unregister_mtd_user);
 EXPORT_SYMBOL_GPL(default_mtd_writev);
+EXPORT_SYMBOL_GPL(mtd_kmalloc_up_to);
 
 #ifdef CONFIG_PROC_FS
 
@@ -656,44 +740,32 @@ EXPORT_SYMBOL_GPL(default_mtd_writev);
 
 static struct proc_dir_entry *proc_mtd;
 
-static inline int mtd_proc_info(char *buf, struct mtd_info *this)
-{
-	return sprintf(buf, "mtd%d: %8.8llx %8.8x \"%s\"\n", this->index,
-		       (unsigned long long)this->size,
-		       this->erasesize, this->name);
-}
-
-static int mtd_read_proc (char *page, char **start, off_t off, int count,
-			  int *eof, void *data_unused)
+static int mtd_proc_show(struct seq_file *m, void *v)
 {
 	struct mtd_info *mtd;
-	int len, l;
-        off_t   begin = 0;
 
+	seq_puts(m, "dev:    size   erasesize  name\n");
 	mutex_lock(&mtd_table_mutex);
-
-	len = sprintf(page, "dev:    size   erasesize  name\n");
 	mtd_for_each_device(mtd) {
-		l = mtd_proc_info(page + len, mtd);
-                len += l;
-                if (len+begin > off+count)
-                        goto done;
-                if (len+begin < off) {
-                        begin += len;
-                        len = 0;
-                }
-        }
-
-        *eof = 1;
-
-done:
+		seq_printf(m, "mtd%d: %8.8llx %8.8x \"%s\"\n",
+			   mtd->index, (unsigned long long)mtd->size,
+			   mtd->erasesize, mtd->name);
+	}
 	mutex_unlock(&mtd_table_mutex);
-        if (off >= len+begin)
-                return 0;
-        *start = page + (off-begin);
-        return ((count < begin+len-off) ? count : begin+len-off);
+	return 0;
+}
+
+static int mtd_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mtd_proc_show, NULL);
 }
 
+static const struct file_operations mtd_proc_ops = {
+	.open		= mtd_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
 #endif /* CONFIG_PROC_FS */
 
 /*====================================================================*/
@@ -734,8 +806,7 @@ static int __init init_mtd(void)
 		goto err_bdi3;
 
 #ifdef CONFIG_PROC_FS
-	if ((proc_mtd = create_proc_entry( "mtd", 0, NULL )))
-		proc_mtd->read_proc = mtd_read_proc;
+	proc_mtd = proc_create("mtd", 0, NULL, &mtd_proc_ops);
 #endif /* CONFIG_PROC_FS */
 	return 0;
 
@@ -753,7 +824,7 @@ err_reg:
 static void __exit cleanup_mtd(void)
 {
 #ifdef CONFIG_PROC_FS
-        if (proc_mtd)
+	if (proc_mtd)
 		remove_proc_entry( "mtd", NULL);
 #endif /* CONFIG_PROC_FS */
 	class_unregister(&mtd_class);
diff --git a/drivers/mtd/mtdcore.h b/drivers/mtd/mtdcore.h
index 6a64fdebc898..0ed6126b4c1f 100644
--- a/drivers/mtd/mtdcore.h
+++ b/drivers/mtd/mtdcore.h
@@ -10,6 +10,12 @@
 extern struct mutex mtd_table_mutex;
 extern struct mtd_info *__mtd_next_device(int i);
 
+extern int add_mtd_device(struct mtd_info *mtd);
+extern int del_mtd_device(struct mtd_info *mtd);
+extern int add_mtd_partitions(struct mtd_info *, const struct mtd_partition *,
+			      int);
+extern int del_mtd_partitions(struct mtd_info *);
+
 #define mtd_for_each_device(mtd)			\
 	for ((mtd) = __mtd_next_device(0);		\
 	     (mtd) != NULL;				\
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index 0a4760174782..630be3e7da04 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -31,6 +31,8 @@
 #include <linux/mtd/partitions.h>
 #include <linux/err.h>
 
+#include "mtdcore.h"
+
 /* Our partition linked list */
 static LIST_HEAD(mtd_partitions);
 static DEFINE_MUTEX(mtd_partitions_mutex);
@@ -376,7 +378,6 @@ int del_mtd_partitions(struct mtd_info *master)
 
 	return err;
 }
-EXPORT_SYMBOL(del_mtd_partitions);
 
 static struct mtd_part *allocate_partition(struct mtd_info *master,
 			const struct mtd_partition *part, int partno,
@@ -671,7 +672,6 @@ int add_mtd_partitions(struct mtd_info *master,
 
 	return 0;
 }
-EXPORT_SYMBOL(add_mtd_partitions);
 
 static DEFINE_SPINLOCK(part_parser_lock);
 static LIST_HEAD(part_parsers);
@@ -722,11 +722,8 @@ int parse_mtd_partitions(struct mtd_info *master, const char **types,
 		parser = get_partition_parser(*types);
 		if (!parser && !request_module("%s", *types))
 				parser = get_partition_parser(*types);
-		if (!parser) {
-			printk(KERN_NOTICE "%s partition parsing not available\n",
-			       *types);
+		if (!parser)
 			continue;
-		}
 		ret = (*parser->parse_fn)(master, pparts, origin);
 		if (ret > 0) {
 			printk(KERN_NOTICE "%d %s partitions found on MTD device %s\n",
diff --git a/drivers/mtd/mtdswap.c b/drivers/mtd/mtdswap.c
index fed215c4cfa1..fd7885327611 100644
--- a/drivers/mtd/mtdswap.c
+++ b/drivers/mtd/mtdswap.c
@@ -1450,7 +1450,13 @@ static void mtdswap_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd)
 	}
 
 	oinfo = mtd->ecclayout;
-	if (!mtd->oobsize || !oinfo || oinfo->oobavail < MTDSWAP_OOBSIZE) {
+	if (!oinfo) {
+		printk(KERN_ERR "%s: mtd%d does not have OOB\n",
+			MTDSWAP_PREFIX, mtd->index);
+		return;
+	}
+
+	if (!mtd->oobsize || oinfo->oobavail < MTDSWAP_OOBSIZE) {
 		printk(KERN_ERR "%s: Not enough free bytes in OOB, "
 			"%d available, %zu needed.\n",
 			MTDSWAP_PREFIX, oinfo->oobavail, MTDSWAP_OOBSIZE);
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index edec457d361d..4c3425235adc 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -92,7 +92,7 @@ config MTD_NAND_EDB7312
 
 config MTD_NAND_H1900
 	tristate "iPAQ H1900 flash"
-	depends on ARCH_PXA && MTD_PARTITIONS
+	depends on ARCH_PXA
 	help
 	  This enables the driver for the iPAQ h1900 flash.
 
@@ -419,7 +419,6 @@ config MTD_NAND_TMIO
 
 config MTD_NAND_NANDSIM
 	tristate "Support for NAND Flash Simulator"
-	depends on MTD_PARTITIONS
 	help
 	  The simulator may simulate various NAND flash chips for the
 	  MTD nand layer.
@@ -513,7 +512,7 @@ config MTD_NAND_SOCRATES
 
 config MTD_NAND_NUC900
 	tristate "Support for NAND on Nuvoton NUC9xx/w90p910 evaluation boards."
-	depends on ARCH_W90X900 && MTD_PARTITIONS
+	depends on ARCH_W90X900
 	help
 	  This enables the driver for the NAND Flash on evaluation board based
 	  on w90p910 / NUC9xx.
diff --git a/drivers/mtd/nand/alauda.c b/drivers/mtd/nand/alauda.c
index 8691e0482ed2..eb40ea829ab2 100644
--- a/drivers/mtd/nand/alauda.c
+++ b/drivers/mtd/nand/alauda.c
@@ -120,7 +120,7 @@ static void alauda_delete(struct kref *kref)
 	struct alauda *al = container_of(kref, struct alauda, kref);
 
 	if (al->mtd) {
-		del_mtd_device(al->mtd);
+		mtd_device_unregister(al->mtd);
 		kfree(al->mtd);
 	}
 	usb_put_dev(al->dev);
@@ -592,7 +592,7 @@ static int alauda_init_media(struct alauda *al)
 	mtd->priv = al;
 	mtd->owner = THIS_MODULE;
 
-	err = add_mtd_device(mtd);
+	err = mtd_device_register(mtd, NULL, 0);
 	if (err) {
 		err = -ENFILE;
 		goto error;
diff --git a/drivers/mtd/nand/ams-delta.c b/drivers/mtd/nand/ams-delta.c
index bc65bf71e1a2..78017eb9318e 100644
--- a/drivers/mtd/nand/ams-delta.c
+++ b/drivers/mtd/nand/ams-delta.c
@@ -235,8 +235,8 @@ static int __devinit ams_delta_init(struct platform_device *pdev)
 	}
 
 	/* Register the partitions */
-	add_mtd_partitions(ams_delta_mtd, partition_info,
-			   ARRAY_SIZE(partition_info));
+	mtd_device_register(ams_delta_mtd, partition_info,
+			    ARRAY_SIZE(partition_info));
 
 	goto out;
 
diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index 950646aa4c4b..b300705d41cb 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -30,6 +30,7 @@
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
 
+#include <linux/dmaengine.h>
 #include <linux/gpio.h>
 #include <linux/io.h>
 
@@ -494,11 +495,8 @@ static int __init atmel_nand_probe(struct platform_device *pdev)
 	struct resource *regs;
 	struct resource *mem;
 	int res;
-
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *partitions = NULL;
 	int num_partitions = 0;
-#endif
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!mem) {
@@ -656,7 +654,6 @@ static int __init atmel_nand_probe(struct platform_device *pdev)
 		goto err_scan_tail;
 	}
 
-#ifdef CONFIG_MTD_PARTITIONS
 #ifdef CONFIG_MTD_CMDLINE_PARTS
 	mtd->name = "atmel_nand";
 	num_partitions = parse_mtd_partitions(mtd, part_probes,
@@ -672,17 +669,11 @@ static int __init atmel_nand_probe(struct platform_device *pdev)
 		goto err_no_partitions;
 	}
 
-	res = add_mtd_partitions(mtd, partitions, num_partitions);
-#else
-	res = add_mtd_device(mtd);
-#endif
-
+	res = mtd_device_register(mtd, partitions, num_partitions);
 	if (!res)
 		return res;
 
-#ifdef CONFIG_MTD_PARTITIONS
 err_no_partitions:
-#endif
 	nand_release(mtd);
 err_scan_tail:
 err_scan_ident:
diff --git a/drivers/mtd/nand/au1550nd.c b/drivers/mtd/nand/au1550nd.c
index 5d513b54a7d7..e7767eef4505 100644
--- a/drivers/mtd/nand/au1550nd.c
+++ b/drivers/mtd/nand/au1550nd.c
@@ -581,7 +581,8 @@ static int __init au1xxx_nand_init(void)
 	}
 
 	/* Register the partitions */
-	add_mtd_partitions(au1550_mtd, partition_info, ARRAY_SIZE(partition_info));
+	mtd_device_register(au1550_mtd, partition_info,
+			    ARRAY_SIZE(partition_info));
 
 	return 0;
 
diff --git a/drivers/mtd/nand/autcpu12.c b/drivers/mtd/nand/autcpu12.c
index 0911cf03db80..eddc9a224985 100644
--- a/drivers/mtd/nand/autcpu12.c
+++ b/drivers/mtd/nand/autcpu12.c
@@ -185,20 +185,20 @@ static int __init autcpu12_init(void)
 	/* Register the partitions */
 	switch (autcpu12_mtd->size) {
 		case SZ_16M:
-			add_mtd_partitions(autcpu12_mtd, partition_info16k,
-					   NUM_PARTITIONS16K);
+			mtd_device_register(autcpu12_mtd, partition_info16k,
+					    NUM_PARTITIONS16K);
 			break;
 		case SZ_32M:
-			add_mtd_partitions(autcpu12_mtd, partition_info32k,
-					   NUM_PARTITIONS32K);
+			mtd_device_register(autcpu12_mtd, partition_info32k,
+					    NUM_PARTITIONS32K);
 			break;
 		case SZ_64M:
-			add_mtd_partitions(autcpu12_mtd, partition_info64k,
-					   NUM_PARTITIONS64K);
+			mtd_device_register(autcpu12_mtd, partition_info64k,
+					    NUM_PARTITIONS64K);
 			break;
 		case SZ_128M:
-			add_mtd_partitions(autcpu12_mtd, partition_info128k,
-					   NUM_PARTITIONS128K);
+			mtd_device_register(autcpu12_mtd, partition_info128k,
+					    NUM_PARTITIONS128K);
 			break;
 		default:
 			printk("Unsupported SmartMedia device\n");
diff --git a/drivers/mtd/nand/bcm_umi_nand.c b/drivers/mtd/nand/bcm_umi_nand.c
index dfe262c726fb..9ec280738a9a 100644
--- a/drivers/mtd/nand/bcm_umi_nand.c
+++ b/drivers/mtd/nand/bcm_umi_nand.c
@@ -52,9 +52,7 @@
 static const __devinitconst char gBanner[] = KERN_INFO \
 	"BCM UMI MTD NAND Driver: 1.00\n";
 
-#ifdef CONFIG_MTD_PARTITIONS
 const char *part_probes[] = { "cmdlinepart", NULL };
-#endif
 
 #if NAND_ECC_BCH
 static uint8_t scan_ff_pattern[] = { 0xff };
@@ -509,7 +507,7 @@ static int __devinit bcm_umi_nand_probe(struct platform_device *pdev)
 			kfree(board_mtd);
 			return -EIO;
 		}
-		add_mtd_partitions(board_mtd, partition_info, nr_partitions);
+		mtd_device_register(board_mtd, partition_info, nr_partitions);
 	}
 
 	/* Return happy */
diff --git a/drivers/mtd/nand/bf5xx_nand.c b/drivers/mtd/nand/bf5xx_nand.c
index 79947bea4d57..dd899cb5d366 100644
--- a/drivers/mtd/nand/bf5xx_nand.c
+++ b/drivers/mtd/nand/bf5xx_nand.c
@@ -659,15 +659,10 @@ static int bf5xx_nand_hw_init(struct bf5xx_nand_info *info)
 static int __devinit bf5xx_nand_add_partition(struct bf5xx_nand_info *info)
 {
 	struct mtd_info *mtd = &info->mtd;
-
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *parts = info->platform->partitions;
 	int nr = info->platform->nr_partitions;
 
-	return add_mtd_partitions(mtd, parts, nr);
-#else
-	return add_mtd_device(mtd);
-#endif
+	return mtd_device_register(mtd, parts, nr);
 }
 
 static int __devexit bf5xx_nand_remove(struct platform_device *pdev)
diff --git a/drivers/mtd/nand/cafe_nand.c b/drivers/mtd/nand/cafe_nand.c
index e06c8983978e..87ebb4e5b0c3 100644
--- a/drivers/mtd/nand/cafe_nand.c
+++ b/drivers/mtd/nand/cafe_nand.c
@@ -90,9 +90,7 @@ static unsigned int numtimings;
 static int timing[3];
 module_param_array(timing, int, &numtimings, 0644);
 
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *part_probes[] = { "cmdlinepart", "RedBoot", NULL };
-#endif
 
 /* Hrm. Why isn't this already conditional on something in the struct device? */
 #define cafe_dev_dbg(dev, args...) do { if (debug) dev_dbg(dev, ##args); } while(0)
@@ -632,10 +630,8 @@ static int __devinit cafe_nand_probe(struct pci_dev *pdev,
 	struct cafe_priv *cafe;
 	uint32_t ctrl;
 	int err = 0;
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *parts;
 	int nr_parts;
-#endif
 
 	/* Very old versions shared the same PCI ident for all three
 	   functions on the chip. Verify the class too... */
@@ -804,9 +800,8 @@ static int __devinit cafe_nand_probe(struct pci_dev *pdev,
 	pci_set_drvdata(pdev, mtd);
 
 	/* We register the whole device first, separate from the partitions */
-	add_mtd_device(mtd);
+	mtd_device_register(mtd, NULL, 0);
 
-#ifdef CONFIG_MTD_PARTITIONS
 #ifdef CONFIG_MTD_CMDLINE_PARTS
 	mtd->name = "cafe_nand";
 #endif
@@ -814,9 +809,8 @@ static int __devinit cafe_nand_probe(struct pci_dev *pdev,
 	if (nr_parts > 0) {
 		cafe->parts = parts;
 		dev_info(&cafe->pdev->dev, "%d partitions found\n", nr_parts);
-		add_mtd_partitions(mtd, parts, nr_parts);
+		mtd_device_register(mtd, parts, nr_parts);
 	}
-#endif
 	goto out;
 
  out_irq:
@@ -838,7 +832,6 @@ static void __devexit cafe_nand_remove(struct pci_dev *pdev)
 	struct mtd_info *mtd = pci_get_drvdata(pdev);
 	struct cafe_priv *cafe = mtd->priv;
 
-	del_mtd_device(mtd);
 	/* Disable NAND IRQ in global IRQ mask register */
 	cafe_writel(cafe, ~1 & cafe_readl(cafe, GLOBAL_IRQ_MASK), GLOBAL_IRQ_MASK);
 	free_irq(pdev->irq, mtd);
diff --git a/drivers/mtd/nand/cmx270_nand.c b/drivers/mtd/nand/cmx270_nand.c
index 6e6495278258..6fc043a30d1e 100644
--- a/drivers/mtd/nand/cmx270_nand.c
+++ b/drivers/mtd/nand/cmx270_nand.c
@@ -238,7 +238,7 @@ static int __init cmx270_init(void)
 
 	/* Register the partitions */
 	pr_notice("Using %s partition definition\n", part_type);
-	ret = add_mtd_partitions(cmx270_nand_mtd, mtd_parts, mtd_parts_nb);
+	ret = mtd_device_register(cmx270_nand_mtd, mtd_parts, mtd_parts_nb);
 	if (ret)
 		goto err_scan;
 
diff --git a/drivers/mtd/nand/cs553x_nand.c b/drivers/mtd/nand/cs553x_nand.c
index 71c35a0b9826..f59ad1f2d5db 100644
--- a/drivers/mtd/nand/cs553x_nand.c
+++ b/drivers/mtd/nand/cs553x_nand.c
@@ -277,22 +277,15 @@ static int is_geode(void)
 	return 0;
 }
 
-
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *part_probes[] = { "cmdlinepart", NULL };
-#endif
-
 
 static int __init cs553x_init(void)
 {
 	int err = -ENXIO;
 	int i;
 	uint64_t val;
-
-#ifdef CONFIG_MTD_PARTITIONS
 	int mtd_parts_nb = 0;
 	struct mtd_partition *mtd_parts = NULL;
-#endif
 
 	/* If the CPU isn't a Geode GX or LX, abort */
 	if (!is_geode())
@@ -324,17 +317,11 @@ static int __init cs553x_init(void)
 		if (cs553x_mtd[i]) {
 
 			/* If any devices registered, return success. Else the last error. */
-#ifdef CONFIG_MTD_PARTITIONS
 			mtd_parts_nb = parse_mtd_partitions(cs553x_mtd[i], part_probes, &mtd_parts, 0);
-			if (mtd_parts_nb > 0) {
+			if (mtd_parts_nb > 0)
 				printk(KERN_NOTICE "Using command line partition definition\n");
-				add_mtd_partitions(cs553x_mtd[i], mtd_parts, mtd_parts_nb);
-			} else {
-				add_mtd_device(cs553x_mtd[i]);
-			}
-#else
-			add_mtd_device(cs553x_mtd[i]);
-#endif
+			mtd_device_register(cs553x_mtd[i], mtd_parts,
+					    mtd_parts_nb);
 			err = 0;
 		}
 	}
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index aff3468867ac..1f34951ae1a7 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -530,6 +530,8 @@ static int __init nand_davinci_probe(struct platform_device *pdev)
 	int				ret;
 	uint32_t			val;
 	nand_ecc_modes_t		ecc_mode;
+	struct mtd_partition		*mtd_parts = NULL;
+	int				mtd_parts_nb = 0;
 
 	/* insist on board-specific configuration */
 	if (!pdata)
@@ -749,41 +751,33 @@ syndrome_done:
 	if (ret < 0)
 		goto err_scan;
 
-	if (mtd_has_partitions()) {
-		struct mtd_partition	*mtd_parts = NULL;
-		int			mtd_parts_nb = 0;
+	if (mtd_has_cmdlinepart()) {
+		static const char *probes[] __initconst = {
+			"cmdlinepart", NULL
+		};
 
-		if (mtd_has_cmdlinepart()) {
-			static const char *probes[] __initconst =
-				{ "cmdlinepart", NULL };
-
-			mtd_parts_nb = parse_mtd_partitions(&info->mtd, probes,
-							    &mtd_parts, 0);
-		}
-
-		if (mtd_parts_nb <= 0) {
-			mtd_parts = pdata->parts;
-			mtd_parts_nb = pdata->nr_parts;
-		}
+		mtd_parts_nb = parse_mtd_partitions(&info->mtd, probes,
+						    &mtd_parts, 0);
+	}
 
-		/* Register any partitions */
-		if (mtd_parts_nb > 0) {
-			ret = add_mtd_partitions(&info->mtd,
-					mtd_parts, mtd_parts_nb);
-			if (ret == 0)
-				info->partitioned = true;
-		}
+	if (mtd_parts_nb <= 0) {
+		mtd_parts = pdata->parts;
+		mtd_parts_nb = pdata->nr_parts;
+	}
 
-	} else if (pdata->nr_parts) {
-		dev_warn(&pdev->dev, "ignoring %d default partitions on %s\n",
-				pdata->nr_parts, info->mtd.name);
+	/* Register any partitions */
+	if (mtd_parts_nb > 0) {
+		ret = mtd_device_register(&info->mtd, mtd_parts,
+					  mtd_parts_nb);
+		if (ret == 0)
+			info->partitioned = true;
 	}
 
 	/* If there's no partition info, just package the whole chip
 	 * as a single MTD device.
 	 */
 	if (!info->partitioned)
-		ret = add_mtd_device(&info->mtd) ? -ENODEV : 0;
+		ret = mtd_device_register(&info->mtd, NULL, 0) ? -ENODEV : 0;
 
 	if (ret < 0)
 		goto err_scan;
@@ -824,10 +818,7 @@ static int __exit nand_davinci_remove(struct platform_device *pdev)
 	struct davinci_nand_info *info = platform_get_drvdata(pdev);
 	int status;
 
-	if (mtd_has_partitions() && info->partitioned)
-		status = del_mtd_partitions(&info->mtd);
-	else
-		status = del_mtd_device(&info->mtd);
+	status = mtd_device_unregister(&info->mtd);
 
 	spin_lock_irq(&davinci_nand_lock);
 	if (info->chip.ecc.mode == NAND_ECC_HW_SYNDROME)
diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c
index 4633f094c510..d5276218945f 100644
--- a/drivers/mtd/nand/denali.c
+++ b/drivers/mtd/nand/denali.c
@@ -19,6 +19,7 @@
 
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/wait.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
@@ -44,16 +45,16 @@ MODULE_PARM_DESC(onfi_timing_mode, "Overrides default ONFI setting."
 
 /* We define a macro here that combines all interrupts this driver uses into
  * a single constant value, for convenience. */
-#define DENALI_IRQ_ALL	(INTR_STATUS0__DMA_CMD_COMP | \
-			INTR_STATUS0__ECC_TRANSACTION_DONE | \
-			INTR_STATUS0__ECC_ERR | \
-			INTR_STATUS0__PROGRAM_FAIL | \
-			INTR_STATUS0__LOAD_COMP | \
-			INTR_STATUS0__PROGRAM_COMP | \
-			INTR_STATUS0__TIME_OUT | \
-			INTR_STATUS0__ERASE_FAIL | \
-			INTR_STATUS0__RST_COMP | \
-			INTR_STATUS0__ERASE_COMP)
+#define DENALI_IRQ_ALL	(INTR_STATUS__DMA_CMD_COMP | \
+			INTR_STATUS__ECC_TRANSACTION_DONE | \
+			INTR_STATUS__ECC_ERR | \
+			INTR_STATUS__PROGRAM_FAIL | \
+			INTR_STATUS__LOAD_COMP | \
+			INTR_STATUS__PROGRAM_COMP | \
+			INTR_STATUS__TIME_OUT | \
+			INTR_STATUS__ERASE_FAIL | \
+			INTR_STATUS__RST_COMP | \
+			INTR_STATUS__ERASE_COMP)
 
 /* indicates whether or not the internal value for the flash bank is
  * valid or not */
@@ -95,30 +96,6 @@ static const struct pci_device_id denali_pci_ids[] = {
 	{ /* end: all zeroes */ }
 };
 
-
-/* these are static lookup tables that give us easy access to
- * registers in the NAND controller.
- */
-static const uint32_t intr_status_addresses[4] = {INTR_STATUS0,
-						  INTR_STATUS1,
-						  INTR_STATUS2,
-						  INTR_STATUS3};
-
-static const uint32_t device_reset_banks[4] = {DEVICE_RESET__BANK0,
-							DEVICE_RESET__BANK1,
-							DEVICE_RESET__BANK2,
-							DEVICE_RESET__BANK3};
-
-static const uint32_t operation_timeout[4] = {INTR_STATUS0__TIME_OUT,
-							INTR_STATUS1__TIME_OUT,
-							INTR_STATUS2__TIME_OUT,
-							INTR_STATUS3__TIME_OUT};
-
-static const uint32_t reset_complete[4] = {INTR_STATUS0__RST_COMP,
-							INTR_STATUS1__RST_COMP,
-							INTR_STATUS2__RST_COMP,
-							INTR_STATUS3__RST_COMP};
-
 /* forward declarations */
 static void clear_interrupts(struct denali_nand_info *denali);
 static uint32_t wait_for_irq(struct denali_nand_info *denali,
@@ -180,19 +157,17 @@ static void read_status(struct denali_nand_info *denali)
 static void reset_bank(struct denali_nand_info *denali)
 {
 	uint32_t irq_status = 0;
-	uint32_t irq_mask = reset_complete[denali->flash_bank] |
-			    operation_timeout[denali->flash_bank];
-	int bank = 0;
+	uint32_t irq_mask = INTR_STATUS__RST_COMP |
+			    INTR_STATUS__TIME_OUT;
 
 	clear_interrupts(denali);
 
-	bank = device_reset_banks[denali->flash_bank];
-	iowrite32(bank, denali->flash_reg + DEVICE_RESET);
+	iowrite32(1 << denali->flash_bank, denali->flash_reg + DEVICE_RESET);
 
 	irq_status = wait_for_irq(denali, irq_mask);
 
-	if (irq_status & operation_timeout[denali->flash_bank])
-		dev_err(&denali->dev->dev, "reset bank failed.\n");
+	if (irq_status & INTR_STATUS__TIME_OUT)
+		dev_err(denali->dev, "reset bank failed.\n");
 }
 
 /* Reset the flash controller */
@@ -200,29 +175,28 @@ static uint16_t denali_nand_reset(struct denali_nand_info *denali)
 {
 	uint32_t i;
 
-	dev_dbg(&denali->dev->dev, "%s, Line %d, Function: %s\n",
+	dev_dbg(denali->dev, "%s, Line %d, Function: %s\n",
 		       __FILE__, __LINE__, __func__);
 
-	for (i = 0 ; i < LLD_MAX_FLASH_BANKS; i++)
-		iowrite32(reset_complete[i] | operation_timeout[i],
-		denali->flash_reg + intr_status_addresses[i]);
+	for (i = 0 ; i < denali->max_banks; i++)
+		iowrite32(INTR_STATUS__RST_COMP | INTR_STATUS__TIME_OUT,
+		denali->flash_reg + INTR_STATUS(i));
 
-	for (i = 0 ; i < LLD_MAX_FLASH_BANKS; i++) {
-		iowrite32(device_reset_banks[i],
-				denali->flash_reg + DEVICE_RESET);
+	for (i = 0 ; i < denali->max_banks; i++) {
+		iowrite32(1 << i, denali->flash_reg + DEVICE_RESET);
 		while (!(ioread32(denali->flash_reg +
-				intr_status_addresses[i]) &
-			(reset_complete[i] | operation_timeout[i])))
+				INTR_STATUS(i)) &
+			(INTR_STATUS__RST_COMP | INTR_STATUS__TIME_OUT)))
 			cpu_relax();
-		if (ioread32(denali->flash_reg + intr_status_addresses[i]) &
-			operation_timeout[i])
-			dev_dbg(&denali->dev->dev,
+		if (ioread32(denali->flash_reg + INTR_STATUS(i)) &
+			INTR_STATUS__TIME_OUT)
+			dev_dbg(denali->dev,
 			"NAND Reset operation timed out on bank %d\n", i);
 	}
 
-	for (i = 0; i < LLD_MAX_FLASH_BANKS; i++)
-		iowrite32(reset_complete[i] | operation_timeout[i],
-			denali->flash_reg + intr_status_addresses[i]);
+	for (i = 0; i < denali->max_banks; i++)
+		iowrite32(INTR_STATUS__RST_COMP | INTR_STATUS__TIME_OUT,
+			denali->flash_reg + INTR_STATUS(i));
 
 	return PASS;
 }
@@ -254,7 +228,7 @@ static void nand_onfi_timing_set(struct denali_nand_info *denali,
 	uint16_t acc_clks;
 	uint16_t addr_2_data, re_2_we, re_2_re, we_2_re, cs_cnt;
 
-	dev_dbg(&denali->dev->dev, "%s, Line %d, Function: %s\n",
+	dev_dbg(denali->dev, "%s, Line %d, Function: %s\n",
 		       __FILE__, __LINE__, __func__);
 
 	en_lo = CEIL_DIV(Trp[mode], CLK_X);
@@ -291,7 +265,7 @@ static void nand_onfi_timing_set(struct denali_nand_info *denali,
 		acc_clks++;
 
 	if ((data_invalid - acc_clks * CLK_X) < 2)
-		dev_warn(&denali->dev->dev, "%s, Line %d: Warning!\n",
+		dev_warn(denali->dev, "%s, Line %d: Warning!\n",
 			__FILE__, __LINE__);
 
 	addr_2_data = CEIL_DIV(Tadl[mode], CLK_X);
@@ -419,7 +393,7 @@ static void get_hynix_nand_para(struct denali_nand_info *denali,
 #endif
 		break;
 	default:
-		dev_warn(&denali->dev->dev,
+		dev_warn(denali->dev,
 			"Spectra: Unknown Hynix NAND (Device ID: 0x%x)."
 			"Will use default parameter values instead.\n",
 			device_id);
@@ -431,17 +405,17 @@ static void get_hynix_nand_para(struct denali_nand_info *denali,
  */
 static void find_valid_banks(struct denali_nand_info *denali)
 {
-	uint32_t id[LLD_MAX_FLASH_BANKS];
+	uint32_t id[denali->max_banks];
 	int i;
 
 	denali->total_used_banks = 1;
-	for (i = 0; i < LLD_MAX_FLASH_BANKS; i++) {
+	for (i = 0; i < denali->max_banks; i++) {
 		index_addr(denali, (uint32_t)(MODE_11 | (i << 24) | 0), 0x90);
 		index_addr(denali, (uint32_t)(MODE_11 | (i << 24) | 1), 0);
 		index_addr_read_data(denali,
 				(uint32_t)(MODE_11 | (i << 24) | 2), &id[i]);
 
-		dev_dbg(&denali->dev->dev,
+		dev_dbg(denali->dev,
 			"Return 1st ID for bank[%d]: %x\n", i, id[i]);
 
 		if (i == 0) {
@@ -461,16 +435,27 @@ static void find_valid_banks(struct denali_nand_info *denali)
 		 * Multichip support is not enabled.
 		 */
 		if (denali->total_used_banks != 1) {
-			dev_err(&denali->dev->dev,
+			dev_err(denali->dev,
 					"Sorry, Intel CE4100 only supports "
 					"a single NAND device.\n");
 			BUG();
 		}
 	}
-	dev_dbg(&denali->dev->dev,
+	dev_dbg(denali->dev,
 		"denali->total_used_banks: %d\n", denali->total_used_banks);
 }
 
+/*
+ * Use the configuration feature register to determine the maximum number of
+ * banks that the hardware supports.
+ */
+static void detect_max_banks(struct denali_nand_info *denali)
+{
+	uint32_t features = ioread32(denali->flash_reg + FEATURES);
+
+	denali->max_banks = 2 << (features & FEATURES__N_BANKS);
+}
+
 static void detect_partition_feature(struct denali_nand_info *denali)
 {
 	/* For MRST platform, denali->fwblks represent the
@@ -480,15 +465,15 @@ static void detect_partition_feature(struct denali_nand_info *denali)
 	 * blocks it can't touch.
 	 * */
 	if (ioread32(denali->flash_reg + FEATURES) & FEATURES__PARTITION) {
-		if ((ioread32(denali->flash_reg + PERM_SRC_ID_1) &
-			PERM_SRC_ID_1__SRCID) == SPECTRA_PARTITION_ID) {
+		if ((ioread32(denali->flash_reg + PERM_SRC_ID(1)) &
+			PERM_SRC_ID__SRCID) == SPECTRA_PARTITION_ID) {
 			denali->fwblks =
-			    ((ioread32(denali->flash_reg + MIN_MAX_BANK_1) &
-			      MIN_MAX_BANK_1__MIN_VALUE) *
+			    ((ioread32(denali->flash_reg + MIN_MAX_BANK(1)) &
+			      MIN_MAX_BANK__MIN_VALUE) *
 			     denali->blksperchip)
 			    +
-			    (ioread32(denali->flash_reg + MIN_BLK_ADDR_1) &
-			    MIN_BLK_ADDR_1__VALUE);
+			    (ioread32(denali->flash_reg + MIN_BLK_ADDR(1)) &
+			    MIN_BLK_ADDR__VALUE);
 		} else
 			denali->fwblks = SPECTRA_START_BLOCK;
 	} else
@@ -501,7 +486,7 @@ static uint16_t denali_nand_timing_set(struct denali_nand_info *denali)
 	uint32_t id_bytes[5], addr;
 	uint8_t i, maf_id, device_id;
 
-	dev_dbg(&denali->dev->dev,
+	dev_dbg(denali->dev,
 			"%s, Line %d, Function: %s\n",
 			__FILE__, __LINE__, __func__);
 
@@ -530,7 +515,7 @@ static uint16_t denali_nand_timing_set(struct denali_nand_info *denali)
 		get_hynix_nand_para(denali, device_id);
 	}
 
-	dev_info(&denali->dev->dev,
+	dev_info(denali->dev,
 			"Dump timing register values:"
 			"acc_clks: %d, re_2_we: %d, re_2_re: %d\n"
 			"we_2_re: %d, addr_2_data: %d, rdwr_en_lo_cnt: %d\n"
@@ -560,7 +545,7 @@ static uint16_t denali_nand_timing_set(struct denali_nand_info *denali)
 static void denali_set_intr_modes(struct denali_nand_info *denali,
 					uint16_t INT_ENABLE)
 {
-	dev_dbg(&denali->dev->dev, "%s, Line %d, Function: %s\n",
+	dev_dbg(denali->dev, "%s, Line %d, Function: %s\n",
 		       __FILE__, __LINE__, __func__);
 
 	if (INT_ENABLE)
@@ -580,6 +565,7 @@ static inline bool is_flash_bank_valid(int flash_bank)
 static void denali_irq_init(struct denali_nand_info *denali)
 {
 	uint32_t int_mask = 0;
+	int i;
 
 	/* Disable global interrupts */
 	denali_set_intr_modes(denali, false);
@@ -587,10 +573,8 @@ static void denali_irq_init(struct denali_nand_info *denali)
 	int_mask = DENALI_IRQ_ALL;
 
 	/* Clear all status bits */
-	iowrite32(0xFFFF, denali->flash_reg + INTR_STATUS0);
-	iowrite32(0xFFFF, denali->flash_reg + INTR_STATUS1);
-	iowrite32(0xFFFF, denali->flash_reg + INTR_STATUS2);
-	iowrite32(0xFFFF, denali->flash_reg + INTR_STATUS3);
+	for (i = 0; i < denali->max_banks; ++i)
+		iowrite32(0xFFFF, denali->flash_reg + INTR_STATUS(i));
 
 	denali_irq_enable(denali, int_mask);
 }
@@ -604,10 +588,10 @@ static void denali_irq_cleanup(int irqnum, struct denali_nand_info *denali)
 static void denali_irq_enable(struct denali_nand_info *denali,
 							uint32_t int_mask)
 {
-	iowrite32(int_mask, denali->flash_reg + INTR_EN0);
-	iowrite32(int_mask, denali->flash_reg + INTR_EN1);
-	iowrite32(int_mask, denali->flash_reg + INTR_EN2);
-	iowrite32(int_mask, denali->flash_reg + INTR_EN3);
+	int i;
+
+	for (i = 0; i < denali->max_banks; ++i)
+		iowrite32(int_mask, denali->flash_reg + INTR_EN(i));
 }
 
 /* This function only returns when an interrupt that this driver cares about
@@ -624,7 +608,7 @@ static inline void clear_interrupt(struct denali_nand_info *denali,
 {
 	uint32_t intr_status_reg = 0;
 
-	intr_status_reg = intr_status_addresses[denali->flash_bank];
+	intr_status_reg = INTR_STATUS(denali->flash_bank);
 
 	iowrite32(irq_mask, denali->flash_reg + intr_status_reg);
 }
@@ -645,7 +629,7 @@ static uint32_t read_interrupt_status(struct denali_nand_info *denali)
 {
 	uint32_t intr_status_reg = 0;
 
-	intr_status_reg = intr_status_addresses[denali->flash_bank];
+	intr_status_reg = INTR_STATUS(denali->flash_bank);
 
 	return ioread32(denali->flash_reg + intr_status_reg);
 }
@@ -754,7 +738,7 @@ static int denali_send_pipeline_cmd(struct denali_nand_info *denali,
 		 irq_mask = 0;
 
 	if (op == DENALI_READ)
-		irq_mask = INTR_STATUS0__LOAD_COMP;
+		irq_mask = INTR_STATUS__LOAD_COMP;
 	else if (op == DENALI_WRITE)
 		irq_mask = 0;
 	else
@@ -800,7 +784,7 @@ static int denali_send_pipeline_cmd(struct denali_nand_info *denali,
 			irq_status = wait_for_irq(denali, irq_mask);
 
 			if (irq_status == 0) {
-				dev_err(&denali->dev->dev,
+				dev_err(denali->dev,
 						"cmd, page, addr on timeout "
 						"(0x%x, 0x%x, 0x%x)\n",
 						cmd, denali->page, addr);
@@ -861,8 +845,8 @@ static int write_oob_data(struct mtd_info *mtd, uint8_t *buf, int page)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
 	uint32_t irq_status = 0;
-	uint32_t irq_mask = INTR_STATUS0__PROGRAM_COMP |
-						INTR_STATUS0__PROGRAM_FAIL;
+	uint32_t irq_mask = INTR_STATUS__PROGRAM_COMP |
+						INTR_STATUS__PROGRAM_FAIL;
 	int status = 0;
 
 	denali->page = page;
@@ -875,11 +859,11 @@ static int write_oob_data(struct mtd_info *mtd, uint8_t *buf, int page)
 		irq_status = wait_for_irq(denali, irq_mask);
 
 		if (irq_status == 0) {
-			dev_err(&denali->dev->dev, "OOB write failed\n");
+			dev_err(denali->dev, "OOB write failed\n");
 			status = -EIO;
 		}
 	} else {
-		dev_err(&denali->dev->dev, "unable to send pipeline command\n");
+		dev_err(denali->dev, "unable to send pipeline command\n");
 		status = -EIO;
 	}
 	return status;
@@ -889,7 +873,7 @@ static int write_oob_data(struct mtd_info *mtd, uint8_t *buf, int page)
 static void read_oob_data(struct mtd_info *mtd, uint8_t *buf, int page)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	uint32_t irq_mask = INTR_STATUS0__LOAD_COMP,
+	uint32_t irq_mask = INTR_STATUS__LOAD_COMP,
 			 irq_status = 0, addr = 0x0, cmd = 0x0;
 
 	denali->page = page;
@@ -904,7 +888,7 @@ static void read_oob_data(struct mtd_info *mtd, uint8_t *buf, int page)
 		irq_status = wait_for_irq(denali, irq_mask);
 
 		if (irq_status == 0)
-			dev_err(&denali->dev->dev, "page on OOB timeout %d\n",
+			dev_err(denali->dev, "page on OOB timeout %d\n",
 					denali->page);
 
 		/* We set the device back to MAIN_ACCESS here as I observed
@@ -944,7 +928,7 @@ static bool handle_ecc(struct denali_nand_info *denali, uint8_t *buf,
 {
 	bool check_erased_page = false;
 
-	if (irq_status & INTR_STATUS0__ECC_ERR) {
+	if (irq_status & INTR_STATUS__ECC_ERR) {
 		/* read the ECC errors. we'll ignore them for now */
 		uint32_t err_address = 0, err_correction_info = 0;
 		uint32_t err_byte = 0, err_sector = 0, err_device = 0;
@@ -995,7 +979,7 @@ static bool handle_ecc(struct denali_nand_info *denali, uint8_t *buf,
 		 * for a while for this interrupt
 		 * */
 		while (!(read_interrupt_status(denali) &
-				INTR_STATUS0__ECC_TRANSACTION_DONE))
+				INTR_STATUS__ECC_TRANSACTION_DONE))
 			cpu_relax();
 		clear_interrupts(denali);
 		denali_set_intr_modes(denali, true);
@@ -1045,14 +1029,13 @@ static void write_page(struct mtd_info *mtd, struct nand_chip *chip,
 			const uint8_t *buf, bool raw_xfer)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	struct pci_dev *pci_dev = denali->dev;
 
 	dma_addr_t addr = denali->buf.dma_buf;
 	size_t size = denali->mtd.writesize + denali->mtd.oobsize;
 
 	uint32_t irq_status = 0;
-	uint32_t irq_mask = INTR_STATUS0__DMA_CMD_COMP |
-						INTR_STATUS0__PROGRAM_FAIL;
+	uint32_t irq_mask = INTR_STATUS__DMA_CMD_COMP |
+						INTR_STATUS__PROGRAM_FAIL;
 
 	/* if it is a raw xfer, we want to disable ecc, and send
 	 * the spare area.
@@ -1071,7 +1054,7 @@ static void write_page(struct mtd_info *mtd, struct nand_chip *chip,
 			mtd->oobsize);
 	}
 
-	pci_dma_sync_single_for_device(pci_dev, addr, size, PCI_DMA_TODEVICE);
+	dma_sync_single_for_device(denali->dev, addr, size, DMA_TO_DEVICE);
 
 	clear_interrupts(denali);
 	denali_enable_dma(denali, true);
@@ -1082,16 +1065,16 @@ static void write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	irq_status = wait_for_irq(denali, irq_mask);
 
 	if (irq_status == 0) {
-		dev_err(&denali->dev->dev,
+		dev_err(denali->dev,
 				"timeout on write_page (type = %d)\n",
 				raw_xfer);
 		denali->status =
-			(irq_status & INTR_STATUS0__PROGRAM_FAIL) ?
+			(irq_status & INTR_STATUS__PROGRAM_FAIL) ?
 			NAND_STATUS_FAIL : PASS;
 	}
 
 	denali_enable_dma(denali, false);
-	pci_dma_sync_single_for_cpu(pci_dev, addr, size, PCI_DMA_TODEVICE);
+	dma_sync_single_for_cpu(denali->dev, addr, size, DMA_TO_DEVICE);
 }
 
 /* NAND core entry points */
@@ -1139,18 +1122,17 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 			    uint8_t *buf, int page)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	struct pci_dev *pci_dev = denali->dev;
 
 	dma_addr_t addr = denali->buf.dma_buf;
 	size_t size = denali->mtd.writesize + denali->mtd.oobsize;
 
 	uint32_t irq_status = 0;
-	uint32_t irq_mask = INTR_STATUS0__ECC_TRANSACTION_DONE |
-			    INTR_STATUS0__ECC_ERR;
+	uint32_t irq_mask = INTR_STATUS__ECC_TRANSACTION_DONE |
+			    INTR_STATUS__ECC_ERR;
 	bool check_erased_page = false;
 
 	if (page != denali->page) {
-		dev_err(&denali->dev->dev, "IN %s: page %d is not"
+		dev_err(denali->dev, "IN %s: page %d is not"
 				" equal to denali->page %d, investigate!!",
 				__func__, page, denali->page);
 		BUG();
@@ -1159,7 +1141,7 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 	setup_ecc_for_xfer(denali, true, false);
 
 	denali_enable_dma(denali, true);
-	pci_dma_sync_single_for_device(pci_dev, addr, size, PCI_DMA_FROMDEVICE);
+	dma_sync_single_for_device(denali->dev, addr, size, DMA_FROM_DEVICE);
 
 	clear_interrupts(denali);
 	denali_setup_dma(denali, DENALI_READ);
@@ -1167,7 +1149,7 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 	/* wait for operation to complete */
 	irq_status = wait_for_irq(denali, irq_mask);
 
-	pci_dma_sync_single_for_cpu(pci_dev, addr, size, PCI_DMA_FROMDEVICE);
+	dma_sync_single_for_cpu(denali->dev, addr, size, DMA_FROM_DEVICE);
 
 	memcpy(buf, denali->buf.buf, mtd->writesize);
 
@@ -1192,16 +1174,15 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 				uint8_t *buf, int page)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	struct pci_dev *pci_dev = denali->dev;
 
 	dma_addr_t addr = denali->buf.dma_buf;
 	size_t size = denali->mtd.writesize + denali->mtd.oobsize;
 
 	uint32_t irq_status = 0;
-	uint32_t irq_mask = INTR_STATUS0__DMA_CMD_COMP;
+	uint32_t irq_mask = INTR_STATUS__DMA_CMD_COMP;
 
 	if (page != denali->page) {
-		dev_err(&denali->dev->dev, "IN %s: page %d is not"
+		dev_err(denali->dev, "IN %s: page %d is not"
 				" equal to denali->page %d, investigate!!",
 				__func__, page, denali->page);
 		BUG();
@@ -1210,7 +1191,7 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 	setup_ecc_for_xfer(denali, false, true);
 	denali_enable_dma(denali, true);
 
-	pci_dma_sync_single_for_device(pci_dev, addr, size, PCI_DMA_FROMDEVICE);
+	dma_sync_single_for_device(denali->dev, addr, size, DMA_FROM_DEVICE);
 
 	clear_interrupts(denali);
 	denali_setup_dma(denali, DENALI_READ);
@@ -1218,7 +1199,7 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 	/* wait for operation to complete */
 	irq_status = wait_for_irq(denali, irq_mask);
 
-	pci_dma_sync_single_for_cpu(pci_dev, addr, size, PCI_DMA_FROMDEVICE);
+	dma_sync_single_for_cpu(denali->dev, addr, size, DMA_FROM_DEVICE);
 
 	denali_enable_dma(denali, false);
 
@@ -1271,10 +1252,10 @@ static void denali_erase(struct mtd_info *mtd, int page)
 	index_addr(denali, (uint32_t)cmd, 0x1);
 
 	/* wait for erase to complete or failure to occur */
-	irq_status = wait_for_irq(denali, INTR_STATUS0__ERASE_COMP |
-					INTR_STATUS0__ERASE_FAIL);
+	irq_status = wait_for_irq(denali, INTR_STATUS__ERASE_COMP |
+					INTR_STATUS__ERASE_FAIL);
 
-	denali->status = (irq_status & INTR_STATUS0__ERASE_FAIL) ?
+	denali->status = (irq_status & INTR_STATUS__ERASE_FAIL) ?
 						NAND_STATUS_FAIL : PASS;
 }
 
@@ -1330,7 +1311,7 @@ static int denali_ecc_calculate(struct mtd_info *mtd, const uint8_t *data,
 				uint8_t *ecc_code)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	dev_err(&denali->dev->dev,
+	dev_err(denali->dev,
 			"denali_ecc_calculate called unexpectedly\n");
 	BUG();
 	return -EIO;
@@ -1340,7 +1321,7 @@ static int denali_ecc_correct(struct mtd_info *mtd, uint8_t *data,
 				uint8_t *read_ecc, uint8_t *calc_ecc)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	dev_err(&denali->dev->dev,
+	dev_err(denali->dev,
 			"denali_ecc_correct called unexpectedly\n");
 	BUG();
 	return -EIO;
@@ -1349,7 +1330,7 @@ static int denali_ecc_correct(struct mtd_info *mtd, uint8_t *data,
 static void denali_ecc_hwctl(struct mtd_info *mtd, int mode)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	dev_err(&denali->dev->dev,
+	dev_err(denali->dev,
 			"denali_ecc_hwctl called unexpectedly\n");
 	BUG();
 }
@@ -1375,6 +1356,7 @@ static void denali_hw_init(struct denali_nand_info *denali)
 	/* Should set value for these registers when init */
 	iowrite32(0, denali->flash_reg + TWO_ROW_ADDR_CYCLES);
 	iowrite32(1, denali->flash_reg + ECC_ENABLE);
+	detect_max_banks(denali);
 	denali_nand_timing_set(denali);
 	denali_irq_init(denali);
 }
@@ -1484,24 +1466,22 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	}
 
 	/* Is 32-bit DMA supported? */
-	ret = pci_set_dma_mask(dev, DMA_BIT_MASK(32));
-
+	ret = dma_set_mask(&dev->dev, DMA_BIT_MASK(32));
 	if (ret) {
 		printk(KERN_ERR "Spectra: no usable DMA configuration\n");
 		goto failed_enable_dev;
 	}
-	denali->buf.dma_buf =
-		pci_map_single(dev, denali->buf.buf,
-						DENALI_BUF_SIZE,
-						PCI_DMA_BIDIRECTIONAL);
+	denali->buf.dma_buf = dma_map_single(&dev->dev, denali->buf.buf,
+					     DENALI_BUF_SIZE,
+					     DMA_BIDIRECTIONAL);
 
-	if (pci_dma_mapping_error(dev, denali->buf.dma_buf)) {
+	if (dma_mapping_error(&dev->dev, denali->buf.dma_buf)) {
 		dev_err(&dev->dev, "Spectra: failed to map DMA buffer\n");
 		goto failed_enable_dev;
 	}
 
 	pci_set_master(dev);
-	denali->dev = dev;
+	denali->dev = &dev->dev;
 	denali->mtd.dev.parent = &dev->dev;
 
 	ret = pci_request_regions(dev, DENALI_NAND_NAME);
@@ -1554,7 +1534,7 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	/* scan for NAND devices attached to the controller
 	 * this is the first stage in a two step process to register
 	 * with the nand subsystem */
-	if (nand_scan_ident(&denali->mtd, LLD_MAX_FLASH_BANKS, NULL)) {
+	if (nand_scan_ident(&denali->mtd, denali->max_banks, NULL)) {
 		ret = -ENXIO;
 		goto failed_req_irq;
 	}
@@ -1664,7 +1644,7 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		goto failed_req_irq;
 	}
 
-	ret = add_mtd_device(&denali->mtd);
+	ret = mtd_device_register(&denali->mtd, NULL, 0);
 	if (ret) {
 		dev_err(&dev->dev, "Spectra: Failed to register MTD: %d\n",
 				ret);
@@ -1681,8 +1661,8 @@ failed_remap_reg:
 failed_req_regions:
 	pci_release_regions(dev);
 failed_dma_map:
-	pci_unmap_single(dev, denali->buf.dma_buf, DENALI_BUF_SIZE,
-							PCI_DMA_BIDIRECTIONAL);
+	dma_unmap_single(&dev->dev, denali->buf.dma_buf, DENALI_BUF_SIZE,
+			 DMA_BIDIRECTIONAL);
 failed_enable_dev:
 	pci_disable_device(dev);
 failed_alloc_memery:
@@ -1696,7 +1676,7 @@ static void denali_pci_remove(struct pci_dev *dev)
 	struct denali_nand_info *denali = pci_get_drvdata(dev);
 
 	nand_release(&denali->mtd);
-	del_mtd_device(&denali->mtd);
+	mtd_device_unregister(&denali->mtd);
 
 	denali_irq_cleanup(dev->irq, denali);
 
@@ -1704,8 +1684,8 @@ static void denali_pci_remove(struct pci_dev *dev)
 	iounmap(denali->flash_mem);
 	pci_release_regions(dev);
 	pci_disable_device(dev);
-	pci_unmap_single(dev, denali->buf.dma_buf, DENALI_BUF_SIZE,
-							PCI_DMA_BIDIRECTIONAL);
+	dma_unmap_single(&dev->dev, denali->buf.dma_buf, DENALI_BUF_SIZE,
+			 DMA_BIDIRECTIONAL);
 	pci_set_drvdata(dev, NULL);
 	kfree(denali);
 }
@@ -1721,8 +1701,7 @@ static struct pci_driver denali_pci_driver = {
 
 static int __devinit denali_init(void)
 {
-	printk(KERN_INFO "Spectra MTD driver built on %s @ %s\n",
-			__DATE__, __TIME__);
+	printk(KERN_INFO "Spectra MTD driver\n");
 	return pci_register_driver(&denali_pci_driver);
 }
 
diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h
index 3918bcb1561e..fabb9d56b39e 100644
--- a/drivers/mtd/nand/denali.h
+++ b/drivers/mtd/nand/denali.h
@@ -211,185 +211,46 @@
 #define TRANSFER_MODE				0x400
 #define     TRANSFER_MODE__VALUE			0x0003
 
-#define INTR_STATUS0				0x410
-#define     INTR_STATUS0__ECC_TRANSACTION_DONE		0x0001
-#define     INTR_STATUS0__ECC_ERR			0x0002
-#define     INTR_STATUS0__DMA_CMD_COMP			0x0004
-#define     INTR_STATUS0__TIME_OUT			0x0008
-#define     INTR_STATUS0__PROGRAM_FAIL			0x0010
-#define     INTR_STATUS0__ERASE_FAIL			0x0020
-#define     INTR_STATUS0__LOAD_COMP			0x0040
-#define     INTR_STATUS0__PROGRAM_COMP			0x0080
-#define     INTR_STATUS0__ERASE_COMP			0x0100
-#define     INTR_STATUS0__PIPE_CPYBCK_CMD_COMP		0x0200
-#define     INTR_STATUS0__LOCKED_BLK			0x0400
-#define     INTR_STATUS0__UNSUP_CMD			0x0800
-#define     INTR_STATUS0__INT_ACT			0x1000
-#define     INTR_STATUS0__RST_COMP			0x2000
-#define     INTR_STATUS0__PIPE_CMD_ERR			0x4000
-#define     INTR_STATUS0__PAGE_XFER_INC			0x8000
-
-#define INTR_EN0					0x420
-#define     INTR_EN0__ECC_TRANSACTION_DONE		0x0001
-#define     INTR_EN0__ECC_ERR				0x0002
-#define     INTR_EN0__DMA_CMD_COMP			0x0004
-#define     INTR_EN0__TIME_OUT				0x0008
-#define     INTR_EN0__PROGRAM_FAIL			0x0010
-#define     INTR_EN0__ERASE_FAIL			0x0020
-#define     INTR_EN0__LOAD_COMP				0x0040
-#define     INTR_EN0__PROGRAM_COMP			0x0080
-#define     INTR_EN0__ERASE_COMP			0x0100
-#define     INTR_EN0__PIPE_CPYBCK_CMD_COMP		0x0200
-#define     INTR_EN0__LOCKED_BLK			0x0400
-#define     INTR_EN0__UNSUP_CMD				0x0800
-#define     INTR_EN0__INT_ACT				0x1000
-#define     INTR_EN0__RST_COMP				0x2000
-#define     INTR_EN0__PIPE_CMD_ERR			0x4000
-#define     INTR_EN0__PAGE_XFER_INC			0x8000
-
-#define PAGE_CNT0				0x430
-#define     PAGE_CNT0__VALUE				0x00ff
-
-#define ERR_PAGE_ADDR0				0x440
-#define     ERR_PAGE_ADDR0__VALUE			0xffff
-
-#define ERR_BLOCK_ADDR0				0x450
-#define     ERR_BLOCK_ADDR0__VALUE			0xffff
-
-#define INTR_STATUS1				0x460
-#define     INTR_STATUS1__ECC_TRANSACTION_DONE		0x0001
-#define     INTR_STATUS1__ECC_ERR			0x0002
-#define     INTR_STATUS1__DMA_CMD_COMP			0x0004
-#define     INTR_STATUS1__TIME_OUT			0x0008
-#define     INTR_STATUS1__PROGRAM_FAIL			0x0010
-#define     INTR_STATUS1__ERASE_FAIL			0x0020
-#define     INTR_STATUS1__LOAD_COMP			0x0040
-#define     INTR_STATUS1__PROGRAM_COMP			0x0080
-#define     INTR_STATUS1__ERASE_COMP			0x0100
-#define     INTR_STATUS1__PIPE_CPYBCK_CMD_COMP		0x0200
-#define     INTR_STATUS1__LOCKED_BLK			0x0400
-#define     INTR_STATUS1__UNSUP_CMD			0x0800
-#define     INTR_STATUS1__INT_ACT			0x1000
-#define     INTR_STATUS1__RST_COMP			0x2000
-#define     INTR_STATUS1__PIPE_CMD_ERR			0x4000
-#define     INTR_STATUS1__PAGE_XFER_INC			0x8000
-
-#define INTR_EN1					0x470
-#define     INTR_EN1__ECC_TRANSACTION_DONE		0x0001
-#define     INTR_EN1__ECC_ERR				0x0002
-#define     INTR_EN1__DMA_CMD_COMP			0x0004
-#define     INTR_EN1__TIME_OUT				0x0008
-#define     INTR_EN1__PROGRAM_FAIL			0x0010
-#define     INTR_EN1__ERASE_FAIL			0x0020
-#define     INTR_EN1__LOAD_COMP				0x0040
-#define     INTR_EN1__PROGRAM_COMP			0x0080
-#define     INTR_EN1__ERASE_COMP			0x0100
-#define     INTR_EN1__PIPE_CPYBCK_CMD_COMP		0x0200
-#define     INTR_EN1__LOCKED_BLK			0x0400
-#define     INTR_EN1__UNSUP_CMD				0x0800
-#define     INTR_EN1__INT_ACT				0x1000
-#define     INTR_EN1__RST_COMP				0x2000
-#define     INTR_EN1__PIPE_CMD_ERR			0x4000
-#define     INTR_EN1__PAGE_XFER_INC			0x8000
-
-#define PAGE_CNT1				0x480
-#define     PAGE_CNT1__VALUE				0x00ff
-
-#define ERR_PAGE_ADDR1				0x490
-#define     ERR_PAGE_ADDR1__VALUE			0xffff
-
-#define ERR_BLOCK_ADDR1				0x4a0
-#define     ERR_BLOCK_ADDR1__VALUE			0xffff
-
-#define INTR_STATUS2				0x4b0
-#define     INTR_STATUS2__ECC_TRANSACTION_DONE		0x0001
-#define     INTR_STATUS2__ECC_ERR			0x0002
-#define     INTR_STATUS2__DMA_CMD_COMP			0x0004
-#define     INTR_STATUS2__TIME_OUT			0x0008
-#define     INTR_STATUS2__PROGRAM_FAIL			0x0010
-#define     INTR_STATUS2__ERASE_FAIL			0x0020
-#define     INTR_STATUS2__LOAD_COMP			0x0040
-#define     INTR_STATUS2__PROGRAM_COMP			0x0080
-#define     INTR_STATUS2__ERASE_COMP			0x0100
-#define     INTR_STATUS2__PIPE_CPYBCK_CMD_COMP		0x0200
-#define     INTR_STATUS2__LOCKED_BLK			0x0400
-#define     INTR_STATUS2__UNSUP_CMD			0x0800
-#define     INTR_STATUS2__INT_ACT			0x1000
-#define     INTR_STATUS2__RST_COMP			0x2000
-#define     INTR_STATUS2__PIPE_CMD_ERR			0x4000
-#define     INTR_STATUS2__PAGE_XFER_INC			0x8000
-
-#define INTR_EN2					0x4c0
-#define     INTR_EN2__ECC_TRANSACTION_DONE		0x0001
-#define     INTR_EN2__ECC_ERR				0x0002
-#define     INTR_EN2__DMA_CMD_COMP			0x0004
-#define     INTR_EN2__TIME_OUT				0x0008
-#define     INTR_EN2__PROGRAM_FAIL			0x0010
-#define     INTR_EN2__ERASE_FAIL			0x0020
-#define     INTR_EN2__LOAD_COMP				0x0040
-#define     INTR_EN2__PROGRAM_COMP			0x0080
-#define     INTR_EN2__ERASE_COMP			0x0100
-#define     INTR_EN2__PIPE_CPYBCK_CMD_COMP		0x0200
-#define     INTR_EN2__LOCKED_BLK			0x0400
-#define     INTR_EN2__UNSUP_CMD				0x0800
-#define     INTR_EN2__INT_ACT				0x1000
-#define     INTR_EN2__RST_COMP				0x2000
-#define     INTR_EN2__PIPE_CMD_ERR			0x4000
-#define     INTR_EN2__PAGE_XFER_INC			0x8000
-
-#define PAGE_CNT2				0x4d0
-#define     PAGE_CNT2__VALUE				0x00ff
-
-#define ERR_PAGE_ADDR2				0x4e0
-#define     ERR_PAGE_ADDR2__VALUE			0xffff
-
-#define ERR_BLOCK_ADDR2				0x4f0
-#define     ERR_BLOCK_ADDR2__VALUE			0xffff
-
-#define INTR_STATUS3				0x500
-#define     INTR_STATUS3__ECC_TRANSACTION_DONE		0x0001
-#define     INTR_STATUS3__ECC_ERR			0x0002
-#define     INTR_STATUS3__DMA_CMD_COMP			0x0004
-#define     INTR_STATUS3__TIME_OUT			0x0008
-#define     INTR_STATUS3__PROGRAM_FAIL			0x0010
-#define     INTR_STATUS3__ERASE_FAIL			0x0020
-#define     INTR_STATUS3__LOAD_COMP			0x0040
-#define     INTR_STATUS3__PROGRAM_COMP			0x0080
-#define     INTR_STATUS3__ERASE_COMP			0x0100
-#define     INTR_STATUS3__PIPE_CPYBCK_CMD_COMP		0x0200
-#define     INTR_STATUS3__LOCKED_BLK			0x0400
-#define     INTR_STATUS3__UNSUP_CMD			0x0800
-#define     INTR_STATUS3__INT_ACT			0x1000
-#define     INTR_STATUS3__RST_COMP			0x2000
-#define     INTR_STATUS3__PIPE_CMD_ERR			0x4000
-#define     INTR_STATUS3__PAGE_XFER_INC			0x8000
-
-#define INTR_EN3					0x510
-#define     INTR_EN3__ECC_TRANSACTION_DONE		0x0001
-#define     INTR_EN3__ECC_ERR				0x0002
-#define     INTR_EN3__DMA_CMD_COMP			0x0004
-#define     INTR_EN3__TIME_OUT				0x0008
-#define     INTR_EN3__PROGRAM_FAIL			0x0010
-#define     INTR_EN3__ERASE_FAIL			0x0020
-#define     INTR_EN3__LOAD_COMP				0x0040
-#define     INTR_EN3__PROGRAM_COMP			0x0080
-#define     INTR_EN3__ERASE_COMP			0x0100
-#define     INTR_EN3__PIPE_CPYBCK_CMD_COMP		0x0200
-#define     INTR_EN3__LOCKED_BLK			0x0400
-#define     INTR_EN3__UNSUP_CMD				0x0800
-#define     INTR_EN3__INT_ACT				0x1000
-#define     INTR_EN3__RST_COMP				0x2000
-#define     INTR_EN3__PIPE_CMD_ERR			0x4000
-#define     INTR_EN3__PAGE_XFER_INC			0x8000
-
-#define PAGE_CNT3				0x520
-#define     PAGE_CNT3__VALUE				0x00ff
-
-#define ERR_PAGE_ADDR3				0x530
-#define     ERR_PAGE_ADDR3__VALUE			0xffff
-
-#define ERR_BLOCK_ADDR3				0x540
-#define     ERR_BLOCK_ADDR3__VALUE			0xffff
+#define INTR_STATUS(__bank)	(0x410 + ((__bank) * 0x50))
+#define INTR_EN(__bank)		(0x420 + ((__bank) * 0x50))
+
+#define     INTR_STATUS__ECC_TRANSACTION_DONE		0x0001
+#define     INTR_STATUS__ECC_ERR			0x0002
+#define     INTR_STATUS__DMA_CMD_COMP			0x0004
+#define     INTR_STATUS__TIME_OUT			0x0008
+#define     INTR_STATUS__PROGRAM_FAIL			0x0010
+#define     INTR_STATUS__ERASE_FAIL			0x0020
+#define     INTR_STATUS__LOAD_COMP			0x0040
+#define     INTR_STATUS__PROGRAM_COMP			0x0080
+#define     INTR_STATUS__ERASE_COMP			0x0100
+#define     INTR_STATUS__PIPE_CPYBCK_CMD_COMP		0x0200
+#define     INTR_STATUS__LOCKED_BLK			0x0400
+#define     INTR_STATUS__UNSUP_CMD			0x0800
+#define     INTR_STATUS__INT_ACT			0x1000
+#define     INTR_STATUS__RST_COMP			0x2000
+#define     INTR_STATUS__PIPE_CMD_ERR			0x4000
+#define     INTR_STATUS__PAGE_XFER_INC			0x8000
+
+#define     INTR_EN__ECC_TRANSACTION_DONE		0x0001
+#define     INTR_EN__ECC_ERR				0x0002
+#define     INTR_EN__DMA_CMD_COMP			0x0004
+#define     INTR_EN__TIME_OUT				0x0008
+#define     INTR_EN__PROGRAM_FAIL			0x0010
+#define     INTR_EN__ERASE_FAIL				0x0020
+#define     INTR_EN__LOAD_COMP				0x0040
+#define     INTR_EN__PROGRAM_COMP			0x0080
+#define     INTR_EN__ERASE_COMP				0x0100
+#define     INTR_EN__PIPE_CPYBCK_CMD_COMP		0x0200
+#define     INTR_EN__LOCKED_BLK				0x0400
+#define     INTR_EN__UNSUP_CMD				0x0800
+#define     INTR_EN__INT_ACT				0x1000
+#define     INTR_EN__RST_COMP				0x2000
+#define     INTR_EN__PIPE_CMD_ERR			0x4000
+#define     INTR_EN__PAGE_XFER_INC			0x8000
+
+#define PAGE_CNT(__bank)	(0x430 + ((__bank) * 0x50))
+#define ERR_PAGE_ADDR(__bank)	(0x440 + ((__bank) * 0x50))
+#define ERR_BLOCK_ADDR(__bank)	(0x450 + ((__bank) * 0x50))
 
 #define DATA_INTR				0x550
 #define     DATA_INTR__WRITE_SPACE_AV			0x0001
@@ -484,141 +345,23 @@
 #define     PTN_INTR_EN__ACCESS_ERROR_BANK3		0x0010
 #define     PTN_INTR_EN__REG_ACCESS_ERROR		0x0020
 
-#define PERM_SRC_ID_0				0x830
-#define     PERM_SRC_ID_0__SRCID			0x00ff
-#define     PERM_SRC_ID_0__DIRECT_ACCESS_ACTIVE		0x0800
-#define     PERM_SRC_ID_0__WRITE_ACTIVE			0x2000
-#define     PERM_SRC_ID_0__READ_ACTIVE			0x4000
-#define     PERM_SRC_ID_0__PARTITION_VALID		0x8000
-
-#define MIN_BLK_ADDR_0				0x840
-#define     MIN_BLK_ADDR_0__VALUE			0xffff
-
-#define MAX_BLK_ADDR_0				0x850
-#define     MAX_BLK_ADDR_0__VALUE			0xffff
-
-#define MIN_MAX_BANK_0				0x860
-#define     MIN_MAX_BANK_0__MIN_VALUE			0x0003
-#define     MIN_MAX_BANK_0__MAX_VALUE			0x000c
-
-#define PERM_SRC_ID_1				0x870
-#define     PERM_SRC_ID_1__SRCID			0x00ff
-#define     PERM_SRC_ID_1__DIRECT_ACCESS_ACTIVE		0x0800
-#define     PERM_SRC_ID_1__WRITE_ACTIVE			0x2000
-#define     PERM_SRC_ID_1__READ_ACTIVE			0x4000
-#define     PERM_SRC_ID_1__PARTITION_VALID		0x8000
-
-#define MIN_BLK_ADDR_1				0x880
-#define     MIN_BLK_ADDR_1__VALUE			0xffff
-
-#define MAX_BLK_ADDR_1				0x890
-#define     MAX_BLK_ADDR_1__VALUE			0xffff
-
-#define MIN_MAX_BANK_1				0x8a0
-#define     MIN_MAX_BANK_1__MIN_VALUE			0x0003
-#define     MIN_MAX_BANK_1__MAX_VALUE			0x000c
-
-#define PERM_SRC_ID_2				0x8b0
-#define     PERM_SRC_ID_2__SRCID			0x00ff
-#define     PERM_SRC_ID_2__DIRECT_ACCESS_ACTIVE		0x0800
-#define     PERM_SRC_ID_2__WRITE_ACTIVE			0x2000
-#define     PERM_SRC_ID_2__READ_ACTIVE			0x4000
-#define     PERM_SRC_ID_2__PARTITION_VALID		0x8000
-
-#define MIN_BLK_ADDR_2				0x8c0
-#define     MIN_BLK_ADDR_2__VALUE			0xffff
-
-#define MAX_BLK_ADDR_2				0x8d0
-#define     MAX_BLK_ADDR_2__VALUE			0xffff
-
-#define MIN_MAX_BANK_2				0x8e0
-#define     MIN_MAX_BANK_2__MIN_VALUE			0x0003
-#define     MIN_MAX_BANK_2__MAX_VALUE			0x000c
-
-#define PERM_SRC_ID_3				0x8f0
-#define     PERM_SRC_ID_3__SRCID			0x00ff
-#define     PERM_SRC_ID_3__DIRECT_ACCESS_ACTIVE		0x0800
-#define     PERM_SRC_ID_3__WRITE_ACTIVE			0x2000
-#define     PERM_SRC_ID_3__READ_ACTIVE			0x4000
-#define     PERM_SRC_ID_3__PARTITION_VALID		0x8000
-
-#define MIN_BLK_ADDR_3				0x900
-#define     MIN_BLK_ADDR_3__VALUE			0xffff
-
-#define MAX_BLK_ADDR_3				0x910
-#define     MAX_BLK_ADDR_3__VALUE			0xffff
-
-#define MIN_MAX_BANK_3				0x920
-#define     MIN_MAX_BANK_3__MIN_VALUE			0x0003
-#define     MIN_MAX_BANK_3__MAX_VALUE			0x000c
-
-#define PERM_SRC_ID_4				0x930
-#define     PERM_SRC_ID_4__SRCID			0x00ff
-#define     PERM_SRC_ID_4__DIRECT_ACCESS_ACTIVE		0x0800
-#define     PERM_SRC_ID_4__WRITE_ACTIVE			0x2000
-#define     PERM_SRC_ID_4__READ_ACTIVE			0x4000
-#define     PERM_SRC_ID_4__PARTITION_VALID		0x8000
-
-#define MIN_BLK_ADDR_4				0x940
-#define     MIN_BLK_ADDR_4__VALUE			0xffff
-
-#define MAX_BLK_ADDR_4				0x950
-#define     MAX_BLK_ADDR_4__VALUE			0xffff
-
-#define MIN_MAX_BANK_4				0x960
-#define     MIN_MAX_BANK_4__MIN_VALUE			0x0003
-#define     MIN_MAX_BANK_4__MAX_VALUE			0x000c
-
-#define PERM_SRC_ID_5				0x970
-#define     PERM_SRC_ID_5__SRCID			0x00ff
-#define     PERM_SRC_ID_5__DIRECT_ACCESS_ACTIVE		0x0800
-#define     PERM_SRC_ID_5__WRITE_ACTIVE			0x2000
-#define     PERM_SRC_ID_5__READ_ACTIVE			0x4000
-#define     PERM_SRC_ID_5__PARTITION_VALID		0x8000
-
-#define MIN_BLK_ADDR_5				0x980
-#define     MIN_BLK_ADDR_5__VALUE			0xffff
-
-#define MAX_BLK_ADDR_5				0x990
-#define     MAX_BLK_ADDR_5__VALUE			0xffff
-
-#define MIN_MAX_BANK_5				0x9a0
-#define     MIN_MAX_BANK_5__MIN_VALUE			0x0003
-#define     MIN_MAX_BANK_5__MAX_VALUE			0x000c
-
-#define PERM_SRC_ID_6				0x9b0
-#define     PERM_SRC_ID_6__SRCID			0x00ff
-#define     PERM_SRC_ID_6__DIRECT_ACCESS_ACTIVE		0x0800
-#define     PERM_SRC_ID_6__WRITE_ACTIVE			0x2000
-#define     PERM_SRC_ID_6__READ_ACTIVE			0x4000
-#define     PERM_SRC_ID_6__PARTITION_VALID		0x8000
-
-#define MIN_BLK_ADDR_6				0x9c0
-#define     MIN_BLK_ADDR_6__VALUE			0xffff
-
-#define MAX_BLK_ADDR_6				0x9d0
-#define     MAX_BLK_ADDR_6__VALUE			0xffff
-
-#define MIN_MAX_BANK_6				0x9e0
-#define     MIN_MAX_BANK_6__MIN_VALUE			0x0003
-#define     MIN_MAX_BANK_6__MAX_VALUE			0x000c
-
-#define PERM_SRC_ID_7				0x9f0
-#define     PERM_SRC_ID_7__SRCID			0x00ff
-#define     PERM_SRC_ID_7__DIRECT_ACCESS_ACTIVE		0x0800
-#define     PERM_SRC_ID_7__WRITE_ACTIVE			0x2000
-#define     PERM_SRC_ID_7__READ_ACTIVE			0x4000
-#define     PERM_SRC_ID_7__PARTITION_VALID		0x8000
+#define PERM_SRC_ID(__bank)	(0x830 + ((__bank) * 0x40))
+#define     PERM_SRC_ID__SRCID				0x00ff
+#define     PERM_SRC_ID__DIRECT_ACCESS_ACTIVE		0x0800
+#define     PERM_SRC_ID__WRITE_ACTIVE			0x2000
+#define     PERM_SRC_ID__READ_ACTIVE			0x4000
+#define     PERM_SRC_ID__PARTITION_VALID		0x8000
+
+#define MIN_BLK_ADDR(__bank)	(0x840 + ((__bank) * 0x40))
+#define     MIN_BLK_ADDR__VALUE				0xffff
+
+#define MAX_BLK_ADDR(__bank)	(0x850 + ((__bank) * 0x40))
+#define     MAX_BLK_ADDR__VALUE				0xffff
+
+#define MIN_MAX_BANK(__bank)	(0x860 + ((__bank) * 0x40))
+#define     MIN_MAX_BANK__MIN_VALUE			0x0003
+#define     MIN_MAX_BANK__MAX_VALUE			0x000c
 
-#define MIN_BLK_ADDR_7				0xa00
-#define     MIN_BLK_ADDR_7__VALUE			0xffff
-
-#define MAX_BLK_ADDR_7				0xa10
-#define     MAX_BLK_ADDR_7__VALUE			0xffff
-
-#define MIN_MAX_BANK_7				0xa20
-#define     MIN_MAX_BANK_7__MIN_VALUE			0x0003
-#define     MIN_MAX_BANK_7__MAX_VALUE			0x000c
 
 /* ffsdefs.h */
 #define CLEAR 0                 /*use this to clear a field instead of "fail"*/
@@ -711,7 +454,6 @@
 #define READ_WRITE_ENABLE_HIGH_COUNT    22
 
 #define ECC_SECTOR_SIZE     512
-#define LLD_MAX_FLASH_BANKS     4
 
 #define DENALI_BUF_SIZE		(NAND_MAX_PAGESIZE + NAND_MAX_OOBSIZE)
 
@@ -732,7 +474,7 @@ struct denali_nand_info {
 	int status;
 	int platform;
 	struct nand_buf buf;
-	struct pci_dev *dev;
+	struct device *dev;
 	int total_used_banks;
 	uint32_t block;  /* stored for future use */
 	uint16_t page;
@@ -751,6 +493,7 @@ struct denali_nand_info {
 	uint32_t totalblks;
 	uint32_t blksperchip;
 	uint32_t bbtskipbytes;
+	uint32_t max_banks;
 };
 
 #endif /*_LLD_NAND_*/
diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c
index 657b9f4b6f9b..7837728d02ff 100644
--- a/drivers/mtd/nand/diskonchip.c
+++ b/drivers/mtd/nand/diskonchip.c
@@ -1360,11 +1360,9 @@ static int __init nftl_scan_bbt(struct mtd_info *mtd)
 	   At least as nand_bbt.c is currently written. */
 	if ((ret = nand_scan_bbt(mtd, NULL)))
 		return ret;
-	add_mtd_device(mtd);
-#ifdef CONFIG_MTD_PARTITIONS
+	mtd_device_register(mtd, NULL, 0);
 	if (!no_autopart)
-		add_mtd_partitions(mtd, parts, numparts);
-#endif
+		mtd_device_register(mtd, parts, numparts);
 	return 0;
 }
 
@@ -1419,11 +1417,9 @@ static int __init inftl_scan_bbt(struct mtd_info *mtd)
 	   autopartitioning, but I want to give it more thought. */
 	if (!numparts)
 		return -EIO;
-	add_mtd_device(mtd);
-#ifdef CONFIG_MTD_PARTITIONS
+	mtd_device_register(mtd, NULL, 0);
 	if (!no_autopart)
-		add_mtd_partitions(mtd, parts, numparts);
-#endif
+		mtd_device_register(mtd, parts, numparts);
 	return 0;
 }
 
@@ -1678,9 +1674,9 @@ static int __init doc_probe(unsigned long physadr)
 		/* DBB note: i believe nand_release is necessary here, as
 		   buffers may have been allocated in nand_base.  Check with
 		   Thomas. FIX ME! */
-		/* nand_release will call del_mtd_device, but we haven't yet
-		   added it.  This is handled without incident by
-		   del_mtd_device, as far as I can tell. */
+		/* nand_release will call mtd_device_unregister, but we
+		   haven't yet added it.  This is handled without incident by
+		   mtd_device_unregister, as far as I can tell. */
 		nand_release(mtd);
 		kfree(mtd);
 		goto fail;
diff --git a/drivers/mtd/nand/edb7312.c b/drivers/mtd/nand/edb7312.c
index 86366bfba9f8..8400d0f6dada 100644
--- a/drivers/mtd/nand/edb7312.c
+++ b/drivers/mtd/nand/edb7312.c
@@ -55,7 +55,6 @@ static unsigned long ep7312_fio_pbase = EP7312_FIO_PBASE;
 static void __iomem *ep7312_pxdr = (void __iomem *)EP7312_PXDR;
 static void __iomem *ep7312_pxddr = (void __iomem *)EP7312_PXDDR;
 
-#ifdef CONFIG_MTD_PARTITIONS
 /*
  * Define static partitions for flash device
  */
@@ -67,8 +66,6 @@ static struct mtd_partition partition_info[] = {
 
 #define NUM_PARTITIONS 1
 
-#endif
-
 /*
  *	hardware specific access to control-lines
  *
@@ -101,9 +98,7 @@ static int ep7312_device_ready(struct mtd_info *mtd)
 	return 1;
 }
 
-#ifdef CONFIG_MTD_PARTITIONS
 const char *part_probes[] = { "cmdlinepart", NULL };
-#endif
 
 /*
  * Main initialization routine
@@ -162,14 +157,12 @@ static int __init ep7312_init(void)
 		kfree(ep7312_mtd);
 		return -ENXIO;
 	}
-#ifdef CONFIG_MTD_PARTITIONS
 	ep7312_mtd->name = "edb7312-nand";
 	mtd_parts_nb = parse_mtd_partitions(ep7312_mtd, part_probes, &mtd_parts, 0);
 	if (mtd_parts_nb > 0)
 		part_type = "command line";
 	else
 		mtd_parts_nb = 0;
-#endif
 	if (mtd_parts_nb == 0) {
 		mtd_parts = partition_info;
 		mtd_parts_nb = NUM_PARTITIONS;
@@ -178,7 +171,7 @@ static int __init ep7312_init(void)
 
 	/* Register the partitions */
 	printk(KERN_NOTICE "Using %s partition definition\n", part_type);
-	add_mtd_partitions(ep7312_mtd, mtd_parts, mtd_parts_nb);
+	mtd_device_register(ep7312_mtd, mtd_parts, mtd_parts_nb);
 
 	/* Return happy */
 	return 0;
diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index 537e380b8dcb..0bb254c7d2b1 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -841,12 +841,9 @@ static int __devinit fsl_elbc_nand_probe(struct platform_device *pdev)
 	struct fsl_elbc_mtd *priv;
 	struct resource res;
 	struct fsl_elbc_fcm_ctrl *elbc_fcm_ctrl;
-
-#ifdef CONFIG_MTD_PARTITIONS
 	static const char *part_probe_types[]
 		= { "cmdlinepart", "RedBoot", NULL };
 	struct mtd_partition *parts;
-#endif
 	int ret;
 	int bank;
 	struct device *dev;
@@ -935,26 +932,19 @@ static int __devinit fsl_elbc_nand_probe(struct platform_device *pdev)
 	if (ret)
 		goto err;
 
-#ifdef CONFIG_MTD_PARTITIONS
 	/* First look for RedBoot table or partitions on the command
 	 * line, these take precedence over device tree information */
 	ret = parse_mtd_partitions(&priv->mtd, part_probe_types, &parts, 0);
 	if (ret < 0)
 		goto err;
 
-#ifdef CONFIG_MTD_OF_PARTS
 	if (ret == 0) {
 		ret = of_mtd_parse_partitions(priv->dev, node, &parts);
 		if (ret < 0)
 			goto err;
 	}
-#endif
 
-	if (ret > 0)
-		add_mtd_partitions(&priv->mtd, parts, ret);
-	else
-#endif
-		add_mtd_device(&priv->mtd);
+	mtd_device_register(&priv->mtd, parts, ret);
 
 	printk(KERN_INFO "eLBC NAND device at 0x%llx, bank %d\n",
 	       (unsigned long long)res.start, priv->bank);
diff --git a/drivers/mtd/nand/fsl_upm.c b/drivers/mtd/nand/fsl_upm.c
index 073ee026a17c..23752fd5bc59 100644
--- a/drivers/mtd/nand/fsl_upm.c
+++ b/drivers/mtd/nand/fsl_upm.c
@@ -33,10 +33,7 @@ struct fsl_upm_nand {
 	struct mtd_info mtd;
 	struct nand_chip chip;
 	int last_ctrl;
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *parts;
-#endif
-
 	struct fsl_upm upm;
 	uint8_t upm_addr_offset;
 	uint8_t upm_cmd_offset;
@@ -161,9 +158,7 @@ static int __devinit fun_chip_init(struct fsl_upm_nand *fun,
 {
 	int ret;
 	struct device_node *flash_np;
-#ifdef CONFIG_MTD_PARTITIONS
 	static const char *part_types[] = { "cmdlinepart", NULL, };
-#endif
 
 	fun->chip.IO_ADDR_R = fun->io_base;
 	fun->chip.IO_ADDR_W = fun->io_base;
@@ -197,7 +192,6 @@ static int __devinit fun_chip_init(struct fsl_upm_nand *fun,
 	if (ret)
 		goto err;
 
-#ifdef CONFIG_MTD_PARTITIONS
 	ret = parse_mtd_partitions(&fun->mtd, part_types, &fun->parts, 0);
 
 #ifdef CONFIG_MTD_OF_PARTS
@@ -207,11 +201,7 @@ static int __devinit fun_chip_init(struct fsl_upm_nand *fun,
 			goto err;
 	}
 #endif
-	if (ret > 0)
-		ret = add_mtd_partitions(&fun->mtd, fun->parts, ret);
-	else
-#endif
-		ret = add_mtd_device(&fun->mtd);
+	ret = mtd_device_register(&fun->mtd, fun->parts, ret);
 err:
 	of_node_put(flash_np);
 	return ret;
diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index 0d45ef3883e8..e9b275ac381c 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -120,8 +120,6 @@ static struct fsmc_eccplace fsmc_ecc4_sp_place = {
 	}
 };
 
-
-#ifdef CONFIG_MTD_PARTITIONS
 /*
  * Default partition tables to be used if the partition information not
  * provided through platform data.
@@ -182,7 +180,6 @@ static struct mtd_partition partition_info_128KB_blk[] = {
 #ifdef CONFIG_MTD_CMDLINE_PARTS
 const char *part_probes[] = { "cmdlinepart", NULL };
 #endif
-#endif
 
 /**
  * struct fsmc_nand_data - structure for FSMC NAND device state
@@ -719,7 +716,6 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	 * platform data,
 	 * default partition information present in driver.
 	 */
-#ifdef CONFIG_MTD_PARTITIONS
 #ifdef CONFIG_MTD_CMDLINE_PARTS
 	/*
 	 * Check if partition info passed via command line
@@ -777,19 +773,10 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	}
 #endif
 
-	if (host->partitions) {
-		ret = add_mtd_partitions(&host->mtd, host->partitions,
-				host->nr_partitions);
-		if (ret)
-			goto err_probe;
-	}
-#else
-	dev_info(&pdev->dev, "Registering %s as whole device\n", mtd->name);
-	if (!add_mtd_device(mtd)) {
-		ret = -ENXIO;
+	ret = mtd_device_register(&host->mtd, host->partitions,
+				  host->nr_partitions);
+	if (ret)
 		goto err_probe;
-	}
-#endif
 
 	platform_set_drvdata(pdev, host);
 	dev_info(&pdev->dev, "FSMC NAND driver registration successful\n");
@@ -835,11 +822,7 @@ static int fsmc_nand_remove(struct platform_device *pdev)
 	platform_set_drvdata(pdev, NULL);
 
 	if (host) {
-#ifdef CONFIG_MTD_PARTITIONS
-		del_mtd_partitions(&host->mtd);
-#else
-		del_mtd_device(&host->mtd);
-#endif
+		mtd_device_unregister(&host->mtd);
 		clk_disable(host->clk);
 		clk_put(host->clk);
 
diff --git a/drivers/mtd/nand/gpio.c b/drivers/mtd/nand/gpio.c
index 0cde618bcc1e..2c2060b2800e 100644
--- a/drivers/mtd/nand/gpio.c
+++ b/drivers/mtd/nand/gpio.c
@@ -316,8 +316,8 @@ static int __devinit gpio_nand_probe(struct platform_device *dev)
 		gpiomtd->plat.adjust_parts(&gpiomtd->plat,
 					   gpiomtd->mtd_info.size);
 
-	add_mtd_partitions(&gpiomtd->mtd_info, gpiomtd->plat.parts,
-			   gpiomtd->plat.num_parts);
+	mtd_device_register(&gpiomtd->mtd_info, gpiomtd->plat.parts,
+			    gpiomtd->plat.num_parts);
 	platform_set_drvdata(dev, gpiomtd);
 
 	return 0;
diff --git a/drivers/mtd/nand/h1910.c b/drivers/mtd/nand/h1910.c
index f8ce79b446ed..02a03e67109c 100644
--- a/drivers/mtd/nand/h1910.c
+++ b/drivers/mtd/nand/h1910.c
@@ -38,7 +38,6 @@ static struct mtd_info *h1910_nand_mtd = NULL;
  * Module stuff
  */
 
-#ifdef CONFIG_MTD_PARTITIONS
 /*
  * Define static partitions for flash device
  */
@@ -50,8 +49,6 @@ static struct mtd_partition partition_info[] = {
 
 #define NUM_PARTITIONS 1
 
-#endif
-
 /*
  *	hardware specific access to control-lines
  *
@@ -154,7 +151,7 @@ static int __init h1910_init(void)
 
 	/* Register the partitions */
 	printk(KERN_NOTICE "Using %s partition definition\n", part_type);
-	add_mtd_partitions(h1910_nand_mtd, mtd_parts, mtd_parts_nb);
+	mtd_device_register(h1910_nand_mtd, mtd_parts, mtd_parts_nb);
 
 	/* Return happy */
 	return 0;
diff --git a/drivers/mtd/nand/jz4740_nand.c b/drivers/mtd/nand/jz4740_nand.c
index cea38a5d4ac5..6e813daed068 100644
--- a/drivers/mtd/nand/jz4740_nand.c
+++ b/drivers/mtd/nand/jz4740_nand.c
@@ -299,10 +299,8 @@ static int __devinit jz_nand_probe(struct platform_device *pdev)
 	struct nand_chip *chip;
 	struct mtd_info *mtd;
 	struct jz_nand_platform_data *pdata = pdev->dev.platform_data;
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *partition_info;
 	int num_partitions = 0;
-#endif
 
 	nand = kzalloc(sizeof(*nand), GFP_KERNEL);
 	if (!nand) {
@@ -375,7 +373,6 @@ static int __devinit jz_nand_probe(struct platform_device *pdev)
 		goto err_gpio_free;
 	}
 
-#ifdef CONFIG_MTD_PARTITIONS
 #ifdef CONFIG_MTD_CMDLINE_PARTS
 	num_partitions = parse_mtd_partitions(mtd, part_probes,
 						&partition_info, 0);
@@ -384,12 +381,7 @@ static int __devinit jz_nand_probe(struct platform_device *pdev)
 		num_partitions = pdata->num_partitions;
 		partition_info = pdata->partitions;
 	}
-
-	if (num_partitions > 0)
-		ret = add_mtd_partitions(mtd, partition_info, num_partitions);
-	else
-#endif
-	ret = add_mtd_device(mtd);
+	ret = mtd_device_register(mtd, partition_info, num_partitions);
 
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to add mtd device\n");
diff --git a/drivers/mtd/nand/mpc5121_nfc.c b/drivers/mtd/nand/mpc5121_nfc.c
index 0b81b5b499d1..2f7c930872f9 100644
--- a/drivers/mtd/nand/mpc5121_nfc.c
+++ b/drivers/mtd/nand/mpc5121_nfc.c
@@ -131,9 +131,7 @@ struct mpc5121_nfc_prv {
 
 static void mpc5121_nfc_done(struct mtd_info *mtd);
 
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *mpc5121_nfc_pprobes[] = { "cmdlinepart", NULL };
-#endif
 
 /* Read NFC register */
 static inline u16 nfc_read(struct mtd_info *mtd, uint reg)
@@ -658,9 +656,7 @@ static int __devinit mpc5121_nfc_probe(struct platform_device *op)
 	struct mpc5121_nfc_prv *prv;
 	struct resource res;
 	struct mtd_info *mtd;
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *parts;
-#endif
 	struct nand_chip *chip;
 	unsigned long regs_paddr, regs_size;
 	const __be32 *chips_no;
@@ -841,7 +837,6 @@ static int __devinit mpc5121_nfc_probe(struct platform_device *op)
 	dev_set_drvdata(dev, mtd);
 
 	/* Register device in MTD */
-#ifdef CONFIG_MTD_PARTITIONS
 	retval = parse_mtd_partitions(mtd, mpc5121_nfc_pprobes, &parts, 0);
 #ifdef CONFIG_MTD_OF_PARTS
 	if (retval == 0)
@@ -854,12 +849,7 @@ static int __devinit mpc5121_nfc_probe(struct platform_device *op)
 		goto error;
 	}
 
-	if (retval > 0)
-		retval = add_mtd_partitions(mtd, parts, retval);
-	else
-#endif
-		retval = add_mtd_device(mtd);
-
+	retval = mtd_device_register(mtd, parts, retval);
 	if (retval) {
 		dev_err(dev, "Error adding MTD device!\n");
 		devm_free_irq(dev, prv->irq, mtd);
diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c
index 42a95fb41504..90df34c4d26c 100644
--- a/drivers/mtd/nand/mxc_nand.c
+++ b/drivers/mtd/nand/mxc_nand.c
@@ -56,8 +56,14 @@
 #define NFC_V1_V2_WRPROT		(host->regs + 0x12)
 #define NFC_V1_UNLOCKSTART_BLKADDR	(host->regs + 0x14)
 #define NFC_V1_UNLOCKEND_BLKADDR	(host->regs + 0x16)
-#define NFC_V21_UNLOCKSTART_BLKADDR	(host->regs + 0x20)
-#define NFC_V21_UNLOCKEND_BLKADDR	(host->regs + 0x22)
+#define NFC_V21_UNLOCKSTART_BLKADDR0	(host->regs + 0x20)
+#define NFC_V21_UNLOCKSTART_BLKADDR1	(host->regs + 0x24)
+#define NFC_V21_UNLOCKSTART_BLKADDR2	(host->regs + 0x28)
+#define NFC_V21_UNLOCKSTART_BLKADDR3	(host->regs + 0x2c)
+#define NFC_V21_UNLOCKEND_BLKADDR0	(host->regs + 0x22)
+#define NFC_V21_UNLOCKEND_BLKADDR1	(host->regs + 0x26)
+#define NFC_V21_UNLOCKEND_BLKADDR2	(host->regs + 0x2a)
+#define NFC_V21_UNLOCKEND_BLKADDR3	(host->regs + 0x2e)
 #define NFC_V1_V2_NF_WRPRST		(host->regs + 0x18)
 #define NFC_V1_V2_CONFIG1		(host->regs + 0x1a)
 #define NFC_V1_V2_CONFIG2		(host->regs + 0x1c)
@@ -152,6 +158,7 @@ struct mxc_nand_host {
 	int			clk_act;
 	int			irq;
 	int			eccsize;
+	int			active_cs;
 
 	struct completion	op_completion;
 
@@ -236,9 +243,7 @@ static struct nand_ecclayout nandv2_hw_eccoob_4k = {
 	}
 };
 
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *part_probes[] = { "RedBoot", "cmdlinepart", NULL };
-#endif
 
 static irqreturn_t mxc_nfc_irq(int irq, void *dev_id)
 {
@@ -445,7 +450,7 @@ static void send_page_v1_v2(struct mtd_info *mtd, unsigned int ops)
 	for (i = 0; i < bufs; i++) {
 
 		/* NANDFC buffer 0 is used for page read/write */
-		writew(i, NFC_V1_V2_BUF_ADDR);
+		writew((host->active_cs << 4) | i, NFC_V1_V2_BUF_ADDR);
 
 		writew(ops, NFC_V1_V2_CONFIG2);
 
@@ -470,7 +475,7 @@ static void send_read_id_v1_v2(struct mxc_nand_host *host)
 	struct nand_chip *this = &host->nand;
 
 	/* NANDFC buffer 0 is used for device ID output */
-	writew(0x0, NFC_V1_V2_BUF_ADDR);
+	writew(host->active_cs << 4, NFC_V1_V2_BUF_ADDR);
 
 	writew(NFC_ID, NFC_V1_V2_CONFIG2);
 
@@ -505,7 +510,7 @@ static uint16_t get_dev_status_v1_v2(struct mxc_nand_host *host)
 	uint32_t store;
 	uint16_t ret;
 
-	writew(0x0, NFC_V1_V2_BUF_ADDR);
+	writew(host->active_cs << 4, NFC_V1_V2_BUF_ADDR);
 
 	/*
 	 * The device status is stored in main_area0. To
@@ -686,24 +691,24 @@ static void mxc_nand_select_chip(struct mtd_info *mtd, int chip)
 	struct nand_chip *nand_chip = mtd->priv;
 	struct mxc_nand_host *host = nand_chip->priv;
 
-	switch (chip) {
-	case -1:
+	if (chip == -1) {
 		/* Disable the NFC clock */
 		if (host->clk_act) {
 			clk_disable(host->clk);
 			host->clk_act = 0;
 		}
-		break;
-	case 0:
+		return;
+	}
+
+	if (!host->clk_act) {
 		/* Enable the NFC clock */
-		if (!host->clk_act) {
-			clk_enable(host->clk);
-			host->clk_act = 1;
-		}
-		break;
+		clk_enable(host->clk);
+		host->clk_act = 1;
+	}
 
-	default:
-		break;
+	if (nfc_is_v21()) {
+		host->active_cs = chip;
+		writew(host->active_cs << 4, NFC_V1_V2_BUF_ADDR);
 	}
 }
 
@@ -834,8 +839,14 @@ static void preset_v1_v2(struct mtd_info *mtd)
 
 	/* Blocks to be unlocked */
 	if (nfc_is_v21()) {
-		writew(0x0, NFC_V21_UNLOCKSTART_BLKADDR);
-		writew(0xffff, NFC_V21_UNLOCKEND_BLKADDR);
+		writew(0x0, NFC_V21_UNLOCKSTART_BLKADDR0);
+		writew(0x0, NFC_V21_UNLOCKSTART_BLKADDR1);
+		writew(0x0, NFC_V21_UNLOCKSTART_BLKADDR2);
+		writew(0x0, NFC_V21_UNLOCKSTART_BLKADDR3);
+		writew(0xffff, NFC_V21_UNLOCKEND_BLKADDR0);
+		writew(0xffff, NFC_V21_UNLOCKEND_BLKADDR1);
+		writew(0xffff, NFC_V21_UNLOCKEND_BLKADDR2);
+		writew(0xffff, NFC_V21_UNLOCKEND_BLKADDR3);
 	} else if (nfc_is_v1()) {
 		writew(0x0, NFC_V1_UNLOCKSTART_BLKADDR);
 		writew(0x4000, NFC_V1_UNLOCKEND_BLKADDR);
@@ -1200,7 +1211,7 @@ static int __init mxcnd_probe(struct platform_device *pdev)
 		irq_control_v1_v2(host, 1);
 
 	/* first scan to find the device and get the page size */
-	if (nand_scan_ident(mtd, 1, NULL)) {
+	if (nand_scan_ident(mtd, nfc_is_v21() ? 4 : 1, NULL)) {
 		err = -ENXIO;
 		goto escan;
 	}
@@ -1220,18 +1231,15 @@ static int __init mxcnd_probe(struct platform_device *pdev)
 	}
 
 	/* Register the partitions */
-#ifdef CONFIG_MTD_PARTITIONS
 	nr_parts =
 	    parse_mtd_partitions(mtd, part_probes, &host->parts, 0);
 	if (nr_parts > 0)
-		add_mtd_partitions(mtd, host->parts, nr_parts);
+		mtd_device_register(mtd, host->parts, nr_parts);
 	else if (pdata->parts)
-		add_mtd_partitions(mtd, pdata->parts, pdata->nr_parts);
-	else
-#endif
-	{
+		mtd_device_register(mtd, pdata->parts, pdata->nr_parts);
+	else {
 		pr_info("Registering %s as whole device\n", mtd->name);
-		add_mtd_device(mtd);
+		mtd_device_register(mtd, NULL, 0);
 	}
 
 	platform_set_drvdata(pdev, host);
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index c54a4cbac6bc..a46e9bb847bd 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -47,10 +47,7 @@
 #include <linux/bitops.h>
 #include <linux/leds.h>
 #include <linux/io.h>
-
-#ifdef CONFIG_MTD_PARTITIONS
 #include <linux/mtd/partitions.h>
-#endif
 
 /* Define default oob placement schemes for large and small page devices */
 static struct nand_ecclayout nand_oob_8 = {
@@ -976,9 +973,6 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	ret = __nand_unlock(mtd, ofs, len, 0);
 
 out:
-	/* de-select the NAND device */
-	chip->select_chip(mtd, -1);
-
 	nand_release_device(mtd);
 
 	return ret;
@@ -1046,9 +1040,6 @@ int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	ret = __nand_unlock(mtd, ofs, len, 0x1);
 
 out:
-	/* de-select the NAND device */
-	chip->select_chip(mtd, -1);
-
 	nand_release_device(mtd);
 
 	return ret;
@@ -3112,6 +3103,8 @@ ident_done:
 		chip->chip_shift += 32 - 1;
 	}
 
+	chip->badblockbits = 8;
+
 	/* Set the bad block position */
 	if (mtd->writesize > 512 || (busw & NAND_BUSWIDTH_16))
 		chip->badblockpos = NAND_LARGE_BADBLOCK_POS;
@@ -3539,12 +3532,7 @@ void nand_release(struct mtd_info *mtd)
 	if (chip->ecc.mode == NAND_ECC_SOFT_BCH)
 		nand_bch_free((struct nand_bch_control *)chip->ecc.priv);
 
-#ifdef CONFIG_MTD_PARTITIONS
-	/* Deregister partitions */
-	del_mtd_partitions(mtd);
-#endif
-	/* Deregister the device */
-	del_mtd_device(mtd);
+	mtd_device_unregister(mtd);
 
 	/* Free bad block table memory */
 	kfree(chip->bbt);
diff --git a/drivers/mtd/nand/nand_bbt.c b/drivers/mtd/nand/nand_bbt.c
index af46428286fe..ccbeaa1e4a8e 100644
--- a/drivers/mtd/nand/nand_bbt.c
+++ b/drivers/mtd/nand/nand_bbt.c
@@ -1276,20 +1276,6 @@ int nand_update_bbt(struct mtd_info *mtd, loff_t offs)
  * while scanning a device for factory marked good / bad blocks. */
 static uint8_t scan_ff_pattern[] = { 0xff, 0xff };
 
-static struct nand_bbt_descr smallpage_flashbased = {
-	.options = NAND_BBT_SCAN2NDPAGE,
-	.offs = NAND_SMALL_BADBLOCK_POS,
-	.len = 1,
-	.pattern = scan_ff_pattern
-};
-
-static struct nand_bbt_descr largepage_flashbased = {
-	.options = NAND_BBT_SCAN2NDPAGE,
-	.offs = NAND_LARGE_BADBLOCK_POS,
-	.len = 2,
-	.pattern = scan_ff_pattern
-};
-
 static uint8_t scan_agand_pattern[] = { 0x1C, 0x71, 0xC7, 0x1C, 0x71, 0xC7 };
 
 static struct nand_bbt_descr agand_flashbased = {
@@ -1355,10 +1341,6 @@ static struct nand_bbt_descr bbt_mirror_no_bbt_descr = {
  * this->badblock_pattern. Thus, this->badblock_pattern should be NULL when
  * passed to this function.
  *
- * TODO: Handle other flags, replace other static structs
- *        (e.g. handle NAND_BBT_FLASH for flash-based BBT,
- *             replace smallpage_flashbased)
- *
  */
 static int nand_create_default_bbt_descr(struct nand_chip *this)
 {
@@ -1422,15 +1404,14 @@ int nand_default_bbt(struct mtd_info *mtd)
 				this->bbt_md = &bbt_mirror_descr;
 			}
 		}
-		if (!this->badblock_pattern) {
-			this->badblock_pattern = (mtd->writesize > 512) ? &largepage_flashbased : &smallpage_flashbased;
-		}
 	} else {
 		this->bbt_td = NULL;
 		this->bbt_md = NULL;
-		if (!this->badblock_pattern)
-			nand_create_default_bbt_descr(this);
 	}
+
+	if (!this->badblock_pattern)
+		nand_create_default_bbt_descr(this);
+
 	return nand_scan_bbt(mtd, this->badblock_pattern);
 }
 
diff --git a/drivers/mtd/nand/nandsim.c b/drivers/mtd/nand/nandsim.c
index 893d95bfea48..357e8c5252a8 100644
--- a/drivers/mtd/nand/nandsim.c
+++ b/drivers/mtd/nand/nandsim.c
@@ -2383,7 +2383,9 @@ static int __init ns_init_module(void)
 		goto err_exit;
 
 	/* Register NAND partitions */
-	if ((retval = add_mtd_partitions(nsmtd, &nand->partitions[0], nand->nbparts)) != 0)
+	retval = mtd_device_register(nsmtd, &nand->partitions[0],
+				     nand->nbparts);
+	if (retval != 0)
 		goto err_exit;
 
         return 0;
diff --git a/drivers/mtd/nand/ndfc.c b/drivers/mtd/nand/ndfc.c
index bbe6d451290d..ea2dea8a9c88 100644
--- a/drivers/mtd/nand/ndfc.c
+++ b/drivers/mtd/nand/ndfc.c
@@ -33,6 +33,7 @@
 #include <linux/of_platform.h>
 #include <asm/io.h>
 
+#define NDFC_MAX_CS    4
 
 struct ndfc_controller {
 	struct platform_device *ofdev;
@@ -41,17 +42,16 @@ struct ndfc_controller {
 	struct nand_chip chip;
 	int chip_select;
 	struct nand_hw_control ndfc_control;
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *parts;
-#endif
 };
 
-static struct ndfc_controller ndfc_ctrl;
+static struct ndfc_controller ndfc_ctrl[NDFC_MAX_CS];
 
 static void ndfc_select_chip(struct mtd_info *mtd, int chip)
 {
 	uint32_t ccr;
-	struct ndfc_controller *ndfc = &ndfc_ctrl;
+	struct nand_chip *nchip = mtd->priv;
+	struct ndfc_controller *ndfc = nchip->priv;
 
 	ccr = in_be32(ndfc->ndfcbase + NDFC_CCR);
 	if (chip >= 0) {
@@ -64,7 +64,8 @@ static void ndfc_select_chip(struct mtd_info *mtd, int chip)
 
 static void ndfc_hwcontrol(struct mtd_info *mtd, int cmd, unsigned int ctrl)
 {
-	struct ndfc_controller *ndfc = &ndfc_ctrl;
+	struct nand_chip *chip = mtd->priv;
+	struct ndfc_controller *ndfc = chip->priv;
 
 	if (cmd == NAND_CMD_NONE)
 		return;
@@ -77,7 +78,8 @@ static void ndfc_hwcontrol(struct mtd_info *mtd, int cmd, unsigned int ctrl)
 
 static int ndfc_ready(struct mtd_info *mtd)
 {
-	struct ndfc_controller *ndfc = &ndfc_ctrl;
+	struct nand_chip *chip = mtd->priv;
+	struct ndfc_controller *ndfc = chip->priv;
 
 	return in_be32(ndfc->ndfcbase + NDFC_STAT) & NDFC_STAT_IS_READY;
 }
@@ -85,7 +87,8 @@ static int ndfc_ready(struct mtd_info *mtd)
 static void ndfc_enable_hwecc(struct mtd_info *mtd, int mode)
 {
 	uint32_t ccr;
-	struct ndfc_controller *ndfc = &ndfc_ctrl;
+	struct nand_chip *chip = mtd->priv;
+	struct ndfc_controller *ndfc = chip->priv;
 
 	ccr = in_be32(ndfc->ndfcbase + NDFC_CCR);
 	ccr |= NDFC_CCR_RESET_ECC;
@@ -96,7 +99,8 @@ static void ndfc_enable_hwecc(struct mtd_info *mtd, int mode)
 static int ndfc_calculate_ecc(struct mtd_info *mtd,
 			      const u_char *dat, u_char *ecc_code)
 {
-	struct ndfc_controller *ndfc = &ndfc_ctrl;
+	struct nand_chip *chip = mtd->priv;
+	struct ndfc_controller *ndfc = chip->priv;
 	uint32_t ecc;
 	uint8_t *p = (uint8_t *)&ecc;
 
@@ -119,7 +123,8 @@ static int ndfc_calculate_ecc(struct mtd_info *mtd,
  */
 static void ndfc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 {
-	struct ndfc_controller *ndfc = &ndfc_ctrl;
+	struct nand_chip *chip = mtd->priv;
+	struct ndfc_controller *ndfc = chip->priv;
 	uint32_t *p = (uint32_t *) buf;
 
 	for(;len > 0; len -= 4)
@@ -128,7 +133,8 @@ static void ndfc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 
 static void ndfc_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 {
-	struct ndfc_controller *ndfc = &ndfc_ctrl;
+	struct nand_chip *chip = mtd->priv;
+	struct ndfc_controller *ndfc = chip->priv;
 	uint32_t *p = (uint32_t *) buf;
 
 	for(;len > 0; len -= 4)
@@ -137,7 +143,8 @@ static void ndfc_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 
 static int ndfc_verify_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 {
-	struct ndfc_controller *ndfc = &ndfc_ctrl;
+	struct nand_chip *chip = mtd->priv;
+	struct ndfc_controller *ndfc = chip->priv;
 	uint32_t *p = (uint32_t *) buf;
 
 	for(;len > 0; len -= 4)
@@ -152,13 +159,11 @@ static int ndfc_verify_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 static int ndfc_chip_init(struct ndfc_controller *ndfc,
 			  struct device_node *node)
 {
-#ifdef CONFIG_MTD_PARTITIONS
 #ifdef CONFIG_MTD_CMDLINE_PARTS
 	static const char *part_types[] = { "cmdlinepart", NULL };
 #else
 	static const char *part_types[] = { NULL };
 #endif
-#endif
 	struct device_node *flash_np;
 	struct nand_chip *chip = &ndfc->chip;
 	int ret;
@@ -179,6 +184,7 @@ static int ndfc_chip_init(struct ndfc_controller *ndfc,
 	chip->ecc.mode = NAND_ECC_HW;
 	chip->ecc.size = 256;
 	chip->ecc.bytes = 3;
+	chip->priv = ndfc;
 
 	ndfc->mtd.priv = chip;
 	ndfc->mtd.owner = THIS_MODULE;
@@ -198,25 +204,18 @@ static int ndfc_chip_init(struct ndfc_controller *ndfc,
 	if (ret)
 		goto err;
 
-#ifdef CONFIG_MTD_PARTITIONS
 	ret = parse_mtd_partitions(&ndfc->mtd, part_types, &ndfc->parts, 0);
 	if (ret < 0)
 		goto err;
 
-#ifdef CONFIG_MTD_OF_PARTS
 	if (ret == 0) {
 		ret = of_mtd_parse_partitions(&ndfc->ofdev->dev, flash_np,
 					      &ndfc->parts);
 		if (ret < 0)
 			goto err;
 	}
-#endif
 
-	if (ret > 0)
-		ret = add_mtd_partitions(&ndfc->mtd, ndfc->parts, ret);
-	else
-#endif
-		ret = add_mtd_device(&ndfc->mtd);
+	ret = mtd_device_register(&ndfc->mtd, ndfc->parts, ret);
 
 err:
 	of_node_put(flash_np);
@@ -227,15 +226,10 @@ err:
 
 static int __devinit ndfc_probe(struct platform_device *ofdev)
 {
-	struct ndfc_controller *ndfc = &ndfc_ctrl;
+	struct ndfc_controller *ndfc;
 	const __be32 *reg;
 	u32 ccr;
-	int err, len;
-
-	spin_lock_init(&ndfc->ndfc_control.lock);
-	init_waitqueue_head(&ndfc->ndfc_control.wq);
-	ndfc->ofdev = ofdev;
-	dev_set_drvdata(&ofdev->dev, ndfc);
+	int err, len, cs;
 
 	/* Read the reg property to get the chip select */
 	reg = of_get_property(ofdev->dev.of_node, "reg", &len);
@@ -243,7 +237,20 @@ static int __devinit ndfc_probe(struct platform_device *ofdev)
 		dev_err(&ofdev->dev, "unable read reg property (%d)\n", len);
 		return -ENOENT;
 	}
-	ndfc->chip_select = be32_to_cpu(reg[0]);
+
+	cs = be32_to_cpu(reg[0]);
+	if (cs >= NDFC_MAX_CS) {
+		dev_err(&ofdev->dev, "invalid CS number (%d)\n", cs);
+		return -EINVAL;
+	}
+
+	ndfc = &ndfc_ctrl[cs];
+	ndfc->chip_select = cs;
+
+	spin_lock_init(&ndfc->ndfc_control.lock);
+	init_waitqueue_head(&ndfc->ndfc_control.wq);
+	ndfc->ofdev = ofdev;
+	dev_set_drvdata(&ofdev->dev, ndfc);
 
 	ndfc->ndfcbase = of_iomap(ofdev->dev.of_node, 0);
 	if (!ndfc->ndfcbase) {
diff --git a/drivers/mtd/nand/nomadik_nand.c b/drivers/mtd/nand/nomadik_nand.c
index a045a4a581b6..b6a5c86ab31e 100644
--- a/drivers/mtd/nand/nomadik_nand.c
+++ b/drivers/mtd/nand/nomadik_nand.c
@@ -158,12 +158,7 @@ static int nomadik_nand_probe(struct platform_device *pdev)
 		goto err_unmap;
 	}
 
-#ifdef CONFIG_MTD_PARTITIONS
-	add_mtd_partitions(&host->mtd, pdata->parts, pdata->nparts);
-#else
-	pr_info("Registering %s as whole device\n", mtd->name);
-	add_mtd_device(mtd);
-#endif
+	mtd_device_register(&host->mtd, pdata->parts, pdata->nparts);
 
 	platform_set_drvdata(pdev, host);
 	return 0;
diff --git a/drivers/mtd/nand/nuc900_nand.c b/drivers/mtd/nand/nuc900_nand.c
index 6eddf7361ed7..9c30a0b03171 100644
--- a/drivers/mtd/nand/nuc900_nand.c
+++ b/drivers/mtd/nand/nuc900_nand.c
@@ -321,8 +321,8 @@ static int __devinit nuc900_nand_probe(struct platform_device *pdev)
 		goto fail3;
 	}
 
-	add_mtd_partitions(&(nuc900_nand->mtd), partitions,
-						ARRAY_SIZE(partitions));
+	mtd_device_register(&(nuc900_nand->mtd), partitions,
+			    ARRAY_SIZE(partitions));
 
 	platform_set_drvdata(pdev, nuc900_nand);
 
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index da9a351c9d79..0db2c0e7656a 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -94,9 +94,7 @@
 #define P4e_s(a)	(TF(a & NAND_Ecc_P4e)		<< 0)
 #define P4o_s(a)	(TF(a & NAND_Ecc_P4o)		<< 1)
 
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *part_probes[] = { "cmdlinepart", NULL };
-#endif
 
 /* oob info generated runtime depending on ecc algorithm and layout selected */
 static struct nand_ecclayout omap_oobinfo;
@@ -263,11 +261,10 @@ static void omap_read_buf_pref(struct mtd_info *mtd, u_char *buf, int len)
 	if (ret) {
 		/* PFPW engine is busy, use cpu copy method */
 		if (info->nand.options & NAND_BUSWIDTH_16)
-			omap_read_buf16(mtd, buf, len);
+			omap_read_buf16(mtd, (u_char *)p, len);
 		else
-			omap_read_buf8(mtd, buf, len);
+			omap_read_buf8(mtd, (u_char *)p, len);
 	} else {
-		p = (u32 *) buf;
 		do {
 			r_count = gpmc_read_status(GPMC_PREFETCH_FIFO_CNT);
 			r_count = r_count >> 2;
@@ -293,7 +290,7 @@ static void omap_write_buf_pref(struct mtd_info *mtd,
 						struct omap_nand_info, mtd);
 	uint32_t w_count = 0;
 	int i = 0, ret = 0;
-	u16 *p;
+	u16 *p = (u16 *)buf;
 	unsigned long tim, limit;
 
 	/* take care of subpage writes */
@@ -309,11 +306,10 @@ static void omap_write_buf_pref(struct mtd_info *mtd,
 	if (ret) {
 		/* PFPW engine is busy, use cpu copy method */
 		if (info->nand.options & NAND_BUSWIDTH_16)
-			omap_write_buf16(mtd, buf, len);
+			omap_write_buf16(mtd, (u_char *)p, len);
 		else
-			omap_write_buf8(mtd, buf, len);
+			omap_write_buf8(mtd, (u_char *)p, len);
 	} else {
-		p = (u16 *) buf;
 		while (len) {
 			w_count = gpmc_read_status(GPMC_PREFETCH_FIFO_CNT);
 			w_count = w_count >> 1;
@@ -1073,9 +1069,9 @@ static int __devinit omap_nand_probe(struct platform_device *pdev)
 	/* DIP switches on some boards change between 8 and 16 bit
 	 * bus widths for flash.  Try the other width if the first try fails.
 	 */
-	if (nand_scan(&info->mtd, 1)) {
+	if (nand_scan_ident(&info->mtd, 1, NULL)) {
 		info->nand.options ^= NAND_BUSWIDTH_16;
-		if (nand_scan(&info->mtd, 1)) {
+		if (nand_scan_ident(&info->mtd, 1, NULL)) {
 			err = -ENXIO;
 			goto out_release_mem_region;
 		}
@@ -1101,15 +1097,19 @@ static int __devinit omap_nand_probe(struct platform_device *pdev)
 		info->nand.ecc.layout = &omap_oobinfo;
 	}
 
-#ifdef CONFIG_MTD_PARTITIONS
+	/* second phase scan */
+	if (nand_scan_tail(&info->mtd)) {
+		err = -ENXIO;
+		goto out_release_mem_region;
+	}
+
 	err = parse_mtd_partitions(&info->mtd, part_probes, &info->parts, 0);
 	if (err > 0)
-		add_mtd_partitions(&info->mtd, info->parts, err);
+		mtd_device_register(&info->mtd, info->parts, err);
 	else if (pdata->parts)
-		add_mtd_partitions(&info->mtd, pdata->parts, pdata->nr_parts);
+		mtd_device_register(&info->mtd, pdata->parts, pdata->nr_parts);
 	else
-#endif
-		add_mtd_device(&info->mtd);
+		mtd_device_register(&info->mtd, NULL, 0);
 
 	platform_set_drvdata(pdev, &info->mtd);
 
diff --git a/drivers/mtd/nand/orion_nand.c b/drivers/mtd/nand/orion_nand.c
index da6e75343052..7794d0680f91 100644
--- a/drivers/mtd/nand/orion_nand.c
+++ b/drivers/mtd/nand/orion_nand.c
@@ -21,9 +21,7 @@
 #include <mach/hardware.h>
 #include <plat/orion_nand.h>
 
-#ifdef CONFIG_MTD_CMDLINE_PARTS
 static const char *part_probes[] = { "cmdlinepart", NULL };
-#endif
 
 static void orion_nand_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl)
 {
@@ -83,10 +81,8 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 	struct resource *res;
 	void __iomem *io_base;
 	int ret = 0;
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *partitions = NULL;
 	int num_part = 0;
-#endif
 
 	nc = kzalloc(sizeof(struct nand_chip) + sizeof(struct mtd_info), GFP_KERNEL);
 	if (!nc) {
@@ -136,7 +132,6 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 		goto no_dev;
 	}
 
-#ifdef CONFIG_MTD_PARTITIONS
 #ifdef CONFIG_MTD_CMDLINE_PARTS
 	mtd->name = "orion_nand";
 	num_part = parse_mtd_partitions(mtd, part_probes, &partitions, 0);
@@ -147,14 +142,7 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 		partitions = board->parts;
 	}
 
-	if (partitions && num_part > 0)
-		ret = add_mtd_partitions(mtd, partitions, num_part);
-	else
-		ret = add_mtd_device(mtd);
-#else
-	ret = add_mtd_device(mtd);
-#endif
-
+	ret = mtd_device_register(mtd, partitions, num_part);
 	if (ret) {
 		nand_release(mtd);
 		goto no_dev;
diff --git a/drivers/mtd/nand/pasemi_nand.c b/drivers/mtd/nand/pasemi_nand.c
index 20bfe5f15afd..b1aa41b8a4eb 100644
--- a/drivers/mtd/nand/pasemi_nand.c
+++ b/drivers/mtd/nand/pasemi_nand.c
@@ -163,7 +163,7 @@ static int __devinit pasemi_nand_probe(struct platform_device *ofdev)
 		goto out_lpc;
 	}
 
-	if (add_mtd_device(pasemi_nand_mtd)) {
+	if (mtd_device_register(pasemi_nand_mtd, NULL, 0)) {
 		printk(KERN_ERR "pasemi_nand: Unable to register MTD device\n");
 		err = -ENODEV;
 		goto out_lpc;
diff --git a/drivers/mtd/nand/plat_nand.c b/drivers/mtd/nand/plat_nand.c
index caf5a736340a..633c04bf76f6 100644
--- a/drivers/mtd/nand/plat_nand.c
+++ b/drivers/mtd/nand/plat_nand.c
@@ -21,10 +21,8 @@ struct plat_nand_data {
 	struct nand_chip	chip;
 	struct mtd_info		mtd;
 	void __iomem		*io_base;
-#ifdef CONFIG_MTD_PARTITIONS
 	int			nr_parts;
 	struct mtd_partition	*parts;
-#endif
 };
 
 /*
@@ -101,13 +99,12 @@ static int __devinit plat_nand_probe(struct platform_device *pdev)
 		goto out;
 	}
 
-#ifdef CONFIG_MTD_PARTITIONS
 	if (pdata->chip.part_probe_types) {
 		err = parse_mtd_partitions(&data->mtd,
 					pdata->chip.part_probe_types,
 					&data->parts, 0);
 		if (err > 0) {
-			add_mtd_partitions(&data->mtd, data->parts, err);
+			mtd_device_register(&data->mtd, data->parts, err);
 			return 0;
 		}
 	}
@@ -115,11 +112,10 @@ static int __devinit plat_nand_probe(struct platform_device *pdev)
 		pdata->chip.set_parts(data->mtd.size, &pdata->chip);
 	if (pdata->chip.partitions) {
 		data->parts = pdata->chip.partitions;
-		err = add_mtd_partitions(&data->mtd, data->parts,
+		err = mtd_device_register(&data->mtd, data->parts,
 			pdata->chip.nr_partitions);
 	} else
-#endif
-	err = add_mtd_device(&data->mtd);
+		err = mtd_device_register(&data->mtd, NULL, 0);
 
 	if (!err)
 		return err;
@@ -149,10 +145,8 @@ static int __devexit plat_nand_remove(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 
 	nand_release(&data->mtd);
-#ifdef CONFIG_MTD_PARTITIONS
 	if (data->parts && data->parts != pdata->chip.partitions)
 		kfree(data->parts);
-#endif
 	if (pdata->ctrl.remove)
 		pdata->ctrl.remove(pdev);
 	iounmap(data->io_base);
diff --git a/drivers/mtd/nand/ppchameleonevb.c b/drivers/mtd/nand/ppchameleonevb.c
index cc8658431851..3bbb796b451c 100644
--- a/drivers/mtd/nand/ppchameleonevb.c
+++ b/drivers/mtd/nand/ppchameleonevb.c
@@ -73,7 +73,6 @@ __setup("ppchameleon_fio_pbase=", ppchameleon_fio_pbase);
 __setup("ppchameleonevb_fio_pbase=", ppchameleonevb_fio_pbase);
 #endif
 
-#ifdef CONFIG_MTD_PARTITIONS
 /*
  * Define static partitions for flash devices
  */
@@ -101,7 +100,6 @@ static struct mtd_partition partition_info_evb[] = {
 #define NUM_PARTITIONS 1
 
 extern int parse_cmdline_partitions(struct mtd_info *master, struct mtd_partition **pparts, const char *mtd_id);
-#endif
 
 /*
  *	hardware specific access to control-lines
@@ -189,10 +187,8 @@ static int ppchameleonevb_device_ready(struct mtd_info *minfo)
 }
 #endif
 
-#ifdef CONFIG_MTD_PARTITIONS
 const char *part_probes[] = { "cmdlinepart", NULL };
 const char *part_probes_evb[] = { "cmdlinepart", NULL };
-#endif
 
 /*
  * Main initialization routine
@@ -284,14 +280,13 @@ static int __init ppchameleonevb_init(void)
 		this->chip_delay = NAND_SMALL_DELAY_US;
 #endif
 
-#ifdef CONFIG_MTD_PARTITIONS
 	ppchameleon_mtd->name = "ppchameleon-nand";
 	mtd_parts_nb = parse_mtd_partitions(ppchameleon_mtd, part_probes, &mtd_parts, 0);
 	if (mtd_parts_nb > 0)
 		part_type = "command line";
 	else
 		mtd_parts_nb = 0;
-#endif
+
 	if (mtd_parts_nb == 0) {
 		if (ppchameleon_mtd->size == NAND_SMALL_SIZE)
 			mtd_parts = partition_info_me;
@@ -303,7 +298,7 @@ static int __init ppchameleonevb_init(void)
 
 	/* Register the partitions */
 	printk(KERN_NOTICE "Using %s partition definition\n", part_type);
-	add_mtd_partitions(ppchameleon_mtd, mtd_parts, mtd_parts_nb);
+	mtd_device_register(ppchameleon_mtd, mtd_parts, mtd_parts_nb);
 
  nand_evb_init:
 	/****************************
@@ -385,14 +380,14 @@ static int __init ppchameleonevb_init(void)
 			iounmap(ppchameleon_fio_base);
 		return -ENXIO;
 	}
-#ifdef CONFIG_MTD_PARTITIONS
+
 	ppchameleonevb_mtd->name = NAND_EVB_MTD_NAME;
 	mtd_parts_nb = parse_mtd_partitions(ppchameleonevb_mtd, part_probes_evb, &mtd_parts, 0);
 	if (mtd_parts_nb > 0)
 		part_type = "command line";
 	else
 		mtd_parts_nb = 0;
-#endif
+
 	if (mtd_parts_nb == 0) {
 		mtd_parts = partition_info_evb;
 		mtd_parts_nb = NUM_PARTITIONS;
@@ -401,7 +396,7 @@ static int __init ppchameleonevb_init(void)
 
 	/* Register the partitions */
 	printk(KERN_NOTICE "Using %s partition definition\n", part_type);
-	add_mtd_partitions(ppchameleonevb_mtd, mtd_parts, mtd_parts_nb);
+	mtd_device_register(ppchameleonevb_mtd, mtd_parts, mtd_parts_nb);
 
 	/* Return happy */
 	return 0;
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index ff0701276d65..1fb3b3a80581 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -1119,10 +1119,7 @@ static int pxa3xx_nand_remove(struct platform_device *pdev)
 	clk_put(info->clk);
 
 	if (mtd) {
-		del_mtd_device(mtd);
-#ifdef CONFIG_MTD_PARTITIONS
-		del_mtd_partitions(mtd);
-#endif
+		mtd_device_unregister(mtd);
 		kfree(mtd);
 	}
 	return 0;
@@ -1149,7 +1146,6 @@ static int pxa3xx_nand_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-#ifdef CONFIG_MTD_PARTITIONS
 	if (mtd_has_cmdlinepart()) {
 		const char *probes[] = { "cmdlinepart", NULL };
 		struct mtd_partition *parts;
@@ -1158,13 +1154,10 @@ static int pxa3xx_nand_probe(struct platform_device *pdev)
 		nr_parts = parse_mtd_partitions(info->mtd, probes, &parts, 0);
 
 		if (nr_parts)
-			return add_mtd_partitions(info->mtd, parts, nr_parts);
+			return mtd_device_register(info->mtd, parts, nr_parts);
 	}
 
-	return add_mtd_partitions(info->mtd, pdata->parts, pdata->nr_parts);
-#else
-	return 0;
-#endif
+	return mtd_device_register(info->mtd, pdata->parts, pdata->nr_parts);
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/mtd/nand/rtc_from4.c b/drivers/mtd/nand/rtc_from4.c
index 67440b5beef8..c9f9127ff770 100644
--- a/drivers/mtd/nand/rtc_from4.c
+++ b/drivers/mtd/nand/rtc_from4.c
@@ -580,7 +580,8 @@ static int __init rtc_from4_init(void)
 #endif
 
 	/* Register the partitions */
-	ret = add_mtd_partitions(rtc_from4_mtd, partition_info, NUM_PARTITIONS);
+	ret = mtd_device_register(rtc_from4_mtd, partition_info,
+				  NUM_PARTITIONS);
 	if (ret)
 		goto err_3;
 
diff --git a/drivers/mtd/nand/s3c2410.c b/drivers/mtd/nand/s3c2410.c
index 33d832dddfdd..4405468f196b 100644
--- a/drivers/mtd/nand/s3c2410.c
+++ b/drivers/mtd/nand/s3c2410.c
@@ -55,7 +55,7 @@ static int hardware_ecc = 0;
 #endif
 
 #ifdef CONFIG_MTD_NAND_S3C2410_CLKSTOP
-static int clock_stop = 1;
+static const int clock_stop = 1;
 #else
 static const int clock_stop = 0;
 #endif
@@ -96,6 +96,12 @@ enum s3c_cpu_type {
 	TYPE_S3C2440,
 };
 
+enum s3c_nand_clk_state {
+	CLOCK_DISABLE	= 0,
+	CLOCK_ENABLE,
+	CLOCK_SUSPEND,
+};
+
 /* overview of the s3c2410 nand state */
 
 /**
@@ -111,6 +117,7 @@ enum s3c_cpu_type {
  * @mtd_count: The number of MTDs created from this controller.
  * @save_sel: The contents of @sel_reg to be saved over suspend.
  * @clk_rate: The clock rate from @clk.
+ * @clk_state: The current clock state.
  * @cpu_type: The exact type of this controller.
  */
 struct s3c2410_nand_info {
@@ -129,6 +136,7 @@ struct s3c2410_nand_info {
 	int				mtd_count;
 	unsigned long			save_sel;
 	unsigned long			clk_rate;
+	enum s3c_nand_clk_state		clk_state;
 
 	enum s3c_cpu_type		cpu_type;
 
@@ -159,11 +167,33 @@ static struct s3c2410_platform_nand *to_nand_plat(struct platform_device *dev)
 	return dev->dev.platform_data;
 }
 
-static inline int allow_clk_stop(struct s3c2410_nand_info *info)
+static inline int allow_clk_suspend(struct s3c2410_nand_info *info)
 {
 	return clock_stop;
 }
 
+/**
+ * s3c2410_nand_clk_set_state - Enable, disable or suspend NAND clock.
+ * @info: The controller instance.
+ * @new_state: State to which clock should be set.
+ */
+static void s3c2410_nand_clk_set_state(struct s3c2410_nand_info *info,
+		enum s3c_nand_clk_state new_state)
+{
+	if (!allow_clk_suspend(info) && new_state == CLOCK_SUSPEND)
+		return;
+
+	if (info->clk_state == CLOCK_ENABLE) {
+		if (new_state != CLOCK_ENABLE)
+			clk_disable(info->clk);
+	} else {
+		if (new_state == CLOCK_ENABLE)
+			clk_enable(info->clk);
+	}
+
+	info->clk_state = new_state;
+}
+
 /* timing calculations */
 
 #define NS_IN_KHZ 1000000
@@ -333,8 +363,8 @@ static void s3c2410_nand_select_chip(struct mtd_info *mtd, int chip)
 	nmtd = this->priv;
 	info = nmtd->info;
 
-	if (chip != -1 && allow_clk_stop(info))
-		clk_enable(info->clk);
+	if (chip != -1)
+		s3c2410_nand_clk_set_state(info, CLOCK_ENABLE);
 
 	cur = readl(info->sel_reg);
 
@@ -356,8 +386,8 @@ static void s3c2410_nand_select_chip(struct mtd_info *mtd, int chip)
 
 	writel(cur, info->sel_reg);
 
-	if (chip == -1 && allow_clk_stop(info))
-		clk_disable(info->clk);
+	if (chip == -1)
+		s3c2410_nand_clk_set_state(info, CLOCK_SUSPEND);
 }
 
 /* s3c2410_nand_hwcontrol
@@ -694,8 +724,7 @@ static int s3c24xx_nand_remove(struct platform_device *pdev)
 	/* free the common resources */
 
 	if (info->clk != NULL && !IS_ERR(info->clk)) {
-		if (!allow_clk_stop(info))
-			clk_disable(info->clk);
+		s3c2410_nand_clk_set_state(info, CLOCK_DISABLE);
 		clk_put(info->clk);
 	}
 
@@ -715,7 +744,6 @@ static int s3c24xx_nand_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_MTD_PARTITIONS
 const char *part_probes[] = { "cmdlinepart", NULL };
 static int s3c2410_nand_add_partition(struct s3c2410_nand_info *info,
 				      struct s3c2410_nand_mtd *mtd,
@@ -725,7 +753,7 @@ static int s3c2410_nand_add_partition(struct s3c2410_nand_info *info,
 	int nr_part = 0;
 
 	if (set == NULL)
-		return add_mtd_device(&mtd->mtd);
+		return mtd_device_register(&mtd->mtd, NULL, 0);
 
 	mtd->mtd.name = set->name;
 	nr_part = parse_mtd_partitions(&mtd->mtd, part_probes, &part_info, 0);
@@ -735,19 +763,8 @@ static int s3c2410_nand_add_partition(struct s3c2410_nand_info *info,
 		part_info = set->partitions;
 	}
 
-	if (nr_part > 0 && part_info)
-		return add_mtd_partitions(&mtd->mtd, part_info, nr_part);
-
-	return add_mtd_device(&mtd->mtd);
-}
-#else
-static int s3c2410_nand_add_partition(struct s3c2410_nand_info *info,
-				      struct s3c2410_nand_mtd *mtd,
-				      struct s3c2410_nand_set *set)
-{
-	return add_mtd_device(&mtd->mtd);
+	return mtd_device_register(&mtd->mtd, part_info, nr_part);
 }
-#endif
 
 /**
  * s3c2410_nand_init_chip - initialise a single instance of an chip
@@ -947,7 +964,7 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 		goto exit_error;
 	}
 
-	clk_enable(info->clk);
+	s3c2410_nand_clk_set_state(info, CLOCK_ENABLE);
 
 	/* allocate and map the resource */
 
@@ -1026,9 +1043,9 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 		goto exit_error;
 	}
 
-	if (allow_clk_stop(info)) {
+	if (allow_clk_suspend(info)) {
 		dev_info(&pdev->dev, "clock idle support enabled\n");
-		clk_disable(info->clk);
+		s3c2410_nand_clk_set_state(info, CLOCK_SUSPEND);
 	}
 
 	pr_debug("initialised ok\n");
@@ -1059,8 +1076,7 @@ static int s3c24xx_nand_suspend(struct platform_device *dev, pm_message_t pm)
 
 		writel(info->save_sel | info->sel_bit, info->sel_reg);
 
-		if (!allow_clk_stop(info))
-			clk_disable(info->clk);
+		s3c2410_nand_clk_set_state(info, CLOCK_DISABLE);
 	}
 
 	return 0;
@@ -1072,7 +1088,7 @@ static int s3c24xx_nand_resume(struct platform_device *dev)
 	unsigned long sel;
 
 	if (info) {
-		clk_enable(info->clk);
+		s3c2410_nand_clk_set_state(info, CLOCK_ENABLE);
 		s3c2410_nand_inithw(info);
 
 		/* Restore the state of the nFCE line. */
@@ -1082,8 +1098,7 @@ static int s3c24xx_nand_resume(struct platform_device *dev)
 		sel |= info->save_sel & info->sel_bit;
 		writel(sel, info->sel_reg);
 
-		if (allow_clk_stop(info))
-			clk_disable(info->clk);
+		s3c2410_nand_clk_set_state(info, CLOCK_SUSPEND);
 	}
 
 	return 0;
diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c
index 81bbb5ee148d..93b1f74321c2 100644
--- a/drivers/mtd/nand/sh_flctl.c
+++ b/drivers/mtd/nand/sh_flctl.c
@@ -867,7 +867,7 @@ static int __devinit flctl_probe(struct platform_device *pdev)
 	if (ret)
 		goto err;
 
-	add_mtd_partitions(flctl_mtd, pdata->parts, pdata->nr_parts);
+	mtd_device_register(flctl_mtd, pdata->parts, pdata->nr_parts);
 
 	return 0;
 
diff --git a/drivers/mtd/nand/sharpsl.c b/drivers/mtd/nand/sharpsl.c
index 54ec7542a7b7..19e24ed089ea 100644
--- a/drivers/mtd/nand/sharpsl.c
+++ b/drivers/mtd/nand/sharpsl.c
@@ -103,9 +103,7 @@ static int sharpsl_nand_calculate_ecc(struct mtd_info *mtd, const u_char * dat,
 	return readb(sharpsl->io + ECCCNTR) != 0;
 }
 
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *part_probes[] = { "cmdlinepart", NULL };
-#endif
 
 /*
  * Main initialization routine
@@ -113,10 +111,8 @@ static const char *part_probes[] = { "cmdlinepart", NULL };
 static int __devinit sharpsl_nand_probe(struct platform_device *pdev)
 {
 	struct nand_chip *this;
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *sharpsl_partition_info;
 	int nr_partitions;
-#endif
 	struct resource *r;
 	int err = 0;
 	struct sharpsl_nand *sharpsl;
@@ -188,18 +184,14 @@ static int __devinit sharpsl_nand_probe(struct platform_device *pdev)
 
 	/* Register the partitions */
 	sharpsl->mtd.name = "sharpsl-nand";
-#ifdef CONFIG_MTD_PARTITIONS
 	nr_partitions = parse_mtd_partitions(&sharpsl->mtd, part_probes, &sharpsl_partition_info, 0);
 	if (nr_partitions <= 0) {
 		nr_partitions = data->nr_partitions;
 		sharpsl_partition_info = data->partitions;
 	}
 
-	if (nr_partitions > 0)
-		err = add_mtd_partitions(&sharpsl->mtd, sharpsl_partition_info, nr_partitions);
-	else
-#endif
-	err = add_mtd_device(&sharpsl->mtd);
+	err = mtd_device_register(&sharpsl->mtd, sharpsl_partition_info,
+				  nr_partitions);
 	if (err)
 		goto err_add;
 
diff --git a/drivers/mtd/nand/sm_common.c b/drivers/mtd/nand/sm_common.c
index 57cc80cd01a3..b6332e83b289 100644
--- a/drivers/mtd/nand/sm_common.c
+++ b/drivers/mtd/nand/sm_common.c
@@ -139,7 +139,7 @@ int sm_register_device(struct mtd_info *mtd, int smartmedia)
 	if (ret)
 		return ret;
 
-	return add_mtd_device(mtd);
+	return mtd_device_register(mtd, NULL, 0);
 }
 EXPORT_SYMBOL_GPL(sm_register_device);
 
diff --git a/drivers/mtd/nand/socrates_nand.c b/drivers/mtd/nand/socrates_nand.c
index a853548986f0..ca2d0555729e 100644
--- a/drivers/mtd/nand/socrates_nand.c
+++ b/drivers/mtd/nand/socrates_nand.c
@@ -155,9 +155,7 @@ static int socrates_nand_device_ready(struct mtd_info *mtd)
 	return 1;
 }
 
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *part_probes[] = { "cmdlinepart", NULL };
-#endif
 
 /*
  * Probe for the NAND device.
@@ -168,11 +166,8 @@ static int __devinit socrates_nand_probe(struct platform_device *ofdev)
 	struct mtd_info *mtd;
 	struct nand_chip *nand_chip;
 	int res;
-
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *partitions = NULL;
 	int num_partitions = 0;
-#endif
 
 	/* Allocate memory for the device structure (and zero it) */
 	host = kzalloc(sizeof(struct socrates_nand_host), GFP_KERNEL);
@@ -230,7 +225,6 @@ static int __devinit socrates_nand_probe(struct platform_device *ofdev)
 		goto out;
 	}
 
-#ifdef CONFIG_MTD_PARTITIONS
 #ifdef CONFIG_MTD_CMDLINE_PARTS
 	num_partitions = parse_mtd_partitions(mtd, part_probes,
 					      &partitions, 0);
@@ -240,7 +234,6 @@ static int __devinit socrates_nand_probe(struct platform_device *ofdev)
 	}
 #endif
 
-#ifdef CONFIG_MTD_OF_PARTS
 	if (num_partitions == 0) {
 		num_partitions = of_mtd_parse_partitions(&ofdev->dev,
 							 ofdev->dev.of_node,
@@ -250,19 +243,12 @@ static int __devinit socrates_nand_probe(struct platform_device *ofdev)
 			goto release;
 		}
 	}
-#endif
-	if (partitions && (num_partitions > 0))
-		res = add_mtd_partitions(mtd, partitions, num_partitions);
-	else
-#endif
-		res = add_mtd_device(mtd);
 
+	res = mtd_device_register(mtd, partitions, num_partitions);
 	if (!res)
 		return res;
 
-#ifdef CONFIG_MTD_PARTITIONS
 release:
-#endif
 	nand_release(mtd);
 
 out:
diff --git a/drivers/mtd/nand/spia.c b/drivers/mtd/nand/spia.c
index 0cc6d0acb8fe..bef76cd7c24c 100644
--- a/drivers/mtd/nand/spia.c
+++ b/drivers/mtd/nand/spia.c
@@ -149,7 +149,7 @@ static int __init spia_init(void)
 	}
 
 	/* Register the partitions */
-	add_mtd_partitions(spia_mtd, partition_info, NUM_PARTITIONS);
+	mtd_device_register(spia_mtd, partition_info, NUM_PARTITIONS);
 
 	/* Return happy */
 	return 0;
diff --git a/drivers/mtd/nand/tmio_nand.c b/drivers/mtd/nand/tmio_nand.c
index c004e474631b..11e8371b5683 100644
--- a/drivers/mtd/nand/tmio_nand.c
+++ b/drivers/mtd/nand/tmio_nand.c
@@ -381,10 +381,8 @@ static int tmio_probe(struct platform_device *dev)
 	struct tmio_nand *tmio;
 	struct mtd_info *mtd;
 	struct nand_chip *nand_chip;
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *parts;
 	int nbparts = 0;
-#endif
 	int retval;
 
 	if (data == NULL)
@@ -463,7 +461,6 @@ static int tmio_probe(struct platform_device *dev)
 		goto err_scan;
 	}
 	/* Register the partitions */
-#ifdef CONFIG_MTD_PARTITIONS
 #ifdef CONFIG_MTD_CMDLINE_PARTS
 	nbparts = parse_mtd_partitions(mtd, part_probes, &parts, 0);
 #endif
@@ -472,12 +469,7 @@ static int tmio_probe(struct platform_device *dev)
 		nbparts = data->num_partitions;
 	}
 
-	if (nbparts)
-		retval = add_mtd_partitions(mtd, parts, nbparts);
-	else
-#endif
-	retval = add_mtd_device(mtd);
-
+	retval = mtd_device_register(mtd, parts, nbparts);
 	if (!retval)
 		return retval;
 
diff --git a/drivers/mtd/nand/txx9ndfmc.c b/drivers/mtd/nand/txx9ndfmc.c
index ca270a4881a4..bfba4e39a6c5 100644
--- a/drivers/mtd/nand/txx9ndfmc.c
+++ b/drivers/mtd/nand/txx9ndfmc.c
@@ -74,9 +74,7 @@ struct txx9ndfmc_drvdata {
 	unsigned char hold;	/* in gbusclock */
 	unsigned char spw;	/* in gbusclock */
 	struct nand_hw_control hw_control;
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *parts[MAX_TXX9NDFMC_DEV];
-#endif
 };
 
 static struct platform_device *mtd_to_platdev(struct mtd_info *mtd)
@@ -289,9 +287,7 @@ static int txx9ndfmc_nand_scan(struct mtd_info *mtd)
 static int __init txx9ndfmc_probe(struct platform_device *dev)
 {
 	struct txx9ndfmc_platform_data *plat = dev->dev.platform_data;
-#ifdef CONFIG_MTD_PARTITIONS
 	static const char *probes[] = { "cmdlinepart", NULL };
-#endif
 	int hold, spw;
 	int i;
 	struct txx9ndfmc_drvdata *drvdata;
@@ -337,9 +333,7 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		struct txx9ndfmc_priv *txx9_priv;
 		struct nand_chip *chip;
 		struct mtd_info *mtd;
-#ifdef CONFIG_MTD_PARTITIONS
 		int nr_parts;
-#endif
 
 		if (!(plat->ch_mask & (1 << i)))
 			continue;
@@ -399,13 +393,9 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		}
 		mtd->name = txx9_priv->mtdname;
 
-#ifdef CONFIG_MTD_PARTITIONS
 		nr_parts = parse_mtd_partitions(mtd, probes,
 						&drvdata->parts[i], 0);
-		if (nr_parts > 0)
-			add_mtd_partitions(mtd, drvdata->parts[i], nr_parts);
-#endif
-		add_mtd_device(mtd);
+		mtd_device_register(mtd, drvdata->parts[i], nr_parts);
 		drvdata->mtds[i] = mtd;
 	}
 
@@ -431,9 +421,7 @@ static int __exit txx9ndfmc_remove(struct platform_device *dev)
 		txx9_priv = chip->priv;
 
 		nand_release(mtd);
-#ifdef CONFIG_MTD_PARTITIONS
 		kfree(drvdata->parts[i]);
-#endif
 		kfree(txx9_priv->mtdname);
 		kfree(txx9_priv);
 	}
diff --git a/drivers/mtd/onenand/Kconfig b/drivers/mtd/onenand/Kconfig
index 4f426195f8db..772ad2966619 100644
--- a/drivers/mtd/onenand/Kconfig
+++ b/drivers/mtd/onenand/Kconfig
@@ -1,7 +1,6 @@
 menuconfig MTD_ONENAND
 	tristate "OneNAND Device Support"
 	depends on MTD
-	select MTD_PARTITIONS
 	help
 	  This enables support for accessing all type of OneNAND flash
 	  devices. For further information see
diff --git a/drivers/mtd/onenand/generic.c b/drivers/mtd/onenand/generic.c
index ac08750748a3..2d70d354d846 100644
--- a/drivers/mtd/onenand/generic.c
+++ b/drivers/mtd/onenand/generic.c
@@ -30,9 +30,7 @@
  */
 #define DRIVER_NAME	"onenand-flash"
 
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *part_probes[] = { "cmdlinepart", NULL,  };
-#endif
 
 struct onenand_info {
 	struct mtd_info		mtd;
@@ -75,15 +73,13 @@ static int __devinit generic_onenand_probe(struct platform_device *pdev)
 		goto out_iounmap;
 	}
 
-#ifdef CONFIG_MTD_PARTITIONS
 	err = parse_mtd_partitions(&info->mtd, part_probes, &info->parts, 0);
 	if (err > 0)
-		add_mtd_partitions(&info->mtd, info->parts, err);
+		mtd_device_register(&info->mtd, info->parts, err);
 	else if (err <= 0 && pdata && pdata->parts)
-		add_mtd_partitions(&info->mtd, pdata->parts, pdata->nr_parts);
+		mtd_device_register(&info->mtd, pdata->parts, pdata->nr_parts);
 	else
-#endif
-		err = add_mtd_device(&info->mtd);
+		err = mtd_device_register(&info->mtd, NULL, 0);
 
 	platform_set_drvdata(pdev, info);
 
@@ -108,11 +104,7 @@ static int __devexit generic_onenand_remove(struct platform_device *pdev)
 	platform_set_drvdata(pdev, NULL);
 
 	if (info) {
-		if (info->parts)
-			del_mtd_partitions(&info->mtd);
-		else
-			del_mtd_device(&info->mtd);
-
+		mtd_device_unregister(&info->mtd);
 		onenand_release(&info->mtd);
 		release_mem_region(res->start, size);
 		iounmap(info->onenand.base);
diff --git a/drivers/mtd/onenand/omap2.c b/drivers/mtd/onenand/omap2.c
index 1fcb41adab07..a916dec29215 100644
--- a/drivers/mtd/onenand/omap2.c
+++ b/drivers/mtd/onenand/omap2.c
@@ -67,9 +67,7 @@ struct omap2_onenand {
 	struct regulator *regulator;
 };
 
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *part_probes[] = { "cmdlinepart", NULL,  };
-#endif
 
 static void omap2_onenand_dma_cb(int lch, u16 ch_status, void *data)
 {
@@ -755,15 +753,13 @@ static int __devinit omap2_onenand_probe(struct platform_device *pdev)
 	if ((r = onenand_scan(&c->mtd, 1)) < 0)
 		goto err_release_regulator;
 
-#ifdef CONFIG_MTD_PARTITIONS
 	r = parse_mtd_partitions(&c->mtd, part_probes, &c->parts, 0);
 	if (r > 0)
-		r = add_mtd_partitions(&c->mtd, c->parts, r);
+		r = mtd_device_register(&c->mtd, c->parts, r);
 	else if (pdata->parts != NULL)
-		r = add_mtd_partitions(&c->mtd, pdata->parts, pdata->nr_parts);
+		r = mtd_device_register(&c->mtd, pdata->parts, pdata->nr_parts);
 	else
-#endif
-		r = add_mtd_device(&c->mtd);
+		r = mtd_device_register(&c->mtd, NULL, 0);
 	if (r)
 		goto err_release_onenand;
 
diff --git a/drivers/mtd/onenand/onenand_base.c b/drivers/mtd/onenand/onenand_base.c
index 56a8b2005bda..ac9e959802a7 100644
--- a/drivers/mtd/onenand/onenand_base.c
+++ b/drivers/mtd/onenand/onenand_base.c
@@ -65,11 +65,11 @@ MODULE_PARM_DESC(otp,	"Corresponding behaviour of OneNAND in OTP"
 			"	   : 2 -> 1st Block lock"
 			"	   : 3 -> BOTH OTP Block and 1st Block lock");
 
-/**
- *  onenand_oob_128 - oob info for Flex-Onenand with 4KB page
- *  For now, we expose only 64 out of 80 ecc bytes
+/*
+ * flexonenand_oob_128 - oob info for Flex-Onenand with 4KB page
+ * For now, we expose only 64 out of 80 ecc bytes
  */
-static struct nand_ecclayout onenand_oob_128 = {
+static struct nand_ecclayout flexonenand_oob_128 = {
 	.eccbytes	= 64,
 	.eccpos		= {
 		6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
@@ -86,6 +86,35 @@ static struct nand_ecclayout onenand_oob_128 = {
 	}
 };
 
+/*
+ * onenand_oob_128 - oob info for OneNAND with 4KB page
+ *
+ * Based on specification:
+ * 4Gb M-die OneNAND Flash (KFM4G16Q4M, KFN8G16Q4M). Rev. 1.3, Apr. 2010
+ *
+ * For eccpos we expose only 64 bytes out of 72 (see struct nand_ecclayout)
+ *
+ * oobfree uses the spare area fields marked as
+ * "Managed by internal ECC logic for Logical Sector Number area"
+ */
+static struct nand_ecclayout onenand_oob_128 = {
+	.eccbytes	= 64,
+	.eccpos		= {
+		7, 8, 9, 10, 11, 12, 13, 14, 15,
+		23, 24, 25, 26, 27, 28, 29, 30, 31,
+		39, 40, 41, 42, 43, 44, 45, 46, 47,
+		55, 56, 57, 58, 59, 60, 61, 62, 63,
+		71, 72, 73, 74, 75, 76, 77, 78, 79,
+		87, 88, 89, 90, 91, 92, 93, 94, 95,
+		103, 104, 105, 106, 107, 108, 109, 110, 111,
+		119
+	},
+	.oobfree	= {
+		{2, 3}, {18, 3}, {34, 3}, {50, 3},
+		{66, 3}, {82, 3}, {98, 3}, {114, 3}
+	}
+};
+
 /**
  * onenand_oob_64 - oob info for large (2KB) page
  */
@@ -2424,7 +2453,7 @@ static int onenand_block_by_block_erase(struct mtd_info *mtd,
 		len -= block_size;
 		addr += block_size;
 
-		if (addr == region_end) {
+		if (region && addr == region_end) {
 			if (!len)
 				break;
 			region++;
@@ -4018,8 +4047,13 @@ int onenand_scan(struct mtd_info *mtd, int maxchips)
 	 */
 	switch (mtd->oobsize) {
 	case 128:
-		this->ecclayout = &onenand_oob_128;
-		mtd->subpage_sft = 0;
+		if (FLEXONENAND(this)) {
+			this->ecclayout = &flexonenand_oob_128;
+			mtd->subpage_sft = 0;
+		} else {
+			this->ecclayout = &onenand_oob_128;
+			mtd->subpage_sft = 2;
+		}
 		break;
 	case 64:
 		this->ecclayout = &onenand_oob_64;
@@ -4108,12 +4142,8 @@ void onenand_release(struct mtd_info *mtd)
 {
 	struct onenand_chip *this = mtd->priv;
 
-#ifdef CONFIG_MTD_PARTITIONS
 	/* Deregister partitions */
-	del_mtd_partitions (mtd);
-#endif
-	/* Deregister the device */
-	del_mtd_device (mtd);
+	mtd_device_unregister(mtd);
 
 	/* Free bad block table memory, if allocated */
 	if (this->bbm) {
diff --git a/drivers/mtd/onenand/onenand_sim.c b/drivers/mtd/onenand/onenand_sim.c
index 5ef3bd547772..85399e3accda 100644
--- a/drivers/mtd/onenand/onenand_sim.c
+++ b/drivers/mtd/onenand/onenand_sim.c
@@ -539,7 +539,8 @@ static int __init onenand_sim_init(void)
 		return -ENXIO;
 	}
 
-	add_mtd_partitions(&info->mtd, info->parts, ARRAY_SIZE(os_partitions));
+	mtd_device_register(&info->mtd, info->parts,
+			    ARRAY_SIZE(os_partitions));
 
 	return 0;
 }
diff --git a/drivers/mtd/onenand/samsung.c b/drivers/mtd/onenand/samsung.c
index a4c74a9ba430..3306b5b3c736 100644
--- a/drivers/mtd/onenand/samsung.c
+++ b/drivers/mtd/onenand/samsung.c
@@ -147,9 +147,7 @@ struct s3c_onenand {
 	struct resource *dma_res;
 	unsigned long	phys_base;
 	struct completion	complete;
-#ifdef CONFIG_MTD_PARTITIONS
 	struct mtd_partition *parts;
-#endif
 };
 
 #define CMD_MAP_00(dev, addr)		(dev->cmd_map(MAP_00, ((addr) << 1)))
@@ -159,9 +157,7 @@ struct s3c_onenand {
 
 static struct s3c_onenand *onenand;
 
-#ifdef CONFIG_MTD_PARTITIONS
 static const char *part_probes[] = { "cmdlinepart", NULL, };
-#endif
 
 static inline int s3c_read_reg(int offset)
 {
@@ -1021,15 +1017,13 @@ static int s3c_onenand_probe(struct platform_device *pdev)
 	if (s3c_read_reg(MEM_CFG_OFFSET) & ONENAND_SYS_CFG1_SYNC_READ)
 		dev_info(&onenand->pdev->dev, "OneNAND Sync. Burst Read enabled\n");
 
-#ifdef CONFIG_MTD_PARTITIONS
 	err = parse_mtd_partitions(mtd, part_probes, &onenand->parts, 0);
 	if (err > 0)
-		add_mtd_partitions(mtd, onenand->parts, err);
+		mtd_device_register(mtd, onenand->parts, err);
 	else if (err <= 0 && pdata && pdata->parts)
-		add_mtd_partitions(mtd, pdata->parts, pdata->nr_parts);
+		mtd_device_register(mtd, pdata->parts, pdata->nr_parts);
 	else
-#endif
-		err = add_mtd_device(mtd);
+		err = mtd_device_register(mtd, NULL, 0);
 
 	platform_set_drvdata(pdev, mtd);
 
diff --git a/drivers/mtd/ubi/gluebi.c b/drivers/mtd/ubi/gluebi.c
index 9aa81584c8a2..941bc3c05d6e 100644
--- a/drivers/mtd/ubi/gluebi.c
+++ b/drivers/mtd/ubi/gluebi.c
@@ -365,7 +365,7 @@ static int gluebi_create(struct ubi_device_info *di,
 			vi->vol_id);
 	mutex_unlock(&devices_mutex);
 
-	if (add_mtd_device(mtd)) {
+	if (mtd_device_register(mtd, NULL, 0)) {
 		err_msg("cannot add MTD device");
 		kfree(mtd->name);
 		kfree(gluebi);
@@ -407,7 +407,7 @@ static int gluebi_remove(struct ubi_volume_info *vi)
 		return err;
 
 	mtd = &gluebi->mtd;
-	err = del_mtd_device(mtd);
+	err = mtd_device_unregister(mtd);
 	if (err) {
 		err_msg("cannot remove fake MTD device %d, UBI device %d, "
 			"volume %d, error %d", mtd->index, gluebi->ubi_num,
@@ -524,7 +524,7 @@ static void __exit ubi_gluebi_exit(void)
 		int err;
 		struct mtd_info *mtd = &gluebi->mtd;
 
-		err = del_mtd_device(mtd);
+		err = mtd_device_unregister(mtd);
 		if (err)
 			err_msg("error %d while removing gluebi MTD device %d, "
 				"UBI device %d, volume %d - ignoring", err,
diff --git a/drivers/net/3c503.c b/drivers/net/3c503.c
index d84f6e8903a5..5b732988d493 100644
--- a/drivers/net/3c503.c
+++ b/drivers/net/3c503.c
@@ -412,7 +412,7 @@ el2_open(struct net_device *dev)
 		outb_p(0x04 << ((*irqp == 9) ? 2 : *irqp), E33G_IDCFR);
 		outb_p(0x00, E33G_IDCFR);
 		msleep(1);
-		free_irq(*irqp, el2_probe_interrupt);
+		free_irq(*irqp, &seen);
 		if (!seen)
 			continue;
 
@@ -422,6 +422,7 @@ el2_open(struct net_device *dev)
 			continue;
 		if (retval < 0)
 			goto err_disable;
+		break;
 	} while (*++irqp);
 
 	if (*irqp == 0) {
diff --git a/drivers/net/3c509.c b/drivers/net/3c509.c
index 5f25889e27ef..44b28b2d7003 100644
--- a/drivers/net/3c509.c
+++ b/drivers/net/3c509.c
@@ -185,7 +185,7 @@ static int max_interrupt_work = 10;
 static int nopnp;
 #endif
 
-static int el3_common_init(struct net_device *dev);
+static int __devinit el3_common_init(struct net_device *dev);
 static void el3_common_remove(struct net_device *dev);
 static ushort id_read_eeprom(int index);
 static ushort read_eeprom(int ioaddr, int index);
@@ -395,7 +395,7 @@ static struct isa_driver el3_isa_driver = {
 static int isa_registered;
 
 #ifdef CONFIG_PNP
-static const struct pnp_device_id el3_pnp_ids[] __devinitconst = {
+static struct pnp_device_id el3_pnp_ids[] = {
 	{ .id = "TCM5090" }, /* 3Com Etherlink III (TP) */
 	{ .id = "TCM5091" }, /* 3Com Etherlink III */
 	{ .id = "TCM5094" }, /* 3Com Etherlink III (combo) */
@@ -478,7 +478,7 @@ static int pnp_registered;
 #endif /* CONFIG_PNP */
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id el3_eisa_ids[] __devinitconst = {
+static struct eisa_device_id el3_eisa_ids[] = {
 		{ "TCM5090" },
 		{ "TCM5091" },
 		{ "TCM5092" },
@@ -508,7 +508,7 @@ static int eisa_registered;
 #ifdef CONFIG_MCA
 static int el3_mca_probe(struct device *dev);
 
-static const short el3_mca_adapter_ids[] __devinitconst = {
+static short el3_mca_adapter_ids[] __initdata = {
 		0x627c,
 		0x627d,
 		0x62db,
@@ -517,7 +517,7 @@ static const short el3_mca_adapter_ids[] __devinitconst = {
 		0x0000
 };
 
-static const char *const el3_mca_adapter_names[] __devinitconst = {
+static char *el3_mca_adapter_names[] __initdata = {
 		"3Com 3c529 EtherLink III (10base2)",
 		"3Com 3c529 EtherLink III (10baseT)",
 		"3Com 3c529 EtherLink III (test mode)",
@@ -601,7 +601,7 @@ static void el3_common_remove (struct net_device *dev)
 }
 
 #ifdef CONFIG_MCA
-static int __devinit el3_mca_probe(struct device *device)
+static int __init el3_mca_probe(struct device *device)
 {
 	/* Based on Erik Nygren's (nygren@mit.edu) 3c529 patch,
 	 * heavily modified by Chris Beauregard
@@ -671,7 +671,7 @@ static int __devinit el3_mca_probe(struct device *device)
 #endif /* CONFIG_MCA */
 
 #ifdef CONFIG_EISA
-static int __devinit el3_eisa_probe (struct device *device)
+static int __init el3_eisa_probe (struct device *device)
 {
 	short i;
 	int ioaddr, irq, if_port;
diff --git a/drivers/net/3c59x.c b/drivers/net/3c59x.c
index 99f43d275442..8cc22568ebd3 100644
--- a/drivers/net/3c59x.c
+++ b/drivers/net/3c59x.c
@@ -901,14 +901,14 @@ static const struct dev_pm_ops vortex_pm_ops = {
 #endif /* !CONFIG_PM */
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id vortex_eisa_ids[] __devinitconst = {
+static struct eisa_device_id vortex_eisa_ids[] = {
 	{ "TCM5920", CH_3C592 },
 	{ "TCM5970", CH_3C597 },
 	{ "" }
 };
 MODULE_DEVICE_TABLE(eisa, vortex_eisa_ids);
 
-static int __devinit vortex_eisa_probe(struct device *device)
+static int __init vortex_eisa_probe(struct device *device)
 {
 	void __iomem *ioaddr;
 	struct eisa_device *edev;
diff --git a/drivers/net/arm/am79c961a.c b/drivers/net/arm/am79c961a.c
index 0c9217f48b72..7b3e23f38913 100644
--- a/drivers/net/arm/am79c961a.c
+++ b/drivers/net/arm/am79c961a.c
@@ -50,7 +50,7 @@ static const char version[] =
 #ifdef __arm__
 static void write_rreg(u_long base, u_int reg, u_int val)
 {
-	__asm__(
+	asm volatile(
 	"str%?h	%1, [%2]	@ NET_RAP\n\t"
 	"str%?h	%0, [%2, #-4]	@ NET_RDP"
 	:
@@ -60,7 +60,7 @@ static void write_rreg(u_long base, u_int reg, u_int val)
 static inline unsigned short read_rreg(u_long base_addr, u_int reg)
 {
 	unsigned short v;
-	__asm__(
+	asm volatile(
 	"str%?h	%1, [%2]	@ NET_RAP\n\t"
 	"ldr%?h	%0, [%2, #-4]	@ NET_RDP"
 	: "=r" (v)
@@ -70,7 +70,7 @@ static inline unsigned short read_rreg(u_long base_addr, u_int reg)
 
 static inline void write_ireg(u_long base, u_int reg, u_int val)
 {
-	__asm__(
+	asm volatile(
 	"str%?h	%1, [%2]	@ NET_RAP\n\t"
 	"str%?h	%0, [%2, #8]	@ NET_IDP"
 	:
@@ -80,7 +80,7 @@ static inline void write_ireg(u_long base, u_int reg, u_int val)
 static inline unsigned short read_ireg(u_long base_addr, u_int reg)
 {
 	u_short v;
-	__asm__(
+	asm volatile(
 	"str%?h	%1, [%2]	@ NAT_RAP\n\t"
 	"ldr%?h	%0, [%2, #8]	@ NET_IDP\n\t"
 	: "=r" (v)
@@ -91,47 +91,48 @@ static inline unsigned short read_ireg(u_long base_addr, u_int reg)
 #define am_writeword(dev,off,val) __raw_writew(val, ISAMEM_BASE + ((off) << 1))
 #define am_readword(dev,off)      __raw_readw(ISAMEM_BASE + ((off) << 1))
 
-static inline void
+static void
 am_writebuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigned int length)
 {
 	offset = ISAMEM_BASE + (offset << 1);
 	length = (length + 1) & ~1;
 	if ((int)buf & 2) {
-		__asm__ __volatile__("str%?h	%2, [%0], #4"
+		asm volatile("str%?h	%2, [%0], #4"
 		 : "=&r" (offset) : "0" (offset), "r" (buf[0] | (buf[1] << 8)));
 		buf += 2;
 		length -= 2;
 	}
 	while (length > 8) {
-		unsigned int tmp, tmp2;
-		__asm__ __volatile__(
-			"ldm%?ia	%1!, {%2, %3}\n\t"
+		register unsigned int tmp asm("r2"), tmp2 asm("r3");
+		asm volatile(
+			"ldm%?ia	%0!, {%1, %2}"
+			: "+r" (buf), "=&r" (tmp), "=&r" (tmp2));
+		length -= 8;
+		asm volatile(
+			"str%?h	%1, [%0], #4\n\t"
+			"mov%?	%1, %1, lsr #16\n\t"
+			"str%?h	%1, [%0], #4\n\t"
 			"str%?h	%2, [%0], #4\n\t"
 			"mov%?	%2, %2, lsr #16\n\t"
-			"str%?h	%2, [%0], #4\n\t"
-			"str%?h	%3, [%0], #4\n\t"
-			"mov%?	%3, %3, lsr #16\n\t"
-			"str%?h	%3, [%0], #4"
-		: "=&r" (offset), "=&r" (buf), "=r" (tmp), "=r" (tmp2)
-		: "0" (offset), "1" (buf));
-		length -= 8;
+			"str%?h	%2, [%0], #4"
+		: "+r" (offset), "=&r" (tmp), "=&r" (tmp2));
 	}
 	while (length > 0) {
-		__asm__ __volatile__("str%?h	%2, [%0], #4"
+		asm volatile("str%?h	%2, [%0], #4"
 		 : "=&r" (offset) : "0" (offset), "r" (buf[0] | (buf[1] << 8)));
 		buf += 2;
 		length -= 2;
 	}
 }
 
-static inline void
+static void
 am_readbuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigned int length)
 {
 	offset = ISAMEM_BASE + (offset << 1);
 	length = (length + 1) & ~1;
 	if ((int)buf & 2) {
 		unsigned int tmp;
-		__asm__ __volatile__(
+		asm volatile(
 			"ldr%?h	%2, [%0], #4\n\t"
 			"str%?b	%2, [%1], #1\n\t"
 			"mov%?	%2, %2, lsr #8\n\t"
@@ -140,12 +141,12 @@ am_readbuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigned
 		length -= 2;
 	}
 	while (length > 8) {
-		unsigned int tmp, tmp2, tmp3;
-		__asm__ __volatile__(
+		register unsigned int tmp asm("r2"), tmp2 asm("r3"), tmp3;
+		asm volatile(
 			"ldr%?h	%2, [%0], #4\n\t"
+			"ldr%?h	%4, [%0], #4\n\t"
 			"ldr%?h	%3, [%0], #4\n\t"
-			"orr%?	%2, %2, %3, lsl #16\n\t"
-			"ldr%?h	%3, [%0], #4\n\t"
+			"orr%?	%2, %2, %4, lsl #16\n\t"
 			"ldr%?h	%4, [%0], #4\n\t"
 			"orr%?	%3, %3, %4, lsl #16\n\t"
 			"stm%?ia	%1!, {%2, %3}"
@@ -155,7 +156,7 @@ am_readbuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigned
 	}
 	while (length > 0) {
 		unsigned int tmp;
-		__asm__ __volatile__(
+		asm volatile(
 			"ldr%?h	%2, [%0], #4\n\t"
 			"str%?b	%2, [%1], #1\n\t"
 			"mov%?	%2, %2, lsr #8\n\t"
@@ -196,6 +197,42 @@ am79c961_ramtest(struct net_device *dev, unsigned int val)
 	return errorcount;
 }
 
+static void am79c961_mc_hash(char *addr, u16 *hash)
+{
+	if (addr[0] & 0x01) {
+		int idx, bit;
+		u32 crc;
+
+		crc = ether_crc_le(ETH_ALEN, addr);
+
+		idx = crc >> 30;
+		bit = (crc >> 26) & 15;
+
+		hash[idx] |= 1 << bit;
+	}
+}
+
+static unsigned int am79c961_get_rx_mode(struct net_device *dev, u16 *hash)
+{
+	unsigned int mode = MODE_PORT_10BT;
+
+	if (dev->flags & IFF_PROMISC) {
+		mode |= MODE_PROMISC;
+		memset(hash, 0xff, 4 * sizeof(*hash));
+	} else if (dev->flags & IFF_ALLMULTI) {
+		memset(hash, 0xff, 4 * sizeof(*hash));
+	} else {
+		struct netdev_hw_addr *ha;
+
+		memset(hash, 0, 4 * sizeof(*hash));
+
+		netdev_for_each_mc_addr(ha, dev)
+			am79c961_mc_hash(ha->addr, hash);
+	}
+
+	return mode;
+}
+
 static void
 am79c961_init_for_open(struct net_device *dev)
 {
@@ -203,6 +240,7 @@ am79c961_init_for_open(struct net_device *dev)
 	unsigned long flags;
 	unsigned char *p;
 	u_int hdr_addr, first_free_addr;
+	u16 multi_hash[4], mode = am79c961_get_rx_mode(dev, multi_hash);
 	int i;
 
 	/*
@@ -218,16 +256,12 @@ am79c961_init_for_open(struct net_device *dev)
 	write_ireg (dev->base_addr, 2, 0x0000); /* MODE register selects media */
 
 	for (i = LADRL; i <= LADRH; i++)
-		write_rreg (dev->base_addr, i, 0);
+		write_rreg (dev->base_addr, i, multi_hash[i - LADRL]);
 
 	for (i = PADRL, p = dev->dev_addr; i <= PADRH; i++, p += 2)
 		write_rreg (dev->base_addr, i, p[0] | (p[1] << 8));
 
-	i = MODE_PORT_10BT;
-	if (dev->flags & IFF_PROMISC)
-		i |= MODE_PROMISC;
-
-	write_rreg (dev->base_addr, MODE, i);
+	write_rreg (dev->base_addr, MODE, mode);
 	write_rreg (dev->base_addr, POLLINT, 0);
 	write_rreg (dev->base_addr, SIZERXR, -RX_BUFFERS);
 	write_rreg (dev->base_addr, SIZETXR, -TX_BUFFERS);
@@ -340,21 +374,6 @@ am79c961_close(struct net_device *dev)
 	return 0;
 }
 
-static void am79c961_mc_hash(char *addr, unsigned short *hash)
-{
-	if (addr[0] & 0x01) {
-		int idx, bit;
-		u32 crc;
-
-		crc = ether_crc_le(ETH_ALEN, addr);
-
-		idx = crc >> 30;
-		bit = (crc >> 26) & 15;
-
-		hash[idx] |= 1 << bit;
-	}
-}
-
 /*
  * Set or clear promiscuous/multicast mode filter for this adapter.
  */
@@ -362,24 +381,9 @@ static void am79c961_setmulticastlist (struct net_device *dev)
 {
 	struct dev_priv *priv = netdev_priv(dev);
 	unsigned long flags;
-	unsigned short multi_hash[4], mode;
+	u16 multi_hash[4], mode = am79c961_get_rx_mode(dev, multi_hash);
 	int i, stopped;
 
-	mode = MODE_PORT_10BT;
-
-	if (dev->flags & IFF_PROMISC) {
-		mode |= MODE_PROMISC;
-	} else if (dev->flags & IFF_ALLMULTI) {
-		memset(multi_hash, 0xff, sizeof(multi_hash));
-	} else {
-		struct netdev_hw_addr *ha;
-
-		memset(multi_hash, 0x00, sizeof(multi_hash));
-
-		netdev_for_each_mc_addr(ha, dev)
-			am79c961_mc_hash(ha->addr, multi_hash);
-	}
-
 	spin_lock_irqsave(&priv->chip_lock, flags);
 
 	stopped = read_rreg(dev->base_addr, CSR0) & CSR0_STOP;
diff --git a/drivers/net/arm/ep93xx_eth.c b/drivers/net/arm/ep93xx_eth.c
index 5a77001b6d10..0b46b8ea0e80 100644
--- a/drivers/net/arm/ep93xx_eth.c
+++ b/drivers/net/arm/ep93xx_eth.c
@@ -283,10 +283,14 @@ static int ep93xx_rx(struct net_device *dev, int processed, int budget)
 
 		skb = dev_alloc_skb(length + 2);
 		if (likely(skb != NULL)) {
+			struct ep93xx_rdesc *rxd = &ep->descs->rdesc[entry];
 			skb_reserve(skb, 2);
-			dma_sync_single_for_cpu(NULL, ep->descs->rdesc[entry].buf_addr,
+			dma_sync_single_for_cpu(dev->dev.parent, rxd->buf_addr,
 						length, DMA_FROM_DEVICE);
 			skb_copy_to_linear_data(skb, ep->rx_buf[entry], length);
+			dma_sync_single_for_device(dev->dev.parent,
+						   rxd->buf_addr, length,
+						   DMA_FROM_DEVICE);
 			skb_put(skb, length);
 			skb->protocol = eth_type_trans(skb, dev);
 
@@ -348,6 +352,7 @@ poll_some_more:
 static int ep93xx_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ep93xx_priv *ep = netdev_priv(dev);
+	struct ep93xx_tdesc *txd;
 	int entry;
 
 	if (unlikely(skb->len > MAX_PKT_SIZE)) {
@@ -359,11 +364,14 @@ static int ep93xx_xmit(struct sk_buff *skb, struct net_device *dev)
 	entry = ep->tx_pointer;
 	ep->tx_pointer = (ep->tx_pointer + 1) & (TX_QUEUE_ENTRIES - 1);
 
-	ep->descs->tdesc[entry].tdesc1 =
-		TDESC1_EOF | (entry << 16) | (skb->len & 0xfff);
+	txd = &ep->descs->tdesc[entry];
+
+	txd->tdesc1 = TDESC1_EOF | (entry << 16) | (skb->len & 0xfff);
+	dma_sync_single_for_cpu(dev->dev.parent, txd->buf_addr, skb->len,
+				DMA_TO_DEVICE);
 	skb_copy_and_csum_dev(skb, ep->tx_buf[entry]);
-	dma_sync_single_for_cpu(NULL, ep->descs->tdesc[entry].buf_addr,
-				skb->len, DMA_TO_DEVICE);
+	dma_sync_single_for_device(dev->dev.parent, txd->buf_addr, skb->len,
+				   DMA_TO_DEVICE);
 	dev_kfree_skb(skb);
 
 	spin_lock_irq(&ep->tx_pending_lock);
@@ -457,89 +465,80 @@ static irqreturn_t ep93xx_irq(int irq, void *dev_id)
 
 static void ep93xx_free_buffers(struct ep93xx_priv *ep)
 {
+	struct device *dev = ep->dev->dev.parent;
 	int i;
 
-	for (i = 0; i < RX_QUEUE_ENTRIES; i += 2) {
+	for (i = 0; i < RX_QUEUE_ENTRIES; i++) {
 		dma_addr_t d;
 
 		d = ep->descs->rdesc[i].buf_addr;
 		if (d)
-			dma_unmap_single(NULL, d, PAGE_SIZE, DMA_FROM_DEVICE);
+			dma_unmap_single(dev, d, PKT_BUF_SIZE, DMA_FROM_DEVICE);
 
 		if (ep->rx_buf[i] != NULL)
-			free_page((unsigned long)ep->rx_buf[i]);
+			kfree(ep->rx_buf[i]);
 	}
 
-	for (i = 0; i < TX_QUEUE_ENTRIES; i += 2) {
+	for (i = 0; i < TX_QUEUE_ENTRIES; i++) {
 		dma_addr_t d;
 
 		d = ep->descs->tdesc[i].buf_addr;
 		if (d)
-			dma_unmap_single(NULL, d, PAGE_SIZE, DMA_TO_DEVICE);
+			dma_unmap_single(dev, d, PKT_BUF_SIZE, DMA_TO_DEVICE);
 
 		if (ep->tx_buf[i] != NULL)
-			free_page((unsigned long)ep->tx_buf[i]);
+			kfree(ep->tx_buf[i]);
 	}
 
-	dma_free_coherent(NULL, sizeof(struct ep93xx_descs), ep->descs,
+	dma_free_coherent(dev, sizeof(struct ep93xx_descs), ep->descs,
 							ep->descs_dma_addr);
 }
 
-/*
- * The hardware enforces a sub-2K maximum packet size, so we put
- * two buffers on every hardware page.
- */
 static int ep93xx_alloc_buffers(struct ep93xx_priv *ep)
 {
+	struct device *dev = ep->dev->dev.parent;
 	int i;
 
-	ep->descs = dma_alloc_coherent(NULL, sizeof(struct ep93xx_descs),
-				&ep->descs_dma_addr, GFP_KERNEL | GFP_DMA);
+	ep->descs = dma_alloc_coherent(dev, sizeof(struct ep93xx_descs),
+				&ep->descs_dma_addr, GFP_KERNEL);
 	if (ep->descs == NULL)
 		return 1;
 
-	for (i = 0; i < RX_QUEUE_ENTRIES; i += 2) {
-		void *page;
+	for (i = 0; i < RX_QUEUE_ENTRIES; i++) {
+		void *buf;
 		dma_addr_t d;
 
-		page = (void *)__get_free_page(GFP_KERNEL | GFP_DMA);
-		if (page == NULL)
+		buf = kmalloc(PKT_BUF_SIZE, GFP_KERNEL);
+		if (buf == NULL)
 			goto err;
 
-		d = dma_map_single(NULL, page, PAGE_SIZE, DMA_FROM_DEVICE);
-		if (dma_mapping_error(NULL, d)) {
-			free_page((unsigned long)page);
+		d = dma_map_single(dev, buf, PKT_BUF_SIZE, DMA_FROM_DEVICE);
+		if (dma_mapping_error(dev, d)) {
+			kfree(buf);
 			goto err;
 		}
 
-		ep->rx_buf[i] = page;
+		ep->rx_buf[i] = buf;
 		ep->descs->rdesc[i].buf_addr = d;
 		ep->descs->rdesc[i].rdesc1 = (i << 16) | PKT_BUF_SIZE;
-
-		ep->rx_buf[i + 1] = page + PKT_BUF_SIZE;
-		ep->descs->rdesc[i + 1].buf_addr = d + PKT_BUF_SIZE;
-		ep->descs->rdesc[i + 1].rdesc1 = ((i + 1) << 16) | PKT_BUF_SIZE;
 	}
 
-	for (i = 0; i < TX_QUEUE_ENTRIES; i += 2) {
-		void *page;
+	for (i = 0; i < TX_QUEUE_ENTRIES; i++) {
+		void *buf;
 		dma_addr_t d;
 
-		page = (void *)__get_free_page(GFP_KERNEL | GFP_DMA);
-		if (page == NULL)
+		buf = kmalloc(PKT_BUF_SIZE, GFP_KERNEL);
+		if (buf == NULL)
 			goto err;
 
-		d = dma_map_single(NULL, page, PAGE_SIZE, DMA_TO_DEVICE);
-		if (dma_mapping_error(NULL, d)) {
-			free_page((unsigned long)page);
+		d = dma_map_single(dev, buf, PKT_BUF_SIZE, DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, d)) {
+			kfree(buf);
 			goto err;
 		}
 
-		ep->tx_buf[i] = page;
+		ep->tx_buf[i] = buf;
 		ep->descs->tdesc[i].buf_addr = d;
-
-		ep->tx_buf[i + 1] = page + PKT_BUF_SIZE;
-		ep->descs->tdesc[i + 1].buf_addr = d + PKT_BUF_SIZE;
 	}
 
 	return 0;
@@ -829,6 +828,7 @@ static int ep93xx_eth_probe(struct platform_device *pdev)
 	}
 	ep = netdev_priv(dev);
 	ep->dev = dev;
+	SET_NETDEV_DEV(dev, &pdev->dev);
 	netif_napi_add(dev, &ep->napi, ep93xx_poll, 64);
 
 	platform_set_drvdata(pdev, dev);
diff --git a/drivers/net/bfin_mac.c b/drivers/net/bfin_mac.c
index 68d45ba2d9b9..6c019e148546 100644
--- a/drivers/net/bfin_mac.c
+++ b/drivers/net/bfin_mac.c
@@ -52,13 +52,13 @@ MODULE_DESCRIPTION(DRV_DESC);
 MODULE_ALIAS("platform:bfin_mac");
 
 #if defined(CONFIG_BFIN_MAC_USE_L1)
-# define bfin_mac_alloc(dma_handle, size)  l1_data_sram_zalloc(size)
-# define bfin_mac_free(dma_handle, ptr)    l1_data_sram_free(ptr)
+# define bfin_mac_alloc(dma_handle, size, num)  l1_data_sram_zalloc(size*num)
+# define bfin_mac_free(dma_handle, ptr, num)    l1_data_sram_free(ptr)
 #else
-# define bfin_mac_alloc(dma_handle, size) \
-	dma_alloc_coherent(NULL, size, dma_handle, GFP_KERNEL)
-# define bfin_mac_free(dma_handle, ptr) \
-	dma_free_coherent(NULL, sizeof(*ptr), ptr, dma_handle)
+# define bfin_mac_alloc(dma_handle, size, num) \
+	dma_alloc_coherent(NULL, size*num, dma_handle, GFP_KERNEL)
+# define bfin_mac_free(dma_handle, ptr, num) \
+	dma_free_coherent(NULL, sizeof(*ptr)*num, ptr, dma_handle)
 #endif
 
 #define PKT_BUF_SZ 1580
@@ -95,7 +95,7 @@ static void desc_list_free(void)
 				t = t->next;
 			}
 		}
-		bfin_mac_free(dma_handle, tx_desc);
+		bfin_mac_free(dma_handle, tx_desc, CONFIG_BFIN_TX_DESC_NUM);
 	}
 
 	if (rx_desc) {
@@ -109,7 +109,7 @@ static void desc_list_free(void)
 				r = r->next;
 			}
 		}
-		bfin_mac_free(dma_handle, rx_desc);
+		bfin_mac_free(dma_handle, rx_desc, CONFIG_BFIN_RX_DESC_NUM);
 	}
 }
 
@@ -126,13 +126,13 @@ static int desc_list_init(void)
 #endif
 
 	tx_desc = bfin_mac_alloc(&dma_handle,
-				sizeof(struct net_dma_desc_tx) *
+				sizeof(struct net_dma_desc_tx),
 				CONFIG_BFIN_TX_DESC_NUM);
 	if (tx_desc == NULL)
 		goto init_error;
 
 	rx_desc = bfin_mac_alloc(&dma_handle,
-				sizeof(struct net_dma_desc_rx) *
+				sizeof(struct net_dma_desc_rx),
 				CONFIG_BFIN_RX_DESC_NUM);
 	if (rx_desc == NULL)
 		goto init_error;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 6141667c5fb7..eafe44a528ac 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -113,9 +113,11 @@ MODULE_PARM_DESC(max_bonds, "Max number of bonded devices");
 module_param(tx_queues, int, 0);
 MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)");
 module_param_named(num_grat_arp, num_peer_notif, int, 0644);
-MODULE_PARM_DESC(num_grat_arp, "Number of peer notifications to send on failover event (alias of num_unsol_na)");
+MODULE_PARM_DESC(num_grat_arp, "Number of peer notifications to send on "
+			       "failover event (alias of num_unsol_na)");
 module_param_named(num_unsol_na, num_peer_notif, int, 0644);
-MODULE_PARM_DESC(num_unsol_na, "Number of peer notifications to send on failover event (alias of num_grat_arp)");
+MODULE_PARM_DESC(num_unsol_na, "Number of peer notifications to send on "
+			       "failover event (alias of num_grat_arp)");
 module_param(miimon, int, 0);
 MODULE_PARM_DESC(miimon, "Link check interval in milliseconds");
 module_param(updelay, int, 0);
@@ -127,7 +129,7 @@ module_param(use_carrier, int, 0);
 MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; "
 			      "0 for off, 1 for on (default)");
 module_param(mode, charp, 0);
-MODULE_PARM_DESC(mode, "Mode of operation : 0 for balance-rr, "
+MODULE_PARM_DESC(mode, "Mode of operation; 0 for balance-rr, "
 		       "1 for active-backup, 2 for balance-xor, "
 		       "3 for broadcast, 4 for 802.3ad, 5 for balance-tlb, "
 		       "6 for balance-alb");
@@ -142,27 +144,35 @@ MODULE_PARM_DESC(primary_reselect, "Reselect primary slave "
 				   "2 for only on active slave "
 				   "failure");
 module_param(lacp_rate, charp, 0);
-MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner "
-			    "(slow/fast)");
+MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner; "
+			    "0 for slow, 1 for fast");
 module_param(ad_select, charp, 0);
-MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic: stable (0, default), bandwidth (1), count (2)");
+MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic; "
+			    "0 for stable (default), 1 for bandwidth, "
+			    "2 for count");
 module_param(xmit_hash_policy, charp, 0);
-MODULE_PARM_DESC(xmit_hash_policy, "XOR hashing method: 0 for layer 2 (default)"
-				   ", 1 for layer 3+4");
+MODULE_PARM_DESC(xmit_hash_policy, "balance-xor and 802.3ad hashing method; "
+				   "0 for layer 2 (default), 1 for layer 3+4, "
+				   "2 for layer 2+3");
 module_param(arp_interval, int, 0);
 MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds");
 module_param_array(arp_ip_target, charp, NULL, 0);
 MODULE_PARM_DESC(arp_ip_target, "arp targets in n.n.n.n form");
 module_param(arp_validate, charp, 0);
-MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes: none (default), active, backup or all");
+MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes; "
+			       "0 for none (default), 1 for active, "
+			       "2 for backup, 3 for all");
 module_param(fail_over_mac, charp, 0);
-MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to the same MAC.  none (default), active or follow");
+MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to "
+				"the same MAC; 0 for none (default), "
+				"1 for active, 2 for follow");
 module_param(all_slaves_active, int, 0);
 MODULE_PARM_DESC(all_slaves_active, "Keep all frames received on an interface"
-				     "by setting active flag for all slaves.  "
+				     "by setting active flag for all slaves; "
 				     "0 for never (default), 1 for always.");
 module_param(resend_igmp, int, 0);
-MODULE_PARM_DESC(resend_igmp, "Number of IGMP membership reports to send on link failure");
+MODULE_PARM_DESC(resend_igmp, "Number of IGMP membership reports to send on "
+			      "link failure");
 
 /*----------------------------- Global variables ----------------------------*/
 
@@ -378,6 +388,8 @@ struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr)
 	return next;
 }
 
+#define bond_queue_mapping(skb) (*(u16 *)((skb)->cb))
+
 /**
  * bond_dev_queue_xmit - Prepare skb for xmit.
  *
@@ -390,6 +402,9 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
 {
 	skb->dev = slave_dev;
 	skb->priority = 1;
+
+	skb->queue_mapping = bond_queue_mapping(skb);
+
 	if (unlikely(netpoll_tx_running(slave_dev)))
 		bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb);
 	else
@@ -1282,6 +1297,7 @@ static inline int slave_enable_netpoll(struct slave *slave)
 		goto out;
 
 	np->dev = slave->dev;
+	strlcpy(np->dev_name, slave->dev->name, IFNAMSIZ);
 	err = __netpoll_setup(np);
 	if (err) {
 		kfree(np);
@@ -4196,6 +4212,7 @@ static inline int bond_slave_override(struct bonding *bond,
 	return res;
 }
 
+
 static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb)
 {
 	/*
@@ -4206,6 +4223,11 @@ static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb)
 	 */
 	u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0;
 
+	/*
+	 * Save the original txq to restore before passing to the driver
+	 */
+	bond_queue_mapping(skb) = skb->queue_mapping;
+
 	if (unlikely(txq >= dev->real_num_tx_queues)) {
 		do {
 			txq -= dev->real_num_tx_queues;
diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c
index 73c7e03617ec..3df0c0f8b8bf 100644
--- a/drivers/net/caif/caif_serial.c
+++ b/drivers/net/caif/caif_serial.c
@@ -167,8 +167,8 @@ static inline void debugfs_tx(struct ser_device *ser, const u8 *data, int size)
 
 #endif
 
-static unsigned int ldisc_receive(struct tty_struct *tty,
-		const u8 *data, char *flags, int count)
+static void ldisc_receive(struct tty_struct *tty, const u8 *data,
+			char *flags, int count)
 {
 	struct sk_buff *skb = NULL;
 	struct ser_device *ser;
@@ -215,8 +215,6 @@ static unsigned int ldisc_receive(struct tty_struct *tty,
 	} else
 		++ser->dev->stats.rx_dropped;
 	update_tty_status(ser);
-
-	return count;
 }
 
 static int handle_tx(struct ser_device *ser)
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index d4990568baee..17678117ed69 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -923,7 +923,7 @@ static int __devinit flexcan_probe(struct platform_device *pdev)
 	mem_size = resource_size(mem);
 	if (!request_mem_region(mem->start, mem_size, pdev->name)) {
 		err = -EBUSY;
-		goto failed_req;
+		goto failed_get;
 	}
 
 	base = ioremap(mem->start, mem_size);
@@ -977,9 +977,8 @@ static int __devinit flexcan_probe(struct platform_device *pdev)
 	iounmap(base);
  failed_map:
 	release_mem_region(mem->start, mem_size);
- failed_req:
-	clk_put(clk);
  failed_get:
+	clk_put(clk);
  failed_clock:
 	return err;
 }
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 75622d54581f..1b49df6b2470 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -425,17 +425,16 @@ static void slc_setup(struct net_device *dev)
  * in parallel
  */
 
-static unsigned int slcan_receive_buf(struct tty_struct *tty,
+static void slcan_receive_buf(struct tty_struct *tty,
 			      const unsigned char *cp, char *fp, int count)
 {
 	struct slcan *sl = (struct slcan *) tty->disc_data;
-	int bytes = count;
 
 	if (!sl || sl->magic != SLCAN_MAGIC || !netif_running(sl->dev))
-		return -ENODEV;
+		return;
 
 	/* Read the characters out of the buffer */
-	while (bytes--) {
+	while (count--) {
 		if (fp && *fp++) {
 			if (!test_and_set_bit(SLF_ERROR, &sl->flags))
 				sl->dev->stats.rx_errors++;
@@ -444,8 +443,6 @@ static unsigned int slcan_receive_buf(struct tty_struct *tty,
 		}
 		slcan_unesc(sl, *cp++);
 	}
-
-	return count;
 }
 
 /************************************
diff --git a/drivers/net/davinci_emac.c b/drivers/net/davinci_emac.c
index 807b6bb200eb..dcc4a170b0f3 100644
--- a/drivers/net/davinci_emac.c
+++ b/drivers/net/davinci_emac.c
@@ -1772,7 +1772,7 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
 	/* obtain emac clock from kernel */
 	emac_clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(emac_clk)) {
-		printk(KERN_ERR "DaVinci EMAC: Failed to get EMAC clock\n");
+		dev_err(&pdev->dev, "failed to get EMAC clock\n");
 		return -EBUSY;
 	}
 	emac_bus_frequency = clk_get_rate(emac_clk);
@@ -1780,9 +1780,9 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
 
 	ndev = alloc_etherdev(sizeof(struct emac_priv));
 	if (!ndev) {
-		printk(KERN_ERR "DaVinci EMAC: Error allocating net_device\n");
-		clk_put(emac_clk);
-		return -ENOMEM;
+		dev_err(&pdev->dev, "error allocating net_device\n");
+		rc = -ENOMEM;
+		goto free_clk;
 	}
 
 	platform_set_drvdata(pdev, ndev);
@@ -1795,8 +1795,9 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
 
 	pdata = pdev->dev.platform_data;
 	if (!pdata) {
-		printk(KERN_ERR "DaVinci EMAC: No platform data\n");
-		return -ENODEV;
+		dev_err(&pdev->dev, "no platform data\n");
+		rc = -ENODEV;
+		goto probe_quit;
 	}
 
 	/* MAC addr and PHY mask , RMII enable info from platform_data */
@@ -1814,7 +1815,7 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
 	/* Get EMAC platform data */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
-		dev_err(emac_dev, "DaVinci EMAC: Error getting res\n");
+		dev_err(&pdev->dev,"error getting res\n");
 		rc = -ENOENT;
 		goto probe_quit;
 	}
@@ -1822,14 +1823,14 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
 	priv->emac_base_phys = res->start + pdata->ctrl_reg_offset;
 	size = res->end - res->start + 1;
 	if (!request_mem_region(res->start, size, ndev->name)) {
-		dev_err(emac_dev, "DaVinci EMAC: failed request_mem_region() for regs\n");
+		dev_err(&pdev->dev, "failed request_mem_region() for regs\n");
 		rc = -ENXIO;
 		goto probe_quit;
 	}
 
 	priv->remap_addr = ioremap(res->start, size);
 	if (!priv->remap_addr) {
-		dev_err(emac_dev, "Unable to map IO\n");
+		dev_err(&pdev->dev, "unable to map IO\n");
 		rc = -ENOMEM;
 		release_mem_region(res->start, size);
 		goto probe_quit;
@@ -1863,7 +1864,7 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
 
 	priv->dma = cpdma_ctlr_create(&dma_params);
 	if (!priv->dma) {
-		dev_err(emac_dev, "DaVinci EMAC: Error initializing DMA\n");
+		dev_err(&pdev->dev, "error initializing DMA\n");
 		rc = -ENOMEM;
 		goto no_dma;
 	}
@@ -1879,7 +1880,7 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
 
 	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (!res) {
-		dev_err(emac_dev, "DaVinci EMAC: Error getting irq res\n");
+		dev_err(&pdev->dev, "error getting irq res\n");
 		rc = -ENOENT;
 		goto no_irq_res;
 	}
@@ -1888,8 +1889,8 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
 	if (!is_valid_ether_addr(priv->mac_addr)) {
 		/* Use random MAC if none passed */
 		random_ether_addr(priv->mac_addr);
-		printk(KERN_WARNING "%s: using random MAC addr: %pM\n",
-				__func__, priv->mac_addr);
+		dev_warn(&pdev->dev, "using random MAC addr: %pM\n",
+							priv->mac_addr);
 	}
 
 	ndev->netdev_ops = &emac_netdev_ops;
@@ -1902,7 +1903,7 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
 	SET_NETDEV_DEV(ndev, &pdev->dev);
 	rc = register_netdev(ndev);
 	if (rc) {
-		dev_err(emac_dev, "DaVinci EMAC: Error in register_netdev\n");
+		dev_err(&pdev->dev, "error in register_netdev\n");
 		rc = -ENODEV;
 		goto netdev_reg_err;
 	}
@@ -1929,8 +1930,9 @@ no_dma:
 	iounmap(priv->remap_addr);
 
 probe_quit:
-	clk_put(emac_clk);
 	free_netdev(ndev);
+free_clk:
+	clk_put(emac_clk);
 	return rc;
 }
 
diff --git a/drivers/net/depca.c b/drivers/net/depca.c
index 17654059922d..8b0084d17c8c 100644
--- a/drivers/net/depca.c
+++ b/drivers/net/depca.c
@@ -331,18 +331,18 @@ static struct {
                          "DE422",\
                          ""}
 
-static const char* const depca_signature[] __devinitconst = DEPCA_SIGNATURE;
+static char* __initdata depca_signature[] = DEPCA_SIGNATURE;
 
 enum depca_type {
 	DEPCA, de100, de101, de200, de201, de202, de210, de212, de422, unknown
 };
 
-static const char depca_string[] = "depca";
+static char depca_string[] = "depca";
 
 static int depca_device_remove (struct device *device);
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id depca_eisa_ids[] __devinitconst = {
+static struct eisa_device_id depca_eisa_ids[] = {
 	{ "DEC4220", de422 },
 	{ "" }
 };
@@ -367,19 +367,19 @@ static struct eisa_driver depca_eisa_driver = {
 #define DE210_ID 0x628d
 #define DE212_ID 0x6def
 
-static const short depca_mca_adapter_ids[] __devinitconst = {
+static short depca_mca_adapter_ids[] = {
 	DE210_ID,
 	DE212_ID,
 	0x0000
 };
 
-static const char *depca_mca_adapter_name[] = {
+static char *depca_mca_adapter_name[] = {
 	"DEC EtherWORKS MC Adapter (DE210)",
 	"DEC EtherWORKS MC Adapter (DE212)",
 	NULL
 };
 
-static const enum depca_type depca_mca_adapter_type[] = {
+static enum depca_type depca_mca_adapter_type[] = {
 	de210,
 	de212,
 	0
@@ -541,9 +541,10 @@ static void SetMulticastFilter(struct net_device *dev);
 static int load_packet(struct net_device *dev, struct sk_buff *skb);
 static void depca_dbg_open(struct net_device *dev);
 
-static const u_char de1xx_irq[] __devinitconst = { 2, 3, 4, 5, 7, 9, 0 };
-static const u_char de2xx_irq[] __devinitconst = { 5, 9, 10, 11, 15, 0 };
-static const u_char de422_irq[] __devinitconst = { 5, 9, 10, 11, 0 };
+static u_char de1xx_irq[] __initdata = { 2, 3, 4, 5, 7, 9, 0 };
+static u_char de2xx_irq[] __initdata = { 5, 9, 10, 11, 15, 0 };
+static u_char de422_irq[] __initdata = { 5, 9, 10, 11, 0 };
+static u_char *depca_irq;
 
 static int irq;
 static int io;
@@ -579,7 +580,7 @@ static const struct net_device_ops depca_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
-static int __devinit depca_hw_init (struct net_device *dev, struct device *device)
+static int __init depca_hw_init (struct net_device *dev, struct device *device)
 {
 	struct depca_private *lp;
 	int i, j, offset, netRAM, mem_len, status = 0;
@@ -747,7 +748,6 @@ static int __devinit depca_hw_init (struct net_device *dev, struct device *devic
 	if (dev->irq < 2) {
 		unsigned char irqnum;
 		unsigned long irq_mask, delay;
-		const u_char *depca_irq;
 
 		irq_mask = probe_irq_on();
 
@@ -770,7 +770,6 @@ static int __devinit depca_hw_init (struct net_device *dev, struct device *devic
 			break;
 
 		default:
-			depca_irq = NULL;
 			break;	/* Not reached */
 		}
 
@@ -1303,7 +1302,7 @@ static void SetMulticastFilter(struct net_device *dev)
 	}
 }
 
-static int __devinit depca_common_init (u_long ioaddr, struct net_device **devp)
+static int __init depca_common_init (u_long ioaddr, struct net_device **devp)
 {
 	int status = 0;
 
@@ -1334,7 +1333,7 @@ static int __devinit depca_common_init (u_long ioaddr, struct net_device **devp)
 /*
 ** Microchannel bus I/O device probe
 */
-static int __devinit depca_mca_probe(struct device *device)
+static int __init depca_mca_probe(struct device *device)
 {
 	unsigned char pos[2];
 	unsigned char where;
@@ -1458,7 +1457,7 @@ static int __devinit depca_mca_probe(struct device *device)
 ** ISA bus I/O device probe
 */
 
-static void __devinit depca_platform_probe (void)
+static void __init depca_platform_probe (void)
 {
 	int i;
 	struct platform_device *pldev;
@@ -1498,7 +1497,7 @@ static void __devinit depca_platform_probe (void)
 	}
 }
 
-static enum depca_type __devinit depca_shmem_probe (ulong *mem_start)
+static enum depca_type __init depca_shmem_probe (ulong *mem_start)
 {
 	u_long mem_base[] = DEPCA_RAM_BASE_ADDRESSES;
 	enum depca_type adapter = unknown;
@@ -1559,7 +1558,7 @@ static int __devinit depca_isa_probe (struct platform_device *device)
 */
 
 #ifdef CONFIG_EISA
-static int __devinit depca_eisa_probe (struct device *device)
+static int __init depca_eisa_probe (struct device *device)
 {
 	enum depca_type adapter = unknown;
 	struct eisa_device *edev;
@@ -1630,7 +1629,7 @@ static int __devexit depca_device_remove (struct device *device)
 ** and Boot (readb) ROM. This will also give us a clue to the network RAM
 ** base address.
 */
-static int __devinit DepcaSignature(char *name, u_long base_addr)
+static int __init DepcaSignature(char *name, u_long base_addr)
 {
 	u_int i, j, k;
 	void __iomem *ptr;
diff --git a/drivers/net/dl2k.c b/drivers/net/dl2k.c
index c445457b66d5..23179dbcedd2 100644
--- a/drivers/net/dl2k.c
+++ b/drivers/net/dl2k.c
@@ -346,7 +346,7 @@ parse_eeprom (struct net_device *dev)
 	if (np->pdev->vendor == PCI_VENDOR_ID_DLINK) {	/* D-Link Only */
 		/* Check CRC */
 		crc = ~ether_crc_le (256 - 4, sromdata);
-		if (psrom->crc != crc) {
+		if (psrom->crc != cpu_to_le32(crc)) {
 			printk (KERN_ERR "%s: EEPROM data CRC error.\n",
 					dev->name);
 			return -1;
diff --git a/drivers/net/dm9000.c b/drivers/net/dm9000.c
index fbaff3584bd4..ee597e676ee5 100644
--- a/drivers/net/dm9000.c
+++ b/drivers/net/dm9000.c
@@ -1157,9 +1157,6 @@ dm9000_open(struct net_device *dev)
 
 	irqflags |= IRQF_SHARED;
 
-	if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev))
-		return -EAGAIN;
-
 	/* GPIO0 on pre-activate PHY, Reg 1F is not set by reset */
 	iow(db, DM9000_GPR, 0);	/* REG_1F bit0 activate phyxcer */
 	mdelay(1); /* delay needs by DM9000B */
@@ -1168,6 +1165,9 @@ dm9000_open(struct net_device *dev)
 	dm9000_reset(db);
 	dm9000_init_dm9000(dev);
 
+	if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev))
+		return -EAGAIN;
+
 	/* Init driver variable */
 	db->dbug_cnt = 0;
 
diff --git a/drivers/net/fs_enet/mac-fcc.c b/drivers/net/fs_enet/mac-fcc.c
index 7a84e45487e8..7583a9572bcc 100644
--- a/drivers/net/fs_enet/mac-fcc.c
+++ b/drivers/net/fs_enet/mac-fcc.c
@@ -105,7 +105,7 @@ static int do_pd_setup(struct fs_enet_private *fep)
 		goto out_ep;
 
 	fep->fcc.mem = (void __iomem *)cpm2_immr;
-	fpi->dpram_offset = cpm_dpalloc(128, 8);
+	fpi->dpram_offset = cpm_dpalloc(128, 32);
 	if (IS_ERR_VALUE(fpi->dpram_offset)) {
 		ret = fpi->dpram_offset;
 		goto out_fcccp;
diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c
index ff60b23a5b74..2dfcc8047847 100644
--- a/drivers/net/gianfar.c
+++ b/drivers/net/gianfar.c
@@ -10,7 +10,7 @@
  * Maintainer: Kumar Gala
  * Modifier: Sandeep Gopalpet <sandeep.kumar@freescale.com>
  *
- * Copyright 2002-2009 Freescale Semiconductor, Inc.
+ * Copyright 2002-2009, 2011 Freescale Semiconductor, Inc.
  * Copyright 2007 MontaVista Software, Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
@@ -476,9 +476,6 @@ static const struct net_device_ops gfar_netdev_ops = {
 #endif
 };
 
-unsigned int ftp_rqfpr[MAX_FILER_IDX + 1];
-unsigned int ftp_rqfcr[MAX_FILER_IDX + 1];
-
 void lock_rx_qs(struct gfar_private *priv)
 {
 	int i = 0x0;
@@ -868,28 +865,28 @@ static u32 cluster_entry_per_class(struct gfar_private *priv, u32 rqfar,
 
 	rqfar--;
 	rqfcr = RQFCR_CLE | RQFCR_PID_MASK | RQFCR_CMP_EXACT;
-	ftp_rqfpr[rqfar] = rqfpr;
-	ftp_rqfcr[rqfar] = rqfcr;
+	priv->ftp_rqfpr[rqfar] = rqfpr;
+	priv->ftp_rqfcr[rqfar] = rqfcr;
 	gfar_write_filer(priv, rqfar, rqfcr, rqfpr);
 
 	rqfar--;
 	rqfcr = RQFCR_CMP_NOMATCH;
-	ftp_rqfpr[rqfar] = rqfpr;
-	ftp_rqfcr[rqfar] = rqfcr;
+	priv->ftp_rqfpr[rqfar] = rqfpr;
+	priv->ftp_rqfcr[rqfar] = rqfcr;
 	gfar_write_filer(priv, rqfar, rqfcr, rqfpr);
 
 	rqfar--;
 	rqfcr = RQFCR_CMP_EXACT | RQFCR_PID_PARSE | RQFCR_CLE | RQFCR_AND;
 	rqfpr = class;
-	ftp_rqfcr[rqfar] = rqfcr;
-	ftp_rqfpr[rqfar] = rqfpr;
+	priv->ftp_rqfcr[rqfar] = rqfcr;
+	priv->ftp_rqfpr[rqfar] = rqfpr;
 	gfar_write_filer(priv, rqfar, rqfcr, rqfpr);
 
 	rqfar--;
 	rqfcr = RQFCR_CMP_EXACT | RQFCR_PID_MASK | RQFCR_AND;
 	rqfpr = class;
-	ftp_rqfcr[rqfar] = rqfcr;
-	ftp_rqfpr[rqfar] = rqfpr;
+	priv->ftp_rqfcr[rqfar] = rqfcr;
+	priv->ftp_rqfpr[rqfar] = rqfpr;
 	gfar_write_filer(priv, rqfar, rqfcr, rqfpr);
 
 	return rqfar;
@@ -904,8 +901,8 @@ static void gfar_init_filer_table(struct gfar_private *priv)
 
 	/* Default rule */
 	rqfcr = RQFCR_CMP_MATCH;
-	ftp_rqfcr[rqfar] = rqfcr;
-	ftp_rqfpr[rqfar] = rqfpr;
+	priv->ftp_rqfcr[rqfar] = rqfcr;
+	priv->ftp_rqfpr[rqfar] = rqfpr;
 	gfar_write_filer(priv, rqfar, rqfcr, rqfpr);
 
 	rqfar = cluster_entry_per_class(priv, rqfar, RQFPR_IPV6);
@@ -921,8 +918,8 @@ static void gfar_init_filer_table(struct gfar_private *priv)
 	/* Rest are masked rules */
 	rqfcr = RQFCR_CMP_NOMATCH;
 	for (i = 0; i < rqfar; i++) {
-		ftp_rqfcr[i] = rqfcr;
-		ftp_rqfpr[i] = rqfpr;
+		priv->ftp_rqfcr[i] = rqfcr;
+		priv->ftp_rqfpr[i] = rqfpr;
 		gfar_write_filer(priv, i, rqfcr, rqfpr);
 	}
 }
diff --git a/drivers/net/gianfar.h b/drivers/net/gianfar.h
index fc86f5195445..ba36dc7a3435 100644
--- a/drivers/net/gianfar.h
+++ b/drivers/net/gianfar.h
@@ -9,7 +9,7 @@
  * Maintainer: Kumar Gala
  * Modifier: Sandeep Gopalpet <sandeep.kumar@freescale.com>
  *
- * Copyright 2002-2009 Freescale Semiconductor, Inc.
+ * Copyright 2002-2009, 2011 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
@@ -1107,10 +1107,12 @@ struct gfar_private {
 	/* HW time stamping enabled flag */
 	int hwts_rx_en;
 	int hwts_tx_en;
+
+	/*Filer table*/
+	unsigned int ftp_rqfpr[MAX_FILER_IDX + 1];
+	unsigned int ftp_rqfcr[MAX_FILER_IDX + 1];
 };
 
-extern unsigned int ftp_rqfpr[MAX_FILER_IDX + 1];
-extern unsigned int ftp_rqfcr[MAX_FILER_IDX + 1];
 
 static inline int gfar_has_errata(struct gfar_private *priv,
 				  enum gfar_errata err)
diff --git a/drivers/net/gianfar_ethtool.c b/drivers/net/gianfar_ethtool.c
index 493d743839d9..239e3330495f 100644
--- a/drivers/net/gianfar_ethtool.c
+++ b/drivers/net/gianfar_ethtool.c
@@ -9,7 +9,7 @@
  *  Maintainer: Kumar Gala
  *  Modifier: Sandeep Gopalpet <sandeep.kumar@freescale.com>
  *
- *  Copyright 2003-2006, 2008-2009 Freescale Semiconductor, Inc.
+ *  Copyright 2003-2006, 2008-2009, 2011 Freescale Semiconductor, Inc.
  *
  *  This software may be used and distributed according to
  *  the terms of the GNU Public License, Version 2, incorporated herein
@@ -609,15 +609,15 @@ static void ethflow_to_filer_rules (struct gfar_private *priv, u64 ethflow)
 	if (ethflow & RXH_L2DA) {
 		fcr = RQFCR_PID_DAH |RQFCR_CMP_NOMATCH |
 			RQFCR_HASH | RQFCR_AND | RQFCR_HASHTBL_0;
-		ftp_rqfpr[priv->cur_filer_idx] = fpr;
-		ftp_rqfcr[priv->cur_filer_idx] = fcr;
+		priv->ftp_rqfpr[priv->cur_filer_idx] = fpr;
+		priv->ftp_rqfcr[priv->cur_filer_idx] = fcr;
 		gfar_write_filer(priv, priv->cur_filer_idx, fcr, fpr);
 		priv->cur_filer_idx = priv->cur_filer_idx - 1;
 
 		fcr = RQFCR_PID_DAL | RQFCR_AND | RQFCR_CMP_NOMATCH |
 				RQFCR_HASH | RQFCR_AND | RQFCR_HASHTBL_0;
-		ftp_rqfpr[priv->cur_filer_idx] = fpr;
-		ftp_rqfcr[priv->cur_filer_idx] = fcr;
+		priv->ftp_rqfpr[priv->cur_filer_idx] = fpr;
+		priv->ftp_rqfcr[priv->cur_filer_idx] = fcr;
 		gfar_write_filer(priv, priv->cur_filer_idx, fcr, fpr);
 		priv->cur_filer_idx = priv->cur_filer_idx - 1;
 	}
@@ -626,16 +626,16 @@ static void ethflow_to_filer_rules (struct gfar_private *priv, u64 ethflow)
 		fcr = RQFCR_PID_VID | RQFCR_CMP_NOMATCH | RQFCR_HASH |
 				RQFCR_AND | RQFCR_HASHTBL_0;
 		gfar_write_filer(priv, priv->cur_filer_idx, fcr, fpr);
-		ftp_rqfpr[priv->cur_filer_idx] = fpr;
-		ftp_rqfcr[priv->cur_filer_idx] = fcr;
+		priv->ftp_rqfpr[priv->cur_filer_idx] = fpr;
+		priv->ftp_rqfcr[priv->cur_filer_idx] = fcr;
 		priv->cur_filer_idx = priv->cur_filer_idx - 1;
 	}
 
 	if (ethflow & RXH_IP_SRC) {
 		fcr = RQFCR_PID_SIA | RQFCR_CMP_NOMATCH | RQFCR_HASH |
 			RQFCR_AND | RQFCR_HASHTBL_0;
-		ftp_rqfpr[priv->cur_filer_idx] = fpr;
-		ftp_rqfcr[priv->cur_filer_idx] = fcr;
+		priv->ftp_rqfpr[priv->cur_filer_idx] = fpr;
+		priv->ftp_rqfcr[priv->cur_filer_idx] = fcr;
 		gfar_write_filer(priv, priv->cur_filer_idx, fcr, fpr);
 		priv->cur_filer_idx = priv->cur_filer_idx - 1;
 	}
@@ -643,8 +643,8 @@ static void ethflow_to_filer_rules (struct gfar_private *priv, u64 ethflow)
 	if (ethflow & (RXH_IP_DST)) {
 		fcr = RQFCR_PID_DIA | RQFCR_CMP_NOMATCH | RQFCR_HASH |
 			RQFCR_AND | RQFCR_HASHTBL_0;
-		ftp_rqfpr[priv->cur_filer_idx] = fpr;
-		ftp_rqfcr[priv->cur_filer_idx] = fcr;
+		priv->ftp_rqfpr[priv->cur_filer_idx] = fpr;
+		priv->ftp_rqfcr[priv->cur_filer_idx] = fcr;
 		gfar_write_filer(priv, priv->cur_filer_idx, fcr, fpr);
 		priv->cur_filer_idx = priv->cur_filer_idx - 1;
 	}
@@ -652,8 +652,8 @@ static void ethflow_to_filer_rules (struct gfar_private *priv, u64 ethflow)
 	if (ethflow & RXH_L3_PROTO) {
 		fcr = RQFCR_PID_L4P | RQFCR_CMP_NOMATCH | RQFCR_HASH |
 			RQFCR_AND | RQFCR_HASHTBL_0;
-		ftp_rqfpr[priv->cur_filer_idx] = fpr;
-		ftp_rqfcr[priv->cur_filer_idx] = fcr;
+		priv->ftp_rqfpr[priv->cur_filer_idx] = fpr;
+		priv->ftp_rqfcr[priv->cur_filer_idx] = fcr;
 		gfar_write_filer(priv, priv->cur_filer_idx, fcr, fpr);
 		priv->cur_filer_idx = priv->cur_filer_idx - 1;
 	}
@@ -661,8 +661,8 @@ static void ethflow_to_filer_rules (struct gfar_private *priv, u64 ethflow)
 	if (ethflow & RXH_L4_B_0_1) {
 		fcr = RQFCR_PID_SPT | RQFCR_CMP_NOMATCH | RQFCR_HASH |
 			RQFCR_AND | RQFCR_HASHTBL_0;
-		ftp_rqfpr[priv->cur_filer_idx] = fpr;
-		ftp_rqfcr[priv->cur_filer_idx] = fcr;
+		priv->ftp_rqfpr[priv->cur_filer_idx] = fpr;
+		priv->ftp_rqfcr[priv->cur_filer_idx] = fcr;
 		gfar_write_filer(priv, priv->cur_filer_idx, fcr, fpr);
 		priv->cur_filer_idx = priv->cur_filer_idx - 1;
 	}
@@ -670,8 +670,8 @@ static void ethflow_to_filer_rules (struct gfar_private *priv, u64 ethflow)
 	if (ethflow & RXH_L4_B_2_3) {
 		fcr = RQFCR_PID_DPT | RQFCR_CMP_NOMATCH | RQFCR_HASH |
 			RQFCR_AND | RQFCR_HASHTBL_0;
-		ftp_rqfpr[priv->cur_filer_idx] = fpr;
-		ftp_rqfcr[priv->cur_filer_idx] = fcr;
+		priv->ftp_rqfpr[priv->cur_filer_idx] = fpr;
+		priv->ftp_rqfcr[priv->cur_filer_idx] = fcr;
 		gfar_write_filer(priv, priv->cur_filer_idx, fcr, fpr);
 		priv->cur_filer_idx = priv->cur_filer_idx - 1;
 	}
@@ -705,12 +705,12 @@ static int gfar_ethflow_to_filer_table(struct gfar_private *priv, u64 ethflow, u
 	}
 
 	for (i = 0; i < MAX_FILER_IDX + 1; i++) {
-		local_rqfpr[j] = ftp_rqfpr[i];
-		local_rqfcr[j] = ftp_rqfcr[i];
+		local_rqfpr[j] = priv->ftp_rqfpr[i];
+		local_rqfcr[j] = priv->ftp_rqfcr[i];
 		j--;
-		if ((ftp_rqfcr[i] == (RQFCR_PID_PARSE |
+		if ((priv->ftp_rqfcr[i] == (RQFCR_PID_PARSE |
 			RQFCR_CLE |RQFCR_AND)) &&
-			(ftp_rqfpr[i] == cmp_rqfpr))
+			(priv->ftp_rqfpr[i] == cmp_rqfpr))
 			break;
 	}
 
@@ -724,20 +724,22 @@ static int gfar_ethflow_to_filer_table(struct gfar_private *priv, u64 ethflow, u
 	 * if it was already programmed, we need to overwrite these rules
 	 */
 	for (l = i+1; l < MAX_FILER_IDX; l++) {
-		if ((ftp_rqfcr[l] & RQFCR_CLE) &&
-			!(ftp_rqfcr[l] & RQFCR_AND)) {
-			ftp_rqfcr[l] = RQFCR_CLE | RQFCR_CMP_EXACT |
+		if ((priv->ftp_rqfcr[l] & RQFCR_CLE) &&
+			!(priv->ftp_rqfcr[l] & RQFCR_AND)) {
+			priv->ftp_rqfcr[l] = RQFCR_CLE | RQFCR_CMP_EXACT |
 				RQFCR_HASHTBL_0 | RQFCR_PID_MASK;
-			ftp_rqfpr[l] = FPR_FILER_MASK;
-			gfar_write_filer(priv, l, ftp_rqfcr[l], ftp_rqfpr[l]);
+			priv->ftp_rqfpr[l] = FPR_FILER_MASK;
+			gfar_write_filer(priv, l, priv->ftp_rqfcr[l],
+				priv->ftp_rqfpr[l]);
 			break;
 		}
 
-		if (!(ftp_rqfcr[l] & RQFCR_CLE) && (ftp_rqfcr[l] & RQFCR_AND))
+		if (!(priv->ftp_rqfcr[l] & RQFCR_CLE) &&
+			(priv->ftp_rqfcr[l] & RQFCR_AND))
 			continue;
 		else {
-			local_rqfpr[j] = ftp_rqfpr[l];
-			local_rqfcr[j] = ftp_rqfcr[l];
+			local_rqfpr[j] = priv->ftp_rqfpr[l];
+			local_rqfcr[j] = priv->ftp_rqfcr[l];
 			j--;
 		}
 	}
@@ -750,8 +752,8 @@ static int gfar_ethflow_to_filer_table(struct gfar_private *priv, u64 ethflow, u
 
 	/* Write back the popped out rules again */
 	for (k = j+1; k < MAX_FILER_IDX; k++) {
-		ftp_rqfpr[priv->cur_filer_idx] = local_rqfpr[k];
-		ftp_rqfcr[priv->cur_filer_idx] = local_rqfcr[k];
+		priv->ftp_rqfpr[priv->cur_filer_idx] = local_rqfpr[k];
+		priv->ftp_rqfcr[priv->cur_filer_idx] = local_rqfcr[k];
 		gfar_write_filer(priv, priv->cur_filer_idx,
 				local_rqfcr[k], local_rqfpr[k]);
 		if (!priv->cur_filer_idx)
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 992089639ea4..3e5d0b6b6516 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -456,7 +456,7 @@ out:
  * a block of 6pack data has been received, which can now be decapsulated
  * and sent on to some IP layer for further processing.
  */
-static unsigned int sixpack_receive_buf(struct tty_struct *tty,
+static void sixpack_receive_buf(struct tty_struct *tty,
 	const unsigned char *cp, char *fp, int count)
 {
 	struct sixpack *sp;
@@ -464,11 +464,11 @@ static unsigned int sixpack_receive_buf(struct tty_struct *tty,
 	int count1;
 
 	if (!count)
-		return 0;
+		return;
 
 	sp = sp_get(tty);
 	if (!sp)
-		return -ENODEV;
+		return;
 
 	memcpy(buf, cp, count < sizeof(buf) ? count : sizeof(buf));
 
@@ -487,8 +487,6 @@ static unsigned int sixpack_receive_buf(struct tty_struct *tty,
 
 	sp_put(sp);
 	tty_unthrottle(tty);
-
-	return count1;
 }
 
 /*
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 0e4f23531140..4c628393c8b1 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -923,14 +923,13 @@ static long mkiss_compat_ioctl(struct tty_struct *tty, struct file *file,
  * a block of data has been received, which can now be decapsulated
  * and sent on to the AX.25 layer for further processing.
  */
-static unsigned int mkiss_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void mkiss_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+	char *fp, int count)
 {
 	struct mkiss *ax = mkiss_get(tty);
-	int bytes = count;
 
 	if (!ax)
-		return -ENODEV;
+		return;
 
 	/*
 	 * Argh! mtu change time! - costs us the packet part received
@@ -940,7 +939,7 @@ static unsigned int mkiss_receive_buf(struct tty_struct *tty,
 		ax_changedmtu(ax);
 
 	/* Read the characters out of the buffer */
-	while (bytes--) {
+	while (count--) {
 		if (fp != NULL && *fp++) {
 			if (!test_and_set_bit(AXF_ERROR, &ax->flags))
 				ax->dev->stats.rx_errors++;
@@ -953,8 +952,6 @@ static unsigned int mkiss_receive_buf(struct tty_struct *tty,
 
 	mkiss_put(ax);
 	tty_unthrottle(tty);
-
-	return count;
 }
 
 /*
diff --git a/drivers/net/hp100.c b/drivers/net/hp100.c
index c52a1df5d922..c3ecb118c1df 100644
--- a/drivers/net/hp100.c
+++ b/drivers/net/hp100.c
@@ -188,14 +188,14 @@ struct hp100_private {
  *  variables
  */
 #ifdef CONFIG_ISA
-static const char *const hp100_isa_tbl[] __devinitconst = {
+static const char *hp100_isa_tbl[] = {
 	"HWPF150", /* HP J2573 rev A */
 	"HWP1950", /* HP J2573 */
 };
 #endif
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id hp100_eisa_tbl[] __devinitconst = {
+static struct eisa_device_id hp100_eisa_tbl[] = {
 	{ "HWPF180" }, /* HP J2577 rev A */
 	{ "HWP1920" }, /* HP 27248B */
 	{ "HWP1940" }, /* HP J2577 */
@@ -336,7 +336,7 @@ static __devinit const char *hp100_read_id(int ioaddr)
 }
 
 #ifdef CONFIG_ISA
-static __devinit int hp100_isa_probe1(struct net_device *dev, int ioaddr)
+static __init int hp100_isa_probe1(struct net_device *dev, int ioaddr)
 {
 	const char *sig;
 	int i;
@@ -372,7 +372,7 @@ static __devinit int hp100_isa_probe1(struct net_device *dev, int ioaddr)
  * EISA and PCI are handled by device infrastructure.
  */
 
-static int  __devinit hp100_isa_probe(struct net_device *dev, int addr)
+static int  __init hp100_isa_probe(struct net_device *dev, int addr)
 {
 	int err = -ENODEV;
 
@@ -396,7 +396,7 @@ static int  __devinit hp100_isa_probe(struct net_device *dev, int addr)
 #endif /* CONFIG_ISA */
 
 #if !defined(MODULE) && defined(CONFIG_ISA)
-struct net_device * __devinit hp100_probe(int unit)
+struct net_device * __init hp100_probe(int unit)
 {
 	struct net_device *dev = alloc_etherdev(sizeof(struct hp100_private));
 	int err;
@@ -1580,12 +1580,12 @@ static netdev_tx_t hp100_start_xmit_bm(struct sk_buff *skb,
 	hp100_outl(ringptr->pdl_paddr, TX_PDA_L);	/* Low Prio. Queue */
 
 	lp->txrcommit++;
-	spin_unlock_irqrestore(&lp->lock, flags);
 
-	/* Update statistics */
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
 
+	spin_unlock_irqrestore(&lp->lock, flags);
+
 	return NETDEV_TX_OK;
 
 drop:
@@ -2843,7 +2843,7 @@ static void cleanup_dev(struct net_device *d)
 }
 
 #ifdef CONFIG_EISA
-static int __devinit hp100_eisa_probe (struct device *gendev)
+static int __init hp100_eisa_probe (struct device *gendev)
 {
 	struct net_device *dev = alloc_etherdev(sizeof(struct hp100_private));
 	struct eisa_device *edev = to_eisa_device(gendev);
diff --git a/drivers/net/hplance.c b/drivers/net/hplance.c
index b6060f7538df..a900d5bf2948 100644
--- a/drivers/net/hplance.c
+++ b/drivers/net/hplance.c
@@ -135,7 +135,7 @@ static void __devexit hplance_remove_one(struct dio_dev *d)
 }
 
 /* Initialise a single lance board at the given DIO device */
-static void __init hplance_init(struct net_device *dev, struct dio_dev *d)
+static void __devinit hplance_init(struct net_device *dev, struct dio_dev *d)
 {
         unsigned long va = (d->resource.start + DIO_VIRADDRBASE);
         struct hplance_private *lp;
diff --git a/drivers/net/ibmlana.c b/drivers/net/ibmlana.c
index 136d7544cc33..a7d6cad32953 100644
--- a/drivers/net/ibmlana.c
+++ b/drivers/net/ibmlana.c
@@ -895,12 +895,12 @@ static int ibmlana_irq;
 static int ibmlana_io;
 static int startslot;		/* counts through slots when probing multiple devices */
 
-static const short ibmlana_adapter_ids[] __devinitconst = {
+static short ibmlana_adapter_ids[] __initdata = {
 	IBM_LANA_ID,
 	0x0000
 };
 
-static const char *const ibmlana_adapter_names[] __devinitconst = {
+static char *ibmlana_adapter_names[] __devinitdata = {
 	"IBM LAN Adapter/A",
 	NULL
 };
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 18fccf913635..2c28621eb30b 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -2373,6 +2373,9 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter)
 	}
 #endif /* CONFIG_PCI_IOV */
 	adapter->rss_queues = min_t(u32, IGB_MAX_RX_QUEUES, num_online_cpus());
+	/* i350 cannot do RSS and SR-IOV at the same time */
+	if (hw->mac.type == e1000_i350 && adapter->vfs_allocated_count)
+		adapter->rss_queues = 1;
 
 	/*
 	 * if rss_queues > 4 or vfs are going to be allocated with rss_queues
diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c
index 035861d8acb1..3352b2443e58 100644
--- a/drivers/net/irda/irtty-sir.c
+++ b/drivers/net/irda/irtty-sir.c
@@ -216,23 +216,23 @@ static int irtty_do_write(struct sir_dev *dev, const unsigned char *ptr, size_t
  * usbserial:	urb-complete-interrupt / softint
  */
 
-static unsigned int irtty_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void irtty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+			      char *fp, int count) 
 {
 	struct sir_dev *dev;
 	struct sirtty_cb *priv = tty->disc_data;
 	int	i;
 
-	IRDA_ASSERT(priv != NULL, return -ENODEV;);
-	IRDA_ASSERT(priv->magic == IRTTY_MAGIC, return -EINVAL;);
+	IRDA_ASSERT(priv != NULL, return;);
+	IRDA_ASSERT(priv->magic == IRTTY_MAGIC, return;);
 
 	if (unlikely(count==0))		/* yes, this happens */
-		return 0;
+		return;
 
 	dev = priv->dev;
 	if (!dev) {
 		IRDA_WARNING("%s(), not ready yet!\n", __func__);
-		return -ENODEV;
+		return;
 	}
 
 	for (i = 0; i < count; i++) {
@@ -242,13 +242,11 @@ static unsigned int irtty_receive_buf(struct tty_struct *tty,
  		if (fp && *fp++) { 
 			IRDA_DEBUG(0, "Framing or parity error!\n");
 			sirdev_receive(dev, NULL, 0);	/* notify sir_dev (updating stats) */
-			return -EINVAL;
+			return;
  		}
 	}
 
 	sirdev_receive(dev, cp, count);
-
-	return count;
 }
 
 /*
diff --git a/drivers/net/irda/smsc-ircc2.c b/drivers/net/irda/smsc-ircc2.c
index 69b5707db369..8800e1fe4129 100644
--- a/drivers/net/irda/smsc-ircc2.c
+++ b/drivers/net/irda/smsc-ircc2.c
@@ -222,19 +222,19 @@ static void smsc_ircc_set_transceiver_for_speed(struct smsc_ircc_cb *self, u32 s
 static void smsc_ircc_sir_wait_hw_transmitter_finish(struct smsc_ircc_cb *self);
 
 /* Probing */
-static int smsc_ircc_look_for_chips(void);
-static const struct smsc_chip * smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type);
-static int smsc_superio_flat(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
-static int smsc_superio_paged(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
-static int smsc_superio_fdc(unsigned short cfg_base);
-static int smsc_superio_lpc(unsigned short cfg_base);
+static int __init smsc_ircc_look_for_chips(void);
+static const struct smsc_chip * __init smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type);
+static int __init smsc_superio_flat(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
+static int __init smsc_superio_paged(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
+static int __init smsc_superio_fdc(unsigned short cfg_base);
+static int __init smsc_superio_lpc(unsigned short cfg_base);
 #ifdef CONFIG_PCI
-static int preconfigure_smsc_chip(struct smsc_ircc_subsystem_configuration *conf);
-static int preconfigure_through_82801(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
-static void preconfigure_ali_port(struct pci_dev *dev,
+static int __init preconfigure_smsc_chip(struct smsc_ircc_subsystem_configuration *conf);
+static int __init preconfigure_through_82801(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
+static void __init preconfigure_ali_port(struct pci_dev *dev,
 					 unsigned short port);
-static int preconfigure_through_ali(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
-static int smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
+static int __init preconfigure_through_ali(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
+static int __init smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
 						    unsigned short ircc_fir,
 						    unsigned short ircc_sir,
 						    unsigned char ircc_dma,
@@ -366,7 +366,7 @@ static inline void register_bank(int iobase, int bank)
 }
 
 /* PNP hotplug support */
-static const struct pnp_device_id smsc_ircc_pnp_table[] __devinitconst = {
+static const struct pnp_device_id smsc_ircc_pnp_table[] = {
 	{ .id = "SMCf010", .driver_data = 0 },
 	/* and presumably others */
 	{ }
@@ -515,7 +515,7 @@ static const struct net_device_ops smsc_ircc_netdev_ops = {
  *    Try to open driver instance
  *
  */
-static int __devinit smsc_ircc_open(unsigned int fir_base, unsigned int sir_base, u8 dma, u8 irq)
+static int __init smsc_ircc_open(unsigned int fir_base, unsigned int sir_base, u8 dma, u8 irq)
 {
 	struct smsc_ircc_cb *self;
 	struct net_device *dev;
@@ -2273,7 +2273,7 @@ static int __init smsc_superio_paged(const struct smsc_chip *chips, unsigned sho
 }
 
 
-static int __devinit smsc_access(unsigned short cfg_base, unsigned char reg)
+static int __init smsc_access(unsigned short cfg_base, unsigned char reg)
 {
 	IRDA_DEBUG(1, "%s\n", __func__);
 
@@ -2281,7 +2281,7 @@ static int __devinit smsc_access(unsigned short cfg_base, unsigned char reg)
 	return inb(cfg_base) != reg ? -1 : 0;
 }
 
-static const struct smsc_chip * __devinit smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type)
+static const struct smsc_chip * __init smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type)
 {
 	u8 devid, xdevid, rev;
 
@@ -2406,7 +2406,7 @@ static int __init smsc_superio_lpc(unsigned short cfg_base)
 #ifdef CONFIG_PCI
 #define PCIID_VENDOR_INTEL 0x8086
 #define PCIID_VENDOR_ALI 0x10b9
-static const struct smsc_ircc_subsystem_configuration subsystem_configurations[] __devinitconst = {
+static struct smsc_ircc_subsystem_configuration subsystem_configurations[] __initdata = {
 	/*
 	 * Subsystems needing entries:
 	 * 0x10b9:0x1533 0x103c:0x0850 HP nx9010 family
@@ -2532,7 +2532,7 @@ static const struct smsc_ircc_subsystem_configuration subsystem_configurations[]
  * (FIR port, SIR port, FIR DMA, FIR IRQ)
  * through the chip configuration port.
  */
-static int __devinit preconfigure_smsc_chip(struct
+static int __init preconfigure_smsc_chip(struct
 					 smsc_ircc_subsystem_configuration
 					 *conf)
 {
@@ -2633,7 +2633,7 @@ static int __devinit preconfigure_smsc_chip(struct
  * or Intel 82801DB/DBL (ICH4/ICH4-L) LPC Interface Bridge.
  * They all work the same way!
  */
-static int __devinit preconfigure_through_82801(struct pci_dev *dev,
+static int __init preconfigure_through_82801(struct pci_dev *dev,
 					     struct
 					     smsc_ircc_subsystem_configuration
 					     *conf)
@@ -2786,7 +2786,7 @@ static int __devinit preconfigure_through_82801(struct pci_dev *dev,
  * This is based on reverse-engineering since ALi does not
  * provide any data sheet for the 1533 chip.
  */
-static void __devinit preconfigure_ali_port(struct pci_dev *dev,
+static void __init preconfigure_ali_port(struct pci_dev *dev,
 					 unsigned short port)
 {
 	unsigned char reg;
@@ -2824,7 +2824,7 @@ static void __devinit preconfigure_ali_port(struct pci_dev *dev,
 	IRDA_MESSAGE("Activated ALi 1533 ISA bridge port 0x%04x.\n", port);
 }
 
-static int __devinit preconfigure_through_ali(struct pci_dev *dev,
+static int __init preconfigure_through_ali(struct pci_dev *dev,
 					   struct
 					   smsc_ircc_subsystem_configuration
 					   *conf)
@@ -2837,7 +2837,7 @@ static int __devinit preconfigure_through_ali(struct pci_dev *dev,
 	return preconfigure_smsc_chip(conf);
 }
 
-static int __devinit smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
+static int __init smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
 						    unsigned short ircc_fir,
 						    unsigned short ircc_sir,
 						    unsigned char ircc_dma,
@@ -2849,7 +2849,7 @@ static int __devinit smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
 	int ret = 0;
 
 	for_each_pci_dev(dev) {
-		const struct smsc_ircc_subsystem_configuration *conf;
+		struct smsc_ircc_subsystem_configuration *conf;
 
 		/*
 		 * Cache the subsystem vendor/device:
diff --git a/drivers/net/ks8842.c b/drivers/net/ks8842.c
index 4d40626b3bfa..fc12ac0d9f2e 100644
--- a/drivers/net/ks8842.c
+++ b/drivers/net/ks8842.c
@@ -661,7 +661,7 @@ static void ks8842_rx_frame(struct net_device *netdev,
 
 	/* check the status */
 	if ((status & RXSR_VALID) && !(status & RXSR_ERROR)) {
-		struct sk_buff *skb = netdev_alloc_skb_ip_align(netdev, len);
+		struct sk_buff *skb = netdev_alloc_skb_ip_align(netdev, len + 3);
 
 		if (skb) {
 
diff --git a/drivers/net/ne3210.c b/drivers/net/ne3210.c
index e8984b0ca521..243ed2aee88e 100644
--- a/drivers/net/ne3210.c
+++ b/drivers/net/ne3210.c
@@ -80,20 +80,17 @@ static void ne3210_block_output(struct net_device *dev, int count, const unsigne
 
 #define NE3210_DEBUG	0x0
 
-static const unsigned char irq_map[] __devinitconst =
-	{ 15, 12, 11, 10, 9, 7, 5, 3 };
-static const unsigned int shmem_map[] __devinitconst =
-	{ 0xff0, 0xfe0, 0xfff0, 0xd8, 0xffe0, 0xffc0, 0xd0, 0x0 };
-static const char *const ifmap[] __devinitconst =
-	{ "UTP", "?", "BNC", "AUI" };
-static const int ifmap_val[] __devinitconst = {
+static unsigned char irq_map[] __initdata = {15, 12, 11, 10, 9, 7, 5, 3};
+static unsigned int shmem_map[] __initdata = {0xff0, 0xfe0, 0xfff0, 0xd8, 0xffe0, 0xffc0, 0xd0, 0x0};
+static const char *ifmap[] __initdata = {"UTP", "?", "BNC", "AUI"};
+static int ifmap_val[] __initdata = {
 		IF_PORT_10BASET,
 		IF_PORT_UNKNOWN,
 		IF_PORT_10BASE2,
 		IF_PORT_AUI,
 };
 
-static int __devinit ne3210_eisa_probe (struct device *device)
+static int __init ne3210_eisa_probe (struct device *device)
 {
 	unsigned long ioaddr, phys_mem;
 	int i, retval, port_index;
@@ -316,7 +313,7 @@ static void ne3210_block_output(struct net_device *dev, int count,
 	memcpy_toio(shmem, buf, count);
 }
 
-static const struct eisa_device_id ne3210_ids[] __devinitconst = {
+static struct eisa_device_id ne3210_ids[] = {
 	{ "EGL0101" },
 	{ "NVL1801" },
 	{ "" },
diff --git a/drivers/net/netxen/netxen_nic_main.c b/drivers/net/netxen/netxen_nic_main.c
index b644383017f9..c0788a31ff0f 100644
--- a/drivers/net/netxen/netxen_nic_main.c
+++ b/drivers/net/netxen/netxen_nic_main.c
@@ -1965,11 +1965,11 @@ netxen_nic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 
 	netxen_tso_check(netdev, tx_ring, first_desc, skb);
 
-	netxen_nic_update_cmd_producer(adapter, tx_ring);
-
 	adapter->stats.txbytes += skb->len;
 	adapter->stats.xmitcalled++;
 
+	netxen_nic_update_cmd_producer(adapter, tx_ring);
+
 	return NETDEV_TX_OK;
 
 drop_packet:
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 392a6c4b72e5..a70244306c94 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -58,6 +58,7 @@ config BROADCOM_PHY
 
 config BCM63XX_PHY
 	tristate "Drivers for Broadcom 63xx SOCs internal PHY"
+	depends on BCM63XX
 	---help---
 	  Currently supports the 6348 and 6358 PHYs.
 
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index b0c9522bb535..2cd8dc5847b4 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -543,11 +543,20 @@ static void recalibrate(struct dp83640_clock *clock)
 
 /* time stamping methods */
 
-static void decode_evnt(struct dp83640_private *dp83640,
-			struct phy_txts *phy_txts, u16 ests)
+static int decode_evnt(struct dp83640_private *dp83640,
+		       void *data, u16 ests)
 {
+	struct phy_txts *phy_txts;
 	struct ptp_clock_event event;
 	int words = (ests >> EVNT_TS_LEN_SHIFT) & EVNT_TS_LEN_MASK;
+	u16 ext_status = 0;
+
+	if (ests & MULT_EVNT) {
+		ext_status = *(u16 *) data;
+		data += sizeof(ext_status);
+	}
+
+	phy_txts = data;
 
 	switch (words) { /* fall through in every case */
 	case 3:
@@ -565,6 +574,9 @@ static void decode_evnt(struct dp83640_private *dp83640,
 	event.timestamp = phy2txts(&dp83640->edata);
 
 	ptp_clock_event(dp83640->clock->ptp_clock, &event);
+
+	words = ext_status ? words + 2 : words + 1;
+	return words * sizeof(u16);
 }
 
 static void decode_rxts(struct dp83640_private *dp83640,
@@ -643,9 +655,7 @@ static void decode_status_frame(struct dp83640_private *dp83640,
 
 		} else if (PSF_EVNT == type && len >= sizeof(*phy_txts)) {
 
-			phy_txts = (struct phy_txts *) ptr;
-			decode_evnt(dp83640, phy_txts, ests);
-			size = sizeof(*phy_txts);
+			size = decode_evnt(dp83640, ptr, ests);
 
 		} else {
 			size = 0;
@@ -1034,8 +1044,8 @@ static bool dp83640_rxtstamp(struct phy_device *phydev,
 
 	if (is_status_frame(skb, type)) {
 		decode_status_frame(dp83640, skb);
-		/* Let the stack drop this frame. */
-		return false;
+		kfree_skb(skb);
+		return true;
 	}
 
 	SKB_PTP_TYPE(skb) = type;
diff --git a/drivers/net/ppp_async.c b/drivers/net/ppp_async.c
index 53872d7d7382..c554a397e558 100644
--- a/drivers/net/ppp_async.c
+++ b/drivers/net/ppp_async.c
@@ -340,7 +340,7 @@ ppp_asynctty_poll(struct tty_struct *tty, struct file *file, poll_table *wait)
 }
 
 /* May sleep, don't call from interrupt level or with interrupts disabled */
-static unsigned int
+static void
 ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf,
 		  char *cflags, int count)
 {
@@ -348,7 +348,7 @@ ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf,
 	unsigned long flags;
 
 	if (!ap)
-		return -ENODEV;
+		return;
 	spin_lock_irqsave(&ap->recv_lock, flags);
 	ppp_async_input(ap, buf, cflags, count);
 	spin_unlock_irqrestore(&ap->recv_lock, flags);
@@ -356,8 +356,6 @@ ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf,
 		tasklet_schedule(&ap->tsk);
 	ap_put(ap);
 	tty_unthrottle(tty);
-
-	return count;
 }
 
 static void
@@ -525,7 +523,7 @@ static void ppp_async_process(unsigned long arg)
 #define PUT_BYTE(ap, buf, c, islcp)	do {		\
 	if ((islcp && c < 0x20) || (ap->xaccm[c >> 5] & (1 << (c & 0x1f)))) {\
 		*buf++ = PPP_ESCAPE;			\
-		*buf++ = c ^ 0x20;			\
+		*buf++ = c ^ PPP_TRANS;			\
 	} else						\
 		*buf++ = c;				\
 } while (0)
@@ -898,7 +896,7 @@ ppp_async_input(struct asyncppp *ap, const unsigned char *buf,
 				sp = skb_put(skb, n);
 				memcpy(sp, buf, n);
 				if (ap->state & SC_ESCAPE) {
-					sp[0] ^= 0x20;
+					sp[0] ^= PPP_TRANS;
 					ap->state &= ~SC_ESCAPE;
 				}
 			}
diff --git a/drivers/net/ppp_synctty.c b/drivers/net/ppp_synctty.c
index 0815790a5cf9..2573f525f11c 100644
--- a/drivers/net/ppp_synctty.c
+++ b/drivers/net/ppp_synctty.c
@@ -381,7 +381,7 @@ ppp_sync_poll(struct tty_struct *tty, struct file *file, poll_table *wait)
 }
 
 /* May sleep, don't call from interrupt level or with interrupts disabled */
-static unsigned int
+static void
 ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf,
 		  char *cflags, int count)
 {
@@ -389,7 +389,7 @@ ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf,
 	unsigned long flags;
 
 	if (!ap)
-		return -ENODEV;
+		return;
 	spin_lock_irqsave(&ap->recv_lock, flags);
 	ppp_sync_input(ap, buf, cflags, count);
 	spin_unlock_irqrestore(&ap->recv_lock, flags);
@@ -397,8 +397,6 @@ ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf,
 		tasklet_schedule(&ap->tsk);
 	sp_put(ap);
 	tty_unthrottle(tty);
-
-	return count;
 }
 
 static void
diff --git a/drivers/net/pxa168_eth.c b/drivers/net/pxa168_eth.c
index 89f7540d90f9..5f597ca592bb 100644
--- a/drivers/net/pxa168_eth.c
+++ b/drivers/net/pxa168_eth.c
@@ -1273,7 +1273,7 @@ static int pxa168_eth_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	wmb();
 	wrl(pep, SDMA_CMD, SDMA_CMD_TXDH | SDMA_CMD_ERD);
 
-	stats->tx_bytes += skb->len;
+	stats->tx_bytes += length;
 	stats->tx_packets++;
 	dev->trans_start = jiffies;
 	if (pep->tx_ring_size - pep->tx_desc_count <= 1) {
diff --git a/drivers/net/qlcnic/qlcnic_hw.c b/drivers/net/qlcnic/qlcnic_hw.c
index e9656616f2a2..a5d9fbf9d816 100644
--- a/drivers/net/qlcnic/qlcnic_hw.c
+++ b/drivers/net/qlcnic/qlcnic_hw.c
@@ -1406,6 +1406,7 @@ qlcnic_dump_que(struct qlcnic_adapter *adapter, struct qlcnic_dump_entry *entry,
 
 	for (loop = 0; loop < que->no_ops; loop++) {
 		QLCNIC_WR_DUMP_REG(que->sel_addr, base, que_id);
+		addr = que->read_addr;
 		for (i = 0; i < cnt; i++) {
 			QLCNIC_RD_DUMP_REG(addr, base, &data);
 			*buffer++ = cpu_to_le32(data);
diff --git a/drivers/net/qlcnic/qlcnic_main.c b/drivers/net/qlcnic/qlcnic_main.c
index 3ab7d2c7baf2..0f6af5c61a7c 100644
--- a/drivers/net/qlcnic/qlcnic_main.c
+++ b/drivers/net/qlcnic/qlcnic_main.c
@@ -2159,6 +2159,7 @@ qlcnic_unmap_buffers(struct pci_dev *pdev, struct sk_buff *skb,
 
 	nf = &pbuf->frag_array[0];
 	pci_unmap_single(pdev, nf->dma, skb_headlen(skb), PCI_DMA_TODEVICE);
+	pbuf->skb = NULL;
 }
 
 static inline void
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index ef1ce2ebeb4a..05d81780d1fd 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -1621,7 +1621,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp,
 	 *
 	 * (RTL_R32(TxConfig) & 0x700000) == 0x200000 ? 8101Eb : 8101Ec
 	 */
-	static const struct {
+	static const struct rtl_mac_info {
 		u32 mask;
 		u32 val;
 		int mac_version;
@@ -1689,7 +1689,8 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp,
 
 		/* Catch-all */
 		{ 0x00000000, 0x00000000,	RTL_GIGA_MAC_NONE   }
-	}, *p = mac_info;
+	};
+	const struct rtl_mac_info *p = mac_info;
 	u32 reg;
 
 	reg = RTL_R32(TxConfig);
@@ -3681,7 +3682,7 @@ static void rtl_set_rx_max_size(void __iomem *ioaddr, unsigned int rx_buf_sz)
 
 static void rtl8169_set_magic_reg(void __iomem *ioaddr, unsigned mac_version)
 {
-	static const struct {
+	static const struct rtl_cfg2_info {
 		u32 mac_version;
 		u32 clk;
 		u32 val;
@@ -3690,7 +3691,8 @@ static void rtl8169_set_magic_reg(void __iomem *ioaddr, unsigned mac_version)
 		{ RTL_GIGA_MAC_VER_05, PCI_Clock_66MHz, 0x000fffff },
 		{ RTL_GIGA_MAC_VER_06, PCI_Clock_33MHz, 0x00ffff00 }, // 8110SCe
 		{ RTL_GIGA_MAC_VER_06, PCI_Clock_66MHz, 0x00ffffff }
-	}, *p = cfg2_info;
+	};
+	const struct rtl_cfg2_info *p = cfg2_info;
 	unsigned int i;
 	u32 clk;
 
diff --git a/drivers/net/sfc/mtd.c b/drivers/net/sfc/mtd.c
index e646bfce2d84..b6304486f244 100644
--- a/drivers/net/sfc/mtd.c
+++ b/drivers/net/sfc/mtd.c
@@ -216,7 +216,7 @@ static void efx_mtd_remove_partition(struct efx_mtd_partition *part)
 	int rc;
 
 	for (;;) {
-		rc = del_mtd_device(&part->mtd);
+		rc = mtd_device_unregister(&part->mtd);
 		if (rc != -EBUSY)
 			break;
 		ssleep(1);
@@ -268,7 +268,7 @@ static int efx_mtd_probe_device(struct efx_nic *efx, struct efx_mtd *efx_mtd)
 		part->mtd.write = efx_mtd->ops->write;
 		part->mtd.sync = efx_mtd_sync;
 
-		if (add_mtd_device(&part->mtd))
+		if (mtd_device_register(&part->mtd, NULL, 0))
 			goto fail;
 	}
 
@@ -280,7 +280,7 @@ fail:
 		--part;
 		efx_mtd_remove_partition(part);
 	}
-	/* add_mtd_device() returns 1 if the MTD table is full */
+	/* mtd_device_register() returns 1 if the MTD table is full */
 	return -ENOMEM;
 }
 
diff --git a/drivers/net/slip.c b/drivers/net/slip.c
index 584809c656d5..8ec1a9a0bb9a 100644
--- a/drivers/net/slip.c
+++ b/drivers/net/slip.c
@@ -670,17 +670,16 @@ static void sl_setup(struct net_device *dev)
  * in parallel
  */
 
-static unsigned int slip_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void slip_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+							char *fp, int count)
 {
 	struct slip *sl = tty->disc_data;
-	int bytes = count;
 
 	if (!sl || sl->magic != SLIP_MAGIC || !netif_running(sl->dev))
-		return -ENODEV;
+		return;
 
 	/* Read the characters out of the buffer */
-	while (bytes--) {
+	while (count--) {
 		if (fp && *fp++) {
 			if (!test_and_set_bit(SLF_ERROR, &sl->flags))
 				sl->dev->stats.rx_errors++;
@@ -694,8 +693,6 @@ static unsigned int slip_receive_buf(struct tty_struct *tty,
 #endif
 			slip_unesc(sl, *cp++);
 	}
-
-	return count;
 }
 
 /************************************
diff --git a/drivers/net/smc-mca.c b/drivers/net/smc-mca.c
index 0f29f261fcfe..d07c39cb4daf 100644
--- a/drivers/net/smc-mca.c
+++ b/drivers/net/smc-mca.c
@@ -156,7 +156,7 @@ static const struct {
    { 14, 15 }
 };
 
-static const short smc_mca_adapter_ids[] __devinitconst = {
+static short smc_mca_adapter_ids[] __initdata = {
 	0x61c8,
 	0x61c9,
 	0x6fc0,
@@ -168,7 +168,7 @@ static const short smc_mca_adapter_ids[] __devinitconst = {
 	0x0000
 };
 
-static const char *const smc_mca_adapter_names[] __devinitconst = {
+static char *smc_mca_adapter_names[] __initdata = {
 	"SMC Ethercard PLUS Elite/A BNC/AUI (WD8013EP/A)",
 	"SMC Ethercard PLUS Elite/A UTP/AUI (WD8013WP/A)",
 	"WD Ethercard PLUS/A (WD8003E/A or WD8003ET/A)",
@@ -199,7 +199,7 @@ static const struct net_device_ops ultramca_netdev_ops = {
 #endif
 };
 
-static int __devinit ultramca_probe(struct device *gen_dev)
+static int __init ultramca_probe(struct device *gen_dev)
 {
 	unsigned short ioaddr;
 	struct net_device *dev;
diff --git a/drivers/net/smc91x.c b/drivers/net/smc91x.c
index dc4805f473e3..f6285748bd3c 100644
--- a/drivers/net/smc91x.c
+++ b/drivers/net/smc91x.c
@@ -2400,8 +2400,10 @@ static const struct of_device_id smc91x_match[] = {
 	{ .compatible = "smsc,lan91c94", },
 	{ .compatible = "smsc,lan91c111", },
 	{},
-}
+};
 MODULE_DEVICE_TABLE(of, smc91x_match);
+#else
+#define smc91x_match NULL
 #endif
 
 static struct dev_pm_ops smc_drv_pm_ops = {
@@ -2416,9 +2418,7 @@ static struct platform_driver smc_driver = {
 		.name	= CARDNAME,
 		.owner	= THIS_MODULE,
 		.pm	= &smc_drv_pm_ops,
-#ifdef CONFIG_OF
 		.of_match_table = smc91x_match,
-#endif
 	},
 };
 
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index f4b01c638a33..a1f9f9eef37d 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -5774,7 +5774,7 @@ static void tg3_skb_error_unmap(struct tg3_napi *tnapi,
 			 dma_unmap_addr(txb, mapping),
 			 skb_headlen(skb),
 			 PCI_DMA_TODEVICE);
-	for (i = 0; i <= last; i++) {
+	for (i = 0; i < last; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
 		entry = NEXT_TX(entry);
diff --git a/drivers/net/tokenring/madgemc.c b/drivers/net/tokenring/madgemc.c
index 1313aa1315f0..2bedc0ace812 100644
--- a/drivers/net/tokenring/madgemc.c
+++ b/drivers/net/tokenring/madgemc.c
@@ -727,7 +727,7 @@ static int __devexit madgemc_remove(struct device *device)
 	return 0;
 }
 
-static const short madgemc_adapter_ids[] __devinitconst = {
+static short madgemc_adapter_ids[] __initdata = {
 	0x002d,
 	0x0000
 };
diff --git a/drivers/net/tulip/de4x5.c b/drivers/net/tulip/de4x5.c
index 45144d5bd11b..efaa1d69b720 100644
--- a/drivers/net/tulip/de4x5.c
+++ b/drivers/net/tulip/de4x5.c
@@ -1995,7 +1995,7 @@ SetMulticastFilter(struct net_device *dev)
 
 static u_char de4x5_irq[] = EISA_ALLOWED_IRQ_LIST;
 
-static int __devinit de4x5_eisa_probe (struct device *gendev)
+static int __init de4x5_eisa_probe (struct device *gendev)
 {
 	struct eisa_device *edev;
 	u_long iobase;
@@ -2097,7 +2097,7 @@ static int __devexit de4x5_eisa_remove (struct device *device)
 	return 0;
 }
 
-static const struct eisa_device_id de4x5_eisa_ids[] __devinitconst = {
+static struct eisa_device_id de4x5_eisa_ids[] = {
         { "DEC4250", 0 },	/* 0 is the board name index... */
         { "" }
 };
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 74e94054ab1a..5235f48be1be 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -460,7 +460,23 @@ static u32 tun_net_fix_features(struct net_device *dev, u32 features)
 
 	return (features & tun->set_features) | (features & ~TUN_USER_FEATURES);
 }
-
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void tun_poll_controller(struct net_device *dev)
+{
+	/*
+	 * Tun only receives frames when:
+	 * 1) the char device endpoint gets data from user space
+	 * 2) the tun socket gets a sendmsg call from user space
+	 * Since both of those are syncronous operations, we are guaranteed
+	 * never to have pending data when we poll for it
+	 * so theres nothing to do here but return.
+	 * We need this though so netpoll recognizes us as an interface that
+	 * supports polling, which enables bridge devices in virt setups to
+	 * still use netconsole
+	 */
+	return;
+}
+#endif
 static const struct net_device_ops tun_netdev_ops = {
 	.ndo_uninit		= tun_net_uninit,
 	.ndo_open		= tun_net_open,
@@ -468,6 +484,9 @@ static const struct net_device_ops tun_netdev_ops = {
 	.ndo_start_xmit		= tun_net_xmit,
 	.ndo_change_mtu		= tun_net_change_mtu,
 	.ndo_fix_features	= tun_net_fix_features,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= tun_poll_controller,
+#endif
 };
 
 static const struct net_device_ops tap_netdev_ops = {
@@ -480,6 +499,9 @@ static const struct net_device_ops tap_netdev_ops = {
 	.ndo_set_multicast_list	= tun_net_mclist,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= tun_poll_controller,
+#endif
 };
 
 /* Initialize net device. */
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 9d4f9117260f..84d4608153c9 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -385,6 +385,16 @@ config USB_NET_CX82310_ETH
 	  router with USB ethernet port. This driver is for routers only,
 	  it will not work with ADSL modems (use cxacru driver instead).
 
+config USB_NET_KALMIA
+	tristate "Samsung Kalmia based LTE USB modem"
+	depends on USB_USBNET
+	help
+	  Choose this option if you have a Samsung Kalmia based USB modem
+	  as Samsung GT-B3730.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called kalmia.
+
 config USB_HSO
 	tristate "Option USB High Speed Mobile Devices"
 	depends on USB && RFKILL
diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile
index c7ec8a5f0a90..c203fa21f6b1 100644
--- a/drivers/net/usb/Makefile
+++ b/drivers/net/usb/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_USB_NET_MCS7830)	+= mcs7830.o
 obj-$(CONFIG_USB_USBNET)	+= usbnet.o
 obj-$(CONFIG_USB_NET_INT51X1)	+= int51x1.o
 obj-$(CONFIG_USB_CDC_PHONET)	+= cdc-phonet.o
+obj-$(CONFIG_USB_NET_KALMIA)	+= kalmia.o
 obj-$(CONFIG_USB_IPHETH)	+= ipheth.o
 obj-$(CONFIG_USB_SIERRA_NET)	+= sierra_net.o
 obj-$(CONFIG_USB_NET_CX82310_ETH)	+= cx82310_eth.o
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index d7221c4a5dcf..8056f8a27c6a 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -495,7 +495,7 @@ static void catc_ctrl_run(struct catc *catc)
 	if (!q->dir && q->buf && q->len)
 		memcpy(catc->ctrl_buf, q->buf, q->len);
 
-	if ((status = usb_submit_urb(catc->ctrl_urb, GFP_KERNEL)))
+	if ((status = usb_submit_urb(catc->ctrl_urb, GFP_ATOMIC)))
 		err("submit(ctrl_urb) status %d", status);
 }
 
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index cdd3ae486109..f33ca6aa29e9 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -54,7 +54,7 @@
 #include <linux/usb/usbnet.h>
 #include <linux/usb/cdc.h>
 
-#define	DRIVER_VERSION				"24-May-2011"
+#define	DRIVER_VERSION				"01-June-2011"
 
 /* CDC NCM subclass 3.2.1 */
 #define USB_CDC_NCM_NDP16_LENGTH_MIN		0x10
@@ -1234,6 +1234,7 @@ static struct usb_driver cdc_ncm_driver = {
 	.disconnect = cdc_ncm_disconnect,
 	.suspend = usbnet_suspend,
 	.resume = usbnet_resume,
+	.reset_resume =	usbnet_resume,
 	.supports_autosuspend = 1,
 };
 
diff --git a/drivers/net/usb/kalmia.c b/drivers/net/usb/kalmia.c
new file mode 100644
index 000000000000..d965fb1e013e
--- /dev/null
+++ b/drivers/net/usb/kalmia.c
@@ -0,0 +1,384 @@
+/*
+ * USB network interface driver for Samsung Kalmia based LTE USB modem like the
+ * Samsung GT-B3730 and GT-B3710.
+ *
+ * Copyright (C) 2011 Marius Bjoernstad Kotsbak <marius@kotsbak.com>
+ *
+ * Sponsored by Quicklink Video Distribution Services Ltd.
+ *
+ * Based on the cdc_eem module.
+ *
+ * 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/module.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ctype.h>
+#include <linux/ethtool.h>
+#include <linux/workqueue.h>
+#include <linux/mii.h>
+#include <linux/usb.h>
+#include <linux/crc32.h>
+#include <linux/usb/cdc.h>
+#include <linux/usb/usbnet.h>
+#include <linux/gfp.h>
+
+/*
+ * The Samsung Kalmia based LTE USB modems have a CDC ACM port for modem control
+ * handled by the "option" module and an ethernet data port handled by this
+ * module.
+ *
+ * The stick must first be switched into modem mode by usb_modeswitch
+ * or similar tool. Then the modem gets sent two initialization packets by
+ * this module, which gives the MAC address of the device. User space can then
+ * connect the modem using AT commands through the ACM port and then use
+ * DHCP on the network interface exposed by this module. Network packets are
+ * sent to and from the modem in a proprietary format discovered after watching
+ * the behavior of the windows driver for the modem.
+ *
+ * More information about the use of the modem is available in usb_modeswitch
+ * forum and the project page:
+ *
+ * http://www.draisberghof.de/usb_modeswitch/bb/viewtopic.php?t=465
+ * https://github.com/mkotsbak/Samsung-GT-B3730-linux-driver
+ */
+
+/* #define	DEBUG */
+/* #define	VERBOSE */
+
+#define KALMIA_HEADER_LENGTH 6
+#define KALMIA_ALIGN_SIZE 4
+#define KALMIA_USB_TIMEOUT 10000
+
+/*-------------------------------------------------------------------------*/
+
+static int
+kalmia_send_init_packet(struct usbnet *dev, u8 *init_msg, u8 init_msg_len,
+	u8 *buffer, u8 expected_len)
+{
+	int act_len;
+	int status;
+
+	netdev_dbg(dev->net, "Sending init packet");
+
+	status = usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 0x02),
+		init_msg, init_msg_len, &act_len, KALMIA_USB_TIMEOUT);
+	if (status != 0) {
+		netdev_err(dev->net,
+			"Error sending init packet. Status %i, length %i\n",
+			status, act_len);
+		return status;
+	}
+	else if (act_len != init_msg_len) {
+		netdev_err(dev->net,
+			"Did not send all of init packet. Bytes sent: %i",
+			act_len);
+	}
+	else {
+		netdev_dbg(dev->net, "Successfully sent init packet.");
+	}
+
+	status = usb_bulk_msg(dev->udev, usb_rcvbulkpipe(dev->udev, 0x81),
+		buffer, expected_len, &act_len, KALMIA_USB_TIMEOUT);
+
+	if (status != 0)
+		netdev_err(dev->net,
+			"Error receiving init result. Status %i, length %i\n",
+			status, act_len);
+	else if (act_len != expected_len)
+		netdev_err(dev->net, "Unexpected init result length: %i\n",
+			act_len);
+
+	return status;
+}
+
+static int
+kalmia_init_and_get_ethernet_addr(struct usbnet *dev, u8 *ethernet_addr)
+{
+	char init_msg_1[] =
+		{ 0x57, 0x50, 0x04, 0x00, 0x00, 0x00, 0x00, 0x20, 0x00, 0x00,
+		0x00, 0x00 };
+	char init_msg_2[] =
+		{ 0x57, 0x50, 0x04, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0xf4,
+		0x00, 0x00 };
+	char receive_buf[28];
+	int status;
+
+	status = kalmia_send_init_packet(dev, init_msg_1, sizeof(init_msg_1)
+		/ sizeof(init_msg_1[0]), receive_buf, 24);
+	if (status != 0)
+		return status;
+
+	status = kalmia_send_init_packet(dev, init_msg_2, sizeof(init_msg_2)
+		/ sizeof(init_msg_2[0]), receive_buf, 28);
+	if (status != 0)
+		return status;
+
+	memcpy(ethernet_addr, receive_buf + 10, ETH_ALEN);
+
+	return status;
+}
+
+static int
+kalmia_bind(struct usbnet *dev, struct usb_interface *intf)
+{
+	u8 status;
+	u8 ethernet_addr[ETH_ALEN];
+
+	/* Don't bind to AT command interface */
+	if (intf->cur_altsetting->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC)
+		return -EINVAL;
+
+	dev->in = usb_rcvbulkpipe(dev->udev, 0x81 & USB_ENDPOINT_NUMBER_MASK);
+	dev->out = usb_sndbulkpipe(dev->udev, 0x02 & USB_ENDPOINT_NUMBER_MASK);
+	dev->status = NULL;
+
+	dev->net->hard_header_len += KALMIA_HEADER_LENGTH;
+	dev->hard_mtu = 1400;
+	dev->rx_urb_size = dev->hard_mtu * 10; // Found as optimal after testing
+
+	status = kalmia_init_and_get_ethernet_addr(dev, ethernet_addr);
+
+	if (status < 0) {
+		usb_set_intfdata(intf, NULL);
+		usb_driver_release_interface(driver_of(intf), intf);
+		return status;
+	}
+
+	memcpy(dev->net->dev_addr, ethernet_addr, ETH_ALEN);
+	memcpy(dev->net->perm_addr, ethernet_addr, ETH_ALEN);
+
+	return status;
+}
+
+static struct sk_buff *
+kalmia_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags)
+{
+	struct sk_buff *skb2 = NULL;
+	u16 content_len;
+	unsigned char *header_start;
+	unsigned char ether_type_1, ether_type_2;
+	u8 remainder, padlen = 0;
+
+	if (!skb_cloned(skb)) {
+		int headroom = skb_headroom(skb);
+		int tailroom = skb_tailroom(skb);
+
+		if ((tailroom >= KALMIA_ALIGN_SIZE) && (headroom
+			>= KALMIA_HEADER_LENGTH))
+			goto done;
+
+		if ((headroom + tailroom) > (KALMIA_HEADER_LENGTH
+			+ KALMIA_ALIGN_SIZE)) {
+			skb->data = memmove(skb->head + KALMIA_HEADER_LENGTH,
+				skb->data, skb->len);
+			skb_set_tail_pointer(skb, skb->len);
+			goto done;
+		}
+	}
+
+	skb2 = skb_copy_expand(skb, KALMIA_HEADER_LENGTH,
+		KALMIA_ALIGN_SIZE, flags);
+	if (!skb2)
+		return NULL;
+
+	dev_kfree_skb_any(skb);
+	skb = skb2;
+
+	done: header_start = skb_push(skb, KALMIA_HEADER_LENGTH);
+	ether_type_1 = header_start[KALMIA_HEADER_LENGTH + 12];
+	ether_type_2 = header_start[KALMIA_HEADER_LENGTH + 13];
+
+	netdev_dbg(dev->net, "Sending etherType: %02x%02x", ether_type_1,
+		ether_type_2);
+
+	/* According to empiric data for data packages */
+	header_start[0] = 0x57;
+	header_start[1] = 0x44;
+	content_len = skb->len - KALMIA_HEADER_LENGTH;
+	header_start[2] = (content_len & 0xff); /* low byte */
+	header_start[3] = (content_len >> 8); /* high byte */
+
+	header_start[4] = ether_type_1;
+	header_start[5] = ether_type_2;
+
+	/* Align to 4 bytes by padding with zeros */
+	remainder = skb->len % KALMIA_ALIGN_SIZE;
+	if (remainder > 0) {
+		padlen = KALMIA_ALIGN_SIZE - remainder;
+		memset(skb_put(skb, padlen), 0, padlen);
+	}
+
+	netdev_dbg(
+		dev->net,
+		"Sending package with length %i and padding %i. Header: %02x:%02x:%02x:%02x:%02x:%02x.",
+		content_len, padlen, header_start[0], header_start[1],
+		header_start[2], header_start[3], header_start[4],
+		header_start[5]);
+
+	return skb;
+}
+
+static int
+kalmia_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
+{
+	/*
+	 * Our task here is to strip off framing, leaving skb with one
+	 * data frame for the usbnet framework code to process.
+	 */
+	const u8 HEADER_END_OF_USB_PACKET[] =
+		{ 0x57, 0x5a, 0x00, 0x00, 0x08, 0x00 };
+	const u8 EXPECTED_UNKNOWN_HEADER_1[] =
+		{ 0x57, 0x43, 0x1e, 0x00, 0x15, 0x02 };
+	const u8 EXPECTED_UNKNOWN_HEADER_2[] =
+		{ 0x57, 0x50, 0x0e, 0x00, 0x00, 0x00 };
+	u8 i = 0;
+
+	/* incomplete header? */
+	if (skb->len < KALMIA_HEADER_LENGTH)
+		return 0;
+
+	do {
+		struct sk_buff *skb2 = NULL;
+		u8 *header_start;
+		u16 usb_packet_length, ether_packet_length;
+		int is_last;
+
+		header_start = skb->data;
+
+		if (unlikely(header_start[0] != 0x57 || header_start[1] != 0x44)) {
+			if (!memcmp(header_start, EXPECTED_UNKNOWN_HEADER_1,
+				sizeof(EXPECTED_UNKNOWN_HEADER_1)) || !memcmp(
+				header_start, EXPECTED_UNKNOWN_HEADER_2,
+				sizeof(EXPECTED_UNKNOWN_HEADER_2))) {
+				netdev_dbg(
+					dev->net,
+					"Received expected unknown frame header: %02x:%02x:%02x:%02x:%02x:%02x. Package length: %i\n",
+					header_start[0], header_start[1],
+					header_start[2], header_start[3],
+					header_start[4], header_start[5],
+					skb->len - KALMIA_HEADER_LENGTH);
+			}
+			else {
+				netdev_err(
+					dev->net,
+					"Received unknown frame header: %02x:%02x:%02x:%02x:%02x:%02x. Package length: %i\n",
+					header_start[0], header_start[1],
+					header_start[2], header_start[3],
+					header_start[4], header_start[5],
+					skb->len - KALMIA_HEADER_LENGTH);
+				return 0;
+			}
+		}
+		else
+			netdev_dbg(
+				dev->net,
+				"Received header: %02x:%02x:%02x:%02x:%02x:%02x. Package length: %i\n",
+				header_start[0], header_start[1], header_start[2],
+				header_start[3], header_start[4], header_start[5],
+				skb->len - KALMIA_HEADER_LENGTH);
+
+		/* subtract start header and end header */
+		usb_packet_length = skb->len - (2 * KALMIA_HEADER_LENGTH);
+		ether_packet_length = header_start[2] + (header_start[3] << 8);
+		skb_pull(skb, KALMIA_HEADER_LENGTH);
+
+		/* Some small packets misses end marker */
+		if (usb_packet_length < ether_packet_length) {
+			ether_packet_length = usb_packet_length
+				+ KALMIA_HEADER_LENGTH;
+			is_last = true;
+		}
+		else {
+			netdev_dbg(dev->net, "Correct package length #%i", i
+				+ 1);
+
+			is_last = (memcmp(skb->data + ether_packet_length,
+				HEADER_END_OF_USB_PACKET,
+				sizeof(HEADER_END_OF_USB_PACKET)) == 0);
+			if (!is_last) {
+				header_start = skb->data + ether_packet_length;
+				netdev_dbg(
+					dev->net,
+					"End header: %02x:%02x:%02x:%02x:%02x:%02x. Package length: %i\n",
+					header_start[0], header_start[1],
+					header_start[2], header_start[3],
+					header_start[4], header_start[5],
+					skb->len - KALMIA_HEADER_LENGTH);
+			}
+		}
+
+		if (is_last) {
+			skb2 = skb;
+		}
+		else {
+			skb2 = skb_clone(skb, GFP_ATOMIC);
+			if (unlikely(!skb2))
+				return 0;
+		}
+
+		skb_trim(skb2, ether_packet_length);
+
+		if (is_last) {
+			return 1;
+		}
+		else {
+			usbnet_skb_return(dev, skb2);
+			skb_pull(skb, ether_packet_length);
+		}
+
+		i++;
+	}
+	while (skb->len);
+
+	return 1;
+}
+
+static const struct driver_info kalmia_info = {
+	.description = "Samsung Kalmia LTE USB dongle",
+	.flags = FLAG_WWAN,
+	.bind = kalmia_bind,
+	.rx_fixup = kalmia_rx_fixup,
+	.tx_fixup = kalmia_tx_fixup
+};
+
+/*-------------------------------------------------------------------------*/
+
+static const struct usb_device_id products[] = {
+	/* The unswitched USB ID, to get the module auto loaded: */
+	{ USB_DEVICE(0x04e8, 0x689a) },
+	/* The stick swithed into modem (by e.g. usb_modeswitch): */
+	{ USB_DEVICE(0x04e8, 0x6889),
+		.driver_info = (unsigned long) &kalmia_info, },
+	{ /* EMPTY == end of list */} };
+MODULE_DEVICE_TABLE( usb, products);
+
+static struct usb_driver kalmia_driver = {
+	.name = "kalmia",
+	.id_table = products,
+	.probe = usbnet_probe,
+	.disconnect = usbnet_disconnect,
+	.suspend = usbnet_suspend,
+	.resume = usbnet_resume
+};
+
+static int __init kalmia_init(void)
+{
+	return usb_register(&kalmia_driver);
+}
+module_init( kalmia_init);
+
+static void __exit kalmia_exit(void)
+{
+	usb_deregister(&kalmia_driver);
+}
+module_exit( kalmia_exit);
+
+MODULE_AUTHOR("Marius Bjoernstad Kotsbak <marius@kotsbak.com>");
+MODULE_DESCRIPTION("Samsung Kalmia USB network driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 0cb0b0632672..f6853247a620 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -609,7 +609,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * before it gets out of hand.  Naturally, this wastes entries. */
 	if (capacity < 2+MAX_SKB_FRAGS) {
 		netif_stop_queue(dev);
-		if (unlikely(!virtqueue_enable_cb(vi->svq))) {
+		if (unlikely(!virtqueue_enable_cb_delayed(vi->svq))) {
 			/* More just got used, free them then recheck. */
 			capacity += free_old_xmit_skbs(vi);
 			if (capacity >= 2+MAX_SKB_FRAGS) {
diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index e050bd65e037..777d1a4e81b2 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -2203,8 +2203,10 @@ fst_open(struct net_device *dev)
 
 	if (port->mode != FST_RAW) {
 		err = hdlc_open(dev);
-		if (err)
+		if (err) {
+			module_put(THIS_MODULE);
 			return err;
+		}
 	}
 
 	fst_openport(port);
diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index 40398bf7d036..24297b274cd4 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -517,18 +517,17 @@ static int x25_asy_close(struct net_device *dev)
  * and sent on to some IP layer for further processing.
  */
 
-static unsigned int x25_asy_receive_buf(struct tty_struct *tty,
+static void x25_asy_receive_buf(struct tty_struct *tty,
 				const unsigned char *cp, char *fp, int count)
 {
 	struct x25_asy *sl = tty->disc_data;
-	int bytes = count;
 
 	if (!sl || sl->magic != X25_ASY_MAGIC || !netif_running(sl->dev))
 		return;
 
 
 	/* Read the characters out of the buffer */
-	while (bytes--) {
+	while (count--) {
 		if (fp && *fp++) {
 			if (!test_and_set_bit(SLF_ERROR, &sl->flags))
 				sl->dev->stats.rx_errors++;
@@ -537,8 +536,6 @@ static unsigned int x25_asy_receive_buf(struct tty_struct *tty,
 		}
 		x25_asy_unesc(sl, *cp++);
 	}
-
-	return count;
 }
 
 /*
diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c
index 22047628ccfa..b6c5d3715b96 100644
--- a/drivers/net/wireless/ath/ath5k/base.c
+++ b/drivers/net/wireless/ath/ath5k/base.c
@@ -72,6 +72,11 @@ static int modparam_all_channels;
 module_param_named(all_channels, modparam_all_channels, bool, S_IRUGO);
 MODULE_PARM_DESC(all_channels, "Expose all channels the device can use.");
 
+static int modparam_fastchanswitch;
+module_param_named(fastchanswitch, modparam_fastchanswitch, bool, S_IRUGO);
+MODULE_PARM_DESC(fastchanswitch, "Enable fast channel switching for AR2413/AR5413 radios.");
+
+
 /* Module info */
 MODULE_AUTHOR("Jiri Slaby");
 MODULE_AUTHOR("Nick Kossifidis");
@@ -2686,6 +2691,7 @@ ath5k_reset(struct ath5k_softc *sc, struct ieee80211_channel *chan,
 	struct ath5k_hw *ah = sc->ah;
 	struct ath_common *common = ath5k_hw_common(ah);
 	int ret, ani_mode;
+	bool fast;
 
 	ATH5K_DBG(sc, ATH5K_DEBUG_RESET, "resetting\n");
 
@@ -2705,7 +2711,10 @@ ath5k_reset(struct ath5k_softc *sc, struct ieee80211_channel *chan,
 	ath5k_drain_tx_buffs(sc);
 	if (chan)
 		sc->curchan = chan;
-	ret = ath5k_hw_reset(ah, sc->opmode, sc->curchan, chan != NULL,
+
+	fast = ((chan != NULL) && modparam_fastchanswitch) ? 1 : 0;
+
+	ret = ath5k_hw_reset(ah, sc->opmode, sc->curchan, fast,
 								skip_pcu);
 	if (ret) {
 		ATH5K_ERR(sc, "can't reset hardware (%d)\n", ret);
diff --git a/drivers/net/wireless/ath/ath5k/reset.c b/drivers/net/wireless/ath/ath5k/reset.c
index 3510de2cf622..126a4eab35f3 100644
--- a/drivers/net/wireless/ath/ath5k/reset.c
+++ b/drivers/net/wireless/ath/ath5k/reset.c
@@ -1124,8 +1124,11 @@ int ath5k_hw_reset(struct ath5k_hw *ah, enum nl80211_iftype op_mode,
 			/* Non fatal, can happen eg.
 			 * on mode change */
 			ret = 0;
-		} else
+		} else {
+			ATH5K_DBG(ah->ah_sc, ATH5K_DEBUG_RESET,
+				"fast chan change successful\n");
 			return 0;
+		}
 	}
 
 	/*
diff --git a/drivers/net/wireless/ath/ath9k/Kconfig b/drivers/net/wireless/ath/ath9k/Kconfig
index d9ff8413ab9a..d9c08c619a3a 100644
--- a/drivers/net/wireless/ath/ath9k/Kconfig
+++ b/drivers/net/wireless/ath/ath9k/Kconfig
@@ -26,7 +26,6 @@ config ATH9K
 config ATH9K_PCI
 	bool "Atheros ath9k PCI/PCIe bus support"
 	depends on ATH9K && PCI
-	default PCI
 	---help---
 	  This option enables the PCI bus support in ath9k.
 
diff --git a/drivers/net/wireless/ath/ath9k/ar9002_calib.c b/drivers/net/wireless/ath/ath9k/ar9002_calib.c
index 015d97439935..2d4c0910295b 100644
--- a/drivers/net/wireless/ath/ath9k/ar9002_calib.c
+++ b/drivers/net/wireless/ath/ath9k/ar9002_calib.c
@@ -829,7 +829,7 @@ static bool ar9002_hw_init_cal(struct ath_hw *ah, struct ath9k_channel *chan)
 	if (AR_SREV_9271(ah)) {
 		if (!ar9285_hw_cl_cal(ah, chan))
 			return false;
-	} else if (AR_SREV_9285_12_OR_LATER(ah)) {
+	} else if (AR_SREV_9285(ah) && AR_SREV_9285_12_OR_LATER(ah)) {
 		if (!ar9285_hw_clc(ah, chan))
 			return false;
 	} else {
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
index 0ca7635d0669..ff8150e46f0e 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
@@ -4645,10 +4645,16 @@ static void ar9003_hw_set_power_per_rate_table(struct ath_hw *ah,
 	case 1:
 		break;
 	case 2:
-		scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+		if (scaledPower > REDUCE_SCALED_POWER_BY_TWO_CHAIN)
+			scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+		else
+			scaledPower = 0;
 		break;
 	case 3:
-		scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+		if (scaledPower > REDUCE_SCALED_POWER_BY_THREE_CHAIN)
+			scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+		else
+			scaledPower = 0;
 		break;
 	}
 
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
index eee23ecd118a..892c48b15434 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
@@ -1381,3 +1381,25 @@ void ar9003_hw_bb_watchdog_dbg_info(struct ath_hw *ah)
 		"==== BB update: done ====\n\n");
 }
 EXPORT_SYMBOL(ar9003_hw_bb_watchdog_dbg_info);
+
+void ar9003_hw_disable_phy_restart(struct ath_hw *ah)
+{
+	u32 val;
+
+	/* While receiving unsupported rate frame rx state machine
+	 * gets into a state 0xb and if phy_restart happens in that
+	 * state, BB would go hang. If RXSM is in 0xb state after
+	 * first bb panic, ensure to disable the phy_restart.
+	 */
+	if (!((MS(ah->bb_watchdog_last_status,
+		  AR_PHY_WATCHDOG_RX_OFDM_SM) == 0xb) ||
+	    ah->bb_hang_rx_ofdm))
+		return;
+
+	ah->bb_hang_rx_ofdm = true;
+	val = REG_READ(ah, AR_PHY_RESTART);
+	val &= ~AR_PHY_RESTART_ENA;
+
+	REG_WRITE(ah, AR_PHY_RESTART, val);
+}
+EXPORT_SYMBOL(ar9003_hw_disable_phy_restart);
diff --git a/drivers/net/wireless/ath/ath9k/eeprom_9287.c b/drivers/net/wireless/ath/ath9k/eeprom_9287.c
index 7856f0d4512d..343fc9f946db 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom_9287.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom_9287.c
@@ -524,10 +524,16 @@ static void ath9k_hw_set_ar9287_power_per_rate_table(struct ath_hw *ah,
 	case 1:
 		break;
 	case 2:
-		scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+		if (scaledPower > REDUCE_SCALED_POWER_BY_TWO_CHAIN)
+			scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+		else
+			scaledPower = 0;
 		break;
 	case 3:
-		scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+		if (scaledPower > REDUCE_SCALED_POWER_BY_THREE_CHAIN)
+			scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+		else
+			scaledPower = 0;
 		break;
 	}
 	scaledPower = max((u16)0, scaledPower);
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 72543ce8f616..1be7c8bbef84 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -1555,9 +1555,12 @@ int ath9k_hw_reset(struct ath_hw *ah, struct ath9k_channel *chan,
 	if (ah->btcoex_hw.enabled)
 		ath9k_hw_btcoex_enable(ah);
 
-	if (AR_SREV_9300_20_OR_LATER(ah))
+	if (AR_SREV_9300_20_OR_LATER(ah)) {
 		ar9003_hw_bb_watchdog_config(ah);
 
+		ar9003_hw_disable_phy_restart(ah);
+	}
+
 	ath9k_hw_apply_gpio_override(ah);
 
 	return 0;
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index 57435ce62792..4b157c53d1a8 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -842,6 +842,7 @@ struct ath_hw {
 
 	u32 bb_watchdog_last_status;
 	u32 bb_watchdog_timeout_ms; /* in ms, 0 to disable */
+	u8 bb_hang_rx_ofdm; /* true if bb hang due to rx_ofdm */
 
 	unsigned int paprd_target_power;
 	unsigned int paprd_training_power;
@@ -990,6 +991,7 @@ void ar9002_hw_enable_wep_aggregation(struct ath_hw *ah);
 void ar9003_hw_bb_watchdog_config(struct ath_hw *ah);
 void ar9003_hw_bb_watchdog_read(struct ath_hw *ah);
 void ar9003_hw_bb_watchdog_dbg_info(struct ath_hw *ah);
+void ar9003_hw_disable_phy_restart(struct ath_hw *ah);
 void ar9003_paprd_enable(struct ath_hw *ah, bool val);
 void ar9003_paprd_populate_single_table(struct ath_hw *ah,
 					struct ath9k_hw_cal_data *caldata,
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index a198ee374b05..2ca351fe6d3c 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -670,7 +670,8 @@ void ath9k_tasklet(unsigned long data)
 	u32 status = sc->intrstatus;
 	u32 rxmask;
 
-	if (status & ATH9K_INT_FATAL) {
+	if ((status & ATH9K_INT_FATAL) ||
+	    (status & ATH9K_INT_BB_WATCHDOG)) {
 		ath_reset(sc, true);
 		return;
 	}
@@ -737,6 +738,7 @@ irqreturn_t ath_isr(int irq, void *dev)
 {
 #define SCHED_INTR (				\
 		ATH9K_INT_FATAL |		\
+		ATH9K_INT_BB_WATCHDOG |		\
 		ATH9K_INT_RXORN |		\
 		ATH9K_INT_RXEOL |		\
 		ATH9K_INT_RX |			\
diff --git a/drivers/net/wireless/ath/ath9k/rc.c b/drivers/net/wireless/ath/ath9k/rc.c
index 17542214c93f..ba7f36ab0a74 100644
--- a/drivers/net/wireless/ath/ath9k/rc.c
+++ b/drivers/net/wireless/ath/ath9k/rc.c
@@ -689,7 +689,8 @@ static void ath_rc_rate_set_series(const struct ath_rate_table *rate_table,
 
 	if (WLAN_RC_PHY_HT(rate_table->info[rix].phy)) {
 		rate->flags |= IEEE80211_TX_RC_MCS;
-		if (WLAN_RC_PHY_40(rate_table->info[rix].phy))
+		if (WLAN_RC_PHY_40(rate_table->info[rix].phy) &&
+		    conf_is_ht40(&txrc->hw->conf))
 			rate->flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;
 		if (WLAN_RC_PHY_SGI(rate_table->info[rix].phy))
 			rate->flags |= IEEE80211_TX_RC_SHORT_GI;
diff --git a/drivers/net/wireless/b43/phy_n.c b/drivers/net/wireless/b43/phy_n.c
index 9ed65157bef5..05960ddde24e 100644
--- a/drivers/net/wireless/b43/phy_n.c
+++ b/drivers/net/wireless/b43/phy_n.c
@@ -3093,7 +3093,7 @@ static int b43_nphy_cal_tx_iq_lo(struct b43_wldev *dev,
 	int freq;
 	bool avoid = false;
 	u8 length;
-	u16 tmp, core, type, count, max, numb, last, cmd;
+	u16 tmp, core, type, count, max, numb, last = 0, cmd;
 	const u16 *table;
 	bool phy6or5x;
 
diff --git a/drivers/net/wireless/iwlegacy/iwl-4965-lib.c b/drivers/net/wireless/iwlegacy/iwl-4965-lib.c
index 7e5e85a017b5..a7a4739880dc 100644
--- a/drivers/net/wireless/iwlegacy/iwl-4965-lib.c
+++ b/drivers/net/wireless/iwlegacy/iwl-4965-lib.c
@@ -628,11 +628,11 @@ void iwl4965_rx_reply_rx(struct iwl_priv *priv,
 
 	/* rx_status carries information about the packet to mac80211 */
 	rx_status.mactime = le64_to_cpu(phy_res->timestamp);
+	rx_status.band = (phy_res->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ?
+				IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ;
 	rx_status.freq =
 		ieee80211_channel_to_frequency(le16_to_cpu(phy_res->channel),
 							rx_status.band);
-	rx_status.band = (phy_res->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ?
-				IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ;
 	rx_status.rate_idx =
 		iwl4965_hwrate_to_mac80211_idx(rate_n_flags, rx_status.band);
 	rx_status.flag = 0;
diff --git a/drivers/net/wireless/iwlegacy/iwl-4965.c b/drivers/net/wireless/iwlegacy/iwl-4965.c
index f5433c74b845..facc94e74b07 100644
--- a/drivers/net/wireless/iwlegacy/iwl-4965.c
+++ b/drivers/net/wireless/iwlegacy/iwl-4965.c
@@ -1218,10 +1218,10 @@ static int iwl4965_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *c
 	 * receive commit_rxon request
 	 * abort any previous channel switch if still in process
 	 */
-	if (priv->switch_rxon.switch_in_progress &&
-	    (priv->switch_rxon.channel != ctx->staging.channel)) {
+	if (test_bit(STATUS_CHANNEL_SWITCH_PENDING, &priv->status) &&
+	    (priv->switch_channel != ctx->staging.channel)) {
 		IWL_DEBUG_11H(priv, "abort channel switch on %d\n",
-		      le16_to_cpu(priv->switch_rxon.channel));
+		      le16_to_cpu(priv->switch_channel));
 		iwl_legacy_chswitch_done(priv, false);
 	}
 
@@ -1237,7 +1237,7 @@ static int iwl4965_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *c
 
 		memcpy(active_rxon, &ctx->staging, sizeof(*active_rxon));
 		iwl_legacy_print_rx_config_cmd(priv, ctx);
-		return 0;
+		goto set_tx_power;
 	}
 
 	/* If we are currently associated and the new config requires
@@ -1317,6 +1317,7 @@ static int iwl4965_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *c
 
 	iwl4965_init_sensitivity(priv);
 
+set_tx_power:
 	/* If we issue a new RXON command which required a tune then we must
 	 * send a new TXPOWER command or we won't be able to Tx any frames */
 	ret = iwl_legacy_set_tx_power(priv, priv->tx_power_next, true);
@@ -1403,9 +1404,6 @@ static int iwl4965_hw_channel_switch(struct iwl_priv *priv,
 		return rc;
 	}
 
-	priv->switch_rxon.channel = cmd.channel;
-	priv->switch_rxon.switch_in_progress = true;
-
 	return iwl_legacy_send_cmd_pdu(priv,
 			 REPLY_CHANNEL_SWITCH, sizeof(cmd), &cmd);
 }
@@ -1543,7 +1541,7 @@ static void iwl4965_temperature_calib(struct iwl_priv *priv)
 	s32 temp;
 
 	temp = iwl4965_hw_get_temperature(priv);
-	if (temp < 0)
+	if (IWL_TX_POWER_TEMPERATURE_OUT_OF_RANGE(temp))
 		return;
 
 	if (priv->temperature != temp) {
diff --git a/drivers/net/wireless/iwlegacy/iwl-core.c b/drivers/net/wireless/iwlegacy/iwl-core.c
index 42df8321dae8..3be76bd5499a 100644
--- a/drivers/net/wireless/iwlegacy/iwl-core.c
+++ b/drivers/net/wireless/iwlegacy/iwl-core.c
@@ -859,12 +859,8 @@ void iwl_legacy_chswitch_done(struct iwl_priv *priv, bool is_success)
 	if (test_bit(STATUS_EXIT_PENDING, &priv->status))
 		return;
 
-	if (priv->switch_rxon.switch_in_progress) {
+	if (test_and_clear_bit(STATUS_CHANNEL_SWITCH_PENDING, &priv->status))
 		ieee80211_chswitch_done(ctx->vif, is_success);
-		mutex_lock(&priv->mutex);
-		priv->switch_rxon.switch_in_progress = false;
-		mutex_unlock(&priv->mutex);
-	}
 }
 EXPORT_SYMBOL(iwl_legacy_chswitch_done);
 
@@ -876,19 +872,19 @@ void iwl_legacy_rx_csa(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb)
 	struct iwl_rxon_context *ctx = &priv->contexts[IWL_RXON_CTX_BSS];
 	struct iwl_legacy_rxon_cmd *rxon = (void *)&ctx->active;
 
-	if (priv->switch_rxon.switch_in_progress) {
-		if (!le32_to_cpu(csa->status) &&
-		    (csa->channel == priv->switch_rxon.channel)) {
-			rxon->channel = csa->channel;
-			ctx->staging.channel = csa->channel;
-			IWL_DEBUG_11H(priv, "CSA notif: channel %d\n",
-			      le16_to_cpu(csa->channel));
-			iwl_legacy_chswitch_done(priv, true);
-		} else {
-			IWL_ERR(priv, "CSA notif (fail) : channel %d\n",
+	if (!test_bit(STATUS_CHANNEL_SWITCH_PENDING, &priv->status))
+		return;
+
+	if (!le32_to_cpu(csa->status) && csa->channel == priv->switch_channel) {
+		rxon->channel = csa->channel;
+		ctx->staging.channel = csa->channel;
+		IWL_DEBUG_11H(priv, "CSA notif: channel %d\n",
 			      le16_to_cpu(csa->channel));
-			iwl_legacy_chswitch_done(priv, false);
-		}
+		iwl_legacy_chswitch_done(priv, true);
+	} else {
+		IWL_ERR(priv, "CSA notif (fail) : channel %d\n",
+			le16_to_cpu(csa->channel));
+		iwl_legacy_chswitch_done(priv, false);
 	}
 }
 EXPORT_SYMBOL(iwl_legacy_rx_csa);
diff --git a/drivers/net/wireless/iwlegacy/iwl-core.h b/drivers/net/wireless/iwlegacy/iwl-core.h
index bc66c604106c..c5fbda0760de 100644
--- a/drivers/net/wireless/iwlegacy/iwl-core.h
+++ b/drivers/net/wireless/iwlegacy/iwl-core.h
@@ -560,7 +560,7 @@ void iwl_legacy_free_geos(struct iwl_priv *priv);
 #define STATUS_SCAN_HW		15
 #define STATUS_POWER_PMI	16
 #define STATUS_FW_ERROR		17
-
+#define STATUS_CHANNEL_SWITCH_PENDING 18
 
 static inline int iwl_legacy_is_ready(struct iwl_priv *priv)
 {
diff --git a/drivers/net/wireless/iwlegacy/iwl-dev.h b/drivers/net/wireless/iwlegacy/iwl-dev.h
index be0106c6a2da..ea30122669ee 100644
--- a/drivers/net/wireless/iwlegacy/iwl-dev.h
+++ b/drivers/net/wireless/iwlegacy/iwl-dev.h
@@ -855,17 +855,6 @@ struct traffic_stats {
 };
 
 /*
- * iwl_switch_rxon: "channel switch" structure
- *
- * @ switch_in_progress: channel switch in progress
- * @ channel: new channel
- */
-struct iwl_switch_rxon {
-	bool switch_in_progress;
-	__le16 channel;
-};
-
-/*
  * schedule the timer to wake up every UCODE_TRACE_PERIOD milliseconds
  * to perform continuous uCode event logging operation if enabled
  */
@@ -1115,7 +1104,7 @@ struct iwl_priv {
 
 	struct iwl_rxon_context contexts[NUM_IWL_RXON_CTX];
 
-	struct iwl_switch_rxon switch_rxon;
+	__le16 switch_channel;
 
 	/* 1st responses from initialize and runtime uCode images.
 	 * _4965's initialize alive response contains some calibration data. */
diff --git a/drivers/net/wireless/iwlegacy/iwl4965-base.c b/drivers/net/wireless/iwlegacy/iwl4965-base.c
index af2ae22fcfd3..7157ba529680 100644
--- a/drivers/net/wireless/iwlegacy/iwl4965-base.c
+++ b/drivers/net/wireless/iwlegacy/iwl4965-base.c
@@ -2861,16 +2861,13 @@ void iwl4965_mac_channel_switch(struct ieee80211_hw *hw,
 		goto out;
 
 	if (test_bit(STATUS_EXIT_PENDING, &priv->status) ||
-	    test_bit(STATUS_SCANNING, &priv->status))
+	    test_bit(STATUS_SCANNING, &priv->status) ||
+	    test_bit(STATUS_CHANNEL_SWITCH_PENDING, &priv->status))
 		goto out;
 
 	if (!iwl_legacy_is_associated_ctx(ctx))
 		goto out;
 
-	/* channel switch in progress */
-	if (priv->switch_rxon.switch_in_progress == true)
-		goto out;
-
 	if (priv->cfg->ops->lib->set_channel_switch) {
 
 		ch = channel->hw_value;
@@ -2919,15 +2916,18 @@ void iwl4965_mac_channel_switch(struct ieee80211_hw *hw,
 			 * at this point, staging_rxon has the
 			 * configuration for channel switch
 			 */
-			if (priv->cfg->ops->lib->set_channel_switch(priv,
-								    ch_switch))
-				priv->switch_rxon.switch_in_progress = false;
+			set_bit(STATUS_CHANNEL_SWITCH_PENDING, &priv->status);
+			priv->switch_channel = cpu_to_le16(ch);
+			if (priv->cfg->ops->lib->set_channel_switch(priv, ch_switch)) {
+				clear_bit(STATUS_CHANNEL_SWITCH_PENDING,
+					  &priv->status);
+				priv->switch_channel = 0;
+				ieee80211_chswitch_done(ctx->vif, false);
+			}
 		}
 	}
 out:
 	mutex_unlock(&priv->mutex);
-	if (!priv->switch_rxon.switch_in_progress)
-		ieee80211_chswitch_done(ctx->vif, false);
 	IWL_DEBUG_MAC80211(priv, "leave\n");
 }
 
diff --git a/drivers/net/wireless/iwlwifi/iwl-2000.c b/drivers/net/wireless/iwlwifi/iwl-2000.c
index 86feec86d130..2282279cffc4 100644
--- a/drivers/net/wireless/iwlwifi/iwl-2000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-2000.c
@@ -177,79 +177,6 @@ static int iwl2000_hw_set_hw_params(struct iwl_priv *priv)
 	return 0;
 }
 
-static int iwl2030_hw_channel_switch(struct iwl_priv *priv,
-                                    struct ieee80211_channel_switch *ch_switch)
-{
-	/*
-	 * MULTI-FIXME
-	 * See iwl_mac_channel_switch.
-	 */
-	struct iwl_rxon_context *ctx = &priv->contexts[IWL_RXON_CTX_BSS];
-	struct iwl6000_channel_switch_cmd cmd;
-	const struct iwl_channel_info *ch_info;
-	u32 switch_time_in_usec, ucode_switch_time;
-	u16 ch;
-	u32 tsf_low;
-	u8 switch_count;
-	u16 beacon_interval = le16_to_cpu(ctx->timing.beacon_interval);
-	struct ieee80211_vif *vif = ctx->vif;
-	struct iwl_host_cmd hcmd = {
-		.id = REPLY_CHANNEL_SWITCH,
-		.len = { sizeof(cmd), },
-		.flags = CMD_SYNC,
-		.data = { &cmd, },
-	};
-
-	cmd.band = priv->band == IEEE80211_BAND_2GHZ;
-	ch = ch_switch->channel->hw_value;
-	IWL_DEBUG_11H(priv, "channel switch from %u to %u\n",
-		ctx->active.channel, ch);
-	cmd.channel = cpu_to_le16(ch);
-	cmd.rxon_flags = ctx->staging.flags;
-	cmd.rxon_filter_flags = ctx->staging.filter_flags;
-	switch_count = ch_switch->count;
-	tsf_low = ch_switch->timestamp & 0x0ffffffff;
-	/*
-	 * calculate the ucode channel switch time
-	 * adding TSF as one of the factor for when to switch
-	 */
-	if ((priv->ucode_beacon_time > tsf_low) && beacon_interval) {
-		if (switch_count > ((priv->ucode_beacon_time - tsf_low) /
-		    beacon_interval)) {
-			switch_count -= (priv->ucode_beacon_time -
-				tsf_low) / beacon_interval;
-		} else
-			switch_count = 0;
-	}
-	if (switch_count <= 1)
-		cmd.switch_time = cpu_to_le32(priv->ucode_beacon_time);
-	else {
-		switch_time_in_usec =
-			vif->bss_conf.beacon_int * switch_count * TIME_UNIT;
-		ucode_switch_time = iwl_usecs_to_beacons(priv,
-						switch_time_in_usec,
-						beacon_interval);
-		cmd.switch_time = iwl_add_beacon_time(priv,
-						priv->ucode_beacon_time,
-						ucode_switch_time,
-						beacon_interval);
-	}
-	IWL_DEBUG_11H(priv, "uCode time for the switch is 0x%x\n",
-		      cmd.switch_time);
-	ch_info = iwl_get_channel_info(priv, priv->band, ch);
-	if (ch_info)
-		cmd.expect_beacon = is_channel_radar(ch_info);
-	else {
-		IWL_ERR(priv, "invalid channel switch from %u to %u\n",
-			ctx->active.channel, ch);
-		return -EFAULT;
-	}
-	priv->switch_rxon.channel = cmd.channel;
-	priv->switch_rxon.switch_in_progress = true;
-
-	return iwl_send_cmd_sync(priv, &hcmd);
-}
-
 static struct iwl_lib_ops iwl2000_lib = {
 	.set_hw_params = iwl2000_hw_set_hw_params,
 	.rx_handler_setup = iwlagn_rx_handler_setup,
@@ -258,7 +185,6 @@ static struct iwl_lib_ops iwl2000_lib = {
 	.is_valid_rtc_data_addr = iwlagn_hw_valid_rtc_data_addr,
 	.send_tx_power = iwlagn_send_tx_power,
 	.update_chain_flags = iwl_update_chain_flags,
-	.set_channel_switch = iwl2030_hw_channel_switch,
 	.apm_ops = {
 		.init = iwl_apm_init,
 		.config = iwl2000_nic_config,
diff --git a/drivers/net/wireless/iwlwifi/iwl-5000.c b/drivers/net/wireless/iwlwifi/iwl-5000.c
index a70b8cfafda1..f99f9c193352 100644
--- a/drivers/net/wireless/iwlwifi/iwl-5000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-5000.c
@@ -331,8 +331,6 @@ static int iwl5000_hw_channel_switch(struct iwl_priv *priv,
 			ctx->active.channel, ch);
 		return -EFAULT;
 	}
-	priv->switch_rxon.channel = cmd.channel;
-	priv->switch_rxon.switch_in_progress = true;
 
 	return iwl_send_cmd_sync(priv, &hcmd);
 }
@@ -425,7 +423,6 @@ static struct iwl_base_params iwl5000_base_params = {
 };
 static struct iwl_ht_params iwl5000_ht_params = {
 	.ht_greenfield_support = true,
-	.use_rts_for_aggregation = true, /* use rts/cts protection */
 };
 
 #define IWL_DEVICE_5000						\
diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c
index f8c710db6e6f..fbe565c816e3 100644
--- a/drivers/net/wireless/iwlwifi/iwl-6000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-6000.c
@@ -270,8 +270,6 @@ static int iwl6000_hw_channel_switch(struct iwl_priv *priv,
 			ctx->active.channel, ch);
 		return -EFAULT;
 	}
-	priv->switch_rxon.channel = cmd.channel;
-	priv->switch_rxon.switch_in_progress = true;
 
 	return iwl_send_cmd_sync(priv, &hcmd);
 }
@@ -603,19 +601,27 @@ struct iwl_cfg iwl6050_2abg_cfg = {
 	IWL_DEVICE_6050,
 };
 
+#define IWL_DEVICE_6150						\
+	.fw_name_pre = IWL6050_FW_PRE,				\
+	.ucode_api_max = IWL6050_UCODE_API_MAX,			\
+	.ucode_api_min = IWL6050_UCODE_API_MIN,			\
+	.ops = &iwl6150_ops,					\
+	.eeprom_ver = EEPROM_6150_EEPROM_VERSION,		\
+	.eeprom_calib_ver = EEPROM_6150_TX_POWER_VERSION,	\
+	.base_params = &iwl6050_base_params,			\
+	.need_dc_calib = true,					\
+	.led_mode = IWL_LED_BLINK,				\
+	.internal_wimax_coex = true
+
 struct iwl_cfg iwl6150_bgn_cfg = {
 	.name = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BGN",
-	.fw_name_pre = IWL6050_FW_PRE,
-	.ucode_api_max = IWL6050_UCODE_API_MAX,
-	.ucode_api_min = IWL6050_UCODE_API_MIN,
-	.eeprom_ver = EEPROM_6150_EEPROM_VERSION,
-	.eeprom_calib_ver = EEPROM_6150_TX_POWER_VERSION,
-	.ops = &iwl6150_ops,
-	.base_params = &iwl6050_base_params,
+	IWL_DEVICE_6150,
 	.ht_params = &iwl6000_ht_params,
-	.need_dc_calib = true,
-	.led_mode = IWL_LED_RF_STATE,
-	.internal_wimax_coex = true,
+};
+
+struct iwl_cfg iwl6150_bg_cfg = {
+	.name = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BG",
+	IWL_DEVICE_6150,
 };
 
 struct iwl_cfg iwl6000_3agn_cfg = {
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c b/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c
index b12c72d63ccb..23fa93deae96 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c
@@ -163,17 +163,9 @@ static void iwlagn_tx_cmd_protection(struct iwl_priv *priv,
 				     __le16 fc, __le32 *tx_flags)
 {
 	if (info->control.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS ||
-	    info->control.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT) {
+	    info->control.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT ||
+	    info->flags & IEEE80211_TX_CTL_AMPDU)
 		*tx_flags |= TX_CMD_FLG_PROT_REQUIRE_MSK;
-		return;
-	}
-
-	if (priv->cfg->ht_params &&
-	    priv->cfg->ht_params->use_rts_for_aggregation &&
-	    info->flags & IEEE80211_TX_CTL_AMPDU) {
-		*tx_flags |= TX_CMD_FLG_PROT_REQUIRE_MSK;
-		return;
-	}
 }
 
 /* Calc max signal level (dBm) among 3 possible receivers */
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c b/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c
index a95ad84c5377..09f679d6046f 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c
@@ -325,6 +325,14 @@ int iwlagn_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *ctx)
 			return 0;
 	}
 
+	/*
+	 * force CTS-to-self frames protection if RTS-CTS is not preferred
+	 * one aggregation protection method
+	 */
+	if (!(priv->cfg->ht_params &&
+	      priv->cfg->ht_params->use_rts_for_aggregation))
+		ctx->staging.flags |= RXON_FLG_SELF_CTS_EN;
+
 	if ((ctx->vif && ctx->vif->bss_conf.use_short_slot) ||
 	    !(ctx->staging.flags & RXON_FLG_BAND_24G_MSK))
 		ctx->staging.flags |= RXON_FLG_SHORT_SLOT_MSK;
@@ -342,10 +350,10 @@ int iwlagn_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *ctx)
 	 * receive commit_rxon request
 	 * abort any previous channel switch if still in process
 	 */
-	if (priv->switch_rxon.switch_in_progress &&
-	    (priv->switch_rxon.channel != ctx->staging.channel)) {
+	if (test_bit(STATUS_CHANNEL_SWITCH_PENDING, &priv->status) &&
+	    (priv->switch_channel != ctx->staging.channel)) {
 		IWL_DEBUG_11H(priv, "abort channel switch on %d\n",
-		      le16_to_cpu(priv->switch_rxon.channel));
+			      le16_to_cpu(priv->switch_channel));
 		iwl_chswitch_done(priv, false);
 	}
 
@@ -362,6 +370,11 @@ int iwlagn_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *ctx)
 		}
 
 		memcpy(active, &ctx->staging, sizeof(*active));
+		/*
+		 * We do not commit tx power settings while channel changing,
+		 * do it now if after settings changed.
+		 */
+		iwl_set_tx_power(priv, priv->tx_power_next, false);
 		return 0;
 	}
 
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c
index 11c6c1169e78..8e1942ebd9a0 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.c
@@ -2843,16 +2843,13 @@ static void iwlagn_mac_channel_switch(struct ieee80211_hw *hw,
 		goto out;
 
 	if (test_bit(STATUS_EXIT_PENDING, &priv->status) ||
-	    test_bit(STATUS_SCANNING, &priv->status))
+	    test_bit(STATUS_SCANNING, &priv->status) ||
+	    test_bit(STATUS_CHANNEL_SWITCH_PENDING, &priv->status))
 		goto out;
 
 	if (!iwl_is_associated_ctx(ctx))
 		goto out;
 
-	/* channel switch in progress */
-	if (priv->switch_rxon.switch_in_progress == true)
-		goto out;
-
 	if (priv->cfg->ops->lib->set_channel_switch) {
 
 		ch = channel->hw_value;
@@ -2901,15 +2898,19 @@ static void iwlagn_mac_channel_switch(struct ieee80211_hw *hw,
 			 * at this point, staging_rxon has the
 			 * configuration for channel switch
 			 */
+			set_bit(STATUS_CHANNEL_SWITCH_PENDING, &priv->status);
+			priv->switch_channel = cpu_to_le16(ch);
 			if (priv->cfg->ops->lib->set_channel_switch(priv,
-								    ch_switch))
-				priv->switch_rxon.switch_in_progress = false;
+								    ch_switch)) {
+				clear_bit(STATUS_CHANNEL_SWITCH_PENDING,
+					  &priv->status);
+				priv->switch_channel = 0;
+				ieee80211_chswitch_done(ctx->vif, false);
+			}
 		}
 	}
 out:
 	mutex_unlock(&priv->mutex);
-	if (!priv->switch_rxon.switch_in_progress)
-		ieee80211_chswitch_done(ctx->vif, false);
 	IWL_DEBUG_MAC80211(priv, "leave\n");
 }
 
@@ -3831,11 +3832,11 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 
 /* 6150 WiFi/WiMax Series */
 	{IWL_PCI_DEVICE(0x0885, 0x1305, iwl6150_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0885, 0x1306, iwl6150_bgn_cfg)},
+	{IWL_PCI_DEVICE(0x0885, 0x1307, iwl6150_bg_cfg)},
 	{IWL_PCI_DEVICE(0x0885, 0x1325, iwl6150_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0885, 0x1326, iwl6150_bgn_cfg)},
+	{IWL_PCI_DEVICE(0x0885, 0x1327, iwl6150_bg_cfg)},
 	{IWL_PCI_DEVICE(0x0886, 0x1315, iwl6150_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0886, 0x1316, iwl6150_bgn_cfg)},
+	{IWL_PCI_DEVICE(0x0886, 0x1317, iwl6150_bg_cfg)},
 
 /* 1000 Series WiFi */
 	{IWL_PCI_DEVICE(0x0083, 0x1205, iwl1000_bgn_cfg)},
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.h b/drivers/net/wireless/iwlwifi/iwl-agn.h
index 2495fe7a58cb..d1716844002e 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.h
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.h
@@ -89,6 +89,7 @@ extern struct iwl_cfg iwl6000_3agn_cfg;
 extern struct iwl_cfg iwl6050_2agn_cfg;
 extern struct iwl_cfg iwl6050_2abg_cfg;
 extern struct iwl_cfg iwl6150_bgn_cfg;
+extern struct iwl_cfg iwl6150_bg_cfg;
 extern struct iwl_cfg iwl1000_bgn_cfg;
 extern struct iwl_cfg iwl1000_bg_cfg;
 extern struct iwl_cfg iwl100_bgn_cfg;
diff --git a/drivers/net/wireless/iwlwifi/iwl-core.c b/drivers/net/wireless/iwlwifi/iwl-core.c
index 4653deada05b..213c80c6a668 100644
--- a/drivers/net/wireless/iwlwifi/iwl-core.c
+++ b/drivers/net/wireless/iwlwifi/iwl-core.c
@@ -843,12 +843,8 @@ void iwl_chswitch_done(struct iwl_priv *priv, bool is_success)
 	if (test_bit(STATUS_EXIT_PENDING, &priv->status))
 		return;
 
-	if (priv->switch_rxon.switch_in_progress) {
+	if (test_and_clear_bit(STATUS_CHANNEL_SWITCH_PENDING, &priv->status))
 		ieee80211_chswitch_done(ctx->vif, is_success);
-		mutex_lock(&priv->mutex);
-		priv->switch_rxon.switch_in_progress = false;
-		mutex_unlock(&priv->mutex);
-	}
 }
 
 #ifdef CONFIG_IWLWIFI_DEBUG
diff --git a/drivers/net/wireless/iwlwifi/iwl-core.h b/drivers/net/wireless/iwlwifi/iwl-core.h
index 3bb76f6ea410..a54d416ec345 100644
--- a/drivers/net/wireless/iwlwifi/iwl-core.h
+++ b/drivers/net/wireless/iwlwifi/iwl-core.h
@@ -560,6 +560,7 @@ void iwlcore_free_geos(struct iwl_priv *priv);
 #define STATUS_POWER_PMI	16
 #define STATUS_FW_ERROR		17
 #define STATUS_DEVICE_ENABLED	18
+#define STATUS_CHANNEL_SWITCH_PENDING 19
 
 
 static inline int iwl_is_ready(struct iwl_priv *priv)
diff --git a/drivers/net/wireless/iwlwifi/iwl-dev.h b/drivers/net/wireless/iwlwifi/iwl-dev.h
index 22a6e3ec7094..c8de236c141b 100644
--- a/drivers/net/wireless/iwlwifi/iwl-dev.h
+++ b/drivers/net/wireless/iwlwifi/iwl-dev.h
@@ -982,17 +982,6 @@ struct traffic_stats {
 };
 
 /*
- * iwl_switch_rxon: "channel switch" structure
- *
- * @ switch_in_progress: channel switch in progress
- * @ channel: new channel
- */
-struct iwl_switch_rxon {
-	bool switch_in_progress;
-	__le16 channel;
-};
-
-/*
  * schedule the timer to wake up every UCODE_TRACE_PERIOD milliseconds
  * to perform continuous uCode event logging operation if enabled
  */
@@ -1287,7 +1276,7 @@ struct iwl_priv {
 
 	struct iwl_rxon_context contexts[NUM_IWL_RXON_CTX];
 
-	struct iwl_switch_rxon switch_rxon;
+	__le16 switch_channel;
 
 	struct {
 		u32 error_event_table;
diff --git a/drivers/net/wireless/iwlwifi/iwl-rx.c b/drivers/net/wireless/iwlwifi/iwl-rx.c
index 0053e9ea9021..b774517aa9fa 100644
--- a/drivers/net/wireless/iwlwifi/iwl-rx.c
+++ b/drivers/net/wireless/iwlwifi/iwl-rx.c
@@ -250,19 +250,19 @@ static void iwl_rx_csa(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb)
 	struct iwl_rxon_context *ctx = &priv->contexts[IWL_RXON_CTX_BSS];
 	struct iwl_rxon_cmd *rxon = (void *)&ctx->active;
 
-	if (priv->switch_rxon.switch_in_progress) {
-		if (!le32_to_cpu(csa->status) &&
-		    (csa->channel == priv->switch_rxon.channel)) {
-			rxon->channel = csa->channel;
-			ctx->staging.channel = csa->channel;
-			IWL_DEBUG_11H(priv, "CSA notif: channel %d\n",
-			      le16_to_cpu(csa->channel));
-			iwl_chswitch_done(priv, true);
-		} else {
-			IWL_ERR(priv, "CSA notif (fail) : channel %d\n",
+	if (!test_bit(STATUS_CHANNEL_SWITCH_PENDING, &priv->status))
+		return;
+
+	if (!le32_to_cpu(csa->status) && csa->channel == priv->switch_channel) {
+		rxon->channel = csa->channel;
+		ctx->staging.channel = csa->channel;
+		IWL_DEBUG_11H(priv, "CSA notif: channel %d\n",
 			      le16_to_cpu(csa->channel));
-			iwl_chswitch_done(priv, false);
-		}
+		iwl_chswitch_done(priv, true);
+	} else {
+		IWL_ERR(priv, "CSA notif (fail) : channel %d\n",
+			le16_to_cpu(csa->channel));
+		iwl_chswitch_done(priv, false);
 	}
 }
 
diff --git a/drivers/net/wireless/libertas/cmd.c b/drivers/net/wireless/libertas/cmd.c
index 84566db486d2..71c8f3fccfa1 100644
--- a/drivers/net/wireless/libertas/cmd.c
+++ b/drivers/net/wireless/libertas/cmd.c
@@ -994,6 +994,8 @@ static void lbs_submit_command(struct lbs_private *priv,
 	cmd = cmdnode->cmdbuf;
 
 	spin_lock_irqsave(&priv->driver_lock, flags);
+	priv->seqnum++;
+	cmd->seqnum = cpu_to_le16(priv->seqnum);
 	priv->cur_cmd = cmdnode;
 	spin_unlock_irqrestore(&priv->driver_lock, flags);
 
@@ -1621,11 +1623,9 @@ struct cmd_ctrl_node *__lbs_cmd_async(struct lbs_private *priv,
 	/* Copy the incoming command to the buffer */
 	memcpy(cmdnode->cmdbuf, in_cmd, in_cmd_size);
 
-	/* Set sequence number, clean result, move to buffer */
-	priv->seqnum++;
+	/* Set command, clean result, move to buffer */
 	cmdnode->cmdbuf->command = cpu_to_le16(command);
 	cmdnode->cmdbuf->size    = cpu_to_le16(in_cmd_size);
-	cmdnode->cmdbuf->seqnum  = cpu_to_le16(priv->seqnum);
 	cmdnode->cmdbuf->result  = 0;
 
 	lbs_deb_host("PREP_CMD: command 0x%04x\n", command);
diff --git a/drivers/net/wireless/libertas/if_sdio.c b/drivers/net/wireless/libertas/if_sdio.c
index a7b5cb0c2753..224e9853c480 100644
--- a/drivers/net/wireless/libertas/if_sdio.c
+++ b/drivers/net/wireless/libertas/if_sdio.c
@@ -907,7 +907,7 @@ static void if_sdio_interrupt(struct sdio_func *func)
 	card = sdio_get_drvdata(func);
 
 	cause = sdio_readb(card->func, IF_SDIO_H_INT_STATUS, &ret);
-	if (ret)
+	if (ret || !cause)
 		goto out;
 
 	lbs_deb_sdio("interrupt: 0x%X\n", (unsigned)cause);
@@ -1008,10 +1008,6 @@ static int if_sdio_probe(struct sdio_func *func,
 	if (ret)
 		goto release;
 
-	ret = sdio_claim_irq(func, if_sdio_interrupt);
-	if (ret)
-		goto disable;
-
 	/* For 1-bit transfers to the 8686 model, we need to enable the
 	 * interrupt flag in the CCCR register. Set the MMC_QUIRK_LENIENT_FN0
 	 * bit to allow access to non-vendor registers. */
@@ -1083,6 +1079,21 @@ static int if_sdio_probe(struct sdio_func *func,
 		card->rx_unit = 0;
 
 	/*
+	 * Set up the interrupt handler late.
+	 *
+	 * If we set it up earlier, the (buggy) hardware generates a spurious
+	 * interrupt, even before the interrupt has been enabled, with
+	 * CCCR_INTx = 0.
+	 *
+	 * We register the interrupt handler late so that we can handle any
+	 * spurious interrupts, and also to avoid generation of that known
+	 * spurious interrupt in the first place.
+	 */
+	ret = sdio_claim_irq(func, if_sdio_interrupt);
+	if (ret)
+		goto disable;
+
+	/*
 	 * Enable interrupts now that everything is set up
 	 */
 	sdio_writeb(func, 0x0f, IF_SDIO_H_INT_MASK, &ret);
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index 660831ce293c..687c1f223497 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -1288,6 +1288,8 @@ int mwifiex_register_cfg80211(struct net_device *dev, u8 *mac,
 
 	*(unsigned long *) wdev_priv = (unsigned long) priv;
 
+	set_wiphy_dev(wdev->wiphy, (struct device *) priv->adapter->dev);
+
 	ret = wiphy_register(wdev->wiphy);
 	if (ret < 0) {
 		dev_err(priv->adapter->dev, "%s: registering cfg80211 device\n",
diff --git a/drivers/net/wireless/mwifiex/sdio.h b/drivers/net/wireless/mwifiex/sdio.h
index a0e9bc5253e0..4e97e90aa399 100644
--- a/drivers/net/wireless/mwifiex/sdio.h
+++ b/drivers/net/wireless/mwifiex/sdio.h
@@ -167,8 +167,8 @@
 /* Rx unit register */
 #define CARD_RX_UNIT_REG		0x63
 
-/* Event header Len*/
-#define MWIFIEX_EVENT_HEADER_LEN           8
+/* Event header len w/o 4 bytes of interface header */
+#define MWIFIEX_EVENT_HEADER_LEN           4
 
 /* Max retry number of CMD53 write */
 #define MAX_WRITE_IOMEM_RETRY		2
diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c
index 32261189bcef..aeac3cc4dbe4 100644
--- a/drivers/net/wireless/mwl8k.c
+++ b/drivers/net/wireless/mwl8k.c
@@ -2474,6 +2474,7 @@ struct mwl8k_cmd_set_hw_spec {
  * faster client.
  */
 #define MWL8K_SET_HW_SPEC_FLAG_ENABLE_LIFE_TIME_EXPIRY	0x00000400
+#define MWL8K_SET_HW_SPEC_FLAG_GENERATE_CCMP_HDR	0x00000200
 #define MWL8K_SET_HW_SPEC_FLAG_HOST_DECR_MGMT		0x00000080
 #define MWL8K_SET_HW_SPEC_FLAG_HOSTFORM_PROBERESP	0x00000020
 #define MWL8K_SET_HW_SPEC_FLAG_HOSTFORM_BEACON		0x00000010
@@ -2510,7 +2511,8 @@ static int mwl8k_cmd_set_hw_spec(struct ieee80211_hw *hw)
 	cmd->flags = cpu_to_le32(MWL8K_SET_HW_SPEC_FLAG_HOST_DECR_MGMT |
 				 MWL8K_SET_HW_SPEC_FLAG_HOSTFORM_PROBERESP |
 				 MWL8K_SET_HW_SPEC_FLAG_HOSTFORM_BEACON |
-				 MWL8K_SET_HW_SPEC_FLAG_ENABLE_LIFE_TIME_EXPIRY);
+				 MWL8K_SET_HW_SPEC_FLAG_ENABLE_LIFE_TIME_EXPIRY |
+				 MWL8K_SET_HW_SPEC_FLAG_GENERATE_CCMP_HDR);
 	cmd->num_tx_desc_per_queue = cpu_to_le32(MWL8K_TX_DESCS);
 	cmd->total_rxd = cpu_to_le32(MWL8K_RX_DESCS);
 
diff --git a/drivers/net/wireless/rt2x00/Kconfig b/drivers/net/wireless/rt2x00/Kconfig
index 9def1e5369a1..b2f8b8fd4d2d 100644
--- a/drivers/net/wireless/rt2x00/Kconfig
+++ b/drivers/net/wireless/rt2x00/Kconfig
@@ -166,7 +166,6 @@ config RT2800USB_RT35XX
 config RT2800USB_RT53XX
        bool "rt2800usb - Include support for rt53xx devices (EXPERIMENTAL)"
        depends on EXPERIMENTAL
-       default y
        ---help---
          This adds support for rt53xx wireless chipset family to the
          rt2800pci driver.
diff --git a/drivers/net/wireless/rt2x00/rt2x00config.c b/drivers/net/wireless/rt2x00/rt2x00config.c
index 555180d8f4aa..b704e5b183d0 100644
--- a/drivers/net/wireless/rt2x00/rt2x00config.c
+++ b/drivers/net/wireless/rt2x00/rt2x00config.c
@@ -250,7 +250,8 @@ void rt2x00lib_config(struct rt2x00_dev *rt2x00dev,
 	if (ieee80211_flags & IEEE80211_CONF_CHANGE_CHANNEL)
 		rt2x00link_reset_tuner(rt2x00dev, false);
 
-	if (test_bit(REQUIRE_PS_AUTOWAKE, &rt2x00dev->cap_flags) &&
+	if (test_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags) &&
+	    test_bit(REQUIRE_PS_AUTOWAKE, &rt2x00dev->cap_flags) &&
 	    (ieee80211_flags & IEEE80211_CONF_CHANGE_PS) &&
 	    (conf->flags & IEEE80211_CONF_PS)) {
 		beacon_diff = (long)jiffies - (long)rt2x00dev->last_beacon;
diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c
index c018d67aab8e..939821b4af2f 100644
--- a/drivers/net/wireless/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/rt2x00/rt2x00dev.c
@@ -146,6 +146,9 @@ static void rt2x00lib_autowakeup(struct work_struct *work)
 	struct rt2x00_dev *rt2x00dev =
 	    container_of(work, struct rt2x00_dev, autowakeup_work.work);
 
+	if (!test_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags))
+		return;
+
 	if (rt2x00dev->ops->lib->set_device_state(rt2x00dev, STATE_AWAKE))
 		ERROR(rt2x00dev, "Device failed to wakeup.\n");
 	clear_bit(CONFIG_POWERSAVING, &rt2x00dev->flags);
@@ -1160,6 +1163,7 @@ void rt2x00lib_remove_dev(struct rt2x00_dev *rt2x00dev)
 	 * Stop all work.
 	 */
 	cancel_work_sync(&rt2x00dev->intf_work);
+	cancel_delayed_work_sync(&rt2x00dev->autowakeup_work);
 	if (rt2x00_is_usb(rt2x00dev)) {
 		del_timer_sync(&rt2x00dev->txstatus_timer);
 		cancel_work_sync(&rt2x00dev->rxdone_work);
diff --git a/drivers/net/wireless/rtlwifi/pci.c b/drivers/net/wireless/rtlwifi/pci.c
index a40952845436..9f8ccae93317 100644
--- a/drivers/net/wireless/rtlwifi/pci.c
+++ b/drivers/net/wireless/rtlwifi/pci.c
@@ -669,6 +669,14 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 							 &rx_status,
 							 (u8 *) pdesc, skb);
 
+			new_skb = dev_alloc_skb(rtlpci->rxbuffersize);
+			if (unlikely(!new_skb)) {
+				RT_TRACE(rtlpriv, (COMP_INTR | COMP_RECV),
+					 DBG_DMESG,
+					 ("can't alloc skb for rx\n"));
+				goto done;
+			}
+
 			pci_unmap_single(rtlpci->pdev,
 					 *((dma_addr_t *) skb->cb),
 					 rtlpci->rxbuffersize,
@@ -690,7 +698,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 			hdr = rtl_get_hdr(skb);
 			fc = rtl_get_fc(skb);
 
-			if (!stats.crc || !stats.hwerror) {
+			if (!stats.crc && !stats.hwerror) {
 				memcpy(IEEE80211_SKB_RXCB(skb), &rx_status,
 				       sizeof(rx_status));
 
@@ -758,15 +766,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 				rtl_lps_leave(hw);
 			}
 
-			new_skb = dev_alloc_skb(rtlpci->rxbuffersize);
-			if (unlikely(!new_skb)) {
-				RT_TRACE(rtlpriv, (COMP_INTR | COMP_RECV),
-					 DBG_DMESG,
-					 ("can't alloc skb for rx\n"));
-				goto done;
-			}
 			skb = new_skb;
-			/*skb->dev = dev; */
 
 			rtlpci->rx_ring[rx_queue_idx].rx_buf[rtlpci->
 							     rx_ring
@@ -1113,6 +1113,13 @@ static int _rtl_pci_init_rx_ring(struct ieee80211_hw *hw)
 
 		rtlpci->rx_ring[rx_queue_idx].idx = 0;
 
+		/* If amsdu_8k is disabled, set buffersize to 4096. This
+		 * change will reduce memory fragmentation.
+		 */
+		if (rtlpci->rxbuffersize > 4096 &&
+		    rtlpriv->rtlhal.disable_amsdu_8k)
+			rtlpci->rxbuffersize = 4096;
+
 		for (i = 0; i < rtlpci->rxringcount; i++) {
 			struct sk_buff *skb =
 			    dev_alloc_skb(rtlpci->rxbuffersize);
diff --git a/drivers/net/wireless/wl12xx/conf.h b/drivers/net/wireless/wl12xx/conf.h
index 1ab6c86aac40..c83fefb6662f 100644
--- a/drivers/net/wireless/wl12xx/conf.h
+++ b/drivers/net/wireless/wl12xx/conf.h
@@ -1157,6 +1157,9 @@ struct conf_sched_scan_settings {
 	/* time to wait on the channel for passive scans (in TUs) */
 	u32 dwell_time_passive;
 
+	/* time to wait on the channel for DFS scans (in TUs) */
+	u32 dwell_time_dfs;
+
 	/* number of probe requests to send on each channel in active scans */
 	u8 num_probe_reqs;
 
diff --git a/drivers/net/wireless/wl12xx/main.c b/drivers/net/wireless/wl12xx/main.c
index bc00e52f6445..e6497dc669df 100644
--- a/drivers/net/wireless/wl12xx/main.c
+++ b/drivers/net/wireless/wl12xx/main.c
@@ -311,6 +311,7 @@ static struct conf_drv_settings default_conf = {
 		.min_dwell_time_active = 8,
 		.max_dwell_time_active = 30,
 		.dwell_time_passive    = 100,
+		.dwell_time_dfs        = 150,
 		.num_probe_reqs        = 2,
 		.rssi_threshold        = -90,
 		.snr_threshold         = 0,
diff --git a/drivers/net/wireless/wl12xx/scan.c b/drivers/net/wireless/wl12xx/scan.c
index f37e5a391976..56f76abc754d 100644
--- a/drivers/net/wireless/wl12xx/scan.c
+++ b/drivers/net/wireless/wl12xx/scan.c
@@ -331,16 +331,22 @@ wl1271_scan_get_sched_scan_channels(struct wl1271 *wl,
 	struct conf_sched_scan_settings *c = &wl->conf.sched_scan;
 	int i, j;
 	u32 flags;
+	bool force_passive = !req->n_ssids;
 
 	for (i = 0, j = start;
 	     i < req->n_channels && j < MAX_CHANNELS_ALL_BANDS;
 	     i++) {
 		flags = req->channels[i]->flags;
 
-		if (!(flags & IEEE80211_CHAN_DISABLED) &&
-		    ((flags & IEEE80211_CHAN_PASSIVE_SCAN) == passive) &&
-		    ((flags & IEEE80211_CHAN_RADAR) == radar) &&
-		    (req->channels[i]->band == band)) {
+		if (force_passive)
+			flags |= IEEE80211_CHAN_PASSIVE_SCAN;
+
+		if ((req->channels[i]->band == band) &&
+		    !(flags & IEEE80211_CHAN_DISABLED) &&
+		    (!!(flags & IEEE80211_CHAN_RADAR) == radar) &&
+		    /* if radar is set, we ignore the passive flag */
+		    (radar ||
+		     !!(flags & IEEE80211_CHAN_PASSIVE_SCAN) == passive)) {
 			wl1271_debug(DEBUG_SCAN, "band %d, center_freq %d ",
 				     req->channels[i]->band,
 				     req->channels[i]->center_freq);
@@ -350,7 +356,12 @@ wl1271_scan_get_sched_scan_channels(struct wl1271 *wl,
 			wl1271_debug(DEBUG_SCAN, "max_power %d",
 				     req->channels[i]->max_power);
 
-			if (flags & IEEE80211_CHAN_PASSIVE_SCAN) {
+			if (flags & IEEE80211_CHAN_RADAR) {
+				channels[j].flags |= SCAN_CHANNEL_FLAGS_DFS;
+				channels[j].passive_duration =
+					cpu_to_le16(c->dwell_time_dfs);
+			}
+			else if (flags & IEEE80211_CHAN_PASSIVE_SCAN) {
 				channels[j].passive_duration =
 					cpu_to_le16(c->dwell_time_passive);
 			} else {
@@ -359,7 +370,7 @@ wl1271_scan_get_sched_scan_channels(struct wl1271 *wl,
 				channels[j].max_duration =
 					cpu_to_le16(c->max_dwell_time_active);
 			}
-			channels[j].tx_power_att = req->channels[j]->max_power;
+			channels[j].tx_power_att = req->channels[i]->max_power;
 			channels[j].channel = req->channels[i]->hw_value;
 
 			j++;
@@ -386,7 +397,11 @@ wl1271_scan_sched_scan_channels(struct wl1271 *wl,
 		wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
 						    IEEE80211_BAND_2GHZ,
 						    false, false, idx);
-	idx += cfg->active[0];
+	/*
+	 * 5GHz channels always start at position 14, not immediately
+	 * after the last 2.4GHz channel
+	 */
+	idx = 14;
 
 	cfg->passive[1] =
 		wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
@@ -394,22 +409,23 @@ wl1271_scan_sched_scan_channels(struct wl1271 *wl,
 						    false, true, idx);
 	idx += cfg->passive[1];
 
-	cfg->active[1] =
+	cfg->dfs =
 		wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
 						    IEEE80211_BAND_5GHZ,
-						    false, false, 14);
-	idx += cfg->active[1];
+						    true, true, idx);
+	idx += cfg->dfs;
 
-	cfg->dfs =
+	cfg->active[1] =
 		wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
 						    IEEE80211_BAND_5GHZ,
-						    true, false, idx);
-	idx += cfg->dfs;
+						    false, false, idx);
+	idx += cfg->active[1];
 
 	wl1271_debug(DEBUG_SCAN, "    2.4GHz: active %d passive %d",
 		     cfg->active[0], cfg->passive[0]);
 	wl1271_debug(DEBUG_SCAN, "    5GHz: active %d passive %d",
 		     cfg->active[1], cfg->passive[1]);
+	wl1271_debug(DEBUG_SCAN, "    DFS: %d", cfg->dfs);
 
 	return idx;
 }
@@ -421,6 +437,7 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl,
 	struct wl1271_cmd_sched_scan_config *cfg = NULL;
 	struct conf_sched_scan_settings *c = &wl->conf.sched_scan;
 	int i, total_channels, ret;
+	bool force_passive = !req->n_ssids;
 
 	wl1271_debug(DEBUG_CMD, "cmd sched_scan scan config");
 
@@ -444,7 +461,7 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl,
 	for (i = 0; i < SCAN_MAX_CYCLE_INTERVALS; i++)
 		cfg->intervals[i] = cpu_to_le32(req->interval);
 
-	if (req->ssids[0].ssid_len && req->ssids[0].ssid) {
+	if (!force_passive && req->ssids[0].ssid_len && req->ssids[0].ssid) {
 		cfg->filter_type = SCAN_SSID_FILTER_SPECIFIC;
 		cfg->ssid_len = req->ssids[0].ssid_len;
 		memcpy(cfg->ssid, req->ssids[0].ssid,
@@ -461,7 +478,7 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl,
 		goto out;
 	}
 
-	if (cfg->active[0]) {
+	if (!force_passive && cfg->active[0]) {
 		ret = wl1271_cmd_build_probe_req(wl, req->ssids[0].ssid,
 						 req->ssids[0].ssid_len,
 						 ies->ie[IEEE80211_BAND_2GHZ],
@@ -473,7 +490,7 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl,
 		}
 	}
 
-	if (cfg->active[1]) {
+	if (!force_passive && cfg->active[1]) {
 		ret = wl1271_cmd_build_probe_req(wl,  req->ssids[0].ssid,
 						 req->ssids[0].ssid_len,
 						 ies->ie[IEEE80211_BAND_5GHZ],
diff --git a/drivers/net/wireless/wl12xx/scan.h b/drivers/net/wireless/wl12xx/scan.h
index c83319579ca3..a0b6c5d67b07 100644
--- a/drivers/net/wireless/wl12xx/scan.h
+++ b/drivers/net/wireless/wl12xx/scan.h
@@ -137,6 +137,9 @@ enum {
 	SCAN_BSS_TYPE_ANY,
 };
 
+#define SCAN_CHANNEL_FLAGS_DFS		BIT(0)
+#define SCAN_CHANNEL_FLAGS_DFS_ENABLED	BIT(1)
+
 struct conn_scan_ch_params {
 	__le16 min_duration;
 	__le16 max_duration;
diff --git a/drivers/net/wireless/zd1211rw/zd_usb.c b/drivers/net/wireless/zd1211rw/zd_usb.c
index 0e819943b9e4..631194d49828 100644
--- a/drivers/net/wireless/zd1211rw/zd_usb.c
+++ b/drivers/net/wireless/zd1211rw/zd_usb.c
@@ -1533,6 +1533,31 @@ static void __exit usb_exit(void)
 module_init(usb_init);
 module_exit(usb_exit);
 
+static int zd_ep_regs_out_msg(struct usb_device *udev, void *data, int len,
+			      int *actual_length, int timeout)
+{
+	/* In USB 2.0 mode EP_REGS_OUT endpoint is interrupt type. However in
+	 * USB 1.1 mode endpoint is bulk. Select correct type URB by endpoint
+	 * descriptor.
+	 */
+	struct usb_host_endpoint *ep;
+	unsigned int pipe;
+
+	pipe = usb_sndintpipe(udev, EP_REGS_OUT);
+	ep = usb_pipe_endpoint(udev, pipe);
+	if (!ep)
+		return -EINVAL;
+
+	if (usb_endpoint_xfer_int(&ep->desc)) {
+		return usb_interrupt_msg(udev, pipe, data, len,
+					 actual_length, timeout);
+	} else {
+		pipe = usb_sndbulkpipe(udev, EP_REGS_OUT);
+		return usb_bulk_msg(udev, pipe, data, len, actual_length,
+				    timeout);
+	}
+}
+
 static int usb_int_regs_length(unsigned int count)
 {
 	return sizeof(struct usb_int_regs) + count * sizeof(struct reg_data);
@@ -1648,15 +1673,14 @@ int zd_usb_ioread16v(struct zd_usb *usb, u16 *values,
 
 	udev = zd_usb_to_usbdev(usb);
 	prepare_read_regs_int(usb);
-	r = usb_interrupt_msg(udev, usb_sndintpipe(udev, EP_REGS_OUT),
-			      req, req_len, &actual_req_len, 50 /* ms */);
+	r = zd_ep_regs_out_msg(udev, req, req_len, &actual_req_len, 50 /*ms*/);
 	if (r) {
 		dev_dbg_f(zd_usb_dev(usb),
-			"error in usb_interrupt_msg(). Error number %d\n", r);
+			"error in zd_ep_regs_out_msg(). Error number %d\n", r);
 		goto error;
 	}
 	if (req_len != actual_req_len) {
-		dev_dbg_f(zd_usb_dev(usb), "error in usb_interrupt_msg()\n"
+		dev_dbg_f(zd_usb_dev(usb), "error in zd_ep_regs_out_msg()\n"
 			" req_len %d != actual_req_len %d\n",
 			req_len, actual_req_len);
 		r = -EIO;
@@ -1818,9 +1842,17 @@ int zd_usb_iowrite16v_async(struct zd_usb *usb, const struct zd_ioreq16 *ioreqs,
 		rw->value = cpu_to_le16(ioreqs[i].value);
 	}
 
-	usb_fill_int_urb(urb, udev, usb_sndintpipe(udev, EP_REGS_OUT),
-			 req, req_len, iowrite16v_urb_complete, usb,
-			 ep->desc.bInterval);
+	/* In USB 2.0 mode endpoint is interrupt type. However in USB 1.1 mode
+	 * endpoint is bulk. Select correct type URB by endpoint descriptor.
+	 */
+	if (usb_endpoint_xfer_int(&ep->desc))
+		usb_fill_int_urb(urb, udev, usb_sndintpipe(udev, EP_REGS_OUT),
+				 req, req_len, iowrite16v_urb_complete, usb,
+				 ep->desc.bInterval);
+	else
+		usb_fill_bulk_urb(urb, udev, usb_sndbulkpipe(udev, EP_REGS_OUT),
+				  req, req_len, iowrite16v_urb_complete, usb);
+
 	urb->transfer_flags |= URB_FREE_BUFFER;
 
 	/* Submit previous URB */
@@ -1924,15 +1956,14 @@ int zd_usb_rfwrite(struct zd_usb *usb, u32 value, u8 bits)
 	}
 
 	udev = zd_usb_to_usbdev(usb);
-	r = usb_interrupt_msg(udev, usb_sndintpipe(udev, EP_REGS_OUT),
-			      req, req_len, &actual_req_len, 50 /* ms */);
+	r = zd_ep_regs_out_msg(udev, req, req_len, &actual_req_len, 50 /*ms*/);
 	if (r) {
 		dev_dbg_f(zd_usb_dev(usb),
-			"error in usb_interrupt_msg(). Error number %d\n", r);
+			"error in zd_ep_regs_out_msg(). Error number %d\n", r);
 		goto out;
 	}
 	if (req_len != actual_req_len) {
-		dev_dbg_f(zd_usb_dev(usb), "error in usb_interrupt_msg()"
+		dev_dbg_f(zd_usb_dev(usb), "error in zd_ep_regs_out_msg()"
 			" req_len %d != actual_req_len %d\n",
 			req_len, actual_req_len);
 		r = -EIO;
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 8b63a691a9ed..65200af29c52 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -670,7 +670,7 @@ int __init early_init_dt_scan_chosen(unsigned long node, const char *uname,
 
 	pr_debug("search \"chosen\", depth: %d, uname: %s\n", depth, uname);
 
-	if (depth != 1 ||
+	if (depth != 1 || !data ||
 	    (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0))
 		return 0;
 
@@ -679,16 +679,16 @@ int __init early_init_dt_scan_chosen(unsigned long node, const char *uname,
 	/* Retrieve command line */
 	p = of_get_flat_dt_prop(node, "bootargs", &l);
 	if (p != NULL && l > 0)
-		strlcpy(cmd_line, p, min((int)l, COMMAND_LINE_SIZE));
+		strlcpy(data, p, min((int)l, COMMAND_LINE_SIZE));
 
 #ifdef CONFIG_CMDLINE
 #ifndef CONFIG_CMDLINE_FORCE
 	if (p == NULL || l == 0 || (l == 1 && (*p) == 0))
 #endif
-		strlcpy(cmd_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+		strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
 #endif /* CONFIG_CMDLINE */
 
-	pr_debug("Command line is: %s\n", cmd_line);
+	pr_debug("Command line is: %s\n", (char*)data);
 
 	/* break now */
 	return 1;
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index a3984f4ef192..f34b5b29fb95 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -141,6 +141,13 @@ static struct notifier_block module_load_nb = {
 	.notifier_call = module_load_notify,
 };
 
+static void free_all_tasks(void)
+{
+	/* make sure we don't leak task structs */
+	process_task_mortuary();
+	process_task_mortuary();
+}
+
 int sync_start(void)
 {
 	int err;
@@ -148,8 +155,6 @@ int sync_start(void)
 	if (!zalloc_cpumask_var(&marked_cpus, GFP_KERNEL))
 		return -ENOMEM;
 
-	mutex_lock(&buffer_mutex);
-
 	err = task_handoff_register(&task_free_nb);
 	if (err)
 		goto out1;
@@ -166,7 +171,6 @@ int sync_start(void)
 	start_cpu_work();
 
 out:
-	mutex_unlock(&buffer_mutex);
 	return err;
 out4:
 	profile_event_unregister(PROFILE_MUNMAP, &munmap_nb);
@@ -174,6 +178,7 @@ out3:
 	profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb);
 out2:
 	task_handoff_unregister(&task_free_nb);
+	free_all_tasks();
 out1:
 	free_cpumask_var(marked_cpus);
 	goto out;
@@ -182,20 +187,16 @@ out1:
 
 void sync_stop(void)
 {
-	/* flush buffers */
-	mutex_lock(&buffer_mutex);
 	end_cpu_work();
 	unregister_module_notifier(&module_load_nb);
 	profile_event_unregister(PROFILE_MUNMAP, &munmap_nb);
 	profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb);
 	task_handoff_unregister(&task_free_nb);
-	mutex_unlock(&buffer_mutex);
-	flush_cpu_work();
+	barrier();			/* do all of the above first */
 
-	/* make sure we don't leak task structs */
-	process_task_mortuary();
-	process_task_mortuary();
+	flush_cpu_work();
 
+	free_all_tasks();
 	free_cpumask_var(marked_cpus);
 }
 
diff --git a/drivers/oprofile/event_buffer.h b/drivers/oprofile/event_buffer.h
index 4e70749f8d16..a8d5bb3cba89 100644
--- a/drivers/oprofile/event_buffer.h
+++ b/drivers/oprofile/event_buffer.h
@@ -11,7 +11,7 @@
 #define EVENT_BUFFER_H
 
 #include <linux/types.h>
-#include <asm/mutex.h>
+#include <linux/mutex.h>
 
 int alloc_event_buffer(void);
 
diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
index f9bda64fcd1b..dccd8636095c 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -14,7 +14,7 @@
 #include <linux/moduleparam.h>
 #include <linux/workqueue.h>
 #include <linux/time.h>
-#include <asm/mutex.h>
+#include <linux/mutex.h>
 
 #include "oprof.h"
 #include "event_buffer.h"
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index c85f744270a5..094308e41be5 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -51,6 +51,7 @@ obj-$(CONFIG_X86_VISWS) += setup-irq.o
 obj-$(CONFIG_MN10300) += setup-bus.o
 obj-$(CONFIG_MICROBLAZE) += setup-bus.o
 obj-$(CONFIG_TILE) += setup-bus.o setup-irq.o
+obj-$(CONFIG_SPARC_LEON) += setup-bus.o setup-irq.o
 
 #
 # ACPI Related PCI FW Functions
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 12e02bf92c4a..3dc9befa5aec 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -698,12 +698,7 @@ int __init detect_intel_iommu(void)
 	{
 #ifdef CONFIG_INTR_REMAP
 		struct acpi_table_dmar *dmar;
-		/*
-		 * for now we will disable dma-remapping when interrupt
-		 * remapping is enabled.
-		 * When support for queued invalidation for IOTLB invalidation
-		 * is added, we will not need this any more.
-		 */
+
 		dmar = (struct acpi_table_dmar *) dmar_tbl;
 		if (ret && cpu_has_x2apic && dmar->flags & 0x1)
 			printk(KERN_INFO
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 6af6b628175b..f02c34d26d1b 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -47,6 +47,8 @@
 #define ROOT_SIZE		VTD_PAGE_SIZE
 #define CONTEXT_SIZE		VTD_PAGE_SIZE
 
+#define IS_BRIDGE_HOST_DEVICE(pdev) \
+			    ((pdev->class >> 8) == PCI_CLASS_BRIDGE_HOST)
 #define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY)
 #define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
 #define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e)
@@ -116,6 +118,11 @@ static inline unsigned long align_to_level(unsigned long pfn, int level)
 	return (pfn + level_size(level) - 1) & level_mask(level);
 }
 
+static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
+{
+	return  1 << ((lvl - 1) * LEVEL_STRIDE);
+}
+
 /* VT-d pages must always be _smaller_ than MM pages. Otherwise things
    are never going to work. */
 static inline unsigned long dma_to_mm_pfn(unsigned long dma_pfn)
@@ -143,6 +150,12 @@ static void __init check_tylersburg_isoch(void);
 static int rwbf_quirk;
 
 /*
+ * set to 1 to panic kernel if can't successfully enable VT-d
+ * (used when kernel is launched w/ TXT)
+ */
+static int force_on = 0;
+
+/*
  * 0: Present
  * 1-11: Reserved
  * 12-63: Context Ptr (12 - (haw-1))
@@ -338,6 +351,9 @@ struct dmar_domain {
 	int		iommu_coherency;/* indicate coherency of iommu access */
 	int		iommu_snooping; /* indicate snooping control feature*/
 	int		iommu_count;	/* reference count of iommu */
+	int		iommu_superpage;/* Level of superpages supported:
+					   0 == 4KiB (no superpages), 1 == 2MiB,
+					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
 	spinlock_t	iommu_lock;	/* protect iommu set in domain */
 	u64		max_addr;	/* maximum mapped address */
 };
@@ -387,6 +403,7 @@ int dmar_disabled = 1;
 static int dmar_map_gfx = 1;
 static int dmar_forcedac;
 static int intel_iommu_strict;
+static int intel_iommu_superpage = 1;
 
 #define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
 static DEFINE_SPINLOCK(device_domain_lock);
@@ -417,6 +434,10 @@ static int __init intel_iommu_setup(char *str)
 			printk(KERN_INFO
 				"Intel-IOMMU: disable batched IOTLB flush\n");
 			intel_iommu_strict = 1;
+		} else if (!strncmp(str, "sp_off", 6)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: disable supported super page\n");
+			intel_iommu_superpage = 0;
 		}
 
 		str += strcspn(str, ",");
@@ -555,11 +576,32 @@ static void domain_update_iommu_snooping(struct dmar_domain *domain)
 	}
 }
 
+static void domain_update_iommu_superpage(struct dmar_domain *domain)
+{
+	int i, mask = 0xf;
+
+	if (!intel_iommu_superpage) {
+		domain->iommu_superpage = 0;
+		return;
+	}
+
+	domain->iommu_superpage = 4; /* 1TiB */
+
+	for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) {
+		mask |= cap_super_page_val(g_iommus[i]->cap);
+		if (!mask) {
+			break;
+		}
+	}
+	domain->iommu_superpage = fls(mask);
+}
+
 /* Some capabilities may be different across iommus */
 static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
 	domain_update_iommu_coherency(domain);
 	domain_update_iommu_snooping(domain);
+	domain_update_iommu_superpage(domain);
 }
 
 static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn)
@@ -689,23 +731,31 @@ out:
 }
 
 static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
-				      unsigned long pfn)
+				      unsigned long pfn, int large_level)
 {
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
 	struct dma_pte *parent, *pte = NULL;
 	int level = agaw_to_level(domain->agaw);
-	int offset;
+	int offset, target_level;
 
 	BUG_ON(!domain->pgd);
 	BUG_ON(addr_width < BITS_PER_LONG && pfn >> addr_width);
 	parent = domain->pgd;
 
+	/* Search pte */
+	if (!large_level)
+		target_level = 1;
+	else
+		target_level = large_level;
+
 	while (level > 0) {
 		void *tmp_page;
 
 		offset = pfn_level_offset(pfn, level);
 		pte = &parent[offset];
-		if (level == 1)
+		if (!large_level && (pte->val & DMA_PTE_LARGE_PAGE))
+			break;
+		if (level == target_level)
 			break;
 
 		if (!dma_pte_present(pte)) {
@@ -733,10 +783,11 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 	return pte;
 }
 
+
 /* return address's pte at specific level */
 static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain,
 					 unsigned long pfn,
-					 int level)
+					 int level, int *large_page)
 {
 	struct dma_pte *parent, *pte = NULL;
 	int total = agaw_to_level(domain->agaw);
@@ -749,8 +800,16 @@ static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain,
 		if (level == total)
 			return pte;
 
-		if (!dma_pte_present(pte))
+		if (!dma_pte_present(pte)) {
+			*large_page = total;
 			break;
+		}
+
+		if (pte->val & DMA_PTE_LARGE_PAGE) {
+			*large_page = total;
+			return pte;
+		}
+
 		parent = phys_to_virt(dma_pte_addr(pte));
 		total--;
 	}
@@ -763,6 +822,7 @@ static void dma_pte_clear_range(struct dmar_domain *domain,
 				unsigned long last_pfn)
 {
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
+	unsigned int large_page = 1;
 	struct dma_pte *first_pte, *pte;
 
 	BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
@@ -771,14 +831,15 @@ static void dma_pte_clear_range(struct dmar_domain *domain,
 
 	/* we don't need lock here; nobody else touches the iova range */
 	do {
-		first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1);
+		large_page = 1;
+		first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1, &large_page);
 		if (!pte) {
-			start_pfn = align_to_level(start_pfn + 1, 2);
+			start_pfn = align_to_level(start_pfn + 1, large_page + 1);
 			continue;
 		}
-		do { 
+		do {
 			dma_clear_pte(pte);
-			start_pfn++;
+			start_pfn += lvl_to_nr_pages(large_page);
 			pte++;
 		} while (start_pfn <= last_pfn && !first_pte_in_page(pte));
 
@@ -798,6 +859,7 @@ static void dma_pte_free_pagetable(struct dmar_domain *domain,
 	int total = agaw_to_level(domain->agaw);
 	int level;
 	unsigned long tmp;
+	int large_page = 2;
 
 	BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
 	BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width);
@@ -813,7 +875,10 @@ static void dma_pte_free_pagetable(struct dmar_domain *domain,
 			return;
 
 		do {
-			first_pte = pte = dma_pfn_level_pte(domain, tmp, level);
+			large_page = level;
+			first_pte = pte = dma_pfn_level_pte(domain, tmp, level, &large_page);
+			if (large_page > level)
+				level = large_page + 1;
 			if (!pte) {
 				tmp = align_to_level(tmp + 1, level + 1);
 				continue;
@@ -1397,6 +1462,7 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 	else
 		domain->iommu_snooping = 0;
 
+	domain->iommu_superpage = fls(cap_super_page_val(iommu->cap));
 	domain->iommu_count = 1;
 	domain->nid = iommu->node;
 
@@ -1417,6 +1483,10 @@ static void domain_exit(struct dmar_domain *domain)
 	if (!domain)
 		return;
 
+	/* Flush any lazy unmaps that may reference this domain */
+	if (!intel_iommu_strict)
+		flush_unmaps_timeout(0);
+
 	domain_remove_dev_info(domain);
 	/* destroy iovas */
 	put_iova_domain(&domain->iovad);
@@ -1648,6 +1718,34 @@ static inline unsigned long aligned_nrpages(unsigned long host_addr,
 	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
 }
 
+/* Return largest possible superpage level for a given mapping */
+static inline int hardware_largepage_caps(struct dmar_domain *domain,
+					  unsigned long iov_pfn,
+					  unsigned long phy_pfn,
+					  unsigned long pages)
+{
+	int support, level = 1;
+	unsigned long pfnmerge;
+
+	support = domain->iommu_superpage;
+
+	/* To use a large page, the virtual *and* physical addresses
+	   must be aligned to 2MiB/1GiB/etc. Lower bits set in either
+	   of them will mean we have to use smaller pages. So just
+	   merge them and check both at once. */
+	pfnmerge = iov_pfn | phy_pfn;
+
+	while (support && !(pfnmerge & ~VTD_STRIDE_MASK)) {
+		pages >>= VTD_STRIDE_SHIFT;
+		if (!pages)
+			break;
+		pfnmerge >>= VTD_STRIDE_SHIFT;
+		level++;
+		support--;
+	}
+	return level;
+}
+
 static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			    struct scatterlist *sg, unsigned long phys_pfn,
 			    unsigned long nr_pages, int prot)
@@ -1656,6 +1754,8 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 	phys_addr_t uninitialized_var(pteval);
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
 	unsigned long sg_res;
+	unsigned int largepage_lvl = 0;
+	unsigned long lvl_pages = 0;
 
 	BUG_ON(addr_width < BITS_PER_LONG && (iov_pfn + nr_pages - 1) >> addr_width);
 
@@ -1671,7 +1771,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
 	}
 
-	while (nr_pages--) {
+	while (nr_pages > 0) {
 		uint64_t tmp;
 
 		if (!sg_res) {
@@ -1679,11 +1779,21 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset;
 			sg->dma_length = sg->length;
 			pteval = page_to_phys(sg_page(sg)) | prot;
+			phys_pfn = pteval >> VTD_PAGE_SHIFT;
 		}
+
 		if (!pte) {
-			first_pte = pte = pfn_to_dma_pte(domain, iov_pfn);
+			largepage_lvl = hardware_largepage_caps(domain, iov_pfn, phys_pfn, sg_res);
+
+			first_pte = pte = pfn_to_dma_pte(domain, iov_pfn, largepage_lvl);
 			if (!pte)
 				return -ENOMEM;
+			/* It is large page*/
+			if (largepage_lvl > 1)
+				pteval |= DMA_PTE_LARGE_PAGE;
+			else
+				pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE;
+
 		}
 		/* We don't need lock here, nobody else
 		 * touches the iova range
@@ -1699,16 +1809,38 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			}
 			WARN_ON(1);
 		}
+
+		lvl_pages = lvl_to_nr_pages(largepage_lvl);
+
+		BUG_ON(nr_pages < lvl_pages);
+		BUG_ON(sg_res < lvl_pages);
+
+		nr_pages -= lvl_pages;
+		iov_pfn += lvl_pages;
+		phys_pfn += lvl_pages;
+		pteval += lvl_pages * VTD_PAGE_SIZE;
+		sg_res -= lvl_pages;
+
+		/* If the next PTE would be the first in a new page, then we
+		   need to flush the cache on the entries we've just written.
+		   And then we'll need to recalculate 'pte', so clear it and
+		   let it get set again in the if (!pte) block above.
+
+		   If we're done (!nr_pages) we need to flush the cache too.
+
+		   Also if we've been setting superpages, we may need to
+		   recalculate 'pte' and switch back to smaller pages for the
+		   end of the mapping, if the trailing size is not enough to
+		   use another superpage (i.e. sg_res < lvl_pages). */
 		pte++;
-		if (!nr_pages || first_pte_in_page(pte)) {
+		if (!nr_pages || first_pte_in_page(pte) ||
+		    (largepage_lvl > 1 && sg_res < lvl_pages)) {
 			domain_flush_cache(domain, first_pte,
 					   (void *)pte - (void *)first_pte);
 			pte = NULL;
 		}
-		iov_pfn++;
-		pteval += VTD_PAGE_SIZE;
-		sg_res--;
-		if (!sg_res)
+
+		if (!sg_res && nr_pages)
 			sg = sg_next(sg);
 	}
 	return 0;
@@ -2016,7 +2148,7 @@ static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr,
 	if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
 		return 0;
 	return iommu_prepare_identity_map(pdev, rmrr->base_address,
-		rmrr->end_address + 1);
+		rmrr->end_address);
 }
 
 #ifdef CONFIG_DMAR_FLOPPY_WA
@@ -2030,7 +2162,7 @@ static inline void iommu_prepare_isa(void)
 		return;
 
 	printk(KERN_INFO "IOMMU: Prepare 0-16MiB unity mapping for LPC\n");
-	ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024);
+	ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024 - 1);
 
 	if (ret)
 		printk(KERN_ERR "IOMMU: Failed to create 0-16MiB identity map; "
@@ -2106,10 +2238,10 @@ static int identity_mapping(struct pci_dev *pdev)
 	if (likely(!iommu_identity_mapping))
 		return 0;
 
+	info = pdev->dev.archdata.iommu;
+	if (info && info != DUMMY_DEVICE_DOMAIN_INFO)
+		return (info->domain == si_domain);
 
-	list_for_each_entry(info, &si_domain->devices, link)
-		if (info->dev == pdev)
-			return 1;
 	return 0;
 }
 
@@ -2187,8 +2319,19 @@ static int iommu_should_identity_map(struct pci_dev *pdev, int startup)
 	 * Assume that they will -- if they turn out not to be, then we can 
 	 * take them out of the 1:1 domain later.
 	 */
-	if (!startup)
-		return pdev->dma_mask > DMA_BIT_MASK(32);
+	if (!startup) {
+		/*
+		 * If the device's dma_mask is less than the system's memory
+		 * size then this is not a candidate for identity mapping.
+		 */
+		u64 dma_mask = pdev->dma_mask;
+
+		if (pdev->dev.coherent_dma_mask &&
+		    pdev->dev.coherent_dma_mask < dma_mask)
+			dma_mask = pdev->dev.coherent_dma_mask;
+
+		return dma_mask >= dma_get_required_mask(&pdev->dev);
+	}
 
 	return 1;
 }
@@ -2203,6 +2346,9 @@ static int __init iommu_prepare_static_identity_mapping(int hw)
 		return -EFAULT;
 
 	for_each_pci_dev(pdev) {
+		/* Skip Host/PCI Bridge devices */
+		if (IS_BRIDGE_HOST_DEVICE(pdev))
+			continue;
 		if (iommu_should_identity_map(pdev, 1)) {
 			printk(KERN_INFO "IOMMU: %s identity mapping for device %s\n",
 			       hw ? "hardware" : "software", pci_name(pdev));
@@ -2218,7 +2364,7 @@ static int __init iommu_prepare_static_identity_mapping(int hw)
 	return 0;
 }
 
-static int __init init_dmars(int force_on)
+static int __init init_dmars(void)
 {
 	struct dmar_drhd_unit *drhd;
 	struct dmar_rmrr_unit *rmrr;
@@ -2592,8 +2738,7 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr,
 	iommu = domain_get_iommu(domain);
 	size = aligned_nrpages(paddr, size);
 
-	iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size),
-				pdev->dma_mask);
+	iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size), dma_mask);
 	if (!iova)
 		goto error;
 
@@ -3118,7 +3263,17 @@ static int init_iommu_hw(void)
 		if (iommu->qi)
 			dmar_reenable_qi(iommu);
 
-	for_each_active_iommu(iommu, drhd) {
+	for_each_iommu(iommu, drhd) {
+		if (drhd->ignored) {
+			/*
+			 * we always have to disable PMRs or DMA may fail on
+			 * this device
+			 */
+			if (force_on)
+				iommu_disable_protect_mem_regions(iommu);
+			continue;
+		}
+	
 		iommu_flush_write_buffer(iommu);
 
 		iommu_set_root_entry(iommu);
@@ -3127,7 +3282,8 @@ static int init_iommu_hw(void)
 					   DMA_CCMD_GLOBAL_INVL);
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
 					 DMA_TLB_GLOBAL_FLUSH);
-		iommu_enable_translation(iommu);
+		if (iommu_enable_translation(iommu))
+			return 1;
 		iommu_disable_protect_mem_regions(iommu);
 	}
 
@@ -3194,7 +3350,10 @@ static void iommu_resume(void)
 	unsigned long flag;
 
 	if (init_iommu_hw()) {
-		WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
+		if (force_on)
+			panic("tboot: IOMMU setup failed, DMAR can not resume!\n");
+		else
+			WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
 		return;
 	}
 
@@ -3229,7 +3388,7 @@ static void __init init_iommu_pm_ops(void)
 }
 
 #else
-static inline int init_iommu_pm_ops(void) { }
+static inline void init_iommu_pm_ops(void) {}
 #endif	/* CONFIG_PM */
 
 /*
@@ -3271,7 +3430,6 @@ static struct notifier_block device_nb = {
 int __init intel_iommu_init(void)
 {
 	int ret = 0;
-	int force_on = 0;
 
 	/* VT-d is required for a TXT/tboot launch, so enforce that */
 	force_on = tboot_force_iommu();
@@ -3309,7 +3467,7 @@ int __init intel_iommu_init(void)
 
 	init_no_remapping_devices();
 
-	ret = init_dmars(force_on);
+	ret = init_dmars();
 	if (ret) {
 		if (force_on)
 			panic("tboot: Failed to initialize DMARs\n");
@@ -3380,8 +3538,8 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain,
 	spin_lock_irqsave(&device_domain_lock, flags);
 	list_for_each_safe(entry, tmp, &domain->devices) {
 		info = list_entry(entry, struct device_domain_info, link);
-		/* No need to compare PCI domain; it has to be the same */
-		if (info->bus == pdev->bus->number &&
+		if (info->segment == pci_domain_nr(pdev->bus) &&
+		    info->bus == pdev->bus->number &&
 		    info->devfn == pdev->devfn) {
 			list_del(&info->link);
 			list_del(&info->global);
@@ -3419,10 +3577,13 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain,
 		domain_update_iommu_cap(domain);
 		spin_unlock_irqrestore(&domain->iommu_lock, tmp_flags);
 
-		spin_lock_irqsave(&iommu->lock, tmp_flags);
-		clear_bit(domain->id, iommu->domain_ids);
-		iommu->domains[domain->id] = NULL;
-		spin_unlock_irqrestore(&iommu->lock, tmp_flags);
+		if (!(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) &&
+		    !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY)) {
+			spin_lock_irqsave(&iommu->lock, tmp_flags);
+			clear_bit(domain->id, iommu->domain_ids);
+			iommu->domains[domain->id] = NULL;
+			spin_unlock_irqrestore(&iommu->lock, tmp_flags);
+		}
 	}
 
 	spin_unlock_irqrestore(&device_domain_lock, flags);
@@ -3505,6 +3666,7 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 	domain->iommu_count = 0;
 	domain->iommu_coherency = 0;
 	domain->iommu_snooping = 0;
+	domain->iommu_superpage = 0;
 	domain->max_addr = 0;
 	domain->nid = -1;
 
@@ -3720,7 +3882,7 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	struct dma_pte *pte;
 	u64 phys = 0;
 
-	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT);
+	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, 0);
 	if (pte)
 		phys = dma_pte_addr(pte);
 
diff --git a/drivers/pci/iova.c b/drivers/pci/iova.c
index 9606e599a475..c5c274ab5c5a 100644
--- a/drivers/pci/iova.c
+++ b/drivers/pci/iova.c
@@ -63,8 +63,16 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 	curr = iovad->cached32_node;
 	cached_iova = container_of(curr, struct iova, node);
 
-	if (free->pfn_lo >= cached_iova->pfn_lo)
-		iovad->cached32_node = rb_next(&free->node);
+	if (free->pfn_lo >= cached_iova->pfn_lo) {
+		struct rb_node *node = rb_next(&free->node);
+		struct iova *iova = container_of(node, struct iova, node);
+
+		/* only cache if it's below 32bit pfn */
+		if (node && iova->pfn_lo < iovad->dma_32bit_pfn)
+			iovad->cached32_node = node;
+		else
+			iovad->cached32_node = NULL;
+	}
 }
 
 /* Computes the padding size required, to make the
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 7c3b18e78cee..d36f41ea8cbf 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -195,6 +195,8 @@ static pci_power_t acpi_pci_choose_state(struct pci_dev *pdev)
 		return PCI_D2;
 	case ACPI_STATE_D3:
 		return PCI_D3hot;
+	case ACPI_STATE_D3_COLD:
+		return PCI_D3cold;
 	}
 	return PCI_POWER_ERROR;
 }
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 135df164a4c1..46767c53917a 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -624,7 +624,7 @@ static int pci_pm_prepare(struct device *dev)
 	 * system from the sleep state, we'll have to prevent it from signaling
 	 * wake-up.
 	 */
-	pm_runtime_resume(dev);
+	pm_runtime_get_sync(dev);
 
 	if (drv && drv->pm && drv->pm->prepare)
 		error = drv->pm->prepare(dev);
@@ -638,6 +638,8 @@ static void pci_pm_complete(struct device *dev)
 
 	if (drv && drv->pm && drv->pm->complete)
 		drv->pm->complete(dev);
+
+	pm_runtime_put_sync(dev);
 }
 
 #else /* !CONFIG_PM_SLEEP */
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 56098b3e17c0..2c5b9b991279 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3271,11 +3271,11 @@ void __init pci_register_set_vga_state(arch_set_vga_state_t func)
 }
 
 static int pci_set_vga_state_arch(struct pci_dev *dev, bool decode,
-		      unsigned int command_bits, bool change_bridge)
+		      unsigned int command_bits, u32 flags)
 {
 	if (arch_set_vga_state)
 		return arch_set_vga_state(dev, decode, command_bits,
-						change_bridge);
+						flags);
 	return 0;
 }
 
@@ -3284,7 +3284,7 @@ static int pci_set_vga_state_arch(struct pci_dev *dev, bool decode,
  * @dev: the PCI device
  * @decode: true = enable decoding, false = disable decoding
  * @command_bits: PCI_COMMAND_IO and/or PCI_COMMAND_MEMORY
- * @change_bridge_flags: traverse ancestors and change bridges
+ * @flags: traverse ancestors and change bridges
  * CHANGE_BRIDGE_ONLY / CHANGE_BRIDGE
  */
 int pci_set_vga_state(struct pci_dev *dev, bool decode,
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 48849ffdd672..bafb3c3d4a89 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -168,7 +168,7 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 		res->flags |= pci_calc_resource_flags(l) | IORESOURCE_SIZEALIGN;
 		if (type == pci_bar_io) {
 			l &= PCI_BASE_ADDRESS_IO_MASK;
-			mask = PCI_BASE_ADDRESS_IO_MASK & IO_SPACE_LIMIT;
+			mask = PCI_BASE_ADDRESS_IO_MASK & (u32) IO_SPACE_LIMIT;
 		} else {
 			l &= PCI_BASE_ADDRESS_MEM_MASK;
 			mask = (u32)PCI_BASE_ADDRESS_MEM_MASK;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index e8a140669f90..02145e9697a9 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2761,6 +2761,8 @@ static void ricoh_mmc_fixup_r5c832(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832);
 DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE823, ricoh_mmc_fixup_r5c832);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE823, ricoh_mmc_fixup_r5c832);
 #endif /*CONFIG_MMC_RICOH_MMC*/
 
 #if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP)
diff --git a/drivers/pcmcia/pxa2xx_vpac270.c b/drivers/pcmcia/pxa2xx_vpac270.c
index 435002dfc3ca..712baab3c83d 100644
--- a/drivers/pcmcia/pxa2xx_vpac270.c
+++ b/drivers/pcmcia/pxa2xx_vpac270.c
@@ -11,6 +11,7 @@
  *
  */
 
+#include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 5cb999b50f95..45e0191c35dd 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -39,7 +39,7 @@ config ACER_WMI
 
 config ACERHDF
 	tristate "Acer Aspire One temperature and fan driver"
-	depends on THERMAL && THERMAL_HWMON && ACPI
+	depends on THERMAL && ACPI
 	---help---
 	  This is a driver for Acer Aspire One netbooks. It allows to access
 	  the temperature sensor and to control the fan.
@@ -760,4 +760,13 @@ config MXM_WMI
           MXM is a standard for laptop graphics cards, the WMI interface
 	  is required for switchable nvidia graphics machines
 
+config INTEL_OAKTRAIL
+	tristate "Intel Oaktrail Platform Extras"
+	depends on ACPI
+	depends on RFKILL && BACKLIGHT_CLASS_DEVICE && ACPI
+	---help---
+	  Intel Oaktrail platform need this driver to provide interfaces to
+	  enable/disable the Camera, WiFi, BT etc. devices. If in doubt, say Y
+	  here; it will only load on supported platforms.
+
 endif # X86_PLATFORM_DEVICES
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index a7ab3bc7b3a1..afc1f832aa67 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -41,5 +41,6 @@ obj-$(CONFIG_XO1_RFKILL)	+= xo1-rfkill.o
 obj-$(CONFIG_XO15_EBOOK)	+= xo15-ebook.o
 obj-$(CONFIG_IBM_RTL)		+= ibm_rtl.o
 obj-$(CONFIG_SAMSUNG_LAPTOP)	+= samsung-laptop.o
-obj-$(CONFIG_INTEL_MFLD_THERMAL)	+= intel_mid_thermal.o
 obj-$(CONFIG_MXM_WMI)		+= mxm-wmi.o
+obj-$(CONFIG_INTEL_MID_POWER_BUTTON)	+= intel_mid_powerbtn.o
+obj-$(CONFIG_INTEL_OAKTRAIL)	+= intel_oaktrail.o
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index ac4e7f83ce6c..005417bd429e 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -98,13 +98,26 @@ enum acer_wmi_event_ids {
 
 static const struct key_entry acer_wmi_keymap[] = {
 	{KE_KEY, 0x01, {KEY_WLAN} },     /* WiFi */
+	{KE_KEY, 0x03, {KEY_WLAN} },     /* WiFi */
 	{KE_KEY, 0x12, {KEY_BLUETOOTH} },	/* BT */
 	{KE_KEY, 0x21, {KEY_PROG1} },    /* Backup */
 	{KE_KEY, 0x22, {KEY_PROG2} },    /* Arcade */
 	{KE_KEY, 0x23, {KEY_PROG3} },    /* P_Key */
 	{KE_KEY, 0x24, {KEY_PROG4} },    /* Social networking_Key */
+	{KE_IGNORE, 0x41, {KEY_MUTE} },
+	{KE_IGNORE, 0x42, {KEY_PREVIOUSSONG} },
+	{KE_IGNORE, 0x43, {KEY_NEXTSONG} },
+	{KE_IGNORE, 0x44, {KEY_PLAYPAUSE} },
+	{KE_IGNORE, 0x45, {KEY_STOP} },
+	{KE_IGNORE, 0x48, {KEY_VOLUMEUP} },
+	{KE_IGNORE, 0x49, {KEY_VOLUMEDOWN} },
+	{KE_IGNORE, 0x61, {KEY_SWITCHVIDEOMODE} },
+	{KE_IGNORE, 0x62, {KEY_BRIGHTNESSUP} },
+	{KE_IGNORE, 0x63, {KEY_BRIGHTNESSDOWN} },
 	{KE_KEY, 0x64, {KEY_SWITCHVIDEOMODE} },	/* Display Switch */
+	{KE_IGNORE, 0x81, {KEY_SLEEP} },
 	{KE_KEY, 0x82, {KEY_TOUCHPAD_TOGGLE} },	/* Touch Pad On/Off */
+	{KE_IGNORE, 0x83, {KEY_TOUCHPAD_TOGGLE} },
 	{KE_END, 0}
 };
 
@@ -122,6 +135,7 @@ struct event_return_value {
  */
 #define ACER_WMID3_GDS_WIRELESS		(1<<0)	/* WiFi */
 #define ACER_WMID3_GDS_THREEG		(1<<6)	/* 3G */
+#define ACER_WMID3_GDS_WIMAX		(1<<7)	/* WiMAX */
 #define ACER_WMID3_GDS_BLUETOOTH	(1<<11)	/* BT */
 
 struct lm_input_params {
@@ -737,8 +751,11 @@ WMI_execute_u32(u32 method_id, u32 in, u32 *out)
 
 	obj = (union acpi_object *) result.pointer;
 	if (obj && obj->type == ACPI_TYPE_BUFFER &&
-		obj->buffer.length == sizeof(u32)) {
+		(obj->buffer.length == sizeof(u32) ||
+		obj->buffer.length == sizeof(u64))) {
 		tmp = *((u32 *) obj->buffer.pointer);
+	} else if (obj->type == ACPI_TYPE_INTEGER) {
+		tmp = (u32) obj->integer.value;
 	} else {
 		tmp = 0;
 	}
@@ -866,8 +883,11 @@ static acpi_status WMID_set_capabilities(void)
 
 	obj = (union acpi_object *) out.pointer;
 	if (obj && obj->type == ACPI_TYPE_BUFFER &&
-		obj->buffer.length == sizeof(u32)) {
+		(obj->buffer.length == sizeof(u32) ||
+		obj->buffer.length == sizeof(u64))) {
 		devices = *((u32 *) obj->buffer.pointer);
+	} else if (obj->type == ACPI_TYPE_INTEGER) {
+		devices = (u32) obj->integer.value;
 	} else {
 		kfree(out.pointer);
 		return AE_ERROR;
@@ -876,7 +896,8 @@ static acpi_status WMID_set_capabilities(void)
 	dmi_walk(type_aa_dmi_decode, NULL);
 	if (!has_type_aa) {
 		interface->capability |= ACER_CAP_WIRELESS;
-		interface->capability |= ACER_CAP_THREEG;
+		if (devices & 0x40)
+			interface->capability |= ACER_CAP_THREEG;
 		if (devices & 0x10)
 			interface->capability |= ACER_CAP_BLUETOOTH;
 	}
@@ -961,10 +982,12 @@ static void __init acer_commandline_init(void)
 	 * These will all fail silently if the value given is invalid, or the
 	 * capability isn't available on the given interface
 	 */
-	set_u32(mailled, ACER_CAP_MAILLED);
-	if (!has_type_aa)
+	if (mailled >= 0)
+		set_u32(mailled, ACER_CAP_MAILLED);
+	if (!has_type_aa && threeg >= 0)
 		set_u32(threeg, ACER_CAP_THREEG);
-	set_u32(brightness, ACER_CAP_BRIGHTNESS);
+	if (brightness >= 0)
+		set_u32(brightness, ACER_CAP_BRIGHTNESS);
 }
 
 /*
@@ -1081,7 +1104,7 @@ static acpi_status wmid3_get_device_status(u32 *value, u16 device)
 		return AE_ERROR;
 	}
 	if (obj->buffer.length != 8) {
-		pr_warning("Unknown buffer length %d\n", obj->buffer.length);
+		pr_warn("Unknown buffer length %d\n", obj->buffer.length);
 		kfree(obj);
 		return AE_ERROR;
 	}
@@ -1090,8 +1113,8 @@ static acpi_status wmid3_get_device_status(u32 *value, u16 device)
 	kfree(obj);
 
 	if (return_value.error_code || return_value.ec_return_value)
-		pr_warning("Get Device Status failed: "
-			"0x%x - 0x%x\n", return_value.error_code,
+		pr_warn("Get Device Status failed: 0x%x - 0x%x\n",
+			return_value.error_code,
 			return_value.ec_return_value);
 	else
 		*value = !!(return_value.devices & device);
@@ -1124,6 +1147,114 @@ static acpi_status get_device_status(u32 *value, u32 cap)
 	}
 }
 
+static acpi_status wmid3_set_device_status(u32 value, u16 device)
+{
+	struct wmid3_gds_return_value return_value;
+	acpi_status status;
+	union acpi_object *obj;
+	u16 devices;
+	struct wmid3_gds_input_param params = {
+		.function_num = 0x1,
+		.hotkey_number = 0x01,
+		.devices = ACER_WMID3_GDS_WIRELESS &
+				ACER_WMID3_GDS_THREEG &
+				ACER_WMID3_GDS_WIMAX &
+				ACER_WMID3_GDS_BLUETOOTH,
+	};
+	struct acpi_buffer input = {
+		sizeof(struct wmid3_gds_input_param),
+		&params
+	};
+	struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct acpi_buffer output2 = { ACPI_ALLOCATE_BUFFER, NULL };
+
+	status = wmi_evaluate_method(WMID_GUID3, 0, 0x2, &input, &output);
+	if (ACPI_FAILURE(status))
+		return status;
+
+	obj = output.pointer;
+
+	if (!obj)
+		return AE_ERROR;
+	else if (obj->type != ACPI_TYPE_BUFFER) {
+		kfree(obj);
+		return AE_ERROR;
+	}
+	if (obj->buffer.length != 8) {
+		pr_warning("Unknown buffer length %d\n", obj->buffer.length);
+		kfree(obj);
+		return AE_ERROR;
+	}
+
+	return_value = *((struct wmid3_gds_return_value *)obj->buffer.pointer);
+	kfree(obj);
+
+	if (return_value.error_code || return_value.ec_return_value) {
+		pr_warning("Get Current Device Status failed: "
+			"0x%x - 0x%x\n", return_value.error_code,
+			return_value.ec_return_value);
+		return status;
+	}
+
+	devices = return_value.devices;
+	params.function_num = 0x2;
+	params.hotkey_number = 0x01;
+	params.devices = (value) ? (devices | device) : (devices & ~device);
+
+	status = wmi_evaluate_method(WMID_GUID3, 0, 0x1, &input, &output2);
+	if (ACPI_FAILURE(status))
+		return status;
+
+	obj = output2.pointer;
+
+	if (!obj)
+		return AE_ERROR;
+	else if (obj->type != ACPI_TYPE_BUFFER) {
+		kfree(obj);
+		return AE_ERROR;
+	}
+	if (obj->buffer.length != 4) {
+		pr_warning("Unknown buffer length %d\n", obj->buffer.length);
+		kfree(obj);
+		return AE_ERROR;
+	}
+
+	return_value = *((struct wmid3_gds_return_value *)obj->buffer.pointer);
+	kfree(obj);
+
+	if (return_value.error_code || return_value.ec_return_value)
+		pr_warning("Set Device Status failed: "
+			"0x%x - 0x%x\n", return_value.error_code,
+			return_value.ec_return_value);
+
+	return status;
+}
+
+static acpi_status set_device_status(u32 value, u32 cap)
+{
+	if (wmi_has_guid(WMID_GUID3)) {
+		u16 device;
+
+		switch (cap) {
+		case ACER_CAP_WIRELESS:
+			device = ACER_WMID3_GDS_WIRELESS;
+			break;
+		case ACER_CAP_BLUETOOTH:
+			device = ACER_WMID3_GDS_BLUETOOTH;
+			break;
+		case ACER_CAP_THREEG:
+			device = ACER_WMID3_GDS_THREEG;
+			break;
+		default:
+			return AE_ERROR;
+		}
+		return wmid3_set_device_status(value, device);
+
+	} else {
+		return set_u32(value, cap);
+	}
+}
+
 /*
  * Rfkill devices
  */
@@ -1160,7 +1291,7 @@ static int acer_rfkill_set(void *data, bool blocked)
 	u32 cap = (unsigned long)data;
 
 	if (rfkill_inited) {
-		status = set_u32(!blocked, cap);
+		status = set_device_status(!blocked, cap);
 		if (ACPI_FAILURE(status))
 			return -ENODEV;
 	}
@@ -1317,7 +1448,7 @@ static void acer_wmi_notify(u32 value, void *context)
 
 	status = wmi_get_event_data(value, &response);
 	if (status != AE_OK) {
-		pr_warning("bad event status 0x%x\n", status);
+		pr_warn("bad event status 0x%x\n", status);
 		return;
 	}
 
@@ -1326,12 +1457,12 @@ static void acer_wmi_notify(u32 value, void *context)
 	if (!obj)
 		return;
 	if (obj->type != ACPI_TYPE_BUFFER) {
-		pr_warning("Unknown response received %d\n", obj->type);
+		pr_warn("Unknown response received %d\n", obj->type);
 		kfree(obj);
 		return;
 	}
 	if (obj->buffer.length != 8) {
-		pr_warning("Unknown buffer length %d\n", obj->buffer.length);
+		pr_warn("Unknown buffer length %d\n", obj->buffer.length);
 		kfree(obj);
 		return;
 	}
@@ -1343,7 +1474,7 @@ static void acer_wmi_notify(u32 value, void *context)
 	case WMID_HOTKEY_EVENT:
 		if (return_value.device_state) {
 			u16 device_state = return_value.device_state;
-			pr_debug("deivces states: 0x%x\n", device_state);
+			pr_debug("device state: 0x%x\n", device_state);
 			if (has_cap(ACER_CAP_WIRELESS))
 				rfkill_set_sw_state(wireless_rfkill,
 				!(device_state & ACER_WMID3_GDS_WIRELESS));
@@ -1356,11 +1487,11 @@ static void acer_wmi_notify(u32 value, void *context)
 		}
 		if (!sparse_keymap_report_event(acer_wmi_input_dev,
 				return_value.key_num, 1, true))
-			pr_warning("Unknown key number - 0x%x\n",
+			pr_warn("Unknown key number - 0x%x\n",
 				return_value.key_num);
 		break;
 	default:
-		pr_warning("Unknown function number - %d - %d\n",
+		pr_warn("Unknown function number - %d - %d\n",
 			return_value.function, return_value.key_num);
 		break;
 	}
@@ -1389,7 +1520,7 @@ wmid3_set_lm_mode(struct lm_input_params *params,
 		return AE_ERROR;
 	}
 	if (obj->buffer.length != 4) {
-		pr_warning("Unknown buffer length %d\n", obj->buffer.length);
+		pr_warn("Unknown buffer length %d\n", obj->buffer.length);
 		kfree(obj);
 		return AE_ERROR;
 	}
@@ -1414,11 +1545,11 @@ static int acer_wmi_enable_ec_raw(void)
 	status = wmid3_set_lm_mode(&params, &return_value);
 
 	if (return_value.error_code || return_value.ec_return_value)
-		pr_warning("Enabling EC raw mode failed: "
-		       "0x%x - 0x%x\n", return_value.error_code,
-		       return_value.ec_return_value);
+		pr_warn("Enabling EC raw mode failed: 0x%x - 0x%x\n",
+			return_value.error_code,
+			return_value.ec_return_value);
 	else
-		pr_info("Enabled EC raw mode");
+		pr_info("Enabled EC raw mode\n");
 
 	return status;
 }
@@ -1437,9 +1568,9 @@ static int acer_wmi_enable_lm(void)
 	status = wmid3_set_lm_mode(&params, &return_value);
 
 	if (return_value.error_code || return_value.ec_return_value)
-		pr_warning("Enabling Launch Manager failed: "
-		       "0x%x - 0x%x\n", return_value.error_code,
-		       return_value.ec_return_value);
+		pr_warn("Enabling Launch Manager failed: 0x%x - 0x%x\n",
+			return_value.error_code,
+			return_value.ec_return_value);
 
 	return status;
 }
@@ -1506,8 +1637,11 @@ static u32 get_wmid_devices(void)
 
 	obj = (union acpi_object *) out.pointer;
 	if (obj && obj->type == ACPI_TYPE_BUFFER &&
-		obj->buffer.length == sizeof(u32)) {
+		(obj->buffer.length == sizeof(u32) ||
+		obj->buffer.length == sizeof(u64))) {
 		devices = *((u32 *) obj->buffer.pointer);
+	} else if (obj->type == ACPI_TYPE_INTEGER) {
+		devices = (u32) obj->integer.value;
 	}
 
 	kfree(out.pointer);
diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c
index 60f9cfcac93f..fca3489218b7 100644
--- a/drivers/platform/x86/acerhdf.c
+++ b/drivers/platform/x86/acerhdf.c
@@ -35,10 +35,8 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/fs.h>
 #include <linux/dmi.h>
-#include <acpi/acpi_drivers.h>
-#include <linux/sched.h>
+#include <linux/acpi.h>
 #include <linux/thermal.h>
 #include <linux/platform_device.h>
 
diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c
index c53b3ff7978a..d65df92e2acc 100644
--- a/drivers/platform/x86/asus-laptop.c
+++ b/drivers/platform/x86/asus-laptop.c
@@ -318,7 +318,7 @@ static int acpi_check_handle(acpi_handle handle, const char *method,
 
 	if (status != AE_OK) {
 		if (ret)
-			pr_warning("Error finding %s\n", method);
+			pr_warn("Error finding %s\n", method);
 		return -ENODEV;
 	}
 	return 0;
@@ -383,7 +383,7 @@ static int asus_kled_lvl(struct asus_laptop *asus)
 	rv = acpi_evaluate_integer(asus->handle, METHOD_KBD_LIGHT_GET,
 				   &params, &kblv);
 	if (ACPI_FAILURE(rv)) {
-		pr_warning("Error reading kled level\n");
+		pr_warn("Error reading kled level\n");
 		return -ENODEV;
 	}
 	return kblv;
@@ -397,7 +397,7 @@ static int asus_kled_set(struct asus_laptop *asus, int kblv)
 		kblv = 0;
 
 	if (write_acpi_int(asus->handle, METHOD_KBD_LIGHT_SET, kblv)) {
-		pr_warning("Keyboard LED display write failed\n");
+		pr_warn("Keyboard LED display write failed\n");
 		return -EINVAL;
 	}
 	return 0;
@@ -531,7 +531,7 @@ static int asus_read_brightness(struct backlight_device *bd)
 	rv = acpi_evaluate_integer(asus->handle, METHOD_BRIGHTNESS_GET,
 				   NULL, &value);
 	if (ACPI_FAILURE(rv))
-		pr_warning("Error reading brightness\n");
+		pr_warn("Error reading brightness\n");
 
 	return value;
 }
@@ -541,7 +541,7 @@ static int asus_set_brightness(struct backlight_device *bd, int value)
 	struct asus_laptop *asus = bl_get_data(bd);
 
 	if (write_acpi_int(asus->handle, METHOD_BRIGHTNESS_SET, value)) {
-		pr_warning("Error changing brightness\n");
+		pr_warn("Error changing brightness\n");
 		return -EIO;
 	}
 	return 0;
@@ -730,7 +730,7 @@ static ssize_t store_ledd(struct device *dev, struct device_attribute *attr,
 	rv = parse_arg(buf, count, &value);
 	if (rv > 0) {
 		if (write_acpi_int(asus->handle, METHOD_LEDD, value)) {
-			pr_warning("LED display write failed\n");
+			pr_warn("LED display write failed\n");
 			return -ENODEV;
 		}
 		asus->ledd_status = (u32) value;
@@ -752,7 +752,7 @@ static int asus_wireless_status(struct asus_laptop *asus, int mask)
 	rv = acpi_evaluate_integer(asus->handle, METHOD_WL_STATUS,
 				   NULL, &status);
 	if (ACPI_FAILURE(rv)) {
-		pr_warning("Error reading Wireless status\n");
+		pr_warn("Error reading Wireless status\n");
 		return -EINVAL;
 	}
 	return !!(status & mask);
@@ -764,7 +764,7 @@ static int asus_wireless_status(struct asus_laptop *asus, int mask)
 static int asus_wlan_set(struct asus_laptop *asus, int status)
 {
 	if (write_acpi_int(asus->handle, METHOD_WLAN, !!status)) {
-		pr_warning("Error setting wlan status to %d", status);
+		pr_warn("Error setting wlan status to %d\n", status);
 		return -EIO;
 	}
 	return 0;
@@ -792,7 +792,7 @@ static ssize_t store_wlan(struct device *dev, struct device_attribute *attr,
 static int asus_bluetooth_set(struct asus_laptop *asus, int status)
 {
 	if (write_acpi_int(asus->handle, METHOD_BLUETOOTH, !!status)) {
-		pr_warning("Error setting bluetooth status to %d", status);
+		pr_warn("Error setting bluetooth status to %d\n", status);
 		return -EIO;
 	}
 	return 0;
@@ -821,7 +821,7 @@ static ssize_t store_bluetooth(struct device *dev,
 static int asus_wimax_set(struct asus_laptop *asus, int status)
 {
 	if (write_acpi_int(asus->handle, METHOD_WIMAX, !!status)) {
-		pr_warning("Error setting wimax status to %d", status);
+		pr_warn("Error setting wimax status to %d\n", status);
 		return -EIO;
 	}
 	return 0;
@@ -850,7 +850,7 @@ static ssize_t store_wimax(struct device *dev,
 static int asus_wwan_set(struct asus_laptop *asus, int status)
 {
 	if (write_acpi_int(asus->handle, METHOD_WWAN, !!status)) {
-		pr_warning("Error setting wwan status to %d", status);
+		pr_warn("Error setting wwan status to %d\n", status);
 		return -EIO;
 	}
 	return 0;
@@ -880,7 +880,7 @@ static void asus_set_display(struct asus_laptop *asus, int value)
 {
 	/* no sanity check needed for now */
 	if (write_acpi_int(asus->handle, METHOD_SWITCH_DISPLAY, value))
-		pr_warning("Error setting display\n");
+		pr_warn("Error setting display\n");
 	return;
 }
 
@@ -909,7 +909,7 @@ static ssize_t store_disp(struct device *dev, struct device_attribute *attr,
 static void asus_als_switch(struct asus_laptop *asus, int value)
 {
 	if (write_acpi_int(asus->handle, METHOD_ALS_CONTROL, value))
-		pr_warning("Error setting light sensor switch\n");
+		pr_warn("Error setting light sensor switch\n");
 	asus->light_switch = value;
 }
 
@@ -937,7 +937,7 @@ static ssize_t store_lssw(struct device *dev, struct device_attribute *attr,
 static void asus_als_level(struct asus_laptop *asus, int value)
 {
 	if (write_acpi_int(asus->handle, METHOD_ALS_LEVEL, value))
-		pr_warning("Error setting light sensor level\n");
+		pr_warn("Error setting light sensor level\n");
 	asus->light_level = value;
 }
 
@@ -976,7 +976,7 @@ static int asus_gps_status(struct asus_laptop *asus)
 	rv = acpi_evaluate_integer(asus->handle, METHOD_GPS_STATUS,
 				   NULL, &status);
 	if (ACPI_FAILURE(rv)) {
-		pr_warning("Error reading GPS status\n");
+		pr_warn("Error reading GPS status\n");
 		return -ENODEV;
 	}
 	return !!status;
@@ -1284,7 +1284,7 @@ static int asus_laptop_get_info(struct asus_laptop *asus)
 	 */
 	status = acpi_get_table(ACPI_SIG_DSDT, 1, &asus->dsdt_info);
 	if (ACPI_FAILURE(status))
-		pr_warning("Couldn't get the DSDT table header\n");
+		pr_warn("Couldn't get the DSDT table header\n");
 
 	/* We have to write 0 on init this far for all ASUS models */
 	if (write_acpi_int_ret(asus->handle, "INIT", 0, &buffer)) {
@@ -1296,7 +1296,7 @@ static int asus_laptop_get_info(struct asus_laptop *asus)
 	status =
 	    acpi_evaluate_integer(asus->handle, "BSTS", NULL, &bsts_result);
 	if (ACPI_FAILURE(status))
-		pr_warning("Error calling BSTS\n");
+		pr_warn("Error calling BSTS\n");
 	else if (bsts_result)
 		pr_notice("BSTS called, 0x%02x returned\n",
 		       (uint) bsts_result);
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 832a3fd7c1c8..00460cb9587b 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -425,7 +425,7 @@ static void asus_rfkill_hotplug(struct asus_wmi *asus)
 	if (asus->hotplug_slot) {
 		bus = pci_find_bus(0, 1);
 		if (!bus) {
-			pr_warning("Unable to find PCI bus 1?\n");
+			pr_warn("Unable to find PCI bus 1?\n");
 			goto out_unlock;
 		}
 
@@ -436,12 +436,12 @@ static void asus_rfkill_hotplug(struct asus_wmi *asus)
 		absent = (l == 0xffffffff);
 
 		if (blocked != absent) {
-			pr_warning("BIOS says wireless lan is %s, "
-				   "but the pci device is %s\n",
-				   blocked ? "blocked" : "unblocked",
-				   absent ? "absent" : "present");
-			pr_warning("skipped wireless hotplug as probably "
-				   "inappropriate for this model\n");
+			pr_warn("BIOS says wireless lan is %s, "
+				"but the pci device is %s\n",
+				blocked ? "blocked" : "unblocked",
+				absent ? "absent" : "present");
+			pr_warn("skipped wireless hotplug as probably "
+				"inappropriate for this model\n");
 			goto out_unlock;
 		}
 
@@ -500,7 +500,7 @@ static int asus_register_rfkill_notifier(struct asus_wmi *asus, char *node)
 						     ACPI_SYSTEM_NOTIFY,
 						     asus_rfkill_notify, asus);
 		if (ACPI_FAILURE(status))
-			pr_warning("Failed to register notify on %s\n", node);
+			pr_warn("Failed to register notify on %s\n", node);
 	} else
 		return -ENODEV;
 
@@ -1223,7 +1223,7 @@ static int asus_wmi_sysfs_init(struct platform_device *device)
 /*
  * Platform device
  */
-static int __init asus_wmi_platform_init(struct asus_wmi *asus)
+static int asus_wmi_platform_init(struct asus_wmi *asus)
 {
 	int rv;
 
@@ -1583,12 +1583,12 @@ static int asus_wmi_probe(struct platform_device *pdev)
 	int ret;
 
 	if (!wmi_has_guid(ASUS_WMI_MGMT_GUID)) {
-		pr_warning("Management GUID not found\n");
+		pr_warn("Management GUID not found\n");
 		return -ENODEV;
 	}
 
 	if (wdrv->event_guid && !wmi_has_guid(wdrv->event_guid)) {
-		pr_warning("Event GUID not found\n");
+		pr_warn("Event GUID not found\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/platform/x86/asus_acpi.c b/drivers/platform/x86/asus_acpi.c
index f503607c0645..d9312b3073e5 100644
--- a/drivers/platform/x86/asus_acpi.c
+++ b/drivers/platform/x86/asus_acpi.c
@@ -30,6 +30,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -581,8 +583,7 @@ static int read_led(const char *ledname, int ledmask)
 		if (read_acpi_int(NULL, ledname, &led_status))
 			return led_status;
 		else
-			printk(KERN_WARNING "Asus ACPI: Error reading LED "
-			       "status\n");
+			pr_warn("Error reading LED status\n");
 	}
 	return (hotk->status & ledmask) ? 1 : 0;
 }
@@ -621,8 +622,7 @@ write_led(const char __user *buffer, unsigned long count,
 		led_out = !led_out;
 
 	if (!write_acpi_int(hotk->handle, ledname, led_out, NULL))
-		printk(KERN_WARNING "Asus ACPI: LED (%s) write failed\n",
-		       ledname);
+		pr_warn("LED (%s) write failed\n", ledname);
 
 	return rv;
 }
@@ -679,8 +679,7 @@ static ssize_t ledd_proc_write(struct file *file, const char __user *buffer,
 	if (rv > 0) {
 		if (!write_acpi_int
 		    (hotk->handle, hotk->methods->mt_ledd, value, NULL))
-			printk(KERN_WARNING
-			       "Asus ACPI: LED display write failed\n");
+			pr_warn("LED display write failed\n");
 		else
 			hotk->ledd_status = (u32) value;
 	}
@@ -838,8 +837,7 @@ static int get_lcd_state(void)
 	} else {
 		/* We don't have to check anything if we are here */
 		if (!read_acpi_int(NULL, hotk->methods->lcd_status, &lcd))
-			printk(KERN_WARNING
-			       "Asus ACPI: Error reading LCD status\n");
+			pr_warn("Error reading LCD status\n");
 
 		if (hotk->model == L2D)
 			lcd = ~lcd;
@@ -871,7 +869,7 @@ static int set_lcd_state(int value)
 			   the exact behaviour is simulated here */
 		}
 		if (ACPI_FAILURE(status))
-			printk(KERN_WARNING "Asus ACPI: Error switching LCD\n");
+			pr_warn("Error switching LCD\n");
 	}
 	return 0;
 
@@ -915,13 +913,11 @@ static int read_brightness(struct backlight_device *bd)
 	if (hotk->methods->brightness_get) {	/* SPLV/GPLV laptop */
 		if (!read_acpi_int(hotk->handle, hotk->methods->brightness_get,
 				   &value))
-			printk(KERN_WARNING
-			       "Asus ACPI: Error reading brightness\n");
+			pr_warn("Error reading brightness\n");
 	} else if (hotk->methods->brightness_status) {	/* For D1 for example */
 		if (!read_acpi_int(NULL, hotk->methods->brightness_status,
 				   &value))
-			printk(KERN_WARNING
-			       "Asus ACPI: Error reading brightness\n");
+			pr_warn("Error reading brightness\n");
 	} else			/* No GPLV method */
 		value = hotk->brightness;
 	return value;
@@ -939,8 +935,7 @@ static int set_brightness(int value)
 	if (hotk->methods->brightness_set) {
 		if (!write_acpi_int(hotk->handle, hotk->methods->brightness_set,
 				    value, NULL)) {
-			printk(KERN_WARNING
-			       "Asus ACPI: Error changing brightness\n");
+			pr_warn("Error changing brightness\n");
 			ret = -EIO;
 		}
 		goto out;
@@ -955,8 +950,7 @@ static int set_brightness(int value)
 					      NULL, NULL);
 		(value > 0) ? value-- : value++;
 		if (ACPI_FAILURE(status)) {
-			printk(KERN_WARNING
-			       "Asus ACPI: Error changing brightness\n");
+			pr_warn("Error changing brightness\n");
 			ret = -EIO;
 		}
 	}
@@ -1008,7 +1002,7 @@ static void set_display(int value)
 	/* no sanity check needed for now */
 	if (!write_acpi_int(hotk->handle, hotk->methods->display_set,
 			    value, NULL))
-		printk(KERN_WARNING "Asus ACPI: Error setting display\n");
+		pr_warn("Error setting display\n");
 	return;
 }
 
@@ -1021,8 +1015,7 @@ static int disp_proc_show(struct seq_file *m, void *v)
 	int value = 0;
 
 	if (!read_acpi_int(hotk->handle, hotk->methods->display_get, &value))
-		printk(KERN_WARNING
-		       "Asus ACPI: Error reading display status\n");
+		pr_warn("Error reading display status\n");
 	value &= 0x07;	/* needed for some models, shouldn't hurt others */
 	seq_printf(m, "%d\n", value);
 	return 0;
@@ -1068,7 +1061,7 @@ asus_proc_add(char *name, const struct file_operations *proc_fops, mode_t mode,
 	proc = proc_create_data(name, mode, acpi_device_dir(device),
 				proc_fops, acpi_driver_data(device));
 	if (!proc) {
-		printk(KERN_WARNING "  Unable to create %s fs entry\n", name);
+		pr_warn("  Unable to create %s fs entry\n", name);
 		return -1;
 	}
 	proc->uid = asus_uid;
@@ -1085,8 +1078,8 @@ static int asus_hotk_add_fs(struct acpi_device *device)
 		mode = S_IFREG | S_IRUGO | S_IWUSR | S_IWGRP;
 	} else {
 		mode = S_IFREG | S_IRUSR | S_IRGRP | S_IWUSR | S_IWGRP;
-		printk(KERN_WARNING "  asus_uid and asus_gid parameters are "
-		       "deprecated, use chown and chmod instead!\n");
+		pr_warn("  asus_uid and asus_gid parameters are "
+			"deprecated, use chown and chmod instead!\n");
 	}
 
 	acpi_device_dir(device) = asus_proc_dir;
@@ -1099,8 +1092,7 @@ static int asus_hotk_add_fs(struct acpi_device *device)
 		proc->uid = asus_uid;
 		proc->gid = asus_gid;
 	} else {
-		printk(KERN_WARNING "  Unable to create " PROC_INFO
-		       " fs entry\n");
+		pr_warn("  Unable to create " PROC_INFO " fs entry\n");
 	}
 
 	if (hotk->methods->mt_wled) {
@@ -1283,20 +1275,19 @@ static int asus_hotk_get_info(void)
 	 */
 	status = acpi_get_table(ACPI_SIG_DSDT, 1, &asus_info);
 	if (ACPI_FAILURE(status))
-		printk(KERN_WARNING "  Couldn't get the DSDT table header\n");
+		pr_warn("  Couldn't get the DSDT table header\n");
 
 	/* We have to write 0 on init this far for all ASUS models */
 	if (!write_acpi_int(hotk->handle, "INIT", 0, &buffer)) {
-		printk(KERN_ERR "  Hotkey initialization failed\n");
+		pr_err("  Hotkey initialization failed\n");
 		return -ENODEV;
 	}
 
 	/* This needs to be called for some laptops to init properly */
 	if (!read_acpi_int(hotk->handle, "BSTS", &bsts_result))
-		printk(KERN_WARNING "  Error calling BSTS\n");
+		pr_warn("  Error calling BSTS\n");
 	else if (bsts_result)
-		printk(KERN_NOTICE "  BSTS called, 0x%02x returned\n",
-		       bsts_result);
+		pr_notice("  BSTS called, 0x%02x returned\n", bsts_result);
 
 	/*
 	 * Try to match the object returned by INIT to the specific model.
@@ -1324,23 +1315,21 @@ static int asus_hotk_get_info(void)
 		if (asus_info &&
 		    strncmp(asus_info->oem_table_id, "ODEM", 4) == 0) {
 			hotk->model = P30;
-			printk(KERN_NOTICE
-			       "  Samsung P30 detected, supported\n");
+			pr_notice("  Samsung P30 detected, supported\n");
 			hotk->methods = &model_conf[hotk->model];
 			kfree(model);
 			return 0;
 		} else {
 			hotk->model = M2E;
-			printk(KERN_NOTICE "  unsupported model %s, trying "
-			       "default values\n", string);
-			printk(KERN_NOTICE
-			       "  send /proc/acpi/dsdt to the developers\n");
+			pr_notice("  unsupported model %s, trying default values\n",
+				  string);
+			pr_notice("  send /proc/acpi/dsdt to the developers\n");
 			kfree(model);
 			return -ENODEV;
 		}
 	}
 	hotk->methods = &model_conf[hotk->model];
-	printk(KERN_NOTICE "  %s model detected, supported\n", string);
+	pr_notice("  %s model detected, supported\n", string);
 
 	/* Sort of per-model blacklist */
 	if (strncmp(string, "L2B", 3) == 0)
@@ -1385,7 +1374,7 @@ static int asus_hotk_check(void)
 	if (hotk->device->status.present) {
 		result = asus_hotk_get_info();
 	} else {
-		printk(KERN_ERR "  Hotkey device not present, aborting\n");
+		pr_err("  Hotkey device not present, aborting\n");
 		return -EINVAL;
 	}
 
@@ -1399,8 +1388,7 @@ static int asus_hotk_add(struct acpi_device *device)
 	acpi_status status = AE_OK;
 	int result;
 
-	printk(KERN_NOTICE "Asus Laptop ACPI Extras version %s\n",
-	       ASUS_ACPI_VERSION);
+	pr_notice("Asus Laptop ACPI Extras version %s\n", ASUS_ACPI_VERSION);
 
 	hotk = kzalloc(sizeof(struct asus_hotk), GFP_KERNEL);
 	if (!hotk)
@@ -1428,15 +1416,14 @@ static int asus_hotk_add(struct acpi_device *device)
 		    acpi_evaluate_object(NULL, hotk->methods->brightness_down,
 					 NULL, NULL);
 		if (ACPI_FAILURE(status))
-			printk(KERN_WARNING "  Error changing brightness\n");
+			pr_warn("  Error changing brightness\n");
 		else {
 			status =
 			    acpi_evaluate_object(NULL,
 						 hotk->methods->brightness_up,
 						 NULL, NULL);
 			if (ACPI_FAILURE(status))
-				printk(KERN_WARNING "  Strange, error changing"
-				       " brightness\n");
+				pr_warn("  Strange, error changing brightness\n");
 		}
 	}
 
@@ -1488,7 +1475,7 @@ static int __init asus_acpi_init(void)
 
 	asus_proc_dir = proc_mkdir(PROC_ASUS, acpi_root_dir);
 	if (!asus_proc_dir) {
-		printk(KERN_ERR "Asus ACPI: Unable to create /proc entry\n");
+		pr_err("Unable to create /proc entry\n");
 		acpi_bus_unregister_driver(&asus_hotk_driver);
 		return -ENODEV;
 	}
@@ -1513,7 +1500,7 @@ static int __init asus_acpi_init(void)
 							  &asus_backlight_data,
 							  &props);
 	if (IS_ERR(asus_backlight_device)) {
-		printk(KERN_ERR "Could not register asus backlight device\n");
+		pr_err("Could not register asus backlight device\n");
 		asus_backlight_device = NULL;
 		asus_acpi_exit();
 		return -ENODEV;
diff --git a/drivers/platform/x86/compal-laptop.c b/drivers/platform/x86/compal-laptop.c
index c16a27641ced..3f204fde1b02 100644
--- a/drivers/platform/x86/compal-laptop.c
+++ b/drivers/platform/x86/compal-laptop.c
@@ -68,6 +68,8 @@
  * only enabled on a JHL90 board until it is verified that they work on the
  * other boards too.  See the extra_features variable. */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -200,8 +202,8 @@ static bool extra_features;
  * watching the output of address 0x4F (do an ec_transaction writing 0x33
  * into 0x4F and read a few bytes from the output, like so:
  *	u8 writeData = 0x33;
- *	ec_transaction(0x4F, &writeData, 1, buffer, 32, 0);
- * That address is labelled "fan1 table information" in the service manual.
+ *	ec_transaction(0x4F, &writeData, 1, buffer, 32);
+ * That address is labeled "fan1 table information" in the service manual.
  * It should be clear which value in 'buffer' changes). This seems to be
  * related to fan speed. It isn't a proper 'realtime' fan speed value
  * though, because physically stopping or speeding up the fan doesn't
@@ -286,7 +288,7 @@ static int get_backlight_level(void)
 static void set_backlight_state(bool on)
 {
 	u8 data = on ? BACKLIGHT_STATE_ON_DATA : BACKLIGHT_STATE_OFF_DATA;
-	ec_transaction(BACKLIGHT_STATE_ADDR, &data, 1, NULL, 0, 0);
+	ec_transaction(BACKLIGHT_STATE_ADDR, &data, 1, NULL, 0);
 }
 
 
@@ -294,24 +296,24 @@ static void set_backlight_state(bool on)
 static void pwm_enable_control(void)
 {
 	unsigned char writeData = PWM_ENABLE_DATA;
-	ec_transaction(PWM_ENABLE_ADDR, &writeData, 1, NULL, 0, 0);
+	ec_transaction(PWM_ENABLE_ADDR, &writeData, 1, NULL, 0);
 }
 
 static void pwm_disable_control(void)
 {
 	unsigned char writeData = PWM_DISABLE_DATA;
-	ec_transaction(PWM_DISABLE_ADDR, &writeData, 1, NULL, 0, 0);
+	ec_transaction(PWM_DISABLE_ADDR, &writeData, 1, NULL, 0);
 }
 
 static void set_pwm(int pwm)
 {
-	ec_transaction(PWM_ADDRESS, &pwm_lookup_table[pwm], 1, NULL, 0, 0);
+	ec_transaction(PWM_ADDRESS, &pwm_lookup_table[pwm], 1, NULL, 0);
 }
 
 static int get_fan_rpm(void)
 {
 	u8 value, data = FAN_DATA;
-	ec_transaction(FAN_ADDRESS, &data, 1, &value, 1, 0);
+	ec_transaction(FAN_ADDRESS, &data, 1, &value, 1);
 	return 100 * (int)value;
 }
 
@@ -760,16 +762,14 @@ static struct rfkill *bt_rfkill;
 
 static int dmi_check_cb(const struct dmi_system_id *id)
 {
-	printk(KERN_INFO DRIVER_NAME": Identified laptop model '%s'\n",
-		id->ident);
+	pr_info("Identified laptop model '%s'\n", id->ident);
 	extra_features = false;
 	return 1;
 }
 
 static int dmi_check_cb_extra(const struct dmi_system_id *id)
 {
-	printk(KERN_INFO DRIVER_NAME": Identified laptop model '%s', "
-		"enabling extra features\n",
+	pr_info("Identified laptop model '%s', enabling extra features\n",
 		id->ident);
 	extra_features = true;
 	return 1;
@@ -956,14 +956,12 @@ static int __init compal_init(void)
 	int ret;
 
 	if (acpi_disabled) {
-		printk(KERN_ERR DRIVER_NAME": ACPI needs to be enabled for "
-						"this driver to work!\n");
+		pr_err("ACPI needs to be enabled for this driver to work!\n");
 		return -ENODEV;
 	}
 
 	if (!force && !dmi_check_system(compal_dmi_table)) {
-		printk(KERN_ERR DRIVER_NAME": Motherboard not recognized (You "
-				"could try the module's force-parameter)");
+		pr_err("Motherboard not recognized (You could try the module's force-parameter)\n");
 		return -ENODEV;
 	}
 
@@ -998,8 +996,7 @@ static int __init compal_init(void)
 	if (ret)
 		goto err_rfkill;
 
-	printk(KERN_INFO DRIVER_NAME": Driver "DRIVER_VERSION
-						" successfully loaded\n");
+	pr_info("Driver " DRIVER_VERSION " successfully loaded\n");
 	return 0;
 
 err_rfkill:
@@ -1064,7 +1061,7 @@ static void __exit compal_cleanup(void)
 	rfkill_destroy(wifi_rfkill);
 	rfkill_destroy(bt_rfkill);
 
-	printk(KERN_INFO DRIVER_NAME": Driver unloaded\n");
+	pr_info("Driver unloaded\n");
 }
 
 static int __devexit compal_remove(struct platform_device *pdev)
@@ -1074,8 +1071,7 @@ static int __devexit compal_remove(struct platform_device *pdev)
 	if (!extra_features)
 		return 0;
 
-	printk(KERN_INFO DRIVER_NAME": Unloading: resetting fan control "
-							"to motherboard\n");
+	pr_info("Unloading: resetting fan control to motherboard\n");
 	pwm_disable_control();
 
 	data = platform_get_drvdata(pdev);
diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c
index de301aa8e5c3..d3841de6a8cf 100644
--- a/drivers/platform/x86/dell-laptop.c
+++ b/drivers/platform/x86/dell-laptop.c
@@ -11,6 +11,8 @@
  *  published by the Free Software Foundation.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -434,8 +436,7 @@ static int __init dell_setup_rfkill(void)
 	int ret;
 
 	if (dmi_check_system(dell_blacklist)) {
-		printk(KERN_INFO "dell-laptop: Blacklisted hardware detected - "
-				"not enabling rfkill\n");
+		pr_info("Blacklisted hardware detected - not enabling rfkill\n");
 		return 0;
 	}
 
@@ -606,7 +607,7 @@ static int __init dell_init(void)
 	dmi_walk(find_tokens, NULL);
 
 	if (!da_tokens)  {
-		printk(KERN_INFO "dell-laptop: Unable to find dmi tokens\n");
+		pr_info("Unable to find dmi tokens\n");
 		return -ENODEV;
 	}
 
@@ -636,14 +637,13 @@ static int __init dell_init(void)
 	ret = dell_setup_rfkill();
 
 	if (ret) {
-		printk(KERN_WARNING "dell-laptop: Unable to setup rfkill\n");
+		pr_warn("Unable to setup rfkill\n");
 		goto fail_rfkill;
 	}
 
 	ret = i8042_install_filter(dell_laptop_i8042_filter);
 	if (ret) {
-		printk(KERN_WARNING
-		       "dell-laptop: Unable to install key filter\n");
+		pr_warn("Unable to install key filter\n");
 		goto fail_filter;
 	}
 
diff --git a/drivers/platform/x86/dell-wmi-aio.c b/drivers/platform/x86/dell-wmi-aio.c
index 0ed84573ae1f..3f945457f71c 100644
--- a/drivers/platform/x86/dell-wmi-aio.c
+++ b/drivers/platform/x86/dell-wmi-aio.c
@@ -15,6 +15,7 @@
  *  along with this program; if not, write to the Free Software
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
+
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
@@ -138,7 +139,7 @@ static int __init dell_wmi_aio_init(void)
 
 	guid = dell_wmi_aio_find();
 	if (!guid) {
-		pr_warning("No known WMI GUID found\n");
+		pr_warn("No known WMI GUID found\n");
 		return -ENXIO;
 	}
 
diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c
index 77f1d55414c6..ce790827e199 100644
--- a/drivers/platform/x86/dell-wmi.c
+++ b/drivers/platform/x86/dell-wmi.c
@@ -23,6 +23,8 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -141,7 +143,7 @@ static void dell_wmi_notify(u32 value, void *context)
 
 	status = wmi_get_event_data(value, &response);
 	if (status != AE_OK) {
-		printk(KERN_INFO "dell-wmi: bad event status 0x%x\n", status);
+		pr_info("bad event status 0x%x\n", status);
 		return;
 	}
 
@@ -153,8 +155,8 @@ static void dell_wmi_notify(u32 value, void *context)
 		u16 *buffer_entry = (u16 *)obj->buffer.pointer;
 
 		if (dell_new_hk_type && (buffer_entry[1] != 0x10)) {
-			printk(KERN_INFO "dell-wmi: Received unknown WMI event"
-					 " (0x%x)\n", buffer_entry[1]);
+			pr_info("Received unknown WMI event (0x%x)\n",
+				buffer_entry[1]);
 			kfree(obj);
 			return;
 		}
@@ -167,8 +169,7 @@ static void dell_wmi_notify(u32 value, void *context)
 		key = sparse_keymap_entry_from_scancode(dell_wmi_input_dev,
 							reported_key);
 		if (!key) {
-			printk(KERN_INFO "dell-wmi: Unknown key %x pressed\n",
-				reported_key);
+			pr_info("Unknown key %x pressed\n", reported_key);
 		} else if ((key->keycode == KEY_BRIGHTNESSUP ||
 			    key->keycode == KEY_BRIGHTNESSDOWN) && acpi_video) {
 			/* Don't report brightness notifications that will also
@@ -275,7 +276,7 @@ static int __init dell_wmi_init(void)
 	acpi_status status;
 
 	if (!wmi_has_guid(DELL_EVENT_GUID)) {
-		printk(KERN_WARNING "dell-wmi: No known WMI GUID found\n");
+		pr_warn("No known WMI GUID found\n");
 		return -ENODEV;
 	}
 
@@ -290,9 +291,7 @@ static int __init dell_wmi_init(void)
 					 dell_wmi_notify, NULL);
 	if (ACPI_FAILURE(status)) {
 		dell_wmi_input_destroy();
-		printk(KERN_ERR
-			"dell-wmi: Unable to register notify handler - %d\n",
-			status);
+		pr_err("Unable to register notify handler - %d\n", status);
 		return -ENODEV;
 	}
 
diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c
index 2c1abf63957f..1c45d92e2163 100644
--- a/drivers/platform/x86/eeepc-laptop.c
+++ b/drivers/platform/x86/eeepc-laptop.c
@@ -228,7 +228,7 @@ static int set_acpi(struct eeepc_laptop *eeepc, int cm, int value)
 		return -ENODEV;
 
 	if (write_acpi_int(eeepc->handle, method, value))
-		pr_warning("Error writing %s\n", method);
+		pr_warn("Error writing %s\n", method);
 	return 0;
 }
 
@@ -243,7 +243,7 @@ static int get_acpi(struct eeepc_laptop *eeepc, int cm)
 		return -ENODEV;
 
 	if (read_acpi_int(eeepc->handle, method, &value))
-		pr_warning("Error reading %s\n", method);
+		pr_warn("Error reading %s\n", method);
 	return value;
 }
 
@@ -261,7 +261,7 @@ static int acpi_setter_handle(struct eeepc_laptop *eeepc, int cm,
 	status = acpi_get_handle(eeepc->handle, (char *)method,
 				 handle);
 	if (status != AE_OK) {
-		pr_warning("Error finding %s\n", method);
+		pr_warn("Error finding %s\n", method);
 		return -ENODEV;
 	}
 	return 0;
@@ -417,7 +417,7 @@ static ssize_t store_cpufv_disabled(struct device *dev,
 	switch (value) {
 	case 0:
 		if (eeepc->cpufv_disabled)
-			pr_warning("cpufv enabled (not officially supported "
+			pr_warn("cpufv enabled (not officially supported "
 				"on this model)\n");
 		eeepc->cpufv_disabled = false;
 		return rv;
@@ -609,7 +609,7 @@ static void eeepc_rfkill_hotplug(struct eeepc_laptop *eeepc, acpi_handle handle)
 		bus = port->subordinate;
 
 		if (!bus) {
-			pr_warning("Unable to find PCI bus?\n");
+			pr_warn("Unable to find PCI bus 1?\n");
 			goto out_unlock;
 		}
 
@@ -621,12 +621,12 @@ static void eeepc_rfkill_hotplug(struct eeepc_laptop *eeepc, acpi_handle handle)
 		absent = (l == 0xffffffff);
 
 		if (blocked != absent) {
-			pr_warning("BIOS says wireless lan is %s, "
-					"but the pci device is %s\n",
+			pr_warn("BIOS says wireless lan is %s, "
+				"but the pci device is %s\n",
 				blocked ? "blocked" : "unblocked",
 				absent ? "absent" : "present");
-			pr_warning("skipped wireless hotplug as probably "
-					"inappropriate for this model\n");
+			pr_warn("skipped wireless hotplug as probably "
+				"inappropriate for this model\n");
 			goto out_unlock;
 		}
 
@@ -691,7 +691,8 @@ static int eeepc_register_rfkill_notifier(struct eeepc_laptop *eeepc,
 						     eeepc_rfkill_notify,
 						     eeepc);
 		if (ACPI_FAILURE(status))
-			pr_warning("Failed to register notify on %s\n", node);
+			pr_warn("Failed to register notify on %s\n", node);
+
 		/*
 		 * Refresh pci hotplug in case the rfkill state was
 		 * changed during setup.
diff --git a/drivers/platform/x86/eeepc-wmi.c b/drivers/platform/x86/eeepc-wmi.c
index 649dcadd8ea3..4aa867a9b88b 100644
--- a/drivers/platform/x86/eeepc-wmi.c
+++ b/drivers/platform/x86/eeepc-wmi.c
@@ -84,7 +84,7 @@ static const struct key_entry eeepc_wmi_keymap[] = {
 static acpi_status eeepc_wmi_parse_device(acpi_handle handle, u32 level,
 						 void *context, void **retval)
 {
-	pr_warning("Found legacy ATKD device (%s)", EEEPC_ACPI_HID);
+	pr_warn("Found legacy ATKD device (%s)\n", EEEPC_ACPI_HID);
 	*(bool *)context = true;
 	return AE_CTRL_TERMINATE;
 }
@@ -105,12 +105,12 @@ static int eeepc_wmi_check_atkd(void)
 static int eeepc_wmi_probe(struct platform_device *pdev)
 {
 	if (eeepc_wmi_check_atkd()) {
-		pr_warning("WMI device present, but legacy ATKD device is also "
-			   "present and enabled.");
-		pr_warning("You probably booted with acpi_osi=\"Linux\" or "
-			   "acpi_osi=\"!Windows 2009\"");
-		pr_warning("Can't load eeepc-wmi, use default acpi_osi "
-			   "(preferred) or eeepc-laptop");
+		pr_warn("WMI device present, but legacy ATKD device is also "
+			"present and enabled\n");
+		pr_warn("You probably booted with acpi_osi=\"Linux\" or "
+			"acpi_osi=\"!Windows 2009\"\n");
+		pr_warn("Can't load eeepc-wmi, use default acpi_osi "
+			"(preferred) or eeepc-laptop\n");
 		return -EBUSY;
 	}
 	return 0;
diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c
index 493054c2dbe1..6b26666b37f2 100644
--- a/drivers/platform/x86/fujitsu-laptop.c
+++ b/drivers/platform/x86/fujitsu-laptop.c
@@ -56,6 +56,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -585,8 +587,7 @@ static struct platform_driver fujitsupf_driver = {
 static void dmi_check_cb_common(const struct dmi_system_id *id)
 {
 	acpi_handle handle;
-	printk(KERN_INFO "fujitsu-laptop: Identified laptop model '%s'.\n",
-	       id->ident);
+	pr_info("Identified laptop model '%s'\n", id->ident);
 	if (use_alt_lcd_levels == -1) {
 		if (ACPI_SUCCESS(acpi_get_handle(NULL,
 				"\\_SB.PCI0.LPCB.FJEX.SBL2", &handle)))
@@ -691,11 +692,11 @@ static int acpi_fujitsu_add(struct acpi_device *device)
 
 	result = acpi_bus_update_power(fujitsu->acpi_handle, &state);
 	if (result) {
-		printk(KERN_ERR "Error reading power state\n");
+		pr_err("Error reading power state\n");
 		goto err_unregister_input_dev;
 	}
 
-	printk(KERN_INFO "ACPI: %s [%s] (%s)\n",
+	pr_info("ACPI: %s [%s] (%s)\n",
 	       acpi_device_name(device), acpi_device_bid(device),
 	       !device->power.state ? "on" : "off");
 
@@ -707,7 +708,7 @@ static int acpi_fujitsu_add(struct acpi_device *device)
 		if (ACPI_FAILURE
 		    (acpi_evaluate_object
 		     (device->handle, METHOD_NAME__INI, NULL, NULL)))
-			printk(KERN_ERR "_INI Method failed\n");
+			pr_err("_INI Method failed\n");
 	}
 
 	/* do config (detect defaults) */
@@ -827,7 +828,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 	error = kfifo_alloc(&fujitsu_hotkey->fifo, RINGBUFFERSIZE * sizeof(int),
 			GFP_KERNEL);
 	if (error) {
-		printk(KERN_ERR "kfifo_alloc failed\n");
+		pr_err("kfifo_alloc failed\n");
 		goto err_stop;
 	}
 
@@ -859,13 +860,13 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 
 	result = acpi_bus_update_power(fujitsu_hotkey->acpi_handle, &state);
 	if (result) {
-		printk(KERN_ERR "Error reading power state\n");
+		pr_err("Error reading power state\n");
 		goto err_unregister_input_dev;
 	}
 
-	printk(KERN_INFO "ACPI: %s [%s] (%s)\n",
-	       acpi_device_name(device), acpi_device_bid(device),
-	       !device->power.state ? "on" : "off");
+	pr_info("ACPI: %s [%s] (%s)\n",
+		acpi_device_name(device), acpi_device_bid(device),
+		!device->power.state ? "on" : "off");
 
 	fujitsu_hotkey->dev = device;
 
@@ -875,7 +876,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 		if (ACPI_FAILURE
 		    (acpi_evaluate_object
 		     (device->handle, METHOD_NAME__INI, NULL, NULL)))
-			printk(KERN_ERR "_INI Method failed\n");
+			pr_err("_INI Method failed\n");
 	}
 
 	i = 0;
@@ -897,8 +898,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 			call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0);
 
 	/* Suspect this is a keymap of the application panel, print it */
-	printk(KERN_INFO "fujitsu-laptop: BTNI: [0x%x]\n",
-		call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0));
+	pr_info("BTNI: [0x%x]\n", call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0));
 
 #if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
 	if (call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & LOGOLAMP_POWERON) {
@@ -907,8 +907,8 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 		if (result == 0) {
 			fujitsu_hotkey->logolamp_registered = 1;
 		} else {
-			printk(KERN_ERR "fujitsu-laptop: Could not register "
-			"LED handler for logo lamp, error %i\n", result);
+			pr_err("Could not register LED handler for logo lamp, error %i\n",
+			       result);
 		}
 	}
 
@@ -919,8 +919,8 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 		if (result == 0) {
 			fujitsu_hotkey->kblamps_registered = 1;
 		} else {
-			printk(KERN_ERR "fujitsu-laptop: Could not register "
-			"LED handler for keyboard lamps, error %i\n", result);
+			pr_err("Could not register LED handler for keyboard lamps, error %i\n",
+			       result);
 		}
 	}
 #endif
@@ -1169,8 +1169,7 @@ static int __init fujitsu_init(void)
 			fujitsu->bl_device->props.power = 0;
 	}
 
-	printk(KERN_INFO "fujitsu-laptop: driver " FUJITSU_DRIVER_VERSION
-	       " successfully loaded.\n");
+	pr_info("driver " FUJITSU_DRIVER_VERSION " successfully loaded\n");
 
 	return 0;
 
@@ -1216,7 +1215,7 @@ static void __exit fujitsu_cleanup(void)
 
 	kfree(fujitsu);
 
-	printk(KERN_INFO "fujitsu-laptop: driver unloaded.\n");
+	pr_info("driver unloaded\n");
 }
 
 module_init(fujitsu_init);
diff --git a/drivers/platform/x86/hdaps.c b/drivers/platform/x86/hdaps.c
index 067bf36d32f3..5a34973dc164 100644
--- a/drivers/platform/x86/hdaps.c
+++ b/drivers/platform/x86/hdaps.c
@@ -26,6 +26,8 @@
  * 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/input-polldev.h>
@@ -238,7 +240,7 @@ static int hdaps_device_init(void)
 		     __check_latch(0x1611, 0x01))
 		goto out;
 
-	printk(KERN_DEBUG "hdaps: initial latch check good (0x%02x).\n",
+	printk(KERN_DEBUG "hdaps: initial latch check good (0x%02x)\n",
 	       __get_latch(0x1611));
 
 	outb(0x17, 0x1610);
@@ -299,7 +301,7 @@ static int hdaps_probe(struct platform_device *dev)
 	if (ret)
 		return ret;
 
-	printk(KERN_INFO "hdaps: device successfully initialized.\n");
+	pr_info("device successfully initialized\n");
 	return 0;
 }
 
@@ -480,7 +482,7 @@ static struct attribute_group hdaps_attribute_group = {
 /* hdaps_dmi_match - found a match.  return one, short-circuiting the hunt. */
 static int __init hdaps_dmi_match(const struct dmi_system_id *id)
 {
-	printk(KERN_INFO "hdaps: %s detected.\n", id->ident);
+	pr_info("%s detected\n", id->ident);
 	return 1;
 }
 
@@ -488,8 +490,7 @@ static int __init hdaps_dmi_match(const struct dmi_system_id *id)
 static int __init hdaps_dmi_match_invert(const struct dmi_system_id *id)
 {
 	hdaps_invert = (unsigned long)id->driver_data;
-	printk(KERN_INFO "hdaps: inverting axis (%u) readings.\n",
-	       hdaps_invert);
+	pr_info("inverting axis (%u) readings\n", hdaps_invert);
 	return hdaps_dmi_match(id);
 }
 
@@ -543,7 +544,7 @@ static int __init hdaps_init(void)
 	int ret;
 
 	if (!dmi_check_system(hdaps_whitelist)) {
-		printk(KERN_WARNING "hdaps: supported laptop not found!\n");
+		pr_warn("supported laptop not found!\n");
 		ret = -ENODEV;
 		goto out;
 	}
@@ -595,7 +596,7 @@ static int __init hdaps_init(void)
 	if (ret)
 		goto out_idev;
 
-	printk(KERN_INFO "hdaps: driver successfully loaded.\n");
+	pr_info("driver successfully loaded\n");
 	return 0;
 
 out_idev:
@@ -609,7 +610,7 @@ out_driver:
 out_region:
 	release_region(HDAPS_LOW_PORT, HDAPS_NR_PORTS);
 out:
-	printk(KERN_WARNING "hdaps: driver init failed (ret=%d)!\n", ret);
+	pr_warn("driver init failed (ret=%d)!\n", ret);
 	return ret;
 }
 
@@ -622,7 +623,7 @@ static void __exit hdaps_exit(void)
 	platform_driver_unregister(&hdaps_driver);
 	release_region(HDAPS_LOW_PORT, HDAPS_NR_PORTS);
 
-	printk(KERN_INFO "hdaps: driver unloaded.\n");
+	pr_info("driver unloaded\n");
 }
 
 module_init(hdaps_init);
diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index 1bc4a7539ba9..f94017bcdd6e 100644
--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@@ -24,6 +24,8 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -54,9 +56,6 @@ MODULE_ALIAS("wmi:5FB7F034-2C63-45e9-BE91-3D44E2C707E4");
 #define HPWMI_HOTKEY_QUERY 0xc
 #define HPWMI_WIRELESS2_QUERY 0x1b
 
-#define PREFIX "HP WMI: "
-#define UNIMP "Unimplemented "
-
 enum hp_wmi_radio {
 	HPWMI_WIFI = 0,
 	HPWMI_BLUETOOTH = 1,
@@ -228,9 +227,8 @@ static int hp_wmi_perform_query(int query, int write, void *buffer,
 
 	if (bios_return->return_code) {
 		if (bios_return->return_code != HPWMI_RET_UNKNOWN_CMDTYPE)
-			printk(KERN_WARNING PREFIX "query 0x%x returned "
-						   "error 0x%x\n",
-			       query, bios_return->return_code);
+			pr_warn("query 0x%x returned error 0x%x\n",
+				query, bios_return->return_code);
 		kfree(obj);
 		return bios_return->return_code;
 	}
@@ -384,8 +382,7 @@ static int hp_wmi_rfkill2_refresh(void)
 
 		if (num >= state.count ||
 		    devstate->rfkill_id != rfkill2[i].id) {
-			printk(KERN_WARNING PREFIX "power configuration of "
-			       "the wireless devices unexpectedly changed\n");
+			pr_warn("power configuration of the wireless devices unexpectedly changed\n");
 			continue;
 		}
 
@@ -471,7 +468,7 @@ static void hp_wmi_notify(u32 value, void *context)
 
 	status = wmi_get_event_data(value, &response);
 	if (status != AE_OK) {
-		printk(KERN_INFO PREFIX "bad event status 0x%x\n", status);
+		pr_info("bad event status 0x%x\n", status);
 		return;
 	}
 
@@ -480,8 +477,7 @@ static void hp_wmi_notify(u32 value, void *context)
 	if (!obj)
 		return;
 	if (obj->type != ACPI_TYPE_BUFFER) {
-		printk(KERN_INFO "hp-wmi: Unknown response received %d\n",
-		       obj->type);
+		pr_info("Unknown response received %d\n", obj->type);
 		kfree(obj);
 		return;
 	}
@@ -498,8 +494,7 @@ static void hp_wmi_notify(u32 value, void *context)
 		event_id = *location;
 		event_data = *(location + 2);
 	} else {
-		printk(KERN_INFO "hp-wmi: Unknown buffer length %d\n",
-		       obj->buffer.length);
+		pr_info("Unknown buffer length %d\n", obj->buffer.length);
 		kfree(obj);
 		return;
 	}
@@ -527,8 +522,7 @@ static void hp_wmi_notify(u32 value, void *context)
 
 		if (!sparse_keymap_report_event(hp_wmi_input_dev,
 						key_code, 1, true))
-			printk(KERN_INFO PREFIX "Unknown key code - 0x%x\n",
-			       key_code);
+			pr_info("Unknown key code - 0x%x\n", key_code);
 		break;
 	case HPWMI_WIRELESS:
 		if (rfkill2_count) {
@@ -550,14 +544,12 @@ static void hp_wmi_notify(u32 value, void *context)
 					  hp_wmi_get_hw_state(HPWMI_WWAN));
 		break;
 	case HPWMI_CPU_BATTERY_THROTTLE:
-		printk(KERN_INFO PREFIX UNIMP "CPU throttle because of 3 Cell"
-		       " battery event detected\n");
+		pr_info("Unimplemented CPU throttle because of 3 Cell battery event detected\n");
 		break;
 	case HPWMI_LOCK_SWITCH:
 		break;
 	default:
-		printk(KERN_INFO PREFIX "Unknown event_id - %d - 0x%x\n",
-		       event_id, event_data);
+		pr_info("Unknown event_id - %d - 0x%x\n", event_id, event_data);
 		break;
 	}
 }
@@ -705,7 +697,7 @@ static int __devinit hp_wmi_rfkill2_setup(struct platform_device *device)
 		return err;
 
 	if (state.count > HPWMI_MAX_RFKILL2_DEVICES) {
-		printk(KERN_WARNING PREFIX "unable to parse 0x1b query output\n");
+		pr_warn("unable to parse 0x1b query output\n");
 		return -EINVAL;
 	}
 
@@ -727,14 +719,14 @@ static int __devinit hp_wmi_rfkill2_setup(struct platform_device *device)
 			name = "hp-wwan";
 			break;
 		default:
-			printk(KERN_WARNING PREFIX "unknown device type 0x%x\n",
-				 state.device[i].radio_type);
+			pr_warn("unknown device type 0x%x\n",
+				state.device[i].radio_type);
 			continue;
 		}
 
 		if (!state.device[i].vendor_id) {
-			printk(KERN_WARNING PREFIX "zero device %d while %d "
-			       "reported\n", i, state.count);
+			pr_warn("zero device %d while %d reported\n",
+				i, state.count);
 			continue;
 		}
 
@@ -755,8 +747,7 @@ static int __devinit hp_wmi_rfkill2_setup(struct platform_device *device)
 				    IS_HWBLOCKED(state.device[i].power));
 
 		if (!(state.device[i].power & HPWMI_POWER_BIOS))
-			printk(KERN_INFO PREFIX "device %s blocked by BIOS\n",
-			       name);
+			pr_info("device %s blocked by BIOS\n", name);
 
 		err = rfkill_register(rfkill);
 		if (err) {
diff --git a/drivers/platform/x86/ibm_rtl.c b/drivers/platform/x86/ibm_rtl.c
index b1396e5b2953..811d436cd677 100644
--- a/drivers/platform/x86/ibm_rtl.c
+++ b/drivers/platform/x86/ibm_rtl.c
@@ -22,6 +22,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/module.h>
@@ -69,9 +71,10 @@ struct ibm_rtl_table {
 #define RTL_SIGNATURE 0x0000005f4c54525fULL
 #define RTL_MASK      0x000000ffffffffffULL
 
-#define RTL_DEBUG(A, ...) do { \
-	if (debug) \
-		pr_info("ibm-rtl: " A, ##__VA_ARGS__ ); \
+#define RTL_DEBUG(fmt, ...)				\
+do {							\
+	if (debug)					\
+		pr_info(fmt, ##__VA_ARGS__);		\
 } while (0)
 
 static DEFINE_MUTEX(rtl_lock);
@@ -114,7 +117,7 @@ static int ibm_rtl_write(u8 value)
 	int ret = 0, count = 0;
 	static u32 cmd_port_val;
 
-	RTL_DEBUG("%s(%d)\n", __FUNCTION__, value);
+	RTL_DEBUG("%s(%d)\n", __func__, value);
 
 	value = value == 1 ? RTL_CMD_ENTER_PRTM : RTL_CMD_EXIT_PRTM;
 
@@ -144,8 +147,8 @@ static int ibm_rtl_write(u8 value)
 		while (ioread8(&rtl_table->command)) {
 			msleep(10);
 			if (count++ > 500) {
-				pr_err("ibm-rtl: Hardware not responding to "
-					"mode switch request\n");
+				pr_err("Hardware not responding to "
+				       "mode switch request\n");
 				ret = -EIO;
 				break;
 			}
@@ -250,7 +253,7 @@ static int __init ibm_rtl_init(void) {
 	int ret = -ENODEV, i;
 
 	if (force)
-		pr_warning("ibm-rtl: module loaded by force\n");
+		pr_warn("module loaded by force\n");
 	/* first ensure that we are running on IBM HW */
 	else if (efi_enabled || !dmi_check_system(ibm_rtl_dmi_table))
 		return -ENODEV;
@@ -288,19 +291,19 @@ static int __init ibm_rtl_init(void) {
 		if ((readq(&tmp->signature) & RTL_MASK) == RTL_SIGNATURE) {
 			phys_addr_t addr;
 			unsigned int plen;
-			RTL_DEBUG("found RTL_SIGNATURE at %#llx\n", (u64)tmp);
+			RTL_DEBUG("found RTL_SIGNATURE at %p\n", tmp);
 			rtl_table = tmp;
 			/* The address, value, width and offset are platform
 			 * dependent and found in the ibm_rtl_table */
 			rtl_cmd_width = ioread8(&rtl_table->cmd_granularity);
 			rtl_cmd_type = ioread8(&rtl_table->cmd_address_type);
 			RTL_DEBUG("rtl_cmd_width = %u, rtl_cmd_type = %u\n",
-			      rtl_cmd_width, rtl_cmd_type);
+				  rtl_cmd_width, rtl_cmd_type);
 			addr = ioread32(&rtl_table->cmd_port_address);
 			RTL_DEBUG("addr = %#llx\n", (unsigned long long)addr);
 			plen = rtl_cmd_width/sizeof(char);
 			rtl_cmd_addr = rtl_port_map(addr, plen);
-			RTL_DEBUG("rtl_cmd_addr = %#llx\n", (u64)rtl_cmd_addr);
+			RTL_DEBUG("rtl_cmd_addr = %p\n", rtl_cmd_addr);
 			if (!rtl_cmd_addr) {
 				ret = -ENOMEM;
 				break;
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index 21b101899bae..bfdda33feb26 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -20,6 +20,8 @@
  *  02110-1301, USA.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
diff --git a/drivers/platform/x86/intel_menlow.c b/drivers/platform/x86/intel_menlow.c
index eacd5da7dd24..809adea4965f 100644
--- a/drivers/platform/x86/intel_menlow.c
+++ b/drivers/platform/x86/intel_menlow.c
@@ -27,6 +27,8 @@
  *  to get/set bandwidth.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -135,8 +137,7 @@ static int memory_set_cur_bandwidth(struct thermal_cooling_device *cdev,
 	    acpi_evaluate_integer(handle, MEMORY_SET_BANDWIDTH, &arg_list,
 				  &temp);
 
-	printk(KERN_INFO
-	       "Bandwidth value was %ld: status is %d\n", state, status);
+	pr_info("Bandwidth value was %ld: status is %d\n", state, status);
 	if (ACPI_FAILURE(status))
 		return -EFAULT;
 
diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c
index 213e79ba68d5..f1ae5078b7ec 100644
--- a/drivers/platform/x86/intel_mid_powerbtn.c
+++ b/drivers/platform/x86/intel_mid_powerbtn.c
@@ -23,58 +23,48 @@
 #include <linux/slab.h>
 #include <linux/platform_device.h>
 #include <linux/input.h>
+
 #include <asm/intel_scu_ipc.h>
 
 #define DRIVER_NAME "msic_power_btn"
 
-#define MSIC_IRQ_STAT	0x02
-  #define MSIC_IRQ_PB	(1 << 0)
-#define MSIC_PB_CONFIG	0x3e
 #define MSIC_PB_STATUS	0x3f
-  #define MSIC_PB_LEVEL (1 << 3) /* 1 - release, 0 - press */
-
-struct mfld_pb_priv {
-	struct input_dev *input;
-	unsigned int irq;
-};
+#define MSIC_PB_LEVEL	(1 << 3) /* 1 - release, 0 - press */
 
 static irqreturn_t mfld_pb_isr(int irq, void *dev_id)
 {
-	struct mfld_pb_priv *priv = dev_id;
+	struct input_dev *input = dev_id;
 	int ret;
 	u8 pbstat;
 
 	ret = intel_scu_ipc_ioread8(MSIC_PB_STATUS, &pbstat);
-	if (ret < 0)
-		return IRQ_HANDLED;
-
-	input_event(priv->input, EV_KEY, KEY_POWER, !(pbstat & MSIC_PB_LEVEL));
-	input_sync(priv->input);
+	if (ret < 0) {
+		dev_err(input->dev.parent, "Read error %d while reading"
+			       " MSIC_PB_STATUS\n", ret);
+	} else {
+		input_event(input, EV_KEY, KEY_POWER,
+			       !(pbstat & MSIC_PB_LEVEL));
+		input_sync(input);
+	}
 
 	return IRQ_HANDLED;
 }
 
 static int __devinit mfld_pb_probe(struct platform_device *pdev)
 {
-	struct mfld_pb_priv *priv;
 	struct input_dev *input;
-	int irq;
+	int irq = platform_get_irq(pdev, 0);
 	int error;
 
-	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
 		return -EINVAL;
 
-	priv = kzalloc(sizeof(struct mfld_pb_priv), GFP_KERNEL);
 	input = input_allocate_device();
-	if (!priv || !input) {
-		error = -ENOMEM;
-		goto err_free_mem;
+	if (!input) {
+		dev_err(&pdev->dev, "Input device allocation error\n");
+		return -ENOMEM;
 	}
 
-	priv->input = input;
-	priv->irq = irq;
-
 	input->name = pdev->name;
 	input->phys = "power-button/input0";
 	input->id.bustype = BUS_HOST;
@@ -82,42 +72,40 @@ static int __devinit mfld_pb_probe(struct platform_device *pdev)
 
 	input_set_capability(input, EV_KEY, KEY_POWER);
 
-	error = request_threaded_irq(priv->irq, NULL, mfld_pb_isr,
-				     0, DRIVER_NAME, priv);
+	error = request_threaded_irq(irq, NULL, mfld_pb_isr, 0,
+			DRIVER_NAME, input);
 	if (error) {
-		dev_err(&pdev->dev,
-			"unable to request irq %d for mfld power button\n",
-			irq);
-		goto err_free_mem;
+		dev_err(&pdev->dev, "Unable to request irq %d for mfld power"
+				"button\n", irq);
+		goto err_free_input;
 	}
 
 	error = input_register_device(input);
 	if (error) {
-		dev_err(&pdev->dev,
-			"unable to register input dev, error %d\n", error);
+		dev_err(&pdev->dev, "Unable to register input dev, error "
+				"%d\n", error);
 		goto err_free_irq;
 	}
 
-	platform_set_drvdata(pdev, priv);
+	platform_set_drvdata(pdev, input);
 	return 0;
 
 err_free_irq:
-	free_irq(priv->irq, priv);
-err_free_mem:
+	free_irq(irq, input);
+err_free_input:
 	input_free_device(input);
-	kfree(priv);
 	return error;
 }
 
 static int __devexit mfld_pb_remove(struct platform_device *pdev)
 {
-	struct mfld_pb_priv *priv = platform_get_drvdata(pdev);
-
-	free_irq(priv->irq, priv);
-	input_unregister_device(priv->input);
-	kfree(priv);
+	struct input_dev *input = platform_get_drvdata(pdev);
+	int irq = platform_get_irq(pdev, 0);
 
+	free_irq(irq, input);
+	input_unregister_device(input);
 	platform_set_drvdata(pdev, NULL);
+
 	return 0;
 }
 
diff --git a/drivers/platform/x86/intel_mid_thermal.c b/drivers/platform/x86/intel_mid_thermal.c
index c2f4bd8013b5..3a578323122b 100644
--- a/drivers/platform/x86/intel_mid_thermal.c
+++ b/drivers/platform/x86/intel_mid_thermal.c
@@ -37,49 +37,50 @@
 #include <asm/intel_scu_ipc.h>
 
 /* Number of thermal sensors */
-#define MSIC_THERMAL_SENSORS   4
+#define MSIC_THERMAL_SENSORS	4
 
 /* ADC1 - thermal registers */
-#define MSIC_THERM_ADC1CNTL1   0x1C0
-#define MSIC_ADC_ENBL          0x10
-#define MSIC_ADC_START         0x08
+#define MSIC_THERM_ADC1CNTL1	0x1C0
+#define MSIC_ADC_ENBL		0x10
+#define MSIC_ADC_START		0x08
 
-#define MSIC_THERM_ADC1CNTL3   0x1C2
-#define MSIC_ADCTHERM_ENBL     0x04
-#define MSIC_ADCRRDATA_ENBL    0x05
-#define MSIC_CHANL_MASK_VAL    0x0F
+#define MSIC_THERM_ADC1CNTL3	0x1C2
+#define MSIC_ADCTHERM_ENBL	0x04
+#define MSIC_ADCRRDATA_ENBL	0x05
+#define MSIC_CHANL_MASK_VAL	0x0F
 
-#define MSIC_STOPBIT_MASK      16
-#define MSIC_ADCTHERM_MASK     4
-#define ADC_CHANLS_MAX         15 /* Number of ADC channels */
-#define ADC_LOOP_MAX           (ADC_CHANLS_MAX - MSIC_THERMAL_SENSORS)
+#define MSIC_STOPBIT_MASK	16
+#define MSIC_ADCTHERM_MASK	4
+/* Number of ADC channels */
+#define ADC_CHANLS_MAX		15
+#define ADC_LOOP_MAX		(ADC_CHANLS_MAX - MSIC_THERMAL_SENSORS)
 
 /* ADC channel code values */
-#define SKIN_SENSOR0_CODE      0x08
-#define SKIN_SENSOR1_CODE      0x09
-#define SYS_SENSOR_CODE                0x0A
-#define MSIC_DIE_SENSOR_CODE   0x03
+#define SKIN_SENSOR0_CODE	0x08
+#define SKIN_SENSOR1_CODE	0x09
+#define SYS_SENSOR_CODE		0x0A
+#define MSIC_DIE_SENSOR_CODE	0x03
 
-#define SKIN_THERM_SENSOR0     0
-#define SKIN_THERM_SENSOR1     1
-#define SYS_THERM_SENSOR2      2
-#define MSIC_DIE_THERM_SENSOR3 3
+#define SKIN_THERM_SENSOR0	0
+#define SKIN_THERM_SENSOR1	1
+#define SYS_THERM_SENSOR2	2
+#define MSIC_DIE_THERM_SENSOR3	3
 
 /* ADC code range */
-#define ADC_MAX                        977
-#define ADC_MIN                        162
-#define ADC_VAL0C              887
-#define ADC_VAL20C             720
-#define ADC_VAL40C             508
-#define ADC_VAL60C             315
+#define ADC_MAX			977
+#define ADC_MIN			162
+#define ADC_VAL0C		887
+#define ADC_VAL20C		720
+#define ADC_VAL40C		508
+#define ADC_VAL60C		315
 
 /* ADC base addresses */
-#define ADC_CHNL_START_ADDR    0x1C5   /* increments by 1 */
-#define ADC_DATA_START_ADDR     0x1D4   /* increments by 2 */
+#define ADC_CHNL_START_ADDR	0x1C5	/* increments by 1 */
+#define ADC_DATA_START_ADDR	0x1D4	/* increments by 2 */
 
 /* MSIC die attributes */
-#define MSIC_DIE_ADC_MIN       488
-#define MSIC_DIE_ADC_MAX       1004
+#define MSIC_DIE_ADC_MIN	488
+#define MSIC_DIE_ADC_MAX	1004
 
 /* This holds the address of the first free ADC channel,
  * among the 15 channels
@@ -87,15 +88,15 @@
 static int channel_index;
 
 struct platform_info {
-       struct platform_device *pdev;
-       struct thermal_zone_device *tzd[MSIC_THERMAL_SENSORS];
+	struct platform_device *pdev;
+	struct thermal_zone_device *tzd[MSIC_THERMAL_SENSORS];
 };
 
 struct thermal_device_info {
-       unsigned int chnl_addr;
-       int direct;
-       /* This holds the current temperature in millidegree celsius */
-       long curr_temp;
+	unsigned int chnl_addr;
+	int direct;
+	/* This holds the current temperature in millidegree celsius */
+	long curr_temp;
 };
 
 /**
@@ -106,7 +107,7 @@ struct thermal_device_info {
  */
 static int to_msic_die_temp(uint16_t adc_val)
 {
-       return (368 * (adc_val) / 1000) - 220;
+	return (368 * (adc_val) / 1000) - 220;
 }
 
 /**
@@ -118,7 +119,7 @@ static int to_msic_die_temp(uint16_t adc_val)
  */
 static int is_valid_adc(uint16_t adc_val, uint16_t min, uint16_t max)
 {
-       return (adc_val >= min) && (adc_val <= max);
+	return (adc_val >= min) && (adc_val <= max);
 }
 
 /**
@@ -136,35 +137,35 @@ static int is_valid_adc(uint16_t adc_val, uint16_t min, uint16_t max)
  */
 static int adc_to_temp(int direct, uint16_t adc_val, unsigned long *tp)
 {
-       int temp;
-
-       /* Direct conversion for die temperature */
-       if (direct) {
-               if (is_valid_adc(adc_val, MSIC_DIE_ADC_MIN, MSIC_DIE_ADC_MAX)) {
-                       *tp = to_msic_die_temp(adc_val) * 1000;
-                       return 0;
-               }
-               return -ERANGE;
-       }
-
-       if (!is_valid_adc(adc_val, ADC_MIN, ADC_MAX))
-               return -ERANGE;
-
-       /* Linear approximation for skin temperature */
-       if (adc_val > ADC_VAL0C)
-               temp = 177 - (adc_val/5);
-       else if ((adc_val <= ADC_VAL0C) && (adc_val > ADC_VAL20C))
-               temp = 111 - (adc_val/8);
-       else if ((adc_val <= ADC_VAL20C) && (adc_val > ADC_VAL40C))
-               temp = 92 - (adc_val/10);
-       else if ((adc_val <= ADC_VAL40C) && (adc_val > ADC_VAL60C))
-               temp = 91 - (adc_val/10);
-       else
-               temp = 112 - (adc_val/6);
-
-       /* Convert temperature in celsius to milli degree celsius */
-       *tp = temp * 1000;
-       return 0;
+	int temp;
+
+	/* Direct conversion for die temperature */
+	if (direct) {
+		if (is_valid_adc(adc_val, MSIC_DIE_ADC_MIN, MSIC_DIE_ADC_MAX)) {
+			*tp = to_msic_die_temp(adc_val) * 1000;
+			return 0;
+		}
+		return -ERANGE;
+	}
+
+	if (!is_valid_adc(adc_val, ADC_MIN, ADC_MAX))
+		return -ERANGE;
+
+	/* Linear approximation for skin temperature */
+	if (adc_val > ADC_VAL0C)
+		temp = 177 - (adc_val/5);
+	else if ((adc_val <= ADC_VAL0C) && (adc_val > ADC_VAL20C))
+		temp = 111 - (adc_val/8);
+	else if ((adc_val <= ADC_VAL20C) && (adc_val > ADC_VAL40C))
+		temp = 92 - (adc_val/10);
+	else if ((adc_val <= ADC_VAL40C) && (adc_val > ADC_VAL60C))
+		temp = 91 - (adc_val/10);
+	else
+		temp = 112 - (adc_val/6);
+
+	/* Convert temperature in celsius to milli degree celsius */
+	*tp = temp * 1000;
+	return 0;
 }
 
 /**
@@ -178,47 +179,47 @@ static int adc_to_temp(int direct, uint16_t adc_val, unsigned long *tp)
  */
 static int mid_read_temp(struct thermal_zone_device *tzd, unsigned long *temp)
 {
-       struct thermal_device_info *td_info = tzd->devdata;
-       uint16_t adc_val, addr;
-       uint8_t data = 0;
-       int ret;
-       unsigned long curr_temp;
-
-
-       addr = td_info->chnl_addr;
-
-       /* Enable the msic for conversion before reading */
-       ret = intel_scu_ipc_iowrite8(MSIC_THERM_ADC1CNTL3, MSIC_ADCRRDATA_ENBL);
-       if (ret)
-               return ret;
-
-       /* Re-toggle the RRDATARD bit (temporary workaround) */
-       ret = intel_scu_ipc_iowrite8(MSIC_THERM_ADC1CNTL3, MSIC_ADCTHERM_ENBL);
-       if (ret)
-               return ret;
-
-       /* Read the higher bits of data */
-       ret = intel_scu_ipc_ioread8(addr, &data);
-       if (ret)
-               return ret;
-
-       /* Shift bits to accommodate the lower two data bits */
-       adc_val = (data << 2);
-       addr++;
-
-       ret = intel_scu_ipc_ioread8(addr, &data);/* Read lower bits */
-       if (ret)
-               return ret;
-
-       /* Adding lower two bits to the higher bits */
-       data &= 03;
-       adc_val += data;
-
-       /* Convert ADC value to temperature */
-       ret = adc_to_temp(td_info->direct, adc_val, &curr_temp);
-       if (ret == 0)
-               *temp = td_info->curr_temp = curr_temp;
-       return ret;
+	struct thermal_device_info *td_info = tzd->devdata;
+	uint16_t adc_val, addr;
+	uint8_t data = 0;
+	int ret;
+	unsigned long curr_temp;
+
+
+	addr = td_info->chnl_addr;
+
+	/* Enable the msic for conversion before reading */
+	ret = intel_scu_ipc_iowrite8(MSIC_THERM_ADC1CNTL3, MSIC_ADCRRDATA_ENBL);
+	if (ret)
+		return ret;
+
+	/* Re-toggle the RRDATARD bit (temporary workaround) */
+	ret = intel_scu_ipc_iowrite8(MSIC_THERM_ADC1CNTL3, MSIC_ADCTHERM_ENBL);
+	if (ret)
+		return ret;
+
+	/* Read the higher bits of data */
+	ret = intel_scu_ipc_ioread8(addr, &data);
+	if (ret)
+		return ret;
+
+	/* Shift bits to accommodate the lower two data bits */
+	adc_val = (data << 2);
+	addr++;
+
+	ret = intel_scu_ipc_ioread8(addr, &data);/* Read lower bits */
+	if (ret)
+		return ret;
+
+	/* Adding lower two bits to the higher bits */
+	data &= 03;
+	adc_val += data;
+
+	/* Convert ADC value to temperature */
+	ret = adc_to_temp(td_info->direct, adc_val, &curr_temp);
+	if (ret == 0)
+		*temp = td_info->curr_temp = curr_temp;
+	return ret;
 }
 
 /**
@@ -231,22 +232,21 @@ static int mid_read_temp(struct thermal_zone_device *tzd, unsigned long *temp)
  */
 static int configure_adc(int val)
 {
-       int ret;
-       uint8_t data;
-
-       ret = intel_scu_ipc_ioread8(MSIC_THERM_ADC1CNTL1, &data);
-       if (ret)
-               return ret;
-
-       if (val) {
-               /* Enable and start the ADC */
-               data |= (MSIC_ADC_ENBL | MSIC_ADC_START);
-       } else {
-               /* Just stop the ADC */
-               data &= (~MSIC_ADC_START);
-       }
-
-       return intel_scu_ipc_iowrite8(MSIC_THERM_ADC1CNTL1, data);
+	int ret;
+	uint8_t data;
+
+	ret = intel_scu_ipc_ioread8(MSIC_THERM_ADC1CNTL1, &data);
+	if (ret)
+		return ret;
+
+	if (val) {
+		/* Enable and start the ADC */
+		data |= (MSIC_ADC_ENBL | MSIC_ADC_START);
+	} else {
+		/* Just stop the ADC */
+		data &= (~MSIC_ADC_START);
+	}
+	return intel_scu_ipc_iowrite8(MSIC_THERM_ADC1CNTL1, data);
 }
 
 /**
@@ -259,30 +259,30 @@ static int configure_adc(int val)
  */
 static int set_up_therm_channel(u16 base_addr)
 {
-       int ret;
-
-       /* Enable all the sensor channels */
-       ret = intel_scu_ipc_iowrite8(base_addr, SKIN_SENSOR0_CODE);
-       if (ret)
-               return ret;
-
-       ret = intel_scu_ipc_iowrite8(base_addr + 1, SKIN_SENSOR1_CODE);
-       if (ret)
-               return ret;
-
-       ret = intel_scu_ipc_iowrite8(base_addr + 2, SYS_SENSOR_CODE);
-       if (ret)
-               return ret;
-
-       /* Since this is the last channel, set the stop bit
-          to 1 by ORing the DIE_SENSOR_CODE with 0x10 */
-       ret = intel_scu_ipc_iowrite8(base_addr + 3,
-                                       (MSIC_DIE_SENSOR_CODE | 0x10));
-       if (ret)
-               return ret;
-
-       /* Enable ADC and start it */
-       return configure_adc(1);
+	int ret;
+
+	/* Enable all the sensor channels */
+	ret = intel_scu_ipc_iowrite8(base_addr, SKIN_SENSOR0_CODE);
+	if (ret)
+		return ret;
+
+	ret = intel_scu_ipc_iowrite8(base_addr + 1, SKIN_SENSOR1_CODE);
+	if (ret)
+		return ret;
+
+	ret = intel_scu_ipc_iowrite8(base_addr + 2, SYS_SENSOR_CODE);
+	if (ret)
+		return ret;
+
+	/* Since this is the last channel, set the stop bit
+	 * to 1 by ORing the DIE_SENSOR_CODE with 0x10 */
+	ret = intel_scu_ipc_iowrite8(base_addr + 3,
+			(MSIC_DIE_SENSOR_CODE | 0x10));
+	if (ret)
+		return ret;
+
+	/* Enable ADC and start it */
+	return configure_adc(1);
 }
 
 /**
@@ -293,13 +293,13 @@ static int set_up_therm_channel(u16 base_addr)
  */
 static int reset_stopbit(uint16_t addr)
 {
-       int ret;
-       uint8_t data;
-       ret = intel_scu_ipc_ioread8(addr, &data);
-       if (ret)
-               return ret;
-       /* Set the stop bit to zero */
-       return intel_scu_ipc_iowrite8(addr, (data & 0xEF));
+	int ret;
+	uint8_t data;
+	ret = intel_scu_ipc_ioread8(addr, &data);
+	if (ret)
+		return ret;
+	/* Set the stop bit to zero */
+	return intel_scu_ipc_iowrite8(addr, (data & 0xEF));
 }
 
 /**
@@ -317,30 +317,30 @@ static int reset_stopbit(uint16_t addr)
  */
 static int find_free_channel(void)
 {
-       int ret;
-       int i;
-       uint8_t data;
-
-       /* check whether ADC is enabled */
-       ret = intel_scu_ipc_ioread8(MSIC_THERM_ADC1CNTL1, &data);
-       if (ret)
-               return ret;
-
-       if ((data & MSIC_ADC_ENBL) == 0)
-               return 0;
-
-       /* ADC is already enabled; Looking for an empty channel */
-       for (i = 0; i < ADC_CHANLS_MAX; i++) {
-               ret = intel_scu_ipc_ioread8(ADC_CHNL_START_ADDR + i, &data);
-               if (ret)
-                       return ret;
-
-               if (data & MSIC_STOPBIT_MASK) {
-                       ret = i;
-                       break;
-               }
-       }
-       return (ret > ADC_LOOP_MAX) ? (-EINVAL) : ret;
+	int ret;
+	int i;
+	uint8_t data;
+
+	/* check whether ADC is enabled */
+	ret = intel_scu_ipc_ioread8(MSIC_THERM_ADC1CNTL1, &data);
+	if (ret)
+		return ret;
+
+	if ((data & MSIC_ADC_ENBL) == 0)
+		return 0;
+
+	/* ADC is already enabled; Looking for an empty channel */
+	for (i = 0; i < ADC_CHANLS_MAX; i++) {
+		ret = intel_scu_ipc_ioread8(ADC_CHNL_START_ADDR + i, &data);
+		if (ret)
+			return ret;
+
+		if (data & MSIC_STOPBIT_MASK) {
+			ret = i;
+			break;
+		}
+	}
+	return (ret > ADC_LOOP_MAX) ? (-EINVAL) : ret;
 }
 
 /**
@@ -351,48 +351,48 @@ static int find_free_channel(void)
  */
 static int mid_initialize_adc(struct device *dev)
 {
-       u8  data;
-       u16 base_addr;
-       int ret;
-
-       /*
-        * Ensure that adctherm is disabled before we
-        * initialize the ADC
-        */
-       ret = intel_scu_ipc_ioread8(MSIC_THERM_ADC1CNTL3, &data);
-       if (ret)
-               return ret;
-
-       if (data & MSIC_ADCTHERM_MASK)
-               dev_warn(dev, "ADCTHERM already set");
-
-       /* Index of the first channel in which the stop bit is set */
-       channel_index = find_free_channel();
-       if (channel_index < 0) {
-               dev_err(dev, "No free ADC channels");
-               return channel_index;
-       }
-
-       base_addr = ADC_CHNL_START_ADDR + channel_index;
-
-       if (!(channel_index == 0 || channel_index == ADC_LOOP_MAX)) {
-               /* Reset stop bit for channels other than 0 and 12 */
-               ret = reset_stopbit(base_addr);
-               if (ret)
-                       return ret;
-
-               /* Index of the first free channel */
-               base_addr++;
-               channel_index++;
-       }
-
-       ret = set_up_therm_channel(base_addr);
-       if (ret) {
-               dev_err(dev, "unable to enable ADC");
-               return ret;
-       }
-       dev_dbg(dev, "ADC initialization successful");
-       return ret;
+	u8  data;
+	u16 base_addr;
+	int ret;
+
+	/*
+	 * Ensure that adctherm is disabled before we
+	 * initialize the ADC
+	 */
+	ret = intel_scu_ipc_ioread8(MSIC_THERM_ADC1CNTL3, &data);
+	if (ret)
+		return ret;
+
+	if (data & MSIC_ADCTHERM_MASK)
+		dev_warn(dev, "ADCTHERM already set");
+
+	/* Index of the first channel in which the stop bit is set */
+	channel_index = find_free_channel();
+	if (channel_index < 0) {
+		dev_err(dev, "No free ADC channels");
+		return channel_index;
+	}
+
+	base_addr = ADC_CHNL_START_ADDR + channel_index;
+
+	if (!(channel_index == 0 || channel_index == ADC_LOOP_MAX)) {
+		/* Reset stop bit for channels other than 0 and 12 */
+		ret = reset_stopbit(base_addr);
+		if (ret)
+			return ret;
+
+		/* Index of the first free channel */
+		base_addr++;
+		channel_index++;
+	}
+
+	ret = set_up_therm_channel(base_addr);
+	if (ret) {
+		dev_err(dev, "unable to enable ADC");
+		return ret;
+	}
+	dev_dbg(dev, "ADC initialization successful");
+	return ret;
 }
 
 /**
@@ -403,18 +403,18 @@ static int mid_initialize_adc(struct device *dev)
  */
 static struct thermal_device_info *initialize_sensor(int index)
 {
-       struct thermal_device_info *td_info =
-               kzalloc(sizeof(struct thermal_device_info), GFP_KERNEL);
-
-       if (!td_info)
-               return NULL;
-
-       /* Set the base addr of the channel for this sensor */
-       td_info->chnl_addr = ADC_DATA_START_ADDR + 2 * (channel_index + index);
-       /* Sensor 3 is direct conversion */
-       if (index == 3)
-               td_info->direct = 1;
-       return td_info;
+	struct thermal_device_info *td_info =
+		kzalloc(sizeof(struct thermal_device_info), GFP_KERNEL);
+
+	if (!td_info)
+		return NULL;
+
+	/* Set the base addr of the channel for this sensor */
+	td_info->chnl_addr = ADC_DATA_START_ADDR + 2 * (channel_index + index);
+	/* Sensor 3 is direct conversion */
+	if (index == 3)
+		td_info->direct = 1;
+	return td_info;
 }
 
 /**
@@ -425,7 +425,7 @@ static struct thermal_device_info *initialize_sensor(int index)
  */
 static int mid_thermal_resume(struct platform_device *pdev)
 {
-       return mid_initialize_adc(&pdev->dev);
+	return mid_initialize_adc(&pdev->dev);
 }
 
 /**
@@ -437,12 +437,12 @@ static int mid_thermal_resume(struct platform_device *pdev)
  */
 static int mid_thermal_suspend(struct platform_device *pdev, pm_message_t mesg)
 {
-       /*
-        * This just stops the ADC and does not disable it.
-        * temporary workaround until we have a generic ADC driver.
-        * If 0 is passed, it disables the ADC.
-        */
-       return configure_adc(0);
+	/*
+	 * This just stops the ADC and does not disable it.
+	 * temporary workaround until we have a generic ADC driver.
+	 * If 0 is passed, it disables the ADC.
+	 */
+	return configure_adc(0);
 }
 
 /**
@@ -453,16 +453,15 @@ static int mid_thermal_suspend(struct platform_device *pdev, pm_message_t mesg)
  */
 static int read_curr_temp(struct thermal_zone_device *tzd, unsigned long *temp)
 {
-       WARN_ON(tzd == NULL);
-       return mid_read_temp(tzd, temp);
+	WARN_ON(tzd == NULL);
+	return mid_read_temp(tzd, temp);
 }
 
 /* Can't be const */
 static struct thermal_zone_device_ops tzd_ops = {
-       .get_temp = read_curr_temp,
+	.get_temp = read_curr_temp,
 };
 
-
 /**
  * mid_thermal_probe - mfld thermal initialize
  * @pdev: platform device structure
@@ -472,46 +471,45 @@ static struct thermal_zone_device_ops tzd_ops = {
  */
 static int mid_thermal_probe(struct platform_device *pdev)
 {
-       static char *name[MSIC_THERMAL_SENSORS] = {
-               "skin0", "skin1", "sys", "msicdie"
-       };
-
-       int ret;
-       int i;
-       struct platform_info *pinfo;
-
-       pinfo = kzalloc(sizeof(struct platform_info), GFP_KERNEL);
-       if (!pinfo)
-               return -ENOMEM;
-
-       /* Initializing the hardware */
-       ret = mid_initialize_adc(&pdev->dev);
-       if (ret) {
-               dev_err(&pdev->dev, "ADC init failed");
-               kfree(pinfo);
-               return ret;
-       }
-
-       /* Register each sensor with the generic thermal framework*/
-       for (i = 0; i < MSIC_THERMAL_SENSORS; i++) {
-               pinfo->tzd[i] = thermal_zone_device_register(name[i],
-                                       0, initialize_sensor(i),
-                                       &tzd_ops, 0, 0, 0, 0);
-               if (IS_ERR(pinfo->tzd[i]))
-                       goto reg_fail;
-       }
-
-       pinfo->pdev = pdev;
-       platform_set_drvdata(pdev, pinfo);
-       return 0;
+	static char *name[MSIC_THERMAL_SENSORS] = {
+		"skin0", "skin1", "sys", "msicdie"
+	};
+
+	int ret;
+	int i;
+	struct platform_info *pinfo;
+
+	pinfo = kzalloc(sizeof(struct platform_info), GFP_KERNEL);
+	if (!pinfo)
+		return -ENOMEM;
+
+	/* Initializing the hardware */
+	ret = mid_initialize_adc(&pdev->dev);
+	if (ret) {
+		dev_err(&pdev->dev, "ADC init failed");
+		kfree(pinfo);
+		return ret;
+	}
+
+	/* Register each sensor with the generic thermal framework*/
+	for (i = 0; i < MSIC_THERMAL_SENSORS; i++) {
+		pinfo->tzd[i] = thermal_zone_device_register(name[i],
+				0, initialize_sensor(i), &tzd_ops, 0, 0, 0, 0);
+		if (IS_ERR(pinfo->tzd[i]))
+			goto reg_fail;
+	}
+
+	pinfo->pdev = pdev;
+	platform_set_drvdata(pdev, pinfo);
+	return 0;
 
 reg_fail:
-       ret = PTR_ERR(pinfo->tzd[i]);
-       while (--i >= 0)
-               thermal_zone_device_unregister(pinfo->tzd[i]);
-       configure_adc(0);
-       kfree(pinfo);
-       return ret;
+	ret = PTR_ERR(pinfo->tzd[i]);
+	while (--i >= 0)
+		thermal_zone_device_unregister(pinfo->tzd[i]);
+	configure_adc(0);
+	kfree(pinfo);
+	return ret;
 }
 
 /**
@@ -523,49 +521,46 @@ reg_fail:
  */
 static int mid_thermal_remove(struct platform_device *pdev)
 {
-       int i;
-       struct platform_info *pinfo = platform_get_drvdata(pdev);
+	int i;
+	struct platform_info *pinfo = platform_get_drvdata(pdev);
 
-       for (i = 0; i < MSIC_THERMAL_SENSORS; i++)
-               thermal_zone_device_unregister(pinfo->tzd[i]);
+	for (i = 0; i < MSIC_THERMAL_SENSORS; i++)
+		thermal_zone_device_unregister(pinfo->tzd[i]);
 
-       platform_set_drvdata(pdev, NULL);
+	kfree(pinfo);
+	platform_set_drvdata(pdev, NULL);
 
-       /* Stop the ADC */
-       return configure_adc(0);
+	/* Stop the ADC */
+	return configure_adc(0);
 }
 
-/*********************************************************************
- *             Driver initialisation and finalization
- *********************************************************************/
-
 #define DRIVER_NAME "msic_sensor"
 
 static const struct platform_device_id therm_id_table[] = {
-       { DRIVER_NAME, 1 },
-       { }
+	{ DRIVER_NAME, 1 },
+	{ }
 };
 
 static struct platform_driver mid_thermal_driver = {
-       .driver = {
-               .name = DRIVER_NAME,
-               .owner = THIS_MODULE,
-       },
-       .probe = mid_thermal_probe,
-       .suspend = mid_thermal_suspend,
-       .resume = mid_thermal_resume,
-       .remove = __devexit_p(mid_thermal_remove),
-       .id_table = therm_id_table,
+	.driver = {
+		.name = DRIVER_NAME,
+		.owner = THIS_MODULE,
+	},
+	.probe = mid_thermal_probe,
+	.suspend = mid_thermal_suspend,
+	.resume = mid_thermal_resume,
+	.remove = __devexit_p(mid_thermal_remove),
+	.id_table = therm_id_table,
 };
 
 static int __init mid_thermal_module_init(void)
 {
-       return platform_driver_register(&mid_thermal_driver);
+	return platform_driver_register(&mid_thermal_driver);
 }
 
 static void __exit mid_thermal_module_exit(void)
 {
-       platform_driver_unregister(&mid_thermal_driver);
+	platform_driver_unregister(&mid_thermal_driver);
 }
 
 module_init(mid_thermal_module_init);
diff --git a/drivers/platform/x86/intel_oaktrail.c b/drivers/platform/x86/intel_oaktrail.c
new file mode 100644
index 000000000000..e936364a609d
--- /dev/null
+++ b/drivers/platform/x86/intel_oaktrail.c
@@ -0,0 +1,396 @@
+/*
+ * intel_oaktrail.c - Intel OakTrail Platform support.
+ *
+ * Copyright (C) 2010-2011 Intel Corporation
+ * Author: Yin Kangkai (kangkai.yin@intel.com)
+ *
+ * based on Compal driver, Copyright (C) 2008 Cezary Jackiewicz
+ * <cezary.jackiewicz (at) gmail.com>, based on MSI driver
+ * Copyright (C) 2006 Lennart Poettering <mzxreary (at) 0pointer (dot) de>
+ *
+ *  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., 51 Franklin Street, Fifth Floor, Boston, MA
+ *  02110-1301, USA.
+ *
+ * This driver does below things:
+ * 1. registers itself in the Linux backlight control in
+ *    /sys/class/backlight/intel_oaktrail/
+ *
+ * 2. registers in the rfkill subsystem here: /sys/class/rfkill/rfkillX/
+ *    for these components: wifi, bluetooth, wwan (3g), gps
+ *
+ * This driver might work on other products based on Oaktrail. If you
+ * want to try it you can pass force=1 as argument to the module which
+ * will force it to load even when the DMI data doesn't identify the
+ * product as compatible.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/fb.h>
+#include <linux/mutex.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/backlight.h>
+#include <linux/platform_device.h>
+#include <linux/dmi.h>
+#include <linux/rfkill.h>
+#include <acpi/acpi_bus.h>
+#include <acpi/acpi_drivers.h>
+
+
+#define DRIVER_NAME	"intel_oaktrail"
+#define DRIVER_VERSION	"0.4ac1"
+
+/*
+ * This is the devices status address in EC space, and the control bits
+ * definition:
+ *
+ * (1 << 0):	Camera enable/disable, RW.
+ * (1 << 1):	Bluetooth enable/disable, RW.
+ * (1 << 2):	GPS enable/disable, RW.
+ * (1 << 3):	WiFi enable/disable, RW.
+ * (1 << 4):	WWAN (3G) enable/disalbe, RW.
+ * (1 << 5):	Touchscreen enable/disable, Read Only.
+ */
+#define OT_EC_DEVICE_STATE_ADDRESS	0xD6
+
+#define OT_EC_CAMERA_MASK	(1 << 0)
+#define OT_EC_BT_MASK		(1 << 1)
+#define OT_EC_GPS_MASK		(1 << 2)
+#define OT_EC_WIFI_MASK		(1 << 3)
+#define OT_EC_WWAN_MASK		(1 << 4)
+#define OT_EC_TS_MASK		(1 << 5)
+
+/*
+ * This is the address in EC space and commands used to control LCD backlight:
+ *
+ * Two steps needed to change the LCD backlight:
+ *   1. write the backlight percentage into OT_EC_BL_BRIGHTNESS_ADDRESS;
+ *   2. write OT_EC_BL_CONTROL_ON_DATA into OT_EC_BL_CONTROL_ADDRESS.
+ *
+ * To read the LCD back light, just read out the value from
+ * OT_EC_BL_BRIGHTNESS_ADDRESS.
+ *
+ * LCD backlight brightness range: 0 - 100 (OT_EC_BL_BRIGHTNESS_MAX)
+ */
+#define OT_EC_BL_BRIGHTNESS_ADDRESS	0x44
+#define OT_EC_BL_BRIGHTNESS_MAX		100
+#define OT_EC_BL_CONTROL_ADDRESS	0x3A
+#define OT_EC_BL_CONTROL_ON_DATA	0x1A
+
+
+static int force;
+module_param(force, bool, 0);
+MODULE_PARM_DESC(force, "Force driver load, ignore DMI data");
+
+static struct platform_device *oaktrail_device;
+static struct backlight_device *oaktrail_bl_device;
+static struct rfkill *bt_rfkill;
+static struct rfkill *gps_rfkill;
+static struct rfkill *wifi_rfkill;
+static struct rfkill *wwan_rfkill;
+
+
+/* rfkill */
+static int oaktrail_rfkill_set(void *data, bool blocked)
+{
+	u8 value;
+	u8 result;
+	unsigned long radio = (unsigned long) data;
+
+	ec_read(OT_EC_DEVICE_STATE_ADDRESS, &result);
+
+	if (!blocked)
+		value = (u8) (result | radio);
+	else
+		value = (u8) (result & ~radio);
+
+	ec_write(OT_EC_DEVICE_STATE_ADDRESS, value);
+
+	return 0;
+}
+
+static const struct rfkill_ops oaktrail_rfkill_ops = {
+	.set_block = oaktrail_rfkill_set,
+};
+
+static struct rfkill *oaktrail_rfkill_new(char *name, enum rfkill_type type,
+					  unsigned long mask)
+{
+	struct rfkill *rfkill_dev;
+	u8 value;
+	int err;
+
+	rfkill_dev = rfkill_alloc(name, &oaktrail_device->dev, type,
+				  &oaktrail_rfkill_ops, (void *)mask);
+	if (!rfkill_dev)
+		return ERR_PTR(-ENOMEM);
+
+	ec_read(OT_EC_DEVICE_STATE_ADDRESS, &value);
+	rfkill_init_sw_state(rfkill_dev, (value & mask) != 1);
+
+	err = rfkill_register(rfkill_dev);
+	if (err) {
+		rfkill_destroy(rfkill_dev);
+		return ERR_PTR(err);
+	}
+
+	return rfkill_dev;
+}
+
+static inline void __oaktrail_rfkill_cleanup(struct rfkill *rf)
+{
+	if (rf) {
+		rfkill_unregister(rf);
+		rfkill_destroy(rf);
+	}
+}
+
+static void oaktrail_rfkill_cleanup(void)
+{
+	__oaktrail_rfkill_cleanup(wifi_rfkill);
+	__oaktrail_rfkill_cleanup(bt_rfkill);
+	__oaktrail_rfkill_cleanup(gps_rfkill);
+	__oaktrail_rfkill_cleanup(wwan_rfkill);
+}
+
+static int oaktrail_rfkill_init(void)
+{
+	int ret;
+
+	wifi_rfkill = oaktrail_rfkill_new("oaktrail-wifi",
+					  RFKILL_TYPE_WLAN,
+					  OT_EC_WIFI_MASK);
+	if (IS_ERR(wifi_rfkill)) {
+		ret = PTR_ERR(wifi_rfkill);
+		wifi_rfkill = NULL;
+		goto cleanup;
+	}
+
+	bt_rfkill = oaktrail_rfkill_new("oaktrail-bluetooth",
+					RFKILL_TYPE_BLUETOOTH,
+					OT_EC_BT_MASK);
+	if (IS_ERR(bt_rfkill)) {
+		ret = PTR_ERR(bt_rfkill);
+		bt_rfkill = NULL;
+		goto cleanup;
+	}
+
+	gps_rfkill = oaktrail_rfkill_new("oaktrail-gps",
+					 RFKILL_TYPE_GPS,
+					 OT_EC_GPS_MASK);
+	if (IS_ERR(gps_rfkill)) {
+		ret = PTR_ERR(gps_rfkill);
+		gps_rfkill = NULL;
+		goto cleanup;
+	}
+
+	wwan_rfkill = oaktrail_rfkill_new("oaktrail-wwan",
+					  RFKILL_TYPE_WWAN,
+					  OT_EC_WWAN_MASK);
+	if (IS_ERR(wwan_rfkill)) {
+		ret = PTR_ERR(wwan_rfkill);
+		wwan_rfkill = NULL;
+		goto cleanup;
+	}
+
+	return 0;
+
+cleanup:
+	oaktrail_rfkill_cleanup();
+	return ret;
+}
+
+
+/* backlight */
+static int get_backlight_brightness(struct backlight_device *b)
+{
+	u8 value;
+	ec_read(OT_EC_BL_BRIGHTNESS_ADDRESS, &value);
+
+	return value;
+}
+
+static int set_backlight_brightness(struct backlight_device *b)
+{
+	u8 percent = (u8) b->props.brightness;
+	if (percent < 0 || percent > OT_EC_BL_BRIGHTNESS_MAX)
+		return -EINVAL;
+
+	ec_write(OT_EC_BL_BRIGHTNESS_ADDRESS, percent);
+	ec_write(OT_EC_BL_CONTROL_ADDRESS, OT_EC_BL_CONTROL_ON_DATA);
+
+	return 0;
+}
+
+static const struct backlight_ops oaktrail_bl_ops = {
+	.get_brightness = get_backlight_brightness,
+	.update_status	= set_backlight_brightness,
+};
+
+static int oaktrail_backlight_init(void)
+{
+	struct backlight_device *bd;
+	struct backlight_properties props;
+
+	memset(&props, 0, sizeof(struct backlight_properties));
+	props.max_brightness = OT_EC_BL_BRIGHTNESS_MAX;
+	bd = backlight_device_register(DRIVER_NAME,
+				       &oaktrail_device->dev, NULL,
+				       &oaktrail_bl_ops,
+				       &props);
+
+	if (IS_ERR(bd)) {
+		oaktrail_bl_device = NULL;
+		pr_warning("Unable to register backlight device\n");
+		return PTR_ERR(bd);
+	}
+
+	oaktrail_bl_device = bd;
+
+	bd->props.brightness = get_backlight_brightness(bd);
+	bd->props.power = FB_BLANK_UNBLANK;
+	backlight_update_status(bd);
+
+	return 0;
+}
+
+static void oaktrail_backlight_exit(void)
+{
+	if (oaktrail_bl_device)
+		backlight_device_unregister(oaktrail_bl_device);
+}
+
+static int __devinit oaktrail_probe(struct platform_device *pdev)
+{
+	return 0;
+}
+
+static int __devexit oaktrail_remove(struct platform_device *pdev)
+{
+	return 0;
+}
+
+static struct platform_driver oaktrail_driver = {
+	.driver = {
+		.name = DRIVER_NAME,
+		.owner = THIS_MODULE,
+	},
+	.probe	= oaktrail_probe,
+	.remove	= __devexit_p(oaktrail_remove)
+};
+
+static int dmi_check_cb(const struct dmi_system_id *id)
+{
+	pr_info("Identified model '%s'\n", id->ident);
+	return 0;
+}
+
+static struct dmi_system_id __initdata oaktrail_dmi_table[] = {
+	{
+		.ident = "OakTrail platform",
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_NAME, "OakTrail platform"),
+		},
+		.callback = dmi_check_cb
+	},
+	{ }
+};
+
+static int __init oaktrail_init(void)
+{
+	int ret;
+
+	if (acpi_disabled) {
+		pr_err("ACPI needs to be enabled for this driver to work!\n");
+		return -ENODEV;
+	}
+
+	if (!force && !dmi_check_system(oaktrail_dmi_table)) {
+		pr_err("Platform not recognized (You could try the module's force-parameter)");
+		return -ENODEV;
+	}
+
+	ret = platform_driver_register(&oaktrail_driver);
+	if (ret) {
+		pr_warning("Unable to register platform driver\n");
+		goto err_driver_reg;
+	}
+
+	oaktrail_device = platform_device_alloc(DRIVER_NAME, -1);
+	if (!oaktrail_device) {
+		pr_warning("Unable to allocate platform device\n");
+		ret = -ENOMEM;
+		goto err_device_alloc;
+	}
+
+	ret = platform_device_add(oaktrail_device);
+	if (ret) {
+		pr_warning("Unable to add platform device\n");
+		goto err_device_add;
+	}
+
+	if (!acpi_video_backlight_support()) {
+		ret = oaktrail_backlight_init();
+		if (ret)
+			goto err_backlight;
+
+	} else
+		pr_info("Backlight controlled by ACPI video driver\n");
+
+	ret = oaktrail_rfkill_init();
+	if (ret) {
+		pr_warning("Setup rfkill failed\n");
+		goto err_rfkill;
+	}
+
+	pr_info("Driver "DRIVER_VERSION" successfully loaded\n");
+	return 0;
+
+err_rfkill:
+	oaktrail_backlight_exit();
+err_backlight:
+	platform_device_del(oaktrail_device);
+err_device_add:
+	platform_device_put(oaktrail_device);
+err_device_alloc:
+	platform_driver_unregister(&oaktrail_driver);
+err_driver_reg:
+
+	return ret;
+}
+
+static void __exit oaktrail_cleanup(void)
+{
+	oaktrail_backlight_exit();
+	oaktrail_rfkill_cleanup();
+	platform_device_unregister(oaktrail_device);
+	platform_driver_unregister(&oaktrail_driver);
+
+	pr_info("Driver unloaded\n");
+}
+
+module_init(oaktrail_init);
+module_exit(oaktrail_cleanup);
+
+MODULE_AUTHOR("Yin Kangkai (kangkai.yin@intel.com)");
+MODULE_DESCRIPTION("Intel Oaktrail Platform ACPI Extras");
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("dmi:*:svnIntelCorporation:pnOakTrailplatform:*");
diff --git a/drivers/platform/x86/intel_pmic_gpio.c b/drivers/platform/x86/intel_pmic_gpio.c
index 464bb3fc4d88..1686c1e07d5d 100644
--- a/drivers/platform/x86/intel_pmic_gpio.c
+++ b/drivers/platform/x86/intel_pmic_gpio.c
@@ -19,6 +19,8 @@
  * Moorestown platform PMIC chip
  */
 
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
@@ -90,8 +92,7 @@ static void pmic_program_irqtype(int gpio, int type)
 static int pmic_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 {
 	if (offset > 8) {
-		printk(KERN_ERR
-			"%s: only pin 0-7 support input\n", __func__);
+		pr_err("only pin 0-7 support input\n");
 		return -1;/* we only have 8 GPIO can use as input */
 	}
 	return intel_scu_ipc_update_register(GPIO0 + offset,
@@ -116,8 +117,7 @@ static int pmic_gpio_direction_output(struct gpio_chip *chip,
 				value ? 1 << (offset - 16) : 0,
 				1 << (offset - 16));
 	else {
-		printk(KERN_ERR
-			"%s: invalid PMIC GPIO pin %d!\n", __func__, offset);
+		pr_err("invalid PMIC GPIO pin %d!\n", offset);
 		WARN_ON(1);
 	}
 
@@ -260,7 +260,7 @@ static int __devinit platform_pmic_gpio_probe(struct platform_device *pdev)
 	/* setting up SRAM mapping for GPIOINT register */
 	pg->gpiointr = ioremap_nocache(pdata->gpiointr, 8);
 	if (!pg->gpiointr) {
-		printk(KERN_ERR "%s: Can not map GPIOINT.\n", __func__);
+		pr_err("Can not map GPIOINT\n");
 		retval = -EINVAL;
 		goto err2;
 	}
@@ -281,13 +281,13 @@ static int __devinit platform_pmic_gpio_probe(struct platform_device *pdev)
 	pg->chip.dev = dev;
 	retval = gpiochip_add(&pg->chip);
 	if (retval) {
-		printk(KERN_ERR "%s: Can not add pmic gpio chip.\n", __func__);
+		pr_err("Can not add pmic gpio chip\n");
 		goto err;
 	}
 
 	retval = request_irq(pg->irq, pmic_irq_handler, 0, "pmic", pg);
 	if (retval) {
-		printk(KERN_WARNING "pmic: Interrupt request failed\n");
+		pr_warn("Interrupt request failed\n");
 		goto err;
 	}
 
diff --git a/drivers/platform/x86/msi-laptop.c b/drivers/platform/x86/msi-laptop.c
index 23fb2afda00b..3ff629df9f01 100644
--- a/drivers/platform/x86/msi-laptop.c
+++ b/drivers/platform/x86/msi-laptop.c
@@ -135,7 +135,7 @@ static int set_lcd_level(int level)
 	buf[1] = (u8) (level*31);
 
 	return ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, buf, sizeof(buf),
-			      NULL, 0, 1);
+			      NULL, 0);
 }
 
 static int get_lcd_level(void)
@@ -144,7 +144,7 @@ static int get_lcd_level(void)
 	int result;
 
 	result = ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, &wdata, 1,
-				&rdata, 1, 1);
+				&rdata, 1);
 	if (result < 0)
 		return result;
 
@@ -157,7 +157,7 @@ static int get_auto_brightness(void)
 	int result;
 
 	result = ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, &wdata, 1,
-				&rdata, 1, 1);
+				&rdata, 1);
 	if (result < 0)
 		return result;
 
@@ -172,7 +172,7 @@ static int set_auto_brightness(int enable)
 	wdata[0] = 4;
 
 	result = ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, wdata, 1,
-				&rdata, 1, 1);
+				&rdata, 1);
 	if (result < 0)
 		return result;
 
@@ -180,7 +180,7 @@ static int set_auto_brightness(int enable)
 	wdata[1] = (rdata & 0xF7) | (enable ? 8 : 0);
 
 	return ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, wdata, 2,
-			      NULL, 0, 1);
+			      NULL, 0);
 }
 
 static ssize_t set_device_state(const char *buf, size_t count, u8 mask)
@@ -217,7 +217,7 @@ static int get_wireless_state(int *wlan, int *bluetooth)
 	u8 wdata = 0, rdata;
 	int result;
 
-	result = ec_transaction(MSI_EC_COMMAND_WIRELESS, &wdata, 1, &rdata, 1, 1);
+	result = ec_transaction(MSI_EC_COMMAND_WIRELESS, &wdata, 1, &rdata, 1);
 	if (result < 0)
 		return -1;
 
@@ -447,7 +447,7 @@ static struct platform_device *msipf_device;
 
 static int dmi_check_cb(const struct dmi_system_id *id)
 {
-	pr_info("Identified laptop model '%s'.\n", id->ident);
+	pr_info("Identified laptop model '%s'\n", id->ident);
 	return 1;
 }
 
@@ -800,7 +800,7 @@ static void msi_laptop_input_destroy(void)
 	input_unregister_device(msi_laptop_input_dev);
 }
 
-static int load_scm_model_init(struct platform_device *sdev)
+static int __init load_scm_model_init(struct platform_device *sdev)
 {
 	u8 data;
 	int result;
@@ -875,8 +875,7 @@ static int __init msi_init(void)
 	/* Register backlight stuff */
 
 	if (acpi_video_backlight_support()) {
-		pr_info("Brightness ignored, must be controlled "
-		       "by ACPI video driver\n");
+		pr_info("Brightness ignored, must be controlled by ACPI video driver\n");
 	} else {
 		struct backlight_properties props;
 		memset(&props, 0, sizeof(struct backlight_properties));
@@ -930,7 +929,7 @@ static int __init msi_init(void)
 	if (auto_brightness != 2)
 		set_auto_brightness(auto_brightness);
 
-	pr_info("driver "MSI_DRIVER_VERSION" successfully loaded.\n");
+	pr_info("driver " MSI_DRIVER_VERSION " successfully loaded\n");
 
 	return 0;
 
@@ -978,7 +977,7 @@ static void __exit msi_cleanup(void)
 	if (auto_brightness != 2)
 		set_auto_brightness(1);
 
-	pr_info("driver unloaded.\n");
+	pr_info("driver unloaded\n");
 }
 
 module_init(msi_init);
diff --git a/drivers/platform/x86/msi-wmi.c b/drivers/platform/x86/msi-wmi.c
index d5419c9ec07a..c832e3356cd6 100644
--- a/drivers/platform/x86/msi-wmi.c
+++ b/drivers/platform/x86/msi-wmi.c
@@ -20,6 +20,7 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
 #include <linux/input.h>
@@ -36,13 +37,10 @@ MODULE_ALIAS("wmi:551A1F84-FBDD-4125-91DB-3EA8F44F1D45");
 MODULE_ALIAS("wmi:B6F3EEF2-3D2F-49DC-9DE3-85BCE18C62F2");
 
 #define DRV_NAME "msi-wmi"
-#define DRV_PFX DRV_NAME ": "
 
 #define MSIWMI_BIOS_GUID "551A1F84-FBDD-4125-91DB-3EA8F44F1D45"
 #define MSIWMI_EVENT_GUID "B6F3EEF2-3D2F-49DC-9DE3-85BCE18C62F2"
 
-#define dprintk(msg...) pr_debug(DRV_PFX msg)
-
 #define SCANCODE_BASE 0xD0
 #define MSI_WMI_BRIGHTNESSUP   SCANCODE_BASE
 #define MSI_WMI_BRIGHTNESSDOWN (SCANCODE_BASE + 1)
@@ -78,7 +76,7 @@ static int msi_wmi_query_block(int instance, int *ret)
 
 	if (!obj || obj->type != ACPI_TYPE_INTEGER) {
 		if (obj) {
-			printk(KERN_ERR DRV_PFX "query block returned object "
+			pr_err("query block returned object "
 			       "type: %d - buffer length:%d\n", obj->type,
 			       obj->type == ACPI_TYPE_BUFFER ?
 			       obj->buffer.length : 0);
@@ -97,8 +95,8 @@ static int msi_wmi_set_block(int instance, int value)
 
 	struct acpi_buffer input = { sizeof(int), &value };
 
-	dprintk("Going to set block of instance: %d - value: %d\n",
-		instance, value);
+	pr_debug("Going to set block of instance: %d - value: %d\n",
+		 instance, value);
 
 	status = wmi_set_block(MSIWMI_BIOS_GUID, instance, &input);
 
@@ -112,20 +110,19 @@ static int bl_get(struct backlight_device *bd)
 	/* Instance 1 is "get backlight", cmp with DSDT */
 	err = msi_wmi_query_block(1, &ret);
 	if (err) {
-		printk(KERN_ERR DRV_PFX "Could not query backlight: %d\n", err);
+		pr_err("Could not query backlight: %d\n", err);
 		return -EINVAL;
 	}
-	dprintk("Get: Query block returned: %d\n", ret);
+	pr_debug("Get: Query block returned: %d\n", ret);
 	for (level = 0; level < ARRAY_SIZE(backlight_map); level++) {
 		if (backlight_map[level] == ret) {
-			dprintk("Current backlight level: 0x%X - index: %d\n",
-				backlight_map[level], level);
+			pr_debug("Current backlight level: 0x%X - index: %d\n",
+				 backlight_map[level], level);
 			break;
 		}
 	}
 	if (level == ARRAY_SIZE(backlight_map)) {
-		printk(KERN_ERR DRV_PFX "get: Invalid brightness value: 0x%X\n",
-		       ret);
+		pr_err("get: Invalid brightness value: 0x%X\n", ret);
 		return -EINVAL;
 	}
 	return level;
@@ -156,7 +153,7 @@ static void msi_wmi_notify(u32 value, void *context)
 
 	status = wmi_get_event_data(value, &response);
 	if (status != AE_OK) {
-		printk(KERN_INFO DRV_PFX "bad event status 0x%x\n", status);
+		pr_info("bad event status 0x%x\n", status);
 		return;
 	}
 
@@ -164,7 +161,7 @@ static void msi_wmi_notify(u32 value, void *context)
 
 	if (obj && obj->type == ACPI_TYPE_INTEGER) {
 		int eventcode = obj->integer.value;
-		dprintk("Eventcode: 0x%x\n", eventcode);
+		pr_debug("Eventcode: 0x%x\n", eventcode);
 		key = sparse_keymap_entry_from_scancode(msi_wmi_input_dev,
 				eventcode);
 		if (key) {
@@ -175,8 +172,8 @@ static void msi_wmi_notify(u32 value, void *context)
 			/* Ignore event if the same event happened in a 50 ms
 			   timeframe -> Key press may result in 10-20 GPEs */
 			if (ktime_to_us(diff) < 1000 * 50) {
-				dprintk("Suppressed key event 0x%X - "
-					"Last press was %lld us ago\n",
+				pr_debug("Suppressed key event 0x%X - "
+					 "Last press was %lld us ago\n",
 					 key->code, ktime_to_us(diff));
 				return;
 			}
@@ -187,17 +184,16 @@ static void msi_wmi_notify(u32 value, void *context)
 			(!acpi_video_backlight_support() ||
 			(key->code != MSI_WMI_BRIGHTNESSUP &&
 			key->code != MSI_WMI_BRIGHTNESSDOWN))) {
-				dprintk("Send key: 0x%X - "
-					"Input layer keycode: %d\n", key->code,
-					 key->keycode);
+				pr_debug("Send key: 0x%X - "
+					 "Input layer keycode: %d\n",
+					 key->code, key->keycode);
 				sparse_keymap_report_entry(msi_wmi_input_dev,
 						key, 1, true);
 			}
 		} else
-			printk(KERN_INFO "Unknown key pressed - %x\n",
-			       eventcode);
+			pr_info("Unknown key pressed - %x\n", eventcode);
 	} else
-		printk(KERN_INFO DRV_PFX "Unknown event received\n");
+		pr_info("Unknown event received\n");
 	kfree(response.pointer);
 }
 
@@ -238,8 +234,7 @@ static int __init msi_wmi_init(void)
 	int err;
 
 	if (!wmi_has_guid(MSIWMI_EVENT_GUID)) {
-		printk(KERN_ERR
-		       "This machine doesn't have MSI-hotkeys through WMI\n");
+		pr_err("This machine doesn't have MSI-hotkeys through WMI\n");
 		return -ENODEV;
 	}
 	err = wmi_install_notify_handler(MSIWMI_EVENT_GUID,
@@ -270,7 +265,7 @@ static int __init msi_wmi_init(void)
 
 		backlight->props.brightness = err;
 	}
-	dprintk("Event handler installed\n");
+	pr_debug("Event handler installed\n");
 
 	return 0;
 
diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c
index 6fe8cd6e23b5..bbd182e178cb 100644
--- a/drivers/platform/x86/sony-laptop.c
+++ b/drivers/platform/x86/sony-laptop.c
@@ -42,6 +42,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -70,10 +72,10 @@
 #include <linux/miscdevice.h>
 #endif
 
-#define DRV_PFX			"sony-laptop: "
-#define dprintk(msg...)		do {	\
-	if (debug)			\
-		pr_warn(DRV_PFX msg);	\
+#define dprintk(fmt, ...)			\
+do {						\
+	if (debug)				\
+		pr_warn(fmt, ##__VA_ARGS__);	\
 } while (0)
 
 #define SONY_LAPTOP_DRIVER_VERSION	"0.6"
@@ -418,7 +420,7 @@ static int sony_laptop_setup_input(struct acpi_device *acpi_device)
 	error = kfifo_alloc(&sony_laptop_input.fifo,
 			    SONY_LAPTOP_BUF_SIZE, GFP_KERNEL);
 	if (error) {
-		pr_err(DRV_PFX "kfifo_alloc failed\n");
+		pr_err("kfifo_alloc failed\n");
 		goto err_dec_users;
 	}
 
@@ -702,7 +704,7 @@ static int acpi_callgetfunc(acpi_handle handle, char *name, int *result)
 		return 0;
 	}
 
-	pr_warn(DRV_PFX "acpi_callreadfunc failed\n");
+	pr_warn("acpi_callreadfunc failed\n");
 
 	return -1;
 }
@@ -728,8 +730,7 @@ static int acpi_callsetfunc(acpi_handle handle, char *name, int value,
 	if (status == AE_OK) {
 		if (result != NULL) {
 			if (out_obj.type != ACPI_TYPE_INTEGER) {
-				pr_warn(DRV_PFX "acpi_evaluate_object bad "
-				       "return type\n");
+				pr_warn("acpi_evaluate_object bad return type\n");
 				return -1;
 			}
 			*result = out_obj.integer.value;
@@ -737,7 +738,7 @@ static int acpi_callsetfunc(acpi_handle handle, char *name, int value,
 		return 0;
 	}
 
-	pr_warn(DRV_PFX "acpi_evaluate_object failed\n");
+	pr_warn("acpi_evaluate_object failed\n");
 
 	return -1;
 }
@@ -961,7 +962,6 @@ static int sony_backlight_get_brightness(struct backlight_device *bd)
 static int sony_nc_get_brightness_ng(struct backlight_device *bd)
 {
 	int result;
-	int *handle = (int *)bl_get_data(bd);
 	struct sony_backlight_props *sdev =
 		(struct sony_backlight_props *)bl_get_data(bd);
 
@@ -973,7 +973,6 @@ static int sony_nc_get_brightness_ng(struct backlight_device *bd)
 static int sony_nc_update_status_ng(struct backlight_device *bd)
 {
 	int value, result;
-	int *handle = (int *)bl_get_data(bd);
 	struct sony_backlight_props *sdev =
 		(struct sony_backlight_props *)bl_get_data(bd);
 
@@ -1104,10 +1103,8 @@ static void sony_nc_notify(struct acpi_device *device, u32 event)
 				}
 
 				if (!key_event->data)
-					pr_info(DRV_PFX
-							"Unknown event: 0x%x 0x%x\n",
-							key_handle,
-							ev);
+					pr_info("Unknown event: 0x%x 0x%x\n",
+						key_handle, ev);
 				else
 					sony_laptop_report_input_event(ev);
 			}
@@ -1128,7 +1125,7 @@ static acpi_status sony_walk_callback(acpi_handle handle, u32 level,
 	struct acpi_device_info *info;
 
 	if (ACPI_SUCCESS(acpi_get_object_info(handle, &info))) {
-		pr_warn(DRV_PFX "method: name: %4.4s, args %X\n",
+		pr_warn("method: name: %4.4s, args %X\n",
 			(char *)&info->name, info->param_count);
 
 		kfree(info);
@@ -1169,7 +1166,7 @@ static int sony_nc_resume(struct acpi_device *device)
 		ret = acpi_callsetfunc(sony_nc_acpi_handle, *item->acpiset,
 				       item->value, NULL);
 		if (ret < 0) {
-			pr_err(DRV_PFX "%s: %d\n", __func__, ret);
+			pr_err("%s: %d\n", __func__, ret);
 			break;
 		}
 	}
@@ -1336,12 +1333,12 @@ static void sony_nc_rfkill_setup(struct acpi_device *device)
 
 	device_enum = (union acpi_object *) buffer.pointer;
 	if (!device_enum) {
-		pr_err(DRV_PFX "No SN06 return object.");
+		pr_err("No SN06 return object\n");
 		goto out_no_enum;
 	}
 	if (device_enum->type != ACPI_TYPE_BUFFER) {
-		pr_err(DRV_PFX "Invalid SN06 return object 0x%.2x\n",
-				device_enum->type);
+		pr_err("Invalid SN06 return object 0x%.2x\n",
+		       device_enum->type);
 		goto out_no_enum;
 	}
 
@@ -1662,7 +1659,7 @@ static void sony_nc_backlight_setup(void)
 						      ops, &props);
 
 	if (IS_ERR(sony_bl_props.dev)) {
-		pr_warn(DRV_PFX "unable to register backlight device\n");
+		pr_warn("unable to register backlight device\n");
 		sony_bl_props.dev = NULL;
 	} else
 		sony_bl_props.dev->props.brightness =
@@ -1682,8 +1679,7 @@ static int sony_nc_add(struct acpi_device *device)
 	acpi_handle handle;
 	struct sony_nc_value *item;
 
-	pr_info(DRV_PFX "%s v%s.\n", SONY_NC_DRIVER_NAME,
-			SONY_LAPTOP_DRIVER_VERSION);
+	pr_info("%s v%s\n", SONY_NC_DRIVER_NAME, SONY_LAPTOP_DRIVER_VERSION);
 
 	sony_nc_acpi_device = device;
 	strcpy(acpi_device_class(device), "sony/hotkey");
@@ -1708,7 +1704,7 @@ static int sony_nc_add(struct acpi_device *device)
 				sony_nc_acpi_handle, 1, sony_walk_callback,
 				NULL, NULL, NULL);
 		if (ACPI_FAILURE(status)) {
-			pr_warn(DRV_PFX "unable to walk acpi resources\n");
+			pr_warn("unable to walk acpi resources\n");
 			result = -ENODEV;
 			goto outpresent;
 		}
@@ -1736,13 +1732,12 @@ static int sony_nc_add(struct acpi_device *device)
 	/* setup input devices and helper fifo */
 	result = sony_laptop_setup_input(device);
 	if (result) {
-		pr_err(DRV_PFX "Unable to create input devices.\n");
+		pr_err("Unable to create input devices\n");
 		goto outkbdbacklight;
 	}
 
 	if (acpi_video_backlight_support()) {
-		pr_info(DRV_PFX "brightness ignored, must be "
-		       "controlled by ACPI video driver\n");
+		pr_info("brightness ignored, must be controlled by ACPI video driver\n");
 	} else {
 		sony_nc_backlight_setup();
 	}
@@ -2265,9 +2260,9 @@ out:
 	if (pcidev)
 		pci_dev_put(pcidev);
 
-	pr_info(DRV_PFX "detected Type%d model\n",
-			dev->model == SONYPI_DEVICE_TYPE1 ? 1 :
-			dev->model == SONYPI_DEVICE_TYPE2 ? 2 : 3);
+	pr_info("detected Type%d model\n",
+		dev->model == SONYPI_DEVICE_TYPE1 ? 1 :
+		dev->model == SONYPI_DEVICE_TYPE2 ? 2 : 3);
 }
 
 /* camera tests and poweron/poweroff */
@@ -2313,7 +2308,7 @@ static int __sony_pic_camera_ready(void)
 static int __sony_pic_camera_off(void)
 {
 	if (!camera) {
-		pr_warn(DRV_PFX "camera control not enabled\n");
+		pr_warn("camera control not enabled\n");
 		return -ENODEV;
 	}
 
@@ -2333,7 +2328,7 @@ static int __sony_pic_camera_on(void)
 	int i, j, x;
 
 	if (!camera) {
-		pr_warn(DRV_PFX "camera control not enabled\n");
+		pr_warn("camera control not enabled\n");
 		return -ENODEV;
 	}
 
@@ -2356,7 +2351,7 @@ static int __sony_pic_camera_on(void)
 	}
 
 	if (j == 0) {
-		pr_warn(DRV_PFX "failed to power on camera\n");
+		pr_warn("failed to power on camera\n");
 		return -ENODEV;
 	}
 
@@ -2412,8 +2407,7 @@ int sony_pic_camera_command(int command, u8 value)
 				ITERATIONS_SHORT);
 		break;
 	default:
-		pr_err(DRV_PFX "sony_pic_camera_command invalid: %d\n",
-		       command);
+		pr_err("sony_pic_camera_command invalid: %d\n", command);
 		break;
 	}
 	mutex_unlock(&spic_dev.lock);
@@ -2819,7 +2813,7 @@ static int sonypi_compat_init(void)
 	error =
 	 kfifo_alloc(&sonypi_compat.fifo, SONY_LAPTOP_BUF_SIZE, GFP_KERNEL);
 	if (error) {
-		pr_err(DRV_PFX "kfifo_alloc failed\n");
+		pr_err("kfifo_alloc failed\n");
 		return error;
 	}
 
@@ -2829,12 +2823,12 @@ static int sonypi_compat_init(void)
 		sonypi_misc_device.minor = minor;
 	error = misc_register(&sonypi_misc_device);
 	if (error) {
-		pr_err(DRV_PFX "misc_register failed\n");
+		pr_err("misc_register failed\n");
 		goto err_free_kfifo;
 	}
 	if (minor == -1)
-		pr_info(DRV_PFX "device allocated minor is %d\n",
-		       sonypi_misc_device.minor);
+		pr_info("device allocated minor is %d\n",
+			sonypi_misc_device.minor);
 
 	return 0;
 
@@ -2893,8 +2887,8 @@ sony_pic_read_possible_resource(struct acpi_resource *resource, void *context)
 			}
 			for (i = 0; i < p->interrupt_count; i++) {
 				if (!p->interrupts[i]) {
-					pr_warn(DRV_PFX "Invalid IRQ %d\n",
-							p->interrupts[i]);
+					pr_warn("Invalid IRQ %d\n",
+						p->interrupts[i]);
 					continue;
 				}
 				interrupt = kzalloc(sizeof(*interrupt),
@@ -2932,14 +2926,14 @@ sony_pic_read_possible_resource(struct acpi_resource *resource, void *context)
 						ioport->io2.address_length);
 			}
 			else {
-				pr_err(DRV_PFX "Unknown SPIC Type, more than 2 IO Ports\n");
+				pr_err("Unknown SPIC Type, more than 2 IO Ports\n");
 				return AE_ERROR;
 			}
 			return AE_OK;
 		}
 	default:
 		dprintk("Resource %d isn't an IRQ nor an IO port\n",
-				resource->type);
+			resource->type);
 
 	case ACPI_RESOURCE_TYPE_END_TAG:
 		return AE_OK;
@@ -2960,7 +2954,7 @@ static int sony_pic_possible_resources(struct acpi_device *device)
 	dprintk("Evaluating _STA\n");
 	result = acpi_bus_get_status(device);
 	if (result) {
-		pr_warn(DRV_PFX "Unable to read status\n");
+		pr_warn("Unable to read status\n");
 		goto end;
 	}
 
@@ -2976,8 +2970,7 @@ static int sony_pic_possible_resources(struct acpi_device *device)
 	status = acpi_walk_resources(device->handle, METHOD_NAME__PRS,
 			sony_pic_read_possible_resource, &spic_dev);
 	if (ACPI_FAILURE(status)) {
-		pr_warn(DRV_PFX "Failure evaluating %s\n",
-				METHOD_NAME__PRS);
+		pr_warn("Failure evaluating %s\n", METHOD_NAME__PRS);
 		result = -ENODEV;
 	}
 end:
@@ -3090,7 +3083,7 @@ static int sony_pic_enable(struct acpi_device *device,
 
 	/* check for total failure */
 	if (ACPI_FAILURE(status)) {
-		pr_err(DRV_PFX "Error evaluating _SRS\n");
+		pr_err("Error evaluating _SRS\n");
 		result = -ENODEV;
 		goto end;
 	}
@@ -3182,7 +3175,7 @@ static int sony_pic_remove(struct acpi_device *device, int type)
 	struct sony_pic_irq *irq, *tmp_irq;
 
 	if (sony_pic_disable(device)) {
-		pr_err(DRV_PFX "Couldn't disable device.\n");
+		pr_err("Couldn't disable device\n");
 		return -ENXIO;
 	}
 
@@ -3222,8 +3215,7 @@ static int sony_pic_add(struct acpi_device *device)
 	struct sony_pic_ioport *io, *tmp_io;
 	struct sony_pic_irq *irq, *tmp_irq;
 
-	pr_info(DRV_PFX "%s v%s.\n", SONY_PIC_DRIVER_NAME,
-			SONY_LAPTOP_DRIVER_VERSION);
+	pr_info("%s v%s\n", SONY_PIC_DRIVER_NAME, SONY_LAPTOP_DRIVER_VERSION);
 
 	spic_dev.acpi_dev = device;
 	strcpy(acpi_device_class(device), "sony/hotkey");
@@ -3233,14 +3225,14 @@ static int sony_pic_add(struct acpi_device *device)
 	/* read _PRS resources */
 	result = sony_pic_possible_resources(device);
 	if (result) {
-		pr_err(DRV_PFX "Unable to read possible resources.\n");
+		pr_err("Unable to read possible resources\n");
 		goto err_free_resources;
 	}
 
 	/* setup input devices and helper fifo */
 	result = sony_laptop_setup_input(device);
 	if (result) {
-		pr_err(DRV_PFX "Unable to create input devices.\n");
+		pr_err("Unable to create input devices\n");
 		goto err_free_resources;
 	}
 
@@ -3281,7 +3273,7 @@ static int sony_pic_add(struct acpi_device *device)
 		}
 	}
 	if (!spic_dev.cur_ioport) {
-		pr_err(DRV_PFX "Failed to request_region.\n");
+		pr_err("Failed to request_region\n");
 		result = -ENODEV;
 		goto err_remove_compat;
 	}
@@ -3301,7 +3293,7 @@ static int sony_pic_add(struct acpi_device *device)
 		}
 	}
 	if (!spic_dev.cur_irq) {
-		pr_err(DRV_PFX "Failed to request_irq.\n");
+		pr_err("Failed to request_irq\n");
 		result = -ENODEV;
 		goto err_release_region;
 	}
@@ -3309,7 +3301,7 @@ static int sony_pic_add(struct acpi_device *device)
 	/* set resource status _SRS */
 	result = sony_pic_enable(device, spic_dev.cur_ioport, spic_dev.cur_irq);
 	if (result) {
-		pr_err(DRV_PFX "Couldn't enable device.\n");
+		pr_err("Couldn't enable device\n");
 		goto err_free_irq;
 	}
 
@@ -3418,7 +3410,7 @@ static int __init sony_laptop_init(void)
 	if (!no_spic && dmi_check_system(sonypi_dmi_table)) {
 		result = acpi_bus_register_driver(&sony_pic_driver);
 		if (result) {
-			pr_err(DRV_PFX "Unable to register SPIC driver.");
+			pr_err("Unable to register SPIC driver\n");
 			goto out;
 		}
 		spic_drv_registered = 1;
@@ -3426,7 +3418,7 @@ static int __init sony_laptop_init(void)
 
 	result = acpi_bus_register_driver(&sony_nc_driver);
 	if (result) {
-		pr_err(DRV_PFX "Unable to register SNC driver.");
+		pr_err("Unable to register SNC driver\n");
 		goto out_unregister_pic;
 	}
 
diff --git a/drivers/platform/x86/tc1100-wmi.c b/drivers/platform/x86/tc1100-wmi.c
index 865ef78d6f1a..e24f5ae475af 100644
--- a/drivers/platform/x86/tc1100-wmi.c
+++ b/drivers/platform/x86/tc1100-wmi.c
@@ -25,6 +25,8 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -40,9 +42,6 @@
 #define TC1100_INSTANCE_WIRELESS		1
 #define TC1100_INSTANCE_JOGDIAL		2
 
-#define TC1100_LOGPREFIX "tc1100-wmi: "
-#define TC1100_INFO KERN_INFO TC1100_LOGPREFIX
-
 MODULE_AUTHOR("Jamey Hicks, Carlos Corbacho");
 MODULE_DESCRIPTION("HP Compaq TC1100 Tablet WMI Extras");
 MODULE_LICENSE("GPL");
@@ -264,7 +263,7 @@ static int __init tc1100_init(void)
 	if (error)
 		goto err_device_del;
 
-	printk(TC1100_INFO "HP Compaq TC1100 Tablet WMI Extras loaded\n");
+	pr_info("HP Compaq TC1100 Tablet WMI Extras loaded\n");
 	return 0;
 
  err_device_del:
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 562fcf0dd2b5..77f6e707a2a9 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -21,6 +21,8 @@
  *  02110-1301, USA.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #define TPACPI_VERSION "0.24"
 #define TPACPI_SYSFS_VERSION 0x020700
 
@@ -224,17 +226,6 @@ enum tpacpi_hkey_event_t {
 
 #define TPACPI_MAX_ACPI_ARGS 3
 
-/* printk headers */
-#define TPACPI_LOG TPACPI_FILE ": "
-#define TPACPI_EMERG	KERN_EMERG	TPACPI_LOG
-#define TPACPI_ALERT	KERN_ALERT	TPACPI_LOG
-#define TPACPI_CRIT	KERN_CRIT	TPACPI_LOG
-#define TPACPI_ERR	KERN_ERR	TPACPI_LOG
-#define TPACPI_WARN	KERN_WARNING	TPACPI_LOG
-#define TPACPI_NOTICE	KERN_NOTICE	TPACPI_LOG
-#define TPACPI_INFO	KERN_INFO	TPACPI_LOG
-#define TPACPI_DEBUG	KERN_DEBUG	TPACPI_LOG
-
 /* Debugging printk groups */
 #define TPACPI_DBG_ALL		0xffff
 #define TPACPI_DBG_DISCLOSETASK	0x8000
@@ -389,34 +380,36 @@ static int tpacpi_uwb_emulstate;
  *  Debugging helpers
  */
 
-#define dbg_printk(a_dbg_level, format, arg...) \
-	do { if (dbg_level & (a_dbg_level)) \
-		printk(TPACPI_DEBUG "%s: " format, __func__ , ## arg); \
-	} while (0)
+#define dbg_printk(a_dbg_level, format, arg...)				\
+do {									\
+	if (dbg_level & (a_dbg_level))					\
+		printk(KERN_DEBUG pr_fmt("%s: " format),		\
+		       __func__, ##arg);				\
+} while (0)
 
 #ifdef CONFIG_THINKPAD_ACPI_DEBUG
 #define vdbg_printk dbg_printk
 static const char *str_supported(int is_supported);
 #else
-#define vdbg_printk(a_dbg_level, format, arg...) \
-	do { } while (0)
+static inline const char *str_supported(int is_supported) { return ""; }
+#define vdbg_printk(a_dbg_level, format, arg...)	\
+	no_printk(format, ##arg)
 #endif
 
 static void tpacpi_log_usertask(const char * const what)
 {
-	printk(TPACPI_DEBUG "%s: access by process with PID %d\n",
-		what, task_tgid_vnr(current));
+	printk(KERN_DEBUG pr_fmt("%s: access by process with PID %d\n"),
+	       what, task_tgid_vnr(current));
 }
 
-#define tpacpi_disclose_usertask(what, format, arg...) \
-	do { \
-		if (unlikely( \
-		    (dbg_level & TPACPI_DBG_DISCLOSETASK) && \
-		    (tpacpi_lifecycle == TPACPI_LIFE_RUNNING))) { \
-			printk(TPACPI_DEBUG "%s: PID %d: " format, \
-				what, task_tgid_vnr(current), ## arg); \
-		} \
-	} while (0)
+#define tpacpi_disclose_usertask(what, format, arg...)			\
+do {									\
+	if (unlikely((dbg_level & TPACPI_DBG_DISCLOSETASK) &&		\
+		     (tpacpi_lifecycle == TPACPI_LIFE_RUNNING))) {	\
+		printk(KERN_DEBUG pr_fmt("%s: PID %d: " format),	\
+		       what, task_tgid_vnr(current), ## arg);		\
+	}								\
+} while (0)
 
 /*
  * Quirk handling helpers
@@ -535,15 +528,6 @@ TPACPI_HANDLE(hkey, ec, "\\_SB.HKEY",	/* 600e/x, 770e, 770x */
 	   "HKEY",		/* all others */
 	   );			/* 570 */
 
-TPACPI_HANDLE(vid, root, "\\_SB.PCI.AGP.VGA",	/* 570 */
-	   "\\_SB.PCI0.AGP0.VID0",	/* 600e/x, 770x */
-	   "\\_SB.PCI0.VID0",	/* 770e */
-	   "\\_SB.PCI0.VID",	/* A21e, G4x, R50e, X30, X40 */
-	   "\\_SB.PCI0.AGP.VGA",	/* X100e and a few others */
-	   "\\_SB.PCI0.AGP.VID",	/* all others */
-	   );				/* R30, R31 */
-
-
 /*************************************************************************
  * ACPI helpers
  */
@@ -563,7 +547,7 @@ static int acpi_evalf(acpi_handle handle,
 	int quiet;
 
 	if (!*fmt) {
-		printk(TPACPI_ERR "acpi_evalf() called with empty format\n");
+		pr_err("acpi_evalf() called with empty format\n");
 		return 0;
 	}
 
@@ -588,7 +572,7 @@ static int acpi_evalf(acpi_handle handle,
 			break;
 			/* add more types as needed */
 		default:
-			printk(TPACPI_ERR "acpi_evalf() called "
+			pr_err("acpi_evalf() called "
 			       "with invalid format character '%c'\n", c);
 			va_end(ap);
 			return 0;
@@ -617,13 +601,13 @@ static int acpi_evalf(acpi_handle handle,
 		break;
 		/* add more types as needed */
 	default:
-		printk(TPACPI_ERR "acpi_evalf() called "
+		pr_err("acpi_evalf() called "
 		       "with invalid format character '%c'\n", res_type);
 		return 0;
 	}
 
 	if (!success && !quiet)
-		printk(TPACPI_ERR "acpi_evalf(%s, %s, ...) failed: %s\n",
+		pr_err("acpi_evalf(%s, %s, ...) failed: %s\n",
 		       method, fmt0, acpi_format_exception(status));
 
 	return success;
@@ -767,8 +751,7 @@ static int __init setup_acpi_notify(struct ibm_struct *ibm)
 
 	rc = acpi_bus_get_device(*ibm->acpi->handle, &ibm->acpi->device);
 	if (rc < 0) {
-		printk(TPACPI_ERR "acpi_bus_get_device(%s) failed: %d\n",
-			ibm->name, rc);
+		pr_err("acpi_bus_get_device(%s) failed: %d\n", ibm->name, rc);
 		return -ENODEV;
 	}
 
@@ -781,12 +764,10 @@ static int __init setup_acpi_notify(struct ibm_struct *ibm)
 			ibm->acpi->type, dispatch_acpi_notify, ibm);
 	if (ACPI_FAILURE(status)) {
 		if (status == AE_ALREADY_EXISTS) {
-			printk(TPACPI_NOTICE
-			       "another device driver is already "
-			       "handling %s events\n", ibm->name);
+			pr_notice("another device driver is already "
+				  "handling %s events\n", ibm->name);
 		} else {
-			printk(TPACPI_ERR
-			       "acpi_install_notify_handler(%s) failed: %s\n",
+			pr_err("acpi_install_notify_handler(%s) failed: %s\n",
 			       ibm->name, acpi_format_exception(status));
 		}
 		return -ENODEV;
@@ -811,8 +792,7 @@ static int __init register_tpacpi_subdriver(struct ibm_struct *ibm)
 
 	ibm->acpi->driver = kzalloc(sizeof(struct acpi_driver), GFP_KERNEL);
 	if (!ibm->acpi->driver) {
-		printk(TPACPI_ERR
-		       "failed to allocate memory for ibm->acpi->driver\n");
+		pr_err("failed to allocate memory for ibm->acpi->driver\n");
 		return -ENOMEM;
 	}
 
@@ -823,7 +803,7 @@ static int __init register_tpacpi_subdriver(struct ibm_struct *ibm)
 
 	rc = acpi_bus_register_driver(ibm->acpi->driver);
 	if (rc < 0) {
-		printk(TPACPI_ERR "acpi_bus_register_driver(%s) failed: %d\n",
+		pr_err("acpi_bus_register_driver(%s) failed: %d\n",
 		       ibm->name, rc);
 		kfree(ibm->acpi->driver);
 		ibm->acpi->driver = NULL;
@@ -1081,15 +1061,14 @@ static int parse_strtoul(const char *buf,
 static void tpacpi_disable_brightness_delay(void)
 {
 	if (acpi_evalf(hkey_handle, NULL, "PWMS", "qvd", 0))
-		printk(TPACPI_NOTICE
-			"ACPI backlight control delay disabled\n");
+		pr_notice("ACPI backlight control delay disabled\n");
 }
 
 static void printk_deprecated_attribute(const char * const what,
 					const char * const details)
 {
 	tpacpi_log_usertask("deprecated sysfs attribute");
-	printk(TPACPI_WARN "WARNING: sysfs attribute %s is deprecated and "
+	pr_warn("WARNING: sysfs attribute %s is deprecated and "
 		"will be removed. %s\n",
 		what, details);
 }
@@ -1264,8 +1243,7 @@ static int __init tpacpi_new_rfkill(const enum tpacpi_rfk_id id,
 						&tpacpi_rfk_rfkill_ops,
 						atp_rfk);
 	if (!atp_rfk || !atp_rfk->rfkill) {
-		printk(TPACPI_ERR
-			"failed to allocate memory for rfkill class\n");
+		pr_err("failed to allocate memory for rfkill class\n");
 		kfree(atp_rfk);
 		return -ENOMEM;
 	}
@@ -1275,9 +1253,8 @@ static int __init tpacpi_new_rfkill(const enum tpacpi_rfk_id id,
 
 	sw_status = (tp_rfkops->get_status)();
 	if (sw_status < 0) {
-		printk(TPACPI_ERR
-			"failed to read initial state for %s, error %d\n",
-			name, sw_status);
+		pr_err("failed to read initial state for %s, error %d\n",
+		       name, sw_status);
 	} else {
 		sw_state = (sw_status == TPACPI_RFK_RADIO_OFF);
 		if (set_default) {
@@ -1291,9 +1268,7 @@ static int __init tpacpi_new_rfkill(const enum tpacpi_rfk_id id,
 
 	res = rfkill_register(atp_rfk->rfkill);
 	if (res < 0) {
-		printk(TPACPI_ERR
-			"failed to register %s rfkill switch: %d\n",
-			name, res);
+		pr_err("failed to register %s rfkill switch: %d\n", name, res);
 		rfkill_destroy(atp_rfk->rfkill);
 		kfree(atp_rfk);
 		return res;
@@ -1301,7 +1276,7 @@ static int __init tpacpi_new_rfkill(const enum tpacpi_rfk_id id,
 
 	tpacpi_rfkill_switches[id] = atp_rfk;
 
-	printk(TPACPI_INFO "rfkill switch %s: radio is %sblocked\n",
+	pr_info("rfkill switch %s: radio is %sblocked\n",
 		name, (sw_state || hw_state) ? "" : "un");
 	return 0;
 }
@@ -1825,10 +1800,8 @@ static void __init tpacpi_check_outdated_fw(void)
 		 * broken, or really stable to begin with, so it is
 		 * best if the user upgrades the firmware anyway.
 		 */
-		printk(TPACPI_WARN
-			"WARNING: Outdated ThinkPad BIOS/EC firmware\n");
-		printk(TPACPI_WARN
-			"WARNING: This firmware may be missing critical bug "
+		pr_warn("WARNING: Outdated ThinkPad BIOS/EC firmware\n");
+		pr_warn("WARNING: This firmware may be missing critical bug "
 			"fixes and/or important features\n");
 	}
 }
@@ -2117,9 +2090,7 @@ void static hotkey_mask_warn_incomplete_mask(void)
 		(hotkey_all_mask | TPACPI_HKEY_NVRAM_KNOWN_MASK);
 
 	if (wantedmask)
-		printk(TPACPI_NOTICE
-			"required events 0x%08x not enabled!\n",
-			wantedmask);
+		pr_notice("required events 0x%08x not enabled!\n", wantedmask);
 }
 
 /*
@@ -2157,10 +2128,9 @@ static int hotkey_mask_set(u32 mask)
 	 * a given event.
 	 */
 	if (!hotkey_mask_get() && !rc && (fwmask & ~hotkey_acpi_mask)) {
-		printk(TPACPI_NOTICE
-		       "asked for hotkey mask 0x%08x, but "
-		       "firmware forced it to 0x%08x\n",
-		       fwmask, hotkey_acpi_mask);
+		pr_notice("asked for hotkey mask 0x%08x, but "
+			  "firmware forced it to 0x%08x\n",
+			  fwmask, hotkey_acpi_mask);
 	}
 
 	if (tpacpi_lifecycle != TPACPI_LIFE_EXITING)
@@ -2184,13 +2154,11 @@ static int hotkey_user_mask_set(const u32 mask)
 	    (mask == 0xffff || mask == 0xffffff ||
 	     mask == 0xffffffff)) {
 		tp_warned.hotkey_mask_ff = 1;
-		printk(TPACPI_NOTICE
-		       "setting the hotkey mask to 0x%08x is likely "
-		       "not the best way to go about it\n", mask);
-		printk(TPACPI_NOTICE
-		       "please consider using the driver defaults, "
-		       "and refer to up-to-date thinkpad-acpi "
-		       "documentation\n");
+		pr_notice("setting the hotkey mask to 0x%08x is likely "
+			  "not the best way to go about it\n", mask);
+		pr_notice("please consider using the driver defaults, "
+			  "and refer to up-to-date thinkpad-acpi "
+			  "documentation\n");
 	}
 
 	/* Try to enable what the user asked for, plus whatever we need.
@@ -2574,8 +2542,7 @@ static void hotkey_poll_setup(const bool may_warn)
 					NULL, TPACPI_NVRAM_KTHREAD_NAME);
 			if (IS_ERR(tpacpi_hotkey_task)) {
 				tpacpi_hotkey_task = NULL;
-				printk(TPACPI_ERR
-				       "could not create kernel thread "
+				pr_err("could not create kernel thread "
 				       "for hotkey polling\n");
 			}
 		}
@@ -2583,11 +2550,10 @@ static void hotkey_poll_setup(const bool may_warn)
 		hotkey_poll_stop_sync();
 		if (may_warn && (poll_driver_mask || poll_user_mask) &&
 		    hotkey_poll_freq == 0) {
-			printk(TPACPI_NOTICE
-				"hot keys 0x%08x and/or events 0x%08x "
-				"require polling, which is currently "
-				"disabled\n",
-				poll_user_mask, poll_driver_mask);
+			pr_notice("hot keys 0x%08x and/or events 0x%08x "
+				  "require polling, which is currently "
+				  "disabled\n",
+				  poll_user_mask, poll_driver_mask);
 		}
 	}
 }
@@ -2811,13 +2777,13 @@ static ssize_t hotkey_source_mask_store(struct device *dev,
 	mutex_unlock(&hotkey_mutex);
 
 	if (rc < 0)
-		printk(TPACPI_ERR "hotkey_source_mask: failed to update the"
-			"firmware event mask!\n");
+		pr_err("hotkey_source_mask: "
+		       "failed to update the firmware event mask!\n");
 
 	if (r_ev)
-		printk(TPACPI_NOTICE "hotkey_source_mask: "
-			"some important events were disabled: "
-			"0x%04x\n", r_ev);
+		pr_notice("hotkey_source_mask: "
+			  "some important events were disabled: 0x%04x\n",
+			  r_ev);
 
 	tpacpi_disclose_usertask("hotkey_source_mask", "set to 0x%08lx\n", t);
 
@@ -3048,8 +3014,7 @@ static void hotkey_exit(void)
 	if (((tp_features.hotkey_mask &&
 	      hotkey_mask_set(hotkey_orig_mask)) |
 	     hotkey_status_set(false)) != 0)
-		printk(TPACPI_ERR
-		       "failed to restore hot key mask "
+		pr_err("failed to restore hot key mask "
 		       "to BIOS defaults\n");
 }
 
@@ -3288,10 +3253,9 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
 	   for HKEY interface version 0x100 */
 	if (acpi_evalf(hkey_handle, &hkeyv, "MHKV", "qd")) {
 		if ((hkeyv >> 8) != 1) {
-			printk(TPACPI_ERR "unknown version of the "
-			       "HKEY interface: 0x%x\n", hkeyv);
-			printk(TPACPI_ERR "please report this to %s\n",
-			       TPACPI_MAIL);
+			pr_err("unknown version of the HKEY interface: 0x%x\n",
+			       hkeyv);
+			pr_err("please report this to %s\n", TPACPI_MAIL);
 		} else {
 			/*
 			 * MHKV 0x100 in A31, R40, R40e,
@@ -3304,8 +3268,7 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
 			/* Paranoia check AND init hotkey_all_mask */
 			if (!acpi_evalf(hkey_handle, &hotkey_all_mask,
 					"MHKA", "qd")) {
-				printk(TPACPI_ERR
-				       "missing MHKA handler, "
+				pr_err("missing MHKA handler, "
 				       "please report this to %s\n",
 				       TPACPI_MAIL);
 				/* Fallback: pre-init for FN+F3,F4,F12 */
@@ -3343,16 +3306,14 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
 	if (dbg_wlswemul) {
 		tp_features.hotkey_wlsw = 1;
 		radiosw_state = !!tpacpi_wlsw_emulstate;
-		printk(TPACPI_INFO
-			"radio switch emulation enabled\n");
+		pr_info("radio switch emulation enabled\n");
 	} else
 #endif
 	/* Not all thinkpads have a hardware radio switch */
 	if (acpi_evalf(hkey_handle, &status, "WLSW", "qd")) {
 		tp_features.hotkey_wlsw = 1;
 		radiosw_state = !!status;
-		printk(TPACPI_INFO
-			"radio switch found; radios are %s\n",
+		pr_info("radio switch found; radios are %s\n",
 			enabled(status, 0));
 	}
 	if (tp_features.hotkey_wlsw)
@@ -3363,8 +3324,7 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
 	if (!res && acpi_evalf(hkey_handle, &status, "MHKG", "qd")) {
 		tp_features.hotkey_tablet = 1;
 		tabletsw_state = !!(status & TP_HOTKEY_TABLET_MASK);
-		printk(TPACPI_INFO
-			"possible tablet mode switch found; "
+		pr_info("possible tablet mode switch found; "
 			"ThinkPad in %s mode\n",
 			(tabletsw_state) ? "tablet" : "laptop");
 		res = add_to_attr_set(hotkey_dev_attributes,
@@ -3382,8 +3342,7 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
 	hotkey_keycode_map = kmalloc(TPACPI_HOTKEY_MAP_SIZE,
 					GFP_KERNEL);
 	if (!hotkey_keycode_map) {
-		printk(TPACPI_ERR
-			"failed to allocate memory for key map\n");
+		pr_err("failed to allocate memory for key map\n");
 		res = -ENOMEM;
 		goto err_exit;
 	}
@@ -3426,13 +3385,11 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
 	 * userspace. tpacpi_detect_brightness_capabilities() must have
 	 * been called before this point  */
 	if (tp_features.bright_acpimode && acpi_video_backlight_support()) {
-		printk(TPACPI_INFO
-		       "This ThinkPad has standard ACPI backlight "
-		       "brightness control, supported by the ACPI "
-		       "video driver\n");
-		printk(TPACPI_NOTICE
-		       "Disabling thinkpad-acpi brightness events "
-		       "by default...\n");
+		pr_info("This ThinkPad has standard ACPI backlight "
+			"brightness control, supported by the ACPI "
+			"video driver\n");
+		pr_notice("Disabling thinkpad-acpi brightness events "
+			  "by default...\n");
 
 		/* Disable brightness up/down on Lenovo thinkpads when
 		 * ACPI is handling them, otherwise it is plain impossible
@@ -3539,8 +3496,7 @@ static bool hotkey_notify_wakeup(const u32 hkey,
 
 	case TP_HKEY_EV_WKUP_S3_BATLOW: /* Battery on critical low level/S3 */
 	case TP_HKEY_EV_WKUP_S4_BATLOW: /* Battery on critical low level/S4 */
-		printk(TPACPI_ALERT
-			"EMERGENCY WAKEUP: battery almost empty\n");
+		pr_alert("EMERGENCY WAKEUP: battery almost empty\n");
 		/* how to auto-heal: */
 		/* 2313: woke up from S3, go to S4/S5 */
 		/* 2413: woke up from S4, go to S5 */
@@ -3551,9 +3507,7 @@ static bool hotkey_notify_wakeup(const u32 hkey,
 	}
 
 	if (hotkey_wakeup_reason != TP_ACPI_WAKEUP_NONE) {
-		printk(TPACPI_INFO
-		       "woke up due to a hot-unplug "
-		       "request...\n");
+		pr_info("woke up due to a hot-unplug request...\n");
 		hotkey_wakeup_reason_notify_change();
 	}
 	return true;
@@ -3605,37 +3559,31 @@ static bool hotkey_notify_thermal(const u32 hkey,
 
 	switch (hkey) {
 	case TP_HKEY_EV_THM_TABLE_CHANGED:
-		printk(TPACPI_INFO
-			"EC reports that Thermal Table has changed\n");
+		pr_info("EC reports that Thermal Table has changed\n");
 		/* recommended action: do nothing, we don't have
 		 * Lenovo ATM information */
 		return true;
 	case TP_HKEY_EV_ALARM_BAT_HOT:
-		printk(TPACPI_CRIT
-			"THERMAL ALARM: battery is too hot!\n");
+		pr_crit("THERMAL ALARM: battery is too hot!\n");
 		/* recommended action: warn user through gui */
 		break;
 	case TP_HKEY_EV_ALARM_BAT_XHOT:
-		printk(TPACPI_ALERT
-			"THERMAL EMERGENCY: battery is extremely hot!\n");
+		pr_alert("THERMAL EMERGENCY: battery is extremely hot!\n");
 		/* recommended action: immediate sleep/hibernate */
 		break;
 	case TP_HKEY_EV_ALARM_SENSOR_HOT:
-		printk(TPACPI_CRIT
-			"THERMAL ALARM: "
+		pr_crit("THERMAL ALARM: "
 			"a sensor reports something is too hot!\n");
 		/* recommended action: warn user through gui, that */
 		/* some internal component is too hot */
 		break;
 	case TP_HKEY_EV_ALARM_SENSOR_XHOT:
-		printk(TPACPI_ALERT
-			"THERMAL EMERGENCY: "
-			"a sensor reports something is extremely hot!\n");
+		pr_alert("THERMAL EMERGENCY: "
+			 "a sensor reports something is extremely hot!\n");
 		/* recommended action: immediate sleep/hibernate */
 		break;
 	default:
-		printk(TPACPI_ALERT
-			 "THERMAL ALERT: unknown thermal alarm received\n");
+		pr_alert("THERMAL ALERT: unknown thermal alarm received\n");
 		known = false;
 	}
 
@@ -3652,8 +3600,7 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event)
 	bool known_ev;
 
 	if (event != 0x80) {
-		printk(TPACPI_ERR
-		       "unknown HKEY notification event %d\n", event);
+		pr_err("unknown HKEY notification event %d\n", event);
 		/* forward it to userspace, maybe it knows how to handle it */
 		acpi_bus_generate_netlink_event(
 					ibm->acpi->device->pnp.device_class,
@@ -3664,7 +3611,7 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event)
 
 	while (1) {
 		if (!acpi_evalf(hkey_handle, &hkey, "MHKP", "d")) {
-			printk(TPACPI_ERR "failed to retrieve HKEY event\n");
+			pr_err("failed to retrieve HKEY event\n");
 			return;
 		}
 
@@ -3692,8 +3639,7 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event)
 			switch (hkey) {
 			case TP_HKEY_EV_BAYEJ_ACK:
 				hotkey_autosleep_ack = 1;
-				printk(TPACPI_INFO
-				       "bay ejected\n");
+				pr_info("bay ejected\n");
 				hotkey_wakeup_hotunplug_complete_notify_change();
 				known_ev = true;
 				break;
@@ -3709,8 +3655,7 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event)
 			/* 0x4000-0x4FFF: dock-related wakeups */
 			if (hkey == TP_HKEY_EV_UNDOCK_ACK) {
 				hotkey_autosleep_ack = 1;
-				printk(TPACPI_INFO
-				       "undocked\n");
+				pr_info("undocked\n");
 				hotkey_wakeup_hotunplug_complete_notify_change();
 				known_ev = true;
 			} else {
@@ -3741,11 +3686,9 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event)
 			known_ev = false;
 		}
 		if (!known_ev) {
-			printk(TPACPI_NOTICE
-			       "unhandled HKEY event 0x%04x\n", hkey);
-			printk(TPACPI_NOTICE
-			       "please report the conditions when this "
-			       "event happened to %s\n", TPACPI_MAIL);
+			pr_notice("unhandled HKEY event 0x%04x\n", hkey);
+			pr_notice("please report the conditions when this "
+				  "event happened to %s\n", TPACPI_MAIL);
 		}
 
 		/* Legacy events */
@@ -3778,8 +3721,7 @@ static void hotkey_resume(void)
 
 	if (hotkey_status_set(true) < 0 ||
 	    hotkey_mask_set(hotkey_acpi_mask) < 0)
-		printk(TPACPI_ERR
-		       "error while attempting to reset the event "
+		pr_err("error while attempting to reset the event "
 		       "firmware interface\n");
 
 	tpacpi_send_radiosw_update();
@@ -3824,14 +3766,12 @@ static void hotkey_enabledisable_warn(bool enable)
 {
 	tpacpi_log_usertask("procfs hotkey enable/disable");
 	if (!WARN((tpacpi_lifecycle == TPACPI_LIFE_RUNNING || !enable),
-			TPACPI_WARN
-			"hotkey enable/disable functionality has been "
-			"removed from the driver.  Hotkeys are always "
-			"enabled\n"))
-		printk(TPACPI_ERR
-			"Please remove the hotkey=enable module "
-			"parameter, it is deprecated.  Hotkeys are always "
-			"enabled\n");
+		  pr_fmt("hotkey enable/disable functionality has been "
+			 "removed from the driver.  "
+			 "Hotkeys are always enabled.\n")))
+		pr_err("Please remove the hotkey=enable module "
+		       "parameter, it is deprecated.  "
+		       "Hotkeys are always enabled.\n");
 }
 
 static int hotkey_write(char *buf)
@@ -4011,8 +3951,7 @@ static void bluetooth_shutdown(void)
 	/* Order firmware to save current state to NVRAM */
 	if (!acpi_evalf(NULL, NULL, "\\BLTH", "vd",
 			TP_ACPI_BLTH_SAVE_STATE))
-		printk(TPACPI_NOTICE
-			"failed to save bluetooth state to NVRAM\n");
+		pr_notice("failed to save bluetooth state to NVRAM\n");
 	else
 		vdbg_printk(TPACPI_DBG_RFKILL,
 			"bluestooth state saved to NVRAM\n");
@@ -4051,8 +3990,7 @@ static int __init bluetooth_init(struct ibm_init_struct *iibm)
 #ifdef CONFIG_THINKPAD_ACPI_DEBUGFACILITIES
 	if (dbg_bluetoothemul) {
 		tp_features.bluetooth = 1;
-		printk(TPACPI_INFO
-			"bluetooth switch emulation enabled\n");
+		pr_info("bluetooth switch emulation enabled\n");
 	} else
 #endif
 	if (tp_features.bluetooth &&
@@ -4203,8 +4141,7 @@ static void wan_shutdown(void)
 	/* Order firmware to save current state to NVRAM */
 	if (!acpi_evalf(NULL, NULL, "\\WGSV", "vd",
 			TP_ACPI_WGSV_SAVE_STATE))
-		printk(TPACPI_NOTICE
-			"failed to save WWAN state to NVRAM\n");
+		pr_notice("failed to save WWAN state to NVRAM\n");
 	else
 		vdbg_printk(TPACPI_DBG_RFKILL,
 			"WWAN state saved to NVRAM\n");
@@ -4241,8 +4178,7 @@ static int __init wan_init(struct ibm_init_struct *iibm)
 #ifdef CONFIG_THINKPAD_ACPI_DEBUGFACILITIES
 	if (dbg_wwanemul) {
 		tp_features.wan = 1;
-		printk(TPACPI_INFO
-			"wwan switch emulation enabled\n");
+		pr_info("wwan switch emulation enabled\n");
 	} else
 #endif
 	if (tp_features.wan &&
@@ -4382,8 +4318,7 @@ static int __init uwb_init(struct ibm_init_struct *iibm)
 #ifdef CONFIG_THINKPAD_ACPI_DEBUGFACILITIES
 	if (dbg_uwbemul) {
 		tp_features.uwb = 1;
-		printk(TPACPI_INFO
-			"uwb switch emulation enabled\n");
+		pr_info("uwb switch emulation enabled\n");
 	} else
 #endif
 	if (tp_features.uwb &&
@@ -4444,6 +4379,15 @@ static int video_orig_autosw;
 static int video_autosw_get(void);
 static int video_autosw_set(int enable);
 
+TPACPI_HANDLE(vid, root,
+	      "\\_SB.PCI.AGP.VGA",	/* 570 */
+	      "\\_SB.PCI0.AGP0.VID0",	/* 600e/x, 770x */
+	      "\\_SB.PCI0.VID0",	/* 770e */
+	      "\\_SB.PCI0.VID",		/* A21e, G4x, R50e, X30, X40 */
+	      "\\_SB.PCI0.AGP.VGA",	/* X100e and a few others */
+	      "\\_SB.PCI0.AGP.VID",	/* all others */
+	);				/* R30, R31 */
+
 TPACPI_HANDLE(vid2, root, "\\_SB.PCI0.AGPB.VID");	/* G41 */
 
 static int __init video_init(struct ibm_init_struct *iibm)
@@ -4487,7 +4431,7 @@ static void video_exit(void)
 	dbg_printk(TPACPI_DBG_EXIT,
 		   "restoring original video autoswitch mode\n");
 	if (video_autosw_set(video_orig_autosw))
-		printk(TPACPI_ERR "error while trying to restore original "
+		pr_err("error while trying to restore original "
 			"video autoswitch mode\n");
 }
 
@@ -4560,8 +4504,7 @@ static int video_outputsw_set(int status)
 		res = acpi_evalf(vid_handle, NULL,
 				 "ASWT", "vdd", status * 0x100, 0);
 		if (!autosw && video_autosw_set(autosw)) {
-			printk(TPACPI_ERR
-			       "video auto-switch left enabled due to error\n");
+			pr_err("video auto-switch left enabled due to error\n");
 			return -EIO;
 		}
 		break;
@@ -4630,8 +4573,7 @@ static int video_outputsw_cycle(void)
 		return -ENOSYS;
 	}
 	if (!autosw && video_autosw_set(autosw)) {
-		printk(TPACPI_ERR
-		       "video auto-switch left enabled due to error\n");
+		pr_err("video auto-switch left enabled due to error\n");
 		return -EIO;
 	}
 
@@ -5348,7 +5290,7 @@ static int __init led_init(struct ibm_init_struct *iibm)
 	tpacpi_leds = kzalloc(sizeof(*tpacpi_leds) * TPACPI_LED_NUMLEDS,
 			      GFP_KERNEL);
 	if (!tpacpi_leds) {
-		printk(TPACPI_ERR "Out of memory for LED data\n");
+		pr_err("Out of memory for LED data\n");
 		return -ENOMEM;
 	}
 
@@ -5367,9 +5309,8 @@ static int __init led_init(struct ibm_init_struct *iibm)
 	}
 
 #ifdef CONFIG_THINKPAD_ACPI_UNSAFE_LEDS
-	printk(TPACPI_NOTICE
-		"warning: userspace override of important "
-		"firmware LEDs is enabled\n");
+	pr_notice("warning: userspace override of important "
+		  "firmware LEDs is enabled\n");
 #endif
 	return 0;
 }
@@ -5639,17 +5580,16 @@ static void thermal_dump_all_sensors(void)
 	if (n <= 0)
 		return;
 
-	printk(TPACPI_NOTICE
-		"temperatures (Celsius):");
+	pr_notice("temperatures (Celsius):");
 
 	for (i = 0; i < n; i++) {
 		if (t.temp[i] != TPACPI_THERMAL_SENSOR_NA)
-			printk(KERN_CONT " %d", (int)(t.temp[i] / 1000));
+			pr_cont(" %d", (int)(t.temp[i] / 1000));
 		else
-			printk(KERN_CONT " N/A");
+			pr_cont(" N/A");
 	}
 
-	printk(KERN_CONT "\n");
+	pr_cont("\n");
 }
 
 /* sysfs temp##_input -------------------------------------------------- */
@@ -5769,14 +5709,12 @@ static int __init thermal_init(struct ibm_init_struct *iibm)
 		if (ta1 == 0) {
 			/* This is sheer paranoia, but we handle it anyway */
 			if (acpi_tmp7) {
-				printk(TPACPI_ERR
-				       "ThinkPad ACPI EC access misbehaving, "
+				pr_err("ThinkPad ACPI EC access misbehaving, "
 				       "falling back to ACPI TMPx access "
 				       "mode\n");
 				thermal_read_mode = TPACPI_THERMAL_ACPI_TMP07;
 			} else {
-				printk(TPACPI_ERR
-				       "ThinkPad ACPI EC access misbehaving, "
+				pr_err("ThinkPad ACPI EC access misbehaving, "
 				       "disabling thermal sensors access\n");
 				thermal_read_mode = TPACPI_THERMAL_NONE;
 			}
@@ -6129,8 +6067,8 @@ static int __init tpacpi_query_bcl_levels(acpi_handle handle)
 	if (ACPI_SUCCESS(acpi_evaluate_object(handle, "_BCL", NULL, &buffer))) {
 		obj = (union acpi_object *)buffer.pointer;
 		if (!obj || (obj->type != ACPI_TYPE_PACKAGE)) {
-			printk(TPACPI_ERR "Unknown _BCL data, "
-			       "please report this to %s\n", TPACPI_MAIL);
+			pr_err("Unknown _BCL data, please report this to %s\n",
+			       TPACPI_MAIL);
 			rc = 0;
 		} else {
 			rc = obj->package.count;
@@ -6214,18 +6152,15 @@ static void __init tpacpi_detect_brightness_capabilities(void)
 	switch (b) {
 	case 16:
 		bright_maxlvl = 15;
-		printk(TPACPI_INFO
-		       "detected a 16-level brightness capable ThinkPad\n");
+		pr_info("detected a 16-level brightness capable ThinkPad\n");
 		break;
 	case 8:
 	case 0:
 		bright_maxlvl = 7;
-		printk(TPACPI_INFO
-		       "detected a 8-level brightness capable ThinkPad\n");
+		pr_info("detected a 8-level brightness capable ThinkPad\n");
 		break;
 	default:
-		printk(TPACPI_ERR
-		       "Unsupported brightness interface, "
+		pr_err("Unsupported brightness interface, "
 		       "please contact %s\n", TPACPI_MAIL);
 		tp_features.bright_unkfw = 1;
 		bright_maxlvl = b - 1;
@@ -6260,22 +6195,19 @@ static int __init brightness_init(struct ibm_init_struct *iibm)
 
 	if (acpi_video_backlight_support()) {
 		if (brightness_enable > 1) {
-			printk(TPACPI_INFO
-			       "Standard ACPI backlight interface "
-			       "available, not loading native one.\n");
+			pr_info("Standard ACPI backlight interface "
+				"available, not loading native one\n");
 			return 1;
 		} else if (brightness_enable == 1) {
-			printk(TPACPI_WARN
-				"Cannot enable backlight brightness support, "
+			pr_warn("Cannot enable backlight brightness support, "
 				"ACPI is already handling it.  Refer to the "
-				"acpi_backlight kernel parameter\n");
+				"acpi_backlight kernel parameter.\n");
 			return 1;
 		}
 	} else if (tp_features.bright_acpimode && brightness_enable > 1) {
-		printk(TPACPI_NOTICE
-			"Standard ACPI backlight interface not "
-			"available, thinkpad_acpi native "
-			"brightness control enabled\n");
+		pr_notice("Standard ACPI backlight interface not "
+			  "available, thinkpad_acpi native "
+			  "brightness control enabled\n");
 	}
 
 	/*
@@ -6319,19 +6251,17 @@ static int __init brightness_init(struct ibm_init_struct *iibm)
 	if (IS_ERR(ibm_backlight_device)) {
 		int rc = PTR_ERR(ibm_backlight_device);
 		ibm_backlight_device = NULL;
-		printk(TPACPI_ERR "Could not register backlight device\n");
+		pr_err("Could not register backlight device\n");
 		return rc;
 	}
 	vdbg_printk(TPACPI_DBG_INIT | TPACPI_DBG_BRGHT,
 			"brightness is supported\n");
 
 	if (quirks & TPACPI_BRGHT_Q_ASK) {
-		printk(TPACPI_NOTICE
-			"brightness: will use unverified default: "
-			"brightness_mode=%d\n", brightness_mode);
-		printk(TPACPI_NOTICE
-			"brightness: please report to %s whether it works well "
-			"or not on your ThinkPad\n", TPACPI_MAIL);
+		pr_notice("brightness: will use unverified default: "
+			  "brightness_mode=%d\n", brightness_mode);
+		pr_notice("brightness: please report to %s whether it works well "
+			  "or not on your ThinkPad\n", TPACPI_MAIL);
 	}
 
 	/* Added by mistake in early 2007.  Probably useless, but it could
@@ -6804,8 +6734,7 @@ static int __init volume_create_alsa_mixer(void)
 	rc = snd_card_create(alsa_index, alsa_id, THIS_MODULE,
 			    sizeof(struct tpacpi_alsa_data), &card);
 	if (rc < 0 || !card) {
-		printk(TPACPI_ERR
-			"Failed to create ALSA card structures: %d\n", rc);
+		pr_err("Failed to create ALSA card structures: %d\n", rc);
 		return 1;
 	}
 
@@ -6839,9 +6768,8 @@ static int __init volume_create_alsa_mixer(void)
 		ctl_vol = snd_ctl_new1(&volume_alsa_control_vol, NULL);
 		rc = snd_ctl_add(card, ctl_vol);
 		if (rc < 0) {
-			printk(TPACPI_ERR
-				"Failed to create ALSA volume control: %d\n",
-				rc);
+			pr_err("Failed to create ALSA volume control: %d\n",
+			       rc);
 			goto err_exit;
 		}
 		data->ctl_vol_id = &ctl_vol->id;
@@ -6850,8 +6778,7 @@ static int __init volume_create_alsa_mixer(void)
 	ctl_mute = snd_ctl_new1(&volume_alsa_control_mute, NULL);
 	rc = snd_ctl_add(card, ctl_mute);
 	if (rc < 0) {
-		printk(TPACPI_ERR "Failed to create ALSA mute control: %d\n",
-			rc);
+		pr_err("Failed to create ALSA mute control: %d\n", rc);
 		goto err_exit;
 	}
 	data->ctl_mute_id = &ctl_mute->id;
@@ -6859,7 +6786,7 @@ static int __init volume_create_alsa_mixer(void)
 	snd_card_set_dev(card, &tpacpi_pdev->dev);
 	rc = snd_card_register(card);
 	if (rc < 0) {
-		printk(TPACPI_ERR "Failed to register ALSA card: %d\n", rc);
+		pr_err("Failed to register ALSA card: %d\n", rc);
 		goto err_exit;
 	}
 
@@ -6915,9 +6842,8 @@ static int __init volume_init(struct ibm_init_struct *iibm)
 		return -EINVAL;
 
 	if (volume_mode == TPACPI_VOL_MODE_UCMS_STEP) {
-		printk(TPACPI_ERR
-			"UCMS step volume mode not implemented, "
-			"please contact %s\n", TPACPI_MAIL);
+		pr_err("UCMS step volume mode not implemented, "
+		       "please contact %s\n", TPACPI_MAIL);
 		return 1;
 	}
 
@@ -6981,13 +6907,11 @@ static int __init volume_init(struct ibm_init_struct *iibm)
 
 	rc = volume_create_alsa_mixer();
 	if (rc) {
-		printk(TPACPI_ERR
-			"Could not create the ALSA mixer interface\n");
+		pr_err("Could not create the ALSA mixer interface\n");
 		return rc;
 	}
 
-	printk(TPACPI_INFO
-		"Console audio control enabled, mode: %s\n",
+	pr_info("Console audio control enabled, mode: %s\n",
 		(volume_control_allowed) ?
 			"override (read/write)" :
 			"monitor (read only)");
@@ -7049,12 +6973,10 @@ static int volume_write(char *buf)
 	if (!volume_control_allowed && tpacpi_lifecycle != TPACPI_LIFE_INIT) {
 		if (unlikely(!tp_warned.volume_ctrl_forbidden)) {
 			tp_warned.volume_ctrl_forbidden = 1;
-			printk(TPACPI_NOTICE
-				"Console audio control in monitor mode, "
-				"changes are not allowed.\n");
-			printk(TPACPI_NOTICE
-				"Use the volume_control=1 module parameter "
-				"to enable volume control\n");
+			pr_notice("Console audio control in monitor mode, "
+				  "changes are not allowed\n");
+			pr_notice("Use the volume_control=1 module parameter "
+				  "to enable volume control\n");
 		}
 		return -EPERM;
 	}
@@ -7129,8 +7051,7 @@ static void inline volume_alsa_notify_change(void)
 
 static int __init volume_init(struct ibm_init_struct *iibm)
 {
-	printk(TPACPI_INFO
-		"volume: disabled as there is no ALSA support in this kernel\n");
+	pr_info("volume: disabled as there is no ALSA support in this kernel\n");
 
 	return 1;
 }
@@ -7337,9 +7258,8 @@ TPACPI_HANDLE(sfan, ec, "SFAN",	/* 570 */
 static void fan_quirk1_setup(void)
 {
 	if (fan_control_initial_status == 0x07) {
-		printk(TPACPI_NOTICE
-		       "fan_init: initial fan status is unknown, "
-		       "assuming it is in auto mode\n");
+		pr_notice("fan_init: initial fan status is unknown, "
+			  "assuming it is in auto mode\n");
 		tp_features.fan_ctrl_status_undef = 1;
 	}
 }
@@ -7726,8 +7646,7 @@ static void fan_watchdog_reset(void)
 		if (!queue_delayed_work(tpacpi_wq, &fan_watchdog_task,
 				msecs_to_jiffies(fan_watchdog_maxinterval
 						 * 1000))) {
-			printk(TPACPI_ERR
-			       "failed to queue the fan watchdog, "
+			pr_err("failed to queue the fan watchdog, "
 			       "watchdog will not trigger\n");
 		}
 	} else
@@ -7741,11 +7660,11 @@ static void fan_watchdog_fire(struct work_struct *ignored)
 	if (tpacpi_lifecycle != TPACPI_LIFE_RUNNING)
 		return;
 
-	printk(TPACPI_NOTICE "fan watchdog: enabling fan\n");
+	pr_notice("fan watchdog: enabling fan\n");
 	rc = fan_set_enable();
 	if (rc < 0) {
-		printk(TPACPI_ERR "fan watchdog: error %d while enabling fan, "
-			"will try again later...\n", -rc);
+		pr_err("fan watchdog: error %d while enabling fan, "
+		       "will try again later...\n", -rc);
 		/* reschedule for later */
 		fan_watchdog_reset();
 	}
@@ -8049,8 +7968,7 @@ static int __init fan_init(struct ibm_init_struct *iibm)
 					"secondary fan support enabled\n");
 			}
 		} else {
-			printk(TPACPI_ERR
-			       "ThinkPad ACPI EC access misbehaving, "
+			pr_err("ThinkPad ACPI EC access misbehaving, "
 			       "fan status and control unavailable\n");
 			return 1;
 		}
@@ -8150,9 +8068,8 @@ static void fan_suspend(pm_message_t state)
 	fan_control_resume_level = 0;
 	rc = fan_get_status_safe(&fan_control_resume_level);
 	if (rc < 0)
-		printk(TPACPI_NOTICE
-			"failed to read fan level for later "
-			"restore during resume: %d\n", rc);
+		pr_notice("failed to read fan level for later "
+			  "restore during resume: %d\n", rc);
 
 	/* if it is undefined, don't attempt to restore it.
 	 * KEEP THIS LAST */
@@ -8207,13 +8124,11 @@ static void fan_resume(void)
 		return;
 	}
 	if (do_set) {
-		printk(TPACPI_NOTICE
-			"restoring fan level to 0x%02x\n",
-			fan_control_resume_level);
+		pr_notice("restoring fan level to 0x%02x\n",
+			  fan_control_resume_level);
 		rc = fan_set_level_safe(fan_control_resume_level);
 		if (rc < 0)
-			printk(TPACPI_NOTICE
-				"failed to restore fan level: %d\n", rc);
+			pr_notice("failed to restore fan level: %d\n", rc);
 	}
 }
 
@@ -8305,8 +8220,8 @@ static int fan_write_cmd_level(const char *cmd, int *rc)
 
 	*rc = fan_set_level_safe(level);
 	if (*rc == -ENXIO)
-		printk(TPACPI_ERR "level command accepted for unsupported "
-		       "access mode %d", fan_control_access_mode);
+		pr_err("level command accepted for unsupported access mode %d\n",
+		       fan_control_access_mode);
 	else if (!*rc)
 		tpacpi_disclose_usertask("procfs fan",
 			"set level to %d\n", level);
@@ -8321,8 +8236,8 @@ static int fan_write_cmd_enable(const char *cmd, int *rc)
 
 	*rc = fan_set_enable();
 	if (*rc == -ENXIO)
-		printk(TPACPI_ERR "enable command accepted for unsupported "
-		       "access mode %d", fan_control_access_mode);
+		pr_err("enable command accepted for unsupported access mode %d\n",
+		       fan_control_access_mode);
 	else if (!*rc)
 		tpacpi_disclose_usertask("procfs fan", "enable\n");
 
@@ -8336,8 +8251,8 @@ static int fan_write_cmd_disable(const char *cmd, int *rc)
 
 	*rc = fan_set_disable();
 	if (*rc == -ENXIO)
-		printk(TPACPI_ERR "disable command accepted for unsupported "
-		       "access mode %d", fan_control_access_mode);
+		pr_err("disable command accepted for unsupported access mode %d\n",
+		       fan_control_access_mode);
 	else if (!*rc)
 		tpacpi_disclose_usertask("procfs fan", "disable\n");
 
@@ -8356,8 +8271,8 @@ static int fan_write_cmd_speed(const char *cmd, int *rc)
 
 	*rc = fan_set_speed(speed);
 	if (*rc == -ENXIO)
-		printk(TPACPI_ERR "speed command accepted for unsupported "
-		       "access mode %d", fan_control_access_mode);
+		pr_err("speed command accepted for unsupported access mode %d\n",
+		       fan_control_access_mode);
 	else if (!*rc)
 		tpacpi_disclose_usertask("procfs fan",
 			"set speed to %d\n", speed);
@@ -8560,8 +8475,8 @@ static int __init ibm_init(struct ibm_init_struct *iibm)
 		if (ibm->acpi->notify) {
 			ret = setup_acpi_notify(ibm);
 			if (ret == -ENODEV) {
-				printk(TPACPI_NOTICE "disabling subdriver %s\n",
-					ibm->name);
+				pr_notice("disabling subdriver %s\n",
+					  ibm->name);
 				ret = 0;
 				goto err_out;
 			}
@@ -8583,8 +8498,7 @@ static int __init ibm_init(struct ibm_init_struct *iibm)
 		entry = proc_create_data(ibm->name, mode, proc_dir,
 					 &dispatch_proc_fops, ibm);
 		if (!entry) {
-			printk(TPACPI_ERR "unable to create proc entry %s\n",
-			       ibm->name);
+			pr_err("unable to create proc entry %s\n", ibm->name);
 			ret = -ENODEV;
 			goto err_out;
 		}
@@ -8683,13 +8597,11 @@ static int __must_check __init get_thinkpad_model_data(
 				tp->ec_release = (ec_fw_string[4] << 8)
 						| ec_fw_string[5];
 			} else {
-				printk(TPACPI_NOTICE
-					"ThinkPad firmware release %s "
-					"doesn't match the known patterns\n",
-					ec_fw_string);
-				printk(TPACPI_NOTICE
-					"please report this to %s\n",
-					TPACPI_MAIL);
+				pr_notice("ThinkPad firmware release %s "
+					  "doesn't match the known patterns\n",
+					  ec_fw_string);
+				pr_notice("please report this to %s\n",
+					  TPACPI_MAIL);
 			}
 			break;
 		}
@@ -8733,8 +8645,7 @@ static int __init probe_for_thinkpad(void)
 	tpacpi_acpi_handle_locate("ec", TPACPI_ACPI_EC_HID, &ec_handle);
 	if (!ec_handle) {
 		if (is_thinkpad)
-			printk(TPACPI_ERR
-				"Not yet supported ThinkPad detected!\n");
+			pr_err("Not yet supported ThinkPad detected!\n");
 		return -ENODEV;
 	}
 
@@ -8746,10 +8657,10 @@ static int __init probe_for_thinkpad(void)
 
 static void __init thinkpad_acpi_init_banner(void)
 {
-	printk(TPACPI_INFO "%s v%s\n", TPACPI_DESC, TPACPI_VERSION);
-	printk(TPACPI_INFO "%s\n", TPACPI_URL);
+	pr_info("%s v%s\n", TPACPI_DESC, TPACPI_VERSION);
+	pr_info("%s\n", TPACPI_URL);
 
-	printk(TPACPI_INFO "ThinkPad BIOS %s, EC %s\n",
+	pr_info("ThinkPad BIOS %s, EC %s\n",
 		(thinkpad_id.bios_version_str) ?
 			thinkpad_id.bios_version_str : "unknown",
 		(thinkpad_id.ec_version_str) ?
@@ -8758,7 +8669,7 @@ static void __init thinkpad_acpi_init_banner(void)
 	BUG_ON(!thinkpad_id.vendor);
 
 	if (thinkpad_id.model_str)
-		printk(TPACPI_INFO "%s %s, model %s\n",
+		pr_info("%s %s, model %s\n",
 			(thinkpad_id.vendor == PCI_VENDOR_ID_IBM) ?
 				"IBM" : ((thinkpad_id.vendor ==
 						PCI_VENDOR_ID_LENOVO) ?
@@ -9024,8 +8935,7 @@ static int __init thinkpad_acpi_module_init(void)
 
 	ret = get_thinkpad_model_data(&thinkpad_id);
 	if (ret) {
-		printk(TPACPI_ERR
-			"unable to get DMI data: %d\n", ret);
+		pr_err("unable to get DMI data: %d\n", ret);
 		thinkpad_acpi_module_exit();
 		return ret;
 	}
@@ -9051,16 +8961,14 @@ static int __init thinkpad_acpi_module_init(void)
 
 	proc_dir = proc_mkdir(TPACPI_PROC_DIR, acpi_root_dir);
 	if (!proc_dir) {
-		printk(TPACPI_ERR
-		       "unable to create proc dir " TPACPI_PROC_DIR);
+		pr_err("unable to create proc dir " TPACPI_PROC_DIR "\n");
 		thinkpad_acpi_module_exit();
 		return -ENODEV;
 	}
 
 	ret = platform_driver_register(&tpacpi_pdriver);
 	if (ret) {
-		printk(TPACPI_ERR
-		       "unable to register main platform driver\n");
+		pr_err("unable to register main platform driver\n");
 		thinkpad_acpi_module_exit();
 		return ret;
 	}
@@ -9068,8 +8976,7 @@ static int __init thinkpad_acpi_module_init(void)
 
 	ret = platform_driver_register(&tpacpi_hwmon_pdriver);
 	if (ret) {
-		printk(TPACPI_ERR
-		       "unable to register hwmon platform driver\n");
+		pr_err("unable to register hwmon platform driver\n");
 		thinkpad_acpi_module_exit();
 		return ret;
 	}
@@ -9082,8 +8989,7 @@ static int __init thinkpad_acpi_module_init(void)
 					&tpacpi_hwmon_pdriver.driver);
 	}
 	if (ret) {
-		printk(TPACPI_ERR
-		       "unable to create sysfs driver attributes\n");
+		pr_err("unable to create sysfs driver attributes\n");
 		thinkpad_acpi_module_exit();
 		return ret;
 	}
@@ -9096,7 +9002,7 @@ static int __init thinkpad_acpi_module_init(void)
 	if (IS_ERR(tpacpi_pdev)) {
 		ret = PTR_ERR(tpacpi_pdev);
 		tpacpi_pdev = NULL;
-		printk(TPACPI_ERR "unable to register platform device\n");
+		pr_err("unable to register platform device\n");
 		thinkpad_acpi_module_exit();
 		return ret;
 	}
@@ -9106,16 +9012,14 @@ static int __init thinkpad_acpi_module_init(void)
 	if (IS_ERR(tpacpi_sensors_pdev)) {
 		ret = PTR_ERR(tpacpi_sensors_pdev);
 		tpacpi_sensors_pdev = NULL;
-		printk(TPACPI_ERR
-		       "unable to register hwmon platform device\n");
+		pr_err("unable to register hwmon platform device\n");
 		thinkpad_acpi_module_exit();
 		return ret;
 	}
 	ret = device_create_file(&tpacpi_sensors_pdev->dev,
 				 &dev_attr_thinkpad_acpi_pdev_name);
 	if (ret) {
-		printk(TPACPI_ERR
-		       "unable to create sysfs hwmon device attributes\n");
+		pr_err("unable to create sysfs hwmon device attributes\n");
 		thinkpad_acpi_module_exit();
 		return ret;
 	}
@@ -9124,14 +9028,14 @@ static int __init thinkpad_acpi_module_init(void)
 	if (IS_ERR(tpacpi_hwmon)) {
 		ret = PTR_ERR(tpacpi_hwmon);
 		tpacpi_hwmon = NULL;
-		printk(TPACPI_ERR "unable to register hwmon device\n");
+		pr_err("unable to register hwmon device\n");
 		thinkpad_acpi_module_exit();
 		return ret;
 	}
 	mutex_init(&tpacpi_inputdev_send_mutex);
 	tpacpi_inputdev = input_allocate_device();
 	if (!tpacpi_inputdev) {
-		printk(TPACPI_ERR "unable to allocate input device\n");
+		pr_err("unable to allocate input device\n");
 		thinkpad_acpi_module_exit();
 		return -ENOMEM;
 	} else {
@@ -9163,7 +9067,7 @@ static int __init thinkpad_acpi_module_init(void)
 
 	ret = input_register_device(tpacpi_inputdev);
 	if (ret < 0) {
-		printk(TPACPI_ERR "unable to register input device\n");
+		pr_err("unable to register input device\n");
 		thinkpad_acpi_module_exit();
 		return ret;
 	} else {
diff --git a/drivers/platform/x86/topstar-laptop.c b/drivers/platform/x86/topstar-laptop.c
index 1d07d6d09f27..4c20447ddbb7 100644
--- a/drivers/platform/x86/topstar-laptop.c
+++ b/drivers/platform/x86/topstar-laptop.c
@@ -194,7 +194,7 @@ static int __init topstar_laptop_init(void)
 	if (ret < 0)
 		return ret;
 
-	printk(KERN_INFO "Topstar Laptop ACPI extras driver loaded\n");
+	pr_info("ACPI extras driver loaded\n");
 
 	return 0;
 }
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index 63f42a22e102..cb009b2629ee 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -35,6 +35,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #define TOSHIBA_ACPI_VERSION	"0.19"
 #define PROC_INTERFACE_VERSION	1
 
@@ -60,11 +62,6 @@ MODULE_AUTHOR("John Belmonte");
 MODULE_DESCRIPTION("Toshiba Laptop ACPI Extras Driver");
 MODULE_LICENSE("GPL");
 
-#define MY_LOGPREFIX "toshiba_acpi: "
-#define MY_ERR KERN_ERR MY_LOGPREFIX
-#define MY_NOTICE KERN_NOTICE MY_LOGPREFIX
-#define MY_INFO KERN_INFO MY_LOGPREFIX
-
 /* Toshiba ACPI method paths */
 #define METHOD_LCD_BRIGHTNESS	"\\_SB_.PCI0.VGA_.LCD_._BCM"
 #define TOSH_INTERFACE_1	"\\_SB_.VALD"
@@ -301,7 +298,7 @@ static int toshiba_illumination_available(void)
 	in[0] = 0xf100;
 	status = hci_raw(in, out);
 	if (ACPI_FAILURE(status)) {
-		printk(MY_INFO "Illumination device not available\n");
+		pr_info("Illumination device not available\n");
 		return 0;
 	}
 	in[0] = 0xf400;
@@ -320,7 +317,7 @@ static void toshiba_illumination_set(struct led_classdev *cdev,
 	in[0] = 0xf100;
 	status = hci_raw(in, out);
 	if (ACPI_FAILURE(status)) {
-		printk(MY_INFO "Illumination device not available\n");
+		pr_info("Illumination device not available\n");
 		return;
 	}
 
@@ -331,7 +328,7 @@ static void toshiba_illumination_set(struct led_classdev *cdev,
 		in[2] = 1;
 		status = hci_raw(in, out);
 		if (ACPI_FAILURE(status)) {
-			printk(MY_INFO "ACPI call for illumination failed.\n");
+			pr_info("ACPI call for illumination failed\n");
 			return;
 		}
 	} else {
@@ -341,7 +338,7 @@ static void toshiba_illumination_set(struct led_classdev *cdev,
 		in[2] = 0;
 		status = hci_raw(in, out);
 		if (ACPI_FAILURE(status)) {
-			printk(MY_INFO "ACPI call for illumination failed.\n");
+			pr_info("ACPI call for illumination failed.\n");
 			return;
 		}
 	}
@@ -364,7 +361,7 @@ static enum led_brightness toshiba_illumination_get(struct led_classdev *cdev)
 	in[0] = 0xf100;
 	status = hci_raw(in, out);
 	if (ACPI_FAILURE(status)) {
-		printk(MY_INFO "Illumination device not available\n");
+		pr_info("Illumination device not available\n");
 		return LED_OFF;
 	}
 
@@ -373,7 +370,7 @@ static enum led_brightness toshiba_illumination_get(struct led_classdev *cdev)
 	in[1] = 0x14e;
 	status = hci_raw(in, out);
 	if (ACPI_FAILURE(status)) {
-		printk(MY_INFO "ACPI call for illumination failed.\n");
+		pr_info("ACPI call for illumination failed.\n");
 		return LED_OFF;
 	}
 
@@ -517,7 +514,7 @@ static int lcd_proc_show(struct seq_file *m, void *v)
 		seq_printf(m, "brightness_levels:       %d\n",
 			     HCI_LCD_BRIGHTNESS_LEVELS);
 	} else {
-		printk(MY_ERR "Error reading LCD brightness\n");
+		pr_err("Error reading LCD brightness\n");
 	}
 
 	return 0;
@@ -592,7 +589,7 @@ static int video_proc_show(struct seq_file *m, void *v)
 		seq_printf(m, "crt_out:                 %d\n", is_crt);
 		seq_printf(m, "tv_out:                  %d\n", is_tv);
 	} else {
-		printk(MY_ERR "Error reading video out status\n");
+		pr_err("Error reading video out status\n");
 	}
 
 	return 0;
@@ -686,7 +683,7 @@ static int fan_proc_show(struct seq_file *m, void *v)
 		seq_printf(m, "running:                 %d\n", (value > 0));
 		seq_printf(m, "force_on:                %d\n", force_fan);
 	} else {
-		printk(MY_ERR "Error reading fan status\n");
+		pr_err("Error reading fan status\n");
 	}
 
 	return 0;
@@ -750,9 +747,9 @@ static int keys_proc_show(struct seq_file *m, void *v)
 			 * some machines where system events sporadically
 			 * become disabled. */
 			hci_write1(HCI_SYSTEM_EVENT, 1, &hci_result);
-			printk(MY_NOTICE "Re-enabled hotkeys\n");
+			pr_notice("Re-enabled hotkeys\n");
 		} else {
-			printk(MY_ERR "Error reading hotkey status\n");
+			pr_err("Error reading hotkey status\n");
 			goto end;
 		}
 	}
@@ -863,7 +860,7 @@ static void toshiba_acpi_notify(acpi_handle handle, u32 event, void *context)
 
 			if (!sparse_keymap_report_event(toshiba_acpi.hotkey_dev,
 							value, 1, true)) {
-				printk(MY_INFO "Unknown key %x\n",
+				pr_info("Unknown key %x\n",
 				       value);
 			}
 		} else if (hci_result == HCI_NOT_SUPPORTED) {
@@ -871,7 +868,7 @@ static void toshiba_acpi_notify(acpi_handle handle, u32 event, void *context)
 			 * some machines where system events sporadically
 			 * become disabled. */
 			hci_write1(HCI_SYSTEM_EVENT, 1, &hci_result);
-			printk(MY_NOTICE "Re-enabled hotkeys\n");
+			pr_notice("Re-enabled hotkeys\n");
 		}
 	} while (hci_result != HCI_EMPTY);
 }
@@ -883,13 +880,13 @@ static int __init toshiba_acpi_setup_keyboard(char *device)
 
 	status = acpi_get_handle(NULL, device, &toshiba_acpi.handle);
 	if (ACPI_FAILURE(status)) {
-		printk(MY_INFO "Unable to get notification device\n");
+		pr_info("Unable to get notification device\n");
 		return -ENODEV;
 	}
 
 	toshiba_acpi.hotkey_dev = input_allocate_device();
 	if (!toshiba_acpi.hotkey_dev) {
-		printk(MY_INFO "Unable to register input device\n");
+		pr_info("Unable to register input device\n");
 		return -ENOMEM;
 	}
 
@@ -905,21 +902,21 @@ static int __init toshiba_acpi_setup_keyboard(char *device)
 	status = acpi_install_notify_handler(toshiba_acpi.handle,
 				ACPI_DEVICE_NOTIFY, toshiba_acpi_notify, NULL);
 	if (ACPI_FAILURE(status)) {
-		printk(MY_INFO "Unable to install hotkey notification\n");
+		pr_info("Unable to install hotkey notification\n");
 		error = -ENODEV;
 		goto err_free_keymap;
 	}
 
 	status = acpi_evaluate_object(toshiba_acpi.handle, "ENAB", NULL, NULL);
 	if (ACPI_FAILURE(status)) {
-		printk(MY_INFO "Unable to enable hotkeys\n");
+		pr_info("Unable to enable hotkeys\n");
 		error = -ENODEV;
 		goto err_remove_notify;
 	}
 
 	error = input_register_device(toshiba_acpi.hotkey_dev);
 	if (error) {
-		printk(MY_INFO "Unable to register input device\n");
+		pr_info("Unable to register input device\n");
 		goto err_remove_notify;
 	}
 
@@ -980,17 +977,17 @@ static int __init toshiba_acpi_init(void)
 	if (is_valid_acpi_path(TOSH_INTERFACE_1 GHCI_METHOD)) {
 		method_hci = TOSH_INTERFACE_1 GHCI_METHOD;
 		if (toshiba_acpi_setup_keyboard(TOSH_INTERFACE_1))
-			printk(MY_INFO "Unable to activate hotkeys\n");
+			pr_info("Unable to activate hotkeys\n");
 	} else if (is_valid_acpi_path(TOSH_INTERFACE_2 GHCI_METHOD)) {
 		method_hci = TOSH_INTERFACE_2 GHCI_METHOD;
 		if (toshiba_acpi_setup_keyboard(TOSH_INTERFACE_2))
-			printk(MY_INFO "Unable to activate hotkeys\n");
+			pr_info("Unable to activate hotkeys\n");
 	} else
 		return -ENODEV;
 
-	printk(MY_INFO "Toshiba Laptop ACPI Extras version %s\n",
+	pr_info("Toshiba Laptop ACPI Extras version %s\n",
 	       TOSHIBA_ACPI_VERSION);
-	printk(MY_INFO "    HCI method: %s\n", method_hci);
+	pr_info("    HCI method: %s\n", method_hci);
 
 	mutex_init(&toshiba_acpi.mutex);
 
@@ -998,7 +995,7 @@ static int __init toshiba_acpi_init(void)
 							      -1, NULL, 0);
 	if (IS_ERR(toshiba_acpi.p_dev)) {
 		ret = PTR_ERR(toshiba_acpi.p_dev);
-		printk(MY_ERR "unable to register platform device\n");
+		pr_err("unable to register platform device\n");
 		toshiba_acpi.p_dev = NULL;
 		toshiba_acpi_exit();
 		return ret;
@@ -1028,7 +1025,7 @@ static int __init toshiba_acpi_init(void)
         if (IS_ERR(toshiba_backlight_device)) {
 		ret = PTR_ERR(toshiba_backlight_device);
 
-		printk(KERN_ERR "Could not register toshiba backlight device\n");
+		pr_err("Could not register toshiba backlight device\n");
 		toshiba_backlight_device = NULL;
 		toshiba_acpi_exit();
 		return ret;
@@ -1042,14 +1039,14 @@ static int __init toshiba_acpi_init(void)
 						   &toshiba_rfk_ops,
 						   &toshiba_acpi);
 		if (!toshiba_acpi.bt_rfk) {
-			printk(MY_ERR "unable to allocate rfkill device\n");
+			pr_err("unable to allocate rfkill device\n");
 			toshiba_acpi_exit();
 			return -ENOMEM;
 		}
 
 		ret = rfkill_register(toshiba_acpi.bt_rfk);
 		if (ret) {
-			printk(MY_ERR "unable to register rfkill device\n");
+			pr_err("unable to register rfkill device\n");
 			rfkill_destroy(toshiba_acpi.bt_rfk);
 			toshiba_acpi_exit();
 			return ret;
diff --git a/drivers/platform/x86/toshiba_bluetooth.c b/drivers/platform/x86/toshiba_bluetooth.c
index 944068611919..5fb7186694df 100644
--- a/drivers/platform/x86/toshiba_bluetooth.c
+++ b/drivers/platform/x86/toshiba_bluetooth.c
@@ -17,6 +17,8 @@
  * delivered.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -70,14 +72,13 @@ static int toshiba_bluetooth_enable(acpi_handle handle)
 	if (!(result & 0x01))
 		return 0;
 
-	printk(KERN_INFO "toshiba_bluetooth: Re-enabling Toshiba Bluetooth\n");
+	pr_info("Re-enabling Toshiba Bluetooth\n");
 	res1 = acpi_evaluate_object(handle, "AUSB", NULL, NULL);
 	res2 = acpi_evaluate_object(handle, "BTPO", NULL, NULL);
 	if (!ACPI_FAILURE(res1) || !ACPI_FAILURE(res2))
 		return 0;
 
-	printk(KERN_WARNING "toshiba_bluetooth: Failed to re-enable "
-	       "Toshiba Bluetooth\n");
+	pr_warn("Failed to re-enable Toshiba Bluetooth\n");
 
 	return -ENODEV;
 }
@@ -107,8 +108,8 @@ static int toshiba_bt_rfkill_add(struct acpi_device *device)
 				       &bt_present);
 
 	if (!ACPI_FAILURE(status) && bt_present) {
-		printk(KERN_INFO "Detected Toshiba ACPI Bluetooth device - "
-		      "installing RFKill handler\n");
+		pr_info("Detected Toshiba ACPI Bluetooth device - "
+			"installing RFKill handler\n");
 		result = toshiba_bluetooth_enable(device->handle);
 	}
 
diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index 05cc79672a8b..f23d5a84e7b1 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -486,16 +486,16 @@ static void wmi_dump_wdg(const struct guid_block *g)
 	pr_info("\tnotify_id: %02X\n", g->notify_id);
 	pr_info("\treserved: %02X\n", g->reserved);
 	pr_info("\tinstance_count: %d\n", g->instance_count);
-	pr_info("\tflags: %#x ", g->flags);
+	pr_info("\tflags: %#x", g->flags);
 	if (g->flags) {
 		if (g->flags & ACPI_WMI_EXPENSIVE)
-			pr_cont("ACPI_WMI_EXPENSIVE ");
+			pr_cont(" ACPI_WMI_EXPENSIVE");
 		if (g->flags & ACPI_WMI_METHOD)
-			pr_cont("ACPI_WMI_METHOD ");
+			pr_cont(" ACPI_WMI_METHOD");
 		if (g->flags & ACPI_WMI_STRING)
-			pr_cont("ACPI_WMI_STRING ");
+			pr_cont(" ACPI_WMI_STRING");
 		if (g->flags & ACPI_WMI_EVENT)
-			pr_cont("ACPI_WMI_EVENT ");
+			pr_cont(" ACPI_WMI_EVENT");
 	}
 	pr_cont("\n");
 
diff --git a/drivers/platform/x86/xo15-ebook.c b/drivers/platform/x86/xo15-ebook.c
index c1372ed9d2e9..fad153dc0355 100644
--- a/drivers/platform/x86/xo15-ebook.c
+++ b/drivers/platform/x86/xo15-ebook.c
@@ -11,6 +11,8 @@
  *  your option) any later version.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -20,7 +22,6 @@
 #include <acpi/acpi_drivers.h>
 
 #define MODULE_NAME "xo15-ebook"
-#define PREFIX MODULE_NAME ": "
 
 #define XO15_EBOOK_CLASS		MODULE_NAME
 #define XO15_EBOOK_TYPE_UNKNOWN	0x00
@@ -105,7 +106,7 @@ static int ebook_switch_add(struct acpi_device *device)
 	class = acpi_device_class(device);
 
 	if (strcmp(hid, XO15_EBOOK_HID)) {
-		printk(KERN_ERR PREFIX "Unsupported hid [%s]\n", hid);
+		pr_err("Unsupported hid [%s]\n", hid);
 		error = -ENODEV;
 		goto err_free_input;
 	}
diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index dc8c531ed276..e57b50b38565 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -210,6 +210,15 @@ config CHARGER_ISP1704
 	  Say Y to enable support for USB Charger Detection with
 	  ISP1707/ISP1704 USB transceivers.
 
+config CHARGER_MAX8903
+	tristate "MAX8903 Battery DC-DC Charger for USB and Adapter Power"
+	depends on GENERIC_HARDIRQS
+	help
+	  Say Y to enable support for the MAX8903 DC-DC charger and sysfs.
+	  The driver supports controlling charger-enable and current-limit
+	  pins based on the status of charger connections with interrupt
+	  handlers.
+
 config CHARGER_TWL4030
 	tristate "OMAP TWL4030 BCI charger driver"
 	depends on TWL4030_CORE
diff --git a/drivers/power/Makefile b/drivers/power/Makefile
index 8224990b933d..009a90fa8ac9 100644
--- a/drivers/power/Makefile
+++ b/drivers/power/Makefile
@@ -33,5 +33,6 @@ obj-$(CONFIG_CHARGER_PCF50633)	+= pcf50633-charger.o
 obj-$(CONFIG_BATTERY_JZ4740)	+= jz4740-battery.o
 obj-$(CONFIG_BATTERY_INTEL_MID)	+= intel_mid_battery.o
 obj-$(CONFIG_CHARGER_ISP1704)	+= isp1704_charger.o
+obj-$(CONFIG_CHARGER_MAX8903)	+= max8903_charger.o
 obj-$(CONFIG_CHARGER_TWL4030)	+= twl4030_charger.o
 obj-$(CONFIG_CHARGER_GPIO)	+= gpio-charger.o
diff --git a/drivers/power/bq27x00_battery.c b/drivers/power/bq27x00_battery.c
index 59e68dbd028b..bb16f5b7e167 100644
--- a/drivers/power/bq27x00_battery.c
+++ b/drivers/power/bq27x00_battery.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2008 Rodolfo Giometti <giometti@linux.it>
  * Copyright (C) 2008 Eurotech S.p.A. <info@eurotech.it>
  * Copyright (C) 2010-2011 Lars-Peter Clausen <lars@metafoo.de>
+ * Copyright (C) 2011 Pali Rohár <pali.rohar@gmail.com>
  *
  * Based on a previous work by Copyright (C) 2008 Texas Instruments, Inc.
  *
@@ -76,7 +77,7 @@ struct bq27x00_reg_cache {
 	int time_to_empty_avg;
 	int time_to_full;
 	int charge_full;
-	int charge_counter;
+	int cycle_count;
 	int capacity;
 	int flags;
 
@@ -115,7 +116,7 @@ static enum power_supply_property bq27x00_battery_props[] = {
 	POWER_SUPPLY_PROP_CHARGE_FULL,
 	POWER_SUPPLY_PROP_CHARGE_NOW,
 	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
-	POWER_SUPPLY_PROP_CHARGE_COUNTER,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
 	POWER_SUPPLY_PROP_ENERGY_NOW,
 };
 
@@ -267,7 +268,7 @@ static void bq27x00_update(struct bq27x00_device_info *di)
 		cache.time_to_empty_avg = bq27x00_battery_read_time(di, BQ27x00_REG_TTECP);
 		cache.time_to_full = bq27x00_battery_read_time(di, BQ27x00_REG_TTF);
 		cache.charge_full = bq27x00_battery_read_lmd(di);
-		cache.charge_counter = bq27x00_battery_read_cyct(di);
+		cache.cycle_count = bq27x00_battery_read_cyct(di);
 
 		if (!is_bq27500)
 			cache.current_now = bq27x00_read(di, BQ27x00_REG_AI, false);
@@ -496,8 +497,8 @@ static int bq27x00_battery_get_property(struct power_supply *psy,
 	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
 		ret = bq27x00_simple_value(di->charge_design_full, val);
 		break;
-	case POWER_SUPPLY_PROP_CHARGE_COUNTER:
-		ret = bq27x00_simple_value(di->cache.charge_counter, val);
+	case POWER_SUPPLY_PROP_CYCLE_COUNT:
+		ret = bq27x00_simple_value(di->cache.cycle_count, val);
 		break;
 	case POWER_SUPPLY_PROP_ENERGY_NOW:
 		ret = bq27x00_battery_energy(di, val);
diff --git a/drivers/power/ds2760_battery.c b/drivers/power/ds2760_battery.c
index e534290f3256..f2c9cc33c0f9 100644
--- a/drivers/power/ds2760_battery.c
+++ b/drivers/power/ds2760_battery.c
@@ -86,7 +86,11 @@ static int rated_capacities[] = {
 	920,	/* NEC */
 	1440,	/* Samsung */
 	1440,	/* BYD */
+#ifdef CONFIG_MACH_H4700
+	1800,	/* HP iPAQ hx4700 3.7V 1800mAh (359113-001) */
+#else
 	1440,	/* Lishen */
+#endif
 	1440,	/* NEC */
 	2880,	/* Samsung */
 	2880,	/* BYD */
@@ -186,7 +190,7 @@ static int ds2760_battery_read_status(struct ds2760_device_info *di)
 
 	scale[0] = di->full_active_uAh;
 	for (i = 1; i < 5; i++)
-		scale[i] = scale[i - 1] + di->raw[DS2760_ACTIVE_FULL + 2 + i];
+		scale[i] = scale[i - 1] + di->raw[DS2760_ACTIVE_FULL + 1 + i];
 
 	di->full_active_uAh = battery_interpolate(scale, di->temp_C / 10);
 	di->full_active_uAh *= 1000; /* convert to µAh */
diff --git a/drivers/power/gpio-charger.c b/drivers/power/gpio-charger.c
index 25b88ac1d44c..718f2c537827 100644
--- a/drivers/power/gpio-charger.c
+++ b/drivers/power/gpio-charger.c
@@ -161,12 +161,27 @@ static int __devexit gpio_charger_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int gpio_charger_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct gpio_charger *gpio_charger = platform_get_drvdata(pdev);
+
+	power_supply_changed(&gpio_charger->charger);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(gpio_charger_pm_ops, NULL, gpio_charger_resume);
+
 static struct platform_driver gpio_charger_driver = {
 	.probe = gpio_charger_probe,
 	.remove = __devexit_p(gpio_charger_remove),
 	.driver = {
 		.name = "gpio-charger",
 		.owner = THIS_MODULE,
+		.pm = &gpio_charger_pm_ops,
 	},
 };
 
diff --git a/drivers/power/isp1704_charger.c b/drivers/power/isp1704_charger.c
index 2ad9b14a5ce3..f6d72b402a8e 100644
--- a/drivers/power/isp1704_charger.c
+++ b/drivers/power/isp1704_charger.c
@@ -33,6 +33,7 @@
 #include <linux/usb/ulpi.h>
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
+#include <linux/power/isp1704_charger.h>
 
 /* Vendor specific Power Control register */
 #define ISP1704_PWR_CTRL		0x3d
@@ -71,6 +72,18 @@ struct isp1704_charger {
 };
 
 /*
+ * Disable/enable the power from the isp1704 if a function for it
+ * has been provided with platform data.
+ */
+static void isp1704_charger_set_power(struct isp1704_charger *isp, bool on)
+{
+	struct isp1704_charger_data	*board = isp->dev->platform_data;
+
+	if (board->set_power)
+		board->set_power(on);
+}
+
+/*
  * Determine is the charging port DCP (dedicated charger) or CDP (Host/HUB
  * chargers).
  *
@@ -222,6 +235,9 @@ static void isp1704_charger_work(struct work_struct *data)
 
 	mutex_lock(&lock);
 
+	if (event != USB_EVENT_NONE)
+		isp1704_charger_set_power(isp, 1);
+
 	switch (event) {
 	case USB_EVENT_VBUS:
 		isp->online = true;
@@ -269,6 +285,8 @@ static void isp1704_charger_work(struct work_struct *data)
 		 */
 		if (isp->otg->gadget)
 			usb_gadget_disconnect(isp->otg->gadget);
+
+		isp1704_charger_set_power(isp, 0);
 		break;
 	case USB_EVENT_ENUMERATED:
 		if (isp->present)
@@ -394,6 +412,8 @@ static int __devinit isp1704_charger_probe(struct platform_device *pdev)
 	isp->dev = &pdev->dev;
 	platform_set_drvdata(pdev, isp);
 
+	isp1704_charger_set_power(isp, 1);
+
 	ret = isp1704_test_ulpi(isp);
 	if (ret < 0)
 		goto fail1;
@@ -434,6 +454,7 @@ static int __devinit isp1704_charger_probe(struct platform_device *pdev)
 
 	/* Detect charger if VBUS is valid (the cable was already plugged). */
 	ret = otg_io_read(isp->otg, ULPI_USB_INT_STS);
+	isp1704_charger_set_power(isp, 0);
 	if ((ret & ULPI_INT_VBUS_VALID) && !isp->otg->default_a) {
 		isp->event = USB_EVENT_VBUS;
 		schedule_work(&isp->work);
@@ -459,6 +480,7 @@ static int __devexit isp1704_charger_remove(struct platform_device *pdev)
 	otg_unregister_notifier(isp->otg, &isp->nb);
 	power_supply_unregister(&isp->psy);
 	otg_put_transceiver(isp->otg);
+	isp1704_charger_set_power(isp, 0);
 	kfree(isp);
 
 	return 0;
diff --git a/drivers/power/max8903_charger.c b/drivers/power/max8903_charger.c
new file mode 100644
index 000000000000..33ff0e37809e
--- /dev/null
+++ b/drivers/power/max8903_charger.c
@@ -0,0 +1,391 @@
+/*
+ * max8903_charger.c - Maxim 8903 USB/Adapter Charger Driver
+ *
+ * Copyright (C) 2011 Samsung Electronics
+ * MyungJoo Ham <myungjoo.ham@samsung.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.
+ *
+ * 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/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/power_supply.h>
+#include <linux/platform_device.h>
+#include <linux/power/max8903_charger.h>
+
+struct max8903_data {
+	struct max8903_pdata *pdata;
+	struct device *dev;
+	struct power_supply psy;
+	bool fault;
+	bool usb_in;
+	bool ta_in;
+};
+
+static enum power_supply_property max8903_charger_props[] = {
+	POWER_SUPPLY_PROP_STATUS, /* Charger status output */
+	POWER_SUPPLY_PROP_ONLINE, /* External power source */
+	POWER_SUPPLY_PROP_HEALTH, /* Fault or OK */
+};
+
+static int max8903_get_property(struct power_supply *psy,
+		enum power_supply_property psp,
+		union power_supply_propval *val)
+{
+	struct max8903_data *data = container_of(psy,
+			struct max8903_data, psy);
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_STATUS:
+		val->intval = POWER_SUPPLY_STATUS_UNKNOWN;
+		if (data->pdata->chg) {
+			if (gpio_get_value(data->pdata->chg) == 0)
+				val->intval = POWER_SUPPLY_STATUS_CHARGING;
+			else if (data->usb_in || data->ta_in)
+				val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING;
+			else
+				val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
+		}
+		break;
+	case POWER_SUPPLY_PROP_ONLINE:
+		val->intval = 0;
+		if (data->usb_in || data->ta_in)
+			val->intval = 1;
+		break;
+	case POWER_SUPPLY_PROP_HEALTH:
+		val->intval = POWER_SUPPLY_HEALTH_GOOD;
+		if (data->fault)
+			val->intval = POWER_SUPPLY_HEALTH_UNSPEC_FAILURE;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static irqreturn_t max8903_dcin(int irq, void *_data)
+{
+	struct max8903_data *data = _data;
+	struct max8903_pdata *pdata = data->pdata;
+	bool ta_in;
+	enum power_supply_type old_type;
+
+	ta_in = gpio_get_value(pdata->dok) ? false : true;
+
+	if (ta_in == data->ta_in)
+		return IRQ_HANDLED;
+
+	data->ta_in = ta_in;
+
+	/* Set Current-Limit-Mode 1:DC 0:USB */
+	if (pdata->dcm)
+		gpio_set_value(pdata->dcm, ta_in ? 1 : 0);
+
+	/* Charger Enable / Disable (cen is negated) */
+	if (pdata->cen)
+		gpio_set_value(pdata->cen, ta_in ? 0 :
+				(data->usb_in ? 0 : 1));
+
+	dev_dbg(data->dev, "TA(DC-IN) Charger %s.\n", ta_in ?
+			"Connected" : "Disconnected");
+
+	old_type = data->psy.type;
+
+	if (data->ta_in)
+		data->psy.type = POWER_SUPPLY_TYPE_MAINS;
+	else if (data->usb_in)
+		data->psy.type = POWER_SUPPLY_TYPE_USB;
+	else
+		data->psy.type = POWER_SUPPLY_TYPE_BATTERY;
+
+	if (old_type != data->psy.type)
+		power_supply_changed(&data->psy);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t max8903_usbin(int irq, void *_data)
+{
+	struct max8903_data *data = _data;
+	struct max8903_pdata *pdata = data->pdata;
+	bool usb_in;
+	enum power_supply_type old_type;
+
+	usb_in = gpio_get_value(pdata->uok) ? false : true;
+
+	if (usb_in == data->usb_in)
+		return IRQ_HANDLED;
+
+	data->usb_in = usb_in;
+
+	/* Do not touch Current-Limit-Mode */
+
+	/* Charger Enable / Disable (cen is negated) */
+	if (pdata->cen)
+		gpio_set_value(pdata->cen, usb_in ? 0 :
+				(data->ta_in ? 0 : 1));
+
+	dev_dbg(data->dev, "USB Charger %s.\n", usb_in ?
+			"Connected" : "Disconnected");
+
+	old_type = data->psy.type;
+
+	if (data->ta_in)
+		data->psy.type = POWER_SUPPLY_TYPE_MAINS;
+	else if (data->usb_in)
+		data->psy.type = POWER_SUPPLY_TYPE_USB;
+	else
+		data->psy.type = POWER_SUPPLY_TYPE_BATTERY;
+
+	if (old_type != data->psy.type)
+		power_supply_changed(&data->psy);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t max8903_fault(int irq, void *_data)
+{
+	struct max8903_data *data = _data;
+	struct max8903_pdata *pdata = data->pdata;
+	bool fault;
+
+	fault = gpio_get_value(pdata->flt) ? false : true;
+
+	if (fault == data->fault)
+		return IRQ_HANDLED;
+
+	data->fault = fault;
+
+	if (fault)
+		dev_err(data->dev, "Charger suffers a fault and stops.\n");
+	else
+		dev_err(data->dev, "Charger recovered from a fault.\n");
+
+	return IRQ_HANDLED;
+}
+
+static __devinit int max8903_probe(struct platform_device *pdev)
+{
+	struct max8903_data *data;
+	struct device *dev = &pdev->dev;
+	struct max8903_pdata *pdata = pdev->dev.platform_data;
+	int ret = 0;
+	int gpio;
+	int ta_in = 0;
+	int usb_in = 0;
+
+	data = kzalloc(sizeof(struct max8903_data), GFP_KERNEL);
+	if (data == NULL) {
+		dev_err(dev, "Cannot allocate memory.\n");
+		return -ENOMEM;
+	}
+	data->pdata = pdata;
+	data->dev = dev;
+	platform_set_drvdata(pdev, data);
+
+	if (pdata->dc_valid == false && pdata->usb_valid == false) {
+		dev_err(dev, "No valid power sources.\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	if (pdata->dc_valid) {
+		if (pdata->dok && gpio_is_valid(pdata->dok) &&
+				pdata->dcm && gpio_is_valid(pdata->dcm)) {
+			gpio = pdata->dok; /* PULL_UPed Interrupt */
+			ta_in = gpio_get_value(gpio) ? 0 : 1;
+
+			gpio = pdata->dcm; /* Output */
+			gpio_set_value(gpio, ta_in);
+		} else {
+			dev_err(dev, "When DC is wired, DOK and DCM should"
+					" be wired as well.\n");
+			ret = -EINVAL;
+			goto err;
+		}
+	} else {
+		if (pdata->dcm) {
+			if (gpio_is_valid(pdata->dcm))
+				gpio_set_value(pdata->dcm, 0);
+			else {
+				dev_err(dev, "Invalid pin: dcm.\n");
+				ret = -EINVAL;
+				goto err;
+			}
+		}
+	}
+
+	if (pdata->usb_valid) {
+		if (pdata->uok && gpio_is_valid(pdata->uok)) {
+			gpio = pdata->uok;
+			usb_in = gpio_get_value(gpio) ? 0 : 1;
+		} else {
+			dev_err(dev, "When USB is wired, UOK should be wired."
+					"as well.\n");
+			ret = -EINVAL;
+			goto err;
+		}
+	}
+
+	if (pdata->cen) {
+		if (gpio_is_valid(pdata->cen)) {
+			gpio_set_value(pdata->cen, (ta_in || usb_in) ? 0 : 1);
+		} else {
+			dev_err(dev, "Invalid pin: cen.\n");
+			ret = -EINVAL;
+			goto err;
+		}
+	}
+
+	if (pdata->chg) {
+		if (!gpio_is_valid(pdata->chg)) {
+			dev_err(dev, "Invalid pin: chg.\n");
+			ret = -EINVAL;
+			goto err;
+		}
+	}
+
+	if (pdata->flt) {
+		if (!gpio_is_valid(pdata->flt)) {
+			dev_err(dev, "Invalid pin: flt.\n");
+			ret = -EINVAL;
+			goto err;
+		}
+	}
+
+	if (pdata->usus) {
+		if (!gpio_is_valid(pdata->usus)) {
+			dev_err(dev, "Invalid pin: usus.\n");
+			ret = -EINVAL;
+			goto err;
+		}
+	}
+
+	data->fault = false;
+	data->ta_in = ta_in;
+	data->usb_in = usb_in;
+
+	data->psy.name = "max8903_charger";
+	data->psy.type = (ta_in) ? POWER_SUPPLY_TYPE_MAINS :
+			((usb_in) ? POWER_SUPPLY_TYPE_USB :
+			 POWER_SUPPLY_TYPE_BATTERY);
+	data->psy.get_property = max8903_get_property;
+	data->psy.properties = max8903_charger_props;
+	data->psy.num_properties = ARRAY_SIZE(max8903_charger_props);
+
+	ret = power_supply_register(dev, &data->psy);
+	if (ret) {
+		dev_err(dev, "failed: power supply register.\n");
+		goto err;
+	}
+
+	if (pdata->dc_valid) {
+		ret = request_threaded_irq(gpio_to_irq(pdata->dok),
+				NULL, max8903_dcin,
+				IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
+				"MAX8903 DC IN", data);
+		if (ret) {
+			dev_err(dev, "Cannot request irq %d for DC (%d)\n",
+					gpio_to_irq(pdata->dok), ret);
+			goto err_psy;
+		}
+	}
+
+	if (pdata->usb_valid) {
+		ret = request_threaded_irq(gpio_to_irq(pdata->uok),
+				NULL, max8903_usbin,
+				IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
+				"MAX8903 USB IN", data);
+		if (ret) {
+			dev_err(dev, "Cannot request irq %d for USB (%d)\n",
+					gpio_to_irq(pdata->uok), ret);
+			goto err_dc_irq;
+		}
+	}
+
+	if (pdata->flt) {
+		ret = request_threaded_irq(gpio_to_irq(pdata->flt),
+				NULL, max8903_fault,
+				IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
+				"MAX8903 Fault", data);
+		if (ret) {
+			dev_err(dev, "Cannot request irq %d for Fault (%d)\n",
+					gpio_to_irq(pdata->flt), ret);
+			goto err_usb_irq;
+		}
+	}
+
+	return 0;
+
+err_usb_irq:
+	if (pdata->usb_valid)
+		free_irq(gpio_to_irq(pdata->uok), data);
+err_dc_irq:
+	if (pdata->dc_valid)
+		free_irq(gpio_to_irq(pdata->dok), data);
+err_psy:
+	power_supply_unregister(&data->psy);
+err:
+	kfree(data);
+	return ret;
+}
+
+static __devexit int max8903_remove(struct platform_device *pdev)
+{
+	struct max8903_data *data = platform_get_drvdata(pdev);
+
+	if (data) {
+		struct max8903_pdata *pdata = data->pdata;
+
+		if (pdata->flt)
+			free_irq(gpio_to_irq(pdata->flt), data);
+		if (pdata->usb_valid)
+			free_irq(gpio_to_irq(pdata->uok), data);
+		if (pdata->dc_valid)
+			free_irq(gpio_to_irq(pdata->dok), data);
+		power_supply_unregister(&data->psy);
+		kfree(data);
+	}
+
+	return 0;
+}
+
+static struct platform_driver max8903_driver = {
+	.probe	= max8903_probe,
+	.remove	= __devexit_p(max8903_remove),
+	.driver = {
+		.name	= "max8903-charger",
+		.owner	= THIS_MODULE,
+	},
+};
+
+static int __init max8903_init(void)
+{
+	return platform_driver_register(&max8903_driver);
+}
+module_init(max8903_init);
+
+static void __exit max8903_exit(void)
+{
+	platform_driver_unregister(&max8903_driver);
+}
+module_exit(max8903_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MAX8903 Charger Driver");
+MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
+MODULE_ALIAS("max8903-charger");
diff --git a/drivers/power/test_power.c b/drivers/power/test_power.c
index 0cd9f67d33e5..b527c93bf2f3 100644
--- a/drivers/power/test_power.c
+++ b/drivers/power/test_power.c
@@ -3,6 +3,12 @@
  *
  * Copyright 2010  Anton Vorontsov <cbouatmailru@gmail.com>
  *
+ * Dynamic module parameter code from the Virtual Battery Driver
+ * Copyright (C) 2008 Pylone, Inc.
+ * By: Masashi YOKOTA <yokota@pylone.jp>
+ * Originally found here:
+ * http://downloads.pylone.jp/src/virtual_battery/virtual_battery-0.0.1.tar.bz2
+ *
  * 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.
@@ -15,8 +21,12 @@
 #include <linux/delay.h>
 #include <linux/vermagic.h>
 
-static int test_power_ac_online = 1;
-static int test_power_battery_status = POWER_SUPPLY_STATUS_CHARGING;
+static int ac_online			= 1;
+static int battery_status		= POWER_SUPPLY_STATUS_DISCHARGING;
+static int battery_health		= POWER_SUPPLY_HEALTH_GOOD;
+static int battery_present		= 1; /* true */
+static int battery_technology		= POWER_SUPPLY_TECHNOLOGY_LION;
+static int battery_capacity		= 50;
 
 static int test_power_get_ac_property(struct power_supply *psy,
 				      enum power_supply_property psp,
@@ -24,7 +34,7 @@ static int test_power_get_ac_property(struct power_supply *psy,
 {
 	switch (psp) {
 	case POWER_SUPPLY_PROP_ONLINE:
-		val->intval = test_power_ac_online;
+		val->intval = ac_online;
 		break;
 	default:
 		return -EINVAL;
@@ -47,22 +57,30 @@ static int test_power_get_battery_property(struct power_supply *psy,
 		val->strval = UTS_RELEASE;
 		break;
 	case POWER_SUPPLY_PROP_STATUS:
-		val->intval = test_power_battery_status;
+		val->intval = battery_status;
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_TYPE:
 		val->intval = POWER_SUPPLY_CHARGE_TYPE_FAST;
 		break;
 	case POWER_SUPPLY_PROP_HEALTH:
-		val->intval = POWER_SUPPLY_HEALTH_GOOD;
+		val->intval = battery_health;
+		break;
+	case POWER_SUPPLY_PROP_PRESENT:
+		val->intval = battery_present;
 		break;
 	case POWER_SUPPLY_PROP_TECHNOLOGY:
-		val->intval = POWER_SUPPLY_TECHNOLOGY_LION;
+		val->intval = battery_technology;
 		break;
 	case POWER_SUPPLY_PROP_CAPACITY_LEVEL:
 		val->intval = POWER_SUPPLY_CAPACITY_LEVEL_NORMAL;
 		break;
 	case POWER_SUPPLY_PROP_CAPACITY:
-		val->intval = 50;
+	case POWER_SUPPLY_PROP_CHARGE_NOW:
+		val->intval = battery_capacity;
+		break;
+	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
+	case POWER_SUPPLY_PROP_CHARGE_FULL:
+		val->intval = 100;
 		break;
 	case POWER_SUPPLY_PROP_TIME_TO_EMPTY_AVG:
 	case POWER_SUPPLY_PROP_TIME_TO_FULL_NOW:
@@ -84,9 +102,11 @@ static enum power_supply_property test_power_battery_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_CHARGE_TYPE,
 	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_PRESENT,
 	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
 	POWER_SUPPLY_PROP_CHARGE_FULL,
-	POWER_SUPPLY_PROP_CHARGE_EMPTY,
+	POWER_SUPPLY_PROP_CHARGE_NOW,
 	POWER_SUPPLY_PROP_CAPACITY,
 	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
 	POWER_SUPPLY_PROP_TIME_TO_EMPTY_AVG,
@@ -118,6 +138,7 @@ static struct power_supply test_power_supplies[] = {
 	},
 };
 
+
 static int __init test_power_init(void)
 {
 	int i;
@@ -145,8 +166,8 @@ static void __exit test_power_exit(void)
 	int i;
 
 	/* Let's see how we handle changes... */
-	test_power_ac_online = 0;
-	test_power_battery_status = POWER_SUPPLY_STATUS_DISCHARGING;
+	ac_online = 0;
+	battery_status = POWER_SUPPLY_STATUS_DISCHARGING;
 	for (i = 0; i < ARRAY_SIZE(test_power_supplies); i++)
 		power_supply_changed(&test_power_supplies[i]);
 	pr_info("%s: 'changed' event sent, sleeping for 10 seconds...\n",
@@ -158,6 +179,241 @@ static void __exit test_power_exit(void)
 }
 module_exit(test_power_exit);
 
+
+
+#define MAX_KEYLENGTH 256
+struct battery_property_map {
+	int value;
+	char const *key;
+};
+
+static struct battery_property_map map_ac_online[] = {
+	{ 0,  "on"  },
+	{ 1,  "off" },
+	{ -1, NULL  },
+};
+
+static struct battery_property_map map_status[] = {
+	{ POWER_SUPPLY_STATUS_CHARGING,     "charging"     },
+	{ POWER_SUPPLY_STATUS_DISCHARGING,  "discharging"  },
+	{ POWER_SUPPLY_STATUS_NOT_CHARGING, "not-charging" },
+	{ POWER_SUPPLY_STATUS_FULL,         "full"         },
+	{ -1,                               NULL           },
+};
+
+static struct battery_property_map map_health[] = {
+	{ POWER_SUPPLY_HEALTH_GOOD,           "good"        },
+	{ POWER_SUPPLY_HEALTH_OVERHEAT,       "overheat"    },
+	{ POWER_SUPPLY_HEALTH_DEAD,           "dead"        },
+	{ POWER_SUPPLY_HEALTH_OVERVOLTAGE,    "overvoltage" },
+	{ POWER_SUPPLY_HEALTH_UNSPEC_FAILURE, "failure"     },
+	{ -1,                                 NULL          },
+};
+
+static struct battery_property_map map_present[] = {
+	{ 0,  "false" },
+	{ 1,  "true"  },
+	{ -1, NULL    },
+};
+
+static struct battery_property_map map_technology[] = {
+	{ POWER_SUPPLY_TECHNOLOGY_NiMH, "NiMH" },
+	{ POWER_SUPPLY_TECHNOLOGY_LION, "LION" },
+	{ POWER_SUPPLY_TECHNOLOGY_LIPO, "LIPO" },
+	{ POWER_SUPPLY_TECHNOLOGY_LiFe, "LiFe" },
+	{ POWER_SUPPLY_TECHNOLOGY_NiCd, "NiCd" },
+	{ POWER_SUPPLY_TECHNOLOGY_LiMn, "LiMn" },
+	{ -1,				NULL   },
+};
+
+
+static int map_get_value(struct battery_property_map *map, const char *key,
+				int def_val)
+{
+	char buf[MAX_KEYLENGTH];
+	int cr;
+
+	strncpy(buf, key, MAX_KEYLENGTH);
+	buf[MAX_KEYLENGTH-1] = '\0';
+
+	cr = strnlen(buf, MAX_KEYLENGTH) - 1;
+	if (buf[cr] == '\n')
+		buf[cr] = '\0';
+
+	while (map->key) {
+		if (strncasecmp(map->key, buf, MAX_KEYLENGTH) == 0)
+			return map->value;
+		map++;
+	}
+
+	return def_val;
+}
+
+
+static const char *map_get_key(struct battery_property_map *map, int value,
+				const char *def_key)
+{
+	while (map->key) {
+		if (map->value == value)
+			return map->key;
+		map++;
+	}
+
+	return def_key;
+}
+
+static int param_set_ac_online(const char *key, const struct kernel_param *kp)
+{
+	ac_online = map_get_value(map_ac_online, key, ac_online);
+	power_supply_changed(&test_power_supplies[0]);
+	return 0;
+}
+
+static int param_get_ac_online(char *buffer, const struct kernel_param *kp)
+{
+	strcpy(buffer, map_get_key(map_ac_online, ac_online, "unknown"));
+	return strlen(buffer);
+}
+
+static int param_set_battery_status(const char *key,
+					const struct kernel_param *kp)
+{
+	battery_status = map_get_value(map_status, key, battery_status);
+	power_supply_changed(&test_power_supplies[1]);
+	return 0;
+}
+
+static int param_get_battery_status(char *buffer, const struct kernel_param *kp)
+{
+	strcpy(buffer, map_get_key(map_status, battery_status, "unknown"));
+	return strlen(buffer);
+}
+
+static int param_set_battery_health(const char *key,
+					const struct kernel_param *kp)
+{
+	battery_health = map_get_value(map_health, key, battery_health);
+	power_supply_changed(&test_power_supplies[1]);
+	return 0;
+}
+
+static int param_get_battery_health(char *buffer, const struct kernel_param *kp)
+{
+	strcpy(buffer, map_get_key(map_health, battery_health, "unknown"));
+	return strlen(buffer);
+}
+
+static int param_set_battery_present(const char *key,
+					const struct kernel_param *kp)
+{
+	battery_present = map_get_value(map_present, key, battery_present);
+	power_supply_changed(&test_power_supplies[0]);
+	return 0;
+}
+
+static int param_get_battery_present(char *buffer,
+					const struct kernel_param *kp)
+{
+	strcpy(buffer, map_get_key(map_present, battery_present, "unknown"));
+	return strlen(buffer);
+}
+
+static int param_set_battery_technology(const char *key,
+					const struct kernel_param *kp)
+{
+	battery_technology = map_get_value(map_technology, key,
+						battery_technology);
+	power_supply_changed(&test_power_supplies[1]);
+	return 0;
+}
+
+static int param_get_battery_technology(char *buffer,
+					const struct kernel_param *kp)
+{
+	strcpy(buffer,
+		map_get_key(map_technology, battery_technology, "unknown"));
+	return strlen(buffer);
+}
+
+static int param_set_battery_capacity(const char *key,
+					const struct kernel_param *kp)
+{
+	int tmp;
+
+	if (1 != sscanf(key, "%d", &tmp))
+		return -EINVAL;
+
+	battery_capacity = tmp;
+	power_supply_changed(&test_power_supplies[1]);
+	return 0;
+}
+
+#define param_get_battery_capacity param_get_int
+
+
+
+static struct kernel_param_ops param_ops_ac_online = {
+	.set = param_set_ac_online,
+	.get = param_get_ac_online,
+};
+
+static struct kernel_param_ops param_ops_battery_status = {
+	.set = param_set_battery_status,
+	.get = param_get_battery_status,
+};
+
+static struct kernel_param_ops param_ops_battery_present = {
+	.set = param_set_battery_present,
+	.get = param_get_battery_present,
+};
+
+static struct kernel_param_ops param_ops_battery_technology = {
+	.set = param_set_battery_technology,
+	.get = param_get_battery_technology,
+};
+
+static struct kernel_param_ops param_ops_battery_health = {
+	.set = param_set_battery_health,
+	.get = param_get_battery_health,
+};
+
+static struct kernel_param_ops param_ops_battery_capacity = {
+	.set = param_set_battery_capacity,
+	.get = param_get_battery_capacity,
+};
+
+
+#define param_check_ac_online(name, p) __param_check(name, p, void);
+#define param_check_battery_status(name, p) __param_check(name, p, void);
+#define param_check_battery_present(name, p) __param_check(name, p, void);
+#define param_check_battery_technology(name, p) __param_check(name, p, void);
+#define param_check_battery_health(name, p) __param_check(name, p, void);
+#define param_check_battery_capacity(name, p) __param_check(name, p, void);
+
+
+module_param(ac_online, ac_online, 0644);
+MODULE_PARM_DESC(ac_online, "AC charging state <on|off>");
+
+module_param(battery_status, battery_status, 0644);
+MODULE_PARM_DESC(battery_status,
+	"battery status <charging|discharging|not-charging|full>");
+
+module_param(battery_present, battery_present, 0644);
+MODULE_PARM_DESC(battery_present,
+	"battery presence state <good|overheat|dead|overvoltage|failure>");
+
+module_param(battery_technology, battery_technology, 0644);
+MODULE_PARM_DESC(battery_technology,
+	"battery technology <NiMH|LION|LIPO|LiFe|NiCd|LiMn>");
+
+module_param(battery_health, battery_health, 0644);
+MODULE_PARM_DESC(battery_health,
+	"battery health state <good|overheat|dead|overvoltage|failure>");
+
+module_param(battery_capacity, battery_capacity, 0644);
+MODULE_PARM_DESC(battery_capacity, "battery capacity (percentage)");
+
+
 MODULE_DESCRIPTION("Power supply driver for testing");
 MODULE_AUTHOR("Anton Vorontsov <cbouatmailru@gmail.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/power/z2_battery.c b/drivers/power/z2_battery.c
index e5ced3a4c1ed..d119c38b3ff6 100644
--- a/drivers/power/z2_battery.c
+++ b/drivers/power/z2_battery.c
@@ -271,24 +271,33 @@ static int __devexit z2_batt_remove(struct i2c_client *client)
 }
 
 #ifdef CONFIG_PM
-static int z2_batt_suspend(struct i2c_client *client, pm_message_t state)
+static int z2_batt_suspend(struct device *dev)
 {
+	struct i2c_client *client = to_i2c_client(dev);
 	struct z2_charger *charger = i2c_get_clientdata(client);
 
 	flush_work_sync(&charger->bat_work);
 	return 0;
 }
 
-static int z2_batt_resume(struct i2c_client *client)
+static int z2_batt_resume(struct device *dev)
 {
+	struct i2c_client *client = to_i2c_client(dev);
 	struct z2_charger *charger = i2c_get_clientdata(client);
 
 	schedule_work(&charger->bat_work);
 	return 0;
 }
+
+static const struct dev_pm_ops z2_battery_pm_ops = {
+	.suspend	= z2_batt_suspend,
+	.resume		= z2_batt_resume,
+};
+
+#define	Z2_BATTERY_PM_OPS	(&z2_battery_pm_ops)
+
 #else
-#define z2_batt_suspend NULL
-#define z2_batt_resume NULL
+#define	Z2_BATTERY_PM_OPS	(NULL)
 #endif
 
 static const struct i2c_device_id z2_batt_id[] = {
@@ -301,11 +310,10 @@ static struct i2c_driver z2_batt_driver = {
 	.driver	= {
 		.name	= "z2-battery",
 		.owner	= THIS_MODULE,
+		.pm	= Z2_BATTERY_PM_OPS
 	},
 	.probe		= z2_batt_probe,
 	.remove		= z2_batt_remove,
-	.suspend	= z2_batt_suspend,
-	.resume		= z2_batt_resume,
 	.id_table	= z2_batt_id,
 };
 
diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index a8d03aeb4051..e7f301da2902 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -46,7 +46,8 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 		caps.n_ext_ts = ptp->info->n_ext_ts;
 		caps.n_per_out = ptp->info->n_per_out;
 		caps.pps = ptp->info->pps;
-		err = copy_to_user((void __user *)arg, &caps, sizeof(caps));
+		if (copy_to_user((void __user *)arg, &caps, sizeof(caps)))
+			err = -EFAULT;
 		break;
 
 	case PTP_EXTTS_REQUEST:
@@ -129,8 +130,10 @@ ssize_t ptp_read(struct posix_clock *pc,
 		return -ERESTARTSYS;
 	}
 
-	if (ptp->defunct)
+	if (ptp->defunct) {
+		mutex_unlock(&ptp->tsevq_mux);
 		return -ENODEV;
+	}
 
 	spin_lock_irqsave(&queue->lock, flags);
 
@@ -150,10 +153,8 @@ ssize_t ptp_read(struct posix_clock *pc,
 
 	mutex_unlock(&ptp->tsevq_mux);
 
-	if (copy_to_user(buf, event, cnt)) {
-		mutex_unlock(&ptp->tsevq_mux);
+	if (copy_to_user(buf, event, cnt))
 		return -EFAULT;
-	}
 
 	return cnt;
 }
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index f0b13a0d1851..d7ed20f293d7 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -297,5 +297,11 @@ config REGULATOR_TPS6524X
 	  serial interface currently supported on the sequencer serial
 	  port controller.
 
+config REGULATOR_TPS65910
+	tristate "TI TPS65910 Power Regulator"
+	depends on MFD_TPS65910
+	help
+	  This driver supports TPS65910 voltage regulator chips.
+
 endif
 
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index 165ff5371e9e..3932d2ec38f3 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -42,5 +42,6 @@ obj-$(CONFIG_REGULATOR_88PM8607) += 88pm8607.o
 obj-$(CONFIG_REGULATOR_ISL6271A) += isl6271a-regulator.o
 obj-$(CONFIG_REGULATOR_AB8500)	+= ab8500.o
 obj-$(CONFIG_REGULATOR_DB8500_PRCMU) += db8500-prcmu.o
+obj-$(CONFIG_REGULATOR_TPS65910) += tps65910-regulator.o
 
 ccflags-$(CONFIG_REGULATOR_DEBUG) += -DDEBUG
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 0fae51c4845a..d3e38790906e 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -158,6 +158,13 @@ static int regulator_check_consumers(struct regulator_dev *rdev,
 	struct regulator *regulator;
 
 	list_for_each_entry(regulator, &rdev->consumer_list, list) {
+		/*
+		 * Assume consumers that didn't say anything are OK
+		 * with anything in the constraint range.
+		 */
+		if (!regulator->min_uV && !regulator->max_uV)
+			continue;
+
 		if (*max_uV > regulator->max_uV)
 			*max_uV = regulator->max_uV;
 		if (*min_uV < regulator->min_uV)
@@ -197,9 +204,9 @@ static int regulator_check_current_limit(struct regulator_dev *rdev,
 }
 
 /* operating mode constraint check */
-static int regulator_check_mode(struct regulator_dev *rdev, int mode)
+static int regulator_mode_constrain(struct regulator_dev *rdev, int *mode)
 {
-	switch (mode) {
+	switch (*mode) {
 	case REGULATOR_MODE_FAST:
 	case REGULATOR_MODE_NORMAL:
 	case REGULATOR_MODE_IDLE:
@@ -217,11 +224,17 @@ static int regulator_check_mode(struct regulator_dev *rdev, int mode)
 		rdev_err(rdev, "operation not allowed\n");
 		return -EPERM;
 	}
-	if (!(rdev->constraints->valid_modes_mask & mode)) {
-		rdev_err(rdev, "invalid mode %x\n", mode);
-		return -EINVAL;
+
+	/* The modes are bitmasks, the most power hungry modes having
+	 * the lowest values. If the requested mode isn't supported
+	 * try higher modes. */
+	while (*mode) {
+		if (rdev->constraints->valid_modes_mask & *mode)
+			return 0;
+		*mode /= 2;
 	}
-	return 0;
+
+	return -EINVAL;
 }
 
 /* dynamic regulator mode switching constraint check */
@@ -612,7 +625,7 @@ static void drms_uA_update(struct regulator_dev *rdev)
 						  output_uV, current_uA);
 
 	/* check the new mode is allowed */
-	err = regulator_check_mode(rdev, mode);
+	err = regulator_mode_constrain(rdev, &mode);
 	if (err == 0)
 		rdev->desc->ops->set_mode(rdev, mode);
 }
@@ -718,6 +731,10 @@ static void print_constraints(struct regulator_dev *rdev)
 			count += sprintf(buf + count, "at %d mV ", ret / 1000);
 	}
 
+	if (constraints->uV_offset)
+		count += sprintf(buf, "%dmV offset ",
+				 constraints->uV_offset / 1000);
+
 	if (constraints->min_uA && constraints->max_uA) {
 		if (constraints->min_uA == constraints->max_uA)
 			count += sprintf(buf + count, "%d mA ",
@@ -1498,13 +1515,14 @@ static int _regulator_force_disable(struct regulator_dev *rdev,
  */
 int regulator_force_disable(struct regulator *regulator)
 {
+	struct regulator_dev *rdev = regulator->rdev;
 	struct regulator_dev *supply_rdev = NULL;
 	int ret;
 
-	mutex_lock(&regulator->rdev->mutex);
+	mutex_lock(&rdev->mutex);
 	regulator->uA_load = 0;
-	ret = _regulator_force_disable(regulator->rdev, &supply_rdev);
-	mutex_unlock(&regulator->rdev->mutex);
+	ret = _regulator_force_disable(rdev, &supply_rdev);
+	mutex_unlock(&rdev->mutex);
 
 	if (supply_rdev)
 		regulator_disable(get_device_regulator(rdev_get_dev(supply_rdev)));
@@ -1634,6 +1652,9 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev,
 
 	trace_regulator_set_voltage(rdev_get_name(rdev), min_uV, max_uV);
 
+	min_uV += rdev->constraints->uV_offset;
+	max_uV += rdev->constraints->uV_offset;
+
 	if (rdev->desc->ops->set_voltage) {
 		ret = rdev->desc->ops->set_voltage(rdev, min_uV, max_uV,
 						   &selector);
@@ -1858,18 +1879,22 @@ EXPORT_SYMBOL_GPL(regulator_sync_voltage);
 
 static int _regulator_get_voltage(struct regulator_dev *rdev)
 {
-	int sel;
+	int sel, ret;
 
 	if (rdev->desc->ops->get_voltage_sel) {
 		sel = rdev->desc->ops->get_voltage_sel(rdev);
 		if (sel < 0)
 			return sel;
-		return rdev->desc->ops->list_voltage(rdev, sel);
-	}
-	if (rdev->desc->ops->get_voltage)
-		return rdev->desc->ops->get_voltage(rdev);
-	else
+		ret = rdev->desc->ops->list_voltage(rdev, sel);
+	} else if (rdev->desc->ops->get_voltage) {
+		ret = rdev->desc->ops->get_voltage(rdev);
+	} else {
 		return -EINVAL;
+	}
+
+	if (ret < 0)
+		return ret;
+	return ret - rdev->constraints->uV_offset;
 }
 
 /**
@@ -2005,7 +2030,7 @@ int regulator_set_mode(struct regulator *regulator, unsigned int mode)
 	}
 
 	/* constraints check */
-	ret = regulator_check_mode(rdev, mode);
+	ret = regulator_mode_constrain(rdev, &mode);
 	if (ret < 0)
 		goto out;
 
@@ -2081,16 +2106,26 @@ int regulator_set_optimum_mode(struct regulator *regulator, int uA_load)
 
 	mutex_lock(&rdev->mutex);
 
+	/*
+	 * first check to see if we can set modes at all, otherwise just
+	 * tell the consumer everything is OK.
+	 */
 	regulator->uA_load = uA_load;
 	ret = regulator_check_drms(rdev);
-	if (ret < 0)
+	if (ret < 0) {
+		ret = 0;
 		goto out;
-	ret = -EINVAL;
+	}
 
-	/* sanity check */
 	if (!rdev->desc->ops->get_optimum_mode)
 		goto out;
 
+	/*
+	 * we can actually do this so any errors are indicators of
+	 * potential real failure.
+	 */
+	ret = -EINVAL;
+
 	/* get output voltage */
 	output_uV = _regulator_get_voltage(rdev);
 	if (output_uV <= 0) {
@@ -2116,7 +2151,7 @@ int regulator_set_optimum_mode(struct regulator *regulator, int uA_load)
 	mode = rdev->desc->ops->get_optimum_mode(rdev,
 						 input_uV, output_uV,
 						 total_uA_load);
-	ret = regulator_check_mode(rdev, mode);
+	ret = regulator_mode_constrain(rdev, &mode);
 	if (ret < 0) {
 		rdev_err(rdev, "failed to get optimum mode @ %d uA %d -> %d uV\n",
 			 total_uA_load, input_uV, output_uV);
@@ -2589,14 +2624,6 @@ struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc,
 	if (ret < 0)
 		goto scrub;
 
-	/* set supply regulator if it exists */
-	if (init_data->supply_regulator && init_data->supply_regulator_dev) {
-		dev_err(dev,
-			"Supply regulator specified by both name and dev\n");
-		ret = -EINVAL;
-		goto scrub;
-	}
-
 	if (init_data->supply_regulator) {
 		struct regulator_dev *r;
 		int found = 0;
@@ -2621,14 +2648,6 @@ struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc,
 			goto scrub;
 	}
 
-	if (init_data->supply_regulator_dev) {
-		dev_warn(dev, "Uses supply_regulator_dev instead of regulator_supply\n");
-		ret = set_supply(rdev,
-			dev_get_drvdata(init_data->supply_regulator_dev));
-		if (ret < 0)
-			goto scrub;
-	}
-
 	/* add consumers devices */
 	for (i = 0; i < init_data->num_consumer_supplies; i++) {
 		ret = set_consumer_device_supply(rdev,
diff --git a/drivers/regulator/max8997.c b/drivers/regulator/max8997.c
index 77e0cfb30b23..10d5a1d9768e 100644
--- a/drivers/regulator/max8997.c
+++ b/drivers/regulator/max8997.c
@@ -267,7 +267,6 @@ static int max8997_get_enable_register(struct regulator_dev *rdev,
 	default:
 		/* Not controllable or not exists */
 		return -EINVAL;
-		break;
 	}
 
 	return 0;
@@ -1033,11 +1032,11 @@ static __devinit int max8997_pmic_probe(struct platform_device *pdev)
 
 	/* For the safety, set max voltage before setting up */
 	for (i = 0; i < 8; i++) {
-		max8997_update_reg(i2c, MAX8997_REG_BUCK1DVS(i + 1),
+		max8997_update_reg(i2c, MAX8997_REG_BUCK1DVS1 + i,
 				max_buck1, 0x3f);
-		max8997_update_reg(i2c, MAX8997_REG_BUCK2DVS(i + 1),
+		max8997_update_reg(i2c, MAX8997_REG_BUCK2DVS1 + i,
 				max_buck2, 0x3f);
-		max8997_update_reg(i2c, MAX8997_REG_BUCK5DVS(i + 1),
+		max8997_update_reg(i2c, MAX8997_REG_BUCK5DVS1 + i,
 				max_buck5, 0x3f);
 	}
 
@@ -1114,13 +1113,13 @@ static __devinit int max8997_pmic_probe(struct platform_device *pdev)
 
 	/* Initialize all the DVS related BUCK registers */
 	for (i = 0; i < 8; i++) {
-		max8997_update_reg(i2c, MAX8997_REG_BUCK1DVS(i + 1),
+		max8997_update_reg(i2c, MAX8997_REG_BUCK1DVS1 + i,
 				max8997->buck1_vol[i],
 				0x3f);
-		max8997_update_reg(i2c, MAX8997_REG_BUCK2DVS(i + 1),
+		max8997_update_reg(i2c, MAX8997_REG_BUCK2DVS1 + i,
 				max8997->buck2_vol[i],
 				0x3f);
-		max8997_update_reg(i2c, MAX8997_REG_BUCK5DVS(i + 1),
+		max8997_update_reg(i2c, MAX8997_REG_BUCK5DVS1 + i,
 				max8997->buck5_vol[i],
 				0x3f);
 	}
diff --git a/drivers/regulator/max8998.c b/drivers/regulator/max8998.c
index f57e9c42fdb4..41a1495eec2b 100644
--- a/drivers/regulator/max8998.c
+++ b/drivers/regulator/max8998.c
@@ -732,13 +732,15 @@ static __devinit int max8998_pmic_probe(struct platform_device *pdev)
 		if (!pdata->buck1_set1) {
 			printk(KERN_ERR "MAX8998 SET1 GPIO defined as 0 !\n");
 			WARN_ON(!pdata->buck1_set1);
-			return -EIO;
+			ret = -EIO;
+			goto err_free_mem;
 		}
 		/* Check if SET2 is not equal to 0 */
 		if (!pdata->buck1_set2) {
 			printk(KERN_ERR "MAX8998 SET2 GPIO defined as 0 !\n");
 			WARN_ON(!pdata->buck1_set2);
-			return -EIO;
+			ret = -EIO;
+			goto err_free_mem;
 		}
 
 		gpio_request(pdata->buck1_set1, "MAX8998 BUCK1_SET1");
@@ -758,7 +760,7 @@ static __devinit int max8998_pmic_probe(struct platform_device *pdev)
 		max8998->buck1_vol[0] = i;
 		ret = max8998_write_reg(i2c, MAX8998_REG_BUCK1_VOLTAGE1, i);
 		if (ret)
-			return ret;
+			goto err_free_mem;
 
 		/* Set predefined value for BUCK1 register 2 */
 		i = 0;
@@ -770,7 +772,7 @@ static __devinit int max8998_pmic_probe(struct platform_device *pdev)
 		max8998->buck1_vol[1] = i;
 		ret = max8998_write_reg(i2c, MAX8998_REG_BUCK1_VOLTAGE2, i);
 		if (ret)
-			return ret;
+			goto err_free_mem;
 
 		/* Set predefined value for BUCK1 register 3 */
 		i = 0;
@@ -782,7 +784,7 @@ static __devinit int max8998_pmic_probe(struct platform_device *pdev)
 		max8998->buck1_vol[2] = i;
 		ret = max8998_write_reg(i2c, MAX8998_REG_BUCK1_VOLTAGE3, i);
 		if (ret)
-			return ret;
+			goto err_free_mem;
 
 		/* Set predefined value for BUCK1 register 4 */
 		i = 0;
@@ -794,7 +796,7 @@ static __devinit int max8998_pmic_probe(struct platform_device *pdev)
 		max8998->buck1_vol[3] = i;
 		ret = max8998_write_reg(i2c, MAX8998_REG_BUCK1_VOLTAGE4, i);
 		if (ret)
-			return ret;
+			goto err_free_mem;
 
 	}
 
@@ -803,7 +805,8 @@ static __devinit int max8998_pmic_probe(struct platform_device *pdev)
 		if (!pdata->buck2_set3) {
 			printk(KERN_ERR "MAX8998 SET3 GPIO defined as 0 !\n");
 			WARN_ON(!pdata->buck2_set3);
-			return -EIO;
+			ret = -EIO;
+			goto err_free_mem;
 		}
 		gpio_request(pdata->buck2_set3, "MAX8998 BUCK2_SET3");
 		gpio_direction_output(pdata->buck2_set3,
@@ -818,7 +821,7 @@ static __devinit int max8998_pmic_probe(struct platform_device *pdev)
 		max8998->buck2_vol[0] = i;
 		ret = max8998_write_reg(i2c, MAX8998_REG_BUCK2_VOLTAGE1, i);
 		if (ret)
-			return ret;
+			goto err_free_mem;
 
 		/* BUCK2 register 2 */
 		i = 0;
@@ -830,7 +833,7 @@ static __devinit int max8998_pmic_probe(struct platform_device *pdev)
 		max8998->buck2_vol[1] = i;
 		ret = max8998_write_reg(i2c, MAX8998_REG_BUCK2_VOLTAGE2, i);
 		if (ret)
-			return ret;
+			goto err_free_mem;
 	}
 
 	for (i = 0; i < pdata->num_regulators; i++) {
@@ -860,6 +863,7 @@ err:
 		if (rdev[i])
 			regulator_unregister(rdev[i]);
 
+err_free_mem:
 	kfree(max8998->rdev);
 	kfree(max8998);
 
diff --git a/drivers/regulator/mc13892-regulator.c b/drivers/regulator/mc13892-regulator.c
index 1b8f7398a4a8..3285d41842f2 100644
--- a/drivers/regulator/mc13892-regulator.c
+++ b/drivers/regulator/mc13892-regulator.c
@@ -431,7 +431,8 @@ static int mc13892_sw_regulator_set_voltage(struct regulator_dev *rdev,
 		int min_uV, int max_uV, unsigned *selector)
 {
 	struct mc13xxx_regulator_priv *priv = rdev_get_drvdata(rdev);
-	int hi, value, val, mask, id = rdev_get_id(rdev);
+	int hi, value, mask, id = rdev_get_id(rdev);
+	u32 valread;
 	int ret;
 
 	dev_dbg(rdev_get_dev(rdev), "%s id: %d min_uV: %d max_uV: %d\n",
@@ -447,15 +448,16 @@ static int mc13892_sw_regulator_set_voltage(struct regulator_dev *rdev,
 
 	mc13xxx_lock(priv->mc13xxx);
 	ret = mc13xxx_reg_read(priv->mc13xxx,
-		mc13892_regulators[id].vsel_reg, &val);
+		mc13892_regulators[id].vsel_reg, &valread);
 	if (ret)
 		goto err;
 
-	hi  = val & MC13892_SWITCHERS0_SWxHI;
-	if (value > 1375)
+	if (value > 1375000)
 		hi = 1;
-	if (value < 1100)
+	else if (value < 1100000)
 		hi = 0;
+	else
+		hi = valread & MC13892_SWITCHERS0_SWxHI;
 
 	if (hi) {
 		value = (value - 1100000) / 25000;
@@ -464,8 +466,10 @@ static int mc13892_sw_regulator_set_voltage(struct regulator_dev *rdev,
 		value = (value - 600000) / 25000;
 
 	mask = mc13892_regulators[id].vsel_mask | MC13892_SWITCHERS0_SWxHI;
-	ret = mc13xxx_reg_rmw(priv->mc13xxx, mc13892_regulators[id].vsel_reg,
-			mask, value << mc13892_regulators[id].vsel_shift);
+	valread = (valread & ~mask) |
+			(value << mc13892_regulators[id].vsel_shift);
+	ret = mc13xxx_reg_write(priv->mc13xxx, mc13892_regulators[id].vsel_reg,
+			valread);
 err:
 	mc13xxx_unlock(priv->mc13xxx);
 
diff --git a/drivers/regulator/mc13xxx-regulator-core.c b/drivers/regulator/mc13xxx-regulator-core.c
index 2bb5de1f2421..bc27ab136378 100644
--- a/drivers/regulator/mc13xxx-regulator-core.c
+++ b/drivers/regulator/mc13xxx-regulator-core.c
@@ -174,7 +174,7 @@ static int mc13xxx_regulator_get_voltage(struct regulator_dev *rdev)
 
 	dev_dbg(rdev_get_dev(rdev), "%s id: %d val: %d\n", __func__, id, val);
 
-	BUG_ON(val > mc13xxx_regulators[id].desc.n_voltages);
+	BUG_ON(val >= mc13xxx_regulators[id].desc.n_voltages);
 
 	return mc13xxx_regulators[id].voltages[val];
 }
diff --git a/drivers/regulator/tps6105x-regulator.c b/drivers/regulator/tps6105x-regulator.c
index a4d7f4540c18..1011873896dc 100644
--- a/drivers/regulator/tps6105x-regulator.c
+++ b/drivers/regulator/tps6105x-regulator.c
@@ -158,6 +158,7 @@ static int __devinit tps6105x_regulator_probe(struct platform_device *pdev)
 			"failed to register regulator\n");
 		return ret;
 	}
+	platform_set_drvdata(pdev, tps6105x);
 
 	return 0;
 }
diff --git a/drivers/regulator/tps65023-regulator.c b/drivers/regulator/tps65023-regulator.c
index 60a7ca5409e9..fbddc15e1811 100644
--- a/drivers/regulator/tps65023-regulator.c
+++ b/drivers/regulator/tps65023-regulator.c
@@ -466,7 +466,6 @@ static struct regulator_ops tps65023_ldo_ops = {
 static int __devinit tps_65023_probe(struct i2c_client *client,
 				     const struct i2c_device_id *id)
 {
-	static int desc_id;
 	const struct tps_info *info = (void *)id->driver_data;
 	struct regulator_init_data *init_data;
 	struct regulator_dev *rdev;
@@ -499,7 +498,7 @@ static int __devinit tps_65023_probe(struct i2c_client *client,
 		tps->info[i] = info;
 
 		tps->desc[i].name = info->name;
-		tps->desc[i].id = desc_id++;
+		tps->desc[i].id = i;
 		tps->desc[i].n_voltages = num_voltages[i];
 		tps->desc[i].ops = (i > TPS65023_DCDC_3 ?
 					&tps65023_ldo_ops : &tps65023_dcdc_ops);
diff --git a/drivers/regulator/tps6507x-regulator.c b/drivers/regulator/tps6507x-regulator.c
index 064755290599..bfffabc21eda 100644
--- a/drivers/regulator/tps6507x-regulator.c
+++ b/drivers/regulator/tps6507x-regulator.c
@@ -553,7 +553,6 @@ static __devinit
 int tps6507x_pmic_probe(struct platform_device *pdev)
 {
 	struct tps6507x_dev *tps6507x_dev = dev_get_drvdata(pdev->dev.parent);
-	static int desc_id;
 	struct tps_info *info = &tps6507x_pmic_regs[0];
 	struct regulator_init_data *init_data;
 	struct regulator_dev *rdev;
@@ -598,7 +597,7 @@ int tps6507x_pmic_probe(struct platform_device *pdev)
 		}
 
 		tps->desc[i].name = info->name;
-		tps->desc[i].id = desc_id++;
+		tps->desc[i].id = i;
 		tps->desc[i].n_voltages = num_voltages[i];
 		tps->desc[i].ops = (i > TPS6507X_DCDC_3 ?
 		&tps6507x_pmic_ldo_ops : &tps6507x_pmic_dcdc_ops);
diff --git a/drivers/regulator/tps65910-regulator.c b/drivers/regulator/tps65910-regulator.c
new file mode 100644
index 000000000000..55dd4e6650db
--- /dev/null
+++ b/drivers/regulator/tps65910-regulator.c
@@ -0,0 +1,993 @@
+/*
+ * tps65910.c  --  TI tps65910
+ *
+ * Copyright 2010 Texas Instruments Inc.
+ *
+ * Author: Graeme Gregory <gg@slimlogic.co.uk>
+ * Author: Jorge Eduardo Candelaria <jedu@slimlogic.co.uk>
+ *
+ *  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/init.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/gpio.h>
+#include <linux/mfd/tps65910.h>
+
+#define TPS65910_REG_VRTC		0
+#define TPS65910_REG_VIO		1
+#define TPS65910_REG_VDD1		2
+#define TPS65910_REG_VDD2		3
+#define TPS65910_REG_VDD3		4
+#define TPS65910_REG_VDIG1		5
+#define TPS65910_REG_VDIG2		6
+#define TPS65910_REG_VPLL		7
+#define TPS65910_REG_VDAC		8
+#define TPS65910_REG_VAUX1		9
+#define TPS65910_REG_VAUX2		10
+#define TPS65910_REG_VAUX33		11
+#define TPS65910_REG_VMMC		12
+
+#define TPS65911_REG_VDDCTRL		4
+#define TPS65911_REG_LDO1		5
+#define TPS65911_REG_LDO2		6
+#define TPS65911_REG_LDO3		7
+#define TPS65911_REG_LDO4		8
+#define TPS65911_REG_LDO5		9
+#define TPS65911_REG_LDO6		10
+#define TPS65911_REG_LDO7		11
+#define TPS65911_REG_LDO8		12
+
+#define TPS65910_NUM_REGULATOR		13
+#define TPS65910_SUPPLY_STATE_ENABLED	0x1
+
+/* supported VIO voltages in milivolts */
+static const u16 VIO_VSEL_table[] = {
+	1500, 1800, 2500, 3300,
+};
+
+/* VSEL tables for TPS65910 specific LDOs and dcdc's */
+
+/* supported VDD3 voltages in milivolts */
+static const u16 VDD3_VSEL_table[] = {
+	5000,
+};
+
+/* supported VDIG1 voltages in milivolts */
+static const u16 VDIG1_VSEL_table[] = {
+	1200, 1500, 1800, 2700,
+};
+
+/* supported VDIG2 voltages in milivolts */
+static const u16 VDIG2_VSEL_table[] = {
+	1000, 1100, 1200, 1800,
+};
+
+/* supported VPLL voltages in milivolts */
+static const u16 VPLL_VSEL_table[] = {
+	1000, 1100, 1800, 2500,
+};
+
+/* supported VDAC voltages in milivolts */
+static const u16 VDAC_VSEL_table[] = {
+	1800, 2600, 2800, 2850,
+};
+
+/* supported VAUX1 voltages in milivolts */
+static const u16 VAUX1_VSEL_table[] = {
+	1800, 2500, 2800, 2850,
+};
+
+/* supported VAUX2 voltages in milivolts */
+static const u16 VAUX2_VSEL_table[] = {
+	1800, 2800, 2900, 3300,
+};
+
+/* supported VAUX33 voltages in milivolts */
+static const u16 VAUX33_VSEL_table[] = {
+	1800, 2000, 2800, 3300,
+};
+
+/* supported VMMC voltages in milivolts */
+static const u16 VMMC_VSEL_table[] = {
+	1800, 2800, 3000, 3300,
+};
+
+struct tps_info {
+	const char *name;
+	unsigned min_uV;
+	unsigned max_uV;
+	u8 table_len;
+	const u16 *table;
+};
+
+static struct tps_info tps65910_regs[] = {
+	{
+		.name = "VRTC",
+	},
+	{
+		.name = "VIO",
+		.min_uV = 1500000,
+		.max_uV = 3300000,
+		.table_len = ARRAY_SIZE(VIO_VSEL_table),
+		.table = VIO_VSEL_table,
+	},
+	{
+		.name = "VDD1",
+		.min_uV = 600000,
+		.max_uV = 4500000,
+	},
+	{
+		.name = "VDD2",
+		.min_uV = 600000,
+		.max_uV = 4500000,
+	},
+	{
+		.name = "VDD3",
+		.min_uV = 5000000,
+		.max_uV = 5000000,
+		.table_len = ARRAY_SIZE(VDD3_VSEL_table),
+		.table = VDD3_VSEL_table,
+	},
+	{
+		.name = "VDIG1",
+		.min_uV = 1200000,
+		.max_uV = 2700000,
+		.table_len = ARRAY_SIZE(VDIG1_VSEL_table),
+		.table = VDIG1_VSEL_table,
+	},
+	{
+		.name = "VDIG2",
+		.min_uV = 1000000,
+		.max_uV = 1800000,
+		.table_len = ARRAY_SIZE(VDIG2_VSEL_table),
+		.table = VDIG2_VSEL_table,
+	},
+	{
+		.name = "VPLL",
+		.min_uV = 1000000,
+		.max_uV = 2500000,
+		.table_len = ARRAY_SIZE(VPLL_VSEL_table),
+		.table = VPLL_VSEL_table,
+	},
+	{
+		.name = "VDAC",
+		.min_uV = 1800000,
+		.max_uV = 2850000,
+		.table_len = ARRAY_SIZE(VDAC_VSEL_table),
+		.table = VDAC_VSEL_table,
+	},
+	{
+		.name = "VAUX1",
+		.min_uV = 1800000,
+		.max_uV = 2850000,
+		.table_len = ARRAY_SIZE(VAUX1_VSEL_table),
+		.table = VAUX1_VSEL_table,
+	},
+	{
+		.name = "VAUX2",
+		.min_uV = 1800000,
+		.max_uV = 3300000,
+		.table_len = ARRAY_SIZE(VAUX2_VSEL_table),
+		.table = VAUX2_VSEL_table,
+	},
+	{
+		.name = "VAUX33",
+		.min_uV = 1800000,
+		.max_uV = 3300000,
+		.table_len = ARRAY_SIZE(VAUX33_VSEL_table),
+		.table = VAUX33_VSEL_table,
+	},
+	{
+		.name = "VMMC",
+		.min_uV = 1800000,
+		.max_uV = 3300000,
+		.table_len = ARRAY_SIZE(VMMC_VSEL_table),
+		.table = VMMC_VSEL_table,
+	},
+};
+
+static struct tps_info tps65911_regs[] = {
+	{
+		.name = "VIO",
+		.min_uV = 1500000,
+		.max_uV = 3300000,
+		.table_len = ARRAY_SIZE(VIO_VSEL_table),
+		.table = VIO_VSEL_table,
+	},
+	{
+		.name = "VDD1",
+		.min_uV = 600000,
+		.max_uV = 4500000,
+	},
+	{
+		.name = "VDD2",
+		.min_uV = 600000,
+		.max_uV = 4500000,
+	},
+	{
+		.name = "VDDCTRL",
+		.min_uV = 600000,
+		.max_uV = 1400000,
+	},
+	{
+		.name = "LDO1",
+		.min_uV = 1000000,
+		.max_uV = 3300000,
+	},
+	{
+		.name = "LDO2",
+		.min_uV = 1000000,
+		.max_uV = 3300000,
+	},
+	{
+		.name = "LDO3",
+		.min_uV = 1000000,
+		.max_uV = 3300000,
+	},
+	{
+		.name = "LDO4",
+		.min_uV = 1000000,
+		.max_uV = 3300000,
+	},
+	{
+		.name = "LDO5",
+		.min_uV = 1000000,
+		.max_uV = 3300000,
+	},
+	{
+		.name = "LDO6",
+		.min_uV = 1000000,
+		.max_uV = 3300000,
+	},
+	{
+		.name = "LDO7",
+		.min_uV = 1000000,
+		.max_uV = 3300000,
+	},
+	{
+		.name = "LDO8",
+		.min_uV = 1000000,
+		.max_uV = 3300000,
+	},
+};
+
+struct tps65910_reg {
+	struct regulator_desc desc[TPS65910_NUM_REGULATOR];
+	struct tps65910 *mfd;
+	struct regulator_dev *rdev[TPS65910_NUM_REGULATOR];
+	struct tps_info *info[TPS65910_NUM_REGULATOR];
+	struct mutex mutex;
+	int mode;
+	int  (*get_ctrl_reg)(int);
+};
+
+static inline int tps65910_read(struct tps65910_reg *pmic, u8 reg)
+{
+	u8 val;
+	int err;
+
+	err = pmic->mfd->read(pmic->mfd, reg, 1, &val);
+	if (err)
+		return err;
+
+	return val;
+}
+
+static inline int tps65910_write(struct tps65910_reg *pmic, u8 reg, u8 val)
+{
+	return pmic->mfd->write(pmic->mfd, reg, 1, &val);
+}
+
+static int tps65910_modify_bits(struct tps65910_reg *pmic, u8 reg,
+					u8 set_mask, u8 clear_mask)
+{
+	int err, data;
+
+	mutex_lock(&pmic->mutex);
+
+	data = tps65910_read(pmic, reg);
+	if (data < 0) {
+		dev_err(pmic->mfd->dev, "Read from reg 0x%x failed\n", reg);
+		err = data;
+		goto out;
+	}
+
+	data &= ~clear_mask;
+	data |= set_mask;
+	err = tps65910_write(pmic, reg, data);
+	if (err)
+		dev_err(pmic->mfd->dev, "Write for reg 0x%x failed\n", reg);
+
+out:
+	mutex_unlock(&pmic->mutex);
+	return err;
+}
+
+static int tps65910_reg_read(struct tps65910_reg *pmic, u8 reg)
+{
+	int data;
+
+	mutex_lock(&pmic->mutex);
+
+	data = tps65910_read(pmic, reg);
+	if (data < 0)
+		dev_err(pmic->mfd->dev, "Read from reg 0x%x failed\n", reg);
+
+	mutex_unlock(&pmic->mutex);
+	return data;
+}
+
+static int tps65910_reg_write(struct tps65910_reg *pmic, u8 reg, u8 val)
+{
+	int err;
+
+	mutex_lock(&pmic->mutex);
+
+	err = tps65910_write(pmic, reg, val);
+	if (err < 0)
+		dev_err(pmic->mfd->dev, "Write for reg 0x%x failed\n", reg);
+
+	mutex_unlock(&pmic->mutex);
+	return err;
+}
+
+static int tps65910_get_ctrl_register(int id)
+{
+	switch (id) {
+	case TPS65910_REG_VRTC:
+		return TPS65910_VRTC;
+	case TPS65910_REG_VIO:
+		return TPS65910_VIO;
+	case TPS65910_REG_VDD1:
+		return TPS65910_VDD1;
+	case TPS65910_REG_VDD2:
+		return TPS65910_VDD2;
+	case TPS65910_REG_VDD3:
+		return TPS65910_VDD3;
+	case TPS65910_REG_VDIG1:
+		return TPS65910_VDIG1;
+	case TPS65910_REG_VDIG2:
+		return TPS65910_VDIG2;
+	case TPS65910_REG_VPLL:
+		return TPS65910_VPLL;
+	case TPS65910_REG_VDAC:
+		return TPS65910_VDAC;
+	case TPS65910_REG_VAUX1:
+		return TPS65910_VAUX1;
+	case TPS65910_REG_VAUX2:
+		return TPS65910_VAUX2;
+	case TPS65910_REG_VAUX33:
+		return TPS65910_VAUX33;
+	case TPS65910_REG_VMMC:
+		return TPS65910_VMMC;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int tps65911_get_ctrl_register(int id)
+{
+	switch (id) {
+	case TPS65910_REG_VRTC:
+		return TPS65910_VRTC;
+	case TPS65910_REG_VIO:
+		return TPS65910_VIO;
+	case TPS65910_REG_VDD1:
+		return TPS65910_VDD1;
+	case TPS65910_REG_VDD2:
+		return TPS65910_VDD2;
+	case TPS65911_REG_VDDCTRL:
+		return TPS65911_VDDCTRL;
+	case TPS65911_REG_LDO1:
+		return TPS65911_LDO1;
+	case TPS65911_REG_LDO2:
+		return TPS65911_LDO2;
+	case TPS65911_REG_LDO3:
+		return TPS65911_LDO3;
+	case TPS65911_REG_LDO4:
+		return TPS65911_LDO4;
+	case TPS65911_REG_LDO5:
+		return TPS65911_LDO5;
+	case TPS65911_REG_LDO6:
+		return TPS65911_LDO6;
+	case TPS65911_REG_LDO7:
+		return TPS65911_LDO7;
+	case TPS65911_REG_LDO8:
+		return TPS65911_LDO8;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int tps65910_is_enabled(struct regulator_dev *dev)
+{
+	struct tps65910_reg *pmic = rdev_get_drvdata(dev);
+	int reg, value, id = rdev_get_id(dev);
+
+	reg = pmic->get_ctrl_reg(id);
+	if (reg < 0)
+		return reg;
+
+	value = tps65910_reg_read(pmic, reg);
+	if (value < 0)
+		return value;
+
+	return value & TPS65910_SUPPLY_STATE_ENABLED;
+}
+
+static int tps65910_enable(struct regulator_dev *dev)
+{
+	struct tps65910_reg *pmic = rdev_get_drvdata(dev);
+	struct tps65910 *mfd = pmic->mfd;
+	int reg, id = rdev_get_id(dev);
+
+	reg = pmic->get_ctrl_reg(id);
+	if (reg < 0)
+		return reg;
+
+	return tps65910_set_bits(mfd, reg, TPS65910_SUPPLY_STATE_ENABLED);
+}
+
+static int tps65910_disable(struct regulator_dev *dev)
+{
+	struct tps65910_reg *pmic = rdev_get_drvdata(dev);
+	struct tps65910 *mfd = pmic->mfd;
+	int reg, id = rdev_get_id(dev);
+
+	reg = pmic->get_ctrl_reg(id);
+	if (reg < 0)
+		return reg;
+
+	return tps65910_clear_bits(mfd, reg, TPS65910_SUPPLY_STATE_ENABLED);
+}
+
+
+static int tps65910_set_mode(struct regulator_dev *dev, unsigned int mode)
+{
+	struct tps65910_reg *pmic = rdev_get_drvdata(dev);
+	struct tps65910 *mfd = pmic->mfd;
+	int reg, value, id = rdev_get_id(dev);
+
+	reg = pmic->get_ctrl_reg(id);
+	if (reg < 0)
+		return reg;
+
+	switch (mode) {
+	case REGULATOR_MODE_NORMAL:
+		return tps65910_modify_bits(pmic, reg, LDO_ST_ON_BIT,
+							LDO_ST_MODE_BIT);
+	case REGULATOR_MODE_IDLE:
+		value = LDO_ST_ON_BIT | LDO_ST_MODE_BIT;
+		return tps65910_set_bits(mfd, reg, value);
+	case REGULATOR_MODE_STANDBY:
+		return tps65910_clear_bits(mfd, reg, LDO_ST_ON_BIT);
+	}
+
+	return -EINVAL;
+}
+
+static unsigned int tps65910_get_mode(struct regulator_dev *dev)
+{
+	struct tps65910_reg *pmic = rdev_get_drvdata(dev);
+	int reg, value, id = rdev_get_id(dev);
+
+	reg = pmic->get_ctrl_reg(id);
+	if (reg < 0)
+		return reg;
+
+	value = tps65910_reg_read(pmic, reg);
+	if (value < 0)
+		return value;
+
+	if (value & LDO_ST_ON_BIT)
+		return REGULATOR_MODE_STANDBY;
+	else if (value & LDO_ST_MODE_BIT)
+		return REGULATOR_MODE_IDLE;
+	else
+		return REGULATOR_MODE_NORMAL;
+}
+
+static int tps65910_get_voltage_dcdc(struct regulator_dev *dev)
+{
+	struct tps65910_reg *pmic = rdev_get_drvdata(dev);
+	int id = rdev_get_id(dev), voltage = 0;
+	int opvsel = 0, srvsel = 0, vselmax = 0, mult = 0, sr = 0;
+
+	switch (id) {
+	case TPS65910_REG_VDD1:
+		opvsel = tps65910_reg_read(pmic, TPS65910_VDD1_OP);
+		mult = tps65910_reg_read(pmic, TPS65910_VDD1);
+		mult = (mult & VDD1_VGAIN_SEL_MASK) >> VDD1_VGAIN_SEL_SHIFT;
+		srvsel = tps65910_reg_read(pmic, TPS65910_VDD1_SR);
+		sr = opvsel & VDD1_OP_CMD_MASK;
+		opvsel &= VDD1_OP_SEL_MASK;
+		srvsel &= VDD1_SR_SEL_MASK;
+		vselmax = 75;
+		break;
+	case TPS65910_REG_VDD2:
+		opvsel = tps65910_reg_read(pmic, TPS65910_VDD2_OP);
+		mult = tps65910_reg_read(pmic, TPS65910_VDD2);
+		mult = (mult & VDD2_VGAIN_SEL_MASK) >> VDD2_VGAIN_SEL_SHIFT;
+		srvsel = tps65910_reg_read(pmic, TPS65910_VDD2_SR);
+		sr = opvsel & VDD2_OP_CMD_MASK;
+		opvsel &= VDD2_OP_SEL_MASK;
+		srvsel &= VDD2_SR_SEL_MASK;
+		vselmax = 75;
+		break;
+	case TPS65911_REG_VDDCTRL:
+		opvsel = tps65910_reg_read(pmic, TPS65911_VDDCTRL_OP);
+		srvsel = tps65910_reg_read(pmic, TPS65911_VDDCTRL_SR);
+		sr = opvsel & VDDCTRL_OP_CMD_MASK;
+		opvsel &= VDDCTRL_OP_SEL_MASK;
+		srvsel &= VDDCTRL_SR_SEL_MASK;
+		vselmax = 64;
+		break;
+	}
+
+	/* multiplier 0 == 1 but 2,3 normal */
+	if (!mult)
+		mult=1;
+
+	if (sr) {
+		/* normalise to valid range */
+		if (srvsel < 3)
+			srvsel = 3;
+		if (srvsel > vselmax)
+			srvsel = vselmax;
+		srvsel -= 3;
+
+		voltage = (srvsel * VDD1_2_OFFSET + VDD1_2_MIN_VOLT) * 100;
+	} else {
+
+		/* normalise to valid range*/
+		if (opvsel < 3)
+			opvsel = 3;
+		if (opvsel > vselmax)
+			opvsel = vselmax;
+		opvsel -= 3;
+
+		voltage = (opvsel * VDD1_2_OFFSET + VDD1_2_MIN_VOLT) * 100;
+	}
+
+	voltage *= mult;
+
+	return voltage;
+}
+
+static int tps65910_get_voltage(struct regulator_dev *dev)
+{
+	struct tps65910_reg *pmic = rdev_get_drvdata(dev);
+	int reg, value, id = rdev_get_id(dev), voltage = 0;
+
+	reg = pmic->get_ctrl_reg(id);
+	if (reg < 0)
+		return reg;
+
+	value = tps65910_reg_read(pmic, reg);
+	if (value < 0)
+		return value;
+
+	switch (id) {
+	case TPS65910_REG_VIO:
+	case TPS65910_REG_VDIG1:
+	case TPS65910_REG_VDIG2:
+	case TPS65910_REG_VPLL:
+	case TPS65910_REG_VDAC:
+	case TPS65910_REG_VAUX1:
+	case TPS65910_REG_VAUX2:
+	case TPS65910_REG_VAUX33:
+	case TPS65910_REG_VMMC:
+		value &= LDO_SEL_MASK;
+		value >>= LDO_SEL_SHIFT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	voltage = pmic->info[id]->table[value] * 1000;
+
+	return voltage;
+}
+
+static int tps65910_get_voltage_vdd3(struct regulator_dev *dev)
+{
+	return 5 * 1000 * 1000;
+}
+
+static int tps65911_get_voltage(struct regulator_dev *dev)
+{
+	struct tps65910_reg *pmic = rdev_get_drvdata(dev);
+	int step_mv, id = rdev_get_id(dev);
+	u8 value, reg;
+
+	reg = pmic->get_ctrl_reg(id);
+
+	value = tps65910_reg_read(pmic, reg);
+
+	switch (id) {
+	case TPS65911_REG_LDO1:
+	case TPS65911_REG_LDO2:
+	case TPS65911_REG_LDO4:
+		value &= LDO1_SEL_MASK;
+		value >>= LDO_SEL_SHIFT;
+		/* The first 5 values of the selector correspond to 1V */
+		if (value < 5)
+			value = 0;
+		else
+			value -= 4;
+
+		step_mv = 50;
+		break;
+	case TPS65911_REG_LDO3:
+	case TPS65911_REG_LDO5:
+	case TPS65911_REG_LDO6:
+	case TPS65911_REG_LDO7:
+	case TPS65911_REG_LDO8:
+		value &= LDO3_SEL_MASK;
+		value >>= LDO_SEL_SHIFT;
+		/* The first 3 values of the selector correspond to 1V */
+		if (value < 3)
+			value = 0;
+		else
+			value -= 2;
+
+		step_mv = 100;
+		break;
+	case TPS65910_REG_VIO:
+		return pmic->info[id]->table[value] * 1000;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return (LDO_MIN_VOLT + value * step_mv) * 1000;
+}
+
+static int tps65910_set_voltage_dcdc(struct regulator_dev *dev,
+				unsigned selector)
+{
+	struct tps65910_reg *pmic = rdev_get_drvdata(dev);
+	int id = rdev_get_id(dev), vsel;
+	int dcdc_mult = 0;
+
+	switch (id) {
+	case TPS65910_REG_VDD1:
+		dcdc_mult = (selector / VDD1_2_NUM_VOLTS) + 1;
+		if (dcdc_mult == 1)
+			dcdc_mult--;
+		vsel = (selector % VDD1_2_NUM_VOLTS) + 3;
+
+		tps65910_modify_bits(pmic, TPS65910_VDD1,
+				(dcdc_mult << VDD1_VGAIN_SEL_SHIFT),
+						VDD1_VGAIN_SEL_MASK);
+		tps65910_reg_write(pmic, TPS65910_VDD1_OP, vsel);
+		break;
+	case TPS65910_REG_VDD2:
+		dcdc_mult = (selector / VDD1_2_NUM_VOLTS) + 1;
+		if (dcdc_mult == 1)
+			dcdc_mult--;
+		vsel = (selector % VDD1_2_NUM_VOLTS) + 3;
+
+		tps65910_modify_bits(pmic, TPS65910_VDD2,
+				(dcdc_mult << VDD2_VGAIN_SEL_SHIFT),
+						VDD1_VGAIN_SEL_MASK);
+		tps65910_reg_write(pmic, TPS65910_VDD2_OP, vsel);
+		break;
+	case TPS65911_REG_VDDCTRL:
+		vsel = selector;
+		tps65910_reg_write(pmic, TPS65911_VDDCTRL_OP, vsel);
+	}
+
+	return 0;
+}
+
+static int tps65910_set_voltage(struct regulator_dev *dev, unsigned selector)
+{
+	struct tps65910_reg *pmic = rdev_get_drvdata(dev);
+	int reg, id = rdev_get_id(dev);
+
+	reg = pmic->get_ctrl_reg(id);
+	if (reg < 0)
+		return reg;
+
+	switch (id) {
+	case TPS65910_REG_VIO:
+	case TPS65910_REG_VDIG1:
+	case TPS65910_REG_VDIG2:
+	case TPS65910_REG_VPLL:
+	case TPS65910_REG_VDAC:
+	case TPS65910_REG_VAUX1:
+	case TPS65910_REG_VAUX2:
+	case TPS65910_REG_VAUX33:
+	case TPS65910_REG_VMMC:
+		return tps65910_modify_bits(pmic, reg,
+				(selector << LDO_SEL_SHIFT), LDO_SEL_MASK);
+	}
+
+	return -EINVAL;
+}
+
+static int tps65911_set_voltage(struct regulator_dev *dev, unsigned selector)
+{
+	struct tps65910_reg *pmic = rdev_get_drvdata(dev);
+	int reg, id = rdev_get_id(dev);
+
+	reg = pmic->get_ctrl_reg(id);
+	if (reg < 0)
+		return reg;
+
+	switch (id) {
+	case TPS65911_REG_LDO1:
+	case TPS65911_REG_LDO2:
+	case TPS65911_REG_LDO4:
+		return tps65910_modify_bits(pmic, reg,
+				(selector << LDO_SEL_SHIFT), LDO1_SEL_MASK);
+	case TPS65911_REG_LDO3:
+	case TPS65911_REG_LDO5:
+	case TPS65911_REG_LDO6:
+	case TPS65911_REG_LDO7:
+	case TPS65911_REG_LDO8:
+	case TPS65910_REG_VIO:
+		return tps65910_modify_bits(pmic, reg,
+				(selector << LDO_SEL_SHIFT), LDO3_SEL_MASK);
+	}
+
+	return -EINVAL;
+}
+
+
+static int tps65910_list_voltage_dcdc(struct regulator_dev *dev,
+					unsigned selector)
+{
+	int volt, mult = 1, id = rdev_get_id(dev);
+
+	switch (id) {
+	case TPS65910_REG_VDD1:
+	case TPS65910_REG_VDD2:
+		mult = (selector / VDD1_2_NUM_VOLTS) + 1;
+		volt = VDD1_2_MIN_VOLT +
+				(selector % VDD1_2_NUM_VOLTS) * VDD1_2_OFFSET;
+	case TPS65911_REG_VDDCTRL:
+		volt = VDDCTRL_MIN_VOLT + (selector * VDDCTRL_OFFSET);
+	}
+
+	return  volt * 100 * mult;
+}
+
+static int tps65910_list_voltage(struct regulator_dev *dev,
+					unsigned selector)
+{
+	struct tps65910_reg *pmic = rdev_get_drvdata(dev);
+	int id = rdev_get_id(dev), voltage;
+
+	if (id < TPS65910_REG_VIO || id > TPS65910_REG_VMMC)
+		return -EINVAL;
+
+	if (selector >= pmic->info[id]->table_len)
+		return -EINVAL;
+	else
+		voltage = pmic->info[id]->table[selector] * 1000;
+
+	return voltage;
+}
+
+static int tps65911_list_voltage(struct regulator_dev *dev, unsigned selector)
+{
+	struct tps65910_reg *pmic = rdev_get_drvdata(dev);
+	int step_mv = 0, id = rdev_get_id(dev);
+
+	switch(id) {
+	case TPS65911_REG_LDO1:
+	case TPS65911_REG_LDO2:
+	case TPS65911_REG_LDO4:
+		/* The first 5 values of the selector correspond to 1V */
+		if (selector < 5)
+			selector = 0;
+		else
+			selector -= 4;
+
+		step_mv = 50;
+		break;
+	case TPS65911_REG_LDO3:
+	case TPS65911_REG_LDO5:
+	case TPS65911_REG_LDO6:
+	case TPS65911_REG_LDO7:
+	case TPS65911_REG_LDO8:
+		/* The first 3 values of the selector correspond to 1V */
+		if (selector < 3)
+			selector = 0;
+		else
+			selector -= 2;
+
+		step_mv = 100;
+		break;
+	case TPS65910_REG_VIO:
+		return pmic->info[id]->table[selector] * 1000;
+	default:
+		return -EINVAL;
+	}
+
+	return (LDO_MIN_VOLT + selector * step_mv) * 1000;
+}
+
+/* Regulator ops (except VRTC) */
+static struct regulator_ops tps65910_ops_dcdc = {
+	.is_enabled		= tps65910_is_enabled,
+	.enable			= tps65910_enable,
+	.disable		= tps65910_disable,
+	.set_mode		= tps65910_set_mode,
+	.get_mode		= tps65910_get_mode,
+	.get_voltage		= tps65910_get_voltage_dcdc,
+	.set_voltage_sel	= tps65910_set_voltage_dcdc,
+	.list_voltage		= tps65910_list_voltage_dcdc,
+};
+
+static struct regulator_ops tps65910_ops_vdd3 = {
+	.is_enabled		= tps65910_is_enabled,
+	.enable			= tps65910_enable,
+	.disable		= tps65910_disable,
+	.set_mode		= tps65910_set_mode,
+	.get_mode		= tps65910_get_mode,
+	.get_voltage		= tps65910_get_voltage_vdd3,
+	.list_voltage		= tps65910_list_voltage,
+};
+
+static struct regulator_ops tps65910_ops = {
+	.is_enabled		= tps65910_is_enabled,
+	.enable			= tps65910_enable,
+	.disable		= tps65910_disable,
+	.set_mode		= tps65910_set_mode,
+	.get_mode		= tps65910_get_mode,
+	.get_voltage		= tps65910_get_voltage,
+	.set_voltage_sel	= tps65910_set_voltage,
+	.list_voltage		= tps65910_list_voltage,
+};
+
+static struct regulator_ops tps65911_ops = {
+	.is_enabled		= tps65910_is_enabled,
+	.enable			= tps65910_enable,
+	.disable		= tps65910_disable,
+	.set_mode		= tps65910_set_mode,
+	.get_mode		= tps65910_get_mode,
+	.get_voltage		= tps65911_get_voltage,
+	.set_voltage_sel	= tps65911_set_voltage,
+	.list_voltage		= tps65911_list_voltage,
+};
+
+static __devinit int tps65910_probe(struct platform_device *pdev)
+{
+	struct tps65910 *tps65910 = dev_get_drvdata(pdev->dev.parent);
+	struct tps_info *info;
+	struct regulator_init_data *reg_data;
+	struct regulator_dev *rdev;
+	struct tps65910_reg *pmic;
+	struct tps65910_board *pmic_plat_data;
+	int i, err;
+
+	pmic_plat_data = dev_get_platdata(tps65910->dev);
+	if (!pmic_plat_data)
+		return -EINVAL;
+
+	reg_data = pmic_plat_data->tps65910_pmic_init_data;
+
+	pmic = kzalloc(sizeof(*pmic), GFP_KERNEL);
+	if (!pmic)
+		return -ENOMEM;
+
+	mutex_init(&pmic->mutex);
+	pmic->mfd = tps65910;
+	platform_set_drvdata(pdev, pmic);
+
+	/* Give control of all register to control port */
+	tps65910_set_bits(pmic->mfd, TPS65910_DEVCTRL,
+				DEVCTRL_SR_CTL_I2C_SEL_MASK);
+
+	switch(tps65910_chip_id(tps65910)) {
+	case TPS65910:
+		pmic->get_ctrl_reg = &tps65910_get_ctrl_register;
+		info = tps65910_regs;
+	case TPS65911:
+		pmic->get_ctrl_reg = &tps65911_get_ctrl_register;
+		info = tps65911_regs;
+	default:
+		pr_err("Invalid tps chip version\n");
+		return -ENODEV;
+	}
+
+	for (i = 0; i < TPS65910_NUM_REGULATOR; i++, info++, reg_data++) {
+		/* Register the regulators */
+		pmic->info[i] = info;
+
+		pmic->desc[i].name = info->name;
+		pmic->desc[i].id = i;
+		pmic->desc[i].n_voltages = info->table_len;
+
+		if (i == TPS65910_REG_VDD1 || i == TPS65910_REG_VDD2) {
+			pmic->desc[i].ops = &tps65910_ops_dcdc;
+		} else if (i == TPS65910_REG_VDD3) {
+			if (tps65910_chip_id(tps65910) == TPS65910)
+				pmic->desc[i].ops = &tps65910_ops_vdd3;
+			else
+				pmic->desc[i].ops = &tps65910_ops_dcdc;
+		} else {
+			if (tps65910_chip_id(tps65910) == TPS65910)
+				pmic->desc[i].ops = &tps65910_ops;
+			else
+				pmic->desc[i].ops = &tps65911_ops;
+		}
+
+		pmic->desc[i].type = REGULATOR_VOLTAGE;
+		pmic->desc[i].owner = THIS_MODULE;
+
+		rdev = regulator_register(&pmic->desc[i],
+				tps65910->dev, reg_data, pmic);
+		if (IS_ERR(rdev)) {
+			dev_err(tps65910->dev,
+				"failed to register %s regulator\n",
+				pdev->name);
+			err = PTR_ERR(rdev);
+			goto err;
+		}
+
+		/* Save regulator for cleanup */
+		pmic->rdev[i] = rdev;
+	}
+	return 0;
+
+err:
+	while (--i >= 0)
+		regulator_unregister(pmic->rdev[i]);
+
+	kfree(pmic);
+	return err;
+}
+
+static int __devexit tps65910_remove(struct platform_device *pdev)
+{
+	struct tps65910_reg *tps65910_reg = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < TPS65910_NUM_REGULATOR; i++)
+		regulator_unregister(tps65910_reg->rdev[i]);
+
+	kfree(tps65910_reg);
+	return 0;
+}
+
+static struct platform_driver tps65910_driver = {
+	.driver = {
+		.name = "tps65910-pmic",
+		.owner = THIS_MODULE,
+	},
+	.probe = tps65910_probe,
+	.remove = __devexit_p(tps65910_remove),
+};
+
+static int __init tps65910_init(void)
+{
+	return platform_driver_register(&tps65910_driver);
+}
+subsys_initcall(tps65910_init);
+
+static void __exit tps65910_cleanup(void)
+{
+	platform_driver_unregister(&tps65910_driver);
+}
+module_exit(tps65910_cleanup);
+
+MODULE_AUTHOR("Graeme Gregory <gg@slimlogic.co.uk>");
+MODULE_DESCRIPTION("TPS6507x voltage regulator driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:tps65910-pmic");
diff --git a/drivers/regulator/twl-regulator.c b/drivers/regulator/twl-regulator.c
index 6a292852a358..87fe0f75a56e 100644
--- a/drivers/regulator/twl-regulator.c
+++ b/drivers/regulator/twl-regulator.c
@@ -51,8 +51,13 @@ struct twlreg_info {
 	u16			min_mV;
 	u16			max_mV;
 
+	u8			flags;
+
 	/* used by regulator core */
 	struct regulator_desc	desc;
+
+	/* chip specific features */
+	unsigned long 		features;
 };
 
 
@@ -70,12 +75,35 @@ struct twlreg_info {
 #define VREG_TRANS		1
 #define VREG_STATE		2
 #define VREG_VOLTAGE		3
+#define VREG_VOLTAGE_SMPS	4
 /* TWL6030 Misc register offsets */
 #define VREG_BC_ALL		1
 #define VREG_BC_REF		2
 #define VREG_BC_PROC		3
 #define VREG_BC_CLK_RST		4
 
+/* TWL6030 LDO register values for CFG_STATE */
+#define TWL6030_CFG_STATE_OFF	0x00
+#define TWL6030_CFG_STATE_ON	0x01
+#define TWL6030_CFG_STATE_OFF2	0x02
+#define TWL6030_CFG_STATE_SLEEP	0x03
+#define TWL6030_CFG_STATE_GRP_SHIFT	5
+#define TWL6030_CFG_STATE_APP_SHIFT	2
+#define TWL6030_CFG_STATE_APP_MASK	(0x03 << TWL6030_CFG_STATE_APP_SHIFT)
+#define TWL6030_CFG_STATE_APP(v)	(((v) & TWL6030_CFG_STATE_APP_MASK) >>\
+						TWL6030_CFG_STATE_APP_SHIFT)
+
+/* Flags for SMPS Voltage reading */
+#define SMPS_OFFSET_EN		BIT(0)
+#define SMPS_EXTENDED_EN	BIT(1)
+
+/* twl6025 SMPS EPROM values */
+#define TWL6030_SMPS_OFFSET		0xB0
+#define TWL6030_SMPS_MULT		0xB3
+#define SMPS_MULTOFFSET_SMPS4	BIT(0)
+#define SMPS_MULTOFFSET_VIO	BIT(1)
+#define SMPS_MULTOFFSET_SMPS3	BIT(6)
+
 static inline int
 twlreg_read(struct twlreg_info *info, unsigned slave_subgp, unsigned offset)
 {
@@ -118,21 +146,38 @@ static int twlreg_grp(struct regulator_dev *rdev)
 #define P2_GRP_6030	BIT(1)		/* "peripherals" */
 #define P1_GRP_6030	BIT(0)		/* CPU/Linux */
 
-static int twlreg_is_enabled(struct regulator_dev *rdev)
+static int twl4030reg_is_enabled(struct regulator_dev *rdev)
 {
 	int	state = twlreg_grp(rdev);
 
 	if (state < 0)
 		return state;
 
-	if (twl_class_is_4030())
-		state &= P1_GRP_4030;
+	return state & P1_GRP_4030;
+}
+
+static int twl6030reg_is_enabled(struct regulator_dev *rdev)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+	int			grp = 0, val;
+
+	if (!(twl_class_is_6030() && (info->features & TWL6025_SUBCLASS)))
+		grp = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_GRP);
+	if (grp < 0)
+		return grp;
+
+	if (!(twl_class_is_6030() && (info->features & TWL6025_SUBCLASS)))
+		grp &= P1_GRP_6030;
 	else
-		state &= P1_GRP_6030;
-	return state;
+		grp = 1;
+
+	val = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_STATE);
+	val = TWL6030_CFG_STATE_APP(val);
+
+	return grp && (val == TWL6030_CFG_STATE_ON);
 }
 
-static int twlreg_enable(struct regulator_dev *rdev)
+static int twl4030reg_enable(struct regulator_dev *rdev)
 {
 	struct twlreg_info	*info = rdev_get_drvdata(rdev);
 	int			grp;
@@ -142,10 +187,7 @@ static int twlreg_enable(struct regulator_dev *rdev)
 	if (grp < 0)
 		return grp;
 
-	if (twl_class_is_4030())
-		grp |= P1_GRP_4030;
-	else
-		grp |= P1_GRP_6030;
+	grp |= P1_GRP_4030;
 
 	ret = twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_GRP, grp);
 
@@ -154,29 +196,63 @@ static int twlreg_enable(struct regulator_dev *rdev)
 	return ret;
 }
 
-static int twlreg_disable(struct regulator_dev *rdev)
+static int twl6030reg_enable(struct regulator_dev *rdev)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+	int			grp = 0;
+	int			ret;
+
+	if (!(twl_class_is_6030() && (info->features & TWL6025_SUBCLASS)))
+		grp = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_GRP);
+	if (grp < 0)
+		return grp;
+
+	ret = twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_STATE,
+			grp << TWL6030_CFG_STATE_GRP_SHIFT |
+			TWL6030_CFG_STATE_ON);
+
+	udelay(info->delay);
+
+	return ret;
+}
+
+static int twl4030reg_disable(struct regulator_dev *rdev)
 {
 	struct twlreg_info	*info = rdev_get_drvdata(rdev);
 	int			grp;
+	int			ret;
 
 	grp = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_GRP);
 	if (grp < 0)
 		return grp;
 
-	if (twl_class_is_4030())
-		grp &= ~(P1_GRP_4030 | P2_GRP_4030 | P3_GRP_4030);
-	else
-		grp &= ~(P1_GRP_6030 | P2_GRP_6030 | P3_GRP_6030);
+	grp &= ~(P1_GRP_4030 | P2_GRP_4030 | P3_GRP_4030);
 
-	return twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_GRP, grp);
+	ret = twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_GRP, grp);
+
+	return ret;
 }
 
-static int twlreg_get_status(struct regulator_dev *rdev)
+static int twl6030reg_disable(struct regulator_dev *rdev)
 {
-	int	state = twlreg_grp(rdev);
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+	int			grp = 0;
+	int			ret;
+
+	if (!(twl_class_is_6030() && (info->features & TWL6025_SUBCLASS)))
+		grp = P1_GRP_6030 | P2_GRP_6030 | P3_GRP_6030;
+
+	/* For 6030, set the off state for all grps enabled */
+	ret = twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_STATE,
+			(grp) << TWL6030_CFG_STATE_GRP_SHIFT |
+			TWL6030_CFG_STATE_OFF);
+
+	return ret;
+}
 
-	if (twl_class_is_6030())
-		return 0; /* FIXME return for 6030 regulator */
+static int twl4030reg_get_status(struct regulator_dev *rdev)
+{
+	int	state = twlreg_grp(rdev);
 
 	if (state < 0)
 		return state;
@@ -190,15 +266,39 @@ static int twlreg_get_status(struct regulator_dev *rdev)
 		: REGULATOR_STATUS_STANDBY;
 }
 
-static int twlreg_set_mode(struct regulator_dev *rdev, unsigned mode)
+static int twl6030reg_get_status(struct regulator_dev *rdev)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+	int			val;
+
+	val = twlreg_grp(rdev);
+	if (val < 0)
+		return val;
+
+	val = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_STATE);
+
+	switch (TWL6030_CFG_STATE_APP(val)) {
+	case TWL6030_CFG_STATE_ON:
+		return REGULATOR_STATUS_NORMAL;
+
+	case TWL6030_CFG_STATE_SLEEP:
+		return REGULATOR_STATUS_STANDBY;
+
+	case TWL6030_CFG_STATE_OFF:
+	case TWL6030_CFG_STATE_OFF2:
+	default:
+		break;
+	}
+
+	return REGULATOR_STATUS_OFF;
+}
+
+static int twl4030reg_set_mode(struct regulator_dev *rdev, unsigned mode)
 {
 	struct twlreg_info	*info = rdev_get_drvdata(rdev);
 	unsigned		message;
 	int			status;
 
-	if (twl_class_is_6030())
-		return 0; /* FIXME return for 6030 regulator */
-
 	/* We can only set the mode through state machine commands... */
 	switch (mode) {
 	case REGULATOR_MODE_NORMAL:
@@ -227,6 +327,36 @@ static int twlreg_set_mode(struct regulator_dev *rdev, unsigned mode)
 			message & 0xff, TWL4030_PM_MASTER_PB_WORD_LSB);
 }
 
+static int twl6030reg_set_mode(struct regulator_dev *rdev, unsigned mode)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+	int grp = 0;
+	int val;
+
+	if (!(twl_class_is_6030() && (info->features & TWL6025_SUBCLASS)))
+		grp = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_GRP);
+
+	if (grp < 0)
+		return grp;
+
+	/* Compose the state register settings */
+	val = grp << TWL6030_CFG_STATE_GRP_SHIFT;
+	/* We can only set the mode through state machine commands... */
+	switch (mode) {
+	case REGULATOR_MODE_NORMAL:
+		val |= TWL6030_CFG_STATE_ON;
+		break;
+	case REGULATOR_MODE_STANDBY:
+		val |= TWL6030_CFG_STATE_SLEEP;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_STATE, val);
+}
+
 /*----------------------------------------------------------------------*/
 
 /*
@@ -375,13 +505,13 @@ static struct regulator_ops twl4030ldo_ops = {
 	.set_voltage	= twl4030ldo_set_voltage,
 	.get_voltage	= twl4030ldo_get_voltage,
 
-	.enable		= twlreg_enable,
-	.disable	= twlreg_disable,
-	.is_enabled	= twlreg_is_enabled,
+	.enable		= twl4030reg_enable,
+	.disable	= twl4030reg_disable,
+	.is_enabled	= twl4030reg_is_enabled,
 
-	.set_mode	= twlreg_set_mode,
+	.set_mode	= twl4030reg_set_mode,
 
-	.get_status	= twlreg_get_status,
+	.get_status	= twl4030reg_get_status,
 };
 
 static int twl6030ldo_list_voltage(struct regulator_dev *rdev, unsigned index)
@@ -433,13 +563,13 @@ static struct regulator_ops twl6030ldo_ops = {
 	.set_voltage	= twl6030ldo_set_voltage,
 	.get_voltage	= twl6030ldo_get_voltage,
 
-	.enable		= twlreg_enable,
-	.disable	= twlreg_disable,
-	.is_enabled	= twlreg_is_enabled,
+	.enable		= twl6030reg_enable,
+	.disable	= twl6030reg_disable,
+	.is_enabled	= twl6030reg_is_enabled,
 
-	.set_mode	= twlreg_set_mode,
+	.set_mode	= twl6030reg_set_mode,
 
-	.get_status	= twlreg_get_status,
+	.get_status	= twl6030reg_get_status,
 };
 
 /*----------------------------------------------------------------------*/
@@ -461,25 +591,242 @@ static int twlfixed_get_voltage(struct regulator_dev *rdev)
 	return info->min_mV * 1000;
 }
 
-static struct regulator_ops twlfixed_ops = {
+static struct regulator_ops twl4030fixed_ops = {
+	.list_voltage	= twlfixed_list_voltage,
+
+	.get_voltage	= twlfixed_get_voltage,
+
+	.enable		= twl4030reg_enable,
+	.disable	= twl4030reg_disable,
+	.is_enabled	= twl4030reg_is_enabled,
+
+	.set_mode	= twl4030reg_set_mode,
+
+	.get_status	= twl4030reg_get_status,
+};
+
+static struct regulator_ops twl6030fixed_ops = {
 	.list_voltage	= twlfixed_list_voltage,
 
 	.get_voltage	= twlfixed_get_voltage,
 
-	.enable		= twlreg_enable,
-	.disable	= twlreg_disable,
-	.is_enabled	= twlreg_is_enabled,
+	.enable		= twl6030reg_enable,
+	.disable	= twl6030reg_disable,
+	.is_enabled	= twl6030reg_is_enabled,
 
-	.set_mode	= twlreg_set_mode,
+	.set_mode	= twl6030reg_set_mode,
 
-	.get_status	= twlreg_get_status,
+	.get_status	= twl6030reg_get_status,
 };
 
 static struct regulator_ops twl6030_fixed_resource = {
-	.enable		= twlreg_enable,
-	.disable	= twlreg_disable,
-	.is_enabled	= twlreg_is_enabled,
-	.get_status	= twlreg_get_status,
+	.enable		= twl6030reg_enable,
+	.disable	= twl6030reg_disable,
+	.is_enabled	= twl6030reg_is_enabled,
+	.get_status	= twl6030reg_get_status,
+};
+
+/*
+ * SMPS status and control
+ */
+
+static int twl6030smps_list_voltage(struct regulator_dev *rdev, unsigned index)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+
+	int voltage = 0;
+
+	switch (info->flags) {
+	case SMPS_OFFSET_EN:
+		voltage = 100000;
+		/* fall through */
+	case 0:
+		switch (index) {
+		case 0:
+			voltage = 0;
+			break;
+		case 58:
+			voltage = 1350 * 1000;
+			break;
+		case 59:
+			voltage = 1500 * 1000;
+			break;
+		case 60:
+			voltage = 1800 * 1000;
+			break;
+		case 61:
+			voltage = 1900 * 1000;
+			break;
+		case 62:
+			voltage = 2100 * 1000;
+			break;
+		default:
+			voltage += (600000 + (12500 * (index - 1)));
+		}
+		break;
+	case SMPS_EXTENDED_EN:
+		switch (index) {
+		case 0:
+			voltage = 0;
+			break;
+		case 58:
+			voltage = 2084 * 1000;
+			break;
+		case 59:
+			voltage = 2315 * 1000;
+			break;
+		case 60:
+			voltage = 2778 * 1000;
+			break;
+		case 61:
+			voltage = 2932 * 1000;
+			break;
+		case 62:
+			voltage = 3241 * 1000;
+			break;
+		default:
+			voltage = (1852000 + (38600 * (index - 1)));
+		}
+		break;
+	case SMPS_OFFSET_EN | SMPS_EXTENDED_EN:
+		switch (index) {
+		case 0:
+			voltage = 0;
+			break;
+		case 58:
+			voltage = 4167 * 1000;
+			break;
+		case 59:
+			voltage = 2315 * 1000;
+			break;
+		case 60:
+			voltage = 2778 * 1000;
+			break;
+		case 61:
+			voltage = 2932 * 1000;
+			break;
+		case 62:
+			voltage = 3241 * 1000;
+			break;
+		default:
+			voltage = (2161000 + (38600 * (index - 1)));
+		}
+		break;
+	}
+
+	return voltage;
+}
+
+static int
+twl6030smps_set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV,
+			unsigned int *selector)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+	int	vsel = 0;
+
+	switch (info->flags) {
+	case 0:
+		if (min_uV == 0)
+			vsel = 0;
+		else if ((min_uV >= 600000) && (max_uV <= 1300000)) {
+			vsel = (min_uV - 600000) / 125;
+			if (vsel % 100)
+				vsel += 100;
+			vsel /= 100;
+			vsel++;
+		}
+		/* Values 1..57 for vsel are linear and can be calculated
+		 * values 58..62 are non linear.
+		 */
+		else if ((min_uV > 1900000) && (max_uV >= 2100000))
+			vsel = 62;
+		else if ((min_uV > 1800000) && (max_uV >= 1900000))
+			vsel = 61;
+		else if ((min_uV > 1500000) && (max_uV >= 1800000))
+			vsel = 60;
+		else if ((min_uV > 1350000) && (max_uV >= 1500000))
+			vsel = 59;
+		else if ((min_uV > 1300000) && (max_uV >= 1350000))
+			vsel = 58;
+		else
+			return -EINVAL;
+		break;
+	case SMPS_OFFSET_EN:
+		if (min_uV == 0)
+			vsel = 0;
+		else if ((min_uV >= 700000) && (max_uV <= 1420000)) {
+			vsel = (min_uV - 700000) / 125;
+			if (vsel % 100)
+				vsel += 100;
+			vsel /= 100;
+			vsel++;
+		}
+		/* Values 1..57 for vsel are linear and can be calculated
+		 * values 58..62 are non linear.
+		 */
+		else if ((min_uV > 1900000) && (max_uV >= 2100000))
+			vsel = 62;
+		else if ((min_uV > 1800000) && (max_uV >= 1900000))
+			vsel = 61;
+		else if ((min_uV > 1350000) && (max_uV >= 1800000))
+			vsel = 60;
+		else if ((min_uV > 1350000) && (max_uV >= 1500000))
+			vsel = 59;
+		else if ((min_uV > 1300000) && (max_uV >= 1350000))
+			vsel = 58;
+		else
+			return -EINVAL;
+		break;
+	case SMPS_EXTENDED_EN:
+		if (min_uV == 0)
+			vsel = 0;
+		else if ((min_uV >= 1852000) && (max_uV <= 4013600)) {
+			vsel = (min_uV - 1852000) / 386;
+			if (vsel % 100)
+				vsel += 100;
+			vsel /= 100;
+			vsel++;
+		}
+		break;
+	case SMPS_OFFSET_EN|SMPS_EXTENDED_EN:
+		if (min_uV == 0)
+			vsel = 0;
+		else if ((min_uV >= 2161000) && (max_uV <= 4321000)) {
+			vsel = (min_uV - 1852000) / 386;
+			if (vsel % 100)
+				vsel += 100;
+			vsel /= 100;
+			vsel++;
+		}
+		break;
+	}
+
+	*selector = vsel;
+
+	return twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_VOLTAGE_SMPS,
+							vsel);
+}
+
+static int twl6030smps_get_voltage_sel(struct regulator_dev *rdev)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+
+	return twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_VOLTAGE_SMPS);
+}
+
+static struct regulator_ops twlsmps_ops = {
+	.list_voltage		= twl6030smps_list_voltage,
+
+	.set_voltage		= twl6030smps_set_voltage,
+	.get_voltage_sel	= twl6030smps_get_voltage_sel,
+
+	.enable			= twl6030reg_enable,
+	.disable		= twl6030reg_disable,
+	.is_enabled		= twl6030reg_is_enabled,
+
+	.set_mode		= twl6030reg_set_mode,
+
+	.get_status		= twl6030reg_get_status,
 };
 
 /*----------------------------------------------------------------------*/
@@ -487,11 +834,10 @@ static struct regulator_ops twl6030_fixed_resource = {
 #define TWL4030_FIXED_LDO(label, offset, mVolts, num, turnon_delay, \
 			remap_conf) \
 		TWL_FIXED_LDO(label, offset, mVolts, num, turnon_delay, \
-			remap_conf, TWL4030)
-#define TWL6030_FIXED_LDO(label, offset, mVolts, num, turnon_delay, \
-			remap_conf) \
+			remap_conf, TWL4030, twl4030fixed_ops)
+#define TWL6030_FIXED_LDO(label, offset, mVolts, num, turnon_delay) \
 		TWL_FIXED_LDO(label, offset, mVolts, num, turnon_delay, \
-			remap_conf, TWL6030)
+			0x0, TWL6030, twl6030fixed_ops)
 
 #define TWL4030_ADJUSTABLE_LDO(label, offset, num, turnon_delay, remap_conf) { \
 	.base = offset, \
@@ -510,13 +856,11 @@ static struct regulator_ops twl6030_fixed_resource = {
 		}, \
 	}
 
-#define TWL6030_ADJUSTABLE_LDO(label, offset, min_mVolts, max_mVolts, num, \
-		remap_conf) { \
+#define TWL6030_ADJUSTABLE_LDO(label, offset, min_mVolts, max_mVolts, num) { \
 	.base = offset, \
 	.id = num, \
 	.min_mV = min_mVolts, \
 	.max_mV = max_mVolts, \
-	.remap = remap_conf, \
 	.desc = { \
 		.name = #label, \
 		.id = TWL6030_REG_##label, \
@@ -527,9 +871,23 @@ static struct regulator_ops twl6030_fixed_resource = {
 		}, \
 	}
 
+#define TWL6025_ADJUSTABLE_LDO(label, offset, min_mVolts, max_mVolts, num) { \
+	.base = offset, \
+	.id = num, \
+	.min_mV = min_mVolts, \
+	.max_mV = max_mVolts, \
+	.desc = { \
+		.name = #label, \
+		.id = TWL6025_REG_##label, \
+		.n_voltages = ((max_mVolts - min_mVolts)/100) + 1, \
+		.ops = &twl6030ldo_ops, \
+		.type = REGULATOR_VOLTAGE, \
+		.owner = THIS_MODULE, \
+		}, \
+	}
 
 #define TWL_FIXED_LDO(label, offset, mVolts, num, turnon_delay, remap_conf, \
-		family) { \
+		family, operations) { \
 	.base = offset, \
 	.id = num, \
 	.min_mV = mVolts, \
@@ -539,17 +897,16 @@ static struct regulator_ops twl6030_fixed_resource = {
 		.name = #label, \
 		.id = family##_REG_##label, \
 		.n_voltages = 1, \
-		.ops = &twlfixed_ops, \
+		.ops = &operations, \
 		.type = REGULATOR_VOLTAGE, \
 		.owner = THIS_MODULE, \
 		}, \
 	}
 
-#define TWL6030_FIXED_RESOURCE(label, offset, num, turnon_delay, remap_conf) { \
+#define TWL6030_FIXED_RESOURCE(label, offset, num, turnon_delay) { \
 	.base = offset, \
 	.id = num, \
 	.delay = turnon_delay, \
-	.remap = remap_conf, \
 	.desc = { \
 		.name = #label, \
 		.id = TWL6030_REG_##label, \
@@ -559,6 +916,21 @@ static struct regulator_ops twl6030_fixed_resource = {
 		}, \
 	}
 
+#define TWL6025_ADJUSTABLE_SMPS(label, offset, num) { \
+	.base = offset, \
+	.id = num, \
+	.min_mV = 600, \
+	.max_mV = 2100, \
+	.desc = { \
+		.name = #label, \
+		.id = TWL6025_REG_##label, \
+		.n_voltages = 63, \
+		.ops = &twlsmps_ops, \
+		.type = REGULATOR_VOLTAGE, \
+		.owner = THIS_MODULE, \
+		}, \
+	}
+
 /*
  * We list regulators here if systems need some level of
  * software control over them after boot.
@@ -589,19 +961,52 @@ static struct twlreg_info twl_regs[] = {
 	/* 6030 REG with base as PMC Slave Misc : 0x0030 */
 	/* Turnon-delay and remap configuration values for 6030 are not
 	   verified since the specification is not public */
-	TWL6030_ADJUSTABLE_LDO(VAUX1_6030, 0x54, 1000, 3300, 1, 0x21),
-	TWL6030_ADJUSTABLE_LDO(VAUX2_6030, 0x58, 1000, 3300, 2, 0x21),
-	TWL6030_ADJUSTABLE_LDO(VAUX3_6030, 0x5c, 1000, 3300, 3, 0x21),
-	TWL6030_ADJUSTABLE_LDO(VMMC, 0x68, 1000, 3300, 4, 0x21),
-	TWL6030_ADJUSTABLE_LDO(VPP, 0x6c, 1000, 3300, 5, 0x21),
-	TWL6030_ADJUSTABLE_LDO(VUSIM, 0x74, 1000, 3300, 7, 0x21),
-	TWL6030_FIXED_LDO(VANA, 0x50, 2100, 15, 0, 0x21),
-	TWL6030_FIXED_LDO(VCXIO, 0x60, 1800, 16, 0, 0x21),
-	TWL6030_FIXED_LDO(VDAC, 0x64, 1800, 17, 0, 0x21),
-	TWL6030_FIXED_LDO(VUSB, 0x70, 3300, 18, 0, 0x21),
-	TWL6030_FIXED_RESOURCE(CLK32KG, 0x8C, 48, 0, 0x21),
+	TWL6030_ADJUSTABLE_LDO(VAUX1_6030, 0x54, 1000, 3300, 1),
+	TWL6030_ADJUSTABLE_LDO(VAUX2_6030, 0x58, 1000, 3300, 2),
+	TWL6030_ADJUSTABLE_LDO(VAUX3_6030, 0x5c, 1000, 3300, 3),
+	TWL6030_ADJUSTABLE_LDO(VMMC, 0x68, 1000, 3300, 4),
+	TWL6030_ADJUSTABLE_LDO(VPP, 0x6c, 1000, 3300, 5),
+	TWL6030_ADJUSTABLE_LDO(VUSIM, 0x74, 1000, 3300, 7),
+	TWL6030_FIXED_LDO(VANA, 0x50, 2100, 15, 0),
+	TWL6030_FIXED_LDO(VCXIO, 0x60, 1800, 16, 0),
+	TWL6030_FIXED_LDO(VDAC, 0x64, 1800, 17, 0),
+	TWL6030_FIXED_LDO(VUSB, 0x70, 3300, 18, 0),
+	TWL6030_FIXED_RESOURCE(CLK32KG, 0x8C, 48, 0),
+
+	/* 6025 are renamed compared to 6030 versions */
+	TWL6025_ADJUSTABLE_LDO(LDO2, 0x54, 1000, 3300, 1),
+	TWL6025_ADJUSTABLE_LDO(LDO4, 0x58, 1000, 3300, 2),
+	TWL6025_ADJUSTABLE_LDO(LDO3, 0x5c, 1000, 3300, 3),
+	TWL6025_ADJUSTABLE_LDO(LDO5, 0x68, 1000, 3300, 4),
+	TWL6025_ADJUSTABLE_LDO(LDO1, 0x6c, 1000, 3300, 5),
+	TWL6025_ADJUSTABLE_LDO(LDO7, 0x74, 1000, 3300, 7),
+	TWL6025_ADJUSTABLE_LDO(LDO6, 0x60, 1000, 3300, 16),
+	TWL6025_ADJUSTABLE_LDO(LDOLN, 0x64, 1000, 3300, 17),
+	TWL6025_ADJUSTABLE_LDO(LDOUSB, 0x70, 1000, 3300, 18),
+
+	TWL6025_ADJUSTABLE_SMPS(SMPS3, 0x34, 1),
+	TWL6025_ADJUSTABLE_SMPS(SMPS4, 0x10, 2),
+	TWL6025_ADJUSTABLE_SMPS(VIO, 0x16, 3),
 };
 
+static u8 twl_get_smps_offset(void)
+{
+	u8 value;
+
+	twl_i2c_read_u8(TWL_MODULE_PM_RECEIVER, &value,
+			TWL6030_SMPS_OFFSET);
+	return value;
+}
+
+static u8 twl_get_smps_mult(void)
+{
+	u8 value;
+
+	twl_i2c_read_u8(TWL_MODULE_PM_RECEIVER, &value,
+			TWL6030_SMPS_MULT);
+	return value;
+}
+
 static int __devinit twlreg_probe(struct platform_device *pdev)
 {
 	int				i;
@@ -623,6 +1028,9 @@ static int __devinit twlreg_probe(struct platform_device *pdev)
 	if (!initdata)
 		return -EINVAL;
 
+	/* copy the features into regulator data */
+	info->features = (unsigned long)initdata->driver_data;
+
 	/* Constrain board-specific capabilities according to what
 	 * this driver and the chip itself can actually do.
 	 */
@@ -645,6 +1053,27 @@ static int __devinit twlreg_probe(struct platform_device *pdev)
 		break;
 	}
 
+	switch (pdev->id) {
+	case TWL6025_REG_SMPS3:
+		if (twl_get_smps_mult() & SMPS_MULTOFFSET_SMPS3)
+			info->flags |= SMPS_EXTENDED_EN;
+		if (twl_get_smps_offset() & SMPS_MULTOFFSET_SMPS3)
+			info->flags |= SMPS_OFFSET_EN;
+		break;
+	case TWL6025_REG_SMPS4:
+		if (twl_get_smps_mult() & SMPS_MULTOFFSET_SMPS4)
+			info->flags |= SMPS_EXTENDED_EN;
+		if (twl_get_smps_offset() & SMPS_MULTOFFSET_SMPS4)
+			info->flags |= SMPS_OFFSET_EN;
+		break;
+	case TWL6025_REG_VIO:
+		if (twl_get_smps_mult() & SMPS_MULTOFFSET_VIO)
+			info->flags |= SMPS_EXTENDED_EN;
+		if (twl_get_smps_offset() & SMPS_MULTOFFSET_VIO)
+			info->flags |= SMPS_OFFSET_EN;
+		break;
+	}
+
 	rdev = regulator_register(&info->desc, &pdev->dev, initdata, info);
 	if (IS_ERR(rdev)) {
 		dev_err(&pdev->dev, "can't register %s, %ld\n",
@@ -653,7 +1082,8 @@ static int __devinit twlreg_probe(struct platform_device *pdev)
 	}
 	platform_set_drvdata(pdev, rdev);
 
-	twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_REMAP,
+	if (twl_class_is_4030())
+		twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_REMAP,
 						info->remap);
 
 	/* NOTE:  many regulators support short-circuit IRQs (presentable
diff --git a/drivers/regulator/wm831x-dcdc.c b/drivers/regulator/wm831x-dcdc.c
index e93453b1b978..a0982e809851 100644
--- a/drivers/regulator/wm831x-dcdc.c
+++ b/drivers/regulator/wm831x-dcdc.c
@@ -600,7 +600,6 @@ err:
 static __devexit int wm831x_buckv_remove(struct platform_device *pdev)
 {
 	struct wm831x_dcdc *dcdc = platform_get_drvdata(pdev);
-	struct wm831x *wm831x = dcdc->wm831x;
 
 	platform_set_drvdata(pdev, NULL);
 
@@ -776,7 +775,6 @@ err:
 static __devexit int wm831x_buckp_remove(struct platform_device *pdev)
 {
 	struct wm831x_dcdc *dcdc = platform_get_drvdata(pdev);
-	struct wm831x *wm831x = dcdc->wm831x;
 
 	platform_set_drvdata(pdev, NULL);
 
diff --git a/drivers/regulator/wm8400-regulator.c b/drivers/regulator/wm8400-regulator.c
index b42d01cef35a..0f12c70bebc9 100644
--- a/drivers/regulator/wm8400-regulator.c
+++ b/drivers/regulator/wm8400-regulator.c
@@ -55,7 +55,7 @@ static int wm8400_ldo_list_voltage(struct regulator_dev *dev,
 		return 1600000 + ((selector - 14) * 100000);
 }
 
-static int wm8400_ldo_get_voltage(struct regulator_dev *dev)
+static int wm8400_ldo_get_voltage_sel(struct regulator_dev *dev)
 {
 	struct wm8400 *wm8400 = rdev_get_drvdata(dev);
 	u16 val;
@@ -63,7 +63,7 @@ static int wm8400_ldo_get_voltage(struct regulator_dev *dev)
 	val = wm8400_reg_read(wm8400, WM8400_LDO1_CONTROL + rdev_get_id(dev));
 	val &= WM8400_LDO1_VSEL_MASK;
 
-	return wm8400_ldo_list_voltage(dev, val);
+	return val;
 }
 
 static int wm8400_ldo_set_voltage(struct regulator_dev *dev,
@@ -104,7 +104,7 @@ static struct regulator_ops wm8400_ldo_ops = {
 	.enable = wm8400_ldo_enable,
 	.disable = wm8400_ldo_disable,
 	.list_voltage = wm8400_ldo_list_voltage,
-	.get_voltage = wm8400_ldo_get_voltage,
+	.get_voltage_sel = wm8400_ldo_get_voltage_sel,
 	.set_voltage = wm8400_ldo_set_voltage,
 };
 
@@ -145,7 +145,7 @@ static int wm8400_dcdc_list_voltage(struct regulator_dev *dev,
 	return 850000 + (selector * 25000);
 }
 
-static int wm8400_dcdc_get_voltage(struct regulator_dev *dev)
+static int wm8400_dcdc_get_voltage_sel(struct regulator_dev *dev)
 {
 	struct wm8400 *wm8400 = rdev_get_drvdata(dev);
 	u16 val;
@@ -154,7 +154,7 @@ static int wm8400_dcdc_get_voltage(struct regulator_dev *dev)
 	val = wm8400_reg_read(wm8400, WM8400_DCDC1_CONTROL_1 + offset);
 	val &= WM8400_DC1_VSEL_MASK;
 
-	return 850000 + (25000 * val);
+	return val;
 }
 
 static int wm8400_dcdc_set_voltage(struct regulator_dev *dev,
@@ -261,7 +261,7 @@ static struct regulator_ops wm8400_dcdc_ops = {
 	.enable = wm8400_dcdc_enable,
 	.disable = wm8400_dcdc_disable,
 	.list_voltage = wm8400_dcdc_list_voltage,
-	.get_voltage = wm8400_dcdc_get_voltage,
+	.get_voltage_sel = wm8400_dcdc_get_voltage_sel,
 	.set_voltage = wm8400_dcdc_set_voltage,
 	.get_mode = wm8400_dcdc_get_mode,
 	.set_mode = wm8400_dcdc_set_mode,
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index f822e13dc04b..ce2aabf5c550 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -1051,4 +1051,13 @@ config RTC_DRV_TILE
 	  Enable support for the Linux driver side of the Tilera
 	  hypervisor's real-time clock interface.
 
+config RTC_DRV_PUV3
+	tristate "PKUnity v3 RTC support"
+	depends on ARCH_PUV3
+	help
+	  This enables support for the RTC in the PKUnity-v3 SoCs.
+
+	  This drive can also be built as a module. If so, the module
+	  will be called rtc-puv3.
+
 endif # RTC_CLASS
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 213d725f16d4..0ffefe877bfa 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -78,6 +78,7 @@ obj-$(CONFIG_RTC_DRV_PCF50633)	+= rtc-pcf50633.o
 obj-$(CONFIG_RTC_DRV_PL030)	+= rtc-pl030.o
 obj-$(CONFIG_RTC_DRV_PL031)	+= rtc-pl031.o
 obj-$(CONFIG_RTC_DRV_PS3)	+= rtc-ps3.o
+obj-$(CONFIG_RTC_DRV_PUV3)	+= rtc-puv3.o
 obj-$(CONFIG_RTC_DRV_PXA)	+= rtc-pxa.o
 obj-$(CONFIG_RTC_DRV_R9701)	+= rtc-r9701.o
 obj-$(CONFIG_RTC_DRV_RP5C01)	+= rtc-rp5c01.o
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index ef6316acec43..df68618f6dbb 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -318,7 +318,7 @@ int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 }
 EXPORT_SYMBOL_GPL(rtc_read_alarm);
 
-int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
+static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 {
 	struct rtc_time tm;
 	long now, scheduled;
diff --git a/drivers/rtc/rtc-dev.c b/drivers/rtc/rtc-dev.c
index d0e06edb14c5..cace6d3aed9a 100644
--- a/drivers/rtc/rtc-dev.c
+++ b/drivers/rtc/rtc-dev.c
@@ -421,7 +421,8 @@ static long rtc_dev_ioctl(struct file *file,
 			err = ops->ioctl(rtc->dev.parent, cmd, arg);
 			if (err == -ENOIOCTLCMD)
 				err = -ENOTTY;
-		}
+		} else
+			err = -ENOTTY;
 		break;
 	}
 
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index 4724ba3acf1a..b2005b44e4f7 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -149,6 +149,7 @@ static const struct i2c_device_id ds1307_id[] = {
 	{ "ds1340", ds_1340 },
 	{ "ds3231", ds_3231 },
 	{ "m41t00", m41t00 },
+	{ "pt7c4338", ds_1307 },
 	{ "rx8025", rx_8025 },
 	{ }
 };
diff --git a/drivers/rtc/rtc-m41t93.c b/drivers/rtc/rtc-m41t93.c
index 1a84b3e227d1..7317d3b9a3d5 100644
--- a/drivers/rtc/rtc-m41t93.c
+++ b/drivers/rtc/rtc-m41t93.c
@@ -189,7 +189,7 @@ static int __devinit m41t93_probe(struct spi_device *spi)
 
 static int __devexit m41t93_remove(struct spi_device *spi)
 {
-	struct rtc_device *rtc = platform_get_drvdata(spi);
+	struct rtc_device *rtc = spi_get_drvdata(spi);
 
 	if (rtc)
 		rtc_device_unregister(rtc);
diff --git a/arch/unicore32/kernel/rtc.c b/drivers/rtc/rtc-puv3.c
index 8cad70b3302c..46f14b82f3ab 100644
--- a/arch/unicore32/kernel/rtc.c
+++ b/drivers/rtc/rtc-puv3.c
@@ -1,7 +1,5 @@
 /*
- * linux/arch/unicore32/kernel/rtc.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
+ * RTC driver code specific to PKUnity SoC and UniCore ISA
  *
  *	Maintained by GUAN Xue-tao <gxt@mprc.pku.edu.cn>
  *	Copyright (C) 2001-2010 Guan Xuetao
@@ -36,7 +34,6 @@ static int puv3_rtc_tickno  = IRQ_RTC;
 static DEFINE_SPINLOCK(puv3_rtc_pie_lock);
 
 /* IRQ Handlers */
-
 static irqreturn_t puv3_rtc_alarmirq(int irq, void *id)
 {
 	struct rtc_device *rdev = id;
@@ -89,7 +86,6 @@ static int puv3_rtc_setpie(struct device *dev, int enabled)
 }
 
 /* Time read/write */
-
 static int puv3_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm)
 {
 	rtc_time_to_tm(readl(RTC_RCNR), rtc_tm);
@@ -196,7 +192,6 @@ static void puv3_rtc_release(struct device *dev)
 	struct rtc_device *rtc_dev = platform_get_drvdata(pdev);
 
 	/* do not clear AIE here, it may be needed for wake */
-
 	puv3_rtc_setpie(dev, 0);
 	free_irq(puv3_rtc_alarmno, rtc_dev);
 	free_irq(puv3_rtc_tickno, rtc_dev);
@@ -218,7 +213,6 @@ static void puv3_rtc_enable(struct platform_device *pdev, int en)
 		writel(readl(RTC_RTSR) & ~RTC_RTSR_HZE, RTC_RTSR);
 	} else {
 		/* re-enable the device, and check it is ok */
-
 		if ((readl(RTC_RTSR) & RTC_RTSR_HZE) == 0) {
 			dev_info(&pdev->dev, "rtc disabled, re-enabling\n");
 			writel(readl(RTC_RTSR) | RTC_RTSR_HZE, RTC_RTSR);
@@ -251,7 +245,6 @@ static int puv3_rtc_probe(struct platform_device *pdev)
 	pr_debug("%s: probe=%p\n", __func__, pdev);
 
 	/* find the IRQs */
-
 	puv3_rtc_tickno = platform_get_irq(pdev, 1);
 	if (puv3_rtc_tickno < 0) {
 		dev_err(&pdev->dev, "no irq for rtc tick\n");
@@ -268,7 +261,6 @@ static int puv3_rtc_probe(struct platform_device *pdev)
 		 puv3_rtc_tickno, puv3_rtc_alarmno);
 
 	/* get the memory region */
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (res == NULL) {
 		dev_err(&pdev->dev, "failed to get memory region resource\n");
@@ -288,7 +280,6 @@ static int puv3_rtc_probe(struct platform_device *pdev)
 	puv3_rtc_enable(pdev, 1);
 
 	/* register RTC and exit */
-
 	rtc = rtc_device_register("pkunity", &pdev->dev, &puv3_rtcops,
 				  THIS_MODULE);
 
@@ -315,8 +306,6 @@ static int puv3_rtc_probe(struct platform_device *pdev)
 
 #ifdef CONFIG_PM
 
-/* RTC Power management control */
-
 static int ticnt_save;
 
 static int puv3_rtc_suspend(struct platform_device *pdev, pm_message_t state)
@@ -368,4 +357,3 @@ module_exit(puv3_rtc_exit);
 MODULE_DESCRIPTION("RTC Driver for the PKUnity v3 chip");
 MODULE_AUTHOR("Hu Dongliang");
 MODULE_LICENSE("GPL v2");
-
diff --git a/drivers/rtc/rtc-vt8500.c b/drivers/rtc/rtc-vt8500.c
index b8bc862903ae..efd6066b5cd2 100644
--- a/drivers/rtc/rtc-vt8500.c
+++ b/drivers/rtc/rtc-vt8500.c
@@ -78,7 +78,6 @@ struct vt8500_rtc {
 	void __iomem		*regbase;
 	struct resource		*res;
 	int			irq_alarm;
-	int			irq_hz;
 	struct rtc_device	*rtc;
 	spinlock_t		lock;		/* Protects this structure */
 };
@@ -100,10 +99,6 @@ static irqreturn_t vt8500_rtc_irq(int irq, void *dev_id)
 	if (isr & 1)
 		events |= RTC_AF | RTC_IRQF;
 
-	/* Only second/minute interrupts are supported */
-	if (isr & 2)
-		events |= RTC_UF | RTC_IRQF;
-
 	rtc_update_irq(vt8500_rtc->rtc, 1, events);
 
 	return IRQ_HANDLED;
@@ -199,27 +194,12 @@ static int vt8500_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int vt8500_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	struct vt8500_rtc *vt8500_rtc = dev_get_drvdata(dev);
-	unsigned long tmp = readl(vt8500_rtc->regbase + VT8500_RTC_CR);
-
-	if (enabled)
-		tmp |= VT8500_RTC_CR_SM_SEC | VT8500_RTC_CR_SM_ENABLE;
-	else
-		tmp &= ~VT8500_RTC_CR_SM_ENABLE;
-
-	writel(tmp, vt8500_rtc->regbase + VT8500_RTC_CR);
-	return 0;
-}
-
 static const struct rtc_class_ops vt8500_rtc_ops = {
 	.read_time = vt8500_rtc_read_time,
 	.set_time = vt8500_rtc_set_time,
 	.read_alarm = vt8500_rtc_read_alarm,
 	.set_alarm = vt8500_rtc_set_alarm,
 	.alarm_irq_enable = vt8500_alarm_irq_enable,
-	.update_irq_enable = vt8500_update_irq_enable,
 };
 
 static int __devinit vt8500_rtc_probe(struct platform_device *pdev)
@@ -248,13 +228,6 @@ static int __devinit vt8500_rtc_probe(struct platform_device *pdev)
 		goto err_free;
 	}
 
-	vt8500_rtc->irq_hz = platform_get_irq(pdev, 1);
-	if (vt8500_rtc->irq_hz < 0) {
-		dev_err(&pdev->dev, "No 1Hz IRQ resource defined\n");
-		ret = -ENXIO;
-		goto err_free;
-	}
-
 	vt8500_rtc->res = request_mem_region(vt8500_rtc->res->start,
 					     resource_size(vt8500_rtc->res),
 					     "vt8500-rtc");
@@ -272,9 +245,8 @@ static int __devinit vt8500_rtc_probe(struct platform_device *pdev)
 		goto err_release;
 	}
 
-	/* Enable the second/minute interrupt generation and enable RTC */
-	writel(VT8500_RTC_CR_ENABLE | VT8500_RTC_CR_24H
-		| VT8500_RTC_CR_SM_ENABLE | VT8500_RTC_CR_SM_SEC,
+	/* Enable RTC and set it to 24-hour mode */
+	writel(VT8500_RTC_CR_ENABLE | VT8500_RTC_CR_24H,
 	       vt8500_rtc->regbase + VT8500_RTC_CR);
 
 	vt8500_rtc->rtc = rtc_device_register("vt8500-rtc", &pdev->dev,
@@ -286,26 +258,16 @@ static int __devinit vt8500_rtc_probe(struct platform_device *pdev)
 		goto err_unmap;
 	}
 
-	ret = request_irq(vt8500_rtc->irq_hz, vt8500_rtc_irq, 0,
-			  "rtc 1Hz", vt8500_rtc);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "can't get irq %i, err %d\n",
-			vt8500_rtc->irq_hz, ret);
-		goto err_unreg;
-	}
-
 	ret = request_irq(vt8500_rtc->irq_alarm, vt8500_rtc_irq, 0,
 			  "rtc alarm", vt8500_rtc);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "can't get irq %i, err %d\n",
 			vt8500_rtc->irq_alarm, ret);
-		goto err_free_hz;
+		goto err_unreg;
 	}
 
 	return 0;
 
-err_free_hz:
-	free_irq(vt8500_rtc->irq_hz, vt8500_rtc);
 err_unreg:
 	rtc_device_unregister(vt8500_rtc->rtc);
 err_unmap:
@@ -323,7 +285,6 @@ static int __devexit vt8500_rtc_remove(struct platform_device *pdev)
 	struct vt8500_rtc *vt8500_rtc = platform_get_drvdata(pdev);
 
 	free_irq(vt8500_rtc->irq_alarm, vt8500_rtc);
-	free_irq(vt8500_rtc->irq_hz, vt8500_rtc);
 
 	rtc_device_unregister(vt8500_rtc->rtc);
 
diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c
index 85dddb1e4126..46784b83c5c4 100644
--- a/drivers/s390/block/dasd_diag.c
+++ b/drivers/s390/block/dasd_diag.c
@@ -24,7 +24,7 @@
 #include <asm/debug.h>
 #include <asm/ebcdic.h>
 #include <asm/io.h>
-#include <asm/s390_ext.h>
+#include <asm/irq.h>
 #include <asm/vtoc.h>
 #include <asm/diag.h>
 
@@ -642,7 +642,7 @@ dasd_diag_init(void)
 	}
 	ASCEBC(dasd_diag_discipline.ebcname, 4);
 
-	ctl_set_bit(0, 9);
+	service_subclass_irq_register();
 	register_external_interrupt(0x2603, dasd_ext_handler);
 	dasd_diag_discipline_pointer = &dasd_diag_discipline;
 	return 0;
@@ -652,7 +652,7 @@ static void __exit
 dasd_diag_cleanup(void)
 {
 	unregister_external_interrupt(0x2603, dasd_ext_handler);
-	ctl_clear_bit(0, 9);
+	service_subclass_irq_unregister();
 	dasd_diag_discipline_pointer = NULL;
 }
 
diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c
index b76c61f82485..eaa7e78186f9 100644
--- a/drivers/s390/char/sclp.c
+++ b/drivers/s390/char/sclp.c
@@ -19,7 +19,6 @@
 #include <linux/suspend.h>
 #include <linux/completion.h>
 #include <linux/platform_device.h>
-#include <asm/s390_ext.h>
 #include <asm/types.h>
 #include <asm/irq.h>
 
@@ -885,12 +884,12 @@ sclp_check_interface(void)
 		spin_unlock_irqrestore(&sclp_lock, flags);
 		/* Enable service-signal interruption - needs to happen
 		 * with IRQs enabled. */
-		ctl_set_bit(0, 9);
+		service_subclass_irq_register();
 		/* Wait for signal from interrupt or timeout */
 		sclp_sync_wait();
 		/* Disable service-signal interruption - needs to happen
 		 * with IRQs enabled. */
-		ctl_clear_bit(0,9);
+		service_subclass_irq_unregister();
 		spin_lock_irqsave(&sclp_lock, flags);
 		del_timer(&sclp_request_timer);
 		if (sclp_init_req.status == SCLP_REQ_DONE &&
@@ -1070,7 +1069,7 @@ sclp_init(void)
 	spin_unlock_irqrestore(&sclp_lock, flags);
 	/* Enable service-signal external interruption - needs to happen with
 	 * IRQs enabled. */
-	ctl_set_bit(0, 9);
+	service_subclass_irq_register();
 	sclp_init_mask(1);
 	return 0;
 
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 55e8f721e38a..570d4da10696 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -416,7 +416,7 @@ static void process_buffer_error(struct qdio_q *q, int count)
 
 	/* special handling for no target buffer empty */
 	if ((!q->is_input_q &&
-	    (q->sbal[q->first_to_check]->element[15].flags & 0xff) == 0x10)) {
+	    (q->sbal[q->first_to_check]->element[15].sflags) == 0x10)) {
 		qperf_inc(q, target_full);
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "OUTFULL FTC:%02x",
 			      q->first_to_check);
@@ -427,8 +427,8 @@ static void process_buffer_error(struct qdio_q *q, int count)
 	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->sbal[q->first_to_check]->element[14].sflags,
+		  q->sbal[q->first_to_check]->element[15].sflags);
 
 	/*
 	 * Interrupts may be avoided as long as the error is present
diff --git a/drivers/s390/kvm/kvm_virtio.c b/drivers/s390/kvm/kvm_virtio.c
index 607998f0b7d8..aec60d55b10d 100644
--- a/drivers/s390/kvm/kvm_virtio.c
+++ b/drivers/s390/kvm/kvm_virtio.c
@@ -25,7 +25,6 @@
 #include <asm/kvm_para.h>
 #include <asm/kvm_virtio.h>
 #include <asm/setup.h>
-#include <asm/s390_ext.h>
 #include <asm/irq.h>
 
 #define VIRTIO_SUBCODE_64 0x0D00
@@ -441,7 +440,7 @@ static int __init kvm_devices_init(void)
 
 	INIT_WORK(&hotplug_work, hotplug_devices);
 
-	ctl_set_bit(0, 9);
+	service_subclass_irq_register();
 	register_external_interrupt(0x2603, kvm_extint_handler);
 
 	scan_devices();
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 55c6aa1c9704..d3cee33e554c 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -361,7 +361,7 @@ enum qeth_header_ids {
 
 static inline int qeth_is_last_sbale(struct qdio_buffer_element *sbale)
 {
-	return (sbale->flags & SBAL_FLAGS_LAST_ENTRY);
+	return (sbale->eflags & SBAL_EFLAGS_LAST_ENTRY);
 }
 
 enum qeth_qdio_buffer_states {
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 503678a30981..dd08f7b42fb8 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -890,7 +890,7 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
 	struct sk_buff *skb;
 
 	/* is PCI flag set on buffer? */
-	if (buf->buffer->element[0].flags & 0x40)
+	if (buf->buffer->element[0].sflags & SBAL_SFLAGS0_PCI_REQ)
 		atomic_dec(&queue->set_pci_flags_count);
 
 	skb = skb_dequeue(&buf->skb_list);
@@ -906,9 +906,11 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
 		buf->is_header[i] = 0;
 		buf->buffer->element[i].length = 0;
 		buf->buffer->element[i].addr = NULL;
-		buf->buffer->element[i].flags = 0;
+		buf->buffer->element[i].eflags = 0;
+		buf->buffer->element[i].sflags = 0;
 	}
-	buf->buffer->element[15].flags = 0;
+	buf->buffer->element[15].eflags = 0;
+	buf->buffer->element[15].sflags = 0;
 	buf->next_element_to_fill = 0;
 	atomic_set(&buf->state, QETH_QDIO_BUF_EMPTY);
 }
@@ -2368,9 +2370,10 @@ static int qeth_init_input_buffer(struct qeth_card *card,
 		buf->buffer->element[i].length = PAGE_SIZE;
 		buf->buffer->element[i].addr =  pool_entry->elements[i];
 		if (i == QETH_MAX_BUFFER_ELEMENTS(card) - 1)
-			buf->buffer->element[i].flags = SBAL_FLAGS_LAST_ENTRY;
+			buf->buffer->element[i].eflags = SBAL_EFLAGS_LAST_ENTRY;
 		else
-			buf->buffer->element[i].flags = 0;
+			buf->buffer->element[i].eflags = 0;
+		buf->buffer->element[i].sflags = 0;
 	}
 	return 0;
 }
@@ -2718,11 +2721,11 @@ int qeth_check_qdio_errors(struct qeth_card *card, struct qdio_buffer *buf,
 	if (qdio_error) {
 		QETH_CARD_TEXT(card, 2, dbftext);
 		QETH_CARD_TEXT_(card, 2, " F15=%02X",
-			       buf->element[15].flags & 0xff);
+			       buf->element[15].sflags);
 		QETH_CARD_TEXT_(card, 2, " F14=%02X",
-			       buf->element[14].flags & 0xff);
+			       buf->element[14].sflags);
 		QETH_CARD_TEXT_(card, 2, " qerr=%X", qdio_error);
-		if ((buf->element[15].flags & 0xff) == 0x12) {
+		if ((buf->element[15].sflags) == 0x12) {
 			card->stats.rx_dropped++;
 			return 0;
 		} else
@@ -2798,7 +2801,7 @@ EXPORT_SYMBOL_GPL(qeth_queue_input_buffer);
 static int qeth_handle_send_error(struct qeth_card *card,
 		struct qeth_qdio_out_buffer *buffer, unsigned int qdio_err)
 {
-	int sbalf15 = buffer->buffer->element[15].flags & 0xff;
+	int sbalf15 = buffer->buffer->element[15].sflags;
 
 	QETH_CARD_TEXT(card, 6, "hdsnderr");
 	if (card->info.type == QETH_CARD_TYPE_IQD) {
@@ -2907,8 +2910,8 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 
 	for (i = index; i < index + count; ++i) {
 		buf = &queue->bufs[i % QDIO_MAX_BUFFERS_PER_Q];
-		buf->buffer->element[buf->next_element_to_fill - 1].flags |=
-				SBAL_FLAGS_LAST_ENTRY;
+		buf->buffer->element[buf->next_element_to_fill - 1].eflags |=
+				SBAL_EFLAGS_LAST_ENTRY;
 
 		if (queue->card->info.type == QETH_CARD_TYPE_IQD)
 			continue;
@@ -2921,7 +2924,7 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 				/* it's likely that we'll go to packing
 				 * mode soon */
 				atomic_inc(&queue->set_pci_flags_count);
-				buf->buffer->element[0].flags |= 0x40;
+				buf->buffer->element[0].sflags |= SBAL_SFLAGS0_PCI_REQ;
 			}
 		} else {
 			if (!atomic_read(&queue->set_pci_flags_count)) {
@@ -2934,7 +2937,7 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 				 * further send was requested by the stack
 				 */
 				atomic_inc(&queue->set_pci_flags_count);
-				buf->buffer->element[0].flags |= 0x40;
+				buf->buffer->element[0].sflags |= SBAL_SFLAGS0_PCI_REQ;
 			}
 		}
 	}
@@ -3180,20 +3183,20 @@ static inline void __qeth_fill_buffer(struct sk_buff *skb,
 		if (!length) {
 			if (first_lap)
 				if (skb_shinfo(skb)->nr_frags)
-					buffer->element[element].flags =
-						SBAL_FLAGS_FIRST_FRAG;
+					buffer->element[element].eflags =
+						SBAL_EFLAGS_FIRST_FRAG;
 				else
-					buffer->element[element].flags = 0;
+					buffer->element[element].eflags = 0;
 			else
-				buffer->element[element].flags =
-				    SBAL_FLAGS_MIDDLE_FRAG;
+				buffer->element[element].eflags =
+				    SBAL_EFLAGS_MIDDLE_FRAG;
 		} else {
 			if (first_lap)
-				buffer->element[element].flags =
-				    SBAL_FLAGS_FIRST_FRAG;
+				buffer->element[element].eflags =
+				    SBAL_EFLAGS_FIRST_FRAG;
 			else
-				buffer->element[element].flags =
-				    SBAL_FLAGS_MIDDLE_FRAG;
+				buffer->element[element].eflags =
+				    SBAL_EFLAGS_MIDDLE_FRAG;
 		}
 		data += length_here;
 		element++;
@@ -3205,12 +3208,12 @@ static inline void __qeth_fill_buffer(struct sk_buff *skb,
 		buffer->element[element].addr = (char *)page_to_phys(frag->page)
 			+ frag->page_offset;
 		buffer->element[element].length = frag->size;
-		buffer->element[element].flags = SBAL_FLAGS_MIDDLE_FRAG;
+		buffer->element[element].eflags = SBAL_EFLAGS_MIDDLE_FRAG;
 		element++;
 	}
 
-	if (buffer->element[element - 1].flags)
-		buffer->element[element - 1].flags = SBAL_FLAGS_LAST_FRAG;
+	if (buffer->element[element - 1].eflags)
+		buffer->element[element - 1].eflags = SBAL_EFLAGS_LAST_FRAG;
 	*next_element_to_fill = element;
 }
 
@@ -3234,7 +3237,7 @@ static inline int qeth_fill_buffer(struct qeth_qdio_out_q *queue,
 		/*fill first buffer entry only with header information */
 		buffer->element[element].addr = skb->data;
 		buffer->element[element].length = hdr_len;
-		buffer->element[element].flags = SBAL_FLAGS_FIRST_FRAG;
+		buffer->element[element].eflags = SBAL_EFLAGS_FIRST_FRAG;
 		buf->next_element_to_fill++;
 		skb->data += hdr_len;
 		skb->len  -= hdr_len;
@@ -3246,7 +3249,7 @@ static inline int qeth_fill_buffer(struct qeth_qdio_out_q *queue,
 		buffer->element[element].addr = hdr;
 		buffer->element[element].length = sizeof(struct qeth_hdr) +
 							hd_len;
-		buffer->element[element].flags = SBAL_FLAGS_FIRST_FRAG;
+		buffer->element[element].eflags = SBAL_EFLAGS_FIRST_FRAG;
 		buf->is_header[element] = 1;
 		buf->next_element_to_fill++;
 	}
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index 8512b5c0ef82..022fb6a8cb83 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -640,7 +640,7 @@ static struct fsf_qtcb *zfcp_qtcb_alloc(mempool_t *pool)
 }
 
 static struct zfcp_fsf_req *zfcp_fsf_req_create(struct zfcp_qdio *qdio,
-						u32 fsf_cmd, u32 sbtype,
+						u32 fsf_cmd, u8 sbtype,
 						mempool_t *pool)
 {
 	struct zfcp_adapter *adapter = qdio->adapter;
@@ -841,7 +841,7 @@ struct zfcp_fsf_req *zfcp_fsf_abort_fcp_cmnd(struct scsi_cmnd *scmnd)
 	if (zfcp_qdio_sbal_get(qdio))
 		goto out;
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_ABORT_FCP_CMND,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.scsi_abort);
 	if (IS_ERR(req)) {
 		req = NULL;
@@ -1012,7 +1012,7 @@ int zfcp_fsf_send_ct(struct zfcp_fc_wka_port *wka_port,
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_SEND_GENERIC,
-				  SBAL_FLAGS0_TYPE_WRITE_READ, pool);
+				  SBAL_SFLAGS0_TYPE_WRITE_READ, pool);
 
 	if (IS_ERR(req)) {
 		ret = PTR_ERR(req);
@@ -1110,7 +1110,7 @@ int zfcp_fsf_send_els(struct zfcp_adapter *adapter, u32 d_id,
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_SEND_ELS,
-				  SBAL_FLAGS0_TYPE_WRITE_READ, NULL);
+				  SBAL_SFLAGS0_TYPE_WRITE_READ, NULL);
 
 	if (IS_ERR(req)) {
 		ret = PTR_ERR(req);
@@ -1156,7 +1156,7 @@ int zfcp_fsf_exchange_config_data(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_EXCHANGE_CONFIG_DATA,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1198,7 +1198,7 @@ int zfcp_fsf_exchange_config_data_sync(struct zfcp_qdio *qdio,
 		goto out_unlock;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_EXCHANGE_CONFIG_DATA,
-				  SBAL_FLAGS0_TYPE_READ, NULL);
+				  SBAL_SFLAGS0_TYPE_READ, NULL);
 
 	if (IS_ERR(req)) {
 		retval = PTR_ERR(req);
@@ -1250,7 +1250,7 @@ int zfcp_fsf_exchange_port_data(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_EXCHANGE_PORT_DATA,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1296,7 +1296,7 @@ int zfcp_fsf_exchange_port_data_sync(struct zfcp_qdio *qdio,
 		goto out_unlock;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_EXCHANGE_PORT_DATA,
-				  SBAL_FLAGS0_TYPE_READ, NULL);
+				  SBAL_SFLAGS0_TYPE_READ, NULL);
 
 	if (IS_ERR(req)) {
 		retval = PTR_ERR(req);
@@ -1412,7 +1412,7 @@ int zfcp_fsf_open_port(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_OPEN_PORT_WITH_DID,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1478,7 +1478,7 @@ int zfcp_fsf_close_port(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_CLOSE_PORT,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1553,7 +1553,7 @@ int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_OPEN_PORT_WITH_DID,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1606,7 +1606,7 @@ int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_CLOSE_PORT,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1698,7 +1698,7 @@ int zfcp_fsf_close_physical_port(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_CLOSE_PHYSICAL_PORT,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1812,7 +1812,7 @@ int zfcp_fsf_open_lun(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_OPEN_LUN,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1901,7 +1901,7 @@ int zfcp_fsf_close_lun(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_CLOSE_LUN,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -2161,7 +2161,7 @@ int zfcp_fsf_fcp_cmnd(struct scsi_cmnd *scsi_cmnd)
 {
 	struct zfcp_fsf_req *req;
 	struct fcp_cmnd *fcp_cmnd;
-	unsigned int sbtype = SBAL_FLAGS0_TYPE_READ;
+	u8 sbtype = SBAL_SFLAGS0_TYPE_READ;
 	int real_bytes, retval = -EIO, dix_bytes = 0;
 	struct scsi_device *sdev = scsi_cmnd->device;
 	struct zfcp_scsi_dev *zfcp_sdev = sdev_to_zfcp(sdev);
@@ -2181,7 +2181,7 @@ int zfcp_fsf_fcp_cmnd(struct scsi_cmnd *scsi_cmnd)
 	}
 
 	if (scsi_cmnd->sc_data_direction == DMA_TO_DEVICE)
-		sbtype = SBAL_FLAGS0_TYPE_WRITE;
+		sbtype = SBAL_SFLAGS0_TYPE_WRITE;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_FCP_CMND,
 				  sbtype, adapter->pool.scsi_req);
@@ -2280,7 +2280,7 @@ struct zfcp_fsf_req *zfcp_fsf_fcp_task_mgmt(struct scsi_cmnd *scmnd,
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_FCP_CMND,
-				  SBAL_FLAGS0_TYPE_WRITE,
+				  SBAL_SFLAGS0_TYPE_WRITE,
 				  qdio->adapter->pool.scsi_req);
 
 	if (IS_ERR(req)) {
@@ -2328,17 +2328,18 @@ struct zfcp_fsf_req *zfcp_fsf_control_file(struct zfcp_adapter *adapter,
 	struct zfcp_qdio *qdio = adapter->qdio;
 	struct zfcp_fsf_req *req = NULL;
 	struct fsf_qtcb_bottom_support *bottom;
-	int direction, retval = -EIO, bytes;
+	int retval = -EIO, bytes;
+	u8 direction;
 
 	if (!(adapter->adapter_features & FSF_FEATURE_CFDC))
 		return ERR_PTR(-EOPNOTSUPP);
 
 	switch (fsf_cfdc->command) {
 	case FSF_QTCB_DOWNLOAD_CONTROL_FILE:
-		direction = SBAL_FLAGS0_TYPE_WRITE;
+		direction = SBAL_SFLAGS0_TYPE_WRITE;
 		break;
 	case FSF_QTCB_UPLOAD_CONTROL_FILE:
-		direction = SBAL_FLAGS0_TYPE_READ;
+		direction = SBAL_SFLAGS0_TYPE_READ;
 		break;
 	default:
 		return ERR_PTR(-EINVAL);
@@ -2413,7 +2414,7 @@ void zfcp_fsf_reqid_check(struct zfcp_qdio *qdio, int sbal_idx)
 		fsf_req->qdio_req.sbal_response = sbal_idx;
 		zfcp_fsf_req_complete(fsf_req);
 
-		if (likely(sbale->flags & SBAL_FLAGS_LAST_ENTRY))
+		if (likely(sbale->eflags & SBAL_EFLAGS_LAST_ENTRY))
 			break;
 	}
 }
diff --git a/drivers/s390/scsi/zfcp_qdio.c b/drivers/s390/scsi/zfcp_qdio.c
index 98e97d90835b..d9c40ea73eef 100644
--- a/drivers/s390/scsi/zfcp_qdio.c
+++ b/drivers/s390/scsi/zfcp_qdio.c
@@ -124,7 +124,7 @@ zfcp_qdio_sbal_chain(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req)
 
 	/* set last entry flag in current SBALE of current SBAL */
 	sbale = zfcp_qdio_sbale_curr(qdio, q_req);
-	sbale->flags |= SBAL_FLAGS_LAST_ENTRY;
+	sbale->eflags |= SBAL_EFLAGS_LAST_ENTRY;
 
 	/* don't exceed last allowed SBAL */
 	if (q_req->sbal_last == q_req->sbal_limit)
@@ -132,7 +132,7 @@ zfcp_qdio_sbal_chain(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req)
 
 	/* set chaining flag in first SBALE of current SBAL */
 	sbale = zfcp_qdio_sbale_req(qdio, q_req);
-	sbale->flags |= SBAL_FLAGS0_MORE_SBALS;
+	sbale->sflags |= SBAL_SFLAGS0_MORE_SBALS;
 
 	/* calculate index of next SBAL */
 	q_req->sbal_last++;
@@ -147,7 +147,7 @@ zfcp_qdio_sbal_chain(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req)
 
 	/* set storage-block type for new SBAL */
 	sbale = zfcp_qdio_sbale_curr(qdio, q_req);
-	sbale->flags |= q_req->sbtype;
+	sbale->sflags |= q_req->sbtype;
 
 	return sbale;
 }
@@ -177,7 +177,7 @@ int zfcp_qdio_sbals_from_sg(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req,
 
 	/* set storage-block type for this request */
 	sbale = zfcp_qdio_sbale_req(qdio, q_req);
-	sbale->flags |= q_req->sbtype;
+	sbale->sflags |= q_req->sbtype;
 
 	for (; sg; sg = sg_next(sg)) {
 		sbale = zfcp_qdio_sbale_next(qdio, q_req);
@@ -384,7 +384,8 @@ int zfcp_qdio_open(struct zfcp_qdio *qdio)
 	for (cc = 0; cc < QDIO_MAX_BUFFERS_PER_Q; cc++) {
 		sbale = &(qdio->res_q[cc]->element[0]);
 		sbale->length = 0;
-		sbale->flags = SBAL_FLAGS_LAST_ENTRY;
+		sbale->eflags = SBAL_EFLAGS_LAST_ENTRY;
+		sbale->sflags = 0;
 		sbale->addr = NULL;
 	}
 
diff --git a/drivers/s390/scsi/zfcp_qdio.h b/drivers/s390/scsi/zfcp_qdio.h
index 2297d8d3e947..54e22ace012b 100644
--- a/drivers/s390/scsi/zfcp_qdio.h
+++ b/drivers/s390/scsi/zfcp_qdio.h
@@ -67,7 +67,7 @@ struct zfcp_qdio {
  * @qdio_outb_usage: usage of outbound queue
  */
 struct zfcp_qdio_req {
-	u32	sbtype;
+	u8	sbtype;
 	u8	sbal_number;
 	u8	sbal_first;
 	u8	sbal_last;
@@ -116,7 +116,7 @@ zfcp_qdio_sbale_curr(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req)
  */
 static inline
 void zfcp_qdio_req_init(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req,
-			unsigned long req_id, u32 sbtype, void *data, u32 len)
+			unsigned long req_id, u8 sbtype, void *data, u32 len)
 {
 	struct qdio_buffer_element *sbale;
 	int count = min(atomic_read(&qdio->req_q_free),
@@ -131,7 +131,8 @@ void zfcp_qdio_req_init(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req,
 
 	sbale = zfcp_qdio_sbale_req(qdio, q_req);
 	sbale->addr = (void *) req_id;
-	sbale->flags = SBAL_FLAGS0_COMMAND | sbtype;
+	sbale->eflags = 0;
+	sbale->sflags = SBAL_SFLAGS0_COMMAND | sbtype;
 
 	if (unlikely(!data))
 		return;
@@ -173,7 +174,7 @@ void zfcp_qdio_set_sbale_last(struct zfcp_qdio *qdio,
 	struct qdio_buffer_element *sbale;
 
 	sbale = zfcp_qdio_sbale_curr(qdio, q_req);
-	sbale->flags |= SBAL_FLAGS_LAST_ENTRY;
+	sbale->eflags |= SBAL_EFLAGS_LAST_ENTRY;
 }
 
 /**
diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c
index 3b7e83d2dab4..d5ff142c93a2 100644
--- a/drivers/scsi/aic94xx/aic94xx_init.c
+++ b/drivers/scsi/aic94xx/aic94xx_init.c
@@ -486,7 +486,7 @@ static ssize_t asd_show_update_bios(struct device *dev,
 			flash_error_table[i].reason);
 }
 
-static DEVICE_ATTR(update_bios, S_IRUGO|S_IWUGO,
+static DEVICE_ATTR(update_bios, S_IRUGO|S_IWUSR,
 	asd_show_update_bios, asd_store_update_bios);
 
 static int asd_create_dev_attrs(struct asd_ha_struct *asd_ha)
diff --git a/drivers/scsi/bfa/bfa_ioc.c b/drivers/scsi/bfa/bfa_ioc.c
index c1f72c49196f..6c7e0339dda4 100644
--- a/drivers/scsi/bfa/bfa_ioc.c
+++ b/drivers/scsi/bfa/bfa_ioc.c
@@ -56,6 +56,8 @@ BFA_TRC_FILE(CNA, IOC);
 #define bfa_ioc_map_port(__ioc) ((__ioc)->ioc_hwif->ioc_map_port(__ioc))
 #define bfa_ioc_notify_fail(__ioc)              \
 			((__ioc)->ioc_hwif->ioc_notify_fail(__ioc))
+#define bfa_ioc_sync_start(__ioc)               \
+			((__ioc)->ioc_hwif->ioc_sync_start(__ioc))
 #define bfa_ioc_sync_join(__ioc)                \
 			((__ioc)->ioc_hwif->ioc_sync_join(__ioc))
 #define bfa_ioc_sync_leave(__ioc)               \
@@ -647,7 +649,7 @@ bfa_iocpf_sm_fwcheck(struct bfa_iocpf_s *iocpf, enum iocpf_event event)
 	switch (event) {
 	case IOCPF_E_SEMLOCKED:
 		if (bfa_ioc_firmware_lock(ioc)) {
-			if (bfa_ioc_sync_complete(ioc)) {
+			if (bfa_ioc_sync_start(ioc)) {
 				iocpf->retry_count = 0;
 				bfa_ioc_sync_join(ioc);
 				bfa_fsm_set_state(iocpf, bfa_iocpf_sm_hwinit);
diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h
index ec9cf08b0e7f..c85182a704fb 100644
--- a/drivers/scsi/bfa/bfa_ioc.h
+++ b/drivers/scsi/bfa/bfa_ioc.h
@@ -263,6 +263,7 @@ struct bfa_ioc_hwif_s {
 					bfa_boolean_t msix);
 	void		(*ioc_notify_fail)	(struct bfa_ioc_s *ioc);
 	void		(*ioc_ownership_reset)	(struct bfa_ioc_s *ioc);
+	bfa_boolean_t   (*ioc_sync_start)       (struct bfa_ioc_s *ioc);
 	void		(*ioc_sync_join)	(struct bfa_ioc_s *ioc);
 	void		(*ioc_sync_leave)	(struct bfa_ioc_s *ioc);
 	void		(*ioc_sync_ack)		(struct bfa_ioc_s *ioc);
diff --git a/drivers/scsi/bfa/bfa_ioc_cb.c b/drivers/scsi/bfa/bfa_ioc_cb.c
index e4a0713185b6..89ae4c8f95a2 100644
--- a/drivers/scsi/bfa/bfa_ioc_cb.c
+++ b/drivers/scsi/bfa/bfa_ioc_cb.c
@@ -32,6 +32,7 @@ static void bfa_ioc_cb_map_port(struct bfa_ioc_s *ioc);
 static void bfa_ioc_cb_isr_mode_set(struct bfa_ioc_s *ioc, bfa_boolean_t msix);
 static void bfa_ioc_cb_notify_fail(struct bfa_ioc_s *ioc);
 static void bfa_ioc_cb_ownership_reset(struct bfa_ioc_s *ioc);
+static bfa_boolean_t bfa_ioc_cb_sync_start(struct bfa_ioc_s *ioc);
 static void bfa_ioc_cb_sync_join(struct bfa_ioc_s *ioc);
 static void bfa_ioc_cb_sync_leave(struct bfa_ioc_s *ioc);
 static void bfa_ioc_cb_sync_ack(struct bfa_ioc_s *ioc);
@@ -53,6 +54,7 @@ bfa_ioc_set_cb_hwif(struct bfa_ioc_s *ioc)
 	hwif_cb.ioc_isr_mode_set = bfa_ioc_cb_isr_mode_set;
 	hwif_cb.ioc_notify_fail = bfa_ioc_cb_notify_fail;
 	hwif_cb.ioc_ownership_reset = bfa_ioc_cb_ownership_reset;
+	hwif_cb.ioc_sync_start = bfa_ioc_cb_sync_start;
 	hwif_cb.ioc_sync_join = bfa_ioc_cb_sync_join;
 	hwif_cb.ioc_sync_leave = bfa_ioc_cb_sync_leave;
 	hwif_cb.ioc_sync_ack = bfa_ioc_cb_sync_ack;
@@ -195,6 +197,15 @@ bfa_ioc_cb_isr_mode_set(struct bfa_ioc_s *ioc, bfa_boolean_t msix)
 }
 
 /*
+ * Synchronized IOC failure processing routines
+ */
+static bfa_boolean_t
+bfa_ioc_cb_sync_start(struct bfa_ioc_s *ioc)
+{
+	return bfa_ioc_cb_sync_complete(ioc);
+}
+
+/*
  * Cleanup hw semaphore and usecnt registers
  */
 static void
diff --git a/drivers/scsi/bfa/bfa_ioc_ct.c b/drivers/scsi/bfa/bfa_ioc_ct.c
index 008d129ddfcd..93612520f0d2 100644
--- a/drivers/scsi/bfa/bfa_ioc_ct.c
+++ b/drivers/scsi/bfa/bfa_ioc_ct.c
@@ -41,6 +41,7 @@ static void bfa_ioc_ct_map_port(struct bfa_ioc_s *ioc);
 static void bfa_ioc_ct_isr_mode_set(struct bfa_ioc_s *ioc, bfa_boolean_t msix);
 static void bfa_ioc_ct_notify_fail(struct bfa_ioc_s *ioc);
 static void bfa_ioc_ct_ownership_reset(struct bfa_ioc_s *ioc);
+static bfa_boolean_t bfa_ioc_ct_sync_start(struct bfa_ioc_s *ioc);
 static void bfa_ioc_ct_sync_join(struct bfa_ioc_s *ioc);
 static void bfa_ioc_ct_sync_leave(struct bfa_ioc_s *ioc);
 static void bfa_ioc_ct_sync_ack(struct bfa_ioc_s *ioc);
@@ -62,6 +63,7 @@ bfa_ioc_set_ct_hwif(struct bfa_ioc_s *ioc)
 	hwif_ct.ioc_isr_mode_set = bfa_ioc_ct_isr_mode_set;
 	hwif_ct.ioc_notify_fail = bfa_ioc_ct_notify_fail;
 	hwif_ct.ioc_ownership_reset = bfa_ioc_ct_ownership_reset;
+	hwif_ct.ioc_sync_start = bfa_ioc_ct_sync_start;
 	hwif_ct.ioc_sync_join = bfa_ioc_ct_sync_join;
 	hwif_ct.ioc_sync_leave = bfa_ioc_ct_sync_leave;
 	hwif_ct.ioc_sync_ack = bfa_ioc_ct_sync_ack;
@@ -351,6 +353,30 @@ bfa_ioc_ct_ownership_reset(struct bfa_ioc_s *ioc)
 	writel(1, ioc->ioc_regs.ioc_sem_reg);
 }
 
+static bfa_boolean_t
+bfa_ioc_ct_sync_start(struct bfa_ioc_s *ioc)
+{
+	uint32_t r32 = readl(ioc->ioc_regs.ioc_fail_sync);
+	uint32_t sync_reqd = bfa_ioc_ct_get_sync_reqd(r32);
+
+	/*
+	 * Driver load time.  If the sync required bit for this PCI fn
+	 * is set, it is due to an unclean exit by the driver for this
+	 * PCI fn in the previous incarnation. Whoever comes here first
+	 * should clean it up, no matter which PCI fn.
+	 */
+
+	if (sync_reqd & bfa_ioc_ct_sync_pos(ioc)) {
+		writel(0, ioc->ioc_regs.ioc_fail_sync);
+		writel(1, ioc->ioc_regs.ioc_usage_reg);
+		writel(BFI_IOC_UNINIT, ioc->ioc_regs.ioc_fwstate);
+		writel(BFI_IOC_UNINIT, ioc->ioc_regs.alt_ioc_fwstate);
+		return BFA_TRUE;
+	}
+
+	return bfa_ioc_ct_sync_complete(ioc);
+}
+
 /*
  * Synchronized IOC failure processing routines
  */
diff --git a/drivers/scsi/bnx2i/bnx2i.h b/drivers/scsi/bnx2i/bnx2i.h
index cfd59023227b..6bdd25a93db9 100644
--- a/drivers/scsi/bnx2i/bnx2i.h
+++ b/drivers/scsi/bnx2i/bnx2i.h
@@ -66,11 +66,11 @@
 #define BD_SPLIT_SIZE			32768
 
 /* min, max & default values for SQ/RQ/CQ size, configurable via' modparam */
-#define BNX2I_SQ_WQES_MIN 		16
-#define BNX2I_570X_SQ_WQES_MAX 		128
-#define BNX2I_5770X_SQ_WQES_MAX 	512
-#define BNX2I_570X_SQ_WQES_DEFAULT 	128
-#define BNX2I_5770X_SQ_WQES_DEFAULT 	256
+#define BNX2I_SQ_WQES_MIN		16
+#define BNX2I_570X_SQ_WQES_MAX		128
+#define BNX2I_5770X_SQ_WQES_MAX		512
+#define BNX2I_570X_SQ_WQES_DEFAULT	128
+#define BNX2I_5770X_SQ_WQES_DEFAULT	128
 
 #define BNX2I_570X_CQ_WQES_MAX 		128
 #define BNX2I_5770X_CQ_WQES_MAX 	512
@@ -115,6 +115,7 @@
 #define BNX2X_MAX_CQS			8
 
 #define CNIC_ARM_CQE			1
+#define CNIC_ARM_CQE_FP			2
 #define CNIC_DISARM_CQE			0
 
 #define REG_RD(__hba, offset)				\
@@ -666,7 +667,9 @@ enum {
  *                      after HBA reset is completed by bnx2i/cnic/bnx2
  *                      modules
  * @state:              tracks offload connection state machine
- * @teardown_mode:      indicates if conn teardown is abortive or orderly
+ * @timestamp:          tracks the start time when the ep begins to connect
+ * @num_active_cmds:    tracks the number of outstanding commands for this ep
+ * @ec_shift:           the amount of shift as part of the event coal calc
  * @qp:                 QP information
  * @ids:                contains chip allocated *context id* & driver assigned
  *                      *iscsi cid*
@@ -685,6 +688,7 @@ struct bnx2i_endpoint {
 	u32 state;
 	unsigned long timestamp;
 	int num_active_cmds;
+	u32 ec_shift;
 
 	struct qp_info qp;
 	struct ep_handles ids;
diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c
index f0b89513faed..5c54a2d9b834 100644
--- a/drivers/scsi/bnx2i/bnx2i_hwi.c
+++ b/drivers/scsi/bnx2i/bnx2i_hwi.c
@@ -138,7 +138,6 @@ void bnx2i_arm_cq_event_coalescing(struct bnx2i_endpoint *ep, u8 action)
 	u16 next_index;
 	u32 num_active_cmds;
 
-
 	/* Coalesce CQ entries only on 10G devices */
 	if (!test_bit(BNX2I_NX2_DEV_57710, &ep->hba->cnic_dev_type))
 		return;
@@ -148,16 +147,19 @@ void bnx2i_arm_cq_event_coalescing(struct bnx2i_endpoint *ep, u8 action)
 	 * interrupts and other unwanted results
 	 */
 	cq_db = (struct bnx2i_5771x_cq_db *) ep->qp.cq_pgtbl_virt;
-	if (cq_db->sqn[0] && cq_db->sqn[0] != 0xFFFF)
-		return;
 
-	if (action == CNIC_ARM_CQE) {
+	if (action != CNIC_ARM_CQE_FP)
+		if (cq_db->sqn[0] && cq_db->sqn[0] != 0xFFFF)
+			return;
+
+	if (action == CNIC_ARM_CQE || action == CNIC_ARM_CQE_FP) {
 		num_active_cmds = ep->num_active_cmds;
 		if (num_active_cmds <= event_coal_min)
 			next_index = 1;
 		else
 			next_index = event_coal_min +
-				(num_active_cmds - event_coal_min) / event_coal_div;
+				     ((num_active_cmds - event_coal_min) >>
+				     ep->ec_shift);
 		if (!next_index)
 			next_index = 1;
 		cq_index = ep->qp.cqe_exp_seq_sn + next_index - 1;
@@ -1274,6 +1276,7 @@ int bnx2i_send_fw_iscsi_init_msg(struct bnx2i_hba *hba)
 	iscsi_init.dummy_buffer_addr_hi =
 		(u32) ((u64) hba->dummy_buf_dma >> 32);
 
+	hba->num_ccell = hba->max_sqes >> 1;
 	hba->ctx_ccell_tasks =
 			((hba->num_ccell & 0xFFFF) | (hba->max_sqes << 16));
 	iscsi_init.num_ccells_per_conn = hba->num_ccell;
@@ -1934,7 +1937,6 @@ cqe_out:
 			qp->cq_cons_idx++;
 		}
 	}
-	bnx2i_arm_cq_event_coalescing(bnx2i_conn->ep, CNIC_ARM_CQE);
 }
 
 /**
@@ -1948,22 +1950,23 @@ cqe_out:
 static void bnx2i_fastpath_notification(struct bnx2i_hba *hba,
 					struct iscsi_kcqe *new_cqe_kcqe)
 {
-	struct bnx2i_conn *conn;
+	struct bnx2i_conn *bnx2i_conn;
 	u32 iscsi_cid;
 
 	iscsi_cid = new_cqe_kcqe->iscsi_conn_id;
-	conn = bnx2i_get_conn_from_id(hba, iscsi_cid);
+	bnx2i_conn = bnx2i_get_conn_from_id(hba, iscsi_cid);
 
-	if (!conn) {
+	if (!bnx2i_conn) {
 		printk(KERN_ALERT "cid #%x not valid\n", iscsi_cid);
 		return;
 	}
-	if (!conn->ep) {
+	if (!bnx2i_conn->ep) {
 		printk(KERN_ALERT "cid #%x - ep not bound\n", iscsi_cid);
 		return;
 	}
-
-	bnx2i_process_new_cqes(conn);
+	bnx2i_process_new_cqes(bnx2i_conn);
+	bnx2i_arm_cq_event_coalescing(bnx2i_conn->ep, CNIC_ARM_CQE_FP);
+	bnx2i_process_new_cqes(bnx2i_conn);
 }
 
 
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index 1d24a2819736..6adbdc34a9a5 100644
--- a/drivers/scsi/bnx2i/bnx2i_init.c
+++ b/drivers/scsi/bnx2i/bnx2i_init.c
@@ -244,7 +244,7 @@ void bnx2i_stop(void *handle)
 	wait_event_interruptible_timeout(hba->eh_wait,
 					 (list_empty(&hba->ep_ofld_list) &&
 					 list_empty(&hba->ep_destroy_list)),
-					 10 * HZ);
+					 2 * HZ);
 	/* Wait for all endpoints to be torn down, Chip will be reset once
 	 *  control returns to network driver. So it is required to cleanup and
 	 * release all connection resources before returning from this routine.
diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c
index 1809f9ccc4ce..041928b23cb0 100644
--- a/drivers/scsi/bnx2i/bnx2i_iscsi.c
+++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c
@@ -379,6 +379,7 @@ static struct iscsi_endpoint *bnx2i_alloc_ep(struct bnx2i_hba *hba)
 {
 	struct iscsi_endpoint *ep;
 	struct bnx2i_endpoint *bnx2i_ep;
+	u32 ec_div;
 
 	ep = iscsi_create_endpoint(sizeof(*bnx2i_ep));
 	if (!ep) {
@@ -393,6 +394,11 @@ static struct iscsi_endpoint *bnx2i_alloc_ep(struct bnx2i_hba *hba)
 	bnx2i_ep->ep_iscsi_cid = (u16) -1;
 	bnx2i_ep->hba = hba;
 	bnx2i_ep->hba_age = hba->age;
+
+	ec_div = event_coal_div;
+	while (ec_div >>= 1)
+		bnx2i_ep->ec_shift += 1;
+
 	hba->ofld_conns_active++;
 	init_waitqueue_head(&bnx2i_ep->ofld_wait);
 	return ep;
@@ -858,7 +864,7 @@ struct bnx2i_hba *bnx2i_alloc_hba(struct cnic_dev *cnic)
 	mutex_init(&hba->net_dev_lock);
 	init_waitqueue_head(&hba->eh_wait);
 	if (test_bit(BNX2I_NX2_DEV_57710, &hba->cnic_dev_type)) {
-		hba->hba_shutdown_tmo = 20 * HZ;
+		hba->hba_shutdown_tmo = 30 * HZ;
 		hba->conn_teardown_tmo = 20 * HZ;
 		hba->conn_ctx_destroy_tmo = 6 * HZ;
 	} else {	/* 5706/5708/5709 */
@@ -1208,6 +1214,9 @@ static int bnx2i_task_xmit(struct iscsi_task *task)
 	struct bnx2i_cmd *cmd = task->dd_data;
 	struct iscsi_cmd *hdr = (struct iscsi_cmd *) task->hdr;
 
+	if (bnx2i_conn->ep->num_active_cmds + 1 > hba->max_sqes)
+		return -ENOMEM;
+
 	/*
 	 * If there is no scsi_cmnd this must be a mgmt task
 	 */
@@ -2156,7 +2165,7 @@ static struct scsi_host_template bnx2i_host_template = {
 	.change_queue_depth	= iscsi_change_queue_depth,
 	.can_queue		= 1024,
 	.max_sectors		= 127,
-	.cmd_per_lun		= 32,
+	.cmd_per_lun		= 24,
 	.this_id		= -1,
 	.use_clustering		= ENABLE_CLUSTERING,
 	.sg_tablesize		= ISCSI_MAX_BDS_PER_CMD,
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index cc23bd9480b2..155d7b9bdeae 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -137,6 +137,7 @@ static int fcoe_vport_create(struct fc_vport *, bool disabled);
 static int fcoe_vport_disable(struct fc_vport *, bool disable);
 static void fcoe_set_vport_symbolic_name(struct fc_vport *);
 static void fcoe_set_port_id(struct fc_lport *, u32, struct fc_frame *);
+static int fcoe_validate_vport_create(struct fc_vport *);
 
 static struct libfc_function_template fcoe_libfc_fcn_templ = {
 	.frame_send = fcoe_xmit,
@@ -2351,6 +2352,17 @@ static int fcoe_vport_create(struct fc_vport *vport, bool disabled)
 	struct fcoe_interface *fcoe = port->priv;
 	struct net_device *netdev = fcoe->netdev;
 	struct fc_lport *vn_port;
+	int rc;
+	char buf[32];
+
+	rc = fcoe_validate_vport_create(vport);
+	if (rc) {
+		wwn_to_str(vport->port_name, buf, sizeof(buf));
+		printk(KERN_ERR "fcoe: Failed to create vport, "
+			"WWPN (0x%s) already exists\n",
+			buf);
+		return rc;
+	}
 
 	mutex_lock(&fcoe_config_mutex);
 	vn_port = fcoe_if_create(fcoe, &vport->dev, 1);
@@ -2497,3 +2509,49 @@ static void fcoe_set_port_id(struct fc_lport *lport,
 	if (fp && fc_frame_payload_op(fp) == ELS_FLOGI)
 		fcoe_ctlr_recv_flogi(&fcoe->ctlr, lport, fp);
 }
+
+/**
+ * fcoe_validate_vport_create() - Validate a vport before creating it
+ * @vport: NPIV port to be created
+ *
+ * This routine is meant to add validation for a vport before creating it
+ * via fcoe_vport_create().
+ * Current validations are:
+ *      - WWPN supplied is unique for given lport
+ *
+ *
+*/
+static int fcoe_validate_vport_create(struct fc_vport *vport)
+{
+	struct Scsi_Host *shost = vport_to_shost(vport);
+	struct fc_lport *n_port = shost_priv(shost);
+	struct fc_lport *vn_port;
+	int rc = 0;
+	char buf[32];
+
+	mutex_lock(&n_port->lp_mutex);
+
+	wwn_to_str(vport->port_name, buf, sizeof(buf));
+	/* Check if the wwpn is not same as that of the lport */
+	if (!memcmp(&n_port->wwpn, &vport->port_name, sizeof(u64))) {
+		FCOE_DBG("vport WWPN 0x%s is same as that of the "
+			"base port WWPN\n", buf);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	/* Check if there is any existing vport with same wwpn */
+	list_for_each_entry(vn_port, &n_port->vports, list) {
+		if (!memcmp(&vn_port->wwpn, &vport->port_name, sizeof(u64))) {
+			FCOE_DBG("vport with given WWPN 0x%s already "
+			"exists\n", buf);
+			rc = -EINVAL;
+			break;
+		}
+	}
+
+out:
+	mutex_unlock(&n_port->lp_mutex);
+
+	return rc;
+}
diff --git a/drivers/scsi/fcoe/fcoe.h b/drivers/scsi/fcoe/fcoe.h
index 408a6fd78fb4..c4a93993c0cf 100644
--- a/drivers/scsi/fcoe/fcoe.h
+++ b/drivers/scsi/fcoe/fcoe.h
@@ -99,4 +99,14 @@ static inline struct net_device *fcoe_netdev(const struct fc_lport *lport)
 			((struct fcoe_port *)lport_priv(lport))->priv)->netdev;
 }
 
+static inline void wwn_to_str(u64 wwn, char *buf, int len)
+{
+	u8 wwpn[8];
+
+	u64_to_wwn(wwn, wwpn);
+	snprintf(buf, len, "%02x%02x%02x%02x%02x%02x%02x%02x",
+		wwpn[0], wwpn[1], wwpn[2], wwpn[3],
+		wwpn[4], wwpn[5], wwpn[6], wwpn[7]);
+}
+
 #endif /* _FCOE_H_ */
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index 229e4af5508a..c74c4b8e71ef 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -1173,7 +1173,9 @@ static void fcoe_ctlr_recv_clr_vlink(struct fcoe_ctlr *fip,
 	struct fc_lport *lport = fip->lp;
 	struct fc_lport *vn_port = NULL;
 	u32 desc_mask;
-	int is_vn_port = 0;
+	int num_vlink_desc;
+	int reset_phys_port = 0;
+	struct fip_vn_desc **vlink_desc_arr = NULL;
 
 	LIBFCOE_FIP_DBG(fip, "Clear Virtual Link received\n");
 
@@ -1183,70 +1185,73 @@ static void fcoe_ctlr_recv_clr_vlink(struct fcoe_ctlr *fip,
 	/*
 	 * mask of required descriptors.  Validating each one clears its bit.
 	 */
-	desc_mask = BIT(FIP_DT_MAC) | BIT(FIP_DT_NAME) | BIT(FIP_DT_VN_ID);
+	desc_mask = BIT(FIP_DT_MAC) | BIT(FIP_DT_NAME);
 
 	rlen = ntohs(fh->fip_dl_len) * FIP_BPW;
 	desc = (struct fip_desc *)(fh + 1);
+
+	/*
+	 * Actually need to subtract 'sizeof(*mp) - sizeof(*wp)' from 'rlen'
+	 * before determining max Vx_Port descriptor but a buggy FCF could have
+	 * omited either or both MAC Address and Name Identifier descriptors
+	 */
+	num_vlink_desc = rlen / sizeof(*vp);
+	if (num_vlink_desc)
+		vlink_desc_arr = kmalloc(sizeof(vp) * num_vlink_desc,
+					 GFP_ATOMIC);
+	if (!vlink_desc_arr)
+		return;
+	num_vlink_desc = 0;
+
 	while (rlen >= sizeof(*desc)) {
 		dlen = desc->fip_dlen * FIP_BPW;
 		if (dlen > rlen)
-			return;
+			goto err;
 		/* Drop CVL if there are duplicate critical descriptors */
 		if ((desc->fip_dtype < 32) &&
+		    (desc->fip_dtype != FIP_DT_VN_ID) &&
 		    !(desc_mask & 1U << desc->fip_dtype)) {
 			LIBFCOE_FIP_DBG(fip, "Duplicate Critical "
 					"Descriptors in FIP CVL\n");
-			return;
+			goto err;
 		}
 		switch (desc->fip_dtype) {
 		case FIP_DT_MAC:
 			mp = (struct fip_mac_desc *)desc;
 			if (dlen < sizeof(*mp))
-				return;
+				goto err;
 			if (compare_ether_addr(mp->fd_mac, fcf->fcf_mac))
-				return;
+				goto err;
 			desc_mask &= ~BIT(FIP_DT_MAC);
 			break;
 		case FIP_DT_NAME:
 			wp = (struct fip_wwn_desc *)desc;
 			if (dlen < sizeof(*wp))
-				return;
+				goto err;
 			if (get_unaligned_be64(&wp->fd_wwn) != fcf->switch_name)
-				return;
+				goto err;
 			desc_mask &= ~BIT(FIP_DT_NAME);
 			break;
 		case FIP_DT_VN_ID:
 			vp = (struct fip_vn_desc *)desc;
 			if (dlen < sizeof(*vp))
-				return;
-			if (compare_ether_addr(vp->fd_mac,
-					       fip->get_src_addr(lport)) == 0 &&
-			    get_unaligned_be64(&vp->fd_wwpn) == lport->wwpn &&
-			    ntoh24(vp->fd_fc_id) == lport->port_id) {
-				desc_mask &= ~BIT(FIP_DT_VN_ID);
-				break;
+				goto err;
+			vlink_desc_arr[num_vlink_desc++] = vp;
+			vn_port = fc_vport_id_lookup(lport,
+						      ntoh24(vp->fd_fc_id));
+			if (vn_port && (vn_port == lport)) {
+				mutex_lock(&fip->ctlr_mutex);
+				per_cpu_ptr(lport->dev_stats,
+					    get_cpu())->VLinkFailureCount++;
+				put_cpu();
+				fcoe_ctlr_reset(fip);
+				mutex_unlock(&fip->ctlr_mutex);
 			}
-			/* check if clr_vlink is for NPIV port */
-			mutex_lock(&lport->lp_mutex);
-			list_for_each_entry(vn_port, &lport->vports, list) {
-				if (compare_ether_addr(vp->fd_mac,
-				    fip->get_src_addr(vn_port)) == 0 &&
-				    (get_unaligned_be64(&vp->fd_wwpn)
-							== vn_port->wwpn) &&
-				    (ntoh24(vp->fd_fc_id) ==
-					    fc_host_port_id(vn_port->host))) {
-					desc_mask &= ~BIT(FIP_DT_VN_ID);
-					is_vn_port = 1;
-					break;
-				}
-			}
-			mutex_unlock(&lport->lp_mutex);
-
 			break;
 		default:
 			/* standard says ignore unknown descriptors >= 128 */
 			if (desc->fip_dtype < FIP_DT_VENDOR_BASE)
-				return;
+				goto err;
 			break;
 		}
 		desc = (struct fip_desc *)((char *)desc + dlen);
@@ -1256,26 +1261,68 @@ static void fcoe_ctlr_recv_clr_vlink(struct fcoe_ctlr *fip,
 	/*
 	 * reset only if all required descriptors were present and valid.
 	 */
-	if (desc_mask) {
+	if (desc_mask)
 		LIBFCOE_FIP_DBG(fip, "missing descriptors mask %x\n",
 				desc_mask);
+	else if (!num_vlink_desc) {
+		LIBFCOE_FIP_DBG(fip, "CVL: no Vx_Port descriptor found\n");
+		/*
+		 * No Vx_Port description. Clear all NPIV ports,
+		 * followed by physical port
+		 */
+		mutex_lock(&lport->lp_mutex);
+		list_for_each_entry(vn_port, &lport->vports, list)
+			fc_lport_reset(vn_port);
+		mutex_unlock(&lport->lp_mutex);
+
+		mutex_lock(&fip->ctlr_mutex);
+		per_cpu_ptr(lport->dev_stats,
+			    get_cpu())->VLinkFailureCount++;
+		put_cpu();
+		fcoe_ctlr_reset(fip);
+		mutex_unlock(&fip->ctlr_mutex);
+
+		fc_lport_reset(fip->lp);
+		fcoe_ctlr_solicit(fip, NULL);
 	} else {
-		LIBFCOE_FIP_DBG(fip, "performing Clear Virtual Link\n");
+		int i;
 
-		if (is_vn_port)
-			fc_lport_reset(vn_port);
-		else {
-			mutex_lock(&fip->ctlr_mutex);
-			per_cpu_ptr(lport->dev_stats,
-				    get_cpu())->VLinkFailureCount++;
-			put_cpu();
-			fcoe_ctlr_reset(fip);
-			mutex_unlock(&fip->ctlr_mutex);
+		LIBFCOE_FIP_DBG(fip, "performing Clear Virtual Link\n");
+		for (i = 0; i < num_vlink_desc; i++) {
+			vp = vlink_desc_arr[i];
+			vn_port = fc_vport_id_lookup(lport,
+						     ntoh24(vp->fd_fc_id));
+			if (!vn_port)
+				continue;
+
+			/*
+			 * 'port_id' is already validated, check MAC address and
+			 * wwpn
+			 */
+			if (compare_ether_addr(fip->get_src_addr(vn_port),
+						vp->fd_mac) != 0 ||
+				get_unaligned_be64(&vp->fd_wwpn) !=
+							vn_port->wwpn)
+				continue;
+
+			if (vn_port == lport)
+				/*
+				 * Physical port, defer processing till all
+				 * listed NPIV ports are cleared
+				 */
+				reset_phys_port = 1;
+			else    /* NPIV port */
+				fc_lport_reset(vn_port);
+		}
 
+		if (reset_phys_port) {
 			fc_lport_reset(fip->lp);
 			fcoe_ctlr_solicit(fip, NULL);
 		}
 	}
+
+err:
+	kfree(vlink_desc_arr);
 }
 
 /**
diff --git a/drivers/scsi/fcoe/fcoe_transport.c b/drivers/scsi/fcoe/fcoe_transport.c
index f81f77c8569e..41068e8748e7 100644
--- a/drivers/scsi/fcoe/fcoe_transport.c
+++ b/drivers/scsi/fcoe/fcoe_transport.c
@@ -544,16 +544,6 @@ static int fcoe_transport_create(const char *buffer, struct kernel_param *kp)
 	struct fcoe_transport *ft = NULL;
 	enum fip_state fip_mode = (enum fip_state)(long)kp->arg;
 
-#ifdef CONFIG_LIBFCOE_MODULE
-	/*
-	 * Make sure the module has been initialized, and is not about to be
-	 * removed.  Module parameter sysfs files are writable before the
-	 * module_init function is called and after module_exit.
-	 */
-	if (THIS_MODULE->state != MODULE_STATE_LIVE)
-		goto out_nodev;
-#endif
-
 	mutex_lock(&ft_mutex);
 
 	netdev = fcoe_if_to_netdev(buffer);
@@ -618,16 +608,6 @@ static int fcoe_transport_destroy(const char *buffer, struct kernel_param *kp)
 	struct net_device *netdev = NULL;
 	struct fcoe_transport *ft = NULL;
 
-#ifdef CONFIG_LIBFCOE_MODULE
-	/*
-	 * Make sure the module has been initialized, and is not about to be
-	 * removed.  Module parameter sysfs files are writable before the
-	 * module_init function is called and after module_exit.
-	 */
-	if (THIS_MODULE->state != MODULE_STATE_LIVE)
-		goto out_nodev;
-#endif
-
 	mutex_lock(&ft_mutex);
 
 	netdev = fcoe_if_to_netdev(buffer);
@@ -672,16 +652,6 @@ static int fcoe_transport_disable(const char *buffer, struct kernel_param *kp)
 	struct net_device *netdev = NULL;
 	struct fcoe_transport *ft = NULL;
 
-#ifdef CONFIG_LIBFCOE_MODULE
-	/*
-	 * Make sure the module has been initialized, and is not about to be
-	 * removed.  Module parameter sysfs files are writable before the
-	 * module_init function is called and after module_exit.
-	 */
-	if (THIS_MODULE->state != MODULE_STATE_LIVE)
-		goto out_nodev;
-#endif
-
 	mutex_lock(&ft_mutex);
 
 	netdev = fcoe_if_to_netdev(buffer);
@@ -720,16 +690,6 @@ static int fcoe_transport_enable(const char *buffer, struct kernel_param *kp)
 	struct net_device *netdev = NULL;
 	struct fcoe_transport *ft = NULL;
 
-#ifdef CONFIG_LIBFCOE_MODULE
-	/*
-	 * Make sure the module has been initialized, and is not about to be
-	 * removed.  Module parameter sysfs files are writable before the
-	 * module_init function is called and after module_exit.
-	 */
-	if (THIS_MODULE->state != MODULE_STATE_LIVE)
-		goto out_nodev;
-#endif
-
 	mutex_lock(&ft_mutex);
 
 	netdev = fcoe_if_to_netdev(buffer);
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 12868ca46110..888086c4e709 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -5149,21 +5149,21 @@ static irqreturn_t ipr_isr(int irq, void *devp)
 
 		if (ipr_cmd != NULL) {
 			/* Clear the PCI interrupt */
+			num_hrrq = 0;
 			do {
 				writel(IPR_PCII_HRRQ_UPDATED, ioa_cfg->regs.clr_interrupt_reg32);
 				int_reg = readl(ioa_cfg->regs.sense_interrupt_reg32);
 			} while (int_reg & IPR_PCII_HRRQ_UPDATED &&
 					num_hrrq++ < IPR_MAX_HRRQ_RETRIES);
 
-			if (int_reg & IPR_PCII_HRRQ_UPDATED) {
-				ipr_isr_eh(ioa_cfg, "Error clearing HRRQ");
-				spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
-				return IRQ_HANDLED;
-			}
-
 		} else if (rc == IRQ_NONE && irq_none == 0) {
 			int_reg = readl(ioa_cfg->regs.sense_interrupt_reg32);
 			irq_none++;
+		} else if (num_hrrq == IPR_MAX_HRRQ_RETRIES &&
+			   int_reg & IPR_PCII_HRRQ_UPDATED) {
+			ipr_isr_eh(ioa_cfg, "Error clearing HRRQ");
+			spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
+			return IRQ_HANDLED;
 		} else
 			break;
 	}
diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c
index 911b2736cafa..b9cb8140b398 100644
--- a/drivers/scsi/libfc/fc_disc.c
+++ b/drivers/scsi/libfc/fc_disc.c
@@ -205,6 +205,7 @@ static void fc_disc_recv_req(struct fc_lport *lport, struct fc_frame *fp)
 	default:
 		FC_DISC_DBG(disc, "Received an unsupported request, "
 			    "the opcode is (%x)\n", op);
+		fc_frame_free(fp);
 		break;
 	}
 }
diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 77035a746f60..3b8a6451ea28 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -1434,6 +1434,7 @@ static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp)
 	    (f_ctl & (FC_FC_LAST_SEQ | FC_FC_END_SEQ)) ==
 	    (FC_FC_LAST_SEQ | FC_FC_END_SEQ)) {
 		spin_lock_bh(&ep->ex_lock);
+		resp = ep->resp;
 		rc = fc_exch_done_locked(ep);
 		WARN_ON(fc_seq_exch(sp) != ep);
 		spin_unlock_bh(&ep->ex_lock);
@@ -1978,6 +1979,7 @@ static struct fc_seq *fc_exch_seq_send(struct fc_lport *lport,
 	spin_unlock_bh(&ep->ex_lock);
 	return sp;
 err:
+	fc_fcp_ddp_done(fr_fsp(fp));
 	rc = fc_exch_done_locked(ep);
 	spin_unlock_bh(&ep->ex_lock);
 	if (!rc)
diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index 2a3a4720a771..9cd2149519ac 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -312,7 +312,7 @@ void fc_fcp_ddp_setup(struct fc_fcp_pkt *fsp, u16 xid)
  *		       DDP related resources for a fcp_pkt
  * @fsp: The FCP packet that DDP had been used on
  */
-static void fc_fcp_ddp_done(struct fc_fcp_pkt *fsp)
+void fc_fcp_ddp_done(struct fc_fcp_pkt *fsp)
 {
 	struct fc_lport *lport;
 
@@ -681,8 +681,7 @@ static int fc_fcp_send_data(struct fc_fcp_pkt *fsp, struct fc_seq *seq,
 		error = lport->tt.seq_send(lport, seq, fp);
 		if (error) {
 			WARN_ON(1);		/* send error should be rare */
-			fc_fcp_retry_cmd(fsp);
-			return 0;
+			return error;
 		}
 		fp = NULL;
 	}
@@ -1673,7 +1672,8 @@ static void fc_fcp_srr(struct fc_fcp_pkt *fsp, enum fc_rctl r_ctl, u32 offset)
 		       FC_FCTL_REQ, 0);
 
 	rec_tov = get_fsp_rec_tov(fsp);
-	seq = lport->tt.exch_seq_send(lport, fp, fc_fcp_srr_resp, NULL,
+	seq = lport->tt.exch_seq_send(lport, fp, fc_fcp_srr_resp,
+				      fc_fcp_pkt_destroy,
 				      fsp, jiffies_to_msecs(rec_tov));
 	if (!seq)
 		goto retry;
@@ -1720,7 +1720,6 @@ static void fc_fcp_srr_resp(struct fc_seq *seq, struct fc_frame *fp, void *arg)
 		return;
 	}
 
-	fsp->recov_seq = NULL;
 	switch (fc_frame_payload_op(fp)) {
 	case ELS_LS_ACC:
 		fsp->recov_retry = 0;
@@ -1732,10 +1731,9 @@ static void fc_fcp_srr_resp(struct fc_seq *seq, struct fc_frame *fp, void *arg)
 		break;
 	}
 	fc_fcp_unlock_pkt(fsp);
-	fsp->lp->tt.exch_done(seq);
 out:
+	fsp->lp->tt.exch_done(seq);
 	fc_frame_free(fp);
-	fc_fcp_pkt_release(fsp);	/* drop hold for outstanding SRR */
 }
 
 /**
@@ -1747,8 +1745,6 @@ static void fc_fcp_srr_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp)
 {
 	if (fc_fcp_lock_pkt(fsp))
 		goto out;
-	fsp->lp->tt.exch_done(fsp->recov_seq);
-	fsp->recov_seq = NULL;
 	switch (PTR_ERR(fp)) {
 	case -FC_EX_TIMEOUT:
 		if (fsp->recov_retry++ < FC_MAX_RECOV_RETRY)
@@ -1764,7 +1760,7 @@ static void fc_fcp_srr_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp)
 	}
 	fc_fcp_unlock_pkt(fsp);
 out:
-	fc_fcp_pkt_release(fsp);	/* drop hold for outstanding SRR */
+	fsp->lp->tt.exch_done(fsp->recov_seq);
 }
 
 /**
diff --git a/drivers/scsi/libfc/fc_libfc.h b/drivers/scsi/libfc/fc_libfc.h
index fedc819d70c0..c7d071289af5 100644
--- a/drivers/scsi/libfc/fc_libfc.h
+++ b/drivers/scsi/libfc/fc_libfc.h
@@ -108,6 +108,7 @@ extern struct fc4_prov fc_rport_fcp_init;	/* FCP initiator provider */
  * Set up direct-data placement for this I/O request
  */
 void fc_fcp_ddp_setup(struct fc_fcp_pkt *fsp, u16 xid);
+void fc_fcp_ddp_done(struct fc_fcp_pkt *fsp);
 
 /*
  * Module setup functions
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 31fc21f4d831..db9238f2ecb8 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -99,19 +99,29 @@ static void sas_ata_task_done(struct sas_task *task)
 	struct sas_ha_struct *sas_ha;
 	enum ata_completion_errors ac;
 	unsigned long flags;
+	struct ata_link *link;
 
 	if (!qc)
 		goto qc_already_gone;
 
 	dev = qc->ap->private_data;
 	sas_ha = dev->port->ha;
+	link = &dev->sata_dev.ap->link;
 
 	spin_lock_irqsave(dev->sata_dev.ap->lock, flags);
 	if (stat->stat == SAS_PROTO_RESPONSE || stat->stat == SAM_STAT_GOOD ||
 	    ((stat->stat == SAM_STAT_CHECK_CONDITION &&
 	      dev->sata_dev.command_set == ATAPI_COMMAND_SET))) {
 		ata_tf_from_fis(resp->ending_fis, &dev->sata_dev.tf);
-		qc->err_mask |= ac_err_mask(dev->sata_dev.tf.command);
+
+		if (!link->sactive) {
+			qc->err_mask |= ac_err_mask(dev->sata_dev.tf.command);
+		} else {
+			link->eh_info.err_mask |= ac_err_mask(dev->sata_dev.tf.command);
+			if (unlikely(link->eh_info.err_mask))
+				qc->flags |= ATA_QCFLAG_FAILED;
+		}
+
 		dev->sata_dev.sstatus = resp->sstatus;
 		dev->sata_dev.serror = resp->serror;
 		dev->sata_dev.scontrol = resp->scontrol;
@@ -121,7 +131,13 @@ static void sas_ata_task_done(struct sas_task *task)
 			SAS_DPRINTK("%s: SAS error %x\n", __func__,
 				    stat->stat);
 			/* We saw a SAS error. Send a vague error. */
-			qc->err_mask = ac;
+			if (!link->sactive) {
+				qc->err_mask = ac;
+			} else {
+				link->eh_info.err_mask |= AC_ERR_DEV;
+				qc->flags |= ATA_QCFLAG_FAILED;
+			}
+
 			dev->sata_dev.tf.feature = 0x04; /* status err */
 			dev->sata_dev.tf.command = ATA_ERR;
 		}
@@ -279,6 +295,44 @@ static int sas_ata_hard_reset(struct ata_link *link, unsigned int *class,
 	return ret;
 }
 
+static int sas_ata_soft_reset(struct ata_link *link, unsigned int *class,
+			       unsigned long deadline)
+{
+	struct ata_port *ap = link->ap;
+	struct domain_device *dev = ap->private_data;
+	struct sas_internal *i =
+		to_sas_internal(dev->port->ha->core.shost->transportt);
+	int res = TMF_RESP_FUNC_FAILED;
+	int ret = 0;
+
+	if (i->dft->lldd_ata_soft_reset)
+		res = i->dft->lldd_ata_soft_reset(dev);
+
+	if (res != TMF_RESP_FUNC_COMPLETE) {
+		SAS_DPRINTK("%s: Unable to soft reset\n", __func__);
+		ret = -EAGAIN;
+	}
+
+	switch (dev->sata_dev.command_set) {
+	case ATA_COMMAND_SET:
+		SAS_DPRINTK("%s: Found ATA device.\n", __func__);
+		*class = ATA_DEV_ATA;
+		break;
+	case ATAPI_COMMAND_SET:
+		SAS_DPRINTK("%s: Found ATAPI device.\n", __func__);
+		*class = ATA_DEV_ATAPI;
+		break;
+	default:
+		SAS_DPRINTK("%s: Unknown SATA command set: %d.\n",
+			    __func__, dev->sata_dev.command_set);
+		*class = ATA_DEV_UNKNOWN;
+		break;
+	}
+
+	ap->cbl = ATA_CBL_SATA;
+	return ret;
+}
+
 static void sas_ata_post_internal(struct ata_queued_cmd *qc)
 {
 	if (qc->flags & ATA_QCFLAG_FAILED)
@@ -309,7 +363,7 @@ static void sas_ata_post_internal(struct ata_queued_cmd *qc)
 
 static struct ata_port_operations sas_sata_ops = {
 	.prereset		= ata_std_prereset,
-	.softreset		= NULL,
+	.softreset		= sas_ata_soft_reset,
 	.hardreset		= sas_ata_hard_reset,
 	.postreset		= ata_std_postreset,
 	.error_handler		= ata_std_error_handler,
diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h
index 8b538bd1ff2b..14e21b5fb8ba 100644
--- a/drivers/scsi/libsas/sas_internal.h
+++ b/drivers/scsi/libsas/sas_internal.h
@@ -57,7 +57,7 @@ int  sas_init_queue(struct sas_ha_struct *sas_ha);
 int  sas_init_events(struct sas_ha_struct *sas_ha);
 void sas_shutdown_queue(struct sas_ha_struct *sas_ha);
 
-void sas_deform_port(struct asd_sas_phy *phy);
+void sas_deform_port(struct asd_sas_phy *phy, int gone);
 
 void sas_porte_bytes_dmaed(struct work_struct *work);
 void sas_porte_broadcast_rcvd(struct work_struct *work);
diff --git a/drivers/scsi/libsas/sas_phy.c b/drivers/scsi/libsas/sas_phy.c
index b459c4b635b1..e0f5018e9071 100644
--- a/drivers/scsi/libsas/sas_phy.c
+++ b/drivers/scsi/libsas/sas_phy.c
@@ -39,7 +39,7 @@ static void sas_phye_loss_of_signal(struct work_struct *work)
 	sas_begin_event(PHYE_LOSS_OF_SIGNAL, &phy->ha->event_lock,
 			&phy->phy_events_pending);
 	phy->error = 0;
-	sas_deform_port(phy);
+	sas_deform_port(phy, 1);
 }
 
 static void sas_phye_oob_done(struct work_struct *work)
@@ -66,7 +66,7 @@ static void sas_phye_oob_error(struct work_struct *work)
 	sas_begin_event(PHYE_OOB_ERROR, &phy->ha->event_lock,
 			&phy->phy_events_pending);
 
-	sas_deform_port(phy);
+	sas_deform_port(phy, 1);
 
 	if (!port && phy->enabled && i->dft->lldd_control_phy) {
 		phy->error++;
diff --git a/drivers/scsi/libsas/sas_port.c b/drivers/scsi/libsas/sas_port.c
index 5257fdfe699a..42fd1f25b664 100644
--- a/drivers/scsi/libsas/sas_port.c
+++ b/drivers/scsi/libsas/sas_port.c
@@ -57,7 +57,7 @@ static void sas_form_port(struct asd_sas_phy *phy)
 
 	if (port) {
 		if (!phy_is_wideport_member(port, phy))
-			sas_deform_port(phy);
+			sas_deform_port(phy, 0);
 		else {
 			SAS_DPRINTK("%s: phy%d belongs to port%d already(%d)!\n",
 				    __func__, phy->id, phy->port->id,
@@ -153,28 +153,31 @@ static void sas_form_port(struct asd_sas_phy *phy)
  * This is called when the physical link to the other phy has been
  * lost (on this phy), in Event thread context. We cannot delay here.
  */
-void sas_deform_port(struct asd_sas_phy *phy)
+void sas_deform_port(struct asd_sas_phy *phy, int gone)
 {
 	struct sas_ha_struct *sas_ha = phy->ha;
 	struct asd_sas_port *port = phy->port;
 	struct sas_internal *si =
 		to_sas_internal(sas_ha->core.shost->transportt);
+	struct domain_device *dev;
 	unsigned long flags;
 
 	if (!port)
 		return;		  /* done by a phy event */
 
-	if (port->port_dev)
-		port->port_dev->pathways--;
+	dev = port->port_dev;
+	if (dev)
+		dev->pathways--;
 
 	if (port->num_phys == 1) {
+		if (dev && gone)
+			dev->gone = 1;
 		sas_unregister_domain_devices(port);
 		sas_port_delete(port->port);
 		port->port = NULL;
 	} else
 		sas_port_delete_phy(port->port, phy->phy);
 
-
 	if (si->dft->lldd_port_deformed)
 		si->dft->lldd_port_deformed(phy);
 
@@ -244,7 +247,7 @@ void sas_porte_link_reset_err(struct work_struct *work)
 	sas_begin_event(PORTE_LINK_RESET_ERR, &phy->ha->event_lock,
 			&phy->port_events_pending);
 
-	sas_deform_port(phy);
+	sas_deform_port(phy, 1);
 }
 
 void sas_porte_timer_event(struct work_struct *work)
@@ -256,7 +259,7 @@ void sas_porte_timer_event(struct work_struct *work)
 	sas_begin_event(PORTE_TIMER_EVENT, &phy->ha->event_lock,
 			&phy->port_events_pending);
 
-	sas_deform_port(phy);
+	sas_deform_port(phy, 1);
 }
 
 void sas_porte_hard_reset(struct work_struct *work)
@@ -268,7 +271,7 @@ void sas_porte_hard_reset(struct work_struct *work)
 	sas_begin_event(PORTE_HARD_RESET, &phy->ha->event_lock,
 			&phy->port_events_pending);
 
-	sas_deform_port(phy);
+	sas_deform_port(phy, 1);
 }
 
 /* ---------- SAS port registration ---------- */
@@ -306,6 +309,6 @@ void sas_unregister_ports(struct sas_ha_struct *sas_ha)
 
 	for (i = 0; i < sas_ha->num_phys; i++)
 		if (sas_ha->sas_phy[i]->port)
-			sas_deform_port(sas_ha->sas_phy[i]);
+			sas_deform_port(sas_ha->sas_phy[i], 0);
 
 }
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index f6e189f40917..eeba76cdf774 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -207,6 +207,13 @@ static int sas_queuecommand_lck(struct scsi_cmnd *cmd,
 		struct sas_ha_struct *sas_ha = dev->port->ha;
 		struct sas_task *task;
 
+		/* If the device fell off, no sense in issuing commands */
+		if (dev->gone) {
+			cmd->result = DID_BAD_TARGET << 16;
+			scsi_done(cmd);
+			goto out;
+		}
+
 		if (dev_is_sata(dev)) {
 			unsigned long flags;
 
@@ -216,13 +223,6 @@ static int sas_queuecommand_lck(struct scsi_cmnd *cmd,
 			goto out;
 		}
 
-		/* If the device fell off, no sense in issuing commands */
-		if (dev->gone) {
-			cmd->result = DID_BAD_TARGET << 16;
-			scsi_done(cmd);
-			goto out;
-		}
-
 		res = -ENOMEM;
 		task = sas_create_task(cmd, dev, GFP_ATOMIC);
 		if (!task)
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 02d53d89534f..8ec2c86a49d4 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -41,6 +41,7 @@ struct lpfc_sli2_slim;
 		downloads using bsg */
 #define LPFC_DEFAULT_PROT_SG_SEG_CNT 4096 /* sg protection elements count */
 #define LPFC_MAX_SG_SEG_CNT	4096	/* sg element count per scsi cmnd */
+#define LPFC_MAX_SGE_SIZE       0x80000000 /* Maximum data allowed in a SGE */
 #define LPFC_MAX_PROT_SG_SEG_CNT 4096	/* prot sg element count per scsi cmd*/
 #define LPFC_IOCB_LIST_CNT	2250	/* list of IOCBs for fast-path usage. */
 #define LPFC_Q_RAMP_UP_INTERVAL 120     /* lun q_depth ramp up interval */
@@ -486,6 +487,42 @@ struct unsol_rcv_ct_ctx {
 				     (1 << LPFC_USER_LINK_SPEED_AUTO))
 #define LPFC_LINK_SPEED_STRING "0, 1, 2, 4, 8, 10, 16"
 
+enum nemb_type {
+	nemb_mse = 1,
+	nemb_hbd
+};
+
+enum mbox_type {
+	mbox_rd = 1,
+	mbox_wr
+};
+
+enum dma_type {
+	dma_mbox = 1,
+	dma_ebuf
+};
+
+enum sta_type {
+	sta_pre_addr = 1,
+	sta_pos_addr
+};
+
+struct lpfc_mbox_ext_buf_ctx {
+	uint32_t state;
+#define LPFC_BSG_MBOX_IDLE		0
+#define LPFC_BSG_MBOX_HOST              1
+#define LPFC_BSG_MBOX_PORT		2
+#define LPFC_BSG_MBOX_DONE		3
+#define LPFC_BSG_MBOX_ABTS		4
+	enum nemb_type nembType;
+	enum mbox_type mboxType;
+	uint32_t numBuf;
+	uint32_t mbxTag;
+	uint32_t seqNum;
+	struct lpfc_dmabuf *mbx_dmabuf;
+	struct list_head ext_dmabuf_list;
+};
+
 struct lpfc_hba {
 	/* SCSI interface function jump table entries */
 	int (*lpfc_new_scsi_buf)
@@ -589,6 +626,7 @@ struct lpfc_hba {
 
 	MAILBOX_t *mbox;
 	uint32_t *mbox_ext;
+	struct lpfc_mbox_ext_buf_ctx mbox_ext_buf_ctx;
 	uint32_t ha_copy;
 	struct _PCB *pcb;
 	struct _IOCB *IOCBs;
@@ -659,6 +697,7 @@ struct lpfc_hba {
 	uint32_t cfg_hostmem_hgp;
 	uint32_t cfg_log_verbose;
 	uint32_t cfg_aer_support;
+	uint32_t cfg_sriov_nr_virtfn;
 	uint32_t cfg_iocb_cnt;
 	uint32_t cfg_suppress_link_up;
 #define LPFC_INITIALIZE_LINK              0	/* do normal init_link mbox */
@@ -706,7 +745,6 @@ struct lpfc_hba {
 	uint32_t          *hbq_get;     /* Host mem address of HBQ get ptrs */
 
 	int brd_no;			/* FC board number */
-
 	char SerialNumber[32];		/* adapter Serial Number */
 	char OptionROMVersion[32];	/* adapter BIOS / Fcode version */
 	char ModelDesc[256];		/* Model Description */
@@ -778,6 +816,9 @@ struct lpfc_hba {
 	uint16_t vpi_base;
 	uint16_t vfi_base;
 	unsigned long *vpi_bmask;	/* vpi allocation table */
+	uint16_t *vpi_ids;
+	uint16_t vpi_count;
+	struct list_head lpfc_vpi_blk_list;
 
 	/* Data structure used by fabric iocb scheduler */
 	struct list_head fabric_iocb_list;
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 8dcbf8fff673..135a53baa735 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -755,6 +755,73 @@ lpfc_issue_reset(struct device *dev, struct device_attribute *attr,
 }
 
 /**
+ * lpfc_sli4_pdev_reg_request - Request physical dev to perform a register acc
+ * @phba: lpfc_hba pointer.
+ *
+ * Description:
+ * Request SLI4 interface type-2 device to perform a physical register set
+ * access.
+ *
+ * Returns:
+ * zero for success
+ **/
+static ssize_t
+lpfc_sli4_pdev_reg_request(struct lpfc_hba *phba, uint32_t opcode)
+{
+	struct completion online_compl;
+	uint32_t reg_val;
+	int status = 0;
+	int rc;
+
+	if (!phba->cfg_enable_hba_reset)
+		return -EIO;
+
+	if ((phba->sli_rev < LPFC_SLI_REV4) ||
+	    (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
+	     LPFC_SLI_INTF_IF_TYPE_2))
+		return -EPERM;
+
+	status = lpfc_do_offline(phba, LPFC_EVT_OFFLINE);
+
+	if (status != 0)
+		return status;
+
+	/* wait for the device to be quiesced before firmware reset */
+	msleep(100);
+
+	reg_val = readl(phba->sli4_hba.conf_regs_memmap_p +
+			LPFC_CTL_PDEV_CTL_OFFSET);
+
+	if (opcode == LPFC_FW_DUMP)
+		reg_val |= LPFC_FW_DUMP_REQUEST;
+	else if (opcode == LPFC_FW_RESET)
+		reg_val |= LPFC_CTL_PDEV_CTL_FRST;
+	else if (opcode == LPFC_DV_RESET)
+		reg_val |= LPFC_CTL_PDEV_CTL_DRST;
+
+	writel(reg_val, phba->sli4_hba.conf_regs_memmap_p +
+	       LPFC_CTL_PDEV_CTL_OFFSET);
+	/* flush */
+	readl(phba->sli4_hba.conf_regs_memmap_p + LPFC_CTL_PDEV_CTL_OFFSET);
+
+	/* delay driver action following IF_TYPE_2 reset */
+	msleep(100);
+
+	init_completion(&online_compl);
+	rc = lpfc_workq_post_event(phba, &status, &online_compl,
+				   LPFC_EVT_ONLINE);
+	if (rc == 0)
+		return -ENOMEM;
+
+	wait_for_completion(&online_compl);
+
+	if (status != 0)
+		return -EIO;
+
+	return 0;
+}
+
+/**
  * lpfc_nport_evt_cnt_show - Return the number of nport events
  * @dev: class device that is converted into a Scsi_host.
  * @attr: device attribute, not used.
@@ -848,6 +915,12 @@ lpfc_board_mode_store(struct device *dev, struct device_attribute *attr,
 			return -EINVAL;
 		else
 			status = lpfc_do_offline(phba, LPFC_EVT_KILL);
+	else if (strncmp(buf, "dump", sizeof("dump") - 1) == 0)
+		status = lpfc_sli4_pdev_reg_request(phba, LPFC_FW_DUMP);
+	else if (strncmp(buf, "fw_reset", sizeof("fw_reset") - 1) == 0)
+		status = lpfc_sli4_pdev_reg_request(phba, LPFC_FW_RESET);
+	else if (strncmp(buf, "dv_reset", sizeof("dv_reset") - 1) == 0)
+		status = lpfc_sli4_pdev_reg_request(phba, LPFC_DV_RESET);
 	else
 		return -EINVAL;
 
@@ -1322,6 +1395,102 @@ lpfc_dss_show(struct device *dev, struct device_attribute *attr,
 }
 
 /**
+ * lpfc_sriov_hw_max_virtfn_show - Return maximum number of virtual functions
+ * @dev: class converted to a Scsi_host structure.
+ * @attr: device attribute, not used.
+ * @buf: on return contains the formatted support level.
+ *
+ * Description:
+ * Returns the maximum number of virtual functions a physical function can
+ * support, 0 will be returned if called on virtual function.
+ *
+ * Returns: size of formatted string.
+ **/
+static ssize_t
+lpfc_sriov_hw_max_virtfn_show(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+	struct lpfc_vport *vport = (struct lpfc_vport *) shost->hostdata;
+	struct lpfc_hba *phba = vport->phba;
+	struct pci_dev *pdev = phba->pcidev;
+	union  lpfc_sli4_cfg_shdr *shdr;
+	uint32_t shdr_status, shdr_add_status;
+	LPFC_MBOXQ_t *mboxq;
+	struct lpfc_mbx_get_prof_cfg *get_prof_cfg;
+	struct lpfc_rsrc_desc_pcie *desc;
+	uint32_t max_nr_virtfn;
+	uint32_t desc_count;
+	int length, rc, i;
+
+	if ((phba->sli_rev < LPFC_SLI_REV4) ||
+	    (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
+	     LPFC_SLI_INTF_IF_TYPE_2))
+		return -EPERM;
+
+	if (!pdev->is_physfn)
+		return snprintf(buf, PAGE_SIZE, "%d\n", 0);
+
+	mboxq = (LPFC_MBOXQ_t *)mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!mboxq)
+		return -ENOMEM;
+
+	/* get the maximum number of virtfn support by physfn */
+	length = (sizeof(struct lpfc_mbx_get_prof_cfg) -
+		  sizeof(struct lpfc_sli4_cfg_mhdr));
+	lpfc_sli4_config(phba, mboxq, LPFC_MBOX_SUBSYSTEM_COMMON,
+			 LPFC_MBOX_OPCODE_GET_PROFILE_CONFIG,
+			 length, LPFC_SLI4_MBX_EMBED);
+	shdr = (union lpfc_sli4_cfg_shdr *)
+		&mboxq->u.mqe.un.sli4_config.header.cfg_shdr;
+	bf_set(lpfc_mbox_hdr_pf_num, &shdr->request,
+	       phba->sli4_hba.iov.pf_number + 1);
+
+	get_prof_cfg = &mboxq->u.mqe.un.get_prof_cfg;
+	bf_set(lpfc_mbx_get_prof_cfg_prof_tp, &get_prof_cfg->u.request,
+	       LPFC_CFG_TYPE_CURRENT_ACTIVE);
+
+	rc = lpfc_sli_issue_mbox_wait(phba, mboxq,
+				lpfc_mbox_tmo_val(phba, MBX_SLI4_CONFIG));
+
+	if (rc != MBX_TIMEOUT) {
+		/* check return status */
+		shdr_status = bf_get(lpfc_mbox_hdr_status, &shdr->response);
+		shdr_add_status = bf_get(lpfc_mbox_hdr_add_status,
+					 &shdr->response);
+		if (shdr_status || shdr_add_status || rc)
+			goto error_out;
+
+	} else
+		goto error_out;
+
+	desc_count = get_prof_cfg->u.response.prof_cfg.rsrc_desc_count;
+
+	for (i = 0; i < LPFC_RSRC_DESC_MAX_NUM; i++) {
+		desc = (struct lpfc_rsrc_desc_pcie *)
+			&get_prof_cfg->u.response.prof_cfg.desc[i];
+		if (LPFC_RSRC_DESC_TYPE_PCIE ==
+		    bf_get(lpfc_rsrc_desc_pcie_type, desc)) {
+			max_nr_virtfn = bf_get(lpfc_rsrc_desc_pcie_nr_virtfn,
+					       desc);
+			break;
+		}
+	}
+
+	if (i < LPFC_RSRC_DESC_MAX_NUM) {
+		if (rc != MBX_TIMEOUT)
+			mempool_free(mboxq, phba->mbox_mem_pool);
+		return snprintf(buf, PAGE_SIZE, "%d\n", max_nr_virtfn);
+	}
+
+error_out:
+	if (rc != MBX_TIMEOUT)
+		mempool_free(mboxq, phba->mbox_mem_pool);
+	return -EIO;
+}
+
+/**
  * lpfc_param_show - Return a cfg attribute value in decimal
  *
  * Description:
@@ -1762,6 +1931,8 @@ static DEVICE_ATTR(lpfc_temp_sensor, S_IRUGO, lpfc_temp_sensor_show, NULL);
 static DEVICE_ATTR(lpfc_fips_level, S_IRUGO, lpfc_fips_level_show, NULL);
 static DEVICE_ATTR(lpfc_fips_rev, S_IRUGO, lpfc_fips_rev_show, NULL);
 static DEVICE_ATTR(lpfc_dss, S_IRUGO, lpfc_dss_show, NULL);
+static DEVICE_ATTR(lpfc_sriov_hw_max_virtfn, S_IRUGO,
+		   lpfc_sriov_hw_max_virtfn_show, NULL);
 
 static char *lpfc_soft_wwn_key = "C99G71SL8032A";
 
@@ -3014,7 +3185,7 @@ static DEVICE_ATTR(lpfc_link_speed, S_IRUGO | S_IWUSR,
  *
  * @dev: class device that is converted into a Scsi_host.
  * @attr: device attribute, not used.
- * @buf: containing the string "selective".
+ * @buf: containing enable or disable aer flag.
  * @count: unused variable.
  *
  * Description:
@@ -3098,7 +3269,7 @@ lpfc_param_show(aer_support)
 /**
  * lpfc_aer_support_init - Set the initial adapters aer support flag
  * @phba: lpfc_hba pointer.
- * @val: link speed value.
+ * @val: enable aer or disable aer flag.
  *
  * Description:
  * If val is in a valid range [0,1], then set the adapter's initial
@@ -3137,7 +3308,7 @@ static DEVICE_ATTR(lpfc_aer_support, S_IRUGO | S_IWUSR,
  * lpfc_aer_cleanup_state - Clean up aer state to the aer enabled device
  * @dev: class device that is converted into a Scsi_host.
  * @attr: device attribute, not used.
- * @buf: containing the string "selective".
+ * @buf: containing flag 1 for aer cleanup state.
  * @count: unused variable.
  *
  * Description:
@@ -3180,6 +3351,136 @@ lpfc_aer_cleanup_state(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(lpfc_aer_state_cleanup, S_IWUSR, NULL,
 		   lpfc_aer_cleanup_state);
 
+/**
+ * lpfc_sriov_nr_virtfn_store - Enable the adapter for sr-iov virtual functions
+ *
+ * @dev: class device that is converted into a Scsi_host.
+ * @attr: device attribute, not used.
+ * @buf: containing the string the number of vfs to be enabled.
+ * @count: unused variable.
+ *
+ * Description:
+ * When this api is called either through user sysfs, the driver shall
+ * try to enable or disable SR-IOV virtual functions according to the
+ * following:
+ *
+ * If zero virtual function has been enabled to the physical function,
+ * the driver shall invoke the pci enable virtual function api trying
+ * to enable the virtual functions. If the nr_vfn provided is greater
+ * than the maximum supported, the maximum virtual function number will
+ * be used for invoking the api; otherwise, the nr_vfn provided shall
+ * be used for invoking the api. If the api call returned success, the
+ * actual number of virtual functions enabled will be set to the driver
+ * cfg_sriov_nr_virtfn; otherwise, -EINVAL shall be returned and driver
+ * cfg_sriov_nr_virtfn remains zero.
+ *
+ * If none-zero virtual functions have already been enabled to the
+ * physical function, as reflected by the driver's cfg_sriov_nr_virtfn,
+ * -EINVAL will be returned and the driver does nothing;
+ *
+ * If the nr_vfn provided is zero and none-zero virtual functions have
+ * been enabled, as indicated by the driver's cfg_sriov_nr_virtfn, the
+ * disabling virtual function api shall be invoded to disable all the
+ * virtual functions and driver's cfg_sriov_nr_virtfn shall be set to
+ * zero. Otherwise, if zero virtual function has been enabled, do
+ * nothing.
+ *
+ * Returns:
+ * length of the buf on success if val is in range the intended mode
+ * is supported.
+ * -EINVAL if val out of range or intended mode is not supported.
+ **/
+static ssize_t
+lpfc_sriov_nr_virtfn_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+	struct lpfc_vport *vport = (struct lpfc_vport *)shost->hostdata;
+	struct lpfc_hba *phba = vport->phba;
+	struct pci_dev *pdev = phba->pcidev;
+	int val = 0, rc = -EINVAL;
+
+	/* Sanity check on user data */
+	if (!isdigit(buf[0]))
+		return -EINVAL;
+	if (sscanf(buf, "%i", &val) != 1)
+		return -EINVAL;
+	if (val < 0)
+		return -EINVAL;
+
+	/* Request disabling virtual functions */
+	if (val == 0) {
+		if (phba->cfg_sriov_nr_virtfn > 0) {
+			pci_disable_sriov(pdev);
+			phba->cfg_sriov_nr_virtfn = 0;
+		}
+		return strlen(buf);
+	}
+
+	/* Request enabling virtual functions */
+	if (phba->cfg_sriov_nr_virtfn > 0) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"3018 There are %d virtual functions "
+				"enabled on physical function.\n",
+				phba->cfg_sriov_nr_virtfn);
+		return -EEXIST;
+	}
+
+	if (val <= LPFC_MAX_VFN_PER_PFN)
+		phba->cfg_sriov_nr_virtfn = val;
+	else {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"3019 Enabling %d virtual functions is not "
+				"allowed.\n", val);
+		return -EINVAL;
+	}
+
+	rc = lpfc_sli_probe_sriov_nr_virtfn(phba, phba->cfg_sriov_nr_virtfn);
+	if (rc) {
+		phba->cfg_sriov_nr_virtfn = 0;
+		rc = -EPERM;
+	} else
+		rc = strlen(buf);
+
+	return rc;
+}
+
+static int lpfc_sriov_nr_virtfn = LPFC_DEF_VFN_PER_PFN;
+module_param(lpfc_sriov_nr_virtfn, int, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(lpfc_sriov_nr_virtfn, "Enable PCIe device SR-IOV virtual fn");
+lpfc_param_show(sriov_nr_virtfn)
+
+/**
+ * lpfc_sriov_nr_virtfn_init - Set the initial sr-iov virtual function enable
+ * @phba: lpfc_hba pointer.
+ * @val: link speed value.
+ *
+ * Description:
+ * If val is in a valid range [0,255], then set the adapter's initial
+ * cfg_sriov_nr_virtfn field. If it's greater than the maximum, the maximum
+ * number shall be used instead. It will be up to the driver's probe_one
+ * routine to determine whether the device's SR-IOV is supported or not.
+ *
+ * Returns:
+ * zero if val saved.
+ * -EINVAL val out of range
+ **/
+static int
+lpfc_sriov_nr_virtfn_init(struct lpfc_hba *phba, int val)
+{
+	if (val >= 0 && val <= LPFC_MAX_VFN_PER_PFN) {
+		phba->cfg_sriov_nr_virtfn = val;
+		return 0;
+	}
+
+	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+			"3017 Enabling %d virtual functions is not "
+			"allowed.\n", val);
+	return -EINVAL;
+}
+static DEVICE_ATTR(lpfc_sriov_nr_virtfn, S_IRUGO | S_IWUSR,
+		   lpfc_sriov_nr_virtfn_show, lpfc_sriov_nr_virtfn_store);
+
 /*
 # lpfc_fcp_class:  Determines FC class to use for the FCP protocol.
 # Value range is [2,3]. Default value is 3.
@@ -3497,6 +3798,7 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_prot_sg_seg_cnt,
 	&dev_attr_lpfc_aer_support,
 	&dev_attr_lpfc_aer_state_cleanup,
+	&dev_attr_lpfc_sriov_nr_virtfn,
 	&dev_attr_lpfc_suppress_link_up,
 	&dev_attr_lpfc_iocb_cnt,
 	&dev_attr_iocb_hw,
@@ -3505,6 +3807,7 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_fips_level,
 	&dev_attr_lpfc_fips_rev,
 	&dev_attr_lpfc_dss,
+	&dev_attr_lpfc_sriov_hw_max_virtfn,
 	NULL,
 };
 
@@ -3961,7 +4264,7 @@ static struct bin_attribute sysfs_mbox_attr = {
 		.name = "mbox",
 		.mode = S_IRUSR | S_IWUSR,
 	},
-	.size = MAILBOX_CMD_SIZE,
+	.size = MAILBOX_SYSFS_MAX,
 	.read = sysfs_mbox_read,
 	.write = sysfs_mbox_write,
 };
@@ -4705,6 +5008,7 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	lpfc_hba_queue_depth_init(phba, lpfc_hba_queue_depth);
 	lpfc_hba_log_verbose_init(phba, lpfc_log_verbose);
 	lpfc_aer_support_init(phba, lpfc_aer_support);
+	lpfc_sriov_nr_virtfn_init(phba, lpfc_sriov_nr_virtfn);
 	lpfc_suppress_link_up_init(phba, lpfc_suppress_link_up);
 	lpfc_iocb_cnt_init(phba, lpfc_iocb_cnt);
 	phba->cfg_enable_dss = 1;
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index 853e5042f39c..7fb0ba4cbfa7 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -23,6 +23,7 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
+#include <linux/list.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_host.h>
@@ -79,8 +80,7 @@ struct lpfc_bsg_iocb {
 struct lpfc_bsg_mbox {
 	LPFC_MBOXQ_t *pmboxq;
 	MAILBOX_t *mb;
-	struct lpfc_dmabuf *rxbmp; /* for BIU diags */
-	struct lpfc_dmabufext *dmp; /* for BIU diags */
+	struct lpfc_dmabuf *dmabuffers; /* for BIU diags */
 	uint8_t *ext; /* extended mailbox data */
 	uint32_t mbOffset; /* from app */
 	uint32_t inExtWLen; /* from app */
@@ -332,6 +332,8 @@ lpfc_bsg_send_mgmt_cmd(struct fc_bsg_job *job)
 	cmd->ulpLe = 1;
 	cmd->ulpClass = CLASS3;
 	cmd->ulpContext = ndlp->nlp_rpi;
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		cmd->ulpContext = phba->sli4_hba.rpi_ids[ndlp->nlp_rpi];
 	cmd->ulpOwner = OWN_CHIP;
 	cmdiocbq->vport = phba->pport;
 	cmdiocbq->context3 = bmp;
@@ -1336,6 +1338,10 @@ lpfc_issue_ct_rsp(struct lpfc_hba *phba, struct fc_bsg_job *job, uint32_t tag,
 		}
 
 		icmd->un.ulpWord[3] = ndlp->nlp_rpi;
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			icmd->ulpContext =
+				phba->sli4_hba.rpi_ids[ndlp->nlp_rpi];
+
 		/* The exchange is done, mark the entry as invalid */
 		phba->ct_ctx[tag].flags &= ~UNSOL_VALID;
 	} else
@@ -1463,11 +1469,91 @@ send_mgmt_rsp_exit:
 }
 
 /**
- * lpfc_bsg_diag_mode - process a LPFC_BSG_VENDOR_DIAG_MODE bsg vendor command
+ * lpfc_bsg_diag_mode_enter - process preparing into device diag loopback mode
+ * @phba: Pointer to HBA context object.
  * @job: LPFC_BSG_VENDOR_DIAG_MODE
  *
- * This function is responsible for placing a port into diagnostic loopback
- * mode in order to perform a diagnostic loopback test.
+ * This function is responsible for preparing driver for diag loopback
+ * on device.
+ */
+static int
+lpfc_bsg_diag_mode_enter(struct lpfc_hba *phba, struct fc_bsg_job *job)
+{
+	struct lpfc_vport **vports;
+	struct Scsi_Host *shost;
+	struct lpfc_sli *psli;
+	struct lpfc_sli_ring *pring;
+	int i = 0;
+
+	psli = &phba->sli;
+	if (!psli)
+		return -ENODEV;
+
+	pring = &psli->ring[LPFC_FCP_RING];
+	if (!pring)
+		return -ENODEV;
+
+	if ((phba->link_state == LPFC_HBA_ERROR) ||
+	    (psli->sli_flag & LPFC_BLOCK_MGMT_IO) ||
+	    (!(psli->sli_flag & LPFC_SLI_ACTIVE)))
+		return -EACCES;
+
+	vports = lpfc_create_vport_work_array(phba);
+	if (vports) {
+		for (i = 0; i <= phba->max_vpi && vports[i] != NULL; i++) {
+			shost = lpfc_shost_from_vport(vports[i]);
+			scsi_block_requests(shost);
+		}
+		lpfc_destroy_vport_work_array(phba, vports);
+	} else {
+		shost = lpfc_shost_from_vport(phba->pport);
+		scsi_block_requests(shost);
+	}
+
+	while (pring->txcmplq_cnt) {
+		if (i++ > 500)  /* wait up to 5 seconds */
+			break;
+		msleep(10);
+	}
+	return 0;
+}
+
+/**
+ * lpfc_bsg_diag_mode_exit - exit process from device diag loopback mode
+ * @phba: Pointer to HBA context object.
+ * @job: LPFC_BSG_VENDOR_DIAG_MODE
+ *
+ * This function is responsible for driver exit processing of setting up
+ * diag loopback mode on device.
+ */
+static void
+lpfc_bsg_diag_mode_exit(struct lpfc_hba *phba)
+{
+	struct Scsi_Host *shost;
+	struct lpfc_vport **vports;
+	int i;
+
+	vports = lpfc_create_vport_work_array(phba);
+	if (vports) {
+		for (i = 0; i <= phba->max_vpi && vports[i] != NULL; i++) {
+			shost = lpfc_shost_from_vport(vports[i]);
+			scsi_unblock_requests(shost);
+		}
+		lpfc_destroy_vport_work_array(phba, vports);
+	} else {
+		shost = lpfc_shost_from_vport(phba->pport);
+		scsi_unblock_requests(shost);
+	}
+	return;
+}
+
+/**
+ * lpfc_sli3_bsg_diag_loopback_mode - process an sli3 bsg vendor command
+ * @phba: Pointer to HBA context object.
+ * @job: LPFC_BSG_VENDOR_DIAG_MODE
+ *
+ * This function is responsible for placing an sli3  port into diagnostic
+ * loopback mode in order to perform a diagnostic loopback test.
  * All new scsi requests are blocked, a small delay is used to allow the
  * scsi requests to complete then the link is brought down. If the link is
  * is placed in loopback mode then scsi requests are again allowed
@@ -1475,17 +1561,11 @@ send_mgmt_rsp_exit:
  * All of this is done in-line.
  */
 static int
-lpfc_bsg_diag_mode(struct fc_bsg_job *job)
+lpfc_sli3_bsg_diag_loopback_mode(struct lpfc_hba *phba, struct fc_bsg_job *job)
 {
-	struct Scsi_Host *shost = job->shost;
-	struct lpfc_vport *vport = (struct lpfc_vport *)job->shost->hostdata;
-	struct lpfc_hba *phba = vport->phba;
 	struct diag_mode_set *loopback_mode;
-	struct lpfc_sli *psli = &phba->sli;
-	struct lpfc_sli_ring *pring = &psli->ring[LPFC_FCP_RING];
 	uint32_t link_flags;
 	uint32_t timeout;
-	struct lpfc_vport **vports;
 	LPFC_MBOXQ_t *pmboxq;
 	int mbxstatus;
 	int i = 0;
@@ -1494,53 +1574,33 @@ lpfc_bsg_diag_mode(struct fc_bsg_job *job)
 	/* no data to return just the return code */
 	job->reply->reply_payload_rcv_len = 0;
 
-	if (job->request_len <
-	    sizeof(struct fc_bsg_request) + sizeof(struct diag_mode_set)) {
+	if (job->request_len < sizeof(struct fc_bsg_request) +
+	    sizeof(struct diag_mode_set)) {
 		lpfc_printf_log(phba, KERN_WARNING, LOG_LIBDFC,
-				"2738 Received DIAG MODE request below minimum "
-				"size\n");
+				"2738 Received DIAG MODE request size:%d "
+				"below the minimum size:%d\n",
+				job->request_len,
+				(int)(sizeof(struct fc_bsg_request) +
+				sizeof(struct diag_mode_set)));
 		rc = -EINVAL;
 		goto job_error;
 	}
 
+	rc = lpfc_bsg_diag_mode_enter(phba, job);
+	if (rc)
+		goto job_error;
+
+	/* bring the link to diagnostic mode */
 	loopback_mode = (struct diag_mode_set *)
 		job->request->rqst_data.h_vendor.vendor_cmd;
 	link_flags = loopback_mode->type;
 	timeout = loopback_mode->timeout * 100;
 
-	if ((phba->link_state == LPFC_HBA_ERROR) ||
-	    (psli->sli_flag & LPFC_BLOCK_MGMT_IO) ||
-	    (!(psli->sli_flag & LPFC_SLI_ACTIVE))) {
-		rc = -EACCES;
-		goto job_error;
-	}
-
 	pmboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!pmboxq) {
 		rc = -ENOMEM;
-		goto job_error;
-	}
-
-	vports = lpfc_create_vport_work_array(phba);
-	if (vports) {
-		for (i = 0; i <= phba->max_vpi && vports[i] != NULL; i++) {
-			shost = lpfc_shost_from_vport(vports[i]);
-			scsi_block_requests(shost);
-		}
-
-		lpfc_destroy_vport_work_array(phba, vports);
-	} else {
-		shost = lpfc_shost_from_vport(phba->pport);
-		scsi_block_requests(shost);
+		goto loopback_mode_exit;
 	}
-
-	while (pring->txcmplq_cnt) {
-		if (i++ > 500)	/* wait up to 5 seconds */
-			break;
-
-		msleep(10);
-	}
-
 	memset((void *)pmboxq, 0, sizeof(LPFC_MBOXQ_t));
 	pmboxq->u.mb.mbxCommand = MBX_DOWN_LINK;
 	pmboxq->u.mb.mbxOwner = OWN_HOST;
@@ -1594,22 +1654,186 @@ lpfc_bsg_diag_mode(struct fc_bsg_job *job)
 		rc = -ENODEV;
 
 loopback_mode_exit:
-	vports = lpfc_create_vport_work_array(phba);
-	if (vports) {
-		for (i = 0; i <= phba->max_vpi && vports[i] != NULL; i++) {
-			shost = lpfc_shost_from_vport(vports[i]);
-			scsi_unblock_requests(shost);
+	lpfc_bsg_diag_mode_exit(phba);
+
+	/*
+	 * Let SLI layer release mboxq if mbox command completed after timeout.
+	 */
+	if (mbxstatus != MBX_TIMEOUT)
+		mempool_free(pmboxq, phba->mbox_mem_pool);
+
+job_error:
+	/* make error code available to userspace */
+	job->reply->result = rc;
+	/* complete the job back to userspace if no error */
+	if (rc == 0)
+		job->job_done(job);
+	return rc;
+}
+
+/**
+ * lpfc_sli4_bsg_set_link_diag_state - set sli4 link diag state
+ * @phba: Pointer to HBA context object.
+ * @diag: Flag for set link to diag or nomral operation state.
+ *
+ * This function is responsible for issuing a sli4 mailbox command for setting
+ * link to either diag state or normal operation state.
+ */
+static int
+lpfc_sli4_bsg_set_link_diag_state(struct lpfc_hba *phba, uint32_t diag)
+{
+	LPFC_MBOXQ_t *pmboxq;
+	struct lpfc_mbx_set_link_diag_state *link_diag_state;
+	uint32_t req_len, alloc_len;
+	int mbxstatus = MBX_SUCCESS, rc;
+
+	pmboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!pmboxq)
+		return -ENOMEM;
+
+	req_len = (sizeof(struct lpfc_mbx_set_link_diag_state) -
+		   sizeof(struct lpfc_sli4_cfg_mhdr));
+	alloc_len = lpfc_sli4_config(phba, pmboxq, LPFC_MBOX_SUBSYSTEM_FCOE,
+				LPFC_MBOX_OPCODE_FCOE_LINK_DIAG_STATE,
+				req_len, LPFC_SLI4_MBX_EMBED);
+	if (alloc_len != req_len) {
+		rc = -ENOMEM;
+		goto link_diag_state_set_out;
+	}
+	link_diag_state = &pmboxq->u.mqe.un.link_diag_state;
+	bf_set(lpfc_mbx_set_diag_state_link_num, &link_diag_state->u.req,
+	       phba->sli4_hba.link_state.number);
+	bf_set(lpfc_mbx_set_diag_state_link_type, &link_diag_state->u.req,
+	       phba->sli4_hba.link_state.type);
+	if (diag)
+		bf_set(lpfc_mbx_set_diag_state_diag,
+		       &link_diag_state->u.req, 1);
+	else
+		bf_set(lpfc_mbx_set_diag_state_diag,
+		       &link_diag_state->u.req, 0);
+
+	mbxstatus = lpfc_sli_issue_mbox_wait(phba, pmboxq, LPFC_MBOX_TMO);
+
+	if ((mbxstatus == MBX_SUCCESS) && (pmboxq->u.mb.mbxStatus == 0))
+		rc = 0;
+	else
+		rc = -ENODEV;
+
+link_diag_state_set_out:
+	if (pmboxq && (mbxstatus != MBX_TIMEOUT))
+		mempool_free(pmboxq, phba->mbox_mem_pool);
+
+	return rc;
+}
+
+/**
+ * lpfc_sli4_bsg_diag_loopback_mode - process an sli4 bsg vendor command
+ * @phba: Pointer to HBA context object.
+ * @job: LPFC_BSG_VENDOR_DIAG_MODE
+ *
+ * This function is responsible for placing an sli4 port into diagnostic
+ * loopback mode in order to perform a diagnostic loopback test.
+ */
+static int
+lpfc_sli4_bsg_diag_loopback_mode(struct lpfc_hba *phba, struct fc_bsg_job *job)
+{
+	struct diag_mode_set *loopback_mode;
+	uint32_t link_flags, timeout, req_len, alloc_len;
+	struct lpfc_mbx_set_link_diag_loopback *link_diag_loopback;
+	LPFC_MBOXQ_t *pmboxq = NULL;
+	int mbxstatus, i, rc = 0;
+
+	/* no data to return just the return code */
+	job->reply->reply_payload_rcv_len = 0;
+
+	if (job->request_len < sizeof(struct fc_bsg_request) +
+	    sizeof(struct diag_mode_set)) {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_LIBDFC,
+				"3011 Received DIAG MODE request size:%d "
+				"below the minimum size:%d\n",
+				job->request_len,
+				(int)(sizeof(struct fc_bsg_request) +
+				sizeof(struct diag_mode_set)));
+		rc = -EINVAL;
+		goto job_error;
+	}
+
+	rc = lpfc_bsg_diag_mode_enter(phba, job);
+	if (rc)
+		goto job_error;
+
+	/* bring the link to diagnostic mode */
+	loopback_mode = (struct diag_mode_set *)
+		job->request->rqst_data.h_vendor.vendor_cmd;
+	link_flags = loopback_mode->type;
+	timeout = loopback_mode->timeout * 100;
+
+	rc = lpfc_sli4_bsg_set_link_diag_state(phba, 1);
+	if (rc)
+		goto loopback_mode_exit;
+
+	/* wait for link down before proceeding */
+	i = 0;
+	while (phba->link_state != LPFC_LINK_DOWN) {
+		if (i++ > timeout) {
+			rc = -ETIMEDOUT;
+			goto loopback_mode_exit;
+		}
+		msleep(10);
+	}
+	/* set up loopback mode */
+	pmboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!pmboxq) {
+		rc = -ENOMEM;
+		goto loopback_mode_exit;
+	}
+	req_len = (sizeof(struct lpfc_mbx_set_link_diag_loopback) -
+		   sizeof(struct lpfc_sli4_cfg_mhdr));
+	alloc_len = lpfc_sli4_config(phba, pmboxq, LPFC_MBOX_SUBSYSTEM_FCOE,
+				LPFC_MBOX_OPCODE_FCOE_LINK_DIAG_LOOPBACK,
+				req_len, LPFC_SLI4_MBX_EMBED);
+	if (alloc_len != req_len) {
+		rc = -ENOMEM;
+		goto loopback_mode_exit;
+	}
+	link_diag_loopback = &pmboxq->u.mqe.un.link_diag_loopback;
+	bf_set(lpfc_mbx_set_diag_state_link_num,
+	       &link_diag_loopback->u.req, phba->sli4_hba.link_state.number);
+	bf_set(lpfc_mbx_set_diag_state_link_type,
+	       &link_diag_loopback->u.req, phba->sli4_hba.link_state.type);
+	if (link_flags == INTERNAL_LOOP_BACK)
+		bf_set(lpfc_mbx_set_diag_lpbk_type,
+		       &link_diag_loopback->u.req,
+		       LPFC_DIAG_LOOPBACK_TYPE_INTERNAL);
+	else
+		bf_set(lpfc_mbx_set_diag_lpbk_type,
+		       &link_diag_loopback->u.req,
+		       LPFC_DIAG_LOOPBACK_TYPE_EXTERNAL);
+
+	mbxstatus = lpfc_sli_issue_mbox_wait(phba, pmboxq, LPFC_MBOX_TMO);
+	if ((mbxstatus != MBX_SUCCESS) || (pmboxq->u.mb.mbxStatus))
+		rc = -ENODEV;
+	else {
+		phba->link_flag |= LS_LOOPBACK_MODE;
+		/* wait for the link attention interrupt */
+		msleep(100);
+		i = 0;
+		while (phba->link_state != LPFC_HBA_READY) {
+			if (i++ > timeout) {
+				rc = -ETIMEDOUT;
+				break;
+			}
+			msleep(10);
 		}
-		lpfc_destroy_vport_work_array(phba, vports);
-	} else {
-		shost = lpfc_shost_from_vport(phba->pport);
-		scsi_unblock_requests(shost);
 	}
 
+loopback_mode_exit:
+	lpfc_bsg_diag_mode_exit(phba);
+
 	/*
 	 * Let SLI layer release mboxq if mbox command completed after timeout.
 	 */
-	if (mbxstatus != MBX_TIMEOUT)
+	if (pmboxq && (mbxstatus != MBX_TIMEOUT))
 		mempool_free(pmboxq, phba->mbox_mem_pool);
 
 job_error:
@@ -1622,6 +1846,234 @@ job_error:
 }
 
 /**
+ * lpfc_bsg_diag_loopback_mode - bsg vendor command for diag loopback mode
+ * @job: LPFC_BSG_VENDOR_DIAG_MODE
+ *
+ * This function is responsible for responding to check and dispatch bsg diag
+ * command from the user to proper driver action routines.
+ */
+static int
+lpfc_bsg_diag_loopback_mode(struct fc_bsg_job *job)
+{
+	struct Scsi_Host *shost;
+	struct lpfc_vport *vport;
+	struct lpfc_hba *phba;
+	int rc;
+
+	shost = job->shost;
+	if (!shost)
+		return -ENODEV;
+	vport = (struct lpfc_vport *)job->shost->hostdata;
+	if (!vport)
+		return -ENODEV;
+	phba = vport->phba;
+	if (!phba)
+		return -ENODEV;
+
+	if (phba->sli_rev < LPFC_SLI_REV4)
+		rc = lpfc_sli3_bsg_diag_loopback_mode(phba, job);
+	else if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) ==
+		 LPFC_SLI_INTF_IF_TYPE_2)
+		rc = lpfc_sli4_bsg_diag_loopback_mode(phba, job);
+	else
+		rc = -ENODEV;
+
+	return rc;
+
+}
+
+/**
+ * lpfc_sli4_bsg_diag_mode_end - sli4 bsg vendor command for ending diag mode
+ * @job: LPFC_BSG_VENDOR_DIAG_MODE_END
+ *
+ * This function is responsible for responding to check and dispatch bsg diag
+ * command from the user to proper driver action routines.
+ */
+static int
+lpfc_sli4_bsg_diag_mode_end(struct fc_bsg_job *job)
+{
+	struct Scsi_Host *shost;
+	struct lpfc_vport *vport;
+	struct lpfc_hba *phba;
+	int rc;
+
+	shost = job->shost;
+	if (!shost)
+		return -ENODEV;
+	vport = (struct lpfc_vport *)job->shost->hostdata;
+	if (!vport)
+		return -ENODEV;
+	phba = vport->phba;
+	if (!phba)
+		return -ENODEV;
+
+	if (phba->sli_rev < LPFC_SLI_REV4)
+		return -ENODEV;
+	if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
+	    LPFC_SLI_INTF_IF_TYPE_2)
+		return -ENODEV;
+
+	rc = lpfc_sli4_bsg_set_link_diag_state(phba, 0);
+
+	if (!rc)
+		rc = phba->lpfc_hba_init_link(phba, MBX_NOWAIT);
+
+	return rc;
+}
+
+/**
+ * lpfc_sli4_bsg_link_diag_test - sli4 bsg vendor command for diag link test
+ * @job: LPFC_BSG_VENDOR_DIAG_LINK_TEST
+ *
+ * This function is to perform SLI4 diag link test request from the user
+ * applicaiton.
+ */
+static int
+lpfc_sli4_bsg_link_diag_test(struct fc_bsg_job *job)
+{
+	struct Scsi_Host *shost;
+	struct lpfc_vport *vport;
+	struct lpfc_hba *phba;
+	LPFC_MBOXQ_t *pmboxq;
+	struct sli4_link_diag *link_diag_test_cmd;
+	uint32_t req_len, alloc_len;
+	uint32_t timeout;
+	struct lpfc_mbx_run_link_diag_test *run_link_diag_test;
+	union lpfc_sli4_cfg_shdr *shdr;
+	uint32_t shdr_status, shdr_add_status;
+	struct diag_status *diag_status_reply;
+	int mbxstatus, rc = 0;
+
+	shost = job->shost;
+	if (!shost) {
+		rc = -ENODEV;
+		goto job_error;
+	}
+	vport = (struct lpfc_vport *)job->shost->hostdata;
+	if (!vport) {
+		rc = -ENODEV;
+		goto job_error;
+	}
+	phba = vport->phba;
+	if (!phba) {
+		rc = -ENODEV;
+		goto job_error;
+	}
+
+	if (phba->sli_rev < LPFC_SLI_REV4) {
+		rc = -ENODEV;
+		goto job_error;
+	}
+	if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
+	    LPFC_SLI_INTF_IF_TYPE_2) {
+		rc = -ENODEV;
+		goto job_error;
+	}
+
+	if (job->request_len < sizeof(struct fc_bsg_request) +
+	    sizeof(struct sli4_link_diag)) {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_LIBDFC,
+				"3013 Received LINK DIAG TEST request "
+				" size:%d below the minimum size:%d\n",
+				job->request_len,
+				(int)(sizeof(struct fc_bsg_request) +
+				sizeof(struct sli4_link_diag)));
+		rc = -EINVAL;
+		goto job_error;
+	}
+
+	rc = lpfc_bsg_diag_mode_enter(phba, job);
+	if (rc)
+		goto job_error;
+
+	link_diag_test_cmd = (struct sli4_link_diag *)
+			 job->request->rqst_data.h_vendor.vendor_cmd;
+	timeout = link_diag_test_cmd->timeout * 100;
+
+	rc = lpfc_sli4_bsg_set_link_diag_state(phba, 1);
+
+	if (rc)
+		goto job_error;
+
+	pmboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!pmboxq) {
+		rc = -ENOMEM;
+		goto link_diag_test_exit;
+	}
+
+	req_len = (sizeof(struct lpfc_mbx_set_link_diag_state) -
+		   sizeof(struct lpfc_sli4_cfg_mhdr));
+	alloc_len = lpfc_sli4_config(phba, pmboxq, LPFC_MBOX_SUBSYSTEM_FCOE,
+				     LPFC_MBOX_OPCODE_FCOE_LINK_DIAG_STATE,
+				     req_len, LPFC_SLI4_MBX_EMBED);
+	if (alloc_len != req_len) {
+		rc = -ENOMEM;
+		goto link_diag_test_exit;
+	}
+	run_link_diag_test = &pmboxq->u.mqe.un.link_diag_test;
+	bf_set(lpfc_mbx_run_diag_test_link_num, &run_link_diag_test->u.req,
+	       phba->sli4_hba.link_state.number);
+	bf_set(lpfc_mbx_run_diag_test_link_type, &run_link_diag_test->u.req,
+	       phba->sli4_hba.link_state.type);
+	bf_set(lpfc_mbx_run_diag_test_test_id, &run_link_diag_test->u.req,
+	       link_diag_test_cmd->test_id);
+	bf_set(lpfc_mbx_run_diag_test_loops, &run_link_diag_test->u.req,
+	       link_diag_test_cmd->loops);
+	bf_set(lpfc_mbx_run_diag_test_test_ver, &run_link_diag_test->u.req,
+	       link_diag_test_cmd->test_version);
+	bf_set(lpfc_mbx_run_diag_test_err_act, &run_link_diag_test->u.req,
+	       link_diag_test_cmd->error_action);
+
+	mbxstatus = lpfc_sli_issue_mbox(phba, pmboxq, MBX_POLL);
+
+	shdr = (union lpfc_sli4_cfg_shdr *)
+		&pmboxq->u.mqe.un.sli4_config.header.cfg_shdr;
+	shdr_status = bf_get(lpfc_mbox_hdr_status, &shdr->response);
+	shdr_add_status = bf_get(lpfc_mbox_hdr_add_status, &shdr->response);
+	if (shdr_status || shdr_add_status || mbxstatus) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC,
+				"3010 Run link diag test mailbox failed with "
+				"mbx_status x%x status x%x, add_status x%x\n",
+				mbxstatus, shdr_status, shdr_add_status);
+	}
+
+	diag_status_reply = (struct diag_status *)
+			    job->reply->reply_data.vendor_reply.vendor_rsp;
+
+	if (job->reply_len <
+	    sizeof(struct fc_bsg_request) + sizeof(struct diag_status)) {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_LIBDFC,
+				"3012 Received Run link diag test reply "
+				"below minimum size (%d): reply_len:%d\n",
+				(int)(sizeof(struct fc_bsg_request) +
+				sizeof(struct diag_status)),
+				job->reply_len);
+		rc = -EINVAL;
+		goto job_error;
+	}
+
+	diag_status_reply->mbox_status = mbxstatus;
+	diag_status_reply->shdr_status = shdr_status;
+	diag_status_reply->shdr_add_status = shdr_add_status;
+
+link_diag_test_exit:
+	rc = lpfc_sli4_bsg_set_link_diag_state(phba, 0);
+
+	if (pmboxq)
+		mempool_free(pmboxq, phba->mbox_mem_pool);
+
+	lpfc_bsg_diag_mode_exit(phba);
+
+job_error:
+	/* make error code available to userspace */
+	job->reply->result = rc;
+	/* complete the job back to userspace if no error */
+	if (rc == 0)
+		job->job_done(job);
+	return rc;
+}
+
+/**
  * lpfcdiag_loop_self_reg - obtains a remote port login id
  * @phba: Pointer to HBA context object
  * @rpi: Pointer to a remote port login id
@@ -1851,6 +2303,86 @@ err_get_xri_exit:
 }
 
 /**
+ * lpfc_bsg_dma_page_alloc - allocate a bsg mbox page sized dma buffers
+ * @phba: Pointer to HBA context object
+ *
+ * This function allocates BSG_MBOX_SIZE (4KB) page size dma buffer and.
+ * retruns the pointer to the buffer.
+ **/
+static struct lpfc_dmabuf *
+lpfc_bsg_dma_page_alloc(struct lpfc_hba *phba)
+{
+	struct lpfc_dmabuf *dmabuf;
+	struct pci_dev *pcidev = phba->pcidev;
+
+	/* allocate dma buffer struct */
+	dmabuf = kmalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
+	if (!dmabuf)
+		return NULL;
+
+	INIT_LIST_HEAD(&dmabuf->list);
+
+	/* now, allocate dma buffer */
+	dmabuf->virt = dma_alloc_coherent(&pcidev->dev, BSG_MBOX_SIZE,
+					  &(dmabuf->phys), GFP_KERNEL);
+
+	if (!dmabuf->virt) {
+		kfree(dmabuf);
+		return NULL;
+	}
+	memset((uint8_t *)dmabuf->virt, 0, BSG_MBOX_SIZE);
+
+	return dmabuf;
+}
+
+/**
+ * lpfc_bsg_dma_page_free - free a bsg mbox page sized dma buffer
+ * @phba: Pointer to HBA context object.
+ * @dmabuf: Pointer to the bsg mbox page sized dma buffer descriptor.
+ *
+ * This routine just simply frees a dma buffer and its associated buffer
+ * descriptor referred by @dmabuf.
+ **/
+static void
+lpfc_bsg_dma_page_free(struct lpfc_hba *phba, struct lpfc_dmabuf *dmabuf)
+{
+	struct pci_dev *pcidev = phba->pcidev;
+
+	if (!dmabuf)
+		return;
+
+	if (dmabuf->virt)
+		dma_free_coherent(&pcidev->dev, BSG_MBOX_SIZE,
+				  dmabuf->virt, dmabuf->phys);
+	kfree(dmabuf);
+	return;
+}
+
+/**
+ * lpfc_bsg_dma_page_list_free - free a list of bsg mbox page sized dma buffers
+ * @phba: Pointer to HBA context object.
+ * @dmabuf_list: Pointer to a list of bsg mbox page sized dma buffer descs.
+ *
+ * This routine just simply frees all dma buffers and their associated buffer
+ * descriptors referred by @dmabuf_list.
+ **/
+static void
+lpfc_bsg_dma_page_list_free(struct lpfc_hba *phba,
+			    struct list_head *dmabuf_list)
+{
+	struct lpfc_dmabuf *dmabuf, *next_dmabuf;
+
+	if (list_empty(dmabuf_list))
+		return;
+
+	list_for_each_entry_safe(dmabuf, next_dmabuf, dmabuf_list, list) {
+		list_del_init(&dmabuf->list);
+		lpfc_bsg_dma_page_free(phba, dmabuf);
+	}
+	return;
+}
+
+/**
  * diag_cmd_data_alloc - fills in a bde struct with dma buffers
  * @phba: Pointer to HBA context object
  * @bpl: Pointer to 64 bit bde structure
@@ -2067,7 +2599,7 @@ err_post_rxbufs_exit:
 }
 
 /**
- * lpfc_bsg_diag_test - with a port in loopback issues a Ct cmd to itself
+ * lpfc_bsg_diag_loopback_run - run loopback on a port by issue ct cmd to itself
  * @job: LPFC_BSG_VENDOR_DIAG_TEST fc_bsg_job
  *
  * This function receives a user data buffer to be transmitted and received on
@@ -2086,7 +2618,7 @@ err_post_rxbufs_exit:
  * of loopback mode.
  **/
 static int
-lpfc_bsg_diag_test(struct fc_bsg_job *job)
+lpfc_bsg_diag_loopback_run(struct fc_bsg_job *job)
 {
 	struct lpfc_vport *vport = (struct lpfc_vport *)job->shost->hostdata;
 	struct lpfc_hba *phba = vport->phba;
@@ -2411,7 +2943,7 @@ job_error:
 }
 
 /**
- * lpfc_bsg_wake_mbox_wait - lpfc_bsg_issue_mbox mbox completion handler
+ * lpfc_bsg_issue_mbox_cmpl - lpfc_bsg_issue_mbox mbox completion handler
  * @phba: Pointer to HBA context object.
  * @pmboxq: Pointer to mailbox command.
  *
@@ -2422,15 +2954,13 @@ job_error:
  * of the mailbox.
  **/
 void
-lpfc_bsg_wake_mbox_wait(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
+lpfc_bsg_issue_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 {
 	struct bsg_job_data *dd_data;
 	struct fc_bsg_job *job;
-	struct lpfc_mbx_nembed_cmd *nembed_sge;
 	uint32_t size;
 	unsigned long flags;
-	uint8_t *to;
-	uint8_t *from;
+	uint8_t *pmb, *pmb_buf;
 
 	spin_lock_irqsave(&phba->ct_ev_lock, flags);
 	dd_data = pmboxq->context1;
@@ -2440,62 +2970,21 @@ lpfc_bsg_wake_mbox_wait(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 		return;
 	}
 
-	/* build the outgoing buffer to do an sg copy
-	 * the format is the response mailbox followed by any extended
-	 * mailbox data
+	/*
+	 * The outgoing buffer is readily referred from the dma buffer,
+	 * just need to get header part from mailboxq structure.
 	 */
-	from = (uint8_t *)&pmboxq->u.mb;
-	to = (uint8_t *)dd_data->context_un.mbox.mb;
-	memcpy(to, from, sizeof(MAILBOX_t));
-	if (pmboxq->u.mb.mbxStatus == MBX_SUCCESS) {
-		/* copy the extended data if any, count is in words */
-		if (dd_data->context_un.mbox.outExtWLen) {
-			from = (uint8_t *)dd_data->context_un.mbox.ext;
-			to += sizeof(MAILBOX_t);
-			size = dd_data->context_un.mbox.outExtWLen *
-					sizeof(uint32_t);
-			memcpy(to, from, size);
-		} else if (pmboxq->u.mb.mbxCommand == MBX_RUN_BIU_DIAG64) {
-			from = (uint8_t *)dd_data->context_un.mbox.
-						dmp->dma.virt;
-			to += sizeof(MAILBOX_t);
-			size = dd_data->context_un.mbox.dmp->size;
-			memcpy(to, from, size);
-		} else if ((phba->sli_rev == LPFC_SLI_REV4) &&
-			(pmboxq->u.mb.mbxCommand == MBX_DUMP_MEMORY)) {
-			from = (uint8_t *)dd_data->context_un.mbox.dmp->dma.
-						virt;
-			to += sizeof(MAILBOX_t);
-			size = pmboxq->u.mb.un.varWords[5];
-			memcpy(to, from, size);
-		} else if ((phba->sli_rev == LPFC_SLI_REV4) &&
-			(pmboxq->u.mb.mbxCommand == MBX_SLI4_CONFIG)) {
-			nembed_sge = (struct lpfc_mbx_nembed_cmd *)
-					&pmboxq->u.mb.un.varWords[0];
-
-			from = (uint8_t *)dd_data->context_un.mbox.dmp->dma.
-						virt;
-			to += sizeof(MAILBOX_t);
-			size = nembed_sge->sge[0].length;
-			memcpy(to, from, size);
-		} else if (pmboxq->u.mb.mbxCommand == MBX_READ_EVENT_LOG) {
-			from = (uint8_t *)dd_data->context_un.
-						mbox.dmp->dma.virt;
-			to += sizeof(MAILBOX_t);
-			size = dd_data->context_un.mbox.dmp->size;
-			memcpy(to, from, size);
-		}
-	}
+	pmb = (uint8_t *)&pmboxq->u.mb;
+	pmb_buf = (uint8_t *)dd_data->context_un.mbox.mb;
+	memcpy(pmb_buf, pmb, sizeof(MAILBOX_t));
 
-	from = (uint8_t *)dd_data->context_un.mbox.mb;
 	job = dd_data->context_un.mbox.set_job;
 	if (job) {
 		size = job->reply_payload.payload_len;
 		job->reply->reply_payload_rcv_len =
 			sg_copy_from_buffer(job->reply_payload.sg_list,
-					job->reply_payload.sg_cnt,
-					from, size);
-		job->reply->result = 0;
+					    job->reply_payload.sg_cnt,
+					    pmb_buf, size);
 		/* need to hold the lock until we set job->dd_data to NULL
 		 * to hold off the timeout handler returning to the mid-layer
 		 * while we are still processing the job.
@@ -2503,28 +2992,19 @@ lpfc_bsg_wake_mbox_wait(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 		job->dd_data = NULL;
 		dd_data->context_un.mbox.set_job = NULL;
 		spin_unlock_irqrestore(&phba->ct_ev_lock, flags);
-		job->job_done(job);
 	} else {
 		dd_data->context_un.mbox.set_job = NULL;
 		spin_unlock_irqrestore(&phba->ct_ev_lock, flags);
 	}
 
-	kfree(dd_data->context_un.mbox.mb);
 	mempool_free(dd_data->context_un.mbox.pmboxq, phba->mbox_mem_pool);
-	kfree(dd_data->context_un.mbox.ext);
-	if (dd_data->context_un.mbox.dmp) {
-		dma_free_coherent(&phba->pcidev->dev,
-			dd_data->context_un.mbox.dmp->size,
-			dd_data->context_un.mbox.dmp->dma.virt,
-			dd_data->context_un.mbox.dmp->dma.phys);
-		kfree(dd_data->context_un.mbox.dmp);
-	}
-	if (dd_data->context_un.mbox.rxbmp) {
-		lpfc_mbuf_free(phba, dd_data->context_un.mbox.rxbmp->virt,
-			dd_data->context_un.mbox.rxbmp->phys);
-		kfree(dd_data->context_un.mbox.rxbmp);
-	}
+	lpfc_bsg_dma_page_free(phba, dd_data->context_un.mbox.dmabuffers);
 	kfree(dd_data);
+
+	if (job) {
+		job->reply->result = 0;
+		job->job_done(job);
+	}
 	return;
 }
 
@@ -2619,6 +3099,1006 @@ static int lpfc_bsg_check_cmd_access(struct lpfc_hba *phba,
 }
 
 /**
+ * lpfc_bsg_mbox_ext_cleanup - clean up context of multi-buffer mbox session
+ * @phba: Pointer to HBA context object.
+ *
+ * This is routine clean up and reset BSG handling of multi-buffer mbox
+ * command session.
+ **/
+static void
+lpfc_bsg_mbox_ext_session_reset(struct lpfc_hba *phba)
+{
+	if (phba->mbox_ext_buf_ctx.state == LPFC_BSG_MBOX_IDLE)
+		return;
+
+	/* free all memory, including dma buffers */
+	lpfc_bsg_dma_page_list_free(phba,
+				    &phba->mbox_ext_buf_ctx.ext_dmabuf_list);
+	lpfc_bsg_dma_page_free(phba, phba->mbox_ext_buf_ctx.mbx_dmabuf);
+	/* multi-buffer write mailbox command pass-through complete */
+	memset((char *)&phba->mbox_ext_buf_ctx, 0,
+	       sizeof(struct lpfc_mbox_ext_buf_ctx));
+	INIT_LIST_HEAD(&phba->mbox_ext_buf_ctx.ext_dmabuf_list);
+
+	return;
+}
+
+/**
+ * lpfc_bsg_issue_mbox_ext_handle_job - job handler for multi-buffer mbox cmpl
+ * @phba: Pointer to HBA context object.
+ * @pmboxq: Pointer to mailbox command.
+ *
+ * This is routine handles BSG job for mailbox commands completions with
+ * multiple external buffers.
+ **/
+static struct fc_bsg_job *
+lpfc_bsg_issue_mbox_ext_handle_job(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
+{
+	struct bsg_job_data *dd_data;
+	struct fc_bsg_job *job;
+	uint8_t *pmb, *pmb_buf;
+	unsigned long flags;
+	uint32_t size;
+	int rc = 0;
+
+	spin_lock_irqsave(&phba->ct_ev_lock, flags);
+	dd_data = pmboxq->context1;
+	/* has the job already timed out? */
+	if (!dd_data) {
+		spin_unlock_irqrestore(&phba->ct_ev_lock, flags);
+		job = NULL;
+		goto job_done_out;
+	}
+
+	/*
+	 * The outgoing buffer is readily referred from the dma buffer,
+	 * just need to get header part from mailboxq structure.
+	 */
+	pmb = (uint8_t *)&pmboxq->u.mb;
+	pmb_buf = (uint8_t *)dd_data->context_un.mbox.mb;
+	memcpy(pmb_buf, pmb, sizeof(MAILBOX_t));
+
+	job = dd_data->context_un.mbox.set_job;
+	if (job) {
+		size = job->reply_payload.payload_len;
+		job->reply->reply_payload_rcv_len =
+			sg_copy_from_buffer(job->reply_payload.sg_list,
+					    job->reply_payload.sg_cnt,
+					    pmb_buf, size);
+		/* result for successful */
+		job->reply->result = 0;
+		job->dd_data = NULL;
+		/* need to hold the lock util we set job->dd_data to NULL
+		 * to hold off the timeout handler from midlayer to take
+		 * any action.
+		 */
+		spin_unlock_irqrestore(&phba->ct_ev_lock, flags);
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2937 SLI_CONFIG ext-buffer maibox command "
+				"(x%x/x%x) complete bsg job done, bsize:%d\n",
+				phba->mbox_ext_buf_ctx.nembType,
+				phba->mbox_ext_buf_ctx.mboxType, size);
+	} else
+		spin_unlock_irqrestore(&phba->ct_ev_lock, flags);
+
+job_done_out:
+	if (!job)
+		lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC,
+				"2938 SLI_CONFIG ext-buffer maibox "
+				"command (x%x/x%x) failure, rc:x%x\n",
+				phba->mbox_ext_buf_ctx.nembType,
+				phba->mbox_ext_buf_ctx.mboxType, rc);
+	/* state change */
+	phba->mbox_ext_buf_ctx.state = LPFC_BSG_MBOX_DONE;
+	kfree(dd_data);
+
+	return job;
+}
+
+/**
+ * lpfc_bsg_issue_read_mbox_ext_cmpl - compl handler for multi-buffer read mbox
+ * @phba: Pointer to HBA context object.
+ * @pmboxq: Pointer to mailbox command.
+ *
+ * This is completion handler function for mailbox read commands with multiple
+ * external buffers.
+ **/
+static void
+lpfc_bsg_issue_read_mbox_ext_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
+{
+	struct fc_bsg_job *job;
+
+	/* handle the BSG job with mailbox command */
+	if (phba->mbox_ext_buf_ctx.state == LPFC_BSG_MBOX_ABTS)
+		pmboxq->u.mb.mbxStatus = MBXERR_ERROR;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+			"2939 SLI_CONFIG ext-buffer rd maibox command "
+			"complete, ctxState:x%x, mbxStatus:x%x\n",
+			phba->mbox_ext_buf_ctx.state, pmboxq->u.mb.mbxStatus);
+
+	job = lpfc_bsg_issue_mbox_ext_handle_job(phba, pmboxq);
+
+	if (pmboxq->u.mb.mbxStatus || phba->mbox_ext_buf_ctx.numBuf == 1)
+		lpfc_bsg_mbox_ext_session_reset(phba);
+
+	/* free base driver mailbox structure memory */
+	mempool_free(pmboxq, phba->mbox_mem_pool);
+
+	/* complete the bsg job if we have it */
+	if (job)
+		job->job_done(job);
+
+	return;
+}
+
+/**
+ * lpfc_bsg_issue_write_mbox_ext_cmpl - cmpl handler for multi-buffer write mbox
+ * @phba: Pointer to HBA context object.
+ * @pmboxq: Pointer to mailbox command.
+ *
+ * This is completion handler function for mailbox write commands with multiple
+ * external buffers.
+ **/
+static void
+lpfc_bsg_issue_write_mbox_ext_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
+{
+	struct fc_bsg_job *job;
+
+	/* handle the BSG job with the mailbox command */
+	if (phba->mbox_ext_buf_ctx.state == LPFC_BSG_MBOX_ABTS)
+		pmboxq->u.mb.mbxStatus = MBXERR_ERROR;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+			"2940 SLI_CONFIG ext-buffer wr maibox command "
+			"complete, ctxState:x%x, mbxStatus:x%x\n",
+			phba->mbox_ext_buf_ctx.state, pmboxq->u.mb.mbxStatus);
+
+	job = lpfc_bsg_issue_mbox_ext_handle_job(phba, pmboxq);
+
+	/* free all memory, including dma buffers */
+	mempool_free(pmboxq, phba->mbox_mem_pool);
+	lpfc_bsg_mbox_ext_session_reset(phba);
+
+	/* complete the bsg job if we have it */
+	if (job)
+		job->job_done(job);
+
+	return;
+}
+
+static void
+lpfc_bsg_sli_cfg_dma_desc_setup(struct lpfc_hba *phba, enum nemb_type nemb_tp,
+				uint32_t index, struct lpfc_dmabuf *mbx_dmabuf,
+				struct lpfc_dmabuf *ext_dmabuf)
+{
+	struct lpfc_sli_config_mbox *sli_cfg_mbx;
+
+	/* pointer to the start of mailbox command */
+	sli_cfg_mbx = (struct lpfc_sli_config_mbox *)mbx_dmabuf->virt;
+
+	if (nemb_tp == nemb_mse) {
+		if (index == 0) {
+			sli_cfg_mbx->un.sli_config_emb0_subsys.
+				mse[index].pa_hi =
+				putPaddrHigh(mbx_dmabuf->phys +
+					     sizeof(MAILBOX_t));
+			sli_cfg_mbx->un.sli_config_emb0_subsys.
+				mse[index].pa_lo =
+				putPaddrLow(mbx_dmabuf->phys +
+					    sizeof(MAILBOX_t));
+			lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+					"2943 SLI_CONFIG(mse)[%d], "
+					"bufLen:%d, addrHi:x%x, addrLo:x%x\n",
+					index,
+					sli_cfg_mbx->un.sli_config_emb0_subsys.
+					mse[index].buf_len,
+					sli_cfg_mbx->un.sli_config_emb0_subsys.
+					mse[index].pa_hi,
+					sli_cfg_mbx->un.sli_config_emb0_subsys.
+					mse[index].pa_lo);
+		} else {
+			sli_cfg_mbx->un.sli_config_emb0_subsys.
+				mse[index].pa_hi =
+				putPaddrHigh(ext_dmabuf->phys);
+			sli_cfg_mbx->un.sli_config_emb0_subsys.
+				mse[index].pa_lo =
+				putPaddrLow(ext_dmabuf->phys);
+			lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+					"2944 SLI_CONFIG(mse)[%d], "
+					"bufLen:%d, addrHi:x%x, addrLo:x%x\n",
+					index,
+					sli_cfg_mbx->un.sli_config_emb0_subsys.
+					mse[index].buf_len,
+					sli_cfg_mbx->un.sli_config_emb0_subsys.
+					mse[index].pa_hi,
+					sli_cfg_mbx->un.sli_config_emb0_subsys.
+					mse[index].pa_lo);
+		}
+	} else {
+		if (index == 0) {
+			sli_cfg_mbx->un.sli_config_emb1_subsys.
+				hbd[index].pa_hi =
+				putPaddrHigh(mbx_dmabuf->phys +
+					     sizeof(MAILBOX_t));
+			sli_cfg_mbx->un.sli_config_emb1_subsys.
+				hbd[index].pa_lo =
+				putPaddrLow(mbx_dmabuf->phys +
+					    sizeof(MAILBOX_t));
+			lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+					"3007 SLI_CONFIG(hbd)[%d], "
+					"bufLen:%d, addrHi:x%x, addrLo:x%x\n",
+				index,
+				bsg_bf_get(lpfc_mbox_sli_config_ecmn_hbd_len,
+				&sli_cfg_mbx->un.
+				sli_config_emb1_subsys.hbd[index]),
+				sli_cfg_mbx->un.sli_config_emb1_subsys.
+				hbd[index].pa_hi,
+				sli_cfg_mbx->un.sli_config_emb1_subsys.
+				hbd[index].pa_lo);
+
+		} else {
+			sli_cfg_mbx->un.sli_config_emb1_subsys.
+				hbd[index].pa_hi =
+				putPaddrHigh(ext_dmabuf->phys);
+			sli_cfg_mbx->un.sli_config_emb1_subsys.
+				hbd[index].pa_lo =
+				putPaddrLow(ext_dmabuf->phys);
+			lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+					"3008 SLI_CONFIG(hbd)[%d], "
+					"bufLen:%d, addrHi:x%x, addrLo:x%x\n",
+				index,
+				bsg_bf_get(lpfc_mbox_sli_config_ecmn_hbd_len,
+				&sli_cfg_mbx->un.
+				sli_config_emb1_subsys.hbd[index]),
+				sli_cfg_mbx->un.sli_config_emb1_subsys.
+				hbd[index].pa_hi,
+				sli_cfg_mbx->un.sli_config_emb1_subsys.
+				hbd[index].pa_lo);
+		}
+	}
+	return;
+}
+
+/**
+ * lpfc_bsg_sli_cfg_mse_read_cmd_ext - sli_config non-embedded mailbox cmd read
+ * @phba: Pointer to HBA context object.
+ * @mb: Pointer to a BSG mailbox object.
+ * @nemb_tp: Enumerate of non-embedded mailbox command type.
+ * @dmabuff: Pointer to a DMA buffer descriptor.
+ *
+ * This routine performs SLI_CONFIG (0x9B) read mailbox command operation with
+ * non-embedded external bufffers.
+ **/
+static int
+lpfc_bsg_sli_cfg_read_cmd_ext(struct lpfc_hba *phba, struct fc_bsg_job *job,
+			      enum nemb_type nemb_tp,
+			      struct lpfc_dmabuf *dmabuf)
+{
+	struct lpfc_sli_config_mbox *sli_cfg_mbx;
+	struct dfc_mbox_req *mbox_req;
+	struct lpfc_dmabuf *curr_dmabuf, *next_dmabuf;
+	uint32_t ext_buf_cnt, ext_buf_index;
+	struct lpfc_dmabuf *ext_dmabuf = NULL;
+	struct bsg_job_data *dd_data = NULL;
+	LPFC_MBOXQ_t *pmboxq = NULL;
+	MAILBOX_t *pmb;
+	uint8_t *pmbx;
+	int rc, i;
+
+	mbox_req =
+	   (struct dfc_mbox_req *)job->request->rqst_data.h_vendor.vendor_cmd;
+
+	/* pointer to the start of mailbox command */
+	sli_cfg_mbx = (struct lpfc_sli_config_mbox *)dmabuf->virt;
+
+	if (nemb_tp == nemb_mse) {
+		ext_buf_cnt = bsg_bf_get(lpfc_mbox_hdr_mse_cnt,
+			&sli_cfg_mbx->un.sli_config_emb0_subsys.sli_config_hdr);
+		if (ext_buf_cnt > LPFC_MBX_SLI_CONFIG_MAX_MSE) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC,
+					"2945 Handled SLI_CONFIG(mse) rd, "
+					"ext_buf_cnt(%d) out of range(%d)\n",
+					ext_buf_cnt,
+					LPFC_MBX_SLI_CONFIG_MAX_MSE);
+			rc = -ERANGE;
+			goto job_error;
+		}
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2941 Handled SLI_CONFIG(mse) rd, "
+				"ext_buf_cnt:%d\n", ext_buf_cnt);
+	} else {
+		/* sanity check on interface type for support */
+		if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
+		    LPFC_SLI_INTF_IF_TYPE_2) {
+			rc = -ENODEV;
+			goto job_error;
+		}
+		/* nemb_tp == nemb_hbd */
+		ext_buf_cnt = sli_cfg_mbx->un.sli_config_emb1_subsys.hbd_count;
+		if (ext_buf_cnt > LPFC_MBX_SLI_CONFIG_MAX_HBD) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC,
+					"2946 Handled SLI_CONFIG(hbd) rd, "
+					"ext_buf_cnt(%d) out of range(%d)\n",
+					ext_buf_cnt,
+					LPFC_MBX_SLI_CONFIG_MAX_HBD);
+			rc = -ERANGE;
+			goto job_error;
+		}
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2942 Handled SLI_CONFIG(hbd) rd, "
+				"ext_buf_cnt:%d\n", ext_buf_cnt);
+	}
+
+	/* reject non-embedded mailbox command with none external buffer */
+	if (ext_buf_cnt == 0) {
+		rc = -EPERM;
+		goto job_error;
+	} else if (ext_buf_cnt > 1) {
+		/* additional external read buffers */
+		for (i = 1; i < ext_buf_cnt; i++) {
+			ext_dmabuf = lpfc_bsg_dma_page_alloc(phba);
+			if (!ext_dmabuf) {
+				rc = -ENOMEM;
+				goto job_error;
+			}
+			list_add_tail(&ext_dmabuf->list,
+				      &phba->mbox_ext_buf_ctx.ext_dmabuf_list);
+		}
+	}
+
+	/* bsg tracking structure */
+	dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL);
+	if (!dd_data) {
+		rc = -ENOMEM;
+		goto job_error;
+	}
+
+	/* mailbox command structure for base driver */
+	pmboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!pmboxq) {
+		rc = -ENOMEM;
+		goto job_error;
+	}
+	memset(pmboxq, 0, sizeof(LPFC_MBOXQ_t));
+
+	/* for the first external buffer */
+	lpfc_bsg_sli_cfg_dma_desc_setup(phba, nemb_tp, 0, dmabuf, dmabuf);
+
+	/* for the rest of external buffer descriptors if any */
+	if (ext_buf_cnt > 1) {
+		ext_buf_index = 1;
+		list_for_each_entry_safe(curr_dmabuf, next_dmabuf,
+				&phba->mbox_ext_buf_ctx.ext_dmabuf_list, list) {
+			lpfc_bsg_sli_cfg_dma_desc_setup(phba, nemb_tp,
+						ext_buf_index, dmabuf,
+						curr_dmabuf);
+			ext_buf_index++;
+		}
+	}
+
+	/* construct base driver mbox command */
+	pmb = &pmboxq->u.mb;
+	pmbx = (uint8_t *)dmabuf->virt;
+	memcpy(pmb, pmbx, sizeof(*pmb));
+	pmb->mbxOwner = OWN_HOST;
+	pmboxq->vport = phba->pport;
+
+	/* multi-buffer handling context */
+	phba->mbox_ext_buf_ctx.nembType = nemb_tp;
+	phba->mbox_ext_buf_ctx.mboxType = mbox_rd;
+	phba->mbox_ext_buf_ctx.numBuf = ext_buf_cnt;
+	phba->mbox_ext_buf_ctx.mbxTag = mbox_req->extMboxTag;
+	phba->mbox_ext_buf_ctx.seqNum = mbox_req->extSeqNum;
+	phba->mbox_ext_buf_ctx.mbx_dmabuf = dmabuf;
+
+	/* callback for multi-buffer read mailbox command */
+	pmboxq->mbox_cmpl = lpfc_bsg_issue_read_mbox_ext_cmpl;
+
+	/* context fields to callback function */
+	pmboxq->context1 = dd_data;
+	dd_data->type = TYPE_MBOX;
+	dd_data->context_un.mbox.pmboxq = pmboxq;
+	dd_data->context_un.mbox.mb = (MAILBOX_t *)pmbx;
+	dd_data->context_un.mbox.set_job = job;
+	job->dd_data = dd_data;
+
+	/* state change */
+	phba->mbox_ext_buf_ctx.state = LPFC_BSG_MBOX_PORT;
+
+	rc = lpfc_sli_issue_mbox(phba, pmboxq, MBX_NOWAIT);
+	if ((rc == MBX_SUCCESS) || (rc == MBX_BUSY)) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2947 Issued SLI_CONFIG ext-buffer "
+				"maibox command, rc:x%x\n", rc);
+		return 1;
+	}
+	lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC,
+			"2948 Failed to issue SLI_CONFIG ext-buffer "
+			"maibox command, rc:x%x\n", rc);
+	rc = -EPIPE;
+
+job_error:
+	if (pmboxq)
+		mempool_free(pmboxq, phba->mbox_mem_pool);
+	lpfc_bsg_dma_page_list_free(phba,
+				    &phba->mbox_ext_buf_ctx.ext_dmabuf_list);
+	kfree(dd_data);
+	phba->mbox_ext_buf_ctx.state = LPFC_BSG_MBOX_IDLE;
+	return rc;
+}
+
+/**
+ * lpfc_bsg_sli_cfg_write_cmd_ext - sli_config non-embedded mailbox cmd write
+ * @phba: Pointer to HBA context object.
+ * @mb: Pointer to a BSG mailbox object.
+ * @dmabuff: Pointer to a DMA buffer descriptor.
+ *
+ * This routine performs SLI_CONFIG (0x9B) write mailbox command operation with
+ * non-embedded external bufffers.
+ **/
+static int
+lpfc_bsg_sli_cfg_write_cmd_ext(struct lpfc_hba *phba, struct fc_bsg_job *job,
+			       enum nemb_type nemb_tp,
+			       struct lpfc_dmabuf *dmabuf)
+{
+	struct dfc_mbox_req *mbox_req;
+	struct lpfc_sli_config_mbox *sli_cfg_mbx;
+	uint32_t ext_buf_cnt;
+	struct bsg_job_data *dd_data = NULL;
+	LPFC_MBOXQ_t *pmboxq = NULL;
+	MAILBOX_t *pmb;
+	uint8_t *mbx;
+	int rc = 0, i;
+
+	mbox_req =
+	   (struct dfc_mbox_req *)job->request->rqst_data.h_vendor.vendor_cmd;
+
+	/* pointer to the start of mailbox command */
+	sli_cfg_mbx = (struct lpfc_sli_config_mbox *)dmabuf->virt;
+
+	if (nemb_tp == nemb_mse) {
+		ext_buf_cnt = bsg_bf_get(lpfc_mbox_hdr_mse_cnt,
+			&sli_cfg_mbx->un.sli_config_emb0_subsys.sli_config_hdr);
+		if (ext_buf_cnt > LPFC_MBX_SLI_CONFIG_MAX_MSE) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC,
+					"2953 Handled SLI_CONFIG(mse) wr, "
+					"ext_buf_cnt(%d) out of range(%d)\n",
+					ext_buf_cnt,
+					LPFC_MBX_SLI_CONFIG_MAX_MSE);
+			return -ERANGE;
+		}
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2949 Handled SLI_CONFIG(mse) wr, "
+				"ext_buf_cnt:%d\n", ext_buf_cnt);
+	} else {
+		/* sanity check on interface type for support */
+		if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
+		    LPFC_SLI_INTF_IF_TYPE_2)
+			return -ENODEV;
+		/* nemb_tp == nemb_hbd */
+		ext_buf_cnt = sli_cfg_mbx->un.sli_config_emb1_subsys.hbd_count;
+		if (ext_buf_cnt > LPFC_MBX_SLI_CONFIG_MAX_HBD) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC,
+					"2954 Handled SLI_CONFIG(hbd) wr, "
+					"ext_buf_cnt(%d) out of range(%d)\n",
+					ext_buf_cnt,
+					LPFC_MBX_SLI_CONFIG_MAX_HBD);
+			return -ERANGE;
+		}
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2950 Handled SLI_CONFIG(hbd) wr, "
+				"ext_buf_cnt:%d\n", ext_buf_cnt);
+	}
+
+	if (ext_buf_cnt == 0)
+		return -EPERM;
+
+	/* for the first external buffer */
+	lpfc_bsg_sli_cfg_dma_desc_setup(phba, nemb_tp, 0, dmabuf, dmabuf);
+
+	/* log for looking forward */
+	for (i = 1; i < ext_buf_cnt; i++) {
+		if (nemb_tp == nemb_mse)
+			lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2951 SLI_CONFIG(mse), buf[%d]-length:%d\n",
+				i, sli_cfg_mbx->un.sli_config_emb0_subsys.
+				mse[i].buf_len);
+		else
+			lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2952 SLI_CONFIG(hbd), buf[%d]-length:%d\n",
+				i, bsg_bf_get(lpfc_mbox_sli_config_ecmn_hbd_len,
+				&sli_cfg_mbx->un.sli_config_emb1_subsys.
+				hbd[i]));
+	}
+
+	/* multi-buffer handling context */
+	phba->mbox_ext_buf_ctx.nembType = nemb_tp;
+	phba->mbox_ext_buf_ctx.mboxType = mbox_wr;
+	phba->mbox_ext_buf_ctx.numBuf = ext_buf_cnt;
+	phba->mbox_ext_buf_ctx.mbxTag = mbox_req->extMboxTag;
+	phba->mbox_ext_buf_ctx.seqNum = mbox_req->extSeqNum;
+	phba->mbox_ext_buf_ctx.mbx_dmabuf = dmabuf;
+
+	if (ext_buf_cnt == 1) {
+		/* bsg tracking structure */
+		dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL);
+		if (!dd_data) {
+			rc = -ENOMEM;
+			goto job_error;
+		}
+
+		/* mailbox command structure for base driver */
+		pmboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+		if (!pmboxq) {
+			rc = -ENOMEM;
+			goto job_error;
+		}
+		memset(pmboxq, 0, sizeof(LPFC_MBOXQ_t));
+		pmb = &pmboxq->u.mb;
+		mbx = (uint8_t *)dmabuf->virt;
+		memcpy(pmb, mbx, sizeof(*pmb));
+		pmb->mbxOwner = OWN_HOST;
+		pmboxq->vport = phba->pport;
+
+		/* callback for multi-buffer read mailbox command */
+		pmboxq->mbox_cmpl = lpfc_bsg_issue_write_mbox_ext_cmpl;
+
+		/* context fields to callback function */
+		pmboxq->context1 = dd_data;
+		dd_data->type = TYPE_MBOX;
+		dd_data->context_un.mbox.pmboxq = pmboxq;
+		dd_data->context_un.mbox.mb = (MAILBOX_t *)mbx;
+		dd_data->context_un.mbox.set_job = job;
+		job->dd_data = dd_data;
+
+		/* state change */
+		phba->mbox_ext_buf_ctx.state = LPFC_BSG_MBOX_PORT;
+
+		rc = lpfc_sli_issue_mbox(phba, pmboxq, MBX_NOWAIT);
+		if ((rc == MBX_SUCCESS) || (rc == MBX_BUSY)) {
+			lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+					"2955 Issued SLI_CONFIG ext-buffer "
+					"maibox command, rc:x%x\n", rc);
+			return 1;
+		}
+		lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC,
+				"2956 Failed to issue SLI_CONFIG ext-buffer "
+				"maibox command, rc:x%x\n", rc);
+		rc = -EPIPE;
+	}
+
+job_error:
+	if (pmboxq)
+		mempool_free(pmboxq, phba->mbox_mem_pool);
+	kfree(dd_data);
+
+	return rc;
+}
+
+/**
+ * lpfc_bsg_handle_sli_cfg_mbox - handle sli-cfg mailbox cmd with ext buffer
+ * @phba: Pointer to HBA context object.
+ * @mb: Pointer to a BSG mailbox object.
+ * @dmabuff: Pointer to a DMA buffer descriptor.
+ *
+ * This routine handles SLI_CONFIG (0x9B) mailbox command with non-embedded
+ * external bufffers, including both 0x9B with non-embedded MSEs and 0x9B
+ * with embedded sussystem 0x1 and opcodes with external HBDs.
+ **/
+static int
+lpfc_bsg_handle_sli_cfg_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
+			     struct lpfc_dmabuf *dmabuf)
+{
+	struct lpfc_sli_config_mbox *sli_cfg_mbx;
+	uint32_t subsys;
+	uint32_t opcode;
+	int rc = SLI_CONFIG_NOT_HANDLED;
+
+	/* state change */
+	phba->mbox_ext_buf_ctx.state = LPFC_BSG_MBOX_HOST;
+
+	sli_cfg_mbx = (struct lpfc_sli_config_mbox *)dmabuf->virt;
+
+	if (!bsg_bf_get(lpfc_mbox_hdr_emb,
+	    &sli_cfg_mbx->un.sli_config_emb0_subsys.sli_config_hdr)) {
+		subsys = bsg_bf_get(lpfc_emb0_subcmnd_subsys,
+				    &sli_cfg_mbx->un.sli_config_emb0_subsys);
+		opcode = bsg_bf_get(lpfc_emb0_subcmnd_opcode,
+				    &sli_cfg_mbx->un.sli_config_emb0_subsys);
+		if (subsys == SLI_CONFIG_SUBSYS_FCOE) {
+			switch (opcode) {
+			case FCOE_OPCODE_READ_FCF:
+				lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+						"2957 Handled SLI_CONFIG "
+						"subsys_fcoe, opcode:x%x\n",
+						opcode);
+				rc = lpfc_bsg_sli_cfg_read_cmd_ext(phba, job,
+							nemb_mse, dmabuf);
+				break;
+			case FCOE_OPCODE_ADD_FCF:
+				lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+						"2958 Handled SLI_CONFIG "
+						"subsys_fcoe, opcode:x%x\n",
+						opcode);
+				rc = lpfc_bsg_sli_cfg_write_cmd_ext(phba, job,
+							nemb_mse, dmabuf);
+				break;
+			default:
+				lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+						"2959 Not handled SLI_CONFIG "
+						"subsys_fcoe, opcode:x%x\n",
+						opcode);
+				rc = SLI_CONFIG_NOT_HANDLED;
+				break;
+			}
+		} else {
+			lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+					"2977 Handled SLI_CONFIG "
+					"subsys:x%d, opcode:x%x\n",
+					subsys, opcode);
+			rc = SLI_CONFIG_NOT_HANDLED;
+		}
+	} else {
+		subsys = bsg_bf_get(lpfc_emb1_subcmnd_subsys,
+				    &sli_cfg_mbx->un.sli_config_emb1_subsys);
+		opcode = bsg_bf_get(lpfc_emb1_subcmnd_opcode,
+				    &sli_cfg_mbx->un.sli_config_emb1_subsys);
+		if (subsys == SLI_CONFIG_SUBSYS_COMN) {
+			switch (opcode) {
+			case COMN_OPCODE_READ_OBJECT:
+			case COMN_OPCODE_READ_OBJECT_LIST:
+				lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+						"2960 Handled SLI_CONFIG "
+						"subsys_comn, opcode:x%x\n",
+						opcode);
+				rc = lpfc_bsg_sli_cfg_read_cmd_ext(phba, job,
+							nemb_hbd, dmabuf);
+				break;
+			case COMN_OPCODE_WRITE_OBJECT:
+				lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+						"2961 Handled SLI_CONFIG "
+						"subsys_comn, opcode:x%x\n",
+						opcode);
+				rc = lpfc_bsg_sli_cfg_write_cmd_ext(phba, job,
+							nemb_hbd, dmabuf);
+				break;
+			default:
+				lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+						"2962 Not handled SLI_CONFIG "
+						"subsys_comn, opcode:x%x\n",
+						opcode);
+				rc = SLI_CONFIG_NOT_HANDLED;
+				break;
+			}
+		} else {
+			lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+					"2978 Handled SLI_CONFIG "
+					"subsys:x%d, opcode:x%x\n",
+					subsys, opcode);
+			rc = SLI_CONFIG_NOT_HANDLED;
+		}
+	}
+	return rc;
+}
+
+/**
+ * lpfc_bsg_mbox_ext_abort_req - request to abort mbox command with ext buffers
+ * @phba: Pointer to HBA context object.
+ *
+ * This routine is for requesting to abort a pass-through mailbox command with
+ * multiple external buffers due to error condition.
+ **/
+static void
+lpfc_bsg_mbox_ext_abort(struct lpfc_hba *phba)
+{
+	if (phba->mbox_ext_buf_ctx.state == LPFC_BSG_MBOX_PORT)
+		phba->mbox_ext_buf_ctx.state = LPFC_BSG_MBOX_ABTS;
+	else
+		lpfc_bsg_mbox_ext_session_reset(phba);
+	return;
+}
+
+/**
+ * lpfc_bsg_read_ebuf_get - get the next mailbox read external buffer
+ * @phba: Pointer to HBA context object.
+ * @dmabuf: Pointer to a DMA buffer descriptor.
+ *
+ * This routine extracts the next mailbox read external buffer back to
+ * user space through BSG.
+ **/
+static int
+lpfc_bsg_read_ebuf_get(struct lpfc_hba *phba, struct fc_bsg_job *job)
+{
+	struct lpfc_sli_config_mbox *sli_cfg_mbx;
+	struct lpfc_dmabuf *dmabuf;
+	uint8_t *pbuf;
+	uint32_t size;
+	uint32_t index;
+
+	index = phba->mbox_ext_buf_ctx.seqNum;
+	phba->mbox_ext_buf_ctx.seqNum++;
+
+	sli_cfg_mbx = (struct lpfc_sli_config_mbox *)
+			phba->mbox_ext_buf_ctx.mbx_dmabuf->virt;
+
+	if (phba->mbox_ext_buf_ctx.nembType == nemb_mse) {
+		size = bsg_bf_get(lpfc_mbox_sli_config_mse_len,
+			&sli_cfg_mbx->un.sli_config_emb0_subsys.mse[index]);
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2963 SLI_CONFIG (mse) ext-buffer rd get "
+				"buffer[%d], size:%d\n", index, size);
+	} else {
+		size = bsg_bf_get(lpfc_mbox_sli_config_ecmn_hbd_len,
+			&sli_cfg_mbx->un.sli_config_emb1_subsys.hbd[index]);
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2964 SLI_CONFIG (hbd) ext-buffer rd get "
+				"buffer[%d], size:%d\n", index, size);
+	}
+	if (list_empty(&phba->mbox_ext_buf_ctx.ext_dmabuf_list))
+		return -EPIPE;
+	dmabuf = list_first_entry(&phba->mbox_ext_buf_ctx.ext_dmabuf_list,
+				  struct lpfc_dmabuf, list);
+	list_del_init(&dmabuf->list);
+	pbuf = (uint8_t *)dmabuf->virt;
+	job->reply->reply_payload_rcv_len =
+		sg_copy_from_buffer(job->reply_payload.sg_list,
+				    job->reply_payload.sg_cnt,
+				    pbuf, size);
+
+	lpfc_bsg_dma_page_free(phba, dmabuf);
+
+	if (phba->mbox_ext_buf_ctx.seqNum == phba->mbox_ext_buf_ctx.numBuf) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2965 SLI_CONFIG (hbd) ext-buffer rd mbox "
+				"command session done\n");
+		lpfc_bsg_mbox_ext_session_reset(phba);
+	}
+
+	job->reply->result = 0;
+	job->job_done(job);
+
+	return SLI_CONFIG_HANDLED;
+}
+
+/**
+ * lpfc_bsg_write_ebuf_set - set the next mailbox write external buffer
+ * @phba: Pointer to HBA context object.
+ * @dmabuf: Pointer to a DMA buffer descriptor.
+ *
+ * This routine sets up the next mailbox read external buffer obtained
+ * from user space through BSG.
+ **/
+static int
+lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct fc_bsg_job *job,
+			struct lpfc_dmabuf *dmabuf)
+{
+	struct lpfc_sli_config_mbox *sli_cfg_mbx;
+	struct bsg_job_data *dd_data = NULL;
+	LPFC_MBOXQ_t *pmboxq = NULL;
+	MAILBOX_t *pmb;
+	enum nemb_type nemb_tp;
+	uint8_t *pbuf;
+	uint32_t size;
+	uint32_t index;
+	int rc;
+
+	index = phba->mbox_ext_buf_ctx.seqNum;
+	phba->mbox_ext_buf_ctx.seqNum++;
+	nemb_tp = phba->mbox_ext_buf_ctx.nembType;
+
+	sli_cfg_mbx = (struct lpfc_sli_config_mbox *)
+			phba->mbox_ext_buf_ctx.mbx_dmabuf->virt;
+
+	dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL);
+	if (!dd_data) {
+		rc = -ENOMEM;
+		goto job_error;
+	}
+
+	pbuf = (uint8_t *)dmabuf->virt;
+	size = job->request_payload.payload_len;
+	sg_copy_to_buffer(job->request_payload.sg_list,
+			  job->request_payload.sg_cnt,
+			  pbuf, size);
+
+	if (phba->mbox_ext_buf_ctx.nembType == nemb_mse) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2966 SLI_CONFIG (mse) ext-buffer wr set "
+				"buffer[%d], size:%d\n",
+				phba->mbox_ext_buf_ctx.seqNum, size);
+
+	} else {
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2967 SLI_CONFIG (hbd) ext-buffer wr set "
+				"buffer[%d], size:%d\n",
+				phba->mbox_ext_buf_ctx.seqNum, size);
+
+	}
+
+	/* set up external buffer descriptor and add to external buffer list */
+	lpfc_bsg_sli_cfg_dma_desc_setup(phba, nemb_tp, index,
+					phba->mbox_ext_buf_ctx.mbx_dmabuf,
+					dmabuf);
+	list_add_tail(&dmabuf->list, &phba->mbox_ext_buf_ctx.ext_dmabuf_list);
+
+	if (phba->mbox_ext_buf_ctx.seqNum == phba->mbox_ext_buf_ctx.numBuf) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2968 SLI_CONFIG ext-buffer wr all %d "
+				"ebuffers received\n",
+				phba->mbox_ext_buf_ctx.numBuf);
+		/* mailbox command structure for base driver */
+		pmboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+		if (!pmboxq) {
+			rc = -ENOMEM;
+			goto job_error;
+		}
+		memset(pmboxq, 0, sizeof(LPFC_MBOXQ_t));
+		pbuf = (uint8_t *)phba->mbox_ext_buf_ctx.mbx_dmabuf->virt;
+		pmb = &pmboxq->u.mb;
+		memcpy(pmb, pbuf, sizeof(*pmb));
+		pmb->mbxOwner = OWN_HOST;
+		pmboxq->vport = phba->pport;
+
+		/* callback for multi-buffer write mailbox command */
+		pmboxq->mbox_cmpl = lpfc_bsg_issue_write_mbox_ext_cmpl;
+
+		/* context fields to callback function */
+		pmboxq->context1 = dd_data;
+		dd_data->type = TYPE_MBOX;
+		dd_data->context_un.mbox.pmboxq = pmboxq;
+		dd_data->context_un.mbox.mb = (MAILBOX_t *)pbuf;
+		dd_data->context_un.mbox.set_job = job;
+		job->dd_data = dd_data;
+
+		/* state change */
+		phba->mbox_ext_buf_ctx.state = LPFC_BSG_MBOX_PORT;
+
+		rc = lpfc_sli_issue_mbox(phba, pmboxq, MBX_NOWAIT);
+		if ((rc == MBX_SUCCESS) || (rc == MBX_BUSY)) {
+			lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+					"2969 Issued SLI_CONFIG ext-buffer "
+					"maibox command, rc:x%x\n", rc);
+			return 1;
+		}
+		lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC,
+				"2970 Failed to issue SLI_CONFIG ext-buffer "
+				"maibox command, rc:x%x\n", rc);
+		rc = -EPIPE;
+		goto job_error;
+	}
+
+	/* wait for additoinal external buffers */
+	job->reply->result = 0;
+	job->job_done(job);
+	return SLI_CONFIG_HANDLED;
+
+job_error:
+	lpfc_bsg_dma_page_free(phba, dmabuf);
+	kfree(dd_data);
+
+	return rc;
+}
+
+/**
+ * lpfc_bsg_handle_sli_cfg_ebuf - handle ext buffer with sli-cfg mailbox cmd
+ * @phba: Pointer to HBA context object.
+ * @mb: Pointer to a BSG mailbox object.
+ * @dmabuff: Pointer to a DMA buffer descriptor.
+ *
+ * This routine handles the external buffer with SLI_CONFIG (0x9B) mailbox
+ * command with multiple non-embedded external buffers.
+ **/
+static int
+lpfc_bsg_handle_sli_cfg_ebuf(struct lpfc_hba *phba, struct fc_bsg_job *job,
+			     struct lpfc_dmabuf *dmabuf)
+{
+	int rc;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+			"2971 SLI_CONFIG buffer (type:x%x)\n",
+			phba->mbox_ext_buf_ctx.mboxType);
+
+	if (phba->mbox_ext_buf_ctx.mboxType == mbox_rd) {
+		if (phba->mbox_ext_buf_ctx.state != LPFC_BSG_MBOX_DONE) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC,
+					"2972 SLI_CONFIG rd buffer state "
+					"mismatch:x%x\n",
+					phba->mbox_ext_buf_ctx.state);
+			lpfc_bsg_mbox_ext_abort(phba);
+			return -EPIPE;
+		}
+		rc = lpfc_bsg_read_ebuf_get(phba, job);
+		if (rc == SLI_CONFIG_HANDLED)
+			lpfc_bsg_dma_page_free(phba, dmabuf);
+	} else { /* phba->mbox_ext_buf_ctx.mboxType == mbox_wr */
+		if (phba->mbox_ext_buf_ctx.state != LPFC_BSG_MBOX_HOST) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC,
+					"2973 SLI_CONFIG wr buffer state "
+					"mismatch:x%x\n",
+					phba->mbox_ext_buf_ctx.state);
+			lpfc_bsg_mbox_ext_abort(phba);
+			return -EPIPE;
+		}
+		rc = lpfc_bsg_write_ebuf_set(phba, job, dmabuf);
+	}
+	return rc;
+}
+
+/**
+ * lpfc_bsg_handle_sli_cfg_ext - handle sli-cfg mailbox with external buffer
+ * @phba: Pointer to HBA context object.
+ * @mb: Pointer to a BSG mailbox object.
+ * @dmabuff: Pointer to a DMA buffer descriptor.
+ *
+ * This routine checkes and handles non-embedded multi-buffer SLI_CONFIG
+ * (0x9B) mailbox commands and external buffers.
+ **/
+static int
+lpfc_bsg_handle_sli_cfg_ext(struct lpfc_hba *phba, struct fc_bsg_job *job,
+			    struct lpfc_dmabuf *dmabuf)
+{
+	struct dfc_mbox_req *mbox_req;
+	int rc;
+
+	mbox_req =
+	   (struct dfc_mbox_req *)job->request->rqst_data.h_vendor.vendor_cmd;
+
+	/* mbox command with/without single external buffer */
+	if (mbox_req->extMboxTag == 0 && mbox_req->extSeqNum == 0)
+		return SLI_CONFIG_NOT_HANDLED;
+
+	/* mbox command and first external buffer */
+	if (phba->mbox_ext_buf_ctx.state == LPFC_BSG_MBOX_IDLE) {
+		if (mbox_req->extSeqNum == 1) {
+			lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+					"2974 SLI_CONFIG mailbox: tag:%d, "
+					"seq:%d\n", mbox_req->extMboxTag,
+					mbox_req->extSeqNum);
+			rc = lpfc_bsg_handle_sli_cfg_mbox(phba, job, dmabuf);
+			return rc;
+		} else
+			goto sli_cfg_ext_error;
+	}
+
+	/*
+	 * handle additional external buffers
+	 */
+
+	/* check broken pipe conditions */
+	if (mbox_req->extMboxTag != phba->mbox_ext_buf_ctx.mbxTag)
+		goto sli_cfg_ext_error;
+	if (mbox_req->extSeqNum > phba->mbox_ext_buf_ctx.numBuf)
+		goto sli_cfg_ext_error;
+	if (mbox_req->extSeqNum != phba->mbox_ext_buf_ctx.seqNum + 1)
+		goto sli_cfg_ext_error;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+			"2975 SLI_CONFIG mailbox external buffer: "
+			"extSta:x%x, tag:%d, seq:%d\n",
+			phba->mbox_ext_buf_ctx.state, mbox_req->extMboxTag,
+			mbox_req->extSeqNum);
+	rc = lpfc_bsg_handle_sli_cfg_ebuf(phba, job, dmabuf);
+	return rc;
+
+sli_cfg_ext_error:
+	/* all other cases, broken pipe */
+	lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC,
+			"2976 SLI_CONFIG mailbox broken pipe: "
+			"ctxSta:x%x, ctxNumBuf:%d "
+			"ctxTag:%d, ctxSeq:%d, tag:%d, seq:%d\n",
+			phba->mbox_ext_buf_ctx.state,
+			phba->mbox_ext_buf_ctx.numBuf,
+			phba->mbox_ext_buf_ctx.mbxTag,
+			phba->mbox_ext_buf_ctx.seqNum,
+			mbox_req->extMboxTag, mbox_req->extSeqNum);
+
+	lpfc_bsg_mbox_ext_session_reset(phba);
+
+	return -EPIPE;
+}
+
+/**
  * lpfc_bsg_issue_mbox - issues a mailbox command on behalf of an app
  * @phba: Pointer to HBA context object.
  * @mb: Pointer to a mailbox object.
@@ -2638,22 +4118,21 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 	LPFC_MBOXQ_t *pmboxq = NULL; /* internal mailbox queue */
 	MAILBOX_t *pmb; /* shortcut to the pmboxq mailbox */
 	/* a 4k buffer to hold the mb and extended data from/to the bsg */
-	MAILBOX_t *mb = NULL;
+	uint8_t *pmbx = NULL;
 	struct bsg_job_data *dd_data = NULL; /* bsg data tracking structure */
-	uint32_t size;
-	struct lpfc_dmabuf *rxbmp = NULL; /* for biu diag */
-	struct lpfc_dmabufext *dmp = NULL; /* for biu diag */
-	struct ulp_bde64 *rxbpl = NULL;
-	struct dfc_mbox_req *mbox_req = (struct dfc_mbox_req *)
-		job->request->rqst_data.h_vendor.vendor_cmd;
+	struct lpfc_dmabuf *dmabuf = NULL;
+	struct dfc_mbox_req *mbox_req;
 	struct READ_EVENT_LOG_VAR *rdEventLog;
 	uint32_t transmit_length, receive_length, mode;
+	struct lpfc_mbx_sli4_config *sli4_config;
 	struct lpfc_mbx_nembed_cmd *nembed_sge;
 	struct mbox_header *header;
 	struct ulp_bde64 *bde;
 	uint8_t *ext = NULL;
 	int rc = 0;
 	uint8_t *from;
+	uint32_t size;
+
 
 	/* in case no data is transferred */
 	job->reply->reply_payload_rcv_len = 0;
@@ -2665,6 +4144,18 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 		goto job_done;
 	}
 
+	/*
+	 * Don't allow mailbox commands to be sent when blocked or when in
+	 * the middle of discovery
+	 */
+	 if (phba->sli.sli_flag & LPFC_BLOCK_MGMT_IO) {
+		rc = -EAGAIN;
+		goto job_done;
+	}
+
+	mbox_req =
+	    (struct dfc_mbox_req *)job->request->rqst_data.h_vendor.vendor_cmd;
+
 	/* check if requested extended data lengths are valid */
 	if ((mbox_req->inExtWLen > BSG_MBOX_SIZE/sizeof(uint32_t)) ||
 	    (mbox_req->outExtWLen > BSG_MBOX_SIZE/sizeof(uint32_t))) {
@@ -2672,6 +4163,32 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 		goto job_done;
 	}
 
+	dmabuf = lpfc_bsg_dma_page_alloc(phba);
+	if (!dmabuf || !dmabuf->virt) {
+		rc = -ENOMEM;
+		goto job_done;
+	}
+
+	/* Get the mailbox command or external buffer from BSG */
+	pmbx = (uint8_t *)dmabuf->virt;
+	size = job->request_payload.payload_len;
+	sg_copy_to_buffer(job->request_payload.sg_list,
+			  job->request_payload.sg_cnt, pmbx, size);
+
+	/* Handle possible SLI_CONFIG with non-embedded payloads */
+	if (phba->sli_rev == LPFC_SLI_REV4) {
+		rc = lpfc_bsg_handle_sli_cfg_ext(phba, job, dmabuf);
+		if (rc == SLI_CONFIG_HANDLED)
+			goto job_cont;
+		if (rc)
+			goto job_done;
+		/* SLI_CONFIG_NOT_HANDLED for other mailbox commands */
+	}
+
+	rc = lpfc_bsg_check_cmd_access(phba, (MAILBOX_t *)pmbx, vport);
+	if (rc != 0)
+		goto job_done; /* must be negative */
+
 	/* allocate our bsg tracking structure */
 	dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL);
 	if (!dd_data) {
@@ -2681,12 +4198,6 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 		goto job_done;
 	}
 
-	mb = kzalloc(BSG_MBOX_SIZE, GFP_KERNEL);
-	if (!mb) {
-		rc = -ENOMEM;
-		goto job_done;
-	}
-
 	pmboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!pmboxq) {
 		rc = -ENOMEM;
@@ -2694,17 +4205,8 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 	}
 	memset(pmboxq, 0, sizeof(LPFC_MBOXQ_t));
 
-	size = job->request_payload.payload_len;
-	sg_copy_to_buffer(job->request_payload.sg_list,
-			job->request_payload.sg_cnt,
-			mb, size);
-
-	rc = lpfc_bsg_check_cmd_access(phba, mb, vport);
-	if (rc != 0)
-		goto job_done; /* must be negative */
-
 	pmb = &pmboxq->u.mb;
-	memcpy(pmb, mb, sizeof(*pmb));
+	memcpy(pmb, pmbx, sizeof(*pmb));
 	pmb->mbxOwner = OWN_HOST;
 	pmboxq->vport = vport;
 
@@ -2721,30 +4223,13 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 				"0x%x while in stopped state.\n",
 				pmb->mbxCommand);
 
-	/* Don't allow mailbox commands to be sent when blocked
-	 * or when in the middle of discovery
-	 */
-	if (phba->sli.sli_flag & LPFC_BLOCK_MGMT_IO) {
-		rc = -EAGAIN;
-		goto job_done;
-	}
-
 	/* extended mailbox commands will need an extended buffer */
 	if (mbox_req->inExtWLen || mbox_req->outExtWLen) {
-		ext = kzalloc(MAILBOX_EXT_SIZE, GFP_KERNEL);
-		if (!ext) {
-			rc = -ENOMEM;
-			goto job_done;
-		}
-
 		/* any data for the device? */
 		if (mbox_req->inExtWLen) {
-			from = (uint8_t *)mb;
-			from += sizeof(MAILBOX_t);
-			memcpy((uint8_t *)ext, from,
-				mbox_req->inExtWLen * sizeof(uint32_t));
+			from = pmbx;
+			ext = from + sizeof(MAILBOX_t);
 		}
-
 		pmboxq->context2 = ext;
 		pmboxq->in_ext_byte_len =
 			mbox_req->inExtWLen * sizeof(uint32_t);
@@ -2768,46 +4253,17 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 			rc = -ERANGE;
 			goto job_done;
 		}
-
-		rxbmp = kmalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
-		if (!rxbmp) {
-			rc = -ENOMEM;
-			goto job_done;
-		}
-
-		rxbmp->virt = lpfc_mbuf_alloc(phba, 0, &rxbmp->phys);
-		if (!rxbmp->virt) {
-			rc = -ENOMEM;
-			goto job_done;
-		}
-
-		INIT_LIST_HEAD(&rxbmp->list);
-		rxbpl = (struct ulp_bde64 *) rxbmp->virt;
-		dmp = diag_cmd_data_alloc(phba, rxbpl, transmit_length, 0);
-		if (!dmp) {
-			rc = -ENOMEM;
-			goto job_done;
-		}
-
-		INIT_LIST_HEAD(&dmp->dma.list);
 		pmb->un.varBIUdiag.un.s2.xmit_bde64.addrHigh =
-			putPaddrHigh(dmp->dma.phys);
+			putPaddrHigh(dmabuf->phys + sizeof(MAILBOX_t));
 		pmb->un.varBIUdiag.un.s2.xmit_bde64.addrLow =
-			putPaddrLow(dmp->dma.phys);
+			putPaddrLow(dmabuf->phys + sizeof(MAILBOX_t));
 
 		pmb->un.varBIUdiag.un.s2.rcv_bde64.addrHigh =
-			putPaddrHigh(dmp->dma.phys +
-				pmb->un.varBIUdiag.un.s2.
-					xmit_bde64.tus.f.bdeSize);
+			putPaddrHigh(dmabuf->phys + sizeof(MAILBOX_t)
+			  + pmb->un.varBIUdiag.un.s2.xmit_bde64.tus.f.bdeSize);
 		pmb->un.varBIUdiag.un.s2.rcv_bde64.addrLow =
-			putPaddrLow(dmp->dma.phys +
-				pmb->un.varBIUdiag.un.s2.
-					xmit_bde64.tus.f.bdeSize);
-
-		/* copy the transmit data found in the mailbox extension area */
-		from = (uint8_t *)mb;
-		from += sizeof(MAILBOX_t);
-		memcpy((uint8_t *)dmp->dma.virt, from, transmit_length);
+			putPaddrLow(dmabuf->phys + sizeof(MAILBOX_t)
+			  + pmb->un.varBIUdiag.un.s2.xmit_bde64.tus.f.bdeSize);
 	} else if (pmb->mbxCommand == MBX_READ_EVENT_LOG) {
 		rdEventLog = &pmb->un.varRdEventLog;
 		receive_length = rdEventLog->rcv_bde64.tus.f.bdeSize;
@@ -2823,33 +4279,10 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 
 		/* mode zero uses a bde like biu diags command */
 		if (mode == 0) {
-
-			/* rebuild the command for sli4 using our own buffers
-			* like we do for biu diags
-			*/
-
-			rxbmp = kmalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
-			if (!rxbmp) {
-				rc = -ENOMEM;
-				goto job_done;
-			}
-
-			rxbmp->virt = lpfc_mbuf_alloc(phba, 0, &rxbmp->phys);
-			rxbpl = (struct ulp_bde64 *) rxbmp->virt;
-			if (rxbpl) {
-				INIT_LIST_HEAD(&rxbmp->list);
-				dmp = diag_cmd_data_alloc(phba, rxbpl,
-					receive_length, 0);
-			}
-
-			if (!dmp) {
-				rc = -ENOMEM;
-				goto job_done;
-			}
-
-			INIT_LIST_HEAD(&dmp->dma.list);
-			pmb->un.varWords[3] = putPaddrLow(dmp->dma.phys);
-			pmb->un.varWords[4] = putPaddrHigh(dmp->dma.phys);
+			pmb->un.varWords[3] = putPaddrLow(dmabuf->phys
+							+ sizeof(MAILBOX_t));
+			pmb->un.varWords[4] = putPaddrHigh(dmabuf->phys
+							+ sizeof(MAILBOX_t));
 		}
 	} else if (phba->sli_rev == LPFC_SLI_REV4) {
 		if (pmb->mbxCommand == MBX_DUMP_MEMORY) {
@@ -2860,36 +4293,14 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 			/* receive length cannot be greater than mailbox
 			 * extension size
 			 */
-			if ((receive_length == 0) ||
-				(receive_length > MAILBOX_EXT_SIZE)) {
+			if (receive_length == 0) {
 				rc = -ERANGE;
 				goto job_done;
 			}
-
-			rxbmp = kmalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
-			if (!rxbmp) {
-				rc = -ENOMEM;
-				goto job_done;
-			}
-
-			rxbmp->virt = lpfc_mbuf_alloc(phba, 0, &rxbmp->phys);
-			if (!rxbmp->virt) {
-				rc = -ENOMEM;
-				goto job_done;
-			}
-
-			INIT_LIST_HEAD(&rxbmp->list);
-			rxbpl = (struct ulp_bde64 *) rxbmp->virt;
-			dmp = diag_cmd_data_alloc(phba, rxbpl, receive_length,
-						0);
-			if (!dmp) {
-				rc = -ENOMEM;
-				goto job_done;
-			}
-
-			INIT_LIST_HEAD(&dmp->dma.list);
-			pmb->un.varWords[3] = putPaddrLow(dmp->dma.phys);
-			pmb->un.varWords[4] = putPaddrHigh(dmp->dma.phys);
+			pmb->un.varWords[3] = putPaddrLow(dmabuf->phys
+						+ sizeof(MAILBOX_t));
+			pmb->un.varWords[4] = putPaddrHigh(dmabuf->phys
+						+ sizeof(MAILBOX_t));
 		} else if ((pmb->mbxCommand == MBX_UPDATE_CFG) &&
 			pmb->un.varUpdateCfg.co) {
 			bde = (struct ulp_bde64 *)&pmb->un.varWords[4];
@@ -2899,102 +4310,53 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 				rc = -ERANGE;
 				goto job_done;
 			}
-
-			rxbmp = kmalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
-			if (!rxbmp) {
-				rc = -ENOMEM;
-				goto job_done;
-			}
-
-			rxbmp->virt = lpfc_mbuf_alloc(phba, 0, &rxbmp->phys);
-			if (!rxbmp->virt) {
-				rc = -ENOMEM;
-				goto job_done;
-			}
-
-			INIT_LIST_HEAD(&rxbmp->list);
-			rxbpl = (struct ulp_bde64 *) rxbmp->virt;
-			dmp = diag_cmd_data_alloc(phba, rxbpl,
-					bde->tus.f.bdeSize, 0);
-			if (!dmp) {
-				rc = -ENOMEM;
-				goto job_done;
-			}
-
-			INIT_LIST_HEAD(&dmp->dma.list);
-			bde->addrHigh = putPaddrHigh(dmp->dma.phys);
-			bde->addrLow = putPaddrLow(dmp->dma.phys);
-
-			/* copy the transmit data found in the mailbox
-			 * extension area
-			 */
-			from = (uint8_t *)mb;
-			from += sizeof(MAILBOX_t);
-			memcpy((uint8_t *)dmp->dma.virt, from,
-				bde->tus.f.bdeSize);
+			bde->addrHigh = putPaddrHigh(dmabuf->phys
+						+ sizeof(MAILBOX_t));
+			bde->addrLow = putPaddrLow(dmabuf->phys
+						+ sizeof(MAILBOX_t));
 		} else if (pmb->mbxCommand == MBX_SLI4_CONFIG) {
-			/* rebuild the command for sli4 using our own buffers
-			* like we do for biu diags
-			*/
-			header = (struct mbox_header *)&pmb->un.varWords[0];
-			nembed_sge = (struct lpfc_mbx_nembed_cmd *)
-				&pmb->un.varWords[0];
-			receive_length = nembed_sge->sge[0].length;
-
-			/* receive length cannot be greater than mailbox
-			 * extension size
-			 */
-			if ((receive_length == 0) ||
-				(receive_length > MAILBOX_EXT_SIZE)) {
-				rc = -ERANGE;
-				goto job_done;
-			}
-
-			rxbmp = kmalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
-			if (!rxbmp) {
-				rc = -ENOMEM;
-				goto job_done;
-			}
-
-			rxbmp->virt = lpfc_mbuf_alloc(phba, 0, &rxbmp->phys);
-			if (!rxbmp->virt) {
-				rc = -ENOMEM;
-				goto job_done;
-			}
+			/* Handling non-embedded SLI_CONFIG mailbox command */
+			sli4_config = &pmboxq->u.mqe.un.sli4_config;
+			if (!bf_get(lpfc_mbox_hdr_emb,
+			    &sli4_config->header.cfg_mhdr)) {
+				/* rebuild the command for sli4 using our
+				 * own buffers like we do for biu diags
+				 */
+				header = (struct mbox_header *)
+						&pmb->un.varWords[0];
+				nembed_sge = (struct lpfc_mbx_nembed_cmd *)
+						&pmb->un.varWords[0];
+				receive_length = nembed_sge->sge[0].length;
+
+				/* receive length cannot be greater than
+				 * mailbox extension size
+				 */
+				if ((receive_length == 0) ||
+				    (receive_length > MAILBOX_EXT_SIZE)) {
+					rc = -ERANGE;
+					goto job_done;
+				}
 
-			INIT_LIST_HEAD(&rxbmp->list);
-			rxbpl = (struct ulp_bde64 *) rxbmp->virt;
-			dmp = diag_cmd_data_alloc(phba, rxbpl, receive_length,
-						0);
-			if (!dmp) {
-				rc = -ENOMEM;
-				goto job_done;
+				nembed_sge->sge[0].pa_hi =
+						putPaddrHigh(dmabuf->phys
+						   + sizeof(MAILBOX_t));
+				nembed_sge->sge[0].pa_lo =
+						putPaddrLow(dmabuf->phys
+						   + sizeof(MAILBOX_t));
 			}
-
-			INIT_LIST_HEAD(&dmp->dma.list);
-			nembed_sge->sge[0].pa_hi = putPaddrHigh(dmp->dma.phys);
-			nembed_sge->sge[0].pa_lo = putPaddrLow(dmp->dma.phys);
-			/* copy the transmit data found in the mailbox
-			 * extension area
-			 */
-			from = (uint8_t *)mb;
-			from += sizeof(MAILBOX_t);
-			memcpy((uint8_t *)dmp->dma.virt, from,
-				header->cfg_mhdr.payload_length);
 		}
 	}
 
-	dd_data->context_un.mbox.rxbmp = rxbmp;
-	dd_data->context_un.mbox.dmp = dmp;
+	dd_data->context_un.mbox.dmabuffers = dmabuf;
 
 	/* setup wake call as IOCB callback */
-	pmboxq->mbox_cmpl = lpfc_bsg_wake_mbox_wait;
+	pmboxq->mbox_cmpl = lpfc_bsg_issue_mbox_cmpl;
 
 	/* setup context field to pass wait_queue pointer to wake function */
 	pmboxq->context1 = dd_data;
 	dd_data->type = TYPE_MBOX;
 	dd_data->context_un.mbox.pmboxq = pmboxq;
-	dd_data->context_un.mbox.mb = mb;
+	dd_data->context_un.mbox.mb = (MAILBOX_t *)pmbx;
 	dd_data->context_un.mbox.set_job = job;
 	dd_data->context_un.mbox.ext = ext;
 	dd_data->context_un.mbox.mbOffset = mbox_req->mbOffset;
@@ -3011,11 +4373,11 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 		}
 
 		/* job finished, copy the data */
-		memcpy(mb, pmb, sizeof(*pmb));
+		memcpy(pmbx, pmb, sizeof(*pmb));
 		job->reply->reply_payload_rcv_len =
 			sg_copy_from_buffer(job->reply_payload.sg_list,
-					job->reply_payload.sg_cnt,
-					mb, size);
+					    job->reply_payload.sg_cnt,
+					    pmbx, size);
 		/* not waiting mbox already done */
 		rc = 0;
 		goto job_done;
@@ -3027,22 +4389,12 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 
 job_done:
 	/* common exit for error or job completed inline */
-	kfree(mb);
 	if (pmboxq)
 		mempool_free(pmboxq, phba->mbox_mem_pool);
-	kfree(ext);
-	if (dmp) {
-		dma_free_coherent(&phba->pcidev->dev,
-			dmp->size, dmp->dma.virt,
-				dmp->dma.phys);
-		kfree(dmp);
-	}
-	if (rxbmp) {
-		lpfc_mbuf_free(phba, rxbmp->virt, rxbmp->phys);
-		kfree(rxbmp);
-	}
+	lpfc_bsg_dma_page_free(phba, dmabuf);
 	kfree(dd_data);
 
+job_cont:
 	return rc;
 }
 
@@ -3055,37 +4407,28 @@ lpfc_bsg_mbox_cmd(struct fc_bsg_job *job)
 {
 	struct lpfc_vport *vport = (struct lpfc_vport *)job->shost->hostdata;
 	struct lpfc_hba *phba = vport->phba;
+	struct dfc_mbox_req *mbox_req;
 	int rc = 0;
 
-	/* in case no data is transferred */
+	/* mix-and-match backward compatibility */
 	job->reply->reply_payload_rcv_len = 0;
 	if (job->request_len <
 	    sizeof(struct fc_bsg_request) + sizeof(struct dfc_mbox_req)) {
-		lpfc_printf_log(phba, KERN_WARNING, LOG_LIBDFC,
-				"2737 Received MBOX_REQ request below "
-				"minimum size\n");
-		rc = -EINVAL;
-		goto job_error;
-	}
-
-	if (job->request_payload.payload_len != BSG_MBOX_SIZE) {
-		rc = -EINVAL;
-		goto job_error;
-	}
-
-	if (job->reply_payload.payload_len != BSG_MBOX_SIZE) {
-		rc = -EINVAL;
-		goto job_error;
-	}
-
-	if (phba->sli.sli_flag & LPFC_BLOCK_MGMT_IO) {
-		rc = -EAGAIN;
-		goto job_error;
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2737 Mix-and-match backward compability "
+				"between MBOX_REQ old size:%d and "
+				"new request size:%d\n",
+				(int)(job->request_len -
+				      sizeof(struct fc_bsg_request)),
+				(int)sizeof(struct dfc_mbox_req));
+		mbox_req = (struct dfc_mbox_req *)
+				job->request->rqst_data.h_vendor.vendor_cmd;
+		mbox_req->extMboxTag = 0;
+		mbox_req->extSeqNum = 0;
 	}
 
 	rc = lpfc_bsg_issue_mbox(phba, job, vport);
 
-job_error:
 	if (rc == 0) {
 		/* job done */
 		job->reply->result = 0;
@@ -3416,10 +4759,16 @@ lpfc_bsg_hst_vendor(struct fc_bsg_job *job)
 		rc = lpfc_bsg_send_mgmt_rsp(job);
 		break;
 	case LPFC_BSG_VENDOR_DIAG_MODE:
-		rc = lpfc_bsg_diag_mode(job);
+		rc = lpfc_bsg_diag_loopback_mode(job);
+		break;
+	case LPFC_BSG_VENDOR_DIAG_MODE_END:
+		rc = lpfc_sli4_bsg_diag_mode_end(job);
+		break;
+	case LPFC_BSG_VENDOR_DIAG_RUN_LOOPBACK:
+		rc = lpfc_bsg_diag_loopback_run(job);
 		break;
-	case LPFC_BSG_VENDOR_DIAG_TEST:
-		rc = lpfc_bsg_diag_test(job);
+	case LPFC_BSG_VENDOR_LINK_DIAG_TEST:
+		rc = lpfc_sli4_bsg_link_diag_test(job);
 		break;
 	case LPFC_BSG_VENDOR_GET_MGMT_REV:
 		rc = lpfc_bsg_get_dfc_rev(job);
@@ -3538,6 +4887,8 @@ lpfc_bsg_timeout(struct fc_bsg_job *job)
 		/* the mbox completion handler can now be run */
 		spin_unlock_irqrestore(&phba->ct_ev_lock, flags);
 		job->job_done(job);
+		if (phba->mbox_ext_buf_ctx.state == LPFC_BSG_MBOX_PORT)
+			phba->mbox_ext_buf_ctx.state = LPFC_BSG_MBOX_ABTS;
 		break;
 	case TYPE_MENLO:
 		menlo = &dd_data->context_un.menlo;
diff --git a/drivers/scsi/lpfc/lpfc_bsg.h b/drivers/scsi/lpfc/lpfc_bsg.h
index b542aca6f5ae..c8c2b47ea886 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.h
+++ b/drivers/scsi/lpfc/lpfc_bsg.h
@@ -24,15 +24,17 @@
  * These are the vendor unique structures passed in using the bsg
  * FC_BSG_HST_VENDOR message code type.
  */
-#define LPFC_BSG_VENDOR_SET_CT_EVENT	1
-#define LPFC_BSG_VENDOR_GET_CT_EVENT	2
-#define LPFC_BSG_VENDOR_SEND_MGMT_RESP	3
-#define LPFC_BSG_VENDOR_DIAG_MODE	4
-#define LPFC_BSG_VENDOR_DIAG_TEST	5
-#define LPFC_BSG_VENDOR_GET_MGMT_REV	6
-#define LPFC_BSG_VENDOR_MBOX		7
-#define LPFC_BSG_VENDOR_MENLO_CMD	8
-#define LPFC_BSG_VENDOR_MENLO_DATA	9
+#define LPFC_BSG_VENDOR_SET_CT_EVENT		1
+#define LPFC_BSG_VENDOR_GET_CT_EVENT		2
+#define LPFC_BSG_VENDOR_SEND_MGMT_RESP		3
+#define LPFC_BSG_VENDOR_DIAG_MODE		4
+#define LPFC_BSG_VENDOR_DIAG_RUN_LOOPBACK	5
+#define LPFC_BSG_VENDOR_GET_MGMT_REV		6
+#define LPFC_BSG_VENDOR_MBOX			7
+#define LPFC_BSG_VENDOR_MENLO_CMD		8
+#define LPFC_BSG_VENDOR_MENLO_DATA		9
+#define LPFC_BSG_VENDOR_DIAG_MODE_END		10
+#define LPFC_BSG_VENDOR_LINK_DIAG_TEST		11
 
 struct set_ct_event {
 	uint32_t command;
@@ -67,10 +69,25 @@ struct diag_mode_set {
 	uint32_t timeout;
 };
 
+struct sli4_link_diag {
+	uint32_t command;
+	uint32_t timeout;
+	uint32_t test_id;
+	uint32_t loops;
+	uint32_t test_version;
+	uint32_t error_action;
+};
+
 struct diag_mode_test {
 	uint32_t command;
 };
 
+struct diag_status {
+	uint32_t mbox_status;
+	uint32_t shdr_status;
+	uint32_t shdr_add_status;
+};
+
 #define LPFC_WWNN_TYPE		0
 #define LPFC_WWPN_TYPE		1
 
@@ -92,11 +109,15 @@ struct get_mgmt_rev_reply {
 };
 
 #define BSG_MBOX_SIZE 4096 /* mailbox command plus extended data */
+
+/* BSG mailbox request header */
 struct dfc_mbox_req {
 	uint32_t command;
 	uint32_t mbOffset;
 	uint32_t inExtWLen;
 	uint32_t outExtWLen;
+	uint32_t extMboxTag;
+	uint32_t extSeqNum;
 };
 
 /* Used for menlo command or menlo data. The xri is only used for menlo data */
@@ -171,7 +192,7 @@ struct lpfc_sli_config_mse {
 #define lpfc_mbox_sli_config_mse_len_WORD	buf_len
 };
 
-struct lpfc_sli_config_subcmd_hbd {
+struct lpfc_sli_config_hbd {
 	uint32_t buf_len;
 #define lpfc_mbox_sli_config_ecmn_hbd_len_SHIFT	0
 #define lpfc_mbox_sli_config_ecmn_hbd_len_MASK	0xffffff
@@ -194,21 +215,39 @@ struct lpfc_sli_config_hdr {
 	uint32_t reserved5;
 };
 
-struct lpfc_sli_config_generic {
+struct lpfc_sli_config_emb0_subsys {
 	struct lpfc_sli_config_hdr	sli_config_hdr;
 #define LPFC_MBX_SLI_CONFIG_MAX_MSE     19
 	struct lpfc_sli_config_mse	mse[LPFC_MBX_SLI_CONFIG_MAX_MSE];
+	uint32_t padding;
+	uint32_t word64;
+#define lpfc_emb0_subcmnd_opcode_SHIFT	0
+#define lpfc_emb0_subcmnd_opcode_MASK	0xff
+#define lpfc_emb0_subcmnd_opcode_WORD	word64
+#define lpfc_emb0_subcmnd_subsys_SHIFT	8
+#define lpfc_emb0_subcmnd_subsys_MASK	0xff
+#define lpfc_emb0_subcmnd_subsys_WORD	word64
+/* Subsystem FCOE (0x0C) OpCodes */
+#define SLI_CONFIG_SUBSYS_FCOE		0x0C
+#define FCOE_OPCODE_READ_FCF		0x08
+#define FCOE_OPCODE_ADD_FCF		0x09
 };
 
-struct lpfc_sli_config_subcmnd {
+struct lpfc_sli_config_emb1_subsys {
 	struct lpfc_sli_config_hdr	sli_config_hdr;
 	uint32_t word6;
-#define lpfc_subcmnd_opcode_SHIFT	0
-#define lpfc_subcmnd_opcode_MASK	0xff
-#define lpfc_subcmnd_opcode_WORD	word6
-#define lpfc_subcmnd_subsys_SHIFT	8
-#define lpfc_subcmnd_subsys_MASK	0xff
-#define lpfc_subcmnd_subsys_WORD	word6
+#define lpfc_emb1_subcmnd_opcode_SHIFT	0
+#define lpfc_emb1_subcmnd_opcode_MASK	0xff
+#define lpfc_emb1_subcmnd_opcode_WORD	word6
+#define lpfc_emb1_subcmnd_subsys_SHIFT	8
+#define lpfc_emb1_subcmnd_subsys_MASK	0xff
+#define lpfc_emb1_subcmnd_subsys_WORD	word6
+/* Subsystem COMN (0x01) OpCodes */
+#define SLI_CONFIG_SUBSYS_COMN		0x01
+#define COMN_OPCODE_READ_OBJECT		0xAB
+#define COMN_OPCODE_WRITE_OBJECT	0xAC
+#define COMN_OPCODE_READ_OBJECT_LIST	0xAD
+#define COMN_OPCODE_DELETE_OBJECT	0xAE
 	uint32_t timeout;
 	uint32_t request_length;
 	uint32_t word9;
@@ -222,8 +261,8 @@ struct lpfc_sli_config_subcmnd {
 	uint32_t rd_offset;
 	uint32_t obj_name[26];
 	uint32_t hbd_count;
-#define LPFC_MBX_SLI_CONFIG_MAX_HBD	10
-	struct lpfc_sli_config_subcmd_hbd   hbd[LPFC_MBX_SLI_CONFIG_MAX_HBD];
+#define LPFC_MBX_SLI_CONFIG_MAX_HBD	8
+	struct lpfc_sli_config_hbd	hbd[LPFC_MBX_SLI_CONFIG_MAX_HBD];
 };
 
 struct lpfc_sli_config_mbox {
@@ -235,7 +274,11 @@ struct lpfc_sli_config_mbox {
 #define lpfc_mqe_command_MASK		0x000000FF
 #define lpfc_mqe_command_WORD		word0
 	union {
-		struct lpfc_sli_config_generic	sli_config_generic;
-		struct lpfc_sli_config_subcmnd	sli_config_subcmnd;
+		struct lpfc_sli_config_emb0_subsys sli_config_emb0_subsys;
+		struct lpfc_sli_config_emb1_subsys sli_config_emb1_subsys;
 	} un;
 };
+
+/* driver only */
+#define SLI_CONFIG_NOT_HANDLED		0
+#define SLI_CONFIG_HANDLED		1
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index f0b332f4eedb..fc20c247f36b 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -55,6 +55,8 @@ void lpfc_request_features(struct lpfc_hba *, struct lpfcMboxq *);
 void lpfc_supported_pages(struct lpfcMboxq *);
 void lpfc_pc_sli4_params(struct lpfcMboxq *);
 int lpfc_pc_sli4_params_get(struct lpfc_hba *, LPFC_MBOXQ_t *);
+int lpfc_sli4_mbox_rsrc_extent(struct lpfc_hba *, struct lpfcMboxq *,
+			   uint16_t, uint16_t, bool);
 int lpfc_get_sli4_parameters(struct lpfc_hba *, LPFC_MBOXQ_t *);
 struct lpfc_vport *lpfc_find_vport_by_did(struct lpfc_hba *, uint32_t);
 void lpfc_cleanup_rcv_buffers(struct lpfc_vport *);
@@ -171,6 +173,7 @@ void lpfc_delayed_disc_tmo(unsigned long);
 void lpfc_delayed_disc_timeout_handler(struct lpfc_vport *);
 
 int lpfc_config_port_prep(struct lpfc_hba *);
+void lpfc_update_vport_wwn(struct lpfc_vport *vport);
 int lpfc_config_port_post(struct lpfc_hba *);
 int lpfc_hba_down_prep(struct lpfc_hba *);
 int lpfc_hba_down_post(struct lpfc_hba *);
@@ -365,6 +368,10 @@ extern void lpfc_debugfs_slow_ring_trc(struct lpfc_hba *, char *, uint32_t,
 	uint32_t, uint32_t);
 extern struct lpfc_hbq_init *lpfc_hbq_defs[];
 
+/* SLI4 if_type 2 externs. */
+int lpfc_sli4_alloc_resource_identifiers(struct lpfc_hba *);
+int lpfc_sli4_dealloc_resource_identifiers(struct lpfc_hba *);
+
 /* externs BlockGuard */
 extern char *_dump_buf_data;
 extern unsigned long _dump_buf_data_order;
@@ -429,3 +436,6 @@ void lpfc_cleanup_wt_rrqs(struct lpfc_hba *);
 void lpfc_cleanup_vports_rrqs(struct lpfc_vport *, struct lpfc_nodelist *);
 struct lpfc_node_rrq *lpfc_get_active_rrq(struct lpfc_vport *, uint16_t,
 	uint32_t);
+int lpfc_wr_object(struct lpfc_hba *, struct list_head *, uint32_t, uint32_t *);
+/* functions to support SR-IOV */
+int lpfc_sli_probe_sriov_nr_virtfn(struct lpfc_hba *, int);
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index d9edfd90d7ff..779b88e1469d 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -352,6 +352,8 @@ lpfc_gen_req(struct lpfc_vport *vport, struct lpfc_dmabuf *bmp,
 	icmd->ulpLe = 1;
 	icmd->ulpClass = CLASS3;
 	icmd->ulpContext = ndlp->nlp_rpi;
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		icmd->ulpContext = phba->sli4_hba.rpi_ids[ndlp->nlp_rpi];
 
 	if (phba->sli3_options & LPFC_SLI3_NPIV_ENABLED) {
 		/* For GEN_REQUEST64_CR, use the RPI */
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index c93fca058603..ffe82d169b40 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -1665,7 +1665,8 @@ lpfc_idiag_queinfo_read(struct file *file, char __user *buf, size_t nbytes,
 	/* Get fast-path complete queue information */
 	len += snprintf(pbuffer+len, LPFC_QUE_INFO_GET_BUF_SIZE-len,
 			"Fast-path FCP CQ information:\n");
-	for (fcp_qidx = 0; fcp_qidx < phba->cfg_fcp_eq_count; fcp_qidx++) {
+	fcp_qidx = 0;
+	do {
 		len += snprintf(pbuffer+len, LPFC_QUE_INFO_GET_BUF_SIZE-len,
 				"Associated EQID[%02d]:\n",
 				phba->sli4_hba.fcp_cq[fcp_qidx]->assoc_qid);
@@ -1678,7 +1679,7 @@ lpfc_idiag_queinfo_read(struct file *file, char __user *buf, size_t nbytes,
 				phba->sli4_hba.fcp_cq[fcp_qidx]->entry_size,
 				phba->sli4_hba.fcp_cq[fcp_qidx]->host_index,
 				phba->sli4_hba.fcp_cq[fcp_qidx]->hba_index);
-	}
+	} while (++fcp_qidx < phba->cfg_fcp_eq_count);
 	len += snprintf(pbuffer+len, LPFC_QUE_INFO_GET_BUF_SIZE-len, "\n");
 
 	/* Get mailbox queue information */
@@ -2012,7 +2013,8 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
 			goto pass_check;
 		}
 		/* FCP complete queue */
-		for (qidx = 0; qidx < phba->cfg_fcp_eq_count; qidx++) {
+		qidx = 0;
+		do {
 			if (phba->sli4_hba.fcp_cq[qidx]->queue_id == queid) {
 				/* Sanity check */
 				rc = lpfc_idiag_que_param_check(
@@ -2024,7 +2026,7 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
 						phba->sli4_hba.fcp_cq[qidx];
 				goto pass_check;
 			}
-		}
+		} while (++qidx < phba->cfg_fcp_eq_count);
 		goto error_out;
 		break;
 	case LPFC_IDIAG_MQ:
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index e2c452467c8b..32a084534f3e 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -250,7 +250,7 @@ lpfc_prep_els_iocb(struct lpfc_vport *vport, uint8_t expectRsp,
 		icmd->un.elsreq64.myID = vport->fc_myDID;
 
 		/* For ELS_REQUEST64_CR, use the VPI by default */
-		icmd->ulpContext = vport->vpi + phba->vpi_base;
+		icmd->ulpContext = phba->vpi_ids[vport->vpi];
 		icmd->ulpCt_h = 0;
 		/* The CT field must be 0=INVALID_RPI for the ECHO cmd */
 		if (elscmd == ELS_CMD_ECHO)
@@ -454,6 +454,7 @@ lpfc_issue_reg_vfi(struct lpfc_vport *vport)
 		rc = -ENOMEM;
 		goto fail_free_dmabuf;
 	}
+
 	mboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mboxq) {
 		rc = -ENOMEM;
@@ -6585,6 +6586,26 @@ lpfc_find_vport_by_vpid(struct lpfc_hba *phba, uint16_t vpi)
 {
 	struct lpfc_vport *vport;
 	unsigned long flags;
+	int i;
+
+	/* The physical ports are always vpi 0 - translate is unnecessary. */
+	if (vpi > 0) {
+		/*
+		 * Translate the physical vpi to the logical vpi.  The
+		 * vport stores the logical vpi.
+		 */
+		for (i = 0; i < phba->max_vpi; i++) {
+			if (vpi == phba->vpi_ids[i])
+				break;
+		}
+
+		if (i >= phba->max_vpi) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_ELS,
+					 "2936 Could not find Vport mapped "
+					 "to vpi %d\n", vpi);
+			return NULL;
+		}
+	}
 
 	spin_lock_irqsave(&phba->hbalock, flags);
 	list_for_each_entry(vport, &phba->port_list, listentry) {
@@ -6641,8 +6662,9 @@ lpfc_els_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			vport = phba->pport;
 		else
 			vport = lpfc_find_vport_by_vpid(phba,
-				icmd->unsli3.rcvsli3.vpi - phba->vpi_base);
+						icmd->unsli3.rcvsli3.vpi);
 	}
+
 	/* If there are no BDEs associated
 	 * with this IOCB, there is nothing to do.
 	 */
@@ -7222,7 +7244,7 @@ lpfc_issue_els_fdisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		elsiocb->iocb.ulpCt_h = (SLI4_CT_VPI >> 1) & 1;
 		elsiocb->iocb.ulpCt_l = SLI4_CT_VPI & 1 ;
 		/* Set the ulpContext to the vpi */
-		elsiocb->iocb.ulpContext = vport->vpi + phba->vpi_base;
+		elsiocb->iocb.ulpContext = phba->vpi_ids[vport->vpi];
 	} else {
 		/* For FDISC, Let FDISC rsp set the NPortID for this VPI */
 		icmd->ulpCt_h = 1;
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 7a35df5e2038..18d0dbfda2bc 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -881,7 +881,7 @@ lpfc_linkdown(struct lpfc_hba *phba)
 	/* Clean up any firmware default rpi's */
 	mb = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (mb) {
-		lpfc_unreg_did(phba, 0xffff, 0xffffffff, mb);
+		lpfc_unreg_did(phba, 0xffff, LPFC_UNREG_ALL_DFLT_RPIS, mb);
 		mb->vport = vport;
 		mb->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
 		if (lpfc_sli_issue_mbox(phba, mb, MBX_NOWAIT)
@@ -2690,16 +2690,7 @@ lpfc_mbx_cmpl_read_sparam(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 
 	memcpy((uint8_t *) &vport->fc_sparam, (uint8_t *) mp->virt,
 	       sizeof (struct serv_parm));
-	if (phba->cfg_soft_wwnn)
-		u64_to_wwn(phba->cfg_soft_wwnn,
-			   vport->fc_sparam.nodeName.u.wwn);
-	if (phba->cfg_soft_wwpn)
-		u64_to_wwn(phba->cfg_soft_wwpn,
-			   vport->fc_sparam.portName.u.wwn);
-	memcpy(&vport->fc_nodename, &vport->fc_sparam.nodeName,
-	       sizeof(vport->fc_nodename));
-	memcpy(&vport->fc_portname, &vport->fc_sparam.portName,
-	       sizeof(vport->fc_portname));
+	lpfc_update_vport_wwn(vport);
 	if (vport->port_type == LPFC_PHYSICAL_PORT) {
 		memcpy(&phba->wwnn, &vport->fc_nodename, sizeof(phba->wwnn));
 		memcpy(&phba->wwpn, &vport->fc_portname, sizeof(phba->wwnn));
@@ -3430,7 +3421,8 @@ lpfc_mbx_cmpl_fabric_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		return;
 	}
 
-	ndlp->nlp_rpi = mb->un.varWords[0];
+	if (phba->sli_rev < LPFC_SLI_REV4)
+		ndlp->nlp_rpi = mb->un.varWords[0];
 	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
@@ -3504,7 +3496,8 @@ out:
 		return;
 	}
 
-	ndlp->nlp_rpi = mb->un.varWords[0];
+	if (phba->sli_rev < LPFC_SLI_REV4)
+		ndlp->nlp_rpi = mb->un.varWords[0];
 	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
@@ -3591,7 +3584,6 @@ lpfc_register_remote_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	if (ndlp->nlp_type & NLP_FCP_INITIATOR)
 		rport_ids.roles |= FC_RPORT_ROLE_FCP_INITIATOR;
 
-
 	if (rport_ids.roles !=  FC_RPORT_ROLE_UNKNOWN)
 		fc_remote_port_rolechg(rport, rport_ids.roles);
 
@@ -4106,11 +4098,16 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	struct lpfc_hba *phba = vport->phba;
 	LPFC_MBOXQ_t    *mbox;
 	int rc;
+	uint16_t rpi;
 
 	if (ndlp->nlp_flag & NLP_RPI_REGISTERED) {
 		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 		if (mbox) {
-			lpfc_unreg_login(phba, vport->vpi, ndlp->nlp_rpi, mbox);
+			/* SLI4 ports require the physical rpi value. */
+			rpi = ndlp->nlp_rpi;
+			if (phba->sli_rev == LPFC_SLI_REV4)
+				rpi = phba->sli4_hba.rpi_ids[ndlp->nlp_rpi];
+			lpfc_unreg_login(phba, vport->vpi, rpi, mbox);
 			mbox->vport = vport;
 			mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
 			rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
@@ -4179,7 +4176,8 @@ lpfc_unreg_all_rpis(struct lpfc_vport *vport)
 
 	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (mbox) {
-		lpfc_unreg_login(phba, vport->vpi, 0xffff, mbox);
+		lpfc_unreg_login(phba, vport->vpi, LPFC_UNREG_ALL_RPIS_VPORT,
+				 mbox);
 		mbox->vport = vport;
 		mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
 		mbox->context1 = NULL;
@@ -4203,7 +4201,8 @@ lpfc_unreg_default_rpis(struct lpfc_vport *vport)
 
 	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (mbox) {
-		lpfc_unreg_did(phba, vport->vpi, 0xffffffff, mbox);
+		lpfc_unreg_did(phba, vport->vpi, LPFC_UNREG_ALL_DFLT_RPIS,
+			       mbox);
 		mbox->vport = vport;
 		mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
 		mbox->context1 = NULL;
@@ -4653,10 +4652,7 @@ lpfc_disc_start(struct lpfc_vport *vport)
 	if (num_sent)
 		return;
 
-	/*
-	 * For SLI3, cmpl_reg_vpi will set port_state to READY, and
-	 * continue discovery.
-	 */
+	/* Register the VPI for SLI3, NON-NPIV only. */
 	if ((phba->sli3_options & LPFC_SLI3_NPIV_ENABLED) &&
 	    !(vport->fc_flag & FC_PT2PT) &&
 	    !(vport->fc_flag & FC_RSCN_MODE) &&
@@ -4943,7 +4939,7 @@ restart_disc:
 		if (phba->sli_rev < LPFC_SLI_REV4) {
 			if (phba->sli3_options & LPFC_SLI3_NPIV_ENABLED)
 				lpfc_issue_reg_vpi(phba, vport);
-			else  {	/* NPIV Not enabled */
+			else  {
 				lpfc_issue_clear_la(phba, vport);
 				vport->port_state = LPFC_VPORT_READY;
 			}
@@ -5069,7 +5065,8 @@ lpfc_mbx_cmpl_fdmi_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	pmb->context1 = NULL;
 	pmb->context2 = NULL;
 
-	ndlp->nlp_rpi = mb->un.varWords[0];
+	if (phba->sli_rev < LPFC_SLI_REV4)
+		ndlp->nlp_rpi = mb->un.varWords[0];
 	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
@@ -5354,6 +5351,17 @@ lpfc_fcf_inuse(struct lpfc_hba *phba)
 	for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
 		shost = lpfc_shost_from_vport(vports[i]);
 		spin_lock_irq(shost->host_lock);
+		/*
+		 * IF the CVL_RCVD bit is not set then we have sent the
+		 * flogi.
+		 * If dev_loss fires while we are waiting we do not want to
+		 * unreg the fcf.
+		 */
+		if (!(vports[i]->fc_flag & FC_VPORT_CVL_RCVD)) {
+			spin_unlock_irq(shost->host_lock);
+			ret =  1;
+			goto out;
+		}
 		list_for_each_entry(ndlp, &vports[i]->fc_nodes, nlp_listp) {
 			if (NLP_CHK_NODE_ACT(ndlp) && ndlp->rport &&
 			  (ndlp->rport->roles & FC_RPORT_ROLE_FCP_TARGET)) {
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index 86b6f7e6686a..9059524cf225 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -64,6 +64,8 @@
 #define SLI3_IOCB_CMD_SIZE	128
 #define SLI3_IOCB_RSP_SIZE	64
 
+#define LPFC_UNREG_ALL_RPIS_VPORT	0xffff
+#define LPFC_UNREG_ALL_DFLT_RPIS	0xffffffff
 
 /* vendor ID used in SCSI netlink calls */
 #define LPFC_NL_VENDOR_ID (SCSI_NL_VID_TYPE_PCI | PCI_VENDOR_ID_EMULEX)
@@ -903,6 +905,8 @@ struct RRQ {			/* Structure is in Big Endian format */
 #define rrq_rxid_WORD		rrq_exchg
 };
 
+#define LPFC_MAX_VFN_PER_PFN	255 /* Maximum VFs allowed per ARI */
+#define LPFC_DEF_VFN_PER_PFN	0   /* Default VFs due to platform limitation*/
 
 struct RTV_RSP {		/* Structure is in Big Endian format */
 	uint32_t ratov;
@@ -1199,7 +1203,9 @@ typedef struct {
 #define PCI_DEVICE_ID_BALIUS        0xe131
 #define PCI_DEVICE_ID_PROTEUS_PF    0xe180
 #define PCI_DEVICE_ID_LANCER_FC     0xe200
+#define PCI_DEVICE_ID_LANCER_FC_VF  0xe208
 #define PCI_DEVICE_ID_LANCER_FCOE   0xe260
+#define PCI_DEVICE_ID_LANCER_FCOE_VF 0xe268
 #define PCI_DEVICE_ID_SAT_SMB       0xf011
 #define PCI_DEVICE_ID_SAT_MID       0xf015
 #define PCI_DEVICE_ID_RFLY          0xf095
@@ -3021,7 +3027,7 @@ typedef struct {
 #define MAILBOX_EXT_SIZE	(MAILBOX_EXT_WSIZE * sizeof(uint32_t))
 #define MAILBOX_HBA_EXT_OFFSET  0x100
 /* max mbox xmit size is a page size for sysfs IO operations */
-#define MAILBOX_MAX_XMIT_SIZE   PAGE_SIZE
+#define MAILBOX_SYSFS_MAX	4096
 
 typedef union {
 	uint32_t varWords[MAILBOX_CMD_WSIZE - 1]; /* first word is type/
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 4dff668ebdad..11e26a26b5d1 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -170,6 +170,25 @@ struct lpfc_sli_intf {
 #define LPFC_PCI_FUNC3		3
 #define LPFC_PCI_FUNC4		4
 
+/* SLI4 interface type-2 control register offsets */
+#define LPFC_CTL_PORT_SEM_OFFSET	0x400
+#define LPFC_CTL_PORT_STA_OFFSET	0x404
+#define LPFC_CTL_PORT_CTL_OFFSET	0x408
+#define LPFC_CTL_PORT_ER1_OFFSET	0x40C
+#define LPFC_CTL_PORT_ER2_OFFSET	0x410
+#define LPFC_CTL_PDEV_CTL_OFFSET	0x414
+
+/* Some SLI4 interface type-2 PDEV_CTL register bits */
+#define LPFC_CTL_PDEV_CTL_DRST		0x00000001
+#define LPFC_CTL_PDEV_CTL_FRST		0x00000002
+#define LPFC_CTL_PDEV_CTL_DD		0x00000004
+#define LPFC_CTL_PDEV_CTL_LC		0x00000008
+#define LPFC_CTL_PDEV_CTL_FRL_ALL	0x00
+#define LPFC_CTL_PDEV_CTL_FRL_FC_FCOE	0x10
+#define LPFC_CTL_PDEV_CTL_FRL_NIC	0x20
+
+#define LPFC_FW_DUMP_REQUEST    (LPFC_CTL_PDEV_CTL_DD | LPFC_CTL_PDEV_CTL_FRST)
+
 /* Active interrupt test count */
 #define LPFC_ACT_INTR_CNT	4
 
@@ -210,9 +229,26 @@ struct ulp_bde64 {
 
 struct lpfc_sli4_flags {
 	uint32_t word0;
-#define lpfc_fip_flag_SHIFT 0
-#define lpfc_fip_flag_MASK 0x00000001
-#define lpfc_fip_flag_WORD word0
+#define lpfc_idx_rsrc_rdy_SHIFT		0
+#define lpfc_idx_rsrc_rdy_MASK		0x00000001
+#define lpfc_idx_rsrc_rdy_WORD		word0
+#define LPFC_IDX_RSRC_RDY		1
+#define lpfc_xri_rsrc_rdy_SHIFT		1
+#define lpfc_xri_rsrc_rdy_MASK		0x00000001
+#define lpfc_xri_rsrc_rdy_WORD		word0
+#define LPFC_XRI_RSRC_RDY		1
+#define lpfc_rpi_rsrc_rdy_SHIFT		2
+#define lpfc_rpi_rsrc_rdy_MASK		0x00000001
+#define lpfc_rpi_rsrc_rdy_WORD		word0
+#define LPFC_RPI_RSRC_RDY		1
+#define lpfc_vpi_rsrc_rdy_SHIFT		3
+#define lpfc_vpi_rsrc_rdy_MASK		0x00000001
+#define lpfc_vpi_rsrc_rdy_WORD		word0
+#define LPFC_VPI_RSRC_RDY		1
+#define lpfc_vfi_rsrc_rdy_SHIFT		4
+#define lpfc_vfi_rsrc_rdy_MASK		0x00000001
+#define lpfc_vfi_rsrc_rdy_WORD		word0
+#define LPFC_VFI_RSRC_RDY		1
 };
 
 struct sli4_bls_rsp {
@@ -739,6 +775,12 @@ union lpfc_sli4_cfg_shdr {
 #define lpfc_mbox_hdr_version_SHIFT	0
 #define lpfc_mbox_hdr_version_MASK	0x000000FF
 #define lpfc_mbox_hdr_version_WORD	word9
+#define lpfc_mbox_hdr_pf_num_SHIFT	16
+#define lpfc_mbox_hdr_pf_num_MASK	0x000000FF
+#define lpfc_mbox_hdr_pf_num_WORD	word9
+#define lpfc_mbox_hdr_vh_num_SHIFT	24
+#define lpfc_mbox_hdr_vh_num_MASK	0x000000FF
+#define lpfc_mbox_hdr_vh_num_WORD	word9
 #define LPFC_Q_CREATE_VERSION_2	2
 #define LPFC_Q_CREATE_VERSION_1	1
 #define LPFC_Q_CREATE_VERSION_0	0
@@ -766,12 +808,22 @@ union lpfc_sli4_cfg_shdr {
 	} response;
 };
 
-/* Mailbox structures */
+/* Mailbox Header structures.
+ * struct mbox_header is defined for first generation SLI4_CFG mailbox
+ * calls deployed for BE-based ports.
+ *
+ * struct sli4_mbox_header is defined for second generation SLI4
+ * ports that don't deploy the SLI4_CFG mechanism.
+ */
 struct mbox_header {
 	struct lpfc_sli4_cfg_mhdr cfg_mhdr;
 	union  lpfc_sli4_cfg_shdr cfg_shdr;
 };
 
+#define LPFC_EXTENT_LOCAL		0
+#define LPFC_TIMEOUT_DEFAULT		0
+#define LPFC_EXTENT_VERSION_DEFAULT	0
+
 /* Subsystem Definitions */
 #define LPFC_MBOX_SUBSYSTEM_COMMON	0x1
 #define LPFC_MBOX_SUBSYSTEM_FCOE	0xC
@@ -794,6 +846,13 @@ struct mbox_header {
 #define LPFC_MBOX_OPCODE_QUERY_FW_CFG		0x3A
 #define LPFC_MBOX_OPCODE_FUNCTION_RESET		0x3D
 #define LPFC_MBOX_OPCODE_MQ_CREATE_EXT		0x5A
+#define LPFC_MBOX_OPCODE_GET_RSRC_EXTENT_INFO	0x9A
+#define LPFC_MBOX_OPCODE_GET_ALLOC_RSRC_EXTENT	0x9B
+#define LPFC_MBOX_OPCODE_ALLOC_RSRC_EXTENT	0x9C
+#define LPFC_MBOX_OPCODE_DEALLOC_RSRC_EXTENT	0x9D
+#define LPFC_MBOX_OPCODE_GET_FUNCTION_CONFIG    0xA0
+#define LPFC_MBOX_OPCODE_GET_PROFILE_CONFIG	0xA4
+#define LPFC_MBOX_OPCODE_WRITE_OBJECT		0xAC
 #define LPFC_MBOX_OPCODE_GET_SLI4_PARAMETERS	0xB5
 
 /* FCoE Opcodes */
@@ -808,6 +867,8 @@ struct mbox_header {
 #define LPFC_MBOX_OPCODE_FCOE_DELETE_FCF		0x0A
 #define LPFC_MBOX_OPCODE_FCOE_POST_HDR_TEMPLATE		0x0B
 #define LPFC_MBOX_OPCODE_FCOE_REDISCOVER_FCF		0x10
+#define LPFC_MBOX_OPCODE_FCOE_LINK_DIAG_STATE		0x22
+#define LPFC_MBOX_OPCODE_FCOE_LINK_DIAG_LOOPBACK	0x23
 
 /* Mailbox command structures */
 struct eq_context {
@@ -1210,6 +1271,187 @@ struct lpfc_mbx_mq_destroy {
 	} u;
 };
 
+/* Start Gen 2 SLI4 Mailbox definitions: */
+
+/* Define allocate-ready Gen 2 SLI4 FCoE Resource Extent Types. */
+#define LPFC_RSC_TYPE_FCOE_VFI	0x20
+#define LPFC_RSC_TYPE_FCOE_VPI	0x21
+#define LPFC_RSC_TYPE_FCOE_RPI	0x22
+#define LPFC_RSC_TYPE_FCOE_XRI	0x23
+
+struct lpfc_mbx_get_rsrc_extent_info {
+	struct mbox_header header;
+	union {
+		struct {
+			uint32_t word4;
+#define lpfc_mbx_get_rsrc_extent_info_type_SHIFT	0
+#define lpfc_mbx_get_rsrc_extent_info_type_MASK		0x0000FFFF
+#define lpfc_mbx_get_rsrc_extent_info_type_WORD		word4
+		} req;
+		struct {
+			uint32_t word4;
+#define lpfc_mbx_get_rsrc_extent_info_cnt_SHIFT		0
+#define lpfc_mbx_get_rsrc_extent_info_cnt_MASK		0x0000FFFF
+#define lpfc_mbx_get_rsrc_extent_info_cnt_WORD		word4
+#define lpfc_mbx_get_rsrc_extent_info_size_SHIFT	16
+#define lpfc_mbx_get_rsrc_extent_info_size_MASK		0x0000FFFF
+#define lpfc_mbx_get_rsrc_extent_info_size_WORD		word4
+		} rsp;
+	} u;
+};
+
+struct lpfc_id_range {
+	uint32_t word5;
+#define lpfc_mbx_rsrc_id_word4_0_SHIFT	0
+#define lpfc_mbx_rsrc_id_word4_0_MASK	0x0000FFFF
+#define lpfc_mbx_rsrc_id_word4_0_WORD	word5
+#define lpfc_mbx_rsrc_id_word4_1_SHIFT	16
+#define lpfc_mbx_rsrc_id_word4_1_MASK	0x0000FFFF
+#define lpfc_mbx_rsrc_id_word4_1_WORD	word5
+};
+
+struct lpfc_mbx_set_link_diag_state {
+	struct mbox_header header;
+	union {
+		struct {
+			uint32_t word0;
+#define lpfc_mbx_set_diag_state_diag_SHIFT	0
+#define lpfc_mbx_set_diag_state_diag_MASK	0x00000001
+#define lpfc_mbx_set_diag_state_diag_WORD	word0
+#define lpfc_mbx_set_diag_state_link_num_SHIFT	16
+#define lpfc_mbx_set_diag_state_link_num_MASK	0x0000003F
+#define lpfc_mbx_set_diag_state_link_num_WORD	word0
+#define lpfc_mbx_set_diag_state_link_type_SHIFT 22
+#define lpfc_mbx_set_diag_state_link_type_MASK	0x00000003
+#define lpfc_mbx_set_diag_state_link_type_WORD	word0
+		} req;
+		struct {
+			uint32_t word0;
+		} rsp;
+	} u;
+};
+
+struct lpfc_mbx_set_link_diag_loopback {
+	struct mbox_header header;
+	union {
+		struct {
+			uint32_t word0;
+#define lpfc_mbx_set_diag_lpbk_type_SHIFT	0
+#define lpfc_mbx_set_diag_lpbk_type_MASK	0x00000001
+#define lpfc_mbx_set_diag_lpbk_type_WORD	word0
+#define LPFC_DIAG_LOOPBACK_TYPE_DISABLE		0x0
+#define LPFC_DIAG_LOOPBACK_TYPE_INTERNAL	0x1
+#define LPFC_DIAG_LOOPBACK_TYPE_EXTERNAL	0x2
+#define lpfc_mbx_set_diag_lpbk_link_num_SHIFT	16
+#define lpfc_mbx_set_diag_lpbk_link_num_MASK	0x0000003F
+#define lpfc_mbx_set_diag_lpbk_link_num_WORD	word0
+#define lpfc_mbx_set_diag_lpbk_link_type_SHIFT	22
+#define lpfc_mbx_set_diag_lpbk_link_type_MASK	0x00000003
+#define lpfc_mbx_set_diag_lpbk_link_type_WORD	word0
+		} req;
+		struct {
+			uint32_t word0;
+		} rsp;
+	} u;
+};
+
+struct lpfc_mbx_run_link_diag_test {
+	struct mbox_header header;
+	union {
+		struct {
+			uint32_t word0;
+#define lpfc_mbx_run_diag_test_link_num_SHIFT	16
+#define lpfc_mbx_run_diag_test_link_num_MASK	0x0000003F
+#define lpfc_mbx_run_diag_test_link_num_WORD	word0
+#define lpfc_mbx_run_diag_test_link_type_SHIFT	22
+#define lpfc_mbx_run_diag_test_link_type_MASK	0x00000003
+#define lpfc_mbx_run_diag_test_link_type_WORD	word0
+			uint32_t word1;
+#define lpfc_mbx_run_diag_test_test_id_SHIFT	0
+#define lpfc_mbx_run_diag_test_test_id_MASK	0x0000FFFF
+#define lpfc_mbx_run_diag_test_test_id_WORD	word1
+#define lpfc_mbx_run_diag_test_loops_SHIFT	16
+#define lpfc_mbx_run_diag_test_loops_MASK	0x0000FFFF
+#define lpfc_mbx_run_diag_test_loops_WORD	word1
+			uint32_t word2;
+#define lpfc_mbx_run_diag_test_test_ver_SHIFT	0
+#define lpfc_mbx_run_diag_test_test_ver_MASK	0x0000FFFF
+#define lpfc_mbx_run_diag_test_test_ver_WORD	word2
+#define lpfc_mbx_run_diag_test_err_act_SHIFT	16
+#define lpfc_mbx_run_diag_test_err_act_MASK	0x000000FF
+#define lpfc_mbx_run_diag_test_err_act_WORD	word2
+		} req;
+		struct {
+			uint32_t word0;
+		} rsp;
+	} u;
+};
+
+/*
+ * struct lpfc_mbx_alloc_rsrc_extents:
+ * A mbox is generically 256 bytes long. An SLI4_CONFIG mailbox requires
+ * 6 words of header + 4 words of shared subcommand header +
+ * 1 words of Extent-Opcode-specific header = 11 words or 44 bytes total.
+ *
+ * An embedded version of SLI4_CONFIG therefore has 256 - 44 = 212 bytes
+ * for extents payload.
+ *
+ * 212/2 (bytes per extent) = 106 extents.
+ * 106/2 (extents per word) = 53 words.
+ * lpfc_id_range id is statically size to 53.
+ *
+ * This mailbox definition is used for ALLOC or GET_ALLOCATED
+ * extent ranges.  For ALLOC, the type and cnt are required.
+ * For GET_ALLOCATED, only the type is required.
+ */
+struct lpfc_mbx_alloc_rsrc_extents {
+	struct mbox_header header;
+	union {
+		struct {
+			uint32_t word4;
+#define lpfc_mbx_alloc_rsrc_extents_type_SHIFT	0
+#define lpfc_mbx_alloc_rsrc_extents_type_MASK	0x0000FFFF
+#define lpfc_mbx_alloc_rsrc_extents_type_WORD	word4
+#define lpfc_mbx_alloc_rsrc_extents_cnt_SHIFT	16
+#define lpfc_mbx_alloc_rsrc_extents_cnt_MASK	0x0000FFFF
+#define lpfc_mbx_alloc_rsrc_extents_cnt_WORD	word4
+		} req;
+		struct {
+			uint32_t word4;
+#define lpfc_mbx_rsrc_cnt_SHIFT	0
+#define lpfc_mbx_rsrc_cnt_MASK	0x0000FFFF
+#define lpfc_mbx_rsrc_cnt_WORD	word4
+			struct lpfc_id_range id[53];
+		} rsp;
+	} u;
+};
+
+/*
+ * This is the non-embedded version of ALLOC or GET RSRC_EXTENTS. Word4 in this
+ * structure shares the same SHIFT/MASK/WORD defines provided in the
+ * mbx_alloc_rsrc_extents and mbx_get_alloc_rsrc_extents, word4, provided in
+ * the structures defined above.  This non-embedded structure provides for the
+ * maximum number of extents supported by the port.
+ */
+struct lpfc_mbx_nembed_rsrc_extent {
+	union  lpfc_sli4_cfg_shdr cfg_shdr;
+	uint32_t word4;
+	struct lpfc_id_range id;
+};
+
+struct lpfc_mbx_dealloc_rsrc_extents {
+	struct mbox_header header;
+	struct {
+		uint32_t word4;
+#define lpfc_mbx_dealloc_rsrc_extents_type_SHIFT	0
+#define lpfc_mbx_dealloc_rsrc_extents_type_MASK		0x0000FFFF
+#define lpfc_mbx_dealloc_rsrc_extents_type_WORD		word4
+	} req;
+
+};
+
+/* Start SLI4 FCoE specific mbox structures. */
+
 struct lpfc_mbx_post_hdr_tmpl {
 	struct mbox_header header;
 	uint32_t word10;
@@ -1229,7 +1471,7 @@ struct sli4_sge {	/* SLI-4 */
 
 	uint32_t word2;
 #define lpfc_sli4_sge_offset_SHIFT	0 /* Offset of buffer - Not used*/
-#define lpfc_sli4_sge_offset_MASK	0x00FFFFFF
+#define lpfc_sli4_sge_offset_MASK	0x1FFFFFFF
 #define lpfc_sli4_sge_offset_WORD	word2
 #define lpfc_sli4_sge_last_SHIFT	31 /* Last SEG in the SGL sets
 						this  flag !! */
@@ -1773,61 +2015,31 @@ struct lpfc_mbx_read_rev {
 
 struct lpfc_mbx_read_config {
 	uint32_t word1;
-#define lpfc_mbx_rd_conf_max_bbc_SHIFT		0
-#define lpfc_mbx_rd_conf_max_bbc_MASK		0x000000FF
-#define lpfc_mbx_rd_conf_max_bbc_WORD		word1
-#define lpfc_mbx_rd_conf_init_bbc_SHIFT		8
-#define lpfc_mbx_rd_conf_init_bbc_MASK		0x000000FF
-#define lpfc_mbx_rd_conf_init_bbc_WORD		word1
+#define lpfc_mbx_rd_conf_extnts_inuse_SHIFT	31
+#define lpfc_mbx_rd_conf_extnts_inuse_MASK	0x00000001
+#define lpfc_mbx_rd_conf_extnts_inuse_WORD	word1
 	uint32_t word2;
-#define lpfc_mbx_rd_conf_nport_did_SHIFT	0
-#define lpfc_mbx_rd_conf_nport_did_MASK		0x00FFFFFF
-#define lpfc_mbx_rd_conf_nport_did_WORD		word2
 #define lpfc_mbx_rd_conf_topology_SHIFT		24
 #define lpfc_mbx_rd_conf_topology_MASK		0x000000FF
 #define lpfc_mbx_rd_conf_topology_WORD		word2
-	uint32_t word3;
-#define lpfc_mbx_rd_conf_ao_SHIFT		0
-#define lpfc_mbx_rd_conf_ao_MASK		0x00000001
-#define lpfc_mbx_rd_conf_ao_WORD		word3
-#define lpfc_mbx_rd_conf_bb_scn_SHIFT		8
-#define lpfc_mbx_rd_conf_bb_scn_MASK		0x0000000F
-#define lpfc_mbx_rd_conf_bb_scn_WORD		word3
-#define lpfc_mbx_rd_conf_cbb_scn_SHIFT		12
-#define lpfc_mbx_rd_conf_cbb_scn_MASK		0x0000000F
-#define lpfc_mbx_rd_conf_cbb_scn_WORD		word3
-#define lpfc_mbx_rd_conf_mc_SHIFT		29
-#define lpfc_mbx_rd_conf_mc_MASK		0x00000001
-#define lpfc_mbx_rd_conf_mc_WORD		word3
+	uint32_t rsvd_3;
 	uint32_t word4;
 #define lpfc_mbx_rd_conf_e_d_tov_SHIFT		0
 #define lpfc_mbx_rd_conf_e_d_tov_MASK		0x0000FFFF
 #define lpfc_mbx_rd_conf_e_d_tov_WORD		word4
-	uint32_t word5;
-#define lpfc_mbx_rd_conf_lp_tov_SHIFT		0
-#define lpfc_mbx_rd_conf_lp_tov_MASK		0x0000FFFF
-#define lpfc_mbx_rd_conf_lp_tov_WORD		word5
+	uint32_t rsvd_5;
 	uint32_t word6;
 #define lpfc_mbx_rd_conf_r_a_tov_SHIFT		0
 #define lpfc_mbx_rd_conf_r_a_tov_MASK		0x0000FFFF
 #define lpfc_mbx_rd_conf_r_a_tov_WORD		word6
-	uint32_t word7;
-#define lpfc_mbx_rd_conf_r_t_tov_SHIFT		0
-#define lpfc_mbx_rd_conf_r_t_tov_MASK		0x000000FF
-#define lpfc_mbx_rd_conf_r_t_tov_WORD		word7
-	uint32_t word8;
-#define lpfc_mbx_rd_conf_al_tov_SHIFT		0
-#define lpfc_mbx_rd_conf_al_tov_MASK		0x0000000F
-#define lpfc_mbx_rd_conf_al_tov_WORD		word8
+	uint32_t rsvd_7;
+	uint32_t rsvd_8;
 	uint32_t word9;
 #define lpfc_mbx_rd_conf_lmt_SHIFT		0
 #define lpfc_mbx_rd_conf_lmt_MASK		0x0000FFFF
 #define lpfc_mbx_rd_conf_lmt_WORD		word9
-	uint32_t word10;
-#define lpfc_mbx_rd_conf_max_alpa_SHIFT		0
-#define lpfc_mbx_rd_conf_max_alpa_MASK		0x000000FF
-#define lpfc_mbx_rd_conf_max_alpa_WORD		word10
-	uint32_t word11_rsvd;
+	uint32_t rsvd_10;
+	uint32_t rsvd_11;
 	uint32_t word12;
 #define lpfc_mbx_rd_conf_xri_base_SHIFT		0
 #define lpfc_mbx_rd_conf_xri_base_MASK		0x0000FFFF
@@ -1857,9 +2069,6 @@ struct lpfc_mbx_read_config {
 #define lpfc_mbx_rd_conf_vfi_count_MASK         0x0000FFFF
 #define lpfc_mbx_rd_conf_vfi_count_WORD         word15
 	uint32_t word16;
-#define lpfc_mbx_rd_conf_fcfi_base_SHIFT	0
-#define lpfc_mbx_rd_conf_fcfi_base_MASK		0x0000FFFF
-#define lpfc_mbx_rd_conf_fcfi_base_WORD		word16
 #define lpfc_mbx_rd_conf_fcfi_count_SHIFT	16
 #define lpfc_mbx_rd_conf_fcfi_count_MASK	0x0000FFFF
 #define lpfc_mbx_rd_conf_fcfi_count_WORD	word16
@@ -2169,6 +2378,12 @@ struct lpfc_sli4_parameters {
 #define cfg_fcoe_SHIFT				0
 #define cfg_fcoe_MASK				0x00000001
 #define cfg_fcoe_WORD				word12
+#define cfg_ext_SHIFT				1
+#define cfg_ext_MASK				0x00000001
+#define cfg_ext_WORD				word12
+#define cfg_hdrr_SHIFT				2
+#define cfg_hdrr_MASK				0x00000001
+#define cfg_hdrr_WORD				word12
 #define cfg_phwq_SHIFT				15
 #define cfg_phwq_MASK				0x00000001
 #define cfg_phwq_WORD				word12
@@ -2198,6 +2413,145 @@ struct lpfc_mbx_get_sli4_parameters {
 	struct lpfc_sli4_parameters sli4_parameters;
 };
 
+struct lpfc_rscr_desc_generic {
+#define LPFC_RSRC_DESC_WSIZE			18
+	uint32_t desc[LPFC_RSRC_DESC_WSIZE];
+};
+
+struct lpfc_rsrc_desc_pcie {
+	uint32_t word0;
+#define lpfc_rsrc_desc_pcie_type_SHIFT		0
+#define lpfc_rsrc_desc_pcie_type_MASK		0x000000ff
+#define lpfc_rsrc_desc_pcie_type_WORD		word0
+#define LPFC_RSRC_DESC_TYPE_PCIE		0x40
+	uint32_t word1;
+#define lpfc_rsrc_desc_pcie_pfnum_SHIFT		0
+#define lpfc_rsrc_desc_pcie_pfnum_MASK		0x000000ff
+#define lpfc_rsrc_desc_pcie_pfnum_WORD		word1
+	uint32_t reserved;
+	uint32_t word3;
+#define lpfc_rsrc_desc_pcie_sriov_sta_SHIFT	0
+#define lpfc_rsrc_desc_pcie_sriov_sta_MASK	0x000000ff
+#define lpfc_rsrc_desc_pcie_sriov_sta_WORD	word3
+#define lpfc_rsrc_desc_pcie_pf_sta_SHIFT	8
+#define lpfc_rsrc_desc_pcie_pf_sta_MASK		0x000000ff
+#define lpfc_rsrc_desc_pcie_pf_sta_WORD		word3
+#define lpfc_rsrc_desc_pcie_pf_type_SHIFT	16
+#define lpfc_rsrc_desc_pcie_pf_type_MASK	0x000000ff
+#define lpfc_rsrc_desc_pcie_pf_type_WORD	word3
+	uint32_t word4;
+#define lpfc_rsrc_desc_pcie_nr_virtfn_SHIFT	0
+#define lpfc_rsrc_desc_pcie_nr_virtfn_MASK	0x0000ffff
+#define lpfc_rsrc_desc_pcie_nr_virtfn_WORD	word4
+};
+
+struct lpfc_rsrc_desc_fcfcoe {
+	uint32_t word0;
+#define lpfc_rsrc_desc_fcfcoe_type_SHIFT	0
+#define lpfc_rsrc_desc_fcfcoe_type_MASK		0x000000ff
+#define lpfc_rsrc_desc_fcfcoe_type_WORD		word0
+#define LPFC_RSRC_DESC_TYPE_FCFCOE		0x43
+	uint32_t word1;
+#define lpfc_rsrc_desc_fcfcoe_vfnum_SHIFT	0
+#define lpfc_rsrc_desc_fcfcoe_vfnum_MASK	0x000000ff
+#define lpfc_rsrc_desc_fcfcoe_vfnum_WORD	word1
+#define lpfc_rsrc_desc_fcfcoe_pfnum_SHIFT	16
+#define lpfc_rsrc_desc_fcfcoe_pfnum_MASK        0x000007ff
+#define lpfc_rsrc_desc_fcfcoe_pfnum_WORD        word1
+	uint32_t word2;
+#define lpfc_rsrc_desc_fcfcoe_rpi_cnt_SHIFT	0
+#define lpfc_rsrc_desc_fcfcoe_rpi_cnt_MASK	0x0000ffff
+#define lpfc_rsrc_desc_fcfcoe_rpi_cnt_WORD	word2
+#define lpfc_rsrc_desc_fcfcoe_xri_cnt_SHIFT	16
+#define lpfc_rsrc_desc_fcfcoe_xri_cnt_MASK	0x0000ffff
+#define lpfc_rsrc_desc_fcfcoe_xri_cnt_WORD	word2
+	uint32_t word3;
+#define lpfc_rsrc_desc_fcfcoe_wq_cnt_SHIFT	0
+#define lpfc_rsrc_desc_fcfcoe_wq_cnt_MASK	0x0000ffff
+#define lpfc_rsrc_desc_fcfcoe_wq_cnt_WORD	word3
+#define lpfc_rsrc_desc_fcfcoe_rq_cnt_SHIFT	16
+#define lpfc_rsrc_desc_fcfcoe_rq_cnt_MASK	0x0000ffff
+#define lpfc_rsrc_desc_fcfcoe_rq_cnt_WORD	word3
+	uint32_t word4;
+#define lpfc_rsrc_desc_fcfcoe_cq_cnt_SHIFT	0
+#define lpfc_rsrc_desc_fcfcoe_cq_cnt_MASK	0x0000ffff
+#define lpfc_rsrc_desc_fcfcoe_cq_cnt_WORD	word4
+#define lpfc_rsrc_desc_fcfcoe_vpi_cnt_SHIFT	16
+#define lpfc_rsrc_desc_fcfcoe_vpi_cnt_MASK	0x0000ffff
+#define lpfc_rsrc_desc_fcfcoe_vpi_cnt_WORD	word4
+	uint32_t word5;
+#define lpfc_rsrc_desc_fcfcoe_fcfi_cnt_SHIFT	0
+#define lpfc_rsrc_desc_fcfcoe_fcfi_cnt_MASK	0x0000ffff
+#define lpfc_rsrc_desc_fcfcoe_fcfi_cnt_WORD	word5
+#define lpfc_rsrc_desc_fcfcoe_vfi_cnt_SHIFT	16
+#define lpfc_rsrc_desc_fcfcoe_vfi_cnt_MASK	0x0000ffff
+#define lpfc_rsrc_desc_fcfcoe_vfi_cnt_WORD	word5
+	uint32_t word6;
+	uint32_t word7;
+	uint32_t word8;
+	uint32_t word9;
+	uint32_t word10;
+	uint32_t word11;
+	uint32_t word12;
+	uint32_t word13;
+#define lpfc_rsrc_desc_fcfcoe_lnk_nr_SHIFT	0
+#define lpfc_rsrc_desc_fcfcoe_lnk_nr_MASK	0x0000003f
+#define lpfc_rsrc_desc_fcfcoe_lnk_nr_WORD	word13
+#define lpfc_rsrc_desc_fcfcoe_lnk_tp_SHIFT      6
+#define lpfc_rsrc_desc_fcfcoe_lnk_tp_MASK	0x00000003
+#define lpfc_rsrc_desc_fcfcoe_lnk_tp_WORD	word13
+#define lpfc_rsrc_desc_fcfcoe_lmc_SHIFT		8
+#define lpfc_rsrc_desc_fcfcoe_lmc_MASK		0x00000001
+#define lpfc_rsrc_desc_fcfcoe_lmc_WORD		word13
+#define lpfc_rsrc_desc_fcfcoe_lld_SHIFT		9
+#define lpfc_rsrc_desc_fcfcoe_lld_MASK		0x00000001
+#define lpfc_rsrc_desc_fcfcoe_lld_WORD		word13
+#define lpfc_rsrc_desc_fcfcoe_eq_cnt_SHIFT	16
+#define lpfc_rsrc_desc_fcfcoe_eq_cnt_MASK	0x0000ffff
+#define lpfc_rsrc_desc_fcfcoe_eq_cnt_WORD	word13
+};
+
+struct lpfc_func_cfg {
+#define LPFC_RSRC_DESC_MAX_NUM			2
+	uint32_t rsrc_desc_count;
+	struct lpfc_rscr_desc_generic desc[LPFC_RSRC_DESC_MAX_NUM];
+};
+
+struct lpfc_mbx_get_func_cfg {
+	struct mbox_header header;
+#define LPFC_CFG_TYPE_PERSISTENT_OVERRIDE	0x0
+#define LPFC_CFG_TYPE_FACTURY_DEFAULT		0x1
+#define LPFC_CFG_TYPE_CURRENT_ACTIVE		0x2
+	struct lpfc_func_cfg func_cfg;
+};
+
+struct lpfc_prof_cfg {
+#define LPFC_RSRC_DESC_MAX_NUM			2
+	uint32_t rsrc_desc_count;
+	struct lpfc_rscr_desc_generic desc[LPFC_RSRC_DESC_MAX_NUM];
+};
+
+struct lpfc_mbx_get_prof_cfg {
+	struct mbox_header header;
+#define LPFC_CFG_TYPE_PERSISTENT_OVERRIDE	0x0
+#define LPFC_CFG_TYPE_FACTURY_DEFAULT		0x1
+#define LPFC_CFG_TYPE_CURRENT_ACTIVE		0x2
+	union {
+		struct {
+			uint32_t word10;
+#define lpfc_mbx_get_prof_cfg_prof_id_SHIFT	0
+#define lpfc_mbx_get_prof_cfg_prof_id_MASK	0x000000ff
+#define lpfc_mbx_get_prof_cfg_prof_id_WORD	word10
+#define lpfc_mbx_get_prof_cfg_prof_tp_SHIFT	8
+#define lpfc_mbx_get_prof_cfg_prof_tp_MASK	0x00000003
+#define lpfc_mbx_get_prof_cfg_prof_tp_WORD	word10
+		} request;
+		struct {
+			struct lpfc_prof_cfg prof_cfg;
+		} response;
+	} u;
+};
+
 /* Mailbox Completion Queue Error Messages */
 #define MB_CQE_STATUS_SUCCESS 			0x0
 #define MB_CQE_STATUS_INSUFFICIENT_PRIVILEGES	0x1
@@ -2206,6 +2560,29 @@ struct lpfc_mbx_get_sli4_parameters {
 #define MB_CEQ_STATUS_QUEUE_FLUSHING		0x4
 #define MB_CQE_STATUS_DMA_FAILED		0x5
 
+#define LPFC_MBX_WR_CONFIG_MAX_BDE		8
+struct lpfc_mbx_wr_object {
+	struct mbox_header header;
+	union {
+		struct {
+			uint32_t word4;
+#define lpfc_wr_object_eof_SHIFT		31
+#define lpfc_wr_object_eof_MASK			0x00000001
+#define lpfc_wr_object_eof_WORD			word4
+#define lpfc_wr_object_write_length_SHIFT	0
+#define lpfc_wr_object_write_length_MASK	0x00FFFFFF
+#define lpfc_wr_object_write_length_WORD	word4
+			uint32_t write_offset;
+			uint32_t object_name[26];
+			uint32_t bde_count;
+			struct ulp_bde64 bde[LPFC_MBX_WR_CONFIG_MAX_BDE];
+		} request;
+		struct {
+			uint32_t actual_write_length;
+		} response;
+	} u;
+};
+
 /* mailbox queue entry structure */
 struct lpfc_mqe {
 	uint32_t word0;
@@ -2241,6 +2618,9 @@ struct lpfc_mqe {
 		struct lpfc_mbx_cq_destroy cq_destroy;
 		struct lpfc_mbx_wq_destroy wq_destroy;
 		struct lpfc_mbx_rq_destroy rq_destroy;
+		struct lpfc_mbx_get_rsrc_extent_info rsrc_extent_info;
+		struct lpfc_mbx_alloc_rsrc_extents alloc_rsrc_extents;
+		struct lpfc_mbx_dealloc_rsrc_extents dealloc_rsrc_extents;
 		struct lpfc_mbx_post_sgl_pages post_sgl_pages;
 		struct lpfc_mbx_nembed_cmd nembed_cmd;
 		struct lpfc_mbx_read_rev read_rev;
@@ -2252,7 +2632,13 @@ struct lpfc_mqe {
 		struct lpfc_mbx_supp_pages supp_pages;
 		struct lpfc_mbx_pc_sli4_params sli4_params;
 		struct lpfc_mbx_get_sli4_parameters get_sli4_parameters;
+		struct lpfc_mbx_set_link_diag_state link_diag_state;
+		struct lpfc_mbx_set_link_diag_loopback link_diag_loopback;
+		struct lpfc_mbx_run_link_diag_test link_diag_test;
+		struct lpfc_mbx_get_func_cfg get_func_cfg;
+		struct lpfc_mbx_get_prof_cfg get_prof_cfg;
 		struct lpfc_mbx_nop nop;
+		struct lpfc_mbx_wr_object wr_object;
 	} un;
 };
 
@@ -2458,7 +2844,7 @@ struct lpfc_bmbx_create {
 #define SGL_ALIGN_SZ 64
 #define SGL_PAGE_SIZE 4096
 /* align SGL addr on a size boundary - adjust address up */
-#define NO_XRI  ((uint16_t)-1)
+#define NO_XRI  0xffff
 
 struct wqe_common {
 	uint32_t word6;
@@ -2798,9 +3184,28 @@ union lpfc_wqe {
 	struct gen_req64_wqe gen_req;
 };
 
+#define LPFC_GROUP_OJECT_MAGIC_NUM		0xfeaa0001
+#define LPFC_FILE_TYPE_GROUP			0xf7
+#define LPFC_FILE_ID_GROUP			0xa2
+struct lpfc_grp_hdr {
+	uint32_t size;
+	uint32_t magic_number;
+	uint32_t word2;
+#define lpfc_grp_hdr_file_type_SHIFT	24
+#define lpfc_grp_hdr_file_type_MASK	0x000000FF
+#define lpfc_grp_hdr_file_type_WORD	word2
+#define lpfc_grp_hdr_id_SHIFT		16
+#define lpfc_grp_hdr_id_MASK		0x000000FF
+#define lpfc_grp_hdr_id_WORD		word2
+	uint8_t rev_name[128];
+};
+
 #define FCP_COMMAND 0x0
 #define FCP_COMMAND_DATA_OUT 0x1
 #define ELS_COMMAND_NON_FIP 0xC
 #define ELS_COMMAND_FIP 0xD
 #define OTHER_COMMAND 0x8
 
+#define LPFC_FW_DUMP	1
+#define LPFC_FW_RESET	2
+#define LPFC_DV_RESET	3
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 7dda036a1af3..148b98ddbb1d 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -30,6 +30,7 @@
 #include <linux/ctype.h>
 #include <linux/aer.h>
 #include <linux/slab.h>
+#include <linux/firmware.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_device.h>
@@ -211,7 +212,6 @@ lpfc_config_port_prep(struct lpfc_hba *phba)
 	lpfc_vpd_data = kmalloc(DMP_VPD_SIZE, GFP_KERNEL);
 	if (!lpfc_vpd_data)
 		goto out_free_mbox;
-
 	do {
 		lpfc_dump_mem(phba, pmb, offset, DMP_REGION_VPD);
 		rc = lpfc_sli_issue_mbox(phba, pmb, MBX_POLL);
@@ -309,6 +309,45 @@ lpfc_dump_wakeup_param_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 }
 
 /**
+ * lpfc_update_vport_wwn - Updates the fc_nodename, fc_portname,
+ *	cfg_soft_wwnn, cfg_soft_wwpn
+ * @vport: pointer to lpfc vport data structure.
+ *
+ *
+ * Return codes
+ *   None.
+ **/
+void
+lpfc_update_vport_wwn(struct lpfc_vport *vport)
+{
+	/* If the soft name exists then update it using the service params */
+	if (vport->phba->cfg_soft_wwnn)
+		u64_to_wwn(vport->phba->cfg_soft_wwnn,
+			   vport->fc_sparam.nodeName.u.wwn);
+	if (vport->phba->cfg_soft_wwpn)
+		u64_to_wwn(vport->phba->cfg_soft_wwpn,
+			   vport->fc_sparam.portName.u.wwn);
+
+	/*
+	 * If the name is empty or there exists a soft name
+	 * then copy the service params name, otherwise use the fc name
+	 */
+	if (vport->fc_nodename.u.wwn[0] == 0 || vport->phba->cfg_soft_wwnn)
+		memcpy(&vport->fc_nodename, &vport->fc_sparam.nodeName,
+			sizeof(struct lpfc_name));
+	else
+		memcpy(&vport->fc_sparam.nodeName, &vport->fc_nodename,
+			sizeof(struct lpfc_name));
+
+	if (vport->fc_portname.u.wwn[0] == 0 || vport->phba->cfg_soft_wwpn)
+		memcpy(&vport->fc_portname, &vport->fc_sparam.portName,
+			sizeof(struct lpfc_name));
+	else
+		memcpy(&vport->fc_sparam.portName, &vport->fc_portname,
+			sizeof(struct lpfc_name));
+}
+
+/**
  * lpfc_config_port_post - Perform lpfc initialization after config port
  * @phba: pointer to lpfc hba data structure.
  *
@@ -377,17 +416,7 @@ lpfc_config_port_post(struct lpfc_hba *phba)
 	lpfc_mbuf_free(phba, mp->virt, mp->phys);
 	kfree(mp);
 	pmb->context1 = NULL;
-
-	if (phba->cfg_soft_wwnn)
-		u64_to_wwn(phba->cfg_soft_wwnn,
-			   vport->fc_sparam.nodeName.u.wwn);
-	if (phba->cfg_soft_wwpn)
-		u64_to_wwn(phba->cfg_soft_wwpn,
-			   vport->fc_sparam.portName.u.wwn);
-	memcpy(&vport->fc_nodename, &vport->fc_sparam.nodeName,
-	       sizeof (struct lpfc_name));
-	memcpy(&vport->fc_portname, &vport->fc_sparam.portName,
-	       sizeof (struct lpfc_name));
+	lpfc_update_vport_wwn(vport);
 
 	/* Update the fc_host data structures with new wwn. */
 	fc_host_node_name(shost) = wwn_to_u64(vport->fc_nodename.u.wwn);
@@ -573,7 +602,6 @@ lpfc_config_port_post(struct lpfc_hba *phba)
 			/* Clear all pending interrupts */
 			writel(0xffffffff, phba->HAregaddr);
 			readl(phba->HAregaddr); /* flush */
-
 			phba->link_state = LPFC_HBA_ERROR;
 			if (rc != MBX_BUSY)
 				mempool_free(pmb, phba->mbox_mem_pool);
@@ -1755,7 +1783,9 @@ lpfc_get_hba_model_desc(struct lpfc_hba *phba, uint8_t *mdp, uint8_t *descp)
 		&& descp && descp[0] != '\0')
 		return;
 
-	if (phba->lmt & LMT_10Gb)
+	if (phba->lmt & LMT_16Gb)
+		max_speed = 16;
+	else if (phba->lmt & LMT_10Gb)
 		max_speed = 10;
 	else if (phba->lmt & LMT_8Gb)
 		max_speed = 8;
@@ -1922,12 +1952,13 @@ lpfc_get_hba_model_desc(struct lpfc_hba *phba, uint8_t *mdp, uint8_t *descp)
 				"Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_LANCER_FC:
-		oneConnect = 1;
-		m = (typeof(m)){"Undefined", "PCIe", "Fibre Channel Adapter"};
+	case PCI_DEVICE_ID_LANCER_FC_VF:
+		m = (typeof(m)){"LPe16000", "PCIe", "Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_LANCER_FCOE:
+	case PCI_DEVICE_ID_LANCER_FCOE_VF:
 		oneConnect = 1;
-		m = (typeof(m)){"Undefined", "PCIe", "FCoE"};
+		m = (typeof(m)){"OCe50100", "PCIe", "FCoE"};
 		break;
 	default:
 		m = (typeof(m)){"Unknown", "", ""};
@@ -1936,7 +1967,8 @@ lpfc_get_hba_model_desc(struct lpfc_hba *phba, uint8_t *mdp, uint8_t *descp)
 
 	if (mdp && mdp[0] == '\0')
 		snprintf(mdp, 79,"%s", m.name);
-	/* oneConnect hba requires special processing, they are all initiators
+	/*
+	 * oneConnect hba requires special processing, they are all initiators
 	 * and we put the port number on the end
 	 */
 	if (descp && descp[0] == '\0') {
@@ -2656,6 +2688,7 @@ lpfc_scsi_free(struct lpfc_hba *phba)
 		kfree(io);
 		phba->total_iocbq_bufs--;
 	}
+
 	spin_unlock_irq(&phba->hbalock);
 	return 0;
 }
@@ -3612,6 +3645,7 @@ lpfc_sli4_async_fip_evt(struct lpfc_hba *phba,
 		lpfc_printf_log(phba, KERN_ERR, LOG_FIP | LOG_DISCOVERY,
 			"2718 Clear Virtual Link Received for VPI 0x%x"
 			" tag 0x%x\n", acqe_fip->index, acqe_fip->event_tag);
+
 		vport = lpfc_find_vport_by_vpid(phba,
 				acqe_fip->index - phba->vpi_base);
 		ndlp = lpfc_sli4_perform_vport_cvl(vport);
@@ -3935,6 +3969,10 @@ lpfc_enable_pci_dev(struct lpfc_hba *phba)
 	pci_try_set_mwi(pdev);
 	pci_save_state(pdev);
 
+	/* PCIe EEH recovery on powerpc platforms needs fundamental reset */
+	if (pci_find_capability(pdev, PCI_CAP_ID_EXP))
+		pdev->needs_freset = 1;
+
 	return 0;
 
 out_disable_device:
@@ -3997,6 +4035,36 @@ lpfc_reset_hba(struct lpfc_hba *phba)
 }
 
 /**
+ * lpfc_sli_probe_sriov_nr_virtfn - Enable a number of sr-iov virtual functions
+ * @phba: pointer to lpfc hba data structure.
+ * @nr_vfn: number of virtual functions to be enabled.
+ *
+ * This function enables the PCI SR-IOV virtual functions to a physical
+ * function. It invokes the PCI SR-IOV api with the @nr_vfn provided to
+ * enable the number of virtual functions to the physical function. As
+ * not all devices support SR-IOV, the return code from the pci_enable_sriov()
+ * API call does not considered as an error condition for most of the device.
+ **/
+int
+lpfc_sli_probe_sriov_nr_virtfn(struct lpfc_hba *phba, int nr_vfn)
+{
+	struct pci_dev *pdev = phba->pcidev;
+	int rc;
+
+	rc = pci_enable_sriov(pdev, nr_vfn);
+	if (rc) {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
+				"2806 Failed to enable sriov on this device "
+				"with vfn number nr_vf:%d, rc:%d\n",
+				nr_vfn, rc);
+	} else
+		lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
+				"2807 Successful enable sriov on this device "
+				"with vfn number nr_vf:%d\n", nr_vfn);
+	return rc;
+}
+
+/**
  * lpfc_sli_driver_resource_setup - Setup driver internal resources for SLI3 dev.
  * @phba: pointer to lpfc hba data structure.
  *
@@ -4011,6 +4079,7 @@ static int
 lpfc_sli_driver_resource_setup(struct lpfc_hba *phba)
 {
 	struct lpfc_sli *psli;
+	int rc;
 
 	/*
 	 * Initialize timers used by driver
@@ -4085,6 +4154,23 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba)
 	if (lpfc_mem_alloc(phba, BPL_ALIGN_SZ))
 		return -ENOMEM;
 
+	/*
+	 * Enable sr-iov virtual functions if supported and configured
+	 * through the module parameter.
+	 */
+	if (phba->cfg_sriov_nr_virtfn > 0) {
+		rc = lpfc_sli_probe_sriov_nr_virtfn(phba,
+						 phba->cfg_sriov_nr_virtfn);
+		if (rc) {
+			lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
+					"2808 Requested number of SR-IOV "
+					"virtual functions (%d) is not "
+					"supported\n",
+					phba->cfg_sriov_nr_virtfn);
+			phba->cfg_sriov_nr_virtfn = 0;
+		}
+	}
+
 	return 0;
 }
 
@@ -4161,6 +4247,14 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	phba->fcf.redisc_wait.data = (unsigned long)phba;
 
 	/*
+	 * Control structure for handling external multi-buffer mailbox
+	 * command pass-through.
+	 */
+	memset((uint8_t *)&phba->mbox_ext_buf_ctx, 0,
+		sizeof(struct lpfc_mbox_ext_buf_ctx));
+	INIT_LIST_HEAD(&phba->mbox_ext_buf_ctx.ext_dmabuf_list);
+
+	/*
 	 * We need to do a READ_CONFIG mailbox command here before
 	 * calling lpfc_get_cfgparam. For VFs this will report the
 	 * MAX_XRI, MAX_VPI, MAX_RPI, MAX_IOCB, and MAX_VFI settings.
@@ -4233,7 +4327,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	spin_lock_init(&phba->sli4_hba.abts_sgl_list_lock);
 
 	/*
-	 * Initialize dirver internal slow-path work queues
+	 * Initialize driver internal slow-path work queues
 	 */
 
 	/* Driver internel slow-path CQ Event pool */
@@ -4249,6 +4343,12 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	/* Receive queue CQ Event work queue list */
 	INIT_LIST_HEAD(&phba->sli4_hba.sp_unsol_work_queue);
 
+	/* Initialize extent block lists. */
+	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_rpi_blk_list);
+	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_xri_blk_list);
+	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_vfi_blk_list);
+	INIT_LIST_HEAD(&phba->lpfc_vpi_blk_list);
+
 	/* Initialize the driver internal SLI layer lists. */
 	lpfc_sli_setup(phba);
 	lpfc_sli_queue_setup(phba);
@@ -4323,9 +4423,19 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	}
 	/*
 	 * Get sli4 parameters that override parameters from Port capabilities.
-	 * If this call fails it is not a critical error so continue loading.
+	 * If this call fails, it isn't critical unless the SLI4 parameters come
+	 * back in conflict.
 	 */
-	lpfc_get_sli4_parameters(phba, mboxq);
+	rc = lpfc_get_sli4_parameters(phba, mboxq);
+	if (rc) {
+		if (phba->sli4_hba.extents_in_use &&
+		    phba->sli4_hba.rpi_hdrs_in_use) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"2999 Unsupported SLI4 Parameters "
+				"Extents and RPI headers enabled.\n");
+			goto out_free_bsmbx;
+		}
+	}
 	mempool_free(mboxq, phba->mbox_mem_pool);
 	/* Create all the SLI4 queues */
 	rc = lpfc_sli4_queue_create(phba);
@@ -4350,7 +4460,6 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 				"1430 Failed to initialize sgl list.\n");
 		goto out_free_sgl_list;
 	}
-
 	rc = lpfc_sli4_init_rpi_hdrs(phba);
 	if (rc) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
@@ -4366,6 +4475,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"2759 Failed allocate memory for FCF round "
 				"robin failover bmask\n");
+		rc = -ENOMEM;
 		goto out_remove_rpi_hdrs;
 	}
 
@@ -4375,6 +4485,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"2572 Failed allocate memory for fast-path "
 				"per-EQ handle array\n");
+		rc = -ENOMEM;
 		goto out_free_fcf_rr_bmask;
 	}
 
@@ -4384,9 +4495,27 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"2573 Failed allocate memory for msi-x "
 				"interrupt vector entries\n");
+		rc = -ENOMEM;
 		goto out_free_fcp_eq_hdl;
 	}
 
+	/*
+	 * Enable sr-iov virtual functions if supported and configured
+	 * through the module parameter.
+	 */
+	if (phba->cfg_sriov_nr_virtfn > 0) {
+		rc = lpfc_sli_probe_sriov_nr_virtfn(phba,
+						 phba->cfg_sriov_nr_virtfn);
+		if (rc) {
+			lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
+					"3020 Requested number of SR-IOV "
+					"virtual functions (%d) is not "
+					"supported\n",
+					phba->cfg_sriov_nr_virtfn);
+			phba->cfg_sriov_nr_virtfn = 0;
+		}
+	}
+
 	return rc;
 
 out_free_fcp_eq_hdl:
@@ -4449,6 +4578,9 @@ lpfc_sli4_driver_resource_unset(struct lpfc_hba *phba)
 	lpfc_sli4_cq_event_release_all(phba);
 	lpfc_sli4_cq_event_pool_destroy(phba);
 
+	/* Release resource identifiers. */
+	lpfc_sli4_dealloc_resource_identifiers(phba);
+
 	/* Free the bsmbx region. */
 	lpfc_destroy_bootstrap_mbox(phba);
 
@@ -4649,6 +4781,7 @@ lpfc_init_iocb_list(struct lpfc_hba *phba, int iocb_count)
 				"Unloading driver.\n", __func__);
 			goto out_free_iocbq;
 		}
+		iocbq_entry->sli4_lxritag = NO_XRI;
 		iocbq_entry->sli4_xritag = NO_XRI;
 
 		spin_lock_irq(&phba->hbalock);
@@ -4746,7 +4879,7 @@ lpfc_init_sgl_list(struct lpfc_hba *phba)
 
 	els_xri_cnt = lpfc_sli4_get_els_iocb_cnt(phba);
 	lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
-				"2400 lpfc_init_sgl_list els %d.\n",
+				"2400 ELS XRI count %d.\n",
 				els_xri_cnt);
 	/* Initialize and populate the sglq list per host/VF. */
 	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_sgl_list);
@@ -4779,7 +4912,6 @@ lpfc_init_sgl_list(struct lpfc_hba *phba)
 	phba->sli4_hba.scsi_xri_max =
 			phba->sli4_hba.max_cfg_param.max_xri - els_xri_cnt;
 	phba->sli4_hba.scsi_xri_cnt = 0;
-
 	phba->sli4_hba.lpfc_scsi_psb_array =
 			kzalloc((sizeof(struct lpfc_scsi_buf *) *
 			phba->sli4_hba.scsi_xri_max), GFP_KERNEL);
@@ -4802,13 +4934,6 @@ lpfc_init_sgl_list(struct lpfc_hba *phba)
 			goto out_free_mem;
 		}
 
-		sglq_entry->sli4_xritag = lpfc_sli4_next_xritag(phba);
-		if (sglq_entry->sli4_xritag == NO_XRI) {
-			kfree(sglq_entry);
-			printk(KERN_ERR "%s: failed to allocate XRI.\n"
-				"Unloading driver.\n", __func__);
-			goto out_free_mem;
-		}
 		sglq_entry->buff_type = GEN_BUFF_TYPE;
 		sglq_entry->virt = lpfc_mbuf_alloc(phba, 0, &sglq_entry->phys);
 		if (sglq_entry->virt == NULL) {
@@ -4857,24 +4982,20 @@ int
 lpfc_sli4_init_rpi_hdrs(struct lpfc_hba *phba)
 {
 	int rc = 0;
-	int longs;
-	uint16_t rpi_count;
 	struct lpfc_rpi_hdr *rpi_hdr;
 
 	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_rpi_hdr_list);
-
 	/*
-	 * Provision an rpi bitmask range for discovery. The total count
-	 * is the difference between max and base + 1.
+	 * If the SLI4 port supports extents, posting the rpi header isn't
+	 * required.  Set the expected maximum count and let the actual value
+	 * get set when extents are fully allocated.
 	 */
-	rpi_count = phba->sli4_hba.max_cfg_param.rpi_base +
-		    phba->sli4_hba.max_cfg_param.max_rpi - 1;
-
-	longs = ((rpi_count) + BITS_PER_LONG - 1) / BITS_PER_LONG;
-	phba->sli4_hba.rpi_bmask = kzalloc(longs * sizeof(unsigned long),
-					   GFP_KERNEL);
-	if (!phba->sli4_hba.rpi_bmask)
-		return -ENOMEM;
+	if (!phba->sli4_hba.rpi_hdrs_in_use) {
+		phba->sli4_hba.next_rpi = phba->sli4_hba.max_cfg_param.max_rpi;
+		return rc;
+	}
+	if (phba->sli4_hba.extents_in_use)
+		return -EIO;
 
 	rpi_hdr = lpfc_sli4_create_rpi_hdr(phba);
 	if (!rpi_hdr) {
@@ -4908,11 +5029,28 @@ lpfc_sli4_create_rpi_hdr(struct lpfc_hba *phba)
 	struct lpfc_rpi_hdr *rpi_hdr;
 	uint32_t rpi_count;
 
+	/*
+	 * If the SLI4 port supports extents, posting the rpi header isn't
+	 * required.  Set the expected maximum count and let the actual value
+	 * get set when extents are fully allocated.
+	 */
+	if (!phba->sli4_hba.rpi_hdrs_in_use)
+		return NULL;
+	if (phba->sli4_hba.extents_in_use)
+		return NULL;
+
+	/* The limit on the logical index is just the max_rpi count. */
 	rpi_limit = phba->sli4_hba.max_cfg_param.rpi_base +
-		    phba->sli4_hba.max_cfg_param.max_rpi - 1;
+	phba->sli4_hba.max_cfg_param.max_rpi - 1;
 
 	spin_lock_irq(&phba->hbalock);
-	curr_rpi_range = phba->sli4_hba.next_rpi;
+	/*
+	 * Establish the starting RPI in this header block.  The starting
+	 * rpi is normalized to a zero base because the physical rpi is
+	 * port based.
+	 */
+	curr_rpi_range = phba->sli4_hba.next_rpi -
+		phba->sli4_hba.max_cfg_param.rpi_base;
 	spin_unlock_irq(&phba->hbalock);
 
 	/*
@@ -4925,6 +5063,8 @@ lpfc_sli4_create_rpi_hdr(struct lpfc_hba *phba)
 	else
 		rpi_count = LPFC_RPI_HDR_COUNT;
 
+	if (!rpi_count)
+		return NULL;
 	/*
 	 * First allocate the protocol header region for the port.  The
 	 * port expects a 4KB DMA-mapped memory region that is 4K aligned.
@@ -4957,12 +5097,14 @@ lpfc_sli4_create_rpi_hdr(struct lpfc_hba *phba)
 	rpi_hdr->len = LPFC_HDR_TEMPLATE_SIZE;
 	rpi_hdr->page_count = 1;
 	spin_lock_irq(&phba->hbalock);
-	rpi_hdr->start_rpi = phba->sli4_hba.next_rpi;
+
+	/* The rpi_hdr stores the logical index only. */
+	rpi_hdr->start_rpi = curr_rpi_range;
 	list_add_tail(&rpi_hdr->list, &phba->sli4_hba.lpfc_rpi_hdr_list);
 
 	/*
-	 * The next_rpi stores the next module-64 rpi value to post
-	 * in any subsequent rpi memory region postings.
+	 * The next_rpi stores the next logical module-64 rpi value used
+	 * to post physical rpis in subsequent rpi postings.
 	 */
 	phba->sli4_hba.next_rpi += rpi_count;
 	spin_unlock_irq(&phba->hbalock);
@@ -4981,15 +5123,18 @@ lpfc_sli4_create_rpi_hdr(struct lpfc_hba *phba)
  * @phba: pointer to lpfc hba data structure.
  *
  * This routine is invoked to remove all memory resources allocated
- * to support rpis. This routine presumes the caller has released all
- * rpis consumed by fabric or port logins and is prepared to have
- * the header pages removed.
+ * to support rpis for SLI4 ports not supporting extents. This routine
+ * presumes the caller has released all rpis consumed by fabric or port
+ * logins and is prepared to have the header pages removed.
  **/
 void
 lpfc_sli4_remove_rpi_hdrs(struct lpfc_hba *phba)
 {
 	struct lpfc_rpi_hdr *rpi_hdr, *next_rpi_hdr;
 
+	if (!phba->sli4_hba.rpi_hdrs_in_use)
+		goto exit;
+
 	list_for_each_entry_safe(rpi_hdr, next_rpi_hdr,
 				 &phba->sli4_hba.lpfc_rpi_hdr_list, list) {
 		list_del(&rpi_hdr->list);
@@ -4998,9 +5143,9 @@ lpfc_sli4_remove_rpi_hdrs(struct lpfc_hba *phba)
 		kfree(rpi_hdr->dmabuf);
 		kfree(rpi_hdr);
 	}
-
-	phba->sli4_hba.next_rpi = phba->sli4_hba.max_cfg_param.rpi_base;
-	memset(phba->sli4_hba.rpi_bmask, 0, sizeof(*phba->sli4_hba.rpi_bmask));
+ exit:
+	/* There are no rpis available to the port now. */
+	phba->sli4_hba.next_rpi = 0;
 }
 
 /**
@@ -5487,7 +5632,8 @@ lpfc_sli4_post_status_check(struct lpfc_hba *phba)
 			/* Final checks.  The port status should be clean. */
 			if (lpfc_readl(phba->sli4_hba.u.if_type2.STATUSregaddr,
 				&reg_data.word0) ||
-				bf_get(lpfc_sliport_status_err, &reg_data)) {
+				(bf_get(lpfc_sliport_status_err, &reg_data) &&
+				 !bf_get(lpfc_sliport_status_rn, &reg_data))) {
 				phba->work_status[0] =
 					readl(phba->sli4_hba.u.if_type2.
 					      ERR1regaddr);
@@ -5741,7 +5887,12 @@ lpfc_sli4_read_config(struct lpfc_hba *phba)
 {
 	LPFC_MBOXQ_t *pmb;
 	struct lpfc_mbx_read_config *rd_config;
-	uint32_t rc = 0;
+	union  lpfc_sli4_cfg_shdr *shdr;
+	uint32_t shdr_status, shdr_add_status;
+	struct lpfc_mbx_get_func_cfg *get_func_cfg;
+	struct lpfc_rsrc_desc_fcfcoe *desc;
+	uint32_t desc_count;
+	int length, i, rc = 0;
 
 	pmb = (LPFC_MBOXQ_t *) mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!pmb) {
@@ -5763,6 +5914,8 @@ lpfc_sli4_read_config(struct lpfc_hba *phba)
 		rc = -EIO;
 	} else {
 		rd_config = &pmb->u.mqe.un.rd_config;
+		phba->sli4_hba.extents_in_use =
+			bf_get(lpfc_mbx_rd_conf_extnts_inuse, rd_config);
 		phba->sli4_hba.max_cfg_param.max_xri =
 			bf_get(lpfc_mbx_rd_conf_xri_count, rd_config);
 		phba->sli4_hba.max_cfg_param.xri_base =
@@ -5781,8 +5934,6 @@ lpfc_sli4_read_config(struct lpfc_hba *phba)
 			bf_get(lpfc_mbx_rd_conf_vfi_base, rd_config);
 		phba->sli4_hba.max_cfg_param.max_fcfi =
 			bf_get(lpfc_mbx_rd_conf_fcfi_count, rd_config);
-		phba->sli4_hba.max_cfg_param.fcfi_base =
-			bf_get(lpfc_mbx_rd_conf_fcfi_base, rd_config);
 		phba->sli4_hba.max_cfg_param.max_eq =
 			bf_get(lpfc_mbx_rd_conf_eq_count, rd_config);
 		phba->sli4_hba.max_cfg_param.max_rq =
@@ -5800,11 +5951,13 @@ lpfc_sli4_read_config(struct lpfc_hba *phba)
 				(phba->sli4_hba.max_cfg_param.max_vpi - 1) : 0;
 		phba->max_vports = phba->max_vpi;
 		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
-				"2003 cfg params XRI(B:%d M:%d), "
+				"2003 cfg params Extents? %d "
+				"XRI(B:%d M:%d), "
 				"VPI(B:%d M:%d) "
 				"VFI(B:%d M:%d) "
 				"RPI(B:%d M:%d) "
-				"FCFI(B:%d M:%d)\n",
+				"FCFI(Count:%d)\n",
+				phba->sli4_hba.extents_in_use,
 				phba->sli4_hba.max_cfg_param.xri_base,
 				phba->sli4_hba.max_cfg_param.max_xri,
 				phba->sli4_hba.max_cfg_param.vpi_base,
@@ -5813,10 +5966,11 @@ lpfc_sli4_read_config(struct lpfc_hba *phba)
 				phba->sli4_hba.max_cfg_param.max_vfi,
 				phba->sli4_hba.max_cfg_param.rpi_base,
 				phba->sli4_hba.max_cfg_param.max_rpi,
-				phba->sli4_hba.max_cfg_param.fcfi_base,
 				phba->sli4_hba.max_cfg_param.max_fcfi);
 	}
-	mempool_free(pmb, phba->mbox_mem_pool);
+
+	if (rc)
+		goto read_cfg_out;
 
 	/* Reset the DFT_HBA_Q_DEPTH to the max xri  */
 	if (phba->cfg_hba_queue_depth >
@@ -5825,6 +5979,65 @@ lpfc_sli4_read_config(struct lpfc_hba *phba)
 		phba->cfg_hba_queue_depth =
 			phba->sli4_hba.max_cfg_param.max_xri -
 				lpfc_sli4_get_els_iocb_cnt(phba);
+
+	if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
+	    LPFC_SLI_INTF_IF_TYPE_2)
+		goto read_cfg_out;
+
+	/* get the pf# and vf# for SLI4 if_type 2 port */
+	length = (sizeof(struct lpfc_mbx_get_func_cfg) -
+		  sizeof(struct lpfc_sli4_cfg_mhdr));
+	lpfc_sli4_config(phba, pmb, LPFC_MBOX_SUBSYSTEM_COMMON,
+			 LPFC_MBOX_OPCODE_GET_FUNCTION_CONFIG,
+			 length, LPFC_SLI4_MBX_EMBED);
+
+	rc = lpfc_sli_issue_mbox(phba, pmb, MBX_POLL);
+	shdr = (union lpfc_sli4_cfg_shdr *)
+				&pmb->u.mqe.un.sli4_config.header.cfg_shdr;
+	shdr_status = bf_get(lpfc_mbox_hdr_status, &shdr->response);
+	shdr_add_status = bf_get(lpfc_mbox_hdr_add_status, &shdr->response);
+	if (rc || shdr_status || shdr_add_status) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+				"3026 Mailbox failed , mbxCmd x%x "
+				"GET_FUNCTION_CONFIG, mbxStatus x%x\n",
+				bf_get(lpfc_mqe_command, &pmb->u.mqe),
+				bf_get(lpfc_mqe_status, &pmb->u.mqe));
+		rc = -EIO;
+		goto read_cfg_out;
+	}
+
+	/* search for fc_fcoe resrouce descriptor */
+	get_func_cfg = &pmb->u.mqe.un.get_func_cfg;
+	desc_count = get_func_cfg->func_cfg.rsrc_desc_count;
+
+	for (i = 0; i < LPFC_RSRC_DESC_MAX_NUM; i++) {
+		desc = (struct lpfc_rsrc_desc_fcfcoe *)
+			&get_func_cfg->func_cfg.desc[i];
+		if (LPFC_RSRC_DESC_TYPE_FCFCOE ==
+		    bf_get(lpfc_rsrc_desc_pcie_type, desc)) {
+			phba->sli4_hba.iov.pf_number =
+				bf_get(lpfc_rsrc_desc_fcfcoe_pfnum, desc);
+			phba->sli4_hba.iov.vf_number =
+				bf_get(lpfc_rsrc_desc_fcfcoe_vfnum, desc);
+			break;
+		}
+	}
+
+	if (i < LPFC_RSRC_DESC_MAX_NUM)
+		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
+				"3027 GET_FUNCTION_CONFIG: pf_number:%d, "
+				"vf_number:%d\n", phba->sli4_hba.iov.pf_number,
+				phba->sli4_hba.iov.vf_number);
+	else {
+		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+				"3028 GET_FUNCTION_CONFIG: failed to find "
+				"Resrouce Descriptor:x%x\n",
+				LPFC_RSRC_DESC_TYPE_FCFCOE);
+		rc = -EIO;
+	}
+
+read_cfg_out:
+	mempool_free(pmb, phba->mbox_mem_pool);
 	return rc;
 }
 
@@ -6229,8 +6442,10 @@ lpfc_sli4_queue_destroy(struct lpfc_hba *phba)
 	phba->sli4_hba.mbx_cq = NULL;
 
 	/* Release FCP response complete queue */
-	for (fcp_qidx = 0; fcp_qidx < phba->cfg_fcp_eq_count; fcp_qidx++)
+	fcp_qidx = 0;
+	do
 		lpfc_sli4_queue_free(phba->sli4_hba.fcp_cq[fcp_qidx]);
+	while (++fcp_qidx < phba->cfg_fcp_eq_count);
 	kfree(phba->sli4_hba.fcp_cq);
 	phba->sli4_hba.fcp_cq = NULL;
 
@@ -6353,16 +6568,24 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 			phba->sli4_hba.sp_eq->queue_id);
 
 	/* Set up fast-path FCP Response Complete Queue */
-	for (fcp_cqidx = 0; fcp_cqidx < phba->cfg_fcp_eq_count; fcp_cqidx++) {
+	fcp_cqidx = 0;
+	do {
 		if (!phba->sli4_hba.fcp_cq[fcp_cqidx]) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 					"0526 Fast-path FCP CQ (%d) not "
 					"allocated\n", fcp_cqidx);
 			goto out_destroy_fcp_cq;
 		}
-		rc = lpfc_cq_create(phba, phba->sli4_hba.fcp_cq[fcp_cqidx],
-				    phba->sli4_hba.fp_eq[fcp_cqidx],
-				    LPFC_WCQ, LPFC_FCP);
+		if (phba->cfg_fcp_eq_count)
+			rc = lpfc_cq_create(phba,
+					    phba->sli4_hba.fcp_cq[fcp_cqidx],
+					    phba->sli4_hba.fp_eq[fcp_cqidx],
+					    LPFC_WCQ, LPFC_FCP);
+		else
+			rc = lpfc_cq_create(phba,
+					    phba->sli4_hba.fcp_cq[fcp_cqidx],
+					    phba->sli4_hba.sp_eq,
+					    LPFC_WCQ, LPFC_FCP);
 		if (rc) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 					"0527 Failed setup of fast-path FCP "
@@ -6371,12 +6594,15 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 		}
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"2588 FCP CQ setup: cq[%d]-id=%d, "
-				"parent eq[%d]-id=%d\n",
+				"parent %seq[%d]-id=%d\n",
 				fcp_cqidx,
 				phba->sli4_hba.fcp_cq[fcp_cqidx]->queue_id,
+				(phba->cfg_fcp_eq_count) ? "" : "sp_",
 				fcp_cqidx,
-				phba->sli4_hba.fp_eq[fcp_cqidx]->queue_id);
-	}
+				(phba->cfg_fcp_eq_count) ?
+				   phba->sli4_hba.fp_eq[fcp_cqidx]->queue_id :
+				   phba->sli4_hba.sp_eq->queue_id);
+	} while (++fcp_cqidx < phba->cfg_fcp_eq_count);
 
 	/*
 	 * Set up all the Work Queues (WQs)
@@ -6445,7 +6671,9 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 				fcp_cq_index,
 				phba->sli4_hba.fcp_cq[fcp_cq_index]->queue_id);
 		/* Round robin FCP Work Queue's Completion Queue assignment */
-		fcp_cq_index = ((fcp_cq_index + 1) % phba->cfg_fcp_eq_count);
+		if (phba->cfg_fcp_eq_count)
+			fcp_cq_index = ((fcp_cq_index + 1) %
+					phba->cfg_fcp_eq_count);
 	}
 
 	/*
@@ -6827,6 +7055,8 @@ lpfc_pci_function_reset(struct lpfc_hba *phba)
 			if (rdy_chk < 1000)
 				break;
 		}
+		/* delay driver action following IF_TYPE_2 function reset */
+		msleep(100);
 		break;
 	case LPFC_SLI_INTF_IF_TYPE_1:
 	default:
@@ -7419,11 +7649,15 @@ enable_msix_vectors:
 	/*
 	 * Assign MSI-X vectors to interrupt handlers
 	 */
-
-	/* The first vector must associated to slow-path handler for MQ */
-	rc = request_irq(phba->sli4_hba.msix_entries[0].vector,
-			 &lpfc_sli4_sp_intr_handler, IRQF_SHARED,
-			 LPFC_SP_DRIVER_HANDLER_NAME, phba);
+	if (vectors > 1)
+		rc = request_irq(phba->sli4_hba.msix_entries[0].vector,
+				 &lpfc_sli4_sp_intr_handler, IRQF_SHARED,
+				 LPFC_SP_DRIVER_HANDLER_NAME, phba);
+	else
+		/* All Interrupts need to be handled by one EQ */
+		rc = request_irq(phba->sli4_hba.msix_entries[0].vector,
+				 &lpfc_sli4_intr_handler, IRQF_SHARED,
+				 LPFC_DRIVER_NAME, phba);
 	if (rc) {
 		lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
 				"0485 MSI-X slow-path request_irq failed "
@@ -7765,6 +7999,7 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba)
 {
 	int wait_cnt = 0;
 	LPFC_MBOXQ_t *mboxq;
+	struct pci_dev *pdev = phba->pcidev;
 
 	lpfc_stop_hba_timers(phba);
 	phba->sli4_hba.intr_enable = 0;
@@ -7804,6 +8039,10 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba)
 	/* Disable PCI subsystem interrupt */
 	lpfc_sli4_disable_intr(phba);
 
+	/* Disable SR-IOV if enabled */
+	if (phba->cfg_sriov_nr_virtfn)
+		pci_disable_sriov(pdev);
+
 	/* Stop kthread signal shall trigger work_done one more time */
 	kthread_stop(phba->worker_thread);
 
@@ -7878,6 +8117,11 @@ lpfc_pc_sli4_params_get(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 	sli4_params->hdr_pp_align = bf_get(hdr_pp_align, &mqe->un.sli4_params);
 	sli4_params->sgl_pages_max = bf_get(sgl_pages, &mqe->un.sli4_params);
 	sli4_params->sgl_pp_align = bf_get(sgl_pp_align, &mqe->un.sli4_params);
+
+	/* Make sure that sge_supp_len can be handled by the driver */
+	if (sli4_params->sge_supp_len > LPFC_MAX_SGE_SIZE)
+		sli4_params->sge_supp_len = LPFC_MAX_SGE_SIZE;
+
 	return rc;
 }
 
@@ -7902,6 +8146,13 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 	int length;
 	struct lpfc_sli4_parameters *mbx_sli4_parameters;
 
+	/*
+	 * By default, the driver assumes the SLI4 port requires RPI
+	 * header postings.  The SLI4_PARAM response will correct this
+	 * assumption.
+	 */
+	phba->sli4_hba.rpi_hdrs_in_use = 1;
+
 	/* Read the port's SLI4 Config Parameters */
 	length = (sizeof(struct lpfc_mbx_get_sli4_parameters) -
 		  sizeof(struct lpfc_sli4_cfg_mhdr));
@@ -7938,6 +8189,13 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 					    mbx_sli4_parameters);
 	sli4_params->sgl_pp_align = bf_get(cfg_sgl_pp_align,
 					   mbx_sli4_parameters);
+	phba->sli4_hba.extents_in_use = bf_get(cfg_ext, mbx_sli4_parameters);
+	phba->sli4_hba.rpi_hdrs_in_use = bf_get(cfg_hdrr, mbx_sli4_parameters);
+
+	/* Make sure that sge_supp_len can be handled by the driver */
+	if (sli4_params->sge_supp_len > LPFC_MAX_SGE_SIZE)
+		sli4_params->sge_supp_len = LPFC_MAX_SGE_SIZE;
+
 	return 0;
 }
 
@@ -8173,6 +8431,10 @@ lpfc_pci_remove_one_s3(struct pci_dev *pdev)
 
 	lpfc_debugfs_terminate(vport);
 
+	/* Disable SR-IOV if enabled */
+	if (phba->cfg_sriov_nr_virtfn)
+		pci_disable_sriov(pdev);
+
 	/* Disable interrupt */
 	lpfc_sli_disable_intr(phba);
 
@@ -8565,6 +8827,97 @@ lpfc_sli4_get_els_iocb_cnt(struct lpfc_hba *phba)
 }
 
 /**
+ * lpfc_write_firmware - attempt to write a firmware image to the port
+ * @phba: pointer to lpfc hba data structure.
+ * @fw: pointer to firmware image returned from request_firmware.
+ *
+ * returns the number of bytes written if write is successful.
+ * returns a negative error value if there were errors.
+ * returns 0 if firmware matches currently active firmware on port.
+ **/
+int
+lpfc_write_firmware(struct lpfc_hba *phba, const struct firmware *fw)
+{
+	char fwrev[32];
+	struct lpfc_grp_hdr *image = (struct lpfc_grp_hdr *)fw->data;
+	struct list_head dma_buffer_list;
+	int i, rc = 0;
+	struct lpfc_dmabuf *dmabuf, *next;
+	uint32_t offset = 0, temp_offset = 0;
+
+	INIT_LIST_HEAD(&dma_buffer_list);
+	if ((image->magic_number != LPFC_GROUP_OJECT_MAGIC_NUM) ||
+	    (bf_get(lpfc_grp_hdr_file_type, image) != LPFC_FILE_TYPE_GROUP) ||
+	    (bf_get(lpfc_grp_hdr_id, image) != LPFC_FILE_ID_GROUP) ||
+	    (image->size != fw->size)) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"3022 Invalid FW image found. "
+				"Magic:%d Type:%x ID:%x\n",
+				image->magic_number,
+				bf_get(lpfc_grp_hdr_file_type, image),
+				bf_get(lpfc_grp_hdr_id, image));
+		return -EINVAL;
+	}
+	lpfc_decode_firmware_rev(phba, fwrev, 1);
+	if (strncmp(fwrev, image->rev_name, strnlen(fwrev, 16))) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"3023 Updating Firmware. Current Version:%s "
+				"New Version:%s\n",
+				fwrev, image->rev_name);
+		for (i = 0; i < LPFC_MBX_WR_CONFIG_MAX_BDE; i++) {
+			dmabuf = kzalloc(sizeof(struct lpfc_dmabuf),
+					 GFP_KERNEL);
+			if (!dmabuf) {
+				rc = -ENOMEM;
+				goto out;
+			}
+			dmabuf->virt = dma_alloc_coherent(&phba->pcidev->dev,
+							  SLI4_PAGE_SIZE,
+							  &dmabuf->phys,
+							  GFP_KERNEL);
+			if (!dmabuf->virt) {
+				kfree(dmabuf);
+				rc = -ENOMEM;
+				goto out;
+			}
+			list_add_tail(&dmabuf->list, &dma_buffer_list);
+		}
+		while (offset < fw->size) {
+			temp_offset = offset;
+			list_for_each_entry(dmabuf, &dma_buffer_list, list) {
+				if (offset + SLI4_PAGE_SIZE > fw->size) {
+					temp_offset += fw->size - offset;
+					memcpy(dmabuf->virt,
+					       fw->data + temp_offset,
+					       fw->size - offset);
+					break;
+				}
+				temp_offset += SLI4_PAGE_SIZE;
+				memcpy(dmabuf->virt, fw->data + temp_offset,
+				       SLI4_PAGE_SIZE);
+			}
+			rc = lpfc_wr_object(phba, &dma_buffer_list,
+				    (fw->size - offset), &offset);
+			if (rc) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"3024 Firmware update failed. "
+						"%d\n", rc);
+				goto out;
+			}
+		}
+		rc = offset;
+	}
+out:
+	list_for_each_entry_safe(dmabuf, next, &dma_buffer_list, list) {
+		list_del(&dmabuf->list);
+		dma_free_coherent(&phba->pcidev->dev, SLI4_PAGE_SIZE,
+				  dmabuf->virt, dmabuf->phys);
+		kfree(dmabuf);
+	}
+	return rc;
+}
+
+/**
  * lpfc_pci_probe_one_s4 - PCI probe func to reg SLI-4 device to PCI subsys
  * @pdev: pointer to PCI device
  * @pid: pointer to PCI device identifier
@@ -8591,6 +8944,10 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	int error;
 	uint32_t cfg_mode, intr_mode;
 	int mcnt;
+	int adjusted_fcp_eq_count;
+	int fcp_qidx;
+	const struct firmware *fw;
+	uint8_t file_name[16];
 
 	/* Allocate memory for HBA structure */
 	phba = lpfc_hba_alloc(pdev);
@@ -8688,11 +9045,25 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 			error = -ENODEV;
 			goto out_free_sysfs_attr;
 		}
-		/* Default to single FCP EQ for non-MSI-X */
+		/* Default to single EQ for non-MSI-X */
 		if (phba->intr_type != MSIX)
-			phba->cfg_fcp_eq_count = 1;
-		else if (phba->sli4_hba.msix_vec_nr < phba->cfg_fcp_eq_count)
-			phba->cfg_fcp_eq_count = phba->sli4_hba.msix_vec_nr - 1;
+			adjusted_fcp_eq_count = 0;
+		else if (phba->sli4_hba.msix_vec_nr <
+					phba->cfg_fcp_eq_count + 1)
+			adjusted_fcp_eq_count = phba->sli4_hba.msix_vec_nr - 1;
+		else
+			adjusted_fcp_eq_count = phba->cfg_fcp_eq_count;
+		/* Free unused EQs */
+		for (fcp_qidx = adjusted_fcp_eq_count;
+		     fcp_qidx < phba->cfg_fcp_eq_count;
+		     fcp_qidx++) {
+			lpfc_sli4_queue_free(phba->sli4_hba.fp_eq[fcp_qidx]);
+			/* do not delete the first fcp_cq */
+			if (fcp_qidx)
+				lpfc_sli4_queue_free(
+					phba->sli4_hba.fcp_cq[fcp_qidx]);
+		}
+		phba->cfg_fcp_eq_count = adjusted_fcp_eq_count;
 		/* Set up SLI-4 HBA */
 		if (lpfc_sli4_hba_setup(phba)) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
@@ -8731,6 +9102,14 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	/* Perform post initialization setup */
 	lpfc_post_init_setup(phba);
 
+	/* check for firmware upgrade or downgrade */
+	snprintf(file_name, 16, "%s.grp", phba->ModelName);
+	error = request_firmware(&fw, file_name, &phba->pcidev->dev);
+	if (!error) {
+		lpfc_write_firmware(phba, fw);
+		release_firmware(fw);
+	}
+
 	/* Check if there are static vports to be created. */
 	lpfc_create_static_vport(phba);
 
@@ -9498,6 +9877,10 @@ static struct pci_device_id lpfc_id_table[] = {
 		PCI_ANY_ID, PCI_ANY_ID, },
 	{PCI_VENDOR_ID_EMULEX, PCI_DEVICE_ID_LANCER_FCOE,
 		PCI_ANY_ID, PCI_ANY_ID, },
+	{PCI_VENDOR_ID_EMULEX, PCI_DEVICE_ID_LANCER_FC_VF,
+		PCI_ANY_ID, PCI_ANY_ID, },
+	{PCI_VENDOR_ID_EMULEX, PCI_DEVICE_ID_LANCER_FCOE_VF,
+		PCI_ANY_ID, PCI_ANY_ID, },
 	{ 0 }
 };
 
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index e6ce9033f85e..556767028353 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -610,7 +610,8 @@ lpfc_read_sparam(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb, int vpi)
 	mb->un.varRdSparm.un.sp64.tus.f.bdeSize = sizeof (struct serv_parm);
 	mb->un.varRdSparm.un.sp64.addrHigh = putPaddrHigh(mp->phys);
 	mb->un.varRdSparm.un.sp64.addrLow = putPaddrLow(mp->phys);
-	mb->un.varRdSparm.vpi = vpi + phba->vpi_base;
+	if (phba->sli_rev >= LPFC_SLI_REV3)
+		mb->un.varRdSparm.vpi = phba->vpi_ids[vpi];
 
 	/* save address for completion */
 	pmb->context1 = mp;
@@ -643,9 +644,10 @@ lpfc_unreg_did(struct lpfc_hba * phba, uint16_t vpi, uint32_t did,
 	memset(pmb, 0, sizeof (LPFC_MBOXQ_t));
 
 	mb->un.varUnregDID.did = did;
-	if (vpi != 0xffff)
-		vpi += phba->vpi_base;
 	mb->un.varUnregDID.vpi = vpi;
+	if ((vpi != 0xffff) &&
+	    (phba->sli_rev == LPFC_SLI_REV4))
+		mb->un.varUnregDID.vpi = phba->vpi_ids[vpi];
 
 	mb->mbxCommand = MBX_UNREG_D_ID;
 	mb->mbxOwner = OWN_HOST;
@@ -738,12 +740,10 @@ lpfc_reg_rpi(struct lpfc_hba *phba, uint16_t vpi, uint32_t did,
 	memset(pmb, 0, sizeof (LPFC_MBOXQ_t));
 
 	mb->un.varRegLogin.rpi = 0;
-	if (phba->sli_rev == LPFC_SLI_REV4) {
-		mb->un.varRegLogin.rpi = rpi;
-		if (mb->un.varRegLogin.rpi == LPFC_RPI_ALLOC_ERROR)
-			return 1;
-	}
-	mb->un.varRegLogin.vpi = vpi + phba->vpi_base;
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		mb->un.varRegLogin.rpi = phba->sli4_hba.rpi_ids[rpi];
+	if (phba->sli_rev >= LPFC_SLI_REV3)
+		mb->un.varRegLogin.vpi = phba->vpi_ids[vpi];
 	mb->un.varRegLogin.did = did;
 	mb->mbxOwner = OWN_HOST;
 	/* Get a buffer to hold NPorts Service Parameters */
@@ -757,7 +757,7 @@ lpfc_reg_rpi(struct lpfc_hba *phba, uint16_t vpi, uint32_t did,
 		lpfc_printf_log(phba, KERN_WARNING, LOG_MBOX,
 				"0302 REG_LOGIN: no buffers, VPI:%d DID:x%x, "
 				"rpi x%x\n", vpi, did, rpi);
-		return (1);
+		return 1;
 	}
 	INIT_LIST_HEAD(&mp->list);
 	sparam = mp->virt;
@@ -773,7 +773,7 @@ lpfc_reg_rpi(struct lpfc_hba *phba, uint16_t vpi, uint32_t did,
 	mb->un.varRegLogin.un.sp64.addrHigh = putPaddrHigh(mp->phys);
 	mb->un.varRegLogin.un.sp64.addrLow = putPaddrLow(mp->phys);
 
-	return (0);
+	return 0;
 }
 
 /**
@@ -789,6 +789,9 @@ lpfc_reg_rpi(struct lpfc_hba *phba, uint16_t vpi, uint32_t did,
  *
  * This routine prepares the mailbox command for unregistering remote port
  * login.
+ *
+ * For SLI4 ports, the rpi passed to this function must be the physical
+ * rpi value, not the logical index.
  **/
 void
 lpfc_unreg_login(struct lpfc_hba *phba, uint16_t vpi, uint32_t rpi,
@@ -799,9 +802,10 @@ lpfc_unreg_login(struct lpfc_hba *phba, uint16_t vpi, uint32_t rpi,
 	mb = &pmb->u.mb;
 	memset(pmb, 0, sizeof (LPFC_MBOXQ_t));
 
-	mb->un.varUnregLogin.rpi = (uint16_t) rpi;
+	mb->un.varUnregLogin.rpi = rpi;
 	mb->un.varUnregLogin.rsvd1 = 0;
-	mb->un.varUnregLogin.vpi = vpi + phba->vpi_base;
+	if (phba->sli_rev >= LPFC_SLI_REV3)
+		mb->un.varUnregLogin.vpi = phba->vpi_ids[vpi];
 
 	mb->mbxCommand = MBX_UNREG_LOGIN;
 	mb->mbxOwner = OWN_HOST;
@@ -825,9 +829,16 @@ lpfc_sli4_unreg_all_rpis(struct lpfc_vport *vport)
 
 	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (mbox) {
-		lpfc_unreg_login(phba, vport->vpi,
-			vport->vpi + phba->vpi_base, mbox);
-		mbox->u.mb.un.varUnregLogin.rsvd1 = 0x4000 ;
+		/*
+		 * For SLI4 functions, the rpi field is overloaded for
+		 * the vport context unreg all.  This routine passes
+		 * 0 for the rpi field in lpfc_unreg_login for compatibility
+		 * with SLI3 and then overrides the rpi field with the
+		 * expected value for SLI4.
+		 */
+		lpfc_unreg_login(phba, vport->vpi, phba->vpi_ids[vport->vpi],
+				 mbox);
+		mbox->u.mb.un.varUnregLogin.rsvd1 = 0x4000;
 		mbox->vport = vport;
 		mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
 		mbox->context1 = NULL;
@@ -865,9 +876,13 @@ lpfc_reg_vpi(struct lpfc_vport *vport, LPFC_MBOXQ_t *pmb)
 	if ((phba->sli_rev == LPFC_SLI_REV4) &&
 		!(vport->fc_flag & FC_VPORT_NEEDS_REG_VPI))
 		mb->un.varRegVpi.upd = 1;
-	mb->un.varRegVpi.vpi = vport->vpi + vport->phba->vpi_base;
+
+	mb->un.varRegVpi.vpi = phba->vpi_ids[vport->vpi];
 	mb->un.varRegVpi.sid = vport->fc_myDID;
-	mb->un.varRegVpi.vfi = vport->vfi + vport->phba->vfi_base;
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		mb->un.varRegVpi.vfi = phba->sli4_hba.vfi_ids[vport->vfi];
+	else
+		mb->un.varRegVpi.vfi = vport->vfi + vport->phba->vfi_base;
 	memcpy(mb->un.varRegVpi.wwn, &vport->fc_portname,
 	       sizeof(struct lpfc_name));
 	mb->un.varRegVpi.wwn[0] = cpu_to_le32(mb->un.varRegVpi.wwn[0]);
@@ -901,10 +916,10 @@ lpfc_unreg_vpi(struct lpfc_hba *phba, uint16_t vpi, LPFC_MBOXQ_t *pmb)
 	MAILBOX_t *mb = &pmb->u.mb;
 	memset(pmb, 0, sizeof (LPFC_MBOXQ_t));
 
-	if (phba->sli_rev < LPFC_SLI_REV4)
-		mb->un.varUnregVpi.vpi = vpi + phba->vpi_base;
-	else
-		mb->un.varUnregVpi.sli4_vpi = vpi + phba->vpi_base;
+	if (phba->sli_rev == LPFC_SLI_REV3)
+		mb->un.varUnregVpi.vpi = phba->vpi_ids[vpi];
+	else if (phba->sli_rev >= LPFC_SLI_REV4)
+		mb->un.varUnregVpi.sli4_vpi = phba->vpi_ids[vpi];
 
 	mb->mbxCommand = MBX_UNREG_VPI;
 	mb->mbxOwner = OWN_HOST;
@@ -1735,12 +1750,12 @@ lpfc_sli4_config(struct lpfc_hba *phba, struct lpfcMboxq *mbox,
 		return length;
 	}
 
-	/* Setup for the none-embedded mbox command */
+	/* Setup for the non-embedded mbox command */
 	pcount = (SLI4_PAGE_ALIGN(length))/SLI4_PAGE_SIZE;
 	pcount = (pcount > LPFC_SLI4_MBX_SGE_MAX_PAGES) ?
 				LPFC_SLI4_MBX_SGE_MAX_PAGES : pcount;
 	/* Allocate record for keeping SGE virtual addresses */
-	mbox->sge_array = kmalloc(sizeof(struct lpfc_mbx_nembed_sge_virt),
+	mbox->sge_array = kzalloc(sizeof(struct lpfc_mbx_nembed_sge_virt),
 				  GFP_KERNEL);
 	if (!mbox->sge_array) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX,
@@ -1790,12 +1805,87 @@ lpfc_sli4_config(struct lpfc_hba *phba, struct lpfcMboxq *mbox,
 	/* The sub-header is in DMA memory, which needs endian converstion */
 	if (cfg_shdr)
 		lpfc_sli_pcimem_bcopy(cfg_shdr, cfg_shdr,
-			      sizeof(union  lpfc_sli4_cfg_shdr));
-
+				      sizeof(union  lpfc_sli4_cfg_shdr));
 	return alloc_len;
 }
 
 /**
+ * lpfc_sli4_mbox_rsrc_extent - Initialize the opcode resource extent.
+ * @phba: pointer to lpfc hba data structure.
+ * @mbox: pointer to an allocated lpfc mbox resource.
+ * @exts_count: the number of extents, if required, to allocate.
+ * @rsrc_type: the resource extent type.
+ * @emb: true if LPFC_SLI4_MBX_EMBED. false if LPFC_SLI4_MBX_NEMBED.
+ *
+ * This routine completes the subcommand header for SLI4 resource extent
+ * mailbox commands.  It is called after lpfc_sli4_config.  The caller must
+ * pass an allocated mailbox and the attributes required to initialize the
+ * mailbox correctly.
+ *
+ * Return: the actual length of the mbox command allocated.
+ **/
+int
+lpfc_sli4_mbox_rsrc_extent(struct lpfc_hba *phba, struct lpfcMboxq *mbox,
+			   uint16_t exts_count, uint16_t rsrc_type, bool emb)
+{
+	uint8_t opcode = 0;
+	struct lpfc_mbx_nembed_rsrc_extent *n_rsrc_extnt = NULL;
+	void *virtaddr = NULL;
+
+	/* Set up SLI4 ioctl command header fields */
+	if (emb == LPFC_SLI4_MBX_NEMBED) {
+		/* Get the first SGE entry from the non-embedded DMA memory */
+		virtaddr = mbox->sge_array->addr[0];
+		if (virtaddr == NULL)
+			return 1;
+		n_rsrc_extnt = (struct lpfc_mbx_nembed_rsrc_extent *) virtaddr;
+	}
+
+	/*
+	 * The resource type is common to all extent Opcodes and resides in the
+	 * same position.
+	 */
+	if (emb == LPFC_SLI4_MBX_EMBED)
+		bf_set(lpfc_mbx_alloc_rsrc_extents_type,
+		       &mbox->u.mqe.un.alloc_rsrc_extents.u.req,
+		       rsrc_type);
+	else {
+		/* This is DMA data.  Byteswap is required. */
+		bf_set(lpfc_mbx_alloc_rsrc_extents_type,
+		       n_rsrc_extnt, rsrc_type);
+		lpfc_sli_pcimem_bcopy(&n_rsrc_extnt->word4,
+				      &n_rsrc_extnt->word4,
+				      sizeof(uint32_t));
+	}
+
+	/* Complete the initialization for the particular Opcode. */
+	opcode = lpfc_sli4_mbox_opcode_get(phba, mbox);
+	switch (opcode) {
+	case LPFC_MBOX_OPCODE_ALLOC_RSRC_EXTENT:
+		if (emb == LPFC_SLI4_MBX_EMBED)
+			bf_set(lpfc_mbx_alloc_rsrc_extents_cnt,
+			       &mbox->u.mqe.un.alloc_rsrc_extents.u.req,
+			       exts_count);
+		else
+			bf_set(lpfc_mbx_alloc_rsrc_extents_cnt,
+			       n_rsrc_extnt, exts_count);
+		break;
+	case LPFC_MBOX_OPCODE_GET_ALLOC_RSRC_EXTENT:
+	case LPFC_MBOX_OPCODE_GET_RSRC_EXTENT_INFO:
+	case LPFC_MBOX_OPCODE_DEALLOC_RSRC_EXTENT:
+		/* Initialization is complete.*/
+		break;
+	default:
+		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX,
+				"2929 Resource Extent Opcode x%x is "
+				"unsupported\n", opcode);
+		return 1;
+	}
+
+	return 0;
+}
+
+/**
  * lpfc_sli4_mbox_opcode_get - Get the opcode from a sli4 mailbox command
  * @phba: pointer to lpfc hba data structure.
  * @mbox: pointer to lpfc mbox command.
@@ -1939,9 +2029,12 @@ lpfc_init_vfi(struct lpfcMboxq *mbox, struct lpfc_vport *vport)
 	bf_set(lpfc_init_vfi_vr, init_vfi, 1);
 	bf_set(lpfc_init_vfi_vt, init_vfi, 1);
 	bf_set(lpfc_init_vfi_vp, init_vfi, 1);
-	bf_set(lpfc_init_vfi_vfi, init_vfi, vport->vfi + vport->phba->vfi_base);
-	bf_set(lpfc_init_vpi_vpi, init_vfi, vport->vpi + vport->phba->vpi_base);
-	bf_set(lpfc_init_vfi_fcfi, init_vfi, vport->phba->fcf.fcfi);
+	bf_set(lpfc_init_vfi_vfi, init_vfi,
+	       vport->phba->sli4_hba.vfi_ids[vport->vfi]);
+	bf_set(lpfc_init_vpi_vpi, init_vfi,
+	       vport->phba->vpi_ids[vport->vpi]);
+	bf_set(lpfc_init_vfi_fcfi, init_vfi,
+	       vport->phba->fcf.fcfi);
 }
 
 /**
@@ -1964,9 +2057,10 @@ lpfc_reg_vfi(struct lpfcMboxq *mbox, struct lpfc_vport *vport, dma_addr_t phys)
 	reg_vfi = &mbox->u.mqe.un.reg_vfi;
 	bf_set(lpfc_mqe_command, &mbox->u.mqe, MBX_REG_VFI);
 	bf_set(lpfc_reg_vfi_vp, reg_vfi, 1);
-	bf_set(lpfc_reg_vfi_vfi, reg_vfi, vport->vfi + vport->phba->vfi_base);
+	bf_set(lpfc_reg_vfi_vfi, reg_vfi,
+	       vport->phba->sli4_hba.vfi_ids[vport->vfi]);
 	bf_set(lpfc_reg_vfi_fcfi, reg_vfi, vport->phba->fcf.fcfi);
-	bf_set(lpfc_reg_vfi_vpi, reg_vfi, vport->vpi + vport->phba->vpi_base);
+	bf_set(lpfc_reg_vfi_vpi, reg_vfi, vport->phba->vpi_ids[vport->vpi]);
 	memcpy(reg_vfi->wwn, &vport->fc_portname, sizeof(struct lpfc_name));
 	reg_vfi->wwn[0] = cpu_to_le32(reg_vfi->wwn[0]);
 	reg_vfi->wwn[1] = cpu_to_le32(reg_vfi->wwn[1]);
@@ -1997,9 +2091,9 @@ lpfc_init_vpi(struct lpfc_hba *phba, struct lpfcMboxq *mbox, uint16_t vpi)
 	memset(mbox, 0, sizeof(*mbox));
 	bf_set(lpfc_mqe_command, &mbox->u.mqe, MBX_INIT_VPI);
 	bf_set(lpfc_init_vpi_vpi, &mbox->u.mqe.un.init_vpi,
-	       vpi + phba->vpi_base);
+	       phba->vpi_ids[vpi]);
 	bf_set(lpfc_init_vpi_vfi, &mbox->u.mqe.un.init_vpi,
-	       phba->pport->vfi + phba->vfi_base);
+	       phba->sli4_hba.vfi_ids[phba->pport->vfi]);
 }
 
 /**
@@ -2019,7 +2113,7 @@ lpfc_unreg_vfi(struct lpfcMboxq *mbox, struct lpfc_vport *vport)
 	memset(mbox, 0, sizeof(*mbox));
 	bf_set(lpfc_mqe_command, &mbox->u.mqe, MBX_UNREG_VFI);
 	bf_set(lpfc_unreg_vfi_vfi, &mbox->u.mqe.un.unreg_vfi,
-	       vport->vfi + vport->phba->vfi_base);
+	       vport->phba->sli4_hba.vfi_ids[vport->vfi]);
 }
 
 /**
@@ -2131,12 +2225,14 @@ lpfc_unreg_fcfi(struct lpfcMboxq *mbox, uint16_t fcfi)
 void
 lpfc_resume_rpi(struct lpfcMboxq *mbox, struct lpfc_nodelist *ndlp)
 {
+	struct lpfc_hba *phba = ndlp->phba;
 	struct lpfc_mbx_resume_rpi *resume_rpi;
 
 	memset(mbox, 0, sizeof(*mbox));
 	resume_rpi = &mbox->u.mqe.un.resume_rpi;
 	bf_set(lpfc_mqe_command, &mbox->u.mqe, MBX_RESUME_RPI);
-	bf_set(lpfc_resume_rpi_index, resume_rpi, ndlp->nlp_rpi);
+	bf_set(lpfc_resume_rpi_index, resume_rpi,
+	       phba->sli4_hba.rpi_ids[ndlp->nlp_rpi]);
 	bf_set(lpfc_resume_rpi_ii, resume_rpi, RESUME_INDEX_RPI);
 	resume_rpi->event_tag = ndlp->phba->fc_eventTag;
 }
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index cbb48ee8b0bb..10d5b5e41499 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -62,7 +62,6 @@ int
 lpfc_mem_alloc(struct lpfc_hba *phba, int align)
 {
 	struct lpfc_dma_pool *pool = &phba->lpfc_mbuf_safety_pool;
-	int longs;
 	int i;
 
 	if (phba->sli_rev == LPFC_SLI_REV4)
@@ -138,17 +137,8 @@ lpfc_mem_alloc(struct lpfc_hba *phba, int align)
 		phba->lpfc_hrb_pool = NULL;
 		phba->lpfc_drb_pool = NULL;
 	}
-	/* vpi zero is reserved for the physical port so add 1 to max */
-	longs = ((phba->max_vpi + 1) + BITS_PER_LONG - 1) / BITS_PER_LONG;
-	phba->vpi_bmask = kzalloc(longs * sizeof(unsigned long), GFP_KERNEL);
-	if (!phba->vpi_bmask)
-		goto fail_free_dbq_pool;
 
 	return 0;
-
- fail_free_dbq_pool:
-	pci_pool_destroy(phba->lpfc_drb_pool);
-	phba->lpfc_drb_pool = NULL;
  fail_free_hrb_pool:
 	pci_pool_destroy(phba->lpfc_hrb_pool);
 	phba->lpfc_hrb_pool = NULL;
@@ -191,9 +181,6 @@ lpfc_mem_free(struct lpfc_hba *phba)
 	int i;
 	struct lpfc_dma_pool *pool = &phba->lpfc_mbuf_safety_pool;
 
-	/* Free VPI bitmask memory */
-	kfree(phba->vpi_bmask);
-
 	/* Free HBQ pools */
 	lpfc_sli_hbqbuf_free_all(phba);
 	if (phba->lpfc_drb_pool)
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 0d92d4205ea6..2ddd02f7c603 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -350,11 +350,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ndlp->nlp_maxframe =
 		((sp->cmn.bbRcvSizeMsb & 0x0F) << 8) | sp->cmn.bbRcvSizeLsb;
 
-	/*
-	 * Need to unreg_login if we are already in one of these states and
-	 * change to NPR state. This will block the port until after the ACC
-	 * completes and the reg_login is issued and completed.
-	 */
+	/* no need to reg_login if we are already in one of these states */
 	switch (ndlp->nlp_state) {
 	case  NLP_STE_NPR_NODE:
 		if (!(ndlp->nlp_flag & NLP_NPR_ADISC))
@@ -363,9 +359,8 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	case  NLP_STE_PRLI_ISSUE:
 	case  NLP_STE_UNMAPPED_NODE:
 	case  NLP_STE_MAPPED_NODE:
-		lpfc_unreg_rpi(vport, ndlp);
-		ndlp->nlp_prev_state = ndlp->nlp_state;
-		lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
+		lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, NULL);
+		return 1;
 	}
 
 	if ((vport->fc_flag & FC_PT2PT) &&
@@ -657,6 +652,7 @@ lpfc_disc_set_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	lpfc_unreg_rpi(vport, ndlp);
 	return 0;
 }
+
 /**
  * lpfc_release_rpi - Release a RPI by issuing unreg_login mailbox cmd.
  * @phba : Pointer to lpfc_hba structure.
@@ -1399,8 +1395,11 @@ lpfc_cmpl_reglogin_reglogin_issue(struct lpfc_vport *vport,
 	if (mb->mbxStatus) {
 		/* RegLogin failed */
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY,
-				"0246 RegLogin failed Data: x%x x%x x%x\n",
-				did, mb->mbxStatus, vport->port_state);
+				"0246 RegLogin failed Data: x%x x%x x%x x%x "
+				 "x%x\n",
+				 did, mb->mbxStatus, vport->port_state,
+				 mb->un.varRegLogin.vpi,
+				 mb->un.varRegLogin.rpi);
 		/*
 		 * If RegLogin failed due to lack of HBA resources do not
 		 * retry discovery.
@@ -1424,7 +1423,10 @@ lpfc_cmpl_reglogin_reglogin_issue(struct lpfc_vport *vport,
 		return ndlp->nlp_state;
 	}
 
-	ndlp->nlp_rpi = mb->un.varWords[0];
+	/* SLI4 ports have preallocated logical rpis. */
+	if (vport->phba->sli_rev < LPFC_SLI_REV4)
+		ndlp->nlp_rpi = mb->un.varWords[0];
+
 	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
 
 	/* Only if we are not a fabric nport do we issue PRLI */
@@ -2025,7 +2027,9 @@ lpfc_cmpl_reglogin_npr_node(struct lpfc_vport *vport,
 	MAILBOX_t    *mb = &pmb->u.mb;
 
 	if (!mb->mbxStatus) {
-		ndlp->nlp_rpi = mb->un.varWords[0];
+		/* SLI4 ports have preallocated logical rpis. */
+		if (vport->phba->sli_rev < LPFC_SLI_REV4)
+			ndlp->nlp_rpi = mb->un.varWords[0];
 		ndlp->nlp_flag |= NLP_RPI_REGISTERED;
 	} else {
 		if (ndlp->nlp_flag & NLP_NODEV_REMOVE) {
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 84e4481b2406..3ccc97496ebf 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -743,7 +743,14 @@ lpfc_sli4_repost_scsi_sgl_list(struct lpfc_hba *phba)
 		if (bcnt == 0)
 			continue;
 		/* Now, post the SCSI buffer list sgls as a block */
-		status = lpfc_sli4_post_scsi_sgl_block(phba, &sblist, bcnt);
+		if (!phba->sli4_hba.extents_in_use)
+			status = lpfc_sli4_post_scsi_sgl_block(phba,
+							&sblist,
+							bcnt);
+		else
+			status = lpfc_sli4_post_scsi_sgl_blk_ext(phba,
+							&sblist,
+							bcnt);
 		/* Reset SCSI buffer count for next round of posting */
 		bcnt = 0;
 		while (!list_empty(&sblist)) {
@@ -787,7 +794,7 @@ lpfc_new_scsi_buf_s4(struct lpfc_vport *vport, int num_to_alloc)
 	dma_addr_t pdma_phys_fcp_cmd;
 	dma_addr_t pdma_phys_fcp_rsp;
 	dma_addr_t pdma_phys_bpl, pdma_phys_bpl1;
-	uint16_t iotag, last_xritag = NO_XRI;
+	uint16_t iotag, last_xritag = NO_XRI, lxri = 0;
 	int status = 0, index;
 	int bcnt;
 	int non_sequential_xri = 0;
@@ -823,13 +830,15 @@ lpfc_new_scsi_buf_s4(struct lpfc_vport *vport, int num_to_alloc)
 			break;
 		}
 
-		psb->cur_iocbq.sli4_xritag = lpfc_sli4_next_xritag(phba);
-		if (psb->cur_iocbq.sli4_xritag == NO_XRI) {
+		lxri = lpfc_sli4_next_xritag(phba);
+		if (lxri == NO_XRI) {
 			pci_pool_free(phba->lpfc_scsi_dma_buf_pool,
 			      psb->data, psb->dma_handle);
 			kfree(psb);
 			break;
 		}
+		psb->cur_iocbq.sli4_lxritag = lxri;
+		psb->cur_iocbq.sli4_xritag = phba->sli4_hba.xri_ids[lxri];
 		if (last_xritag != NO_XRI
 			&& psb->cur_iocbq.sli4_xritag != (last_xritag+1)) {
 			non_sequential_xri = 1;
@@ -861,6 +870,7 @@ lpfc_new_scsi_buf_s4(struct lpfc_vport *vport, int num_to_alloc)
 		 */
 		sgl->addr_hi = cpu_to_le32(putPaddrHigh(pdma_phys_fcp_cmd));
 		sgl->addr_lo = cpu_to_le32(putPaddrLow(pdma_phys_fcp_cmd));
+		sgl->word2 = le32_to_cpu(sgl->word2);
 		bf_set(lpfc_sli4_sge_last, sgl, 0);
 		sgl->word2 = cpu_to_le32(sgl->word2);
 		sgl->sge_len = cpu_to_le32(sizeof(struct fcp_cmnd));
@@ -869,6 +879,7 @@ lpfc_new_scsi_buf_s4(struct lpfc_vport *vport, int num_to_alloc)
 		/* Setup the physical region for the FCP RSP */
 		sgl->addr_hi = cpu_to_le32(putPaddrHigh(pdma_phys_fcp_rsp));
 		sgl->addr_lo = cpu_to_le32(putPaddrLow(pdma_phys_fcp_rsp));
+		sgl->word2 = le32_to_cpu(sgl->word2);
 		bf_set(lpfc_sli4_sge_last, sgl, 1);
 		sgl->word2 = cpu_to_le32(sgl->word2);
 		sgl->sge_len = cpu_to_le32(sizeof(struct fcp_rsp));
@@ -914,7 +925,21 @@ lpfc_new_scsi_buf_s4(struct lpfc_vport *vport, int num_to_alloc)
 		}
 	}
 	if (bcnt) {
-		status = lpfc_sli4_post_scsi_sgl_block(phba, &sblist, bcnt);
+		if (!phba->sli4_hba.extents_in_use)
+			status = lpfc_sli4_post_scsi_sgl_block(phba,
+								&sblist,
+								bcnt);
+		else
+			status = lpfc_sli4_post_scsi_sgl_blk_ext(phba,
+								&sblist,
+								bcnt);
+
+		if (status) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
+					"3021 SCSI SGL post error %d\n",
+					status);
+			bcnt = 0;
+		}
 		/* Reset SCSI buffer count for next round of posting */
 		while (!list_empty(&sblist)) {
 			list_remove_head(&sblist, psb, struct lpfc_scsi_buf,
@@ -2081,6 +2106,7 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd)
 			dma_len = sg_dma_len(sgel);
 			sgl->addr_lo = cpu_to_le32(putPaddrLow(physaddr));
 			sgl->addr_hi = cpu_to_le32(putPaddrHigh(physaddr));
+			sgl->word2 = le32_to_cpu(sgl->word2);
 			if ((num_bde + 1) == nseg)
 				bf_set(lpfc_sli4_sge_last, sgl, 1);
 			else
@@ -2794,6 +2820,9 @@ lpfc_scsi_prep_cmnd(struct lpfc_vport *vport, struct lpfc_scsi_buf *lpfc_cmd,
 	 * of the scsi_cmnd request_buffer
 	 */
 	piocbq->iocb.ulpContext = pnode->nlp_rpi;
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		piocbq->iocb.ulpContext =
+		  phba->sli4_hba.rpi_ids[pnode->nlp_rpi];
 	if (pnode->nlp_fcp_info & NLP_FCP_2_DEVICE)
 		piocbq->iocb.ulpFCP2Rcvy = 1;
 	else
@@ -2807,7 +2836,7 @@ lpfc_scsi_prep_cmnd(struct lpfc_vport *vport, struct lpfc_scsi_buf *lpfc_cmd,
 }
 
 /**
- * lpfc_scsi_prep_task_mgmt_cmnd - Convert SLI3 scsi TM cmd to FCP info unit
+ * lpfc_scsi_prep_task_mgmt_cmd - Convert SLI3 scsi TM cmd to FCP info unit
  * @vport: The virtual port for which this call is being executed.
  * @lpfc_cmd: Pointer to lpfc_scsi_buf data structure.
  * @lun: Logical unit number.
@@ -2851,6 +2880,10 @@ lpfc_scsi_prep_task_mgmt_cmd(struct lpfc_vport *vport,
 		lpfc_fcpcmd_to_iocb(piocb->unsli3.fcp_ext.icd, fcp_cmnd);
 	piocb->ulpCommand = CMD_FCP_ICMND64_CR;
 	piocb->ulpContext = ndlp->nlp_rpi;
+	if (vport->phba->sli_rev == LPFC_SLI_REV4) {
+		piocb->ulpContext =
+		  vport->phba->sli4_hba.rpi_ids[ndlp->nlp_rpi];
+	}
 	if (ndlp->nlp_fcp_info & NLP_FCP_2_DEVICE) {
 		piocb->ulpFCP2Rcvy = 1;
 	}
@@ -3405,9 +3438,10 @@ lpfc_send_taskmgmt(struct lpfc_vport *vport, struct lpfc_rport_data *rdata,
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP,
 			 "0702 Issue %s to TGT %d LUN %d "
-			 "rpi x%x nlp_flag x%x\n",
+			 "rpi x%x nlp_flag x%x Data: x%x x%x\n",
 			 lpfc_taskmgmt_name(task_mgmt_cmd), tgt_id, lun_id,
-			 pnode->nlp_rpi, pnode->nlp_flag);
+			 pnode->nlp_rpi, pnode->nlp_flag, iocbq->sli4_xritag,
+			 iocbq->iocb_flag);
 
 	status = lpfc_sli_issue_iocb_wait(phba, LPFC_FCP_RING,
 					  iocbq, iocbqrsp, lpfc_cmd->timeout);
@@ -3419,10 +3453,12 @@ lpfc_send_taskmgmt(struct lpfc_vport *vport, struct lpfc_rport_data *rdata,
 			ret = FAILED;
 		lpfc_cmd->status = IOSTAT_DRIVER_REJECT;
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_FCP,
-			 "0727 TMF %s to TGT %d LUN %d failed (%d, %d)\n",
+			 "0727 TMF %s to TGT %d LUN %d failed (%d, %d) "
+			 "iocb_flag x%x\n",
 			 lpfc_taskmgmt_name(task_mgmt_cmd),
 			 tgt_id, lun_id, iocbqrsp->iocb.ulpStatus,
-			 iocbqrsp->iocb.un.ulpWord[4]);
+			 iocbqrsp->iocb.un.ulpWord[4],
+			 iocbq->iocb_flag);
 	} else if (status == IOCB_BUSY)
 		ret = FAILED;
 	else
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index fd5835e1c039..98999bbd8cbf 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -65,6 +65,9 @@ static struct lpfc_iocbq *lpfc_sli4_els_wcqe_to_rspiocbq(struct lpfc_hba *,
 							 struct lpfc_iocbq *);
 static void lpfc_sli4_send_seq_to_ulp(struct lpfc_vport *,
 				      struct hbq_dmabuf *);
+static int lpfc_sli4_fp_handle_wcqe(struct lpfc_hba *, struct lpfc_queue *,
+				    struct lpfc_cqe *);
+
 static IOCB_t *
 lpfc_get_iocb_from_iocbq(struct lpfc_iocbq *iocbq)
 {
@@ -456,7 +459,6 @@ __lpfc_sli_get_iocbq(struct lpfc_hba *phba)
 	struct lpfc_iocbq * iocbq = NULL;
 
 	list_remove_head(lpfc_iocb_list, iocbq, struct lpfc_iocbq, list);
-
 	if (iocbq)
 		phba->iocb_cnt++;
 	if (phba->iocb_cnt > phba->iocb_max)
@@ -479,13 +481,10 @@ __lpfc_sli_get_iocbq(struct lpfc_hba *phba)
 static struct lpfc_sglq *
 __lpfc_clear_active_sglq(struct lpfc_hba *phba, uint16_t xritag)
 {
-	uint16_t adj_xri;
 	struct lpfc_sglq *sglq;
-	adj_xri = xritag - phba->sli4_hba.max_cfg_param.xri_base;
-	if (adj_xri > phba->sli4_hba.max_cfg_param.max_xri)
-		return NULL;
-	sglq = phba->sli4_hba.lpfc_sglq_active_list[adj_xri];
-	phba->sli4_hba.lpfc_sglq_active_list[adj_xri] = NULL;
+
+	sglq = phba->sli4_hba.lpfc_sglq_active_list[xritag];
+	phba->sli4_hba.lpfc_sglq_active_list[xritag] = NULL;
 	return sglq;
 }
 
@@ -504,12 +503,9 @@ __lpfc_clear_active_sglq(struct lpfc_hba *phba, uint16_t xritag)
 struct lpfc_sglq *
 __lpfc_get_active_sglq(struct lpfc_hba *phba, uint16_t xritag)
 {
-	uint16_t adj_xri;
 	struct lpfc_sglq *sglq;
-	adj_xri = xritag - phba->sli4_hba.max_cfg_param.xri_base;
-	if (adj_xri > phba->sli4_hba.max_cfg_param.max_xri)
-		return NULL;
-	sglq =  phba->sli4_hba.lpfc_sglq_active_list[adj_xri];
+
+	sglq =  phba->sli4_hba.lpfc_sglq_active_list[xritag];
 	return sglq;
 }
 
@@ -532,7 +528,6 @@ static int
 __lpfc_set_rrq_active(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp,
 		uint16_t xritag, uint16_t rxid, uint16_t send_rrq)
 {
-	uint16_t adj_xri;
 	struct lpfc_node_rrq *rrq;
 	int empty;
 	uint32_t did = 0;
@@ -553,21 +548,19 @@ __lpfc_set_rrq_active(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp,
 	/*
 	 * set the active bit even if there is no mem available.
 	 */
-	adj_xri = xritag - phba->sli4_hba.max_cfg_param.xri_base;
-
 	if (NLP_CHK_FREE_REQ(ndlp))
 		goto out;
 
 	if (ndlp->vport && (ndlp->vport->load_flag & FC_UNLOADING))
 		goto out;
 
-	if (test_and_set_bit(adj_xri, ndlp->active_rrqs.xri_bitmap))
+	if (test_and_set_bit(xritag, ndlp->active_rrqs.xri_bitmap))
 		goto out;
 
 	rrq = mempool_alloc(phba->rrq_pool, GFP_KERNEL);
 	if (rrq) {
 		rrq->send_rrq = send_rrq;
-		rrq->xritag = xritag;
+		rrq->xritag = phba->sli4_hba.xri_ids[xritag];
 		rrq->rrq_stop_time = jiffies + HZ * (phba->fc_ratov + 1);
 		rrq->ndlp = ndlp;
 		rrq->nlp_DID = ndlp->nlp_DID;
@@ -603,7 +596,6 @@ lpfc_clr_rrq_active(struct lpfc_hba *phba,
 		    uint16_t xritag,
 		    struct lpfc_node_rrq *rrq)
 {
-	uint16_t adj_xri;
 	struct lpfc_nodelist *ndlp = NULL;
 
 	if ((rrq->vport) && NLP_CHK_NODE_ACT(rrq->ndlp))
@@ -619,8 +611,7 @@ lpfc_clr_rrq_active(struct lpfc_hba *phba,
 	if (!ndlp)
 		goto out;
 
-	adj_xri = xritag - phba->sli4_hba.max_cfg_param.xri_base;
-	if (test_and_clear_bit(adj_xri, ndlp->active_rrqs.xri_bitmap)) {
+	if (test_and_clear_bit(xritag, ndlp->active_rrqs.xri_bitmap)) {
 		rrq->send_rrq = 0;
 		rrq->xritag = 0;
 		rrq->rrq_stop_time = 0;
@@ -796,12 +787,9 @@ int
 lpfc_test_rrq_active(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp,
 			uint16_t  xritag)
 {
-	uint16_t adj_xri;
-
-	adj_xri = xritag - phba->sli4_hba.max_cfg_param.xri_base;
 	if (!ndlp)
 		return 0;
-	if (test_bit(adj_xri, ndlp->active_rrqs.xri_bitmap))
+	if (test_bit(xritag, ndlp->active_rrqs.xri_bitmap))
 			return 1;
 	else
 		return 0;
@@ -841,7 +829,7 @@ lpfc_set_rrq_active(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp,
  * @piocb: Pointer to the iocbq.
  *
  * This function is called with hbalock held. This function
- * Gets a new driver sglq object from the sglq list. If the
+ * gets a new driver sglq object from the sglq list. If the
  * list is not empty then it is successful, it returns pointer to the newly
  * allocated sglq object else it returns NULL.
  **/
@@ -851,7 +839,6 @@ __lpfc_sli_get_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
 	struct list_head *lpfc_sgl_list = &phba->sli4_hba.lpfc_sgl_list;
 	struct lpfc_sglq *sglq = NULL;
 	struct lpfc_sglq *start_sglq = NULL;
-	uint16_t adj_xri;
 	struct lpfc_scsi_buf *lpfc_cmd;
 	struct lpfc_nodelist *ndlp;
 	int found = 0;
@@ -870,8 +857,6 @@ __lpfc_sli_get_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
 	while (!found) {
 		if (!sglq)
 			return NULL;
-		adj_xri = sglq->sli4_xritag -
-				phba->sli4_hba.max_cfg_param.xri_base;
 		if (lpfc_test_rrq_active(phba, ndlp, sglq->sli4_xritag)) {
 			/* This xri has an rrq outstanding for this DID.
 			 * put it back in the list and get another xri.
@@ -888,7 +873,7 @@ __lpfc_sli_get_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
 		}
 		sglq->ndlp = ndlp;
 		found = 1;
-		phba->sli4_hba.lpfc_sglq_active_list[adj_xri] = sglq;
+		phba->sli4_hba.lpfc_sglq_active_list[sglq->sli4_lxritag] = sglq;
 		sglq->state = SGL_ALLOCATED;
 	}
 	return sglq;
@@ -944,7 +929,8 @@ __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 	if (iocbq->sli4_xritag == NO_XRI)
 		sglq = NULL;
 	else
-		sglq = __lpfc_clear_active_sglq(phba, iocbq->sli4_xritag);
+		sglq = __lpfc_clear_active_sglq(phba, iocbq->sli4_lxritag);
+
 	if (sglq)  {
 		if ((iocbq->iocb_flag & LPFC_EXCHANGE_BUSY) &&
 			(sglq->state != SGL_XRI_ABORTED)) {
@@ -971,6 +957,7 @@ __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 	 * Clean all volatile data fields, preserve iotag and node struct.
 	 */
 	memset((char *)iocbq + start_clean, 0, sizeof(*iocbq) - start_clean);
+	iocbq->sli4_lxritag = NO_XRI;
 	iocbq->sli4_xritag = NO_XRI;
 	list_add_tail(&iocbq->list, &phba->lpfc_iocb_list);
 }
@@ -2113,7 +2100,7 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	    pmb->u.mb.mbxCommand == MBX_REG_LOGIN64 &&
 	    !pmb->u.mb.mbxStatus) {
 		rpi = pmb->u.mb.un.varWords[0];
-		vpi = pmb->u.mb.un.varRegLogin.vpi - phba->vpi_base;
+		vpi = pmb->u.mb.un.varRegLogin.vpi;
 		lpfc_unreg_login(phba, vpi, rpi, pmb);
 		pmb->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
 		rc = lpfc_sli_issue_mbox(phba, pmb, MBX_NOWAIT);
@@ -3881,8 +3868,10 @@ lpfc_sli4_brdreset(struct lpfc_hba *phba)
 	list_del_init(&phba->sli4_hba.els_cq->list);
 	for (qindx = 0; qindx < phba->cfg_fcp_wq_count; qindx++)
 		list_del_init(&phba->sli4_hba.fcp_wq[qindx]->list);
-	for (qindx = 0; qindx < phba->cfg_fcp_eq_count; qindx++)
+	qindx = 0;
+	do
 		list_del_init(&phba->sli4_hba.fcp_cq[qindx]->list);
+	while (++qindx < phba->cfg_fcp_eq_count);
 	spin_unlock_irq(&phba->hbalock);
 
 	/* Now physically reset the device */
@@ -4318,6 +4307,7 @@ lpfc_sli_config_port(struct lpfc_hba *phba, int sli_mode)
 			continue;
 		} else if (rc)
 			break;
+
 		phba->link_state = LPFC_INIT_MBX_CMDS;
 		lpfc_config_port(phba, pmb);
 		rc = lpfc_sli_issue_mbox(phba, pmb, MBX_POLL);
@@ -4421,7 +4411,8 @@ int
 lpfc_sli_hba_setup(struct lpfc_hba *phba)
 {
 	uint32_t rc;
-	int  mode = 3;
+	int  mode = 3, i;
+	int longs;
 
 	switch (lpfc_sli_mode) {
 	case 2:
@@ -4491,6 +4482,35 @@ lpfc_sli_hba_setup(struct lpfc_hba *phba)
 	if (rc)
 		goto lpfc_sli_hba_setup_error;
 
+	/* Initialize VPIs. */
+	if (phba->sli_rev == LPFC_SLI_REV3) {
+		/*
+		 * The VPI bitmask and physical ID array are allocated
+		 * and initialized once only - at driver load.  A port
+		 * reset doesn't need to reinitialize this memory.
+		 */
+		if ((phba->vpi_bmask == NULL) && (phba->vpi_ids == NULL)) {
+			longs = (phba->max_vpi + BITS_PER_LONG) / BITS_PER_LONG;
+			phba->vpi_bmask = kzalloc(longs * sizeof(unsigned long),
+						  GFP_KERNEL);
+			if (!phba->vpi_bmask) {
+				rc = -ENOMEM;
+				goto lpfc_sli_hba_setup_error;
+			}
+
+			phba->vpi_ids = kzalloc(
+					(phba->max_vpi+1) * sizeof(uint16_t),
+					GFP_KERNEL);
+			if (!phba->vpi_ids) {
+				kfree(phba->vpi_bmask);
+				rc = -ENOMEM;
+				goto lpfc_sli_hba_setup_error;
+			}
+			for (i = 0; i < phba->max_vpi; i++)
+				phba->vpi_ids[i] = i;
+		}
+	}
+
 	/* Init HBQs */
 	if (phba->sli3_options & LPFC_SLI3_HBQ_ENABLED) {
 		rc = lpfc_sli_hbq_setup(phba);
@@ -4677,9 +4697,11 @@ lpfc_sli4_arm_cqeq_intr(struct lpfc_hba *phba)
 
 	lpfc_sli4_cq_release(phba->sli4_hba.mbx_cq, LPFC_QUEUE_REARM);
 	lpfc_sli4_cq_release(phba->sli4_hba.els_cq, LPFC_QUEUE_REARM);
-	for (fcp_eqidx = 0; fcp_eqidx < phba->cfg_fcp_eq_count; fcp_eqidx++)
+	fcp_eqidx = 0;
+	do
 		lpfc_sli4_cq_release(phba->sli4_hba.fcp_cq[fcp_eqidx],
 				     LPFC_QUEUE_REARM);
+	while (++fcp_eqidx < phba->cfg_fcp_eq_count);
 	lpfc_sli4_eq_release(phba->sli4_hba.sp_eq, LPFC_QUEUE_REARM);
 	for (fcp_eqidx = 0; fcp_eqidx < phba->cfg_fcp_eq_count; fcp_eqidx++)
 		lpfc_sli4_eq_release(phba->sli4_hba.fp_eq[fcp_eqidx],
@@ -4687,6 +4709,803 @@ lpfc_sli4_arm_cqeq_intr(struct lpfc_hba *phba)
 }
 
 /**
+ * lpfc_sli4_get_avail_extnt_rsrc - Get available resource extent count.
+ * @phba: Pointer to HBA context object.
+ * @type: The resource extent type.
+ *
+ * This function allocates all SLI4 resource identifiers.
+ **/
+static int
+lpfc_sli4_get_avail_extnt_rsrc(struct lpfc_hba *phba, uint16_t type,
+			       uint16_t *extnt_count, uint16_t *extnt_size)
+{
+	int rc = 0;
+	uint32_t length;
+	uint32_t mbox_tmo;
+	struct lpfc_mbx_get_rsrc_extent_info *rsrc_info;
+	LPFC_MBOXQ_t *mbox;
+
+	mbox = (LPFC_MBOXQ_t *) mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!mbox)
+		return -ENOMEM;
+
+	/* Find out how many extents are available for this resource type */
+	length = (sizeof(struct lpfc_mbx_get_rsrc_extent_info) -
+		  sizeof(struct lpfc_sli4_cfg_mhdr));
+	lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_COMMON,
+			 LPFC_MBOX_OPCODE_GET_RSRC_EXTENT_INFO,
+			 length, LPFC_SLI4_MBX_EMBED);
+
+	/* Send an extents count of 0 - the GET doesn't use it. */
+	rc = lpfc_sli4_mbox_rsrc_extent(phba, mbox, 0, type,
+					LPFC_SLI4_MBX_EMBED);
+	if (unlikely(rc)) {
+		rc = -EIO;
+		goto err_exit;
+	}
+
+	if (!phba->sli4_hba.intr_enable)
+		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_POLL);
+	else {
+		mbox_tmo = lpfc_mbox_tmo_val(phba, MBX_SLI4_CONFIG);
+		rc = lpfc_sli_issue_mbox_wait(phba, mbox, mbox_tmo);
+	}
+	if (unlikely(rc)) {
+		rc = -EIO;
+		goto err_exit;
+	}
+
+	rsrc_info = &mbox->u.mqe.un.rsrc_extent_info;
+	if (bf_get(lpfc_mbox_hdr_status,
+		   &rsrc_info->header.cfg_shdr.response)) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_INIT,
+				"2930 Failed to get resource extents "
+				"Status 0x%x Add'l Status 0x%x\n",
+				bf_get(lpfc_mbox_hdr_status,
+				       &rsrc_info->header.cfg_shdr.response),
+				bf_get(lpfc_mbox_hdr_add_status,
+				       &rsrc_info->header.cfg_shdr.response));
+		rc = -EIO;
+		goto err_exit;
+	}
+
+	*extnt_count = bf_get(lpfc_mbx_get_rsrc_extent_info_cnt,
+			      &rsrc_info->u.rsp);
+	*extnt_size = bf_get(lpfc_mbx_get_rsrc_extent_info_size,
+			     &rsrc_info->u.rsp);
+ err_exit:
+	mempool_free(mbox, phba->mbox_mem_pool);
+	return rc;
+}
+
+/**
+ * lpfc_sli4_chk_avail_extnt_rsrc - Check for available SLI4 resource extents.
+ * @phba: Pointer to HBA context object.
+ * @type: The extent type to check.
+ *
+ * This function reads the current available extents from the port and checks
+ * if the extent count or extent size has changed since the last access.
+ * Callers use this routine post port reset to understand if there is a
+ * extent reprovisioning requirement.
+ *
+ * Returns:
+ *   -Error: error indicates problem.
+ *   1: Extent count or size has changed.
+ *   0: No changes.
+ **/
+static int
+lpfc_sli4_chk_avail_extnt_rsrc(struct lpfc_hba *phba, uint16_t type)
+{
+	uint16_t curr_ext_cnt, rsrc_ext_cnt;
+	uint16_t size_diff, rsrc_ext_size;
+	int rc = 0;
+	struct lpfc_rsrc_blks *rsrc_entry;
+	struct list_head *rsrc_blk_list = NULL;
+
+	size_diff = 0;
+	curr_ext_cnt = 0;
+	rc = lpfc_sli4_get_avail_extnt_rsrc(phba, type,
+					    &rsrc_ext_cnt,
+					    &rsrc_ext_size);
+	if (unlikely(rc))
+		return -EIO;
+
+	switch (type) {
+	case LPFC_RSC_TYPE_FCOE_RPI:
+		rsrc_blk_list = &phba->sli4_hba.lpfc_rpi_blk_list;
+		break;
+	case LPFC_RSC_TYPE_FCOE_VPI:
+		rsrc_blk_list = &phba->lpfc_vpi_blk_list;
+		break;
+	case LPFC_RSC_TYPE_FCOE_XRI:
+		rsrc_blk_list = &phba->sli4_hba.lpfc_xri_blk_list;
+		break;
+	case LPFC_RSC_TYPE_FCOE_VFI:
+		rsrc_blk_list = &phba->sli4_hba.lpfc_vfi_blk_list;
+		break;
+	default:
+		break;
+	}
+
+	list_for_each_entry(rsrc_entry, rsrc_blk_list, list) {
+		curr_ext_cnt++;
+		if (rsrc_entry->rsrc_size != rsrc_ext_size)
+			size_diff++;
+	}
+
+	if (curr_ext_cnt != rsrc_ext_cnt || size_diff != 0)
+		rc = 1;
+
+	return rc;
+}
+
+/**
+ * lpfc_sli4_cfg_post_extnts -
+ * @phba: Pointer to HBA context object.
+ * @extnt_cnt - number of available extents.
+ * @type - the extent type (rpi, xri, vfi, vpi).
+ * @emb - buffer to hold either MBX_EMBED or MBX_NEMBED operation.
+ * @mbox - pointer to the caller's allocated mailbox structure.
+ *
+ * This function executes the extents allocation request.  It also
+ * takes care of the amount of memory needed to allocate or get the
+ * allocated extents. It is the caller's responsibility to evaluate
+ * the response.
+ *
+ * Returns:
+ *   -Error:  Error value describes the condition found.
+ *   0: if successful
+ **/
+static int
+lpfc_sli4_cfg_post_extnts(struct lpfc_hba *phba, uint16_t *extnt_cnt,
+			  uint16_t type, bool *emb, LPFC_MBOXQ_t *mbox)
+{
+	int rc = 0;
+	uint32_t req_len;
+	uint32_t emb_len;
+	uint32_t alloc_len, mbox_tmo;
+
+	/* Calculate the total requested length of the dma memory */
+	req_len = *extnt_cnt * sizeof(uint16_t);
+
+	/*
+	 * Calculate the size of an embedded mailbox.  The uint32_t
+	 * accounts for extents-specific word.
+	 */
+	emb_len = sizeof(MAILBOX_t) - sizeof(struct mbox_header) -
+		sizeof(uint32_t);
+
+	/*
+	 * Presume the allocation and response will fit into an embedded
+	 * mailbox.  If not true, reconfigure to a non-embedded mailbox.
+	 */
+	*emb = LPFC_SLI4_MBX_EMBED;
+	if (req_len > emb_len) {
+		req_len = *extnt_cnt * sizeof(uint16_t) +
+			sizeof(union lpfc_sli4_cfg_shdr) +
+			sizeof(uint32_t);
+		*emb = LPFC_SLI4_MBX_NEMBED;
+	}
+
+	alloc_len = lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_COMMON,
+				     LPFC_MBOX_OPCODE_ALLOC_RSRC_EXTENT,
+				     req_len, *emb);
+	if (alloc_len < req_len) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+			"9000 Allocated DMA memory size (x%x) is "
+			"less than the requested DMA memory "
+			"size (x%x)\n", alloc_len, req_len);
+		return -ENOMEM;
+	}
+	rc = lpfc_sli4_mbox_rsrc_extent(phba, mbox, *extnt_cnt, type, *emb);
+	if (unlikely(rc))
+		return -EIO;
+
+	if (!phba->sli4_hba.intr_enable)
+		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_POLL);
+	else {
+		mbox_tmo = lpfc_mbox_tmo_val(phba, MBX_SLI4_CONFIG);
+		rc = lpfc_sli_issue_mbox_wait(phba, mbox, mbox_tmo);
+	}
+
+	if (unlikely(rc))
+		rc = -EIO;
+	return rc;
+}
+
+/**
+ * lpfc_sli4_alloc_extent - Allocate an SLI4 resource extent.
+ * @phba: Pointer to HBA context object.
+ * @type:  The resource extent type to allocate.
+ *
+ * This function allocates the number of elements for the specified
+ * resource type.
+ **/
+static int
+lpfc_sli4_alloc_extent(struct lpfc_hba *phba, uint16_t type)
+{
+	bool emb = false;
+	uint16_t rsrc_id_cnt, rsrc_cnt, rsrc_size;
+	uint16_t rsrc_id, rsrc_start, j, k;
+	uint16_t *ids;
+	int i, rc;
+	unsigned long longs;
+	unsigned long *bmask;
+	struct lpfc_rsrc_blks *rsrc_blks;
+	LPFC_MBOXQ_t *mbox;
+	uint32_t length;
+	struct lpfc_id_range *id_array = NULL;
+	void *virtaddr = NULL;
+	struct lpfc_mbx_nembed_rsrc_extent *n_rsrc;
+	struct lpfc_mbx_alloc_rsrc_extents *rsrc_ext;
+	struct list_head *ext_blk_list;
+
+	rc = lpfc_sli4_get_avail_extnt_rsrc(phba, type,
+					    &rsrc_cnt,
+					    &rsrc_size);
+	if (unlikely(rc))
+		return -EIO;
+
+	if ((rsrc_cnt == 0) || (rsrc_size == 0)) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_INIT,
+			"3009 No available Resource Extents "
+			"for resource type 0x%x: Count: 0x%x, "
+			"Size 0x%x\n", type, rsrc_cnt,
+			rsrc_size);
+		return -ENOMEM;
+	}
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_MBOX | LOG_INIT,
+			"2903 Available Resource Extents "
+			"for resource type 0x%x: Count: 0x%x, "
+			"Size 0x%x\n", type, rsrc_cnt,
+			rsrc_size);
+
+	mbox = (LPFC_MBOXQ_t *) mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!mbox)
+		return -ENOMEM;
+
+	rc = lpfc_sli4_cfg_post_extnts(phba, &rsrc_cnt, type, &emb, mbox);
+	if (unlikely(rc)) {
+		rc = -EIO;
+		goto err_exit;
+	}
+
+	/*
+	 * Figure out where the response is located.  Then get local pointers
+	 * to the response data.  The port does not guarantee to respond to
+	 * all extents counts request so update the local variable with the
+	 * allocated count from the port.
+	 */
+	if (emb == LPFC_SLI4_MBX_EMBED) {
+		rsrc_ext = &mbox->u.mqe.un.alloc_rsrc_extents;
+		id_array = &rsrc_ext->u.rsp.id[0];
+		rsrc_cnt = bf_get(lpfc_mbx_rsrc_cnt, &rsrc_ext->u.rsp);
+	} else {
+		virtaddr = mbox->sge_array->addr[0];
+		n_rsrc = (struct lpfc_mbx_nembed_rsrc_extent *) virtaddr;
+		rsrc_cnt = bf_get(lpfc_mbx_rsrc_cnt, n_rsrc);
+		id_array = &n_rsrc->id;
+	}
+
+	longs = ((rsrc_cnt * rsrc_size) + BITS_PER_LONG - 1) / BITS_PER_LONG;
+	rsrc_id_cnt = rsrc_cnt * rsrc_size;
+
+	/*
+	 * Based on the resource size and count, correct the base and max
+	 * resource values.
+	 */
+	length = sizeof(struct lpfc_rsrc_blks);
+	switch (type) {
+	case LPFC_RSC_TYPE_FCOE_RPI:
+		phba->sli4_hba.rpi_bmask = kzalloc(longs *
+						   sizeof(unsigned long),
+						   GFP_KERNEL);
+		if (unlikely(!phba->sli4_hba.rpi_bmask)) {
+			rc = -ENOMEM;
+			goto err_exit;
+		}
+		phba->sli4_hba.rpi_ids = kzalloc(rsrc_id_cnt *
+						 sizeof(uint16_t),
+						 GFP_KERNEL);
+		if (unlikely(!phba->sli4_hba.rpi_ids)) {
+			kfree(phba->sli4_hba.rpi_bmask);
+			rc = -ENOMEM;
+			goto err_exit;
+		}
+
+		/*
+		 * The next_rpi was initialized with the maximum available
+		 * count but the port may allocate a smaller number.  Catch
+		 * that case and update the next_rpi.
+		 */
+		phba->sli4_hba.next_rpi = rsrc_id_cnt;
+
+		/* Initialize local ptrs for common extent processing later. */
+		bmask = phba->sli4_hba.rpi_bmask;
+		ids = phba->sli4_hba.rpi_ids;
+		ext_blk_list = &phba->sli4_hba.lpfc_rpi_blk_list;
+		break;
+	case LPFC_RSC_TYPE_FCOE_VPI:
+		phba->vpi_bmask = kzalloc(longs *
+					  sizeof(unsigned long),
+					  GFP_KERNEL);
+		if (unlikely(!phba->vpi_bmask)) {
+			rc = -ENOMEM;
+			goto err_exit;
+		}
+		phba->vpi_ids = kzalloc(rsrc_id_cnt *
+					 sizeof(uint16_t),
+					 GFP_KERNEL);
+		if (unlikely(!phba->vpi_ids)) {
+			kfree(phba->vpi_bmask);
+			rc = -ENOMEM;
+			goto err_exit;
+		}
+
+		/* Initialize local ptrs for common extent processing later. */
+		bmask = phba->vpi_bmask;
+		ids = phba->vpi_ids;
+		ext_blk_list = &phba->lpfc_vpi_blk_list;
+		break;
+	case LPFC_RSC_TYPE_FCOE_XRI:
+		phba->sli4_hba.xri_bmask = kzalloc(longs *
+						   sizeof(unsigned long),
+						   GFP_KERNEL);
+		if (unlikely(!phba->sli4_hba.xri_bmask)) {
+			rc = -ENOMEM;
+			goto err_exit;
+		}
+		phba->sli4_hba.xri_ids = kzalloc(rsrc_id_cnt *
+						 sizeof(uint16_t),
+						 GFP_KERNEL);
+		if (unlikely(!phba->sli4_hba.xri_ids)) {
+			kfree(phba->sli4_hba.xri_bmask);
+			rc = -ENOMEM;
+			goto err_exit;
+		}
+
+		/* Initialize local ptrs for common extent processing later. */
+		bmask = phba->sli4_hba.xri_bmask;
+		ids = phba->sli4_hba.xri_ids;
+		ext_blk_list = &phba->sli4_hba.lpfc_xri_blk_list;
+		break;
+	case LPFC_RSC_TYPE_FCOE_VFI:
+		phba->sli4_hba.vfi_bmask = kzalloc(longs *
+						   sizeof(unsigned long),
+						   GFP_KERNEL);
+		if (unlikely(!phba->sli4_hba.vfi_bmask)) {
+			rc = -ENOMEM;
+			goto err_exit;
+		}
+		phba->sli4_hba.vfi_ids = kzalloc(rsrc_id_cnt *
+						 sizeof(uint16_t),
+						 GFP_KERNEL);
+		if (unlikely(!phba->sli4_hba.vfi_ids)) {
+			kfree(phba->sli4_hba.vfi_bmask);
+			rc = -ENOMEM;
+			goto err_exit;
+		}
+
+		/* Initialize local ptrs for common extent processing later. */
+		bmask = phba->sli4_hba.vfi_bmask;
+		ids = phba->sli4_hba.vfi_ids;
+		ext_blk_list = &phba->sli4_hba.lpfc_vfi_blk_list;
+		break;
+	default:
+		/* Unsupported Opcode.  Fail call. */
+		id_array = NULL;
+		bmask = NULL;
+		ids = NULL;
+		ext_blk_list = NULL;
+		goto err_exit;
+	}
+
+	/*
+	 * Complete initializing the extent configuration with the
+	 * allocated ids assigned to this function.  The bitmask serves
+	 * as an index into the array and manages the available ids.  The
+	 * array just stores the ids communicated to the port via the wqes.
+	 */
+	for (i = 0, j = 0, k = 0; i < rsrc_cnt; i++) {
+		if ((i % 2) == 0)
+			rsrc_id = bf_get(lpfc_mbx_rsrc_id_word4_0,
+					 &id_array[k]);
+		else
+			rsrc_id = bf_get(lpfc_mbx_rsrc_id_word4_1,
+					 &id_array[k]);
+
+		rsrc_blks = kzalloc(length, GFP_KERNEL);
+		if (unlikely(!rsrc_blks)) {
+			rc = -ENOMEM;
+			kfree(bmask);
+			kfree(ids);
+			goto err_exit;
+		}
+		rsrc_blks->rsrc_start = rsrc_id;
+		rsrc_blks->rsrc_size = rsrc_size;
+		list_add_tail(&rsrc_blks->list, ext_blk_list);
+		rsrc_start = rsrc_id;
+		if ((type == LPFC_RSC_TYPE_FCOE_XRI) && (j == 0))
+			phba->sli4_hba.scsi_xri_start = rsrc_start +
+				lpfc_sli4_get_els_iocb_cnt(phba);
+
+		while (rsrc_id < (rsrc_start + rsrc_size)) {
+			ids[j] = rsrc_id;
+			rsrc_id++;
+			j++;
+		}
+		/* Entire word processed.  Get next word.*/
+		if ((i % 2) == 1)
+			k++;
+	}
+ err_exit:
+	lpfc_sli4_mbox_cmd_free(phba, mbox);
+	return rc;
+}
+
+/**
+ * lpfc_sli4_dealloc_extent - Deallocate an SLI4 resource extent.
+ * @phba: Pointer to HBA context object.
+ * @type: the extent's type.
+ *
+ * This function deallocates all extents of a particular resource type.
+ * SLI4 does not allow for deallocating a particular extent range.  It
+ * is the caller's responsibility to release all kernel memory resources.
+ **/
+static int
+lpfc_sli4_dealloc_extent(struct lpfc_hba *phba, uint16_t type)
+{
+	int rc;
+	uint32_t length, mbox_tmo = 0;
+	LPFC_MBOXQ_t *mbox;
+	struct lpfc_mbx_dealloc_rsrc_extents *dealloc_rsrc;
+	struct lpfc_rsrc_blks *rsrc_blk, *rsrc_blk_next;
+
+	mbox = (LPFC_MBOXQ_t *) mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!mbox)
+		return -ENOMEM;
+
+	/*
+	 * This function sends an embedded mailbox because it only sends the
+	 * the resource type.  All extents of this type are released by the
+	 * port.
+	 */
+	length = (sizeof(struct lpfc_mbx_dealloc_rsrc_extents) -
+		  sizeof(struct lpfc_sli4_cfg_mhdr));
+	lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_COMMON,
+			 LPFC_MBOX_OPCODE_DEALLOC_RSRC_EXTENT,
+			 length, LPFC_SLI4_MBX_EMBED);
+
+	/* Send an extents count of 0 - the dealloc doesn't use it. */
+	rc = lpfc_sli4_mbox_rsrc_extent(phba, mbox, 0, type,
+					LPFC_SLI4_MBX_EMBED);
+	if (unlikely(rc)) {
+		rc = -EIO;
+		goto out_free_mbox;
+	}
+	if (!phba->sli4_hba.intr_enable)
+		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_POLL);
+	else {
+		mbox_tmo = lpfc_mbox_tmo_val(phba, mbox_tmo);
+		rc = lpfc_sli_issue_mbox_wait(phba, mbox, mbox_tmo);
+	}
+	if (unlikely(rc)) {
+		rc = -EIO;
+		goto out_free_mbox;
+	}
+
+	dealloc_rsrc = &mbox->u.mqe.un.dealloc_rsrc_extents;
+	if (bf_get(lpfc_mbox_hdr_status,
+		   &dealloc_rsrc->header.cfg_shdr.response)) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_INIT,
+				"2919 Failed to release resource extents "
+				"for type %d - Status 0x%x Add'l Status 0x%x. "
+				"Resource memory not released.\n",
+				type,
+				bf_get(lpfc_mbox_hdr_status,
+				    &dealloc_rsrc->header.cfg_shdr.response),
+				bf_get(lpfc_mbox_hdr_add_status,
+				    &dealloc_rsrc->header.cfg_shdr.response));
+		rc = -EIO;
+		goto out_free_mbox;
+	}
+
+	/* Release kernel memory resources for the specific type. */
+	switch (type) {
+	case LPFC_RSC_TYPE_FCOE_VPI:
+		kfree(phba->vpi_bmask);
+		kfree(phba->vpi_ids);
+		bf_set(lpfc_vpi_rsrc_rdy, &phba->sli4_hba.sli4_flags, 0);
+		list_for_each_entry_safe(rsrc_blk, rsrc_blk_next,
+				    &phba->lpfc_vpi_blk_list, list) {
+			list_del_init(&rsrc_blk->list);
+			kfree(rsrc_blk);
+		}
+		break;
+	case LPFC_RSC_TYPE_FCOE_XRI:
+		kfree(phba->sli4_hba.xri_bmask);
+		kfree(phba->sli4_hba.xri_ids);
+		bf_set(lpfc_xri_rsrc_rdy, &phba->sli4_hba.sli4_flags, 0);
+		list_for_each_entry_safe(rsrc_blk, rsrc_blk_next,
+				    &phba->sli4_hba.lpfc_xri_blk_list, list) {
+			list_del_init(&rsrc_blk->list);
+			kfree(rsrc_blk);
+		}
+		break;
+	case LPFC_RSC_TYPE_FCOE_VFI:
+		kfree(phba->sli4_hba.vfi_bmask);
+		kfree(phba->sli4_hba.vfi_ids);
+		bf_set(lpfc_vfi_rsrc_rdy, &phba->sli4_hba.sli4_flags, 0);
+		list_for_each_entry_safe(rsrc_blk, rsrc_blk_next,
+				    &phba->sli4_hba.lpfc_vfi_blk_list, list) {
+			list_del_init(&rsrc_blk->list);
+			kfree(rsrc_blk);
+		}
+		break;
+	case LPFC_RSC_TYPE_FCOE_RPI:
+		/* RPI bitmask and physical id array are cleaned up earlier. */
+		list_for_each_entry_safe(rsrc_blk, rsrc_blk_next,
+				    &phba->sli4_hba.lpfc_rpi_blk_list, list) {
+			list_del_init(&rsrc_blk->list);
+			kfree(rsrc_blk);
+		}
+		break;
+	default:
+		break;
+	}
+
+	bf_set(lpfc_idx_rsrc_rdy, &phba->sli4_hba.sli4_flags, 0);
+
+ out_free_mbox:
+	mempool_free(mbox, phba->mbox_mem_pool);
+	return rc;
+}
+
+/**
+ * lpfc_sli4_alloc_resource_identifiers - Allocate all SLI4 resource extents.
+ * @phba: Pointer to HBA context object.
+ *
+ * This function allocates all SLI4 resource identifiers.
+ **/
+int
+lpfc_sli4_alloc_resource_identifiers(struct lpfc_hba *phba)
+{
+	int i, rc, error = 0;
+	uint16_t count, base;
+	unsigned long longs;
+
+	if (phba->sli4_hba.extents_in_use) {
+		/*
+		 * The port supports resource extents. The XRI, VPI, VFI, RPI
+		 * resource extent count must be read and allocated before
+		 * provisioning the resource id arrays.
+		 */
+		if (bf_get(lpfc_idx_rsrc_rdy, &phba->sli4_hba.sli4_flags) ==
+		    LPFC_IDX_RSRC_RDY) {
+			/*
+			 * Extent-based resources are set - the driver could
+			 * be in a port reset. Figure out if any corrective
+			 * actions need to be taken.
+			 */
+			rc = lpfc_sli4_chk_avail_extnt_rsrc(phba,
+						 LPFC_RSC_TYPE_FCOE_VFI);
+			if (rc != 0)
+				error++;
+			rc = lpfc_sli4_chk_avail_extnt_rsrc(phba,
+						 LPFC_RSC_TYPE_FCOE_VPI);
+			if (rc != 0)
+				error++;
+			rc = lpfc_sli4_chk_avail_extnt_rsrc(phba,
+						 LPFC_RSC_TYPE_FCOE_XRI);
+			if (rc != 0)
+				error++;
+			rc = lpfc_sli4_chk_avail_extnt_rsrc(phba,
+						 LPFC_RSC_TYPE_FCOE_RPI);
+			if (rc != 0)
+				error++;
+
+			/*
+			 * It's possible that the number of resources
+			 * provided to this port instance changed between
+			 * resets.  Detect this condition and reallocate
+			 * resources.  Otherwise, there is no action.
+			 */
+			if (error) {
+				lpfc_printf_log(phba, KERN_INFO,
+						LOG_MBOX | LOG_INIT,
+						"2931 Detected extent resource "
+						"change.  Reallocating all "
+						"extents.\n");
+				rc = lpfc_sli4_dealloc_extent(phba,
+						 LPFC_RSC_TYPE_FCOE_VFI);
+				rc = lpfc_sli4_dealloc_extent(phba,
+						 LPFC_RSC_TYPE_FCOE_VPI);
+				rc = lpfc_sli4_dealloc_extent(phba,
+						 LPFC_RSC_TYPE_FCOE_XRI);
+				rc = lpfc_sli4_dealloc_extent(phba,
+						 LPFC_RSC_TYPE_FCOE_RPI);
+			} else
+				return 0;
+		}
+
+		rc = lpfc_sli4_alloc_extent(phba, LPFC_RSC_TYPE_FCOE_VFI);
+		if (unlikely(rc))
+			goto err_exit;
+
+		rc = lpfc_sli4_alloc_extent(phba, LPFC_RSC_TYPE_FCOE_VPI);
+		if (unlikely(rc))
+			goto err_exit;
+
+		rc = lpfc_sli4_alloc_extent(phba, LPFC_RSC_TYPE_FCOE_RPI);
+		if (unlikely(rc))
+			goto err_exit;
+
+		rc = lpfc_sli4_alloc_extent(phba, LPFC_RSC_TYPE_FCOE_XRI);
+		if (unlikely(rc))
+			goto err_exit;
+		bf_set(lpfc_idx_rsrc_rdy, &phba->sli4_hba.sli4_flags,
+		       LPFC_IDX_RSRC_RDY);
+		return rc;
+	} else {
+		/*
+		 * The port does not support resource extents.  The XRI, VPI,
+		 * VFI, RPI resource ids were determined from READ_CONFIG.
+		 * Just allocate the bitmasks and provision the resource id
+		 * arrays.  If a port reset is active, the resources don't
+		 * need any action - just exit.
+		 */
+		if (bf_get(lpfc_idx_rsrc_rdy, &phba->sli4_hba.sli4_flags) ==
+		    LPFC_IDX_RSRC_RDY)
+			return 0;
+
+		/* RPIs. */
+		count = phba->sli4_hba.max_cfg_param.max_rpi;
+		base = phba->sli4_hba.max_cfg_param.rpi_base;
+		longs = (count + BITS_PER_LONG - 1) / BITS_PER_LONG;
+		phba->sli4_hba.rpi_bmask = kzalloc(longs *
+						   sizeof(unsigned long),
+						   GFP_KERNEL);
+		if (unlikely(!phba->sli4_hba.rpi_bmask)) {
+			rc = -ENOMEM;
+			goto err_exit;
+		}
+		phba->sli4_hba.rpi_ids = kzalloc(count *
+						 sizeof(uint16_t),
+						 GFP_KERNEL);
+		if (unlikely(!phba->sli4_hba.rpi_ids)) {
+			rc = -ENOMEM;
+			goto free_rpi_bmask;
+		}
+
+		for (i = 0; i < count; i++)
+			phba->sli4_hba.rpi_ids[i] = base + i;
+
+		/* VPIs. */
+		count = phba->sli4_hba.max_cfg_param.max_vpi;
+		base = phba->sli4_hba.max_cfg_param.vpi_base;
+		longs = (count + BITS_PER_LONG - 1) / BITS_PER_LONG;
+		phba->vpi_bmask = kzalloc(longs *
+					  sizeof(unsigned long),
+					  GFP_KERNEL);
+		if (unlikely(!phba->vpi_bmask)) {
+			rc = -ENOMEM;
+			goto free_rpi_ids;
+		}
+		phba->vpi_ids = kzalloc(count *
+					sizeof(uint16_t),
+					GFP_KERNEL);
+		if (unlikely(!phba->vpi_ids)) {
+			rc = -ENOMEM;
+			goto free_vpi_bmask;
+		}
+
+		for (i = 0; i < count; i++)
+			phba->vpi_ids[i] = base + i;
+
+		/* XRIs. */
+		count = phba->sli4_hba.max_cfg_param.max_xri;
+		base = phba->sli4_hba.max_cfg_param.xri_base;
+		longs = (count + BITS_PER_LONG - 1) / BITS_PER_LONG;
+		phba->sli4_hba.xri_bmask = kzalloc(longs *
+						   sizeof(unsigned long),
+						   GFP_KERNEL);
+		if (unlikely(!phba->sli4_hba.xri_bmask)) {
+			rc = -ENOMEM;
+			goto free_vpi_ids;
+		}
+		phba->sli4_hba.xri_ids = kzalloc(count *
+						 sizeof(uint16_t),
+						 GFP_KERNEL);
+		if (unlikely(!phba->sli4_hba.xri_ids)) {
+			rc = -ENOMEM;
+			goto free_xri_bmask;
+		}
+
+		for (i = 0; i < count; i++)
+			phba->sli4_hba.xri_ids[i] = base + i;
+
+		/* VFIs. */
+		count = phba->sli4_hba.max_cfg_param.max_vfi;
+		base = phba->sli4_hba.max_cfg_param.vfi_base;
+		longs = (count + BITS_PER_LONG - 1) / BITS_PER_LONG;
+		phba->sli4_hba.vfi_bmask = kzalloc(longs *
+						   sizeof(unsigned long),
+						   GFP_KERNEL);
+		if (unlikely(!phba->sli4_hba.vfi_bmask)) {
+			rc = -ENOMEM;
+			goto free_xri_ids;
+		}
+		phba->sli4_hba.vfi_ids = kzalloc(count *
+						 sizeof(uint16_t),
+						 GFP_KERNEL);
+		if (unlikely(!phba->sli4_hba.vfi_ids)) {
+			rc = -ENOMEM;
+			goto free_vfi_bmask;
+		}
+
+		for (i = 0; i < count; i++)
+			phba->sli4_hba.vfi_ids[i] = base + i;
+
+		/*
+		 * Mark all resources ready.  An HBA reset doesn't need
+		 * to reset the initialization.
+		 */
+		bf_set(lpfc_idx_rsrc_rdy, &phba->sli4_hba.sli4_flags,
+		       LPFC_IDX_RSRC_RDY);
+		return 0;
+	}
+
+ free_vfi_bmask:
+	kfree(phba->sli4_hba.vfi_bmask);
+ free_xri_ids:
+	kfree(phba->sli4_hba.xri_ids);
+ free_xri_bmask:
+	kfree(phba->sli4_hba.xri_bmask);
+ free_vpi_ids:
+	kfree(phba->vpi_ids);
+ free_vpi_bmask:
+	kfree(phba->vpi_bmask);
+ free_rpi_ids:
+	kfree(phba->sli4_hba.rpi_ids);
+ free_rpi_bmask:
+	kfree(phba->sli4_hba.rpi_bmask);
+ err_exit:
+	return rc;
+}
+
+/**
+ * lpfc_sli4_dealloc_resource_identifiers - Deallocate all SLI4 resource extents.
+ * @phba: Pointer to HBA context object.
+ *
+ * This function allocates the number of elements for the specified
+ * resource type.
+ **/
+int
+lpfc_sli4_dealloc_resource_identifiers(struct lpfc_hba *phba)
+{
+	if (phba->sli4_hba.extents_in_use) {
+		lpfc_sli4_dealloc_extent(phba, LPFC_RSC_TYPE_FCOE_VPI);
+		lpfc_sli4_dealloc_extent(phba, LPFC_RSC_TYPE_FCOE_RPI);
+		lpfc_sli4_dealloc_extent(phba, LPFC_RSC_TYPE_FCOE_XRI);
+		lpfc_sli4_dealloc_extent(phba, LPFC_RSC_TYPE_FCOE_VFI);
+	} else {
+		kfree(phba->vpi_bmask);
+		kfree(phba->vpi_ids);
+		bf_set(lpfc_vpi_rsrc_rdy, &phba->sli4_hba.sli4_flags, 0);
+		kfree(phba->sli4_hba.xri_bmask);
+		kfree(phba->sli4_hba.xri_ids);
+		bf_set(lpfc_xri_rsrc_rdy, &phba->sli4_hba.sli4_flags, 0);
+		kfree(phba->sli4_hba.vfi_bmask);
+		kfree(phba->sli4_hba.vfi_ids);
+		bf_set(lpfc_vfi_rsrc_rdy, &phba->sli4_hba.sli4_flags, 0);
+		bf_set(lpfc_idx_rsrc_rdy, &phba->sli4_hba.sli4_flags, 0);
+	}
+
+	return 0;
+}
+
+/**
  * lpfc_sli4_hba_setup - SLI4 device intialization PCI function
  * @phba: Pointer to HBA context object.
  *
@@ -4708,10 +5527,6 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 	struct lpfc_vport *vport = phba->pport;
 	struct lpfc_dmabuf *mp;
 
-	/*
-	 * TODO:  Why does this routine execute these task in a different
-	 * order from probe?
-	 */
 	/* Perform a PCI function reset to start from clean */
 	rc = lpfc_pci_function_reset(phba);
 	if (unlikely(rc))
@@ -4740,7 +5555,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 	 * to read FCoE param config regions
 	 */
 	if (lpfc_sli4_read_fcoe_params(phba, mboxq))
-		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_INIT,
+		lpfc_printf_log(phba, KERN_WARNING, LOG_MBOX | LOG_INIT,
 			"2570 Failed to read FCoE parameters\n");
 
 	/* Issue READ_REV to collect vpd and FW information. */
@@ -4873,6 +5688,18 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 	phba->sli3_options |= (LPFC_SLI3_NPIV_ENABLED | LPFC_SLI3_HBQ_ENABLED);
 	spin_unlock_irq(&phba->hbalock);
 
+	/*
+	 * Allocate all resources (xri,rpi,vpi,vfi) now.  Subsequent
+	 * calls depends on these resources to complete port setup.
+	 */
+	rc = lpfc_sli4_alloc_resource_identifiers(phba);
+	if (rc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
+				"2920 Failed to alloc Resource IDs "
+				"rc = x%x\n", rc);
+		goto out_free_mbox;
+	}
+
 	/* Read the port's service parameters. */
 	rc = lpfc_read_sparam(phba, mboxq, vport->vpi);
 	if (rc) {
@@ -4906,35 +5733,37 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 		goto out_free_mbox;
 	}
 
-	if (phba->cfg_soft_wwnn)
-		u64_to_wwn(phba->cfg_soft_wwnn,
-			   vport->fc_sparam.nodeName.u.wwn);
-	if (phba->cfg_soft_wwpn)
-		u64_to_wwn(phba->cfg_soft_wwpn,
-			   vport->fc_sparam.portName.u.wwn);
-	memcpy(&vport->fc_nodename, &vport->fc_sparam.nodeName,
-	       sizeof(struct lpfc_name));
-	memcpy(&vport->fc_portname, &vport->fc_sparam.portName,
-	       sizeof(struct lpfc_name));
+	lpfc_update_vport_wwn(vport);
 
 	/* Update the fc_host data structures with new wwn. */
 	fc_host_node_name(shost) = wwn_to_u64(vport->fc_nodename.u.wwn);
 	fc_host_port_name(shost) = wwn_to_u64(vport->fc_portname.u.wwn);
 
 	/* Register SGL pool to the device using non-embedded mailbox command */
-	rc = lpfc_sli4_post_sgl_list(phba);
-	if (unlikely(rc)) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
-				"0582 Error %d during sgl post operation\n",
-					rc);
-		rc = -ENODEV;
-		goto out_free_mbox;
+	if (!phba->sli4_hba.extents_in_use) {
+		rc = lpfc_sli4_post_els_sgl_list(phba);
+		if (unlikely(rc)) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
+					"0582 Error %d during els sgl post "
+					"operation\n", rc);
+			rc = -ENODEV;
+			goto out_free_mbox;
+		}
+	} else {
+		rc = lpfc_sli4_post_els_sgl_list_ext(phba);
+		if (unlikely(rc)) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
+					"2560 Error %d during els sgl post "
+					"operation\n", rc);
+			rc = -ENODEV;
+			goto out_free_mbox;
+		}
 	}
 
 	/* Register SCSI SGL pool to the device */
 	rc = lpfc_sli4_repost_scsi_sgl_list(phba);
 	if (unlikely(rc)) {
-		lpfc_printf_log(phba, KERN_WARNING, LOG_MBOX | LOG_SLI,
+		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
 				"0383 Error %d during scsi sgl post "
 				"operation\n", rc);
 		/* Some Scsi buffers were moved to the abort scsi list */
@@ -5747,10 +6576,15 @@ lpfc_sli4_post_sync_mbox(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 	lpfc_sli_pcimem_bcopy(&mbox_rgn->mcqe, &mboxq->mcqe,
 			      sizeof(struct lpfc_mcqe));
 	mcqe_status = bf_get(lpfc_mcqe_status, &mbox_rgn->mcqe);
-
-	/* Prefix the mailbox status with range x4000 to note SLI4 status. */
+	/*
+	 * When the CQE status indicates a failure and the mailbox status
+	 * indicates success then copy the CQE status into the mailbox status
+	 * (and prefix it with x4000).
+	 */
 	if (mcqe_status != MB_CQE_STATUS_SUCCESS) {
-		bf_set(lpfc_mqe_status, mb, LPFC_MBX_ERROR_RANGE | mcqe_status);
+		if (bf_get(lpfc_mqe_status, mb) == MBX_SUCCESS)
+			bf_set(lpfc_mqe_status, mb,
+			       (LPFC_MBX_ERROR_RANGE | mcqe_status));
 		rc = MBXERR_ERROR;
 	} else
 		lpfc_sli4_swap_str(phba, mboxq);
@@ -5819,7 +6653,7 @@ lpfc_sli_issue_mbox_s4(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq,
 		else
 			rc = -EIO;
 		if (rc != MBX_SUCCESS)
-			lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
+			lpfc_printf_log(phba, KERN_WARNING, LOG_MBOX | LOG_SLI,
 					"(%d):2541 Mailbox command x%x "
 					"(x%x) cannot issue Data: x%x x%x\n",
 					mboxq->vport ? mboxq->vport->vpi : 0,
@@ -6307,6 +7141,7 @@ lpfc_sli4_bpl2sgl(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq,
 			sgl->addr_hi = bpl->addrHigh;
 			sgl->addr_lo = bpl->addrLow;
 
+			sgl->word2 = le32_to_cpu(sgl->word2);
 			if ((i+1) == numBdes)
 				bf_set(lpfc_sli4_sge_last, sgl, 1);
 			else
@@ -6343,6 +7178,7 @@ lpfc_sli4_bpl2sgl(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq,
 				cpu_to_le32(icmd->un.genreq64.bdl.addrHigh);
 			sgl->addr_lo =
 				cpu_to_le32(icmd->un.genreq64.bdl.addrLow);
+			sgl->word2 = le32_to_cpu(sgl->word2);
 			bf_set(lpfc_sli4_sge_last, sgl, 1);
 			sgl->word2 = cpu_to_le32(sgl->word2);
 			sgl->sge_len =
@@ -6474,7 +7310,8 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 			els_id = ((iocbq->iocb_flag & LPFC_FIP_ELS_ID_MASK)
 					>> LPFC_FIP_ELS_ID_SHIFT);
 		}
-		bf_set(wqe_temp_rpi, &wqe->els_req.wqe_com, ndlp->nlp_rpi);
+		bf_set(wqe_temp_rpi, &wqe->els_req.wqe_com,
+		       phba->sli4_hba.rpi_ids[ndlp->nlp_rpi]);
 		bf_set(wqe_els_id, &wqe->els_req.wqe_com, els_id);
 		bf_set(wqe_dbde, &wqe->els_req.wqe_com, 1);
 		bf_set(wqe_iod, &wqe->els_req.wqe_com, LPFC_WQE_IOD_READ);
@@ -6623,14 +7460,15 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		       iocbq->iocb.ulpContext);
 		if (!iocbq->iocb.ulpCt_h && iocbq->iocb.ulpCt_l)
 			bf_set(wqe_ctxt_tag, &wqe->xmit_els_rsp.wqe_com,
-			       iocbq->vport->vpi + phba->vpi_base);
+			       phba->vpi_ids[iocbq->vport->vpi]);
 		bf_set(wqe_dbde, &wqe->xmit_els_rsp.wqe_com, 1);
 		bf_set(wqe_iod, &wqe->xmit_els_rsp.wqe_com, LPFC_WQE_IOD_WRITE);
 		bf_set(wqe_qosd, &wqe->xmit_els_rsp.wqe_com, 1);
 		bf_set(wqe_lenloc, &wqe->xmit_els_rsp.wqe_com,
 		       LPFC_WQE_LENLOC_WORD3);
 		bf_set(wqe_ebde_cnt, &wqe->xmit_els_rsp.wqe_com, 0);
-		bf_set(wqe_rsp_temp_rpi, &wqe->xmit_els_rsp, ndlp->nlp_rpi);
+		bf_set(wqe_rsp_temp_rpi, &wqe->xmit_els_rsp,
+		       phba->sli4_hba.rpi_ids[ndlp->nlp_rpi]);
 		command_type = OTHER_COMMAND;
 	break;
 	case CMD_CLOSE_XRI_CN:
@@ -6729,6 +7567,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		return IOCB_ERROR;
 	break;
 	}
+
 	bf_set(wqe_xri_tag, &wqe->generic.wqe_com, xritag);
 	bf_set(wqe_reqtag, &wqe->generic.wqe_com, iocbq->iotag);
 	wqe->generic.wqe_com.abort_tag = abort_tag;
@@ -6776,7 +7615,7 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 					return IOCB_BUSY;
 				}
 			} else {
-			sglq = __lpfc_sli_get_sglq(phba, piocb);
+				sglq = __lpfc_sli_get_sglq(phba, piocb);
 				if (!sglq) {
 					if (!(flag & SLI_IOCB_RET_IOCB)) {
 						__lpfc_sli_ringtx_put(phba,
@@ -6789,11 +7628,11 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 			}
 		}
 	} else if (piocb->iocb_flag &  LPFC_IO_FCP) {
-		sglq = NULL; /* These IO's already have an XRI and
-			      * a mapped sgl.
-			      */
+		/* These IO's already have an XRI and a mapped sgl. */
+		sglq = NULL;
 	} else {
-		/* This is a continuation of a commandi,(CX) so this
+		/*
+		 * This is a continuation of a commandi,(CX) so this
 		 * sglq is on the active list
 		 */
 		sglq = __lpfc_get_active_sglq(phba, piocb->sli4_xritag);
@@ -6802,8 +7641,8 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 	}
 
 	if (sglq) {
+		piocb->sli4_lxritag = sglq->sli4_lxritag;
 		piocb->sli4_xritag = sglq->sli4_xritag;
-
 		if (NO_XRI == lpfc_sli4_bpl2sgl(phba, piocb, sglq))
 			return IOCB_ERROR;
 	}
@@ -9799,7 +10638,12 @@ lpfc_sli4_sp_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe)
 		break;
 	case LPFC_WCQ:
 		while ((cqe = lpfc_sli4_cq_get(cq))) {
-			workposted |= lpfc_sli4_sp_handle_cqe(phba, cq, cqe);
+			if (cq->subtype == LPFC_FCP)
+				workposted |= lpfc_sli4_fp_handle_wcqe(phba, cq,
+								       cqe);
+			else
+				workposted |= lpfc_sli4_sp_handle_cqe(phba, cq,
+								      cqe);
 			if (!(++ecount % LPFC_GET_QE_REL_INT))
 				lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
 		}
@@ -11446,6 +12290,7 @@ lpfc_sli4_post_sgl(struct lpfc_hba *phba,
 	LPFC_MBOXQ_t *mbox;
 	int rc;
 	uint32_t shdr_status, shdr_add_status;
+	uint32_t mbox_tmo;
 	union lpfc_sli4_cfg_shdr *shdr;
 
 	if (xritag == NO_XRI) {
@@ -11479,8 +12324,10 @@ lpfc_sli4_post_sgl(struct lpfc_hba *phba,
 				cpu_to_le32(putPaddrHigh(pdma_phys_addr1));
 	if (!phba->sli4_hba.intr_enable)
 		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_POLL);
-	else
-		rc = lpfc_sli_issue_mbox_wait(phba, mbox, LPFC_MBOX_TMO);
+	else {
+		mbox_tmo = lpfc_mbox_tmo_val(phba, MBX_SLI4_CONFIG);
+		rc = lpfc_sli_issue_mbox_wait(phba, mbox, mbox_tmo);
+	}
 	/* The IOCTL status is embedded in the mailbox subheader. */
 	shdr = (union lpfc_sli4_cfg_shdr *) &post_sgl_pages->header.cfg_shdr;
 	shdr_status = bf_get(lpfc_mbox_hdr_status, &shdr->response);
@@ -11498,6 +12345,76 @@ lpfc_sli4_post_sgl(struct lpfc_hba *phba,
 }
 
 /**
+ * lpfc_sli4_init_rpi_hdrs - Post the rpi header memory region to the port
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine is invoked to post rpi header templates to the
+ * port for those SLI4 ports that do not support extents.  This routine
+ * posts a PAGE_SIZE memory region to the port to hold up to
+ * PAGE_SIZE modulo 64 rpi context headers.  This is an initialization routine
+ * and should be called only when interrupts are disabled.
+ *
+ * Return codes
+ *	0 - successful
+ *	-ERROR - otherwise.
+ */
+uint16_t
+lpfc_sli4_alloc_xri(struct lpfc_hba *phba)
+{
+	unsigned long xri;
+
+	/*
+	 * Fetch the next logical xri.  Because this index is logical,
+	 * the driver starts at 0 each time.
+	 */
+	spin_lock_irq(&phba->hbalock);
+	xri = find_next_zero_bit(phba->sli4_hba.xri_bmask,
+				 phba->sli4_hba.max_cfg_param.max_xri, 0);
+	if (xri >= phba->sli4_hba.max_cfg_param.max_xri) {
+		spin_unlock_irq(&phba->hbalock);
+		return NO_XRI;
+	} else {
+		set_bit(xri, phba->sli4_hba.xri_bmask);
+		phba->sli4_hba.max_cfg_param.xri_used++;
+		phba->sli4_hba.xri_count++;
+	}
+
+	spin_unlock_irq(&phba->hbalock);
+	return xri;
+}
+
+/**
+ * lpfc_sli4_free_xri - Release an xri for reuse.
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine is invoked to release an xri to the pool of
+ * available rpis maintained by the driver.
+ **/
+void
+__lpfc_sli4_free_xri(struct lpfc_hba *phba, int xri)
+{
+	if (test_and_clear_bit(xri, phba->sli4_hba.xri_bmask)) {
+		phba->sli4_hba.xri_count--;
+		phba->sli4_hba.max_cfg_param.xri_used--;
+	}
+}
+
+/**
+ * lpfc_sli4_free_xri - Release an xri for reuse.
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine is invoked to release an xri to the pool of
+ * available rpis maintained by the driver.
+ **/
+void
+lpfc_sli4_free_xri(struct lpfc_hba *phba, int xri)
+{
+	spin_lock_irq(&phba->hbalock);
+	__lpfc_sli4_free_xri(phba, xri);
+	spin_unlock_irq(&phba->hbalock);
+}
+
+/**
  * lpfc_sli4_next_xritag - Get an xritag for the io
  * @phba: Pointer to HBA context object.
  *
@@ -11510,30 +12427,23 @@ lpfc_sli4_post_sgl(struct lpfc_hba *phba,
 uint16_t
 lpfc_sli4_next_xritag(struct lpfc_hba *phba)
 {
-	uint16_t xritag;
+	uint16_t xri_index;
 
-	spin_lock_irq(&phba->hbalock);
-	xritag = phba->sli4_hba.next_xri;
-	if ((xritag != (uint16_t) -1) && xritag <
-		(phba->sli4_hba.max_cfg_param.max_xri
-			+ phba->sli4_hba.max_cfg_param.xri_base)) {
-		phba->sli4_hba.next_xri++;
-		phba->sli4_hba.max_cfg_param.xri_used++;
-		spin_unlock_irq(&phba->hbalock);
-		return xritag;
-	}
-	spin_unlock_irq(&phba->hbalock);
-	lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
+	xri_index = lpfc_sli4_alloc_xri(phba);
+	if (xri_index != NO_XRI)
+		return xri_index;
+
+	lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
 			"2004 Failed to allocate XRI.last XRITAG is %d"
 			" Max XRI is %d, Used XRI is %d\n",
-			phba->sli4_hba.next_xri,
+			xri_index,
 			phba->sli4_hba.max_cfg_param.max_xri,
 			phba->sli4_hba.max_cfg_param.xri_used);
-	return -1;
+	return NO_XRI;
 }
 
 /**
- * lpfc_sli4_post_sgl_list - post a block of sgl list to the firmware.
+ * lpfc_sli4_post_els_sgl_list - post a block of ELS sgls to the port.
  * @phba: pointer to lpfc hba data structure.
  *
  * This routine is invoked to post a block of driver's sgl pages to the
@@ -11542,7 +12452,7 @@ lpfc_sli4_next_xritag(struct lpfc_hba *phba)
  * stopped.
  **/
 int
-lpfc_sli4_post_sgl_list(struct lpfc_hba *phba)
+lpfc_sli4_post_els_sgl_list(struct lpfc_hba *phba)
 {
 	struct lpfc_sglq *sglq_entry;
 	struct lpfc_mbx_post_uembed_sgl_page1 *sgl;
@@ -11551,7 +12461,7 @@ lpfc_sli4_post_sgl_list(struct lpfc_hba *phba)
 	LPFC_MBOXQ_t *mbox;
 	uint32_t reqlen, alloclen, pg_pairs;
 	uint32_t mbox_tmo;
-	uint16_t xritag_start = 0;
+	uint16_t xritag_start = 0, lxri = 0;
 	int els_xri_cnt, rc = 0;
 	uint32_t shdr_status, shdr_add_status;
 	union lpfc_sli4_cfg_shdr *shdr;
@@ -11568,11 +12478,8 @@ lpfc_sli4_post_sgl_list(struct lpfc_hba *phba)
 		return -ENOMEM;
 	}
 	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-	if (!mbox) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"2560 Failed to allocate mbox cmd memory\n");
+	if (!mbox)
 		return -ENOMEM;
-	}
 
 	/* Allocate DMA memory and set up the non-embedded mailbox command */
 	alloclen = lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_FCOE,
@@ -11587,15 +12494,30 @@ lpfc_sli4_post_sgl_list(struct lpfc_hba *phba)
 		lpfc_sli4_mbox_cmd_free(phba, mbox);
 		return -ENOMEM;
 	}
-	/* Get the first SGE entry from the non-embedded DMA memory */
-	viraddr = mbox->sge_array->addr[0];
-
 	/* Set up the SGL pages in the non-embedded DMA pages */
+	viraddr = mbox->sge_array->addr[0];
 	sgl = (struct lpfc_mbx_post_uembed_sgl_page1 *)viraddr;
 	sgl_pg_pairs = &sgl->sgl_pg_pairs;
 
 	for (pg_pairs = 0; pg_pairs < els_xri_cnt; pg_pairs++) {
 		sglq_entry = phba->sli4_hba.lpfc_els_sgl_array[pg_pairs];
+
+		/*
+		 * Assign the sglq a physical xri only if the driver has not
+		 * initialized those resources.  A port reset only needs
+		 * the sglq's posted.
+		 */
+		if (bf_get(lpfc_xri_rsrc_rdy, &phba->sli4_hba.sli4_flags) !=
+		    LPFC_XRI_RSRC_RDY) {
+			lxri = lpfc_sli4_next_xritag(phba);
+			if (lxri == NO_XRI) {
+				lpfc_sli4_mbox_cmd_free(phba, mbox);
+				return -ENOMEM;
+			}
+			sglq_entry->sli4_lxritag = lxri;
+			sglq_entry->sli4_xritag = phba->sli4_hba.xri_ids[lxri];
+		}
+
 		/* Set up the sge entry */
 		sgl_pg_pairs->sgl_pg0_addr_lo =
 				cpu_to_le32(putPaddrLow(sglq_entry->phys));
@@ -11605,16 +12527,17 @@ lpfc_sli4_post_sgl_list(struct lpfc_hba *phba)
 				cpu_to_le32(putPaddrLow(0));
 		sgl_pg_pairs->sgl_pg1_addr_hi =
 				cpu_to_le32(putPaddrHigh(0));
+
 		/* Keep the first xritag on the list */
 		if (pg_pairs == 0)
 			xritag_start = sglq_entry->sli4_xritag;
 		sgl_pg_pairs++;
 	}
+
+	/* Complete initialization and perform endian conversion. */
 	bf_set(lpfc_post_sgl_pages_xri, sgl, xritag_start);
 	bf_set(lpfc_post_sgl_pages_xricnt, sgl, els_xri_cnt);
-	/* Perform endian conversion if necessary */
 	sgl->word0 = cpu_to_le32(sgl->word0);
-
 	if (!phba->sli4_hba.intr_enable)
 		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_POLL);
 	else {
@@ -11633,6 +12556,181 @@ lpfc_sli4_post_sgl_list(struct lpfc_hba *phba)
 				shdr_status, shdr_add_status, rc);
 		rc = -ENXIO;
 	}
+
+	if (rc == 0)
+		bf_set(lpfc_xri_rsrc_rdy, &phba->sli4_hba.sli4_flags,
+		       LPFC_XRI_RSRC_RDY);
+	return rc;
+}
+
+/**
+ * lpfc_sli4_post_els_sgl_list_ext - post a block of ELS sgls to the port.
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine is invoked to post a block of driver's sgl pages to the
+ * HBA using non-embedded mailbox command. No Lock is held. This routine
+ * is only called when the driver is loading and after all IO has been
+ * stopped.
+ **/
+int
+lpfc_sli4_post_els_sgl_list_ext(struct lpfc_hba *phba)
+{
+	struct lpfc_sglq *sglq_entry;
+	struct lpfc_mbx_post_uembed_sgl_page1 *sgl;
+	struct sgl_page_pairs *sgl_pg_pairs;
+	void *viraddr;
+	LPFC_MBOXQ_t *mbox;
+	uint32_t reqlen, alloclen, index;
+	uint32_t mbox_tmo;
+	uint16_t rsrc_start, rsrc_size, els_xri_cnt;
+	uint16_t xritag_start = 0, lxri = 0;
+	struct lpfc_rsrc_blks *rsrc_blk;
+	int cnt, ttl_cnt, rc = 0;
+	int loop_cnt;
+	uint32_t shdr_status, shdr_add_status;
+	union lpfc_sli4_cfg_shdr *shdr;
+
+	/* The number of sgls to be posted */
+	els_xri_cnt = lpfc_sli4_get_els_iocb_cnt(phba);
+
+	reqlen = els_xri_cnt * sizeof(struct sgl_page_pairs) +
+		 sizeof(union lpfc_sli4_cfg_shdr) + sizeof(uint32_t);
+	if (reqlen > SLI4_PAGE_SIZE) {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
+				"2989 Block sgl registration required DMA "
+				"size (%d) great than a page\n", reqlen);
+		return -ENOMEM;
+	}
+
+	cnt = 0;
+	ttl_cnt = 0;
+	list_for_each_entry(rsrc_blk, &phba->sli4_hba.lpfc_xri_blk_list,
+			    list) {
+		rsrc_start = rsrc_blk->rsrc_start;
+		rsrc_size = rsrc_blk->rsrc_size;
+
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+				"3014 Working ELS Extent start %d, cnt %d\n",
+				rsrc_start, rsrc_size);
+
+		loop_cnt = min(els_xri_cnt, rsrc_size);
+		if (ttl_cnt + loop_cnt >= els_xri_cnt) {
+			loop_cnt = els_xri_cnt - ttl_cnt;
+			ttl_cnt = els_xri_cnt;
+		}
+
+		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+		if (!mbox)
+			return -ENOMEM;
+		/*
+		 * Allocate DMA memory and set up the non-embedded mailbox
+		 * command.
+		 */
+		alloclen = lpfc_sli4_config(phba, mbox,
+					LPFC_MBOX_SUBSYSTEM_FCOE,
+					LPFC_MBOX_OPCODE_FCOE_POST_SGL_PAGES,
+					reqlen, LPFC_SLI4_MBX_NEMBED);
+		if (alloclen < reqlen) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"2987 Allocated DMA memory size (%d) "
+					"is less than the requested DMA memory "
+					"size (%d)\n", alloclen, reqlen);
+			lpfc_sli4_mbox_cmd_free(phba, mbox);
+			return -ENOMEM;
+		}
+
+		/* Set up the SGL pages in the non-embedded DMA pages */
+		viraddr = mbox->sge_array->addr[0];
+		sgl = (struct lpfc_mbx_post_uembed_sgl_page1 *)viraddr;
+		sgl_pg_pairs = &sgl->sgl_pg_pairs;
+
+		/*
+		 * The starting resource may not begin at zero. Control
+		 * the loop variants via the block resource parameters,
+		 * but handle the sge pointers with a zero-based index
+		 * that doesn't get reset per loop pass.
+		 */
+		for (index = rsrc_start;
+		     index < rsrc_start + loop_cnt;
+		     index++) {
+			sglq_entry = phba->sli4_hba.lpfc_els_sgl_array[cnt];
+
+			/*
+			 * Assign the sglq a physical xri only if the driver
+			 * has not initialized those resources.  A port reset
+			 * only needs the sglq's posted.
+			 */
+			if (bf_get(lpfc_xri_rsrc_rdy,
+				   &phba->sli4_hba.sli4_flags) !=
+				   LPFC_XRI_RSRC_RDY) {
+				lxri = lpfc_sli4_next_xritag(phba);
+				if (lxri == NO_XRI) {
+					lpfc_sli4_mbox_cmd_free(phba, mbox);
+					rc = -ENOMEM;
+					goto err_exit;
+				}
+				sglq_entry->sli4_lxritag = lxri;
+				sglq_entry->sli4_xritag =
+						phba->sli4_hba.xri_ids[lxri];
+			}
+
+			/* Set up the sge entry */
+			sgl_pg_pairs->sgl_pg0_addr_lo =
+				cpu_to_le32(putPaddrLow(sglq_entry->phys));
+			sgl_pg_pairs->sgl_pg0_addr_hi =
+				cpu_to_le32(putPaddrHigh(sglq_entry->phys));
+			sgl_pg_pairs->sgl_pg1_addr_lo =
+				cpu_to_le32(putPaddrLow(0));
+			sgl_pg_pairs->sgl_pg1_addr_hi =
+				cpu_to_le32(putPaddrHigh(0));
+
+			/* Track the starting physical XRI for the mailbox. */
+			if (index == rsrc_start)
+				xritag_start = sglq_entry->sli4_xritag;
+			sgl_pg_pairs++;
+			cnt++;
+		}
+
+		/* Complete initialization and perform endian conversion. */
+		rsrc_blk->rsrc_used += loop_cnt;
+		bf_set(lpfc_post_sgl_pages_xri, sgl, xritag_start);
+		bf_set(lpfc_post_sgl_pages_xricnt, sgl, loop_cnt);
+		sgl->word0 = cpu_to_le32(sgl->word0);
+
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+				"3015 Post ELS Extent SGL, start %d, "
+				"cnt %d, used %d\n",
+				xritag_start, loop_cnt, rsrc_blk->rsrc_used);
+		if (!phba->sli4_hba.intr_enable)
+			rc = lpfc_sli_issue_mbox(phba, mbox, MBX_POLL);
+		else {
+			mbox_tmo = lpfc_mbox_tmo_val(phba, MBX_SLI4_CONFIG);
+			rc = lpfc_sli_issue_mbox_wait(phba, mbox, mbox_tmo);
+		}
+		shdr = (union lpfc_sli4_cfg_shdr *) &sgl->cfg_shdr;
+		shdr_status = bf_get(lpfc_mbox_hdr_status,
+				     &shdr->response);
+		shdr_add_status = bf_get(lpfc_mbox_hdr_add_status,
+					 &shdr->response);
+		if (rc != MBX_TIMEOUT)
+			lpfc_sli4_mbox_cmd_free(phba, mbox);
+		if (shdr_status || shdr_add_status || rc) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+					"2988 POST_SGL_BLOCK mailbox "
+					"command failed status x%x "
+					"add_status x%x mbx status x%x\n",
+					shdr_status, shdr_add_status, rc);
+			rc = -ENXIO;
+			goto err_exit;
+		}
+		if (ttl_cnt >= els_xri_cnt)
+			break;
+	}
+
+ err_exit:
+	if (rc == 0)
+		bf_set(lpfc_xri_rsrc_rdy, &phba->sli4_hba.sli4_flags,
+		       LPFC_XRI_RSRC_RDY);
 	return rc;
 }
 
@@ -11693,6 +12791,7 @@ lpfc_sli4_post_scsi_sgl_block(struct lpfc_hba *phba, struct list_head *sblist,
 		lpfc_sli4_mbox_cmd_free(phba, mbox);
 		return -ENOMEM;
 	}
+
 	/* Get the first SGE entry from the non-embedded DMA memory */
 	viraddr = mbox->sge_array->addr[0];
 
@@ -11748,6 +12847,169 @@ lpfc_sli4_post_scsi_sgl_block(struct lpfc_hba *phba, struct list_head *sblist,
 }
 
 /**
+ * lpfc_sli4_post_scsi_sgl_blk_ext - post a block of scsi sgls to the port.
+ * @phba: pointer to lpfc hba data structure.
+ * @sblist: pointer to scsi buffer list.
+ * @count: number of scsi buffers on the list.
+ *
+ * This routine is invoked to post a block of @count scsi sgl pages from a
+ * SCSI buffer list @sblist to the HBA using non-embedded mailbox command.
+ * No Lock is held.
+ *
+ **/
+int
+lpfc_sli4_post_scsi_sgl_blk_ext(struct lpfc_hba *phba, struct list_head *sblist,
+				int cnt)
+{
+	struct lpfc_scsi_buf *psb = NULL;
+	struct lpfc_mbx_post_uembed_sgl_page1 *sgl;
+	struct sgl_page_pairs *sgl_pg_pairs;
+	void *viraddr;
+	LPFC_MBOXQ_t *mbox;
+	uint32_t reqlen, alloclen, pg_pairs;
+	uint32_t mbox_tmo;
+	uint16_t xri_start = 0, scsi_xri_start;
+	uint16_t rsrc_range;
+	int rc = 0, avail_cnt;
+	uint32_t shdr_status, shdr_add_status;
+	dma_addr_t pdma_phys_bpl1;
+	union lpfc_sli4_cfg_shdr *shdr;
+	struct lpfc_rsrc_blks *rsrc_blk;
+	uint32_t xri_cnt = 0;
+
+	/* Calculate the total requested length of the dma memory */
+	reqlen = cnt * sizeof(struct sgl_page_pairs) +
+		 sizeof(union lpfc_sli4_cfg_shdr) + sizeof(uint32_t);
+	if (reqlen > SLI4_PAGE_SIZE) {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
+				"2932 Block sgl registration required DMA "
+				"size (%d) great than a page\n", reqlen);
+		return -ENOMEM;
+	}
+
+	/*
+	 * The use of extents requires the driver to post the sgl headers
+	 * in multiple postings to meet the contiguous resource assignment.
+	 */
+	psb = list_prepare_entry(psb, sblist, list);
+	scsi_xri_start = phba->sli4_hba.scsi_xri_start;
+	list_for_each_entry(rsrc_blk, &phba->sli4_hba.lpfc_xri_blk_list,
+			    list) {
+		rsrc_range = rsrc_blk->rsrc_start + rsrc_blk->rsrc_size;
+		if (rsrc_range < scsi_xri_start)
+			continue;
+		else if (rsrc_blk->rsrc_used >= rsrc_blk->rsrc_size)
+			continue;
+		else
+			avail_cnt = rsrc_blk->rsrc_size - rsrc_blk->rsrc_used;
+
+		reqlen = (avail_cnt * sizeof(struct sgl_page_pairs)) +
+			sizeof(union lpfc_sli4_cfg_shdr) + sizeof(uint32_t);
+		/*
+		 * Allocate DMA memory and set up the non-embedded mailbox
+		 * command. The mbox is used to post an SGL page per loop
+		 * but the DMA memory has a use-once semantic so the mailbox
+		 * is used and freed per loop pass.
+		 */
+		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+		if (!mbox) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"2933 Failed to allocate mbox cmd "
+					"memory\n");
+			return -ENOMEM;
+		}
+		alloclen = lpfc_sli4_config(phba, mbox,
+					LPFC_MBOX_SUBSYSTEM_FCOE,
+					LPFC_MBOX_OPCODE_FCOE_POST_SGL_PAGES,
+					reqlen,
+					LPFC_SLI4_MBX_NEMBED);
+		if (alloclen < reqlen) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"2934 Allocated DMA memory size (%d) "
+					"is less than the requested DMA memory "
+					"size (%d)\n", alloclen, reqlen);
+			lpfc_sli4_mbox_cmd_free(phba, mbox);
+			return -ENOMEM;
+		}
+
+		/* Get the first SGE entry from the non-embedded DMA memory */
+		viraddr = mbox->sge_array->addr[0];
+
+		/* Set up the SGL pages in the non-embedded DMA pages */
+		sgl = (struct lpfc_mbx_post_uembed_sgl_page1 *)viraddr;
+		sgl_pg_pairs = &sgl->sgl_pg_pairs;
+
+		/* pg_pairs tracks posted SGEs per loop iteration. */
+		pg_pairs = 0;
+		list_for_each_entry_continue(psb, sblist, list) {
+			/* Set up the sge entry */
+			sgl_pg_pairs->sgl_pg0_addr_lo =
+				cpu_to_le32(putPaddrLow(psb->dma_phys_bpl));
+			sgl_pg_pairs->sgl_pg0_addr_hi =
+				cpu_to_le32(putPaddrHigh(psb->dma_phys_bpl));
+			if (phba->cfg_sg_dma_buf_size > SGL_PAGE_SIZE)
+				pdma_phys_bpl1 = psb->dma_phys_bpl +
+					SGL_PAGE_SIZE;
+			else
+				pdma_phys_bpl1 = 0;
+			sgl_pg_pairs->sgl_pg1_addr_lo =
+				cpu_to_le32(putPaddrLow(pdma_phys_bpl1));
+			sgl_pg_pairs->sgl_pg1_addr_hi =
+				cpu_to_le32(putPaddrHigh(pdma_phys_bpl1));
+			/* Keep the first xri for this extent. */
+			if (pg_pairs == 0)
+				xri_start = psb->cur_iocbq.sli4_xritag;
+			sgl_pg_pairs++;
+			pg_pairs++;
+			xri_cnt++;
+
+			/*
+			 * Track two exit conditions - the loop has constructed
+			 * all of the caller's SGE pairs or all available
+			 * resource IDs in this extent are consumed.
+			 */
+			if ((xri_cnt == cnt) || (pg_pairs >= avail_cnt))
+				break;
+		}
+		rsrc_blk->rsrc_used += pg_pairs;
+		bf_set(lpfc_post_sgl_pages_xri, sgl, xri_start);
+		bf_set(lpfc_post_sgl_pages_xricnt, sgl, pg_pairs);
+
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+				"3016 Post SCSI Extent SGL, start %d, cnt %d "
+				"blk use %d\n",
+				xri_start, pg_pairs, rsrc_blk->rsrc_used);
+		/* Perform endian conversion if necessary */
+		sgl->word0 = cpu_to_le32(sgl->word0);
+		if (!phba->sli4_hba.intr_enable)
+			rc = lpfc_sli_issue_mbox(phba, mbox, MBX_POLL);
+		else {
+			mbox_tmo = lpfc_mbox_tmo_val(phba, MBX_SLI4_CONFIG);
+			rc = lpfc_sli_issue_mbox_wait(phba, mbox, mbox_tmo);
+		}
+		shdr = (union lpfc_sli4_cfg_shdr *) &sgl->cfg_shdr;
+		shdr_status = bf_get(lpfc_mbox_hdr_status, &shdr->response);
+		shdr_add_status = bf_get(lpfc_mbox_hdr_add_status,
+					 &shdr->response);
+		if (rc != MBX_TIMEOUT)
+			lpfc_sli4_mbox_cmd_free(phba, mbox);
+		if (shdr_status || shdr_add_status || rc) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+					"2935 POST_SGL_BLOCK mailbox command "
+					"failed status x%x add_status x%x "
+					"mbx status x%x\n",
+					shdr_status, shdr_add_status, rc);
+			return -ENXIO;
+		}
+
+		/* Post only what is requested. */
+		if (xri_cnt >= cnt)
+			break;
+	}
+	return rc;
+}
+
+/**
  * lpfc_fc_frame_check - Check that this frame is a valid frame to handle
  * @phba: pointer to lpfc_hba struct that the frame was received on
  * @fc_hdr: A pointer to the FC Header data (In Big Endian Format)
@@ -12137,6 +13399,28 @@ lpfc_sli4_seq_abort_rsp_cmpl(struct lpfc_hba *phba,
 }
 
 /**
+ * lpfc_sli4_xri_inrange - check xri is in range of xris owned by driver.
+ * @phba: Pointer to HBA context object.
+ * @xri: xri id in transaction.
+ *
+ * This function validates the xri maps to the known range of XRIs allocated an
+ * used by the driver.
+ **/
+static uint16_t
+lpfc_sli4_xri_inrange(struct lpfc_hba *phba,
+		      uint16_t xri)
+{
+	int i;
+
+	for (i = 0; i < phba->sli4_hba.max_cfg_param.max_xri; i++) {
+		if (xri == phba->sli4_hba.xri_ids[i])
+			return i;
+	}
+	return NO_XRI;
+}
+
+
+/**
  * lpfc_sli4_seq_abort_rsp - bls rsp to sequence abort
  * @phba: Pointer to HBA context object.
  * @fc_hdr: pointer to a FC frame header.
@@ -12169,9 +13453,7 @@ lpfc_sli4_seq_abort_rsp(struct lpfc_hba *phba,
 				"SID:x%x\n", oxid, sid);
 		return;
 	}
-	if (rxid >= phba->sli4_hba.max_cfg_param.xri_base
-		&& rxid <= (phba->sli4_hba.max_cfg_param.max_xri
-		+ phba->sli4_hba.max_cfg_param.xri_base))
+	if (lpfc_sli4_xri_inrange(phba, rxid))
 		lpfc_set_rrq_active(phba, ndlp, rxid, oxid, 0);
 
 	/* Allocate buffer for rsp iocb */
@@ -12194,12 +13476,13 @@ lpfc_sli4_seq_abort_rsp(struct lpfc_hba *phba,
 	icmd->ulpBdeCount = 0;
 	icmd->ulpLe = 1;
 	icmd->ulpClass = CLASS3;
-	icmd->ulpContext = ndlp->nlp_rpi;
+	icmd->ulpContext = phba->sli4_hba.rpi_ids[ndlp->nlp_rpi];
 	ctiocb->context1 = ndlp;
 
 	ctiocb->iocb_cmpl = NULL;
 	ctiocb->vport = phba->pport;
 	ctiocb->iocb_cmpl = lpfc_sli4_seq_abort_rsp_cmpl;
+	ctiocb->sli4_lxritag = NO_XRI;
 	ctiocb->sli4_xritag = NO_XRI;
 
 	/* If the oxid maps to the FCP XRI range or if it is out of range,
@@ -12380,8 +13663,8 @@ lpfc_prep_seq(struct lpfc_vport *vport, struct hbq_dmabuf *seq_dmabuf)
 		first_iocbq->iocb.ulpStatus = IOSTAT_SUCCESS;
 		first_iocbq->iocb.ulpCommand = CMD_IOCB_RCV_SEQ64_CX;
 		first_iocbq->iocb.ulpContext = be16_to_cpu(fc_hdr->fh_ox_id);
-		first_iocbq->iocb.unsli3.rcvsli3.vpi =
-					vport->vpi + vport->phba->vpi_base;
+		/* iocbq is prepped for internal consumption.  Logical vpi. */
+		first_iocbq->iocb.unsli3.rcvsli3.vpi = vport->vpi;
 		/* put the first buffer into the first IOCBq */
 		first_iocbq->context2 = &seq_dmabuf->dbuf;
 		first_iocbq->context3 = NULL;
@@ -12461,7 +13744,7 @@ lpfc_sli4_send_seq_to_ulp(struct lpfc_vport *vport,
 				      &phba->sli.ring[LPFC_ELS_RING],
 				      iocbq, fc_hdr->fh_r_ctl,
 				      fc_hdr->fh_type))
-		lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
+		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
 				"2540 Ring %d handler: unexpected Rctl "
 				"x%x Type x%x received\n",
 				LPFC_ELS_RING,
@@ -12558,9 +13841,24 @@ lpfc_sli4_post_all_rpi_hdrs(struct lpfc_hba *phba)
 {
 	struct lpfc_rpi_hdr *rpi_page;
 	uint32_t rc = 0;
+	uint16_t lrpi = 0;
+
+	/* SLI4 ports that support extents do not require RPI headers. */
+	if (!phba->sli4_hba.rpi_hdrs_in_use)
+		goto exit;
+	if (phba->sli4_hba.extents_in_use)
+		return -EIO;
 
-	/* Post all rpi memory regions to the port. */
 	list_for_each_entry(rpi_page, &phba->sli4_hba.lpfc_rpi_hdr_list, list) {
+		/*
+		 * Assign the rpi headers a physical rpi only if the driver
+		 * has not initialized those resources.  A port reset only
+		 * needs the headers posted.
+		 */
+		if (bf_get(lpfc_rpi_rsrc_rdy, &phba->sli4_hba.sli4_flags) !=
+		    LPFC_RPI_RSRC_RDY)
+			rpi_page->start_rpi = phba->sli4_hba.rpi_ids[lrpi];
+
 		rc = lpfc_sli4_post_rpi_hdr(phba, rpi_page);
 		if (rc != MBX_SUCCESS) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
@@ -12571,6 +13869,9 @@ lpfc_sli4_post_all_rpi_hdrs(struct lpfc_hba *phba)
 		}
 	}
 
+ exit:
+	bf_set(lpfc_rpi_rsrc_rdy, &phba->sli4_hba.sli4_flags,
+	       LPFC_RPI_RSRC_RDY);
 	return rc;
 }
 
@@ -12594,10 +13895,15 @@ lpfc_sli4_post_rpi_hdr(struct lpfc_hba *phba, struct lpfc_rpi_hdr *rpi_page)
 	LPFC_MBOXQ_t *mboxq;
 	struct lpfc_mbx_post_hdr_tmpl *hdr_tmpl;
 	uint32_t rc = 0;
-	uint32_t mbox_tmo;
 	uint32_t shdr_status, shdr_add_status;
 	union lpfc_sli4_cfg_shdr *shdr;
 
+	/* SLI4 ports that support extents do not require RPI headers. */
+	if (!phba->sli4_hba.rpi_hdrs_in_use)
+		return rc;
+	if (phba->sli4_hba.extents_in_use)
+		return -EIO;
+
 	/* The port is notified of the header region via a mailbox command. */
 	mboxq = (LPFC_MBOXQ_t *) mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mboxq) {
@@ -12609,16 +13915,19 @@ lpfc_sli4_post_rpi_hdr(struct lpfc_hba *phba, struct lpfc_rpi_hdr *rpi_page)
 
 	/* Post all rpi memory regions to the port. */
 	hdr_tmpl = &mboxq->u.mqe.un.hdr_tmpl;
-	mbox_tmo = lpfc_mbox_tmo_val(phba, MBX_SLI4_CONFIG);
 	lpfc_sli4_config(phba, mboxq, LPFC_MBOX_SUBSYSTEM_FCOE,
 			 LPFC_MBOX_OPCODE_FCOE_POST_HDR_TEMPLATE,
 			 sizeof(struct lpfc_mbx_post_hdr_tmpl) -
 			 sizeof(struct lpfc_sli4_cfg_mhdr),
 			 LPFC_SLI4_MBX_EMBED);
-	bf_set(lpfc_mbx_post_hdr_tmpl_page_cnt,
-	       hdr_tmpl, rpi_page->page_count);
+
+
+	/* Post the physical rpi to the port for this rpi header. */
 	bf_set(lpfc_mbx_post_hdr_tmpl_rpi_offset, hdr_tmpl,
 	       rpi_page->start_rpi);
+	bf_set(lpfc_mbx_post_hdr_tmpl_page_cnt,
+	       hdr_tmpl, rpi_page->page_count);
+
 	hdr_tmpl->rpi_paddr_lo = putPaddrLow(rpi_page->dmabuf->phys);
 	hdr_tmpl->rpi_paddr_hi = putPaddrHigh(rpi_page->dmabuf->phys);
 	rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
@@ -12653,22 +13962,21 @@ lpfc_sli4_post_rpi_hdr(struct lpfc_hba *phba, struct lpfc_rpi_hdr *rpi_page)
 int
 lpfc_sli4_alloc_rpi(struct lpfc_hba *phba)
 {
-	int rpi;
-	uint16_t max_rpi, rpi_base, rpi_limit;
-	uint16_t rpi_remaining;
+	unsigned long rpi;
+	uint16_t max_rpi, rpi_limit;
+	uint16_t rpi_remaining, lrpi = 0;
 	struct lpfc_rpi_hdr *rpi_hdr;
 
 	max_rpi = phba->sli4_hba.max_cfg_param.max_rpi;
-	rpi_base = phba->sli4_hba.max_cfg_param.rpi_base;
 	rpi_limit = phba->sli4_hba.next_rpi;
 
 	/*
-	 * The valid rpi range is not guaranteed to be zero-based.  Start
-	 * the search at the rpi_base as reported by the port.
+	 * Fetch the next logical rpi.  Because this index is logical,
+	 * the  driver starts at 0 each time.
 	 */
 	spin_lock_irq(&phba->hbalock);
-	rpi = find_next_zero_bit(phba->sli4_hba.rpi_bmask, rpi_limit, rpi_base);
-	if (rpi >= rpi_limit || rpi < rpi_base)
+	rpi = find_next_zero_bit(phba->sli4_hba.rpi_bmask, rpi_limit, 0);
+	if (rpi >= rpi_limit)
 		rpi = LPFC_RPI_ALLOC_ERROR;
 	else {
 		set_bit(rpi, phba->sli4_hba.rpi_bmask);
@@ -12678,7 +13986,7 @@ lpfc_sli4_alloc_rpi(struct lpfc_hba *phba)
 
 	/*
 	 * Don't try to allocate more rpi header regions if the device limit
-	 * on available rpis max has been exhausted.
+	 * has been exhausted.
 	 */
 	if ((rpi == LPFC_RPI_ALLOC_ERROR) &&
 	    (phba->sli4_hba.rpi_count >= max_rpi)) {
@@ -12687,13 +13995,21 @@ lpfc_sli4_alloc_rpi(struct lpfc_hba *phba)
 	}
 
 	/*
+	 * RPI header postings are not required for SLI4 ports capable of
+	 * extents.
+	 */
+	if (!phba->sli4_hba.rpi_hdrs_in_use) {
+		spin_unlock_irq(&phba->hbalock);
+		return rpi;
+	}
+
+	/*
 	 * If the driver is running low on rpi resources, allocate another
 	 * page now.  Note that the next_rpi value is used because
 	 * it represents how many are actually in use whereas max_rpi notes
 	 * how many are supported max by the device.
 	 */
-	rpi_remaining = phba->sli4_hba.next_rpi - rpi_base -
-		phba->sli4_hba.rpi_count;
+	rpi_remaining = phba->sli4_hba.next_rpi - phba->sli4_hba.rpi_count;
 	spin_unlock_irq(&phba->hbalock);
 	if (rpi_remaining < LPFC_RPI_LOW_WATER_MARK) {
 		rpi_hdr = lpfc_sli4_create_rpi_hdr(phba);
@@ -12702,6 +14018,8 @@ lpfc_sli4_alloc_rpi(struct lpfc_hba *phba)
 					"2002 Error Could not grow rpi "
 					"count\n");
 		} else {
+			lrpi = rpi_hdr->start_rpi;
+			rpi_hdr->start_rpi = phba->sli4_hba.rpi_ids[lrpi];
 			lpfc_sli4_post_rpi_hdr(phba, rpi_hdr);
 		}
 	}
@@ -12751,6 +14069,8 @@ void
 lpfc_sli4_remove_rpis(struct lpfc_hba *phba)
 {
 	kfree(phba->sli4_hba.rpi_bmask);
+	kfree(phba->sli4_hba.rpi_ids);
+	bf_set(lpfc_rpi_rsrc_rdy, &phba->sli4_hba.sli4_flags, 0);
 }
 
 /**
@@ -13490,6 +14810,96 @@ out:
 }
 
 /**
+ * lpfc_wr_object - write an object to the firmware
+ * @phba: HBA structure that indicates port to create a queue on.
+ * @dmabuf_list: list of dmabufs to write to the port.
+ * @size: the total byte value of the objects to write to the port.
+ * @offset: the current offset to be used to start the transfer.
+ *
+ * This routine will create a wr_object mailbox command to send to the port.
+ * the mailbox command will be constructed using the dma buffers described in
+ * @dmabuf_list to create a list of BDEs. This routine will fill in as many
+ * BDEs that the imbedded mailbox can support. The @offset variable will be
+ * used to indicate the starting offset of the transfer and will also return
+ * the offset after the write object mailbox has completed. @size is used to
+ * determine the end of the object and whether the eof bit should be set.
+ *
+ * Return 0 is successful and offset will contain the the new offset to use
+ * for the next write.
+ * Return negative value for error cases.
+ **/
+int
+lpfc_wr_object(struct lpfc_hba *phba, struct list_head *dmabuf_list,
+	       uint32_t size, uint32_t *offset)
+{
+	struct lpfc_mbx_wr_object *wr_object;
+	LPFC_MBOXQ_t *mbox;
+	int rc = 0, i = 0;
+	uint32_t shdr_status, shdr_add_status;
+	uint32_t mbox_tmo;
+	union lpfc_sli4_cfg_shdr *shdr;
+	struct lpfc_dmabuf *dmabuf;
+	uint32_t written = 0;
+
+	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!mbox)
+		return -ENOMEM;
+
+	lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_COMMON,
+			LPFC_MBOX_OPCODE_WRITE_OBJECT,
+			sizeof(struct lpfc_mbx_wr_object) -
+			sizeof(struct lpfc_sli4_cfg_mhdr), LPFC_SLI4_MBX_EMBED);
+
+	wr_object = (struct lpfc_mbx_wr_object *)&mbox->u.mqe.un.wr_object;
+	wr_object->u.request.write_offset = *offset;
+	sprintf((uint8_t *)wr_object->u.request.object_name, "/");
+	wr_object->u.request.object_name[0] =
+		cpu_to_le32(wr_object->u.request.object_name[0]);
+	bf_set(lpfc_wr_object_eof, &wr_object->u.request, 0);
+	list_for_each_entry(dmabuf, dmabuf_list, list) {
+		if (i >= LPFC_MBX_WR_CONFIG_MAX_BDE || written >= size)
+			break;
+		wr_object->u.request.bde[i].addrLow = putPaddrLow(dmabuf->phys);
+		wr_object->u.request.bde[i].addrHigh =
+			putPaddrHigh(dmabuf->phys);
+		if (written + SLI4_PAGE_SIZE >= size) {
+			wr_object->u.request.bde[i].tus.f.bdeSize =
+				(size - written);
+			written += (size - written);
+			bf_set(lpfc_wr_object_eof, &wr_object->u.request, 1);
+		} else {
+			wr_object->u.request.bde[i].tus.f.bdeSize =
+				SLI4_PAGE_SIZE;
+			written += SLI4_PAGE_SIZE;
+		}
+		i++;
+	}
+	wr_object->u.request.bde_count = i;
+	bf_set(lpfc_wr_object_write_length, &wr_object->u.request, written);
+	if (!phba->sli4_hba.intr_enable)
+		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_POLL);
+	else {
+		mbox_tmo = lpfc_mbox_tmo_val(phba, MBX_SLI4_CONFIG);
+		rc = lpfc_sli_issue_mbox_wait(phba, mbox, mbox_tmo);
+	}
+	/* The IOCTL status is embedded in the mailbox subheader. */
+	shdr = (union lpfc_sli4_cfg_shdr *) &wr_object->header.cfg_shdr;
+	shdr_status = bf_get(lpfc_mbox_hdr_status, &shdr->response);
+	shdr_add_status = bf_get(lpfc_mbox_hdr_add_status, &shdr->response);
+	if (rc != MBX_TIMEOUT)
+		mempool_free(mbox, phba->mbox_mem_pool);
+	if (shdr_status || shdr_add_status || rc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"3025 Write Object mailbox failed with "
+				"status x%x add_status x%x, mbx status x%x\n",
+				shdr_status, shdr_add_status, rc);
+		rc = -ENXIO;
+	} else
+		*offset += wr_object->u.response.actual_write_length;
+	return rc;
+}
+
+/**
  * lpfc_cleanup_pending_mbox - Free up vport discovery mailbox commands.
  * @vport: pointer to vport data structure.
  *
@@ -13644,7 +15054,7 @@ lpfc_drain_txq(struct lpfc_hba *phba)
 				 * never happen
 				 */
 				sglq = __lpfc_clear_active_sglq(phba,
-						 sglq->sli4_xritag);
+						 sglq->sli4_lxritag);
 				spin_unlock_irqrestore(&phba->hbalock, iflags);
 				lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
 					"2823 txq empty and txq_cnt is %d\n ",
@@ -13656,6 +15066,7 @@ lpfc_drain_txq(struct lpfc_hba *phba)
 		/* The xri and iocb resources secured,
 		 * attempt to issue request
 		 */
+		piocbq->sli4_lxritag = sglq->sli4_lxritag;
 		piocbq->sli4_xritag = sglq->sli4_xritag;
 		if (NO_XRI == lpfc_sli4_bpl2sgl(phba, piocbq, sglq))
 			fail_msg = "to convert bpl to sgl";
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 453577c21c14..a0075b0af142 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -52,6 +52,7 @@ struct lpfc_iocbq {
 	struct list_head clist;
 	struct list_head dlist;
 	uint16_t iotag;         /* pre-assigned IO tag */
+	uint16_t sli4_lxritag;  /* logical pre-assigned XRI. */
 	uint16_t sli4_xritag;   /* pre-assigned XRI, (OXID) tag. */
 	struct lpfc_cq_event cq_event;
 
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 1a3cbf88f2ce..4b1703554a26 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -310,7 +310,6 @@ struct lpfc_max_cfg_param {
 	uint16_t vfi_base;
 	uint16_t vfi_used;
 	uint16_t max_fcfi;
-	uint16_t fcfi_base;
 	uint16_t fcfi_used;
 	uint16_t max_eq;
 	uint16_t max_rq;
@@ -365,6 +364,11 @@ struct lpfc_pc_sli4_params {
 	uint8_t rqv;
 };
 
+struct lpfc_iov {
+	uint32_t pf_number;
+	uint32_t vf_number;
+};
+
 /* SLI4 HBA data structure entries */
 struct lpfc_sli4_hba {
 	void __iomem *conf_regs_memmap_p; /* Kernel memory mapped address for
@@ -444,10 +448,13 @@ struct lpfc_sli4_hba {
 	uint32_t intr_enable;
 	struct lpfc_bmbx bmbx;
 	struct lpfc_max_cfg_param max_cfg_param;
+	uint16_t extents_in_use; /* must allocate resource extents. */
+	uint16_t rpi_hdrs_in_use; /* must post rpi hdrs if set. */
 	uint16_t next_xri; /* last_xri - max_cfg_param.xri_base = used */
 	uint16_t next_rpi;
 	uint16_t scsi_xri_max;
 	uint16_t scsi_xri_cnt;
+	uint16_t scsi_xri_start;
 	struct list_head lpfc_free_sgl_list;
 	struct list_head lpfc_sgl_list;
 	struct lpfc_sglq **lpfc_els_sgl_array;
@@ -458,7 +465,17 @@ struct lpfc_sli4_hba {
 	struct lpfc_sglq **lpfc_sglq_active_list;
 	struct list_head lpfc_rpi_hdr_list;
 	unsigned long *rpi_bmask;
+	uint16_t *rpi_ids;
 	uint16_t rpi_count;
+	struct list_head lpfc_rpi_blk_list;
+	unsigned long *xri_bmask;
+	uint16_t *xri_ids;
+	uint16_t xri_count;
+	struct list_head lpfc_xri_blk_list;
+	unsigned long *vfi_bmask;
+	uint16_t *vfi_ids;
+	uint16_t vfi_count;
+	struct list_head lpfc_vfi_blk_list;
 	struct lpfc_sli4_flags sli4_flags;
 	struct list_head sp_queue_event;
 	struct list_head sp_cqe_event_pool;
@@ -467,6 +484,7 @@ struct lpfc_sli4_hba {
 	struct list_head sp_els_xri_aborted_work_queue;
 	struct list_head sp_unsol_work_queue;
 	struct lpfc_sli4_link link_state;
+	struct lpfc_iov iov;
 	spinlock_t abts_scsi_buf_list_lock; /* list of aborted SCSI IOs */
 	spinlock_t abts_sgl_list_lock; /* list of aborted els IOs */
 };
@@ -490,6 +508,7 @@ struct lpfc_sglq {
 	enum lpfc_sgl_state state;
 	struct lpfc_nodelist *ndlp; /* ndlp associated with IO */
 	uint16_t iotag;         /* pre-assigned IO tag */
+	uint16_t sli4_lxritag;  /* logical pre-assigned xri. */
 	uint16_t sli4_xritag;   /* pre-assigned XRI, (OXID) tag. */
 	struct sli4_sge *sgl;	/* pre-assigned SGL */
 	void *virt;		/* virtual address. */
@@ -504,6 +523,13 @@ struct lpfc_rpi_hdr {
 	uint32_t start_rpi;
 };
 
+struct lpfc_rsrc_blks {
+	struct list_head list;
+	uint16_t rsrc_start;
+	uint16_t rsrc_size;
+	uint16_t rsrc_used;
+};
+
 /*
  * SLI4 specific function prototypes
  */
@@ -543,8 +569,11 @@ int lpfc_sli4_post_sgl(struct lpfc_hba *, dma_addr_t, dma_addr_t, uint16_t);
 int lpfc_sli4_repost_scsi_sgl_list(struct lpfc_hba *);
 uint16_t lpfc_sli4_next_xritag(struct lpfc_hba *);
 int lpfc_sli4_post_async_mbox(struct lpfc_hba *);
-int lpfc_sli4_post_sgl_list(struct lpfc_hba *phba);
+int lpfc_sli4_post_els_sgl_list(struct lpfc_hba *phba);
+int lpfc_sli4_post_els_sgl_list_ext(struct lpfc_hba *phba);
 int lpfc_sli4_post_scsi_sgl_block(struct lpfc_hba *, struct list_head *, int);
+int lpfc_sli4_post_scsi_sgl_blk_ext(struct lpfc_hba *, struct list_head *,
+				    int);
 struct lpfc_cq_event *__lpfc_sli4_cq_event_alloc(struct lpfc_hba *);
 struct lpfc_cq_event *lpfc_sli4_cq_event_alloc(struct lpfc_hba *);
 void __lpfc_sli4_cq_event_release(struct lpfc_hba *, struct lpfc_cq_event *);
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index 30ba5440c67a..1feb551a57bc 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -83,7 +83,7 @@ inline void lpfc_vport_set_state(struct lpfc_vport *vport,
 static int
 lpfc_alloc_vpi(struct lpfc_hba *phba)
 {
-	int  vpi;
+	unsigned long vpi;
 
 	spin_lock_irq(&phba->hbalock);
 	/* Start at bit 1 because vpi zero is reserved for the physical port */
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index 046dcc672ec1..7370c084b178 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -33,9 +33,9 @@
 /*
  * MegaRAID SAS Driver meta data
  */
-#define MEGASAS_VERSION				"00.00.05.34-rc1"
-#define MEGASAS_RELDATE				"Feb. 24, 2011"
-#define MEGASAS_EXT_VERSION			"Thu. Feb. 24 17:00:00 PDT 2011"
+#define MEGASAS_VERSION				"00.00.05.38-rc1"
+#define MEGASAS_RELDATE				"May. 11, 2011"
+#define MEGASAS_EXT_VERSION			"Wed. May. 11 17:00:00 PDT 2011"
 
 /*
  * Device IDs
@@ -76,8 +76,8 @@
 #define MFI_STATE_READY				0xB0000000
 #define MFI_STATE_OPERATIONAL			0xC0000000
 #define MFI_STATE_FAULT				0xF0000000
-#define  MFI_RESET_REQUIRED			0x00000001
-
+#define MFI_RESET_REQUIRED			0x00000001
+#define MFI_RESET_ADAPTER			0x00000002
 #define MEGAMFI_FRAME_SIZE			64
 
 /*
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 89c623ebadbc..2d8cdce7b2f5 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -18,7 +18,7 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  *
  *  FILE: megaraid_sas_base.c
- *  Version : v00.00.05.34-rc1
+ *  Version : v00.00.05.38-rc1
  *
  *  Authors: LSI Corporation
  *           Sreenivas Bagalkote
@@ -437,15 +437,18 @@ megasas_read_fw_status_reg_ppc(struct megasas_register_set __iomem * regs)
 static int
 megasas_clear_intr_ppc(struct megasas_register_set __iomem * regs)
 {
-	u32 status;
+	u32 status, mfiStatus = 0;
+
 	/*
 	 * Check if it is our interrupt
 	 */
 	status = readl(&regs->outbound_intr_status);
 
-	if (!(status & MFI_REPLY_1078_MESSAGE_INTERRUPT)) {
-		return 0;
-	}
+	if (status & MFI_REPLY_1078_MESSAGE_INTERRUPT)
+		mfiStatus = MFI_INTR_FLAG_REPLY_MESSAGE;
+
+	if (status & MFI_G2_OUTBOUND_DOORBELL_CHANGE_INTERRUPT)
+		mfiStatus |= MFI_INTR_FLAG_FIRMWARE_STATE_CHANGE;
 
 	/*
 	 * Clear the interrupt by writing back the same value
@@ -455,8 +458,9 @@ megasas_clear_intr_ppc(struct megasas_register_set __iomem * regs)
 	/* Dummy readl to force pci flush */
 	readl(&regs->outbound_doorbell_clear);
 
-	return 1;
+	return mfiStatus;
 }
+
 /**
  * megasas_fire_cmd_ppc -	Sends command to the FW
  * @frame_phys_addr :		Physical address of cmd
@@ -477,17 +481,6 @@ megasas_fire_cmd_ppc(struct megasas_instance *instance,
 }
 
 /**
- * megasas_adp_reset_ppc -	For controller reset
- * @regs:				MFI register set
- */
-static int
-megasas_adp_reset_ppc(struct megasas_instance *instance,
-			struct megasas_register_set __iomem *regs)
-{
-	return 0;
-}
-
-/**
  * megasas_check_reset_ppc -	For controller reset check
  * @regs:				MFI register set
  */
@@ -495,8 +488,12 @@ static int
 megasas_check_reset_ppc(struct megasas_instance *instance,
 			struct megasas_register_set __iomem *regs)
 {
+	if (instance->adprecovery != MEGASAS_HBA_OPERATIONAL)
+		return 1;
+
 	return 0;
 }
+
 static struct megasas_instance_template megasas_instance_template_ppc = {
 
 	.fire_cmd = megasas_fire_cmd_ppc,
@@ -504,7 +501,7 @@ static struct megasas_instance_template megasas_instance_template_ppc = {
 	.disable_intr = megasas_disable_intr_ppc,
 	.clear_intr = megasas_clear_intr_ppc,
 	.read_fw_status_reg = megasas_read_fw_status_reg_ppc,
-	.adp_reset = megasas_adp_reset_ppc,
+	.adp_reset = megasas_adp_reset_xscale,
 	.check_reset = megasas_check_reset_ppc,
 	.service_isr = megasas_isr,
 	.tasklet = megasas_complete_cmd_dpc,
@@ -620,6 +617,9 @@ static int
 megasas_check_reset_skinny(struct megasas_instance *instance,
 				struct megasas_register_set __iomem *regs)
 {
+	if (instance->adprecovery != MEGASAS_HBA_OPERATIONAL)
+		return 1;
+
 	return 0;
 }
 
@@ -3454,7 +3454,7 @@ static int megasas_init_fw(struct megasas_instance *instance)
 {
 	u32 max_sectors_1;
 	u32 max_sectors_2;
-	u32 tmp_sectors;
+	u32 tmp_sectors, msix_enable;
 	struct megasas_register_set __iomem *reg_set;
 	struct megasas_ctrl_info *ctrl_info;
 	unsigned long bar_list;
@@ -3507,6 +3507,13 @@ static int megasas_init_fw(struct megasas_instance *instance)
 	if (megasas_transition_to_ready(instance))
 		goto fail_ready_state;
 
+	/* Check if MSI-X is supported while in ready state */
+	msix_enable = (instance->instancet->read_fw_status_reg(reg_set) &
+		       0x4000000) >> 0x1a;
+	if (msix_enable && !msix_disable &&
+	    !pci_enable_msix(instance->pdev, &instance->msixentry, 1))
+		instance->msi_flag = 1;
+
 	/* Get operational params, sge flags, send init cmd to controller */
 	if (instance->instancet->init_adapter(instance))
 		goto fail_init_adapter;
@@ -4076,14 +4083,6 @@ megasas_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	else
 		INIT_WORK(&instance->work_init, process_fw_state_change_wq);
 
-	/* Try to enable MSI-X */
-	if ((instance->pdev->device != PCI_DEVICE_ID_LSI_SAS1078R) &&
-	    (instance->pdev->device != PCI_DEVICE_ID_LSI_SAS1078DE) &&
-	    (instance->pdev->device != PCI_DEVICE_ID_LSI_VERDE_ZCR) &&
-	    !msix_disable && !pci_enable_msix(instance->pdev,
-					      &instance->msixentry, 1))
-		instance->msi_flag = 1;
-
 	/*
 	 * Initialize MFI Firmware
 	 */
@@ -4116,6 +4115,14 @@ megasas_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	megasas_mgmt_info.max_index++;
 
 	/*
+	 * Register with SCSI mid-layer
+	 */
+	if (megasas_io_attach(instance))
+		goto fail_io_attach;
+
+	instance->unload = 0;
+
+	/*
 	 * Initiate AEN (Asynchronous Event Notification)
 	 */
 	if (megasas_start_aen(instance)) {
@@ -4123,13 +4130,6 @@ megasas_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto fail_start_aen;
 	}
 
-	/*
-	 * Register with SCSI mid-layer
-	 */
-	if (megasas_io_attach(instance))
-		goto fail_io_attach;
-
-	instance->unload = 0;
 	return 0;
 
       fail_start_aen:
@@ -4332,10 +4332,6 @@ megasas_resume(struct pci_dev *pdev)
 	if (megasas_set_dma_mask(pdev))
 		goto fail_set_dma_mask;
 
-	/* Now re-enable MSI-X */
-	if (instance->msi_flag)
-		pci_enable_msix(instance->pdev, &instance->msixentry, 1);
-
 	/*
 	 * Initialize MFI Firmware
 	 */
@@ -4348,6 +4344,10 @@ megasas_resume(struct pci_dev *pdev)
 	if (megasas_transition_to_ready(instance))
 		goto fail_ready_state;
 
+	/* Now re-enable MSI-X */
+	if (instance->msi_flag)
+		pci_enable_msix(instance->pdev, &instance->msixentry, 1);
+
 	switch (instance->pdev->device) {
 	case PCI_DEVICE_ID_LSI_FUSION:
 	{
@@ -4384,12 +4384,6 @@ megasas_resume(struct pci_dev *pdev)
 
 	instance->instancet->enable_intr(instance->reg_set);
 
-	/*
-	 * Initiate AEN (Asynchronous Event Notification)
-	 */
-	if (megasas_start_aen(instance))
-		printk(KERN_ERR "megasas: Start AEN failed\n");
-
 	/* Initialize the cmd completion timer */
 	if (poll_mode_io)
 		megasas_start_timer(instance, &instance->io_completion_timer,
@@ -4397,6 +4391,12 @@ megasas_resume(struct pci_dev *pdev)
 				MEGASAS_COMPLETION_TIMER_INTERVAL);
 	instance->unload = 0;
 
+	/*
+	 * Initiate AEN (Asynchronous Event Notification)
+	 */
+	if (megasas_start_aen(instance))
+		printk(KERN_ERR "megasas: Start AEN failed\n");
+
 	return 0;
 
 fail_irq:
@@ -4527,6 +4527,11 @@ static void megasas_shutdown(struct pci_dev *pdev)
 	instance->unload = 1;
 	megasas_flush_cache(instance);
 	megasas_shutdown_controller(instance, MR_DCMD_CTRL_SHUTDOWN);
+	instance->instancet->disable_intr(instance->reg_set);
+	free_irq(instance->msi_flag ? instance->msixentry.vector :
+		 instance->pdev->irq, instance);
+	if (instance->msi_flag)
+		pci_disable_msix(instance->pdev);
 }
 
 /**
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 145a8cffb1fa..f13e7abd345a 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -696,22 +696,6 @@ fail_get_cmd:
 }
 
 /*
- * megasas_return_cmd_for_smid -	Returns a cmd_fusion for a SMID
- * @instance:				Adapter soft state
- *
- */
-void
-megasas_return_cmd_for_smid(struct megasas_instance *instance, u16 smid)
-{
-	struct fusion_context *fusion;
-	struct megasas_cmd_fusion *cmd;
-
-	fusion = instance->ctrl_context;
-	cmd = fusion->cmd_list[smid - 1];
-	megasas_return_cmd_fusion(instance, cmd);
-}
-
-/*
  * megasas_get_ld_map_info -	Returns FW's ld_map structure
  * @instance:				Adapter soft state
  * @pend:				Pend the command or not
@@ -1153,7 +1137,7 @@ megasas_set_pd_lba(struct MPI2_RAID_SCSI_IO_REQUEST *io_request, u8 cdb_len,
 	u64 start_blk = io_info->pdBlock;
 	u8 *cdb = io_request->CDB.CDB32;
 	u32 num_blocks = io_info->numBlocks;
-	u8 opcode, flagvals, groupnum, control;
+	u8 opcode = 0, flagvals = 0, groupnum = 0, control = 0;
 
 	/* Check if T10 PI (DIF) is enabled for this LD */
 	ld = MR_TargetIdToLdGet(io_info->ldTgtId, local_map_ptr);
@@ -1235,7 +1219,46 @@ megasas_set_pd_lba(struct MPI2_RAID_SCSI_IO_REQUEST *io_request, u8 cdb_len,
 			cdb[8] = (u8)(num_blocks & 0xff);
 			cdb[7] = (u8)((num_blocks >> 8) & 0xff);
 
+			io_request->IoFlags = 10; /* Specify 10-byte cdb */
 			cdb_len = 10;
+		} else if ((cdb_len < 16) && (start_blk > 0xffffffff)) {
+			/* Convert to 16 byte CDB for large LBA's */
+			switch (cdb_len) {
+			case 6:
+				opcode = cdb[0] == READ_6 ? READ_16 : WRITE_16;
+				control = cdb[5];
+				break;
+			case 10:
+				opcode =
+					cdb[0] == READ_10 ? READ_16 : WRITE_16;
+				flagvals = cdb[1];
+				groupnum = cdb[6];
+				control = cdb[9];
+				break;
+			case 12:
+				opcode =
+					cdb[0] == READ_12 ? READ_16 : WRITE_16;
+				flagvals = cdb[1];
+				groupnum = cdb[10];
+				control = cdb[11];
+				break;
+			}
+
+			memset(cdb, 0, sizeof(io_request->CDB.CDB32));
+
+			cdb[0] = opcode;
+			cdb[1] = flagvals;
+			cdb[14] = groupnum;
+			cdb[15] = control;
+
+			/* Transfer length */
+			cdb[13] = (u8)(num_blocks & 0xff);
+			cdb[12] = (u8)((num_blocks >> 8) & 0xff);
+			cdb[11] = (u8)((num_blocks >> 16) & 0xff);
+			cdb[10] = (u8)((num_blocks >> 24) & 0xff);
+
+			io_request->IoFlags = 16; /* Specify 16-byte cdb */
+			cdb_len = 16;
 		}
 
 		/* Normal case, just load LBA here */
@@ -2026,17 +2049,11 @@ int megasas_reset_fusion(struct Scsi_Host *shost)
 	struct fusion_context *fusion;
 	struct megasas_cmd *cmd_mfi;
 	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc;
-	u32 host_diag, abs_state;
+	u32 host_diag, abs_state, status_reg, reset_adapter;
 
 	instance = (struct megasas_instance *)shost->hostdata;
 	fusion = instance->ctrl_context;
 
-	mutex_lock(&instance->reset_mutex);
-	set_bit(MEGASAS_FUSION_IN_RESET, &instance->reset_flags);
-	instance->adprecovery = MEGASAS_ADPRESET_SM_INFAULT;
-	instance->instancet->disable_intr(instance->reg_set);
-	msleep(1000);
-
 	if (instance->adprecovery == MEGASAS_HW_CRITICAL_ERROR) {
 		printk(KERN_WARNING "megaraid_sas: Hardware critical error, "
 		       "returning FAILED.\n");
@@ -2044,6 +2061,12 @@ int megasas_reset_fusion(struct Scsi_Host *shost)
 		goto out;
 	}
 
+	mutex_lock(&instance->reset_mutex);
+	set_bit(MEGASAS_FUSION_IN_RESET, &instance->reset_flags);
+	instance->adprecovery = MEGASAS_ADPRESET_SM_INFAULT;
+	instance->instancet->disable_intr(instance->reg_set);
+	msleep(1000);
+
 	/* First try waiting for commands to complete */
 	if (megasas_wait_for_outstanding_fusion(instance)) {
 		printk(KERN_WARNING "megaraid_sas: resetting fusion "
@@ -2060,7 +2083,12 @@ int megasas_reset_fusion(struct Scsi_Host *shost)
 			}
 		}
 
-		if (instance->disableOnlineCtrlReset == 1) {
+		status_reg = instance->instancet->read_fw_status_reg(
+			instance->reg_set);
+		abs_state = status_reg & MFI_STATE_MASK;
+		reset_adapter = status_reg & MFI_RESET_ADAPTER;
+		if (instance->disableOnlineCtrlReset ||
+		    (abs_state == MFI_STATE_FAULT && !reset_adapter)) {
 			/* Reset not supported, kill adapter */
 			printk(KERN_WARNING "megaraid_sas: Reset not supported"
 			       ", killing adapter.\n");
@@ -2089,6 +2117,7 @@ int megasas_reset_fusion(struct Scsi_Host *shost)
 
 			/* Check that the diag write enable (DRWE) bit is on */
 			host_diag = readl(&instance->reg_set->fusion_host_diag);
+			retry = 0;
 			while (!(host_diag & HOST_DIAG_WRITE_ENABLE)) {
 				msleep(100);
 				host_diag =
@@ -2126,7 +2155,7 @@ int megasas_reset_fusion(struct Scsi_Host *shost)
 
 			abs_state =
 				instance->instancet->read_fw_status_reg(
-					instance->reg_set);
+					instance->reg_set) & MFI_STATE_MASK;
 			retry = 0;
 
 			while ((abs_state <= MFI_STATE_FW_INIT) &&
@@ -2134,7 +2163,7 @@ int megasas_reset_fusion(struct Scsi_Host *shost)
 				msleep(100);
 				abs_state =
 				instance->instancet->read_fw_status_reg(
-					instance->reg_set);
+					instance->reg_set) & MFI_STATE_MASK;
 			}
 			if (abs_state <= MFI_STATE_FW_INIT) {
 				printk(KERN_WARNING "megaraid_sas: firmware "
diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.h b/drivers/scsi/mpt2sas/mpt2sas_base.h
index 2a3c05f6db8b..dcc289c25459 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_base.h
+++ b/drivers/scsi/mpt2sas/mpt2sas_base.h
@@ -69,11 +69,11 @@
 #define MPT2SAS_DRIVER_NAME		"mpt2sas"
 #define MPT2SAS_AUTHOR	"LSI Corporation <DL-MPTFusionLinux@lsi.com>"
 #define MPT2SAS_DESCRIPTION	"LSI MPT Fusion SAS 2.0 Device Driver"
-#define MPT2SAS_DRIVER_VERSION		"08.100.00.01"
+#define MPT2SAS_DRIVER_VERSION		"08.100.00.02"
 #define MPT2SAS_MAJOR_VERSION		08
 #define MPT2SAS_MINOR_VERSION		100
 #define MPT2SAS_BUILD_VERSION		00
-#define MPT2SAS_RELEASE_VERSION		01
+#define MPT2SAS_RELEASE_VERSION		02
 
 /*
  * Set MPT2SAS_SG_DEPTH value based on user input.
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index f12e02358d6d..a7dbc6825f5f 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -113,6 +113,7 @@ struct sense_info {
 };
 
 
+#define MPT2SAS_TURN_ON_FAULT_LED (0xFFFC)
 #define MPT2SAS_RESCAN_AFTER_HOST_RESET (0xFFFF)
 
 /**
@@ -121,6 +122,7 @@ struct sense_info {
  * @work: work object (ioc->fault_reset_work_q)
  * @cancel_pending_work: flag set during reset handling
  * @ioc: per adapter object
+ * @device_handle: device handle
  * @VF_ID: virtual function id
  * @VP_ID: virtual port id
  * @ignore: flag meaning this event has been marked to ignore
@@ -134,6 +136,7 @@ struct fw_event_work {
 	u8			cancel_pending_work;
 	struct delayed_work	delayed_work;
 	struct MPT2SAS_ADAPTER *ioc;
+	u16			device_handle;
 	u8			VF_ID;
 	u8			VP_ID;
 	u8			ignore;
@@ -3499,6 +3502,7 @@ _scsih_setup_eedp(struct scsi_cmnd *scmd, Mpi2SCSIIORequest_t *mpi_request)
 
 	switch (prot_type) {
 	case SCSI_PROT_DIF_TYPE1:
+	case SCSI_PROT_DIF_TYPE2:
 
 		/*
 		* enable ref/guard checking
@@ -3511,13 +3515,6 @@ _scsih_setup_eedp(struct scsi_cmnd *scmd, Mpi2SCSIIORequest_t *mpi_request)
 		    cpu_to_be32(scsi_get_lba(scmd));
 		break;
 
-	case SCSI_PROT_DIF_TYPE2:
-
-		eedp_flags |= MPI2_SCSIIO_EEDPFLAGS_INC_PRI_REFTAG |
-		    MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG |
-		    MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD;
-		break;
-
 	case SCSI_PROT_DIF_TYPE3:
 
 		/*
@@ -4047,17 +4044,75 @@ _scsih_scsi_ioc_info(struct MPT2SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
 #endif
 
 /**
- * _scsih_smart_predicted_fault - illuminate Fault LED
+ * _scsih_turn_on_fault_led - illuminate Fault LED
  * @ioc: per adapter object
  * @handle: device handle
+ * Context: process
  *
  * Return nothing.
  */
 static void
-_scsih_smart_predicted_fault(struct MPT2SAS_ADAPTER *ioc, u16 handle)
+_scsih_turn_on_fault_led(struct MPT2SAS_ADAPTER *ioc, u16 handle)
 {
 	Mpi2SepReply_t mpi_reply;
 	Mpi2SepRequest_t mpi_request;
+
+	memset(&mpi_request, 0, sizeof(Mpi2SepRequest_t));
+	mpi_request.Function = MPI2_FUNCTION_SCSI_ENCLOSURE_PROCESSOR;
+	mpi_request.Action = MPI2_SEP_REQ_ACTION_WRITE_STATUS;
+	mpi_request.SlotStatus =
+	    cpu_to_le32(MPI2_SEP_REQ_SLOTSTATUS_PREDICTED_FAULT);
+	mpi_request.DevHandle = cpu_to_le16(handle);
+	mpi_request.Flags = MPI2_SEP_REQ_FLAGS_DEVHANDLE_ADDRESS;
+	if ((mpt2sas_base_scsi_enclosure_processor(ioc, &mpi_reply,
+	    &mpi_request)) != 0) {
+		printk(MPT2SAS_ERR_FMT "failure at %s:%d/%s()!\n", ioc->name,
+		__FILE__, __LINE__, __func__);
+		return;
+	}
+
+	if (mpi_reply.IOCStatus || mpi_reply.IOCLogInfo) {
+		dewtprintk(ioc, printk(MPT2SAS_INFO_FMT "enclosure_processor: "
+		    "ioc_status (0x%04x), loginfo(0x%08x)\n", ioc->name,
+		    le16_to_cpu(mpi_reply.IOCStatus),
+		    le32_to_cpu(mpi_reply.IOCLogInfo)));
+		return;
+	}
+}
+
+/**
+ * _scsih_send_event_to_turn_on_fault_led - fire delayed event
+ * @ioc: per adapter object
+ * @handle: device handle
+ * Context: interrupt.
+ *
+ * Return nothing.
+ */
+static void
+_scsih_send_event_to_turn_on_fault_led(struct MPT2SAS_ADAPTER *ioc, u16 handle)
+{
+	struct fw_event_work *fw_event;
+
+	fw_event = kzalloc(sizeof(struct fw_event_work), GFP_ATOMIC);
+	if (!fw_event)
+		return;
+	fw_event->event = MPT2SAS_TURN_ON_FAULT_LED;
+	fw_event->device_handle = handle;
+	fw_event->ioc = ioc;
+	_scsih_fw_event_add(ioc, fw_event);
+}
+
+/**
+ * _scsih_smart_predicted_fault - process smart errors
+ * @ioc: per adapter object
+ * @handle: device handle
+ * Context: interrupt.
+ *
+ * Return nothing.
+ */
+static void
+_scsih_smart_predicted_fault(struct MPT2SAS_ADAPTER *ioc, u16 handle)
+{
 	struct scsi_target *starget;
 	struct MPT2SAS_TARGET *sas_target_priv_data;
 	Mpi2EventNotificationReply_t *event_reply;
@@ -4084,30 +4139,8 @@ _scsih_smart_predicted_fault(struct MPT2SAS_ADAPTER *ioc, u16 handle)
 	starget_printk(KERN_WARNING, starget, "predicted fault\n");
 	spin_unlock_irqrestore(&ioc->sas_device_lock, flags);
 
-	if (ioc->pdev->subsystem_vendor == PCI_VENDOR_ID_IBM) {
-		memset(&mpi_request, 0, sizeof(Mpi2SepRequest_t));
-		mpi_request.Function = MPI2_FUNCTION_SCSI_ENCLOSURE_PROCESSOR;
-		mpi_request.Action = MPI2_SEP_REQ_ACTION_WRITE_STATUS;
-		mpi_request.SlotStatus =
-		    cpu_to_le32(MPI2_SEP_REQ_SLOTSTATUS_PREDICTED_FAULT);
-		mpi_request.DevHandle = cpu_to_le16(handle);
-		mpi_request.Flags = MPI2_SEP_REQ_FLAGS_DEVHANDLE_ADDRESS;
-		if ((mpt2sas_base_scsi_enclosure_processor(ioc, &mpi_reply,
-		    &mpi_request)) != 0) {
-			printk(MPT2SAS_ERR_FMT "failure at %s:%d/%s()!\n",
-			    ioc->name, __FILE__, __LINE__, __func__);
-			return;
-		}
-
-		if (mpi_reply.IOCStatus || mpi_reply.IOCLogInfo) {
-			dewtprintk(ioc, printk(MPT2SAS_INFO_FMT
-			    "enclosure_processor: ioc_status (0x%04x), "
-			    "loginfo(0x%08x)\n", ioc->name,
-			    le16_to_cpu(mpi_reply.IOCStatus),
-			    le32_to_cpu(mpi_reply.IOCLogInfo)));
-			return;
-		}
-	}
+	if (ioc->pdev->subsystem_vendor == PCI_VENDOR_ID_IBM)
+		_scsih_send_event_to_turn_on_fault_led(ioc, handle);
 
 	/* insert into event log */
 	sz = offsetof(Mpi2EventNotificationReply_t, EventData) +
@@ -6753,6 +6786,9 @@ _firmware_event_work(struct work_struct *work)
 	}
 
 	switch (fw_event->event) {
+	case MPT2SAS_TURN_ON_FAULT_LED:
+		_scsih_turn_on_fault_led(ioc, fw_event->device_handle);
+		break;
 	case MPI2_EVENT_SAS_TOPOLOGY_CHANGE_LIST:
 		_scsih_sas_topology_change_event(ioc, fw_event);
 		break;
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index 58f5be4740e9..de0b1a704fb5 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -4698,12 +4698,14 @@ static int __os_scsi_tape_open(struct inode * inode, struct file * filp)
 			break;
 
 			if ((SRpnt->sense[2] & 0x0f) == UNIT_ATTENTION) {
+				int j;
+
 				STp->pos_unknown = 0;
 				STp->partition = STp->new_partition = 0;
 				if (STp->can_partitions)
 					STp->nbr_partitions = 1;  /* This guess will be updated later if necessary */
-				for (i=0; i < ST_NBR_PARTITIONS; i++) {
-					STps = &(STp->ps[i]);
+				for (j = 0; j < ST_NBR_PARTITIONS; j++) {
+					STps = &(STp->ps[j]);
 					STps->rw = ST_IDLE;
 					STps->eof = ST_NOEOF;
 					STps->at_sm = 0;
diff --git a/drivers/scsi/qla4xxx/Makefile b/drivers/scsi/qla4xxx/Makefile
index 0339ff03a535..252523d7847e 100644
--- a/drivers/scsi/qla4xxx/Makefile
+++ b/drivers/scsi/qla4xxx/Makefile
@@ -1,5 +1,5 @@
 qla4xxx-y := ql4_os.o ql4_init.o ql4_mbx.o ql4_iocb.o ql4_isr.o \
-		ql4_nx.o ql4_nvram.o ql4_dbg.o
+		ql4_nx.o ql4_nvram.o ql4_dbg.o ql4_attr.o
 
 obj-$(CONFIG_SCSI_QLA_ISCSI) += qla4xxx.o
 
diff --git a/drivers/scsi/qla4xxx/ql4_attr.c b/drivers/scsi/qla4xxx/ql4_attr.c
new file mode 100644
index 000000000000..864d018631c0
--- /dev/null
+++ b/drivers/scsi/qla4xxx/ql4_attr.c
@@ -0,0 +1,69 @@
+/*
+ * QLogic iSCSI HBA Driver
+ * Copyright (c)  2003-2011 QLogic Corporation
+ *
+ * See LICENSE.qla4xxx for copyright and licensing details.
+ */
+
+#include "ql4_def.h"
+#include "ql4_glbl.h"
+#include "ql4_dbg.h"
+
+/* Scsi_Host attributes. */
+static ssize_t
+qla4xxx_fw_version_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct scsi_qla_host *ha = to_qla_host(class_to_shost(dev));
+
+	if (is_qla8022(ha))
+		return snprintf(buf, PAGE_SIZE, "%d.%02d.%02d (%x)\n",
+				ha->firmware_version[0],
+				ha->firmware_version[1],
+				ha->patch_number, ha->build_number);
+	else
+		return snprintf(buf, PAGE_SIZE, "%d.%02d.%02d.%02d\n",
+				ha->firmware_version[0],
+				ha->firmware_version[1],
+				ha->patch_number, ha->build_number);
+}
+
+static ssize_t
+qla4xxx_serial_num_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	struct scsi_qla_host *ha = to_qla_host(class_to_shost(dev));
+	return snprintf(buf, PAGE_SIZE, "%s\n", ha->serial_number);
+}
+
+static ssize_t
+qla4xxx_iscsi_version_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct scsi_qla_host *ha = to_qla_host(class_to_shost(dev));
+	return snprintf(buf, PAGE_SIZE, "%d.%02d\n", ha->iscsi_major,
+			ha->iscsi_minor);
+}
+
+static ssize_t
+qla4xxx_optrom_version_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	struct scsi_qla_host *ha = to_qla_host(class_to_shost(dev));
+	return snprintf(buf, PAGE_SIZE, "%d.%02d.%02d.%02d\n",
+			ha->bootload_major, ha->bootload_minor,
+			ha->bootload_patch, ha->bootload_build);
+}
+
+static DEVICE_ATTR(fw_version, S_IRUGO, qla4xxx_fw_version_show, NULL);
+static DEVICE_ATTR(serial_num, S_IRUGO, qla4xxx_serial_num_show, NULL);
+static DEVICE_ATTR(iscsi_version, S_IRUGO, qla4xxx_iscsi_version_show, NULL);
+static DEVICE_ATTR(optrom_version, S_IRUGO, qla4xxx_optrom_version_show, NULL);
+
+struct device_attribute *qla4xxx_host_attrs[] = {
+	&dev_attr_fw_version,
+	&dev_attr_serial_num,
+	&dev_attr_iscsi_version,
+	&dev_attr_optrom_version,
+	NULL,
+};
diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h
index 4757878d59dd..473c5c872b39 100644
--- a/drivers/scsi/qla4xxx/ql4_def.h
+++ b/drivers/scsi/qla4xxx/ql4_def.h
@@ -115,7 +115,7 @@
 #define INVALID_ENTRY		0xFFFF
 #define MAX_CMDS_TO_RISC	1024
 #define MAX_SRBS		MAX_CMDS_TO_RISC
-#define MBOX_AEN_REG_COUNT	5
+#define MBOX_AEN_REG_COUNT	8
 #define MAX_INIT_RETRIES	5
 
 /*
@@ -368,7 +368,6 @@ struct scsi_qla_host {
 #define AF_INIT_DONE			1 /* 0x00000002 */
 #define AF_MBOX_COMMAND			2 /* 0x00000004 */
 #define AF_MBOX_COMMAND_DONE		3 /* 0x00000008 */
-#define AF_DPC_SCHEDULED		5 /* 0x00000020 */
 #define AF_INTERRUPTS_ON		6 /* 0x00000040 */
 #define AF_GET_CRASH_RECORD		7 /* 0x00000080 */
 #define AF_LINK_UP			8 /* 0x00000100 */
@@ -584,6 +583,14 @@ struct scsi_qla_host {
 	uint32_t nx_reset_timeout;
 
 	struct completion mbx_intr_comp;
+
+	/* --- From About Firmware --- */
+	uint16_t iscsi_major;
+	uint16_t iscsi_minor;
+	uint16_t bootload_major;
+	uint16_t bootload_minor;
+	uint16_t bootload_patch;
+	uint16_t bootload_build;
 };
 
 static inline int is_ipv4_enabled(struct scsi_qla_host *ha)
diff --git a/drivers/scsi/qla4xxx/ql4_fw.h b/drivers/scsi/qla4xxx/ql4_fw.h
index 31e2bf97198c..01082aa77098 100644
--- a/drivers/scsi/qla4xxx/ql4_fw.h
+++ b/drivers/scsi/qla4xxx/ql4_fw.h
@@ -690,6 +690,29 @@ struct mbx_sys_info {
 	uint8_t reserved[12];		  /* 34-3f */
 };
 
+struct about_fw_info {
+	uint16_t fw_major;		/* 00 - 01 */
+	uint16_t fw_minor;		/* 02 - 03 */
+	uint16_t fw_patch;		/* 04 - 05 */
+	uint16_t fw_build;		/* 06 - 07 */
+	uint8_t fw_build_date[16];	/* 08 - 17 ASCII String */
+	uint8_t fw_build_time[16];	/* 18 - 27 ASCII String */
+	uint8_t fw_build_user[16];	/* 28 - 37 ASCII String */
+	uint16_t fw_load_source;	/* 38 - 39 */
+					/* 1 = Flash Primary,
+					   2 = Flash Secondary,
+					   3 = Host Download
+					*/
+	uint8_t reserved1[6];		/* 3A - 3F */
+	uint16_t iscsi_major;		/* 40 - 41 */
+	uint16_t iscsi_minor;		/* 42 - 43 */
+	uint16_t bootload_major;	/* 44 - 45 */
+	uint16_t bootload_minor;	/* 46 - 47 */
+	uint16_t bootload_patch;	/* 48 - 49 */
+	uint16_t bootload_build;	/* 4A - 4B */
+	uint8_t reserved2[180];		/* 4C - FF */
+};
+
 struct crash_record {
 	uint16_t fw_major_version;	/* 00 - 01 */
 	uint16_t fw_minor_version;	/* 02 - 03 */
diff --git a/drivers/scsi/qla4xxx/ql4_glbl.h b/drivers/scsi/qla4xxx/ql4_glbl.h
index cc53e3fbd78c..a53a256c1f8d 100644
--- a/drivers/scsi/qla4xxx/ql4_glbl.h
+++ b/drivers/scsi/qla4xxx/ql4_glbl.h
@@ -61,7 +61,7 @@ struct ddb_entry *qla4xxx_alloc_sess(struct scsi_qla_host *ha);
 int qla4xxx_add_sess(struct ddb_entry *);
 void qla4xxx_destroy_sess(struct ddb_entry *ddb_entry);
 int qla4xxx_is_nvram_configuration_valid(struct scsi_qla_host *ha);
-int qla4xxx_get_fw_version(struct scsi_qla_host * ha);
+int qla4xxx_about_firmware(struct scsi_qla_host *ha);
 void qla4xxx_interrupt_service_routine(struct scsi_qla_host *ha,
 				       uint32_t intr_status);
 int qla4xxx_init_rings(struct scsi_qla_host *ha);
@@ -139,4 +139,5 @@ extern int ql4xextended_error_logging;
 extern int ql4xdontresethba;
 extern int ql4xenablemsix;
 
+extern struct device_attribute *qla4xxx_host_attrs[];
 #endif /* _QLA4x_GBL_H */
diff --git a/drivers/scsi/qla4xxx/ql4_init.c b/drivers/scsi/qla4xxx/ql4_init.c
index 48e2241ddaf4..42ed5db2d530 100644
--- a/drivers/scsi/qla4xxx/ql4_init.c
+++ b/drivers/scsi/qla4xxx/ql4_init.c
@@ -1275,7 +1275,7 @@ int qla4xxx_initialize_adapter(struct scsi_qla_host *ha,
 	if (ha->isp_ops->start_firmware(ha) == QLA_ERROR)
 		goto exit_init_hba;
 
-	if (qla4xxx_get_fw_version(ha) == QLA_ERROR)
+	if (qla4xxx_about_firmware(ha) == QLA_ERROR)
 		goto exit_init_hba;
 
 	if (ha->isp_ops->get_sys_info(ha) == QLA_ERROR)
diff --git a/drivers/scsi/qla4xxx/ql4_isr.c b/drivers/scsi/qla4xxx/ql4_isr.c
index 2f40ac761cd4..0e72921c752d 100644
--- a/drivers/scsi/qla4xxx/ql4_isr.c
+++ b/drivers/scsi/qla4xxx/ql4_isr.c
@@ -25,9 +25,14 @@ static void qla4xxx_copy_sense(struct scsi_qla_host *ha,
 
 	memset(cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
 	sense_len = le16_to_cpu(sts_entry->senseDataByteCnt);
-	if (sense_len == 0)
+	if (sense_len == 0) {
+		DEBUG2(ql4_printk(KERN_INFO, ha, "scsi%ld:%d:%d:%d: %s:"
+				  " sense len 0\n", ha->host_no,
+				  cmd->device->channel, cmd->device->id,
+				  cmd->device->lun, __func__));
+		ha->status_srb = NULL;
 		return;
-
+	}
 	/* Save total available sense length,
 	 * not to exceed cmd's sense buffer size */
 	sense_len = min_t(uint16_t, sense_len, SCSI_SENSE_BUFFERSIZE);
@@ -541,6 +546,7 @@ static void qla4xxx_isr_decode_mailbox(struct scsi_qla_host * ha,
 		case MBOX_ASTS_UNSOLICITED_PDU_RECEIVED:  /* Connection mode */
 		case MBOX_ASTS_IPSEC_SYSTEM_FATAL_ERROR:
 		case MBOX_ASTS_SUBNET_STATE_CHANGE:
+		case MBOX_ASTS_DUPLICATE_IP:
 			/* No action */
 			DEBUG2(printk("scsi%ld: AEN %04x\n", ha->host_no,
 				      mbox_status));
@@ -593,11 +599,13 @@ static void qla4xxx_isr_decode_mailbox(struct scsi_qla_host * ha,
 					    mbox_sts[i];
 
 				/* print debug message */
-				DEBUG2(printk("scsi%ld: AEN[%d] %04x queued"
-				    " mb1:0x%x mb2:0x%x mb3:0x%x mb4:0x%x\n",
-				    ha->host_no, ha->aen_in, mbox_sts[0],
-				    mbox_sts[1], mbox_sts[2],  mbox_sts[3],
-				    mbox_sts[4]));
+				DEBUG2(printk("scsi%ld: AEN[%d] %04x queued "
+					      "mb1:0x%x mb2:0x%x mb3:0x%x "
+					      "mb4:0x%x mb5:0x%x\n",
+					      ha->host_no, ha->aen_in,
+					      mbox_sts[0], mbox_sts[1],
+					      mbox_sts[2], mbox_sts[3],
+					      mbox_sts[4], mbox_sts[5]));
 
 				/* advance pointer */
 				ha->aen_in++;
diff --git a/drivers/scsi/qla4xxx/ql4_mbx.c b/drivers/scsi/qla4xxx/ql4_mbx.c
index d78b58dc5011..fce8289e9752 100644
--- a/drivers/scsi/qla4xxx/ql4_mbx.c
+++ b/drivers/scsi/qla4xxx/ql4_mbx.c
@@ -86,22 +86,8 @@ int qla4xxx_mailbox_command(struct scsi_qla_host *ha, uint8_t inCount,
 		msleep(10);
 	}
 
-	/* To prevent overwriting mailbox registers for a command that has
-	 * not yet been serviced, check to see if an active command
-	 * (AEN, IOCB, etc.) is interrupting, then service it.
-	 * -----------------------------------------------------------------
-	 */
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 
-	if (!is_qla8022(ha)) {
-		intr_status = readl(&ha->reg->ctrl_status);
-		if (intr_status & CSR_SCSI_PROCESSOR_INTR) {
-			/* Service existing interrupt */
-			ha->isp_ops->interrupt_service_routine(ha, intr_status);
-			clear_bit(AF_MBOX_COMMAND_DONE, &ha->flags);
-		}
-	}
-
 	ha->mbox_status_count = outCount;
 	for (i = 0; i < outCount; i++)
 		ha->mbox_status[i] = 0;
@@ -1057,38 +1043,65 @@ int qla4xxx_get_flash(struct scsi_qla_host * ha, dma_addr_t dma_addr,
 }
 
 /**
- * qla4xxx_get_fw_version - gets firmware version
+ * qla4xxx_about_firmware - gets FW, iscsi draft and boot loader version
  * @ha: Pointer to host adapter structure.
  *
- * Retrieves the firmware version on HBA. In QLA4010, mailboxes 2 & 3 may
- * hold an address for data.  Make sure that we write 0 to those mailboxes,
- * if unused.
+ * Retrieves the FW version, iSCSI draft version & bootloader version of HBA.
+ * Mailboxes 2 & 3 may hold an address for data. Make sure that we write 0 to
+ * those mailboxes, if unused.
  **/
-int qla4xxx_get_fw_version(struct scsi_qla_host * ha)
+int qla4xxx_about_firmware(struct scsi_qla_host *ha)
 {
+	struct about_fw_info *about_fw = NULL;
+	dma_addr_t about_fw_dma;
 	uint32_t mbox_cmd[MBOX_REG_COUNT];
 	uint32_t mbox_sts[MBOX_REG_COUNT];
+	int status = QLA_ERROR;
+
+	about_fw = dma_alloc_coherent(&ha->pdev->dev,
+				      sizeof(struct about_fw_info),
+				      &about_fw_dma, GFP_KERNEL);
+	if (!about_fw) {
+		DEBUG2(ql4_printk(KERN_ERR, ha, "%s: Unable to alloc memory "
+				  "for about_fw\n", __func__));
+		return status;
+	}
 
-	/* Get firmware version. */
+	memset(about_fw, 0, sizeof(struct about_fw_info));
 	memset(&mbox_cmd, 0, sizeof(mbox_cmd));
 	memset(&mbox_sts, 0, sizeof(mbox_sts));
 
 	mbox_cmd[0] = MBOX_CMD_ABOUT_FW;
-
-	if (qla4xxx_mailbox_command(ha, MBOX_REG_COUNT, 5, &mbox_cmd[0], &mbox_sts[0]) !=
-	    QLA_SUCCESS) {
-		DEBUG2(printk("scsi%ld: %s: MBOX_CMD_ABOUT_FW failed w/ "
-		    "status %04X\n", ha->host_no, __func__, mbox_sts[0]));
-		return QLA_ERROR;
+	mbox_cmd[2] = LSDW(about_fw_dma);
+	mbox_cmd[3] = MSDW(about_fw_dma);
+	mbox_cmd[4] = sizeof(struct about_fw_info);
+
+	status = qla4xxx_mailbox_command(ha, MBOX_REG_COUNT, MBOX_REG_COUNT,
+					 &mbox_cmd[0], &mbox_sts[0]);
+	if (status != QLA_SUCCESS) {
+		DEBUG2(ql4_printk(KERN_WARNING, ha, "%s: MBOX_CMD_ABOUT_FW "
+				  "failed w/ status %04X\n", __func__,
+				  mbox_sts[0]));
+		goto exit_about_fw;
 	}
 
-	/* Save firmware version information. */
-	ha->firmware_version[0] = mbox_sts[1];
-	ha->firmware_version[1] = mbox_sts[2];
-	ha->patch_number = mbox_sts[3];
-	ha->build_number = mbox_sts[4];
+	/* Save version information. */
+	ha->firmware_version[0] = le16_to_cpu(about_fw->fw_major);
+	ha->firmware_version[1] = le16_to_cpu(about_fw->fw_minor);
+	ha->patch_number = le16_to_cpu(about_fw->fw_patch);
+	ha->build_number = le16_to_cpu(about_fw->fw_build);
+	ha->iscsi_major = le16_to_cpu(about_fw->iscsi_major);
+	ha->iscsi_minor = le16_to_cpu(about_fw->iscsi_minor);
+	ha->bootload_major = le16_to_cpu(about_fw->bootload_major);
+	ha->bootload_minor = le16_to_cpu(about_fw->bootload_minor);
+	ha->bootload_patch = le16_to_cpu(about_fw->bootload_patch);
+	ha->bootload_build = le16_to_cpu(about_fw->bootload_build);
+	status = QLA_SUCCESS;
 
-	return QLA_SUCCESS;
+exit_about_fw:
+	dma_free_coherent(&ha->pdev->dev, sizeof(struct about_fw_info),
+			  about_fw, about_fw_dma);
+	return status;
 }
 
 static int qla4xxx_get_default_ddb(struct scsi_qla_host *ha,
diff --git a/drivers/scsi/qla4xxx/ql4_nx.c b/drivers/scsi/qla4xxx/ql4_nx.c
index 03e522b2fe0b..fdfe27b38698 100644
--- a/drivers/scsi/qla4xxx/ql4_nx.c
+++ b/drivers/scsi/qla4xxx/ql4_nx.c
@@ -964,12 +964,26 @@ qla4_8xxx_pinit_from_rom(struct scsi_qla_host *ha, int verbose)
 	/* Halt all the indiviual PEGs and other blocks of the ISP */
 	qla4_8xxx_rom_lock(ha);
 
-	/* mask all niu interrupts */
+	/* disable all I2Q */
+	qla4_8xxx_wr_32(ha, QLA82XX_CRB_I2Q + 0x10, 0x0);
+	qla4_8xxx_wr_32(ha, QLA82XX_CRB_I2Q + 0x14, 0x0);
+	qla4_8xxx_wr_32(ha, QLA82XX_CRB_I2Q + 0x18, 0x0);
+	qla4_8xxx_wr_32(ha, QLA82XX_CRB_I2Q + 0x1c, 0x0);
+	qla4_8xxx_wr_32(ha, QLA82XX_CRB_I2Q + 0x20, 0x0);
+	qla4_8xxx_wr_32(ha, QLA82XX_CRB_I2Q + 0x24, 0x0);
+
+	/* disable all niu interrupts */
 	qla4_8xxx_wr_32(ha, QLA82XX_CRB_NIU + 0x40, 0xff);
 	/* disable xge rx/tx */
 	qla4_8xxx_wr_32(ha, QLA82XX_CRB_NIU + 0x70000, 0x00);
 	/* disable xg1 rx/tx */
 	qla4_8xxx_wr_32(ha, QLA82XX_CRB_NIU + 0x80000, 0x00);
+	/* disable sideband mac */
+	qla4_8xxx_wr_32(ha, QLA82XX_CRB_NIU + 0x90000, 0x00);
+	/* disable ap0 mac */
+	qla4_8xxx_wr_32(ha, QLA82XX_CRB_NIU + 0xa0000, 0x00);
+	/* disable ap1 mac */
+	qla4_8xxx_wr_32(ha, QLA82XX_CRB_NIU + 0xb0000, 0x00);
 
 	/* halt sre */
 	val = qla4_8xxx_rd_32(ha, QLA82XX_CRB_SRE + 0x1000);
@@ -984,6 +998,7 @@ qla4_8xxx_pinit_from_rom(struct scsi_qla_host *ha, int verbose)
 	qla4_8xxx_wr_32(ha, QLA82XX_CRB_TIMER + 0x10, 0x0);
 	qla4_8xxx_wr_32(ha, QLA82XX_CRB_TIMER + 0x18, 0x0);
 	qla4_8xxx_wr_32(ha, QLA82XX_CRB_TIMER + 0x100, 0x0);
+	qla4_8xxx_wr_32(ha, QLA82XX_CRB_TIMER + 0x200, 0x0);
 
 	/* halt pegs */
 	qla4_8xxx_wr_32(ha, QLA82XX_CRB_PEG_NET_0 + 0x3c, 1);
@@ -991,9 +1006,9 @@ qla4_8xxx_pinit_from_rom(struct scsi_qla_host *ha, int verbose)
 	qla4_8xxx_wr_32(ha, QLA82XX_CRB_PEG_NET_2 + 0x3c, 1);
 	qla4_8xxx_wr_32(ha, QLA82XX_CRB_PEG_NET_3 + 0x3c, 1);
 	qla4_8xxx_wr_32(ha, QLA82XX_CRB_PEG_NET_4 + 0x3c, 1);
+	msleep(5);
 
 	/* big hammer */
-	msleep(1000);
 	if (test_bit(DPC_RESET_HA, &ha->dpc_flags))
 		/* don't reset CAM block on reset */
 		qla4_8xxx_wr_32(ha, QLA82XX_ROMUSB_GLB_SW_RESET, 0xfeffffff);
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index c22f2a764d9d..f2364ec59f03 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -124,6 +124,7 @@ static struct scsi_host_template qla4xxx_driver_template = {
 	.sg_tablesize		= SG_ALL,
 
 	.max_sectors		= 0xFFFF,
+	.shost_attrs		= qla4xxx_host_attrs,
 };
 
 static struct iscsi_transport qla4xxx_iscsi_transport = {
@@ -412,8 +413,7 @@ void qla4xxx_mark_all_devices_missing(struct scsi_qla_host *ha)
 
 static struct srb* qla4xxx_get_new_srb(struct scsi_qla_host *ha,
 				       struct ddb_entry *ddb_entry,
-				       struct scsi_cmnd *cmd,
-				       void (*done)(struct scsi_cmnd *))
+				       struct scsi_cmnd *cmd)
 {
 	struct srb *srb;
 
@@ -427,7 +427,6 @@ static struct srb* qla4xxx_get_new_srb(struct scsi_qla_host *ha,
 	srb->cmd = cmd;
 	srb->flags = 0;
 	CMD_SP(cmd) = (void *)srb;
-	cmd->scsi_done = done;
 
 	return srb;
 }
@@ -458,9 +457,8 @@ void qla4xxx_srb_compl(struct kref *ref)
 
 /**
  * qla4xxx_queuecommand - scsi layer issues scsi command to driver.
+ * @host: scsi host
  * @cmd: Pointer to Linux's SCSI command structure
- * @done_fn: Function that the driver calls to notify the SCSI mid-layer
- *	that the command has been processed.
  *
  * Remarks:
  * This routine is invoked by Linux to send a SCSI command to the driver.
@@ -470,10 +468,9 @@ void qla4xxx_srb_compl(struct kref *ref)
  * completion handling).   Unfortunely, it sometimes calls the scheduler
  * in interrupt context which is a big NO! NO!.
  **/
-static int qla4xxx_queuecommand_lck(struct scsi_cmnd *cmd,
-				void (*done)(struct scsi_cmnd *))
+static int qla4xxx_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 {
-	struct scsi_qla_host *ha = to_qla_host(cmd->device->host);
+	struct scsi_qla_host *ha = to_qla_host(host);
 	struct ddb_entry *ddb_entry = cmd->device->hostdata;
 	struct iscsi_cls_session *sess = ddb_entry->sess;
 	struct srb *srb;
@@ -515,37 +512,29 @@ static int qla4xxx_queuecommand_lck(struct scsi_cmnd *cmd,
 	    test_bit(DPC_RESET_HA_FW_CONTEXT, &ha->dpc_flags))
 		goto qc_host_busy;
 
-	spin_unlock_irq(ha->host->host_lock);
-
-	srb = qla4xxx_get_new_srb(ha, ddb_entry, cmd, done);
+	srb = qla4xxx_get_new_srb(ha, ddb_entry, cmd);
 	if (!srb)
-		goto qc_host_busy_lock;
+		goto qc_host_busy;
 
 	rval = qla4xxx_send_command_to_isp(ha, srb);
 	if (rval != QLA_SUCCESS)
 		goto qc_host_busy_free_sp;
 
-	spin_lock_irq(ha->host->host_lock);
 	return 0;
 
 qc_host_busy_free_sp:
 	qla4xxx_srb_free_dma(ha, srb);
 	mempool_free(srb, ha->srb_mempool);
 
-qc_host_busy_lock:
-	spin_lock_irq(ha->host->host_lock);
-
 qc_host_busy:
 	return SCSI_MLQUEUE_HOST_BUSY;
 
 qc_fail_command:
-	done(cmd);
+	cmd->scsi_done(cmd);
 
 	return 0;
 }
 
-static DEF_SCSI_QCMD(qla4xxx_queuecommand)
-
 /**
  * qla4xxx_mem_free - frees memory allocated to adapter
  * @ha: Pointer to host adapter structure.
@@ -679,7 +668,27 @@ static void qla4_8xxx_check_fw_alive(struct scsi_qla_host *ha)
 		if (ha->seconds_since_last_heartbeat == 2) {
 			ha->seconds_since_last_heartbeat = 0;
 			halt_status = qla4_8xxx_rd_32(ha,
-			    QLA82XX_PEG_HALT_STATUS1);
+						      QLA82XX_PEG_HALT_STATUS1);
+
+			ql4_printk(KERN_INFO, ha,
+				   "scsi(%ld): %s, Dumping hw/fw registers:\n "
+				   " PEG_HALT_STATUS1: 0x%x, PEG_HALT_STATUS2:"
+				   " 0x%x,\n PEG_NET_0_PC: 0x%x, PEG_NET_1_PC:"
+				   " 0x%x,\n PEG_NET_2_PC: 0x%x, PEG_NET_3_PC:"
+				   " 0x%x,\n PEG_NET_4_PC: 0x%x\n",
+				   ha->host_no, __func__, halt_status,
+				   qla4_8xxx_rd_32(ha,
+						   QLA82XX_PEG_HALT_STATUS2),
+				   qla4_8xxx_rd_32(ha, QLA82XX_CRB_PEG_NET_0 +
+						   0x3c),
+				   qla4_8xxx_rd_32(ha, QLA82XX_CRB_PEG_NET_1 +
+						   0x3c),
+				   qla4_8xxx_rd_32(ha, QLA82XX_CRB_PEG_NET_2 +
+						   0x3c),
+				   qla4_8xxx_rd_32(ha, QLA82XX_CRB_PEG_NET_3 +
+						   0x3c),
+				   qla4_8xxx_rd_32(ha, QLA82XX_CRB_PEG_NET_4 +
+						   0x3c));
 
 			/* Since we cannot change dev_state in interrupt
 			 * context, set appropriate DPC flag then wakeup
@@ -715,7 +724,7 @@ void qla4_8xxx_watchdog(struct scsi_qla_host *ha)
 	/* don't poll if reset is going on */
 	if (!(test_bit(DPC_RESET_ACTIVE, &ha->dpc_flags) ||
 	    test_bit(DPC_RESET_HA, &ha->dpc_flags) ||
-	    test_bit(DPC_RESET_ACTIVE, &ha->dpc_flags))) {
+	    test_bit(DPC_RETRY_RESET_HA, &ha->dpc_flags))) {
 		if (dev_state == QLA82XX_DEV_NEED_RESET &&
 		    !test_bit(DPC_RESET_HA, &ha->dpc_flags)) {
 			if (!ql4xdontresethba) {
@@ -839,7 +848,7 @@ static void qla4xxx_timer(struct scsi_qla_host *ha)
 	}
 
 	/* Wakeup the dpc routine for this adapter, if needed. */
-	if ((start_dpc ||
+	if (start_dpc ||
 	     test_bit(DPC_RESET_HA, &ha->dpc_flags) ||
 	     test_bit(DPC_RETRY_RESET_HA, &ha->dpc_flags) ||
 	     test_bit(DPC_RELOGIN_DEVICE, &ha->dpc_flags) ||
@@ -849,9 +858,7 @@ static void qla4xxx_timer(struct scsi_qla_host *ha)
 	     test_bit(DPC_LINK_CHANGED, &ha->dpc_flags) ||
 	     test_bit(DPC_HA_UNRECOVERABLE, &ha->dpc_flags) ||
 	     test_bit(DPC_HA_NEED_QUIESCENT, &ha->dpc_flags) ||
-	     test_bit(DPC_AEN, &ha->dpc_flags)) &&
-	     !test_bit(AF_DPC_SCHEDULED, &ha->flags) &&
-	     ha->dpc_thread) {
+	     test_bit(DPC_AEN, &ha->dpc_flags)) {
 		DEBUG2(printk("scsi%ld: %s: scheduling dpc routine"
 			      " - dpc flags = 0x%lx\n",
 			      ha->host_no, __func__, ha->dpc_flags));
@@ -1241,11 +1248,8 @@ static void qla4xxx_relogin_all_devices(struct scsi_qla_host *ha)
 
 void qla4xxx_wake_dpc(struct scsi_qla_host *ha)
 {
-	if (ha->dpc_thread &&
-	    !test_bit(AF_DPC_SCHEDULED, &ha->flags)) {
-		set_bit(AF_DPC_SCHEDULED, &ha->flags);
+	if (ha->dpc_thread)
 		queue_work(ha->dpc_thread, &ha->dpc_work);
-	}
 }
 
 /**
@@ -1272,12 +1276,12 @@ static void qla4xxx_do_dpc(struct work_struct *work)
 
 	/* Initialization not yet finished. Don't do anything yet. */
 	if (!test_bit(AF_INIT_DONE, &ha->flags))
-		goto do_dpc_exit;
+		return;
 
 	if (test_bit(AF_EEH_BUSY, &ha->flags)) {
 		DEBUG2(printk(KERN_INFO "scsi%ld: %s: flags = %lx\n",
 		    ha->host_no, __func__, ha->flags));
-		goto do_dpc_exit;
+		return;
 	}
 
 	if (is_qla8022(ha)) {
@@ -1384,8 +1388,6 @@ dpc_post_reset_ha:
 		}
 	}
 
-do_dpc_exit:
-	clear_bit(AF_DPC_SCHEDULED, &ha->flags);
 }
 
 /**
diff --git a/drivers/scsi/qla4xxx/ql4_version.h b/drivers/scsi/qla4xxx/ql4_version.h
index 603155769407..610492877253 100644
--- a/drivers/scsi/qla4xxx/ql4_version.h
+++ b/drivers/scsi/qla4xxx/ql4_version.h
@@ -5,4 +5,4 @@
  * See LICENSE.qla4xxx for copyright and licensing details.
  */
 
-#define QLA4XXX_DRIVER_VERSION	"5.02.00-k6"
+#define QLA4XXX_DRIVER_VERSION	"5.02.00-k7"
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index abea2cf05c2e..a4b9cdbaaa0b 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -50,6 +50,8 @@
 #define BUS_RESET_SETTLE_TIME   (10)
 #define HOST_RESET_SETTLE_TIME  (10)
 
+static int scsi_eh_try_stu(struct scsi_cmnd *scmd);
+
 /* called with shost->host_lock held */
 void scsi_eh_wakeup(struct Scsi_Host *shost)
 {
@@ -947,6 +949,48 @@ retry_tur:
 }
 
 /**
+ * scsi_eh_test_devices - check if devices are responding from error recovery.
+ * @cmd_list:	scsi commands in error recovery.
+ * @work_q:     queue for commands which still need more error recovery
+ * @done_q:     queue for commands which are finished
+ * @try_stu:    boolean on if a STU command should be tried in addition to TUR.
+ *
+ * Decription:
+ *    Tests if devices are in a working state.  Commands to devices now in
+ *    a working state are sent to the done_q while commands to devices which
+ *    are still failing to respond are returned to the work_q for more
+ *    processing.
+ **/
+static int scsi_eh_test_devices(struct list_head *cmd_list,
+				struct list_head *work_q,
+				struct list_head *done_q, int try_stu)
+{
+	struct scsi_cmnd *scmd, *next;
+	struct scsi_device *sdev;
+	int finish_cmds;
+
+	while (!list_empty(cmd_list)) {
+		scmd = list_entry(cmd_list->next, struct scsi_cmnd, eh_entry);
+		sdev = scmd->device;
+
+		finish_cmds = !scsi_device_online(scmd->device) ||
+			(try_stu && !scsi_eh_try_stu(scmd) &&
+			 !scsi_eh_tur(scmd)) ||
+			!scsi_eh_tur(scmd);
+
+		list_for_each_entry_safe(scmd, next, cmd_list, eh_entry)
+			if (scmd->device == sdev) {
+				if (finish_cmds)
+					scsi_eh_finish_cmd(scmd, done_q);
+				else
+					list_move_tail(&scmd->eh_entry, work_q);
+			}
+	}
+	return list_empty(work_q);
+}
+
+
+/**
  * scsi_eh_abort_cmds - abort pending commands.
  * @work_q:	&list_head for pending commands.
  * @done_q:	&list_head for processed commands.
@@ -962,6 +1006,7 @@ static int scsi_eh_abort_cmds(struct list_head *work_q,
 			      struct list_head *done_q)
 {
 	struct scsi_cmnd *scmd, *next;
+	LIST_HEAD(check_list);
 	int rtn;
 
 	list_for_each_entry_safe(scmd, next, work_q, eh_entry) {
@@ -973,11 +1018,10 @@ static int scsi_eh_abort_cmds(struct list_head *work_q,
 		rtn = scsi_try_to_abort_cmd(scmd->device->host->hostt, scmd);
 		if (rtn == SUCCESS || rtn == FAST_IO_FAIL) {
 			scmd->eh_eflags &= ~SCSI_EH_CANCEL_CMD;
-			if (!scsi_device_online(scmd->device) ||
-			    rtn == FAST_IO_FAIL ||
-			    !scsi_eh_tur(scmd)) {
+			if (rtn == FAST_IO_FAIL)
 				scsi_eh_finish_cmd(scmd, done_q);
-			}
+			else
+				list_move_tail(&scmd->eh_entry, &check_list);
 		} else
 			SCSI_LOG_ERROR_RECOVERY(3, printk("%s: aborting"
 							  " cmd failed:"
@@ -986,7 +1030,7 @@ static int scsi_eh_abort_cmds(struct list_head *work_q,
 							  scmd));
 	}
 
-	return list_empty(work_q);
+	return scsi_eh_test_devices(&check_list, work_q, done_q, 0);
 }
 
 /**
@@ -1137,6 +1181,7 @@ static int scsi_eh_target_reset(struct Scsi_Host *shost,
 				struct list_head *done_q)
 {
 	LIST_HEAD(tmp_list);
+	LIST_HEAD(check_list);
 
 	list_splice_init(work_q, &tmp_list);
 
@@ -1161,9 +1206,9 @@ static int scsi_eh_target_reset(struct Scsi_Host *shost,
 			if (scmd_id(scmd) != id)
 				continue;
 
-			if ((rtn == SUCCESS || rtn == FAST_IO_FAIL)
-			    && (!scsi_device_online(scmd->device) ||
-				 rtn == FAST_IO_FAIL || !scsi_eh_tur(scmd)))
+			if (rtn == SUCCESS)
+				list_move_tail(&scmd->eh_entry, &check_list);
+			else if (rtn == FAST_IO_FAIL)
 				scsi_eh_finish_cmd(scmd, done_q);
 			else
 				/* push back on work queue for further processing */
@@ -1171,7 +1216,7 @@ static int scsi_eh_target_reset(struct Scsi_Host *shost,
 		}
 	}
 
-	return list_empty(work_q);
+	return scsi_eh_test_devices(&check_list, work_q, done_q, 0);
 }
 
 /**
@@ -1185,6 +1230,7 @@ static int scsi_eh_bus_reset(struct Scsi_Host *shost,
 			     struct list_head *done_q)
 {
 	struct scsi_cmnd *scmd, *chan_scmd, *next;
+	LIST_HEAD(check_list);
 	unsigned int channel;
 	int rtn;
 
@@ -1216,12 +1262,14 @@ static int scsi_eh_bus_reset(struct Scsi_Host *shost,
 		rtn = scsi_try_bus_reset(chan_scmd);
 		if (rtn == SUCCESS || rtn == FAST_IO_FAIL) {
 			list_for_each_entry_safe(scmd, next, work_q, eh_entry) {
-				if (channel == scmd_channel(scmd))
-					if (!scsi_device_online(scmd->device) ||
-					    rtn == FAST_IO_FAIL ||
-					    !scsi_eh_tur(scmd))
+				if (channel == scmd_channel(scmd)) {
+					if (rtn == FAST_IO_FAIL)
 						scsi_eh_finish_cmd(scmd,
 								   done_q);
+					else
+						list_move_tail(&scmd->eh_entry,
+							       &check_list);
+				}
 			}
 		} else {
 			SCSI_LOG_ERROR_RECOVERY(3, printk("%s: BRST"
@@ -1230,7 +1278,7 @@ static int scsi_eh_bus_reset(struct Scsi_Host *shost,
 							  channel));
 		}
 	}
-	return list_empty(work_q);
+	return scsi_eh_test_devices(&check_list, work_q, done_q, 0);
 }
 
 /**
@@ -1242,6 +1290,7 @@ static int scsi_eh_host_reset(struct list_head *work_q,
 			      struct list_head *done_q)
 {
 	struct scsi_cmnd *scmd, *next;
+	LIST_HEAD(check_list);
 	int rtn;
 
 	if (!list_empty(work_q)) {
@@ -1252,12 +1301,10 @@ static int scsi_eh_host_reset(struct list_head *work_q,
 						  , current->comm));
 
 		rtn = scsi_try_host_reset(scmd);
-		if (rtn == SUCCESS || rtn == FAST_IO_FAIL) {
+		if (rtn == SUCCESS) {
+			list_splice_init(work_q, &check_list);
+		} else if (rtn == FAST_IO_FAIL) {
 			list_for_each_entry_safe(scmd, next, work_q, eh_entry) {
-				if (!scsi_device_online(scmd->device) ||
-				    rtn == FAST_IO_FAIL ||
-				    (!scsi_eh_try_stu(scmd) && !scsi_eh_tur(scmd)) ||
-				    !scsi_eh_tur(scmd))
 					scsi_eh_finish_cmd(scmd, done_q);
 			}
 		} else {
@@ -1266,7 +1313,7 @@ static int scsi_eh_host_reset(struct list_head *work_q,
 							  current->comm));
 		}
 	}
-	return list_empty(work_q);
+	return scsi_eh_test_devices(&check_list, work_q, done_q, 1);
 }
 
 /**
diff --git a/drivers/scsi/scsi_proc.c b/drivers/scsi/scsi_proc.c
index f46855cd853d..ad747dc337da 100644
--- a/drivers/scsi/scsi_proc.c
+++ b/drivers/scsi/scsi_proc.c
@@ -381,11 +381,6 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf,
 	return err;
 }
 
-/**
- * proc_scsi_show - show contents of /proc/scsi/scsi (attached devices)
- * @s: output goes here
- * @p: not used
- */
 static int always_match(struct device *dev, void *data)
 {
 	return 1;
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 58584dc0724a..44e8ca398efa 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -297,7 +297,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 		kfree(sdev);
 		goto out;
 	}
-
+	blk_get_queue(sdev->request_queue);
 	sdev->request_queue->queuedata = sdev;
 	scsi_adjust_queue_depth(sdev, 0, sdev->host->cmd_per_lun);
 
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index e63912510fb9..e0bd3f790fca 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -322,6 +322,7 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
 		kfree(evt);
 	}
 
+	blk_put_queue(sdev->request_queue);
 	/* NULL queue means the device can't be used */
 	sdev->request_queue = NULL;
 
diff --git a/drivers/scsi/scsi_trace.c b/drivers/scsi/scsi_trace.c
index b587289cfacb..2bea4f0b684a 100644
--- a/drivers/scsi/scsi_trace.c
+++ b/drivers/scsi/scsi_trace.c
@@ -59,6 +59,10 @@ scsi_trace_rw10(struct trace_seq *p, unsigned char *cdb, int len)
 	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
 			 (unsigned long long)lba, (unsigned long long)txlen,
 			 cdb[1] >> 5);
+
+	if (cdb[0] == WRITE_SAME)
+		trace_seq_printf(p, " unmap=%u", cdb[1] >> 3 & 1);
+
 	trace_seq_putc(p, 0);
 
 	return ret;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index bd0806e64e85..953773cb26d9 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -490,7 +490,8 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	unsigned int max_blocks = 0;
 
 	q->limits.discard_zeroes_data = sdkp->lbprz;
-	q->limits.discard_alignment = sdkp->unmap_alignment;
+	q->limits.discard_alignment = sdkp->unmap_alignment *
+		logical_block_size;
 	q->limits.discard_granularity =
 		max(sdkp->physical_block_size,
 		    sdkp->unmap_granularity * logical_block_size);
@@ -2021,16 +2022,26 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer)
 
 	int dbd;
 	int modepage;
+	int first_len;
 	struct scsi_mode_data data;
 	struct scsi_sense_hdr sshdr;
 	int old_wce = sdkp->WCE;
 	int old_rcd = sdkp->RCD;
 	int old_dpofua = sdkp->DPOFUA;
 
-	if (sdp->skip_ms_page_8)
-		goto defaults;
-
-	if (sdp->type == TYPE_RBC) {
+	first_len = 4;
+	if (sdp->skip_ms_page_8) {
+		if (sdp->type == TYPE_RBC)
+			goto defaults;
+		else {
+			if (sdp->skip_ms_page_3f)
+				goto defaults;
+			modepage = 0x3F;
+			if (sdp->use_192_bytes_for_3f)
+				first_len = 192;
+			dbd = 0;
+		}
+	} else if (sdp->type == TYPE_RBC) {
 		modepage = 6;
 		dbd = 8;
 	} else {
@@ -2039,13 +2050,15 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer)
 	}
 
 	/* cautiously ask */
-	res = sd_do_mode_sense(sdp, dbd, modepage, buffer, 4, &data, &sshdr);
+	res = sd_do_mode_sense(sdp, dbd, modepage, buffer, first_len,
+			&data, &sshdr);
 
 	if (!scsi_status_is_good(res))
 		goto bad_sense;
 
 	if (!data.header_length) {
 		modepage = 6;
+		first_len = 0;
 		sd_printk(KERN_ERR, sdkp, "Missing header in MODE_SENSE response\n");
 	}
 
@@ -2058,30 +2071,61 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer)
 	 */
 	if (len < 3)
 		goto bad_sense;
-	if (len > 20)
-		len = 20;
-
-	/* Take headers and block descriptors into account */
-	len += data.header_length + data.block_descriptor_length;
-	if (len > SD_BUF_SIZE)
-		goto bad_sense;
+	else if (len > SD_BUF_SIZE) {
+		sd_printk(KERN_NOTICE, sdkp, "Truncating mode parameter "
+			  "data from %d to %d bytes\n", len, SD_BUF_SIZE);
+		len = SD_BUF_SIZE;
+	}
+	if (modepage == 0x3F && sdp->use_192_bytes_for_3f)
+		len = 192;
 
 	/* Get the data */
-	res = sd_do_mode_sense(sdp, dbd, modepage, buffer, len, &data, &sshdr);
+	if (len > first_len)
+		res = sd_do_mode_sense(sdp, dbd, modepage, buffer, len,
+				&data, &sshdr);
 
 	if (scsi_status_is_good(res)) {
 		int offset = data.header_length + data.block_descriptor_length;
 
-		if (offset >= SD_BUF_SIZE - 2) {
-			sd_printk(KERN_ERR, sdkp, "Malformed MODE SENSE response\n");
-			goto defaults;
+		while (offset < len) {
+			u8 page_code = buffer[offset] & 0x3F;
+			u8 spf       = buffer[offset] & 0x40;
+
+			if (page_code == 8 || page_code == 6) {
+				/* We're interested only in the first 3 bytes.
+				 */
+				if (len - offset <= 2) {
+					sd_printk(KERN_ERR, sdkp, "Incomplete "
+						  "mode parameter data\n");
+					goto defaults;
+				} else {
+					modepage = page_code;
+					goto Page_found;
+				}
+			} else {
+				/* Go to the next page */
+				if (spf && len - offset > 3)
+					offset += 4 + (buffer[offset+2] << 8) +
+						buffer[offset+3];
+				else if (!spf && len - offset > 1)
+					offset += 2 + buffer[offset+1];
+				else {
+					sd_printk(KERN_ERR, sdkp, "Incomplete "
+						  "mode parameter data\n");
+					goto defaults;
+				}
+			}
 		}
 
-		if ((buffer[offset] & 0x3f) != modepage) {
+		if (modepage == 0x3F) {
+			sd_printk(KERN_ERR, sdkp, "No Caching mode page "
+				  "present\n");
+			goto defaults;
+		} else if ((buffer[offset] & 0x3f) != modepage) {
 			sd_printk(KERN_ERR, sdkp, "Got wrong page\n");
 			goto defaults;
 		}
-
+	Page_found:
 		if (modepage == 8) {
 			sdkp->WCE = ((buffer[offset + 2] & 0x04) != 0);
 			sdkp->RCD = ((buffer[offset + 2] & 0x01) != 0);
diff --git a/drivers/scsi/ultrastor.c b/drivers/scsi/ultrastor.c
index 9f4b58b7daad..7e22b737dfd8 100644
--- a/drivers/scsi/ultrastor.c
+++ b/drivers/scsi/ultrastor.c
@@ -307,7 +307,7 @@ static inline int find_and_clear_bit_16(unsigned long *field)
 	"0: bsfw %1,%w0\n\t"
 	"btr %0,%1\n\t"
 	"jnc 0b"
-	: "=&r" (rv), "=m" (*field) :);
+	: "=&r" (rv), "+m" (*field) :);
 
   return rv;
 }
diff --git a/drivers/sh/clk/core.c b/drivers/sh/clk/core.c
index 4f64183b27fa..7e9c39951ecb 100644
--- a/drivers/sh/clk/core.c
+++ b/drivers/sh/clk/core.c
@@ -635,7 +635,7 @@ static void clks_core_resume(void)
 	struct clk *clkp;
 
 	list_for_each_entry(clkp, &clock_list, node) {
-		if (likely(clkp->ops)) {
+		if (likely(clkp->usecount && clkp->ops)) {
 			unsigned long rate = clkp->rate;
 
 			if (likely(clkp->ops->set_parent))
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index fbd96b29530d..de35c3ad8a69 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -80,6 +80,15 @@ config SPI_BFIN
 	help
 	  This is the SPI controller master driver for Blackfin 5xx processor.
 
+config SPI_BFIN_SPORT
+	tristate "SPI bus via Blackfin SPORT"
+	depends on BLACKFIN
+	help
+	  Enable support for a SPI bus via the Blackfin SPORT peripheral.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called spi_bfin_sport.
+
 config SPI_AU1550
 	tristate "Au1550/Au12x0 SPI Controller"
 	depends on (SOC_AU1550 || SOC_AU1200) && EXPERIMENTAL
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index fd2fc5f6505f..0f8c69b6b19e 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_SPI_ALTERA)		+= spi_altera.o
 obj-$(CONFIG_SPI_ATMEL)			+= atmel_spi.o
 obj-$(CONFIG_SPI_ATH79)			+= ath79_spi.o
 obj-$(CONFIG_SPI_BFIN)			+= spi_bfin5xx.o
+obj-$(CONFIG_SPI_BFIN_SPORT)		+= spi_bfin_sport.o
 obj-$(CONFIG_SPI_BITBANG)		+= spi_bitbang.o
 obj-$(CONFIG_SPI_AU1550)		+= au1550_spi.o
 obj-$(CONFIG_SPI_BUTTERFLY)		+= spi_butterfly.o
diff --git a/drivers/spi/amba-pl022.c b/drivers/spi/amba-pl022.c
index 6a9e58dd36c7..d18ce9e946d8 100644
--- a/drivers/spi/amba-pl022.c
+++ b/drivers/spi/amba-pl022.c
@@ -1861,6 +1861,7 @@ static int pl022_setup(struct spi_device *spi)
 	}
 	if ((clk_freq.cpsdvsr < CPSDVR_MIN)
 	    || (clk_freq.cpsdvsr > CPSDVR_MAX)) {
+		status = -EINVAL;
 		dev_err(&spi->dev,
 			"cpsdvsr is configured incorrectly\n");
 		goto err_config_params;
diff --git a/drivers/spi/omap2_mcspi.c b/drivers/spi/omap2_mcspi.c
index 6f86ba0175ac..969cdd2fe124 100644
--- a/drivers/spi/omap2_mcspi.c
+++ b/drivers/spi/omap2_mcspi.c
@@ -298,7 +298,7 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 	unsigned int		count, c;
 	unsigned long		base, tx_reg, rx_reg;
 	int			word_len, data_type, element_count;
-	int			elements;
+	int			elements = 0;
 	u32			l;
 	u8			* rx;
 	const u8		* tx;
diff --git a/drivers/spi/spi_bfin5xx.c b/drivers/spi/spi_bfin5xx.c
index f706dba165cf..cc880c95e7de 100644
--- a/drivers/spi/spi_bfin5xx.c
+++ b/drivers/spi/spi_bfin5xx.c
@@ -681,13 +681,14 @@ static void bfin_spi_pump_transfers(unsigned long data)
 	drv_data->cs_change = transfer->cs_change;
 
 	/* Bits per word setup */
-	bits_per_word = transfer->bits_per_word ? : message->spi->bits_per_word;
-	if ((bits_per_word > 0) && (bits_per_word % 16 == 0)) {
+	bits_per_word = transfer->bits_per_word ? :
+		message->spi->bits_per_word ? : 8;
+	if (bits_per_word % 16 == 0) {
 		drv_data->n_bytes = bits_per_word/8;
 		drv_data->len = (transfer->len) >> 1;
 		cr_width = BIT_CTL_WORDSIZE;
 		drv_data->ops = &bfin_bfin_spi_transfer_ops_u16;
-	} else if ((bits_per_word > 0) && (bits_per_word % 8 == 0)) {
+	} else if (bits_per_word % 8 == 0) {
 		drv_data->n_bytes = bits_per_word/8;
 		drv_data->len = transfer->len;
 		cr_width = 0;
diff --git a/drivers/spi/spi_bfin_sport.c b/drivers/spi/spi_bfin_sport.c
new file mode 100644
index 000000000000..e557ff617b11
--- /dev/null
+++ b/drivers/spi/spi_bfin_sport.c
@@ -0,0 +1,952 @@
+/*
+ * SPI bus via the Blackfin SPORT peripheral
+ *
+ * Enter bugs at http://blackfin.uclinux.org/
+ *
+ * Copyright 2009-2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/gpio.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/irq.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/workqueue.h>
+
+#include <asm/portmux.h>
+#include <asm/bfin5xx_spi.h>
+#include <asm/blackfin.h>
+#include <asm/bfin_sport.h>
+#include <asm/cacheflush.h>
+
+#define DRV_NAME	"bfin-sport-spi"
+#define DRV_DESC	"SPI bus via the Blackfin SPORT"
+
+MODULE_AUTHOR("Cliff Cai");
+MODULE_DESCRIPTION(DRV_DESC);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:bfin-sport-spi");
+
+enum bfin_sport_spi_state {
+	START_STATE,
+	RUNNING_STATE,
+	DONE_STATE,
+	ERROR_STATE,
+};
+
+struct bfin_sport_spi_master_data;
+
+struct bfin_sport_transfer_ops {
+	void (*write) (struct bfin_sport_spi_master_data *);
+	void (*read) (struct bfin_sport_spi_master_data *);
+	void (*duplex) (struct bfin_sport_spi_master_data *);
+};
+
+struct bfin_sport_spi_master_data {
+	/* Driver model hookup */
+	struct device *dev;
+
+	/* SPI framework hookup */
+	struct spi_master *master;
+
+	/* Regs base of SPI controller */
+	struct sport_register __iomem *regs;
+	int err_irq;
+
+	/* Pin request list */
+	u16 *pin_req;
+
+	/* Driver message queue */
+	struct workqueue_struct *workqueue;
+	struct work_struct pump_messages;
+	spinlock_t lock;
+	struct list_head queue;
+	int busy;
+	bool run;
+
+	/* Message Transfer pump */
+	struct tasklet_struct pump_transfers;
+
+	/* Current message transfer state info */
+	enum bfin_sport_spi_state state;
+	struct spi_message *cur_msg;
+	struct spi_transfer *cur_transfer;
+	struct bfin_sport_spi_slave_data *cur_chip;
+	union {
+		void *tx;
+		u8 *tx8;
+		u16 *tx16;
+	};
+	void *tx_end;
+	union {
+		void *rx;
+		u8 *rx8;
+		u16 *rx16;
+	};
+	void *rx_end;
+
+	int cs_change;
+	struct bfin_sport_transfer_ops *ops;
+};
+
+struct bfin_sport_spi_slave_data {
+	u16 ctl_reg;
+	u16 baud;
+	u16 cs_chg_udelay;	/* Some devices require > 255usec delay */
+	u32 cs_gpio;
+	u16 idle_tx_val;
+	struct bfin_sport_transfer_ops *ops;
+};
+
+static void
+bfin_sport_spi_enable(struct bfin_sport_spi_master_data *drv_data)
+{
+	bfin_write_or(&drv_data->regs->tcr1, TSPEN);
+	bfin_write_or(&drv_data->regs->rcr1, TSPEN);
+	SSYNC();
+}
+
+static void
+bfin_sport_spi_disable(struct bfin_sport_spi_master_data *drv_data)
+{
+	bfin_write_and(&drv_data->regs->tcr1, ~TSPEN);
+	bfin_write_and(&drv_data->regs->rcr1, ~TSPEN);
+	SSYNC();
+}
+
+/* Caculate the SPI_BAUD register value based on input HZ */
+static u16
+bfin_sport_hz_to_spi_baud(u32 speed_hz)
+{
+	u_long clk, sclk = get_sclk();
+	int div = (sclk / (2 * speed_hz)) - 1;
+
+	if (div < 0)
+		div = 0;
+
+	clk = sclk / (2 * (div + 1));
+
+	if (clk > speed_hz)
+		div++;
+
+	return div;
+}
+
+/* Chip select operation functions for cs_change flag */
+static void
+bfin_sport_spi_cs_active(struct bfin_sport_spi_slave_data *chip)
+{
+	gpio_direction_output(chip->cs_gpio, 0);
+}
+
+static void
+bfin_sport_spi_cs_deactive(struct bfin_sport_spi_slave_data *chip)
+{
+	gpio_direction_output(chip->cs_gpio, 1);
+	/* Move delay here for consistency */
+	if (chip->cs_chg_udelay)
+		udelay(chip->cs_chg_udelay);
+}
+
+static void
+bfin_sport_spi_stat_poll_complete(struct bfin_sport_spi_master_data *drv_data)
+{
+	unsigned long timeout = jiffies + HZ;
+	while (!(bfin_read(&drv_data->regs->stat) & RXNE)) {
+		if (!time_before(jiffies, timeout))
+			break;
+	}
+}
+
+static void
+bfin_sport_spi_u8_writer(struct bfin_sport_spi_master_data *drv_data)
+{
+	u16 dummy;
+
+	while (drv_data->tx < drv_data->tx_end) {
+		bfin_write(&drv_data->regs->tx16, *drv_data->tx8++);
+		bfin_sport_spi_stat_poll_complete(drv_data);
+		dummy = bfin_read(&drv_data->regs->rx16);
+	}
+}
+
+static void
+bfin_sport_spi_u8_reader(struct bfin_sport_spi_master_data *drv_data)
+{
+	u16 tx_val = drv_data->cur_chip->idle_tx_val;
+
+	while (drv_data->rx < drv_data->rx_end) {
+		bfin_write(&drv_data->regs->tx16, tx_val);
+		bfin_sport_spi_stat_poll_complete(drv_data);
+		*drv_data->rx8++ = bfin_read(&drv_data->regs->rx16);
+	}
+}
+
+static void
+bfin_sport_spi_u8_duplex(struct bfin_sport_spi_master_data *drv_data)
+{
+	while (drv_data->rx < drv_data->rx_end) {
+		bfin_write(&drv_data->regs->tx16, *drv_data->tx8++);
+		bfin_sport_spi_stat_poll_complete(drv_data);
+		*drv_data->rx8++ = bfin_read(&drv_data->regs->rx16);
+	}
+}
+
+static struct bfin_sport_transfer_ops bfin_sport_transfer_ops_u8 = {
+	.write  = bfin_sport_spi_u8_writer,
+	.read   = bfin_sport_spi_u8_reader,
+	.duplex = bfin_sport_spi_u8_duplex,
+};
+
+static void
+bfin_sport_spi_u16_writer(struct bfin_sport_spi_master_data *drv_data)
+{
+	u16 dummy;
+
+	while (drv_data->tx < drv_data->tx_end) {
+		bfin_write(&drv_data->regs->tx16, *drv_data->tx16++);
+		bfin_sport_spi_stat_poll_complete(drv_data);
+		dummy = bfin_read(&drv_data->regs->rx16);
+	}
+}
+
+static void
+bfin_sport_spi_u16_reader(struct bfin_sport_spi_master_data *drv_data)
+{
+	u16 tx_val = drv_data->cur_chip->idle_tx_val;
+
+	while (drv_data->rx < drv_data->rx_end) {
+		bfin_write(&drv_data->regs->tx16, tx_val);
+		bfin_sport_spi_stat_poll_complete(drv_data);
+		*drv_data->rx16++ = bfin_read(&drv_data->regs->rx16);
+	}
+}
+
+static void
+bfin_sport_spi_u16_duplex(struct bfin_sport_spi_master_data *drv_data)
+{
+	while (drv_data->rx < drv_data->rx_end) {
+		bfin_write(&drv_data->regs->tx16, *drv_data->tx16++);
+		bfin_sport_spi_stat_poll_complete(drv_data);
+		*drv_data->rx16++ = bfin_read(&drv_data->regs->rx16);
+	}
+}
+
+static struct bfin_sport_transfer_ops bfin_sport_transfer_ops_u16 = {
+	.write  = bfin_sport_spi_u16_writer,
+	.read   = bfin_sport_spi_u16_reader,
+	.duplex = bfin_sport_spi_u16_duplex,
+};
+
+/* stop controller and re-config current chip */
+static void
+bfin_sport_spi_restore_state(struct bfin_sport_spi_master_data *drv_data)
+{
+	struct bfin_sport_spi_slave_data *chip = drv_data->cur_chip;
+	unsigned int bits = (drv_data->ops == &bfin_sport_transfer_ops_u8 ? 7 : 15);
+
+	bfin_sport_spi_disable(drv_data);
+	dev_dbg(drv_data->dev, "restoring spi ctl state\n");
+
+	bfin_write(&drv_data->regs->tcr1, chip->ctl_reg);
+	bfin_write(&drv_data->regs->tcr2, bits);
+	bfin_write(&drv_data->regs->tclkdiv, chip->baud);
+	bfin_write(&drv_data->regs->tfsdiv, bits);
+	SSYNC();
+
+	bfin_write(&drv_data->regs->rcr1, chip->ctl_reg & ~(ITCLK | ITFS));
+	bfin_write(&drv_data->regs->rcr2, bits);
+	SSYNC();
+
+	bfin_sport_spi_cs_active(chip);
+}
+
+/* test if there is more transfer to be done */
+static enum bfin_sport_spi_state
+bfin_sport_spi_next_transfer(struct bfin_sport_spi_master_data *drv_data)
+{
+	struct spi_message *msg = drv_data->cur_msg;
+	struct spi_transfer *trans = drv_data->cur_transfer;
+
+	/* Move to next transfer */
+	if (trans->transfer_list.next != &msg->transfers) {
+		drv_data->cur_transfer =
+		    list_entry(trans->transfer_list.next,
+			       struct spi_transfer, transfer_list);
+		return RUNNING_STATE;
+	}
+
+	return DONE_STATE;
+}
+
+/*
+ * caller already set message->status;
+ * dma and pio irqs are blocked give finished message back
+ */
+static void
+bfin_sport_spi_giveback(struct bfin_sport_spi_master_data *drv_data)
+{
+	struct bfin_sport_spi_slave_data *chip = drv_data->cur_chip;
+	unsigned long flags;
+	struct spi_message *msg;
+
+	spin_lock_irqsave(&drv_data->lock, flags);
+	msg = drv_data->cur_msg;
+	drv_data->state = START_STATE;
+	drv_data->cur_msg = NULL;
+	drv_data->cur_transfer = NULL;
+	drv_data->cur_chip = NULL;
+	queue_work(drv_data->workqueue, &drv_data->pump_messages);
+	spin_unlock_irqrestore(&drv_data->lock, flags);
+
+	if (!drv_data->cs_change)
+		bfin_sport_spi_cs_deactive(chip);
+
+	if (msg->complete)
+		msg->complete(msg->context);
+}
+
+static irqreturn_t
+sport_err_handler(int irq, void *dev_id)
+{
+	struct bfin_sport_spi_master_data *drv_data = dev_id;
+	u16 status;
+
+	dev_dbg(drv_data->dev, "%s enter\n", __func__);
+	status = bfin_read(&drv_data->regs->stat) & (TOVF | TUVF | ROVF | RUVF);
+
+	if (status) {
+		bfin_write(&drv_data->regs->stat, status);
+		SSYNC();
+
+		bfin_sport_spi_disable(drv_data);
+		dev_err(drv_data->dev, "status error:%s%s%s%s\n",
+			status & TOVF ? " TOVF" : "",
+			status & TUVF ? " TUVF" : "",
+			status & ROVF ? " ROVF" : "",
+			status & RUVF ? " RUVF" : "");
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void
+bfin_sport_spi_pump_transfers(unsigned long data)
+{
+	struct bfin_sport_spi_master_data *drv_data = (void *)data;
+	struct spi_message *message = NULL;
+	struct spi_transfer *transfer = NULL;
+	struct spi_transfer *previous = NULL;
+	struct bfin_sport_spi_slave_data *chip = NULL;
+	unsigned int bits_per_word;
+	u32 tranf_success = 1;
+	u32 transfer_speed;
+	u8 full_duplex = 0;
+
+	/* Get current state information */
+	message = drv_data->cur_msg;
+	transfer = drv_data->cur_transfer;
+	chip = drv_data->cur_chip;
+
+	if (transfer->speed_hz)
+		transfer_speed = bfin_sport_hz_to_spi_baud(transfer->speed_hz);
+	else
+		transfer_speed = chip->baud;
+	bfin_write(&drv_data->regs->tclkdiv, transfer_speed);
+	SSYNC();
+
+	/*
+	 * if msg is error or done, report it back using complete() callback
+	 */
+
+	 /* Handle for abort */
+	if (drv_data->state == ERROR_STATE) {
+		dev_dbg(drv_data->dev, "transfer: we've hit an error\n");
+		message->status = -EIO;
+		bfin_sport_spi_giveback(drv_data);
+		return;
+	}
+
+	/* Handle end of message */
+	if (drv_data->state == DONE_STATE) {
+		dev_dbg(drv_data->dev, "transfer: all done!\n");
+		message->status = 0;
+		bfin_sport_spi_giveback(drv_data);
+		return;
+	}
+
+	/* Delay if requested at end of transfer */
+	if (drv_data->state == RUNNING_STATE) {
+		dev_dbg(drv_data->dev, "transfer: still running ...\n");
+		previous = list_entry(transfer->transfer_list.prev,
+				      struct spi_transfer, transfer_list);
+		if (previous->delay_usecs)
+			udelay(previous->delay_usecs);
+	}
+
+	if (transfer->len == 0) {
+		/* Move to next transfer of this msg */
+		drv_data->state = bfin_sport_spi_next_transfer(drv_data);
+		/* Schedule next transfer tasklet */
+		tasklet_schedule(&drv_data->pump_transfers);
+	}
+
+	if (transfer->tx_buf != NULL) {
+		drv_data->tx = (void *)transfer->tx_buf;
+		drv_data->tx_end = drv_data->tx + transfer->len;
+		dev_dbg(drv_data->dev, "tx_buf is %p, tx_end is %p\n",
+			transfer->tx_buf, drv_data->tx_end);
+	} else
+		drv_data->tx = NULL;
+
+	if (transfer->rx_buf != NULL) {
+		full_duplex = transfer->tx_buf != NULL;
+		drv_data->rx = transfer->rx_buf;
+		drv_data->rx_end = drv_data->rx + transfer->len;
+		dev_dbg(drv_data->dev, "rx_buf is %p, rx_end is %p\n",
+			transfer->rx_buf, drv_data->rx_end);
+	} else
+		drv_data->rx = NULL;
+
+	drv_data->cs_change = transfer->cs_change;
+
+	/* Bits per word setup */
+	bits_per_word = transfer->bits_per_word ? : message->spi->bits_per_word;
+	if (bits_per_word == 8)
+		drv_data->ops = &bfin_sport_transfer_ops_u8;
+	else
+		drv_data->ops = &bfin_sport_transfer_ops_u16;
+
+	drv_data->state = RUNNING_STATE;
+
+	if (drv_data->cs_change)
+		bfin_sport_spi_cs_active(chip);
+
+	dev_dbg(drv_data->dev,
+		"now pumping a transfer: width is %d, len is %d\n",
+		bits_per_word, transfer->len);
+
+	/* PIO mode write then read */
+	dev_dbg(drv_data->dev, "doing IO transfer\n");
+
+	bfin_sport_spi_enable(drv_data);
+	if (full_duplex) {
+		/* full duplex mode */
+		BUG_ON((drv_data->tx_end - drv_data->tx) !=
+		       (drv_data->rx_end - drv_data->rx));
+		drv_data->ops->duplex(drv_data);
+
+		if (drv_data->tx != drv_data->tx_end)
+			tranf_success = 0;
+	} else if (drv_data->tx != NULL) {
+		/* write only half duplex */
+
+		drv_data->ops->write(drv_data);
+
+		if (drv_data->tx != drv_data->tx_end)
+			tranf_success = 0;
+	} else if (drv_data->rx != NULL) {
+		/* read only half duplex */
+
+		drv_data->ops->read(drv_data);
+		if (drv_data->rx != drv_data->rx_end)
+			tranf_success = 0;
+	}
+	bfin_sport_spi_disable(drv_data);
+
+	if (!tranf_success) {
+		dev_dbg(drv_data->dev, "IO write error!\n");
+		drv_data->state = ERROR_STATE;
+	} else {
+		/* Update total byte transfered */
+		message->actual_length += transfer->len;
+		/* Move to next transfer of this msg */
+		drv_data->state = bfin_sport_spi_next_transfer(drv_data);
+		if (drv_data->cs_change)
+			bfin_sport_spi_cs_deactive(chip);
+	}
+
+	/* Schedule next transfer tasklet */
+	tasklet_schedule(&drv_data->pump_transfers);
+}
+
+/* pop a msg from queue and kick off real transfer */
+static void
+bfin_sport_spi_pump_messages(struct work_struct *work)
+{
+	struct bfin_sport_spi_master_data *drv_data;
+	unsigned long flags;
+	struct spi_message *next_msg;
+
+	drv_data = container_of(work, struct bfin_sport_spi_master_data, pump_messages);
+
+	/* Lock queue and check for queue work */
+	spin_lock_irqsave(&drv_data->lock, flags);
+	if (list_empty(&drv_data->queue) || !drv_data->run) {
+		/* pumper kicked off but no work to do */
+		drv_data->busy = 0;
+		spin_unlock_irqrestore(&drv_data->lock, flags);
+		return;
+	}
+
+	/* Make sure we are not already running a message */
+	if (drv_data->cur_msg) {
+		spin_unlock_irqrestore(&drv_data->lock, flags);
+		return;
+	}
+
+	/* Extract head of queue */
+	next_msg = list_entry(drv_data->queue.next,
+		struct spi_message, queue);
+
+	drv_data->cur_msg = next_msg;
+
+	/* Setup the SSP using the per chip configuration */
+	drv_data->cur_chip = spi_get_ctldata(drv_data->cur_msg->spi);
+
+	list_del_init(&drv_data->cur_msg->queue);
+
+	/* Initialize message state */
+	drv_data->cur_msg->state = START_STATE;
+	drv_data->cur_transfer = list_entry(drv_data->cur_msg->transfers.next,
+					    struct spi_transfer, transfer_list);
+	bfin_sport_spi_restore_state(drv_data);
+	dev_dbg(drv_data->dev, "got a message to pump, "
+		"state is set to: baud %d, cs_gpio %i, ctl 0x%x\n",
+		drv_data->cur_chip->baud, drv_data->cur_chip->cs_gpio,
+		drv_data->cur_chip->ctl_reg);
+
+	dev_dbg(drv_data->dev,
+		"the first transfer len is %d\n",
+		drv_data->cur_transfer->len);
+
+	/* Mark as busy and launch transfers */
+	tasklet_schedule(&drv_data->pump_transfers);
+
+	drv_data->busy = 1;
+	spin_unlock_irqrestore(&drv_data->lock, flags);
+}
+
+/*
+ * got a msg to transfer, queue it in drv_data->queue.
+ * And kick off message pumper
+ */
+static int
+bfin_sport_spi_transfer(struct spi_device *spi, struct spi_message *msg)
+{
+	struct bfin_sport_spi_master_data *drv_data = spi_master_get_devdata(spi->master);
+	unsigned long flags;
+
+	spin_lock_irqsave(&drv_data->lock, flags);
+
+	if (!drv_data->run) {
+		spin_unlock_irqrestore(&drv_data->lock, flags);
+		return -ESHUTDOWN;
+	}
+
+	msg->actual_length = 0;
+	msg->status = -EINPROGRESS;
+	msg->state = START_STATE;
+
+	dev_dbg(&spi->dev, "adding an msg in transfer()\n");
+	list_add_tail(&msg->queue, &drv_data->queue);
+
+	if (drv_data->run && !drv_data->busy)
+		queue_work(drv_data->workqueue, &drv_data->pump_messages);
+
+	spin_unlock_irqrestore(&drv_data->lock, flags);
+
+	return 0;
+}
+
+/* Called every time common spi devices change state */
+static int
+bfin_sport_spi_setup(struct spi_device *spi)
+{
+	struct bfin_sport_spi_slave_data *chip, *first = NULL;
+	int ret;
+
+	/* Only alloc (or use chip_info) on first setup */
+	chip = spi_get_ctldata(spi);
+	if (chip == NULL) {
+		struct bfin5xx_spi_chip *chip_info;
+
+		chip = first = kzalloc(sizeof(*chip), GFP_KERNEL);
+		if (!chip)
+			return -ENOMEM;
+
+		/* platform chip_info isn't required */
+		chip_info = spi->controller_data;
+		if (chip_info) {
+			/*
+			 * DITFS and TDTYPE are only thing we don't set, but
+			 * they probably shouldn't be changed by people.
+			 */
+			if (chip_info->ctl_reg || chip_info->enable_dma) {
+				ret = -EINVAL;
+				dev_err(&spi->dev, "don't set ctl_reg/enable_dma fields");
+				goto error;
+			}
+			chip->cs_chg_udelay = chip_info->cs_chg_udelay;
+			chip->idle_tx_val = chip_info->idle_tx_val;
+			spi->bits_per_word = chip_info->bits_per_word;
+		}
+	}
+
+	if (spi->bits_per_word != 8 && spi->bits_per_word != 16) {
+		ret = -EINVAL;
+		goto error;
+	}
+
+	/* translate common spi framework into our register
+	 * following configure contents are same for tx and rx.
+	 */
+
+	if (spi->mode & SPI_CPHA)
+		chip->ctl_reg &= ~TCKFE;
+	else
+		chip->ctl_reg |= TCKFE;
+
+	if (spi->mode & SPI_LSB_FIRST)
+		chip->ctl_reg |= TLSBIT;
+	else
+		chip->ctl_reg &= ~TLSBIT;
+
+	/* Sport in master mode */
+	chip->ctl_reg |= ITCLK | ITFS | TFSR | LATFS | LTFS;
+
+	chip->baud = bfin_sport_hz_to_spi_baud(spi->max_speed_hz);
+
+	chip->cs_gpio = spi->chip_select;
+	ret = gpio_request(chip->cs_gpio, spi->modalias);
+	if (ret)
+		goto error;
+
+	dev_dbg(&spi->dev, "setup spi chip %s, width is %d\n",
+			spi->modalias, spi->bits_per_word);
+	dev_dbg(&spi->dev, "ctl_reg is 0x%x, GPIO is %i\n",
+			chip->ctl_reg, spi->chip_select);
+
+	spi_set_ctldata(spi, chip);
+
+	bfin_sport_spi_cs_deactive(chip);
+
+	return ret;
+
+ error:
+	kfree(first);
+	return ret;
+}
+
+/*
+ * callback for spi framework.
+ * clean driver specific data
+ */
+static void
+bfin_sport_spi_cleanup(struct spi_device *spi)
+{
+	struct bfin_sport_spi_slave_data *chip = spi_get_ctldata(spi);
+
+	if (!chip)
+		return;
+
+	gpio_free(chip->cs_gpio);
+
+	kfree(chip);
+}
+
+static int
+bfin_sport_spi_init_queue(struct bfin_sport_spi_master_data *drv_data)
+{
+	INIT_LIST_HEAD(&drv_data->queue);
+	spin_lock_init(&drv_data->lock);
+
+	drv_data->run = false;
+	drv_data->busy = 0;
+
+	/* init transfer tasklet */
+	tasklet_init(&drv_data->pump_transfers,
+		     bfin_sport_spi_pump_transfers, (unsigned long)drv_data);
+
+	/* init messages workqueue */
+	INIT_WORK(&drv_data->pump_messages, bfin_sport_spi_pump_messages);
+	drv_data->workqueue =
+	    create_singlethread_workqueue(dev_name(drv_data->master->dev.parent));
+	if (drv_data->workqueue == NULL)
+		return -EBUSY;
+
+	return 0;
+}
+
+static int
+bfin_sport_spi_start_queue(struct bfin_sport_spi_master_data *drv_data)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&drv_data->lock, flags);
+
+	if (drv_data->run || drv_data->busy) {
+		spin_unlock_irqrestore(&drv_data->lock, flags);
+		return -EBUSY;
+	}
+
+	drv_data->run = true;
+	drv_data->cur_msg = NULL;
+	drv_data->cur_transfer = NULL;
+	drv_data->cur_chip = NULL;
+	spin_unlock_irqrestore(&drv_data->lock, flags);
+
+	queue_work(drv_data->workqueue, &drv_data->pump_messages);
+
+	return 0;
+}
+
+static inline int
+bfin_sport_spi_stop_queue(struct bfin_sport_spi_master_data *drv_data)
+{
+	unsigned long flags;
+	unsigned limit = 500;
+	int status = 0;
+
+	spin_lock_irqsave(&drv_data->lock, flags);
+
+	/*
+	 * This is a bit lame, but is optimized for the common execution path.
+	 * A wait_queue on the drv_data->busy could be used, but then the common
+	 * execution path (pump_messages) would be required to call wake_up or
+	 * friends on every SPI message. Do this instead
+	 */
+	drv_data->run = false;
+	while (!list_empty(&drv_data->queue) && drv_data->busy && limit--) {
+		spin_unlock_irqrestore(&drv_data->lock, flags);
+		msleep(10);
+		spin_lock_irqsave(&drv_data->lock, flags);
+	}
+
+	if (!list_empty(&drv_data->queue) || drv_data->busy)
+		status = -EBUSY;
+
+	spin_unlock_irqrestore(&drv_data->lock, flags);
+
+	return status;
+}
+
+static inline int
+bfin_sport_spi_destroy_queue(struct bfin_sport_spi_master_data *drv_data)
+{
+	int status;
+
+	status = bfin_sport_spi_stop_queue(drv_data);
+	if (status)
+		return status;
+
+	destroy_workqueue(drv_data->workqueue);
+
+	return 0;
+}
+
+static int __devinit
+bfin_sport_spi_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct bfin5xx_spi_master *platform_info;
+	struct spi_master *master;
+	struct resource *res, *ires;
+	struct bfin_sport_spi_master_data *drv_data;
+	int status;
+
+	platform_info = dev->platform_data;
+
+	/* Allocate master with space for drv_data */
+	master = spi_alloc_master(dev, sizeof(*master) + 16);
+	if (!master) {
+		dev_err(dev, "cannot alloc spi_master\n");
+		return -ENOMEM;
+	}
+
+	drv_data = spi_master_get_devdata(master);
+	drv_data->master = master;
+	drv_data->dev = dev;
+	drv_data->pin_req = platform_info->pin_req;
+
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST;
+	master->bus_num = pdev->id;
+	master->num_chipselect = platform_info->num_chipselect;
+	master->cleanup = bfin_sport_spi_cleanup;
+	master->setup = bfin_sport_spi_setup;
+	master->transfer = bfin_sport_spi_transfer;
+
+	/* Find and map our resources */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (res == NULL) {
+		dev_err(dev, "cannot get IORESOURCE_MEM\n");
+		status = -ENOENT;
+		goto out_error_get_res;
+	}
+
+	drv_data->regs = ioremap(res->start, resource_size(res));
+	if (drv_data->regs == NULL) {
+		dev_err(dev, "cannot map registers\n");
+		status = -ENXIO;
+		goto out_error_ioremap;
+	}
+
+	ires = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!ires) {
+		dev_err(dev, "cannot get IORESOURCE_IRQ\n");
+		status = -ENODEV;
+		goto out_error_get_ires;
+	}
+	drv_data->err_irq = ires->start;
+
+	/* Initial and start queue */
+	status = bfin_sport_spi_init_queue(drv_data);
+	if (status) {
+		dev_err(dev, "problem initializing queue\n");
+		goto out_error_queue_alloc;
+	}
+
+	status = bfin_sport_spi_start_queue(drv_data);
+	if (status) {
+		dev_err(dev, "problem starting queue\n");
+		goto out_error_queue_alloc;
+	}
+
+	status = request_irq(drv_data->err_irq, sport_err_handler,
+		0, "sport_spi_err", drv_data);
+	if (status) {
+		dev_err(dev, "unable to request sport err irq\n");
+		goto out_error_irq;
+	}
+
+	status = peripheral_request_list(drv_data->pin_req, DRV_NAME);
+	if (status) {
+		dev_err(dev, "requesting peripherals failed\n");
+		goto out_error_peripheral;
+	}
+
+	/* Register with the SPI framework */
+	platform_set_drvdata(pdev, drv_data);
+	status = spi_register_master(master);
+	if (status) {
+		dev_err(dev, "problem registering spi master\n");
+		goto out_error_master;
+	}
+
+	dev_info(dev, "%s, regs_base@%p\n", DRV_DESC, drv_data->regs);
+	return 0;
+
+ out_error_master:
+	peripheral_free_list(drv_data->pin_req);
+ out_error_peripheral:
+	free_irq(drv_data->err_irq, drv_data);
+ out_error_irq:
+ out_error_queue_alloc:
+	bfin_sport_spi_destroy_queue(drv_data);
+ out_error_get_ires:
+	iounmap(drv_data->regs);
+ out_error_ioremap:
+ out_error_get_res:
+	spi_master_put(master);
+
+	return status;
+}
+
+/* stop hardware and remove the driver */
+static int __devexit
+bfin_sport_spi_remove(struct platform_device *pdev)
+{
+	struct bfin_sport_spi_master_data *drv_data = platform_get_drvdata(pdev);
+	int status = 0;
+
+	if (!drv_data)
+		return 0;
+
+	/* Remove the queue */
+	status = bfin_sport_spi_destroy_queue(drv_data);
+	if (status)
+		return status;
+
+	/* Disable the SSP at the peripheral and SOC level */
+	bfin_sport_spi_disable(drv_data);
+
+	/* Disconnect from the SPI framework */
+	spi_unregister_master(drv_data->master);
+
+	peripheral_free_list(drv_data->pin_req);
+
+	/* Prevent double remove */
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int
+bfin_sport_spi_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	struct bfin_sport_spi_master_data *drv_data = platform_get_drvdata(pdev);
+	int status;
+
+	status = bfin_sport_spi_stop_queue(drv_data);
+	if (status)
+		return status;
+
+	/* stop hardware */
+	bfin_sport_spi_disable(drv_data);
+
+	return status;
+}
+
+static int
+bfin_sport_spi_resume(struct platform_device *pdev)
+{
+	struct bfin_sport_spi_master_data *drv_data = platform_get_drvdata(pdev);
+	int status;
+
+	/* Enable the SPI interface */
+	bfin_sport_spi_enable(drv_data);
+
+	/* Start the queue running */
+	status = bfin_sport_spi_start_queue(drv_data);
+	if (status)
+		dev_err(drv_data->dev, "problem resuming queue\n");
+
+	return status;
+}
+#else
+# define bfin_sport_spi_suspend NULL
+# define bfin_sport_spi_resume  NULL
+#endif
+
+static struct platform_driver bfin_sport_spi_driver = {
+	.driver	= {
+		.name = DRV_NAME,
+		.owner = THIS_MODULE,
+	},
+	.probe   = bfin_sport_spi_probe,
+	.remove  = __devexit_p(bfin_sport_spi_remove),
+	.suspend = bfin_sport_spi_suspend,
+	.resume  = bfin_sport_spi_resume,
+};
+
+static int __init bfin_sport_spi_init(void)
+{
+	return platform_driver_register(&bfin_sport_spi_driver);
+}
+module_init(bfin_sport_spi_init);
+
+static void __exit bfin_sport_spi_exit(void)
+{
+	platform_driver_unregister(&bfin_sport_spi_driver);
+}
+module_exit(bfin_sport_spi_exit);
diff --git a/drivers/spi/tle62x0.c b/drivers/spi/tle62x0.c
index a3938958147c..32a40876532f 100644
--- a/drivers/spi/tle62x0.c
+++ b/drivers/spi/tle62x0.c
@@ -283,7 +283,7 @@ static int __devinit tle62x0_probe(struct spi_device *spi)
 	return 0;
 
  err_gpios:
-	for (; ptr > 0; ptr--)
+	while (--ptr >= 0)
 		device_remove_file(&spi->dev, gpio_attrs[ptr]);
 
 	device_remove_file(&spi->dev, &dev_attr_status_show);
@@ -301,6 +301,7 @@ static int __devexit tle62x0_remove(struct spi_device *spi)
 	for (ptr = 0; ptr < st->nr_gpio; ptr++)
 		device_remove_file(&spi->dev, gpio_attrs[ptr]);
 
+	device_remove_file(&spi->dev, &dev_attr_status_show);
 	kfree(st);
 	return 0;
 }
diff --git a/drivers/ssb/driver_pcicore.c b/drivers/ssb/driver_pcicore.c
index 82feb348c8bb..2a20dabec76d 100644
--- a/drivers/ssb/driver_pcicore.c
+++ b/drivers/ssb/driver_pcicore.c
@@ -539,10 +539,12 @@ void ssb_pcicore_init(struct ssb_pcicore *pc)
 	if (!pc->hostmode)
 		ssb_pcicore_init_clientmode(pc);
 
-	/* Additional always once-executed workarounds */
-	ssb_pcicore_serdes_workaround(pc);
-	/* TODO: ASPM */
-	/* TODO: Clock Request Update */
+	/* Additional PCIe always once-executed workarounds */
+	if (dev->id.coreid == SSB_DEV_PCIE) {
+		ssb_pcicore_serdes_workaround(pc);
+		/* TODO: ASPM */
+		/* TODO: Clock Request Update */
+	}
 }
 
 static u32 ssb_pcie_read(struct ssb_pcicore *pc, u32 address)
diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index dfc16f955eb8..196284dc2f36 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -24,23 +24,6 @@ menuconfig STAGING
 
 if STAGING
 
-config STAGING_EXCLUDE_BUILD
-	bool "Exclude Staging drivers from being built" if STAGING
-	default y
-	---help---
-	  Are you sure you really want to build the staging drivers?
-	  They taint your kernel, don't live up to the normal Linux
-	  kernel quality standards, are a bit crufty around the edges,
-	  and might go off and kick your dog when you aren't paying
-	  attention.
-
-	  Say N here to be able to select and build the Staging drivers.
-	  This option is primarily here to prevent them from being built
-	  when selecting 'make allyesconfg' and 'make allmodconfig' so
-	  don't be all that put off, your dog will be just fine.
-
-if !STAGING_EXCLUDE_BUILD
-
 source "drivers/staging/tty/Kconfig"
 
 source "drivers/staging/generic_serial/Kconfig"
@@ -177,5 +160,4 @@ source "drivers/staging/mei/Kconfig"
 
 source "drivers/staging/nvec/Kconfig"
 
-endif # !STAGING_EXCLUDE_BUILD
 endif # STAGING
diff --git a/drivers/staging/altera-stapl/altera-jtag.c b/drivers/staging/altera-stapl/altera-jtag.c
index 876308858b82..8b1620b1b2d0 100644
--- a/drivers/staging/altera-stapl/altera-jtag.c
+++ b/drivers/staging/altera-stapl/altera-jtag.c
@@ -26,7 +26,7 @@
 #include <linux/delay.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
-#include <staging/altera.h>
+#include "altera.h"
 #include "altera-exprt.h"
 #include "altera-jtag.h"
 
diff --git a/drivers/staging/altera-stapl/altera.c b/drivers/staging/altera-stapl/altera.c
index 05aad351b120..9cd5e76880c0 100644
--- a/drivers/staging/altera-stapl/altera.c
+++ b/drivers/staging/altera-stapl/altera.c
@@ -28,7 +28,7 @@
 #include <linux/string.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
-#include <staging/altera.h>
+#include "altera.h"
 #include "altera-exprt.h"
 #include "altera-jtag.h"
 
diff --git a/include/staging/altera.h b/drivers/staging/altera-stapl/altera.h
index 94c0c6181daf..94c0c6181daf 100644
--- a/include/staging/altera.h
+++ b/drivers/staging/altera-stapl/altera.h
diff --git a/drivers/staging/ath6kl/Kconfig b/drivers/staging/ath6kl/Kconfig
index 1f15e1fb1ab2..afd6cc16a2b8 100644
--- a/drivers/staging/ath6kl/Kconfig
+++ b/drivers/staging/ath6kl/Kconfig
@@ -1,6 +1,7 @@
 config ATH6K_LEGACY
 	tristate "Atheros AR6003 support (non mac80211)"
         depends on MMC && WLAN
+	depends on CFG80211
         select WIRELESS_EXT
         select WEXT_PRIV
 	help
diff --git a/drivers/staging/ath6kl/os/linux/cfg80211.c b/drivers/staging/ath6kl/os/linux/cfg80211.c
index 77dfb4070c1d..d3a774dbb7e8 100644
--- a/drivers/staging/ath6kl/os/linux/cfg80211.c
+++ b/drivers/staging/ath6kl/os/linux/cfg80211.c
@@ -870,7 +870,8 @@ ar6k_cfg80211_scanComplete_event(struct ar6_softc *ar, int status)
     if(ar->scan_request)
     {
         /* Translate data to cfg80211 mgmt format */
-        wmi_iterate_nodes(ar->arWmi, ar6k_cfg80211_scan_node, ar->wdev->wiphy);
+	if (ar->arWmi)
+		wmi_iterate_nodes(ar->arWmi, ar6k_cfg80211_scan_node, ar->wdev->wiphy);
 
         cfg80211_scan_done(ar->scan_request,
             ((status & A_ECANCELED) || (status & A_EBUSY)) ? true : false);
diff --git a/drivers/staging/brcm80211/brcmfmac/wl_iw.c b/drivers/staging/brcm80211/brcmfmac/wl_iw.c
index 929ceaf363be..15e1b05ca92d 100644
--- a/drivers/staging/brcm80211/brcmfmac/wl_iw.c
+++ b/drivers/staging/brcm80211/brcmfmac/wl_iw.c
@@ -64,8 +64,6 @@ wl_iw_extra_params_t g_wl_iw_params;
 extern bool wl_iw_conn_status_str(u32 event_type, u32 status,
 				  u32 reason, char *stringBuf, uint buflen);
 
-uint wl_msg_level = WL_ERROR_VAL;
-
 #define MAX_WLIW_IOCTL_LEN 1024
 
 #ifdef CONFIG_WIRELESS_EXT
diff --git a/drivers/staging/gma500/psb_drv.c b/drivers/staging/gma500/psb_drv.c
index 1c45c11a774e..aa87b1b6a44a 100644
--- a/drivers/staging/gma500/psb_drv.c
+++ b/drivers/staging/gma500/psb_drv.c
@@ -542,6 +542,8 @@ static int psb_driver_load(struct drm_device *dev, unsigned long chipset)
 	unsigned long irqflags;
 	int ret = -ENOMEM;
 	uint32_t tt_pages;
+	struct drm_connector *connector;
+	struct psb_intel_output *psb_intel_output;
 
 	dev_priv = kzalloc(sizeof(*dev_priv), GFP_KERNEL);
 	if (dev_priv == NULL)
@@ -663,7 +665,18 @@ static int psb_driver_load(struct drm_device *dev, unsigned long chipset)
 		drm_kms_helper_poll_init(dev);
 	}
 
-	ret = psb_backlight_init(dev);
+	/* Only add backlight support if we have LVDS output */
+	list_for_each_entry(connector, &dev->mode_config.connector_list,
+			    head) {
+		psb_intel_output = to_psb_intel_output(connector);
+
+		switch (psb_intel_output->type) {
+		case INTEL_OUTPUT_LVDS:
+			ret = psb_backlight_init(dev);
+			break;
+		}
+	}
+
 	if (ret)
 		return ret;
 #if 0
diff --git a/drivers/staging/gma500/psb_fb.c b/drivers/staging/gma500/psb_fb.c
index 99c03a2e06bd..084c36bbfe86 100644
--- a/drivers/staging/gma500/psb_fb.c
+++ b/drivers/staging/gma500/psb_fb.c
@@ -441,6 +441,16 @@ static int psbfb_create(struct psb_fbdev *fbdev,
 	info->screen_size = size;
 	memset(info->screen_base, 0, size);
 
+	if (dev_priv->pg->stolen_size) {
+		info->apertures = alloc_apertures(1);
+		if (!info->apertures) {
+			ret = -ENOMEM;
+			goto out_err0;
+		}
+		info->apertures->ranges[0].base = dev->mode_config.fb_base;
+		info->apertures->ranges[0].size = dev_priv->pg->stolen_size;
+	}
+
 	drm_fb_helper_fill_fix(info, fb->pitch, fb->depth);
 	drm_fb_helper_fill_var(info, &fbdev->psb_fb_helper,
 				sizes->fb_width, sizes->fb_height);
diff --git a/drivers/staging/gma500/psb_intel_bios.c b/drivers/staging/gma500/psb_intel_bios.c
index 48ac8ba7f40b..417965da5e24 100644
--- a/drivers/staging/gma500/psb_intel_bios.c
+++ b/drivers/staging/gma500/psb_intel_bios.c
@@ -154,10 +154,15 @@ static void parse_lfp_panel_data(struct drm_psb_private *dev_priv,
 
 	fill_detail_timing_data(panel_fixed_mode, dvo_timing);
 
-	dev_priv->lfp_lvds_vbt_mode = panel_fixed_mode;
-
-	DRM_DEBUG("Found panel mode in BIOS VBT tables:\n");
-	drm_mode_debug_printmodeline(panel_fixed_mode);
+	if (panel_fixed_mode->htotal > 0 && panel_fixed_mode->vtotal > 0) {
+		dev_priv->lfp_lvds_vbt_mode = panel_fixed_mode;
+		DRM_DEBUG("Found panel mode in BIOS VBT tables:\n");
+		drm_mode_debug_printmodeline(panel_fixed_mode);
+	} else {
+		DRM_DEBUG("Ignoring bogus LVDS VBT mode.\n");
+		dev_priv->lvds_vbt = 0;
+		kfree(panel_fixed_mode);
+	}
 
 	return;
 }
diff --git a/drivers/staging/iio/accel/adis16201.h b/drivers/staging/iio/accel/adis16201.h
index 0b9b85424dfa..4cc1a5bfab40 100644
--- a/drivers/staging/iio/accel/adis16201.h
+++ b/drivers/staging/iio/accel/adis16201.h
@@ -81,7 +81,6 @@ struct adis16201_state {
 
 int adis16201_set_irq(struct iio_dev *indio_dev, bool enable);
 
-#ifdef CONFIG_IIO_RING_BUFFER
 enum adis16201_scan {
 	ADIS16201_SCAN_SUPPLY,
 	ADIS16201_SCAN_ACC_X,
@@ -92,6 +91,7 @@ enum adis16201_scan {
 	ADIS16201_SCAN_INCLI_Y,
 };
 
+#ifdef CONFIG_IIO_RING_BUFFER
 void adis16201_remove_trigger(struct iio_dev *indio_dev);
 int adis16201_probe_trigger(struct iio_dev *indio_dev);
 
diff --git a/drivers/staging/iio/accel/adis16203.h b/drivers/staging/iio/accel/adis16203.h
index 8bb8ce50c248..175e21bb9b40 100644
--- a/drivers/staging/iio/accel/adis16203.h
+++ b/drivers/staging/iio/accel/adis16203.h
@@ -76,7 +76,6 @@ struct adis16203_state {
 
 int adis16203_set_irq(struct iio_dev *indio_dev, bool enable);
 
-#ifdef CONFIG_IIO_RING_BUFFER
 enum adis16203_scan {
 	ADIS16203_SCAN_SUPPLY,
 	ADIS16203_SCAN_AUX_ADC,
@@ -85,6 +84,7 @@ enum adis16203_scan {
 	ADIS16203_SCAN_INCLI_Y,
 };
 
+#ifdef CONFIG_IIO_RING_BUFFER
 void adis16203_remove_trigger(struct iio_dev *indio_dev);
 int adis16203_probe_trigger(struct iio_dev *indio_dev);
 
diff --git a/drivers/staging/iio/dac/max517.c b/drivers/staging/iio/dac/max517.c
index 881768df47a6..2fe34d21b6aa 100644
--- a/drivers/staging/iio/dac/max517.c
+++ b/drivers/staging/iio/dac/max517.c
@@ -195,7 +195,7 @@ static const struct iio_info max517_info = {
 };
 
 static const struct iio_info max518_info = {
-	.attrs = &max517_attribute_group,
+	.attrs = &max518_attribute_group,
 	.driver_module = THIS_MODULE,
 };
 
diff --git a/drivers/staging/iio/imu/adis16400_ring.c b/drivers/staging/iio/imu/adis16400_ring.c
index 2589a7e167e4..3612373ddede 100644
--- a/drivers/staging/iio/imu/adis16400_ring.c
+++ b/drivers/staging/iio/imu/adis16400_ring.c
@@ -137,13 +137,13 @@ static irqreturn_t adis16400_trigger_handler(int irq, void *p)
 		if (st->variant->flags & ADIS16400_NO_BURST) {
 			ret = adis16350_spi_read_all(&indio_dev->dev, st->rx);
 			if (ret < 0)
-				return ret;
+				goto err;
 			for (; i < ring->scan_count; i++)
 				data[i]	= *(s16 *)(st->rx + i*2);
 		} else {
 			ret = adis16400_spi_read_burst(&indio_dev->dev, st->rx);
 			if (ret < 0)
-				return ret;
+				goto err;
 			for (; i < indio_dev->ring->scan_count; i++) {
 				j = __ffs(mask);
 				mask &= ~(1 << j);
@@ -158,9 +158,13 @@ static irqreturn_t adis16400_trigger_handler(int irq, void *p)
 	ring->access->store_to(indio_dev->ring, (u8 *) data, pf->timestamp);
 
 	iio_trigger_notify_done(indio_dev->trig);
-	kfree(data);
 
+	kfree(data);
 	return IRQ_HANDLED;
+
+err:
+	kfree(data);
+	return ret;
 }
 
 void adis16400_unconfigure_ring(struct iio_dev *indio_dev)
diff --git a/drivers/staging/iio/industrialio-trigger.c b/drivers/staging/iio/industrialio-trigger.c
index 615902333fb0..d504aa251ced 100644
--- a/drivers/staging/iio/industrialio-trigger.c
+++ b/drivers/staging/iio/industrialio-trigger.c
@@ -294,6 +294,7 @@ struct iio_poll_func
 	pf->h = h;
 	pf->thread = thread;
 	pf->type = type;
+	pf->private_data = private;
 
 	return pf;
 }
diff --git a/drivers/staging/mei/init.c b/drivers/staging/mei/init.c
index 2818851c0761..d1ffa32cd141 100644
--- a/drivers/staging/mei/init.c
+++ b/drivers/staging/mei/init.c
@@ -205,10 +205,10 @@ int mei_hw_init(struct mei_device *dev)
 			"host_hw_state = 0x%08x, me_hw_state = 0x%08x.\n",
 			dev->host_hw_state, dev->me_hw_state);
 
-		if (!(dev->host_hw_state & H_RDY) != H_RDY)
+		if (!(dev->host_hw_state & H_RDY))
 			dev_dbg(&dev->pdev->dev, "host turn off H_RDY.\n");
 
-		if (!(dev->me_hw_state & ME_RDY_HRA) != ME_RDY_HRA)
+		if (!(dev->me_hw_state & ME_RDY_HRA))
 			dev_dbg(&dev->pdev->dev, "ME turn off ME_RDY.\n");
 
 		printk(KERN_ERR "mei: link layer initialization failed.\n");
diff --git a/drivers/staging/olpc_dcon/Kconfig b/drivers/staging/olpc_dcon/Kconfig
index b05306766870..fe40e0b6f675 100644
--- a/drivers/staging/olpc_dcon/Kconfig
+++ b/drivers/staging/olpc_dcon/Kconfig
@@ -2,6 +2,7 @@ config FB_OLPC_DCON
 	tristate "One Laptop Per Child Display CONtroller support"
 	depends on OLPC && FB
 	select I2C
+	select BACKLIGHT_CLASS_DEVICE
 	---help---
 	  Add support for the OLPC XO DCON controller.  This controller is
 	  only available on OLPC platforms.   Unless you have one of these
diff --git a/drivers/staging/rts_pstor/sd.c b/drivers/staging/rts_pstor/sd.c
index bddb0312b31e..cdae497d5467 100644
--- a/drivers/staging/rts_pstor/sd.c
+++ b/drivers/staging/rts_pstor/sd.c
@@ -2328,7 +2328,7 @@ Switch_Fail:
 
 			retval = sd_send_cmd_get_rsp(chip, IO_SEND_OP_COND, 0, SD_RSP_TYPE_R4, rsp, 5);
 			if (retval == STATUS_SUCCESS) {
-				int func_num = (rsp[1] >> 4) && 0x07;
+				int func_num = (rsp[1] >> 4) & 0x07;
 				if (func_num) {
 					RTSX_DEBUGP("SD_IO card (Function number: %d)!\n", func_num);
 					chip->sd_io = 1;
diff --git a/drivers/staging/usbip/stub_dev.c b/drivers/staging/usbip/stub_dev.c
index 6e99ec87fee0..8cbea42b69bc 100644
--- a/drivers/staging/usbip/stub_dev.c
+++ b/drivers/staging/usbip/stub_dev.c
@@ -26,6 +26,8 @@
 static int stub_probe(struct usb_interface *interface,
 		      const struct usb_device_id *id);
 static void stub_disconnect(struct usb_interface *interface);
+static int stub_pre_reset(struct usb_interface *interface);
+static int stub_post_reset(struct usb_interface *interface);
 
 /*
  * Define device IDs here if you want to explicitly limit exportable devices.
@@ -59,6 +61,8 @@ struct usb_driver stub_driver = {
 	.probe		= stub_probe,
 	.disconnect	= stub_disconnect,
 	.id_table	= stub_table,
+	.pre_reset	= stub_pre_reset,
+	.post_reset	= stub_post_reset,
 };
 
 /*
@@ -541,3 +545,20 @@ static void stub_disconnect(struct usb_interface *interface)
 		del_match_busid((char *)udev_busid);
 	}
 }
+
+/* 
+ * Presence of pre_reset and post_reset prevents the driver from being unbound
+ * when the device is being reset
+ */
+ 
+int stub_pre_reset(struct usb_interface *interface)
+{
+	dev_dbg(&interface->dev, "pre_reset\n");
+	return 0;
+}
+
+int stub_post_reset(struct usb_interface *interface)
+{
+	dev_dbg(&interface->dev, "post_reset\n");
+	return 0;
+}
diff --git a/drivers/staging/usbip/stub_rx.c b/drivers/staging/usbip/stub_rx.c
index a5c1fa1f0430..bc57844600b9 100644
--- a/drivers/staging/usbip/stub_rx.c
+++ b/drivers/staging/usbip/stub_rx.c
@@ -175,16 +175,18 @@ static int tweak_reset_device_cmd(struct urb *urb)
 	dev_info(&urb->dev->dev, "usb_queue_reset_device\n");
 
 	/*
-	 * usb_lock_device_for_reset caused a deadlock: it causes the driver
-	 * to unbind. In the shutdown the rx thread is signalled to shut down
-	 * but this thread is pending in the usb_lock_device_for_reset.
-	 *
-	 * Instead queue the reset.
-	 *
-	 * Unfortunatly an existing usbip connection will be dropped due to
-	 * driver unbinding.
+	 * With the implementation of pre_reset and post_reset the driver no 
+	 * longer unbinds. This allows the use of synchronous reset.
 	 */
-	usb_queue_reset_device(sdev->interface);
+
+	if (usb_lock_device_for_reset(sdev->udev, sdev->interface)<0)
+	{
+		dev_err(&urb->dev->dev, "could not obtain lock to reset device\n");
+		return 0;
+	}
+	usb_reset_device(sdev->udev);
+	usb_unlock_device(sdev->udev);
+
 	return 0;
 }
 
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index aed4e464d31c..70c2e7fa6664 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -31,7 +31,7 @@
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_cmnd.h>
-#include <scsi/libsas.h> /* For TASK_ATTR_* */
+#include <scsi/scsi_tcq.h>
 
 #include <target/target_core_base.h>
 #include <target/target_core_transport.h>
@@ -95,17 +95,17 @@ static struct se_cmd *tcm_loop_allocate_core_cmd(
 	if (sc->device->tagged_supported) {
 		switch (sc->tag) {
 		case HEAD_OF_QUEUE_TAG:
-			sam_task_attr = TASK_ATTR_HOQ;
+			sam_task_attr = MSG_HEAD_TAG;
 			break;
 		case ORDERED_QUEUE_TAG:
-			sam_task_attr = TASK_ATTR_ORDERED;
+			sam_task_attr = MSG_ORDERED_TAG;
 			break;
 		default:
-			sam_task_attr = TASK_ATTR_SIMPLE;
+			sam_task_attr = MSG_SIMPLE_TAG;
 			break;
 		}
 	} else
-		sam_task_attr = TASK_ATTR_SIMPLE;
+		sam_task_attr = MSG_SIMPLE_TAG;
 
 	/*
 	 * Initialize struct se_cmd descriptor from target_core_mod infrastructure
@@ -379,14 +379,14 @@ static int tcm_loop_device_reset(struct scsi_cmnd *sc)
 	 * Initialize struct se_cmd descriptor from target_core_mod infrastructure
 	 */
 	transport_init_se_cmd(se_cmd, se_tpg->se_tpg_tfo, se_sess, 0,
-				DMA_NONE, TASK_ATTR_SIMPLE,
+				DMA_NONE, MSG_SIMPLE_TAG,
 				&tl_cmd->tl_sense_buf[0]);
 	/*
 	 * Allocate the LUN_RESET TMR
 	 */
 	se_cmd->se_tmr_req = core_tmr_alloc_req(se_cmd, (void *)tl_tmr,
 				TMR_LUN_RESET);
-	if (!se_cmd->se_tmr_req)
+	if (IS_ERR(se_cmd->se_tmr_req))
 		goto release;
 	/*
 	 * Locate the underlying TCM struct se_lun from sc->device->lun
@@ -939,18 +939,6 @@ static u16 tcm_loop_get_fabric_sense_len(void)
 	return 0;
 }
 
-static u64 tcm_loop_pack_lun(unsigned int lun)
-{
-	u64 result;
-
-	/* LSB of lun into byte 1 big-endian */
-	result = ((lun & 0xff) << 8);
-	/* use flat space addressing method */
-	result |= 0x40 | ((lun >> 8) & 0x3f);
-
-	return cpu_to_le64(result);
-}
-
 static char *tcm_loop_dump_proto_id(struct tcm_loop_hba *tl_hba)
 {
 	switch (tl_hba->tl_proto_id) {
@@ -1029,6 +1017,7 @@ static int tcm_loop_make_nexus(
 	struct se_portal_group *se_tpg;
 	struct tcm_loop_hba *tl_hba = tl_tpg->tl_hba;
 	struct tcm_loop_nexus *tl_nexus;
+	int ret = -ENOMEM;
 
 	if (tl_tpg->tl_hba->tl_nexus) {
 		printk(KERN_INFO "tl_tpg->tl_hba->tl_nexus already exists\n");
@@ -1045,8 +1034,10 @@ static int tcm_loop_make_nexus(
 	 * Initialize the struct se_session pointer
 	 */
 	tl_nexus->se_sess = transport_init_session();
-	if (!tl_nexus->se_sess)
+	if (IS_ERR(tl_nexus->se_sess)) {
+		ret = PTR_ERR(tl_nexus->se_sess);
 		goto out;
+	}
 	/*
 	 * Since we are running in 'demo mode' this call with generate a
 	 * struct se_node_acl for the tcm_loop struct se_portal_group with the SCSI
@@ -1072,7 +1063,7 @@ static int tcm_loop_make_nexus(
 
 out:
 	kfree(tl_nexus);
-	return -ENOMEM;
+	return ret;
 }
 
 static int tcm_loop_drop_nexus(
@@ -1152,7 +1143,7 @@ static ssize_t tcm_loop_tpg_store_nexus(
 	 * the fabric protocol_id set in tcm_loop_make_scsi_hba(), and call
 	 * tcm_loop_make_nexus()
 	 */
-	if (strlen(page) > TL_WWN_ADDR_LEN) {
+	if (strlen(page) >= TL_WWN_ADDR_LEN) {
 		printk(KERN_ERR "Emulated NAA Sas Address: %s, exceeds"
 				" max: %d\n", page, TL_WWN_ADDR_LEN);
 		return -EINVAL;
@@ -1333,7 +1324,7 @@ struct se_wwn *tcm_loop_make_scsi_hba(
 	return ERR_PTR(-EINVAL);
 
 check_len:
-	if (strlen(name) > TL_WWN_ADDR_LEN) {
+	if (strlen(name) >= TL_WWN_ADDR_LEN) {
 		printk(KERN_ERR "Emulated NAA %s Address: %s, exceeds"
 			" max: %d\n", name, tcm_loop_dump_proto_id(tl_hba),
 			TL_WWN_ADDR_LEN);
@@ -1481,7 +1472,6 @@ static int tcm_loop_register_configfs(void)
 	fabric->tf_ops.set_fabric_sense_len = &tcm_loop_set_fabric_sense_len;
 	fabric->tf_ops.get_fabric_sense_len = &tcm_loop_get_fabric_sense_len;
 	fabric->tf_ops.is_state_remove = &tcm_loop_is_state_remove;
-	fabric->tf_ops.pack_lun = &tcm_loop_pack_lun;
 
 	tf_cg = &fabric->tf_group;
 	/*
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index a5f44a6e6e1d..25c1f49a7d8b 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -304,7 +304,7 @@ struct target_fabric_configfs *target_fabric_configfs_init(
 		printk(KERN_ERR "Unable to locate passed fabric name\n");
 		return NULL;
 	}
-	if (strlen(name) > TARGET_FABRIC_NAME_SIZE) {
+	if (strlen(name) >= TARGET_FABRIC_NAME_SIZE) {
 		printk(KERN_ERR "Passed name: %s exceeds TARGET_FABRIC"
 			"_NAME_SIZE\n", name);
 		return NULL;
@@ -312,7 +312,7 @@ struct target_fabric_configfs *target_fabric_configfs_init(
 
 	tf = kzalloc(sizeof(struct target_fabric_configfs), GFP_KERNEL);
 	if (!(tf))
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	INIT_LIST_HEAD(&tf->tf_list);
 	atomic_set(&tf->tf_access_cnt, 0);
@@ -497,10 +497,6 @@ static int target_fabric_tf_ops_check(
 		printk(KERN_ERR "Missing tfo->is_state_remove()\n");
 		return -EINVAL;
 	}
-	if (!(tfo->pack_lun)) {
-		printk(KERN_ERR "Missing tfo->pack_lun()\n");
-		return -EINVAL;
-	}
 	/*
 	 * We at least require tfo->fabric_make_wwn(), tfo->fabric_drop_wwn()
 	 * tfo->fabric_make_tpg() and tfo->fabric_drop_tpg() in
@@ -855,7 +851,7 @@ static ssize_t target_core_dev_wwn_store_attr_vpd_unit_serial(
 		return -EOPNOTSUPP;
 	}
 
-	if ((strlen(page) + 1) > INQUIRY_VPD_SERIAL_LEN) {
+	if (strlen(page) >= INQUIRY_VPD_SERIAL_LEN) {
 		printk(KERN_ERR "Emulated VPD Unit Serial exceeds"
 		" INQUIRY_VPD_SERIAL_LEN: %d\n", INQUIRY_VPD_SERIAL_LEN);
 		return -EOVERFLOW;
@@ -921,7 +917,7 @@ static ssize_t target_core_dev_wwn_show_attr_vpd_protocol_identifier(
 
 		transport_dump_vpd_proto_id(vpd, buf, VPD_TMP_BUF_SIZE);
 
-		if ((len + strlen(buf) > PAGE_SIZE))
+		if ((len + strlen(buf) >= PAGE_SIZE))
 			break;
 
 		len += sprintf(page+len, "%s", buf);
@@ -966,19 +962,19 @@ static ssize_t target_core_dev_wwn_show_attr_##_name(			\
 									\
 		memset(buf, 0, VPD_TMP_BUF_SIZE);			\
 		transport_dump_vpd_assoc(vpd, buf, VPD_TMP_BUF_SIZE);	\
-		if ((len + strlen(buf) > PAGE_SIZE))			\
+		if ((len + strlen(buf) >= PAGE_SIZE))			\
 			break;						\
 		len += sprintf(page+len, "%s", buf);			\
 									\
 		memset(buf, 0, VPD_TMP_BUF_SIZE);			\
 		transport_dump_vpd_ident_type(vpd, buf, VPD_TMP_BUF_SIZE); \
-		if ((len + strlen(buf) > PAGE_SIZE))			\
+		if ((len + strlen(buf) >= PAGE_SIZE))			\
 			break;						\
 		len += sprintf(page+len, "%s", buf);			\
 									\
 		memset(buf, 0, VPD_TMP_BUF_SIZE);			\
 		transport_dump_vpd_ident(vpd, buf, VPD_TMP_BUF_SIZE); \
-		if ((len + strlen(buf) > PAGE_SIZE))			\
+		if ((len + strlen(buf) >= PAGE_SIZE))			\
 			break;						\
 		len += sprintf(page+len, "%s", buf);			\
 	}								\
@@ -1303,7 +1299,7 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_registered_i_pts(
 			&i_buf[0] : "", pr_reg->pr_res_key,
 			pr_reg->pr_res_generation);
 
-		if ((len + strlen(buf) > PAGE_SIZE))
+		if ((len + strlen(buf) >= PAGE_SIZE))
 			break;
 
 		len += sprintf(page+len, "%s", buf);
@@ -1500,7 +1496,7 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata(
 				ret = -ENOMEM;
 				goto out;
 			}
-			if (strlen(i_port) > PR_APTPL_MAX_IPORT_LEN) {
+			if (strlen(i_port) >= PR_APTPL_MAX_IPORT_LEN) {
 				printk(KERN_ERR "APTPL metadata initiator_node="
 					" exceeds PR_APTPL_MAX_IPORT_LEN: %d\n",
 					PR_APTPL_MAX_IPORT_LEN);
@@ -1514,7 +1510,7 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata(
 				ret = -ENOMEM;
 				goto out;
 			}
-			if (strlen(isid) > PR_REG_ISID_LEN) {
+			if (strlen(isid) >= PR_REG_ISID_LEN) {
 				printk(KERN_ERR "APTPL metadata initiator_isid"
 					"= exceeds PR_REG_ISID_LEN: %d\n",
 					PR_REG_ISID_LEN);
@@ -1575,7 +1571,7 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata(
 				ret = -ENOMEM;
 				goto out;
 			}
-			if (strlen(t_port) > PR_APTPL_MAX_TPORT_LEN) {
+			if (strlen(t_port) >= PR_APTPL_MAX_TPORT_LEN) {
 				printk(KERN_ERR "APTPL metadata target_node="
 					" exceeds PR_APTPL_MAX_TPORT_LEN: %d\n",
 					PR_APTPL_MAX_TPORT_LEN);
@@ -3056,7 +3052,7 @@ static struct config_group *target_core_call_addhbatotarget(
 	int ret;
 
 	memset(buf, 0, TARGET_CORE_NAME_MAX_LEN);
-	if (strlen(name) > TARGET_CORE_NAME_MAX_LEN) {
+	if (strlen(name) >= TARGET_CORE_NAME_MAX_LEN) {
 		printk(KERN_ERR "Passed *name strlen(): %d exceeds"
 			" TARGET_CORE_NAME_MAX_LEN: %d\n", (int)strlen(name),
 			TARGET_CORE_NAME_MAX_LEN);
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index d25e20829012..ba698ea62bb2 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -38,6 +38,7 @@
 #include <net/sock.h>
 #include <net/tcp.h>
 #include <scsi/scsi.h>
+#include <scsi/scsi_device.h>
 
 #include <target/target_core_base.h>
 #include <target/target_core_device.h>
@@ -150,13 +151,13 @@ out:
 
 	{
 	struct se_device *dev = se_lun->lun_se_dev;
-	spin_lock(&dev->stats_lock);
+	spin_lock_irq(&dev->stats_lock);
 	dev->num_cmds++;
 	if (se_cmd->data_direction == DMA_TO_DEVICE)
 		dev->write_bytes += se_cmd->data_length;
 	else if (se_cmd->data_direction == DMA_FROM_DEVICE)
 		dev->read_bytes += se_cmd->data_length;
-	spin_unlock(&dev->stats_lock);
+	spin_unlock_irq(&dev->stats_lock);
 	}
 
 	/*
@@ -191,7 +192,7 @@ int transport_get_lun_for_tmr(
 			&SE_NODE_ACL(se_sess)->device_list[unpacked_lun];
 	if (deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) {
 		se_lun = se_cmd->se_lun = se_tmr->tmr_lun = deve->se_lun;
-		dev = se_tmr->tmr_dev = se_lun->lun_se_dev;
+		dev = se_lun->lun_se_dev;
 		se_cmd->pr_res_key = deve->pr_res_key;
 		se_cmd->orig_fe_lun = unpacked_lun;
 		se_cmd->se_orig_obj_ptr = SE_LUN(se_cmd)->lun_se_dev;
@@ -215,6 +216,7 @@ int transport_get_lun_for_tmr(
 		se_cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
 		return -1;
 	}
+	se_tmr->tmr_dev = dev;
 
 	spin_lock(&dev->se_tmr_lock);
 	list_add_tail(&se_tmr->tmr_list, &dev->dev_tmr_list);
@@ -658,8 +660,7 @@ int transport_core_report_lun_response(struct se_cmd *se_cmd)
 	struct se_session *se_sess = SE_SESS(se_cmd);
 	struct se_task *se_task;
 	unsigned char *buf = (unsigned char *)T_TASK(se_cmd)->t_task_buf;
-	u32 cdb_offset = 0, lun_count = 0, offset = 8;
-	u64 i, lun;
+	u32 cdb_offset = 0, lun_count = 0, offset = 8, i;
 
 	list_for_each_entry(se_task, &T_TASK(se_cmd)->t_task_list, t_list)
 		break;
@@ -675,15 +676,7 @@ int transport_core_report_lun_response(struct se_cmd *se_cmd)
 	 * a $FABRIC_MOD.  In that case, report LUN=0 only.
 	 */
 	if (!(se_sess)) {
-		lun = 0;
-		buf[offset++] = ((lun >> 56) & 0xff);
-		buf[offset++] = ((lun >> 48) & 0xff);
-		buf[offset++] = ((lun >> 40) & 0xff);
-		buf[offset++] = ((lun >> 32) & 0xff);
-		buf[offset++] = ((lun >> 24) & 0xff);
-		buf[offset++] = ((lun >> 16) & 0xff);
-		buf[offset++] = ((lun >> 8) & 0xff);
-		buf[offset++] = (lun & 0xff);
+		int_to_scsilun(0, (struct scsi_lun *)&buf[offset]);
 		lun_count = 1;
 		goto done;
 	}
@@ -703,15 +696,8 @@ int transport_core_report_lun_response(struct se_cmd *se_cmd)
 		if ((cdb_offset + 8) >= se_cmd->data_length)
 			continue;
 
-		lun = cpu_to_be64(CMD_TFO(se_cmd)->pack_lun(deve->mapped_lun));
-		buf[offset++] = ((lun >> 56) & 0xff);
-		buf[offset++] = ((lun >> 48) & 0xff);
-		buf[offset++] = ((lun >> 40) & 0xff);
-		buf[offset++] = ((lun >> 32) & 0xff);
-		buf[offset++] = ((lun >> 24) & 0xff);
-		buf[offset++] = ((lun >> 16) & 0xff);
-		buf[offset++] = ((lun >> 8) & 0xff);
-		buf[offset++] = (lun & 0xff);
+		int_to_scsilun(deve->mapped_lun, (struct scsi_lun *)&buf[offset]);
+		offset += 8;
 		cdb_offset += 8;
 	}
 	spin_unlock_irq(&SE_NODE_ACL(se_sess)->device_list_lock);
@@ -1445,7 +1431,7 @@ struct se_lun_acl *core_dev_init_initiator_node_lun_acl(
 	struct se_lun_acl *lacl;
 	struct se_node_acl *nacl;
 
-	if (strlen(initiatorname) > TRANSPORT_IQN_LEN) {
+	if (strlen(initiatorname) >= TRANSPORT_IQN_LEN) {
 		printk(KERN_ERR "%s InitiatorName exceeds maximum size.\n",
 			TPG_TFO(tpg)->get_fabric_name());
 		*ret = -EOVERFLOW;
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index a79f518ca6e2..b662db3a320b 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -1916,7 +1916,7 @@ static int __core_scsi3_update_aptpl_buf(
 				pr_reg->pr_res_mapped_lun);
 		}
 
-		if ((len + strlen(tmp) > pr_aptpl_buf_len)) {
+		if ((len + strlen(tmp) >= pr_aptpl_buf_len)) {
 			printk(KERN_ERR "Unable to update renaming"
 				" APTPL metadata\n");
 			spin_unlock(&T10_RES(su_dev)->registration_lock);
@@ -1934,7 +1934,7 @@ static int __core_scsi3_update_aptpl_buf(
 			TPG_TFO(tpg)->tpg_get_tag(tpg),
 			lun->lun_sep->sep_rtpi, lun->unpacked_lun, reg_count);
 
-		if ((len + strlen(tmp) > pr_aptpl_buf_len)) {
+		if ((len + strlen(tmp) >= pr_aptpl_buf_len)) {
 			printk(KERN_ERR "Unable to update renaming"
 				" APTPL metadata\n");
 			spin_unlock(&T10_RES(su_dev)->registration_lock);
@@ -1986,7 +1986,7 @@ static int __core_scsi3_write_aptpl_to_file(
 	memset(iov, 0, sizeof(struct iovec));
 	memset(path, 0, 512);
 
-	if (strlen(&wwn->unit_serial[0]) > 512) {
+	if (strlen(&wwn->unit_serial[0]) >= 512) {
 		printk(KERN_ERR "WWN value for struct se_device does not fit"
 			" into path buffer\n");
 		return -1;
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 7ff6a35f26ac..331d423fd0e0 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -41,7 +41,7 @@
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_host.h>
-#include <scsi/libsas.h> /* For TASK_ATTR_* */
+#include <scsi/scsi_tcq.h>
 
 #include <target/target_core_base.h>
 #include <target/target_core_device.h>
@@ -911,7 +911,7 @@ static int pscsi_do_task(struct se_task *task)
 	 * descriptor
 	 */
 	blk_execute_rq_nowait(pdv->pdv_sd->request_queue, NULL, pt->pscsi_req,
-			(task->task_se_cmd->sam_task_attr == TASK_ATTR_HOQ),
+			(task->task_se_cmd->sam_task_attr == MSG_HEAD_TAG),
 			pscsi_req_done);
 
 	return PYX_TRANSPORT_SENT_TO_TRANSPORT;
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 4a109835e420..179063d81cdd 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -55,7 +55,8 @@ struct se_tmr_req *core_tmr_alloc_req(
 {
 	struct se_tmr_req *tmr;
 
-	tmr = kmem_cache_zalloc(se_tmr_req_cache, GFP_KERNEL);
+	tmr = kmem_cache_zalloc(se_tmr_req_cache, (in_interrupt()) ?
+					GFP_ATOMIC : GFP_KERNEL);
 	if (!(tmr)) {
 		printk(KERN_ERR "Unable to allocate struct se_tmr_req\n");
 		return ERR_PTR(-ENOMEM);
@@ -74,10 +75,16 @@ void core_tmr_release_req(
 {
 	struct se_device *dev = tmr->tmr_dev;
 
+	if (!dev) {
+		kmem_cache_free(se_tmr_req_cache, tmr);
+		return;
+	}
+
 	spin_lock(&dev->se_tmr_lock);
 	list_del(&tmr->tmr_list);
-	kmem_cache_free(se_tmr_req_cache, tmr);
 	spin_unlock(&dev->se_tmr_lock);
+
+	kmem_cache_free(se_tmr_req_cache, tmr);
 }
 
 static void core_tmr_handle_tas_abort(
@@ -398,9 +405,9 @@ int core_tmr_lun_reset(
 		printk(KERN_INFO "LUN_RESET: SCSI-2 Released reservation\n");
 	}
 
-	spin_lock(&dev->stats_lock);
+	spin_lock_irq(&dev->stats_lock);
 	dev->num_resets++;
-	spin_unlock(&dev->stats_lock);
+	spin_unlock_irq(&dev->stats_lock);
 
 	DEBUG_LR("LUN_RESET: %s for [%s] Complete\n",
 			(preempt_and_abort_list) ? "Preempt" : "TMR",
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index b9d3501bdd91..4b9b7169bdd9 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -42,7 +42,7 @@
 #include <net/tcp.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
-#include <scsi/libsas.h> /* For TASK_ATTR_* */
+#include <scsi/scsi_tcq.h>
 
 #include <target/target_core_base.h>
 #include <target/target_core_device.h>
@@ -536,13 +536,13 @@ EXPORT_SYMBOL(transport_register_session);
 void transport_deregister_session_configfs(struct se_session *se_sess)
 {
 	struct se_node_acl *se_nacl;
-
+	unsigned long flags;
 	/*
 	 * Used by struct se_node_acl's under ConfigFS to locate active struct se_session
 	 */
 	se_nacl = se_sess->se_node_acl;
 	if ((se_nacl)) {
-		spin_lock_irq(&se_nacl->nacl_sess_lock);
+		spin_lock_irqsave(&se_nacl->nacl_sess_lock, flags);
 		list_del(&se_sess->sess_acl_list);
 		/*
 		 * If the session list is empty, then clear the pointer.
@@ -556,7 +556,7 @@ void transport_deregister_session_configfs(struct se_session *se_sess)
 					se_nacl->acl_sess_list.prev,
 					struct se_session, sess_acl_list);
 		}
-		spin_unlock_irq(&se_nacl->nacl_sess_lock);
+		spin_unlock_irqrestore(&se_nacl->nacl_sess_lock, flags);
 	}
 }
 EXPORT_SYMBOL(transport_deregister_session_configfs);
@@ -762,7 +762,6 @@ static void transport_lun_remove_cmd(struct se_cmd *cmd)
 	transport_all_task_dev_remove_state(cmd);
 	spin_unlock_irqrestore(&T_TASK(cmd)->t_state_lock, flags);
 
-	transport_free_dev_tasks(cmd);
 
 check_lun:
 	spin_lock_irqsave(&lun->lun_cmd_lock, flags);
@@ -1075,7 +1074,7 @@ static inline int transport_add_task_check_sam_attr(
 	 * head of the struct se_device->execute_task_list, and task_prev
 	 * after that for each subsequent task
 	 */
-	if (task->task_se_cmd->sam_task_attr == TASK_ATTR_HOQ) {
+	if (task->task_se_cmd->sam_task_attr == MSG_HEAD_TAG) {
 		list_add(&task->t_execute_list,
 				(task_prev != NULL) ?
 				&task_prev->t_execute_list :
@@ -1195,6 +1194,7 @@ transport_get_task_from_execute_queue(struct se_device *dev)
 		break;
 
 	list_del(&task->t_execute_list);
+	atomic_set(&task->task_execute_queue, 0);
 	atomic_dec(&dev->execute_tasks);
 
 	return task;
@@ -1210,8 +1210,14 @@ void transport_remove_task_from_execute_queue(
 {
 	unsigned long flags;
 
+	if (atomic_read(&task->task_execute_queue) == 0) {
+		dump_stack();
+		return;
+	}
+
 	spin_lock_irqsave(&dev->execute_task_lock, flags);
 	list_del(&task->t_execute_list);
+	atomic_set(&task->task_execute_queue, 0);
 	atomic_dec(&dev->execute_tasks);
 	spin_unlock_irqrestore(&dev->execute_task_lock, flags);
 }
@@ -1867,7 +1873,7 @@ static int transport_check_alloc_task_attr(struct se_cmd *cmd)
 	if (SE_DEV(cmd)->dev_task_attr_type != SAM_TASK_ATTR_EMULATED)
 		return 0;
 
-	if (cmd->sam_task_attr == TASK_ATTR_ACA) {
+	if (cmd->sam_task_attr == MSG_ACA_TAG) {
 		DEBUG_STA("SAM Task Attribute ACA"
 			" emulation is not supported\n");
 		return -1;
@@ -2058,6 +2064,13 @@ int transport_generic_handle_tmr(
 }
 EXPORT_SYMBOL(transport_generic_handle_tmr);
 
+void transport_generic_free_cmd_intr(
+	struct se_cmd *cmd)
+{
+	transport_add_cmd_to_queue(cmd, TRANSPORT_FREE_CMD_INTR);
+}
+EXPORT_SYMBOL(transport_generic_free_cmd_intr);
+
 static int transport_stop_tasks_for_cmd(struct se_cmd *cmd)
 {
 	struct se_task *task, *task_tmp;
@@ -2504,7 +2517,7 @@ static inline int transport_execute_task_attr(struct se_cmd *cmd)
 	 * Check for the existence of HEAD_OF_QUEUE, and if true return 1
 	 * to allow the passed struct se_cmd list of tasks to the front of the list.
 	 */
-	 if (cmd->sam_task_attr == TASK_ATTR_HOQ) {
+	 if (cmd->sam_task_attr == MSG_HEAD_TAG) {
 		atomic_inc(&SE_DEV(cmd)->dev_hoq_count);
 		smp_mb__after_atomic_inc();
 		DEBUG_STA("Added HEAD_OF_QUEUE for CDB:"
@@ -2512,7 +2525,7 @@ static inline int transport_execute_task_attr(struct se_cmd *cmd)
 			T_TASK(cmd)->t_task_cdb[0],
 			cmd->se_ordered_id);
 		return 1;
-	} else if (cmd->sam_task_attr == TASK_ATTR_ORDERED) {
+	} else if (cmd->sam_task_attr == MSG_ORDERED_TAG) {
 		spin_lock(&SE_DEV(cmd)->ordered_cmd_lock);
 		list_add_tail(&cmd->se_ordered_list,
 				&SE_DEV(cmd)->ordered_cmd_list);
@@ -3411,7 +3424,7 @@ static int transport_generic_cmd_sequencer(
 		 * See spc4r17 section 5.3
 		 */
 		if (SE_DEV(cmd)->dev_task_attr_type == SAM_TASK_ATTR_EMULATED)
-			cmd->sam_task_attr = TASK_ATTR_HOQ;
+			cmd->sam_task_attr = MSG_HEAD_TAG;
 		cmd->se_cmd_flags |= SCF_SCSI_CONTROL_NONSG_IO_CDB;
 		break;
 	case READ_BUFFER:
@@ -3619,7 +3632,7 @@ static int transport_generic_cmd_sequencer(
 		 * See spc4r17 section 5.3
 		 */
 		if (SE_DEV(cmd)->dev_task_attr_type == SAM_TASK_ATTR_EMULATED)
-			cmd->sam_task_attr = TASK_ATTR_HOQ;
+			cmd->sam_task_attr = MSG_HEAD_TAG;
 		cmd->se_cmd_flags |= SCF_SCSI_CONTROL_NONSG_IO_CDB;
 		break;
 	default:
@@ -3777,21 +3790,21 @@ static void transport_complete_task_attr(struct se_cmd *cmd)
 	struct se_cmd *cmd_p, *cmd_tmp;
 	int new_active_tasks = 0;
 
-	if (cmd->sam_task_attr == TASK_ATTR_SIMPLE) {
+	if (cmd->sam_task_attr == MSG_SIMPLE_TAG) {
 		atomic_dec(&dev->simple_cmds);
 		smp_mb__after_atomic_dec();
 		dev->dev_cur_ordered_id++;
 		DEBUG_STA("Incremented dev->dev_cur_ordered_id: %u for"
 			" SIMPLE: %u\n", dev->dev_cur_ordered_id,
 			cmd->se_ordered_id);
-	} else if (cmd->sam_task_attr == TASK_ATTR_HOQ) {
+	} else if (cmd->sam_task_attr == MSG_HEAD_TAG) {
 		atomic_dec(&dev->dev_hoq_count);
 		smp_mb__after_atomic_dec();
 		dev->dev_cur_ordered_id++;
 		DEBUG_STA("Incremented dev_cur_ordered_id: %u for"
 			" HEAD_OF_QUEUE: %u\n", dev->dev_cur_ordered_id,
 			cmd->se_ordered_id);
-	} else if (cmd->sam_task_attr == TASK_ATTR_ORDERED) {
+	} else if (cmd->sam_task_attr == MSG_ORDERED_TAG) {
 		spin_lock(&dev->ordered_cmd_lock);
 		list_del(&cmd->se_ordered_list);
 		atomic_dec(&dev->dev_ordered_sync);
@@ -3824,7 +3837,7 @@ static void transport_complete_task_attr(struct se_cmd *cmd)
 		new_active_tasks++;
 
 		spin_lock(&dev->delayed_cmd_lock);
-		if (cmd_p->sam_task_attr == TASK_ATTR_ORDERED)
+		if (cmd_p->sam_task_attr == MSG_ORDERED_TAG)
 			break;
 	}
 	spin_unlock(&dev->delayed_cmd_lock);
@@ -4776,18 +4789,20 @@ void transport_do_task_sg_chain(struct se_cmd *cmd)
 				sg_end_cur->page_link &= ~0x02;
 
 				sg_chain(sg_head, task_sg_num, sg_head_cur);
-				sg_count += (task->task_sg_num + 1);
-			} else
 				sg_count += task->task_sg_num;
+				task_sg_num = (task->task_sg_num + 1);
+			} else {
+				sg_chain(sg_head, task_sg_num, sg_head_cur);
+				sg_count += task->task_sg_num;
+				task_sg_num = task->task_sg_num;
+			}
 
 			sg_head = sg_head_cur;
 			sg_link = sg_link_cur;
-			task_sg_num = task->task_sg_num;
 			continue;
 		}
 		sg_head = sg_first = &task->task_sg[0];
 		sg_link = &task->task_sg[task->task_sg_num];
-		task_sg_num = task->task_sg_num;
 		/*
 		 * Check for single task..
 		 */
@@ -4798,9 +4813,12 @@ void transport_do_task_sg_chain(struct se_cmd *cmd)
 			 */
 			sg_end = &task->task_sg[task->task_sg_num - 1];
 			sg_end->page_link &= ~0x02;
-			sg_count += (task->task_sg_num + 1);
-		} else
 			sg_count += task->task_sg_num;
+			task_sg_num = (task->task_sg_num + 1);
+		} else {
+			sg_count += task->task_sg_num;
+			task_sg_num = task->task_sg_num;
+		}
 	}
 	/*
 	 * Setup the starting pointer and total t_tasks_sg_linked_no including
@@ -4809,21 +4827,20 @@ void transport_do_task_sg_chain(struct se_cmd *cmd)
 	T_TASK(cmd)->t_tasks_sg_chained = sg_first;
 	T_TASK(cmd)->t_tasks_sg_chained_no = sg_count;
 
-	DEBUG_CMD_M("Setup T_TASK(cmd)->t_tasks_sg_chained: %p and"
-		" t_tasks_sg_chained_no: %u\n", T_TASK(cmd)->t_tasks_sg_chained,
+	DEBUG_CMD_M("Setup cmd: %p T_TASK(cmd)->t_tasks_sg_chained: %p and"
+		" t_tasks_sg_chained_no: %u\n", cmd, T_TASK(cmd)->t_tasks_sg_chained,
 		T_TASK(cmd)->t_tasks_sg_chained_no);
 
 	for_each_sg(T_TASK(cmd)->t_tasks_sg_chained, sg,
 			T_TASK(cmd)->t_tasks_sg_chained_no, i) {
 
-		DEBUG_CMD_M("SG: %p page: %p length: %d offset: %d\n",
-			sg, sg_page(sg), sg->length, sg->offset);
+		DEBUG_CMD_M("SG[%d]: %p page: %p length: %d offset: %d, magic: 0x%08x\n",
+			i, sg, sg_page(sg), sg->length, sg->offset, sg->sg_magic);
 		if (sg_is_chain(sg))
 			DEBUG_CMD_M("SG: %p sg_is_chain=1\n", sg);
 		if (sg_is_last(sg))
 			DEBUG_CMD_M("SG: %p sg_is_last=1\n", sg);
 	}
-
 }
 EXPORT_SYMBOL(transport_do_task_sg_chain);
 
@@ -5297,6 +5314,8 @@ void transport_generic_free_cmd(
 		if (wait_for_tasks && cmd->transport_wait_for_tasks)
 			cmd->transport_wait_for_tasks(cmd, 0, 0);
 
+		transport_free_dev_tasks(cmd);
+
 		transport_generic_remove(cmd, release_to_pool,
 				session_reinstatement);
 	}
@@ -6132,6 +6151,9 @@ get_cmd:
 		case TRANSPORT_REMOVE:
 			transport_generic_remove(cmd, 1, 0);
 			break;
+		case TRANSPORT_FREE_CMD_INTR:
+			transport_generic_free_cmd(cmd, 0, 1, 0);
+			break;
 		case TRANSPORT_PROCESS_TMR:
 			transport_generic_do_tmr(cmd);
 			break;
diff --git a/drivers/target/tcm_fc/tcm_fc.h b/drivers/target/tcm_fc/tcm_fc.h
index defff32b7880..7b82f1b7fef8 100644
--- a/drivers/target/tcm_fc/tcm_fc.h
+++ b/drivers/target/tcm_fc/tcm_fc.h
@@ -144,7 +144,7 @@ enum ft_cmd_state {
  */
 struct ft_cmd {
 	enum ft_cmd_state state;
-	u16 lun;			/* LUN from request */
+	u32 lun;                        /* LUN from request */
 	struct ft_sess *sess;		/* session held for cmd */
 	struct fc_seq *seq;		/* sequence in exchange mgr */
 	struct se_cmd se_cmd;		/* Local TCM I/O descriptor */
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index 49e51778f733..b2a106729d49 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -35,6 +35,7 @@
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_tcq.h>
 #include <scsi/libfc.h>
 #include <scsi/fc_encode.h>
 
@@ -93,29 +94,6 @@ void ft_dump_cmd(struct ft_cmd *cmd, const char *caller)
 		16, 4, cmd->cdb, MAX_COMMAND_SIZE, 0);
 }
 
-/*
- * Get LUN from CDB.
- */
-static int ft_get_lun_for_cmd(struct ft_cmd *cmd, u8 *lunp)
-{
-	u64 lun;
-
-	lun = lunp[1];
-	switch (lunp[0] >> 6) {
-	case 0:
-		break;
-	case 1:
-		lun |= (lunp[0] & 0x3f) << 8;
-		break;
-	default:
-		return -1;
-	}
-	if (lun >= TRANSPORT_MAX_LUNS_PER_TPG)
-		return -1;
-	cmd->lun = lun;
-	return transport_get_lun_for_cmd(&cmd->se_cmd, NULL, lun);
-}
-
 static void ft_queue_cmd(struct ft_sess *sess, struct ft_cmd *cmd)
 {
 	struct se_queue_obj *qobj;
@@ -417,6 +395,7 @@ static void ft_send_tm(struct ft_cmd *cmd)
 {
 	struct se_tmr_req *tmr;
 	struct fcp_cmnd *fcp;
+	struct ft_sess *sess;
 	u8 tm_func;
 
 	fcp = fc_frame_payload_get(cmd->req_frame, sizeof(*fcp));
@@ -424,13 +403,6 @@ static void ft_send_tm(struct ft_cmd *cmd)
 	switch (fcp->fc_tm_flags) {
 	case FCP_TMF_LUN_RESET:
 		tm_func = TMR_LUN_RESET;
-		if (ft_get_lun_for_cmd(cmd, fcp->fc_lun) < 0) {
-			ft_dump_cmd(cmd, __func__);
-			transport_send_check_condition_and_sense(&cmd->se_cmd,
-				cmd->se_cmd.scsi_sense_reason, 0);
-			ft_sess_put(cmd->sess);
-			return;
-		}
 		break;
 	case FCP_TMF_TGT_RESET:
 		tm_func = TMR_TARGET_WARM_RESET;
@@ -462,6 +434,36 @@ static void ft_send_tm(struct ft_cmd *cmd)
 		return;
 	}
 	cmd->se_cmd.se_tmr_req = tmr;
+
+	switch (fcp->fc_tm_flags) {
+	case FCP_TMF_LUN_RESET:
+		cmd->lun = scsilun_to_int((struct scsi_lun *)fcp->fc_lun);
+		if (transport_get_lun_for_tmr(&cmd->se_cmd, cmd->lun) < 0) {
+			/*
+			 * Make sure to clean up newly allocated TMR request
+			 * since "unable to  handle TMR request because failed
+			 * to get to LUN"
+			 */
+			FT_TM_DBG("Failed to get LUN for TMR func %d, "
+				  "se_cmd %p, unpacked_lun %d\n",
+				  tm_func, &cmd->se_cmd, cmd->lun);
+			ft_dump_cmd(cmd, __func__);
+			sess = cmd->sess;
+			transport_send_check_condition_and_sense(&cmd->se_cmd,
+				cmd->se_cmd.scsi_sense_reason, 0);
+			transport_generic_free_cmd(&cmd->se_cmd, 0, 1, 0);
+			ft_sess_put(sess);
+			return;
+		}
+		break;
+	case FCP_TMF_TGT_RESET:
+	case FCP_TMF_CLR_TASK_SET:
+	case FCP_TMF_ABT_TASK_SET:
+	case FCP_TMF_CLR_ACA:
+		break;
+	default:
+		return;
+	}
 	transport_generic_handle_tmr(&cmd->se_cmd);
 }
 
@@ -592,8 +594,25 @@ static void ft_send_cmd(struct ft_cmd *cmd)
 		case FCP_CFL_WRDATA | FCP_CFL_RDDATA:
 			goto err;	/* TBD not supported by tcm_fc yet */
 		}
+		/*
+		 * Locate the SAM Task Attr from fc_pri_ta
+		 */
+		switch (fcp->fc_pri_ta & FCP_PTA_MASK) {
+		case FCP_PTA_HEADQ:
+			task_attr = MSG_HEAD_TAG;
+			break;
+		case FCP_PTA_ORDERED:
+			task_attr = MSG_ORDERED_TAG;
+			break;
+		case FCP_PTA_ACA:
+			task_attr = MSG_ACA_TAG;
+			break;
+		case FCP_PTA_SIMPLE: /* Fallthrough */
+		default:
+			task_attr = MSG_SIMPLE_TAG;
+		}
+
 
-		/* FCP_PTA_ maps 1:1 to TASK_ATTR_ */
 		task_attr = fcp->fc_pri_ta & FCP_PTA_MASK;
 		data_len = ntohl(fcp->fc_dl);
 		cmd->cdb = fcp->fc_cdb;
@@ -617,7 +636,8 @@ static void ft_send_cmd(struct ft_cmd *cmd)
 
 	fc_seq_exch(cmd->seq)->lp->tt.seq_set_resp(cmd->seq, ft_recv_seq, cmd);
 
-	ret = ft_get_lun_for_cmd(cmd, fcp->fc_lun);
+	cmd->lun = scsilun_to_int((struct scsi_lun *)fcp->fc_lun);
+	ret = transport_get_lun_for_cmd(&cmd->se_cmd, NULL, cmd->lun);
 	if (ret < 0) {
 		ft_dump_cmd(cmd, __func__);
 		transport_send_check_condition_and_sense(&cmd->se_cmd,
diff --git a/drivers/target/tcm_fc/tfc_conf.c b/drivers/target/tcm_fc/tfc_conf.c
index fcdbbffe88cc..84e868c255dd 100644
--- a/drivers/target/tcm_fc/tfc_conf.c
+++ b/drivers/target/tcm_fc/tfc_conf.c
@@ -519,13 +519,6 @@ static u32 ft_tpg_get_inst_index(struct se_portal_group *se_tpg)
 	return tpg->index;
 }
 
-static u64 ft_pack_lun(unsigned int index)
-{
-	WARN_ON(index >= 256);
-	/* Caller wants this byte-swapped */
-	return cpu_to_le64((index & 0xff) << 8);
-}
-
 static struct target_core_fabric_ops ft_fabric_ops = {
 	.get_fabric_name =		ft_get_fabric_name,
 	.get_fabric_proto_ident =	fc_get_fabric_proto_ident,
@@ -564,7 +557,6 @@ static struct target_core_fabric_ops ft_fabric_ops = {
 	.get_fabric_sense_len =		ft_get_fabric_sense_len,
 	.set_fabric_sense_len =		ft_set_fabric_sense_len,
 	.is_state_remove =		ft_is_state_remove,
-	.pack_lun =			ft_pack_lun,
 	/*
 	 * Setup function pointers for generic logic in
 	 * target_core_fabric_configfs.c
diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c
index 4c3c0efbe13f..8c4a24077d9d 100644
--- a/drivers/target/tcm_fc/tfc_io.c
+++ b/drivers/target/tcm_fc/tfc_io.c
@@ -203,7 +203,7 @@ int ft_queue_data_in(struct se_cmd *se_cmd)
 			/* XXX For now, initiator will retry */
 			if (printk_ratelimit())
 				printk(KERN_ERR "%s: Failed to send frame %p, "
-						"xid <0x%x>, remaining <0x%x>, "
+						"xid <0x%x>, remaining %zu, "
 						"lso_max <0x%x>\n",
 						__func__, fp, ep->xid,
 						remaining, lport->lso_max);
diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c
index a3bd57f2ea32..7491e21cc6ae 100644
--- a/drivers/target/tcm_fc/tfc_sess.c
+++ b/drivers/target/tcm_fc/tfc_sess.c
@@ -229,7 +229,7 @@ static struct ft_sess *ft_sess_create(struct ft_tport *tport, u32 port_id,
 		return NULL;
 
 	sess->se_sess = transport_init_session();
-	if (!sess->se_sess) {
+	if (IS_ERR(sess->se_sess)) {
 		kfree(sess);
 		return NULL;
 	}
@@ -332,7 +332,7 @@ void ft_sess_close(struct se_session *se_sess)
 	lport = sess->tport->lport;
 	port_id = sess->port_id;
 	if (port_id == -1) {
-		mutex_lock(&ft_lport_lock);
+		mutex_unlock(&ft_lport_lock);
 		return;
 	}
 	FT_SESS_DBG("port_id %x\n", port_id);
diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c
index fc6f2a5bde01..0b1c82ad6805 100644
--- a/drivers/thermal/thermal_sys.c
+++ b/drivers/thermal/thermal_sys.c
@@ -499,7 +499,7 @@ thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 	dev_set_drvdata(hwmon->device, hwmon);
 	result = device_create_file(hwmon->device, &dev_attr_name);
 	if (result)
-		goto unregister_hwmon_device;
+		goto free_mem;
 
  register_sys_interface:
 	tz->hwmon = hwmon;
@@ -513,7 +513,7 @@ thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 	sysfs_attr_init(&tz->temp_input.attr.attr);
 	result = device_create_file(hwmon->device, &tz->temp_input.attr);
 	if (result)
-		goto unregister_hwmon_device;
+		goto unregister_name;
 
 	if (tz->ops->get_crit_temp) {
 		unsigned long temperature;
@@ -527,7 +527,7 @@ thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 			result = device_create_file(hwmon->device,
 						    &tz->temp_crit.attr);
 			if (result)
-				goto unregister_hwmon_device;
+				goto unregister_input;
 		}
 	}
 
@@ -539,9 +539,9 @@ thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 
 	return 0;
 
- unregister_hwmon_device:
-	device_remove_file(hwmon->device, &tz->temp_crit.attr);
+ unregister_input:
 	device_remove_file(hwmon->device, &tz->temp_input.attr);
+ unregister_name:
 	if (new_hwmon_device) {
 		device_remove_file(hwmon->device, &dev_attr_name);
 		hwmon_device_unregister(hwmon->device);
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index a4c42a75a3bf..09e8c7d53af3 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -2128,8 +2128,8 @@ static void gsmld_detach_gsm(struct tty_struct *tty, struct gsm_mux *gsm)
 	gsm->tty = NULL;
 }
 
-static unsigned int gsmld_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void gsmld_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+			      char *fp, int count)
 {
 	struct gsm_mux *gsm = tty->disc_data;
 	const unsigned char *dp;
@@ -2162,8 +2162,6 @@ static unsigned int gsmld_receive_buf(struct tty_struct *tty,
 	}
 	/* FASYNC if needed ? */
 	/* If clogged call tty_throttle(tty); */
-
-	return count;
 }
 
 /**
diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index cac666314aef..cea56033b34c 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -188,8 +188,8 @@ static unsigned int n_hdlc_tty_poll(struct tty_struct *tty, struct file *filp,
 				    poll_table *wait);
 static int n_hdlc_tty_open(struct tty_struct *tty);
 static void n_hdlc_tty_close(struct tty_struct *tty);
-static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
-		const __u8 *cp, char *fp, int count);
+static void n_hdlc_tty_receive(struct tty_struct *tty, const __u8 *cp,
+			       char *fp, int count);
 static void n_hdlc_tty_wakeup(struct tty_struct *tty);
 
 #define bset(p,b)	((p)[(b) >> 5] |= (1 << ((b) & 0x1f)))
@@ -509,8 +509,8 @@ static void n_hdlc_tty_wakeup(struct tty_struct *tty)
  * Called by tty low level driver when receive data is available. Data is
  * interpreted as one HDLC frame.
  */
-static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
-		const __u8 *data, char *flags, int count)
+static void n_hdlc_tty_receive(struct tty_struct *tty, const __u8 *data,
+			       char *flags, int count)
 {
 	register struct n_hdlc *n_hdlc = tty2n_hdlc (tty);
 	register struct n_hdlc_buf *buf;
@@ -521,20 +521,20 @@ static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
 		
 	/* This can happen if stuff comes in on the backup tty */
 	if (!n_hdlc || tty != n_hdlc->tty)
-		return -ENODEV;
+		return;
 		
 	/* verify line is using HDLC discipline */
 	if (n_hdlc->magic != HDLC_MAGIC) {
 		printk("%s(%d) line not using HDLC discipline\n",
 			__FILE__,__LINE__);
-		return -EINVAL;
+		return;
 	}
 	
 	if ( count>maxframe ) {
 		if (debuglevel >= DEBUG_LEVEL_INFO)	
 			printk("%s(%d) rx count>maxframesize, data discarded\n",
 			       __FILE__,__LINE__);
-		return -EINVAL;
+		return;
 	}
 
 	/* get a free HDLC buffer */	
@@ -550,7 +550,7 @@ static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
 		if (debuglevel >= DEBUG_LEVEL_INFO)	
 			printk("%s(%d) no more rx buffers, data discarded\n",
 			       __FILE__,__LINE__);
-		return -EINVAL;
+		return;
 	}
 		
 	/* copy received data to HDLC buffer */
@@ -565,8 +565,6 @@ static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
 	if (n_hdlc->tty->fasync != NULL)
 		kill_fasync (&n_hdlc->tty->fasync, SIGIO, POLL_IN);
 
-	return count;
-
 }	/* end of n_hdlc_tty_receive() */
 
 /**
diff --git a/drivers/tty/n_r3964.c b/drivers/tty/n_r3964.c
index a4bc39c21a43..5c6c31459a2f 100644
--- a/drivers/tty/n_r3964.c
+++ b/drivers/tty/n_r3964.c
@@ -139,8 +139,8 @@ static int r3964_ioctl(struct tty_struct *tty, struct file *file,
 static void r3964_set_termios(struct tty_struct *tty, struct ktermios *old);
 static unsigned int r3964_poll(struct tty_struct *tty, struct file *file,
 		struct poll_table_struct *wait);
-static unsigned int r3964_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count);
+static void r3964_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+		char *fp, int count);
 
 static struct tty_ldisc_ops tty_ldisc_N_R3964 = {
 	.owner = THIS_MODULE,
@@ -1239,8 +1239,8 @@ static unsigned int r3964_poll(struct tty_struct *tty, struct file *file,
 	return result;
 }
 
-static unsigned int r3964_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void r3964_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+			char *fp, int count)
 {
 	struct r3964_info *pInfo = tty->disc_data;
 	const unsigned char *p;
@@ -1257,8 +1257,6 @@ static unsigned int r3964_receive_buf(struct tty_struct *tty,
 		}
 
 	}
-
-	return count;
 }
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 95d0a9c2dd13..0ad32888091c 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -81,6 +81,38 @@ static inline int tty_put_user(struct tty_struct *tty, unsigned char x,
 	return put_user(x, ptr);
 }
 
+/**
+ *	n_tty_set__room	-	receive space
+ *	@tty: terminal
+ *
+ *	Called by the driver to find out how much data it is
+ *	permitted to feed to the line discipline without any being lost
+ *	and thus to manage flow control. Not serialized. Answers for the
+ *	"instant".
+ */
+
+static void n_tty_set_room(struct tty_struct *tty)
+{
+	/* tty->read_cnt is not read locked ? */
+	int	left = N_TTY_BUF_SIZE - tty->read_cnt - 1;
+	int old_left;
+
+	/*
+	 * If we are doing input canonicalization, and there are no
+	 * pending newlines, let characters through without limit, so
+	 * that erase characters will be handled.  Other excess
+	 * characters will be beeped.
+	 */
+	if (left <= 0)
+		left = tty->icanon && !tty->canon_data;
+	old_left = tty->receive_room;
+	tty->receive_room = left;
+
+	/* Did this open up the receive buffer? We may need to flip */
+	if (left && !old_left)
+		schedule_work(&tty->buf.work);
+}
+
 static void put_tty_queue_nolock(unsigned char c, struct tty_struct *tty)
 {
 	if (tty->read_cnt < N_TTY_BUF_SIZE) {
@@ -152,6 +184,7 @@ static void reset_buffer_flags(struct tty_struct *tty)
 
 	tty->canon_head = tty->canon_data = tty->erasing = 0;
 	memset(&tty->read_flags, 0, sizeof tty->read_flags);
+	n_tty_set_room(tty);
 	check_unthrottle(tty);
 }
 
@@ -1327,19 +1360,17 @@ static void n_tty_write_wakeup(struct tty_struct *tty)
  *	calls one at a time and in order (or using flush_to_ldisc)
  */
 
-static unsigned int n_tty_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+			      char *fp, int count)
 {
 	const unsigned char *p;
 	char *f, flags = TTY_NORMAL;
 	int	i;
 	char	buf[64];
 	unsigned long cpuflags;
-	int left;
-	int ret = 0;
 
 	if (!tty->read_buf)
-		return 0;
+		return;
 
 	if (tty->real_raw) {
 		spin_lock_irqsave(&tty->read_lock, cpuflags);
@@ -1349,7 +1380,6 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty,
 		memcpy(tty->read_buf + tty->read_head, cp, i);
 		tty->read_head = (tty->read_head + i) & (N_TTY_BUF_SIZE-1);
 		tty->read_cnt += i;
-		ret += i;
 		cp += i;
 		count -= i;
 
@@ -1359,10 +1389,8 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty,
 		memcpy(tty->read_buf + tty->read_head, cp, i);
 		tty->read_head = (tty->read_head + i) & (N_TTY_BUF_SIZE-1);
 		tty->read_cnt += i;
-		ret += i;
 		spin_unlock_irqrestore(&tty->read_lock, cpuflags);
 	} else {
-		ret = count;
 		for (i = count, p = cp, f = fp; i; i--, p++) {
 			if (f)
 				flags = *f++;
@@ -1390,6 +1418,8 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty,
 			tty->ops->flush_chars(tty);
 	}
 
+	n_tty_set_room(tty);
+
 	if ((!tty->icanon && (tty->read_cnt >= tty->minimum_to_wake)) ||
 		L_EXTPROC(tty)) {
 		kill_fasync(&tty->fasync, SIGIO, POLL_IN);
@@ -1402,12 +1432,8 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty,
 	 * mode.  We don't want to throttle the driver if we're in
 	 * canonical mode and don't have a newline yet!
 	 */
-	left = N_TTY_BUF_SIZE - tty->read_cnt - 1;
-
-	if (left < TTY_THRESHOLD_THROTTLE)
+	if (tty->receive_room < TTY_THRESHOLD_THROTTLE)
 		tty_throttle(tty);
-
-	return ret;
 }
 
 int is_ignored(int sig)
@@ -1451,6 +1477,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
 	if (test_bit(TTY_HW_COOK_IN, &tty->flags)) {
 		tty->raw = 1;
 		tty->real_raw = 1;
+		n_tty_set_room(tty);
 		return;
 	}
 	if (I_ISTRIP(tty) || I_IUCLC(tty) || I_IGNCR(tty) ||
@@ -1503,6 +1530,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
 		else
 			tty->real_raw = 0;
 	}
+	n_tty_set_room(tty);
 	/* The termios change make the tty ready for I/O */
 	wake_up_interruptible(&tty->write_wait);
 	wake_up_interruptible(&tty->read_wait);
@@ -1784,6 +1812,8 @@ do_it_again:
 				retval = -ERESTARTSYS;
 				break;
 			}
+			/* FIXME: does n_tty_set_room need locking ? */
+			n_tty_set_room(tty);
 			timeout = schedule_timeout(timeout);
 			continue;
 		}
@@ -1855,8 +1885,10 @@ do_it_again:
 		 * longer than TTY_THRESHOLD_UNTHROTTLE in canonical mode,
 		 * we won't get any more characters.
 		 */
-		if (n_tty_chars_in_buffer(tty) <= TTY_THRESHOLD_UNTHROTTLE)
+		if (n_tty_chars_in_buffer(tty) <= TTY_THRESHOLD_UNTHROTTLE) {
+			n_tty_set_room(tty);
 			check_unthrottle(tty);
+		}
 
 		if (b - buf >= minimum)
 			break;
@@ -1878,6 +1910,7 @@ do_it_again:
 	} else if (test_and_clear_bit(TTY_PUSH, &tty->flags))
 		 goto do_it_again;
 
+	n_tty_set_room(tty);
 	return retval;
 }
 
diff --git a/drivers/tty/serial/8250_pci.c b/drivers/tty/serial/8250_pci.c
index 4b4968a294b2..78e98a5cef96 100644
--- a/drivers/tty/serial/8250_pci.c
+++ b/drivers/tty/serial/8250_pci.c
@@ -973,7 +973,7 @@ ce4100_serial_setup(struct serial_private *priv,
 
 static int
 pci_omegapci_setup(struct serial_private *priv,
-		      struct pciserial_board *board,
+		      const struct pciserial_board *board,
 		      struct uart_port *port, int idx)
 {
 	return setup_port(priv, port, 2, idx * 8, 0);
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 652bdac8ce8e..6d5d6e679fc7 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1420,7 +1420,7 @@ static void __devinit atmel_init_port(struct atmel_uart_port *atmel_port,
 	port->flags		= UPF_BOOT_AUTOCONF;
 	port->ops		= &atmel_pops;
 	port->fifosize		= 1;
-	port->line		= pdev->id;
+	port->line		= data->num;
 	port->dev		= &pdev->dev;
 	port->mapbase	= pdev->resource[0].start;
 	port->irq	= pdev->resource[1].start;
diff --git a/drivers/tty/serial/mrst_max3110.c b/drivers/tty/serial/mrst_max3110.c
index 1bd28450ca40..a764bf99743b 100644
--- a/drivers/tty/serial/mrst_max3110.c
+++ b/drivers/tty/serial/mrst_max3110.c
@@ -421,7 +421,6 @@ static int max3110_main_thread(void *_max)
 	int ret = 0;
 	struct circ_buf *xmit = &max->con_xmit;
 
-	init_waitqueue_head(wq);
 	pr_info(PR_FMT "start main thread\n");
 
 	do {
@@ -823,7 +822,7 @@ static int __devinit serial_m3110_probe(struct spi_device *spi)
 	res = RC_TAG;
 	ret = max3110_write_then_read(max, (u8 *)&res, (u8 *)&res, 2, 0);
 	if (ret < 0 || res == 0 || res == 0xffff) {
-		printk(KERN_ERR "MAX3111 deemed not present (conf reg %04x)",
+		dev_dbg(&spi->dev, "MAX3111 deemed not present (conf reg %04x)",
 									res);
 		ret = -ENODEV;
 		goto err_get_page;
@@ -838,6 +837,8 @@ static int __devinit serial_m3110_probe(struct spi_device *spi)
 	max->con_xmit.head = 0;
 	max->con_xmit.tail = 0;
 
+	init_waitqueue_head(&max->wq);
+
 	max->main_thread = kthread_run(max3110_main_thread,
 					max, "max3110_main");
 	if (IS_ERR(max->main_thread)) {
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index f2cb7503fcb2..465210930890 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -1397,6 +1397,7 @@ static struct eg20t_port *pch_uart_init_port(struct pci_dev *pdev,
 	int fifosize, base_baud;
 	int port_type;
 	struct pch_uart_driver_data *board;
+	const char *board_name;
 
 	board = &drv_dat[id->driver_data];
 	port_type = board->port_type;
@@ -1412,7 +1413,8 @@ static struct eg20t_port *pch_uart_init_port(struct pci_dev *pdev,
 	base_baud = 1843200; /* 1.8432MHz */
 
 	/* quirk for CM-iTC board */
-	if (strstr(dmi_get_system_info(DMI_BOARD_NAME), "CM-iTC"))
+	board_name = dmi_get_system_info(DMI_BOARD_NAME);
+	if (board_name && strstr(board_name, "CM-iTC"))
 		base_baud = 192000000; /* 192.0MHz */
 
 	switch (port_type) {
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index 46de2e075dac..6c9b7cd6778a 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -413,10 +413,8 @@ static void flush_to_ldisc(struct work_struct *work)
 	spin_lock_irqsave(&tty->buf.lock, flags);
 
 	if (!test_and_set_bit(TTY_FLUSHING, &tty->flags)) {
-		struct tty_buffer *head, *tail = tty->buf.tail;
-		int seen_tail = 0;
+		struct tty_buffer *head;
 		while ((head = tty->buf.head) != NULL) {
-			int copied;
 			int count;
 			char *char_buf;
 			unsigned char *flag_buf;
@@ -425,15 +423,6 @@ static void flush_to_ldisc(struct work_struct *work)
 			if (!count) {
 				if (head->next == NULL)
 					break;
-				/*
-				  There's a possibility tty might get new buffer
-				  added during the unlock window below. We could
-				  end up spinning in here forever hogging the CPU
-				  completely. To avoid this let's have a rest each
-				  time we processed the tail buffer.
-				*/
-				if (tail == head)
-					seen_tail = 1;
 				tty->buf.head = head->next;
 				tty_buffer_free(tty, head);
 				continue;
@@ -443,19 +432,17 @@ static void flush_to_ldisc(struct work_struct *work)
 			   line discipline as we want to empty the queue */
 			if (test_bit(TTY_FLUSHPENDING, &tty->flags))
 				break;
+			if (!tty->receive_room)
+				break;
+			if (count > tty->receive_room)
+				count = tty->receive_room;
 			char_buf = head->char_buf_ptr + head->read;
 			flag_buf = head->flag_buf_ptr + head->read;
+			head->read += count;
 			spin_unlock_irqrestore(&tty->buf.lock, flags);
-			copied = disc->ops->receive_buf(tty, char_buf,
+			disc->ops->receive_buf(tty, char_buf,
 							flag_buf, count);
 			spin_lock_irqsave(&tty->buf.lock, flags);
-
-			head->read += copied;
-
-			if (copied == 0 || seen_tail) {
-				schedule_work(&tty->buf.work);
-				break;
-			}
 		}
 		clear_bit(TTY_FLUSHING, &tty->flags);
 	}
diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c
index 67b1d0d7c8ac..fb864e7fcd13 100644
--- a/drivers/tty/vt/selection.c
+++ b/drivers/tty/vt/selection.c
@@ -332,7 +332,8 @@ int paste_selection(struct tty_struct *tty)
 			continue;
 		}
 		count = sel_buffer_lth - pasted;
-		count = tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted,
+		count = min(count, tty->receive_room);
+		tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted,
 								NULL, count);
 		pasted += count;
 	}
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 395a347f2ebb..dac7676ce21b 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1530,6 +1530,8 @@ static const struct usb_device_id acm_ids[] = {
 	{ NOKIA_PCSUITE_ACM_INFO(0x04ce), }, /* Nokia E90 */
 	{ NOKIA_PCSUITE_ACM_INFO(0x01d4), }, /* Nokia E55 */
 	{ NOKIA_PCSUITE_ACM_INFO(0x0302), }, /* Nokia N8 */
+	{ NOKIA_PCSUITE_ACM_INFO(0x0335), }, /* Nokia E7 */
+	{ NOKIA_PCSUITE_ACM_INFO(0x03cd), }, /* Nokia C7 */
 	{ SAMSUNG_PCSUITE_ACM_INFO(0x6651), }, /* Samsung GTi8510 (INNOV8) */
 
 	/* NOTE: non-Nokia COMM/ACM/0xff is likely MSFT RNDIS... NOT a modem! */
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index e35a17687c05..aa3cc465a601 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -375,7 +375,7 @@ static int usb_unbind_interface(struct device *dev)
 		 * Just re-enable it without affecting the endpoint toggles.
 		 */
 		usb_enable_interface(udev, intf, false);
-	} else if (!error && !intf->dev.power.in_suspend) {
+	} else if (!error && !intf->dev.power.is_prepared) {
 		r = usb_set_interface(udev, intf->altsetting[0].
 				desc.bInterfaceNumber, 0);
 		if (r < 0)
@@ -960,7 +960,7 @@ void usb_rebind_intf(struct usb_interface *intf)
 	}
 
 	/* Try to rebind the interface */
-	if (!intf->dev.power.in_suspend) {
+	if (!intf->dev.power.is_prepared) {
 		intf->needs_binding = 0;
 		rc = device_attach(&intf->dev);
 		if (rc < 0)
@@ -1107,7 +1107,7 @@ static int usb_resume_interface(struct usb_device *udev,
 	if (intf->condition == USB_INTERFACE_UNBOUND) {
 
 		/* Carry out a deferred switch to altsetting 0 */
-		if (intf->needs_altsetting0 && !intf->dev.power.in_suspend) {
+		if (intf->needs_altsetting0 && !intf->dev.power.is_prepared) {
 			usb_set_interface(udev, intf->altsetting[0].
 					desc.bInterfaceNumber, 0);
 			intf->needs_altsetting0 = 0;
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 79a58c3a2e2a..90ae1753dda1 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -339,7 +339,8 @@ static int get_hub_status(struct usb_device *hdev,
 {
 	int i, status = -ETIMEDOUT;
 
-	for (i = 0; i < USB_STS_RETRIES && status == -ETIMEDOUT; i++) {
+	for (i = 0; i < USB_STS_RETRIES &&
+			(status == -ETIMEDOUT || status == -EPIPE); i++) {
 		status = usb_control_msg(hdev, usb_rcvctrlpipe(hdev, 0),
 			USB_REQ_GET_STATUS, USB_DIR_IN | USB_RT_HUB, 0, 0,
 			data, sizeof(*data), USB_STS_TIMEOUT);
@@ -355,7 +356,8 @@ static int get_port_status(struct usb_device *hdev, int port1,
 {
 	int i, status = -ETIMEDOUT;
 
-	for (i = 0; i < USB_STS_RETRIES && status == -ETIMEDOUT; i++) {
+	for (i = 0; i < USB_STS_RETRIES &&
+			(status == -ETIMEDOUT || status == -EPIPE); i++) {
 		status = usb_control_msg(hdev, usb_rcvctrlpipe(hdev, 0),
 			USB_REQ_GET_STATUS, USB_DIR_IN | USB_RT_PORT, 0, port1,
 			data, sizeof(*data), USB_STS_TIMEOUT);
diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c
index 1b125c224dcf..2278dad886e2 100644
--- a/drivers/usb/core/inode.c
+++ b/drivers/usb/core/inode.c
@@ -389,7 +389,6 @@ static int usbfs_rmdir(struct inode *dir, struct dentry *dentry)
 	mutex_unlock(&inode->i_mutex);
 	if (!error)
 		d_delete(dentry);
-	dput(dentry);
 	return error;
 }
 
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index 58456d1aec21..029e288805b6 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -632,13 +632,10 @@ config USB_DUMMY_HCD
 
 endchoice
 
+# Selected by UDC drivers that support high-speed operation.
 config USB_GADGET_DUALSPEED
 	bool
 	depends on USB_GADGET
-	default n
-	help
-	  Means that gadget drivers should include extra descriptors
-	  and code to handle dual-speed controllers.
 
 #
 # USB Gadget Drivers
diff --git a/drivers/usb/gadget/amd5536udc.c b/drivers/usb/gadget/amd5536udc.c
index 6e42aab75806..95e8138cd48f 100644
--- a/drivers/usb/gadget/amd5536udc.c
+++ b/drivers/usb/gadget/amd5536udc.c
@@ -60,6 +60,7 @@
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/irq.h>
+#include <linux/prefetch.h>
 
 #include <asm/byteorder.h>
 #include <asm/system.h>
diff --git a/drivers/usb/gadget/at91_udc.c b/drivers/usb/gadget/at91_udc.c
index 41dc093c0a1b..f4690ffcb489 100644
--- a/drivers/usb/gadget/at91_udc.c
+++ b/drivers/usb/gadget/at91_udc.c
@@ -38,6 +38,7 @@
 #include <linux/clk.h>
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
+#include <linux/prefetch.h>
 
 #include <asm/byteorder.h>
 #include <mach/hardware.h>
diff --git a/drivers/usb/gadget/dummy_hcd.c b/drivers/usb/gadget/dummy_hcd.c
index 61ff927928ab..d3dcabc1a5fc 100644
--- a/drivers/usb/gadget/dummy_hcd.c
+++ b/drivers/usb/gadget/dummy_hcd.c
@@ -1906,6 +1906,7 @@ static int dummy_hcd_probe(struct platform_device *pdev)
 	if (!hcd)
 		return -ENOMEM;
 	the_controller = hcd_to_dummy (hcd);
+	hcd->has_tt = 1;
 
 	retval = usb_add_hcd(hcd, 0, 0);
 	if (retval != 0) {
diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c
index a01383f71f38..a56876aaf76c 100644
--- a/drivers/usb/gadget/inode.c
+++ b/drivers/usb/gadget/inode.c
@@ -431,8 +431,10 @@ ep_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 
 	/* halt any endpoint by doing a "wrong direction" i/o call */
 	if (!usb_endpoint_dir_in(&data->desc)) {
-		if (usb_endpoint_xfer_isoc(&data->desc))
+		if (usb_endpoint_xfer_isoc(&data->desc)) {
+			mutex_unlock(&data->lock);
 			return -EINVAL;
+		}
 		DBG (data->dev, "%s halt\n", data->name);
 		spin_lock_irq (&data->dev->lock);
 		if (likely (data->ep != NULL))
diff --git a/drivers/usb/gadget/mv_udc_core.c b/drivers/usb/gadget/mv_udc_core.c
index b62b2640deb0..b1a8146b9d50 100644
--- a/drivers/usb/gadget/mv_udc_core.c
+++ b/drivers/usb/gadget/mv_udc_core.c
@@ -2083,7 +2083,7 @@ out:
 }
 
 #ifdef CONFIG_PM
-static int mv_udc_suspend(struct platform_device *_dev, pm_message_t state)
+static int mv_udc_suspend(struct device *_dev)
 {
 	struct mv_udc *udc = the_controller;
 
@@ -2092,7 +2092,7 @@ static int mv_udc_suspend(struct platform_device *_dev, pm_message_t state)
 	return 0;
 }
 
-static int mv_udc_resume(struct platform_device *_dev)
+static int mv_udc_resume(struct device *_dev)
 {
 	struct mv_udc *udc = the_controller;
 	int retval;
@@ -2100,7 +2100,7 @@ static int mv_udc_resume(struct platform_device *_dev)
 	retval = mv_udc_phy_init(udc->phy_regs);
 	if (retval) {
 		dev_err(_dev, "phy initialization error %d\n", retval);
-		goto error;
+		return retval;
 	}
 	udc_reset(udc);
 	ep0_reset(udc);
@@ -2122,7 +2122,7 @@ static struct platform_driver udc_driver = {
 		.owner	= THIS_MODULE,
 		.name	= "pxa-u2o",
 #ifdef CONFIG_PM
-		.pm	= mv_udc_pm_ops,
+		.pm	= &mv_udc_pm_ops,
 #endif
 	},
 };
diff --git a/drivers/usb/gadget/net2280.c b/drivers/usb/gadget/net2280.c
index 24696f7fa6a9..476d88e1ae97 100644
--- a/drivers/usb/gadget/net2280.c
+++ b/drivers/usb/gadget/net2280.c
@@ -63,6 +63,7 @@
 #include <linux/device.h>
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
+#include <linux/prefetch.h>
 
 #include <asm/byteorder.h>
 #include <asm/io.h>
diff --git a/drivers/usb/gadget/pxa25x_udc.c b/drivers/usb/gadget/pxa25x_udc.c
index 365c02fc25fc..774545494cf2 100644
--- a/drivers/usb/gadget/pxa25x_udc.c
+++ b/drivers/usb/gadget/pxa25x_udc.c
@@ -2216,7 +2216,6 @@ static int __init pxa25x_udc_probe(struct platform_device *pdev)
 		if (retval != 0) {
 			pr_err("%s: can't get irq %i, err %d\n",
 				driver_name, LUBBOCK_USB_DISC_IRQ, retval);
-lubbock_fail0:
 			goto err_irq_lub;
 		}
 		retval = request_irq(LUBBOCK_USB_IRQ,
@@ -2226,7 +2225,6 @@ lubbock_fail0:
 		if (retval != 0) {
 			pr_err("%s: can't get irq %i, err %d\n",
 				driver_name, LUBBOCK_USB_IRQ, retval);
-			free_irq(LUBBOCK_USB_DISC_IRQ, dev);
 			goto lubbock_fail0;
 		}
 	} else
@@ -2236,10 +2234,11 @@ lubbock_fail0:
 	return 0;
 
 #ifdef	CONFIG_ARCH_LUBBOCK
+lubbock_fail0:
 	free_irq(LUBBOCK_USB_DISC_IRQ, dev);
  err_irq_lub:
-#endif
 	free_irq(irq, dev);
+#endif
  err_irq1:
 	if (gpio_is_valid(dev->mach->gpio_pullup))
 		gpio_free(dev->mach->gpio_pullup);
diff --git a/drivers/usb/gadget/s3c-hsotg.c b/drivers/usb/gadget/s3c-hsotg.c
index acb9cc418df9..0dfee282878a 100644
--- a/drivers/usb/gadget/s3c-hsotg.c
+++ b/drivers/usb/gadget/s3c-hsotg.c
@@ -2680,9 +2680,9 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver,
 
 	writel(0, hsotg->regs + S3C_DAINTMSK);
 
-	dev_info(hsotg->dev, "EP0: DIEPCTL0=0x%08x, DOEPCTL0=0x%08x\n",
-		 readl(hsotg->regs + S3C_DIEPCTL0),
-		 readl(hsotg->regs + S3C_DOEPCTL0));
+	dev_dbg(hsotg->dev, "EP0: DIEPCTL0=0x%08x, DOEPCTL0=0x%08x\n",
+		readl(hsotg->regs + S3C_DIEPCTL0),
+		readl(hsotg->regs + S3C_DOEPCTL0));
 
 	/* enable in and out endpoint interrupts */
 	s3c_hsotg_en_gsint(hsotg, S3C_GINTSTS_OEPInt | S3C_GINTSTS_IEPInt);
@@ -2701,7 +2701,7 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver,
 	udelay(10);  /* see openiboot */
 	__bic32(hsotg->regs + S3C_DCTL, S3C_DCTL_PWROnPrgDone);
 
-	dev_info(hsotg->dev, "DCTL=0x%08x\n", readl(hsotg->regs + S3C_DCTL));
+	dev_dbg(hsotg->dev, "DCTL=0x%08x\n", readl(hsotg->regs + S3C_DCTL));
 
 	/* S3C_DxEPCTL_USBActEp says RO in manual, but seems to be set by
 	   writing to the EPCTL register.. */
@@ -2721,9 +2721,9 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver,
 
 	s3c_hsotg_enqueue_setup(hsotg);
 
-	dev_info(hsotg->dev, "EP0: DIEPCTL0=0x%08x, DOEPCTL0=0x%08x\n",
-		 readl(hsotg->regs + S3C_DIEPCTL0),
-		 readl(hsotg->regs + S3C_DOEPCTL0));
+	dev_dbg(hsotg->dev, "EP0: DIEPCTL0=0x%08x, DOEPCTL0=0x%08x\n",
+		readl(hsotg->regs + S3C_DIEPCTL0),
+		readl(hsotg->regs + S3C_DOEPCTL0));
 
 	/* clear global NAKs */
 	writel(S3C_DCTL_CGOUTNak | S3C_DCTL_CGNPInNAK,
@@ -2921,9 +2921,9 @@ static void s3c_hsotg_init(struct s3c_hsotg *hsotg)
 
 	/* setup fifos */
 
-	dev_info(hsotg->dev, "GRXFSIZ=0x%08x, GNPTXFSIZ=0x%08x\n",
-		 readl(hsotg->regs + S3C_GRXFSIZ),
-		 readl(hsotg->regs + S3C_GNPTXFSIZ));
+	dev_dbg(hsotg->dev, "GRXFSIZ=0x%08x, GNPTXFSIZ=0x%08x\n",
+		readl(hsotg->regs + S3C_GRXFSIZ),
+		readl(hsotg->regs + S3C_GNPTXFSIZ));
 
 	s3c_hsotg_init_fifo(hsotg);
 
@@ -2945,6 +2945,7 @@ static void s3c_hsotg_init(struct s3c_hsotg *hsotg)
 
 static void s3c_hsotg_dump(struct s3c_hsotg *hsotg)
 {
+#ifdef DEBUG
 	struct device *dev = hsotg->dev;
 	void __iomem *regs = hsotg->regs;
 	u32 val;
@@ -2987,6 +2988,7 @@ static void s3c_hsotg_dump(struct s3c_hsotg *hsotg)
 
 	dev_info(dev, "DVBUSDIS=0x%08x, DVBUSPULSE=%08x\n",
 		 readl(regs + S3C_DVBUSDIS), readl(regs + S3C_DVBUSPULSE));
+#endif
 }
 
 
diff --git a/drivers/usb/gadget/s3c-hsudc.c b/drivers/usb/gadget/s3c-hsudc.c
index cfe3cf56d6bd..d5e3e1e58626 100644
--- a/drivers/usb/gadget/s3c-hsudc.c
+++ b/drivers/usb/gadget/s3c-hsudc.c
@@ -26,6 +26,7 @@
 #include <linux/clk.h>
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
+#include <linux/prefetch.h>
 
 #include <mach/regs-s3c2443-clock.h>
 #include <plat/udc.h>
@@ -1301,7 +1302,8 @@ static int s3c_hsudc_probe(struct platform_device *pdev)
 	hsudc->uclk = clk_get(&pdev->dev, "usb-device");
 	if (IS_ERR(hsudc->uclk)) {
 		dev_err(dev, "failed to find usb-device clock source\n");
-		return PTR_ERR(hsudc->uclk);
+		ret = PTR_ERR(hsudc->uclk);
+		goto err_clk;
 	}
 	clk_enable(hsudc->uclk);
 
@@ -1310,7 +1312,8 @@ static int s3c_hsudc_probe(struct platform_device *pdev)
 	disable_irq(hsudc->irq);
 	local_irq_enable();
 	return 0;
-
+err_clk:
+	free_irq(hsudc->irq, hsudc);
 err_irq:
 	iounmap(hsudc->regs);
 
diff --git a/drivers/usb/gadget/s3c2410_udc.c b/drivers/usb/gadget/s3c2410_udc.c
index 6d8b04061d5d..100f2635cf0a 100644
--- a/drivers/usb/gadget/s3c2410_udc.c
+++ b/drivers/usb/gadget/s3c2410_udc.c
@@ -36,6 +36,7 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/gpio.h>
+#include <linux/prefetch.h>
 
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index 660b80a75cac..1102ce65a3a9 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -348,11 +348,50 @@ static int ehci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
 	return rc;
 }
 
+static bool usb_is_intel_switchable_ehci(struct pci_dev *pdev)
+{
+	return pdev->class == PCI_CLASS_SERIAL_USB_EHCI &&
+		pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		pdev->device == 0x1E26;
+}
+
+static void ehci_enable_xhci_companion(void)
+{
+	struct pci_dev		*companion = NULL;
+
+	/* The xHCI and EHCI controllers are not on the same PCI slot */
+	for_each_pci_dev(companion) {
+		if (!usb_is_intel_switchable_xhci(companion))
+			continue;
+		usb_enable_xhci_ports(companion);
+		return;
+	}
+}
+
 static int ehci_pci_resume(struct usb_hcd *hcd, bool hibernated)
 {
 	struct ehci_hcd		*ehci = hcd_to_ehci(hcd);
 	struct pci_dev		*pdev = to_pci_dev(hcd->self.controller);
 
+	/* The BIOS on systems with the Intel Panther Point chipset may or may
+	 * not support xHCI natively.  That means that during system resume, it
+	 * may switch the ports back to EHCI so that users can use their
+	 * keyboard to select a kernel from GRUB after resume from hibernate.
+	 *
+	 * The BIOS is supposed to remember whether the OS had xHCI ports
+	 * enabled before resume, and switch the ports back to xHCI when the
+	 * BIOS/OS semaphore is written, but we all know we can't trust BIOS
+	 * writers.
+	 *
+	 * Unconditionally switch the ports back to xHCI after a system resume.
+	 * We can't tell whether the EHCI or xHCI controller will be resumed
+	 * first, so we have to do the port switchover in both drivers.  Writing
+	 * a '1' to the port switchover registers should have no effect if the
+	 * port was already switched over.
+	 */
+	if (usb_is_intel_switchable_ehci(pdev))
+		ehci_enable_xhci_companion();
+
 	// maybe restore FLADJ
 
 	if (time_before(jiffies, ehci->next_statechange))
diff --git a/drivers/usb/host/ohci-pxa27x.c b/drivers/usb/host/ohci-pxa27x.c
index afef7b0a4195..80be5472783a 100644
--- a/drivers/usb/host/ohci-pxa27x.c
+++ b/drivers/usb/host/ohci-pxa27x.c
@@ -312,8 +312,10 @@ int usb_hcd_pxa27x_probe (const struct hc_driver *driver, struct platform_device
 		return PTR_ERR(usb_clk);
 
 	hcd = usb_create_hcd (driver, &pdev->dev, "pxa27x");
-	if (!hcd)
-		return -ENOMEM;
+	if (!hcd) {
+		retval = -ENOMEM;
+		goto err0;
+	}
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!r) {
@@ -368,6 +370,7 @@ int usb_hcd_pxa27x_probe (const struct hc_driver *driver, struct platform_device
 	release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
  err1:
 	usb_put_hcd(hcd);
+ err0:
 	clk_put(usb_clk);
 	return retval;
 }
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index f16c59d5f487..fd930618c28f 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -69,6 +69,9 @@
 #define	NB_PIF0_PWRDOWN_0	0x01100012
 #define	NB_PIF0_PWRDOWN_1	0x01100013
 
+#define USB_INTEL_XUSB2PR      0xD0
+#define USB_INTEL_USB3_PSSEN   0xD8
+
 static struct amd_chipset_info {
 	struct pci_dev	*nb_dev;
 	struct pci_dev	*smbus_dev;
@@ -673,6 +676,64 @@ static int handshake(void __iomem *ptr, u32 mask, u32 done,
 	return -ETIMEDOUT;
 }
 
+bool usb_is_intel_switchable_xhci(struct pci_dev *pdev)
+{
+	return pdev->class == PCI_CLASS_SERIAL_USB_XHCI &&
+		pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		pdev->device == PCI_DEVICE_ID_INTEL_PANTHERPOINT_XHCI;
+}
+EXPORT_SYMBOL_GPL(usb_is_intel_switchable_xhci);
+
+/*
+ * Intel's Panther Point chipset has two host controllers (EHCI and xHCI) that
+ * share some number of ports.  These ports can be switched between either
+ * controller.  Not all of the ports under the EHCI host controller may be
+ * switchable.
+ *
+ * The ports should be switched over to xHCI before PCI probes for any device
+ * start.  This avoids active devices under EHCI being disconnected during the
+ * port switchover, which could cause loss of data on USB storage devices, or
+ * failed boot when the root file system is on a USB mass storage device and is
+ * enumerated under EHCI first.
+ *
+ * We write into the xHC's PCI configuration space in some Intel-specific
+ * registers to switch the ports over.  The USB 3.0 terminations and the USB
+ * 2.0 data wires are switched separately.  We want to enable the SuperSpeed
+ * terminations before switching the USB 2.0 wires over, so that USB 3.0
+ * devices connect at SuperSpeed, rather than at USB 2.0 speeds.
+ */
+void usb_enable_xhci_ports(struct pci_dev *xhci_pdev)
+{
+	u32		ports_available;
+
+	ports_available = 0xffffffff;
+	/* Write USB3_PSSEN, the USB 3.0 Port SuperSpeed Enable
+	 * Register, to turn on SuperSpeed terminations for all
+	 * available ports.
+	 */
+	pci_write_config_dword(xhci_pdev, USB_INTEL_USB3_PSSEN,
+			cpu_to_le32(ports_available));
+
+	pci_read_config_dword(xhci_pdev, USB_INTEL_USB3_PSSEN,
+			&ports_available);
+	dev_dbg(&xhci_pdev->dev, "USB 3.0 ports that are now enabled "
+			"under xHCI: 0x%x\n", ports_available);
+
+	ports_available = 0xffffffff;
+	/* Write XUSB2PR, the xHC USB 2.0 Port Routing Register, to
+	 * switch the USB 2.0 power and data lines over to the xHCI
+	 * host.
+	 */
+	pci_write_config_dword(xhci_pdev, USB_INTEL_XUSB2PR,
+			cpu_to_le32(ports_available));
+
+	pci_read_config_dword(xhci_pdev, USB_INTEL_XUSB2PR,
+			&ports_available);
+	dev_dbg(&xhci_pdev->dev, "USB 2.0 ports that are now switched over "
+			"to xHCI: 0x%x\n", ports_available);
+}
+EXPORT_SYMBOL_GPL(usb_enable_xhci_ports);
+
 /**
  * PCI Quirks for xHCI.
  *
@@ -732,6 +793,8 @@ static void __devinit quirk_usb_handoff_xhci(struct pci_dev *pdev)
 	writel(XHCI_LEGACY_DISABLE_SMI,
 			base + ext_cap_offset + XHCI_LEGACY_CONTROL_OFFSET);
 
+	if (usb_is_intel_switchable_xhci(pdev))
+		usb_enable_xhci_ports(pdev);
 hc_init:
 	op_reg_base = base + XHCI_HC_LENGTH(readl(base));
 
diff --git a/drivers/usb/host/pci-quirks.h b/drivers/usb/host/pci-quirks.h
index 6ae9f78e9938..b1002a8ef96f 100644
--- a/drivers/usb/host/pci-quirks.h
+++ b/drivers/usb/host/pci-quirks.h
@@ -8,6 +8,8 @@ int usb_amd_find_chipset_info(void);
 void usb_amd_dev_put(void);
 void usb_amd_quirk_pll_disable(void);
 void usb_amd_quirk_pll_enable(void);
+bool usb_is_intel_switchable_xhci(struct pci_dev *pdev);
+void usb_enable_xhci_ports(struct pci_dev *xhci_pdev);
 #else
 static inline void usb_amd_quirk_pll_disable(void) {}
 static inline void usb_amd_quirk_pll_enable(void) {}
diff --git a/drivers/usb/host/xhci-dbg.c b/drivers/usb/host/xhci-dbg.c
index 2e0486178dbe..1f50b4468e87 100644
--- a/drivers/usb/host/xhci-dbg.c
+++ b/drivers/usb/host/xhci-dbg.c
@@ -438,13 +438,13 @@ char *xhci_get_slot_state(struct xhci_hcd *xhci,
 	struct xhci_slot_ctx *slot_ctx = xhci_get_slot_ctx(xhci, ctx);
 
 	switch (GET_SLOT_STATE(le32_to_cpu(slot_ctx->dev_state))) {
-	case 0:
+	case SLOT_STATE_ENABLED:
 		return "enabled/disabled";
-	case 1:
+	case SLOT_STATE_DEFAULT:
 		return "default";
-	case 2:
+	case SLOT_STATE_ADDRESSED:
 		return "addressed";
-	case 3:
+	case SLOT_STATE_CONFIGURED:
 		return "configured";
 	default:
 		return "reserved";
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 26caba4c1950..0f8e1d29a858 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -985,9 +985,19 @@ static unsigned int xhci_parse_exponent_interval(struct usb_device *udev,
 	interval = clamp_val(ep->desc.bInterval, 1, 16) - 1;
 	if (interval != ep->desc.bInterval - 1)
 		dev_warn(&udev->dev,
-			 "ep %#x - rounding interval to %d microframes\n",
+			 "ep %#x - rounding interval to %d %sframes\n",
 			 ep->desc.bEndpointAddress,
-			 1 << interval);
+			 1 << interval,
+			 udev->speed == USB_SPEED_FULL ? "" : "micro");
+
+	if (udev->speed == USB_SPEED_FULL) {
+		/*
+		 * Full speed isoc endpoints specify interval in frames,
+		 * not microframes. We are using microframes everywhere,
+		 * so adjust accordingly.
+		 */
+		interval += 3;	/* 1 frame = 2^3 uframes */
+	}
 
 	return interval;
 }
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index cbc4d491e626..17541d09eabb 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -106,18 +106,34 @@ static int xhci_pci_setup(struct usb_hcd *hcd)
 
 	/* Look for vendor-specific quirks */
 	if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC &&
-			pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_PDK &&
-			pdev->revision == 0x0) {
+			pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_PDK) {
+		if (pdev->revision == 0x0) {
 			xhci->quirks |= XHCI_RESET_EP_QUIRK;
 			xhci_dbg(xhci, "QUIRK: Fresco Logic xHC needs configure"
 					" endpoint cmd after reset endpoint\n");
+		}
+		/* Fresco Logic confirms: all revisions of this chip do not
+		 * support MSI, even though some of them claim to in their PCI
+		 * capabilities.
+		 */
+		xhci->quirks |= XHCI_BROKEN_MSI;
+		xhci_dbg(xhci, "QUIRK: Fresco Logic revision %u "
+				"has broken MSI implementation\n",
+				pdev->revision);
 	}
+
 	if (pdev->vendor == PCI_VENDOR_ID_NEC)
 		xhci->quirks |= XHCI_NEC_HOST;
 
 	/* AMD PLL quirk */
 	if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info())
 		xhci->quirks |= XHCI_AMD_PLL_FIX;
+	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+			pdev->device == PCI_DEVICE_ID_INTEL_PANTHERPOINT_XHCI) {
+		xhci->quirks |= XHCI_SPURIOUS_SUCCESS;
+		xhci->quirks |= XHCI_EP_LIMIT_QUIRK;
+		xhci->limit_active_eps = 64;
+	}
 
 	/* Make sure the HC is halted. */
 	retval = xhci_halt(xhci);
@@ -242,8 +258,28 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
 static int xhci_pci_resume(struct usb_hcd *hcd, bool hibernated)
 {
 	struct xhci_hcd		*xhci = hcd_to_xhci(hcd);
+	struct pci_dev		*pdev = to_pci_dev(hcd->self.controller);
 	int			retval = 0;
 
+	/* The BIOS on systems with the Intel Panther Point chipset may or may
+	 * not support xHCI natively.  That means that during system resume, it
+	 * may switch the ports back to EHCI so that users can use their
+	 * keyboard to select a kernel from GRUB after resume from hibernate.
+	 *
+	 * The BIOS is supposed to remember whether the OS had xHCI ports
+	 * enabled before resume, and switch the ports back to xHCI when the
+	 * BIOS/OS semaphore is written, but we all know we can't trust BIOS
+	 * writers.
+	 *
+	 * Unconditionally switch the ports back to xHCI after a system resume.
+	 * We can't tell whether the EHCI or xHCI controller will be resumed
+	 * first, so we have to do the port switchover in both drivers.  Writing
+	 * a '1' to the port switchover registers should have no effect if the
+	 * port was already switched over.
+	 */
+	if (usb_is_intel_switchable_xhci(pdev))
+		usb_enable_xhci_ports(pdev);
+
 	retval = xhci_resume(xhci, hibernated);
 	return retval;
 }
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 237a765f8d18..800f417c7309 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -167,12 +167,6 @@ static void inc_deq(struct xhci_hcd *xhci, struct xhci_ring *ring, bool consumer
 		next = ring->dequeue;
 	}
 	addr = (unsigned long long) xhci_trb_virt_to_dma(ring->deq_seg, ring->dequeue);
-	if (ring == xhci->event_ring)
-		xhci_dbg(xhci, "Event ring deq = 0x%llx (DMA)\n", addr);
-	else if (ring == xhci->cmd_ring)
-		xhci_dbg(xhci, "Command ring deq = 0x%llx (DMA)\n", addr);
-	else
-		xhci_dbg(xhci, "Ring deq = 0x%llx (DMA)\n", addr);
 }
 
 /*
@@ -248,12 +242,6 @@ static void inc_enq(struct xhci_hcd *xhci, struct xhci_ring *ring,
 		next = ring->enqueue;
 	}
 	addr = (unsigned long long) xhci_trb_virt_to_dma(ring->enq_seg, ring->enqueue);
-	if (ring == xhci->event_ring)
-		xhci_dbg(xhci, "Event ring enq = 0x%llx (DMA)\n", addr);
-	else if (ring == xhci->cmd_ring)
-		xhci_dbg(xhci, "Command ring enq = 0x%llx (DMA)\n", addr);
-	else
-		xhci_dbg(xhci, "Ring enq = 0x%llx (DMA)\n", addr);
 }
 
 /*
@@ -636,13 +624,11 @@ static void xhci_giveback_urb_in_irq(struct xhci_hcd *xhci,
 			}
 		}
 		usb_hcd_unlink_urb_from_ep(hcd, urb);
-		xhci_dbg(xhci, "Giveback %s URB %p\n", adjective, urb);
 
 		spin_unlock(&xhci->lock);
 		usb_hcd_giveback_urb(hcd, urb, status);
 		xhci_urb_free_priv(xhci, urb_priv);
 		spin_lock(&xhci->lock);
-		xhci_dbg(xhci, "%s URB given back\n", adjective);
 	}
 }
 
@@ -692,6 +678,8 @@ static void handle_stopped_endpoint(struct xhci_hcd *xhci,
 
 	if (list_empty(&ep->cancelled_td_list)) {
 		xhci_stop_watchdog_timer_in_irq(xhci, ep);
+		ep->stopped_td = NULL;
+		ep->stopped_trb = NULL;
 		ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
 		return;
 	}
@@ -1093,8 +1081,13 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 		complete(&xhci->addr_dev);
 		break;
 	case TRB_TYPE(TRB_DISABLE_SLOT):
-		if (xhci->devs[slot_id])
+		if (xhci->devs[slot_id]) {
+			if (xhci->quirks & XHCI_EP_LIMIT_QUIRK)
+				/* Delete default control endpoint resources */
+				xhci_free_device_endpoint_resources(xhci,
+						xhci->devs[slot_id], true);
 			xhci_free_virt_device(xhci, slot_id);
+		}
 		break;
 	case TRB_TYPE(TRB_CONFIG_EP):
 		virt_dev = xhci->devs[slot_id];
@@ -1630,7 +1623,6 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td,
 					"without IOC set??\n");
 			*status = -ESHUTDOWN;
 		} else {
-			xhci_dbg(xhci, "Successful control transfer!\n");
 			*status = 0;
 		}
 		break;
@@ -1727,7 +1719,6 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td,
 	switch (trb_comp_code) {
 	case COMP_SUCCESS:
 		frame->status = 0;
-		xhci_dbg(xhci, "Successful isoc transfer!\n");
 		break;
 	case COMP_SHORT_TX:
 		frame->status = td->urb->transfer_flags & URB_SHORT_NOT_OK ?
@@ -1791,7 +1782,7 @@ static int skip_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td,
 	struct usb_iso_packet_descriptor *frame;
 	int idx;
 
-	ep_ring = xhci_dma_to_transfer_ring(ep, event->buffer);
+	ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer));
 	urb_priv = td->urb->hcpriv;
 	idx = urb_priv->td_cnt;
 	frame = &td->urb->iso_frame_desc[idx];
@@ -1837,12 +1828,6 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td,
 			else
 				*status = 0;
 		} else {
-			if (usb_endpoint_xfer_bulk(&td->urb->ep->desc))
-				xhci_dbg(xhci, "Successful bulk "
-						"transfer!\n");
-			else
-				xhci_dbg(xhci, "Successful interrupt "
-						"transfer!\n");
 			*status = 0;
 		}
 		break;
@@ -1856,11 +1841,12 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td,
 		/* Others already handled above */
 		break;
 	}
-	xhci_dbg(xhci, "ep %#x - asked for %d bytes, "
-			"%d bytes untransferred\n",
-			td->urb->ep->desc.bEndpointAddress,
-			td->urb->transfer_buffer_length,
-		 TRB_LEN(le32_to_cpu(event->transfer_len)));
+	if (trb_comp_code == COMP_SHORT_TX)
+		xhci_dbg(xhci, "ep %#x - asked for %d bytes, "
+				"%d bytes untransferred\n",
+				td->urb->ep->desc.bEndpointAddress,
+				td->urb->transfer_buffer_length,
+				TRB_LEN(le32_to_cpu(event->transfer_len)));
 	/* Fast path - was this the last TRB in the TD for this URB? */
 	if (event_trb == td->last_trb) {
 		if (TRB_LEN(le32_to_cpu(event->transfer_len)) != 0) {
@@ -1954,7 +1940,6 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 
 	/* Endpoint ID is 1 based, our index is zero based */
 	ep_index = TRB_TO_EP_ID(le32_to_cpu(event->flags)) - 1;
-	xhci_dbg(xhci, "%s - ep index = %d\n", __func__, ep_index);
 	ep = &xdev->eps[ep_index];
 	ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer));
 	ep_ctx = xhci_get_ep_ctx(xhci, xdev->out_ctx, ep_index);
@@ -2081,6 +2066,16 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 		if (!event_seg) {
 			if (!ep->skip ||
 			    !usb_endpoint_xfer_isoc(&td->urb->ep->desc)) {
+				/* Some host controllers give a spurious
+				 * successful event after a short transfer.
+				 * Ignore it.
+				 */
+				if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) && 
+						ep_ring->last_td_was_short) {
+					ep_ring->last_td_was_short = false;
+					ret = 0;
+					goto cleanup;
+				}
 				/* HC is busted, give up! */
 				xhci_err(xhci,
 					"ERROR Transfer event TRB DMA ptr not "
@@ -2091,6 +2086,10 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 			ret = skip_isoc_td(xhci, td, event, ep, &status);
 			goto cleanup;
 		}
+		if (trb_comp_code == COMP_SHORT_TX)
+			ep_ring->last_td_was_short = true;
+		else
+			ep_ring->last_td_was_short = false;
 
 		if (ep->skip) {
 			xhci_dbg(xhci, "Found td. Clear skip flag.\n");
@@ -2149,9 +2148,15 @@ cleanup:
 				xhci_urb_free_priv(xhci, urb_priv);
 
 			usb_hcd_unlink_urb_from_ep(bus_to_hcd(urb->dev->bus), urb);
-			xhci_dbg(xhci, "Giveback URB %p, len = %d, "
-					"status = %d\n",
-					urb, urb->actual_length, status);
+			if ((urb->actual_length != urb->transfer_buffer_length &&
+						(urb->transfer_flags &
+						 URB_SHORT_NOT_OK)) ||
+					status != 0)
+				xhci_dbg(xhci, "Giveback URB %p, len = %d, "
+						"expected = %x, status = %d\n",
+						urb, urb->actual_length,
+						urb->transfer_buffer_length,
+						status);
 			spin_unlock(&xhci->lock);
 			usb_hcd_giveback_urb(bus_to_hcd(urb->dev->bus), urb, status);
 			spin_lock(&xhci->lock);
@@ -2180,7 +2185,6 @@ static int xhci_handle_event(struct xhci_hcd *xhci)
 	int update_ptrs = 1;
 	int ret;
 
-	xhci_dbg(xhci, "In %s\n", __func__);
 	if (!xhci->event_ring || !xhci->event_ring->dequeue) {
 		xhci->error_bitmask |= 1 << 1;
 		return 0;
@@ -2193,7 +2197,6 @@ static int xhci_handle_event(struct xhci_hcd *xhci)
 		xhci->error_bitmask |= 1 << 2;
 		return 0;
 	}
-	xhci_dbg(xhci, "%s - OS owns TRB\n", __func__);
 
 	/*
 	 * Barrier between reading the TRB_CYCLE (valid) flag above and any
@@ -2203,20 +2206,14 @@ static int xhci_handle_event(struct xhci_hcd *xhci)
 	/* FIXME: Handle more event types. */
 	switch ((le32_to_cpu(event->event_cmd.flags) & TRB_TYPE_BITMASK)) {
 	case TRB_TYPE(TRB_COMPLETION):
-		xhci_dbg(xhci, "%s - calling handle_cmd_completion\n", __func__);
 		handle_cmd_completion(xhci, &event->event_cmd);
-		xhci_dbg(xhci, "%s - returned from handle_cmd_completion\n", __func__);
 		break;
 	case TRB_TYPE(TRB_PORT_STATUS):
-		xhci_dbg(xhci, "%s - calling handle_port_status\n", __func__);
 		handle_port_status(xhci, event);
-		xhci_dbg(xhci, "%s - returned from handle_port_status\n", __func__);
 		update_ptrs = 0;
 		break;
 	case TRB_TYPE(TRB_TRANSFER):
-		xhci_dbg(xhci, "%s - calling handle_tx_event\n", __func__);
 		ret = handle_tx_event(xhci, &event->trans_event);
-		xhci_dbg(xhci, "%s - returned from handle_tx_event\n", __func__);
 		if (ret < 0)
 			xhci->error_bitmask |= 1 << 9;
 		else
@@ -2273,16 +2270,6 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd)
 		spin_unlock(&xhci->lock);
 		return IRQ_NONE;
 	}
-	xhci_dbg(xhci, "op reg status = %08x\n", status);
-	xhci_dbg(xhci, "Event ring dequeue ptr:\n");
-	xhci_dbg(xhci, "@%llx %08x %08x %08x %08x\n",
-		 (unsigned long long)
-		 xhci_trb_virt_to_dma(xhci->event_ring->deq_seg, trb),
-		 lower_32_bits(le64_to_cpu(trb->link.segment_ptr)),
-		 upper_32_bits(le64_to_cpu(trb->link.segment_ptr)),
-		 (unsigned int) le32_to_cpu(trb->link.intr_target),
-		 (unsigned int) le32_to_cpu(trb->link.control));
-
 	if (status & STS_FATAL) {
 		xhci_warn(xhci, "WARNING: Host System Error\n");
 		xhci_halt(xhci);
@@ -2397,7 +2384,6 @@ static int prepare_ring(struct xhci_hcd *xhci, struct xhci_ring *ep_ring,
 		u32 ep_state, unsigned int num_trbs, gfp_t mem_flags)
 {
 	/* Make sure the endpoint has been added to xHC schedule */
-	xhci_dbg(xhci, "Endpoint state = 0x%x\n", ep_state);
 	switch (ep_state) {
 	case EP_STATE_DISABLED:
 		/*
@@ -2434,7 +2420,6 @@ static int prepare_ring(struct xhci_hcd *xhci, struct xhci_ring *ep_ring,
 		struct xhci_ring *ring = ep_ring;
 		union xhci_trb *next;
 
-		xhci_dbg(xhci, "prepare_ring: pointing to link trb\n");
 		next = ring->enqueue;
 
 		while (last_trb(xhci, ring, ring->enq_seg, next)) {
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 8f2a56ece44f..06e7023258d0 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -430,12 +430,19 @@ int xhci_run(struct usb_hcd *hcd)
 		free_irq(hcd->irq, hcd);
 	hcd->irq = -1;
 
+	/* Some Fresco Logic host controllers advertise MSI, but fail to
+	 * generate interrupts.  Don't even try to enable MSI.
+	 */
+	if (xhci->quirks & XHCI_BROKEN_MSI)
+		goto legacy_irq;
+
 	ret = xhci_setup_msix(xhci);
 	if (ret)
 		/* fall back to msi*/
 		ret = xhci_setup_msi(xhci);
 
 	if (ret) {
+legacy_irq:
 		/* fall back to legacy interrupt*/
 		ret = request_irq(pdev->irq, &usb_hcd_irq, IRQF_SHARED,
 					hcd->irq_descr, hcd);
@@ -1314,8 +1321,10 @@ int xhci_drop_endpoint(struct usb_hcd *hcd, struct usb_device *udev,
 	if (ret <= 0)
 		return ret;
 	xhci = hcd_to_xhci(hcd);
-	xhci_dbg(xhci, "%s called for udev %p\n", __func__, udev);
+	if (xhci->xhc_state & XHCI_STATE_DYING)
+		return -ENODEV;
 
+	xhci_dbg(xhci, "%s called for udev %p\n", __func__, udev);
 	drop_flag = xhci_get_endpoint_flag(&ep->desc);
 	if (drop_flag == SLOT_FLAG || drop_flag == EP0_FLAG) {
 		xhci_dbg(xhci, "xHCI %s - can't drop slot or ep 0 %#x\n",
@@ -1401,6 +1410,8 @@ int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev,
 		return ret;
 	}
 	xhci = hcd_to_xhci(hcd);
+	if (xhci->xhc_state & XHCI_STATE_DYING)
+		return -ENODEV;
 
 	added_ctxs = xhci_get_endpoint_flag(&ep->desc);
 	last_ctx = xhci_last_valid_endpoint(added_ctxs);
@@ -1578,6 +1589,113 @@ static int xhci_evaluate_context_result(struct xhci_hcd *xhci,
 	return ret;
 }
 
+static u32 xhci_count_num_new_endpoints(struct xhci_hcd *xhci,
+		struct xhci_container_ctx *in_ctx)
+{
+	struct xhci_input_control_ctx *ctrl_ctx;
+	u32 valid_add_flags;
+	u32 valid_drop_flags;
+
+	ctrl_ctx = xhci_get_input_control_ctx(xhci, in_ctx);
+	/* Ignore the slot flag (bit 0), and the default control endpoint flag
+	 * (bit 1).  The default control endpoint is added during the Address
+	 * Device command and is never removed until the slot is disabled.
+	 */
+	valid_add_flags = ctrl_ctx->add_flags >> 2;
+	valid_drop_flags = ctrl_ctx->drop_flags >> 2;
+
+	/* Use hweight32 to count the number of ones in the add flags, or
+	 * number of endpoints added.  Don't count endpoints that are changed
+	 * (both added and dropped).
+	 */
+	return hweight32(valid_add_flags) -
+		hweight32(valid_add_flags & valid_drop_flags);
+}
+
+static unsigned int xhci_count_num_dropped_endpoints(struct xhci_hcd *xhci,
+		struct xhci_container_ctx *in_ctx)
+{
+	struct xhci_input_control_ctx *ctrl_ctx;
+	u32 valid_add_flags;
+	u32 valid_drop_flags;
+
+	ctrl_ctx = xhci_get_input_control_ctx(xhci, in_ctx);
+	valid_add_flags = ctrl_ctx->add_flags >> 2;
+	valid_drop_flags = ctrl_ctx->drop_flags >> 2;
+
+	return hweight32(valid_drop_flags) -
+		hweight32(valid_add_flags & valid_drop_flags);
+}
+
+/*
+ * We need to reserve the new number of endpoints before the configure endpoint
+ * command completes.  We can't subtract the dropped endpoints from the number
+ * of active endpoints until the command completes because we can oversubscribe
+ * the host in this case:
+ *
+ *  - the first configure endpoint command drops more endpoints than it adds
+ *  - a second configure endpoint command that adds more endpoints is queued
+ *  - the first configure endpoint command fails, so the config is unchanged
+ *  - the second command may succeed, even though there isn't enough resources
+ *
+ * Must be called with xhci->lock held.
+ */
+static int xhci_reserve_host_resources(struct xhci_hcd *xhci,
+		struct xhci_container_ctx *in_ctx)
+{
+	u32 added_eps;
+
+	added_eps = xhci_count_num_new_endpoints(xhci, in_ctx);
+	if (xhci->num_active_eps + added_eps > xhci->limit_active_eps) {
+		xhci_dbg(xhci, "Not enough ep ctxs: "
+				"%u active, need to add %u, limit is %u.\n",
+				xhci->num_active_eps, added_eps,
+				xhci->limit_active_eps);
+		return -ENOMEM;
+	}
+	xhci->num_active_eps += added_eps;
+	xhci_dbg(xhci, "Adding %u ep ctxs, %u now active.\n", added_eps,
+			xhci->num_active_eps);
+	return 0;
+}
+
+/*
+ * The configure endpoint was failed by the xHC for some other reason, so we
+ * need to revert the resources that failed configuration would have used.
+ *
+ * Must be called with xhci->lock held.
+ */
+static void xhci_free_host_resources(struct xhci_hcd *xhci,
+		struct xhci_container_ctx *in_ctx)
+{
+	u32 num_failed_eps;
+
+	num_failed_eps = xhci_count_num_new_endpoints(xhci, in_ctx);
+	xhci->num_active_eps -= num_failed_eps;
+	xhci_dbg(xhci, "Removing %u failed ep ctxs, %u now active.\n",
+			num_failed_eps,
+			xhci->num_active_eps);
+}
+
+/*
+ * Now that the command has completed, clean up the active endpoint count by
+ * subtracting out the endpoints that were dropped (but not changed).
+ *
+ * Must be called with xhci->lock held.
+ */
+static void xhci_finish_resource_reservation(struct xhci_hcd *xhci,
+		struct xhci_container_ctx *in_ctx)
+{
+	u32 num_dropped_eps;
+
+	num_dropped_eps = xhci_count_num_dropped_endpoints(xhci, in_ctx);
+	xhci->num_active_eps -= num_dropped_eps;
+	if (num_dropped_eps)
+		xhci_dbg(xhci, "Removing %u dropped ep ctxs, %u now active.\n",
+				num_dropped_eps,
+				xhci->num_active_eps);
+}
+
 /* Issue a configure endpoint command or evaluate context command
  * and wait for it to finish.
  */
@@ -1598,6 +1716,15 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
 	virt_dev = xhci->devs[udev->slot_id];
 	if (command) {
 		in_ctx = command->in_ctx;
+		if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK) &&
+				xhci_reserve_host_resources(xhci, in_ctx)) {
+			spin_unlock_irqrestore(&xhci->lock, flags);
+			xhci_warn(xhci, "Not enough host resources, "
+					"active endpoint contexts = %u\n",
+					xhci->num_active_eps);
+			return -ENOMEM;
+		}
+
 		cmd_completion = command->completion;
 		cmd_status = &command->status;
 		command->command_trb = xhci->cmd_ring->enqueue;
@@ -1613,6 +1740,14 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
 		list_add_tail(&command->cmd_list, &virt_dev->cmd_list);
 	} else {
 		in_ctx = virt_dev->in_ctx;
+		if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK) &&
+				xhci_reserve_host_resources(xhci, in_ctx)) {
+			spin_unlock_irqrestore(&xhci->lock, flags);
+			xhci_warn(xhci, "Not enough host resources, "
+					"active endpoint contexts = %u\n",
+					xhci->num_active_eps);
+			return -ENOMEM;
+		}
 		cmd_completion = &virt_dev->cmd_completion;
 		cmd_status = &virt_dev->cmd_status;
 	}
@@ -1627,6 +1762,8 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
 	if (ret < 0) {
 		if (command)
 			list_del(&command->cmd_list);
+		if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK))
+			xhci_free_host_resources(xhci, in_ctx);
 		spin_unlock_irqrestore(&xhci->lock, flags);
 		xhci_dbg(xhci, "FIXME allocate a new ring segment\n");
 		return -ENOMEM;
@@ -1649,8 +1786,22 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
 	}
 
 	if (!ctx_change)
-		return xhci_configure_endpoint_result(xhci, udev, cmd_status);
-	return xhci_evaluate_context_result(xhci, udev, cmd_status);
+		ret = xhci_configure_endpoint_result(xhci, udev, cmd_status);
+	else
+		ret = xhci_evaluate_context_result(xhci, udev, cmd_status);
+
+	if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK)) {
+		spin_lock_irqsave(&xhci->lock, flags);
+		/* If the command failed, remove the reserved resources.
+		 * Otherwise, clean up the estimate to include dropped eps.
+		 */
+		if (ret)
+			xhci_free_host_resources(xhci, in_ctx);
+		else
+			xhci_finish_resource_reservation(xhci, in_ctx);
+		spin_unlock_irqrestore(&xhci->lock, flags);
+	}
+	return ret;
 }
 
 /* Called after one or more calls to xhci_add_endpoint() or
@@ -1676,6 +1827,8 @@ int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev)
 	if (ret <= 0)
 		return ret;
 	xhci = hcd_to_xhci(hcd);
+	if (xhci->xhc_state & XHCI_STATE_DYING)
+		return -ENODEV;
 
 	xhci_dbg(xhci, "%s called for udev %p\n", __func__, udev);
 	virt_dev = xhci->devs[udev->slot_id];
@@ -1703,8 +1856,8 @@ int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev)
 
 	/* Free any rings that were dropped, but not changed. */
 	for (i = 1; i < 31; ++i) {
-		if ((ctrl_ctx->drop_flags & (1 << (i + 1))) &&
-				!(ctrl_ctx->add_flags & (1 << (i + 1))))
+		if ((le32_to_cpu(ctrl_ctx->drop_flags) & (1 << (i + 1))) &&
+		    !(le32_to_cpu(ctrl_ctx->add_flags) & (1 << (i + 1))))
 			xhci_free_or_cache_endpoint_ring(xhci, virt_dev, i);
 	}
 	xhci_zero_in_ctx(xhci, virt_dev);
@@ -2266,6 +2419,34 @@ int xhci_free_streams(struct usb_hcd *hcd, struct usb_device *udev,
 }
 
 /*
+ * Deletes endpoint resources for endpoints that were active before a Reset
+ * Device command, or a Disable Slot command.  The Reset Device command leaves
+ * the control endpoint intact, whereas the Disable Slot command deletes it.
+ *
+ * Must be called with xhci->lock held.
+ */
+void xhci_free_device_endpoint_resources(struct xhci_hcd *xhci,
+	struct xhci_virt_device *virt_dev, bool drop_control_ep)
+{
+	int i;
+	unsigned int num_dropped_eps = 0;
+	unsigned int drop_flags = 0;
+
+	for (i = (drop_control_ep ? 0 : 1); i < 31; i++) {
+		if (virt_dev->eps[i].ring) {
+			drop_flags |= 1 << i;
+			num_dropped_eps++;
+		}
+	}
+	xhci->num_active_eps -= num_dropped_eps;
+	if (num_dropped_eps)
+		xhci_dbg(xhci, "Dropped %u ep ctxs, flags = 0x%x, "
+				"%u now active.\n",
+				num_dropped_eps, drop_flags,
+				xhci->num_active_eps);
+}
+
+/*
  * This submits a Reset Device Command, which will set the device state to 0,
  * set the device address to 0, and disable all the endpoints except the default
  * control endpoint.  The USB core should come back and call
@@ -2293,6 +2474,7 @@ int xhci_discover_or_reset_device(struct usb_hcd *hcd, struct usb_device *udev)
 	struct xhci_command *reset_device_cmd;
 	int timeleft;
 	int last_freed_endpoint;
+	struct xhci_slot_ctx *slot_ctx;
 
 	ret = xhci_check_args(hcd, udev, NULL, 0, false, __func__);
 	if (ret <= 0)
@@ -2325,6 +2507,12 @@ int xhci_discover_or_reset_device(struct usb_hcd *hcd, struct usb_device *udev)
 			return -EINVAL;
 	}
 
+	/* If device is not setup, there is no point in resetting it */
+	slot_ctx = xhci_get_slot_ctx(xhci, virt_dev->out_ctx);
+	if (GET_SLOT_STATE(le32_to_cpu(slot_ctx->dev_state)) ==
+						SLOT_STATE_DISABLED)
+		return 0;
+
 	xhci_dbg(xhci, "Resetting device with slot ID %u\n", slot_id);
 	/* Allocate the command structure that holds the struct completion.
 	 * Assume we're in process context, since the normal device reset
@@ -2406,6 +2594,14 @@ int xhci_discover_or_reset_device(struct usb_hcd *hcd, struct usb_device *udev)
 		goto command_cleanup;
 	}
 
+	/* Free up host controller endpoint resources */
+	if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK)) {
+		spin_lock_irqsave(&xhci->lock, flags);
+		/* Don't delete the default control endpoint resources */
+		xhci_free_device_endpoint_resources(xhci, virt_dev, false);
+		spin_unlock_irqrestore(&xhci->lock, flags);
+	}
+
 	/* Everything but endpoint 0 is disabled, so free or cache the rings. */
 	last_freed_endpoint = 1;
 	for (i = 1; i < 31; ++i) {
@@ -2479,6 +2675,27 @@ void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev)
 }
 
 /*
+ * Checks if we have enough host controller resources for the default control
+ * endpoint.
+ *
+ * Must be called with xhci->lock held.
+ */
+static int xhci_reserve_host_control_ep_resources(struct xhci_hcd *xhci)
+{
+	if (xhci->num_active_eps + 1 > xhci->limit_active_eps) {
+		xhci_dbg(xhci, "Not enough ep ctxs: "
+				"%u active, need to add 1, limit is %u.\n",
+				xhci->num_active_eps, xhci->limit_active_eps);
+		return -ENOMEM;
+	}
+	xhci->num_active_eps += 1;
+	xhci_dbg(xhci, "Adding 1 ep ctx, %u now active.\n",
+			xhci->num_active_eps);
+	return 0;
+}
+
+
+/*
  * Returns 0 if the xHC ran out of device slots, the Enable Slot command
  * timed out, or allocating memory failed.  Returns 1 on success.
  */
@@ -2513,24 +2730,39 @@ int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev)
 		xhci_err(xhci, "Error while assigning device slot ID\n");
 		return 0;
 	}
-	/* xhci_alloc_virt_device() does not touch rings; no need to lock.
-	 * Use GFP_NOIO, since this function can be called from
+
+	if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK)) {
+		spin_lock_irqsave(&xhci->lock, flags);
+		ret = xhci_reserve_host_control_ep_resources(xhci);
+		if (ret) {
+			spin_unlock_irqrestore(&xhci->lock, flags);
+			xhci_warn(xhci, "Not enough host resources, "
+					"active endpoint contexts = %u\n",
+					xhci->num_active_eps);
+			goto disable_slot;
+		}
+		spin_unlock_irqrestore(&xhci->lock, flags);
+	}
+	/* Use GFP_NOIO, since this function can be called from
 	 * xhci_discover_or_reset_device(), which may be called as part of
 	 * mass storage driver error handling.
 	 */
 	if (!xhci_alloc_virt_device(xhci, xhci->slot_id, udev, GFP_NOIO)) {
-		/* Disable slot, if we can do it without mem alloc */
 		xhci_warn(xhci, "Could not allocate xHCI USB device data structures\n");
-		spin_lock_irqsave(&xhci->lock, flags);
-		if (!xhci_queue_slot_control(xhci, TRB_DISABLE_SLOT, udev->slot_id))
-			xhci_ring_cmd_db(xhci);
-		spin_unlock_irqrestore(&xhci->lock, flags);
-		return 0;
+		goto disable_slot;
 	}
 	udev->slot_id = xhci->slot_id;
 	/* Is this a LS or FS device under a HS hub? */
 	/* Hub or peripherial? */
 	return 1;
+
+disable_slot:
+	/* Disable slot, if we can do it without mem alloc */
+	spin_lock_irqsave(&xhci->lock, flags);
+	if (!xhci_queue_slot_control(xhci, TRB_DISABLE_SLOT, udev->slot_id))
+		xhci_ring_cmd_db(xhci);
+	spin_unlock_irqrestore(&xhci->lock, flags);
+	return 0;
 }
 
 /*
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index e12db7cfb9bb..7d1ea3bf5e1f 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -560,6 +560,11 @@ struct xhci_slot_ctx {
 #define SLOT_STATE	(0x1f << 27)
 #define GET_SLOT_STATE(p)	(((p) & (0x1f << 27)) >> 27)
 
+#define SLOT_STATE_DISABLED	0
+#define SLOT_STATE_ENABLED	SLOT_STATE_DISABLED
+#define SLOT_STATE_DEFAULT	1
+#define SLOT_STATE_ADDRESSED	2
+#define SLOT_STATE_CONFIGURED	3
 
 /**
  * struct xhci_ep_ctx
@@ -1123,6 +1128,7 @@ struct xhci_ring {
 	 */
 	u32			cycle_state;
 	unsigned int		stream_id;
+	bool			last_td_was_short;
 };
 
 struct xhci_erst_entry {
@@ -1290,6 +1296,20 @@ struct xhci_hcd {
 #define XHCI_RESET_EP_QUIRK	(1 << 1)
 #define XHCI_NEC_HOST		(1 << 2)
 #define XHCI_AMD_PLL_FIX	(1 << 3)
+#define XHCI_SPURIOUS_SUCCESS	(1 << 4)
+/*
+ * Certain Intel host controllers have a limit to the number of endpoint
+ * contexts they can handle.  Ideally, they would signal that they can't handle
+ * anymore endpoint contexts by returning a Resource Error for the Configure
+ * Endpoint command, but they don't.  Instead they expect software to keep track
+ * of the number of active endpoints for them, across configure endpoint
+ * commands, reset device commands, disable slot commands, and address device
+ * commands.
+ */
+#define XHCI_EP_LIMIT_QUIRK	(1 << 5)
+#define XHCI_BROKEN_MSI		(1 << 6)
+	unsigned int		num_active_eps;
+	unsigned int		limit_active_eps;
 	/* There are two roothubs to keep track of bus suspend info for */
 	struct xhci_bus_state   bus_state[2];
 	/* Is each xHCI roothub port a USB 3.0, USB 2.0, or USB 1.1 port? */
@@ -1338,9 +1358,6 @@ static inline unsigned int xhci_readl(const struct xhci_hcd *xhci,
 static inline void xhci_writel(struct xhci_hcd *xhci,
 		const unsigned int val, __le32 __iomem *regs)
 {
-	xhci_dbg(xhci,
-			"`MEM_WRITE_DWORD(3'b000, 32'h%p, 32'h%0x, 4'hf);\n",
-			regs, val);
 	writel(val, regs);
 }
 
@@ -1368,9 +1385,6 @@ static inline void xhci_write_64(struct xhci_hcd *xhci,
 	u32 val_lo = lower_32_bits(val);
 	u32 val_hi = upper_32_bits(val);
 
-	xhci_dbg(xhci,
-			"`MEM_WRITE_DWORD(3'b000, 64'h%p, 64'h%0lx, 4'hf);\n",
-			regs, (long unsigned int) val);
 	writel(val_lo, ptr);
 	writel(val_hi, ptr + 1);
 }
@@ -1439,6 +1453,8 @@ void xhci_setup_streams_ep_input_ctx(struct xhci_hcd *xhci,
 void xhci_setup_no_streams_ep_input_ctx(struct xhci_hcd *xhci,
 		struct xhci_ep_ctx *ep_ctx,
 		struct xhci_virt_ep *ep);
+void xhci_free_device_endpoint_resources(struct xhci_hcd *xhci,
+	struct xhci_virt_device *virt_dev, bool drop_control_ep);
 struct xhci_ring *xhci_dma_to_transfer_ring(
 		struct xhci_virt_ep *ep,
 		u64 address);
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index ab8e1001e5e2..c71b0372786e 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -96,6 +96,7 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/kobject.h>
+#include <linux/prefetch.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
 
diff --git a/drivers/usb/otg/twl6030-usb.c b/drivers/usb/otg/twl6030-usb.c
index 3f2e07011a48..cfb5aa72b196 100644
--- a/drivers/usb/otg/twl6030-usb.c
+++ b/drivers/usb/otg/twl6030-usb.c
@@ -100,6 +100,7 @@ struct twl6030_usb {
 	u8			linkstat;
 	u8			asleep;
 	bool			irq_enabled;
+	unsigned long		features;
 };
 
 #define xceiv_to_twl(x)		container_of((x), struct twl6030_usb, otg)
@@ -204,6 +205,12 @@ static int twl6030_start_srp(struct otg_transceiver *x)
 
 static int twl6030_usb_ldo_init(struct twl6030_usb *twl)
 {
+	char *regulator_name;
+
+	if (twl->features & TWL6025_SUBCLASS)
+		regulator_name = "ldousb";
+	else
+		regulator_name = "vusb";
 
 	/* Set to OTG_REV 1.3 and turn on the ID_WAKEUP_COMP */
 	twl6030_writeb(twl, TWL6030_MODULE_ID0 , 0x1, TWL6030_BACKUP_REG);
@@ -214,7 +221,7 @@ static int twl6030_usb_ldo_init(struct twl6030_usb *twl)
 	/* Program MISC2 register and set bit VUSB_IN_VBAT */
 	twl6030_writeb(twl, TWL6030_MODULE_ID0 , 0x10, TWL6030_MISC2);
 
-	twl->usb3v3 = regulator_get(twl->dev, "vusb");
+	twl->usb3v3 = regulator_get(twl->dev, regulator_name);
 	if (IS_ERR(twl->usb3v3))
 		return -ENODEV;
 
@@ -409,6 +416,7 @@ static int __devinit twl6030_usb_probe(struct platform_device *pdev)
 	twl->dev		= &pdev->dev;
 	twl->irq1		= platform_get_irq(pdev, 0);
 	twl->irq2		= platform_get_irq(pdev, 1);
+	twl->features		= pdata->features;
 	twl->otg.dev		= twl->dev;
 	twl->otg.label		= "twl6030";
 	twl->otg.set_host	= twl6030_set_host;
diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c
index 206cfabc9286..547486ccd059 100644
--- a/drivers/usb/renesas_usbhs/mod_gadget.c
+++ b/drivers/usb/renesas_usbhs/mod_gadget.c
@@ -1380,5 +1380,6 @@ void __devexit usbhs_mod_gadget_remove(struct usbhs_priv *priv)
 {
 	struct usbhsg_gpriv *gpriv = usbhsg_priv_to_gpriv(priv);
 
+	kfree(gpriv->uep);
 	kfree(gpriv);
 }
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index e8dbde55f6c5..162728977553 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -647,6 +647,7 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(FTDI_VID, EVER_ECO_PRO_CDS) },
 	{ USB_DEVICE(FTDI_VID, FTDI_4N_GALAXY_DE_1_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_4N_GALAXY_DE_2_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_4N_GALAXY_DE_3_PID) },
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_0_PID) },
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_1_PID) },
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_2_PID) },
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 1d946cd238ba..ab1fcdf3c378 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -351,6 +351,7 @@
  */
 #define FTDI_4N_GALAXY_DE_1_PID	0xF3C0
 #define FTDI_4N_GALAXY_DE_2_PID	0xF3C1
+#define FTDI_4N_GALAXY_DE_3_PID	0xF3C2
 
 /*
  * Linx Technologies product ids
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 318dd00040a3..60b25d8ea0e2 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -311,10 +311,6 @@ static void option_instat_callback(struct urb *urb);
 #define ZTE_PRODUCT_AC2726			0xfff5
 #define ZTE_PRODUCT_AC8710T			0xffff
 
-/* ZTE PRODUCTS -- alternate vendor ID */
-#define ZTE_VENDOR_ID2				0x1d6b
-#define ZTE_PRODUCT_MF_330			0x0002
-
 #define BENQ_VENDOR_ID				0x04a5
 #define BENQ_PRODUCT_H10			0x4068
 
@@ -340,11 +336,12 @@ static void option_instat_callback(struct urb *urb);
 #define TOSHIBA_PRODUCT_G450			0x0d45
 
 #define ALINK_VENDOR_ID				0x1e0e
+#define ALINK_PRODUCT_PH300			0x9100
 #define ALINK_PRODUCT_3GU			0x9200
 
 /* ALCATEL PRODUCTS */
 #define ALCATEL_VENDOR_ID			0x1bbb
-#define ALCATEL_PRODUCT_X060S			0x0000
+#define ALCATEL_PRODUCT_X060S_X200		0x0000
 
 #define PIRELLI_VENDOR_ID			0x1266
 #define PIRELLI_PRODUCT_C100_1			0x1002
@@ -379,6 +376,9 @@ static void option_instat_callback(struct urb *urb);
  * It seems to contain a Qualcomm QSC6240/6290 chipset            */
 #define FOUR_G_SYSTEMS_PRODUCT_W14		0x9603
 
+/* Zoom */
+#define ZOOM_PRODUCT_4597			0x9607
+
 /* Haier products */
 #define HAIER_VENDOR_ID				0x201e
 #define HAIER_PRODUCT_CE100			0x2009
@@ -432,6 +432,20 @@ static const struct option_blacklist_info four_g_w14_blacklist = {
 	.reason = OPTION_BLACKLIST_SENDSETUP
 };
 
+static const u8 alcatel_x200_no_sendsetup[] = { 0, 1 };
+static const struct option_blacklist_info alcatel_x200_blacklist = {
+	.infolen = ARRAY_SIZE(alcatel_x200_no_sendsetup),
+	.ifaceinfo = alcatel_x200_no_sendsetup,
+	.reason = OPTION_BLACKLIST_SENDSETUP
+};
+
+static const u8 zte_k3765_z_no_sendsetup[] = { 0, 1, 2 };
+static const struct option_blacklist_info zte_k3765_z_blacklist = {
+	.infolen = ARRAY_SIZE(zte_k3765_z_no_sendsetup),
+	.ifaceinfo = zte_k3765_z_no_sendsetup,
+	.reason = OPTION_BLACKLIST_SENDSETUP
+};
+
 static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) },
 	{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) },
@@ -916,13 +930,13 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0073, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0130, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0141, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x2002, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x2002, 0xff,
+	  0xff, 0xff), .driver_info = (kernel_ulong_t)&zte_k3765_z_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x2003, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_CDMA_TECH, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710T, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE(ZTE_VENDOR_ID2, ZTE_PRODUCT_MF_330) },
 	{ USB_DEVICE(BENQ_VENDOR_ID, BENQ_PRODUCT_H10) },
 	{ USB_DEVICE(DLINK_VENDOR_ID, DLINK_PRODUCT_DWM_652) },
 	{ USB_DEVICE(ALINK_VENDOR_ID, DLINK_PRODUCT_DWM_652_U5) }, /* Yes, ALINK_VENDOR_ID */
@@ -935,13 +949,17 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(TOSHIBA_VENDOR_ID, TOSHIBA_PRODUCT_G450) },
 	{ USB_DEVICE(TOSHIBA_VENDOR_ID, TOSHIBA_PRODUCT_HSDPA_MINICARD ) }, /* Toshiba 3G HSDPA == Novatel Expedite EU870D MiniCard */
 	{ USB_DEVICE(ALINK_VENDOR_ID, 0x9000) },
+	{ USB_DEVICE(ALINK_VENDOR_ID, ALINK_PRODUCT_PH300) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ALINK_VENDOR_ID, ALINK_PRODUCT_3GU, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S) },
+	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S_X200),
+	  .driver_info = (kernel_ulong_t)&alcatel_x200_blacklist
+	},
 	{ USB_DEVICE(AIRPLUS_VENDOR_ID, AIRPLUS_PRODUCT_MCD650) },
 	{ USB_DEVICE(TLAYTECH_VENDOR_ID, TLAYTECH_PRODUCT_TEU800) },
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W14),
   	  .driver_info = (kernel_ulong_t)&four_g_w14_blacklist
   	},
+	{ USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) },
 	{ USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) },
 	/* Pirelli  */
 	{ USB_DEVICE(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_C100_1)},
diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c
index 00418995d8e9..e8ae21b2d387 100644
--- a/drivers/usb/storage/transport.c
+++ b/drivers/usb/storage/transport.c
@@ -819,6 +819,35 @@ Retry_Sense:
 		}
 	}
 
+	/*
+	 * Some devices don't work or return incorrect data the first
+	 * time they get a READ(10) command, or for the first READ(10)
+	 * after a media change.  If the INITIAL_READ10 flag is set,
+	 * keep track of whether READ(10) commands succeed.  If the
+	 * previous one succeeded and this one failed, set the REDO_READ10
+	 * flag to force a retry.
+	 */
+	if (unlikely((us->fflags & US_FL_INITIAL_READ10) &&
+			srb->cmnd[0] == READ_10)) {
+		if (srb->result == SAM_STAT_GOOD) {
+			set_bit(US_FLIDX_READ10_WORKED, &us->dflags);
+		} else if (test_bit(US_FLIDX_READ10_WORKED, &us->dflags)) {
+			clear_bit(US_FLIDX_READ10_WORKED, &us->dflags);
+			set_bit(US_FLIDX_REDO_READ10, &us->dflags);
+		}
+
+		/*
+		 * Next, if the REDO_READ10 flag is set, return a result
+		 * code that will cause the SCSI core to retry the READ(10)
+		 * command immediately.
+		 */
+		if (test_bit(US_FLIDX_REDO_READ10, &us->dflags)) {
+			clear_bit(US_FLIDX_REDO_READ10, &us->dflags);
+			srb->result = DID_IMM_RETRY << 16;
+			srb->sense_buffer[0] = 0;
+		}
+	}
+
 	/* Did we transfer less than the minimum amount required? */
 	if ((srb->result == SAM_STAT_GOOD || srb->sense_buffer[2] == 0) &&
 			scsi_bufflen(srb) - scsi_get_resid(srb) < srb->underflow)
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index c1602b8c5594..ccff3483eebc 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1114,6 +1114,16 @@ UNUSUAL_DEV( 0x090c, 0x1132, 0x0000, 0xffff,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_FIX_CAPACITY ),
 
+/* Reported by Paul Hartman <paul.hartman+linux@gmail.com>
+ * This card reader returns "Illegal Request, Logical Block Address
+ * Out of Range" for the first READ(10) after a new card is inserted.
+ */
+UNUSUAL_DEV(  0x090c, 0x6000, 0x0100, 0x0100,
+		"Feiya",
+		"SD/SDHC Card Reader",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_INITIAL_READ10 ),
+
 /* This Pentax still camera is not conformant
  * to the USB storage specification: -
  * - It does not like the INQUIRY command. So we must handle this command
@@ -1888,6 +1898,15 @@ UNUSUAL_DEV( 0x1908, 0x3335, 0x0200, 0x0200,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_READ_DISC_INFO ),
 
+/* Reported by Sven Geggus <sven-usbst@geggus.net>
+ * This encrypted pen drive returns bogus data for the initial READ(10).
+ */
+UNUSUAL_DEV(  0x1b1c, 0x1ab5, 0x0200, 0x0200,
+		"Corsair",
+		"Padlock v2",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_INITIAL_READ10 ),
+
 /* Patch by Richard Schütz <r.schtz@t-online.de>
  * This external hard drive enclosure uses a JMicron chip which
  * needs the US_FL_IGNORE_RESIDUE flag to work properly. */
diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c
index 5ee7ac42e08f..0ca095820f3e 100644
--- a/drivers/usb/storage/usb.c
+++ b/drivers/usb/storage/usb.c
@@ -440,7 +440,8 @@ static void adjust_quirks(struct us_data *us)
 			US_FL_NOT_LOCKABLE | US_FL_MAX_SECTORS_64 |
 			US_FL_CAPACITY_OK | US_FL_IGNORE_RESIDUE |
 			US_FL_SINGLE_LUN | US_FL_NO_WP_DETECT |
-			US_FL_NO_READ_DISC_INFO | US_FL_NO_READ_CAPACITY_16);
+			US_FL_NO_READ_DISC_INFO | US_FL_NO_READ_CAPACITY_16 |
+			US_FL_INITIAL_READ10);
 
 	p = quirks;
 	while (*p) {
@@ -490,6 +491,9 @@ static void adjust_quirks(struct us_data *us)
 		case 'm':
 			f |= US_FL_MAX_SECTORS_64;
 			break;
+		case 'n':
+			f |= US_FL_INITIAL_READ10;
+			break;
 		case 'o':
 			f |= US_FL_CAPACITY_OK;
 			break;
@@ -953,6 +957,13 @@ int usb_stor_probe2(struct us_data *us)
 	if (result)
 		goto BadDevice;
 
+	/*
+	 * If the device returns invalid data for the first READ(10)
+	 * command, indicate the command should be retried.
+	 */
+	if (us->fflags & US_FL_INITIAL_READ10)
+		set_bit(US_FLIDX_REDO_READ10, &us->dflags);
+
 	/* Acquire all the other resources and add the host */
 	result = usb_stor_acquire_resources(us);
 	if (result)
diff --git a/drivers/usb/storage/usb.h b/drivers/usb/storage/usb.h
index 89d3bfff98df..7b0f2113632e 100644
--- a/drivers/usb/storage/usb.h
+++ b/drivers/usb/storage/usb.h
@@ -73,6 +73,8 @@ struct us_unusual_dev {
 #define US_FLIDX_RESETTING	4	/* device reset in progress */
 #define US_FLIDX_TIMED_OUT	5	/* SCSI midlayer timed out  */
 #define US_FLIDX_DONT_SCAN	6	/* don't scan (disconnect)  */
+#define US_FLIDX_REDO_READ10	7	/* redo READ(10) command    */
+#define US_FLIDX_READ10_WORKED	8	/* previous READ(10) succeeded */
 
 #define USB_STOR_STRING_LEN 32
 
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 2f7c76a85e53..e224a92baa16 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -144,7 +144,7 @@ static void handle_tx(struct vhost_net *net)
 	}
 
 	mutex_lock(&vq->mutex);
-	vhost_disable_notify(vq);
+	vhost_disable_notify(&net->dev, vq);
 
 	if (wmem < sock->sk->sk_sndbuf / 2)
 		tx_poll_stop(net);
@@ -166,8 +166,8 @@ static void handle_tx(struct vhost_net *net)
 				set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
 				break;
 			}
-			if (unlikely(vhost_enable_notify(vq))) {
-				vhost_disable_notify(vq);
+			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+				vhost_disable_notify(&net->dev, vq);
 				continue;
 			}
 			break;
@@ -315,7 +315,7 @@ static void handle_rx(struct vhost_net *net)
 		return;
 
 	mutex_lock(&vq->mutex);
-	vhost_disable_notify(vq);
+	vhost_disable_notify(&net->dev, vq);
 	vhost_hlen = vq->vhost_hlen;
 	sock_hlen = vq->sock_hlen;
 
@@ -334,10 +334,10 @@ static void handle_rx(struct vhost_net *net)
 			break;
 		/* OK, now we need to know about added descriptors. */
 		if (!headcount) {
-			if (unlikely(vhost_enable_notify(vq))) {
+			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
 				/* They have slipped one in as we were
 				 * doing that: check again. */
-				vhost_disable_notify(vq);
+				vhost_disable_notify(&net->dev, vq);
 				continue;
 			}
 			/* Nothing new?  Wait for eventfd to tell us
diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index 099f30230d06..734e1d74ad80 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -49,7 +49,7 @@ static void handle_vq(struct vhost_test *n)
 		return;
 
 	mutex_lock(&vq->mutex);
-	vhost_disable_notify(vq);
+	vhost_disable_notify(&n->dev, vq);
 
 	for (;;) {
 		head = vhost_get_vq_desc(&n->dev, vq, vq->iov,
@@ -61,8 +61,8 @@ static void handle_vq(struct vhost_test *n)
 			break;
 		/* Nothing new?  Wait for eventfd to tell us they refilled. */
 		if (head == vq->num) {
-			if (unlikely(vhost_enable_notify(vq))) {
-				vhost_disable_notify(vq);
+			if (unlikely(vhost_enable_notify(&n->dev, vq))) {
+				vhost_disable_notify(&n->dev, vq);
 				continue;
 			}
 			break;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 7aa4eea930f1..ea966b356352 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -37,6 +37,9 @@ enum {
 	VHOST_MEMORY_F_LOG = 0x1,
 };
 
+#define vhost_used_event(vq) ((u16 __user *)&vq->avail->ring[vq->num])
+#define vhost_avail_event(vq) ((u16 __user *)&vq->used->ring[vq->num])
+
 static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
 			    poll_table *pt)
 {
@@ -161,6 +164,8 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->last_avail_idx = 0;
 	vq->avail_idx = 0;
 	vq->last_used_idx = 0;
+	vq->signalled_used = 0;
+	vq->signalled_used_valid = false;
 	vq->used_flags = 0;
 	vq->log_used = false;
 	vq->log_addr = -1ull;
@@ -489,16 +494,17 @@ static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
 	return 1;
 }
 
-static int vq_access_ok(unsigned int num,
+static int vq_access_ok(struct vhost_dev *d, unsigned int num,
 			struct vring_desc __user *desc,
 			struct vring_avail __user *avail,
 			struct vring_used __user *used)
 {
+	size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 	return access_ok(VERIFY_READ, desc, num * sizeof *desc) &&
 	       access_ok(VERIFY_READ, avail,
-			 sizeof *avail + num * sizeof *avail->ring) &&
+			 sizeof *avail + num * sizeof *avail->ring + s) &&
 	       access_ok(VERIFY_WRITE, used,
-			sizeof *used + num * sizeof *used->ring);
+			sizeof *used + num * sizeof *used->ring + s);
 }
 
 /* Can we log writes? */
@@ -514,9 +520,11 @@ int vhost_log_access_ok(struct vhost_dev *dev)
 
 /* Verify access for write logging. */
 /* Caller should have vq mutex and device mutex */
-static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base)
+static int vq_log_access_ok(struct vhost_dev *d, struct vhost_virtqueue *vq,
+			    void __user *log_base)
 {
 	struct vhost_memory *mp;
+	size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 
 	mp = rcu_dereference_protected(vq->dev->memory,
 				       lockdep_is_held(&vq->mutex));
@@ -524,15 +532,15 @@ static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base)
 			    vhost_has_feature(vq->dev, VHOST_F_LOG_ALL)) &&
 		(!vq->log_used || log_access_ok(log_base, vq->log_addr,
 					sizeof *vq->used +
-					vq->num * sizeof *vq->used->ring));
+					vq->num * sizeof *vq->used->ring + s));
 }
 
 /* Can we start vq? */
 /* Caller should have vq mutex and device mutex */
 int vhost_vq_access_ok(struct vhost_virtqueue *vq)
 {
-	return vq_access_ok(vq->num, vq->desc, vq->avail, vq->used) &&
-		vq_log_access_ok(vq, vq->log_base);
+	return vq_access_ok(vq->dev, vq->num, vq->desc, vq->avail, vq->used) &&
+		vq_log_access_ok(vq->dev, vq, vq->log_base);
 }
 
 static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
@@ -577,6 +585,7 @@ static int init_used(struct vhost_virtqueue *vq,
 
 	if (r)
 		return r;
+	vq->signalled_used_valid = false;
 	return get_user(vq->last_used_idx, &used->idx);
 }
 
@@ -674,7 +683,7 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 		 * If it is not, we don't as size might not have been setup.
 		 * We will verify when backend is configured. */
 		if (vq->private_data) {
-			if (!vq_access_ok(vq->num,
+			if (!vq_access_ok(d, vq->num,
 				(void __user *)(unsigned long)a.desc_user_addr,
 				(void __user *)(unsigned long)a.avail_user_addr,
 				(void __user *)(unsigned long)a.used_user_addr)) {
@@ -818,7 +827,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
 			vq = d->vqs + i;
 			mutex_lock(&vq->mutex);
 			/* If ring is inactive, will check when it's enabled. */
-			if (vq->private_data && !vq_log_access_ok(vq, base))
+			if (vq->private_data && !vq_log_access_ok(d, vq, base))
 				r = -EFAULT;
 			else
 				vq->log_base = base;
@@ -1219,6 +1228,10 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 
 	/* On success, increment avail index. */
 	vq->last_avail_idx++;
+
+	/* Assume notifications from guest are disabled at this point,
+	 * if they aren't we would need to update avail_event index. */
+	BUG_ON(!(vq->used_flags & VRING_USED_F_NO_NOTIFY));
 	return head;
 }
 
@@ -1267,6 +1280,12 @@ int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
 			eventfd_signal(vq->log_ctx, 1);
 	}
 	vq->last_used_idx++;
+	/* If the driver never bothers to signal in a very long while,
+	 * used index might wrap around. If that happens, invalidate
+	 * signalled_used index we stored. TODO: make sure driver
+	 * signals at least once in 2^16 and remove this. */
+	if (unlikely(vq->last_used_idx == vq->signalled_used))
+		vq->signalled_used_valid = false;
 	return 0;
 }
 
@@ -1275,6 +1294,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 			    unsigned count)
 {
 	struct vring_used_elem __user *used;
+	u16 old, new;
 	int start;
 
 	start = vq->last_used_idx % vq->num;
@@ -1292,7 +1312,14 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 			   ((void __user *)used - (void __user *)vq->used),
 			  count * sizeof *used);
 	}
-	vq->last_used_idx += count;
+	old = vq->last_used_idx;
+	new = (vq->last_used_idx += count);
+	/* If the driver never bothers to signal in a very long while,
+	 * used index might wrap around. If that happens, invalidate
+	 * signalled_used index we stored. TODO: make sure driver
+	 * signals at least once in 2^16 and remove this. */
+	if (unlikely((u16)(new - vq->signalled_used) < (u16)(new - old)))
+		vq->signalled_used_valid = false;
 	return 0;
 }
 
@@ -1331,29 +1358,47 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 	return r;
 }
 
-/* This actually signals the guest, using eventfd. */
-void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
-	__u16 flags;
-
+	__u16 old, new, event;
+	bool v;
 	/* Flush out used index updates. This is paired
 	 * with the barrier that the Guest executes when enabling
 	 * interrupts. */
 	smp_mb();
 
-	if (__get_user(flags, &vq->avail->flags)) {
-		vq_err(vq, "Failed to get flags");
-		return;
+	if (vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY) &&
+	    unlikely(vq->avail_idx == vq->last_avail_idx))
+		return true;
+
+	if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+		__u16 flags;
+		if (__get_user(flags, &vq->avail->flags)) {
+			vq_err(vq, "Failed to get flags");
+			return true;
+		}
+		return !(flags & VRING_AVAIL_F_NO_INTERRUPT);
 	}
+	old = vq->signalled_used;
+	v = vq->signalled_used_valid;
+	new = vq->signalled_used = vq->last_used_idx;
+	vq->signalled_used_valid = true;
 
-	/* If they don't want an interrupt, don't signal, unless empty. */
-	if ((flags & VRING_AVAIL_F_NO_INTERRUPT) &&
-	    (vq->avail_idx != vq->last_avail_idx ||
-	     !vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY)))
-		return;
+	if (unlikely(!v))
+		return true;
 
+	if (get_user(event, vhost_used_event(vq))) {
+		vq_err(vq, "Failed to get used event idx");
+		return true;
+	}
+	return vring_need_event(event, new, old);
+}
+
+/* This actually signals the guest, using eventfd. */
+void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+{
 	/* Signal the Guest tell them we used something up. */
-	if (vq->call_ctx)
+	if (vq->call_ctx && vhost_notify(dev, vq))
 		eventfd_signal(vq->call_ctx, 1);
 }
 
@@ -1376,7 +1421,7 @@ void vhost_add_used_and_signal_n(struct vhost_dev *dev,
 }
 
 /* OK, now we need to know about added descriptors. */
-bool vhost_enable_notify(struct vhost_virtqueue *vq)
+bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
 	u16 avail_idx;
 	int r;
@@ -1384,11 +1429,34 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq)
 	if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
 		return false;
 	vq->used_flags &= ~VRING_USED_F_NO_NOTIFY;
-	r = put_user(vq->used_flags, &vq->used->flags);
-	if (r) {
-		vq_err(vq, "Failed to enable notification at %p: %d\n",
-		       &vq->used->flags, r);
-		return false;
+	if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+		r = put_user(vq->used_flags, &vq->used->flags);
+		if (r) {
+			vq_err(vq, "Failed to enable notification at %p: %d\n",
+			       &vq->used->flags, r);
+			return false;
+		}
+	} else {
+		r = put_user(vq->avail_idx, vhost_avail_event(vq));
+		if (r) {
+			vq_err(vq, "Failed to update avail event index at %p: %d\n",
+			       vhost_avail_event(vq), r);
+			return false;
+		}
+	}
+	if (unlikely(vq->log_used)) {
+		void __user *used;
+		/* Make sure data is seen before log. */
+		smp_wmb();
+		used = vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX) ?
+			&vq->used->flags : vhost_avail_event(vq);
+		/* Log used flags or event index entry write. Both are 16 bit
+		 * fields. */
+		log_write(vq->log_base, vq->log_addr +
+			   (used - (void __user *)vq->used),
+			  sizeof(u16));
+		if (vq->log_ctx)
+			eventfd_signal(vq->log_ctx, 1);
 	}
 	/* They could have slipped one in as we were doing that: make
 	 * sure it's written, then check again. */
@@ -1404,15 +1472,17 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq)
 }
 
 /* We don't need to be notified again. */
-void vhost_disable_notify(struct vhost_virtqueue *vq)
+void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
 	int r;
 
 	if (vq->used_flags & VRING_USED_F_NO_NOTIFY)
 		return;
 	vq->used_flags |= VRING_USED_F_NO_NOTIFY;
-	r = put_user(vq->used_flags, &vq->used->flags);
-	if (r)
-		vq_err(vq, "Failed to enable notification at %p: %d\n",
-		       &vq->used->flags, r);
+	if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+		r = put_user(vq->used_flags, &vq->used->flags);
+		if (r)
+			vq_err(vq, "Failed to enable notification at %p: %d\n",
+			       &vq->used->flags, r);
+	}
 }
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index b3363ae38518..8e03379dd30f 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -84,6 +84,12 @@ struct vhost_virtqueue {
 	/* Used flags */
 	u16 used_flags;
 
+	/* Last used index value we have signalled on */
+	u16 signalled_used;
+
+	/* Last used index value we have signalled on */
+	bool signalled_used_valid;
+
 	/* Log writes to used structure. */
 	bool log_used;
 	u64 log_addr;
@@ -149,8 +155,8 @@ void vhost_add_used_and_signal(struct vhost_dev *, struct vhost_virtqueue *,
 void vhost_add_used_and_signal_n(struct vhost_dev *, struct vhost_virtqueue *,
 			       struct vring_used_elem *heads, unsigned count);
 void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
-void vhost_disable_notify(struct vhost_virtqueue *);
-bool vhost_enable_notify(struct vhost_virtqueue *);
+void vhost_disable_notify(struct vhost_dev *, struct vhost_virtqueue *);
+bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
 
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
 		    unsigned int log_num, u64 len);
@@ -162,11 +168,12 @@ int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
 	} while (0)
 
 enum {
-	VHOST_FEATURES = (1 << VIRTIO_F_NOTIFY_ON_EMPTY) |
-			 (1 << VIRTIO_RING_F_INDIRECT_DESC) |
-			 (1 << VHOST_F_LOG_ALL) |
-			 (1 << VHOST_NET_F_VIRTIO_NET_HDR) |
-			 (1 << VIRTIO_NET_F_MRG_RXBUF),
+	VHOST_FEATURES = (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) |
+			 (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
+			 (1ULL << VIRTIO_RING_F_EVENT_IDX) |
+			 (1ULL << VHOST_F_LOG_ALL) |
+			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
+			 (1ULL << VIRTIO_NET_F_MRG_RXBUF),
 };
 
 static inline int vhost_has_feature(struct vhost_dev *dev, int bit)
diff --git a/drivers/video/arcfb.c b/drivers/video/arcfb.c
index 3ec4923c2d84..c22e8d39a2cb 100644
--- a/drivers/video/arcfb.c
+++ b/drivers/video/arcfb.c
@@ -515,11 +515,10 @@ static int __devinit arcfb_probe(struct platform_device *dev)
 
 	/* We need a flat backing store for the Arc's
 	   less-flat actual paged framebuffer */
-	if (!(videomemory = vmalloc(videomemorysize)))
+	videomemory = vzalloc(videomemorysize);
+	if (!videomemory)
 		return retval;
 
-	memset(videomemory, 0, videomemorysize);
-
 	info = framebuffer_alloc(sizeof(struct arcfb_par), &dev->dev);
 	if (!info)
 		goto err;
diff --git a/drivers/video/aty/atyfb_base.c b/drivers/video/aty/atyfb_base.c
index ebb893c49e90..d7aaec5667bf 100644
--- a/drivers/video/aty/atyfb_base.c
+++ b/drivers/video/aty/atyfb_base.c
@@ -248,10 +248,6 @@ static int atyfb_sync(struct fb_info *info);
 
 static int aty_init(struct fb_info *info);
 
-#ifdef CONFIG_ATARI
-static int store_video_par(char *videopar, unsigned char m64_num);
-#endif
-
 static void aty_get_crtc(const struct atyfb_par *par, struct crtc *crtc);
 
 static void aty_set_crtc(const struct atyfb_par *par, const struct crtc *crtc);
@@ -2268,11 +2264,13 @@ error:
 	return;
 }
 
+#ifdef CONFIG_PCI
 static void aty_bl_exit(struct backlight_device *bd)
 {
 	backlight_device_unregister(bd);
 	printk("aty: Backlight unloaded\n");
 }
+#endif /* CONFIG_PCI */
 
 #endif /* CONFIG_FB_ATY_BACKLIGHT */
 
@@ -2789,7 +2787,7 @@ aty_init_exit:
 	return ret;
 }
 
-#ifdef CONFIG_ATARI
+#if defined(CONFIG_ATARI) && !defined(MODULE)
 static int __devinit store_video_par(char *video_str, unsigned char m64_num)
 {
 	char *p;
@@ -2818,7 +2816,7 @@ static int __devinit store_video_par(char *video_str, unsigned char m64_num)
 	phys_vmembase[m64_num] = 0;
 	return -1;
 }
-#endif /* CONFIG_ATARI */
+#endif /* CONFIG_ATARI && !MODULE */
 
 /*
  * Blank the display.
diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig
index 0c9373bedd1f..2d93c8d61ad5 100644
--- a/drivers/video/backlight/Kconfig
+++ b/drivers/video/backlight/Kconfig
@@ -302,6 +302,18 @@ config BACKLIGHT_ADP8860
 	  To compile this driver as a module, choose M here: the module will
 	  be called adp8860_bl.
 
+config BACKLIGHT_ADP8870
+	tristate "Backlight Driver for ADP8870 using WLED"
+	depends on BACKLIGHT_CLASS_DEVICE && I2C
+	select NEW_LEDS
+	select LEDS_CLASS
+	help
+	  If you have a LCD backlight connected to the ADP8870,
+	  say Y here to enable this driver.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called adp8870_bl.
+
 config BACKLIGHT_88PM860X
 	tristate "Backlight Driver for 88PM8606 using WLED"
 	depends on MFD_88PM860X
diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile
index b9ca8490df87..ee72adb8786e 100644
--- a/drivers/video/backlight/Makefile
+++ b/drivers/video/backlight/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_BACKLIGHT_WM831X)	+= wm831x_bl.o
 obj-$(CONFIG_BACKLIGHT_ADX)    += adx_bl.o
 obj-$(CONFIG_BACKLIGHT_ADP5520)	+= adp5520_bl.o
 obj-$(CONFIG_BACKLIGHT_ADP8860)	+= adp8860_bl.o
+obj-$(CONFIG_BACKLIGHT_ADP8870)	+= adp8870_bl.o
 obj-$(CONFIG_BACKLIGHT_88PM860X) += 88pm860x_bl.o
 obj-$(CONFIG_BACKLIGHT_PCF50633)	+= pcf50633-backlight.o
 
diff --git a/drivers/video/backlight/adp8870_bl.c b/drivers/video/backlight/adp8870_bl.c
new file mode 100644
index 000000000000..05a8832bb3eb
--- /dev/null
+++ b/drivers/video/backlight/adp8870_bl.c
@@ -0,0 +1,1012 @@
+/*
+ * Backlight driver for Analog Devices ADP8870 Backlight Devices
+ *
+ * Copyright 2009-2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/module.h>
+#include <linux/version.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+#include <linux/platform_device.h>
+#include <linux/i2c.h>
+#include <linux/fb.h>
+#include <linux/backlight.h>
+#include <linux/leds.h>
+#include <linux/workqueue.h>
+#include <linux/slab.h>
+
+#include <linux/i2c/adp8870.h>
+#define ADP8870_EXT_FEATURES
+#define ADP8870_USE_LEDS
+
+
+#define ADP8870_MFDVID	0x00  /* Manufacturer and device ID */
+#define ADP8870_MDCR	0x01  /* Device mode and status */
+#define ADP8870_INT_STAT 0x02  /* Interrupts status */
+#define ADP8870_INT_EN	0x03  /* Interrupts enable */
+#define ADP8870_CFGR	0x04  /* Configuration register */
+#define ADP8870_BLSEL	0x05  /* Sink enable backlight or independent */
+#define ADP8870_PWMLED	0x06  /* PWM Enable Selection Register */
+#define ADP8870_BLOFF	0x07  /* Backlight off timeout */
+#define ADP8870_BLDIM	0x08  /* Backlight dim timeout */
+#define ADP8870_BLFR	0x09  /* Backlight fade in and out rates */
+#define ADP8870_BLMX1	0x0A  /* Backlight (Brightness Level 1-daylight) maximum current */
+#define ADP8870_BLDM1	0x0B  /* Backlight (Brightness Level 1-daylight) dim current */
+#define ADP8870_BLMX2	0x0C  /* Backlight (Brightness Level 2-bright) maximum current */
+#define ADP8870_BLDM2	0x0D  /* Backlight (Brightness Level 2-bright) dim current */
+#define ADP8870_BLMX3	0x0E  /* Backlight (Brightness Level 3-office) maximum current */
+#define ADP8870_BLDM3	0x0F  /* Backlight (Brightness Level 3-office) dim current */
+#define ADP8870_BLMX4	0x10  /* Backlight (Brightness Level 4-indoor) maximum current */
+#define ADP8870_BLDM4	0x11  /* Backlight (Brightness Level 4-indoor) dim current */
+#define ADP8870_BLMX5	0x12  /* Backlight (Brightness Level 5-dark) maximum current */
+#define ADP8870_BLDM5	0x13  /* Backlight (Brightness Level 5-dark) dim current */
+#define ADP8870_ISCLAW	0x1A  /* Independent sink current fade law register */
+#define ADP8870_ISCC	0x1B  /* Independent sink current control register */
+#define ADP8870_ISCT1	0x1C  /* Independent Sink Current Timer Register LED[7:5] */
+#define ADP8870_ISCT2	0x1D  /* Independent Sink Current Timer Register LED[4:1] */
+#define ADP8870_ISCF	0x1E  /* Independent sink current fade register */
+#define ADP8870_ISC1	0x1F  /* Independent Sink Current LED1 */
+#define ADP8870_ISC2	0x20  /* Independent Sink Current LED2 */
+#define ADP8870_ISC3	0x21  /* Independent Sink Current LED3 */
+#define ADP8870_ISC4	0x22  /* Independent Sink Current LED4 */
+#define ADP8870_ISC5	0x23  /* Independent Sink Current LED5 */
+#define ADP8870_ISC6	0x24  /* Independent Sink Current LED6 */
+#define ADP8870_ISC7	0x25  /* Independent Sink Current LED7 (Brightness Level 1-daylight) */
+#define ADP8870_ISC7_L2	0x26  /* Independent Sink Current LED7 (Brightness Level 2-bright) */
+#define ADP8870_ISC7_L3	0x27  /* Independent Sink Current LED7 (Brightness Level 3-office) */
+#define ADP8870_ISC7_L4	0x28  /* Independent Sink Current LED7 (Brightness Level 4-indoor) */
+#define ADP8870_ISC7_L5	0x29  /* Independent Sink Current LED7 (Brightness Level 5-dark) */
+#define ADP8870_CMP_CTL	0x2D  /* ALS Comparator Control Register */
+#define ADP8870_ALS1_EN	0x2E  /* Main ALS comparator level enable */
+#define ADP8870_ALS2_EN	0x2F  /* Second ALS comparator level enable */
+#define ADP8870_ALS1_STAT 0x30  /* Main ALS Comparator Status Register */
+#define ADP8870_ALS2_STAT 0x31  /* Second ALS Comparator Status Register */
+#define ADP8870_L2TRP	0x32  /* L2 comparator reference */
+#define ADP8870_L2HYS	0x33  /* L2 hysteresis */
+#define ADP8870_L3TRP	0x34  /* L3 comparator reference */
+#define ADP8870_L3HYS	0x35  /* L3 hysteresis */
+#define ADP8870_L4TRP	0x36  /* L4 comparator reference */
+#define ADP8870_L4HYS	0x37  /* L4 hysteresis */
+#define ADP8870_L5TRP	0x38  /* L5 comparator reference */
+#define ADP8870_L5HYS	0x39  /* L5 hysteresis */
+#define ADP8870_PH1LEVL	0x40  /* First phototransistor ambient light level-low byte register */
+#define ADP8870_PH1LEVH	0x41  /* First phototransistor ambient light level-high byte register */
+#define ADP8870_PH2LEVL	0x42  /* Second phototransistor ambient light level-low byte register */
+#define ADP8870_PH2LEVH	0x43  /* Second phototransistor ambient light level-high byte register */
+
+#define ADP8870_MANUFID		0x3  /* Analog Devices AD8870 Manufacturer and device ID */
+#define ADP8870_DEVID(x)	((x) & 0xF)
+#define ADP8870_MANID(x)	((x) >> 4)
+
+/* MDCR Device mode and status */
+#define D7ALSEN			(1 << 7)
+#define INT_CFG			(1 << 6)
+#define NSTBY			(1 << 5)
+#define DIM_EN			(1 << 4)
+#define GDWN_DIS		(1 << 3)
+#define SIS_EN			(1 << 2)
+#define CMP_AUTOEN		(1 << 1)
+#define BLEN			(1 << 0)
+
+/* ADP8870_ALS1_EN Main ALS comparator level enable */
+#define L5_EN			(1 << 3)
+#define L4_EN			(1 << 2)
+#define L3_EN			(1 << 1)
+#define L2_EN			(1 << 0)
+
+#define CFGR_BLV_SHIFT		3
+#define CFGR_BLV_MASK		0x7
+#define ADP8870_FLAG_LED_MASK	0xFF
+
+#define FADE_VAL(in, out)	((0xF & (in)) | ((0xF & (out)) << 4))
+#define BL_CFGR_VAL(law, blv)	((((blv) & CFGR_BLV_MASK) << CFGR_BLV_SHIFT) | ((0x3 & (law)) << 1))
+#define ALS_CMPR_CFG_VAL(filt)	((0x7 & (filt)) << 1)
+
+struct adp8870_bl {
+	struct i2c_client *client;
+	struct backlight_device *bl;
+	struct adp8870_led *led;
+	struct adp8870_backlight_platform_data *pdata;
+	struct mutex lock;
+	unsigned long cached_daylight_max;
+	int id;
+	int revid;
+	int current_brightness;
+};
+
+struct adp8870_led {
+	struct led_classdev	cdev;
+	struct work_struct	work;
+	struct i2c_client	*client;
+	enum led_brightness	new_brightness;
+	int			id;
+	int			flags;
+};
+
+static int adp8870_read(struct i2c_client *client, int reg, uint8_t *val)
+{
+	int ret;
+
+	ret = i2c_smbus_read_byte_data(client, reg);
+	if (ret < 0) {
+		dev_err(&client->dev, "failed reading at 0x%02x\n", reg);
+		return ret;
+	}
+
+	*val = ret;
+	return 0;
+}
+
+
+static int adp8870_write(struct i2c_client *client, u8 reg, u8 val)
+{
+	int ret = i2c_smbus_write_byte_data(client, reg, val);
+	if (ret)
+		dev_err(&client->dev, "failed to write\n");
+
+	return ret;
+}
+
+static int adp8870_set_bits(struct i2c_client *client, int reg, uint8_t bit_mask)
+{
+	struct adp8870_bl *data = i2c_get_clientdata(client);
+	uint8_t reg_val;
+	int ret;
+
+	mutex_lock(&data->lock);
+
+	ret = adp8870_read(client, reg, &reg_val);
+
+	if (!ret && ((reg_val & bit_mask) == 0)) {
+		reg_val |= bit_mask;
+		ret = adp8870_write(client, reg, reg_val);
+	}
+
+	mutex_unlock(&data->lock);
+	return ret;
+}
+
+static int adp8870_clr_bits(struct i2c_client *client, int reg, uint8_t bit_mask)
+{
+	struct adp8870_bl *data = i2c_get_clientdata(client);
+	uint8_t reg_val;
+	int ret;
+
+	mutex_lock(&data->lock);
+
+	ret = adp8870_read(client, reg, &reg_val);
+
+	if (!ret && (reg_val & bit_mask)) {
+		reg_val &= ~bit_mask;
+		ret = adp8870_write(client, reg, reg_val);
+	}
+
+	mutex_unlock(&data->lock);
+	return ret;
+}
+
+/*
+ * Independent sink / LED
+ */
+#if defined(ADP8870_USE_LEDS)
+static void adp8870_led_work(struct work_struct *work)
+{
+	struct adp8870_led *led = container_of(work, struct adp8870_led, work);
+	adp8870_write(led->client, ADP8870_ISC1 + led->id - 1,
+			 led->new_brightness >> 1);
+}
+
+static void adp8870_led_set(struct led_classdev *led_cdev,
+			   enum led_brightness value)
+{
+	struct adp8870_led *led;
+
+	led = container_of(led_cdev, struct adp8870_led, cdev);
+	led->new_brightness = value;
+	/*
+	 * Use workqueue for IO since I2C operations can sleep.
+	 */
+	schedule_work(&led->work);
+}
+
+static int adp8870_led_setup(struct adp8870_led *led)
+{
+	struct i2c_client *client = led->client;
+	int ret = 0;
+
+	ret = adp8870_write(client, ADP8870_ISC1 + led->id - 1, 0);
+	if (ret)
+		return ret;
+
+	ret = adp8870_set_bits(client, ADP8870_ISCC, 1 << (led->id - 1));
+	if (ret)
+		return ret;
+
+	if (led->id > 4)
+		ret = adp8870_set_bits(client, ADP8870_ISCT1,
+				(led->flags & 0x3) << ((led->id - 5) * 2));
+	else
+		ret = adp8870_set_bits(client, ADP8870_ISCT2,
+				(led->flags & 0x3) << ((led->id - 1) * 2));
+
+	return ret;
+}
+
+static int __devinit adp8870_led_probe(struct i2c_client *client)
+{
+	struct adp8870_backlight_platform_data *pdata =
+		client->dev.platform_data;
+	struct adp8870_bl *data = i2c_get_clientdata(client);
+	struct adp8870_led *led, *led_dat;
+	struct led_info *cur_led;
+	int ret, i;
+
+
+	led = kcalloc(pdata->num_leds, sizeof(*led), GFP_KERNEL);
+	if (led == NULL) {
+		dev_err(&client->dev, "failed to alloc memory\n");
+		return -ENOMEM;
+	}
+
+	ret = adp8870_write(client, ADP8870_ISCLAW, pdata->led_fade_law);
+	if (ret)
+		goto err_free;
+
+	ret = adp8870_write(client, ADP8870_ISCT1,
+			(pdata->led_on_time & 0x3) << 6);
+	if (ret)
+		goto err_free;
+
+	ret = adp8870_write(client, ADP8870_ISCF,
+			FADE_VAL(pdata->led_fade_in, pdata->led_fade_out));
+	if (ret)
+		goto err_free;
+
+	for (i = 0; i < pdata->num_leds; ++i) {
+		cur_led = &pdata->leds[i];
+		led_dat = &led[i];
+
+		led_dat->id = cur_led->flags & ADP8870_FLAG_LED_MASK;
+
+		if (led_dat->id > 7 || led_dat->id < 1) {
+			dev_err(&client->dev, "Invalid LED ID %d\n",
+				led_dat->id);
+			goto err;
+		}
+
+		if (pdata->bl_led_assign & (1 << (led_dat->id - 1))) {
+			dev_err(&client->dev, "LED %d used by Backlight\n",
+				led_dat->id);
+			goto err;
+		}
+
+		led_dat->cdev.name = cur_led->name;
+		led_dat->cdev.default_trigger = cur_led->default_trigger;
+		led_dat->cdev.brightness_set = adp8870_led_set;
+		led_dat->cdev.brightness = LED_OFF;
+		led_dat->flags = cur_led->flags >> FLAG_OFFT_SHIFT;
+		led_dat->client = client;
+		led_dat->new_brightness = LED_OFF;
+		INIT_WORK(&led_dat->work, adp8870_led_work);
+
+		ret = led_classdev_register(&client->dev, &led_dat->cdev);
+		if (ret) {
+			dev_err(&client->dev, "failed to register LED %d\n",
+				led_dat->id);
+			goto err;
+		}
+
+		ret = adp8870_led_setup(led_dat);
+		if (ret) {
+			dev_err(&client->dev, "failed to write\n");
+			i++;
+			goto err;
+		}
+	}
+
+	data->led = led;
+
+	return 0;
+
+ err:
+	for (i = i - 1; i >= 0; --i) {
+		led_classdev_unregister(&led[i].cdev);
+		cancel_work_sync(&led[i].work);
+	}
+
+ err_free:
+	kfree(led);
+
+	return ret;
+}
+
+static int __devexit adp8870_led_remove(struct i2c_client *client)
+{
+	struct adp8870_backlight_platform_data *pdata =
+		client->dev.platform_data;
+	struct adp8870_bl *data = i2c_get_clientdata(client);
+	int i;
+
+	for (i = 0; i < pdata->num_leds; i++) {
+		led_classdev_unregister(&data->led[i].cdev);
+		cancel_work_sync(&data->led[i].work);
+	}
+
+	kfree(data->led);
+	return 0;
+}
+#else
+static int __devinit adp8870_led_probe(struct i2c_client *client)
+{
+	return 0;
+}
+
+static int __devexit adp8870_led_remove(struct i2c_client *client)
+{
+	return 0;
+}
+#endif
+
+static int adp8870_bl_set(struct backlight_device *bl, int brightness)
+{
+	struct adp8870_bl *data = bl_get_data(bl);
+	struct i2c_client *client = data->client;
+	int ret = 0;
+
+	if (data->pdata->en_ambl_sens) {
+		if ((brightness > 0) && (brightness < ADP8870_MAX_BRIGHTNESS)) {
+			/* Disable Ambient Light auto adjust */
+			ret = adp8870_clr_bits(client, ADP8870_MDCR,
+					CMP_AUTOEN);
+			if (ret)
+				return ret;
+			ret = adp8870_write(client, ADP8870_BLMX1, brightness);
+			if (ret)
+				return ret;
+		} else {
+			/*
+			 * MAX_BRIGHTNESS -> Enable Ambient Light auto adjust
+			 * restore daylight l1 sysfs brightness
+			 */
+			ret = adp8870_write(client, ADP8870_BLMX1,
+					 data->cached_daylight_max);
+			if (ret)
+				return ret;
+
+			ret = adp8870_set_bits(client, ADP8870_MDCR,
+					 CMP_AUTOEN);
+			if (ret)
+				return ret;
+		}
+	} else {
+		ret = adp8870_write(client, ADP8870_BLMX1, brightness);
+		if (ret)
+			return ret;
+	}
+
+	if (data->current_brightness && brightness == 0)
+		ret = adp8870_set_bits(client,
+				ADP8870_MDCR, DIM_EN);
+	else if (data->current_brightness == 0 && brightness)
+		ret = adp8870_clr_bits(client,
+				ADP8870_MDCR, DIM_EN);
+
+	if (!ret)
+		data->current_brightness = brightness;
+
+	return ret;
+}
+
+static int adp8870_bl_update_status(struct backlight_device *bl)
+{
+	int brightness = bl->props.brightness;
+	if (bl->props.power != FB_BLANK_UNBLANK)
+		brightness = 0;
+
+	if (bl->props.fb_blank != FB_BLANK_UNBLANK)
+		brightness = 0;
+
+	return adp8870_bl_set(bl, brightness);
+}
+
+static int adp8870_bl_get_brightness(struct backlight_device *bl)
+{
+	struct adp8870_bl *data = bl_get_data(bl);
+
+	return data->current_brightness;
+}
+
+static const struct backlight_ops adp8870_bl_ops = {
+	.update_status	= adp8870_bl_update_status,
+	.get_brightness	= adp8870_bl_get_brightness,
+};
+
+static int adp8870_bl_setup(struct backlight_device *bl)
+{
+	struct adp8870_bl *data = bl_get_data(bl);
+	struct i2c_client *client = data->client;
+	struct adp8870_backlight_platform_data *pdata = data->pdata;
+	int ret = 0;
+
+	ret = adp8870_write(client, ADP8870_BLSEL, ~pdata->bl_led_assign);
+	if (ret)
+		return ret;
+
+	ret = adp8870_write(client, ADP8870_PWMLED, pdata->pwm_assign);
+	if (ret)
+		return ret;
+
+	ret = adp8870_write(client, ADP8870_BLMX1, pdata->l1_daylight_max);
+	if (ret)
+		return ret;
+
+	ret = adp8870_write(client, ADP8870_BLDM1, pdata->l1_daylight_dim);
+	if (ret)
+		return ret;
+
+	if (pdata->en_ambl_sens) {
+		data->cached_daylight_max = pdata->l1_daylight_max;
+		ret = adp8870_write(client, ADP8870_BLMX2,
+						pdata->l2_bright_max);
+		if (ret)
+			return ret;
+		ret = adp8870_write(client, ADP8870_BLDM2,
+						pdata->l2_bright_dim);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_BLMX3,
+						pdata->l3_office_max);
+		if (ret)
+			return ret;
+		ret = adp8870_write(client, ADP8870_BLDM3,
+						pdata->l3_office_dim);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_BLMX4,
+						pdata->l4_indoor_max);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_BLDM4,
+						pdata->l4_indor_dim);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_BLMX5,
+						pdata->l5_dark_max);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_BLDM5,
+						pdata->l5_dark_dim);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_L2TRP, pdata->l2_trip);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_L2HYS, pdata->l2_hyst);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_L3TRP, pdata->l3_trip);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_L3HYS, pdata->l3_hyst);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_L4TRP, pdata->l4_trip);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_L4HYS, pdata->l4_hyst);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_L5TRP, pdata->l5_trip);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_L5HYS, pdata->l5_hyst);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_ALS1_EN, L5_EN | L4_EN |
+						L3_EN | L2_EN);
+		if (ret)
+			return ret;
+
+		ret = adp8870_write(client, ADP8870_CMP_CTL,
+			ALS_CMPR_CFG_VAL(pdata->abml_filt));
+		if (ret)
+			return ret;
+	}
+
+	ret = adp8870_write(client, ADP8870_CFGR,
+			BL_CFGR_VAL(pdata->bl_fade_law, 0));
+	if (ret)
+		return ret;
+
+	ret = adp8870_write(client, ADP8870_BLFR, FADE_VAL(pdata->bl_fade_in,
+			pdata->bl_fade_out));
+	if (ret)
+		return ret;
+	/*
+	 * ADP8870 Rev0 requires GDWN_DIS bit set
+	 */
+
+	ret = adp8870_set_bits(client, ADP8870_MDCR, BLEN | DIM_EN | NSTBY |
+			(data->revid == 0 ? GDWN_DIS : 0));
+
+	return ret;
+}
+
+static ssize_t adp8870_show(struct device *dev, char *buf, int reg)
+{
+	struct adp8870_bl *data = dev_get_drvdata(dev);
+	int error;
+	uint8_t reg_val;
+
+	mutex_lock(&data->lock);
+	error = adp8870_read(data->client, reg, &reg_val);
+	mutex_unlock(&data->lock);
+
+	if (error < 0)
+		return error;
+
+	return sprintf(buf, "%u\n", reg_val);
+}
+
+static ssize_t adp8870_store(struct device *dev, const char *buf,
+			 size_t count, int reg)
+{
+	struct adp8870_bl *data = dev_get_drvdata(dev);
+	unsigned long val;
+	int ret;
+
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	mutex_lock(&data->lock);
+	adp8870_write(data->client, reg, val);
+	mutex_unlock(&data->lock);
+
+	return count;
+}
+
+static ssize_t adp8870_bl_l5_dark_max_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return adp8870_show(dev, buf, ADP8870_BLMX5);
+}
+
+static ssize_t adp8870_bl_l5_dark_max_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	return adp8870_store(dev, buf, count, ADP8870_BLMX5);
+}
+static DEVICE_ATTR(l5_dark_max, 0664, adp8870_bl_l5_dark_max_show,
+			adp8870_bl_l5_dark_max_store);
+
+
+static ssize_t adp8870_bl_l4_indoor_max_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return adp8870_show(dev, buf, ADP8870_BLMX4);
+}
+
+static ssize_t adp8870_bl_l4_indoor_max_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	return adp8870_store(dev, buf, count, ADP8870_BLMX4);
+}
+static DEVICE_ATTR(l4_indoor_max, 0664, adp8870_bl_l4_indoor_max_show,
+			adp8870_bl_l4_indoor_max_store);
+
+
+static ssize_t adp8870_bl_l3_office_max_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	return adp8870_show(dev, buf, ADP8870_BLMX3);
+}
+
+static ssize_t adp8870_bl_l3_office_max_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	return adp8870_store(dev, buf, count, ADP8870_BLMX3);
+}
+
+static DEVICE_ATTR(l3_office_max, 0664, adp8870_bl_l3_office_max_show,
+			adp8870_bl_l3_office_max_store);
+
+static ssize_t adp8870_bl_l2_bright_max_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return adp8870_show(dev, buf, ADP8870_BLMX2);
+}
+
+static ssize_t adp8870_bl_l2_bright_max_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	return adp8870_store(dev, buf, count, ADP8870_BLMX2);
+}
+static DEVICE_ATTR(l2_bright_max, 0664, adp8870_bl_l2_bright_max_show,
+			adp8870_bl_l2_bright_max_store);
+
+static ssize_t adp8870_bl_l1_daylight_max_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	return adp8870_show(dev, buf, ADP8870_BLMX1);
+}
+
+static ssize_t adp8870_bl_l1_daylight_max_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct adp8870_bl *data = dev_get_drvdata(dev);
+	int ret = strict_strtoul(buf, 10, &data->cached_daylight_max);
+	if (ret)
+		return ret;
+
+	return adp8870_store(dev, buf, count, ADP8870_BLMX1);
+}
+static DEVICE_ATTR(l1_daylight_max, 0664, adp8870_bl_l1_daylight_max_show,
+			adp8870_bl_l1_daylight_max_store);
+
+static ssize_t adp8870_bl_l5_dark_dim_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	return adp8870_show(dev, buf, ADP8870_BLDM5);
+}
+
+static ssize_t adp8870_bl_l5_dark_dim_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	return adp8870_store(dev, buf, count, ADP8870_BLDM5);
+}
+static DEVICE_ATTR(l5_dark_dim, 0664, adp8870_bl_l5_dark_dim_show,
+			adp8870_bl_l5_dark_dim_store);
+
+static ssize_t adp8870_bl_l4_indoor_dim_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	return adp8870_show(dev, buf, ADP8870_BLDM4);
+}
+
+static ssize_t adp8870_bl_l4_indoor_dim_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	return adp8870_store(dev, buf, count, ADP8870_BLDM4);
+}
+static DEVICE_ATTR(l4_indoor_dim, 0664, adp8870_bl_l4_indoor_dim_show,
+			adp8870_bl_l4_indoor_dim_store);
+
+
+static ssize_t adp8870_bl_l3_office_dim_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	return adp8870_show(dev, buf, ADP8870_BLDM3);
+}
+
+static ssize_t adp8870_bl_l3_office_dim_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	return adp8870_store(dev, buf, count, ADP8870_BLDM3);
+}
+static DEVICE_ATTR(l3_office_dim, 0664, adp8870_bl_l3_office_dim_show,
+			adp8870_bl_l3_office_dim_store);
+
+static ssize_t adp8870_bl_l2_bright_dim_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	return adp8870_show(dev, buf, ADP8870_BLDM2);
+}
+
+static ssize_t adp8870_bl_l2_bright_dim_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	return adp8870_store(dev, buf, count, ADP8870_BLDM2);
+}
+static DEVICE_ATTR(l2_bright_dim, 0664, adp8870_bl_l2_bright_dim_show,
+			adp8870_bl_l2_bright_dim_store);
+
+static ssize_t adp8870_bl_l1_daylight_dim_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	return adp8870_show(dev, buf, ADP8870_BLDM1);
+}
+
+static ssize_t adp8870_bl_l1_daylight_dim_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	return adp8870_store(dev, buf, count, ADP8870_BLDM1);
+}
+static DEVICE_ATTR(l1_daylight_dim, 0664, adp8870_bl_l1_daylight_dim_show,
+			adp8870_bl_l1_daylight_dim_store);
+
+#ifdef ADP8870_EXT_FEATURES
+static ssize_t adp8870_bl_ambient_light_level_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct adp8870_bl *data = dev_get_drvdata(dev);
+	int error;
+	uint8_t reg_val;
+	uint16_t ret_val;
+
+	mutex_lock(&data->lock);
+	error = adp8870_read(data->client, ADP8870_PH1LEVL, &reg_val);
+	if (error < 0) {
+		mutex_unlock(&data->lock);
+		return error;
+	}
+	ret_val = reg_val;
+	error = adp8870_read(data->client, ADP8870_PH1LEVH, &reg_val);
+	mutex_unlock(&data->lock);
+
+	if (error < 0)
+		return error;
+
+	/* Return 13-bit conversion value for the first light sensor */
+	ret_val += (reg_val & 0x1F) << 8;
+
+	return sprintf(buf, "%u\n", ret_val);
+}
+static DEVICE_ATTR(ambient_light_level, 0444,
+		adp8870_bl_ambient_light_level_show, NULL);
+
+static ssize_t adp8870_bl_ambient_light_zone_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct adp8870_bl *data = dev_get_drvdata(dev);
+	int error;
+	uint8_t reg_val;
+
+	mutex_lock(&data->lock);
+	error = adp8870_read(data->client, ADP8870_CFGR, &reg_val);
+	mutex_unlock(&data->lock);
+
+	if (error < 0)
+		return error;
+
+	return sprintf(buf, "%u\n",
+		((reg_val >> CFGR_BLV_SHIFT) & CFGR_BLV_MASK) + 1);
+}
+
+static ssize_t adp8870_bl_ambient_light_zone_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct adp8870_bl *data = dev_get_drvdata(dev);
+	unsigned long val;
+	uint8_t reg_val;
+	int ret;
+
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	if (val == 0) {
+		/* Enable automatic ambient light sensing */
+		adp8870_set_bits(data->client, ADP8870_MDCR, CMP_AUTOEN);
+	} else if ((val > 0) && (val < 6)) {
+		/* Disable automatic ambient light sensing */
+		adp8870_clr_bits(data->client, ADP8870_MDCR, CMP_AUTOEN);
+
+		/* Set user supplied ambient light zone */
+		mutex_lock(&data->lock);
+		adp8870_read(data->client, ADP8870_CFGR, &reg_val);
+		reg_val &= ~(CFGR_BLV_MASK << CFGR_BLV_SHIFT);
+		reg_val |= (val - 1) << CFGR_BLV_SHIFT;
+		adp8870_write(data->client, ADP8870_CFGR, reg_val);
+		mutex_unlock(&data->lock);
+	}
+
+	return count;
+}
+static DEVICE_ATTR(ambient_light_zone, 0664,
+		adp8870_bl_ambient_light_zone_show,
+		adp8870_bl_ambient_light_zone_store);
+#endif
+
+static struct attribute *adp8870_bl_attributes[] = {
+	&dev_attr_l5_dark_max.attr,
+	&dev_attr_l5_dark_dim.attr,
+	&dev_attr_l4_indoor_max.attr,
+	&dev_attr_l4_indoor_dim.attr,
+	&dev_attr_l3_office_max.attr,
+	&dev_attr_l3_office_dim.attr,
+	&dev_attr_l2_bright_max.attr,
+	&dev_attr_l2_bright_dim.attr,
+	&dev_attr_l1_daylight_max.attr,
+	&dev_attr_l1_daylight_dim.attr,
+#ifdef ADP8870_EXT_FEATURES
+	&dev_attr_ambient_light_level.attr,
+	&dev_attr_ambient_light_zone.attr,
+#endif
+	NULL
+};
+
+static const struct attribute_group adp8870_bl_attr_group = {
+	.attrs = adp8870_bl_attributes,
+};
+
+static int __devinit adp8870_probe(struct i2c_client *client,
+					const struct i2c_device_id *id)
+{
+	struct backlight_properties props;
+	struct backlight_device *bl;
+	struct adp8870_bl *data;
+	struct adp8870_backlight_platform_data *pdata =
+		client->dev.platform_data;
+	uint8_t reg_val;
+	int ret;
+
+	if (!i2c_check_functionality(client->adapter,
+					I2C_FUNC_SMBUS_BYTE_DATA)) {
+		dev_err(&client->dev, "SMBUS Byte Data not Supported\n");
+		return -EIO;
+	}
+
+	if (!pdata) {
+		dev_err(&client->dev, "no platform data?\n");
+		return -EINVAL;
+	}
+
+	ret = adp8870_read(client, ADP8870_MFDVID, &reg_val);
+	if (ret < 0)
+		return -EIO;
+
+	if (ADP8870_MANID(reg_val) != ADP8870_MANUFID) {
+		dev_err(&client->dev, "failed to probe\n");
+		return -ENODEV;
+	}
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (data == NULL)
+		return -ENOMEM;
+
+	data->revid = ADP8870_DEVID(reg_val);
+	data->client = client;
+	data->pdata = pdata;
+	data->id = id->driver_data;
+	data->current_brightness = 0;
+	i2c_set_clientdata(client, data);
+
+	mutex_init(&data->lock);
+
+	memset(&props, 0, sizeof(props));
+	props.type = BACKLIGHT_RAW;
+	props.max_brightness = props.brightness = ADP8870_MAX_BRIGHTNESS;
+	bl = backlight_device_register(dev_driver_string(&client->dev),
+			&client->dev, data, &adp8870_bl_ops, &props);
+	if (IS_ERR(bl)) {
+		dev_err(&client->dev, "failed to register backlight\n");
+		ret = PTR_ERR(bl);
+		goto out2;
+	}
+
+	data->bl = bl;
+
+	if (pdata->en_ambl_sens)
+		ret = sysfs_create_group(&bl->dev.kobj,
+			&adp8870_bl_attr_group);
+
+	if (ret) {
+		dev_err(&client->dev, "failed to register sysfs\n");
+		goto out1;
+	}
+
+	ret = adp8870_bl_setup(bl);
+	if (ret) {
+		ret = -EIO;
+		goto out;
+	}
+
+	backlight_update_status(bl);
+
+	dev_info(&client->dev, "Rev.%d Backlight\n", data->revid);
+
+	if (pdata->num_leds)
+		adp8870_led_probe(client);
+
+	return 0;
+
+out:
+	if (data->pdata->en_ambl_sens)
+		sysfs_remove_group(&data->bl->dev.kobj,
+			&adp8870_bl_attr_group);
+out1:
+	backlight_device_unregister(bl);
+out2:
+	i2c_set_clientdata(client, NULL);
+	kfree(data);
+
+	return ret;
+}
+
+static int __devexit adp8870_remove(struct i2c_client *client)
+{
+	struct adp8870_bl *data = i2c_get_clientdata(client);
+
+	adp8870_clr_bits(client, ADP8870_MDCR, NSTBY);
+
+	if (data->led)
+		adp8870_led_remove(client);
+
+	if (data->pdata->en_ambl_sens)
+		sysfs_remove_group(&data->bl->dev.kobj,
+			&adp8870_bl_attr_group);
+
+	backlight_device_unregister(data->bl);
+	i2c_set_clientdata(client, NULL);
+	kfree(data);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int adp8870_i2c_suspend(struct i2c_client *client, pm_message_t message)
+{
+	adp8870_clr_bits(client, ADP8870_MDCR, NSTBY);
+
+	return 0;
+}
+
+static int adp8870_i2c_resume(struct i2c_client *client)
+{
+	adp8870_set_bits(client, ADP8870_MDCR, NSTBY);
+
+	return 0;
+}
+#else
+#define adp8870_i2c_suspend NULL
+#define adp8870_i2c_resume NULL
+#endif
+
+static const struct i2c_device_id adp8870_id[] = {
+	{ "adp8870", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, adp8870_id);
+
+static struct i2c_driver adp8870_driver = {
+	.driver = {
+		.name = KBUILD_MODNAME,
+	},
+	.probe    = adp8870_probe,
+	.remove   = __devexit_p(adp8870_remove),
+	.suspend = adp8870_i2c_suspend,
+	.resume  = adp8870_i2c_resume,
+	.id_table = adp8870_id,
+};
+
+static int __init adp8870_init(void)
+{
+	return i2c_add_driver(&adp8870_driver);
+}
+module_init(adp8870_init);
+
+static void __exit adp8870_exit(void)
+{
+	i2c_del_driver(&adp8870_driver);
+}
+module_exit(adp8870_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Michael Hennerich <hennerich@blackfin.uclinux.org>");
+MODULE_DESCRIPTION("ADP8870 Backlight driver");
+MODULE_ALIAS("platform:adp8870-backlight");
diff --git a/drivers/video/bf537-lq035.c b/drivers/video/bf537-lq035.c
index 47c21fb2c82f..bea53c1a4950 100644
--- a/drivers/video/bf537-lq035.c
+++ b/drivers/video/bf537-lq035.c
@@ -789,6 +789,7 @@ static int __devinit bfin_lq035_probe(struct platform_device *pdev)
 	i2c_add_driver(&ad5280_driver);
 
 	memset(&props, 0, sizeof(props));
+	props.type = BACKLIGHT_RAW;
 	props.max_brightness = MAX_BRIGHENESS;
 	bl_dev = backlight_device_register("bf537-bl", NULL, NULL,
 					   &bfin_lq035fb_bl_ops, &props);
diff --git a/drivers/video/broadsheetfb.c b/drivers/video/broadsheetfb.c
index ebda6876d3a9..377dde3d5bfc 100644
--- a/drivers/video/broadsheetfb.c
+++ b/drivers/video/broadsheetfb.c
@@ -1101,12 +1101,10 @@ static int __devinit broadsheetfb_probe(struct platform_device *dev)
 
 	videomemorysize = roundup((dpyw*dpyh), PAGE_SIZE);
 
-	videomemory = vmalloc(videomemorysize);
+	videomemory = vzalloc(videomemorysize);
 	if (!videomemory)
 		goto err_fb_rel;
 
-	memset(videomemory, 0, videomemorysize);
-
 	info->screen_base = (char *)videomemory;
 	info->fbops = &broadsheetfb_ops;
 
diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c
index fb205843c2c7..784139aed079 100644
--- a/drivers/video/efifb.c
+++ b/drivers/video/efifb.c
@@ -16,6 +16,8 @@
 #include <linux/pci.h>
 #include <video/vga.h>
 
+static bool request_mem_succeeded = false;
+
 static struct fb_var_screeninfo efifb_defined __devinitdata = {
 	.activate		= FB_ACTIVATE_NOW,
 	.height			= -1,
@@ -281,7 +283,9 @@ static void efifb_destroy(struct fb_info *info)
 {
 	if (info->screen_base)
 		iounmap(info->screen_base);
-	release_mem_region(info->apertures->ranges[0].base, info->apertures->ranges[0].size);
+	if (request_mem_succeeded)
+		release_mem_region(info->apertures->ranges[0].base,
+				   info->apertures->ranges[0].size);
 	framebuffer_release(info);
 }
 
@@ -326,14 +330,13 @@ static int __init efifb_setup(char *options)
 	return 0;
 }
 
-static int __devinit efifb_probe(struct platform_device *dev)
+static int __init efifb_probe(struct platform_device *dev)
 {
 	struct fb_info *info;
 	int err;
 	unsigned int size_vmode;
 	unsigned int size_remap;
 	unsigned int size_total;
-	int request_succeeded = 0;
 
 	if (!screen_info.lfb_depth)
 		screen_info.lfb_depth = 32;
@@ -387,7 +390,7 @@ static int __devinit efifb_probe(struct platform_device *dev)
 	efifb_fix.smem_len = size_remap;
 
 	if (request_mem_region(efifb_fix.smem_start, size_remap, "efifb")) {
-		request_succeeded = 1;
+		request_mem_succeeded = true;
 	} else {
 		/* We cannot make this fatal. Sometimes this comes from magic
 		   spaces our resource handlers simply don't know about */
@@ -413,7 +416,7 @@ static int __devinit efifb_probe(struct platform_device *dev)
 	info->apertures->ranges[0].base = efifb_fix.smem_start;
 	info->apertures->ranges[0].size = size_remap;
 
-	info->screen_base = ioremap(efifb_fix.smem_start, efifb_fix.smem_len);
+	info->screen_base = ioremap_wc(efifb_fix.smem_start, efifb_fix.smem_len);
 	if (!info->screen_base) {
 		printk(KERN_ERR "efifb: abort, cannot ioremap video memory "
 				"0x%x @ 0x%lx\n",
@@ -491,13 +494,12 @@ err_unmap:
 err_release_fb:
 	framebuffer_release(info);
 err_release_mem:
-	if (request_succeeded)
+	if (request_mem_succeeded)
 		release_mem_region(efifb_fix.smem_start, size_total);
 	return err;
 }
 
 static struct platform_driver efifb_driver = {
-	.probe	= efifb_probe,
 	.driver	= {
 		.name	= "efifb",
 	},
@@ -528,13 +530,21 @@ static int __init efifb_init(void)
 	if (!screen_info.lfb_linelength)
 		return -ENODEV;
 
-	ret = platform_driver_register(&efifb_driver);
+	ret = platform_device_register(&efifb_device);
+	if (ret)
+		return ret;
 
-	if (!ret) {
-		ret = platform_device_register(&efifb_device);
-		if (ret)
-			platform_driver_unregister(&efifb_driver);
+	/*
+	 * This is not just an optimization.  We will interfere
+	 * with a real driver if we get reprobed, so don't allow
+	 * it.
+	 */
+	ret = platform_driver_probe(&efifb_driver, efifb_probe);
+	if (ret) {
+		platform_device_unregister(&efifb_device);
+		return ret;
 	}
+
 	return ret;
 }
 module_init(efifb_init);
diff --git a/drivers/video/hecubafb.c b/drivers/video/hecubafb.c
index 1b94643ecbcf..fbef15f7a218 100644
--- a/drivers/video/hecubafb.c
+++ b/drivers/video/hecubafb.c
@@ -231,11 +231,10 @@ static int __devinit hecubafb_probe(struct platform_device *dev)
 
 	videomemorysize = (DPY_W*DPY_H)/8;
 
-	if (!(videomemory = vmalloc(videomemorysize)))
+	videomemory = vzalloc(videomemorysize);
+	if (!videomemory)
 		return retval;
 
-	memset(videomemory, 0, videomemorysize);
-
 	info = framebuffer_alloc(sizeof(struct hecubafb_par), &dev->dev);
 	if (!info)
 		goto err_fballoc;
diff --git a/drivers/video/imxfb.c b/drivers/video/imxfb.c
index d2ccfd6e662c..f135dbead07d 100644
--- a/drivers/video/imxfb.c
+++ b/drivers/video/imxfb.c
@@ -856,10 +856,10 @@ failed_platform_init:
 		dma_free_writecombine(&pdev->dev,fbi->map_size,fbi->map_cpu,
 			fbi->map_dma);
 failed_map:
-	clk_put(fbi->clk);
-failed_getclock:
 	iounmap(fbi->regs);
 failed_ioremap:
+	clk_put(fbi->clk);
+failed_getclock:
 	release_mem_region(res->start, resource_size(res));
 failed_req:
 	kfree(info->pseudo_palette);
diff --git a/drivers/video/metronomefb.c b/drivers/video/metronomefb.c
index ed64edfd2c43..97d45e5115e2 100644
--- a/drivers/video/metronomefb.c
+++ b/drivers/video/metronomefb.c
@@ -628,12 +628,10 @@ static int __devinit metronomefb_probe(struct platform_device *dev)
 	/* we need to add a spare page because our csum caching scheme walks
 	 * to the end of the page */
 	videomemorysize = PAGE_SIZE + (fw * fh);
-	videomemory = vmalloc(videomemorysize);
+	videomemory = vzalloc(videomemorysize);
 	if (!videomemory)
 		goto err_fb_rel;
 
-	memset(videomemory, 0, videomemorysize);
-
 	info->screen_base = (char __force __iomem *)videomemory;
 	info->fbops = &metronomefb_ops;
 
diff --git a/drivers/video/modedb.c b/drivers/video/modedb.c
index 48c3ea8652b6..cb175fe7abc0 100644
--- a/drivers/video/modedb.c
+++ b/drivers/video/modedb.c
@@ -1128,3 +1128,4 @@ EXPORT_SYMBOL(fb_find_best_mode);
 EXPORT_SYMBOL(fb_find_nearest_mode);
 EXPORT_SYMBOL(fb_videomode_to_modelist);
 EXPORT_SYMBOL(fb_find_mode);
+EXPORT_SYMBOL(fb_find_mode_cvt);
diff --git a/drivers/video/pxa168fb.c b/drivers/video/pxa168fb.c
index 35f61dd0cb3a..bb95ec56d25d 100644
--- a/drivers/video/pxa168fb.c
+++ b/drivers/video/pxa168fb.c
@@ -623,19 +623,21 @@ static int __devinit pxa168fb_probe(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (res == NULL) {
 		dev_err(&pdev->dev, "no IO memory defined\n");
-		return -ENOENT;
+		ret = -ENOENT;
+		goto failed_put_clk;
 	}
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		dev_err(&pdev->dev, "no IRQ defined\n");
-		return -ENOENT;
+		ret = -ENOENT;
+		goto failed_put_clk;
 	}
 
 	info = framebuffer_alloc(sizeof(struct pxa168fb_info), &pdev->dev);
 	if (info == NULL) {
-		clk_put(clk);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto failed_put_clk;
 	}
 
 	/* Initialize private data */
@@ -671,7 +673,7 @@ static int __devinit pxa168fb_probe(struct platform_device *pdev)
 	fbi->reg_base = ioremap_nocache(res->start, resource_size(res));
 	if (fbi->reg_base == NULL) {
 		ret = -ENOMEM;
-		goto failed;
+		goto failed_free_info;
 	}
 
 	/*
@@ -683,7 +685,7 @@ static int __devinit pxa168fb_probe(struct platform_device *pdev)
 						&fbi->fb_start_dma, GFP_KERNEL);
 	if (info->screen_base == NULL) {
 		ret = -ENOMEM;
-		goto failed;
+		goto failed_free_info;
 	}
 
 	info->fix.smem_start = (unsigned long)fbi->fb_start_dma;
@@ -772,8 +774,9 @@ failed_free_clk:
 failed_free_fbmem:
 	dma_free_coherent(fbi->dev, info->fix.smem_len,
 			info->screen_base, fbi->fb_start_dma);
-failed:
+failed_free_info:
 	kfree(info);
+failed_put_clk:
 	clk_put(clk);
 
 	dev_err(&pdev->dev, "frame buffer device init failed with %d\n", ret);
diff --git a/drivers/video/s3c-fb.c b/drivers/video/s3c-fb.c
index 0352afa49a39..4aecf213c9be 100644
--- a/drivers/video/s3c-fb.c
+++ b/drivers/video/s3c-fb.c
@@ -235,13 +235,12 @@ static int s3c_fb_check_var(struct fb_var_screeninfo *var,
 			    struct fb_info *info)
 {
 	struct s3c_fb_win *win = info->par;
-	struct s3c_fb_pd_win *windata = win->windata;
 	struct s3c_fb *sfb = win->parent;
 
 	dev_dbg(sfb->dev, "checking parameters\n");
 
-	var->xres_virtual = max((unsigned int)windata->virtual_x, var->xres);
-	var->yres_virtual = max((unsigned int)windata->virtual_y, var->yres);
+	var->xres_virtual = max(var->xres_virtual, var->xres);
+	var->yres_virtual = max(var->yres_virtual, var->yres);
 
 	if (!s3c_fb_validate_win_bpp(win, var->bits_per_pixel)) {
 		dev_dbg(sfb->dev, "win %d: unsupported bpp %d\n",
@@ -558,6 +557,13 @@ static int s3c_fb_set_par(struct fb_info *info)
 	vidosd_set_alpha(win, alpha);
 	vidosd_set_size(win, data);
 
+	/* Enable DMA channel for this window */
+	if (sfb->variant.has_shadowcon) {
+		data = readl(sfb->regs + SHADOWCON);
+		data |= SHADOWCON_CHx_ENABLE(win_no);
+		writel(data, sfb->regs + SHADOWCON);
+	}
+
 	data = WINCONx_ENWIN;
 
 	/* note, since we have to round up the bits-per-pixel, we end up
@@ -637,13 +643,6 @@ static int s3c_fb_set_par(struct fb_info *info)
 	writel(data, regs + sfb->variant.wincon + (win_no * 4));
 	writel(0x0, regs + sfb->variant.winmap + (win_no * 4));
 
-	/* Enable DMA channel for this window */
-	if (sfb->variant.has_shadowcon) {
-		data = readl(sfb->regs + SHADOWCON);
-		data |= SHADOWCON_CHx_ENABLE(win_no);
-		writel(data, sfb->regs + SHADOWCON);
-	}
-
 	shadow_protect_win(win, 0);
 
 	return 0;
@@ -1487,11 +1486,10 @@ static int __devexit s3c_fb_remove(struct platform_device *pdev)
 
 	release_mem_region(sfb->regs_res->start, resource_size(sfb->regs_res));
 
-	kfree(sfb);
-
 	pm_runtime_put_sync(sfb->dev);
 	pm_runtime_disable(sfb->dev);
 
+	kfree(sfb);
 	return 0;
 }
 
diff --git a/drivers/video/savage/savagefb_driver.c b/drivers/video/savage/savagefb_driver.c
index 3b7f2f5bae71..4de541ca9c52 100644
--- a/drivers/video/savage/savagefb_driver.c
+++ b/drivers/video/savage/savagefb_driver.c
@@ -2237,6 +2237,22 @@ static int __devinit savagefb_probe(struct pci_dev* dev,
 				 &info->modelist);
 #endif
 	info->var = savagefb_var800x600x8;
+	/* if a panel was detected, default to a CVT mode instead */
+	if (par->SavagePanelWidth) {
+		struct fb_videomode cvt_mode;
+
+		memset(&cvt_mode, 0, sizeof(cvt_mode));
+		cvt_mode.xres = par->SavagePanelWidth;
+		cvt_mode.yres = par->SavagePanelHeight;
+		cvt_mode.refresh = 60;
+		/* FIXME: if we know there is only the panel
+		 * we can enable reduced blanking as well */
+		if (fb_find_mode_cvt(&cvt_mode, 0, 0))
+			printk(KERN_WARNING "No CVT mode found for panel\n");
+		else if (fb_find_mode(&info->var, info, NULL, NULL, 0,
+				      &cvt_mode, 0) != 3)
+			info->var = savagefb_var800x600x8;
+	}
 
 	if (mode_option) {
 		fb_find_mode(&info->var, info, mode_option,
diff --git a/drivers/video/sh_mobile_hdmi.c b/drivers/video/sh_mobile_hdmi.c
index 6ae40b630dc9..7d54e2c612f7 100644
--- a/drivers/video/sh_mobile_hdmi.c
+++ b/drivers/video/sh_mobile_hdmi.c
@@ -1127,23 +1127,16 @@ static void sh_hdmi_edid_work_fn(struct work_struct *work)
 		struct fb_info *info = hdmi->info;
 		unsigned long parent_rate = 0, hdmi_rate;
 
-		/* A device has been plugged in */
-		pm_runtime_get_sync(hdmi->dev);
-
 		ret = sh_hdmi_read_edid(hdmi, &hdmi_rate, &parent_rate);
-		if (ret < 0) {
-			pm_runtime_put(hdmi->dev);
+		if (ret < 0)
 			goto out;
-		}
 
 		hdmi->hp_state = HDMI_HOTPLUG_EDID_DONE;
 
 		/* Reconfigure the clock */
 		ret = sh_hdmi_clk_configure(hdmi, hdmi_rate, parent_rate);
-		if (ret < 0) {
-			pm_runtime_put(hdmi->dev);
+		if (ret < 0)
 			goto out;
-		}
 
 		msleep(10);
 		sh_hdmi_configure(hdmi);
@@ -1191,7 +1184,6 @@ static void sh_hdmi_edid_work_fn(struct work_struct *work)
 		fb_set_suspend(hdmi->info, 1);
 
 		console_unlock();
-		pm_runtime_put(hdmi->dev);
 	}
 
 out:
@@ -1312,7 +1304,7 @@ static int __init sh_hdmi_probe(struct platform_device *pdev)
 	INIT_DELAYED_WORK(&hdmi->edid_work, sh_hdmi_edid_work_fn);
 
 	pm_runtime_enable(&pdev->dev);
-	pm_runtime_resume(&pdev->dev);
+	pm_runtime_get_sync(&pdev->dev);
 
 	/* Product and revision IDs are 0 in sh-mobile version */
 	dev_info(&pdev->dev, "Detected HDMI controller 0x%x:0x%x\n",
@@ -1340,7 +1332,7 @@ static int __init sh_hdmi_probe(struct platform_device *pdev)
 ecodec:
 	free_irq(irq, hdmi);
 ereqirq:
-	pm_runtime_suspend(&pdev->dev);
+	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	iounmap(hdmi->base);
 emap:
@@ -1377,7 +1369,7 @@ static int __exit sh_hdmi_remove(struct platform_device *pdev)
 	free_irq(irq, hdmi);
 	/* Wait for already scheduled work */
 	cancel_delayed_work_sync(&hdmi->edid_work);
-	pm_runtime_suspend(&pdev->dev);
+	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	clk_disable(hdmi->hdmi_clk);
 	clk_put(hdmi->hdmi_clk);
diff --git a/drivers/video/sh_mobile_lcdcfb.c b/drivers/video/sh_mobile_lcdcfb.c
index 404c03b4b7c7..019dbd3f12b2 100644
--- a/drivers/video/sh_mobile_lcdcfb.c
+++ b/drivers/video/sh_mobile_lcdcfb.c
@@ -470,7 +470,7 @@ static int sh_mobile_lcdc_start(struct sh_mobile_lcdc_priv *priv)
 	unsigned long tmp;
 	int bpp = 0;
 	unsigned long ldddsr;
-	int k, m;
+	int k, m, ret;
 
 	/* enable clocks before accessing the hardware */
 	for (k = 0; k < ARRAY_SIZE(priv->ch); k++) {
@@ -540,7 +540,7 @@ static int sh_mobile_lcdc_start(struct sh_mobile_lcdc_priv *priv)
 
 		board_cfg = &ch->cfg.board_cfg;
 		if (board_cfg->setup_sys) {
-			int ret = board_cfg->setup_sys(board_cfg->board_data,
+			ret = board_cfg->setup_sys(board_cfg->board_data,
 						ch, &sh_mobile_lcdc_sys_bus_ops);
 			if (ret)
 				return ret;
diff --git a/drivers/video/vga16fb.c b/drivers/video/vga16fb.c
index 53b2c5aae067..305c975b1787 100644
--- a/drivers/video/vga16fb.c
+++ b/drivers/video/vga16fb.c
@@ -1265,9 +1265,11 @@ static void vga16fb_imageblit(struct fb_info *info, const struct fb_image *image
 
 static void vga16fb_destroy(struct fb_info *info)
 {
+	struct platform_device *dev = container_of(info->device, struct platform_device, dev);
 	iounmap(info->screen_base);
 	fb_dealloc_cmap(&info->cmap);
 	/* XXX unshare VGA regions */
+	platform_set_drvdata(dev, NULL);
 	framebuffer_release(info);
 }
 
diff --git a/drivers/video/xen-fbfront.c b/drivers/video/xen-fbfront.c
index a20218c2fda8..beac52fc1c0e 100644
--- a/drivers/video/xen-fbfront.c
+++ b/drivers/video/xen-fbfront.c
@@ -395,10 +395,9 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
 	spin_lock_init(&info->dirty_lock);
 	spin_lock_init(&info->resize_lock);
 
-	info->fb = vmalloc(fb_size);
+	info->fb = vzalloc(fb_size);
 	if (info->fb == NULL)
 		goto error_nomem;
-	memset(info->fb, 0, fb_size);
 
 	info->nr_pages = (fb_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 0f1da45ba47d..e058ace2a4ad 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -40,9 +40,6 @@ struct virtio_balloon
 	/* Waiting for host to ack the pages we released. */
 	struct completion acked;
 
-	/* Do we have to tell Host *before* we reuse pages? */
-	bool tell_host_first;
-
 	/* The pages we've told the Host we're not using. */
 	unsigned int num_pages;
 	struct list_head pages;
@@ -151,13 +148,14 @@ static void leak_balloon(struct virtio_balloon *vb, size_t num)
 		vb->num_pages--;
 	}
 
-	if (vb->tell_host_first) {
-		tell_host(vb, vb->deflate_vq);
-		release_pages_by_pfn(vb->pfns, vb->num_pfns);
-	} else {
-		release_pages_by_pfn(vb->pfns, vb->num_pfns);
-		tell_host(vb, vb->deflate_vq);
-	}
+
+	/*
+	 * Note that if
+	 * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
+	 * is true, we *have* to do it in this order
+	 */
+	tell_host(vb, vb->deflate_vq);
+	release_pages_by_pfn(vb->pfns, vb->num_pfns);
 }
 
 static inline void update_stat(struct virtio_balloon *vb, int idx,
@@ -325,9 +323,6 @@ static int virtballoon_probe(struct virtio_device *vdev)
 		goto out_del_vqs;
 	}
 
-	vb->tell_host_first
-		= virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
-
 	return 0;
 
 out_del_vqs:
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index b0043fb26a4d..68b9136847af 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -82,6 +82,9 @@ struct vring_virtqueue
 	/* Host supports indirect buffers */
 	bool indirect;
 
+	/* Host publishes avail event idx */
+	bool event;
+
 	/* Number of free buffers */
 	unsigned int num_free;
 	/* Head of free buffer list. */
@@ -237,18 +240,22 @@ EXPORT_SYMBOL_GPL(virtqueue_add_buf_gfp);
 void virtqueue_kick(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 new, old;
 	START_USE(vq);
 	/* Descriptors and available array need to be set before we expose the
 	 * new available array entries. */
 	virtio_wmb();
 
-	vq->vring.avail->idx += vq->num_added;
+	old = vq->vring.avail->idx;
+	new = vq->vring.avail->idx = old + vq->num_added;
 	vq->num_added = 0;
 
 	/* Need to update avail index before checking if we should notify */
 	virtio_mb();
 
-	if (!(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
+	if (vq->event ?
+	    vring_need_event(vring_avail_event(&vq->vring), new, old) :
+	    !(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
 		/* Prod other side to tell it about changes. */
 		vq->notify(&vq->vq);
 
@@ -324,6 +331,14 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
 	ret = vq->data[i];
 	detach_buf(vq, i);
 	vq->last_used_idx++;
+	/* If we expect an interrupt for the next entry, tell host
+	 * by writing event index and flush out the write before
+	 * the read in the next get_buf call. */
+	if (!(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) {
+		vring_used_event(&vq->vring) = vq->last_used_idx;
+		virtio_mb();
+	}
+
 	END_USE(vq);
 	return ret;
 }
@@ -345,7 +360,11 @@ bool virtqueue_enable_cb(struct virtqueue *_vq)
 
 	/* We optimistically turn back on interrupts, then check if there was
 	 * more to do. */
+	/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
+	 * either clear the flags bit or point the event index at the next
+	 * entry. Always do both to keep code simple. */
 	vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+	vring_used_event(&vq->vring) = vq->last_used_idx;
 	virtio_mb();
 	if (unlikely(more_used(vq))) {
 		END_USE(vq);
@@ -357,6 +376,33 @@ bool virtqueue_enable_cb(struct virtqueue *_vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
 
+bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 bufs;
+
+	START_USE(vq);
+
+	/* We optimistically turn back on interrupts, then check if there was
+	 * more to do. */
+	/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
+	 * either clear the flags bit or point the event index at the next
+	 * entry. Always do both to keep code simple. */
+	vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+	/* TODO: tune this threshold */
+	bufs = (u16)(vq->vring.avail->idx - vq->last_used_idx) * 3 / 4;
+	vring_used_event(&vq->vring) = vq->last_used_idx + bufs;
+	virtio_mb();
+	if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) {
+		END_USE(vq);
+		return false;
+	}
+
+	END_USE(vq);
+	return true;
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
+
 void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -438,6 +484,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int num,
 #endif
 
 	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC);
+	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 
 	/* No callback?  Tell other side not to bother us. */
 	if (!callback)
@@ -472,6 +519,8 @@ void vring_transport_features(struct virtio_device *vdev)
 		switch (i) {
 		case VIRTIO_RING_F_INDIRECT_DESC:
 			break;
+		case VIRTIO_RING_F_EVENT_IDX:
+			break;
 		default:
 			/* We don't understand this bit. */
 			clear_bit(i, vdev->features);
diff --git a/drivers/w1/masters/Kconfig b/drivers/w1/masters/Kconfig
index 00d615d7aa21..979d6eed9a0f 100644
--- a/drivers/w1/masters/Kconfig
+++ b/drivers/w1/masters/Kconfig
@@ -42,7 +42,7 @@ config W1_MASTER_MXC
 
 config W1_MASTER_DS1WM
 	tristate "Maxim DS1WM 1-wire busmaster"
-	depends on W1
+	depends on W1 && GENERIC_HARDIRQS
 	help
 	  Say Y here to enable the DS1WM 1-wire driver, such as that
 	  in HP iPAQ devices like h5xxx, h2200, and ASIC3-based like
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 3ff822b48145..30df85d8fca8 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -395,9 +395,9 @@ static void unmask_evtchn(int port)
 static void xen_irq_init(unsigned irq)
 {
 	struct irq_info *info;
+#ifdef CONFIG_SMP
 	struct irq_desc *desc = irq_to_desc(irq);
 
-#ifdef CONFIG_SMP
 	/* By default all event channels notify CPU#0. */
 	cpumask_copy(desc->irq_data.affinity, cpumask_of(0));
 #endif
@@ -626,6 +626,9 @@ int xen_allocate_pirq_gsi(unsigned gsi)
  *
  * Note: We don't assign an event channel until the irq actually started
  * up.  Return an existing irq if we've already got one for the gsi.
+ *
+ * Shareable implies level triggered, not shareable implies edge
+ * triggered here.
  */
 int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 			     unsigned pirq, int shareable, char *name)
@@ -664,16 +667,13 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 
 	pirq_query_unmask(irq);
 	/* We try to use the handler with the appropriate semantic for the
-	 * type of interrupt: if the interrupt doesn't need an eoi
-	 * (pirq_needs_eoi returns false), we treat it like an edge
-	 * triggered interrupt so we use handle_edge_irq.
-	 * As a matter of fact this only happens when the corresponding
-	 * physical interrupt is edge triggered or an msi.
+	 * type of interrupt: if the interrupt is an edge triggered
+	 * interrupt we use handle_edge_irq.
 	 *
-	 * On the other hand if the interrupt needs an eoi (pirq_needs_eoi
-	 * returns true) we treat it like a level triggered interrupt so we
-	 * use handle_fasteoi_irq like the native code does for this kind of
+	 * On the other hand if the interrupt is level triggered we use
+	 * handle_fasteoi_irq like the native code does for this kind of
 	 * interrupts.
+	 *
 	 * Depending on the Xen version, pirq_needs_eoi might return true
 	 * not only for level triggered interrupts but for edge triggered
 	 * interrupts too. In any case Xen always honors the eoi mechanism,
@@ -681,7 +681,7 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 	 * hasn't received an eoi yet. Therefore using the fasteoi handler
 	 * is the right choice either way.
 	 */
-	if (pirq_needs_eoi(irq))
+	if (shareable)
 		irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
 				handle_fasteoi_irq, name);
 	else
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 65ea21a97492..6e8c15a23201 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -147,9 +147,15 @@ void __init xen_swiotlb_init(int verbose)
 {
 	unsigned long bytes;
 	int rc;
-
-	xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
-	xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
+	unsigned long nr_tbl;
+
+	nr_tbl = swioltb_nr_tbl();
+	if (nr_tbl)
+		xen_io_tlb_nslabs = nr_tbl;
+	else {
+		xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
+		xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
+	}
 
 	bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
 
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 8d7f3e69ae29..7f6c67703195 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -814,7 +814,6 @@ int v9fs_vfs_unlink(struct inode *i, struct dentry *d)
 
 int v9fs_vfs_rmdir(struct inode *i, struct dentry *d)
 {
-	dentry_unhash(d);
 	return v9fs_remove(i, d, 1);
 }
 
@@ -840,9 +839,6 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct p9_fid *newdirfid;
 	struct p9_wstat wstat;
 
-	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	P9_DPRINTK(P9_DEBUG_VFS, "\n");
 	retval = 0;
 	old_inode = old_dentry->d_inode;
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 03330e2e390c..e3e9efc1fdd8 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -320,8 +320,6 @@ affs_rmdir(struct inode *dir, struct dentry *dentry)
 		 dentry->d_inode->i_ino,
 		 (int)dentry->d_name.len, dentry->d_name.name);
 
-	dentry_unhash(dentry);
-
 	return affs_remove_header(dentry);
 }
 
@@ -419,9 +417,6 @@ affs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct buffer_head *bh = NULL;
 	int retval;
 
-	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	pr_debug("AFFS: rename(old=%u,\"%*s\" to new=%u,\"%*s\")\n",
 		 (u32)old_dir->i_ino, (int)old_dentry->d_name.len, old_dentry->d_name.name,
 		 (u32)new_dir->i_ino, (int)new_dentry->d_name.len, new_dentry->d_name.name);
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 2c4e05160042..1b0b19550015 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -584,11 +584,11 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 
 success:
 	d_add(dentry, inode);
-	_leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%llu }",
+	_leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%u }",
 	       fid.vnode,
 	       fid.unique,
 	       dentry->d_inode->i_ino,
-	       (unsigned long long)dentry->d_inode->i_version);
+	       dentry->d_inode->i_generation);
 
 	return NULL;
 }
@@ -671,10 +671,10 @@ static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
 		 * been deleted and replaced, and the original vnode ID has
 		 * been reused */
 		if (fid.unique != vnode->fid.unique) {
-			_debug("%s: file deleted (uq %u -> %u I:%llu)",
+			_debug("%s: file deleted (uq %u -> %u I:%u)",
 			       dentry->d_name.name, fid.unique,
 			       vnode->fid.unique,
-			       (unsigned long long)dentry->d_inode->i_version);
+			       dentry->d_inode->i_generation);
 			spin_lock(&vnode->lock);
 			set_bit(AFS_VNODE_DELETED, &vnode->flags);
 			spin_unlock(&vnode->lock);
@@ -845,8 +845,6 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
 	_enter("{%x:%u},{%s}",
 	       dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name);
 
-	dentry_unhash(dentry);
-
 	ret = -ENAMETOOLONG;
 	if (dentry->d_name.len >= AFSNAMEMAX)
 		goto error;
@@ -1148,9 +1146,6 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct key *key;
 	int ret;
 
-	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	vnode = AFS_FS_I(old_dentry->d_inode);
 	orig_dvnode = AFS_FS_I(old_dir);
 	new_dvnode = AFS_FS_I(new_dir);
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 4bd0218473a9..346e3289abd7 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -89,7 +89,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
 			i_size_write(&vnode->vfs_inode, size);
 			vnode->vfs_inode.i_uid = status->owner;
 			vnode->vfs_inode.i_gid = status->group;
-			vnode->vfs_inode.i_version = vnode->fid.unique;
+			vnode->vfs_inode.i_generation = vnode->fid.unique;
 			vnode->vfs_inode.i_nlink = status->nlink;
 
 			mode = vnode->vfs_inode.i_mode;
@@ -102,6 +102,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
 		vnode->vfs_inode.i_ctime.tv_sec	= status->mtime_server;
 		vnode->vfs_inode.i_mtime	= vnode->vfs_inode.i_ctime;
 		vnode->vfs_inode.i_atime	= vnode->vfs_inode.i_ctime;
+		vnode->vfs_inode.i_version	= data_version;
 	}
 
 	expected_version = status->data_version;
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index db66c5201474..0fdab6e03d87 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -75,7 +75,8 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
 	inode->i_ctime.tv_nsec	= 0;
 	inode->i_atime		= inode->i_mtime = inode->i_ctime;
 	inode->i_blocks		= 0;
-	inode->i_version	= vnode->fid.unique;
+	inode->i_generation	= vnode->fid.unique;
+	inode->i_version	= vnode->status.data_version;
 	inode->i_mapping->a_ops	= &afs_fs_aops;
 
 	/* check to see whether a symbolic link is really a mountpoint */
@@ -100,7 +101,7 @@ static int afs_iget5_test(struct inode *inode, void *opaque)
 	struct afs_iget_data *data = opaque;
 
 	return inode->i_ino == data->fid.vnode &&
-		inode->i_version == data->fid.unique;
+		inode->i_generation == data->fid.unique;
 }
 
 /*
@@ -122,7 +123,7 @@ static int afs_iget5_set(struct inode *inode, void *opaque)
 	struct afs_vnode *vnode = AFS_FS_I(inode);
 
 	inode->i_ino = data->fid.vnode;
-	inode->i_version = data->fid.unique;
+	inode->i_generation = data->fid.unique;
 	vnode->fid = data->fid;
 	vnode->volume = data->volume;
 
@@ -380,8 +381,7 @@ int afs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 
 	inode = dentry->d_inode;
 
-	_enter("{ ino=%lu v=%llu }", inode->i_ino,
-		(unsigned long long)inode->i_version);
+	_enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation);
 
 	generic_fillattr(inode, stat);
 	return 0;
diff --git a/fs/afs/super.c b/fs/afs/super.c
index fb240e8766d6..356dcf0929e8 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -31,8 +31,8 @@
 static void afs_i_init_once(void *foo);
 static struct dentry *afs_mount(struct file_system_type *fs_type,
 		      int flags, const char *dev_name, void *data);
+static void afs_kill_super(struct super_block *sb);
 static struct inode *afs_alloc_inode(struct super_block *sb);
-static void afs_put_super(struct super_block *sb);
 static void afs_destroy_inode(struct inode *inode);
 static int afs_statfs(struct dentry *dentry, struct kstatfs *buf);
 
@@ -40,7 +40,7 @@ struct file_system_type afs_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "afs",
 	.mount		= afs_mount,
-	.kill_sb	= kill_anon_super,
+	.kill_sb	= afs_kill_super,
 	.fs_flags	= 0,
 };
 
@@ -50,7 +50,6 @@ static const struct super_operations afs_super_ops = {
 	.drop_inode	= afs_drop_inode,
 	.destroy_inode	= afs_destroy_inode,
 	.evict_inode	= afs_evict_inode,
-	.put_super	= afs_put_super,
 	.show_options	= generic_show_options,
 };
 
@@ -282,19 +281,25 @@ static int afs_parse_device_name(struct afs_mount_params *params,
  */
 static int afs_test_super(struct super_block *sb, void *data)
 {
-	struct afs_mount_params *params = data;
+	struct afs_super_info *as1 = data;
 	struct afs_super_info *as = sb->s_fs_info;
 
-	return as->volume == params->volume;
+	return as->volume == as1->volume;
+}
+
+static int afs_set_super(struct super_block *sb, void *data)
+{
+	sb->s_fs_info = data;
+	return set_anon_super(sb, NULL);
 }
 
 /*
  * fill in the superblock
  */
-static int afs_fill_super(struct super_block *sb, void *data)
+static int afs_fill_super(struct super_block *sb,
+			  struct afs_mount_params *params)
 {
-	struct afs_mount_params *params = data;
-	struct afs_super_info *as = NULL;
+	struct afs_super_info *as = sb->s_fs_info;
 	struct afs_fid fid;
 	struct dentry *root = NULL;
 	struct inode *inode = NULL;
@@ -302,23 +307,13 @@ static int afs_fill_super(struct super_block *sb, void *data)
 
 	_enter("");
 
-	/* allocate a superblock info record */
-	as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL);
-	if (!as) {
-		_leave(" = -ENOMEM");
-		return -ENOMEM;
-	}
-
-	afs_get_volume(params->volume);
-	as->volume = params->volume;
-
 	/* fill in the superblock */
 	sb->s_blocksize		= PAGE_CACHE_SIZE;
 	sb->s_blocksize_bits	= PAGE_CACHE_SHIFT;
 	sb->s_magic		= AFS_FS_MAGIC;
 	sb->s_op		= &afs_super_ops;
-	sb->s_fs_info		= as;
 	sb->s_bdi		= &as->volume->bdi;
+	strlcpy(sb->s_id, as->volume->vlocation->vldb.name, sizeof(sb->s_id));
 
 	/* allocate the root inode and dentry */
 	fid.vid		= as->volume->vid;
@@ -326,7 +321,7 @@ static int afs_fill_super(struct super_block *sb, void *data)
 	fid.unique	= 1;
 	inode = afs_iget(sb, params->key, &fid, NULL, NULL);
 	if (IS_ERR(inode))
-		goto error_inode;
+		return PTR_ERR(inode);
 
 	if (params->autocell)
 		set_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(inode)->flags);
@@ -342,16 +337,8 @@ static int afs_fill_super(struct super_block *sb, void *data)
 	_leave(" = 0");
 	return 0;
 
-error_inode:
-	ret = PTR_ERR(inode);
-	inode = NULL;
 error:
 	iput(inode);
-	afs_put_volume(as->volume);
-	kfree(as);
-
-	sb->s_fs_info = NULL;
-
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -367,6 +354,7 @@ static struct dentry *afs_mount(struct file_system_type *fs_type,
 	struct afs_volume *vol;
 	struct key *key;
 	char *new_opts = kstrdup(options, GFP_KERNEL);
+	struct afs_super_info *as;
 	int ret;
 
 	_enter(",,%s,%p", dev_name, options);
@@ -399,12 +387,22 @@ static struct dentry *afs_mount(struct file_system_type *fs_type,
 		ret = PTR_ERR(vol);
 		goto error;
 	}
-	params.volume = vol;
+
+	/* allocate a superblock info record */
+	as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL);
+	if (!as) {
+		ret = -ENOMEM;
+		afs_put_volume(vol);
+		goto error;
+	}
+	as->volume = vol;
 
 	/* allocate a deviceless superblock */
-	sb = sget(fs_type, afs_test_super, set_anon_super, &params);
+	sb = sget(fs_type, afs_test_super, afs_set_super, as);
 	if (IS_ERR(sb)) {
 		ret = PTR_ERR(sb);
+		afs_put_volume(vol);
+		kfree(as);
 		goto error;
 	}
 
@@ -422,16 +420,16 @@ static struct dentry *afs_mount(struct file_system_type *fs_type,
 	} else {
 		_debug("reuse");
 		ASSERTCMP(sb->s_flags, &, MS_ACTIVE);
+		afs_put_volume(vol);
+		kfree(as);
 	}
 
-	afs_put_volume(params.volume);
 	afs_put_cell(params.cell);
 	kfree(new_opts);
 	_leave(" = 0 [%p]", sb);
 	return dget(sb->s_root);
 
 error:
-	afs_put_volume(params.volume);
 	afs_put_cell(params.cell);
 	key_put(params.key);
 	kfree(new_opts);
@@ -439,18 +437,12 @@ error:
 	return ERR_PTR(ret);
 }
 
-/*
- * finish the unmounting process on the superblock
- */
-static void afs_put_super(struct super_block *sb)
+static void afs_kill_super(struct super_block *sb)
 {
 	struct afs_super_info *as = sb->s_fs_info;
-
-	_enter("");
-
+	kill_anon_super(sb);
 	afs_put_volume(as->volume);
-
-	_leave("");
+	kfree(as);
 }
 
 /*
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 789b3afb3423..b806285ff853 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -84,23 +84,21 @@ void afs_put_writeback(struct afs_writeback *wb)
  * partly or wholly fill a page that's under preparation for writing
  */
 static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
-			 loff_t pos, unsigned len, struct page *page)
+			 loff_t pos, struct page *page)
 {
 	loff_t i_size;
-	unsigned eof;
 	int ret;
+	int len;
 
-	_enter(",,%llu,%u", (unsigned long long)pos, len);
-
-	ASSERTCMP(len, <=, PAGE_CACHE_SIZE);
+	_enter(",,%llu", (unsigned long long)pos);
 
 	i_size = i_size_read(&vnode->vfs_inode);
-	if (pos + len > i_size)
-		eof = i_size;
+	if (pos + PAGE_CACHE_SIZE > i_size)
+		len = i_size - pos;
 	else
-		eof = PAGE_CACHE_SIZE;
+		len = PAGE_CACHE_SIZE;
 
-	ret = afs_vnode_fetch_data(vnode, key, 0, eof, page);
+	ret = afs_vnode_fetch_data(vnode, key, pos, len, page);
 	if (ret < 0) {
 		if (ret == -ENOENT) {
 			_debug("got NOENT from server"
@@ -153,9 +151,8 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 	*pagep = page;
 	/* page won't leak in error case: it eventually gets cleaned off LRU */
 
-	if (!PageUptodate(page)) {
-		_debug("not up to date");
-		ret = afs_fill_page(vnode, key, pos, len, page);
+	if (!PageUptodate(page) && len != PAGE_CACHE_SIZE) {
+		ret = afs_fill_page(vnode, key, index << PAGE_CACHE_SHIFT, page);
 		if (ret < 0) {
 			kfree(candidate);
 			_leave(" = %d [prep]", ret);
diff --git a/fs/attr.c b/fs/attr.c
index 91dbe2a107f2..caf2aa521e2b 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -175,6 +175,13 @@ int notify_change(struct dentry * dentry, struct iattr * attr)
 			return -EPERM;
 	}
 
+	if ((ia_valid & ATTR_MODE)) {
+		mode_t amode = attr->ia_mode;
+		/* Flag setting protected by i_mutex */
+		if (is_sxid(amode))
+			inode->i_flags &= ~S_NOSEC;
+	}
+
 	now = current_fs_time(inode->i_sb);
 
 	attr->ia_ctime = now;
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 87d95a8cddbc..f55ae23b137e 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -583,8 +583,6 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
 	if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
-	dentry_unhash(dentry);
-
 	if (atomic_dec_and_test(&ino->count)) {
 		p_ino = autofs4_dentry_ino(dentry->d_parent);
 		if (p_ino && dentry->d_parent != dentry)
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 9ad2369d9e35..bfcb18feb1df 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -231,9 +231,6 @@ static int bad_inode_readlink(struct dentry *dentry, char __user *buffer,
 
 static int bad_inode_permission(struct inode *inode, int mask, unsigned int flags)
 {
-	if (flags & IPERM_FLAG_RCU)
-		return -ECHILD;
-
 	return -EIO;
 }
 
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index c7d1d06b0483..b14cebfd9047 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -224,9 +224,6 @@ static int bfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct bfs_sb_info *info;
 	int error = -ENOENT;
 
-	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	old_bh = new_bh = NULL;
 	old_inode = old_dentry->d_inode;
 	if (S_ISDIR(old_inode->i_mode))
diff --git a/fs/bio.c b/fs/bio.c
index 840a0d755248..9bfade8a609b 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -638,10 +638,11 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
  *	@offset: vec entry offset
  *
  *	Attempt to add a page to the bio_vec maplist. This can fail for a
- *	number of reasons, such as the bio being full or target block
- *	device limitations. The target block device must allow bio's
- *      smaller than PAGE_SIZE, so it is always possible to add a single
- *      page to an empty bio. This should only be used by REQ_PC bios.
+ *	number of reasons, such as the bio being full or target block device
+ *	limitations. The target block device must allow bio's up to PAGE_SIZE,
+ *	so it is always possible to add a single page to an empty bio.
+ *
+ *	This should only be used by REQ_PC bios.
  */
 int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page,
 		    unsigned int len, unsigned int offset)
@@ -659,10 +660,9 @@ EXPORT_SYMBOL(bio_add_pc_page);
  *	@offset: vec entry offset
  *
  *	Attempt to add a page to the bio_vec maplist. This can fail for a
- *	number of reasons, such as the bio being full or target block
- *	device limitations. The target block device must allow bio's
- *      smaller than PAGE_SIZE, so it is always possible to add a single
- *      page to an empty bio.
+ *	number of reasons, such as the bio being full or target block device
+ *	limitations. The target block device must allow bio's up to PAGE_SIZE,
+ *	so it is always possible to add a single page to an empty bio.
  */
 int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
 		 unsigned int offset)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1f2b19978333..610e8e0b04b8 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -762,7 +762,19 @@ static struct block_device *bd_start_claiming(struct block_device *bdev,
 	if (!disk)
 		return ERR_PTR(-ENXIO);
 
-	whole = bdget_disk(disk, 0);
+	/*
+	 * Normally, @bdev should equal what's returned from bdget_disk()
+	 * if partno is 0; however, some drivers (floppy) use multiple
+	 * bdev's for the same physical device and @bdev may be one of the
+	 * aliases.  Keep @bdev if partno is 0.  This means claimer
+	 * tracking is broken for those devices but it has always been that
+	 * way.
+	 */
+	if (partno)
+		whole = bdget_disk(disk, 0);
+	else
+		whole = bdgrab(bdev);
+
 	module_put(disk->fops->owner);
 	put_disk(disk);
 	if (!whole)
@@ -1272,8 +1284,8 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 		 * individual writeable reference is too fragile given the
 		 * way @mode is used in blkdev_get/put().
 		 */
-		if ((disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE) &&
-		    !res && (mode & FMODE_WRITE) && !bdev->bd_write_holder) {
+		if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder &&
+		    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
 			bdev->bd_write_holder = true;
 			disk_block_events(disk);
 		}
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 31610ea73aec..9b72dcf1cd25 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -7,4 +7,4 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
 	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
 	   export.o tree-log.o acl.o free-space-cache.o zlib.o lzo.o \
-	   compression.o delayed-ref.o relocation.o
+	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 44ea5b92e1ba..f66fc9959733 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -288,7 +288,7 @@ int btrfs_acl_chmod(struct inode *inode)
 		return 0;
 
 	acl = btrfs_get_acl(inode, ACL_TYPE_ACCESS);
-	if (IS_ERR(acl) || !acl)
+	if (IS_ERR_OR_NULL(acl))
 		return PTR_ERR(acl);
 
 	clone = posix_acl_clone(acl, GFP_KERNEL);
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 57c3bb2884ce..52d7eca8c7bf 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -22,6 +22,7 @@
 #include "extent_map.h"
 #include "extent_io.h"
 #include "ordered-data.h"
+#include "delayed-inode.h"
 
 /* in memory btrfs inode */
 struct btrfs_inode {
@@ -120,9 +121,6 @@ struct btrfs_inode {
 	 */
 	u64 index_cnt;
 
-	/* the start of block group preferred for allocations. */
-	u64 block_group;
-
 	/* the fsync log has some corner cases that mean we have to check
 	 * directories to see if any unlinks have been done before
 	 * the directory was logged.  See tree-log.c for all the
@@ -152,20 +150,34 @@ struct btrfs_inode {
 	unsigned ordered_data_close:1;
 	unsigned orphan_meta_reserved:1;
 	unsigned dummy_inode:1;
+	unsigned in_defrag:1;
 
 	/*
 	 * always compress this one file
 	 */
 	unsigned force_compress:4;
 
+	struct btrfs_delayed_node *delayed_node;
+
 	struct inode vfs_inode;
 };
 
+extern unsigned char btrfs_filetype_table[];
+
 static inline struct btrfs_inode *BTRFS_I(struct inode *inode)
 {
 	return container_of(inode, struct btrfs_inode, vfs_inode);
 }
 
+static inline u64 btrfs_ino(struct inode *inode)
+{
+	u64 ino = BTRFS_I(inode)->location.objectid;
+
+	if (ino <= BTRFS_FIRST_FREE_OBJECTID)
+		ino = inode->i_ino;
+	return ino;
+}
+
 static inline void btrfs_i_size_write(struct inode *inode, u64 size)
 {
 	i_size_write(inode, size);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 41d1d7c70e29..bfe42b03eaf9 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -125,9 +125,10 @@ static int check_compressed_csum(struct inode *inode,
 		kunmap_atomic(kaddr, KM_USER0);
 
 		if (csum != *cb_sum) {
-			printk(KERN_INFO "btrfs csum failed ino %lu "
+			printk(KERN_INFO "btrfs csum failed ino %llu "
 			       "extent %llu csum %u "
-			       "wanted %u mirror %d\n", inode->i_ino,
+			       "wanted %u mirror %d\n",
+			       (unsigned long long)btrfs_ino(inode),
 			       (unsigned long long)disk_start,
 			       csum, *cb_sum, cb->mirror_num);
 			ret = -EIO;
@@ -332,7 +333,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	struct compressed_bio *cb;
 	unsigned long bytes_left;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
-	int page_index = 0;
+	int pg_index = 0;
 	struct page *page;
 	u64 first_byte = disk_start;
 	struct block_device *bdev;
@@ -366,8 +367,8 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 
 	/* create and submit bios for the compressed pages */
 	bytes_left = compressed_len;
-	for (page_index = 0; page_index < cb->nr_pages; page_index++) {
-		page = compressed_pages[page_index];
+	for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) {
+		page = compressed_pages[pg_index];
 		page->mapping = inode->i_mapping;
 		if (bio->bi_size)
 			ret = io_tree->ops->merge_bio_hook(page, 0,
@@ -432,7 +433,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 				     struct compressed_bio *cb)
 {
 	unsigned long end_index;
-	unsigned long page_index;
+	unsigned long pg_index;
 	u64 last_offset;
 	u64 isize = i_size_read(inode);
 	int ret;
@@ -456,13 +457,13 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 	end_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
 
 	while (last_offset < compressed_end) {
-		page_index = last_offset >> PAGE_CACHE_SHIFT;
+		pg_index = last_offset >> PAGE_CACHE_SHIFT;
 
-		if (page_index > end_index)
+		if (pg_index > end_index)
 			break;
 
 		rcu_read_lock();
-		page = radix_tree_lookup(&mapping->page_tree, page_index);
+		page = radix_tree_lookup(&mapping->page_tree, pg_index);
 		rcu_read_unlock();
 		if (page) {
 			misses++;
@@ -476,7 +477,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		if (!page)
 			break;
 
-		if (add_to_page_cache_lru(page, mapping, page_index,
+		if (add_to_page_cache_lru(page, mapping, pg_index,
 								GFP_NOFS)) {
 			page_cache_release(page);
 			goto next;
@@ -560,7 +561,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	unsigned long uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE;
 	unsigned long compressed_len;
 	unsigned long nr_pages;
-	unsigned long page_index;
+	unsigned long pg_index;
 	struct page *page;
 	struct block_device *bdev;
 	struct bio *comp_bio;
@@ -613,10 +614,10 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 
 	bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
 
-	for (page_index = 0; page_index < nr_pages; page_index++) {
-		cb->compressed_pages[page_index] = alloc_page(GFP_NOFS |
+	for (pg_index = 0; pg_index < nr_pages; pg_index++) {
+		cb->compressed_pages[pg_index] = alloc_page(GFP_NOFS |
 							      __GFP_HIGHMEM);
-		if (!cb->compressed_pages[page_index])
+		if (!cb->compressed_pages[pg_index])
 			goto fail2;
 	}
 	cb->nr_pages = nr_pages;
@@ -634,8 +635,8 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	comp_bio->bi_end_io = end_compressed_bio_read;
 	atomic_inc(&cb->pending_bios);
 
-	for (page_index = 0; page_index < nr_pages; page_index++) {
-		page = cb->compressed_pages[page_index];
+	for (pg_index = 0; pg_index < nr_pages; pg_index++) {
+		page = cb->compressed_pages[pg_index];
 		page->mapping = inode->i_mapping;
 		page->index = em_start >> PAGE_CACHE_SHIFT;
 
@@ -702,8 +703,8 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	return 0;
 
 fail2:
-	for (page_index = 0; page_index < nr_pages; page_index++)
-		free_page((unsigned long)cb->compressed_pages[page_index]);
+	for (pg_index = 0; pg_index < nr_pages; pg_index++)
+		free_page((unsigned long)cb->compressed_pages[pg_index]);
 
 	kfree(cb->compressed_pages);
 fail1:
@@ -945,7 +946,7 @@ void btrfs_exit_compress(void)
 int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 			      unsigned long total_out, u64 disk_start,
 			      struct bio_vec *bvec, int vcnt,
-			      unsigned long *page_index,
+			      unsigned long *pg_index,
 			      unsigned long *pg_offset)
 {
 	unsigned long buf_offset;
@@ -954,7 +955,7 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 	unsigned long working_bytes = total_out - buf_start;
 	unsigned long bytes;
 	char *kaddr;
-	struct page *page_out = bvec[*page_index].bv_page;
+	struct page *page_out = bvec[*pg_index].bv_page;
 
 	/*
 	 * start byte is the first byte of the page we're currently
@@ -995,11 +996,11 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 
 		/* check if we need to pick another page */
 		if (*pg_offset == PAGE_CACHE_SIZE) {
-			(*page_index)++;
-			if (*page_index >= vcnt)
+			(*pg_index)++;
+			if (*pg_index >= vcnt)
 				return 0;
 
-			page_out = bvec[*page_index].bv_page;
+			page_out = bvec[*pg_index].bv_page;
 			*pg_offset = 0;
 			start_byte = page_offset(page_out) - disk_start;
 
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 51000174b9d7..a12059f4f0fd 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -37,7 +37,7 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 			      unsigned long total_out, u64 disk_start,
 			      struct bio_vec *bvec, int vcnt,
-			      unsigned long *page_index,
+			      unsigned long *pg_index,
 			      unsigned long *pg_offset);
 
 int btrfs_submit_compressed_write(struct inode *inode, u64 start,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 84d7ca1fe0ba..2e667868e0d2 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -38,18 +38,11 @@ static int balance_node_right(struct btrfs_trans_handle *trans,
 			      struct extent_buffer *src_buf);
 static int del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		   struct btrfs_path *path, int level, int slot);
-static int setup_items_for_insert(struct btrfs_trans_handle *trans,
-			struct btrfs_root *root, struct btrfs_path *path,
-			struct btrfs_key *cpu_key, u32 *data_size,
-			u32 total_data, u32 total_size, int nr);
-
 
 struct btrfs_path *btrfs_alloc_path(void)
 {
 	struct btrfs_path *path;
 	path = kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
-	if (path)
-		path->reada = 1;
 	return path;
 }
 
@@ -107,7 +100,7 @@ void btrfs_free_path(struct btrfs_path *p)
 {
 	if (!p)
 		return;
-	btrfs_release_path(NULL, p);
+	btrfs_release_path(p);
 	kmem_cache_free(btrfs_path_cachep, p);
 }
 
@@ -117,7 +110,7 @@ void btrfs_free_path(struct btrfs_path *p)
  *
  * It is safe to call this on paths that no locks or extent buffers held.
  */
-noinline void btrfs_release_path(struct btrfs_root *root, struct btrfs_path *p)
+noinline void btrfs_release_path(struct btrfs_path *p)
 {
 	int i;
 
@@ -1229,11 +1222,13 @@ static void reada_for_search(struct btrfs_root *root,
 	u64 search;
 	u64 target;
 	u64 nread = 0;
+	u64 gen;
 	int direction = path->reada;
 	struct extent_buffer *eb;
 	u32 nr;
 	u32 blocksize;
 	u32 nscan = 0;
+	bool map = true;
 
 	if (level != 1)
 		return;
@@ -1255,7 +1250,19 @@ static void reada_for_search(struct btrfs_root *root,
 
 	nritems = btrfs_header_nritems(node);
 	nr = slot;
+	if (node->map_token || path->skip_locking)
+		map = false;
+
 	while (1) {
+		if (map && !node->map_token) {
+			unsigned long offset = btrfs_node_key_ptr_offset(nr);
+			map_private_extent_buffer(node, offset,
+						  sizeof(struct btrfs_key_ptr),
+						  &node->map_token,
+						  &node->kaddr,
+						  &node->map_start,
+						  &node->map_len, KM_USER1);
+		}
 		if (direction < 0) {
 			if (nr == 0)
 				break;
@@ -1273,14 +1280,23 @@ static void reada_for_search(struct btrfs_root *root,
 		search = btrfs_node_blockptr(node, nr);
 		if ((search <= target && target - search <= 65536) ||
 		    (search > target && search - target <= 65536)) {
-			readahead_tree_block(root, search, blocksize,
-				     btrfs_node_ptr_generation(node, nr));
+			gen = btrfs_node_ptr_generation(node, nr);
+			if (map && node->map_token) {
+				unmap_extent_buffer(node, node->map_token,
+						    KM_USER1);
+				node->map_token = NULL;
+			}
+			readahead_tree_block(root, search, blocksize, gen);
 			nread += blocksize;
 		}
 		nscan++;
 		if ((nread > 65536 || nscan > 32))
 			break;
 	}
+	if (map && node->map_token) {
+		unmap_extent_buffer(node, node->map_token, KM_USER1);
+		node->map_token = NULL;
+	}
 }
 
 /*
@@ -1328,7 +1344,7 @@ static noinline int reada_for_balance(struct btrfs_root *root,
 		ret = -EAGAIN;
 
 		/* release the whole path */
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 
 		/* read the blocks */
 		if (block1)
@@ -1475,7 +1491,7 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 				return 0;
 			}
 			free_extent_buffer(tmp);
-			btrfs_release_path(NULL, p);
+			btrfs_release_path(p);
 			return -EIO;
 		}
 	}
@@ -1494,7 +1510,7 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 	if (p->reada)
 		reada_for_search(root, p, level, slot, key->objectid);
 
-	btrfs_release_path(NULL, p);
+	btrfs_release_path(p);
 
 	ret = -EAGAIN;
 	tmp = read_tree_block(root, blocknr, blocksize, 0);
@@ -1563,7 +1579,7 @@ setup_nodes_for_search(struct btrfs_trans_handle *trans,
 		}
 		b = p->nodes[level];
 		if (!b) {
-			btrfs_release_path(NULL, p);
+			btrfs_release_path(p);
 			goto again;
 		}
 		BUG_ON(btrfs_header_nritems(b) == 1);
@@ -1653,9 +1669,6 @@ again:
 		}
 cow_done:
 		BUG_ON(!cow && ins_len);
-		if (level != btrfs_header_level(b))
-			WARN_ON(1);
-		level = btrfs_header_level(b);
 
 		p->nodes[level] = b;
 		if (!p->skip_locking)
@@ -1753,7 +1766,7 @@ done:
 	if (!p->leave_spinning)
 		btrfs_set_path_blocking(p);
 	if (ret < 0)
-		btrfs_release_path(root, p);
+		btrfs_release_path(p);
 	return ret;
 }
 
@@ -3026,7 +3039,7 @@ static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans,
 				    struct btrfs_file_extent_item);
 		extent_len = btrfs_file_extent_num_bytes(leaf, fi);
 	}
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	path->keep_locks = 1;
 	path->search_for_split = 1;
@@ -3216,7 +3229,6 @@ int btrfs_truncate_item(struct btrfs_trans_handle *trans,
 			struct btrfs_path *path,
 			u32 new_size, int from_end)
 {
-	int ret = 0;
 	int slot;
 	struct extent_buffer *leaf;
 	struct btrfs_item *item;
@@ -3314,12 +3326,11 @@ int btrfs_truncate_item(struct btrfs_trans_handle *trans,
 	btrfs_set_item_size(leaf, item, new_size);
 	btrfs_mark_buffer_dirty(leaf);
 
-	ret = 0;
 	if (btrfs_leaf_free_space(root, leaf) < 0) {
 		btrfs_print_leaf(root, leaf);
 		BUG();
 	}
-	return ret;
+	return 0;
 }
 
 /*
@@ -3329,7 +3340,6 @@ int btrfs_extend_item(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root, struct btrfs_path *path,
 		      u32 data_size)
 {
-	int ret = 0;
 	int slot;
 	struct extent_buffer *leaf;
 	struct btrfs_item *item;
@@ -3394,12 +3404,11 @@ int btrfs_extend_item(struct btrfs_trans_handle *trans,
 	btrfs_set_item_size(leaf, item, old_size + data_size);
 	btrfs_mark_buffer_dirty(leaf);
 
-	ret = 0;
 	if (btrfs_leaf_free_space(root, leaf) < 0) {
 		btrfs_print_leaf(root, leaf);
 		BUG();
 	}
-	return ret;
+	return 0;
 }
 
 /*
@@ -3559,11 +3568,10 @@ out:
  * to save stack depth by doing the bulk of the work in a function
  * that doesn't call btrfs_search_slot
  */
-static noinline_for_stack int
-setup_items_for_insert(struct btrfs_trans_handle *trans,
-		      struct btrfs_root *root, struct btrfs_path *path,
-		      struct btrfs_key *cpu_key, u32 *data_size,
-		      u32 total_data, u32 total_size, int nr)
+int setup_items_for_insert(struct btrfs_trans_handle *trans,
+			   struct btrfs_root *root, struct btrfs_path *path,
+			   struct btrfs_key *cpu_key, u32 *data_size,
+			   u32 total_data, u32 total_size, int nr)
 {
 	struct btrfs_item *item;
 	int i;
@@ -3647,7 +3655,6 @@ setup_items_for_insert(struct btrfs_trans_handle *trans,
 
 	ret = 0;
 	if (slot == 0) {
-		struct btrfs_disk_key disk_key;
 		btrfs_cpu_key_to_disk(&disk_key, cpu_key);
 		ret = fixup_low_keys(trans, root, path, &disk_key, 1);
 	}
@@ -3949,7 +3956,7 @@ int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path)
 	else
 		return 1;
 
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
 		return ret;
@@ -4073,7 +4080,7 @@ find_next_key:
 			sret = btrfs_find_next_key(root, path, min_key, level,
 						  cache_only, min_trans);
 			if (sret == 0) {
-				btrfs_release_path(root, path);
+				btrfs_release_path(path);
 				goto again;
 			} else {
 				goto out;
@@ -4152,7 +4159,7 @@ next:
 				btrfs_node_key_to_cpu(c, &cur_key, slot);
 
 			orig_lowest = path->lowest_level;
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			path->lowest_level = level;
 			ret = btrfs_search_slot(NULL, root, &cur_key, path,
 						0, 0);
@@ -4229,7 +4236,7 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path)
 again:
 	level = 1;
 	next = NULL;
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	path->keep_locks = 1;
 
@@ -4285,7 +4292,7 @@ again:
 			goto again;
 
 		if (ret < 0) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			goto done;
 		}
 
@@ -4324,7 +4331,7 @@ again:
 			goto again;
 
 		if (ret < 0) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			goto done;
 		}
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8f4b81de3ae2..f30ac05dbda7 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -19,10 +19,10 @@
 #ifndef __BTRFS_CTREE__
 #define __BTRFS_CTREE__
 
-#include <linux/version.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/fs.h>
+#include <linux/rwsem.h>
 #include <linux/completion.h>
 #include <linux/backing-dev.h>
 #include <linux/wait.h>
@@ -33,6 +33,7 @@
 #include "extent_io.h"
 #include "extent_map.h"
 #include "async-thread.h"
+#include "ioctl.h"
 
 struct btrfs_trans_handle;
 struct btrfs_transaction;
@@ -105,6 +106,12 @@ struct btrfs_ordered_sum;
 /* For storing free space cache */
 #define BTRFS_FREE_SPACE_OBJECTID -11ULL
 
+/*
+ * The inode number assigned to the special inode for sotring
+ * free ino cache
+ */
+#define BTRFS_FREE_INO_OBJECTID -12ULL
+
 /* dummy objectid represents multiple objectids */
 #define BTRFS_MULTIPLE_OBJECTIDS -255ULL
 
@@ -187,7 +194,6 @@ struct btrfs_mapping_tree {
 	struct extent_map_tree map_tree;
 };
 
-#define BTRFS_UUID_SIZE 16
 struct btrfs_dev_item {
 	/* the internal btrfs device id */
 	__le64 devid;
@@ -294,7 +300,6 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes)
 		sizeof(struct btrfs_stripe) * (num_stripes - 1);
 }
 
-#define BTRFS_FSID_SIZE 16
 #define BTRFS_HEADER_FLAG_WRITTEN	(1ULL << 0)
 #define BTRFS_HEADER_FLAG_RELOC		(1ULL << 1)
 
@@ -510,6 +515,12 @@ struct btrfs_extent_item_v0 {
 /* use full backrefs for extent pointers in the block */
 #define BTRFS_BLOCK_FLAG_FULL_BACKREF	(1ULL << 8)
 
+/*
+ * this flag is only used internally by scrub and may be changed at any time
+ * it is only declared here to avoid collisions
+ */
+#define BTRFS_EXTENT_FLAG_SUPER		(1ULL << 48)
+
 struct btrfs_tree_block_info {
 	struct btrfs_disk_key key;
 	u8 level;
@@ -740,12 +751,12 @@ struct btrfs_space_info {
 	 */
 	unsigned long reservation_progress;
 
-	int full:1;		/* indicates that we cannot allocate any more
+	unsigned int full:1;	/* indicates that we cannot allocate any more
 				   chunks for this space */
-	int chunk_alloc:1;	/* set if we are allocating a chunk */
+	unsigned int chunk_alloc:1;	/* set if we are allocating a chunk */
 
-	int force_alloc;	/* set if we need to force a chunk alloc for
-				   this space */
+	unsigned int force_alloc;	/* set if we need to force a chunk
+					   alloc for this space */
 
 	struct list_head list;
 
@@ -830,9 +841,6 @@ struct btrfs_block_group_cache {
 	u64 bytes_super;
 	u64 flags;
 	u64 sectorsize;
-	int extents_thresh;
-	int free_extents;
-	int total_bitmaps;
 	unsigned int ro:1;
 	unsigned int dirty:1;
 	unsigned int iref:1;
@@ -847,9 +855,7 @@ struct btrfs_block_group_cache {
 	struct btrfs_space_info *space_info;
 
 	/* free space cache stuff */
-	spinlock_t tree_lock;
-	struct rb_root free_space_offset;
-	u64 free_space;
+	struct btrfs_free_space_ctl *free_space_ctl;
 
 	/* block group cache stuff */
 	struct rb_node cache_node;
@@ -869,6 +875,7 @@ struct btrfs_block_group_cache {
 struct reloc_control;
 struct btrfs_device;
 struct btrfs_fs_devices;
+struct btrfs_delayed_root;
 struct btrfs_fs_info {
 	u8 fsid[BTRFS_FSID_SIZE];
 	u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
@@ -895,7 +902,10 @@ struct btrfs_fs_info {
 	/* logical->physical extent mapping */
 	struct btrfs_mapping_tree mapping_tree;
 
-	/* block reservation for extent, checksum and root tree */
+	/*
+	 * block reservation for extent, checksum, root tree and
+	 * delayed dir index item
+	 */
 	struct btrfs_block_rsv global_block_rsv;
 	/* block reservation for delay allocation */
 	struct btrfs_block_rsv delalloc_block_rsv;
@@ -919,7 +929,6 @@ struct btrfs_fs_info {
 	 * is required instead of the faster short fsync log commits
 	 */
 	u64 last_trans_log_full_commit;
-	u64 open_ioctl_trans;
 	unsigned long mount_opt:20;
 	unsigned long compress_type:4;
 	u64 max_inline;
@@ -936,7 +945,6 @@ struct btrfs_fs_info {
 	struct super_block *sb;
 	struct inode *btree_inode;
 	struct backing_dev_info bdi;
-	struct mutex trans_mutex;
 	struct mutex tree_log_mutex;
 	struct mutex transaction_kthread_mutex;
 	struct mutex cleaner_mutex;
@@ -957,6 +965,13 @@ struct btrfs_fs_info {
 	struct rw_semaphore subvol_sem;
 	struct srcu_struct subvol_srcu;
 
+	spinlock_t trans_lock;
+	/*
+	 * the reloc mutex goes with the trans lock, it is taken
+	 * during commit to protect us from the relocation code
+	 */
+	struct mutex reloc_mutex;
+
 	struct list_head trans_list;
 	struct list_head hashers;
 	struct list_head dead_roots;
@@ -969,6 +984,7 @@ struct btrfs_fs_info {
 	atomic_t async_submit_draining;
 	atomic_t nr_async_bios;
 	atomic_t async_delalloc_pages;
+	atomic_t open_ioctl_trans;
 
 	/*
 	 * this is used by the balancing code to wait for all the pending
@@ -1022,6 +1038,7 @@ struct btrfs_fs_info {
 	 * for the sys_munmap function call path
 	 */
 	struct btrfs_workers fixup_workers;
+	struct btrfs_workers delayed_workers;
 	struct task_struct *transaction_kthread;
 	struct task_struct *cleaner_kthread;
 	int thread_pool_size;
@@ -1032,6 +1049,7 @@ struct btrfs_fs_info {
 	int closing;
 	int log_root_recovering;
 	int enospc_unlink;
+	int trans_no_join;
 
 	u64 total_pinned;
 
@@ -1053,7 +1071,6 @@ struct btrfs_fs_info {
 	struct reloc_control *reloc_ctl;
 
 	spinlock_t delalloc_lock;
-	spinlock_t new_trans_lock;
 	u64 delalloc_bytes;
 
 	/* data_alloc_cluster is only used in ssd mode */
@@ -1062,6 +1079,11 @@ struct btrfs_fs_info {
 	/* all metadata allocations go through this cluster */
 	struct btrfs_free_cluster meta_alloc_cluster;
 
+	/* auto defrag inodes go here */
+	spinlock_t defrag_inodes_lock;
+	struct rb_root defrag_inodes;
+	atomic_t defrag_running;
+
 	spinlock_t ref_cache_lock;
 	u64 total_ref_cache_size;
 
@@ -1077,8 +1099,21 @@ struct btrfs_fs_info {
 
 	void *bdev_holder;
 
+	/* private scrub information */
+	struct mutex scrub_lock;
+	atomic_t scrubs_running;
+	atomic_t scrub_pause_req;
+	atomic_t scrubs_paused;
+	atomic_t scrub_cancel_req;
+	wait_queue_head_t scrub_pause_wait;
+	struct rw_semaphore scrub_super_lock;
+	int scrub_workers_refcnt;
+	struct btrfs_workers scrub_workers;
+
 	/* filesystem state */
 	u64 fs_state;
+
+	struct btrfs_delayed_root *delayed_root;
 };
 
 /*
@@ -1088,9 +1123,6 @@ struct btrfs_fs_info {
 struct btrfs_root {
 	struct extent_buffer *node;
 
-	/* the node lock is held while changing the node pointer */
-	spinlock_t node_lock;
-
 	struct extent_buffer *commit_root;
 	struct btrfs_root *log_root;
 	struct btrfs_root *reloc_root;
@@ -1107,6 +1139,16 @@ struct btrfs_root {
 	spinlock_t accounting_lock;
 	struct btrfs_block_rsv *block_rsv;
 
+	/* free ino cache stuff */
+	struct mutex fs_commit_mutex;
+	struct btrfs_free_space_ctl *free_ino_ctl;
+	enum btrfs_caching_type cached;
+	spinlock_t cache_lock;
+	wait_queue_head_t cache_wait;
+	struct btrfs_free_space_ctl *free_ino_pinned;
+	u64 cache_progress;
+	struct inode *cache_inode;
+
 	struct mutex log_mutex;
 	wait_queue_head_t log_writer_wait;
 	wait_queue_head_t log_commit_wait[2];
@@ -1135,6 +1177,14 @@ struct btrfs_root {
 	u32 type;
 
 	u64 highest_objectid;
+
+	/* btrfs_record_root_in_trans is a multi-step process,
+	 * and it can race with the balancing code.   But the
+	 * race is very small, and only the first time the root
+	 * is added to each transaction.  So in_trans_setup
+	 * is used to tell us when more checks are required
+	 */
+	unsigned long in_trans_setup;
 	int ref_cows;
 	int track_dirty;
 	int in_radix;
@@ -1144,7 +1194,6 @@ struct btrfs_root {
 	struct btrfs_key defrag_max;
 	int defrag_running;
 	char *name;
-	int in_sysfs;
 
 	/* the dirty list is only used by non-reference counted roots */
 	struct list_head dirty_list;
@@ -1162,12 +1211,49 @@ struct btrfs_root {
 	struct rb_root inode_tree;
 
 	/*
+	 * radix tree that keeps track of delayed nodes of every inode,
+	 * protected by inode_lock
+	 */
+	struct radix_tree_root delayed_nodes_tree;
+	/*
 	 * right now this just gets used so that a root has its own devid
 	 * for stat.  It may be used for more later
 	 */
 	struct super_block anon_super;
 };
 
+struct btrfs_ioctl_defrag_range_args {
+	/* start of the defrag operation */
+	__u64 start;
+
+	/* number of bytes to defrag, use (u64)-1 to say all */
+	__u64 len;
+
+	/*
+	 * flags for the operation, which can include turning
+	 * on compression for this one defrag
+	 */
+	__u64 flags;
+
+	/*
+	 * any extent bigger than this will be considered
+	 * already defragged.  Use 0 to take the kernel default
+	 * Use 1 to say every single extent must be rewritten
+	 */
+	__u32 extent_thresh;
+
+	/*
+	 * which compression method to use if turning on compression
+	 * for this defrag operation.  If unspecified, zlib will
+	 * be used
+	 */
+	__u32 compress_type;
+
+	/* spare for later */
+	__u32 unused[4];
+};
+
+
 /*
  * inode items have the data typically returned from stat and store other
  * info about object characteristics.  There is one for every file and dir in
@@ -1265,6 +1351,8 @@ struct btrfs_root {
 #define BTRFS_MOUNT_CLEAR_CACHE		(1 << 13)
 #define BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED (1 << 14)
 #define BTRFS_MOUNT_ENOSPC_DEBUG	 (1 << 15)
+#define BTRFS_MOUNT_AUTO_DEFRAG		(1 << 16)
+#define BTRFS_MOUNT_INODE_MAP_CACHE	(1 << 17)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)
@@ -1440,26 +1528,12 @@ static inline u64 btrfs_stripe_offset_nr(struct extent_buffer *eb,
 	return btrfs_stripe_offset(eb, btrfs_stripe_nr(c, nr));
 }
 
-static inline void btrfs_set_stripe_offset_nr(struct extent_buffer *eb,
-					     struct btrfs_chunk *c, int nr,
-					     u64 val)
-{
-	btrfs_set_stripe_offset(eb, btrfs_stripe_nr(c, nr), val);
-}
-
 static inline u64 btrfs_stripe_devid_nr(struct extent_buffer *eb,
 					 struct btrfs_chunk *c, int nr)
 {
 	return btrfs_stripe_devid(eb, btrfs_stripe_nr(c, nr));
 }
 
-static inline void btrfs_set_stripe_devid_nr(struct extent_buffer *eb,
-					     struct btrfs_chunk *c, int nr,
-					     u64 val)
-{
-	btrfs_set_stripe_devid(eb, btrfs_stripe_nr(c, nr), val);
-}
-
 /* struct btrfs_block_group_item */
 BTRFS_SETGET_STACK_FUNCS(block_group_used, struct btrfs_block_group_item,
 			 used, 64);
@@ -1517,14 +1591,6 @@ btrfs_inode_ctime(struct btrfs_inode_item *inode_item)
 	return (struct btrfs_timespec *)ptr;
 }
 
-static inline struct btrfs_timespec *
-btrfs_inode_otime(struct btrfs_inode_item *inode_item)
-{
-	unsigned long ptr = (unsigned long)inode_item;
-	ptr += offsetof(struct btrfs_inode_item, otime);
-	return (struct btrfs_timespec *)ptr;
-}
-
 BTRFS_SETGET_FUNCS(timespec_sec, struct btrfs_timespec, sec, 64);
 BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32);
 
@@ -1875,33 +1941,6 @@ static inline u8 *btrfs_header_chunk_tree_uuid(struct extent_buffer *eb)
 	return (u8 *)ptr;
 }
 
-static inline u8 *btrfs_super_fsid(struct extent_buffer *eb)
-{
-	unsigned long ptr = offsetof(struct btrfs_super_block, fsid);
-	return (u8 *)ptr;
-}
-
-static inline u8 *btrfs_header_csum(struct extent_buffer *eb)
-{
-	unsigned long ptr = offsetof(struct btrfs_header, csum);
-	return (u8 *)ptr;
-}
-
-static inline struct btrfs_node *btrfs_buffer_node(struct extent_buffer *eb)
-{
-	return NULL;
-}
-
-static inline struct btrfs_leaf *btrfs_buffer_leaf(struct extent_buffer *eb)
-{
-	return NULL;
-}
-
-static inline struct btrfs_header *btrfs_buffer_header(struct extent_buffer *eb)
-{
-	return NULL;
-}
-
 static inline int btrfs_is_leaf(struct extent_buffer *eb)
 {
 	return btrfs_header_level(eb) == 0;
@@ -2055,22 +2094,6 @@ static inline struct btrfs_root *btrfs_sb(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
-static inline int btrfs_set_root_name(struct btrfs_root *root,
-				      const char *name, int len)
-{
-	/* if we already have a name just free it */
-	kfree(root->name);
-
-	root->name = kmalloc(len+1, GFP_KERNEL);
-	if (!root->name)
-		return -ENOMEM;
-
-	memcpy(root->name, name, len);
-	root->name[len] = '\0';
-
-	return 0;
-}
-
 static inline u32 btrfs_level_size(struct btrfs_root *root, int level)
 {
 	if (level == 0)
@@ -2099,6 +2122,13 @@ static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info)
 }
 
 /* extent-tree.c */
+static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root,
+						 int num_items)
+{
+	return (root->leafsize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) *
+		3 * num_items;
+}
+
 void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
 int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, unsigned long count);
@@ -2108,12 +2138,9 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 			     u64 num_bytes, u64 *refs, u64 *flags);
 int btrfs_pin_extent(struct btrfs_root *root,
 		     u64 bytenr, u64 num, int reserved);
-int btrfs_drop_leaf_ref(struct btrfs_trans_handle *trans,
-			struct btrfs_root *root, struct extent_buffer *leaf);
 int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root,
 			  u64 objectid, u64 offset, u64 bytenr);
-int btrfs_copy_pinned(struct btrfs_root *root, struct extent_io_tree *copy);
 struct btrfs_block_group_cache *btrfs_lookup_block_group(
 						 struct btrfs_fs_info *info,
 						 u64 bytenr);
@@ -2224,6 +2251,9 @@ int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
 void btrfs_block_rsv_release(struct btrfs_root *root,
 			     struct btrfs_block_rsv *block_rsv,
 			     u64 num_bytes);
+int btrfs_truncate_reserve_metadata(struct btrfs_trans_handle *trans,
+				    struct btrfs_root *root,
+				    struct btrfs_block_rsv *rsv);
 int btrfs_set_block_group_ro(struct btrfs_root *root,
 			     struct btrfs_block_group_cache *cache);
 int btrfs_set_block_group_rw(struct btrfs_root *root,
@@ -2290,10 +2320,12 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root, struct extent_buffer *parent,
 		       int start_slot, int cache_only, u64 *last_ret,
 		       struct btrfs_key *progress);
-void btrfs_release_path(struct btrfs_root *root, struct btrfs_path *p);
+void btrfs_release_path(struct btrfs_path *p);
 struct btrfs_path *btrfs_alloc_path(void);
 void btrfs_free_path(struct btrfs_path *p);
 void btrfs_set_path_blocking(struct btrfs_path *p);
+void btrfs_clear_path_blocking(struct btrfs_path *p,
+			       struct extent_buffer *held);
 void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
 
 int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
@@ -2305,13 +2337,12 @@ static inline int btrfs_del_item(struct btrfs_trans_handle *trans,
 	return btrfs_del_items(trans, root, path, path->slots[0], 1);
 }
 
+int setup_items_for_insert(struct btrfs_trans_handle *trans,
+			   struct btrfs_root *root, struct btrfs_path *path,
+			   struct btrfs_key *cpu_key, u32 *data_size,
+			   u32 total_data, u32 total_size, int nr);
 int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root
 		      *root, struct btrfs_key *key, void *data, u32 data_size);
-int btrfs_insert_some_items(struct btrfs_trans_handle *trans,
-			    struct btrfs_root *root,
-			    struct btrfs_path *path,
-			    struct btrfs_key *cpu_key, u32 *data_size,
-			    int nr);
 int btrfs_insert_empty_items(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root,
 			     struct btrfs_path *path,
@@ -2335,6 +2366,15 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			struct extent_buffer *node,
 			struct extent_buffer *parent);
+static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
+{
+	/*
+	 * Get synced with close_ctree()
+	 */
+	smp_mb();
+	return fs_info->closing;
+}
+
 /* root-item.c */
 int btrfs_find_root_ref(struct btrfs_root *tree_root,
 			struct btrfs_path *path,
@@ -2357,8 +2397,6 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root
 		      *item);
 int btrfs_find_last_root(struct btrfs_root *root, u64 objectid, struct
 			 btrfs_root_item *item, struct btrfs_key *key);
-int btrfs_search_root(struct btrfs_root *root, u64 search_start,
-		      u64 *found_objectid);
 int btrfs_find_dead_roots(struct btrfs_root *root, u64 objectid);
 int btrfs_find_orphan_roots(struct btrfs_root *tree_root);
 int btrfs_set_root_node(struct btrfs_root_item *item,
@@ -2368,7 +2406,7 @@ void btrfs_check_and_init_root_item(struct btrfs_root_item *item);
 /* dir-item.c */
 int btrfs_insert_dir_item(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root, const char *name,
-			  int name_len, u64 dir,
+			  int name_len, struct inode *dir,
 			  struct btrfs_key *location, u8 type, u64 index);
 struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans,
 					     struct btrfs_root *root,
@@ -2413,12 +2451,6 @@ int btrfs_del_orphan_item(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root, u64 offset);
 int btrfs_find_orphan_item(struct btrfs_root *root, u64 offset);
 
-/* inode-map.c */
-int btrfs_find_free_objectid(struct btrfs_trans_handle *trans,
-			     struct btrfs_root *fs_root,
-			     u64 dirid, u64 *objectid);
-int btrfs_find_highest_inode(struct btrfs_root *fs_root, u64 *objectid);
-
 /* inode-item.c */
 int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
@@ -2463,8 +2495,6 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 			   struct btrfs_ordered_sum *sums);
 int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 		       struct bio *bio, u64 file_start, int contig);
-int btrfs_csum_file_bytes(struct btrfs_root *root, struct inode *inode,
-			  u64 start, unsigned long len);
 struct btrfs_csum_item *btrfs_lookup_csum(struct btrfs_trans_handle *trans,
 					  struct btrfs_root *root,
 					  struct btrfs_path *path,
@@ -2472,8 +2502,8 @@ struct btrfs_csum_item *btrfs_lookup_csum(struct btrfs_trans_handle *trans,
 int btrfs_csum_truncate(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root, struct btrfs_path *path,
 			u64 isize);
-int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start,
-			     u64 end, struct list_head *list);
+int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
+			     struct list_head *list, int search_commit);
 /* inode.c */
 
 /* RHEL and EL kernels have a patch that renames PG_checked to FsMisc */
@@ -2502,15 +2532,12 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       u32 min_type);
 
 int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput);
-int btrfs_start_one_delalloc_inode(struct btrfs_root *root, int delay_iput,
-				   int sync);
 int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
 			      struct extent_state **cached_state);
 int btrfs_writepages(struct address_space *mapping,
 		     struct writeback_control *wbc);
 int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
-			     struct btrfs_root *new_root,
-			     u64 new_dirid, u64 alloc_hint);
+			     struct btrfs_root *new_root, u64 new_dirid);
 int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
 			 size_t size, struct bio *bio, unsigned long bio_flags);
 
@@ -2520,9 +2547,8 @@ unsigned long btrfs_force_ra(struct address_space *mapping,
 int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 int btrfs_readpage(struct file *file, struct page *page);
 void btrfs_evict_inode(struct inode *inode);
-void btrfs_put_inode(struct inode *inode);
 int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
-void btrfs_dirty_inode(struct inode *inode);
+void btrfs_dirty_inode(struct inode *inode, int flags);
 struct inode *btrfs_alloc_inode(struct super_block *sb);
 void btrfs_destroy_inode(struct inode *inode);
 int btrfs_drop_inode(struct inode *inode);
@@ -2531,10 +2557,8 @@ void btrfs_destroy_cachep(void);
 long btrfs_ioctl_trans_end(struct file *file);
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 			 struct btrfs_root *root, int *was_new);
-int btrfs_commit_write(struct file *file, struct page *page,
-		       unsigned from, unsigned to);
 struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
-				    size_t page_offset, u64 start, u64 end,
+				    size_t pg_offset, u64 start, u64 end,
 				    int create);
 int btrfs_update_inode(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root,
@@ -2566,12 +2590,16 @@ extern const struct dentry_operations btrfs_dentry_operations;
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 void btrfs_update_iflags(struct inode *inode);
 void btrfs_inherit_iflags(struct inode *inode, struct inode *dir);
-
+int btrfs_defrag_file(struct inode *inode, struct file *file,
+		      struct btrfs_ioctl_defrag_range_args *range,
+		      u64 newer_than, unsigned long max_pages);
 /* file.c */
+int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
+			   struct inode *inode);
+int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info);
 int btrfs_sync_file(struct file *file, int datasync);
 int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 			    int skip_pinned);
-int btrfs_check_file(struct btrfs_root *root, struct inode *inode);
 extern const struct file_operations btrfs_file_operations;
 int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode,
 		       u64 start, u64 end, u64 *hint_byte, int drop_cache);
@@ -2591,10 +2619,6 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 /* sysfs.c */
 int btrfs_init_sysfs(void);
 void btrfs_exit_sysfs(void);
-int btrfs_sysfs_add_super(struct btrfs_fs_info *fs);
-int btrfs_sysfs_add_root(struct btrfs_root *root);
-void btrfs_sysfs_del_root(struct btrfs_root *root);
-void btrfs_sysfs_del_super(struct btrfs_fs_info *root);
 
 /* xattr.c */
 ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
@@ -2637,4 +2661,18 @@ void btrfs_reloc_pre_snapshot(struct btrfs_trans_handle *trans,
 			      u64 *bytes_to_reserve);
 void btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
 			      struct btrfs_pending_snapshot *pending);
+
+/* scrub.c */
+int btrfs_scrub_dev(struct btrfs_root *root, u64 devid, u64 start, u64 end,
+		    struct btrfs_scrub_progress *progress, int readonly);
+int btrfs_scrub_pause(struct btrfs_root *root);
+int btrfs_scrub_pause_super(struct btrfs_root *root);
+int btrfs_scrub_continue(struct btrfs_root *root);
+int btrfs_scrub_continue_super(struct btrfs_root *root);
+int btrfs_scrub_cancel(struct btrfs_root *root);
+int btrfs_scrub_cancel_dev(struct btrfs_root *root, struct btrfs_device *dev);
+int btrfs_scrub_cancel_devid(struct btrfs_root *root, u64 devid);
+int btrfs_scrub_progress(struct btrfs_root *root, u64 devid,
+			 struct btrfs_scrub_progress *progress);
+
 #endif
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
new file mode 100644
index 000000000000..98c68e658a9b
--- /dev/null
+++ b/fs/btrfs/delayed-inode.c
@@ -0,0 +1,1773 @@
+/*
+ * Copyright (C) 2011 Fujitsu.  All rights reserved.
+ * Written by Miao Xie <miaox@cn.fujitsu.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 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 021110-1307, USA.
+ */
+
+#include <linux/slab.h>
+#include "delayed-inode.h"
+#include "disk-io.h"
+#include "transaction.h"
+
+#define BTRFS_DELAYED_WRITEBACK		400
+#define BTRFS_DELAYED_BACKGROUND	100
+
+static struct kmem_cache *delayed_node_cache;
+
+int __init btrfs_delayed_inode_init(void)
+{
+	delayed_node_cache = kmem_cache_create("delayed_node",
+					sizeof(struct btrfs_delayed_node),
+					0,
+					SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
+					NULL);
+	if (!delayed_node_cache)
+		return -ENOMEM;
+	return 0;
+}
+
+void btrfs_delayed_inode_exit(void)
+{
+	if (delayed_node_cache)
+		kmem_cache_destroy(delayed_node_cache);
+}
+
+static inline void btrfs_init_delayed_node(
+				struct btrfs_delayed_node *delayed_node,
+				struct btrfs_root *root, u64 inode_id)
+{
+	delayed_node->root = root;
+	delayed_node->inode_id = inode_id;
+	atomic_set(&delayed_node->refs, 0);
+	delayed_node->count = 0;
+	delayed_node->in_list = 0;
+	delayed_node->inode_dirty = 0;
+	delayed_node->ins_root = RB_ROOT;
+	delayed_node->del_root = RB_ROOT;
+	mutex_init(&delayed_node->mutex);
+	delayed_node->index_cnt = 0;
+	INIT_LIST_HEAD(&delayed_node->n_list);
+	INIT_LIST_HEAD(&delayed_node->p_list);
+	delayed_node->bytes_reserved = 0;
+}
+
+static inline int btrfs_is_continuous_delayed_item(
+					struct btrfs_delayed_item *item1,
+					struct btrfs_delayed_item *item2)
+{
+	if (item1->key.type == BTRFS_DIR_INDEX_KEY &&
+	    item1->key.objectid == item2->key.objectid &&
+	    item1->key.type == item2->key.type &&
+	    item1->key.offset + 1 == item2->key.offset)
+		return 1;
+	return 0;
+}
+
+static inline struct btrfs_delayed_root *btrfs_get_delayed_root(
+							struct btrfs_root *root)
+{
+	return root->fs_info->delayed_root;
+}
+
+static struct btrfs_delayed_node *btrfs_get_delayed_node(struct inode *inode)
+{
+	struct btrfs_inode *btrfs_inode = BTRFS_I(inode);
+	struct btrfs_root *root = btrfs_inode->root;
+	u64 ino = btrfs_ino(inode);
+	struct btrfs_delayed_node *node;
+
+	node = ACCESS_ONCE(btrfs_inode->delayed_node);
+	if (node) {
+		atomic_inc(&node->refs);
+		return node;
+	}
+
+	spin_lock(&root->inode_lock);
+	node = radix_tree_lookup(&root->delayed_nodes_tree, ino);
+	if (node) {
+		if (btrfs_inode->delayed_node) {
+			atomic_inc(&node->refs);	/* can be accessed */
+			BUG_ON(btrfs_inode->delayed_node != node);
+			spin_unlock(&root->inode_lock);
+			return node;
+		}
+		btrfs_inode->delayed_node = node;
+		atomic_inc(&node->refs);	/* can be accessed */
+		atomic_inc(&node->refs);	/* cached in the inode */
+		spin_unlock(&root->inode_lock);
+		return node;
+	}
+	spin_unlock(&root->inode_lock);
+
+	return NULL;
+}
+
+static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node(
+							struct inode *inode)
+{
+	struct btrfs_delayed_node *node;
+	struct btrfs_inode *btrfs_inode = BTRFS_I(inode);
+	struct btrfs_root *root = btrfs_inode->root;
+	u64 ino = btrfs_ino(inode);
+	int ret;
+
+again:
+	node = btrfs_get_delayed_node(inode);
+	if (node)
+		return node;
+
+	node = kmem_cache_alloc(delayed_node_cache, GFP_NOFS);
+	if (!node)
+		return ERR_PTR(-ENOMEM);
+	btrfs_init_delayed_node(node, root, ino);
+
+	atomic_inc(&node->refs);	/* cached in the btrfs inode */
+	atomic_inc(&node->refs);	/* can be accessed */
+
+	ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+	if (ret) {
+		kmem_cache_free(delayed_node_cache, node);
+		return ERR_PTR(ret);
+	}
+
+	spin_lock(&root->inode_lock);
+	ret = radix_tree_insert(&root->delayed_nodes_tree, ino, node);
+	if (ret == -EEXIST) {
+		kmem_cache_free(delayed_node_cache, node);
+		spin_unlock(&root->inode_lock);
+		radix_tree_preload_end();
+		goto again;
+	}
+	btrfs_inode->delayed_node = node;
+	spin_unlock(&root->inode_lock);
+	radix_tree_preload_end();
+
+	return node;
+}
+
+/*
+ * Call it when holding delayed_node->mutex
+ *
+ * If mod = 1, add this node into the prepared list.
+ */
+static void btrfs_queue_delayed_node(struct btrfs_delayed_root *root,
+				     struct btrfs_delayed_node *node,
+				     int mod)
+{
+	spin_lock(&root->lock);
+	if (node->in_list) {
+		if (!list_empty(&node->p_list))
+			list_move_tail(&node->p_list, &root->prepare_list);
+		else if (mod)
+			list_add_tail(&node->p_list, &root->prepare_list);
+	} else {
+		list_add_tail(&node->n_list, &root->node_list);
+		list_add_tail(&node->p_list, &root->prepare_list);
+		atomic_inc(&node->refs);	/* inserted into list */
+		root->nodes++;
+		node->in_list = 1;
+	}
+	spin_unlock(&root->lock);
+}
+
+/* Call it when holding delayed_node->mutex */
+static void btrfs_dequeue_delayed_node(struct btrfs_delayed_root *root,
+				       struct btrfs_delayed_node *node)
+{
+	spin_lock(&root->lock);
+	if (node->in_list) {
+		root->nodes--;
+		atomic_dec(&node->refs);	/* not in the list */
+		list_del_init(&node->n_list);
+		if (!list_empty(&node->p_list))
+			list_del_init(&node->p_list);
+		node->in_list = 0;
+	}
+	spin_unlock(&root->lock);
+}
+
+struct btrfs_delayed_node *btrfs_first_delayed_node(
+			struct btrfs_delayed_root *delayed_root)
+{
+	struct list_head *p;
+	struct btrfs_delayed_node *node = NULL;
+
+	spin_lock(&delayed_root->lock);
+	if (list_empty(&delayed_root->node_list))
+		goto out;
+
+	p = delayed_root->node_list.next;
+	node = list_entry(p, struct btrfs_delayed_node, n_list);
+	atomic_inc(&node->refs);
+out:
+	spin_unlock(&delayed_root->lock);
+
+	return node;
+}
+
+struct btrfs_delayed_node *btrfs_next_delayed_node(
+						struct btrfs_delayed_node *node)
+{
+	struct btrfs_delayed_root *delayed_root;
+	struct list_head *p;
+	struct btrfs_delayed_node *next = NULL;
+
+	delayed_root = node->root->fs_info->delayed_root;
+	spin_lock(&delayed_root->lock);
+	if (!node->in_list) {	/* not in the list */
+		if (list_empty(&delayed_root->node_list))
+			goto out;
+		p = delayed_root->node_list.next;
+	} else if (list_is_last(&node->n_list, &delayed_root->node_list))
+		goto out;
+	else
+		p = node->n_list.next;
+
+	next = list_entry(p, struct btrfs_delayed_node, n_list);
+	atomic_inc(&next->refs);
+out:
+	spin_unlock(&delayed_root->lock);
+
+	return next;
+}
+
+static void __btrfs_release_delayed_node(
+				struct btrfs_delayed_node *delayed_node,
+				int mod)
+{
+	struct btrfs_delayed_root *delayed_root;
+
+	if (!delayed_node)
+		return;
+
+	delayed_root = delayed_node->root->fs_info->delayed_root;
+
+	mutex_lock(&delayed_node->mutex);
+	if (delayed_node->count)
+		btrfs_queue_delayed_node(delayed_root, delayed_node, mod);
+	else
+		btrfs_dequeue_delayed_node(delayed_root, delayed_node);
+	mutex_unlock(&delayed_node->mutex);
+
+	if (atomic_dec_and_test(&delayed_node->refs)) {
+		struct btrfs_root *root = delayed_node->root;
+		spin_lock(&root->inode_lock);
+		if (atomic_read(&delayed_node->refs) == 0) {
+			radix_tree_delete(&root->delayed_nodes_tree,
+					  delayed_node->inode_id);
+			kmem_cache_free(delayed_node_cache, delayed_node);
+		}
+		spin_unlock(&root->inode_lock);
+	}
+}
+
+static inline void btrfs_release_delayed_node(struct btrfs_delayed_node *node)
+{
+	__btrfs_release_delayed_node(node, 0);
+}
+
+struct btrfs_delayed_node *btrfs_first_prepared_delayed_node(
+					struct btrfs_delayed_root *delayed_root)
+{
+	struct list_head *p;
+	struct btrfs_delayed_node *node = NULL;
+
+	spin_lock(&delayed_root->lock);
+	if (list_empty(&delayed_root->prepare_list))
+		goto out;
+
+	p = delayed_root->prepare_list.next;
+	list_del_init(p);
+	node = list_entry(p, struct btrfs_delayed_node, p_list);
+	atomic_inc(&node->refs);
+out:
+	spin_unlock(&delayed_root->lock);
+
+	return node;
+}
+
+static inline void btrfs_release_prepared_delayed_node(
+					struct btrfs_delayed_node *node)
+{
+	__btrfs_release_delayed_node(node, 1);
+}
+
+struct btrfs_delayed_item *btrfs_alloc_delayed_item(u32 data_len)
+{
+	struct btrfs_delayed_item *item;
+	item = kmalloc(sizeof(*item) + data_len, GFP_NOFS);
+	if (item) {
+		item->data_len = data_len;
+		item->ins_or_del = 0;
+		item->bytes_reserved = 0;
+		item->delayed_node = NULL;
+		atomic_set(&item->refs, 1);
+	}
+	return item;
+}
+
+/*
+ * __btrfs_lookup_delayed_item - look up the delayed item by key
+ * @delayed_node: pointer to the delayed node
+ * @key:	  the key to look up
+ * @prev:	  used to store the prev item if the right item isn't found
+ * @next:	  used to store the next item if the right item isn't found
+ *
+ * Note: if we don't find the right item, we will return the prev item and
+ * the next item.
+ */
+static struct btrfs_delayed_item *__btrfs_lookup_delayed_item(
+				struct rb_root *root,
+				struct btrfs_key *key,
+				struct btrfs_delayed_item **prev,
+				struct btrfs_delayed_item **next)
+{
+	struct rb_node *node, *prev_node = NULL;
+	struct btrfs_delayed_item *delayed_item = NULL;
+	int ret = 0;
+
+	node = root->rb_node;
+
+	while (node) {
+		delayed_item = rb_entry(node, struct btrfs_delayed_item,
+					rb_node);
+		prev_node = node;
+		ret = btrfs_comp_cpu_keys(&delayed_item->key, key);
+		if (ret < 0)
+			node = node->rb_right;
+		else if (ret > 0)
+			node = node->rb_left;
+		else
+			return delayed_item;
+	}
+
+	if (prev) {
+		if (!prev_node)
+			*prev = NULL;
+		else if (ret < 0)
+			*prev = delayed_item;
+		else if ((node = rb_prev(prev_node)) != NULL) {
+			*prev = rb_entry(node, struct btrfs_delayed_item,
+					 rb_node);
+		} else
+			*prev = NULL;
+	}
+
+	if (next) {
+		if (!prev_node)
+			*next = NULL;
+		else if (ret > 0)
+			*next = delayed_item;
+		else if ((node = rb_next(prev_node)) != NULL) {
+			*next = rb_entry(node, struct btrfs_delayed_item,
+					 rb_node);
+		} else
+			*next = NULL;
+	}
+	return NULL;
+}
+
+struct btrfs_delayed_item *__btrfs_lookup_delayed_insertion_item(
+					struct btrfs_delayed_node *delayed_node,
+					struct btrfs_key *key)
+{
+	struct btrfs_delayed_item *item;
+
+	item = __btrfs_lookup_delayed_item(&delayed_node->ins_root, key,
+					   NULL, NULL);
+	return item;
+}
+
+struct btrfs_delayed_item *__btrfs_lookup_delayed_deletion_item(
+					struct btrfs_delayed_node *delayed_node,
+					struct btrfs_key *key)
+{
+	struct btrfs_delayed_item *item;
+
+	item = __btrfs_lookup_delayed_item(&delayed_node->del_root, key,
+					   NULL, NULL);
+	return item;
+}
+
+struct btrfs_delayed_item *__btrfs_search_delayed_insertion_item(
+					struct btrfs_delayed_node *delayed_node,
+					struct btrfs_key *key)
+{
+	struct btrfs_delayed_item *item, *next;
+
+	item = __btrfs_lookup_delayed_item(&delayed_node->ins_root, key,
+					   NULL, &next);
+	if (!item)
+		item = next;
+
+	return item;
+}
+
+struct btrfs_delayed_item *__btrfs_search_delayed_deletion_item(
+					struct btrfs_delayed_node *delayed_node,
+					struct btrfs_key *key)
+{
+	struct btrfs_delayed_item *item, *next;
+
+	item = __btrfs_lookup_delayed_item(&delayed_node->del_root, key,
+					   NULL, &next);
+	if (!item)
+		item = next;
+
+	return item;
+}
+
+static int __btrfs_add_delayed_item(struct btrfs_delayed_node *delayed_node,
+				    struct btrfs_delayed_item *ins,
+				    int action)
+{
+	struct rb_node **p, *node;
+	struct rb_node *parent_node = NULL;
+	struct rb_root *root;
+	struct btrfs_delayed_item *item;
+	int cmp;
+
+	if (action == BTRFS_DELAYED_INSERTION_ITEM)
+		root = &delayed_node->ins_root;
+	else if (action == BTRFS_DELAYED_DELETION_ITEM)
+		root = &delayed_node->del_root;
+	else
+		BUG();
+	p = &root->rb_node;
+	node = &ins->rb_node;
+
+	while (*p) {
+		parent_node = *p;
+		item = rb_entry(parent_node, struct btrfs_delayed_item,
+				 rb_node);
+
+		cmp = btrfs_comp_cpu_keys(&item->key, &ins->key);
+		if (cmp < 0)
+			p = &(*p)->rb_right;
+		else if (cmp > 0)
+			p = &(*p)->rb_left;
+		else
+			return -EEXIST;
+	}
+
+	rb_link_node(node, parent_node, p);
+	rb_insert_color(node, root);
+	ins->delayed_node = delayed_node;
+	ins->ins_or_del = action;
+
+	if (ins->key.type == BTRFS_DIR_INDEX_KEY &&
+	    action == BTRFS_DELAYED_INSERTION_ITEM &&
+	    ins->key.offset >= delayed_node->index_cnt)
+			delayed_node->index_cnt = ins->key.offset + 1;
+
+	delayed_node->count++;
+	atomic_inc(&delayed_node->root->fs_info->delayed_root->items);
+	return 0;
+}
+
+static int __btrfs_add_delayed_insertion_item(struct btrfs_delayed_node *node,
+					      struct btrfs_delayed_item *item)
+{
+	return __btrfs_add_delayed_item(node, item,
+					BTRFS_DELAYED_INSERTION_ITEM);
+}
+
+static int __btrfs_add_delayed_deletion_item(struct btrfs_delayed_node *node,
+					     struct btrfs_delayed_item *item)
+{
+	return __btrfs_add_delayed_item(node, item,
+					BTRFS_DELAYED_DELETION_ITEM);
+}
+
+static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
+{
+	struct rb_root *root;
+	struct btrfs_delayed_root *delayed_root;
+
+	delayed_root = delayed_item->delayed_node->root->fs_info->delayed_root;
+
+	BUG_ON(!delayed_root);
+	BUG_ON(delayed_item->ins_or_del != BTRFS_DELAYED_DELETION_ITEM &&
+	       delayed_item->ins_or_del != BTRFS_DELAYED_INSERTION_ITEM);
+
+	if (delayed_item->ins_or_del == BTRFS_DELAYED_INSERTION_ITEM)
+		root = &delayed_item->delayed_node->ins_root;
+	else
+		root = &delayed_item->delayed_node->del_root;
+
+	rb_erase(&delayed_item->rb_node, root);
+	delayed_item->delayed_node->count--;
+	atomic_dec(&delayed_root->items);
+	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND &&
+	    waitqueue_active(&delayed_root->wait))
+		wake_up(&delayed_root->wait);
+}
+
+static void btrfs_release_delayed_item(struct btrfs_delayed_item *item)
+{
+	if (item) {
+		__btrfs_remove_delayed_item(item);
+		if (atomic_dec_and_test(&item->refs))
+			kfree(item);
+	}
+}
+
+struct btrfs_delayed_item *__btrfs_first_delayed_insertion_item(
+					struct btrfs_delayed_node *delayed_node)
+{
+	struct rb_node *p;
+	struct btrfs_delayed_item *item = NULL;
+
+	p = rb_first(&delayed_node->ins_root);
+	if (p)
+		item = rb_entry(p, struct btrfs_delayed_item, rb_node);
+
+	return item;
+}
+
+struct btrfs_delayed_item *__btrfs_first_delayed_deletion_item(
+					struct btrfs_delayed_node *delayed_node)
+{
+	struct rb_node *p;
+	struct btrfs_delayed_item *item = NULL;
+
+	p = rb_first(&delayed_node->del_root);
+	if (p)
+		item = rb_entry(p, struct btrfs_delayed_item, rb_node);
+
+	return item;
+}
+
+struct btrfs_delayed_item *__btrfs_next_delayed_item(
+						struct btrfs_delayed_item *item)
+{
+	struct rb_node *p;
+	struct btrfs_delayed_item *next = NULL;
+
+	p = rb_next(&item->rb_node);
+	if (p)
+		next = rb_entry(p, struct btrfs_delayed_item, rb_node);
+
+	return next;
+}
+
+static inline struct btrfs_root *btrfs_get_fs_root(struct btrfs_root *root,
+						   u64 root_id)
+{
+	struct btrfs_key root_key;
+
+	if (root->objectid == root_id)
+		return root;
+
+	root_key.objectid = root_id;
+	root_key.type = BTRFS_ROOT_ITEM_KEY;
+	root_key.offset = (u64)-1;
+	return btrfs_read_fs_root_no_name(root->fs_info, &root_key);
+}
+
+static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans,
+					       struct btrfs_root *root,
+					       struct btrfs_delayed_item *item)
+{
+	struct btrfs_block_rsv *src_rsv;
+	struct btrfs_block_rsv *dst_rsv;
+	u64 num_bytes;
+	int ret;
+
+	if (!trans->bytes_reserved)
+		return 0;
+
+	src_rsv = trans->block_rsv;
+	dst_rsv = &root->fs_info->global_block_rsv;
+
+	num_bytes = btrfs_calc_trans_metadata_size(root, 1);
+	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
+	if (!ret)
+		item->bytes_reserved = num_bytes;
+
+	return ret;
+}
+
+static void btrfs_delayed_item_release_metadata(struct btrfs_root *root,
+						struct btrfs_delayed_item *item)
+{
+	struct btrfs_block_rsv *rsv;
+
+	if (!item->bytes_reserved)
+		return;
+
+	rsv = &root->fs_info->global_block_rsv;
+	btrfs_block_rsv_release(root, rsv,
+				item->bytes_reserved);
+}
+
+static int btrfs_delayed_inode_reserve_metadata(
+					struct btrfs_trans_handle *trans,
+					struct btrfs_root *root,
+					struct btrfs_delayed_node *node)
+{
+	struct btrfs_block_rsv *src_rsv;
+	struct btrfs_block_rsv *dst_rsv;
+	u64 num_bytes;
+	int ret;
+
+	if (!trans->bytes_reserved)
+		return 0;
+
+	src_rsv = trans->block_rsv;
+	dst_rsv = &root->fs_info->global_block_rsv;
+
+	num_bytes = btrfs_calc_trans_metadata_size(root, 1);
+	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
+	if (!ret)
+		node->bytes_reserved = num_bytes;
+
+	return ret;
+}
+
+static void btrfs_delayed_inode_release_metadata(struct btrfs_root *root,
+						struct btrfs_delayed_node *node)
+{
+	struct btrfs_block_rsv *rsv;
+
+	if (!node->bytes_reserved)
+		return;
+
+	rsv = &root->fs_info->global_block_rsv;
+	btrfs_block_rsv_release(root, rsv,
+				node->bytes_reserved);
+	node->bytes_reserved = 0;
+}
+
+/*
+ * This helper will insert some continuous items into the same leaf according
+ * to the free space of the leaf.
+ */
+static int btrfs_batch_insert_items(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root,
+				struct btrfs_path *path,
+				struct btrfs_delayed_item *item)
+{
+	struct btrfs_delayed_item *curr, *next;
+	int free_space;
+	int total_data_size = 0, total_size = 0;
+	struct extent_buffer *leaf;
+	char *data_ptr;
+	struct btrfs_key *keys;
+	u32 *data_size;
+	struct list_head head;
+	int slot;
+	int nitems;
+	int i;
+	int ret = 0;
+
+	BUG_ON(!path->nodes[0]);
+
+	leaf = path->nodes[0];
+	free_space = btrfs_leaf_free_space(root, leaf);
+	INIT_LIST_HEAD(&head);
+
+	next = item;
+	nitems = 0;
+
+	/*
+	 * count the number of the continuous items that we can insert in batch
+	 */
+	while (total_size + next->data_len + sizeof(struct btrfs_item) <=
+	       free_space) {
+		total_data_size += next->data_len;
+		total_size += next->data_len + sizeof(struct btrfs_item);
+		list_add_tail(&next->tree_list, &head);
+		nitems++;
+
+		curr = next;
+		next = __btrfs_next_delayed_item(curr);
+		if (!next)
+			break;
+
+		if (!btrfs_is_continuous_delayed_item(curr, next))
+			break;
+	}
+
+	if (!nitems) {
+		ret = 0;
+		goto out;
+	}
+
+	/*
+	 * we need allocate some memory space, but it might cause the task
+	 * to sleep, so we set all locked nodes in the path to blocking locks
+	 * first.
+	 */
+	btrfs_set_path_blocking(path);
+
+	keys = kmalloc(sizeof(struct btrfs_key) * nitems, GFP_NOFS);
+	if (!keys) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	data_size = kmalloc(sizeof(u32) * nitems, GFP_NOFS);
+	if (!data_size) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	/* get keys of all the delayed items */
+	i = 0;
+	list_for_each_entry(next, &head, tree_list) {
+		keys[i] = next->key;
+		data_size[i] = next->data_len;
+		i++;
+	}
+
+	/* reset all the locked nodes in the patch to spinning locks. */
+	btrfs_clear_path_blocking(path, NULL);
+
+	/* insert the keys of the items */
+	ret = setup_items_for_insert(trans, root, path, keys, data_size,
+				     total_data_size, total_size, nitems);
+	if (ret)
+		goto error;
+
+	/* insert the dir index items */
+	slot = path->slots[0];
+	list_for_each_entry_safe(curr, next, &head, tree_list) {
+		data_ptr = btrfs_item_ptr(leaf, slot, char);
+		write_extent_buffer(leaf, &curr->data,
+				    (unsigned long)data_ptr,
+				    curr->data_len);
+		slot++;
+
+		btrfs_delayed_item_release_metadata(root, curr);
+
+		list_del(&curr->tree_list);
+		btrfs_release_delayed_item(curr);
+	}
+
+error:
+	kfree(data_size);
+	kfree(keys);
+out:
+	return ret;
+}
+
+/*
+ * This helper can just do simple insertion that needn't extend item for new
+ * data, such as directory name index insertion, inode insertion.
+ */
+static int btrfs_insert_delayed_item(struct btrfs_trans_handle *trans,
+				     struct btrfs_root *root,
+				     struct btrfs_path *path,
+				     struct btrfs_delayed_item *delayed_item)
+{
+	struct extent_buffer *leaf;
+	struct btrfs_item *item;
+	char *ptr;
+	int ret;
+
+	ret = btrfs_insert_empty_item(trans, root, path, &delayed_item->key,
+				      delayed_item->data_len);
+	if (ret < 0 && ret != -EEXIST)
+		return ret;
+
+	leaf = path->nodes[0];
+
+	item = btrfs_item_nr(leaf, path->slots[0]);
+	ptr = btrfs_item_ptr(leaf, path->slots[0], char);
+
+	write_extent_buffer(leaf, delayed_item->data, (unsigned long)ptr,
+			    delayed_item->data_len);
+	btrfs_mark_buffer_dirty(leaf);
+
+	btrfs_delayed_item_release_metadata(root, delayed_item);
+	return 0;
+}
+
+/*
+ * we insert an item first, then if there are some continuous items, we try
+ * to insert those items into the same leaf.
+ */
+static int btrfs_insert_delayed_items(struct btrfs_trans_handle *trans,
+				      struct btrfs_path *path,
+				      struct btrfs_root *root,
+				      struct btrfs_delayed_node *node)
+{
+	struct btrfs_delayed_item *curr, *prev;
+	int ret = 0;
+
+do_again:
+	mutex_lock(&node->mutex);
+	curr = __btrfs_first_delayed_insertion_item(node);
+	if (!curr)
+		goto insert_end;
+
+	ret = btrfs_insert_delayed_item(trans, root, path, curr);
+	if (ret < 0) {
+		btrfs_release_path(path);
+		goto insert_end;
+	}
+
+	prev = curr;
+	curr = __btrfs_next_delayed_item(prev);
+	if (curr && btrfs_is_continuous_delayed_item(prev, curr)) {
+		/* insert the continuous items into the same leaf */
+		path->slots[0]++;
+		btrfs_batch_insert_items(trans, root, path, curr);
+	}
+	btrfs_release_delayed_item(prev);
+	btrfs_mark_buffer_dirty(path->nodes[0]);
+
+	btrfs_release_path(path);
+	mutex_unlock(&node->mutex);
+	goto do_again;
+
+insert_end:
+	mutex_unlock(&node->mutex);
+	return ret;
+}
+
+static int btrfs_batch_delete_items(struct btrfs_trans_handle *trans,
+				    struct btrfs_root *root,
+				    struct btrfs_path *path,
+				    struct btrfs_delayed_item *item)
+{
+	struct btrfs_delayed_item *curr, *next;
+	struct extent_buffer *leaf;
+	struct btrfs_key key;
+	struct list_head head;
+	int nitems, i, last_item;
+	int ret = 0;
+
+	BUG_ON(!path->nodes[0]);
+
+	leaf = path->nodes[0];
+
+	i = path->slots[0];
+	last_item = btrfs_header_nritems(leaf) - 1;
+	if (i > last_item)
+		return -ENOENT;	/* FIXME: Is errno suitable? */
+
+	next = item;
+	INIT_LIST_HEAD(&head);
+	btrfs_item_key_to_cpu(leaf, &key, i);
+	nitems = 0;
+	/*
+	 * count the number of the dir index items that we can delete in batch
+	 */
+	while (btrfs_comp_cpu_keys(&next->key, &key) == 0) {
+		list_add_tail(&next->tree_list, &head);
+		nitems++;
+
+		curr = next;
+		next = __btrfs_next_delayed_item(curr);
+		if (!next)
+			break;
+
+		if (!btrfs_is_continuous_delayed_item(curr, next))
+			break;
+
+		i++;
+		if (i > last_item)
+			break;
+		btrfs_item_key_to_cpu(leaf, &key, i);
+	}
+
+	if (!nitems)
+		return 0;
+
+	ret = btrfs_del_items(trans, root, path, path->slots[0], nitems);
+	if (ret)
+		goto out;
+
+	list_for_each_entry_safe(curr, next, &head, tree_list) {
+		btrfs_delayed_item_release_metadata(root, curr);
+		list_del(&curr->tree_list);
+		btrfs_release_delayed_item(curr);
+	}
+
+out:
+	return ret;
+}
+
+static int btrfs_delete_delayed_items(struct btrfs_trans_handle *trans,
+				      struct btrfs_path *path,
+				      struct btrfs_root *root,
+				      struct btrfs_delayed_node *node)
+{
+	struct btrfs_delayed_item *curr, *prev;
+	int ret = 0;
+
+do_again:
+	mutex_lock(&node->mutex);
+	curr = __btrfs_first_delayed_deletion_item(node);
+	if (!curr)
+		goto delete_fail;
+
+	ret = btrfs_search_slot(trans, root, &curr->key, path, -1, 1);
+	if (ret < 0)
+		goto delete_fail;
+	else if (ret > 0) {
+		/*
+		 * can't find the item which the node points to, so this node
+		 * is invalid, just drop it.
+		 */
+		prev = curr;
+		curr = __btrfs_next_delayed_item(prev);
+		btrfs_release_delayed_item(prev);
+		ret = 0;
+		btrfs_release_path(path);
+		if (curr)
+			goto do_again;
+		else
+			goto delete_fail;
+	}
+
+	btrfs_batch_delete_items(trans, root, path, curr);
+	btrfs_release_path(path);
+	mutex_unlock(&node->mutex);
+	goto do_again;
+
+delete_fail:
+	btrfs_release_path(path);
+	mutex_unlock(&node->mutex);
+	return ret;
+}
+
+static void btrfs_release_delayed_inode(struct btrfs_delayed_node *delayed_node)
+{
+	struct btrfs_delayed_root *delayed_root;
+
+	if (delayed_node && delayed_node->inode_dirty) {
+		BUG_ON(!delayed_node->root);
+		delayed_node->inode_dirty = 0;
+		delayed_node->count--;
+
+		delayed_root = delayed_node->root->fs_info->delayed_root;
+		atomic_dec(&delayed_root->items);
+		if (atomic_read(&delayed_root->items) <
+		    BTRFS_DELAYED_BACKGROUND &&
+		    waitqueue_active(&delayed_root->wait))
+			wake_up(&delayed_root->wait);
+	}
+}
+
+static int btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
+				      struct btrfs_root *root,
+				      struct btrfs_path *path,
+				      struct btrfs_delayed_node *node)
+{
+	struct btrfs_key key;
+	struct btrfs_inode_item *inode_item;
+	struct extent_buffer *leaf;
+	int ret;
+
+	mutex_lock(&node->mutex);
+	if (!node->inode_dirty) {
+		mutex_unlock(&node->mutex);
+		return 0;
+	}
+
+	key.objectid = node->inode_id;
+	btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
+	key.offset = 0;
+	ret = btrfs_lookup_inode(trans, root, path, &key, 1);
+	if (ret > 0) {
+		btrfs_release_path(path);
+		mutex_unlock(&node->mutex);
+		return -ENOENT;
+	} else if (ret < 0) {
+		mutex_unlock(&node->mutex);
+		return ret;
+	}
+
+	btrfs_unlock_up_safe(path, 1);
+	leaf = path->nodes[0];
+	inode_item = btrfs_item_ptr(leaf, path->slots[0],
+				    struct btrfs_inode_item);
+	write_extent_buffer(leaf, &node->inode_item, (unsigned long)inode_item,
+			    sizeof(struct btrfs_inode_item));
+	btrfs_mark_buffer_dirty(leaf);
+	btrfs_release_path(path);
+
+	btrfs_delayed_inode_release_metadata(root, node);
+	btrfs_release_delayed_inode(node);
+	mutex_unlock(&node->mutex);
+
+	return 0;
+}
+
+/* Called when committing the transaction. */
+int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root)
+{
+	struct btrfs_delayed_root *delayed_root;
+	struct btrfs_delayed_node *curr_node, *prev_node;
+	struct btrfs_path *path;
+	struct btrfs_block_rsv *block_rsv;
+	int ret = 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+	path->leave_spinning = 1;
+
+	block_rsv = trans->block_rsv;
+	trans->block_rsv = &root->fs_info->global_block_rsv;
+
+	delayed_root = btrfs_get_delayed_root(root);
+
+	curr_node = btrfs_first_delayed_node(delayed_root);
+	while (curr_node) {
+		root = curr_node->root;
+		ret = btrfs_insert_delayed_items(trans, path, root,
+						 curr_node);
+		if (!ret)
+			ret = btrfs_delete_delayed_items(trans, path, root,
+							 curr_node);
+		if (!ret)
+			ret = btrfs_update_delayed_inode(trans, root, path,
+							 curr_node);
+		if (ret) {
+			btrfs_release_delayed_node(curr_node);
+			break;
+		}
+
+		prev_node = curr_node;
+		curr_node = btrfs_next_delayed_node(curr_node);
+		btrfs_release_delayed_node(prev_node);
+	}
+
+	btrfs_free_path(path);
+	trans->block_rsv = block_rsv;
+	return ret;
+}
+
+static int __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
+					      struct btrfs_delayed_node *node)
+{
+	struct btrfs_path *path;
+	struct btrfs_block_rsv *block_rsv;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+	path->leave_spinning = 1;
+
+	block_rsv = trans->block_rsv;
+	trans->block_rsv = &node->root->fs_info->global_block_rsv;
+
+	ret = btrfs_insert_delayed_items(trans, path, node->root, node);
+	if (!ret)
+		ret = btrfs_delete_delayed_items(trans, path, node->root, node);
+	if (!ret)
+		ret = btrfs_update_delayed_inode(trans, node->root, path, node);
+	btrfs_free_path(path);
+
+	trans->block_rsv = block_rsv;
+	return ret;
+}
+
+int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
+				     struct inode *inode)
+{
+	struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode);
+	int ret;
+
+	if (!delayed_node)
+		return 0;
+
+	mutex_lock(&delayed_node->mutex);
+	if (!delayed_node->count) {
+		mutex_unlock(&delayed_node->mutex);
+		btrfs_release_delayed_node(delayed_node);
+		return 0;
+	}
+	mutex_unlock(&delayed_node->mutex);
+
+	ret = __btrfs_commit_inode_delayed_items(trans, delayed_node);
+	btrfs_release_delayed_node(delayed_node);
+	return ret;
+}
+
+void btrfs_remove_delayed_node(struct inode *inode)
+{
+	struct btrfs_delayed_node *delayed_node;
+
+	delayed_node = ACCESS_ONCE(BTRFS_I(inode)->delayed_node);
+	if (!delayed_node)
+		return;
+
+	BTRFS_I(inode)->delayed_node = NULL;
+	btrfs_release_delayed_node(delayed_node);
+}
+
+struct btrfs_async_delayed_node {
+	struct btrfs_root *root;
+	struct btrfs_delayed_node *delayed_node;
+	struct btrfs_work work;
+};
+
+static void btrfs_async_run_delayed_node_done(struct btrfs_work *work)
+{
+	struct btrfs_async_delayed_node *async_node;
+	struct btrfs_trans_handle *trans;
+	struct btrfs_path *path;
+	struct btrfs_delayed_node *delayed_node = NULL;
+	struct btrfs_root *root;
+	struct btrfs_block_rsv *block_rsv;
+	unsigned long nr = 0;
+	int need_requeue = 0;
+	int ret;
+
+	async_node = container_of(work, struct btrfs_async_delayed_node, work);
+
+	path = btrfs_alloc_path();
+	if (!path)
+		goto out;
+	path->leave_spinning = 1;
+
+	delayed_node = async_node->delayed_node;
+	root = delayed_node->root;
+
+	trans = btrfs_join_transaction(root);
+	if (IS_ERR(trans))
+		goto free_path;
+
+	block_rsv = trans->block_rsv;
+	trans->block_rsv = &root->fs_info->global_block_rsv;
+
+	ret = btrfs_insert_delayed_items(trans, path, root, delayed_node);
+	if (!ret)
+		ret = btrfs_delete_delayed_items(trans, path, root,
+						 delayed_node);
+
+	if (!ret)
+		btrfs_update_delayed_inode(trans, root, path, delayed_node);
+
+	/*
+	 * Maybe new delayed items have been inserted, so we need requeue
+	 * the work. Besides that, we must dequeue the empty delayed nodes
+	 * to avoid the race between delayed items balance and the worker.
+	 * The race like this:
+	 * 	Task1				Worker thread
+	 * 					count == 0, needn't requeue
+	 * 					  also needn't insert the
+	 * 					  delayed node into prepare
+	 * 					  list again.
+	 * 	add lots of delayed items
+	 * 	queue the delayed node
+	 * 	  already in the list,
+	 * 	  and not in the prepare
+	 * 	  list, it means the delayed
+	 * 	  node is being dealt with
+	 * 	  by the worker.
+	 * 	do delayed items balance
+	 * 	  the delayed node is being
+	 * 	  dealt with by the worker
+	 * 	  now, just wait.
+	 * 	  				the worker goto idle.
+	 * Task1 will sleep until the transaction is commited.
+	 */
+	mutex_lock(&delayed_node->mutex);
+	if (delayed_node->count)
+		need_requeue = 1;
+	else
+		btrfs_dequeue_delayed_node(root->fs_info->delayed_root,
+					   delayed_node);
+	mutex_unlock(&delayed_node->mutex);
+
+	nr = trans->blocks_used;
+
+	trans->block_rsv = block_rsv;
+	btrfs_end_transaction_dmeta(trans, root);
+	__btrfs_btree_balance_dirty(root, nr);
+free_path:
+	btrfs_free_path(path);
+out:
+	if (need_requeue)
+		btrfs_requeue_work(&async_node->work);
+	else {
+		btrfs_release_prepared_delayed_node(delayed_node);
+		kfree(async_node);
+	}
+}
+
+static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
+				     struct btrfs_root *root, int all)
+{
+	struct btrfs_async_delayed_node *async_node;
+	struct btrfs_delayed_node *curr;
+	int count = 0;
+
+again:
+	curr = btrfs_first_prepared_delayed_node(delayed_root);
+	if (!curr)
+		return 0;
+
+	async_node = kmalloc(sizeof(*async_node), GFP_NOFS);
+	if (!async_node) {
+		btrfs_release_prepared_delayed_node(curr);
+		return -ENOMEM;
+	}
+
+	async_node->root = root;
+	async_node->delayed_node = curr;
+
+	async_node->work.func = btrfs_async_run_delayed_node_done;
+	async_node->work.flags = 0;
+
+	btrfs_queue_worker(&root->fs_info->delayed_workers, &async_node->work);
+	count++;
+
+	if (all || count < 4)
+		goto again;
+
+	return 0;
+}
+
+void btrfs_assert_delayed_root_empty(struct btrfs_root *root)
+{
+	struct btrfs_delayed_root *delayed_root;
+	delayed_root = btrfs_get_delayed_root(root);
+	WARN_ON(btrfs_first_delayed_node(delayed_root));
+}
+
+void btrfs_balance_delayed_items(struct btrfs_root *root)
+{
+	struct btrfs_delayed_root *delayed_root;
+
+	delayed_root = btrfs_get_delayed_root(root);
+
+	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND)
+		return;
+
+	if (atomic_read(&delayed_root->items) >= BTRFS_DELAYED_WRITEBACK) {
+		int ret;
+		ret = btrfs_wq_run_delayed_node(delayed_root, root, 1);
+		if (ret)
+			return;
+
+		wait_event_interruptible_timeout(
+				delayed_root->wait,
+				(atomic_read(&delayed_root->items) <
+				 BTRFS_DELAYED_BACKGROUND),
+				HZ);
+		return;
+	}
+
+	btrfs_wq_run_delayed_node(delayed_root, root, 0);
+}
+
+int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root, const char *name,
+				   int name_len, struct inode *dir,
+				   struct btrfs_disk_key *disk_key, u8 type,
+				   u64 index)
+{
+	struct btrfs_delayed_node *delayed_node;
+	struct btrfs_delayed_item *delayed_item;
+	struct btrfs_dir_item *dir_item;
+	int ret;
+
+	delayed_node = btrfs_get_or_create_delayed_node(dir);
+	if (IS_ERR(delayed_node))
+		return PTR_ERR(delayed_node);
+
+	delayed_item = btrfs_alloc_delayed_item(sizeof(*dir_item) + name_len);
+	if (!delayed_item) {
+		ret = -ENOMEM;
+		goto release_node;
+	}
+
+	ret = btrfs_delayed_item_reserve_metadata(trans, root, delayed_item);
+	/*
+	 * we have reserved enough space when we start a new transaction,
+	 * so reserving metadata failure is impossible
+	 */
+	BUG_ON(ret);
+
+	delayed_item->key.objectid = btrfs_ino(dir);
+	btrfs_set_key_type(&delayed_item->key, BTRFS_DIR_INDEX_KEY);
+	delayed_item->key.offset = index;
+
+	dir_item = (struct btrfs_dir_item *)delayed_item->data;
+	dir_item->location = *disk_key;
+	dir_item->transid = cpu_to_le64(trans->transid);
+	dir_item->data_len = 0;
+	dir_item->name_len = cpu_to_le16(name_len);
+	dir_item->type = type;
+	memcpy((char *)(dir_item + 1), name, name_len);
+
+	mutex_lock(&delayed_node->mutex);
+	ret = __btrfs_add_delayed_insertion_item(delayed_node, delayed_item);
+	if (unlikely(ret)) {
+		printk(KERN_ERR "err add delayed dir index item(name: %s) into "
+				"the insertion tree of the delayed node"
+				"(root id: %llu, inode id: %llu, errno: %d)\n",
+				name,
+				(unsigned long long)delayed_node->root->objectid,
+				(unsigned long long)delayed_node->inode_id,
+				ret);
+		BUG();
+	}
+	mutex_unlock(&delayed_node->mutex);
+
+release_node:
+	btrfs_release_delayed_node(delayed_node);
+	return ret;
+}
+
+static int btrfs_delete_delayed_insertion_item(struct btrfs_root *root,
+					       struct btrfs_delayed_node *node,
+					       struct btrfs_key *key)
+{
+	struct btrfs_delayed_item *item;
+
+	mutex_lock(&node->mutex);
+	item = __btrfs_lookup_delayed_insertion_item(node, key);
+	if (!item) {
+		mutex_unlock(&node->mutex);
+		return 1;
+	}
+
+	btrfs_delayed_item_release_metadata(root, item);
+	btrfs_release_delayed_item(item);
+	mutex_unlock(&node->mutex);
+	return 0;
+}
+
+int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root, struct inode *dir,
+				   u64 index)
+{
+	struct btrfs_delayed_node *node;
+	struct btrfs_delayed_item *item;
+	struct btrfs_key item_key;
+	int ret;
+
+	node = btrfs_get_or_create_delayed_node(dir);
+	if (IS_ERR(node))
+		return PTR_ERR(node);
+
+	item_key.objectid = btrfs_ino(dir);
+	btrfs_set_key_type(&item_key, BTRFS_DIR_INDEX_KEY);
+	item_key.offset = index;
+
+	ret = btrfs_delete_delayed_insertion_item(root, node, &item_key);
+	if (!ret)
+		goto end;
+
+	item = btrfs_alloc_delayed_item(0);
+	if (!item) {
+		ret = -ENOMEM;
+		goto end;
+	}
+
+	item->key = item_key;
+
+	ret = btrfs_delayed_item_reserve_metadata(trans, root, item);
+	/*
+	 * we have reserved enough space when we start a new transaction,
+	 * so reserving metadata failure is impossible.
+	 */
+	BUG_ON(ret);
+
+	mutex_lock(&node->mutex);
+	ret = __btrfs_add_delayed_deletion_item(node, item);
+	if (unlikely(ret)) {
+		printk(KERN_ERR "err add delayed dir index item(index: %llu) "
+				"into the deletion tree of the delayed node"
+				"(root id: %llu, inode id: %llu, errno: %d)\n",
+				(unsigned long long)index,
+				(unsigned long long)node->root->objectid,
+				(unsigned long long)node->inode_id,
+				ret);
+		BUG();
+	}
+	mutex_unlock(&node->mutex);
+end:
+	btrfs_release_delayed_node(node);
+	return ret;
+}
+
+int btrfs_inode_delayed_dir_index_count(struct inode *inode)
+{
+	struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode);
+
+	if (!delayed_node)
+		return -ENOENT;
+
+	/*
+	 * Since we have held i_mutex of this directory, it is impossible that
+	 * a new directory index is added into the delayed node and index_cnt
+	 * is updated now. So we needn't lock the delayed node.
+	 */
+	if (!delayed_node->index_cnt) {
+		btrfs_release_delayed_node(delayed_node);
+		return -EINVAL;
+	}
+
+	BTRFS_I(inode)->index_cnt = delayed_node->index_cnt;
+	btrfs_release_delayed_node(delayed_node);
+	return 0;
+}
+
+void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
+			     struct list_head *del_list)
+{
+	struct btrfs_delayed_node *delayed_node;
+	struct btrfs_delayed_item *item;
+
+	delayed_node = btrfs_get_delayed_node(inode);
+	if (!delayed_node)
+		return;
+
+	mutex_lock(&delayed_node->mutex);
+	item = __btrfs_first_delayed_insertion_item(delayed_node);
+	while (item) {
+		atomic_inc(&item->refs);
+		list_add_tail(&item->readdir_list, ins_list);
+		item = __btrfs_next_delayed_item(item);
+	}
+
+	item = __btrfs_first_delayed_deletion_item(delayed_node);
+	while (item) {
+		atomic_inc(&item->refs);
+		list_add_tail(&item->readdir_list, del_list);
+		item = __btrfs_next_delayed_item(item);
+	}
+	mutex_unlock(&delayed_node->mutex);
+	/*
+	 * This delayed node is still cached in the btrfs inode, so refs
+	 * must be > 1 now, and we needn't check it is going to be freed
+	 * or not.
+	 *
+	 * Besides that, this function is used to read dir, we do not
+	 * insert/delete delayed items in this period. So we also needn't
+	 * requeue or dequeue this delayed node.
+	 */
+	atomic_dec(&delayed_node->refs);
+}
+
+void btrfs_put_delayed_items(struct list_head *ins_list,
+			     struct list_head *del_list)
+{
+	struct btrfs_delayed_item *curr, *next;
+
+	list_for_each_entry_safe(curr, next, ins_list, readdir_list) {
+		list_del(&curr->readdir_list);
+		if (atomic_dec_and_test(&curr->refs))
+			kfree(curr);
+	}
+
+	list_for_each_entry_safe(curr, next, del_list, readdir_list) {
+		list_del(&curr->readdir_list);
+		if (atomic_dec_and_test(&curr->refs))
+			kfree(curr);
+	}
+}
+
+int btrfs_should_delete_dir_index(struct list_head *del_list,
+				  u64 index)
+{
+	struct btrfs_delayed_item *curr, *next;
+	int ret;
+
+	if (list_empty(del_list))
+		return 0;
+
+	list_for_each_entry_safe(curr, next, del_list, readdir_list) {
+		if (curr->key.offset > index)
+			break;
+
+		list_del(&curr->readdir_list);
+		ret = (curr->key.offset == index);
+
+		if (atomic_dec_and_test(&curr->refs))
+			kfree(curr);
+
+		if (ret)
+			return 1;
+		else
+			continue;
+	}
+	return 0;
+}
+
+/*
+ * btrfs_readdir_delayed_dir_index - read dir info stored in the delayed tree
+ *
+ */
+int btrfs_readdir_delayed_dir_index(struct file *filp, void *dirent,
+				    filldir_t filldir,
+				    struct list_head *ins_list)
+{
+	struct btrfs_dir_item *di;
+	struct btrfs_delayed_item *curr, *next;
+	struct btrfs_key location;
+	char *name;
+	int name_len;
+	int over = 0;
+	unsigned char d_type;
+
+	if (list_empty(ins_list))
+		return 0;
+
+	/*
+	 * Changing the data of the delayed item is impossible. So
+	 * we needn't lock them. And we have held i_mutex of the
+	 * directory, nobody can delete any directory indexes now.
+	 */
+	list_for_each_entry_safe(curr, next, ins_list, readdir_list) {
+		list_del(&curr->readdir_list);
+
+		if (curr->key.offset < filp->f_pos) {
+			if (atomic_dec_and_test(&curr->refs))
+				kfree(curr);
+			continue;
+		}
+
+		filp->f_pos = curr->key.offset;
+
+		di = (struct btrfs_dir_item *)curr->data;
+		name = (char *)(di + 1);
+		name_len = le16_to_cpu(di->name_len);
+
+		d_type = btrfs_filetype_table[di->type];
+		btrfs_disk_key_to_cpu(&location, &di->location);
+
+		over = filldir(dirent, name, name_len, curr->key.offset,
+			       location.objectid, d_type);
+
+		if (atomic_dec_and_test(&curr->refs))
+			kfree(curr);
+
+		if (over)
+			return 1;
+	}
+	return 0;
+}
+
+BTRFS_SETGET_STACK_FUNCS(stack_inode_generation, struct btrfs_inode_item,
+			 generation, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_sequence, struct btrfs_inode_item,
+			 sequence, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_transid, struct btrfs_inode_item,
+			 transid, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_size, struct btrfs_inode_item, size, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_nbytes, struct btrfs_inode_item,
+			 nbytes, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_block_group, struct btrfs_inode_item,
+			 block_group, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_nlink, struct btrfs_inode_item, nlink, 32);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_uid, struct btrfs_inode_item, uid, 32);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_gid, struct btrfs_inode_item, gid, 32);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_mode, struct btrfs_inode_item, mode, 32);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_rdev, struct btrfs_inode_item, rdev, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_flags, struct btrfs_inode_item, flags, 64);
+
+BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32);
+
+static void fill_stack_inode_item(struct btrfs_trans_handle *trans,
+				  struct btrfs_inode_item *inode_item,
+				  struct inode *inode)
+{
+	btrfs_set_stack_inode_uid(inode_item, inode->i_uid);
+	btrfs_set_stack_inode_gid(inode_item, inode->i_gid);
+	btrfs_set_stack_inode_size(inode_item, BTRFS_I(inode)->disk_i_size);
+	btrfs_set_stack_inode_mode(inode_item, inode->i_mode);
+	btrfs_set_stack_inode_nlink(inode_item, inode->i_nlink);
+	btrfs_set_stack_inode_nbytes(inode_item, inode_get_bytes(inode));
+	btrfs_set_stack_inode_generation(inode_item,
+					 BTRFS_I(inode)->generation);
+	btrfs_set_stack_inode_sequence(inode_item, BTRFS_I(inode)->sequence);
+	btrfs_set_stack_inode_transid(inode_item, trans->transid);
+	btrfs_set_stack_inode_rdev(inode_item, inode->i_rdev);
+	btrfs_set_stack_inode_flags(inode_item, BTRFS_I(inode)->flags);
+	btrfs_set_stack_inode_block_group(inode_item, 0);
+
+	btrfs_set_stack_timespec_sec(btrfs_inode_atime(inode_item),
+				     inode->i_atime.tv_sec);
+	btrfs_set_stack_timespec_nsec(btrfs_inode_atime(inode_item),
+				      inode->i_atime.tv_nsec);
+
+	btrfs_set_stack_timespec_sec(btrfs_inode_mtime(inode_item),
+				     inode->i_mtime.tv_sec);
+	btrfs_set_stack_timespec_nsec(btrfs_inode_mtime(inode_item),
+				      inode->i_mtime.tv_nsec);
+
+	btrfs_set_stack_timespec_sec(btrfs_inode_ctime(inode_item),
+				     inode->i_ctime.tv_sec);
+	btrfs_set_stack_timespec_nsec(btrfs_inode_ctime(inode_item),
+				      inode->i_ctime.tv_nsec);
+}
+
+int btrfs_fill_inode(struct inode *inode, u32 *rdev)
+{
+	struct btrfs_delayed_node *delayed_node;
+	struct btrfs_inode_item *inode_item;
+	struct btrfs_timespec *tspec;
+
+	delayed_node = btrfs_get_delayed_node(inode);
+	if (!delayed_node)
+		return -ENOENT;
+
+	mutex_lock(&delayed_node->mutex);
+	if (!delayed_node->inode_dirty) {
+		mutex_unlock(&delayed_node->mutex);
+		btrfs_release_delayed_node(delayed_node);
+		return -ENOENT;
+	}
+
+	inode_item = &delayed_node->inode_item;
+
+	inode->i_uid = btrfs_stack_inode_uid(inode_item);
+	inode->i_gid = btrfs_stack_inode_gid(inode_item);
+	btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item));
+	inode->i_mode = btrfs_stack_inode_mode(inode_item);
+	inode->i_nlink = btrfs_stack_inode_nlink(inode_item);
+	inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item));
+	BTRFS_I(inode)->generation = btrfs_stack_inode_generation(inode_item);
+	BTRFS_I(inode)->sequence = btrfs_stack_inode_sequence(inode_item);
+	inode->i_rdev = 0;
+	*rdev = btrfs_stack_inode_rdev(inode_item);
+	BTRFS_I(inode)->flags = btrfs_stack_inode_flags(inode_item);
+
+	tspec = btrfs_inode_atime(inode_item);
+	inode->i_atime.tv_sec = btrfs_stack_timespec_sec(tspec);
+	inode->i_atime.tv_nsec = btrfs_stack_timespec_nsec(tspec);
+
+	tspec = btrfs_inode_mtime(inode_item);
+	inode->i_mtime.tv_sec = btrfs_stack_timespec_sec(tspec);
+	inode->i_mtime.tv_nsec = btrfs_stack_timespec_nsec(tspec);
+
+	tspec = btrfs_inode_ctime(inode_item);
+	inode->i_ctime.tv_sec = btrfs_stack_timespec_sec(tspec);
+	inode->i_ctime.tv_nsec = btrfs_stack_timespec_nsec(tspec);
+
+	inode->i_generation = BTRFS_I(inode)->generation;
+	BTRFS_I(inode)->index_cnt = (u64)-1;
+
+	mutex_unlock(&delayed_node->mutex);
+	btrfs_release_delayed_node(delayed_node);
+	return 0;
+}
+
+int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root, struct inode *inode)
+{
+	struct btrfs_delayed_node *delayed_node;
+	int ret = 0;
+
+	delayed_node = btrfs_get_or_create_delayed_node(inode);
+	if (IS_ERR(delayed_node))
+		return PTR_ERR(delayed_node);
+
+	mutex_lock(&delayed_node->mutex);
+	if (delayed_node->inode_dirty) {
+		fill_stack_inode_item(trans, &delayed_node->inode_item, inode);
+		goto release_node;
+	}
+
+	ret = btrfs_delayed_inode_reserve_metadata(trans, root, delayed_node);
+	/*
+	 * we must reserve enough space when we start a new transaction,
+	 * so reserving metadata failure is impossible
+	 */
+	BUG_ON(ret);
+
+	fill_stack_inode_item(trans, &delayed_node->inode_item, inode);
+	delayed_node->inode_dirty = 1;
+	delayed_node->count++;
+	atomic_inc(&root->fs_info->delayed_root->items);
+release_node:
+	mutex_unlock(&delayed_node->mutex);
+	btrfs_release_delayed_node(delayed_node);
+	return ret;
+}
+
+static void __btrfs_kill_delayed_node(struct btrfs_delayed_node *delayed_node)
+{
+	struct btrfs_root *root = delayed_node->root;
+	struct btrfs_delayed_item *curr_item, *prev_item;
+
+	mutex_lock(&delayed_node->mutex);
+	curr_item = __btrfs_first_delayed_insertion_item(delayed_node);
+	while (curr_item) {
+		btrfs_delayed_item_release_metadata(root, curr_item);
+		prev_item = curr_item;
+		curr_item = __btrfs_next_delayed_item(prev_item);
+		btrfs_release_delayed_item(prev_item);
+	}
+
+	curr_item = __btrfs_first_delayed_deletion_item(delayed_node);
+	while (curr_item) {
+		btrfs_delayed_item_release_metadata(root, curr_item);
+		prev_item = curr_item;
+		curr_item = __btrfs_next_delayed_item(prev_item);
+		btrfs_release_delayed_item(prev_item);
+	}
+
+	if (delayed_node->inode_dirty) {
+		btrfs_delayed_inode_release_metadata(root, delayed_node);
+		btrfs_release_delayed_inode(delayed_node);
+	}
+	mutex_unlock(&delayed_node->mutex);
+}
+
+void btrfs_kill_delayed_inode_items(struct inode *inode)
+{
+	struct btrfs_delayed_node *delayed_node;
+
+	delayed_node = btrfs_get_delayed_node(inode);
+	if (!delayed_node)
+		return;
+
+	__btrfs_kill_delayed_node(delayed_node);
+	btrfs_release_delayed_node(delayed_node);
+}
+
+void btrfs_kill_all_delayed_nodes(struct btrfs_root *root)
+{
+	u64 inode_id = 0;
+	struct btrfs_delayed_node *delayed_nodes[8];
+	int i, n;
+
+	while (1) {
+		spin_lock(&root->inode_lock);
+		n = radix_tree_gang_lookup(&root->delayed_nodes_tree,
+					   (void **)delayed_nodes, inode_id,
+					   ARRAY_SIZE(delayed_nodes));
+		if (!n) {
+			spin_unlock(&root->inode_lock);
+			break;
+		}
+
+		inode_id = delayed_nodes[n - 1]->inode_id + 1;
+
+		for (i = 0; i < n; i++)
+			atomic_inc(&delayed_nodes[i]->refs);
+		spin_unlock(&root->inode_lock);
+
+		for (i = 0; i < n; i++) {
+			__btrfs_kill_delayed_node(delayed_nodes[i]);
+			btrfs_release_delayed_node(delayed_nodes[i]);
+		}
+	}
+}
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
new file mode 100644
index 000000000000..8d27af4bd8b9
--- /dev/null
+++ b/fs/btrfs/delayed-inode.h
@@ -0,0 +1,145 @@
+/*
+ * Copyright (C) 2011 Fujitsu.  All rights reserved.
+ * Written by Miao Xie <miaox@cn.fujitsu.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 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 021110-1307, USA.
+ */
+
+#ifndef __DELAYED_TREE_OPERATION_H
+#define __DELAYED_TREE_OPERATION_H
+
+#include <linux/rbtree.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/wait.h>
+#include <asm/atomic.h>
+
+#include "ctree.h"
+
+/* types of the delayed item */
+#define BTRFS_DELAYED_INSERTION_ITEM	1
+#define BTRFS_DELAYED_DELETION_ITEM	2
+
+struct btrfs_delayed_root {
+	spinlock_t lock;
+	struct list_head node_list;
+	/*
+	 * Used for delayed nodes which is waiting to be dealt with by the
+	 * worker. If the delayed node is inserted into the work queue, we
+	 * drop it from this list.
+	 */
+	struct list_head prepare_list;
+	atomic_t items;		/* for delayed items */
+	int nodes;		/* for delayed nodes */
+	wait_queue_head_t wait;
+};
+
+struct btrfs_delayed_node {
+	u64 inode_id;
+	u64 bytes_reserved;
+	struct btrfs_root *root;
+	/* Used to add the node into the delayed root's node list. */
+	struct list_head n_list;
+	/*
+	 * Used to add the node into the prepare list, the nodes in this list
+	 * is waiting to be dealt with by the async worker.
+	 */
+	struct list_head p_list;
+	struct rb_root ins_root;
+	struct rb_root del_root;
+	struct mutex mutex;
+	struct btrfs_inode_item inode_item;
+	atomic_t refs;
+	u64 index_cnt;
+	bool in_list;
+	bool inode_dirty;
+	int count;
+};
+
+struct btrfs_delayed_item {
+	struct rb_node rb_node;
+	struct btrfs_key key;
+	struct list_head tree_list;	/* used for batch insert/delete items */
+	struct list_head readdir_list;	/* used for readdir items */
+	u64 bytes_reserved;
+	struct btrfs_delayed_node *delayed_node;
+	atomic_t refs;
+	int ins_or_del;
+	u32 data_len;
+	char data[0];
+};
+
+static inline void btrfs_init_delayed_root(
+				struct btrfs_delayed_root *delayed_root)
+{
+	atomic_set(&delayed_root->items, 0);
+	delayed_root->nodes = 0;
+	spin_lock_init(&delayed_root->lock);
+	init_waitqueue_head(&delayed_root->wait);
+	INIT_LIST_HEAD(&delayed_root->node_list);
+	INIT_LIST_HEAD(&delayed_root->prepare_list);
+}
+
+int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root, const char *name,
+				   int name_len, struct inode *dir,
+				   struct btrfs_disk_key *disk_key, u8 type,
+				   u64 index);
+
+int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root, struct inode *dir,
+				   u64 index);
+
+int btrfs_inode_delayed_dir_index_count(struct inode *inode);
+
+int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root);
+
+void btrfs_balance_delayed_items(struct btrfs_root *root);
+
+int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
+				     struct inode *inode);
+/* Used for evicting the inode. */
+void btrfs_remove_delayed_node(struct inode *inode);
+void btrfs_kill_delayed_inode_items(struct inode *inode);
+
+
+int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root, struct inode *inode);
+int btrfs_fill_inode(struct inode *inode, u32 *rdev);
+
+/* Used for drop dead root */
+void btrfs_kill_all_delayed_nodes(struct btrfs_root *root);
+
+/* Used for readdir() */
+void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
+			     struct list_head *del_list);
+void btrfs_put_delayed_items(struct list_head *ins_list,
+			     struct list_head *del_list);
+int btrfs_should_delete_dir_index(struct list_head *del_list,
+				  u64 index);
+int btrfs_readdir_delayed_dir_index(struct file *filp, void *dirent,
+				    filldir_t filldir,
+				    struct list_head *ins_list);
+
+/* for init */
+int __init btrfs_delayed_inode_init(void);
+void btrfs_delayed_inode_exit(void);
+
+/* for debugging */
+void btrfs_assert_delayed_root_empty(struct btrfs_root *root);
+
+#endif
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index bce28f653899..125cf76fcd08 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -281,44 +281,6 @@ again:
 }
 
 /*
- * This checks to see if there are any delayed refs in the
- * btree for a given bytenr.  It returns one if it finds any
- * and zero otherwise.
- *
- * If it only finds a head node, it returns 0.
- *
- * The idea is to use this when deciding if you can safely delete an
- * extent from the extent allocation tree.  There may be a pending
- * ref in the rbtree that adds or removes references, so as long as this
- * returns one you need to leave the BTRFS_EXTENT_ITEM in the extent
- * allocation tree.
- */
-int btrfs_delayed_ref_pending(struct btrfs_trans_handle *trans, u64 bytenr)
-{
-	struct btrfs_delayed_ref_node *ref;
-	struct btrfs_delayed_ref_root *delayed_refs;
-	struct rb_node *prev_node;
-	int ret = 0;
-
-	delayed_refs = &trans->transaction->delayed_refs;
-	spin_lock(&delayed_refs->lock);
-
-	ref = find_ref_head(&delayed_refs->root, bytenr, NULL);
-	if (ref) {
-		prev_node = rb_prev(&ref->rb_node);
-		if (!prev_node)
-			goto out;
-		ref = rb_entry(prev_node, struct btrfs_delayed_ref_node,
-			       rb_node);
-		if (ref->bytenr == bytenr)
-			ret = 1;
-	}
-out:
-	spin_unlock(&delayed_refs->lock);
-	return ret;
-}
-
-/*
  * helper function to update an extent delayed ref in the
  * rbtree.  existing and update must both have the same
  * bytenr and parent
@@ -747,79 +709,3 @@ btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr)
 		return btrfs_delayed_node_to_head(ref);
 	return NULL;
 }
-
-/*
- * add a delayed ref to the tree.  This does all of the accounting required
- * to make sure the delayed ref is eventually processed before this
- * transaction commits.
- *
- * The main point of this call is to add and remove a backreference in a single
- * shot, taking the lock only once, and only searching for the head node once.
- *
- * It is the same as doing a ref add and delete in two separate calls.
- */
-#if 0
-int btrfs_update_delayed_ref(struct btrfs_trans_handle *trans,
-			  u64 bytenr, u64 num_bytes, u64 orig_parent,
-			  u64 parent, u64 orig_ref_root, u64 ref_root,
-			  u64 orig_ref_generation, u64 ref_generation,
-			  u64 owner_objectid, int pin)
-{
-	struct btrfs_delayed_ref *ref;
-	struct btrfs_delayed_ref *old_ref;
-	struct btrfs_delayed_ref_head *head_ref;
-	struct btrfs_delayed_ref_root *delayed_refs;
-	int ret;
-
-	ref = kmalloc(sizeof(*ref), GFP_NOFS);
-	if (!ref)
-		return -ENOMEM;
-
-	old_ref = kmalloc(sizeof(*old_ref), GFP_NOFS);
-	if (!old_ref) {
-		kfree(ref);
-		return -ENOMEM;
-	}
-
-	/*
-	 * the parent = 0 case comes from cases where we don't actually
-	 * know the parent yet.  It will get updated later via a add/drop
-	 * pair.
-	 */
-	if (parent == 0)
-		parent = bytenr;
-	if (orig_parent == 0)
-		orig_parent = bytenr;
-
-	head_ref = kmalloc(sizeof(*head_ref), GFP_NOFS);
-	if (!head_ref) {
-		kfree(ref);
-		kfree(old_ref);
-		return -ENOMEM;
-	}
-	delayed_refs = &trans->transaction->delayed_refs;
-	spin_lock(&delayed_refs->lock);
-
-	/*
-	 * insert both the head node and the new ref without dropping
-	 * the spin lock
-	 */
-	ret = __btrfs_add_delayed_ref(trans, &head_ref->node, bytenr, num_bytes,
-				      (u64)-1, 0, 0, 0,
-				      BTRFS_UPDATE_DELAYED_HEAD, 0);
-	BUG_ON(ret);
-
-	ret = __btrfs_add_delayed_ref(trans, &ref->node, bytenr, num_bytes,
-				      parent, ref_root, ref_generation,
-				      owner_objectid, BTRFS_ADD_DELAYED_REF, 0);
-	BUG_ON(ret);
-
-	ret = __btrfs_add_delayed_ref(trans, &old_ref->node, bytenr, num_bytes,
-				      orig_parent, orig_ref_root,
-				      orig_ref_generation, owner_objectid,
-				      BTRFS_DROP_DELAYED_REF, pin);
-	BUG_ON(ret);
-	spin_unlock(&delayed_refs->lock);
-	return 0;
-}
-#endif
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 50e3cf92fbda..e287e3b0eab0 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -166,12 +166,6 @@ int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
 
 struct btrfs_delayed_ref_head *
 btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr);
-int btrfs_delayed_ref_pending(struct btrfs_trans_handle *trans, u64 bytenr);
-int btrfs_update_delayed_ref(struct btrfs_trans_handle *trans,
-			  u64 bytenr, u64 num_bytes, u64 orig_parent,
-			  u64 parent, u64 orig_ref_root, u64 ref_root,
-			  u64 orig_ref_generation, u64 ref_generation,
-			  u64 owner_objectid, int pin);
 int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans,
 			   struct btrfs_delayed_ref_head *head);
 int btrfs_find_ref_cluster(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index c62f02f6ae69..685f2593c4f0 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -50,7 +50,6 @@ static struct btrfs_dir_item *insert_with_overflow(struct btrfs_trans_handle
 		if (di)
 			return ERR_PTR(-EEXIST);
 		ret = btrfs_extend_item(trans, root, path, data_size);
-		WARN_ON(ret > 0);
 	}
 	if (ret < 0)
 		return ERR_PTR(ret);
@@ -124,8 +123,9 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans,
  * to use for the second index (if one is created).
  */
 int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
-			  *root, const char *name, int name_len, u64 dir,
-			  struct btrfs_key *location, u8 type, u64 index)
+			  *root, const char *name, int name_len,
+			  struct inode *dir, struct btrfs_key *location,
+			  u8 type, u64 index)
 {
 	int ret = 0;
 	int ret2 = 0;
@@ -137,13 +137,17 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
 	struct btrfs_disk_key disk_key;
 	u32 data_size;
 
-	key.objectid = dir;
+	key.objectid = btrfs_ino(dir);
 	btrfs_set_key_type(&key, BTRFS_DIR_ITEM_KEY);
 	key.offset = btrfs_name_hash(name, name_len);
 
 	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
 	path->leave_spinning = 1;
 
+	btrfs_cpu_key_to_disk(&disk_key, location);
+
 	data_size = sizeof(*dir_item) + name_len;
 	dir_item = insert_with_overflow(trans, root, path, &key, data_size,
 					name, name_len);
@@ -155,7 +159,6 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
 	}
 
 	leaf = path->nodes[0];
-	btrfs_cpu_key_to_disk(&disk_key, location);
 	btrfs_set_dir_item_key(leaf, dir_item, &disk_key);
 	btrfs_set_dir_type(leaf, dir_item, type);
 	btrfs_set_dir_data_len(leaf, dir_item, 0);
@@ -172,29 +175,11 @@ second_insert:
 		ret = 0;
 		goto out_free;
 	}
-	btrfs_release_path(root, path);
-
-	btrfs_set_key_type(&key, BTRFS_DIR_INDEX_KEY);
-	key.offset = index;
-	dir_item = insert_with_overflow(trans, root, path, &key, data_size,
-					name, name_len);
-	if (IS_ERR(dir_item)) {
-		ret2 = PTR_ERR(dir_item);
-		goto out_free;
-	}
-	leaf = path->nodes[0];
-	btrfs_cpu_key_to_disk(&disk_key, location);
-	btrfs_set_dir_item_key(leaf, dir_item, &disk_key);
-	btrfs_set_dir_type(leaf, dir_item, type);
-	btrfs_set_dir_data_len(leaf, dir_item, 0);
-	btrfs_set_dir_name_len(leaf, dir_item, name_len);
-	btrfs_set_dir_transid(leaf, dir_item, trans->transid);
-	name_ptr = (unsigned long)(dir_item + 1);
-	write_extent_buffer(leaf, name, name_ptr, name_len);
-	btrfs_mark_buffer_dirty(leaf);
+	btrfs_release_path(path);
 
+	ret2 = btrfs_insert_delayed_dir_index(trans, root, name, name_len, dir,
+					      &disk_key, type, index);
 out_free:
-
 	btrfs_free_path(path);
 	if (ret)
 		return ret;
@@ -452,7 +437,7 @@ int verify_dir_item(struct btrfs_root *root,
 		namelen = XATTR_NAME_MAX;
 
 	if (btrfs_dir_name_len(leaf, dir_item) > namelen) {
-		printk(KERN_CRIT "btrfS: invalid dir item name len: %u\n",
+		printk(KERN_CRIT "btrfs: invalid dir item name len: %u\n",
 		       (unsigned)btrfs_dir_data_len(leaf, dir_item));
 		return 1;
 	}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 228cf36ece83..1ac8db5dc0a3 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -29,6 +29,7 @@
 #include <linux/crc32c.h>
 #include <linux/slab.h>
 #include <linux/migrate.h>
+#include <linux/ratelimit.h>
 #include <asm/unaligned.h>
 #include "compat.h"
 #include "ctree.h"
@@ -41,6 +42,7 @@
 #include "locking.h"
 #include "tree-log.h"
 #include "free-space-cache.h"
+#include "inode-map.h"
 
 static struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
@@ -137,7 +139,7 @@ static const char *btrfs_eb_name[BTRFS_MAX_LEVEL + 1] = {
  * that covers the entire device
  */
 static struct extent_map *btree_get_extent(struct inode *inode,
-		struct page *page, size_t page_offset, u64 start, u64 len,
+		struct page *page, size_t pg_offset, u64 start, u64 len,
 		int create)
 {
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
@@ -154,7 +156,7 @@ static struct extent_map *btree_get_extent(struct inode *inode,
 	}
 	read_unlock(&em_tree->lock);
 
-	em = alloc_extent_map(GFP_NOFS);
+	em = alloc_extent_map();
 	if (!em) {
 		em = ERR_PTR(-ENOMEM);
 		goto out;
@@ -254,14 +256,12 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
 			memcpy(&found, result, csum_size);
 
 			read_extent_buffer(buf, &val, 0, csum_size);
-			if (printk_ratelimit()) {
-				printk(KERN_INFO "btrfs: %s checksum verify "
+			printk_ratelimited(KERN_INFO "btrfs: %s checksum verify "
 				       "failed on %llu wanted %X found %X "
 				       "level %d\n",
 				       root->fs_info->sb->s_id,
 				       (unsigned long long)buf->start, val, found,
 				       btrfs_header_level(buf));
-			}
 			if (result != (char *)&inline_result)
 				kfree(result);
 			return 1;
@@ -296,13 +296,11 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 		ret = 0;
 		goto out;
 	}
-	if (printk_ratelimit()) {
-		printk("parent transid verify failed on %llu wanted %llu "
+	printk_ratelimited("parent transid verify failed on %llu wanted %llu "
 		       "found %llu\n",
 		       (unsigned long long)eb->start,
 		       (unsigned long long)parent_transid,
 		       (unsigned long long)btrfs_header_generation(eb));
-	}
 	ret = 1;
 	clear_extent_buffer_uptodate(io_tree, eb, &cached_state);
 out:
@@ -380,7 +378,7 @@ static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
 	len = page->private >> 2;
 	WARN_ON(len == 0);
 
-	eb = alloc_extent_buffer(tree, start, len, page, GFP_NOFS);
+	eb = alloc_extent_buffer(tree, start, len, page);
 	if (eb == NULL) {
 		WARN_ON(1);
 		goto out;
@@ -525,7 +523,7 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 	len = page->private >> 2;
 	WARN_ON(len == 0);
 
-	eb = alloc_extent_buffer(tree, start, len, page, GFP_NOFS);
+	eb = alloc_extent_buffer(tree, start, len, page);
 	if (eb == NULL) {
 		ret = -EIO;
 		goto out;
@@ -533,12 +531,10 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 
 	found_start = btrfs_header_bytenr(eb);
 	if (found_start != start) {
-		if (printk_ratelimit()) {
-			printk(KERN_INFO "btrfs bad tree block start "
+		printk_ratelimited(KERN_INFO "btrfs bad tree block start "
 			       "%llu %llu\n",
 			       (unsigned long long)found_start,
 			       (unsigned long long)eb->start);
-		}
 		ret = -EIO;
 		goto err;
 	}
@@ -550,10 +546,8 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 		goto err;
 	}
 	if (check_tree_block_fsid(root, eb)) {
-		if (printk_ratelimit()) {
-			printk(KERN_INFO "btrfs bad fsid on block %llu\n",
+		printk_ratelimited(KERN_INFO "btrfs bad fsid on block %llu\n",
 			       (unsigned long long)eb->start);
-		}
 		ret = -EIO;
 		goto err;
 	}
@@ -650,12 +644,6 @@ unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info)
 	return 256 * limit;
 }
 
-int btrfs_congested_async(struct btrfs_fs_info *info, int iodone)
-{
-	return atomic_read(&info->nr_async_bios) >
-		btrfs_async_submit_limit(info);
-}
-
 static void run_one_async_start(struct btrfs_work *work)
 {
 	struct async_submit_bio *async;
@@ -963,7 +951,7 @@ struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
 	struct inode *btree_inode = root->fs_info->btree_inode;
 	struct extent_buffer *eb;
 	eb = find_extent_buffer(&BTRFS_I(btree_inode)->io_tree,
-				bytenr, blocksize, GFP_NOFS);
+				bytenr, blocksize);
 	return eb;
 }
 
@@ -974,7 +962,7 @@ struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 	struct extent_buffer *eb;
 
 	eb = alloc_extent_buffer(&BTRFS_I(btree_inode)->io_tree,
-				 bytenr, blocksize, NULL, GFP_NOFS);
+				 bytenr, blocksize, NULL);
 	return eb;
 }
 
@@ -1056,15 +1044,14 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	root->last_trans = 0;
 	root->highest_objectid = 0;
 	root->name = NULL;
-	root->in_sysfs = 0;
 	root->inode_tree = RB_ROOT;
+	INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
 	root->block_rsv = NULL;
 	root->orphan_block_rsv = NULL;
 
 	INIT_LIST_HEAD(&root->dirty_list);
 	INIT_LIST_HEAD(&root->orphan_list);
 	INIT_LIST_HEAD(&root->root_list);
-	spin_lock_init(&root->node_lock);
 	spin_lock_init(&root->orphan_lock);
 	spin_lock_init(&root->inode_lock);
 	spin_lock_init(&root->accounting_lock);
@@ -1080,7 +1067,7 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	root->log_transid = 0;
 	root->last_log_commit = 0;
 	extent_io_tree_init(&root->dirty_log_pages,
-			     fs_info->btree_inode->i_mapping, GFP_NOFS);
+			     fs_info->btree_inode->i_mapping);
 
 	memset(&root->root_key, 0, sizeof(root->root_key));
 	memset(&root->root_item, 0, sizeof(root->root_item));
@@ -1283,21 +1270,6 @@ out:
 	return root;
 }
 
-struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
-					u64 root_objectid)
-{
-	struct btrfs_root *root;
-
-	if (root_objectid == BTRFS_ROOT_TREE_OBJECTID)
-		return fs_info->tree_root;
-	if (root_objectid == BTRFS_EXTENT_TREE_OBJECTID)
-		return fs_info->extent_root;
-
-	root = radix_tree_lookup(&fs_info->fs_roots_radix,
-				 (unsigned long)root_objectid);
-	return root;
-}
-
 struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
 					      struct btrfs_key *location)
 {
@@ -1326,7 +1298,22 @@ again:
 	if (IS_ERR(root))
 		return root;
 
-	set_anon_super(&root->anon_super, NULL);
+	root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS);
+	root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned),
+					GFP_NOFS);
+	if (!root->free_ino_pinned || !root->free_ino_ctl) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	btrfs_init_free_ino_ctl(root);
+	mutex_init(&root->fs_commit_mutex);
+	spin_lock_init(&root->cache_lock);
+	init_waitqueue_head(&root->cache_wait);
+
+	ret = set_anon_super(&root->anon_super, NULL);
+	if (ret)
+		goto fail;
 
 	if (btrfs_root_refs(&root->root_item) == 0) {
 		ret = -ENOENT;
@@ -1369,41 +1356,6 @@ fail:
 	return ERR_PTR(ret);
 }
 
-struct btrfs_root *btrfs_read_fs_root(struct btrfs_fs_info *fs_info,
-				      struct btrfs_key *location,
-				      const char *name, int namelen)
-{
-	return btrfs_read_fs_root_no_name(fs_info, location);
-#if 0
-	struct btrfs_root *root;
-	int ret;
-
-	root = btrfs_read_fs_root_no_name(fs_info, location);
-	if (!root)
-		return NULL;
-
-	if (root->in_sysfs)
-		return root;
-
-	ret = btrfs_set_root_name(root, name, namelen);
-	if (ret) {
-		free_extent_buffer(root->node);
-		kfree(root);
-		return ERR_PTR(ret);
-	}
-
-	ret = btrfs_sysfs_add_root(root);
-	if (ret) {
-		free_extent_buffer(root->node);
-		kfree(root->name);
-		kfree(root);
-		return ERR_PTR(ret);
-	}
-	root->in_sysfs = 1;
-	return root;
-#endif
-}
-
 static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 {
 	struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data;
@@ -1411,7 +1363,8 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 	struct btrfs_device *device;
 	struct backing_dev_info *bdi;
 
-	list_for_each_entry(device, &info->fs_devices->devices, dev_list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) {
 		if (!device->bdev)
 			continue;
 		bdi = blk_get_backing_dev_info(device->bdev);
@@ -1420,6 +1373,7 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 			break;
 		}
 	}
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -1522,6 +1476,7 @@ static int cleaner_kthread(void *arg)
 			btrfs_run_delayed_iputs(root);
 			btrfs_clean_old_snapshots(root);
 			mutex_unlock(&root->fs_info->cleaner_mutex);
+			btrfs_run_defrag_inodes(root->fs_info);
 		}
 
 		if (freezing(current)) {
@@ -1551,24 +1506,24 @@ static int transaction_kthread(void *arg)
 		vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE);
 		mutex_lock(&root->fs_info->transaction_kthread_mutex);
 
-		spin_lock(&root->fs_info->new_trans_lock);
+		spin_lock(&root->fs_info->trans_lock);
 		cur = root->fs_info->running_transaction;
 		if (!cur) {
-			spin_unlock(&root->fs_info->new_trans_lock);
+			spin_unlock(&root->fs_info->trans_lock);
 			goto sleep;
 		}
 
 		now = get_seconds();
 		if (!cur->blocked &&
 		    (now < cur->start_time || now - cur->start_time < 30)) {
-			spin_unlock(&root->fs_info->new_trans_lock);
+			spin_unlock(&root->fs_info->trans_lock);
 			delay = HZ * 5;
 			goto sleep;
 		}
 		transid = cur->transid;
-		spin_unlock(&root->fs_info->new_trans_lock);
+		spin_unlock(&root->fs_info->trans_lock);
 
-		trans = btrfs_join_transaction(root, 1);
+		trans = btrfs_join_transaction(root);
 		BUG_ON(IS_ERR(trans));
 		if (transid == trans->transid) {
 			ret = btrfs_commit_transaction(trans, root);
@@ -1611,7 +1566,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	struct btrfs_root *csum_root = kzalloc(sizeof(struct btrfs_root),
 						 GFP_NOFS);
 	struct btrfs_root *tree_root = btrfs_sb(sb);
-	struct btrfs_fs_info *fs_info = tree_root->fs_info;
+	struct btrfs_fs_info *fs_info = NULL;
 	struct btrfs_root *chunk_root = kzalloc(sizeof(struct btrfs_root),
 						GFP_NOFS);
 	struct btrfs_root *dev_root = kzalloc(sizeof(struct btrfs_root),
@@ -1623,11 +1578,12 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 
 	struct btrfs_super_block *disk_super;
 
-	if (!extent_root || !tree_root || !fs_info ||
+	if (!extent_root || !tree_root || !tree_root->fs_info ||
 	    !chunk_root || !dev_root || !csum_root) {
 		err = -ENOMEM;
 		goto fail;
 	}
+	fs_info = tree_root->fs_info;
 
 	ret = init_srcu_struct(&fs_info->subvol_srcu);
 	if (ret) {
@@ -1658,10 +1614,12 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	INIT_LIST_HEAD(&fs_info->ordered_operations);
 	INIT_LIST_HEAD(&fs_info->caching_block_groups);
 	spin_lock_init(&fs_info->delalloc_lock);
-	spin_lock_init(&fs_info->new_trans_lock);
+	spin_lock_init(&fs_info->trans_lock);
 	spin_lock_init(&fs_info->ref_cache_lock);
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
 	spin_lock_init(&fs_info->delayed_iput_lock);
+	spin_lock_init(&fs_info->defrag_inodes_lock);
+	mutex_init(&fs_info->reloc_mutex);
 
 	init_completion(&fs_info->kobj_unregister);
 	fs_info->tree_root = tree_root;
@@ -1684,15 +1642,34 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	atomic_set(&fs_info->async_delalloc_pages, 0);
 	atomic_set(&fs_info->async_submit_draining, 0);
 	atomic_set(&fs_info->nr_async_bios, 0);
+	atomic_set(&fs_info->defrag_running, 0);
 	fs_info->sb = sb;
 	fs_info->max_inline = 8192 * 1024;
 	fs_info->metadata_ratio = 0;
+	fs_info->defrag_inodes = RB_ROOT;
+	fs_info->trans_no_join = 0;
 
 	fs_info->thread_pool_size = min_t(unsigned long,
 					  num_online_cpus() + 2, 8);
 
 	INIT_LIST_HEAD(&fs_info->ordered_extents);
 	spin_lock_init(&fs_info->ordered_extent_lock);
+	fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
+					GFP_NOFS);
+	if (!fs_info->delayed_root) {
+		err = -ENOMEM;
+		goto fail_iput;
+	}
+	btrfs_init_delayed_root(fs_info->delayed_root);
+
+	mutex_init(&fs_info->scrub_lock);
+	atomic_set(&fs_info->scrubs_running, 0);
+	atomic_set(&fs_info->scrub_pause_req, 0);
+	atomic_set(&fs_info->scrubs_paused, 0);
+	atomic_set(&fs_info->scrub_cancel_req, 0);
+	init_waitqueue_head(&fs_info->scrub_pause_wait);
+	init_rwsem(&fs_info->scrub_super_lock);
+	fs_info->scrub_workers_refcnt = 0;
 
 	sb->s_blocksize = 4096;
 	sb->s_blocksize_bits = blksize_bits(4096);
@@ -1711,10 +1688,8 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 
 	RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node);
 	extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree,
-			     fs_info->btree_inode->i_mapping,
-			     GFP_NOFS);
-	extent_map_tree_init(&BTRFS_I(fs_info->btree_inode)->extent_tree,
-			     GFP_NOFS);
+			     fs_info->btree_inode->i_mapping);
+	extent_map_tree_init(&BTRFS_I(fs_info->btree_inode)->extent_tree);
 
 	BTRFS_I(fs_info->btree_inode)->io_tree.ops = &btree_extent_io_ops;
 
@@ -1728,14 +1703,13 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	fs_info->block_group_cache_tree = RB_ROOT;
 
 	extent_io_tree_init(&fs_info->freed_extents[0],
-			     fs_info->btree_inode->i_mapping, GFP_NOFS);
+			     fs_info->btree_inode->i_mapping);
 	extent_io_tree_init(&fs_info->freed_extents[1],
-			     fs_info->btree_inode->i_mapping, GFP_NOFS);
+			     fs_info->btree_inode->i_mapping);
 	fs_info->pinned_extents = &fs_info->freed_extents[0];
 	fs_info->do_barriers = 1;
 
 
-	mutex_init(&fs_info->trans_mutex);
 	mutex_init(&fs_info->ordered_operations_mutex);
 	mutex_init(&fs_info->tree_log_mutex);
 	mutex_init(&fs_info->chunk_mutex);
@@ -1760,7 +1734,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	bh = btrfs_read_dev_super(fs_devices->latest_bdev);
 	if (!bh) {
 		err = -EINVAL;
-		goto fail_iput;
+		goto fail_alloc;
 	}
 
 	memcpy(&fs_info->super_copy, bh->b_data, sizeof(fs_info->super_copy));
@@ -1772,7 +1746,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 
 	disk_super = &fs_info->super_copy;
 	if (!btrfs_super_root(disk_super))
-		goto fail_iput;
+		goto fail_alloc;
 
 	/* check FS state, whether FS is broken. */
 	fs_info->fs_state |= btrfs_super_flags(disk_super);
@@ -1788,7 +1762,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	ret = btrfs_parse_options(tree_root, options);
 	if (ret) {
 		err = ret;
-		goto fail_iput;
+		goto fail_alloc;
 	}
 
 	features = btrfs_super_incompat_flags(disk_super) &
@@ -1798,7 +1772,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 		       "unsupported optional features (%Lx).\n",
 		       (unsigned long long)features);
 		err = -EINVAL;
-		goto fail_iput;
+		goto fail_alloc;
 	}
 
 	features = btrfs_super_incompat_flags(disk_super);
@@ -1814,7 +1788,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 		       "unsupported option features (%Lx).\n",
 		       (unsigned long long)features);
 		err = -EINVAL;
-		goto fail_iput;
+		goto fail_alloc;
 	}
 
 	btrfs_init_workers(&fs_info->generic_worker,
@@ -1861,6 +1835,9 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 			   &fs_info->generic_worker);
 	btrfs_init_workers(&fs_info->endio_freespace_worker, "freespace-write",
 			   1, &fs_info->generic_worker);
+	btrfs_init_workers(&fs_info->delayed_workers, "delayed-meta",
+			   fs_info->thread_pool_size,
+			   &fs_info->generic_worker);
 
 	/*
 	 * endios are largely parallel and should have a very
@@ -1882,6 +1859,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	btrfs_start_workers(&fs_info->endio_meta_write_workers, 1);
 	btrfs_start_workers(&fs_info->endio_write_workers, 1);
 	btrfs_start_workers(&fs_info->endio_freespace_worker, 1);
+	btrfs_start_workers(&fs_info->delayed_workers, 1);
 
 	fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
 	fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
@@ -2138,6 +2116,9 @@ fail_sb_buffer:
 	btrfs_stop_workers(&fs_info->endio_write_workers);
 	btrfs_stop_workers(&fs_info->endio_freespace_worker);
 	btrfs_stop_workers(&fs_info->submit_workers);
+	btrfs_stop_workers(&fs_info->delayed_workers);
+fail_alloc:
+	kfree(fs_info->delayed_root);
 fail_iput:
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	iput(fs_info->btree_inode);
@@ -2165,11 +2146,9 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 	if (uptodate) {
 		set_buffer_uptodate(bh);
 	} else {
-		if (printk_ratelimit()) {
-			printk(KERN_WARNING "lost page write due to "
+		printk_ratelimited(KERN_WARNING "lost page write due to "
 					"I/O error on %s\n",
 				       bdevname(bh->b_bdev, b));
-		}
 		/* note, we dont' set_buffer_write_io_error because we have
 		 * our own ways of dealing with the IO errors
 		 */
@@ -2333,7 +2312,7 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors)
 
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
 	head = &root->fs_info->fs_devices->devices;
-	list_for_each_entry(dev, head, dev_list) {
+	list_for_each_entry_rcu(dev, head, dev_list) {
 		if (!dev->bdev) {
 			total_errors++;
 			continue;
@@ -2366,7 +2345,7 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors)
 	}
 
 	total_errors = 0;
-	list_for_each_entry(dev, head, dev_list) {
+	list_for_each_entry_rcu(dev, head, dev_list) {
 		if (!dev->bdev)
 			continue;
 		if (!dev->in_fs_metadata || !dev->writeable)
@@ -2404,12 +2383,15 @@ int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
 	if (btrfs_root_refs(&root->root_item) == 0)
 		synchronize_srcu(&fs_info->subvol_srcu);
 
+	__btrfs_remove_free_space_cache(root->free_ino_pinned);
+	__btrfs_remove_free_space_cache(root->free_ino_ctl);
 	free_fs_root(root);
 	return 0;
 }
 
 static void free_fs_root(struct btrfs_root *root)
 {
+	iput(root->cache_inode);
 	WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
 	if (root->anon_super.s_dev) {
 		down_write(&root->anon_super.s_umount);
@@ -2417,6 +2399,8 @@ static void free_fs_root(struct btrfs_root *root)
 	}
 	free_extent_buffer(root->node);
 	free_extent_buffer(root->commit_root);
+	kfree(root->free_ino_ctl);
+	kfree(root->free_ino_pinned);
 	kfree(root->name);
 	kfree(root);
 }
@@ -2495,13 +2479,13 @@ int btrfs_commit_super(struct btrfs_root *root)
 	down_write(&root->fs_info->cleanup_work_sem);
 	up_write(&root->fs_info->cleanup_work_sem);
 
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 	ret = btrfs_commit_transaction(trans, root);
 	BUG_ON(ret);
 	/* run commit again to drop the original snapshot */
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 	btrfs_commit_transaction(trans, root);
@@ -2520,6 +2504,15 @@ int close_ctree(struct btrfs_root *root)
 	fs_info->closing = 1;
 	smp_mb();
 
+	btrfs_scrub_cancel(root);
+
+	/* wait for any defraggers to finish */
+	wait_event(fs_info->transaction_wait,
+		   (atomic_read(&fs_info->defrag_running) == 0));
+
+	/* clear out the rbtree of defraggable inodes */
+	btrfs_run_defrag_inodes(root->fs_info);
+
 	btrfs_put_block_group_cache(fs_info);
 
 	/*
@@ -2578,6 +2571,7 @@ int close_ctree(struct btrfs_root *root)
 	del_fs_roots(fs_info);
 
 	iput(fs_info->btree_inode);
+	kfree(fs_info->delayed_root);
 
 	btrfs_stop_workers(&fs_info->generic_worker);
 	btrfs_stop_workers(&fs_info->fixup_workers);
@@ -2589,6 +2583,7 @@ int close_ctree(struct btrfs_root *root)
 	btrfs_stop_workers(&fs_info->endio_write_workers);
 	btrfs_stop_workers(&fs_info->endio_freespace_worker);
 	btrfs_stop_workers(&fs_info->submit_workers);
+	btrfs_stop_workers(&fs_info->delayed_workers);
 
 	btrfs_close_devices(fs_info->fs_devices);
 	btrfs_mapping_tree_free(&fs_info->mapping_tree);
@@ -2665,6 +2660,29 @@ void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr)
 	if (current->flags & PF_MEMALLOC)
 		return;
 
+	btrfs_balance_delayed_items(root);
+
+	num_dirty = root->fs_info->dirty_metadata_bytes;
+
+	if (num_dirty > thresh) {
+		balance_dirty_pages_ratelimited_nr(
+				   root->fs_info->btree_inode->i_mapping, 1);
+	}
+	return;
+}
+
+void __btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr)
+{
+	/*
+	 * looks as though older kernels can get into trouble with
+	 * this code, they end up stuck in balance_dirty_pages forever
+	 */
+	u64 num_dirty;
+	unsigned long thresh = 32 * 1024 * 1024;
+
+	if (current->flags & PF_MEMALLOC)
+		return;
+
 	num_dirty = root->fs_info->dirty_metadata_bytes;
 
 	if (num_dirty > thresh) {
@@ -2697,7 +2715,7 @@ int btree_lock_page_hook(struct page *page)
 		goto out;
 
 	len = page->private >> 2;
-	eb = find_extent_buffer(io_tree, bytenr, len, GFP_NOFS);
+	eb = find_extent_buffer(io_tree, bytenr, len);
 	if (!eb)
 		goto out;
 
@@ -2893,9 +2911,8 @@ static int btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
 
 	INIT_LIST_HEAD(&splice);
 
-	list_splice_init(&root->fs_info->delalloc_inodes, &splice);
-
 	spin_lock(&root->fs_info->delalloc_lock);
+	list_splice_init(&root->fs_info->delalloc_inodes, &splice);
 
 	while (!list_empty(&splice)) {
 		btrfs_inode = list_entry(splice.next, struct btrfs_inode,
@@ -3006,10 +3023,13 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
 
 	WARN_ON(1);
 
-	mutex_lock(&root->fs_info->trans_mutex);
 	mutex_lock(&root->fs_info->transaction_kthread_mutex);
 
+	spin_lock(&root->fs_info->trans_lock);
 	list_splice_init(&root->fs_info->trans_list, &list);
+	root->fs_info->trans_no_join = 1;
+	spin_unlock(&root->fs_info->trans_lock);
+
 	while (!list_empty(&list)) {
 		t = list_entry(list.next, struct btrfs_transaction, list);
 		if (!t)
@@ -3034,23 +3054,18 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
 		t->blocked = 0;
 		if (waitqueue_active(&root->fs_info->transaction_wait))
 			wake_up(&root->fs_info->transaction_wait);
-		mutex_unlock(&root->fs_info->trans_mutex);
 
-		mutex_lock(&root->fs_info->trans_mutex);
 		t->commit_done = 1;
 		if (waitqueue_active(&t->commit_wait))
 			wake_up(&t->commit_wait);
-		mutex_unlock(&root->fs_info->trans_mutex);
-
-		mutex_lock(&root->fs_info->trans_mutex);
 
 		btrfs_destroy_pending_snapshots(t);
 
 		btrfs_destroy_delalloc_inodes(root);
 
-		spin_lock(&root->fs_info->new_trans_lock);
+		spin_lock(&root->fs_info->trans_lock);
 		root->fs_info->running_transaction = NULL;
-		spin_unlock(&root->fs_info->new_trans_lock);
+		spin_unlock(&root->fs_info->trans_lock);
 
 		btrfs_destroy_marked_extents(root, &t->dirty_pages,
 					     EXTENT_DIRTY);
@@ -3064,8 +3079,10 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
 		kmem_cache_free(btrfs_transaction_cachep, t);
 	}
 
+	spin_lock(&root->fs_info->trans_lock);
+	root->fs_info->trans_no_join = 0;
+	spin_unlock(&root->fs_info->trans_lock);
 	mutex_unlock(&root->fs_info->transaction_kthread_mutex);
-	mutex_unlock(&root->fs_info->trans_mutex);
 
 	return 0;
 }
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 07b20dc2fd95..a0b610a67aae 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -55,35 +55,20 @@ int btrfs_commit_super(struct btrfs_root *root);
 int btrfs_error_commit_super(struct btrfs_root *root);
 struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
 					    u64 bytenr, u32 blocksize);
-struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
-					u64 root_objectid);
-struct btrfs_root *btrfs_read_fs_root(struct btrfs_fs_info *fs_info,
-				      struct btrfs_key *location,
-				      const char *name, int namelen);
 struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root,
 					       struct btrfs_key *location);
 struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
 					      struct btrfs_key *location);
 int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info);
-int btrfs_insert_dev_radix(struct btrfs_root *root,
-			   struct block_device *bdev,
-			   u64 device_id,
-			   u64 block_start,
-			   u64 num_blocks);
 void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr);
+void __btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr);
 int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root);
 void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
-void btrfs_mark_buffer_dirty_nonblocking(struct extent_buffer *buf);
 int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid);
 int btrfs_set_buffer_uptodate(struct extent_buffer *buf);
-int wait_on_tree_block_writeback(struct btrfs_root *root,
-				 struct extent_buffer *buf);
 int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid);
 u32 btrfs_csum_data(struct btrfs_root *root, char *data, u32 seed, size_t len);
 void btrfs_csum_final(u32 crc, char *result);
-int btrfs_open_device(struct btrfs_device *dev);
-int btrfs_verify_block_csum(struct btrfs_root *root,
-			    struct extent_buffer *buf);
 int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
 			int metadata);
 int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
@@ -91,8 +76,6 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
 			unsigned long bio_flags, u64 bio_offset,
 			extent_submit_bio_hook_t *submit_bio_start,
 			extent_submit_bio_hook_t *submit_bio_done);
-
-int btrfs_congested_async(struct btrfs_fs_info *info, int iodone);
 unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info);
 int btrfs_write_tree_block(struct extent_buffer *buf);
 int btrfs_wait_tree_block_writeback(struct extent_buffer *buf);
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index b4ffad859adb..1b8dc33778f9 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -32,7 +32,7 @@ static int btrfs_encode_fh(struct dentry *dentry, u32 *fh, int *max_len,
 	len  = BTRFS_FID_SIZE_NON_CONNECTABLE;
 	type = FILEID_BTRFS_WITHOUT_PARENT;
 
-	fid->objectid = inode->i_ino;
+	fid->objectid = btrfs_ino(inode);
 	fid->root_objectid = BTRFS_I(inode)->root->objectid;
 	fid->gen = inode->i_generation;
 
@@ -178,13 +178,13 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
 	if (!path)
 		return ERR_PTR(-ENOMEM);
 
-	if (dir->i_ino == BTRFS_FIRST_FREE_OBJECTID) {
+	if (btrfs_ino(dir) == BTRFS_FIRST_FREE_OBJECTID) {
 		key.objectid = root->root_key.objectid;
 		key.type = BTRFS_ROOT_BACKREF_KEY;
 		key.offset = (u64)-1;
 		root = root->fs_info->tree_root;
 	} else {
-		key.objectid = dir->i_ino;
+		key.objectid = btrfs_ino(dir);
 		key.type = BTRFS_INODE_REF_KEY;
 		key.offset = (u64)-1;
 	}
@@ -244,6 +244,7 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 	struct btrfs_key key;
 	int name_len;
 	int ret;
+	u64 ino;
 
 	if (!dir || !inode)
 		return -EINVAL;
@@ -251,19 +252,21 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 	if (!S_ISDIR(dir->i_mode))
 		return -EINVAL;
 
+	ino = btrfs_ino(inode);
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 	path->leave_spinning = 1;
 
-	if (inode->i_ino == BTRFS_FIRST_FREE_OBJECTID) {
+	if (ino == BTRFS_FIRST_FREE_OBJECTID) {
 		key.objectid = BTRFS_I(inode)->root->root_key.objectid;
 		key.type = BTRFS_ROOT_BACKREF_KEY;
 		key.offset = (u64)-1;
 		root = root->fs_info->tree_root;
 	} else {
-		key.objectid = inode->i_ino;
-		key.offset = dir->i_ino;
+		key.objectid = ino;
+		key.offset = btrfs_ino(dir);
 		key.type = BTRFS_INODE_REF_KEY;
 	}
 
@@ -272,7 +275,7 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 		btrfs_free_path(path);
 		return ret;
 	} else if (ret > 0) {
-		if (inode->i_ino == BTRFS_FIRST_FREE_OBJECTID) {
+		if (ino == BTRFS_FIRST_FREE_OBJECTID) {
 			path->slots[0]--;
 		} else {
 			btrfs_free_path(path);
@@ -281,11 +284,11 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 	}
 	leaf = path->nodes[0];
 
-	if (inode->i_ino == BTRFS_FIRST_FREE_OBJECTID) {
-	       rref = btrfs_item_ptr(leaf, path->slots[0],
+	if (ino == BTRFS_FIRST_FREE_OBJECTID) {
+		rref = btrfs_item_ptr(leaf, path->slots[0],
 				     struct btrfs_root_ref);
-	       name_ptr = (unsigned long)(rref + 1);
-	       name_len = btrfs_root_ref_name_len(leaf, rref);
+		name_ptr = (unsigned long)(rref + 1);
+		name_len = btrfs_root_ref_name_len(leaf, rref);
 	} else {
 		iref = btrfs_item_ptr(leaf, path->slots[0],
 				      struct btrfs_inode_ref);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 9ee6bd55e16c..71cd456fdb60 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -94,7 +94,7 @@ static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits)
 	return (cache->flags & bits) == bits;
 }
 
-void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
+static void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
 {
 	atomic_inc(&cache->count);
 }
@@ -105,6 +105,7 @@ void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
 		WARN_ON(cache->pinned > 0);
 		WARN_ON(cache->reserved > 0);
 		WARN_ON(cache->reserved_pinned > 0);
+		kfree(cache->free_space_ctl);
 		kfree(cache);
 	}
 }
@@ -347,7 +348,7 @@ static int caching_kthread(void *data)
 	 */
 	path->skip_locking = 1;
 	path->search_commit_root = 1;
-	path->reada = 2;
+	path->reada = 1;
 
 	key.objectid = last;
 	key.offset = 0;
@@ -365,8 +366,7 @@ again:
 	nritems = btrfs_header_nritems(leaf);
 
 	while (1) {
-		smp_mb();
-		if (fs_info->closing > 1) {
+		if (btrfs_fs_closing(fs_info) > 1) {
 			last = (u64)-1;
 			break;
 		}
@@ -378,15 +378,18 @@ again:
 			if (ret)
 				break;
 
-			caching_ctl->progress = last;
-			btrfs_release_path(extent_root, path);
-			up_read(&fs_info->extent_commit_sem);
-			mutex_unlock(&caching_ctl->mutex);
-			if (btrfs_transaction_in_commit(fs_info))
-				schedule_timeout(1);
-			else
+			if (need_resched() ||
+			    btrfs_next_leaf(extent_root, path)) {
+				caching_ctl->progress = last;
+				btrfs_release_path(path);
+				up_read(&fs_info->extent_commit_sem);
+				mutex_unlock(&caching_ctl->mutex);
 				cond_resched();
-			goto again;
+				goto again;
+			}
+			leaf = path->nodes[0];
+			nritems = btrfs_header_nritems(leaf);
+			continue;
 		}
 
 		if (key.objectid < block_group->key.objectid) {
@@ -754,8 +757,12 @@ again:
 			atomic_inc(&head->node.refs);
 			spin_unlock(&delayed_refs->lock);
 
-			btrfs_release_path(root->fs_info->extent_root, path);
+			btrfs_release_path(path);
 
+			/*
+			 * Mutex was contended, block until it's released and try
+			 * again
+			 */
 			mutex_lock(&head->mutex);
 			mutex_unlock(&head->mutex);
 			btrfs_put_delayed_ref(&head->node);
@@ -934,7 +941,7 @@ static int convert_extent_item_v0(struct btrfs_trans_handle *trans,
 			break;
 		}
 	}
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	if (owner < BTRFS_FIRST_FREE_OBJECTID)
 		new_size += sizeof(*bi);
@@ -947,7 +954,6 @@ static int convert_extent_item_v0(struct btrfs_trans_handle *trans,
 	BUG_ON(ret);
 
 	ret = btrfs_extend_item(trans, root, path, new_size);
-	BUG_ON(ret);
 
 	leaf = path->nodes[0];
 	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
@@ -1042,7 +1048,7 @@ again:
 			return 0;
 #ifdef BTRFS_COMPAT_EXTENT_TREE_V0
 		key.type = BTRFS_EXTENT_REF_V0_KEY;
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 		if (ret < 0) {
 			err = ret;
@@ -1080,7 +1086,7 @@ again:
 		if (match_extent_data_ref(leaf, ref, root_objectid,
 					  owner, offset)) {
 			if (recow) {
-				btrfs_release_path(root, path);
+				btrfs_release_path(path);
 				goto again;
 			}
 			err = 0;
@@ -1141,7 +1147,7 @@ static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans,
 			if (match_extent_data_ref(leaf, ref, root_objectid,
 						  owner, offset))
 				break;
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			key.offset++;
 			ret = btrfs_insert_empty_item(trans, root, path, &key,
 						      size);
@@ -1167,7 +1173,7 @@ static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	ret = 0;
 fail:
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	return ret;
 }
 
@@ -1293,7 +1299,7 @@ static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
 		ret = -ENOENT;
 #ifdef BTRFS_COMPAT_EXTENT_TREE_V0
 	if (ret == -ENOENT && parent) {
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		key.type = BTRFS_EXTENT_REF_V0_KEY;
 		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 		if (ret > 0)
@@ -1322,7 +1328,7 @@ static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
 	}
 
 	ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	return ret;
 }
 
@@ -1555,7 +1561,6 @@ int setup_inline_extent_backref(struct btrfs_trans_handle *trans,
 	size = btrfs_extent_inline_ref_size(type);
 
 	ret = btrfs_extend_item(trans, root, path, size);
-	BUG_ON(ret);
 
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	refs = btrfs_extent_refs(leaf, ei);
@@ -1608,7 +1613,7 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
 	if (ret != -ENOENT)
 		return ret;
 
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	*ref_ret = NULL;
 
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
@@ -1684,7 +1689,6 @@ int update_inline_extent_backref(struct btrfs_trans_handle *trans,
 					      end - ptr - size);
 		item_size -= size;
 		ret = btrfs_truncate_item(trans, root, path, item_size, 1);
-		BUG_ON(ret);
 	}
 	btrfs_mark_buffer_dirty(leaf);
 	return 0;
@@ -1862,7 +1866,7 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 		__run_delayed_extent_op(extent_op, leaf, item);
 
 	btrfs_mark_buffer_dirty(leaf);
-	btrfs_release_path(root->fs_info->extent_root, path);
+	btrfs_release_path(path);
 
 	path->reada = 1;
 	path->leave_spinning = 1;
@@ -2297,6 +2301,10 @@ again:
 				atomic_inc(&ref->refs);
 
 				spin_unlock(&delayed_refs->lock);
+				/*
+				 * Mutex was contended, block until it's
+				 * released and try again
+				 */
 				mutex_lock(&head->mutex);
 				mutex_unlock(&head->mutex);
 
@@ -2361,8 +2369,12 @@ static noinline int check_delayed_ref(struct btrfs_trans_handle *trans,
 		atomic_inc(&head->node.refs);
 		spin_unlock(&delayed_refs->lock);
 
-		btrfs_release_path(root->fs_info->extent_root, path);
+		btrfs_release_path(path);
 
+		/*
+		 * Mutex was contended, block until it's released and let
+		 * caller try again
+		 */
 		mutex_lock(&head->mutex);
 		mutex_unlock(&head->mutex);
 		btrfs_put_delayed_ref(&head->node);
@@ -2510,126 +2522,6 @@ out:
 	return ret;
 }
 
-#if 0
-int btrfs_cache_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		    struct extent_buffer *buf, u32 nr_extents)
-{
-	struct btrfs_key key;
-	struct btrfs_file_extent_item *fi;
-	u64 root_gen;
-	u32 nritems;
-	int i;
-	int level;
-	int ret = 0;
-	int shared = 0;
-
-	if (!root->ref_cows)
-		return 0;
-
-	if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID) {
-		shared = 0;
-		root_gen = root->root_key.offset;
-	} else {
-		shared = 1;
-		root_gen = trans->transid - 1;
-	}
-
-	level = btrfs_header_level(buf);
-	nritems = btrfs_header_nritems(buf);
-
-	if (level == 0) {
-		struct btrfs_leaf_ref *ref;
-		struct btrfs_extent_info *info;
-
-		ref = btrfs_alloc_leaf_ref(root, nr_extents);
-		if (!ref) {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		ref->root_gen = root_gen;
-		ref->bytenr = buf->start;
-		ref->owner = btrfs_header_owner(buf);
-		ref->generation = btrfs_header_generation(buf);
-		ref->nritems = nr_extents;
-		info = ref->extents;
-
-		for (i = 0; nr_extents > 0 && i < nritems; i++) {
-			u64 disk_bytenr;
-			btrfs_item_key_to_cpu(buf, &key, i);
-			if (btrfs_key_type(&key) != BTRFS_EXTENT_DATA_KEY)
-				continue;
-			fi = btrfs_item_ptr(buf, i,
-					    struct btrfs_file_extent_item);
-			if (btrfs_file_extent_type(buf, fi) ==
-			    BTRFS_FILE_EXTENT_INLINE)
-				continue;
-			disk_bytenr = btrfs_file_extent_disk_bytenr(buf, fi);
-			if (disk_bytenr == 0)
-				continue;
-
-			info->bytenr = disk_bytenr;
-			info->num_bytes =
-				btrfs_file_extent_disk_num_bytes(buf, fi);
-			info->objectid = key.objectid;
-			info->offset = key.offset;
-			info++;
-		}
-
-		ret = btrfs_add_leaf_ref(root, ref, shared);
-		if (ret == -EEXIST && shared) {
-			struct btrfs_leaf_ref *old;
-			old = btrfs_lookup_leaf_ref(root, ref->bytenr);
-			BUG_ON(!old);
-			btrfs_remove_leaf_ref(root, old);
-			btrfs_free_leaf_ref(root, old);
-			ret = btrfs_add_leaf_ref(root, ref, shared);
-		}
-		WARN_ON(ret);
-		btrfs_free_leaf_ref(root, ref);
-	}
-out:
-	return ret;
-}
-
-/* when a block goes through cow, we update the reference counts of
- * everything that block points to.  The internal pointers of the block
- * can be in just about any order, and it is likely to have clusters of
- * things that are close together and clusters of things that are not.
- *
- * To help reduce the seeks that come with updating all of these reference
- * counts, sort them by byte number before actual updates are done.
- *
- * struct refsort is used to match byte number to slot in the btree block.
- * we sort based on the byte number and then use the slot to actually
- * find the item.
- *
- * struct refsort is smaller than strcut btrfs_item and smaller than
- * struct btrfs_key_ptr.  Since we're currently limited to the page size
- * for a btree block, there's no way for a kmalloc of refsorts for a
- * single node to be bigger than a page.
- */
-struct refsort {
-	u64 bytenr;
-	u32 slot;
-};
-
-/*
- * for passing into sort()
- */
-static int refsort_cmp(const void *a_void, const void *b_void)
-{
-	const struct refsort *a = a_void;
-	const struct refsort *b = b_void;
-
-	if (a->bytenr < b->bytenr)
-		return -1;
-	if (a->bytenr > b->bytenr)
-		return 1;
-	return 0;
-}
-#endif
-
 static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct extent_buffer *buf,
@@ -2732,7 +2624,7 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
 	bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
 	write_extent_buffer(leaf, &cache->item, bi, sizeof(cache->item));
 	btrfs_mark_buffer_dirty(leaf);
-	btrfs_release_path(extent_root, path);
+	btrfs_release_path(path);
 fail:
 	if (ret)
 		return ret;
@@ -2785,7 +2677,7 @@ again:
 	inode = lookup_free_space_inode(root, block_group, path);
 	if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
 		ret = PTR_ERR(inode);
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		goto out;
 	}
 
@@ -2854,7 +2746,7 @@ again:
 out_put:
 	iput(inode);
 out_free:
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 out:
 	spin_lock(&block_group->lock);
 	block_group->disk_cache_state = dcs;
@@ -3144,7 +3036,8 @@ int btrfs_check_data_free_space(struct inode *inode, u64 bytes)
 	/* make sure bytes are sectorsize aligned */
 	bytes = (bytes + root->sectorsize - 1) & ~((u64)root->sectorsize - 1);
 
-	if (root == root->fs_info->tree_root) {
+	if (root == root->fs_info->tree_root ||
+	    BTRFS_I(inode)->location.objectid == BTRFS_FREE_INO_OBJECTID) {
 		alloc_chunk = 0;
 		committed = 1;
 	}
@@ -3174,7 +3067,7 @@ again:
 			spin_unlock(&data_sinfo->lock);
 alloc:
 			alloc_target = btrfs_get_alloc_profile(root, 1);
-			trans = btrfs_join_transaction(root, 1);
+			trans = btrfs_join_transaction(root);
 			if (IS_ERR(trans))
 				return PTR_ERR(trans);
 
@@ -3196,13 +3089,21 @@ alloc:
 			}
 			goto again;
 		}
+
+		/*
+		 * If we have less pinned bytes than we want to allocate then
+		 * don't bother committing the transaction, it won't help us.
+		 */
+		if (data_sinfo->bytes_pinned < bytes)
+			committed = 1;
 		spin_unlock(&data_sinfo->lock);
 
 		/* commit the current transaction and try again */
 commit_trans:
-		if (!committed && !root->fs_info->open_ioctl_trans) {
+		if (!committed &&
+		    !atomic_read(&root->fs_info->open_ioctl_trans)) {
 			committed = 1;
-			trans = btrfs_join_transaction(root, 1);
+			trans = btrfs_join_transaction(root);
 			if (IS_ERR(trans))
 				return PTR_ERR(trans);
 			ret = btrfs_commit_transaction(trans, root);
@@ -3211,18 +3112,6 @@ commit_trans:
 			goto again;
 		}
 
-#if 0 /* I hope we never need this code again, just in case */
-		printk(KERN_ERR "no space left, need %llu, %llu bytes_used, "
-		       "%llu bytes_reserved, " "%llu bytes_pinned, "
-		       "%llu bytes_readonly, %llu may use %llu total\n",
-		       (unsigned long long)bytes,
-		       (unsigned long long)data_sinfo->bytes_used,
-		       (unsigned long long)data_sinfo->bytes_reserved,
-		       (unsigned long long)data_sinfo->bytes_pinned,
-		       (unsigned long long)data_sinfo->bytes_readonly,
-		       (unsigned long long)data_sinfo->bytes_may_use,
-		       (unsigned long long)data_sinfo->total_bytes);
-#endif
 		return -ENOSPC;
 	}
 	data_sinfo->bytes_may_use += bytes;
@@ -3589,7 +3478,7 @@ again:
 		goto out;
 
 	ret = -ENOSPC;
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans))
 		goto out;
 	ret = btrfs_commit_transaction(trans, root);
@@ -3651,8 +3540,8 @@ static void block_rsv_add_bytes(struct btrfs_block_rsv *block_rsv,
 	spin_unlock(&block_rsv->lock);
 }
 
-void block_rsv_release_bytes(struct btrfs_block_rsv *block_rsv,
-			     struct btrfs_block_rsv *dest, u64 num_bytes)
+static void block_rsv_release_bytes(struct btrfs_block_rsv *block_rsv,
+				    struct btrfs_block_rsv *dest, u64 num_bytes)
 {
 	struct btrfs_space_info *space_info = block_rsv->space_info;
 
@@ -3816,7 +3705,7 @@ int btrfs_block_rsv_check(struct btrfs_trans_handle *trans,
 		if (trans)
 			return -EAGAIN;
 
-		trans = btrfs_join_transaction(root, 1);
+		trans = btrfs_join_transaction(root);
 		BUG_ON(IS_ERR(trans));
 		ret = btrfs_commit_transaction(trans, root);
 		return 0;
@@ -3855,23 +3744,7 @@ static u64 calc_global_metadata_size(struct btrfs_fs_info *fs_info)
 	u64 meta_used;
 	u64 data_used;
 	int csum_size = btrfs_super_csum_size(&fs_info->super_copy);
-#if 0
-	/*
-	 * per tree used space accounting can be inaccuracy, so we
-	 * can't rely on it.
-	 */
-	spin_lock(&fs_info->extent_root->accounting_lock);
-	num_bytes = btrfs_root_used(&fs_info->extent_root->root_item);
-	spin_unlock(&fs_info->extent_root->accounting_lock);
 
-	spin_lock(&fs_info->csum_root->accounting_lock);
-	num_bytes += btrfs_root_used(&fs_info->csum_root->root_item);
-	spin_unlock(&fs_info->csum_root->accounting_lock);
-
-	spin_lock(&fs_info->tree_root->accounting_lock);
-	num_bytes += btrfs_root_used(&fs_info->tree_root->root_item);
-	spin_unlock(&fs_info->tree_root->accounting_lock);
-#endif
 	sinfo = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_DATA);
 	spin_lock(&sinfo->lock);
 	data_used = sinfo->bytes_used;
@@ -3924,10 +3797,7 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 		block_rsv->reserved = block_rsv->size;
 		block_rsv->full = 1;
 	}
-#if 0
-	printk(KERN_INFO"global block rsv size %llu reserved %llu\n",
-		block_rsv->size, block_rsv->reserved);
-#endif
+
 	spin_unlock(&sinfo->lock);
 	spin_unlock(&block_rsv->lock);
 }
@@ -3973,10 +3843,35 @@ static void release_global_block_rsv(struct btrfs_fs_info *fs_info)
 	WARN_ON(fs_info->chunk_block_rsv.reserved > 0);
 }
 
-static u64 calc_trans_metadata_size(struct btrfs_root *root, int num_items)
+int btrfs_truncate_reserve_metadata(struct btrfs_trans_handle *trans,
+				    struct btrfs_root *root,
+				    struct btrfs_block_rsv *rsv)
 {
-	return (root->leafsize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) *
-		3 * num_items;
+	struct btrfs_block_rsv *trans_rsv = &root->fs_info->trans_block_rsv;
+	u64 num_bytes;
+	int ret;
+
+	/*
+	 * Truncate should be freeing data, but give us 2 items just in case it
+	 * needs to use some space.  We may want to be smarter about this in the
+	 * future.
+	 */
+	num_bytes = btrfs_calc_trans_metadata_size(root, 2);
+
+	/* We already have enough bytes, just return */
+	if (rsv->reserved >= num_bytes)
+		return 0;
+
+	num_bytes -= rsv->reserved;
+
+	/*
+	 * You should have reserved enough space before hand to do this, so this
+	 * should not fail.
+	 */
+	ret = block_rsv_migrate_bytes(trans_rsv, rsv, num_bytes);
+	BUG_ON(ret);
+
+	return 0;
 }
 
 int btrfs_trans_reserve_metadata(struct btrfs_trans_handle *trans,
@@ -3989,7 +3884,7 @@ int btrfs_trans_reserve_metadata(struct btrfs_trans_handle *trans,
 	if (num_items == 0 || root->fs_info->chunk_root == root)
 		return 0;
 
-	num_bytes = calc_trans_metadata_size(root, num_items);
+	num_bytes = btrfs_calc_trans_metadata_size(root, num_items);
 	ret = btrfs_block_rsv_add(trans, root, &root->fs_info->trans_block_rsv,
 				  num_bytes);
 	if (!ret) {
@@ -4019,23 +3914,18 @@ int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
 	struct btrfs_block_rsv *dst_rsv = root->orphan_block_rsv;
 
 	/*
-	 * one for deleting orphan item, one for updating inode and
-	 * two for calling btrfs_truncate_inode_items.
-	 *
-	 * btrfs_truncate_inode_items is a delete operation, it frees
-	 * more space than it uses in most cases. So two units of
-	 * metadata space should be enough for calling it many times.
-	 * If all of the metadata space is used, we can commit
-	 * transaction and use space it freed.
+	 * We need to hold space in order to delete our orphan item once we've
+	 * added it, so this takes the reservation so we can release it later
+	 * when we are truly done with the orphan item.
 	 */
-	u64 num_bytes = calc_trans_metadata_size(root, 4);
+	u64 num_bytes = btrfs_calc_trans_metadata_size(root, 1);
 	return block_rsv_migrate_bytes(src_rsv, dst_rsv, num_bytes);
 }
 
 void btrfs_orphan_release_metadata(struct inode *inode)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	u64 num_bytes = calc_trans_metadata_size(root, 4);
+	u64 num_bytes = btrfs_calc_trans_metadata_size(root, 1);
 	btrfs_block_rsv_release(root, root->orphan_block_rsv, num_bytes);
 }
 
@@ -4049,7 +3939,7 @@ int btrfs_snap_reserve_metadata(struct btrfs_trans_handle *trans,
 	 * two for root back/forward refs, two for directory entries
 	 * and one for root of the snapshot.
 	 */
-	u64 num_bytes = calc_trans_metadata_size(root, 5);
+	u64 num_bytes = btrfs_calc_trans_metadata_size(root, 5);
 	dst_rsv->space_info = src_rsv->space_info;
 	return block_rsv_migrate_bytes(src_rsv, dst_rsv, num_bytes);
 }
@@ -4078,7 +3968,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 
 	if (nr_extents > reserved_extents) {
 		nr_extents -= reserved_extents;
-		to_reserve = calc_trans_metadata_size(root, nr_extents);
+		to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents);
 	} else {
 		nr_extents = 0;
 		to_reserve = 0;
@@ -4132,7 +4022,7 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
 
 	to_free = calc_csum_metadata_size(inode, num_bytes);
 	if (nr_extents > 0)
-		to_free += calc_trans_metadata_size(root, nr_extents);
+		to_free += btrfs_calc_trans_metadata_size(root, nr_extents);
 
 	btrfs_block_rsv_release(root, &root->fs_info->delalloc_block_rsv,
 				to_free);
@@ -4541,7 +4431,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 						    NULL, refs_to_drop,
 						    is_data);
 			BUG_ON(ret);
-			btrfs_release_path(extent_root, path);
+			btrfs_release_path(path);
 			path->leave_spinning = 1;
 
 			key.objectid = bytenr;
@@ -4580,7 +4470,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 					     owner_objectid, 0);
 		BUG_ON(ret < 0);
 
-		btrfs_release_path(extent_root, path);
+		btrfs_release_path(path);
 		path->leave_spinning = 1;
 
 		key.objectid = bytenr;
@@ -4650,7 +4540,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 		ret = btrfs_del_items(trans, extent_root, path, path->slots[0],
 				      num_to_del);
 		BUG_ON(ret);
-		btrfs_release_path(extent_root, path);
+		btrfs_release_path(path);
 
 		if (is_data) {
 			ret = btrfs_del_csums(trans, root, bytenr, num_bytes);
@@ -4893,7 +4783,7 @@ wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
 		return 0;
 
 	wait_event(caching_ctl->wait, block_group_cache_done(cache) ||
-		   (cache->free_space >= num_bytes));
+		   (cache->free_space_ctl->free_space >= num_bytes));
 
 	put_caching_control(caching_ctl);
 	return 0;
@@ -4952,7 +4842,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 				     u64 num_bytes, u64 empty_size,
 				     u64 search_start, u64 search_end,
 				     u64 hint_byte, struct btrfs_key *ins,
-				     int data)
+				     u64 data)
 {
 	int ret = 0;
 	struct btrfs_root *root = orig_root->fs_info->extent_root;
@@ -4979,7 +4869,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 
 	space_info = __find_space_info(root->fs_info, data);
 	if (!space_info) {
-		printk(KERN_ERR "No space info for %d\n", data);
+		printk(KERN_ERR "No space info for %llu\n", data);
 		return -ENOSPC;
 	}
 
@@ -5129,6 +5019,15 @@ have_block_group:
 		if (unlikely(block_group->ro))
 			goto loop;
 
+		spin_lock(&block_group->free_space_ctl->tree_lock);
+		if (cached &&
+		    block_group->free_space_ctl->free_space <
+		    num_bytes + empty_size) {
+			spin_unlock(&block_group->free_space_ctl->tree_lock);
+			goto loop;
+		}
+		spin_unlock(&block_group->free_space_ctl->tree_lock);
+
 		/*
 		 * Ok we want to try and use the cluster allocator, so lets look
 		 * there, unless we are on LOOP_NO_EMPTY_SIZE, since we will
@@ -5292,6 +5191,7 @@ checks:
 			btrfs_add_free_space(block_group, offset,
 					     search_start - offset);
 		BUG_ON(offset > search_start);
+		btrfs_put_block_group(block_group);
 		break;
 loop:
 		failed_cluster_refill = false;
@@ -5314,9 +5214,7 @@ loop:
 	 * LOOP_NO_EMPTY_SIZE, set empty_size and empty_cluster to 0 and try
 	 *			again
 	 */
-	if (!ins->objectid && loop < LOOP_NO_EMPTY_SIZE &&
-	    (found_uncached_bg || empty_size || empty_cluster ||
-	     allowed_chunk_alloc)) {
+	if (!ins->objectid && loop < LOOP_NO_EMPTY_SIZE) {
 		index = 0;
 		if (loop == LOOP_FIND_IDEAL && found_uncached_bg) {
 			found_uncached_bg = false;
@@ -5356,42 +5254,39 @@ loop:
 			goto search;
 		}
 
-		if (loop < LOOP_CACHING_WAIT) {
-			loop++;
-			goto search;
-		}
+		loop++;
 
 		if (loop == LOOP_ALLOC_CHUNK) {
-			empty_size = 0;
-			empty_cluster = 0;
-		}
+		       if (allowed_chunk_alloc) {
+				ret = do_chunk_alloc(trans, root, num_bytes +
+						     2 * 1024 * 1024, data,
+						     CHUNK_ALLOC_LIMITED);
+				allowed_chunk_alloc = 0;
+				if (ret == 1)
+					done_chunk_alloc = 1;
+			} else if (!done_chunk_alloc &&
+				   space_info->force_alloc ==
+				   CHUNK_ALLOC_NO_FORCE) {
+				space_info->force_alloc = CHUNK_ALLOC_LIMITED;
+			}
 
-		if (allowed_chunk_alloc) {
-			ret = do_chunk_alloc(trans, root, num_bytes +
-					     2 * 1024 * 1024, data,
-					     CHUNK_ALLOC_LIMITED);
-			allowed_chunk_alloc = 0;
-			done_chunk_alloc = 1;
-		} else if (!done_chunk_alloc &&
-			   space_info->force_alloc == CHUNK_ALLOC_NO_FORCE) {
-			space_info->force_alloc = CHUNK_ALLOC_LIMITED;
+		       /*
+			* We didn't allocate a chunk, go ahead and drop the
+			* empty size and loop again.
+			*/
+		       if (!done_chunk_alloc)
+			       loop = LOOP_NO_EMPTY_SIZE;
 		}
 
-		if (loop < LOOP_NO_EMPTY_SIZE) {
-			loop++;
-			goto search;
+		if (loop == LOOP_NO_EMPTY_SIZE) {
+			empty_size = 0;
+			empty_cluster = 0;
 		}
-		ret = -ENOSPC;
+
+		goto search;
 	} else if (!ins->objectid) {
 		ret = -ENOSPC;
-	}
-
-	/* we found what we needed */
-	if (ins->objectid) {
-		if (!(data & BTRFS_BLOCK_GROUP_DATA))
-			trans->block_group = block_group->key.objectid;
-
-		btrfs_put_block_group(block_group);
+	} else if (ins->objectid) {
 		ret = 0;
 	}
 
@@ -6480,7 +6375,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 				trans->block_rsv = block_rsv;
 		}
 	}
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	BUG_ON(err);
 
 	ret = btrfs_del_root(trans, tree_root, &root->root_key);
@@ -6584,1514 +6479,6 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-#if 0
-static unsigned long calc_ra(unsigned long start, unsigned long last,
-			     unsigned long nr)
-{
-	return min(last, start + nr - 1);
-}
-
-static noinline int relocate_inode_pages(struct inode *inode, u64 start,
-					 u64 len)
-{
-	u64 page_start;
-	u64 page_end;
-	unsigned long first_index;
-	unsigned long last_index;
-	unsigned long i;
-	struct page *page;
-	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
-	struct file_ra_state *ra;
-	struct btrfs_ordered_extent *ordered;
-	unsigned int total_read = 0;
-	unsigned int total_dirty = 0;
-	int ret = 0;
-
-	ra = kzalloc(sizeof(*ra), GFP_NOFS);
-	if (!ra)
-		return -ENOMEM;
-
-	mutex_lock(&inode->i_mutex);
-	first_index = start >> PAGE_CACHE_SHIFT;
-	last_index = (start + len - 1) >> PAGE_CACHE_SHIFT;
-
-	/* make sure the dirty trick played by the caller work */
-	ret = invalidate_inode_pages2_range(inode->i_mapping,
-					    first_index, last_index);
-	if (ret)
-		goto out_unlock;
-
-	file_ra_state_init(ra, inode->i_mapping);
-
-	for (i = first_index ; i <= last_index; i++) {
-		if (total_read % ra->ra_pages == 0) {
-			btrfs_force_ra(inode->i_mapping, ra, NULL, i,
-				       calc_ra(i, last_index, ra->ra_pages));
-		}
-		total_read++;
-again:
-		if (((u64)i << PAGE_CACHE_SHIFT) > i_size_read(inode))
-			BUG_ON(1);
-		page = grab_cache_page(inode->i_mapping, i);
-		if (!page) {
-			ret = -ENOMEM;
-			goto out_unlock;
-		}
-		if (!PageUptodate(page)) {
-			btrfs_readpage(NULL, page);
-			lock_page(page);
-			if (!PageUptodate(page)) {
-				unlock_page(page);
-				page_cache_release(page);
-				ret = -EIO;
-				goto out_unlock;
-			}
-		}
-		wait_on_page_writeback(page);
-
-		page_start = (u64)page->index << PAGE_CACHE_SHIFT;
-		page_end = page_start + PAGE_CACHE_SIZE - 1;
-		lock_extent(io_tree, page_start, page_end, GFP_NOFS);
-
-		ordered = btrfs_lookup_ordered_extent(inode, page_start);
-		if (ordered) {
-			unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
-			unlock_page(page);
-			page_cache_release(page);
-			btrfs_start_ordered_extent(inode, ordered, 1);
-			btrfs_put_ordered_extent(ordered);
-			goto again;
-		}
-		set_page_extent_mapped(page);
-
-		if (i == first_index)
-			set_extent_bits(io_tree, page_start, page_end,
-					EXTENT_BOUNDARY, GFP_NOFS);
-		btrfs_set_extent_delalloc(inode, page_start, page_end);
-
-		set_page_dirty(page);
-		total_dirty++;
-
-		unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
-		unlock_page(page);
-		page_cache_release(page);
-	}
-
-out_unlock:
-	kfree(ra);
-	mutex_unlock(&inode->i_mutex);
-	balance_dirty_pages_ratelimited_nr(inode->i_mapping, total_dirty);
-	return ret;
-}
-
-static noinline int relocate_data_extent(struct inode *reloc_inode,
-					 struct btrfs_key *extent_key,
-					 u64 offset)
-{
-	struct btrfs_root *root = BTRFS_I(reloc_inode)->root;
-	struct extent_map_tree *em_tree = &BTRFS_I(reloc_inode)->extent_tree;
-	struct extent_map *em;
-	u64 start = extent_key->objectid - offset;
-	u64 end = start + extent_key->offset - 1;
-
-	em = alloc_extent_map(GFP_NOFS);
-	BUG_ON(!em);
-
-	em->start = start;
-	em->len = extent_key->offset;
-	em->block_len = extent_key->offset;
-	em->block_start = extent_key->objectid;
-	em->bdev = root->fs_info->fs_devices->latest_bdev;
-	set_bit(EXTENT_FLAG_PINNED, &em->flags);
-
-	/* setup extent map to cheat btrfs_readpage */
-	lock_extent(&BTRFS_I(reloc_inode)->io_tree, start, end, GFP_NOFS);
-	while (1) {
-		int ret;
-		write_lock(&em_tree->lock);
-		ret = add_extent_mapping(em_tree, em);
-		write_unlock(&em_tree->lock);
-		if (ret != -EEXIST) {
-			free_extent_map(em);
-			break;
-		}
-		btrfs_drop_extent_cache(reloc_inode, start, end, 0);
-	}
-	unlock_extent(&BTRFS_I(reloc_inode)->io_tree, start, end, GFP_NOFS);
-
-	return relocate_inode_pages(reloc_inode, start, extent_key->offset);
-}
-
-struct btrfs_ref_path {
-	u64 extent_start;
-	u64 nodes[BTRFS_MAX_LEVEL];
-	u64 root_objectid;
-	u64 root_generation;
-	u64 owner_objectid;
-	u32 num_refs;
-	int lowest_level;
-	int current_level;
-	int shared_level;
-
-	struct btrfs_key node_keys[BTRFS_MAX_LEVEL];
-	u64 new_nodes[BTRFS_MAX_LEVEL];
-};
-
-struct disk_extent {
-	u64 ram_bytes;
-	u64 disk_bytenr;
-	u64 disk_num_bytes;
-	u64 offset;
-	u64 num_bytes;
-	u8 compression;
-	u8 encryption;
-	u16 other_encoding;
-};
-
-static int is_cowonly_root(u64 root_objectid)
-{
-	if (root_objectid == BTRFS_ROOT_TREE_OBJECTID ||
-	    root_objectid == BTRFS_EXTENT_TREE_OBJECTID ||
-	    root_objectid == BTRFS_CHUNK_TREE_OBJECTID ||
-	    root_objectid == BTRFS_DEV_TREE_OBJECTID ||
-	    root_objectid == BTRFS_TREE_LOG_OBJECTID ||
-	    root_objectid == BTRFS_CSUM_TREE_OBJECTID)
-		return 1;
-	return 0;
-}
-
-static noinline int __next_ref_path(struct btrfs_trans_handle *trans,
-				    struct btrfs_root *extent_root,
-				    struct btrfs_ref_path *ref_path,
-				    int first_time)
-{
-	struct extent_buffer *leaf;
-	struct btrfs_path *path;
-	struct btrfs_extent_ref *ref;
-	struct btrfs_key key;
-	struct btrfs_key found_key;
-	u64 bytenr;
-	u32 nritems;
-	int level;
-	int ret = 1;
-
-	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
-
-	if (first_time) {
-		ref_path->lowest_level = -1;
-		ref_path->current_level = -1;
-		ref_path->shared_level = -1;
-		goto walk_up;
-	}
-walk_down:
-	level = ref_path->current_level - 1;
-	while (level >= -1) {
-		u64 parent;
-		if (level < ref_path->lowest_level)
-			break;
-
-		if (level >= 0)
-			bytenr = ref_path->nodes[level];
-		else
-			bytenr = ref_path->extent_start;
-		BUG_ON(bytenr == 0);
-
-		parent = ref_path->nodes[level + 1];
-		ref_path->nodes[level + 1] = 0;
-		ref_path->current_level = level;
-		BUG_ON(parent == 0);
-
-		key.objectid = bytenr;
-		key.offset = parent + 1;
-		key.type = BTRFS_EXTENT_REF_KEY;
-
-		ret = btrfs_search_slot(trans, extent_root, &key, path, 0, 0);
-		if (ret < 0)
-			goto out;
-		BUG_ON(ret == 0);
-
-		leaf = path->nodes[0];
-		nritems = btrfs_header_nritems(leaf);
-		if (path->slots[0] >= nritems) {
-			ret = btrfs_next_leaf(extent_root, path);
-			if (ret < 0)
-				goto out;
-			if (ret > 0)
-				goto next;
-			leaf = path->nodes[0];
-		}
-
-		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-		if (found_key.objectid == bytenr &&
-		    found_key.type == BTRFS_EXTENT_REF_KEY) {
-			if (level < ref_path->shared_level)
-				ref_path->shared_level = level;
-			goto found;
-		}
-next:
-		level--;
-		btrfs_release_path(extent_root, path);
-		cond_resched();
-	}
-	/* reached lowest level */
-	ret = 1;
-	goto out;
-walk_up:
-	level = ref_path->current_level;
-	while (level < BTRFS_MAX_LEVEL - 1) {
-		u64 ref_objectid;
-
-		if (level >= 0)
-			bytenr = ref_path->nodes[level];
-		else
-			bytenr = ref_path->extent_start;
-
-		BUG_ON(bytenr == 0);
-
-		key.objectid = bytenr;
-		key.offset = 0;
-		key.type = BTRFS_EXTENT_REF_KEY;
-
-		ret = btrfs_search_slot(trans, extent_root, &key, path, 0, 0);
-		if (ret < 0)
-			goto out;
-
-		leaf = path->nodes[0];
-		nritems = btrfs_header_nritems(leaf);
-		if (path->slots[0] >= nritems) {
-			ret = btrfs_next_leaf(extent_root, path);
-			if (ret < 0)
-				goto out;
-			if (ret > 0) {
-				/* the extent was freed by someone */
-				if (ref_path->lowest_level == level)
-					goto out;
-				btrfs_release_path(extent_root, path);
-				goto walk_down;
-			}
-			leaf = path->nodes[0];
-		}
-
-		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-		if (found_key.objectid != bytenr ||
-				found_key.type != BTRFS_EXTENT_REF_KEY) {
-			/* the extent was freed by someone */
-			if (ref_path->lowest_level == level) {
-				ret = 1;
-				goto out;
-			}
-			btrfs_release_path(extent_root, path);
-			goto walk_down;
-		}
-found:
-		ref = btrfs_item_ptr(leaf, path->slots[0],
-				struct btrfs_extent_ref);
-		ref_objectid = btrfs_ref_objectid(leaf, ref);
-		if (ref_objectid < BTRFS_FIRST_FREE_OBJECTID) {
-			if (first_time) {
-				level = (int)ref_objectid;
-				BUG_ON(level >= BTRFS_MAX_LEVEL);
-				ref_path->lowest_level = level;
-				ref_path->current_level = level;
-				ref_path->nodes[level] = bytenr;
-			} else {
-				WARN_ON(ref_objectid != level);
-			}
-		} else {
-			WARN_ON(level != -1);
-		}
-		first_time = 0;
-
-		if (ref_path->lowest_level == level) {
-			ref_path->owner_objectid = ref_objectid;
-			ref_path->num_refs = btrfs_ref_num_refs(leaf, ref);
-		}
-
-		/*
-		 * the block is tree root or the block isn't in reference
-		 * counted tree.
-		 */
-		if (found_key.objectid == found_key.offset ||
-		    is_cowonly_root(btrfs_ref_root(leaf, ref))) {
-			ref_path->root_objectid = btrfs_ref_root(leaf, ref);
-			ref_path->root_generation =
-				btrfs_ref_generation(leaf, ref);
-			if (level < 0) {
-				/* special reference from the tree log */
-				ref_path->nodes[0] = found_key.offset;
-				ref_path->current_level = 0;
-			}
-			ret = 0;
-			goto out;
-		}
-
-		level++;
-		BUG_ON(ref_path->nodes[level] != 0);
-		ref_path->nodes[level] = found_key.offset;
-		ref_path->current_level = level;
-
-		/*
-		 * the reference was created in the running transaction,
-		 * no need to continue walking up.
-		 */
-		if (btrfs_ref_generation(leaf, ref) == trans->transid) {
-			ref_path->root_objectid = btrfs_ref_root(leaf, ref);
-			ref_path->root_generation =
-				btrfs_ref_generation(leaf, ref);
-			ret = 0;
-			goto out;
-		}
-
-		btrfs_release_path(extent_root, path);
-		cond_resched();
-	}
-	/* reached max tree level, but no tree root found. */
-	BUG();
-out:
-	btrfs_free_path(path);
-	return ret;
-}
-
-static int btrfs_first_ref_path(struct btrfs_trans_handle *trans,
-				struct btrfs_root *extent_root,
-				struct btrfs_ref_path *ref_path,
-				u64 extent_start)
-{
-	memset(ref_path, 0, sizeof(*ref_path));
-	ref_path->extent_start = extent_start;
-
-	return __next_ref_path(trans, extent_root, ref_path, 1);
-}
-
-static int btrfs_next_ref_path(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *extent_root,
-			       struct btrfs_ref_path *ref_path)
-{
-	return __next_ref_path(trans, extent_root, ref_path, 0);
-}
-
-static noinline int get_new_locations(struct inode *reloc_inode,
-				      struct btrfs_key *extent_key,
-				      u64 offset, int no_fragment,
-				      struct disk_extent **extents,
-				      int *nr_extents)
-{
-	struct btrfs_root *root = BTRFS_I(reloc_inode)->root;
-	struct btrfs_path *path;
-	struct btrfs_file_extent_item *fi;
-	struct extent_buffer *leaf;
-	struct disk_extent *exts = *extents;
-	struct btrfs_key found_key;
-	u64 cur_pos;
-	u64 last_byte;
-	u32 nritems;
-	int nr = 0;
-	int max = *nr_extents;
-	int ret;
-
-	WARN_ON(!no_fragment && *extents);
-	if (!exts) {
-		max = 1;
-		exts = kmalloc(sizeof(*exts) * max, GFP_NOFS);
-		if (!exts)
-			return -ENOMEM;
-	}
-
-	path = btrfs_alloc_path();
-	if (!path) {
-		if (exts != *extents)
-			kfree(exts);
-		return -ENOMEM;
-	}
-
-	cur_pos = extent_key->objectid - offset;
-	last_byte = extent_key->objectid + extent_key->offset;
-	ret = btrfs_lookup_file_extent(NULL, root, path, reloc_inode->i_ino,
-				       cur_pos, 0);
-	if (ret < 0)
-		goto out;
-	if (ret > 0) {
-		ret = -ENOENT;
-		goto out;
-	}
-
-	while (1) {
-		leaf = path->nodes[0];
-		nritems = btrfs_header_nritems(leaf);
-		if (path->slots[0] >= nritems) {
-			ret = btrfs_next_leaf(root, path);
-			if (ret < 0)
-				goto out;
-			if (ret > 0)
-				break;
-			leaf = path->nodes[0];
-		}
-
-		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-		if (found_key.offset != cur_pos ||
-		    found_key.type != BTRFS_EXTENT_DATA_KEY ||
-		    found_key.objectid != reloc_inode->i_ino)
-			break;
-
-		fi = btrfs_item_ptr(leaf, path->slots[0],
-				    struct btrfs_file_extent_item);
-		if (btrfs_file_extent_type(leaf, fi) !=
-		    BTRFS_FILE_EXTENT_REG ||
-		    btrfs_file_extent_disk_bytenr(leaf, fi) == 0)
-			break;
-
-		if (nr == max) {
-			struct disk_extent *old = exts;
-			max *= 2;
-			exts = kzalloc(sizeof(*exts) * max, GFP_NOFS);
-			if (!exts) {
-				ret = -ENOMEM;
-				goto out;
-			}
-			memcpy(exts, old, sizeof(*exts) * nr);
-			if (old != *extents)
-				kfree(old);
-		}
-
-		exts[nr].disk_bytenr =
-			btrfs_file_extent_disk_bytenr(leaf, fi);
-		exts[nr].disk_num_bytes =
-			btrfs_file_extent_disk_num_bytes(leaf, fi);
-		exts[nr].offset = btrfs_file_extent_offset(leaf, fi);
-		exts[nr].num_bytes = btrfs_file_extent_num_bytes(leaf, fi);
-		exts[nr].ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
-		exts[nr].compression = btrfs_file_extent_compression(leaf, fi);
-		exts[nr].encryption = btrfs_file_extent_encryption(leaf, fi);
-		exts[nr].other_encoding = btrfs_file_extent_other_encoding(leaf,
-									   fi);
-		BUG_ON(exts[nr].offset > 0);
-		BUG_ON(exts[nr].compression || exts[nr].encryption);
-		BUG_ON(exts[nr].num_bytes != exts[nr].disk_num_bytes);
-
-		cur_pos += exts[nr].num_bytes;
-		nr++;
-
-		if (cur_pos + offset >= last_byte)
-			break;
-
-		if (no_fragment) {
-			ret = 1;
-			goto out;
-		}
-		path->slots[0]++;
-	}
-
-	BUG_ON(cur_pos + offset > last_byte);
-	if (cur_pos + offset < last_byte) {
-		ret = -ENOENT;
-		goto out;
-	}
-	ret = 0;
-out:
-	btrfs_free_path(path);
-	if (ret) {
-		if (exts != *extents)
-			kfree(exts);
-	} else {
-		*extents = exts;
-		*nr_extents = nr;
-	}
-	return ret;
-}
-
-static noinline int replace_one_extent(struct btrfs_trans_handle *trans,
-					struct btrfs_root *root,
-					struct btrfs_path *path,
-					struct btrfs_key *extent_key,
-					struct btrfs_key *leaf_key,
-					struct btrfs_ref_path *ref_path,
-					struct disk_extent *new_extents,
-					int nr_extents)
-{
-	struct extent_buffer *leaf;
-	struct btrfs_file_extent_item *fi;
-	struct inode *inode = NULL;
-	struct btrfs_key key;
-	u64 lock_start = 0;
-	u64 lock_end = 0;
-	u64 num_bytes;
-	u64 ext_offset;
-	u64 search_end = (u64)-1;
-	u32 nritems;
-	int nr_scaned = 0;
-	int extent_locked = 0;
-	int extent_type;
-	int ret;
-
-	memcpy(&key, leaf_key, sizeof(key));
-	if (ref_path->owner_objectid != BTRFS_MULTIPLE_OBJECTIDS) {
-		if (key.objectid < ref_path->owner_objectid ||
-		    (key.objectid == ref_path->owner_objectid &&
-		     key.type < BTRFS_EXTENT_DATA_KEY)) {
-			key.objectid = ref_path->owner_objectid;
-			key.type = BTRFS_EXTENT_DATA_KEY;
-			key.offset = 0;
-		}
-	}
-
-	while (1) {
-		ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
-		if (ret < 0)
-			goto out;
-
-		leaf = path->nodes[0];
-		nritems = btrfs_header_nritems(leaf);
-next:
-		if (extent_locked && ret > 0) {
-			/*
-			 * the file extent item was modified by someone
-			 * before the extent got locked.
-			 */
-			unlock_extent(&BTRFS_I(inode)->io_tree, lock_start,
-				      lock_end, GFP_NOFS);
-			extent_locked = 0;
-		}
-
-		if (path->slots[0] >= nritems) {
-			if (++nr_scaned > 2)
-				break;
-
-			BUG_ON(extent_locked);
-			ret = btrfs_next_leaf(root, path);
-			if (ret < 0)
-				goto out;
-			if (ret > 0)
-				break;
-			leaf = path->nodes[0];
-			nritems = btrfs_header_nritems(leaf);
-		}
-
-		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-
-		if (ref_path->owner_objectid != BTRFS_MULTIPLE_OBJECTIDS) {
-			if ((key.objectid > ref_path->owner_objectid) ||
-			    (key.objectid == ref_path->owner_objectid &&
-			     key.type > BTRFS_EXTENT_DATA_KEY) ||
-			    key.offset >= search_end)
-				break;
-		}
-
-		if (inode && key.objectid != inode->i_ino) {
-			BUG_ON(extent_locked);
-			btrfs_release_path(root, path);
-			mutex_unlock(&inode->i_mutex);
-			iput(inode);
-			inode = NULL;
-			continue;
-		}
-
-		if (key.type != BTRFS_EXTENT_DATA_KEY) {
-			path->slots[0]++;
-			ret = 1;
-			goto next;
-		}
-		fi = btrfs_item_ptr(leaf, path->slots[0],
-				    struct btrfs_file_extent_item);
-		extent_type = btrfs_file_extent_type(leaf, fi);
-		if ((extent_type != BTRFS_FILE_EXTENT_REG &&
-		     extent_type != BTRFS_FILE_EXTENT_PREALLOC) ||
-		    (btrfs_file_extent_disk_bytenr(leaf, fi) !=
-		     extent_key->objectid)) {
-			path->slots[0]++;
-			ret = 1;
-			goto next;
-		}
-
-		num_bytes = btrfs_file_extent_num_bytes(leaf, fi);
-		ext_offset = btrfs_file_extent_offset(leaf, fi);
-
-		if (search_end == (u64)-1) {
-			search_end = key.offset - ext_offset +
-				btrfs_file_extent_ram_bytes(leaf, fi);
-		}
-
-		if (!extent_locked) {
-			lock_start = key.offset;
-			lock_end = lock_start + num_bytes - 1;
-		} else {
-			if (lock_start > key.offset ||
-			    lock_end + 1 < key.offset + num_bytes) {
-				unlock_extent(&BTRFS_I(inode)->io_tree,
-					      lock_start, lock_end, GFP_NOFS);
-				extent_locked = 0;
-			}
-		}
-
-		if (!inode) {
-			btrfs_release_path(root, path);
-
-			inode = btrfs_iget_locked(root->fs_info->sb,
-						  key.objectid, root);
-			if (inode->i_state & I_NEW) {
-				BTRFS_I(inode)->root = root;
-				BTRFS_I(inode)->location.objectid =
-					key.objectid;
-				BTRFS_I(inode)->location.type =
-					BTRFS_INODE_ITEM_KEY;
-				BTRFS_I(inode)->location.offset = 0;
-				btrfs_read_locked_inode(inode);
-				unlock_new_inode(inode);
-			}
-			/*
-			 * some code call btrfs_commit_transaction while
-			 * holding the i_mutex, so we can't use mutex_lock
-			 * here.
-			 */
-			if (is_bad_inode(inode) ||
-			    !mutex_trylock(&inode->i_mutex)) {
-				iput(inode);
-				inode = NULL;
-				key.offset = (u64)-1;
-				goto skip;
-			}
-		}
-
-		if (!extent_locked) {
-			struct btrfs_ordered_extent *ordered;
-
-			btrfs_release_path(root, path);
-
-			lock_extent(&BTRFS_I(inode)->io_tree, lock_start,
-				    lock_end, GFP_NOFS);
-			ordered = btrfs_lookup_first_ordered_extent(inode,
-								    lock_end);
-			if (ordered &&
-			    ordered->file_offset <= lock_end &&
-			    ordered->file_offset + ordered->len > lock_start) {
-				unlock_extent(&BTRFS_I(inode)->io_tree,
-					      lock_start, lock_end, GFP_NOFS);
-				btrfs_start_ordered_extent(inode, ordered, 1);
-				btrfs_put_ordered_extent(ordered);
-				key.offset += num_bytes;
-				goto skip;
-			}
-			if (ordered)
-				btrfs_put_ordered_extent(ordered);
-
-			extent_locked = 1;
-			continue;
-		}
-
-		if (nr_extents == 1) {
-			/* update extent pointer in place */
-			btrfs_set_file_extent_disk_bytenr(leaf, fi,
-						new_extents[0].disk_bytenr);
-			btrfs_set_file_extent_disk_num_bytes(leaf, fi,
-						new_extents[0].disk_num_bytes);
-			btrfs_mark_buffer_dirty(leaf);
-
-			btrfs_drop_extent_cache(inode, key.offset,
-						key.offset + num_bytes - 1, 0);
-
-			ret = btrfs_inc_extent_ref(trans, root,
-						new_extents[0].disk_bytenr,
-						new_extents[0].disk_num_bytes,
-						leaf->start,
-						root->root_key.objectid,
-						trans->transid,
-						key.objectid);
-			BUG_ON(ret);
-
-			ret = btrfs_free_extent(trans, root,
-						extent_key->objectid,
-						extent_key->offset,
-						leaf->start,
-						btrfs_header_owner(leaf),
-						btrfs_header_generation(leaf),
-						key.objectid, 0);
-			BUG_ON(ret);
-
-			btrfs_release_path(root, path);
-			key.offset += num_bytes;
-		} else {
-			BUG_ON(1);
-#if 0
-			u64 alloc_hint;
-			u64 extent_len;
-			int i;
-			/*
-			 * drop old extent pointer at first, then insert the
-			 * new pointers one bye one
-			 */
-			btrfs_release_path(root, path);
-			ret = btrfs_drop_extents(trans, root, inode, key.offset,
-						 key.offset + num_bytes,
-						 key.offset, &alloc_hint);
-			BUG_ON(ret);
-
-			for (i = 0; i < nr_extents; i++) {
-				if (ext_offset >= new_extents[i].num_bytes) {
-					ext_offset -= new_extents[i].num_bytes;
-					continue;
-				}
-				extent_len = min(new_extents[i].num_bytes -
-						 ext_offset, num_bytes);
-
-				ret = btrfs_insert_empty_item(trans, root,
-							      path, &key,
-							      sizeof(*fi));
-				BUG_ON(ret);
-
-				leaf = path->nodes[0];
-				fi = btrfs_item_ptr(leaf, path->slots[0],
-						struct btrfs_file_extent_item);
-				btrfs_set_file_extent_generation(leaf, fi,
-							trans->transid);
-				btrfs_set_file_extent_type(leaf, fi,
-							BTRFS_FILE_EXTENT_REG);
-				btrfs_set_file_extent_disk_bytenr(leaf, fi,
-						new_extents[i].disk_bytenr);
-				btrfs_set_file_extent_disk_num_bytes(leaf, fi,
-						new_extents[i].disk_num_bytes);
-				btrfs_set_file_extent_ram_bytes(leaf, fi,
-						new_extents[i].ram_bytes);
-
-				btrfs_set_file_extent_compression(leaf, fi,
-						new_extents[i].compression);
-				btrfs_set_file_extent_encryption(leaf, fi,
-						new_extents[i].encryption);
-				btrfs_set_file_extent_other_encoding(leaf, fi,
-						new_extents[i].other_encoding);
-
-				btrfs_set_file_extent_num_bytes(leaf, fi,
-							extent_len);
-				ext_offset += new_extents[i].offset;
-				btrfs_set_file_extent_offset(leaf, fi,
-							ext_offset);
-				btrfs_mark_buffer_dirty(leaf);
-
-				btrfs_drop_extent_cache(inode, key.offset,
-						key.offset + extent_len - 1, 0);
-
-				ret = btrfs_inc_extent_ref(trans, root,
-						new_extents[i].disk_bytenr,
-						new_extents[i].disk_num_bytes,
-						leaf->start,
-						root->root_key.objectid,
-						trans->transid, key.objectid);
-				BUG_ON(ret);
-				btrfs_release_path(root, path);
-
-				inode_add_bytes(inode, extent_len);
-
-				ext_offset = 0;
-				num_bytes -= extent_len;
-				key.offset += extent_len;
-
-				if (num_bytes == 0)
-					break;
-			}
-			BUG_ON(i >= nr_extents);
-#endif
-		}
-
-		if (extent_locked) {
-			unlock_extent(&BTRFS_I(inode)->io_tree, lock_start,
-				      lock_end, GFP_NOFS);
-			extent_locked = 0;
-		}
-skip:
-		if (ref_path->owner_objectid != BTRFS_MULTIPLE_OBJECTIDS &&
-		    key.offset >= search_end)
-			break;
-
-		cond_resched();
-	}
-	ret = 0;
-out:
-	btrfs_release_path(root, path);
-	if (inode) {
-		mutex_unlock(&inode->i_mutex);
-		if (extent_locked) {
-			unlock_extent(&BTRFS_I(inode)->io_tree, lock_start,
-				      lock_end, GFP_NOFS);
-		}
-		iput(inode);
-	}
-	return ret;
-}
-
-int btrfs_reloc_tree_cache_ref(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root,
-			       struct extent_buffer *buf, u64 orig_start)
-{
-	int level;
-	int ret;
-
-	BUG_ON(btrfs_header_generation(buf) != trans->transid);
-	BUG_ON(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID);
-
-	level = btrfs_header_level(buf);
-	if (level == 0) {
-		struct btrfs_leaf_ref *ref;
-		struct btrfs_leaf_ref *orig_ref;
-
-		orig_ref = btrfs_lookup_leaf_ref(root, orig_start);
-		if (!orig_ref)
-			return -ENOENT;
-
-		ref = btrfs_alloc_leaf_ref(root, orig_ref->nritems);
-		if (!ref) {
-			btrfs_free_leaf_ref(root, orig_ref);
-			return -ENOMEM;
-		}
-
-		ref->nritems = orig_ref->nritems;
-		memcpy(ref->extents, orig_ref->extents,
-			sizeof(ref->extents[0]) * ref->nritems);
-
-		btrfs_free_leaf_ref(root, orig_ref);
-
-		ref->root_gen = trans->transid;
-		ref->bytenr = buf->start;
-		ref->owner = btrfs_header_owner(buf);
-		ref->generation = btrfs_header_generation(buf);
-
-		ret = btrfs_add_leaf_ref(root, ref, 0);
-		WARN_ON(ret);
-		btrfs_free_leaf_ref(root, ref);
-	}
-	return 0;
-}
-
-static noinline int invalidate_extent_cache(struct btrfs_root *root,
-					struct extent_buffer *leaf,
-					struct btrfs_block_group_cache *group,
-					struct btrfs_root *target_root)
-{
-	struct btrfs_key key;
-	struct inode *inode = NULL;
-	struct btrfs_file_extent_item *fi;
-	struct extent_state *cached_state = NULL;
-	u64 num_bytes;
-	u64 skip_objectid = 0;
-	u32 nritems;
-	u32 i;
-
-	nritems = btrfs_header_nritems(leaf);
-	for (i = 0; i < nritems; i++) {
-		btrfs_item_key_to_cpu(leaf, &key, i);
-		if (key.objectid == skip_objectid ||
-		    key.type != BTRFS_EXTENT_DATA_KEY)
-			continue;
-		fi = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item);
-		if (btrfs_file_extent_type(leaf, fi) ==
-		    BTRFS_FILE_EXTENT_INLINE)
-			continue;
-		if (btrfs_file_extent_disk_bytenr(leaf, fi) == 0)
-			continue;
-		if (!inode || inode->i_ino != key.objectid) {
-			iput(inode);
-			inode = btrfs_ilookup(target_root->fs_info->sb,
-					      key.objectid, target_root, 1);
-		}
-		if (!inode) {
-			skip_objectid = key.objectid;
-			continue;
-		}
-		num_bytes = btrfs_file_extent_num_bytes(leaf, fi);
-
-		lock_extent_bits(&BTRFS_I(inode)->io_tree, key.offset,
-				 key.offset + num_bytes - 1, 0, &cached_state,
-				 GFP_NOFS);
-		btrfs_drop_extent_cache(inode, key.offset,
-					key.offset + num_bytes - 1, 1);
-		unlock_extent_cached(&BTRFS_I(inode)->io_tree, key.offset,
-				     key.offset + num_bytes - 1, &cached_state,
-				     GFP_NOFS);
-		cond_resched();
-	}
-	iput(inode);
-	return 0;
-}
-
-static noinline int replace_extents_in_leaf(struct btrfs_trans_handle *trans,
-					struct btrfs_root *root,
-					struct extent_buffer *leaf,
-					struct btrfs_block_group_cache *group,
-					struct inode *reloc_inode)
-{
-	struct btrfs_key key;
-	struct btrfs_key extent_key;
-	struct btrfs_file_extent_item *fi;
-	struct btrfs_leaf_ref *ref;
-	struct disk_extent *new_extent;
-	u64 bytenr;
-	u64 num_bytes;
-	u32 nritems;
-	u32 i;
-	int ext_index;
-	int nr_extent;
-	int ret;
-
-	new_extent = kmalloc(sizeof(*new_extent), GFP_NOFS);
-	if (!new_extent)
-		return -ENOMEM;
-
-	ref = btrfs_lookup_leaf_ref(root, leaf->start);
-	BUG_ON(!ref);
-
-	ext_index = -1;
-	nritems = btrfs_header_nritems(leaf);
-	for (i = 0; i < nritems; i++) {
-		btrfs_item_key_to_cpu(leaf, &key, i);
-		if (btrfs_key_type(&key) != BTRFS_EXTENT_DATA_KEY)
-			continue;
-		fi = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item);
-		if (btrfs_file_extent_type(leaf, fi) ==
-		    BTRFS_FILE_EXTENT_INLINE)
-			continue;
-		bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
-		num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
-		if (bytenr == 0)
-			continue;
-
-		ext_index++;
-		if (bytenr >= group->key.objectid + group->key.offset ||
-		    bytenr + num_bytes <= group->key.objectid)
-			continue;
-
-		extent_key.objectid = bytenr;
-		extent_key.offset = num_bytes;
-		extent_key.type = BTRFS_EXTENT_ITEM_KEY;
-		nr_extent = 1;
-		ret = get_new_locations(reloc_inode, &extent_key,
-					group->key.objectid, 1,
-					&new_extent, &nr_extent);
-		if (ret > 0)
-			continue;
-		BUG_ON(ret < 0);
-
-		BUG_ON(ref->extents[ext_index].bytenr != bytenr);
-		BUG_ON(ref->extents[ext_index].num_bytes != num_bytes);
-		ref->extents[ext_index].bytenr = new_extent->disk_bytenr;
-		ref->extents[ext_index].num_bytes = new_extent->disk_num_bytes;
-
-		btrfs_set_file_extent_disk_bytenr(leaf, fi,
-						new_extent->disk_bytenr);
-		btrfs_set_file_extent_disk_num_bytes(leaf, fi,
-						new_extent->disk_num_bytes);
-		btrfs_mark_buffer_dirty(leaf);
-
-		ret = btrfs_inc_extent_ref(trans, root,
-					new_extent->disk_bytenr,
-					new_extent->disk_num_bytes,
-					leaf->start,
-					root->root_key.objectid,
-					trans->transid, key.objectid);
-		BUG_ON(ret);
-
-		ret = btrfs_free_extent(trans, root,
-					bytenr, num_bytes, leaf->start,
-					btrfs_header_owner(leaf),
-					btrfs_header_generation(leaf),
-					key.objectid, 0);
-		BUG_ON(ret);
-		cond_resched();
-	}
-	kfree(new_extent);
-	BUG_ON(ext_index + 1 != ref->nritems);
-	btrfs_free_leaf_ref(root, ref);
-	return 0;
-}
-
-int btrfs_free_reloc_root(struct btrfs_trans_handle *trans,
-			  struct btrfs_root *root)
-{
-	struct btrfs_root *reloc_root;
-	int ret;
-
-	if (root->reloc_root) {
-		reloc_root = root->reloc_root;
-		root->reloc_root = NULL;
-		list_add(&reloc_root->dead_list,
-			 &root->fs_info->dead_reloc_roots);
-
-		btrfs_set_root_bytenr(&reloc_root->root_item,
-				      reloc_root->node->start);
-		btrfs_set_root_level(&root->root_item,
-				     btrfs_header_level(reloc_root->node));
-		memset(&reloc_root->root_item.drop_progress, 0,
-			sizeof(struct btrfs_disk_key));
-		reloc_root->root_item.drop_level = 0;
-
-		ret = btrfs_update_root(trans, root->fs_info->tree_root,
-					&reloc_root->root_key,
-					&reloc_root->root_item);
-		BUG_ON(ret);
-	}
-	return 0;
-}
-
-int btrfs_drop_dead_reloc_roots(struct btrfs_root *root)
-{
-	struct btrfs_trans_handle *trans;
-	struct btrfs_root *reloc_root;
-	struct btrfs_root *prev_root = NULL;
-	struct list_head dead_roots;
-	int ret;
-	unsigned long nr;
-
-	INIT_LIST_HEAD(&dead_roots);
-	list_splice_init(&root->fs_info->dead_reloc_roots, &dead_roots);
-
-	while (!list_empty(&dead_roots)) {
-		reloc_root = list_entry(dead_roots.prev,
-					struct btrfs_root, dead_list);
-		list_del_init(&reloc_root->dead_list);
-
-		BUG_ON(reloc_root->commit_root != NULL);
-		while (1) {
-			trans = btrfs_join_transaction(root, 1);
-			BUG_ON(IS_ERR(trans));
-
-			mutex_lock(&root->fs_info->drop_mutex);
-			ret = btrfs_drop_snapshot(trans, reloc_root);
-			if (ret != -EAGAIN)
-				break;
-			mutex_unlock(&root->fs_info->drop_mutex);
-
-			nr = trans->blocks_used;
-			ret = btrfs_end_transaction(trans, root);
-			BUG_ON(ret);
-			btrfs_btree_balance_dirty(root, nr);
-		}
-
-		free_extent_buffer(reloc_root->node);
-
-		ret = btrfs_del_root(trans, root->fs_info->tree_root,
-				     &reloc_root->root_key);
-		BUG_ON(ret);
-		mutex_unlock(&root->fs_info->drop_mutex);
-
-		nr = trans->blocks_used;
-		ret = btrfs_end_transaction(trans, root);
-		BUG_ON(ret);
-		btrfs_btree_balance_dirty(root, nr);
-
-		kfree(prev_root);
-		prev_root = reloc_root;
-	}
-	if (prev_root) {
-		btrfs_remove_leaf_refs(prev_root, (u64)-1, 0);
-		kfree(prev_root);
-	}
-	return 0;
-}
-
-int btrfs_add_dead_reloc_root(struct btrfs_root *root)
-{
-	list_add(&root->dead_list, &root->fs_info->dead_reloc_roots);
-	return 0;
-}
-
-int btrfs_cleanup_reloc_trees(struct btrfs_root *root)
-{
-	struct btrfs_root *reloc_root;
-	struct btrfs_trans_handle *trans;
-	struct btrfs_key location;
-	int found;
-	int ret;
-
-	mutex_lock(&root->fs_info->tree_reloc_mutex);
-	ret = btrfs_find_dead_roots(root, BTRFS_TREE_RELOC_OBJECTID, NULL);
-	BUG_ON(ret);
-	found = !list_empty(&root->fs_info->dead_reloc_roots);
-	mutex_unlock(&root->fs_info->tree_reloc_mutex);
-
-	if (found) {
-		trans = btrfs_start_transaction(root, 1);
-		BUG_ON(IS_ERR(trans));
-		ret = btrfs_commit_transaction(trans, root);
-		BUG_ON(ret);
-	}
-
-	location.objectid = BTRFS_DATA_RELOC_TREE_OBJECTID;
-	location.offset = (u64)-1;
-	location.type = BTRFS_ROOT_ITEM_KEY;
-
-	reloc_root = btrfs_read_fs_root_no_name(root->fs_info, &location);
-	BUG_ON(!reloc_root);
-	ret = btrfs_orphan_cleanup(reloc_root);
-	BUG_ON(ret);
-	return 0;
-}
-
-static noinline int init_reloc_tree(struct btrfs_trans_handle *trans,
-				    struct btrfs_root *root)
-{
-	struct btrfs_root *reloc_root;
-	struct extent_buffer *eb;
-	struct btrfs_root_item *root_item;
-	struct btrfs_key root_key;
-	int ret;
-
-	BUG_ON(!root->ref_cows);
-	if (root->reloc_root)
-		return 0;
-
-	root_item = kmalloc(sizeof(*root_item), GFP_NOFS);
-	if (!root_item)
-		return -ENOMEM;
-
-	ret = btrfs_copy_root(trans, root, root->commit_root,
-			      &eb, BTRFS_TREE_RELOC_OBJECTID);
-	BUG_ON(ret);
-
-	root_key.objectid = BTRFS_TREE_RELOC_OBJECTID;
-	root_key.offset = root->root_key.objectid;
-	root_key.type = BTRFS_ROOT_ITEM_KEY;
-
-	memcpy(root_item, &root->root_item, sizeof(root_item));
-	btrfs_set_root_refs(root_item, 0);
-	btrfs_set_root_bytenr(root_item, eb->start);
-	btrfs_set_root_level(root_item, btrfs_header_level(eb));
-	btrfs_set_root_generation(root_item, trans->transid);
-
-	btrfs_tree_unlock(eb);
-	free_extent_buffer(eb);
-
-	ret = btrfs_insert_root(trans, root->fs_info->tree_root,
-				&root_key, root_item);
-	BUG_ON(ret);
-	kfree(root_item);
-
-	reloc_root = btrfs_read_fs_root_no_radix(root->fs_info->tree_root,
-						 &root_key);
-	BUG_ON(IS_ERR(reloc_root));
-	reloc_root->last_trans = trans->transid;
-	reloc_root->commit_root = NULL;
-	reloc_root->ref_tree = &root->fs_info->reloc_ref_tree;
-
-	root->reloc_root = reloc_root;
-	return 0;
-}
-
-/*
- * Core function of space balance.
- *
- * The idea is using reloc trees to relocate tree blocks in reference
- * counted roots. There is one reloc tree for each subvol, and all
- * reloc trees share same root key objectid. Reloc trees are snapshots
- * of the latest committed roots of subvols (root->commit_root).
- *
- * To relocate a tree block referenced by a subvol, there are two steps.
- * COW the block through subvol's reloc tree, then update block pointer
- * in the subvol to point to the new block. Since all reloc trees share
- * same root key objectid, doing special handing for tree blocks owned
- * by them is easy. Once a tree block has been COWed in one reloc tree,
- * we can use the resulting new block directly when the same block is
- * required to COW again through other reloc trees. By this way, relocated
- * tree blocks are shared between reloc trees, so they are also shared
- * between subvols.
- */
-static noinline int relocate_one_path(struct btrfs_trans_handle *trans,
-				      struct btrfs_root *root,
-				      struct btrfs_path *path,
-				      struct btrfs_key *first_key,
-				      struct btrfs_ref_path *ref_path,
-				      struct btrfs_block_group_cache *group,
-				      struct inode *reloc_inode)
-{
-	struct btrfs_root *reloc_root;
-	struct extent_buffer *eb = NULL;
-	struct btrfs_key *keys;
-	u64 *nodes;
-	int level;
-	int shared_level;
-	int lowest_level = 0;
-	int ret;
-
-	if (ref_path->owner_objectid < BTRFS_FIRST_FREE_OBJECTID)
-		lowest_level = ref_path->owner_objectid;
-
-	if (!root->ref_cows) {
-		path->lowest_level = lowest_level;
-		ret = btrfs_search_slot(trans, root, first_key, path, 0, 1);
-		BUG_ON(ret < 0);
-		path->lowest_level = 0;
-		btrfs_release_path(root, path);
-		return 0;
-	}
-
-	mutex_lock(&root->fs_info->tree_reloc_mutex);
-	ret = init_reloc_tree(trans, root);
-	BUG_ON(ret);
-	reloc_root = root->reloc_root;
-
-	shared_level = ref_path->shared_level;
-	ref_path->shared_level = BTRFS_MAX_LEVEL - 1;
-
-	keys = ref_path->node_keys;
-	nodes = ref_path->new_nodes;
-	memset(&keys[shared_level + 1], 0,
-	       sizeof(*keys) * (BTRFS_MAX_LEVEL - shared_level - 1));
-	memset(&nodes[shared_level + 1], 0,
-	       sizeof(*nodes) * (BTRFS_MAX_LEVEL - shared_level - 1));
-
-	if (nodes[lowest_level] == 0) {
-		path->lowest_level = lowest_level;
-		ret = btrfs_search_slot(trans, reloc_root, first_key, path,
-					0, 1);
-		BUG_ON(ret);
-		for (level = lowest_level; level < BTRFS_MAX_LEVEL; level++) {
-			eb = path->nodes[level];
-			if (!eb || eb == reloc_root->node)
-				break;
-			nodes[level] = eb->start;
-			if (level == 0)
-				btrfs_item_key_to_cpu(eb, &keys[level], 0);
-			else
-				btrfs_node_key_to_cpu(eb, &keys[level], 0);
-		}
-		if (nodes[0] &&
-		    ref_path->owner_objectid >= BTRFS_FIRST_FREE_OBJECTID) {
-			eb = path->nodes[0];
-			ret = replace_extents_in_leaf(trans, reloc_root, eb,
-						      group, reloc_inode);
-			BUG_ON(ret);
-		}
-		btrfs_release_path(reloc_root, path);
-	} else {
-		ret = btrfs_merge_path(trans, reloc_root, keys, nodes,
-				       lowest_level);
-		BUG_ON(ret);
-	}
-
-	/*
-	 * replace tree blocks in the fs tree with tree blocks in
-	 * the reloc tree.
-	 */
-	ret = btrfs_merge_path(trans, root, keys, nodes, lowest_level);
-	BUG_ON(ret < 0);
-
-	if (ref_path->owner_objectid >= BTRFS_FIRST_FREE_OBJECTID) {
-		ret = btrfs_search_slot(trans, reloc_root, first_key, path,
-					0, 0);
-		BUG_ON(ret);
-		extent_buffer_get(path->nodes[0]);
-		eb = path->nodes[0];
-		btrfs_release_path(reloc_root, path);
-		ret = invalidate_extent_cache(reloc_root, eb, group, root);
-		BUG_ON(ret);
-		free_extent_buffer(eb);
-	}
-
-	mutex_unlock(&root->fs_info->tree_reloc_mutex);
-	path->lowest_level = 0;
-	return 0;
-}
-
-static noinline int relocate_tree_block(struct btrfs_trans_handle *trans,
-					struct btrfs_root *root,
-					struct btrfs_path *path,
-					struct btrfs_key *first_key,
-					struct btrfs_ref_path *ref_path)
-{
-	int ret;
-
-	ret = relocate_one_path(trans, root, path, first_key,
-				ref_path, NULL, NULL);
-	BUG_ON(ret);
-
-	return 0;
-}
-
-static noinline int del_extent_zero(struct btrfs_trans_handle *trans,
-				    struct btrfs_root *extent_root,
-				    struct btrfs_path *path,
-				    struct btrfs_key *extent_key)
-{
-	int ret;
-
-	ret = btrfs_search_slot(trans, extent_root, extent_key, path, -1, 1);
-	if (ret)
-		goto out;
-	ret = btrfs_del_item(trans, extent_root, path);
-out:
-	btrfs_release_path(extent_root, path);
-	return ret;
-}
-
-static noinline struct btrfs_root *read_ref_root(struct btrfs_fs_info *fs_info,
-						struct btrfs_ref_path *ref_path)
-{
-	struct btrfs_key root_key;
-
-	root_key.objectid = ref_path->root_objectid;
-	root_key.type = BTRFS_ROOT_ITEM_KEY;
-	if (is_cowonly_root(ref_path->root_objectid))
-		root_key.offset = 0;
-	else
-		root_key.offset = (u64)-1;
-
-	return btrfs_read_fs_root_no_name(fs_info, &root_key);
-}
-
-static noinline int relocate_one_extent(struct btrfs_root *extent_root,
-					struct btrfs_path *path,
-					struct btrfs_key *extent_key,
-					struct btrfs_block_group_cache *group,
-					struct inode *reloc_inode, int pass)
-{
-	struct btrfs_trans_handle *trans;
-	struct btrfs_root *found_root;
-	struct btrfs_ref_path *ref_path = NULL;
-	struct disk_extent *new_extents = NULL;
-	int nr_extents = 0;
-	int loops;
-	int ret;
-	int level;
-	struct btrfs_key first_key;
-	u64 prev_block = 0;
-
-
-	trans = btrfs_start_transaction(extent_root, 1);
-	BUG_ON(IS_ERR(trans));
-
-	if (extent_key->objectid == 0) {
-		ret = del_extent_zero(trans, extent_root, path, extent_key);
-		goto out;
-	}
-
-	ref_path = kmalloc(sizeof(*ref_path), GFP_NOFS);
-	if (!ref_path) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	for (loops = 0; ; loops++) {
-		if (loops == 0) {
-			ret = btrfs_first_ref_path(trans, extent_root, ref_path,
-						   extent_key->objectid);
-		} else {
-			ret = btrfs_next_ref_path(trans, extent_root, ref_path);
-		}
-		if (ret < 0)
-			goto out;
-		if (ret > 0)
-			break;
-
-		if (ref_path->root_objectid == BTRFS_TREE_LOG_OBJECTID ||
-		    ref_path->root_objectid == BTRFS_TREE_RELOC_OBJECTID)
-			continue;
-
-		found_root = read_ref_root(extent_root->fs_info, ref_path);
-		BUG_ON(!found_root);
-		/*
-		 * for reference counted tree, only process reference paths
-		 * rooted at the latest committed root.
-		 */
-		if (found_root->ref_cows &&
-		    ref_path->root_generation != found_root->root_key.offset)
-			continue;
-
-		if (ref_path->owner_objectid >= BTRFS_FIRST_FREE_OBJECTID) {
-			if (pass == 0) {
-				/*
-				 * copy data extents to new locations
-				 */
-				u64 group_start = group->key.objectid;
-				ret = relocate_data_extent(reloc_inode,
-							   extent_key,
-							   group_start);
-				if (ret < 0)
-					goto out;
-				break;
-			}
-			level = 0;
-		} else {
-			level = ref_path->owner_objectid;
-		}
-
-		if (prev_block != ref_path->nodes[level]) {
-			struct extent_buffer *eb;
-			u64 block_start = ref_path->nodes[level];
-			u64 block_size = btrfs_level_size(found_root, level);
-
-			eb = read_tree_block(found_root, block_start,
-					     block_size, 0);
-			if (!eb) {
-				ret = -EIO;
-				goto out;
-			}
-			btrfs_tree_lock(eb);
-			BUG_ON(level != btrfs_header_level(eb));
-
-			if (level == 0)
-				btrfs_item_key_to_cpu(eb, &first_key, 0);
-			else
-				btrfs_node_key_to_cpu(eb, &first_key, 0);
-
-			btrfs_tree_unlock(eb);
-			free_extent_buffer(eb);
-			prev_block = block_start;
-		}
-
-		mutex_lock(&extent_root->fs_info->trans_mutex);
-		btrfs_record_root_in_trans(found_root);
-		mutex_unlock(&extent_root->fs_info->trans_mutex);
-		if (ref_path->owner_objectid >= BTRFS_FIRST_FREE_OBJECTID) {
-			/*
-			 * try to update data extent references while
-			 * keeping metadata shared between snapshots.
-			 */
-			if (pass == 1) {
-				ret = relocate_one_path(trans, found_root,
-						path, &first_key, ref_path,
-						group, reloc_inode);
-				if (ret < 0)
-					goto out;
-				continue;
-			}
-			/*
-			 * use fallback method to process the remaining
-			 * references.
-			 */
-			if (!new_extents) {
-				u64 group_start = group->key.objectid;
-				new_extents = kmalloc(sizeof(*new_extents),
-						      GFP_NOFS);
-				if (!new_extents) {
-					ret = -ENOMEM;
-					goto out;
-				}
-				nr_extents = 1;
-				ret = get_new_locations(reloc_inode,
-							extent_key,
-							group_start, 1,
-							&new_extents,
-							&nr_extents);
-				if (ret)
-					goto out;
-			}
-			ret = replace_one_extent(trans, found_root,
-						path, extent_key,
-						&first_key, ref_path,
-						new_extents, nr_extents);
-		} else {
-			ret = relocate_tree_block(trans, found_root, path,
-						  &first_key, ref_path);
-		}
-		if (ret < 0)
-			goto out;
-	}
-	ret = 0;
-out:
-	btrfs_end_transaction(trans, extent_root);
-	kfree(new_extents);
-	kfree(ref_path);
-	return ret;
-}
-#endif
-
 static u64 update_block_group_flags(struct btrfs_root *root, u64 flags)
 {
 	u64 num_devices;
@@ -8176,7 +6563,7 @@ int btrfs_set_block_group_ro(struct btrfs_root *root,
 
 	BUG_ON(cache->ro);
 
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	BUG_ON(IS_ERR(trans));
 
 	alloc_flags = update_block_group_flags(root, cache->flags);
@@ -8532,6 +6919,7 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->reada = 1;
 
 	cache_gen = btrfs_super_cache_generation(&root->fs_info->super_copy);
 	if (cache_gen != 0 &&
@@ -8555,10 +6943,16 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 			ret = -ENOMEM;
 			goto error;
 		}
+		cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
+						GFP_NOFS);
+		if (!cache->free_space_ctl) {
+			kfree(cache);
+			ret = -ENOMEM;
+			goto error;
+		}
 
 		atomic_set(&cache->count, 1);
 		spin_lock_init(&cache->lock);
-		spin_lock_init(&cache->tree_lock);
 		cache->fs_info = info;
 		INIT_LIST_HEAD(&cache->list);
 		INIT_LIST_HEAD(&cache->cluster_list);
@@ -8566,24 +6960,18 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 		if (need_clear)
 			cache->disk_cache_state = BTRFS_DC_CLEAR;
 
-		/*
-		 * we only want to have 32k of ram per block group for keeping
-		 * track of free space, and if we pass 1/2 of that we want to
-		 * start converting things over to using bitmaps
-		 */
-		cache->extents_thresh = ((1024 * 32) / 2) /
-			sizeof(struct btrfs_free_space);
-
 		read_extent_buffer(leaf, &cache->item,
 				   btrfs_item_ptr_offset(leaf, path->slots[0]),
 				   sizeof(cache->item));
 		memcpy(&cache->key, &found_key, sizeof(found_key));
 
 		key.objectid = found_key.objectid + found_key.offset;
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		cache->flags = btrfs_block_group_flags(&cache->item);
 		cache->sectorsize = root->sectorsize;
 
+		btrfs_init_free_space_ctl(cache);
+
 		/*
 		 * We need to exclude the super stripes now so that the space
 		 * info has super bytes accounted for, otherwise we'll think
@@ -8670,6 +7058,12 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	cache = kzalloc(sizeof(*cache), GFP_NOFS);
 	if (!cache)
 		return -ENOMEM;
+	cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
+					GFP_NOFS);
+	if (!cache->free_space_ctl) {
+		kfree(cache);
+		return -ENOMEM;
+	}
 
 	cache->key.objectid = chunk_offset;
 	cache->key.offset = size;
@@ -8677,19 +7071,13 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	cache->sectorsize = root->sectorsize;
 	cache->fs_info = root->fs_info;
 
-	/*
-	 * we only want to have 32k of ram per block group for keeping track
-	 * of free space, and if we pass 1/2 of that we want to start
-	 * converting things over to using bitmaps
-	 */
-	cache->extents_thresh = ((1024 * 32) / 2) /
-		sizeof(struct btrfs_free_space);
 	atomic_set(&cache->count, 1);
 	spin_lock_init(&cache->lock);
-	spin_lock_init(&cache->tree_lock);
 	INIT_LIST_HEAD(&cache->list);
 	INIT_LIST_HEAD(&cache->cluster_list);
 
+	btrfs_init_free_space_ctl(cache);
+
 	btrfs_set_block_group_used(&cache->item, bytes_used);
 	btrfs_set_block_group_chunk_objectid(&cache->item, chunk_objectid);
 	cache->flags = type;
@@ -8802,12 +7190,12 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	if (ret < 0)
 		goto out;
 	if (ret > 0)
-		btrfs_release_path(tree_root, path);
+		btrfs_release_path(path);
 	if (ret == 0) {
 		ret = btrfs_del_item(trans, tree_root, path);
 		if (ret)
 			goto out;
-		btrfs_release_path(tree_root, path);
+		btrfs_release_path(path);
 	}
 
 	spin_lock(&root->fs_info->block_group_cache_lock);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4f9893243dae..7055d11c1efd 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -103,7 +103,7 @@ void extent_io_exit(void)
 }
 
 void extent_io_tree_init(struct extent_io_tree *tree,
-			  struct address_space *mapping, gfp_t mask)
+			 struct address_space *mapping)
 {
 	tree->state = RB_ROOT;
 	INIT_RADIX_TREE(&tree->buffer, GFP_ATOMIC);
@@ -441,6 +441,15 @@ static int clear_state_bit(struct extent_io_tree *tree,
 	return ret;
 }
 
+static struct extent_state *
+alloc_extent_state_atomic(struct extent_state *prealloc)
+{
+	if (!prealloc)
+		prealloc = alloc_extent_state(GFP_ATOMIC);
+
+	return prealloc;
+}
+
 /*
  * clear some bits on a range in the tree.  This may require splitting
  * or inserting elements in the tree, so the gfp mask is used to
@@ -531,8 +540,8 @@ hit_next:
 	 */
 
 	if (state->start < start) {
-		if (!prealloc)
-			prealloc = alloc_extent_state(GFP_ATOMIC);
+		prealloc = alloc_extent_state_atomic(prealloc);
+		BUG_ON(!prealloc);
 		err = split_state(tree, state, prealloc, start);
 		BUG_ON(err == -EEXIST);
 		prealloc = NULL;
@@ -553,8 +562,8 @@ hit_next:
 	 * on the first half
 	 */
 	if (state->start <= end && state->end > end) {
-		if (!prealloc)
-			prealloc = alloc_extent_state(GFP_ATOMIC);
+		prealloc = alloc_extent_state_atomic(prealloc);
+		BUG_ON(!prealloc);
 		err = split_state(tree, state, prealloc, end + 1);
 		BUG_ON(err == -EEXIST);
 		if (wake)
@@ -727,8 +736,7 @@ int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 again:
 	if (!prealloc && (mask & __GFP_WAIT)) {
 		prealloc = alloc_extent_state(mask);
-		if (!prealloc)
-			return -ENOMEM;
+		BUG_ON(!prealloc);
 	}
 
 	spin_lock(&tree->lock);
@@ -745,6 +753,8 @@ again:
 	 */
 	node = tree_search(tree, start);
 	if (!node) {
+		prealloc = alloc_extent_state_atomic(prealloc);
+		BUG_ON(!prealloc);
 		err = insert_state(tree, prealloc, start, end, &bits);
 		prealloc = NULL;
 		BUG_ON(err == -EEXIST);
@@ -773,20 +783,18 @@ hit_next:
 		if (err)
 			goto out;
 
+		next_node = rb_next(node);
 		cache_state(state, cached_state);
 		merge_state(tree, state);
 		if (last_end == (u64)-1)
 			goto out;
 
 		start = last_end + 1;
-		if (start < end && prealloc && !need_resched()) {
-			next_node = rb_next(node);
-			if (next_node) {
-				state = rb_entry(next_node, struct extent_state,
-						 rb_node);
-				if (state->start == start)
-					goto hit_next;
-			}
+		if (next_node && start < end && prealloc && !need_resched()) {
+			state = rb_entry(next_node, struct extent_state,
+					 rb_node);
+			if (state->start == start)
+				goto hit_next;
 		}
 		goto search_again;
 	}
@@ -813,6 +821,9 @@ hit_next:
 			err = -EEXIST;
 			goto out;
 		}
+
+		prealloc = alloc_extent_state_atomic(prealloc);
+		BUG_ON(!prealloc);
 		err = split_state(tree, state, prealloc, start);
 		BUG_ON(err == -EEXIST);
 		prealloc = NULL;
@@ -843,14 +854,25 @@ hit_next:
 			this_end = end;
 		else
 			this_end = last_start - 1;
+
+		prealloc = alloc_extent_state_atomic(prealloc);
+		BUG_ON(!prealloc);
+
+		/*
+		 * Avoid to free 'prealloc' if it can be merged with
+		 * the later extent.
+		 */
+		atomic_inc(&prealloc->refs);
 		err = insert_state(tree, prealloc, start, this_end,
 				   &bits);
 		BUG_ON(err == -EEXIST);
 		if (err) {
+			free_extent_state(prealloc);
 			prealloc = NULL;
 			goto out;
 		}
 		cache_state(prealloc, cached_state);
+		free_extent_state(prealloc);
 		prealloc = NULL;
 		start = this_end + 1;
 		goto search_again;
@@ -867,6 +889,9 @@ hit_next:
 			err = -EEXIST;
 			goto out;
 		}
+
+		prealloc = alloc_extent_state_atomic(prealloc);
+		BUG_ON(!prealloc);
 		err = split_state(tree, state, prealloc, end + 1);
 		BUG_ON(err == -EEXIST);
 
@@ -943,13 +968,6 @@ int set_extent_new(struct extent_io_tree *tree, u64 start, u64 end,
 			      NULL, mask);
 }
 
-static int clear_extent_new(struct extent_io_tree *tree, u64 start, u64 end,
-		       gfp_t mask)
-{
-	return clear_extent_bit(tree, start, end, EXTENT_NEW, 0, 0,
-				NULL, mask);
-}
-
 int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
 			struct extent_state **cached_state, gfp_t mask)
 {
@@ -965,11 +983,6 @@ static int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
 				cached_state, mask);
 }
 
-int wait_on_extent_writeback(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	return wait_extent_bit(tree, start, end, EXTENT_WRITEBACK);
-}
-
 /*
  * either insert or lock state struct between start and end use mask to tell
  * us if waiting is desired.
@@ -1030,25 +1043,6 @@ int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask)
 }
 
 /*
- * helper function to set pages and extents in the tree dirty
- */
-int set_range_dirty(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	unsigned long index = start >> PAGE_CACHE_SHIFT;
-	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
-	struct page *page;
-
-	while (index <= end_index) {
-		page = find_get_page(tree->mapping, index);
-		BUG_ON(!page);
-		__set_page_dirty_nobuffers(page);
-		page_cache_release(page);
-		index++;
-	}
-	return 0;
-}
-
-/*
  * helper function to set both pages and extents in the tree writeback
  */
 static int set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
@@ -1482,7 +1476,7 @@ u64 count_range_bits(struct extent_io_tree *tree,
 			if (total_bytes >= max_bytes)
 				break;
 			if (!found) {
-				*start = state->start;
+				*start = max(cur_start, state->start);
 				found = 1;
 			}
 			last = state->end;
@@ -1821,46 +1815,6 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 	bio_put(bio);
 }
 
-/*
- * IO done from prepare_write is pretty simple, we just unlock
- * the structs in the extent tree when done, and set the uptodate bits
- * as appropriate.
- */
-static void end_bio_extent_preparewrite(struct bio *bio, int err)
-{
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
-	struct extent_io_tree *tree;
-	u64 start;
-	u64 end;
-
-	do {
-		struct page *page = bvec->bv_page;
-		struct extent_state *cached = NULL;
-		tree = &BTRFS_I(page->mapping->host)->io_tree;
-
-		start = ((u64)page->index << PAGE_CACHE_SHIFT) +
-			bvec->bv_offset;
-		end = start + bvec->bv_len - 1;
-
-		if (--bvec >= bio->bi_io_vec)
-			prefetchw(&bvec->bv_page->flags);
-
-		if (uptodate) {
-			set_extent_uptodate(tree, start, end, &cached,
-					    GFP_ATOMIC);
-		} else {
-			ClearPageUptodate(page);
-			SetPageError(page);
-		}
-
-		unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC);
-
-	} while (bvec >= bio->bi_io_vec);
-
-	bio_put(bio);
-}
-
 struct bio *
 btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs,
 		gfp_t gfp_flags)
@@ -2009,7 +1963,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 	struct btrfs_ordered_extent *ordered;
 	int ret;
 	int nr = 0;
-	size_t page_offset = 0;
+	size_t pg_offset = 0;
 	size_t iosize;
 	size_t disk_io_size;
 	size_t blocksize = inode->i_sb->s_blocksize;
@@ -2052,9 +2006,9 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 			char *userpage;
 			struct extent_state *cached = NULL;
 
-			iosize = PAGE_CACHE_SIZE - page_offset;
+			iosize = PAGE_CACHE_SIZE - pg_offset;
 			userpage = kmap_atomic(page, KM_USER0);
-			memset(userpage + page_offset, 0, iosize);
+			memset(userpage + pg_offset, 0, iosize);
 			flush_dcache_page(page);
 			kunmap_atomic(userpage, KM_USER0);
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
@@ -2063,9 +2017,9 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 					     &cached, GFP_NOFS);
 			break;
 		}
-		em = get_extent(inode, page, page_offset, cur,
+		em = get_extent(inode, page, pg_offset, cur,
 				end - cur + 1, 0);
-		if (IS_ERR(em) || !em) {
+		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
 			unlock_extent(tree, cur, end, GFP_NOFS);
 			break;
@@ -2103,7 +2057,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 			struct extent_state *cached = NULL;
 
 			userpage = kmap_atomic(page, KM_USER0);
-			memset(userpage + page_offset, 0, iosize);
+			memset(userpage + pg_offset, 0, iosize);
 			flush_dcache_page(page);
 			kunmap_atomic(userpage, KM_USER0);
 
@@ -2112,7 +2066,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 			unlock_extent_cached(tree, cur, cur + iosize - 1,
 			                     &cached, GFP_NOFS);
 			cur = cur + iosize;
-			page_offset += iosize;
+			pg_offset += iosize;
 			continue;
 		}
 		/* the get_extent function already copied into the page */
@@ -2121,7 +2075,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 			check_page_uptodate(tree, page);
 			unlock_extent(tree, cur, cur + iosize - 1, GFP_NOFS);
 			cur = cur + iosize;
-			page_offset += iosize;
+			pg_offset += iosize;
 			continue;
 		}
 		/* we have an inline extent but it didn't get marked up
@@ -2131,7 +2085,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 			SetPageError(page);
 			unlock_extent(tree, cur, cur + iosize - 1, GFP_NOFS);
 			cur = cur + iosize;
-			page_offset += iosize;
+			pg_offset += iosize;
 			continue;
 		}
 
@@ -2144,7 +2098,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 			unsigned long pnr = (last_byte >> PAGE_CACHE_SHIFT) + 1;
 			pnr -= page->index;
 			ret = submit_extent_page(READ, tree, page,
-					 sector, disk_io_size, page_offset,
+					 sector, disk_io_size, pg_offset,
 					 bdev, bio, pnr,
 					 end_bio_extent_readpage, mirror_num,
 					 *bio_flags,
@@ -2155,7 +2109,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 		if (ret)
 			SetPageError(page);
 		cur = cur + iosize;
-		page_offset += iosize;
+		pg_offset += iosize;
 	}
 out:
 	if (!nr) {
@@ -2351,7 +2305,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 		}
 		em = epd->get_extent(inode, page, pg_offset, cur,
 				     end - cur + 1, 1);
-		if (IS_ERR(em) || !em) {
+		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
 			break;
 		}
@@ -2730,128 +2684,6 @@ int extent_invalidatepage(struct extent_io_tree *tree,
 }
 
 /*
- * simple commit_write call, set_range_dirty is used to mark both
- * the pages and the extent records as dirty
- */
-int extent_commit_write(struct extent_io_tree *tree,
-			struct inode *inode, struct page *page,
-			unsigned from, unsigned to)
-{
-	loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
-
-	set_page_extent_mapped(page);
-	set_page_dirty(page);
-
-	if (pos > inode->i_size) {
-		i_size_write(inode, pos);
-		mark_inode_dirty(inode);
-	}
-	return 0;
-}
-
-int extent_prepare_write(struct extent_io_tree *tree,
-			 struct inode *inode, struct page *page,
-			 unsigned from, unsigned to, get_extent_t *get_extent)
-{
-	u64 page_start = (u64)page->index << PAGE_CACHE_SHIFT;
-	u64 page_end = page_start + PAGE_CACHE_SIZE - 1;
-	u64 block_start;
-	u64 orig_block_start;
-	u64 block_end;
-	u64 cur_end;
-	struct extent_map *em;
-	unsigned blocksize = 1 << inode->i_blkbits;
-	size_t page_offset = 0;
-	size_t block_off_start;
-	size_t block_off_end;
-	int err = 0;
-	int iocount = 0;
-	int ret = 0;
-	int isnew;
-
-	set_page_extent_mapped(page);
-
-	block_start = (page_start + from) & ~((u64)blocksize - 1);
-	block_end = (page_start + to - 1) | (blocksize - 1);
-	orig_block_start = block_start;
-
-	lock_extent(tree, page_start, page_end, GFP_NOFS);
-	while (block_start <= block_end) {
-		em = get_extent(inode, page, page_offset, block_start,
-				block_end - block_start + 1, 1);
-		if (IS_ERR(em) || !em)
-			goto err;
-
-		cur_end = min(block_end, extent_map_end(em) - 1);
-		block_off_start = block_start & (PAGE_CACHE_SIZE - 1);
-		block_off_end = block_off_start + blocksize;
-		isnew = clear_extent_new(tree, block_start, cur_end, GFP_NOFS);
-
-		if (!PageUptodate(page) && isnew &&
-		    (block_off_end > to || block_off_start < from)) {
-			void *kaddr;
-
-			kaddr = kmap_atomic(page, KM_USER0);
-			if (block_off_end > to)
-				memset(kaddr + to, 0, block_off_end - to);
-			if (block_off_start < from)
-				memset(kaddr + block_off_start, 0,
-				       from - block_off_start);
-			flush_dcache_page(page);
-			kunmap_atomic(kaddr, KM_USER0);
-		}
-		if ((em->block_start != EXTENT_MAP_HOLE &&
-		     em->block_start != EXTENT_MAP_INLINE) &&
-		    !isnew && !PageUptodate(page) &&
-		    (block_off_end > to || block_off_start < from) &&
-		    !test_range_bit(tree, block_start, cur_end,
-				    EXTENT_UPTODATE, 1, NULL)) {
-			u64 sector;
-			u64 extent_offset = block_start - em->start;
-			size_t iosize;
-			sector = (em->block_start + extent_offset) >> 9;
-			iosize = (cur_end - block_start + blocksize) &
-				~((u64)blocksize - 1);
-			/*
-			 * we've already got the extent locked, but we
-			 * need to split the state such that our end_bio
-			 * handler can clear the lock.
-			 */
-			set_extent_bit(tree, block_start,
-				       block_start + iosize - 1,
-				       EXTENT_LOCKED, 0, NULL, NULL, GFP_NOFS);
-			ret = submit_extent_page(READ, tree, page,
-					 sector, iosize, page_offset, em->bdev,
-					 NULL, 1,
-					 end_bio_extent_preparewrite, 0,
-					 0, 0);
-			if (ret && !err)
-				err = ret;
-			iocount++;
-			block_start = block_start + iosize;
-		} else {
-			struct extent_state *cached = NULL;
-
-			set_extent_uptodate(tree, block_start, cur_end, &cached,
-					    GFP_NOFS);
-			unlock_extent_cached(tree, block_start, cur_end,
-					     &cached, GFP_NOFS);
-			block_start = cur_end + 1;
-		}
-		page_offset = block_start & (PAGE_CACHE_SIZE - 1);
-		free_extent_map(em);
-	}
-	if (iocount) {
-		wait_extent_bit(tree, orig_block_start,
-				block_end, EXTENT_LOCKED);
-	}
-	check_page_uptodate(tree, page);
-err:
-	/* FIXME, zero out newly allocated blocks on error */
-	return err;
-}
-
-/*
  * a helper for releasepage, this tests for areas of the page that
  * are locked or under IO and drops the related state bits if it is safe
  * to drop the page.
@@ -2909,7 +2741,7 @@ int try_release_extent_mapping(struct extent_map_tree *map,
 			len = end - start + 1;
 			write_lock(&map->lock);
 			em = lookup_extent_mapping(map, start, len);
-			if (!em || IS_ERR(em)) {
+			if (IS_ERR_OR_NULL(em)) {
 				write_unlock(&map->lock);
 				break;
 			}
@@ -2937,33 +2769,6 @@ int try_release_extent_mapping(struct extent_map_tree *map,
 	return try_release_extent_state(map, tree, page, mask);
 }
 
-sector_t extent_bmap(struct address_space *mapping, sector_t iblock,
-		get_extent_t *get_extent)
-{
-	struct inode *inode = mapping->host;
-	struct extent_state *cached_state = NULL;
-	u64 start = iblock << inode->i_blkbits;
-	sector_t sector = 0;
-	size_t blksize = (1 << inode->i_blkbits);
-	struct extent_map *em;
-
-	lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + blksize - 1,
-			 0, &cached_state, GFP_NOFS);
-	em = get_extent(inode, NULL, 0, start, blksize, 0);
-	unlock_extent_cached(&BTRFS_I(inode)->io_tree, start,
-			     start + blksize - 1, &cached_state, GFP_NOFS);
-	if (!em || IS_ERR(em))
-		return 0;
-
-	if (em->block_start > EXTENT_MAP_LAST_BYTE)
-		goto out;
-
-	sector = (em->block_start + start - em->start) >> inode->i_blkbits;
-out:
-	free_extent_map(em);
-	return sector;
-}
-
 /*
  * helper function for fiemap, which doesn't want to see any holes.
  * This maps until we find something past 'last'
@@ -2986,7 +2791,7 @@ static struct extent_map *get_extent_skip_holes(struct inode *inode,
 			break;
 		len = (len + sectorsize - 1) & ~(sectorsize - 1);
 		em = get_extent(inode, NULL, 0, offset, len, 0);
-		if (!em || IS_ERR(em))
+		if (IS_ERR_OR_NULL(em))
 			return em;
 
 		/* if this isn't a hole return it */
@@ -3040,7 +2845,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	 * because there might be preallocation past i_size
 	 */
 	ret = btrfs_lookup_file_extent(NULL, BTRFS_I(inode)->root,
-				       path, inode->i_ino, -1, 0);
+				       path, btrfs_ino(inode), -1, 0);
 	if (ret < 0) {
 		btrfs_free_path(path);
 		return ret;
@@ -3053,7 +2858,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	found_type = btrfs_key_type(&found_key);
 
 	/* No extents, but there might be delalloc bits */
-	if (found_key.objectid != inode->i_ino ||
+	if (found_key.objectid != btrfs_ino(inode) ||
 	    found_type != BTRFS_EXTENT_DATA_KEY) {
 		/* have to trust i_size as the end */
 		last = (u64)-1;
@@ -3276,8 +3081,7 @@ static inline void btrfs_release_extent_buffer(struct extent_buffer *eb)
 
 struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 					  u64 start, unsigned long len,
-					  struct page *page0,
-					  gfp_t mask)
+					  struct page *page0)
 {
 	unsigned long num_pages = num_extent_pages(start, len);
 	unsigned long i;
@@ -3298,7 +3102,7 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 	}
 	rcu_read_unlock();
 
-	eb = __alloc_extent_buffer(tree, start, len, mask);
+	eb = __alloc_extent_buffer(tree, start, len, GFP_NOFS);
 	if (!eb)
 		return NULL;
 
@@ -3315,7 +3119,7 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 		i = 0;
 	}
 	for (; i < num_pages; i++, index++) {
-		p = find_or_create_page(mapping, index, mask | __GFP_HIGHMEM);
+		p = find_or_create_page(mapping, index, GFP_NOFS | __GFP_HIGHMEM);
 		if (!p) {
 			WARN_ON(1);
 			goto free_eb;
@@ -3387,8 +3191,7 @@ free_eb:
 }
 
 struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
-					 u64 start, unsigned long len,
-					  gfp_t mask)
+					 u64 start, unsigned long len)
 {
 	struct extent_buffer *eb;
 
@@ -3449,13 +3252,6 @@ int clear_extent_buffer_dirty(struct extent_io_tree *tree,
 	return 0;
 }
 
-int wait_on_extent_buffer_writeback(struct extent_io_tree *tree,
-				    struct extent_buffer *eb)
-{
-	return wait_on_extent_writeback(tree, eb->start,
-					eb->start + eb->len - 1);
-}
-
 int set_extent_buffer_dirty(struct extent_io_tree *tree,
 			     struct extent_buffer *eb)
 {
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index af2d7179c372..a11a92ee2d30 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -126,9 +126,9 @@ struct extent_buffer {
 	unsigned long map_len;
 	struct page *first_page;
 	unsigned long bflags;
-	atomic_t refs;
 	struct list_head leak_list;
 	struct rcu_head rcu_head;
+	atomic_t refs;
 
 	/* the spinlock is used to protect most operations */
 	spinlock_t lock;
@@ -153,23 +153,14 @@ static inline int extent_compress_type(unsigned long bio_flags)
 
 struct extent_map_tree;
 
-static inline struct extent_state *extent_state_next(struct extent_state *state)
-{
-	struct rb_node *node;
-	node = rb_next(&state->rb_node);
-	if (!node)
-		return NULL;
-	return rb_entry(node, struct extent_state, rb_node);
-}
-
 typedef struct extent_map *(get_extent_t)(struct inode *inode,
 					  struct page *page,
-					  size_t page_offset,
+					  size_t pg_offset,
 					  u64 start, u64 len,
 					  int create);
 
 void extent_io_tree_init(struct extent_io_tree *tree,
-			  struct address_space *mapping, gfp_t mask);
+			 struct address_space *mapping);
 int try_release_extent_mapping(struct extent_map_tree *map,
 			       struct extent_io_tree *tree, struct page *page,
 			       gfp_t mask);
@@ -215,14 +206,8 @@ int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
 		     gfp_t mask);
 int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
 		       gfp_t mask);
-int clear_extent_ordered(struct extent_io_tree *tree, u64 start, u64 end,
-		       gfp_t mask);
-int clear_extent_ordered_metadata(struct extent_io_tree *tree, u64 start,
-				  u64 end, gfp_t mask);
 int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end,
 			struct extent_state **cached_state, gfp_t mask);
-int set_extent_ordered(struct extent_io_tree *tree, u64 start, u64 end,
-		     gfp_t mask);
 int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
 			  u64 *start_ret, u64 *end_ret, int bits);
 struct extent_state *find_first_extent_bit_state(struct extent_io_tree *tree,
@@ -243,28 +228,17 @@ int extent_readpages(struct extent_io_tree *tree,
 		     struct address_space *mapping,
 		     struct list_head *pages, unsigned nr_pages,
 		     get_extent_t get_extent);
-int extent_prepare_write(struct extent_io_tree *tree,
-			 struct inode *inode, struct page *page,
-			 unsigned from, unsigned to, get_extent_t *get_extent);
-int extent_commit_write(struct extent_io_tree *tree,
-			struct inode *inode, struct page *page,
-			unsigned from, unsigned to);
-sector_t extent_bmap(struct address_space *mapping, sector_t iblock,
-		get_extent_t *get_extent);
 int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len, get_extent_t *get_extent);
-int set_range_dirty(struct extent_io_tree *tree, u64 start, u64 end);
 int set_state_private(struct extent_io_tree *tree, u64 start, u64 private);
 int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private);
 void set_page_extent_mapped(struct page *page);
 
 struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 					  u64 start, unsigned long len,
-					  struct page *page0,
-					  gfp_t mask);
+					  struct page *page0);
 struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
-					 u64 start, unsigned long len,
-					  gfp_t mask);
+					 u64 start, unsigned long len);
 void free_extent_buffer(struct extent_buffer *eb);
 int read_extent_buffer_pages(struct extent_io_tree *tree,
 			     struct extent_buffer *eb, u64 start, int wait,
@@ -292,16 +266,11 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 			   unsigned long src_offset, unsigned long len);
 void memset_extent_buffer(struct extent_buffer *eb, char c,
 			  unsigned long start, unsigned long len);
-int wait_on_extent_buffer_writeback(struct extent_io_tree *tree,
-				    struct extent_buffer *eb);
-int wait_on_extent_writeback(struct extent_io_tree *tree, u64 start, u64 end);
 int wait_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, int bits);
 int clear_extent_buffer_dirty(struct extent_io_tree *tree,
 			      struct extent_buffer *eb);
 int set_extent_buffer_dirty(struct extent_io_tree *tree,
 			     struct extent_buffer *eb);
-int test_extent_buffer_dirty(struct extent_io_tree *tree,
-			     struct extent_buffer *eb);
 int set_extent_buffer_uptodate(struct extent_io_tree *tree,
 			       struct extent_buffer *eb);
 int clear_extent_buffer_uptodate(struct extent_io_tree *tree,
@@ -319,7 +288,6 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long offset,
 		      unsigned long *map_start,
 		      unsigned long *map_len, int km);
 void unmap_extent_buffer(struct extent_buffer *eb, char *token, int km);
-int release_extent_buffer_tail_pages(struct extent_buffer *eb);
 int extent_range_uptodate(struct extent_io_tree *tree,
 			  u64 start, u64 end);
 int extent_clear_unlock_delalloc(struct inode *inode,
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index a24a3f2fa13e..2d0410344ea3 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -28,12 +28,11 @@ void extent_map_exit(void)
 /**
  * extent_map_tree_init - initialize extent map tree
  * @tree:		tree to initialize
- * @mask:		flags for memory allocations during tree operations
  *
  * Initialize the extent tree @tree.  Should be called for each new inode
  * or other user of the extent_map interface.
  */
-void extent_map_tree_init(struct extent_map_tree *tree, gfp_t mask)
+void extent_map_tree_init(struct extent_map_tree *tree)
 {
 	tree->map = RB_ROOT;
 	rwlock_init(&tree->lock);
@@ -41,16 +40,15 @@ void extent_map_tree_init(struct extent_map_tree *tree, gfp_t mask)
 
 /**
  * alloc_extent_map - allocate new extent map structure
- * @mask:	memory allocation flags
  *
  * Allocate a new extent_map structure.  The new structure is
  * returned with a reference count of one and needs to be
  * freed using free_extent_map()
  */
-struct extent_map *alloc_extent_map(gfp_t mask)
+struct extent_map *alloc_extent_map(void)
 {
 	struct extent_map *em;
-	em = kmem_cache_alloc(extent_map_cache, mask);
+	em = kmem_cache_alloc(extent_map_cache, GFP_NOFS);
 	if (!em)
 		return NULL;
 	em->in_tree = 0;
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 28b44dbd1e35..33a7890b1f40 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -49,14 +49,14 @@ static inline u64 extent_map_block_end(struct extent_map *em)
 	return em->block_start + em->block_len;
 }
 
-void extent_map_tree_init(struct extent_map_tree *tree, gfp_t mask);
+void extent_map_tree_init(struct extent_map_tree *tree);
 struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree,
 					 u64 start, u64 len);
 int add_extent_mapping(struct extent_map_tree *tree,
 		       struct extent_map *em);
 int remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em);
 
-struct extent_map *alloc_extent_map(gfp_t mask);
+struct extent_map *alloc_extent_map(void);
 void free_extent_map(struct extent_map *em);
 int __init extent_map_init(void);
 void extent_map_exit(void);
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index a6a9d4e8b491..90d4ee52cd45 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -193,7 +193,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 			u32 item_size;
 
 			if (item)
-				btrfs_release_path(root, path);
+				btrfs_release_path(path);
 			item = btrfs_lookup_csum(NULL, root->fs_info->csum_root,
 						 path, disk_bytenr, 0);
 			if (IS_ERR(item)) {
@@ -208,12 +208,13 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 						EXTENT_NODATASUM, GFP_NOFS);
 				} else {
 					printk(KERN_INFO "btrfs no csum found "
-					       "for inode %lu start %llu\n",
-					       inode->i_ino,
+					       "for inode %llu start %llu\n",
+					       (unsigned long long)
+					       btrfs_ino(inode),
 					       (unsigned long long)offset);
 				}
 				item = NULL;
-				btrfs_release_path(root, path);
+				btrfs_release_path(path);
 				goto found;
 			}
 			btrfs_item_key_to_cpu(path->nodes[0], &found_key,
@@ -266,7 +267,7 @@ int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode,
 }
 
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
-			     struct list_head *list)
+			     struct list_head *list, int search_commit)
 {
 	struct btrfs_key key;
 	struct btrfs_path *path;
@@ -283,6 +284,12 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 	path = btrfs_alloc_path();
 	BUG_ON(!path);
 
+	if (search_commit) {
+		path->skip_locking = 1;
+		path->reada = 2;
+		path->search_commit_root = 1;
+	}
+
 	key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
 	key.offset = start;
 	key.type = BTRFS_EXTENT_CSUM_KEY;
@@ -495,7 +502,6 @@ static noinline int truncate_one_csum(struct btrfs_trans_handle *trans,
 		u32 new_size = (bytenr - key->offset) >> blocksize_bits;
 		new_size *= csum_size;
 		ret = btrfs_truncate_item(trans, root, path, new_size, 1);
-		BUG_ON(ret);
 	} else if (key->offset >= bytenr && csum_end > end_byte &&
 		   end_byte > key->offset) {
 		/*
@@ -508,7 +514,6 @@ static noinline int truncate_one_csum(struct btrfs_trans_handle *trans,
 		new_size *= csum_size;
 
 		ret = btrfs_truncate_item(trans, root, path, new_size, 0);
-		BUG_ON(ret);
 
 		key->offset = end_byte;
 		ret = btrfs_set_item_key_safe(trans, root, path, key);
@@ -551,10 +556,10 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 		if (ret > 0) {
 			if (path->slots[0] == 0)
-				goto out;
+				break;
 			path->slots[0]--;
 		} else if (ret < 0) {
-			goto out;
+			break;
 		}
 
 		leaf = path->nodes[0];
@@ -579,7 +584,8 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 		/* delete the entire item, it is inside our range */
 		if (key.offset >= bytenr && csum_end <= end_byte) {
 			ret = btrfs_del_item(trans, root, path);
-			BUG_ON(ret);
+			if (ret)
+				goto out;
 			if (key.offset == bytenr)
 				break;
 		} else if (key.offset < bytenr && csum_end > end_byte) {
@@ -631,11 +637,12 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 			if (key.offset < bytenr)
 				break;
 		}
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 	}
+	ret = 0;
 out:
 	btrfs_free_path(path);
-	return 0;
+	return ret;
 }
 
 int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
@@ -722,7 +729,7 @@ again:
 	 * at this point, we know the tree has an item, but it isn't big
 	 * enough yet to put our csum in.  Grow it
 	 */
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	ret = btrfs_search_slot(trans, root, &file_key, path,
 				csum_size, 1);
 	if (ret < 0)
@@ -761,12 +768,11 @@ again:
 			goto insert;
 
 		ret = btrfs_extend_item(trans, root, path, diff);
-		BUG_ON(ret);
 		goto csum;
 	}
 
 insert:
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	csum_offset = 0;
 	if (found_next) {
 		u64 tmp = total_bytes + root->sectorsize;
@@ -850,7 +856,7 @@ next_sector:
 	}
 	btrfs_mark_buffer_dirty(path->nodes[0]);
 	if (total_bytes < sums->len) {
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		cond_resched();
 		goto again;
 	}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 75899a01dded..fa4ef18b66b1 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -40,6 +40,263 @@
 #include "locking.h"
 #include "compat.h"
 
+/*
+ * when auto defrag is enabled we
+ * queue up these defrag structs to remember which
+ * inodes need defragging passes
+ */
+struct inode_defrag {
+	struct rb_node rb_node;
+	/* objectid */
+	u64 ino;
+	/*
+	 * transid where the defrag was added, we search for
+	 * extents newer than this
+	 */
+	u64 transid;
+
+	/* root objectid */
+	u64 root;
+
+	/* last offset we were able to defrag */
+	u64 last_offset;
+
+	/* if we've wrapped around back to zero once already */
+	int cycled;
+};
+
+/* pop a record for an inode into the defrag tree.  The lock
+ * must be held already
+ *
+ * If you're inserting a record for an older transid than an
+ * existing record, the transid already in the tree is lowered
+ *
+ * If an existing record is found the defrag item you
+ * pass in is freed
+ */
+static int __btrfs_add_inode_defrag(struct inode *inode,
+				    struct inode_defrag *defrag)
+{
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct inode_defrag *entry;
+	struct rb_node **p;
+	struct rb_node *parent = NULL;
+
+	p = &root->fs_info->defrag_inodes.rb_node;
+	while (*p) {
+		parent = *p;
+		entry = rb_entry(parent, struct inode_defrag, rb_node);
+
+		if (defrag->ino < entry->ino)
+			p = &parent->rb_left;
+		else if (defrag->ino > entry->ino)
+			p = &parent->rb_right;
+		else {
+			/* if we're reinserting an entry for
+			 * an old defrag run, make sure to
+			 * lower the transid of our existing record
+			 */
+			if (defrag->transid < entry->transid)
+				entry->transid = defrag->transid;
+			if (defrag->last_offset > entry->last_offset)
+				entry->last_offset = defrag->last_offset;
+			goto exists;
+		}
+	}
+	BTRFS_I(inode)->in_defrag = 1;
+	rb_link_node(&defrag->rb_node, parent, p);
+	rb_insert_color(&defrag->rb_node, &root->fs_info->defrag_inodes);
+	return 0;
+
+exists:
+	kfree(defrag);
+	return 0;
+
+}
+
+/*
+ * insert a defrag record for this inode if auto defrag is
+ * enabled
+ */
+int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
+			   struct inode *inode)
+{
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct inode_defrag *defrag;
+	int ret = 0;
+	u64 transid;
+
+	if (!btrfs_test_opt(root, AUTO_DEFRAG))
+		return 0;
+
+	if (btrfs_fs_closing(root->fs_info))
+		return 0;
+
+	if (BTRFS_I(inode)->in_defrag)
+		return 0;
+
+	if (trans)
+		transid = trans->transid;
+	else
+		transid = BTRFS_I(inode)->root->last_trans;
+
+	defrag = kzalloc(sizeof(*defrag), GFP_NOFS);
+	if (!defrag)
+		return -ENOMEM;
+
+	defrag->ino = btrfs_ino(inode);
+	defrag->transid = transid;
+	defrag->root = root->root_key.objectid;
+
+	spin_lock(&root->fs_info->defrag_inodes_lock);
+	if (!BTRFS_I(inode)->in_defrag)
+		ret = __btrfs_add_inode_defrag(inode, defrag);
+	spin_unlock(&root->fs_info->defrag_inodes_lock);
+	return ret;
+}
+
+/*
+ * must be called with the defrag_inodes lock held
+ */
+struct inode_defrag *btrfs_find_defrag_inode(struct btrfs_fs_info *info, u64 ino,
+					     struct rb_node **next)
+{
+	struct inode_defrag *entry = NULL;
+	struct rb_node *p;
+	struct rb_node *parent = NULL;
+
+	p = info->defrag_inodes.rb_node;
+	while (p) {
+		parent = p;
+		entry = rb_entry(parent, struct inode_defrag, rb_node);
+
+		if (ino < entry->ino)
+			p = parent->rb_left;
+		else if (ino > entry->ino)
+			p = parent->rb_right;
+		else
+			return entry;
+	}
+
+	if (next) {
+		while (parent && ino > entry->ino) {
+			parent = rb_next(parent);
+			entry = rb_entry(parent, struct inode_defrag, rb_node);
+		}
+		*next = parent;
+	}
+	return NULL;
+}
+
+/*
+ * run through the list of inodes in the FS that need
+ * defragging
+ */
+int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
+{
+	struct inode_defrag *defrag;
+	struct btrfs_root *inode_root;
+	struct inode *inode;
+	struct rb_node *n;
+	struct btrfs_key key;
+	struct btrfs_ioctl_defrag_range_args range;
+	u64 first_ino = 0;
+	int num_defrag;
+	int defrag_batch = 1024;
+
+	memset(&range, 0, sizeof(range));
+	range.len = (u64)-1;
+
+	atomic_inc(&fs_info->defrag_running);
+	spin_lock(&fs_info->defrag_inodes_lock);
+	while(1) {
+		n = NULL;
+
+		/* find an inode to defrag */
+		defrag = btrfs_find_defrag_inode(fs_info, first_ino, &n);
+		if (!defrag) {
+			if (n)
+				defrag = rb_entry(n, struct inode_defrag, rb_node);
+			else if (first_ino) {
+				first_ino = 0;
+				continue;
+			} else {
+				break;
+			}
+		}
+
+		/* remove it from the rbtree */
+		first_ino = defrag->ino + 1;
+		rb_erase(&defrag->rb_node, &fs_info->defrag_inodes);
+
+		if (btrfs_fs_closing(fs_info))
+			goto next_free;
+
+		spin_unlock(&fs_info->defrag_inodes_lock);
+
+		/* get the inode */
+		key.objectid = defrag->root;
+		btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
+		key.offset = (u64)-1;
+		inode_root = btrfs_read_fs_root_no_name(fs_info, &key);
+		if (IS_ERR(inode_root))
+			goto next;
+
+		key.objectid = defrag->ino;
+		btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
+		key.offset = 0;
+
+		inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
+		if (IS_ERR(inode))
+			goto next;
+
+		/* do a chunk of defrag */
+		BTRFS_I(inode)->in_defrag = 0;
+		range.start = defrag->last_offset;
+		num_defrag = btrfs_defrag_file(inode, NULL, &range, defrag->transid,
+					       defrag_batch);
+		/*
+		 * if we filled the whole defrag batch, there
+		 * must be more work to do.  Queue this defrag
+		 * again
+		 */
+		if (num_defrag == defrag_batch) {
+			defrag->last_offset = range.start;
+			__btrfs_add_inode_defrag(inode, defrag);
+			/*
+			 * we don't want to kfree defrag, we added it back to
+			 * the rbtree
+			 */
+			defrag = NULL;
+		} else if (defrag->last_offset && !defrag->cycled) {
+			/*
+			 * we didn't fill our defrag batch, but
+			 * we didn't start at zero.  Make sure we loop
+			 * around to the start of the file.
+			 */
+			defrag->last_offset = 0;
+			defrag->cycled = 1;
+			__btrfs_add_inode_defrag(inode, defrag);
+			defrag = NULL;
+		}
+
+		iput(inode);
+next:
+		spin_lock(&fs_info->defrag_inodes_lock);
+next_free:
+		kfree(defrag);
+	}
+	spin_unlock(&fs_info->defrag_inodes_lock);
+
+	atomic_dec(&fs_info->defrag_running);
+
+	/*
+	 * during unmount, we use the transaction_wait queue to
+	 * wait for the defragger to stop
+	 */
+	wake_up(&fs_info->transaction_wait);
+	return 0;
+}
 
 /* simple helper to fault in pages and copy.  This should go away
  * and be replaced with calls into generic code.
@@ -191,9 +448,9 @@ int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 	}
 	while (1) {
 		if (!split)
-			split = alloc_extent_map(GFP_NOFS);
+			split = alloc_extent_map();
 		if (!split2)
-			split2 = alloc_extent_map(GFP_NOFS);
+			split2 = alloc_extent_map();
 		BUG_ON(!split || !split2);
 
 		write_lock(&em_tree->lock);
@@ -298,6 +555,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode,
 	struct btrfs_path *path;
 	struct btrfs_key key;
 	struct btrfs_key new_key;
+	u64 ino = btrfs_ino(inode);
 	u64 search_start = start;
 	u64 disk_bytenr = 0;
 	u64 num_bytes = 0;
@@ -318,14 +576,14 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode,
 
 	while (1) {
 		recow = 0;
-		ret = btrfs_lookup_file_extent(trans, root, path, inode->i_ino,
+		ret = btrfs_lookup_file_extent(trans, root, path, ino,
 					       search_start, -1);
 		if (ret < 0)
 			break;
 		if (ret > 0 && path->slots[0] > 0 && search_start == start) {
 			leaf = path->nodes[0];
 			btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1);
-			if (key.objectid == inode->i_ino &&
+			if (key.objectid == ino &&
 			    key.type == BTRFS_EXTENT_DATA_KEY)
 				path->slots[0]--;
 		}
@@ -346,7 +604,7 @@ next_slot:
 		}
 
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-		if (key.objectid > inode->i_ino ||
+		if (key.objectid > ino ||
 		    key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end)
 			break;
 
@@ -376,7 +634,7 @@ next_slot:
 
 		search_start = max(key.offset, start);
 		if (recow) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			continue;
 		}
 
@@ -393,7 +651,7 @@ next_slot:
 			ret = btrfs_duplicate_item(trans, root, path,
 						   &new_key);
 			if (ret == -EAGAIN) {
-				btrfs_release_path(root, path);
+				btrfs_release_path(path);
 				continue;
 			}
 			if (ret < 0)
@@ -516,7 +774,7 @@ next_slot:
 			del_nr = 0;
 			del_slot = 0;
 
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			continue;
 		}
 
@@ -592,6 +850,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 	int del_slot = 0;
 	int recow;
 	int ret;
+	u64 ino = btrfs_ino(inode);
 
 	btrfs_drop_extent_cache(inode, start, end - 1, 0);
 
@@ -600,7 +859,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 again:
 	recow = 0;
 	split = start;
-	key.objectid = inode->i_ino;
+	key.objectid = ino;
 	key.type = BTRFS_EXTENT_DATA_KEY;
 	key.offset = split;
 
@@ -612,8 +871,7 @@ again:
 
 	leaf = path->nodes[0];
 	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-	BUG_ON(key.objectid != inode->i_ino ||
-	       key.type != BTRFS_EXTENT_DATA_KEY);
+	BUG_ON(key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY);
 	fi = btrfs_item_ptr(leaf, path->slots[0],
 			    struct btrfs_file_extent_item);
 	BUG_ON(btrfs_file_extent_type(leaf, fi) !=
@@ -630,7 +888,7 @@ again:
 		other_start = 0;
 		other_end = start;
 		if (extent_mergeable(leaf, path->slots[0] - 1,
-				     inode->i_ino, bytenr, orig_offset,
+				     ino, bytenr, orig_offset,
 				     &other_start, &other_end)) {
 			new_key.offset = end;
 			btrfs_set_item_key_safe(trans, root, path, &new_key);
@@ -653,7 +911,7 @@ again:
 		other_start = end;
 		other_end = 0;
 		if (extent_mergeable(leaf, path->slots[0] + 1,
-				     inode->i_ino, bytenr, orig_offset,
+				     ino, bytenr, orig_offset,
 				     &other_start, &other_end)) {
 			fi = btrfs_item_ptr(leaf, path->slots[0],
 					    struct btrfs_file_extent_item);
@@ -681,7 +939,7 @@ again:
 		new_key.offset = split;
 		ret = btrfs_duplicate_item(trans, root, path, &new_key);
 		if (ret == -EAGAIN) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			goto again;
 		}
 		BUG_ON(ret < 0);
@@ -702,7 +960,7 @@ again:
 
 		ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0,
 					   root->root_key.objectid,
-					   inode->i_ino, orig_offset);
+					   ino, orig_offset);
 		BUG_ON(ret);
 
 		if (split == start) {
@@ -718,10 +976,10 @@ again:
 	other_start = end;
 	other_end = 0;
 	if (extent_mergeable(leaf, path->slots[0] + 1,
-			     inode->i_ino, bytenr, orig_offset,
+			     ino, bytenr, orig_offset,
 			     &other_start, &other_end)) {
 		if (recow) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			goto again;
 		}
 		extent_end = other_end;
@@ -729,16 +987,16 @@ again:
 		del_nr++;
 		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
 					0, root->root_key.objectid,
-					inode->i_ino, orig_offset);
+					ino, orig_offset);
 		BUG_ON(ret);
 	}
 	other_start = 0;
 	other_end = start;
 	if (extent_mergeable(leaf, path->slots[0] - 1,
-			     inode->i_ino, bytenr, orig_offset,
+			     ino, bytenr, orig_offset,
 			     &other_start, &other_end)) {
 		if (recow) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			goto again;
 		}
 		key.offset = other_start;
@@ -746,7 +1004,7 @@ again:
 		del_nr++;
 		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
 					0, root->root_key.objectid,
-					inode->i_ino, orig_offset);
+					ino, orig_offset);
 		BUG_ON(ret);
 	}
 	if (del_nr == 0) {
@@ -1222,14 +1480,12 @@ int btrfs_sync_file(struct file *file, int datasync)
 	 * the current transaction, we can bail out now without any
 	 * syncing
 	 */
-	mutex_lock(&root->fs_info->trans_mutex);
+	smp_mb();
 	if (BTRFS_I(inode)->last_trans <=
 	    root->fs_info->last_trans_committed) {
 		BTRFS_I(inode)->last_trans = 0;
-		mutex_unlock(&root->fs_info->trans_mutex);
 		goto out;
 	}
-	mutex_unlock(&root->fs_info->trans_mutex);
 
 	/*
 	 * ok we haven't committed the transaction yet, lets do a commit
@@ -1375,7 +1631,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 	while (1) {
 		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
 				      alloc_end - cur_offset, 0);
-		BUG_ON(IS_ERR(em) || !em);
+		BUG_ON(IS_ERR_OR_NULL(em));
 		last_byte = min(extent_map_end(em), alloc_end);
 		last_byte = (last_byte + mask) & ~mask;
 		if (em->block_start == EXTENT_MAP_HOLE ||
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 63731a1fb0a1..bf0d61567f3d 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -25,18 +25,17 @@
 #include "transaction.h"
 #include "disk-io.h"
 #include "extent_io.h"
+#include "inode-map.h"
 
 #define BITS_PER_BITMAP		(PAGE_CACHE_SIZE * 8)
 #define MAX_CACHE_BYTES_PER_GIG	(32 * 1024)
 
-static void recalculate_thresholds(struct btrfs_block_group_cache
-				   *block_group);
-static int link_free_space(struct btrfs_block_group_cache *block_group,
+static int link_free_space(struct btrfs_free_space_ctl *ctl,
 			   struct btrfs_free_space *info);
 
-struct inode *lookup_free_space_inode(struct btrfs_root *root,
-				      struct btrfs_block_group_cache
-				      *block_group, struct btrfs_path *path)
+static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
+					       struct btrfs_path *path,
+					       u64 offset)
 {
 	struct btrfs_key key;
 	struct btrfs_key location;
@@ -46,22 +45,15 @@ struct inode *lookup_free_space_inode(struct btrfs_root *root,
 	struct inode *inode = NULL;
 	int ret;
 
-	spin_lock(&block_group->lock);
-	if (block_group->inode)
-		inode = igrab(block_group->inode);
-	spin_unlock(&block_group->lock);
-	if (inode)
-		return inode;
-
 	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
-	key.offset = block_group->key.objectid;
+	key.offset = offset;
 	key.type = 0;
 
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
 		return ERR_PTR(ret);
 	if (ret > 0) {
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		return ERR_PTR(-ENOENT);
 	}
 
@@ -70,7 +62,7 @@ struct inode *lookup_free_space_inode(struct btrfs_root *root,
 				struct btrfs_free_space_header);
 	btrfs_free_space_key(leaf, header, &disk_key);
 	btrfs_disk_key_to_cpu(&location, &disk_key);
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	inode = btrfs_iget(root->fs_info->sb, &location, root, NULL);
 	if (!inode)
@@ -84,8 +76,29 @@ struct inode *lookup_free_space_inode(struct btrfs_root *root,
 
 	inode->i_mapping->flags &= ~__GFP_FS;
 
+	return inode;
+}
+
+struct inode *lookup_free_space_inode(struct btrfs_root *root,
+				      struct btrfs_block_group_cache
+				      *block_group, struct btrfs_path *path)
+{
+	struct inode *inode = NULL;
+
 	spin_lock(&block_group->lock);
-	if (!root->fs_info->closing) {
+	if (block_group->inode)
+		inode = igrab(block_group->inode);
+	spin_unlock(&block_group->lock);
+	if (inode)
+		return inode;
+
+	inode = __lookup_free_space_inode(root, path,
+					  block_group->key.objectid);
+	if (IS_ERR(inode))
+		return inode;
+
+	spin_lock(&block_group->lock);
+	if (!btrfs_fs_closing(root->fs_info)) {
 		block_group->inode = igrab(inode);
 		block_group->iref = 1;
 	}
@@ -94,24 +107,18 @@ struct inode *lookup_free_space_inode(struct btrfs_root *root,
 	return inode;
 }
 
-int create_free_space_inode(struct btrfs_root *root,
-			    struct btrfs_trans_handle *trans,
-			    struct btrfs_block_group_cache *block_group,
-			    struct btrfs_path *path)
+int __create_free_space_inode(struct btrfs_root *root,
+			      struct btrfs_trans_handle *trans,
+			      struct btrfs_path *path, u64 ino, u64 offset)
 {
 	struct btrfs_key key;
 	struct btrfs_disk_key disk_key;
 	struct btrfs_free_space_header *header;
 	struct btrfs_inode_item *inode_item;
 	struct extent_buffer *leaf;
-	u64 objectid;
 	int ret;
 
-	ret = btrfs_find_free_objectid(trans, root, 0, &objectid);
-	if (ret < 0)
-		return ret;
-
-	ret = btrfs_insert_empty_inode(trans, root, path, objectid);
+	ret = btrfs_insert_empty_inode(trans, root, path, ino);
 	if (ret)
 		return ret;
 
@@ -131,19 +138,18 @@ int create_free_space_inode(struct btrfs_root *root,
 			      BTRFS_INODE_PREALLOC | BTRFS_INODE_NODATASUM);
 	btrfs_set_inode_nlink(leaf, inode_item, 1);
 	btrfs_set_inode_transid(leaf, inode_item, trans->transid);
-	btrfs_set_inode_block_group(leaf, inode_item,
-				    block_group->key.objectid);
+	btrfs_set_inode_block_group(leaf, inode_item, offset);
 	btrfs_mark_buffer_dirty(leaf);
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
-	key.offset = block_group->key.objectid;
+	key.offset = offset;
 	key.type = 0;
 
 	ret = btrfs_insert_empty_item(trans, root, path, &key,
 				      sizeof(struct btrfs_free_space_header));
 	if (ret < 0) {
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		return ret;
 	}
 	leaf = path->nodes[0];
@@ -152,11 +158,27 @@ int create_free_space_inode(struct btrfs_root *root,
 	memset_extent_buffer(leaf, 0, (unsigned long)header, sizeof(*header));
 	btrfs_set_free_space_key(leaf, header, &disk_key);
 	btrfs_mark_buffer_dirty(leaf);
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	return 0;
 }
 
+int create_free_space_inode(struct btrfs_root *root,
+			    struct btrfs_trans_handle *trans,
+			    struct btrfs_block_group_cache *block_group,
+			    struct btrfs_path *path)
+{
+	int ret;
+	u64 ino;
+
+	ret = btrfs_find_free_objectid(root, &ino);
+	if (ret < 0)
+		return ret;
+
+	return __create_free_space_inode(root, trans, path, ino,
+					 block_group->key.objectid);
+}
+
 int btrfs_truncate_free_space_cache(struct btrfs_root *root,
 				    struct btrfs_trans_handle *trans,
 				    struct btrfs_path *path,
@@ -187,7 +209,8 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root,
 		return ret;
 	}
 
-	return btrfs_update_inode(trans, root, inode);
+	ret = btrfs_update_inode(trans, root, inode);
+	return ret;
 }
 
 static int readahead_cache(struct inode *inode)
@@ -209,15 +232,13 @@ static int readahead_cache(struct inode *inode)
 	return 0;
 }
 
-int load_free_space_cache(struct btrfs_fs_info *fs_info,
-			  struct btrfs_block_group_cache *block_group)
+int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
+			    struct btrfs_free_space_ctl *ctl,
+			    struct btrfs_path *path, u64 offset)
 {
-	struct btrfs_root *root = fs_info->tree_root;
-	struct inode *inode;
 	struct btrfs_free_space_header *header;
 	struct extent_buffer *leaf;
 	struct page *page;
-	struct btrfs_path *path;
 	u32 *checksums = NULL, *crc;
 	char *disk_crcs = NULL;
 	struct btrfs_key key;
@@ -225,76 +246,47 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 	u64 num_entries;
 	u64 num_bitmaps;
 	u64 generation;
-	u64 used = btrfs_block_group_used(&block_group->item);
 	u32 cur_crc = ~(u32)0;
 	pgoff_t index = 0;
 	unsigned long first_page_offset;
 	int num_checksums;
 	int ret = 0;
 
-	/*
-	 * If we're unmounting then just return, since this does a search on the
-	 * normal root and not the commit root and we could deadlock.
-	 */
-	smp_mb();
-	if (fs_info->closing)
-		return 0;
-
-	/*
-	 * If this block group has been marked to be cleared for one reason or
-	 * another then we can't trust the on disk cache, so just return.
-	 */
-	spin_lock(&block_group->lock);
-	if (block_group->disk_cache_state != BTRFS_DC_WRITTEN) {
-		spin_unlock(&block_group->lock);
-		return 0;
-	}
-	spin_unlock(&block_group->lock);
-
 	INIT_LIST_HEAD(&bitmaps);
 
-	path = btrfs_alloc_path();
-	if (!path)
-		return 0;
-
-	inode = lookup_free_space_inode(root, block_group, path);
-	if (IS_ERR(inode)) {
-		btrfs_free_path(path);
-		return 0;
-	}
-
 	/* Nothing in the space cache, goodbye */
-	if (!i_size_read(inode)) {
-		btrfs_free_path(path);
+	if (!i_size_read(inode))
 		goto out;
-	}
 
 	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
-	key.offset = block_group->key.objectid;
+	key.offset = offset;
 	key.type = 0;
 
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-	if (ret) {
-		btrfs_free_path(path);
+	if (ret < 0)
+		goto out;
+	else if (ret > 0) {
+		btrfs_release_path(path);
+		ret = 0;
 		goto out;
 	}
 
+	ret = -1;
+
 	leaf = path->nodes[0];
 	header = btrfs_item_ptr(leaf, path->slots[0],
 				struct btrfs_free_space_header);
 	num_entries = btrfs_free_space_entries(leaf, header);
 	num_bitmaps = btrfs_free_space_bitmaps(leaf, header);
 	generation = btrfs_free_space_generation(leaf, header);
-	btrfs_free_path(path);
+	btrfs_release_path(path);
 
 	if (BTRFS_I(inode)->generation != generation) {
 		printk(KERN_ERR "btrfs: free space inode generation (%llu) did"
-		       " not match free space cache generation (%llu) for "
-		       "block group %llu\n",
+		       " not match free space cache generation (%llu)\n",
 		       (unsigned long long)BTRFS_I(inode)->generation,
-		       (unsigned long long)generation,
-		       (unsigned long long)block_group->key.objectid);
-		goto free_cache;
+		       (unsigned long long)generation);
+		goto out;
 	}
 
 	if (!num_entries)
@@ -311,10 +303,8 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 		goto out;
 
 	ret = readahead_cache(inode);
-	if (ret) {
-		ret = 0;
+	if (ret)
 		goto out;
-	}
 
 	while (1) {
 		struct btrfs_free_space_entry *entry;
@@ -333,10 +323,8 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 		}
 
 		page = grab_cache_page(inode->i_mapping, index);
-		if (!page) {
-			ret = 0;
+		if (!page)
 			goto free_cache;
-		}
 
 		if (!PageUptodate(page)) {
 			btrfs_readpage(NULL, page);
@@ -345,9 +333,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 				unlock_page(page);
 				page_cache_release(page);
 				printk(KERN_ERR "btrfs: error reading free "
-				       "space cache: %llu\n",
-				       (unsigned long long)
-				       block_group->key.objectid);
+				       "space cache\n");
 				goto free_cache;
 			}
 		}
@@ -360,13 +346,10 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 			gen = addr + (sizeof(u32) * num_checksums);
 			if (*gen != BTRFS_I(inode)->generation) {
 				printk(KERN_ERR "btrfs: space cache generation"
-				       " (%llu) does not match inode (%llu) "
-				       "for block group %llu\n",
+				       " (%llu) does not match inode (%llu)\n",
 				       (unsigned long long)*gen,
 				       (unsigned long long)
-				       BTRFS_I(inode)->generation,
-				       (unsigned long long)
-				       block_group->key.objectid);
+				       BTRFS_I(inode)->generation);
 				kunmap(page);
 				unlock_page(page);
 				page_cache_release(page);
@@ -382,9 +365,8 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 					  PAGE_CACHE_SIZE - start_offset);
 		btrfs_csum_final(cur_crc, (char *)&cur_crc);
 		if (cur_crc != *crc) {
-			printk(KERN_ERR "btrfs: crc mismatch for page %lu in "
-			       "block group %llu\n", index,
-			       (unsigned long long)block_group->key.objectid);
+			printk(KERN_ERR "btrfs: crc mismatch for page %lu\n",
+			       index);
 			kunmap(page);
 			unlock_page(page);
 			page_cache_release(page);
@@ -417,10 +399,17 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 			}
 
 			if (entry->type == BTRFS_FREE_SPACE_EXTENT) {
-				spin_lock(&block_group->tree_lock);
-				ret = link_free_space(block_group, e);
-				spin_unlock(&block_group->tree_lock);
-				BUG_ON(ret);
+				spin_lock(&ctl->tree_lock);
+				ret = link_free_space(ctl, e);
+				spin_unlock(&ctl->tree_lock);
+				if (ret) {
+					printk(KERN_ERR "Duplicate entries in "
+					       "free space cache, dumping\n");
+					kunmap(page);
+					unlock_page(page);
+					page_cache_release(page);
+					goto free_cache;
+				}
 			} else {
 				e->bitmap = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS);
 				if (!e->bitmap) {
@@ -431,11 +420,19 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 					page_cache_release(page);
 					goto free_cache;
 				}
-				spin_lock(&block_group->tree_lock);
-				ret = link_free_space(block_group, e);
-				block_group->total_bitmaps++;
-				recalculate_thresholds(block_group);
-				spin_unlock(&block_group->tree_lock);
+				spin_lock(&ctl->tree_lock);
+				ret = link_free_space(ctl, e);
+				ctl->total_bitmaps++;
+				ctl->op->recalc_thresholds(ctl);
+				spin_unlock(&ctl->tree_lock);
+				if (ret) {
+					printk(KERN_ERR "Duplicate entries in "
+					       "free space cache, dumping\n");
+					kunmap(page);
+					unlock_page(page);
+					page_cache_release(page);
+					goto free_cache;
+				}
 				list_add_tail(&e->list, &bitmaps);
 			}
 
@@ -471,41 +468,96 @@ next:
 		index++;
 	}
 
-	spin_lock(&block_group->tree_lock);
-	if (block_group->free_space != (block_group->key.offset - used -
-					block_group->bytes_super)) {
-		spin_unlock(&block_group->tree_lock);
-		printk(KERN_ERR "block group %llu has an wrong amount of free "
-		       "space\n", block_group->key.objectid);
-		ret = 0;
-		goto free_cache;
-	}
-	spin_unlock(&block_group->tree_lock);
-
 	ret = 1;
 out:
 	kfree(checksums);
 	kfree(disk_crcs);
-	iput(inode);
 	return ret;
-
 free_cache:
-	/* This cache is bogus, make sure it gets cleared */
+	__btrfs_remove_free_space_cache(ctl);
+	goto out;
+}
+
+int load_free_space_cache(struct btrfs_fs_info *fs_info,
+			  struct btrfs_block_group_cache *block_group)
+{
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
+	struct btrfs_root *root = fs_info->tree_root;
+	struct inode *inode;
+	struct btrfs_path *path;
+	int ret;
+	bool matched;
+	u64 used = btrfs_block_group_used(&block_group->item);
+
+	/*
+	 * If we're unmounting then just return, since this does a search on the
+	 * normal root and not the commit root and we could deadlock.
+	 */
+	if (btrfs_fs_closing(fs_info))
+		return 0;
+
+	/*
+	 * If this block group has been marked to be cleared for one reason or
+	 * another then we can't trust the on disk cache, so just return.
+	 */
 	spin_lock(&block_group->lock);
-	block_group->disk_cache_state = BTRFS_DC_CLEAR;
+	if (block_group->disk_cache_state != BTRFS_DC_WRITTEN) {
+		spin_unlock(&block_group->lock);
+		return 0;
+	}
 	spin_unlock(&block_group->lock);
-	btrfs_remove_free_space_cache(block_group);
-	goto out;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return 0;
+
+	inode = lookup_free_space_inode(root, block_group, path);
+	if (IS_ERR(inode)) {
+		btrfs_free_path(path);
+		return 0;
+	}
+
+	ret = __load_free_space_cache(fs_info->tree_root, inode, ctl,
+				      path, block_group->key.objectid);
+	btrfs_free_path(path);
+	if (ret <= 0)
+		goto out;
+
+	spin_lock(&ctl->tree_lock);
+	matched = (ctl->free_space == (block_group->key.offset - used -
+				       block_group->bytes_super));
+	spin_unlock(&ctl->tree_lock);
+
+	if (!matched) {
+		__btrfs_remove_free_space_cache(ctl);
+		printk(KERN_ERR "block group %llu has an wrong amount of free "
+		       "space\n", block_group->key.objectid);
+		ret = -1;
+	}
+out:
+	if (ret < 0) {
+		/* This cache is bogus, make sure it gets cleared */
+		spin_lock(&block_group->lock);
+		block_group->disk_cache_state = BTRFS_DC_CLEAR;
+		spin_unlock(&block_group->lock);
+		ret = 0;
+
+		printk(KERN_ERR "btrfs: failed to load free space cache "
+		       "for block group %llu\n", block_group->key.objectid);
+	}
+
+	iput(inode);
+	return ret;
 }
 
-int btrfs_write_out_cache(struct btrfs_root *root,
-			  struct btrfs_trans_handle *trans,
-			  struct btrfs_block_group_cache *block_group,
-			  struct btrfs_path *path)
+int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
+			    struct btrfs_free_space_ctl *ctl,
+			    struct btrfs_block_group_cache *block_group,
+			    struct btrfs_trans_handle *trans,
+			    struct btrfs_path *path, u64 offset)
 {
 	struct btrfs_free_space_header *header;
 	struct extent_buffer *leaf;
-	struct inode *inode;
 	struct rb_node *node;
 	struct list_head *pos, *n;
 	struct page **pages;
@@ -522,64 +574,53 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 	int index = 0, num_pages = 0;
 	int entries = 0;
 	int bitmaps = 0;
-	int ret = 0;
+	int ret = -1;
 	bool next_page = false;
 	bool out_of_space = false;
 
-	root = root->fs_info->tree_root;
-
 	INIT_LIST_HEAD(&bitmap_list);
 
-	spin_lock(&block_group->lock);
-	if (block_group->disk_cache_state < BTRFS_DC_SETUP) {
-		spin_unlock(&block_group->lock);
-		return 0;
-	}
-	spin_unlock(&block_group->lock);
-
-	inode = lookup_free_space_inode(root, block_group, path);
-	if (IS_ERR(inode))
-		return 0;
-
-	if (!i_size_read(inode)) {
-		iput(inode);
+	node = rb_first(&ctl->free_space_offset);
+	if (!node)
 		return 0;
-	}
 
-	node = rb_first(&block_group->free_space_offset);
-	if (!node) {
-		iput(inode);
-		return 0;
-	}
+	if (!i_size_read(inode))
+		return -1;
 
 	num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
 		PAGE_CACHE_SHIFT;
+
+	/* Since the first page has all of our checksums and our generation we
+	 * need to calculate the offset into the page that we can start writing
+	 * our entries.
+	 */
+	first_page_offset = (sizeof(u32) * num_pages) + sizeof(u64);
+
 	filemap_write_and_wait(inode->i_mapping);
 	btrfs_wait_ordered_range(inode, inode->i_size &
 				 ~(root->sectorsize - 1), (u64)-1);
 
+	/* make sure we don't overflow that first page */
+	if (first_page_offset + sizeof(struct btrfs_free_space_entry) >= PAGE_CACHE_SIZE) {
+		/* this is really the same as running out of space, where we also return 0 */
+		printk(KERN_CRIT "Btrfs: free space cache was too big for the crc page\n");
+		ret = 0;
+		goto out_update;
+	}
+
 	/* We need a checksum per page. */
 	crc = checksums = kzalloc(sizeof(u32) * num_pages, GFP_NOFS);
-	if (!crc) {
-		iput(inode);
-		return 0;
-	}
+	if (!crc)
+		return -1;
 
 	pages = kzalloc(sizeof(struct page *) * num_pages, GFP_NOFS);
 	if (!pages) {
 		kfree(crc);
-		iput(inode);
-		return 0;
+		return -1;
 	}
 
-	/* Since the first page has all of our checksums and our generation we
-	 * need to calculate the offset into the page that we can start writing
-	 * our entries.
-	 */
-	first_page_offset = (sizeof(u32) * num_pages) + sizeof(u64);
-
 	/* Get the cluster for this block_group if it exists */
-	if (!list_empty(&block_group->cluster_list))
+	if (block_group && !list_empty(&block_group->cluster_list))
 		cluster = list_entry(block_group->cluster_list.next,
 				     struct btrfs_free_cluster,
 				     block_group_list);
@@ -621,7 +662,8 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 	 * When searching for pinned extents, we need to start at our start
 	 * offset.
 	 */
-	start = block_group->key.objectid;
+	if (block_group)
+		start = block_group->key.objectid;
 
 	/* Write out the extent entries */
 	do {
@@ -679,8 +721,9 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 		 * We want to add any pinned extents to our free space cache
 		 * so we don't leak the space
 		 */
-		while (!next_page && (start < block_group->key.objectid +
-				      block_group->key.offset)) {
+		while (block_group && !next_page &&
+		       (start < block_group->key.objectid +
+			block_group->key.offset)) {
 			ret = find_first_extent_bit(unpin, start, &start, &end,
 						    EXTENT_DIRTY);
 			if (ret) {
@@ -798,12 +841,12 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 	filemap_write_and_wait(inode->i_mapping);
 
 	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
-	key.offset = block_group->key.objectid;
+	key.offset = offset;
 	key.type = 0;
 
 	ret = btrfs_search_slot(trans, root, &key, path, 1, 1);
 	if (ret < 0) {
-		ret = 0;
+		ret = -1;
 		clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, bytes - 1,
 				 EXTENT_DIRTY | EXTENT_DELALLOC |
 				 EXTENT_DO_ACCOUNTING, 0, 0, NULL, GFP_NOFS);
@@ -816,13 +859,13 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 		path->slots[0]--;
 		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
 		if (found_key.objectid != BTRFS_FREE_SPACE_OBJECTID ||
-		    found_key.offset != block_group->key.objectid) {
-			ret = 0;
+		    found_key.offset != offset) {
+			ret = -1;
 			clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, bytes - 1,
 					 EXTENT_DIRTY | EXTENT_DELALLOC |
 					 EXTENT_DO_ACCOUNTING, 0, 0, NULL,
 					 GFP_NOFS);
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			goto out_free;
 		}
 	}
@@ -832,49 +875,85 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 	btrfs_set_free_space_bitmaps(leaf, header, bitmaps);
 	btrfs_set_free_space_generation(leaf, header, trans->transid);
 	btrfs_mark_buffer_dirty(leaf);
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	ret = 1;
 
 out_free:
-	if (ret == 0) {
+	kfree(checksums);
+	kfree(pages);
+
+out_update:
+	if (ret != 1) {
 		invalidate_inode_pages2_range(inode->i_mapping, 0, index);
+		BTRFS_I(inode)->generation = 0;
+	}
+	btrfs_update_inode(trans, root, inode);
+	return ret;
+}
+
+int btrfs_write_out_cache(struct btrfs_root *root,
+			  struct btrfs_trans_handle *trans,
+			  struct btrfs_block_group_cache *block_group,
+			  struct btrfs_path *path)
+{
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
+	struct inode *inode;
+	int ret = 0;
+
+	root = root->fs_info->tree_root;
+
+	spin_lock(&block_group->lock);
+	if (block_group->disk_cache_state < BTRFS_DC_SETUP) {
+		spin_unlock(&block_group->lock);
+		return 0;
+	}
+	spin_unlock(&block_group->lock);
+
+	inode = lookup_free_space_inode(root, block_group, path);
+	if (IS_ERR(inode))
+		return 0;
+
+	ret = __btrfs_write_out_cache(root, inode, ctl, block_group, trans,
+				      path, block_group->key.objectid);
+	if (ret < 0) {
 		spin_lock(&block_group->lock);
 		block_group->disk_cache_state = BTRFS_DC_ERROR;
 		spin_unlock(&block_group->lock);
-		BTRFS_I(inode)->generation = 0;
+		ret = 0;
+
+		printk(KERN_ERR "btrfs: failed to write free space cace "
+		       "for block group %llu\n", block_group->key.objectid);
 	}
-	kfree(checksums);
-	kfree(pages);
-	btrfs_update_inode(trans, root, inode);
+
 	iput(inode);
 	return ret;
 }
 
-static inline unsigned long offset_to_bit(u64 bitmap_start, u64 sectorsize,
+static inline unsigned long offset_to_bit(u64 bitmap_start, u32 unit,
 					  u64 offset)
 {
 	BUG_ON(offset < bitmap_start);
 	offset -= bitmap_start;
-	return (unsigned long)(div64_u64(offset, sectorsize));
+	return (unsigned long)(div_u64(offset, unit));
 }
 
-static inline unsigned long bytes_to_bits(u64 bytes, u64 sectorsize)
+static inline unsigned long bytes_to_bits(u64 bytes, u32 unit)
 {
-	return (unsigned long)(div64_u64(bytes, sectorsize));
+	return (unsigned long)(div_u64(bytes, unit));
 }
 
-static inline u64 offset_to_bitmap(struct btrfs_block_group_cache *block_group,
+static inline u64 offset_to_bitmap(struct btrfs_free_space_ctl *ctl,
 				   u64 offset)
 {
 	u64 bitmap_start;
 	u64 bytes_per_bitmap;
 
-	bytes_per_bitmap = BITS_PER_BITMAP * block_group->sectorsize;
-	bitmap_start = offset - block_group->key.objectid;
+	bytes_per_bitmap = BITS_PER_BITMAP * ctl->unit;
+	bitmap_start = offset - ctl->start;
 	bitmap_start = div64_u64(bitmap_start, bytes_per_bitmap);
 	bitmap_start *= bytes_per_bitmap;
-	bitmap_start += block_group->key.objectid;
+	bitmap_start += ctl->start;
 
 	return bitmap_start;
 }
@@ -909,10 +988,16 @@ static int tree_insert_offset(struct rb_root *root, u64 offset,
 			 * logically.
 			 */
 			if (bitmap) {
-				WARN_ON(info->bitmap);
+				if (info->bitmap) {
+					WARN_ON_ONCE(1);
+					return -EEXIST;
+				}
 				p = &(*p)->rb_right;
 			} else {
-				WARN_ON(!info->bitmap);
+				if (!info->bitmap) {
+					WARN_ON_ONCE(1);
+					return -EEXIST;
+				}
 				p = &(*p)->rb_left;
 			}
 		}
@@ -932,10 +1017,10 @@ static int tree_insert_offset(struct rb_root *root, u64 offset,
  * offset.
  */
 static struct btrfs_free_space *
-tree_search_offset(struct btrfs_block_group_cache *block_group,
+tree_search_offset(struct btrfs_free_space_ctl *ctl,
 		   u64 offset, int bitmap_only, int fuzzy)
 {
-	struct rb_node *n = block_group->free_space_offset.rb_node;
+	struct rb_node *n = ctl->free_space_offset.rb_node;
 	struct btrfs_free_space *entry, *prev = NULL;
 
 	/* find entry that is closest to the 'offset' */
@@ -1031,8 +1116,7 @@ tree_search_offset(struct btrfs_block_group_cache *block_group,
 				break;
 			}
 		}
-		if (entry->offset + BITS_PER_BITMAP *
-		    block_group->sectorsize > offset)
+		if (entry->offset + BITS_PER_BITMAP * ctl->unit > offset)
 			return entry;
 	} else if (entry->offset + entry->bytes > offset)
 		return entry;
@@ -1043,7 +1127,7 @@ tree_search_offset(struct btrfs_block_group_cache *block_group,
 	while (1) {
 		if (entry->bitmap) {
 			if (entry->offset + BITS_PER_BITMAP *
-			    block_group->sectorsize > offset)
+			    ctl->unit > offset)
 				break;
 		} else {
 			if (entry->offset + entry->bytes > offset)
@@ -1059,42 +1143,47 @@ tree_search_offset(struct btrfs_block_group_cache *block_group,
 }
 
 static inline void
-__unlink_free_space(struct btrfs_block_group_cache *block_group,
+__unlink_free_space(struct btrfs_free_space_ctl *ctl,
 		    struct btrfs_free_space *info)
 {
-	rb_erase(&info->offset_index, &block_group->free_space_offset);
-	block_group->free_extents--;
+	rb_erase(&info->offset_index, &ctl->free_space_offset);
+	ctl->free_extents--;
 }
 
-static void unlink_free_space(struct btrfs_block_group_cache *block_group,
+static void unlink_free_space(struct btrfs_free_space_ctl *ctl,
 			      struct btrfs_free_space *info)
 {
-	__unlink_free_space(block_group, info);
-	block_group->free_space -= info->bytes;
+	__unlink_free_space(ctl, info);
+	ctl->free_space -= info->bytes;
 }
 
-static int link_free_space(struct btrfs_block_group_cache *block_group,
+static int link_free_space(struct btrfs_free_space_ctl *ctl,
 			   struct btrfs_free_space *info)
 {
 	int ret = 0;
 
 	BUG_ON(!info->bitmap && !info->bytes);
-	ret = tree_insert_offset(&block_group->free_space_offset, info->offset,
+	ret = tree_insert_offset(&ctl->free_space_offset, info->offset,
 				 &info->offset_index, (info->bitmap != NULL));
 	if (ret)
 		return ret;
 
-	block_group->free_space += info->bytes;
-	block_group->free_extents++;
+	ctl->free_space += info->bytes;
+	ctl->free_extents++;
 	return ret;
 }
 
-static void recalculate_thresholds(struct btrfs_block_group_cache *block_group)
+static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
 {
+	struct btrfs_block_group_cache *block_group = ctl->private;
 	u64 max_bytes;
 	u64 bitmap_bytes;
 	u64 extent_bytes;
 	u64 size = block_group->key.offset;
+	u64 bytes_per_bg = BITS_PER_BITMAP * block_group->sectorsize;
+	int max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg);
+
+	BUG_ON(ctl->total_bitmaps > max_bitmaps);
 
 	/*
 	 * The goal is to keep the total amount of memory used per 1gb of space
@@ -1112,10 +1201,10 @@ static void recalculate_thresholds(struct btrfs_block_group_cache *block_group)
 	 * sure we don't go over our overall goal of MAX_CACHE_BYTES_PER_GIG as
 	 * we add more bitmaps.
 	 */
-	bitmap_bytes = (block_group->total_bitmaps + 1) * PAGE_CACHE_SIZE;
+	bitmap_bytes = (ctl->total_bitmaps + 1) * PAGE_CACHE_SIZE;
 
 	if (bitmap_bytes >= max_bytes) {
-		block_group->extents_thresh = 0;
+		ctl->extents_thresh = 0;
 		return;
 	}
 
@@ -1126,47 +1215,43 @@ static void recalculate_thresholds(struct btrfs_block_group_cache *block_group)
 	extent_bytes = max_bytes - bitmap_bytes;
 	extent_bytes = min_t(u64, extent_bytes, div64_u64(max_bytes, 2));
 
-	block_group->extents_thresh =
+	ctl->extents_thresh =
 		div64_u64(extent_bytes, (sizeof(struct btrfs_free_space)));
 }
 
-static void bitmap_clear_bits(struct btrfs_block_group_cache *block_group,
+static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
 			      struct btrfs_free_space *info, u64 offset,
 			      u64 bytes)
 {
-	unsigned long start, end;
-	unsigned long i;
+	unsigned long start, count;
 
-	start = offset_to_bit(info->offset, block_group->sectorsize, offset);
-	end = start + bytes_to_bits(bytes, block_group->sectorsize);
-	BUG_ON(end > BITS_PER_BITMAP);
+	start = offset_to_bit(info->offset, ctl->unit, offset);
+	count = bytes_to_bits(bytes, ctl->unit);
+	BUG_ON(start + count > BITS_PER_BITMAP);
 
-	for (i = start; i < end; i++)
-		clear_bit(i, info->bitmap);
+	bitmap_clear(info->bitmap, start, count);
 
 	info->bytes -= bytes;
-	block_group->free_space -= bytes;
+	ctl->free_space -= bytes;
 }
 
-static void bitmap_set_bits(struct btrfs_block_group_cache *block_group,
+static void bitmap_set_bits(struct btrfs_free_space_ctl *ctl,
 			    struct btrfs_free_space *info, u64 offset,
 			    u64 bytes)
 {
-	unsigned long start, end;
-	unsigned long i;
+	unsigned long start, count;
 
-	start = offset_to_bit(info->offset, block_group->sectorsize, offset);
-	end = start + bytes_to_bits(bytes, block_group->sectorsize);
-	BUG_ON(end > BITS_PER_BITMAP);
+	start = offset_to_bit(info->offset, ctl->unit, offset);
+	count = bytes_to_bits(bytes, ctl->unit);
+	BUG_ON(start + count > BITS_PER_BITMAP);
 
-	for (i = start; i < end; i++)
-		set_bit(i, info->bitmap);
+	bitmap_set(info->bitmap, start, count);
 
 	info->bytes += bytes;
-	block_group->free_space += bytes;
+	ctl->free_space += bytes;
 }
 
-static int search_bitmap(struct btrfs_block_group_cache *block_group,
+static int search_bitmap(struct btrfs_free_space_ctl *ctl,
 			 struct btrfs_free_space *bitmap_info, u64 *offset,
 			 u64 *bytes)
 {
@@ -1174,9 +1259,9 @@ static int search_bitmap(struct btrfs_block_group_cache *block_group,
 	unsigned long bits, i;
 	unsigned long next_zero;
 
-	i = offset_to_bit(bitmap_info->offset, block_group->sectorsize,
+	i = offset_to_bit(bitmap_info->offset, ctl->unit,
 			  max_t(u64, *offset, bitmap_info->offset));
-	bits = bytes_to_bits(*bytes, block_group->sectorsize);
+	bits = bytes_to_bits(*bytes, ctl->unit);
 
 	for (i = find_next_bit(bitmap_info->bitmap, BITS_PER_BITMAP, i);
 	     i < BITS_PER_BITMAP;
@@ -1191,29 +1276,25 @@ static int search_bitmap(struct btrfs_block_group_cache *block_group,
 	}
 
 	if (found_bits) {
-		*offset = (u64)(i * block_group->sectorsize) +
-			bitmap_info->offset;
-		*bytes = (u64)(found_bits) * block_group->sectorsize;
+		*offset = (u64)(i * ctl->unit) + bitmap_info->offset;
+		*bytes = (u64)(found_bits) * ctl->unit;
 		return 0;
 	}
 
 	return -1;
 }
 
-static struct btrfs_free_space *find_free_space(struct btrfs_block_group_cache
-						*block_group, u64 *offset,
-						u64 *bytes, int debug)
+static struct btrfs_free_space *
+find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes)
 {
 	struct btrfs_free_space *entry;
 	struct rb_node *node;
 	int ret;
 
-	if (!block_group->free_space_offset.rb_node)
+	if (!ctl->free_space_offset.rb_node)
 		return NULL;
 
-	entry = tree_search_offset(block_group,
-				   offset_to_bitmap(block_group, *offset),
-				   0, 1);
+	entry = tree_search_offset(ctl, offset_to_bitmap(ctl, *offset), 0, 1);
 	if (!entry)
 		return NULL;
 
@@ -1223,7 +1304,7 @@ static struct btrfs_free_space *find_free_space(struct btrfs_block_group_cache
 			continue;
 
 		if (entry->bitmap) {
-			ret = search_bitmap(block_group, entry, offset, bytes);
+			ret = search_bitmap(ctl, entry, offset, bytes);
 			if (!ret)
 				return entry;
 			continue;
@@ -1237,33 +1318,28 @@ static struct btrfs_free_space *find_free_space(struct btrfs_block_group_cache
 	return NULL;
 }
 
-static void add_new_bitmap(struct btrfs_block_group_cache *block_group,
+static void add_new_bitmap(struct btrfs_free_space_ctl *ctl,
 			   struct btrfs_free_space *info, u64 offset)
 {
-	u64 bytes_per_bg = BITS_PER_BITMAP * block_group->sectorsize;
-	int max_bitmaps = (int)div64_u64(block_group->key.offset +
-					 bytes_per_bg - 1, bytes_per_bg);
-	BUG_ON(block_group->total_bitmaps >= max_bitmaps);
-
-	info->offset = offset_to_bitmap(block_group, offset);
+	info->offset = offset_to_bitmap(ctl, offset);
 	info->bytes = 0;
-	link_free_space(block_group, info);
-	block_group->total_bitmaps++;
+	link_free_space(ctl, info);
+	ctl->total_bitmaps++;
 
-	recalculate_thresholds(block_group);
+	ctl->op->recalc_thresholds(ctl);
 }
 
-static void free_bitmap(struct btrfs_block_group_cache *block_group,
+static void free_bitmap(struct btrfs_free_space_ctl *ctl,
 			struct btrfs_free_space *bitmap_info)
 {
-	unlink_free_space(block_group, bitmap_info);
+	unlink_free_space(ctl, bitmap_info);
 	kfree(bitmap_info->bitmap);
 	kmem_cache_free(btrfs_free_space_cachep, bitmap_info);
-	block_group->total_bitmaps--;
-	recalculate_thresholds(block_group);
+	ctl->total_bitmaps--;
+	ctl->op->recalc_thresholds(ctl);
 }
 
-static noinline int remove_from_bitmap(struct btrfs_block_group_cache *block_group,
+static noinline int remove_from_bitmap(struct btrfs_free_space_ctl *ctl,
 			      struct btrfs_free_space *bitmap_info,
 			      u64 *offset, u64 *bytes)
 {
@@ -1272,8 +1348,7 @@ static noinline int remove_from_bitmap(struct btrfs_block_group_cache *block_gro
 	int ret;
 
 again:
-	end = bitmap_info->offset +
-		(u64)(BITS_PER_BITMAP * block_group->sectorsize) - 1;
+	end = bitmap_info->offset + (u64)(BITS_PER_BITMAP * ctl->unit) - 1;
 
 	/*
 	 * XXX - this can go away after a few releases.
@@ -1288,24 +1363,22 @@ again:
 	search_start = *offset;
 	search_bytes = *bytes;
 	search_bytes = min(search_bytes, end - search_start + 1);
-	ret = search_bitmap(block_group, bitmap_info, &search_start,
-			    &search_bytes);
+	ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes);
 	BUG_ON(ret < 0 || search_start != *offset);
 
 	if (*offset > bitmap_info->offset && *offset + *bytes > end) {
-		bitmap_clear_bits(block_group, bitmap_info, *offset,
-				  end - *offset + 1);
+		bitmap_clear_bits(ctl, bitmap_info, *offset, end - *offset + 1);
 		*bytes -= end - *offset + 1;
 		*offset = end + 1;
 	} else if (*offset >= bitmap_info->offset && *offset + *bytes <= end) {
-		bitmap_clear_bits(block_group, bitmap_info, *offset, *bytes);
+		bitmap_clear_bits(ctl, bitmap_info, *offset, *bytes);
 		*bytes = 0;
 	}
 
 	if (*bytes) {
 		struct rb_node *next = rb_next(&bitmap_info->offset_index);
 		if (!bitmap_info->bytes)
-			free_bitmap(block_group, bitmap_info);
+			free_bitmap(ctl, bitmap_info);
 
 		/*
 		 * no entry after this bitmap, but we still have bytes to
@@ -1332,31 +1405,45 @@ again:
 		 */
 		search_start = *offset;
 		search_bytes = *bytes;
-		ret = search_bitmap(block_group, bitmap_info, &search_start,
+		ret = search_bitmap(ctl, bitmap_info, &search_start,
 				    &search_bytes);
 		if (ret < 0 || search_start != *offset)
 			return -EAGAIN;
 
 		goto again;
 	} else if (!bitmap_info->bytes)
-		free_bitmap(block_group, bitmap_info);
+		free_bitmap(ctl, bitmap_info);
 
 	return 0;
 }
 
-static int insert_into_bitmap(struct btrfs_block_group_cache *block_group,
-			      struct btrfs_free_space *info)
+static u64 add_bytes_to_bitmap(struct btrfs_free_space_ctl *ctl,
+			       struct btrfs_free_space *info, u64 offset,
+			       u64 bytes)
 {
-	struct btrfs_free_space *bitmap_info;
-	int added = 0;
-	u64 bytes, offset, end;
-	int ret;
+	u64 bytes_to_set = 0;
+	u64 end;
+
+	end = info->offset + (u64)(BITS_PER_BITMAP * ctl->unit);
+
+	bytes_to_set = min(end - offset, bytes);
+
+	bitmap_set_bits(ctl, info, offset, bytes_to_set);
+
+	return bytes_to_set;
+
+}
+
+static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
+		      struct btrfs_free_space *info)
+{
+	struct btrfs_block_group_cache *block_group = ctl->private;
 
 	/*
 	 * If we are below the extents threshold then we can add this as an
 	 * extent, and don't have to deal with the bitmap
 	 */
-	if (block_group->free_extents < block_group->extents_thresh) {
+	if (ctl->free_extents < ctl->extents_thresh) {
 		/*
 		 * If this block group has some small extents we don't want to
 		 * use up all of our free slots in the cache with them, we want
@@ -1365,11 +1452,10 @@ static int insert_into_bitmap(struct btrfs_block_group_cache *block_group,
 		 * the overhead of a bitmap if we don't have to.
 		 */
 		if (info->bytes <= block_group->sectorsize * 4) {
-			if (block_group->free_extents * 2 <=
-			    block_group->extents_thresh)
-				return 0;
+			if (ctl->free_extents * 2 <= ctl->extents_thresh)
+				return false;
 		} else {
-			return 0;
+			return false;
 		}
 	}
 
@@ -1379,35 +1465,85 @@ static int insert_into_bitmap(struct btrfs_block_group_cache *block_group,
 	 */
 	if (BITS_PER_BITMAP * block_group->sectorsize >
 	    block_group->key.offset)
-		return 0;
+		return false;
+
+	return true;
+}
+
+static struct btrfs_free_space_op free_space_op = {
+	.recalc_thresholds	= recalculate_thresholds,
+	.use_bitmap		= use_bitmap,
+};
+
+static int insert_into_bitmap(struct btrfs_free_space_ctl *ctl,
+			      struct btrfs_free_space *info)
+{
+	struct btrfs_free_space *bitmap_info;
+	struct btrfs_block_group_cache *block_group = NULL;
+	int added = 0;
+	u64 bytes, offset, bytes_added;
+	int ret;
 
 	bytes = info->bytes;
 	offset = info->offset;
 
+	if (!ctl->op->use_bitmap(ctl, info))
+		return 0;
+
+	if (ctl->op == &free_space_op)
+		block_group = ctl->private;
 again:
-	bitmap_info = tree_search_offset(block_group,
-					 offset_to_bitmap(block_group, offset),
+	/*
+	 * Since we link bitmaps right into the cluster we need to see if we
+	 * have a cluster here, and if so and it has our bitmap we need to add
+	 * the free space to that bitmap.
+	 */
+	if (block_group && !list_empty(&block_group->cluster_list)) {
+		struct btrfs_free_cluster *cluster;
+		struct rb_node *node;
+		struct btrfs_free_space *entry;
+
+		cluster = list_entry(block_group->cluster_list.next,
+				     struct btrfs_free_cluster,
+				     block_group_list);
+		spin_lock(&cluster->lock);
+		node = rb_first(&cluster->root);
+		if (!node) {
+			spin_unlock(&cluster->lock);
+			goto no_cluster_bitmap;
+		}
+
+		entry = rb_entry(node, struct btrfs_free_space, offset_index);
+		if (!entry->bitmap) {
+			spin_unlock(&cluster->lock);
+			goto no_cluster_bitmap;
+		}
+
+		if (entry->offset == offset_to_bitmap(ctl, offset)) {
+			bytes_added = add_bytes_to_bitmap(ctl, entry,
+							  offset, bytes);
+			bytes -= bytes_added;
+			offset += bytes_added;
+		}
+		spin_unlock(&cluster->lock);
+		if (!bytes) {
+			ret = 1;
+			goto out;
+		}
+	}
+
+no_cluster_bitmap:
+	bitmap_info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
 					 1, 0);
 	if (!bitmap_info) {
 		BUG_ON(added);
 		goto new_bitmap;
 	}
 
-	end = bitmap_info->offset +
-		(u64)(BITS_PER_BITMAP * block_group->sectorsize);
-
-	if (offset >= bitmap_info->offset && offset + bytes > end) {
-		bitmap_set_bits(block_group, bitmap_info, offset,
-				end - offset);
-		bytes -= end - offset;
-		offset = end;
-		added = 0;
-	} else if (offset >= bitmap_info->offset && offset + bytes <= end) {
-		bitmap_set_bits(block_group, bitmap_info, offset, bytes);
-		bytes = 0;
-	} else {
-		BUG();
-	}
+	bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes);
+	bytes -= bytes_added;
+	offset += bytes_added;
+	added = 0;
 
 	if (!bytes) {
 		ret = 1;
@@ -1417,19 +1553,19 @@ again:
 
 new_bitmap:
 	if (info && info->bitmap) {
-		add_new_bitmap(block_group, info, offset);
+		add_new_bitmap(ctl, info, offset);
 		added = 1;
 		info = NULL;
 		goto again;
 	} else {
-		spin_unlock(&block_group->tree_lock);
+		spin_unlock(&ctl->tree_lock);
 
 		/* no pre-allocated info, allocate a new one */
 		if (!info) {
 			info = kmem_cache_zalloc(btrfs_free_space_cachep,
 						 GFP_NOFS);
 			if (!info) {
-				spin_lock(&block_group->tree_lock);
+				spin_lock(&ctl->tree_lock);
 				ret = -ENOMEM;
 				goto out;
 			}
@@ -1437,7 +1573,7 @@ new_bitmap:
 
 		/* allocate the bitmap */
 		info->bitmap = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS);
-		spin_lock(&block_group->tree_lock);
+		spin_lock(&ctl->tree_lock);
 		if (!info->bitmap) {
 			ret = -ENOMEM;
 			goto out;
@@ -1455,7 +1591,7 @@ out:
 	return ret;
 }
 
-bool try_merge_free_space(struct btrfs_block_group_cache *block_group,
+static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl,
 			  struct btrfs_free_space *info, bool update_stat)
 {
 	struct btrfs_free_space *left_info;
@@ -1469,18 +1605,18 @@ bool try_merge_free_space(struct btrfs_block_group_cache *block_group,
 	 * are adding, if there is remove that struct and add a new one to
 	 * cover the entire range
 	 */
-	right_info = tree_search_offset(block_group, offset + bytes, 0, 0);
+	right_info = tree_search_offset(ctl, offset + bytes, 0, 0);
 	if (right_info && rb_prev(&right_info->offset_index))
 		left_info = rb_entry(rb_prev(&right_info->offset_index),
 				     struct btrfs_free_space, offset_index);
 	else
-		left_info = tree_search_offset(block_group, offset - 1, 0, 0);
+		left_info = tree_search_offset(ctl, offset - 1, 0, 0);
 
 	if (right_info && !right_info->bitmap) {
 		if (update_stat)
-			unlink_free_space(block_group, right_info);
+			unlink_free_space(ctl, right_info);
 		else
-			__unlink_free_space(block_group, right_info);
+			__unlink_free_space(ctl, right_info);
 		info->bytes += right_info->bytes;
 		kmem_cache_free(btrfs_free_space_cachep, right_info);
 		merged = true;
@@ -1489,9 +1625,9 @@ bool try_merge_free_space(struct btrfs_block_group_cache *block_group,
 	if (left_info && !left_info->bitmap &&
 	    left_info->offset + left_info->bytes == offset) {
 		if (update_stat)
-			unlink_free_space(block_group, left_info);
+			unlink_free_space(ctl, left_info);
 		else
-			__unlink_free_space(block_group, left_info);
+			__unlink_free_space(ctl, left_info);
 		info->offset = left_info->offset;
 		info->bytes += left_info->bytes;
 		kmem_cache_free(btrfs_free_space_cachep, left_info);
@@ -1501,8 +1637,8 @@ bool try_merge_free_space(struct btrfs_block_group_cache *block_group,
 	return merged;
 }
 
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
-			 u64 offset, u64 bytes)
+int __btrfs_add_free_space(struct btrfs_free_space_ctl *ctl,
+			   u64 offset, u64 bytes)
 {
 	struct btrfs_free_space *info;
 	int ret = 0;
@@ -1514,9 +1650,9 @@ int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
 	info->offset = offset;
 	info->bytes = bytes;
 
-	spin_lock(&block_group->tree_lock);
+	spin_lock(&ctl->tree_lock);
 
-	if (try_merge_free_space(block_group, info, true))
+	if (try_merge_free_space(ctl, info, true))
 		goto link;
 
 	/*
@@ -1524,7 +1660,7 @@ int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
 	 * extent then we know we're going to have to allocate a new extent, so
 	 * before we do that see if we need to drop this into a bitmap
 	 */
-	ret = insert_into_bitmap(block_group, info);
+	ret = insert_into_bitmap(ctl, info);
 	if (ret < 0) {
 		goto out;
 	} else if (ret) {
@@ -1532,11 +1668,11 @@ int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
 		goto out;
 	}
 link:
-	ret = link_free_space(block_group, info);
+	ret = link_free_space(ctl, info);
 	if (ret)
 		kmem_cache_free(btrfs_free_space_cachep, info);
 out:
-	spin_unlock(&block_group->tree_lock);
+	spin_unlock(&ctl->tree_lock);
 
 	if (ret) {
 		printk(KERN_CRIT "btrfs: unable to add free space :%d\n", ret);
@@ -1549,21 +1685,21 @@ out:
 int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
 			    u64 offset, u64 bytes)
 {
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *info;
 	struct btrfs_free_space *next_info = NULL;
 	int ret = 0;
 
-	spin_lock(&block_group->tree_lock);
+	spin_lock(&ctl->tree_lock);
 
 again:
-	info = tree_search_offset(block_group, offset, 0, 0);
+	info = tree_search_offset(ctl, offset, 0, 0);
 	if (!info) {
 		/*
 		 * oops didn't find an extent that matched the space we wanted
 		 * to remove, look for a bitmap instead
 		 */
-		info = tree_search_offset(block_group,
-					  offset_to_bitmap(block_group, offset),
+		info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
 					  1, 0);
 		if (!info) {
 			WARN_ON(1);
@@ -1578,8 +1714,8 @@ again:
 					     offset_index);
 
 		if (next_info->bitmap)
-			end = next_info->offset + BITS_PER_BITMAP *
-				block_group->sectorsize - 1;
+			end = next_info->offset +
+			      BITS_PER_BITMAP * ctl->unit - 1;
 		else
 			end = next_info->offset + next_info->bytes;
 
@@ -1599,20 +1735,20 @@ again:
 	}
 
 	if (info->bytes == bytes) {
-		unlink_free_space(block_group, info);
+		unlink_free_space(ctl, info);
 		if (info->bitmap) {
 			kfree(info->bitmap);
-			block_group->total_bitmaps--;
+			ctl->total_bitmaps--;
 		}
 		kmem_cache_free(btrfs_free_space_cachep, info);
 		goto out_lock;
 	}
 
 	if (!info->bitmap && info->offset == offset) {
-		unlink_free_space(block_group, info);
+		unlink_free_space(ctl, info);
 		info->offset += bytes;
 		info->bytes -= bytes;
-		link_free_space(block_group, info);
+		link_free_space(ctl, info);
 		goto out_lock;
 	}
 
@@ -1626,13 +1762,13 @@ again:
 		 * first unlink the old info and then
 		 * insert it again after the hole we're creating
 		 */
-		unlink_free_space(block_group, info);
+		unlink_free_space(ctl, info);
 		if (offset + bytes < info->offset + info->bytes) {
 			u64 old_end = info->offset + info->bytes;
 
 			info->offset = offset + bytes;
 			info->bytes = old_end - info->offset;
-			ret = link_free_space(block_group, info);
+			ret = link_free_space(ctl, info);
 			WARN_ON(ret);
 			if (ret)
 				goto out_lock;
@@ -1642,7 +1778,7 @@ again:
 			 */
 			kmem_cache_free(btrfs_free_space_cachep, info);
 		}
-		spin_unlock(&block_group->tree_lock);
+		spin_unlock(&ctl->tree_lock);
 
 		/* step two, insert a new info struct to cover
 		 * anything before the hole
@@ -1653,12 +1789,12 @@ again:
 		goto out;
 	}
 
-	ret = remove_from_bitmap(block_group, info, &offset, &bytes);
+	ret = remove_from_bitmap(ctl, info, &offset, &bytes);
 	if (ret == -EAGAIN)
 		goto again;
 	BUG_ON(ret);
 out_lock:
-	spin_unlock(&block_group->tree_lock);
+	spin_unlock(&ctl->tree_lock);
 out:
 	return ret;
 }
@@ -1666,11 +1802,12 @@ out:
 void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
 			   u64 bytes)
 {
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *info;
 	struct rb_node *n;
 	int count = 0;
 
-	for (n = rb_first(&block_group->free_space_offset); n; n = rb_next(n)) {
+	for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) {
 		info = rb_entry(n, struct btrfs_free_space, offset_index);
 		if (info->bytes >= bytes)
 			count++;
@@ -1685,19 +1822,23 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
 	       "\n", count);
 }
 
-u64 btrfs_block_group_free_space(struct btrfs_block_group_cache *block_group)
+void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group)
 {
-	struct btrfs_free_space *info;
-	struct rb_node *n;
-	u64 ret = 0;
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 
-	for (n = rb_first(&block_group->free_space_offset); n;
-	     n = rb_next(n)) {
-		info = rb_entry(n, struct btrfs_free_space, offset_index);
-		ret += info->bytes;
-	}
+	spin_lock_init(&ctl->tree_lock);
+	ctl->unit = block_group->sectorsize;
+	ctl->start = block_group->key.objectid;
+	ctl->private = block_group;
+	ctl->op = &free_space_op;
 
-	return ret;
+	/*
+	 * we only want to have 32k of ram per block group for keeping
+	 * track of free space, and if we pass 1/2 of that we want to
+	 * start converting things over to using bitmaps
+	 */
+	ctl->extents_thresh = ((1024 * 32) / 2) /
+				sizeof(struct btrfs_free_space);
 }
 
 /*
@@ -1711,6 +1852,7 @@ __btrfs_return_cluster_to_free_space(
 			     struct btrfs_block_group_cache *block_group,
 			     struct btrfs_free_cluster *cluster)
 {
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *entry;
 	struct rb_node *node;
 
@@ -1732,8 +1874,8 @@ __btrfs_return_cluster_to_free_space(
 
 		bitmap = (entry->bitmap != NULL);
 		if (!bitmap)
-			try_merge_free_space(block_group, entry, false);
-		tree_insert_offset(&block_group->free_space_offset,
+			try_merge_free_space(ctl, entry, false);
+		tree_insert_offset(&ctl->free_space_offset,
 				   entry->offset, &entry->offset_index, bitmap);
 	}
 	cluster->root = RB_ROOT;
@@ -1744,14 +1886,41 @@ out:
 	return 0;
 }
 
-void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
+void __btrfs_remove_free_space_cache_locked(struct btrfs_free_space_ctl *ctl)
 {
 	struct btrfs_free_space *info;
 	struct rb_node *node;
+
+	while ((node = rb_last(&ctl->free_space_offset)) != NULL) {
+		info = rb_entry(node, struct btrfs_free_space, offset_index);
+		if (!info->bitmap) {
+			unlink_free_space(ctl, info);
+			kmem_cache_free(btrfs_free_space_cachep, info);
+		} else {
+			free_bitmap(ctl, info);
+		}
+		if (need_resched()) {
+			spin_unlock(&ctl->tree_lock);
+			cond_resched();
+			spin_lock(&ctl->tree_lock);
+		}
+	}
+}
+
+void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl)
+{
+	spin_lock(&ctl->tree_lock);
+	__btrfs_remove_free_space_cache_locked(ctl);
+	spin_unlock(&ctl->tree_lock);
+}
+
+void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
+{
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_cluster *cluster;
 	struct list_head *head;
 
-	spin_lock(&block_group->tree_lock);
+	spin_lock(&ctl->tree_lock);
 	while ((head = block_group->cluster_list.next) !=
 	       &block_group->cluster_list) {
 		cluster = list_entry(head, struct btrfs_free_cluster,
@@ -1760,60 +1929,46 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
 		WARN_ON(cluster->block_group != block_group);
 		__btrfs_return_cluster_to_free_space(block_group, cluster);
 		if (need_resched()) {
-			spin_unlock(&block_group->tree_lock);
-			cond_resched();
-			spin_lock(&block_group->tree_lock);
-		}
-	}
-
-	while ((node = rb_last(&block_group->free_space_offset)) != NULL) {
-		info = rb_entry(node, struct btrfs_free_space, offset_index);
-		if (!info->bitmap) {
-			unlink_free_space(block_group, info);
-			kmem_cache_free(btrfs_free_space_cachep, info);
-		} else {
-			free_bitmap(block_group, info);
-		}
-
-		if (need_resched()) {
-			spin_unlock(&block_group->tree_lock);
+			spin_unlock(&ctl->tree_lock);
 			cond_resched();
-			spin_lock(&block_group->tree_lock);
+			spin_lock(&ctl->tree_lock);
 		}
 	}
+	__btrfs_remove_free_space_cache_locked(ctl);
+	spin_unlock(&ctl->tree_lock);
 
-	spin_unlock(&block_group->tree_lock);
 }
 
 u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
 			       u64 offset, u64 bytes, u64 empty_size)
 {
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *entry = NULL;
 	u64 bytes_search = bytes + empty_size;
 	u64 ret = 0;
 
-	spin_lock(&block_group->tree_lock);
-	entry = find_free_space(block_group, &offset, &bytes_search, 0);
+	spin_lock(&ctl->tree_lock);
+	entry = find_free_space(ctl, &offset, &bytes_search);
 	if (!entry)
 		goto out;
 
 	ret = offset;
 	if (entry->bitmap) {
-		bitmap_clear_bits(block_group, entry, offset, bytes);
+		bitmap_clear_bits(ctl, entry, offset, bytes);
 		if (!entry->bytes)
-			free_bitmap(block_group, entry);
+			free_bitmap(ctl, entry);
 	} else {
-		unlink_free_space(block_group, entry);
+		unlink_free_space(ctl, entry);
 		entry->offset += bytes;
 		entry->bytes -= bytes;
 		if (!entry->bytes)
 			kmem_cache_free(btrfs_free_space_cachep, entry);
 		else
-			link_free_space(block_group, entry);
+			link_free_space(ctl, entry);
 	}
 
 out:
-	spin_unlock(&block_group->tree_lock);
+	spin_unlock(&ctl->tree_lock);
 
 	return ret;
 }
@@ -1830,6 +1985,7 @@ int btrfs_return_cluster_to_free_space(
 			       struct btrfs_block_group_cache *block_group,
 			       struct btrfs_free_cluster *cluster)
 {
+	struct btrfs_free_space_ctl *ctl;
 	int ret;
 
 	/* first, get a safe pointer to the block group */
@@ -1848,10 +2004,12 @@ int btrfs_return_cluster_to_free_space(
 	atomic_inc(&block_group->count);
 	spin_unlock(&cluster->lock);
 
+	ctl = block_group->free_space_ctl;
+
 	/* now return any extents the cluster had on it */
-	spin_lock(&block_group->tree_lock);
+	spin_lock(&ctl->tree_lock);
 	ret = __btrfs_return_cluster_to_free_space(block_group, cluster);
-	spin_unlock(&block_group->tree_lock);
+	spin_unlock(&ctl->tree_lock);
 
 	/* finally drop our ref */
 	btrfs_put_block_group(block_group);
@@ -1863,6 +2021,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
 				   struct btrfs_free_space *entry,
 				   u64 bytes, u64 min_start)
 {
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	int err;
 	u64 search_start = cluster->window_start;
 	u64 search_bytes = bytes;
@@ -1871,13 +2030,12 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
 	search_start = min_start;
 	search_bytes = bytes;
 
-	err = search_bitmap(block_group, entry, &search_start,
-			    &search_bytes);
+	err = search_bitmap(ctl, entry, &search_start, &search_bytes);
 	if (err)
 		return 0;
 
 	ret = search_start;
-	bitmap_clear_bits(block_group, entry, ret, bytes);
+	bitmap_clear_bits(ctl, entry, ret, bytes);
 
 	return ret;
 }
@@ -1891,6 +2049,7 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
 			     struct btrfs_free_cluster *cluster, u64 bytes,
 			     u64 min_start)
 {
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *entry = NULL;
 	struct rb_node *node;
 	u64 ret = 0;
@@ -1910,8 +2069,6 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
 	while(1) {
 		if (entry->bytes < bytes ||
 		    (!entry->bitmap && entry->offset < min_start)) {
-			struct rb_node *node;
-
 			node = rb_next(&entry->offset_index);
 			if (!node)
 				break;
@@ -1925,7 +2082,6 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
 						      cluster, entry, bytes,
 						      min_start);
 			if (ret == 0) {
-				struct rb_node *node;
 				node = rb_next(&entry->offset_index);
 				if (!node)
 					break;
@@ -1951,20 +2107,20 @@ out:
 	if (!ret)
 		return 0;
 
-	spin_lock(&block_group->tree_lock);
+	spin_lock(&ctl->tree_lock);
 
-	block_group->free_space -= bytes;
+	ctl->free_space -= bytes;
 	if (entry->bytes == 0) {
-		block_group->free_extents--;
+		ctl->free_extents--;
 		if (entry->bitmap) {
 			kfree(entry->bitmap);
-			block_group->total_bitmaps--;
-			recalculate_thresholds(block_group);
+			ctl->total_bitmaps--;
+			ctl->op->recalc_thresholds(ctl);
 		}
 		kmem_cache_free(btrfs_free_space_cachep, entry);
 	}
 
-	spin_unlock(&block_group->tree_lock);
+	spin_unlock(&ctl->tree_lock);
 
 	return ret;
 }
@@ -1974,6 +2130,7 @@ static int btrfs_bitmap_cluster(struct btrfs_block_group_cache *block_group,
 				struct btrfs_free_cluster *cluster,
 				u64 offset, u64 bytes, u64 min_bytes)
 {
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	unsigned long next_zero;
 	unsigned long i;
 	unsigned long search_bits;
@@ -2028,7 +2185,7 @@ again:
 
 	cluster->window_start = start * block_group->sectorsize +
 		entry->offset;
-	rb_erase(&entry->offset_index, &block_group->free_space_offset);
+	rb_erase(&entry->offset_index, &ctl->free_space_offset);
 	ret = tree_insert_offset(&cluster->root, entry->offset,
 				 &entry->offset_index, 1);
 	BUG_ON(ret);
@@ -2039,10 +2196,13 @@ again:
 /*
  * This searches the block group for just extents to fill the cluster with.
  */
-static int setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
-				   struct btrfs_free_cluster *cluster,
-				   u64 offset, u64 bytes, u64 min_bytes)
+static noinline int
+setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
+			struct btrfs_free_cluster *cluster,
+			struct list_head *bitmaps, u64 offset, u64 bytes,
+			u64 min_bytes)
 {
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *first = NULL;
 	struct btrfs_free_space *entry = NULL;
 	struct btrfs_free_space *prev = NULL;
@@ -2053,7 +2213,7 @@ static int setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
 	u64 max_extent;
 	u64 max_gap = 128 * 1024;
 
-	entry = tree_search_offset(block_group, offset, 0, 1);
+	entry = tree_search_offset(ctl, offset, 0, 1);
 	if (!entry)
 		return -ENOSPC;
 
@@ -2062,6 +2222,8 @@ static int setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
 	 * extent entry.
 	 */
 	while (entry->bitmap) {
+		if (list_empty(&entry->list))
+			list_add_tail(&entry->list, bitmaps);
 		node = rb_next(&entry->offset_index);
 		if (!node)
 			return -ENOSPC;
@@ -2081,8 +2243,12 @@ static int setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
 			return -ENOSPC;
 		entry = rb_entry(node, struct btrfs_free_space, offset_index);
 
-		if (entry->bitmap)
+		if (entry->bitmap) {
+			if (list_empty(&entry->list))
+				list_add_tail(&entry->list, bitmaps);
 			continue;
+		}
+
 		/*
 		 * we haven't filled the empty size and the window is
 		 * very large.  reset and try again
@@ -2119,7 +2285,7 @@ static int setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
 		if (entry->bitmap)
 			continue;
 
-		rb_erase(&entry->offset_index, &block_group->free_space_offset);
+		rb_erase(&entry->offset_index, &ctl->free_space_offset);
 		ret = tree_insert_offset(&cluster->root, entry->offset,
 					 &entry->offset_index, 0);
 		BUG_ON(ret);
@@ -2134,23 +2300,53 @@ static int setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
  * This specifically looks for bitmaps that may work in the cluster, we assume
  * that we have already failed to find extents that will work.
  */
-static int setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
-				struct btrfs_free_cluster *cluster,
-				u64 offset, u64 bytes, u64 min_bytes)
+static noinline int
+setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
+		     struct btrfs_free_cluster *cluster,
+		     struct list_head *bitmaps, u64 offset, u64 bytes,
+		     u64 min_bytes)
 {
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *entry;
 	struct rb_node *node;
 	int ret = -ENOSPC;
 
-	if (block_group->total_bitmaps == 0)
+	if (ctl->total_bitmaps == 0)
 		return -ENOSPC;
 
-	entry = tree_search_offset(block_group,
-				   offset_to_bitmap(block_group, offset),
-				   0, 1);
+	/*
+	 * First check our cached list of bitmaps and see if there is an entry
+	 * here that will work.
+	 */
+	list_for_each_entry(entry, bitmaps, list) {
+		if (entry->bytes < min_bytes)
+			continue;
+		ret = btrfs_bitmap_cluster(block_group, entry, cluster, offset,
+					   bytes, min_bytes);
+		if (!ret)
+			return 0;
+	}
+
+	/*
+	 * If we do have entries on our list and we are here then we didn't find
+	 * anything, so go ahead and get the next entry after the last entry in
+	 * this list and start the search from there.
+	 */
+	if (!list_empty(bitmaps)) {
+		entry = list_entry(bitmaps->prev, struct btrfs_free_space,
+				   list);
+		node = rb_next(&entry->offset_index);
+		if (!node)
+			return -ENOSPC;
+		entry = rb_entry(node, struct btrfs_free_space, offset_index);
+		goto search;
+	}
+
+	entry = tree_search_offset(ctl, offset_to_bitmap(ctl, offset), 0, 1);
 	if (!entry)
 		return -ENOSPC;
 
+search:
 	node = &entry->offset_index;
 	do {
 		entry = rb_entry(node, struct btrfs_free_space, offset_index);
@@ -2180,6 +2376,9 @@ int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
 			     struct btrfs_free_cluster *cluster,
 			     u64 offset, u64 bytes, u64 empty_size)
 {
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
+	struct list_head bitmaps;
+	struct btrfs_free_space *entry, *tmp;
 	u64 min_bytes;
 	int ret;
 
@@ -2199,14 +2398,14 @@ int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
 	} else
 		min_bytes = max(bytes, (bytes + empty_size) >> 2);
 
-	spin_lock(&block_group->tree_lock);
+	spin_lock(&ctl->tree_lock);
 
 	/*
 	 * If we know we don't have enough space to make a cluster don't even
 	 * bother doing all the work to try and find one.
 	 */
-	if (block_group->free_space < min_bytes) {
-		spin_unlock(&block_group->tree_lock);
+	if (ctl->free_space < min_bytes) {
+		spin_unlock(&ctl->tree_lock);
 		return -ENOSPC;
 	}
 
@@ -2218,11 +2417,16 @@ int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	ret = setup_cluster_no_bitmap(block_group, cluster, offset, bytes,
-				      min_bytes);
+	INIT_LIST_HEAD(&bitmaps);
+	ret = setup_cluster_no_bitmap(block_group, cluster, &bitmaps, offset,
+				      bytes, min_bytes);
 	if (ret)
-		ret = setup_cluster_bitmap(block_group, cluster, offset,
-					   bytes, min_bytes);
+		ret = setup_cluster_bitmap(block_group, cluster, &bitmaps,
+					   offset, bytes, min_bytes);
+
+	/* Clear our temporary list */
+	list_for_each_entry_safe(entry, tmp, &bitmaps, list)
+		list_del_init(&entry->list);
 
 	if (!ret) {
 		atomic_inc(&block_group->count);
@@ -2232,7 +2436,7 @@ int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
 	}
 out:
 	spin_unlock(&cluster->lock);
-	spin_unlock(&block_group->tree_lock);
+	spin_unlock(&ctl->tree_lock);
 
 	return ret;
 }
@@ -2253,6 +2457,7 @@ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster)
 int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
 			   u64 *trimmed, u64 start, u64 end, u64 minlen)
 {
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *entry = NULL;
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	u64 bytes = 0;
@@ -2262,52 +2467,50 @@ int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
 	*trimmed = 0;
 
 	while (start < end) {
-		spin_lock(&block_group->tree_lock);
+		spin_lock(&ctl->tree_lock);
 
-		if (block_group->free_space < minlen) {
-			spin_unlock(&block_group->tree_lock);
+		if (ctl->free_space < minlen) {
+			spin_unlock(&ctl->tree_lock);
 			break;
 		}
 
-		entry = tree_search_offset(block_group, start, 0, 1);
+		entry = tree_search_offset(ctl, start, 0, 1);
 		if (!entry)
-			entry = tree_search_offset(block_group,
-						   offset_to_bitmap(block_group,
-								    start),
+			entry = tree_search_offset(ctl,
+						   offset_to_bitmap(ctl, start),
 						   1, 1);
 
 		if (!entry || entry->offset >= end) {
-			spin_unlock(&block_group->tree_lock);
+			spin_unlock(&ctl->tree_lock);
 			break;
 		}
 
 		if (entry->bitmap) {
-			ret = search_bitmap(block_group, entry, &start, &bytes);
+			ret = search_bitmap(ctl, entry, &start, &bytes);
 			if (!ret) {
 				if (start >= end) {
-					spin_unlock(&block_group->tree_lock);
+					spin_unlock(&ctl->tree_lock);
 					break;
 				}
 				bytes = min(bytes, end - start);
-				bitmap_clear_bits(block_group, entry,
-						  start, bytes);
+				bitmap_clear_bits(ctl, entry, start, bytes);
 				if (entry->bytes == 0)
-					free_bitmap(block_group, entry);
+					free_bitmap(ctl, entry);
 			} else {
 				start = entry->offset + BITS_PER_BITMAP *
 					block_group->sectorsize;
-				spin_unlock(&block_group->tree_lock);
+				spin_unlock(&ctl->tree_lock);
 				ret = 0;
 				continue;
 			}
 		} else {
 			start = entry->offset;
 			bytes = min(entry->bytes, end - start);
-			unlink_free_space(block_group, entry);
+			unlink_free_space(ctl, entry);
 			kmem_cache_free(btrfs_free_space_cachep, entry);
 		}
 
-		spin_unlock(&block_group->tree_lock);
+		spin_unlock(&ctl->tree_lock);
 
 		if (bytes >= minlen) {
 			int update_ret;
@@ -2319,8 +2522,7 @@ int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
 							 bytes,
 							 &actually_trimmed);
 
-			btrfs_add_free_space(block_group,
-					     start, bytes);
+			btrfs_add_free_space(block_group, start, bytes);
 			if (!update_ret)
 				btrfs_update_reserved_bytes(block_group,
 							    bytes, 0, 1);
@@ -2342,3 +2544,150 @@ int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
 
 	return ret;
 }
+
+/*
+ * Find the left-most item in the cache tree, and then return the
+ * smallest inode number in the item.
+ *
+ * Note: the returned inode number may not be the smallest one in
+ * the tree, if the left-most item is a bitmap.
+ */
+u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root)
+{
+	struct btrfs_free_space_ctl *ctl = fs_root->free_ino_ctl;
+	struct btrfs_free_space *entry = NULL;
+	u64 ino = 0;
+
+	spin_lock(&ctl->tree_lock);
+
+	if (RB_EMPTY_ROOT(&ctl->free_space_offset))
+		goto out;
+
+	entry = rb_entry(rb_first(&ctl->free_space_offset),
+			 struct btrfs_free_space, offset_index);
+
+	if (!entry->bitmap) {
+		ino = entry->offset;
+
+		unlink_free_space(ctl, entry);
+		entry->offset++;
+		entry->bytes--;
+		if (!entry->bytes)
+			kmem_cache_free(btrfs_free_space_cachep, entry);
+		else
+			link_free_space(ctl, entry);
+	} else {
+		u64 offset = 0;
+		u64 count = 1;
+		int ret;
+
+		ret = search_bitmap(ctl, entry, &offset, &count);
+		BUG_ON(ret);
+
+		ino = offset;
+		bitmap_clear_bits(ctl, entry, offset, 1);
+		if (entry->bytes == 0)
+			free_bitmap(ctl, entry);
+	}
+out:
+	spin_unlock(&ctl->tree_lock);
+
+	return ino;
+}
+
+struct inode *lookup_free_ino_inode(struct btrfs_root *root,
+				    struct btrfs_path *path)
+{
+	struct inode *inode = NULL;
+
+	spin_lock(&root->cache_lock);
+	if (root->cache_inode)
+		inode = igrab(root->cache_inode);
+	spin_unlock(&root->cache_lock);
+	if (inode)
+		return inode;
+
+	inode = __lookup_free_space_inode(root, path, 0);
+	if (IS_ERR(inode))
+		return inode;
+
+	spin_lock(&root->cache_lock);
+	if (!btrfs_fs_closing(root->fs_info))
+		root->cache_inode = igrab(inode);
+	spin_unlock(&root->cache_lock);
+
+	return inode;
+}
+
+int create_free_ino_inode(struct btrfs_root *root,
+			  struct btrfs_trans_handle *trans,
+			  struct btrfs_path *path)
+{
+	return __create_free_space_inode(root, trans, path,
+					 BTRFS_FREE_INO_OBJECTID, 0);
+}
+
+int load_free_ino_cache(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
+{
+	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+	struct btrfs_path *path;
+	struct inode *inode;
+	int ret = 0;
+	u64 root_gen = btrfs_root_generation(&root->root_item);
+
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return 0;
+
+	/*
+	 * If we're unmounting then just return, since this does a search on the
+	 * normal root and not the commit root and we could deadlock.
+	 */
+	if (btrfs_fs_closing(fs_info))
+		return 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return 0;
+
+	inode = lookup_free_ino_inode(root, path);
+	if (IS_ERR(inode))
+		goto out;
+
+	if (root_gen != BTRFS_I(inode)->generation)
+		goto out_put;
+
+	ret = __load_free_space_cache(root, inode, ctl, path, 0);
+
+	if (ret < 0)
+		printk(KERN_ERR "btrfs: failed to load free ino cache for "
+		       "root %llu\n", root->root_key.objectid);
+out_put:
+	iput(inode);
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
+int btrfs_write_out_ino_cache(struct btrfs_root *root,
+			      struct btrfs_trans_handle *trans,
+			      struct btrfs_path *path)
+{
+	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+	struct inode *inode;
+	int ret;
+
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return 0;
+
+	inode = lookup_free_ino_inode(root, path);
+	if (IS_ERR(inode))
+		return 0;
+
+	ret = __btrfs_write_out_cache(root, inode, ctl, NULL, trans, path, 0);
+	if (ret < 0)
+		printk(KERN_ERR "btrfs: failed to write free ino cache "
+		       "for root %llu\n", root->root_key.objectid);
+
+	iput(inode);
+	return ret;
+}
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 65c3b935289f..8f2613f779ed 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -27,6 +27,25 @@ struct btrfs_free_space {
 	struct list_head list;
 };
 
+struct btrfs_free_space_ctl {
+	spinlock_t tree_lock;
+	struct rb_root free_space_offset;
+	u64 free_space;
+	int extents_thresh;
+	int free_extents;
+	int total_bitmaps;
+	int unit;
+	u64 start;
+	struct btrfs_free_space_op *op;
+	void *private;
+};
+
+struct btrfs_free_space_op {
+	void (*recalc_thresholds)(struct btrfs_free_space_ctl *ctl);
+	bool (*use_bitmap)(struct btrfs_free_space_ctl *ctl,
+			   struct btrfs_free_space *info);
+};
+
 struct inode *lookup_free_space_inode(struct btrfs_root *root,
 				      struct btrfs_block_group_cache
 				      *block_group, struct btrfs_path *path);
@@ -45,17 +64,38 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 			  struct btrfs_trans_handle *trans,
 			  struct btrfs_block_group_cache *block_group,
 			  struct btrfs_path *path);
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
-			 u64 bytenr, u64 size);
+
+struct inode *lookup_free_ino_inode(struct btrfs_root *root,
+				    struct btrfs_path *path);
+int create_free_ino_inode(struct btrfs_root *root,
+			  struct btrfs_trans_handle *trans,
+			  struct btrfs_path *path);
+int load_free_ino_cache(struct btrfs_fs_info *fs_info,
+			struct btrfs_root *root);
+int btrfs_write_out_ino_cache(struct btrfs_root *root,
+			      struct btrfs_trans_handle *trans,
+			      struct btrfs_path *path);
+
+void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group);
+int __btrfs_add_free_space(struct btrfs_free_space_ctl *ctl,
+			   u64 bytenr, u64 size);
+static inline int
+btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
+		     u64 bytenr, u64 size)
+{
+	return __btrfs_add_free_space(block_group->free_space_ctl,
+				      bytenr, size);
+}
 int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
 			    u64 bytenr, u64 size);
+void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl);
 void btrfs_remove_free_space_cache(struct btrfs_block_group_cache
-				   *block_group);
+				     *block_group);
 u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
 			       u64 offset, u64 bytes, u64 empty_size);
+u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root);
 void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
 			   u64 bytes);
-u64 btrfs_block_group_free_space(struct btrfs_block_group_cache *block_group);
 int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root,
 			     struct btrfs_block_group_cache *block_group,
diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c
index 64f1150bb48d..baa74f3db691 100644
--- a/fs/btrfs/inode-item.c
+++ b/fs/btrfs/inode-item.c
@@ -130,7 +130,6 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans,
 			      item_size - (ptr + sub_item_len - item_start));
 	ret = btrfs_truncate_item(trans, root, path,
 				  item_size - sub_item_len, 1);
-	BUG_ON(ret);
 out:
 	btrfs_free_path(path);
 	return ret;
@@ -167,7 +166,6 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
 
 		old_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
 		ret = btrfs_extend_item(trans, root, path, ins_len);
-		BUG_ON(ret);
 		ref = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				     struct btrfs_inode_ref);
 		ref = (struct btrfs_inode_ref *)((unsigned long)ref + old_size);
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index c05a08f4c411..b4087e0fa871 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -16,11 +16,476 @@
  * Boston, MA 021110-1307, USA.
  */
 
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/pagemap.h>
+
 #include "ctree.h"
 #include "disk-io.h"
+#include "free-space-cache.h"
+#include "inode-map.h"
 #include "transaction.h"
 
-int btrfs_find_highest_inode(struct btrfs_root *root, u64 *objectid)
+static int caching_kthread(void *data)
+{
+	struct btrfs_root *root = data;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+	struct btrfs_key key;
+	struct btrfs_path *path;
+	struct extent_buffer *leaf;
+	u64 last = (u64)-1;
+	int slot;
+	int ret;
+
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	/* Since the commit root is read-only, we can safely skip locking. */
+	path->skip_locking = 1;
+	path->search_commit_root = 1;
+	path->reada = 2;
+
+	key.objectid = BTRFS_FIRST_FREE_OBJECTID;
+	key.offset = 0;
+	key.type = BTRFS_INODE_ITEM_KEY;
+again:
+	/* need to make sure the commit_root doesn't disappear */
+	mutex_lock(&root->fs_commit_mutex);
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+
+	while (1) {
+		if (btrfs_fs_closing(fs_info))
+			goto out;
+
+		leaf = path->nodes[0];
+		slot = path->slots[0];
+		if (slot >= btrfs_header_nritems(leaf)) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto out;
+			else if (ret > 0)
+				break;
+
+			if (need_resched() ||
+			    btrfs_transaction_in_commit(fs_info)) {
+				leaf = path->nodes[0];
+
+				if (btrfs_header_nritems(leaf) == 0) {
+					WARN_ON(1);
+					break;
+				}
+
+				/*
+				 * Save the key so we can advances forward
+				 * in the next search.
+				 */
+				btrfs_item_key_to_cpu(leaf, &key, 0);
+				btrfs_release_path(path);
+				root->cache_progress = last;
+				mutex_unlock(&root->fs_commit_mutex);
+				schedule_timeout(1);
+				goto again;
+			} else
+				continue;
+		}
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+
+		if (key.type != BTRFS_INODE_ITEM_KEY)
+			goto next;
+
+		if (key.objectid >= root->highest_objectid)
+			break;
+
+		if (last != (u64)-1 && last + 1 != key.objectid) {
+			__btrfs_add_free_space(ctl, last + 1,
+					       key.objectid - last - 1);
+			wake_up(&root->cache_wait);
+		}
+
+		last = key.objectid;
+next:
+		path->slots[0]++;
+	}
+
+	if (last < root->highest_objectid - 1) {
+		__btrfs_add_free_space(ctl, last + 1,
+				       root->highest_objectid - last - 1);
+	}
+
+	spin_lock(&root->cache_lock);
+	root->cached = BTRFS_CACHE_FINISHED;
+	spin_unlock(&root->cache_lock);
+
+	root->cache_progress = (u64)-1;
+	btrfs_unpin_free_ino(root);
+out:
+	wake_up(&root->cache_wait);
+	mutex_unlock(&root->fs_commit_mutex);
+
+	btrfs_free_path(path);
+
+	return ret;
+}
+
+static void start_caching(struct btrfs_root *root)
+{
+	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+	struct task_struct *tsk;
+	int ret;
+	u64 objectid;
+
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return;
+
+	spin_lock(&root->cache_lock);
+	if (root->cached != BTRFS_CACHE_NO) {
+		spin_unlock(&root->cache_lock);
+		return;
+	}
+
+	root->cached = BTRFS_CACHE_STARTED;
+	spin_unlock(&root->cache_lock);
+
+	ret = load_free_ino_cache(root->fs_info, root);
+	if (ret == 1) {
+		spin_lock(&root->cache_lock);
+		root->cached = BTRFS_CACHE_FINISHED;
+		spin_unlock(&root->cache_lock);
+		return;
+	}
+
+	/*
+	 * It can be quite time-consuming to fill the cache by searching
+	 * through the extent tree, and this can keep ino allocation path
+	 * waiting. Therefore at start we quickly find out the highest
+	 * inode number and we know we can use inode numbers which fall in
+	 * [highest_ino + 1, BTRFS_LAST_FREE_OBJECTID].
+	 */
+	ret = btrfs_find_free_objectid(root, &objectid);
+	if (!ret && objectid <= BTRFS_LAST_FREE_OBJECTID) {
+		__btrfs_add_free_space(ctl, objectid,
+				       BTRFS_LAST_FREE_OBJECTID - objectid + 1);
+	}
+
+	tsk = kthread_run(caching_kthread, root, "btrfs-ino-cache-%llu\n",
+			  root->root_key.objectid);
+	BUG_ON(IS_ERR(tsk));
+}
+
+int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid)
+{
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return btrfs_find_free_objectid(root, objectid);
+
+again:
+	*objectid = btrfs_find_ino_for_alloc(root);
+
+	if (*objectid != 0)
+		return 0;
+
+	start_caching(root);
+
+	wait_event(root->cache_wait,
+		   root->cached == BTRFS_CACHE_FINISHED ||
+		   root->free_ino_ctl->free_space > 0);
+
+	if (root->cached == BTRFS_CACHE_FINISHED &&
+	    root->free_ino_ctl->free_space == 0)
+		return -ENOSPC;
+	else
+		goto again;
+}
+
+void btrfs_return_ino(struct btrfs_root *root, u64 objectid)
+{
+	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+	struct btrfs_free_space_ctl *pinned = root->free_ino_pinned;
+
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return;
+
+again:
+	if (root->cached == BTRFS_CACHE_FINISHED) {
+		__btrfs_add_free_space(ctl, objectid, 1);
+	} else {
+		/*
+		 * If we are in the process of caching free ino chunks,
+		 * to avoid adding the same inode number to the free_ino
+		 * tree twice due to cross transaction, we'll leave it
+		 * in the pinned tree until a transaction is committed
+		 * or the caching work is done.
+		 */
+
+		mutex_lock(&root->fs_commit_mutex);
+		spin_lock(&root->cache_lock);
+		if (root->cached == BTRFS_CACHE_FINISHED) {
+			spin_unlock(&root->cache_lock);
+			mutex_unlock(&root->fs_commit_mutex);
+			goto again;
+		}
+		spin_unlock(&root->cache_lock);
+
+		start_caching(root);
+
+		if (objectid <= root->cache_progress ||
+		    objectid > root->highest_objectid)
+			__btrfs_add_free_space(ctl, objectid, 1);
+		else
+			__btrfs_add_free_space(pinned, objectid, 1);
+
+		mutex_unlock(&root->fs_commit_mutex);
+	}
+}
+
+/*
+ * When a transaction is committed, we'll move those inode numbers which
+ * are smaller than root->cache_progress from pinned tree to free_ino tree,
+ * and others will just be dropped, because the commit root we were
+ * searching has changed.
+ *
+ * Must be called with root->fs_commit_mutex held
+ */
+void btrfs_unpin_free_ino(struct btrfs_root *root)
+{
+	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+	struct rb_root *rbroot = &root->free_ino_pinned->free_space_offset;
+	struct btrfs_free_space *info;
+	struct rb_node *n;
+	u64 count;
+
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return;
+
+	while (1) {
+		n = rb_first(rbroot);
+		if (!n)
+			break;
+
+		info = rb_entry(n, struct btrfs_free_space, offset_index);
+		BUG_ON(info->bitmap);
+
+		if (info->offset > root->cache_progress)
+			goto free;
+		else if (info->offset + info->bytes > root->cache_progress)
+			count = root->cache_progress - info->offset + 1;
+		else
+			count = info->bytes;
+
+		__btrfs_add_free_space(ctl, info->offset, count);
+free:
+		rb_erase(&info->offset_index, rbroot);
+		kfree(info);
+	}
+}
+
+#define INIT_THRESHOLD	(((1024 * 32) / 2) / sizeof(struct btrfs_free_space))
+#define INODES_PER_BITMAP (PAGE_CACHE_SIZE * 8)
+
+/*
+ * The goal is to keep the memory used by the free_ino tree won't
+ * exceed the memory if we use bitmaps only.
+ */
+static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
+{
+	struct btrfs_free_space *info;
+	struct rb_node *n;
+	int max_ino;
+	int max_bitmaps;
+
+	n = rb_last(&ctl->free_space_offset);
+	if (!n) {
+		ctl->extents_thresh = INIT_THRESHOLD;
+		return;
+	}
+	info = rb_entry(n, struct btrfs_free_space, offset_index);
+
+	/*
+	 * Find the maximum inode number in the filesystem. Note we
+	 * ignore the fact that this can be a bitmap, because we are
+	 * not doing precise calculation.
+	 */
+	max_ino = info->bytes - 1;
+
+	max_bitmaps = ALIGN(max_ino, INODES_PER_BITMAP) / INODES_PER_BITMAP;
+	if (max_bitmaps <= ctl->total_bitmaps) {
+		ctl->extents_thresh = 0;
+		return;
+	}
+
+	ctl->extents_thresh = (max_bitmaps - ctl->total_bitmaps) *
+				PAGE_CACHE_SIZE / sizeof(*info);
+}
+
+/*
+ * We don't fall back to bitmap, if we are below the extents threshold
+ * or this chunk of inode numbers is a big one.
+ */
+static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
+		       struct btrfs_free_space *info)
+{
+	if (ctl->free_extents < ctl->extents_thresh ||
+	    info->bytes > INODES_PER_BITMAP / 10)
+		return false;
+
+	return true;
+}
+
+static struct btrfs_free_space_op free_ino_op = {
+	.recalc_thresholds	= recalculate_thresholds,
+	.use_bitmap		= use_bitmap,
+};
+
+static void pinned_recalc_thresholds(struct btrfs_free_space_ctl *ctl)
+{
+}
+
+static bool pinned_use_bitmap(struct btrfs_free_space_ctl *ctl,
+			      struct btrfs_free_space *info)
+{
+	/*
+	 * We always use extents for two reasons:
+	 *
+	 * - The pinned tree is only used during the process of caching
+	 *   work.
+	 * - Make code simpler. See btrfs_unpin_free_ino().
+	 */
+	return false;
+}
+
+static struct btrfs_free_space_op pinned_free_ino_op = {
+	.recalc_thresholds	= pinned_recalc_thresholds,
+	.use_bitmap		= pinned_use_bitmap,
+};
+
+void btrfs_init_free_ino_ctl(struct btrfs_root *root)
+{
+	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+	struct btrfs_free_space_ctl *pinned = root->free_ino_pinned;
+
+	spin_lock_init(&ctl->tree_lock);
+	ctl->unit = 1;
+	ctl->start = 0;
+	ctl->private = NULL;
+	ctl->op = &free_ino_op;
+
+	/*
+	 * Initially we allow to use 16K of ram to cache chunks of
+	 * inode numbers before we resort to bitmaps. This is somewhat
+	 * arbitrary, but it will be adjusted in runtime.
+	 */
+	ctl->extents_thresh = INIT_THRESHOLD;
+
+	spin_lock_init(&pinned->tree_lock);
+	pinned->unit = 1;
+	pinned->start = 0;
+	pinned->private = NULL;
+	pinned->extents_thresh = 0;
+	pinned->op = &pinned_free_ino_op;
+}
+
+int btrfs_save_ino_cache(struct btrfs_root *root,
+			 struct btrfs_trans_handle *trans)
+{
+	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+	struct btrfs_path *path;
+	struct inode *inode;
+	u64 alloc_hint = 0;
+	int ret;
+	int prealloc;
+	bool retry = false;
+
+	/* only fs tree and subvol/snap needs ino cache */
+	if (root->root_key.objectid != BTRFS_FS_TREE_OBJECTID &&
+	    (root->root_key.objectid < BTRFS_FIRST_FREE_OBJECTID ||
+	     root->root_key.objectid > BTRFS_LAST_FREE_OBJECTID))
+		return 0;
+
+	/* Don't save inode cache if we are deleting this root */
+	if (btrfs_root_refs(&root->root_item) == 0 &&
+	    root != root->fs_info->tree_root)
+		return 0;
+
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+again:
+	inode = lookup_free_ino_inode(root, path);
+	if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
+		ret = PTR_ERR(inode);
+		goto out;
+	}
+
+	if (IS_ERR(inode)) {
+		BUG_ON(retry);
+		retry = true;
+
+		ret = create_free_ino_inode(root, trans, path);
+		if (ret)
+			goto out;
+		goto again;
+	}
+
+	BTRFS_I(inode)->generation = 0;
+	ret = btrfs_update_inode(trans, root, inode);
+	WARN_ON(ret);
+
+	if (i_size_read(inode) > 0) {
+		ret = btrfs_truncate_free_space_cache(root, trans, path, inode);
+		if (ret)
+			goto out_put;
+	}
+
+	spin_lock(&root->cache_lock);
+	if (root->cached != BTRFS_CACHE_FINISHED) {
+		ret = -1;
+		spin_unlock(&root->cache_lock);
+		goto out_put;
+	}
+	spin_unlock(&root->cache_lock);
+
+	spin_lock(&ctl->tree_lock);
+	prealloc = sizeof(struct btrfs_free_space) * ctl->free_extents;
+	prealloc = ALIGN(prealloc, PAGE_CACHE_SIZE);
+	prealloc += ctl->total_bitmaps * PAGE_CACHE_SIZE;
+	spin_unlock(&ctl->tree_lock);
+
+	/* Just to make sure we have enough space */
+	prealloc += 8 * PAGE_CACHE_SIZE;
+
+	ret = btrfs_check_data_free_space(inode, prealloc);
+	if (ret)
+		goto out_put;
+
+	ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
+					      prealloc, prealloc, &alloc_hint);
+	if (ret)
+		goto out_put;
+	btrfs_free_reserved_data_space(inode, prealloc);
+
+out_put:
+	iput(inode);
+out:
+	if (ret == 0)
+		ret = btrfs_write_out_ino_cache(root, trans, path);
+
+	btrfs_free_path(path);
+	return ret;
+}
+
+static int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
 {
 	struct btrfs_path *path;
 	int ret;
@@ -55,15 +520,14 @@ error:
 	return ret;
 }
 
-int btrfs_find_free_objectid(struct btrfs_trans_handle *trans,
-			     struct btrfs_root *root,
-			     u64 dirid, u64 *objectid)
+int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid)
 {
 	int ret;
 	mutex_lock(&root->objectid_mutex);
 
 	if (unlikely(root->highest_objectid < BTRFS_FIRST_FREE_OBJECTID)) {
-		ret = btrfs_find_highest_inode(root, &root->highest_objectid);
+		ret = btrfs_find_highest_objectid(root,
+						  &root->highest_objectid);
 		if (ret)
 			goto out;
 	}
diff --git a/fs/btrfs/inode-map.h b/fs/btrfs/inode-map.h
new file mode 100644
index 000000000000..ddb347bfee23
--- /dev/null
+++ b/fs/btrfs/inode-map.h
@@ -0,0 +1,13 @@
+#ifndef __BTRFS_INODE_MAP
+#define __BTRFS_INODE_MAP
+
+void btrfs_init_free_ino_ctl(struct btrfs_root *root);
+void btrfs_unpin_free_ino(struct btrfs_root *root);
+void btrfs_return_ino(struct btrfs_root *root, u64 objectid);
+int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid);
+int btrfs_save_ino_cache(struct btrfs_root *root,
+			 struct btrfs_trans_handle *trans);
+
+int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid);
+
+#endif
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 7cd8ab0ef04d..d340f63d8f07 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -37,6 +37,7 @@
 #include <linux/posix_acl.h>
 #include <linux/falloc.h>
 #include <linux/slab.h>
+#include <linux/ratelimit.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"
@@ -51,6 +52,7 @@
 #include "compression.h"
 #include "locking.h"
 #include "free-space-cache.h"
+#include "inode-map.h"
 
 struct btrfs_iget_args {
 	u64 ino;
@@ -136,9 +138,8 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 
 	path->leave_spinning = 1;
-	btrfs_set_trans_block_group(trans, inode);
 
-	key.objectid = inode->i_ino;
+	key.objectid = btrfs_ino(inode);
 	key.offset = start;
 	btrfs_set_key_type(&key, BTRFS_EXTENT_DATA_KEY);
 	datasize = btrfs_file_extent_calc_inline_size(cur_size);
@@ -340,6 +341,10 @@ static noinline int compress_file_range(struct inode *inode,
 	int will_compress;
 	int compress_type = root->fs_info->compress_type;
 
+	/* if this is a small write inside eof, kick off a defragbot */
+	if (end <= BTRFS_I(inode)->disk_i_size && (end - start + 1) < 16 * 1024)
+		btrfs_add_inode_defrag(NULL, inode);
+
 	actual_end = min_t(u64, isize, end + 1);
 again:
 	will_compress = 0;
@@ -420,9 +425,8 @@ again:
 		}
 	}
 	if (start == 0) {
-		trans = btrfs_join_transaction(root, 1);
+		trans = btrfs_join_transaction(root);
 		BUG_ON(IS_ERR(trans));
-		btrfs_set_trans_block_group(trans, inode);
 		trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 		/* lets try to make an inline extent */
@@ -617,8 +621,9 @@ retry:
 			    async_extent->start + async_extent->ram_size - 1,
 			    GFP_NOFS);
 
-		trans = btrfs_join_transaction(root, 1);
+		trans = btrfs_join_transaction(root);
 		BUG_ON(IS_ERR(trans));
+		trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 		ret = btrfs_reserve_extent(trans, root,
 					   async_extent->compressed_size,
 					   async_extent->compressed_size,
@@ -649,7 +654,7 @@ retry:
 					async_extent->start +
 					async_extent->ram_size - 1, 0);
 
-		em = alloc_extent_map(GFP_NOFS);
+		em = alloc_extent_map();
 		BUG_ON(!em);
 		em->start = async_extent->start;
 		em->len = async_extent->ram_size;
@@ -745,6 +750,15 @@ static u64 get_extent_allocation_hint(struct inode *inode, u64 start,
 	return alloc_hint;
 }
 
+static inline bool is_free_space_inode(struct btrfs_root *root,
+				       struct inode *inode)
+{
+	if (root == root->fs_info->tree_root ||
+	    BTRFS_I(inode)->location.objectid == BTRFS_FREE_INO_OBJECTID)
+		return true;
+	return false;
+}
+
 /*
  * when extent_io.c finds a delayed allocation range in the file,
  * the call backs end up in this code.  The basic idea is to
@@ -777,10 +791,9 @@ static noinline int cow_file_range(struct inode *inode,
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	int ret = 0;
 
-	BUG_ON(root == root->fs_info->tree_root);
-	trans = btrfs_join_transaction(root, 1);
+	BUG_ON(is_free_space_inode(root, inode));
+	trans = btrfs_join_transaction(root);
 	BUG_ON(IS_ERR(trans));
-	btrfs_set_trans_block_group(trans, inode);
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	num_bytes = (end - start + blocksize) & ~(blocksize - 1);
@@ -788,6 +801,10 @@ static noinline int cow_file_range(struct inode *inode,
 	disk_num_bytes = num_bytes;
 	ret = 0;
 
+	/* if this is a small write inside eof, kick off defrag */
+	if (end <= BTRFS_I(inode)->disk_i_size && num_bytes < 64 * 1024)
+		btrfs_add_inode_defrag(trans, inode);
+
 	if (start == 0) {
 		/* lets try to make an inline extent */
 		ret = cow_file_range_inline(trans, root, inode,
@@ -826,7 +843,7 @@ static noinline int cow_file_range(struct inode *inode,
 					   (u64)-1, &ins, 1);
 		BUG_ON(ret);
 
-		em = alloc_extent_map(GFP_NOFS);
+		em = alloc_extent_map();
 		BUG_ON(!em);
 		em->start = start;
 		em->orig_start = em->start;
@@ -1008,7 +1025,7 @@ static noinline int csum_exist_in_range(struct btrfs_root *root,
 	LIST_HEAD(list);
 
 	ret = btrfs_lookup_csums_range(root->fs_info->csum_root, bytenr,
-				       bytenr + num_bytes - 1, &list);
+				       bytenr + num_bytes - 1, &list, 0);
 	if (ret == 0 && list_empty(&list))
 		return 0;
 
@@ -1049,29 +1066,33 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 	int type;
 	int nocow;
 	int check_prev = 1;
-	bool nolock = false;
+	bool nolock;
+	u64 ino = btrfs_ino(inode);
 
 	path = btrfs_alloc_path();
 	BUG_ON(!path);
-	if (root == root->fs_info->tree_root) {
-		nolock = true;
-		trans = btrfs_join_transaction_nolock(root, 1);
-	} else {
-		trans = btrfs_join_transaction(root, 1);
-	}
+
+	nolock = is_free_space_inode(root, inode);
+
+	if (nolock)
+		trans = btrfs_join_transaction_nolock(root);
+	else
+		trans = btrfs_join_transaction(root);
+
 	BUG_ON(IS_ERR(trans));
+	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	cow_start = (u64)-1;
 	cur_offset = start;
 	while (1) {
-		ret = btrfs_lookup_file_extent(trans, root, path, inode->i_ino,
+		ret = btrfs_lookup_file_extent(trans, root, path, ino,
 					       cur_offset, 0);
 		BUG_ON(ret < 0);
 		if (ret > 0 && path->slots[0] > 0 && check_prev) {
 			leaf = path->nodes[0];
 			btrfs_item_key_to_cpu(leaf, &found_key,
 					      path->slots[0] - 1);
-			if (found_key.objectid == inode->i_ino &&
+			if (found_key.objectid == ino &&
 			    found_key.type == BTRFS_EXTENT_DATA_KEY)
 				path->slots[0]--;
 		}
@@ -1092,7 +1113,7 @@ next_slot:
 		num_bytes = 0;
 		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
 
-		if (found_key.objectid > inode->i_ino ||
+		if (found_key.objectid > ino ||
 		    found_key.type > BTRFS_EXTENT_DATA_KEY ||
 		    found_key.offset > end)
 			break;
@@ -1127,7 +1148,7 @@ next_slot:
 				goto out_check;
 			if (btrfs_extent_readonly(root, disk_bytenr))
 				goto out_check;
-			if (btrfs_cross_ref_exist(trans, root, inode->i_ino,
+			if (btrfs_cross_ref_exist(trans, root, ino,
 						  found_key.offset -
 						  extent_offset, disk_bytenr))
 				goto out_check;
@@ -1164,7 +1185,7 @@ out_check:
 			goto next_slot;
 		}
 
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		if (cow_start != (u64)-1) {
 			ret = cow_file_range(inode, locked_page, cow_start,
 					found_key.offset - 1, page_started,
@@ -1177,7 +1198,7 @@ out_check:
 			struct extent_map *em;
 			struct extent_map_tree *em_tree;
 			em_tree = &BTRFS_I(inode)->extent_tree;
-			em = alloc_extent_map(GFP_NOFS);
+			em = alloc_extent_map();
 			BUG_ON(!em);
 			em->start = cur_offset;
 			em->orig_start = em->start;
@@ -1222,7 +1243,7 @@ out_check:
 		if (cur_offset > end)
 			break;
 	}
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	if (cur_offset <= end && cow_start == (u64)-1)
 		cow_start = cur_offset;
@@ -1310,14 +1331,13 @@ static int btrfs_set_bit_hook(struct inode *inode,
 
 	/*
 	 * set_bit and clear bit hooks normally require _irqsave/restore
-	 * but in this case, we are only testeing for the DELALLOC
+	 * but in this case, we are only testing for the DELALLOC
 	 * bit, which is only set or cleared with irqs on
 	 */
 	if (!(state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
 		struct btrfs_root *root = BTRFS_I(inode)->root;
 		u64 len = state->end + 1 - state->start;
-		int do_list = (root->root_key.objectid !=
-			       BTRFS_ROOT_TREE_OBJECTID);
+		bool do_list = !is_free_space_inode(root, inode);
 
 		if (*bits & EXTENT_FIRST_DELALLOC)
 			*bits &= ~EXTENT_FIRST_DELALLOC;
@@ -1344,14 +1364,13 @@ static int btrfs_clear_bit_hook(struct inode *inode,
 {
 	/*
 	 * set_bit and clear bit hooks normally require _irqsave/restore
-	 * but in this case, we are only testeing for the DELALLOC
+	 * but in this case, we are only testing for the DELALLOC
 	 * bit, which is only set or cleared with irqs on
 	 */
 	if ((state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
 		struct btrfs_root *root = BTRFS_I(inode)->root;
 		u64 len = state->end + 1 - state->start;
-		int do_list = (root->root_key.objectid !=
-			       BTRFS_ROOT_TREE_OBJECTID);
+		bool do_list = !is_free_space_inode(root, inode);
 
 		if (*bits & EXTENT_FIRST_DELALLOC)
 			*bits &= ~EXTENT_FIRST_DELALLOC;
@@ -1458,7 +1477,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 
 	skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
-	if (root == root->fs_info->tree_root)
+	if (is_free_space_inode(root, inode))
 		ret = btrfs_bio_wq_end_io(root->fs_info, bio, 2);
 	else
 		ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
@@ -1500,8 +1519,6 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_ordered_sum *sum;
 
-	btrfs_set_trans_block_group(trans, inode);
-
 	list_for_each_entry(sum, list, list) {
 		btrfs_csum_file_blocks(trans,
 		       BTRFS_I(inode)->root->fs_info->csum_root, sum);
@@ -1644,7 +1661,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
 				 &hint, 0);
 	BUG_ON(ret);
 
-	ins.objectid = inode->i_ino;
+	ins.objectid = btrfs_ino(inode);
 	ins.offset = file_pos;
 	ins.type = BTRFS_EXTENT_DATA_KEY;
 	ret = btrfs_insert_empty_item(trans, root, path, &ins, sizeof(*fi));
@@ -1675,7 +1692,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
 	ins.type = BTRFS_EXTENT_ITEM_KEY;
 	ret = btrfs_alloc_reserved_file_extent(trans, root,
 					root->root_key.objectid,
-					inode->i_ino, file_pos, &ins);
+					btrfs_ino(inode), file_pos, &ins);
 	BUG_ON(ret);
 	btrfs_free_path(path);
 
@@ -1701,7 +1718,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 	struct extent_state *cached_state = NULL;
 	int compress_type = 0;
 	int ret;
-	bool nolock = false;
+	bool nolock;
 
 	ret = btrfs_dec_test_ordered_pending(inode, &ordered_extent, start,
 					     end - start + 1);
@@ -1709,18 +1726,17 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 		return 0;
 	BUG_ON(!ordered_extent);
 
-	nolock = (root == root->fs_info->tree_root);
+	nolock = is_free_space_inode(root, inode);
 
 	if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) {
 		BUG_ON(!list_empty(&ordered_extent->list));
 		ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
 		if (!ret) {
 			if (nolock)
-				trans = btrfs_join_transaction_nolock(root, 1);
+				trans = btrfs_join_transaction_nolock(root);
 			else
-				trans = btrfs_join_transaction(root, 1);
+				trans = btrfs_join_transaction(root);
 			BUG_ON(IS_ERR(trans));
-			btrfs_set_trans_block_group(trans, inode);
 			trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 			ret = btrfs_update_inode(trans, root, inode);
 			BUG_ON(ret);
@@ -1733,11 +1749,10 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 			 0, &cached_state, GFP_NOFS);
 
 	if (nolock)
-		trans = btrfs_join_transaction_nolock(root, 1);
+		trans = btrfs_join_transaction_nolock(root);
 	else
-		trans = btrfs_join_transaction(root, 1);
+		trans = btrfs_join_transaction(root);
 	BUG_ON(IS_ERR(trans));
-	btrfs_set_trans_block_group(trans, inode);
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
@@ -1855,7 +1870,7 @@ static int btrfs_io_failed_hook(struct bio *failed_bio,
 		}
 		read_unlock(&em_tree->lock);
 
-		if (!em || IS_ERR(em)) {
+		if (IS_ERR_OR_NULL(em)) {
 			kfree(failrec);
 			return -EIO;
 		}
@@ -1971,7 +1986,7 @@ static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 	}
 
 	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
-		return 0;
+		goto good;
 
 	if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID &&
 	    test_range_bit(io_tree, start, end, EXTENT_NODATASUM, 1, NULL)) {
@@ -2004,12 +2019,11 @@ good:
 	return 0;
 
 zeroit:
-	if (printk_ratelimit()) {
-		printk(KERN_INFO "btrfs csum failed ino %lu off %llu csum %u "
-		       "private %llu\n", page->mapping->host->i_ino,
+	printk_ratelimited(KERN_INFO "btrfs csum failed ino %llu off %llu csum %u "
+		       "private %llu\n",
+		       (unsigned long long)btrfs_ino(page->mapping->host),
 		       (unsigned long long)start, csum,
 		       (unsigned long long)private);
-	}
 	memset(kaddr + offset, 1, end - start + 1);
 	flush_dcache_page(page);
 	kunmap_atomic(kaddr, KM_USER0);
@@ -2244,7 +2258,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 
 	/* insert an orphan item to track this unlinked/truncated file */
 	if (insert >= 1) {
-		ret = btrfs_insert_orphan_item(trans, root, inode->i_ino);
+		ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode));
 		BUG_ON(ret);
 	}
 
@@ -2281,7 +2295,7 @@ int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode)
 	spin_unlock(&root->orphan_lock);
 
 	if (trans && delete_item) {
-		ret = btrfs_del_orphan_item(trans, root, inode->i_ino);
+		ret = btrfs_del_orphan_item(trans, root, btrfs_ino(inode));
 		BUG_ON(ret);
 	}
 
@@ -2346,7 +2360,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 			break;
 
 		/* release the path since we're done with it */
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 
 		/*
 		 * this is where we are basically btrfs_lookup, without the
@@ -2413,7 +2427,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 					(u64)-1);
 
 	if (root->orphan_block_rsv || root->orphan_item_inserted) {
-		trans = btrfs_join_transaction(root, 1);
+		trans = btrfs_join_transaction(root);
 		if (!IS_ERR(trans))
 			btrfs_end_transaction(trans, root);
 	}
@@ -2493,12 +2507,17 @@ static void btrfs_read_locked_inode(struct inode *inode)
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_key location;
 	int maybe_acls;
-	u64 alloc_group_block;
 	u32 rdev;
 	int ret;
+	bool filled = false;
+
+	ret = btrfs_fill_inode(inode, &rdev);
+	if (!ret)
+		filled = true;
 
 	path = btrfs_alloc_path();
 	BUG_ON(!path);
+	path->leave_spinning = 1;
 	memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
 
 	ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
@@ -2506,8 +2525,18 @@ static void btrfs_read_locked_inode(struct inode *inode)
 		goto make_bad;
 
 	leaf = path->nodes[0];
+
+	if (filled)
+		goto cache_acl;
+
 	inode_item = btrfs_item_ptr(leaf, path->slots[0],
 				    struct btrfs_inode_item);
+	if (!leaf->map_token)
+		map_private_extent_buffer(leaf, (unsigned long)inode_item,
+					  sizeof(struct btrfs_inode_item),
+					  &leaf->map_token, &leaf->kaddr,
+					  &leaf->map_start, &leaf->map_len,
+					  KM_USER1);
 
 	inode->i_mode = btrfs_inode_mode(leaf, inode_item);
 	inode->i_nlink = btrfs_inode_nlink(leaf, inode_item);
@@ -2536,21 +2565,22 @@ static void btrfs_read_locked_inode(struct inode *inode)
 
 	BTRFS_I(inode)->index_cnt = (u64)-1;
 	BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);
-
-	alloc_group_block = btrfs_inode_block_group(leaf, inode_item);
-
+cache_acl:
 	/*
 	 * try to precache a NULL acl entry for files that don't have
 	 * any xattrs or acls
 	 */
-	maybe_acls = acls_after_inode_item(leaf, path->slots[0], inode->i_ino);
+	maybe_acls = acls_after_inode_item(leaf, path->slots[0],
+					   btrfs_ino(inode));
 	if (!maybe_acls)
 		cache_no_acl(inode);
 
-	BTRFS_I(inode)->block_group = btrfs_find_block_group(root, 0,
-						alloc_group_block, 0);
+	if (leaf->map_token) {
+		unmap_extent_buffer(leaf, leaf->map_token, KM_USER1);
+		leaf->map_token = NULL;
+	}
+
 	btrfs_free_path(path);
-	inode_item = NULL;
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
@@ -2628,7 +2658,7 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 	btrfs_set_inode_transid(leaf, item, trans->transid);
 	btrfs_set_inode_rdev(leaf, item, inode->i_rdev);
 	btrfs_set_inode_flags(leaf, item, BTRFS_I(inode)->flags);
-	btrfs_set_inode_block_group(leaf, item, BTRFS_I(inode)->block_group);
+	btrfs_set_inode_block_group(leaf, item, 0);
 
 	if (leaf->map_token) {
 		unmap_extent_buffer(leaf, leaf->map_token, KM_USER1);
@@ -2647,11 +2677,26 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 	int ret;
 
+	/*
+	 * If root is tree root, it means this inode is used to
+	 * store free space information. And these inodes are updated
+	 * when committing the transaction, so they needn't delaye to
+	 * be updated, or deadlock will occured.
+	 */
+	if (!is_free_space_inode(root, inode)) {
+		ret = btrfs_delayed_update_inode(trans, root, inode);
+		if (!ret)
+			btrfs_set_inode_last_trans(trans, inode);
+		return ret;
+	}
+
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path)
+		return -ENOMEM;
+
 	path->leave_spinning = 1;
-	ret = btrfs_lookup_inode(trans, root, path,
-				 &BTRFS_I(inode)->location, 1);
+	ret = btrfs_lookup_inode(trans, root, path, &BTRFS_I(inode)->location,
+				 1);
 	if (ret) {
 		if (ret > 0)
 			ret = -ENOENT;
@@ -2661,7 +2706,7 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
 	btrfs_unlock_up_safe(path, 1);
 	leaf = path->nodes[0];
 	inode_item = btrfs_item_ptr(leaf, path->slots[0],
-				  struct btrfs_inode_item);
+				    struct btrfs_inode_item);
 
 	fill_inode_item(trans, leaf, inode_item, inode);
 	btrfs_mark_buffer_dirty(leaf);
@@ -2672,7 +2717,6 @@ failed:
 	return ret;
 }
 
-
 /*
  * unlink helper that gets used here in inode.c and in the tree logging
  * recovery code.  It remove a link in a directory with a given name, and
@@ -2689,6 +2733,8 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 	struct btrfs_dir_item *di;
 	struct btrfs_key key;
 	u64 index;
+	u64 ino = btrfs_ino(inode);
+	u64 dir_ino = btrfs_ino(dir);
 
 	path = btrfs_alloc_path();
 	if (!path) {
@@ -2697,7 +2743,7 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 	}
 
 	path->leave_spinning = 1;
-	di = btrfs_lookup_dir_item(trans, root, path, dir->i_ino,
+	di = btrfs_lookup_dir_item(trans, root, path, dir_ino,
 				    name, name_len, -1);
 	if (IS_ERR(di)) {
 		ret = PTR_ERR(di);
@@ -2712,33 +2758,23 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 	ret = btrfs_delete_one_dir_name(trans, root, path, di);
 	if (ret)
 		goto err;
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
-	ret = btrfs_del_inode_ref(trans, root, name, name_len,
-				  inode->i_ino,
-				  dir->i_ino, &index);
+	ret = btrfs_del_inode_ref(trans, root, name, name_len, ino,
+				  dir_ino, &index);
 	if (ret) {
 		printk(KERN_INFO "btrfs failed to delete reference to %.*s, "
-		       "inode %lu parent %lu\n", name_len, name,
-		       inode->i_ino, dir->i_ino);
+		       "inode %llu parent %llu\n", name_len, name,
+		       (unsigned long long)ino, (unsigned long long)dir_ino);
 		goto err;
 	}
 
-	di = btrfs_lookup_dir_index_item(trans, root, path, dir->i_ino,
-					 index, name, name_len, -1);
-	if (IS_ERR(di)) {
-		ret = PTR_ERR(di);
-		goto err;
-	}
-	if (!di) {
-		ret = -ENOENT;
+	ret = btrfs_delete_delayed_dir_index(trans, root, dir, index);
+	if (ret)
 		goto err;
-	}
-	ret = btrfs_delete_one_dir_name(trans, root, path, di);
-	btrfs_release_path(root, path);
 
 	ret = btrfs_del_inode_ref_in_log(trans, root, name, name_len,
-					 inode, dir->i_ino);
+					 inode, dir_ino);
 	BUG_ON(ret != 0 && ret != -ENOENT);
 
 	ret = btrfs_del_dir_entries_in_log(trans, root, name, name_len,
@@ -2816,12 +2852,14 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir,
 	int check_link = 1;
 	int err = -ENOSPC;
 	int ret;
+	u64 ino = btrfs_ino(inode);
+	u64 dir_ino = btrfs_ino(dir);
 
 	trans = btrfs_start_transaction(root, 10);
 	if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
 		return trans;
 
-	if (inode->i_ino == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
+	if (ino == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
 		return ERR_PTR(-ENOSPC);
 
 	/* check if there is someone else holds reference */
@@ -2862,7 +2900,7 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir,
 	} else {
 		check_link = 0;
 	}
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	ret = btrfs_lookup_inode(trans, root, path,
 				&BTRFS_I(inode)->location, 0);
@@ -2876,11 +2914,11 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir,
 	} else {
 		check_link = 0;
 	}
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	if (ret == 0 && S_ISREG(inode->i_mode)) {
 		ret = btrfs_lookup_file_extent(trans, root, path,
-					       inode->i_ino, (u64)-1, 0);
+					       ino, (u64)-1, 0);
 		if (ret < 0) {
 			err = ret;
 			goto out;
@@ -2888,7 +2926,7 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir,
 		BUG_ON(ret == 0);
 		if (check_path_shared(root, path))
 			goto out;
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 	}
 
 	if (!check_link) {
@@ -2896,7 +2934,7 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir,
 		goto out;
 	}
 
-	di = btrfs_lookup_dir_item(trans, root, path, dir->i_ino,
+	di = btrfs_lookup_dir_item(trans, root, path, dir_ino,
 				dentry->d_name.name, dentry->d_name.len, 0);
 	if (IS_ERR(di)) {
 		err = PTR_ERR(di);
@@ -2909,11 +2947,11 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir,
 		err = 0;
 		goto out;
 	}
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	ref = btrfs_lookup_inode_ref(trans, root, path,
 				dentry->d_name.name, dentry->d_name.len,
-				inode->i_ino, dir->i_ino, 0);
+				ino, dir_ino, 0);
 	if (IS_ERR(ref)) {
 		err = PTR_ERR(ref);
 		goto out;
@@ -2922,9 +2960,17 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir,
 	if (check_path_shared(root, path))
 		goto out;
 	index = btrfs_inode_ref_index(path->nodes[0], ref);
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
-	di = btrfs_lookup_dir_index_item(trans, root, path, dir->i_ino, index,
+	/*
+	 * This is a commit root search, if we can lookup inode item and other
+	 * relative items in the commit root, it means the transaction of
+	 * dir/file creation has been committed, and the dir index item that we
+	 * delay to insert has also been inserted into the commit root. So
+	 * we needn't worry about the delayed insertion of the dir index item
+	 * here.
+	 */
+	di = btrfs_lookup_dir_index_item(trans, root, path, dir_ino, index,
 				dentry->d_name.name, dentry->d_name.len, 0);
 	if (IS_ERR(di)) {
 		err = PTR_ERR(di);
@@ -2969,8 +3015,6 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	btrfs_set_trans_block_group(trans, dir);
-
 	btrfs_record_unlink_dir(trans, dir, dentry->d_inode, 0);
 
 	ret = btrfs_unlink_inode(trans, root, dir, dentry->d_inode,
@@ -2999,47 +3043,41 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	u64 index;
 	int ret;
+	u64 dir_ino = btrfs_ino(dir);
 
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
-	di = btrfs_lookup_dir_item(trans, root, path, dir->i_ino,
+	di = btrfs_lookup_dir_item(trans, root, path, dir_ino,
 				   name, name_len, -1);
-	BUG_ON(!di || IS_ERR(di));
+	BUG_ON(IS_ERR_OR_NULL(di));
 
 	leaf = path->nodes[0];
 	btrfs_dir_item_key_to_cpu(leaf, di, &key);
 	WARN_ON(key.type != BTRFS_ROOT_ITEM_KEY || key.objectid != objectid);
 	ret = btrfs_delete_one_dir_name(trans, root, path, di);
 	BUG_ON(ret);
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	ret = btrfs_del_root_ref(trans, root->fs_info->tree_root,
 				 objectid, root->root_key.objectid,
-				 dir->i_ino, &index, name, name_len);
+				 dir_ino, &index, name, name_len);
 	if (ret < 0) {
 		BUG_ON(ret != -ENOENT);
-		di = btrfs_search_dir_index_item(root, path, dir->i_ino,
+		di = btrfs_search_dir_index_item(root, path, dir_ino,
 						 name, name_len);
-		BUG_ON(!di || IS_ERR(di));
+		BUG_ON(IS_ERR_OR_NULL(di));
 
 		leaf = path->nodes[0];
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		index = key.offset;
 	}
+	btrfs_release_path(path);
 
-	di = btrfs_lookup_dir_index_item(trans, root, path, dir->i_ino,
-					 index, name, name_len, -1);
-	BUG_ON(!di || IS_ERR(di));
-
-	leaf = path->nodes[0];
-	btrfs_dir_item_key_to_cpu(leaf, di, &key);
-	WARN_ON(key.type != BTRFS_ROOT_ITEM_KEY || key.objectid != objectid);
-	ret = btrfs_delete_one_dir_name(trans, root, path, di);
+	ret = btrfs_delete_delayed_dir_index(trans, root, dir, index);
 	BUG_ON(ret);
-	btrfs_release_path(root, path);
 
 	btrfs_i_size_write(dir, dir->i_size - name_len * 2);
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
@@ -3059,16 +3097,14 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 	unsigned long nr = 0;
 
 	if (inode->i_size > BTRFS_EMPTY_DIR_SIZE ||
-	    inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)
+	    btrfs_ino(inode) == BTRFS_FIRST_FREE_OBJECTID)
 		return -ENOTEMPTY;
 
 	trans = __unlink_start_trans(dir, dentry);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	btrfs_set_trans_block_group(trans, dir);
-
-	if (unlikely(inode->i_ino == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
+	if (unlikely(btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
 		err = btrfs_unlink_subvol(trans, root, dir,
 					  BTRFS_I(inode)->location.objectid,
 					  dentry->d_name.name,
@@ -3093,178 +3129,6 @@ out:
 	return err;
 }
 
-#if 0
-/*
- * when truncating bytes in a file, it is possible to avoid reading
- * the leaves that contain only checksum items.  This can be the
- * majority of the IO required to delete a large file, but it must
- * be done carefully.
- *
- * The keys in the level just above the leaves are checked to make sure
- * the lowest key in a given leaf is a csum key, and starts at an offset
- * after the new  size.
- *
- * Then the key for the next leaf is checked to make sure it also has
- * a checksum item for the same file.  If it does, we know our target leaf
- * contains only checksum items, and it can be safely freed without reading
- * it.
- *
- * This is just an optimization targeted at large files.  It may do
- * nothing.  It will return 0 unless things went badly.
- */
-static noinline int drop_csum_leaves(struct btrfs_trans_handle *trans,
-				     struct btrfs_root *root,
-				     struct btrfs_path *path,
-				     struct inode *inode, u64 new_size)
-{
-	struct btrfs_key key;
-	int ret;
-	int nritems;
-	struct btrfs_key found_key;
-	struct btrfs_key other_key;
-	struct btrfs_leaf_ref *ref;
-	u64 leaf_gen;
-	u64 leaf_start;
-
-	path->lowest_level = 1;
-	key.objectid = inode->i_ino;
-	key.type = BTRFS_CSUM_ITEM_KEY;
-	key.offset = new_size;
-again:
-	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
-	if (ret < 0)
-		goto out;
-
-	if (path->nodes[1] == NULL) {
-		ret = 0;
-		goto out;
-	}
-	ret = 0;
-	btrfs_node_key_to_cpu(path->nodes[1], &found_key, path->slots[1]);
-	nritems = btrfs_header_nritems(path->nodes[1]);
-
-	if (!nritems)
-		goto out;
-
-	if (path->slots[1] >= nritems)
-		goto next_node;
-
-	/* did we find a key greater than anything we want to delete? */
-	if (found_key.objectid > inode->i_ino ||
-	   (found_key.objectid == inode->i_ino && found_key.type > key.type))
-		goto out;
-
-	/* we check the next key in the node to make sure the leave contains
-	 * only checksum items.  This comparison doesn't work if our
-	 * leaf is the last one in the node
-	 */
-	if (path->slots[1] + 1 >= nritems) {
-next_node:
-		/* search forward from the last key in the node, this
-		 * will bring us into the next node in the tree
-		 */
-		btrfs_node_key_to_cpu(path->nodes[1], &found_key, nritems - 1);
-
-		/* unlikely, but we inc below, so check to be safe */
-		if (found_key.offset == (u64)-1)
-			goto out;
-
-		/* search_forward needs a path with locks held, do the
-		 * search again for the original key.  It is possible
-		 * this will race with a balance and return a path that
-		 * we could modify, but this drop is just an optimization
-		 * and is allowed to miss some leaves.
-		 */
-		btrfs_release_path(root, path);
-		found_key.offset++;
-
-		/* setup a max key for search_forward */
-		other_key.offset = (u64)-1;
-		other_key.type = key.type;
-		other_key.objectid = key.objectid;
-
-		path->keep_locks = 1;
-		ret = btrfs_search_forward(root, &found_key, &other_key,
-					   path, 0, 0);
-		path->keep_locks = 0;
-		if (ret || found_key.objectid != key.objectid ||
-		    found_key.type != key.type) {
-			ret = 0;
-			goto out;
-		}
-
-		key.offset = found_key.offset;
-		btrfs_release_path(root, path);
-		cond_resched();
-		goto again;
-	}
-
-	/* we know there's one more slot after us in the tree,
-	 * read that key so we can verify it is also a checksum item
-	 */
-	btrfs_node_key_to_cpu(path->nodes[1], &other_key, path->slots[1] + 1);
-
-	if (found_key.objectid < inode->i_ino)
-		goto next_key;
-
-	if (found_key.type != key.type || found_key.offset < new_size)
-		goto next_key;
-
-	/*
-	 * if the key for the next leaf isn't a csum key from this objectid,
-	 * we can't be sure there aren't good items inside this leaf.
-	 * Bail out
-	 */
-	if (other_key.objectid != inode->i_ino || other_key.type != key.type)
-		goto out;
-
-	leaf_start = btrfs_node_blockptr(path->nodes[1], path->slots[1]);
-	leaf_gen = btrfs_node_ptr_generation(path->nodes[1], path->slots[1]);
-	/*
-	 * it is safe to delete this leaf, it contains only
-	 * csum items from this inode at an offset >= new_size
-	 */
-	ret = btrfs_del_leaf(trans, root, path, leaf_start);
-	BUG_ON(ret);
-
-	if (root->ref_cows && leaf_gen < trans->transid) {
-		ref = btrfs_alloc_leaf_ref(root, 0);
-		if (ref) {
-			ref->root_gen = root->root_key.offset;
-			ref->bytenr = leaf_start;
-			ref->owner = 0;
-			ref->generation = leaf_gen;
-			ref->nritems = 0;
-
-			btrfs_sort_leaf_ref(ref);
-
-			ret = btrfs_add_leaf_ref(root, ref, 0);
-			WARN_ON(ret);
-			btrfs_free_leaf_ref(root, ref);
-		} else {
-			WARN_ON(1);
-		}
-	}
-next_key:
-	btrfs_release_path(root, path);
-
-	if (other_key.objectid == inode->i_ino &&
-	    other_key.type == key.type && other_key.offset > key.offset) {
-		key.offset = other_key.offset;
-		cond_resched();
-		goto again;
-	}
-	ret = 0;
-out:
-	/* fixup any changes we've made to the path */
-	path->lowest_level = 0;
-	path->keep_locks = 0;
-	btrfs_release_path(root, path);
-	return ret;
-}
-
-#endif
-
 /*
  * this can truncate away extent items, csum items and directory items.
  * It starts at a high offset and removes keys until it can't find
@@ -3300,17 +3164,27 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	int encoding;
 	int ret;
 	int err = 0;
+	u64 ino = btrfs_ino(inode);
 
 	BUG_ON(new_size > 0 && min_type != BTRFS_EXTENT_DATA_KEY);
 
 	if (root->ref_cows || root == root->fs_info->tree_root)
 		btrfs_drop_extent_cache(inode, new_size & (~mask), (u64)-1, 0);
 
+	/*
+	 * This function is also used to drop the items in the log tree before
+	 * we relog the inode, so if root != BTRFS_I(inode)->root, it means
+	 * it is used to drop the loged items. So we shouldn't kill the delayed
+	 * items.
+	 */
+	if (min_type == 0 && root == BTRFS_I(inode)->root)
+		btrfs_kill_delayed_inode_items(inode);
+
 	path = btrfs_alloc_path();
 	BUG_ON(!path);
 	path->reada = -1;
 
-	key.objectid = inode->i_ino;
+	key.objectid = ino;
 	key.offset = (u64)-1;
 	key.type = (u8)-1;
 
@@ -3338,7 +3212,7 @@ search_again:
 		found_type = btrfs_key_type(&found_key);
 		encoding = 0;
 
-		if (found_key.objectid != inode->i_ino)
+		if (found_key.objectid != ino)
 			break;
 
 		if (found_type < min_type)
@@ -3428,7 +3302,6 @@ search_again:
 				    btrfs_file_extent_calc_inline_size(size);
 				ret = btrfs_truncate_item(trans, root, path,
 							  size, 1);
-				BUG_ON(ret);
 			} else if (root->ref_cows) {
 				inode_sub_bytes(inode, item_end + 1 -
 						found_key.offset);
@@ -3457,7 +3330,7 @@ delete:
 			ret = btrfs_free_extent(trans, root, extent_start,
 						extent_num_bytes, 0,
 						btrfs_header_owner(leaf),
-						inode->i_ino, extent_offset);
+						ino, extent_offset);
 			BUG_ON(ret);
 		}
 
@@ -3466,7 +3339,9 @@ delete:
 
 		if (path->slots[0] == 0 ||
 		    path->slots[0] != pending_del_slot) {
-			if (root->ref_cows) {
+			if (root->ref_cows &&
+			    BTRFS_I(inode)->location.objectid !=
+						BTRFS_FREE_INO_OBJECTID) {
 				err = -EAGAIN;
 				goto out;
 			}
@@ -3477,7 +3352,7 @@ delete:
 				BUG_ON(ret);
 				pending_del_nr = 0;
 			}
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			goto search_again;
 		} else {
 			path->slots[0]--;
@@ -3635,7 +3510,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 	while (1) {
 		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
 				block_end - cur_offset, 0);
-		BUG_ON(IS_ERR(em) || !em);
+		BUG_ON(IS_ERR_OR_NULL(em));
 		last_byte = min(extent_map_end(em), block_end);
 		last_byte = (last_byte + mask) & ~mask;
 		if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
@@ -3647,7 +3522,6 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 				err = PTR_ERR(trans);
 				break;
 			}
-			btrfs_set_trans_block_group(trans, inode);
 
 			err = btrfs_drop_extents(trans, inode, cur_offset,
 						 cur_offset + hole_size,
@@ -3656,7 +3530,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 				break;
 
 			err = btrfs_insert_file_extent(trans, root,
-					inode->i_ino, cur_offset, 0,
+					btrfs_ino(inode), cur_offset, 0,
 					0, hole_size, 0, hole_size,
 					0, 0, 0);
 			if (err)
@@ -3758,7 +3632,7 @@ void btrfs_evict_inode(struct inode *inode)
 
 	truncate_inode_pages(&inode->i_data, 0);
 	if (inode->i_nlink && (btrfs_root_refs(&root->root_item) != 0 ||
-			       root == root->fs_info->tree_root))
+			       is_free_space_inode(root, inode)))
 		goto no_delete;
 
 	if (is_bad_inode(inode)) {
@@ -3781,9 +3655,8 @@ void btrfs_evict_inode(struct inode *inode)
 	btrfs_i_size_write(inode, 0);
 
 	while (1) {
-		trans = btrfs_start_transaction(root, 0);
+		trans = btrfs_join_transaction(root);
 		BUG_ON(IS_ERR(trans));
-		btrfs_set_trans_block_group(trans, inode);
 		trans->block_rsv = root->orphan_block_rsv;
 
 		ret = btrfs_block_rsv_check(trans, root,
@@ -3811,6 +3684,10 @@ void btrfs_evict_inode(struct inode *inode)
 		BUG_ON(ret);
 	}
 
+	if (!(root == root->fs_info->tree_root ||
+	      root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID))
+		btrfs_return_ino(root, btrfs_ino(inode));
+
 	nr = trans->blocks_used;
 	btrfs_end_transaction(trans, root);
 	btrfs_btree_balance_dirty(root, nr);
@@ -3836,12 +3713,12 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry,
 	path = btrfs_alloc_path();
 	BUG_ON(!path);
 
-	di = btrfs_lookup_dir_item(NULL, root, path, dir->i_ino, name,
+	di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(dir), name,
 				    namelen, 0);
 	if (IS_ERR(di))
 		ret = PTR_ERR(di);
 
-	if (!di || IS_ERR(di))
+	if (IS_ERR_OR_NULL(di))
 		goto out_err;
 
 	btrfs_dir_item_key_to_cpu(path->nodes[0], di, location);
@@ -3889,7 +3766,7 @@ static int fixup_tree_root_location(struct btrfs_root *root,
 
 	leaf = path->nodes[0];
 	ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref);
-	if (btrfs_root_ref_dirid(leaf, ref) != dir->i_ino ||
+	if (btrfs_root_ref_dirid(leaf, ref) != btrfs_ino(dir) ||
 	    btrfs_root_ref_name_len(leaf, ref) != dentry->d_name.len)
 		goto out;
 
@@ -3899,7 +3776,7 @@ static int fixup_tree_root_location(struct btrfs_root *root,
 	if (ret)
 		goto out;
 
-	btrfs_release_path(root->fs_info->tree_root, path);
+	btrfs_release_path(path);
 
 	new_root = btrfs_read_fs_root_no_name(root->fs_info, location);
 	if (IS_ERR(new_root)) {
@@ -3928,6 +3805,7 @@ static void inode_tree_add(struct inode *inode)
 	struct btrfs_inode *entry;
 	struct rb_node **p;
 	struct rb_node *parent;
+	u64 ino = btrfs_ino(inode);
 again:
 	p = &root->inode_tree.rb_node;
 	parent = NULL;
@@ -3940,9 +3818,9 @@ again:
 		parent = *p;
 		entry = rb_entry(parent, struct btrfs_inode, rb_node);
 
-		if (inode->i_ino < entry->vfs_inode.i_ino)
+		if (ino < btrfs_ino(&entry->vfs_inode))
 			p = &parent->rb_left;
-		else if (inode->i_ino > entry->vfs_inode.i_ino)
+		else if (ino > btrfs_ino(&entry->vfs_inode))
 			p = &parent->rb_right;
 		else {
 			WARN_ON(!(entry->vfs_inode.i_state &
@@ -4006,9 +3884,9 @@ again:
 		prev = node;
 		entry = rb_entry(node, struct btrfs_inode, rb_node);
 
-		if (objectid < entry->vfs_inode.i_ino)
+		if (objectid < btrfs_ino(&entry->vfs_inode))
 			node = node->rb_left;
-		else if (objectid > entry->vfs_inode.i_ino)
+		else if (objectid > btrfs_ino(&entry->vfs_inode))
 			node = node->rb_right;
 		else
 			break;
@@ -4016,7 +3894,7 @@ again:
 	if (!node) {
 		while (prev) {
 			entry = rb_entry(prev, struct btrfs_inode, rb_node);
-			if (objectid <= entry->vfs_inode.i_ino) {
+			if (objectid <= btrfs_ino(&entry->vfs_inode)) {
 				node = prev;
 				break;
 			}
@@ -4025,7 +3903,7 @@ again:
 	}
 	while (node) {
 		entry = rb_entry(node, struct btrfs_inode, rb_node);
-		objectid = entry->vfs_inode.i_ino + 1;
+		objectid = btrfs_ino(&entry->vfs_inode) + 1;
 		inode = igrab(&entry->vfs_inode);
 		if (inode) {
 			spin_unlock(&root->inode_lock);
@@ -4063,7 +3941,7 @@ static int btrfs_init_locked_inode(struct inode *inode, void *p)
 static int btrfs_find_actor(struct inode *inode, void *opaque)
 {
 	struct btrfs_iget_args *args = opaque;
-	return args->ino == inode->i_ino &&
+	return args->ino == btrfs_ino(inode) &&
 		args->root == BTRFS_I(inode)->root;
 }
 
@@ -4208,7 +4086,7 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
 	return d_splice_alias(inode, dentry);
 }
 
-static unsigned char btrfs_filetype_table[] = {
+unsigned char btrfs_filetype_table[] = {
 	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
 };
 
@@ -4222,6 +4100,8 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
 	struct btrfs_key key;
 	struct btrfs_key found_key;
 	struct btrfs_path *path;
+	struct list_head ins_list;
+	struct list_head del_list;
 	int ret;
 	struct extent_buffer *leaf;
 	int slot;
@@ -4234,6 +4114,7 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
 	char tmp_name[32];
 	char *name_ptr;
 	int name_len;
+	int is_curr = 0;	/* filp->f_pos points to the current index? */
 
 	/* FIXME, use a real flag for deciding about the key type */
 	if (root->fs_info->tree_root == root)
@@ -4241,9 +4122,7 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
 
 	/* special case for "." */
 	if (filp->f_pos == 0) {
-		over = filldir(dirent, ".", 1,
-			       1, inode->i_ino,
-			       DT_DIR);
+		over = filldir(dirent, ".", 1, 1, btrfs_ino(inode), DT_DIR);
 		if (over)
 			return 0;
 		filp->f_pos = 1;
@@ -4258,11 +4137,20 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
 		filp->f_pos = 2;
 	}
 	path = btrfs_alloc_path();
-	path->reada = 2;
+	if (!path)
+		return -ENOMEM;
+
+	path->reada = 1;
+
+	if (key_type == BTRFS_DIR_INDEX_KEY) {
+		INIT_LIST_HEAD(&ins_list);
+		INIT_LIST_HEAD(&del_list);
+		btrfs_get_delayed_items(inode, &ins_list, &del_list);
+	}
 
 	btrfs_set_key_type(&key, key_type);
 	key.offset = filp->f_pos;
-	key.objectid = inode->i_ino;
+	key.objectid = btrfs_ino(inode);
 
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
@@ -4289,8 +4177,13 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
 			break;
 		if (found_key.offset < filp->f_pos)
 			goto next;
+		if (key_type == BTRFS_DIR_INDEX_KEY &&
+		    btrfs_should_delete_dir_index(&del_list,
+						  found_key.offset))
+			goto next;
 
 		filp->f_pos = found_key.offset;
+		is_curr = 1;
 
 		di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
 		di_cur = 0;
@@ -4345,6 +4238,15 @@ next:
 		path->slots[0]++;
 	}
 
+	if (key_type == BTRFS_DIR_INDEX_KEY) {
+		if (is_curr)
+			filp->f_pos++;
+		ret = btrfs_readdir_delayed_dir_index(filp, dirent, filldir,
+						      &ins_list);
+		if (ret)
+			goto nopos;
+	}
+
 	/* Reached end of directory/root. Bump pos past the last item. */
 	if (key_type == BTRFS_DIR_INDEX_KEY)
 		/*
@@ -4357,6 +4259,8 @@ next:
 nopos:
 	ret = 0;
 err:
+	if (key_type == BTRFS_DIR_INDEX_KEY)
+		btrfs_put_delayed_items(&ins_list, &del_list);
 	btrfs_free_path(path);
 	return ret;
 }
@@ -4371,17 +4275,16 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	if (BTRFS_I(inode)->dummy_inode)
 		return 0;
 
-	smp_mb();
-	nolock = (root->fs_info->closing && root == root->fs_info->tree_root);
+	if (btrfs_fs_closing(root->fs_info) && is_free_space_inode(root, inode))
+		nolock = true;
 
 	if (wbc->sync_mode == WB_SYNC_ALL) {
 		if (nolock)
-			trans = btrfs_join_transaction_nolock(root, 1);
+			trans = btrfs_join_transaction_nolock(root);
 		else
-			trans = btrfs_join_transaction(root, 1);
+			trans = btrfs_join_transaction(root);
 		if (IS_ERR(trans))
 			return PTR_ERR(trans);
-		btrfs_set_trans_block_group(trans, inode);
 		if (nolock)
 			ret = btrfs_end_transaction_nolock(trans, root);
 		else
@@ -4396,7 +4299,7 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
  * FIXME, needs more benchmarking...there are no reasons other than performance
  * to keep or drop this code.
  */
-void btrfs_dirty_inode(struct inode *inode)
+void btrfs_dirty_inode(struct inode *inode, int flags)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
@@ -4405,9 +4308,8 @@ void btrfs_dirty_inode(struct inode *inode)
 	if (BTRFS_I(inode)->dummy_inode)
 		return;
 
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	BUG_ON(IS_ERR(trans));
-	btrfs_set_trans_block_group(trans, inode);
 
 	ret = btrfs_update_inode(trans, root, inode);
 	if (ret && ret == -ENOSPC) {
@@ -4415,25 +4317,24 @@ void btrfs_dirty_inode(struct inode *inode)
 		btrfs_end_transaction(trans, root);
 		trans = btrfs_start_transaction(root, 1);
 		if (IS_ERR(trans)) {
-			if (printk_ratelimit()) {
-				printk(KERN_ERR "btrfs: fail to "
-				       "dirty  inode %lu error %ld\n",
-				       inode->i_ino, PTR_ERR(trans));
-			}
+			printk_ratelimited(KERN_ERR "btrfs: fail to "
+				       "dirty  inode %llu error %ld\n",
+				       (unsigned long long)btrfs_ino(inode),
+				       PTR_ERR(trans));
 			return;
 		}
-		btrfs_set_trans_block_group(trans, inode);
 
 		ret = btrfs_update_inode(trans, root, inode);
 		if (ret) {
-			if (printk_ratelimit()) {
-				printk(KERN_ERR "btrfs: fail to "
-				       "dirty  inode %lu error %d\n",
-				       inode->i_ino, ret);
-			}
+			printk_ratelimited(KERN_ERR "btrfs: fail to "
+				       "dirty  inode %llu error %d\n",
+				       (unsigned long long)btrfs_ino(inode),
+				       ret);
 		}
 	}
 	btrfs_end_transaction(trans, root);
+	if (BTRFS_I(inode)->delayed_node)
+		btrfs_balance_delayed_items(root);
 }
 
 /*
@@ -4449,7 +4350,7 @@ static int btrfs_set_inode_index_count(struct inode *inode)
 	struct extent_buffer *leaf;
 	int ret;
 
-	key.objectid = inode->i_ino;
+	key.objectid = btrfs_ino(inode);
 	btrfs_set_key_type(&key, BTRFS_DIR_INDEX_KEY);
 	key.offset = (u64)-1;
 
@@ -4481,7 +4382,7 @@ static int btrfs_set_inode_index_count(struct inode *inode)
 	leaf = path->nodes[0];
 	btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
 
-	if (found_key.objectid != inode->i_ino ||
+	if (found_key.objectid != btrfs_ino(inode) ||
 	    btrfs_key_type(&found_key) != BTRFS_DIR_INDEX_KEY) {
 		BTRFS_I(inode)->index_cnt = 2;
 		goto out;
@@ -4502,9 +4403,12 @@ int btrfs_set_inode_index(struct inode *dir, u64 *index)
 	int ret = 0;
 
 	if (BTRFS_I(dir)->index_cnt == (u64)-1) {
-		ret = btrfs_set_inode_index_count(dir);
-		if (ret)
-			return ret;
+		ret = btrfs_inode_delayed_dir_index_count(dir);
+		if (ret) {
+			ret = btrfs_set_inode_index_count(dir);
+			if (ret)
+				return ret;
+		}
 	}
 
 	*index = BTRFS_I(dir)->index_cnt;
@@ -4517,8 +4421,8 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root,
 				     struct inode *dir,
 				     const char *name, int name_len,
-				     u64 ref_objectid, u64 objectid,
-				     u64 alloc_hint, int mode, u64 *index)
+				     u64 ref_objectid, u64 objectid, int mode,
+				     u64 *index)
 {
 	struct inode *inode;
 	struct btrfs_inode_item *inode_item;
@@ -4540,6 +4444,12 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 		return ERR_PTR(-ENOMEM);
 	}
 
+	/*
+	 * we have to initialize this early, so we can reclaim the inode
+	 * number if we fail afterwards in this function.
+	 */
+	inode->i_ino = objectid;
+
 	if (dir) {
 		trace_btrfs_inode_request(dir);
 
@@ -4565,8 +4475,6 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 		owner = 0;
 	else
 		owner = 1;
-	BTRFS_I(inode)->block_group =
-			btrfs_find_block_group(root, 0, alloc_hint, owner);
 
 	key[0].objectid = objectid;
 	btrfs_set_key_type(&key[0], BTRFS_INODE_ITEM_KEY);
@@ -4585,7 +4493,6 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 		goto fail;
 
 	inode_init_owner(inode, dir, mode);
-	inode->i_ino = objectid;
 	inode_set_bytes(inode, 0);
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
@@ -4621,6 +4528,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	inode_tree_add(inode);
 
 	trace_btrfs_inode_new(inode);
+	btrfs_set_inode_last_trans(trans, inode);
 
 	return inode;
 fail:
@@ -4649,29 +4557,29 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 	int ret = 0;
 	struct btrfs_key key;
 	struct btrfs_root *root = BTRFS_I(parent_inode)->root;
+	u64 ino = btrfs_ino(inode);
+	u64 parent_ino = btrfs_ino(parent_inode);
 
-	if (unlikely(inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)) {
+	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		memcpy(&key, &BTRFS_I(inode)->root->root_key, sizeof(key));
 	} else {
-		key.objectid = inode->i_ino;
+		key.objectid = ino;
 		btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
 		key.offset = 0;
 	}
 
-	if (unlikely(inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)) {
+	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		ret = btrfs_add_root_ref(trans, root->fs_info->tree_root,
 					 key.objectid, root->root_key.objectid,
-					 parent_inode->i_ino,
-					 index, name, name_len);
+					 parent_ino, index, name, name_len);
 	} else if (add_backref) {
-		ret = btrfs_insert_inode_ref(trans, root,
-					     name, name_len, inode->i_ino,
-					     parent_inode->i_ino, index);
+		ret = btrfs_insert_inode_ref(trans, root, name, name_len, ino,
+					     parent_ino, index);
 	}
 
 	if (ret == 0) {
 		ret = btrfs_insert_dir_item(trans, root, name, name_len,
-					    parent_inode->i_ino, &key,
+					    parent_inode, &key,
 					    btrfs_inode_type(inode), index);
 		BUG_ON(ret);
 
@@ -4714,10 +4622,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 	if (!new_valid_dev(rdev))
 		return -EINVAL;
 
-	err = btrfs_find_free_objectid(NULL, root, dir->i_ino, &objectid);
-	if (err)
-		return err;
-
 	/*
 	 * 2 for inode item and ref
 	 * 2 for dir items
@@ -4727,11 +4631,13 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	btrfs_set_trans_block_group(trans, dir);
+	err = btrfs_find_free_ino(root, &objectid);
+	if (err)
+		goto out_unlock;
 
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
-				dentry->d_name.len, dir->i_ino, objectid,
-				BTRFS_I(dir)->block_group, mode, &index);
+				dentry->d_name.len, btrfs_ino(dir), objectid,
+				mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto out_unlock;
@@ -4743,7 +4649,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 		goto out_unlock;
 	}
 
-	btrfs_set_trans_block_group(trans, inode);
 	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
 	if (err)
 		drop_inode = 1;
@@ -4752,8 +4657,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 		init_special_inode(inode, inode->i_mode, rdev);
 		btrfs_update_inode(trans, root, inode);
 	}
-	btrfs_update_inode_block_group(trans, inode);
-	btrfs_update_inode_block_group(trans, dir);
 out_unlock:
 	nr = trans->blocks_used;
 	btrfs_end_transaction_throttle(trans, root);
@@ -4777,9 +4680,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 	u64 objectid;
 	u64 index = 0;
 
-	err = btrfs_find_free_objectid(NULL, root, dir->i_ino, &objectid);
-	if (err)
-		return err;
 	/*
 	 * 2 for inode item and ref
 	 * 2 for dir items
@@ -4789,11 +4689,13 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	btrfs_set_trans_block_group(trans, dir);
+	err = btrfs_find_free_ino(root, &objectid);
+	if (err)
+		goto out_unlock;
 
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
-				dentry->d_name.len, dir->i_ino, objectid,
-				BTRFS_I(dir)->block_group, mode, &index);
+				dentry->d_name.len, btrfs_ino(dir), objectid,
+				mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto out_unlock;
@@ -4805,7 +4707,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 		goto out_unlock;
 	}
 
-	btrfs_set_trans_block_group(trans, inode);
 	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
 	if (err)
 		drop_inode = 1;
@@ -4816,8 +4717,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 		inode->i_op = &btrfs_file_inode_operations;
 		BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 	}
-	btrfs_update_inode_block_group(trans, inode);
-	btrfs_update_inode_block_group(trans, dir);
 out_unlock:
 	nr = trans->blocks_used;
 	btrfs_end_transaction_throttle(trans, root);
@@ -4864,8 +4763,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 
 	btrfs_inc_nlink(inode);
 	inode->i_ctime = CURRENT_TIME;
-
-	btrfs_set_trans_block_group(trans, dir);
 	ihold(inode);
 
 	err = btrfs_add_nondir(trans, dir, dentry, inode, 1, index);
@@ -4874,7 +4771,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 		drop_inode = 1;
 	} else {
 		struct dentry *parent = dget_parent(dentry);
-		btrfs_update_inode_block_group(trans, dir);
 		err = btrfs_update_inode(trans, root, inode);
 		BUG_ON(err);
 		btrfs_log_new_name(trans, inode, NULL, parent);
@@ -4903,10 +4799,6 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	u64 index = 0;
 	unsigned long nr = 1;
 
-	err = btrfs_find_free_objectid(NULL, root, dir->i_ino, &objectid);
-	if (err)
-		return err;
-
 	/*
 	 * 2 items for inode and ref
 	 * 2 items for dir items
@@ -4915,12 +4807,14 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	trans = btrfs_start_transaction(root, 5);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
-	btrfs_set_trans_block_group(trans, dir);
+
+	err = btrfs_find_free_ino(root, &objectid);
+	if (err)
+		goto out_fail;
 
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
-				dentry->d_name.len, dir->i_ino, objectid,
-				BTRFS_I(dir)->block_group, S_IFDIR | mode,
-				&index);
+				dentry->d_name.len, btrfs_ino(dir), objectid,
+				S_IFDIR | mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto out_fail;
@@ -4934,7 +4828,6 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 
 	inode->i_op = &btrfs_dir_inode_operations;
 	inode->i_fop = &btrfs_dir_file_operations;
-	btrfs_set_trans_block_group(trans, inode);
 
 	btrfs_i_size_write(inode, 0);
 	err = btrfs_update_inode(trans, root, inode);
@@ -4948,8 +4841,6 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 
 	d_instantiate(dentry, inode);
 	drop_on_err = 0;
-	btrfs_update_inode_block_group(trans, inode);
-	btrfs_update_inode_block_group(trans, dir);
 
 out_fail:
 	nr = trans->blocks_used;
@@ -5041,7 +4932,7 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 	u64 bytenr;
 	u64 extent_start = 0;
 	u64 extent_end = 0;
-	u64 objectid = inode->i_ino;
+	u64 objectid = btrfs_ino(inode);
 	u32 found_type;
 	struct btrfs_path *path = NULL;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -5069,7 +4960,7 @@ again:
 		else
 			goto out;
 	}
-	em = alloc_extent_map(GFP_NOFS);
+	em = alloc_extent_map();
 	if (!em) {
 		err = -ENOMEM;
 		goto out;
@@ -5082,7 +4973,15 @@ again:
 
 	if (!path) {
 		path = btrfs_alloc_path();
-		BUG_ON(!path);
+		if (!path) {
+			err = -ENOMEM;
+			goto out;
+		}
+		/*
+		 * Chances are we'll be called again, so go ahead and do
+		 * readahead
+		 */
+		path->reada = 1;
 	}
 
 	ret = btrfs_lookup_file_extent(trans, root, path,
@@ -5223,8 +5122,10 @@ again:
 				kunmap(page);
 				free_extent_map(em);
 				em = NULL;
-				btrfs_release_path(root, path);
-				trans = btrfs_join_transaction(root, 1);
+
+				btrfs_release_path(path);
+				trans = btrfs_join_transaction(root);
+
 				if (IS_ERR(trans))
 					return ERR_CAST(trans);
 				goto again;
@@ -5249,7 +5150,7 @@ not_found_em:
 	em->block_start = EXTENT_MAP_HOLE;
 	set_bit(EXTENT_FLAG_VACANCY, &em->flags);
 insert:
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	if (em->start > start || extent_map_end(em) <= start) {
 		printk(KERN_ERR "Btrfs: bad extent! em: [%llu %llu] passed "
 		       "[%llu %llu]\n", (unsigned long long)em->start,
@@ -5382,7 +5283,7 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
 		u64 hole_start = start;
 		u64 hole_len = len;
 
-		em = alloc_extent_map(GFP_NOFS);
+		em = alloc_extent_map();
 		if (!em) {
 			err = -ENOMEM;
 			goto out;
@@ -5468,10 +5369,13 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
 		btrfs_drop_extent_cache(inode, start, start + len - 1, 0);
 	}
 
-	trans = btrfs_join_transaction(root, 0);
+	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans))
 		return ERR_CAST(trans);
 
+	if (start <= BTRFS_I(inode)->disk_i_size && len < 64 * 1024)
+		btrfs_add_inode_defrag(trans, inode);
+
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	alloc_hint = get_extent_allocation_hint(inode, start, len);
@@ -5483,7 +5387,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
 	}
 
 	if (!em) {
-		em = alloc_extent_map(GFP_NOFS);
+		em = alloc_extent_map();
 		if (!em) {
 			em = ERR_PTR(-ENOMEM);
 			goto out;
@@ -5549,7 +5453,7 @@ static noinline int can_nocow_odirect(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	ret = btrfs_lookup_file_extent(trans, root, path, inode->i_ino,
+	ret = btrfs_lookup_file_extent(trans, root, path, btrfs_ino(inode),
 				       offset, 0);
 	if (ret < 0)
 		goto out;
@@ -5566,7 +5470,7 @@ static noinline int can_nocow_odirect(struct btrfs_trans_handle *trans,
 	ret = 0;
 	leaf = path->nodes[0];
 	btrfs_item_key_to_cpu(leaf, &key, slot);
-	if (key.objectid != inode->i_ino ||
+	if (key.objectid != btrfs_ino(inode) ||
 	    key.type != BTRFS_EXTENT_DATA_KEY) {
 		/* not our file or wrong item type, must cow */
 		goto out;
@@ -5600,7 +5504,7 @@ static noinline int can_nocow_odirect(struct btrfs_trans_handle *trans,
 	 * look for other files referencing this extent, if we
 	 * find any we must cow
 	 */
-	if (btrfs_cross_ref_exist(trans, root, inode->i_ino,
+	if (btrfs_cross_ref_exist(trans, root, btrfs_ino(inode),
 				  key.offset - backref_offset, disk_bytenr))
 		goto out;
 
@@ -5701,7 +5605,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 		 * to make sure the current transaction stays open
 		 * while we look for nocow cross refs
 		 */
-		trans = btrfs_join_transaction(root, 0);
+		trans = btrfs_join_transaction(root);
 		if (IS_ERR(trans))
 			goto must_cow;
 
@@ -5790,9 +5694,10 @@ static void btrfs_endio_direct_read(struct bio *bio, int err)
 
 			flush_dcache_page(bvec->bv_page);
 			if (csum != *private) {
-				printk(KERN_ERR "btrfs csum failed ino %lu off"
+				printk(KERN_ERR "btrfs csum failed ino %llu off"
 				      " %llu csum %u private %u\n",
-				      inode->i_ino, (unsigned long long)start,
+				      (unsigned long long)btrfs_ino(inode),
+				      (unsigned long long)start,
 				      csum, *private);
 				err = -EIO;
 			}
@@ -5839,7 +5744,7 @@ again:
 
 	BUG_ON(!ordered);
 
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans)) {
 		err = -ENOMEM;
 		goto out;
@@ -5939,9 +5844,9 @@ static void btrfs_end_dio_bio(struct bio *bio, int err)
 	struct btrfs_dio_private *dip = bio->bi_private;
 
 	if (err) {
-		printk(KERN_ERR "btrfs direct IO failed ino %lu rw %lu "
+		printk(KERN_ERR "btrfs direct IO failed ino %llu rw %lu "
 		      "sector %#Lx len %u err no %d\n",
-		      dip->inode->i_ino, bio->bi_rw,
+		      (unsigned long long)btrfs_ino(dip->inode), bio->bi_rw,
 		      (unsigned long long)bio->bi_sector, bio->bi_size, err);
 		dip->errors = 1;
 
@@ -6589,6 +6494,7 @@ out:
 static int btrfs_truncate(struct inode *inode)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_block_rsv *rsv;
 	int ret;
 	int err = 0;
 	struct btrfs_trans_handle *trans;
@@ -6602,28 +6508,80 @@ static int btrfs_truncate(struct inode *inode)
 	btrfs_wait_ordered_range(inode, inode->i_size & (~mask), (u64)-1);
 	btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
 
-	trans = btrfs_start_transaction(root, 5);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
+	/*
+	 * Yes ladies and gentelment, this is indeed ugly.  The fact is we have
+	 * 3 things going on here
+	 *
+	 * 1) We need to reserve space for our orphan item and the space to
+	 * delete our orphan item.  Lord knows we don't want to have a dangling
+	 * orphan item because we didn't reserve space to remove it.
+	 *
+	 * 2) We need to reserve space to update our inode.
+	 *
+	 * 3) We need to have something to cache all the space that is going to
+	 * be free'd up by the truncate operation, but also have some slack
+	 * space reserved in case it uses space during the truncate (thank you
+	 * very much snapshotting).
+	 *
+	 * And we need these to all be seperate.  The fact is we can use alot of
+	 * space doing the truncate, and we have no earthly idea how much space
+	 * we will use, so we need the truncate reservation to be seperate so it
+	 * doesn't end up using space reserved for updating the inode or
+	 * removing the orphan item.  We also need to be able to stop the
+	 * transaction and start a new one, which means we need to be able to
+	 * update the inode several times, and we have no idea of knowing how
+	 * many times that will be, so we can't just reserve 1 item for the
+	 * entirety of the opration, so that has to be done seperately as well.
+	 * Then there is the orphan item, which does indeed need to be held on
+	 * to for the whole operation, and we need nobody to touch this reserved
+	 * space except the orphan code.
+	 *
+	 * So that leaves us with
+	 *
+	 * 1) root->orphan_block_rsv - for the orphan deletion.
+	 * 2) rsv - for the truncate reservation, which we will steal from the
+	 * transaction reservation.
+	 * 3) fs_info->trans_block_rsv - this will have 1 items worth left for
+	 * updating the inode.
+	 */
+	rsv = btrfs_alloc_block_rsv(root);
+	if (!rsv)
+		return -ENOMEM;
+	btrfs_add_durable_block_rsv(root->fs_info, rsv);
 
-	btrfs_set_trans_block_group(trans, inode);
+	trans = btrfs_start_transaction(root, 4);
+	if (IS_ERR(trans)) {
+		err = PTR_ERR(trans);
+		goto out;
+	}
+
+	/*
+	 * Reserve space for the truncate process.  Truncate should be adding
+	 * space, but if there are snapshots it may end up using space.
+	 */
+	ret = btrfs_truncate_reserve_metadata(trans, root, rsv);
+	BUG_ON(ret);
 
 	ret = btrfs_orphan_add(trans, inode);
 	if (ret) {
 		btrfs_end_transaction(trans, root);
-		return ret;
+		goto out;
 	}
 
 	nr = trans->blocks_used;
 	btrfs_end_transaction(trans, root);
 	btrfs_btree_balance_dirty(root, nr);
 
-	/* Now start a transaction for the truncate */
-	trans = btrfs_start_transaction(root, 0);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
-	btrfs_set_trans_block_group(trans, inode);
-	trans->block_rsv = root->orphan_block_rsv;
+	/*
+	 * Ok so we've already migrated our bytes over for the truncate, so here
+	 * just reserve the one slot we need for updating the inode.
+	 */
+	trans = btrfs_start_transaction(root, 1);
+	if (IS_ERR(trans)) {
+		err = PTR_ERR(trans);
+		goto out;
+	}
+	trans->block_rsv = rsv;
 
 	/*
 	 * setattr is responsible for setting the ordered_data_close flag,
@@ -6647,24 +6605,17 @@ static int btrfs_truncate(struct inode *inode)
 
 	while (1) {
 		if (!trans) {
-			trans = btrfs_start_transaction(root, 0);
-			if (IS_ERR(trans))
-				return PTR_ERR(trans);
-			btrfs_set_trans_block_group(trans, inode);
-			trans->block_rsv = root->orphan_block_rsv;
-		}
+			trans = btrfs_start_transaction(root, 3);
+			if (IS_ERR(trans)) {
+				err = PTR_ERR(trans);
+				goto out;
+			}
 
-		ret = btrfs_block_rsv_check(trans, root,
-					    root->orphan_block_rsv, 0, 5);
-		if (ret == -EAGAIN) {
-			ret = btrfs_commit_transaction(trans, root);
-			if (ret)
-				return ret;
-			trans = NULL;
-			continue;
-		} else if (ret) {
-			err = ret;
-			break;
+			ret = btrfs_truncate_reserve_metadata(trans, root,
+							      rsv);
+			BUG_ON(ret);
+
+			trans->block_rsv = rsv;
 		}
 
 		ret = btrfs_truncate_inode_items(trans, root, inode,
@@ -6675,6 +6626,7 @@ static int btrfs_truncate(struct inode *inode)
 			break;
 		}
 
+		trans->block_rsv = &root->fs_info->trans_block_rsv;
 		ret = btrfs_update_inode(trans, root, inode);
 		if (ret) {
 			err = ret;
@@ -6688,6 +6640,7 @@ static int btrfs_truncate(struct inode *inode)
 	}
 
 	if (ret == 0 && inode->i_nlink > 0) {
+		trans->block_rsv = root->orphan_block_rsv;
 		ret = btrfs_orphan_del(trans, inode);
 		if (ret)
 			err = ret;
@@ -6699,15 +6652,20 @@ static int btrfs_truncate(struct inode *inode)
 		ret = btrfs_orphan_del(NULL, inode);
 	}
 
+	trans->block_rsv = &root->fs_info->trans_block_rsv;
 	ret = btrfs_update_inode(trans, root, inode);
 	if (ret && !err)
 		err = ret;
 
 	nr = trans->blocks_used;
 	ret = btrfs_end_transaction_throttle(trans, root);
+	btrfs_btree_balance_dirty(root, nr);
+
+out:
+	btrfs_free_block_rsv(root, rsv);
+
 	if (ret && !err)
 		err = ret;
-	btrfs_btree_balance_dirty(root, nr);
 
 	return err;
 }
@@ -6716,15 +6674,14 @@ static int btrfs_truncate(struct inode *inode)
  * create a new subvolume directory/inode (helper for the ioctl).
  */
 int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
-			     struct btrfs_root *new_root,
-			     u64 new_dirid, u64 alloc_hint)
+			     struct btrfs_root *new_root, u64 new_dirid)
 {
 	struct inode *inode;
 	int err;
 	u64 index = 0;
 
 	inode = btrfs_new_inode(trans, new_root, NULL, "..", 2, new_dirid,
-				new_dirid, alloc_hint, S_IFDIR | 0700, &index);
+				new_dirid, S_IFDIR | 0700, &index);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 	inode->i_op = &btrfs_dir_inode_operations;
@@ -6782,12 +6739,15 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->ordered_data_close = 0;
 	ei->orphan_meta_reserved = 0;
 	ei->dummy_inode = 0;
+	ei->in_defrag = 0;
 	ei->force_compress = BTRFS_COMPRESS_NONE;
 
+	ei->delayed_node = NULL;
+
 	inode = &ei->vfs_inode;
-	extent_map_tree_init(&ei->extent_tree, GFP_NOFS);
-	extent_io_tree_init(&ei->io_tree, &inode->i_data, GFP_NOFS);
-	extent_io_tree_init(&ei->io_failure_tree, &inode->i_data, GFP_NOFS);
+	extent_map_tree_init(&ei->extent_tree);
+	extent_io_tree_init(&ei->io_tree, &inode->i_data);
+	extent_io_tree_init(&ei->io_failure_tree, &inode->i_data);
 	mutex_init(&ei->log_mutex);
 	btrfs_ordered_inode_tree_init(&ei->ordered_tree);
 	INIT_LIST_HEAD(&ei->i_orphan);
@@ -6834,25 +6794,10 @@ void btrfs_destroy_inode(struct inode *inode)
 		spin_unlock(&root->fs_info->ordered_extent_lock);
 	}
 
-	if (root == root->fs_info->tree_root) {
-		struct btrfs_block_group_cache *block_group;
-
-		block_group = btrfs_lookup_block_group(root->fs_info,
-						BTRFS_I(inode)->block_group);
-		if (block_group && block_group->inode == inode) {
-			spin_lock(&block_group->lock);
-			block_group->inode = NULL;
-			spin_unlock(&block_group->lock);
-			btrfs_put_block_group(block_group);
-		} else if (block_group) {
-			btrfs_put_block_group(block_group);
-		}
-	}
-
 	spin_lock(&root->orphan_lock);
 	if (!list_empty(&BTRFS_I(inode)->i_orphan)) {
-		printk(KERN_INFO "BTRFS: inode %lu still on the orphan list\n",
-		       inode->i_ino);
+		printk(KERN_INFO "BTRFS: inode %llu still on the orphan list\n",
+		       (unsigned long long)btrfs_ino(inode));
 		list_del_init(&BTRFS_I(inode)->i_orphan);
 	}
 	spin_unlock(&root->orphan_lock);
@@ -6874,6 +6819,7 @@ void btrfs_destroy_inode(struct inode *inode)
 	inode_tree_del(inode);
 	btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
 free:
+	btrfs_remove_delayed_node(inode);
 	call_rcu(&inode->i_rcu, btrfs_i_callback);
 }
 
@@ -6882,7 +6828,7 @@ int btrfs_drop_inode(struct inode *inode)
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 
 	if (btrfs_root_refs(&root->root_item) == 0 &&
-	    root != root->fs_info->tree_root)
+	    !is_free_space_inode(root, inode))
 		return 1;
 	else
 		return generic_drop_inode(inode);
@@ -6991,16 +6937,17 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	u64 index = 0;
 	u64 root_objectid;
 	int ret;
+	u64 old_ino = btrfs_ino(old_inode);
 
-	if (new_dir->i_ino == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
+	if (btrfs_ino(new_dir) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
 		return -EPERM;
 
 	/* we only allow rename subvolume link between subvolumes */
-	if (old_inode->i_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest)
+	if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest)
 		return -EXDEV;
 
-	if (old_inode->i_ino == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID ||
-	    (new_inode && new_inode->i_ino == BTRFS_FIRST_FREE_OBJECTID))
+	if (old_ino == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID ||
+	    (new_inode && btrfs_ino(new_inode) == BTRFS_FIRST_FREE_OBJECTID))
 		return -ENOTEMPTY;
 
 	if (S_ISDIR(old_inode->i_mode) && new_inode &&
@@ -7016,7 +6963,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		filemap_flush(old_inode->i_mapping);
 
 	/* close the racy window with snapshot create/destroy ioctl */
-	if (old_inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)
+	if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
 		down_read(&root->fs_info->subvol_sem);
 	/*
 	 * We want to reserve the absolute worst case amount of items.  So if
@@ -7032,8 +6979,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
                 goto out_notrans;
         }
 
-	btrfs_set_trans_block_group(trans, new_dir);
-
 	if (dest != root)
 		btrfs_record_root_in_trans(trans, dest);
 
@@ -7041,15 +6986,15 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (ret)
 		goto out_fail;
 
-	if (unlikely(old_inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)) {
+	if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		/* force full log commit if subvolume involved. */
 		root->fs_info->last_trans_log_full_commit = trans->transid;
 	} else {
 		ret = btrfs_insert_inode_ref(trans, dest,
 					     new_dentry->d_name.name,
 					     new_dentry->d_name.len,
-					     old_inode->i_ino,
-					     new_dir->i_ino, index);
+					     old_ino,
+					     btrfs_ino(new_dir), index);
 		if (ret)
 			goto out_fail;
 		/*
@@ -7065,10 +7010,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 * make sure the inode gets flushed if it is replacing
 	 * something.
 	 */
-	if (new_inode && new_inode->i_size &&
-	    old_inode && S_ISREG(old_inode->i_mode)) {
+	if (new_inode && new_inode->i_size && S_ISREG(old_inode->i_mode))
 		btrfs_add_ordered_operation(trans, root, old_inode);
-	}
 
 	old_dir->i_ctime = old_dir->i_mtime = ctime;
 	new_dir->i_ctime = new_dir->i_mtime = ctime;
@@ -7077,7 +7020,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (old_dentry->d_parent != new_dentry->d_parent)
 		btrfs_record_unlink_dir(trans, old_dir, old_inode, 1);
 
-	if (unlikely(old_inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)) {
+	if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
 		ret = btrfs_unlink_subvol(trans, root, old_dir, root_objectid,
 					old_dentry->d_name.name,
@@ -7094,7 +7037,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	if (new_inode) {
 		new_inode->i_ctime = CURRENT_TIME;
-		if (unlikely(new_inode->i_ino ==
+		if (unlikely(btrfs_ino(new_inode) ==
 			     BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
 			root_objectid = BTRFS_I(new_inode)->location.objectid;
 			ret = btrfs_unlink_subvol(trans, dest, new_dir,
@@ -7122,7 +7065,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			     new_dentry->d_name.len, 0, index);
 	BUG_ON(ret);
 
-	if (old_inode->i_ino != BTRFS_FIRST_FREE_OBJECTID) {
+	if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
 		struct dentry *parent = dget_parent(new_dentry);
 		btrfs_log_new_name(trans, old_inode, old_dir, parent);
 		dput(parent);
@@ -7131,7 +7074,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 out_fail:
 	btrfs_end_transaction_throttle(trans, root);
 out_notrans:
-	if (old_inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)
+	if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
 		up_read(&root->fs_info->subvol_sem);
 
 	return ret;
@@ -7185,58 +7128,6 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
 	return 0;
 }
 
-int btrfs_start_one_delalloc_inode(struct btrfs_root *root, int delay_iput,
-				   int sync)
-{
-	struct btrfs_inode *binode;
-	struct inode *inode = NULL;
-
-	spin_lock(&root->fs_info->delalloc_lock);
-	while (!list_empty(&root->fs_info->delalloc_inodes)) {
-		binode = list_entry(root->fs_info->delalloc_inodes.next,
-				    struct btrfs_inode, delalloc_inodes);
-		inode = igrab(&binode->vfs_inode);
-		if (inode) {
-			list_move_tail(&binode->delalloc_inodes,
-				       &root->fs_info->delalloc_inodes);
-			break;
-		}
-
-		list_del_init(&binode->delalloc_inodes);
-		cond_resched_lock(&root->fs_info->delalloc_lock);
-	}
-	spin_unlock(&root->fs_info->delalloc_lock);
-
-	if (inode) {
-		if (sync) {
-			filemap_write_and_wait(inode->i_mapping);
-			/*
-			 * We have to do this because compression doesn't
-			 * actually set PG_writeback until it submits the pages
-			 * for IO, which happens in an async thread, so we could
-			 * race and not actually wait for any writeback pages
-			 * because they've not been submitted yet.  Technically
-			 * this could still be the case for the ordered stuff
-			 * since the async thread may not have started to do its
-			 * work yet.  If this becomes the case then we need to
-			 * figure out a way to make sure that in writepage we
-			 * wait for any async pages to be submitted before
-			 * returning so that fdatawait does what its supposed to
-			 * do.
-			 */
-			btrfs_wait_ordered_range(inode, 0, (u64)-1);
-		} else {
-			filemap_flush(inode->i_mapping);
-		}
-		if (delay_iput)
-			btrfs_add_delayed_iput(inode);
-		else
-			iput(inode);
-		return 1;
-	}
-	return 0;
-}
-
 static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 			 const char *symname)
 {
@@ -7260,9 +7151,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	if (name_len > BTRFS_MAX_INLINE_DATA_SIZE(root))
 		return -ENAMETOOLONG;
 
-	err = btrfs_find_free_objectid(NULL, root, dir->i_ino, &objectid);
-	if (err)
-		return err;
 	/*
 	 * 2 items for inode item and ref
 	 * 2 items for dir items
@@ -7272,12 +7160,13 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	btrfs_set_trans_block_group(trans, dir);
+	err = btrfs_find_free_ino(root, &objectid);
+	if (err)
+		goto out_unlock;
 
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
-				dentry->d_name.len, dir->i_ino, objectid,
-				BTRFS_I(dir)->block_group, S_IFLNK|S_IRWXUGO,
-				&index);
+				dentry->d_name.len, btrfs_ino(dir), objectid,
+				S_IFLNK|S_IRWXUGO, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto out_unlock;
@@ -7289,7 +7178,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 		goto out_unlock;
 	}
 
-	btrfs_set_trans_block_group(trans, inode);
 	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
 	if (err)
 		drop_inode = 1;
@@ -7300,14 +7188,12 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 		inode->i_op = &btrfs_file_inode_operations;
 		BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 	}
-	btrfs_update_inode_block_group(trans, inode);
-	btrfs_update_inode_block_group(trans, dir);
 	if (drop_inode)
 		goto out_unlock;
 
 	path = btrfs_alloc_path();
 	BUG_ON(!path);
-	key.objectid = inode->i_ino;
+	key.objectid = btrfs_ino(inode);
 	key.offset = 0;
 	btrfs_set_key_type(&key, BTRFS_EXTENT_DATA_KEY);
 	datasize = btrfs_file_extent_calc_inline_size(name_len);
@@ -7315,6 +7201,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 				      datasize);
 	if (err) {
 		drop_inode = 1;
+		btrfs_free_path(path);
 		goto out_unlock;
 	}
 	leaf = path->nodes[0];
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 2616f7ed4799..a3c4751e07db 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -50,6 +50,7 @@
 #include "print-tree.h"
 #include "volumes.h"
 #include "locking.h"
+#include "inode-map.h"
 
 /* Mask out flags that are inappropriate for the given type of inode. */
 static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags)
@@ -242,7 +243,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 		ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
 	}
 
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	BUG_ON(IS_ERR(trans));
 
 	ret = btrfs_update_inode(trans, root, inode);
@@ -281,8 +282,9 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	mutex_lock(&fs_info->fs_devices->device_list_mutex);
-	list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(device, &fs_info->fs_devices->devices,
+				dev_list) {
 		if (!device->bdev)
 			continue;
 		q = bdev_get_queue(device->bdev);
@@ -292,7 +294,7 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
 				     minlen);
 		}
 	}
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	rcu_read_unlock();
 	if (!num_devices)
 		return -EOPNOTSUPP;
 
@@ -329,8 +331,7 @@ static noinline int create_subvol(struct btrfs_root *root,
 	u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
 	u64 index = 0;
 
-	ret = btrfs_find_free_objectid(NULL, root->fs_info->tree_root,
-				       0, &objectid);
+	ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid);
 	if (ret) {
 		dput(parent);
 		return ret;
@@ -413,8 +414,7 @@ static noinline int create_subvol(struct btrfs_root *root,
 
 	btrfs_record_root_in_trans(trans, new_root);
 
-	ret = btrfs_create_subvol_root(trans, new_root, new_dirid,
-				       BTRFS_I(dir)->block_group);
+	ret = btrfs_create_subvol_root(trans, new_root, new_dirid);
 	/*
 	 * insert the directory item
 	 */
@@ -422,7 +422,7 @@ static noinline int create_subvol(struct btrfs_root *root,
 	BUG_ON(ret);
 
 	ret = btrfs_insert_dir_item(trans, root,
-				    name, namelen, dir->i_ino, &key,
+				    name, namelen, dir, &key,
 				    BTRFS_FT_DIR, index);
 	if (ret)
 		goto fail;
@@ -433,7 +433,7 @@ static noinline int create_subvol(struct btrfs_root *root,
 
 	ret = btrfs_add_root_ref(trans, root->fs_info->tree_root,
 				 objectid, root->root_key.objectid,
-				 dir->i_ino, index, name, namelen);
+				 btrfs_ino(dir), index, name, namelen);
 
 	BUG_ON(ret);
 
@@ -482,8 +482,10 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
 	ret = btrfs_snap_reserve_metadata(trans, pending_snapshot);
 	BUG_ON(ret);
 
+	spin_lock(&root->fs_info->trans_lock);
 	list_add(&pending_snapshot->list,
 		 &trans->transaction->pending_snapshots);
+	spin_unlock(&root->fs_info->trans_lock);
 	if (async_transid) {
 		*async_transid = trans->transid;
 		ret = btrfs_commit_transaction_async(trans,
@@ -655,6 +657,107 @@ out_unlock:
 	return error;
 }
 
+/*
+ * When we're defragging a range, we don't want to kick it off again
+ * if it is really just waiting for delalloc to send it down.
+ * If we find a nice big extent or delalloc range for the bytes in the
+ * file you want to defrag, we return 0 to let you know to skip this
+ * part of the file
+ */
+static int check_defrag_in_cache(struct inode *inode, u64 offset, int thresh)
+{
+	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+	struct extent_map *em = NULL;
+	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	u64 end;
+
+	read_lock(&em_tree->lock);
+	em = lookup_extent_mapping(em_tree, offset, PAGE_CACHE_SIZE);
+	read_unlock(&em_tree->lock);
+
+	if (em) {
+		end = extent_map_end(em);
+		free_extent_map(em);
+		if (end - offset > thresh)
+			return 0;
+	}
+	/* if we already have a nice delalloc here, just stop */
+	thresh /= 2;
+	end = count_range_bits(io_tree, &offset, offset + thresh,
+			       thresh, EXTENT_DELALLOC, 1);
+	if (end >= thresh)
+		return 0;
+	return 1;
+}
+
+/*
+ * helper function to walk through a file and find extents
+ * newer than a specific transid, and smaller than thresh.
+ *
+ * This is used by the defragging code to find new and small
+ * extents
+ */
+static int find_new_extents(struct btrfs_root *root,
+			    struct inode *inode, u64 newer_than,
+			    u64 *off, int thresh)
+{
+	struct btrfs_path *path;
+	struct btrfs_key min_key;
+	struct btrfs_key max_key;
+	struct extent_buffer *leaf;
+	struct btrfs_file_extent_item *extent;
+	int type;
+	int ret;
+	u64 ino = btrfs_ino(inode);
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	min_key.objectid = ino;
+	min_key.type = BTRFS_EXTENT_DATA_KEY;
+	min_key.offset = *off;
+
+	max_key.objectid = ino;
+	max_key.type = (u8)-1;
+	max_key.offset = (u64)-1;
+
+	path->keep_locks = 1;
+
+	while(1) {
+		ret = btrfs_search_forward(root, &min_key, &max_key,
+					   path, 0, newer_than);
+		if (ret != 0)
+			goto none;
+		if (min_key.objectid != ino)
+			goto none;
+		if (min_key.type != BTRFS_EXTENT_DATA_KEY)
+			goto none;
+
+		leaf = path->nodes[0];
+		extent = btrfs_item_ptr(leaf, path->slots[0],
+					struct btrfs_file_extent_item);
+
+		type = btrfs_file_extent_type(leaf, extent);
+		if (type == BTRFS_FILE_EXTENT_REG &&
+		    btrfs_file_extent_num_bytes(leaf, extent) < thresh &&
+		    check_defrag_in_cache(inode, min_key.offset, thresh)) {
+			*off = min_key.offset;
+			btrfs_free_path(path);
+			return 0;
+		}
+
+		if (min_key.offset == (u64)-1)
+			goto none;
+
+		min_key.offset++;
+		btrfs_release_path(path);
+	}
+none:
+	btrfs_free_path(path);
+	return -ENOENT;
+}
+
 static int should_defrag_range(struct inode *inode, u64 start, u64 len,
 			       int thresh, u64 *last_len, u64 *skip,
 			       u64 *defrag_end)
@@ -664,10 +767,6 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len,
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	int ret = 1;
 
-
-	if (thresh == 0)
-		thresh = 256 * 1024;
-
 	/*
 	 * make sure that once we start defragging and extent, we keep on
 	 * defragging it
@@ -726,27 +825,176 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len,
 	return ret;
 }
 
-static int btrfs_defrag_file(struct file *file,
-			     struct btrfs_ioctl_defrag_range_args *range)
+/*
+ * it doesn't do much good to defrag one or two pages
+ * at a time.  This pulls in a nice chunk of pages
+ * to COW and defrag.
+ *
+ * It also makes sure the delalloc code has enough
+ * dirty data to avoid making new small extents as part
+ * of the defrag
+ *
+ * It's a good idea to start RA on this range
+ * before calling this.
+ */
+static int cluster_pages_for_defrag(struct inode *inode,
+				    struct page **pages,
+				    unsigned long start_index,
+				    int num_pages)
 {
-	struct inode *inode = fdentry(file)->d_inode;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+	unsigned long file_end;
+	u64 isize = i_size_read(inode);
+	u64 page_start;
+	u64 page_end;
+	int ret;
+	int i;
+	int i_done;
 	struct btrfs_ordered_extent *ordered;
-	struct page *page;
+	struct extent_state *cached_state = NULL;
+
+	if (isize == 0)
+		return 0;
+	file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
+
+	ret = btrfs_delalloc_reserve_space(inode,
+					   num_pages << PAGE_CACHE_SHIFT);
+	if (ret)
+		return ret;
+again:
+	ret = 0;
+	i_done = 0;
+
+	/* step one, lock all the pages */
+	for (i = 0; i < num_pages; i++) {
+		struct page *page;
+		page = grab_cache_page(inode->i_mapping,
+					    start_index + i);
+		if (!page)
+			break;
+
+		if (!PageUptodate(page)) {
+			btrfs_readpage(NULL, page);
+			lock_page(page);
+			if (!PageUptodate(page)) {
+				unlock_page(page);
+				page_cache_release(page);
+				ret = -EIO;
+				break;
+			}
+		}
+		isize = i_size_read(inode);
+		file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
+		if (!isize || page->index > file_end ||
+		    page->mapping != inode->i_mapping) {
+			/* whoops, we blew past eof, skip this page */
+			unlock_page(page);
+			page_cache_release(page);
+			break;
+		}
+		pages[i] = page;
+		i_done++;
+	}
+	if (!i_done || ret)
+		goto out;
+
+	if (!(inode->i_sb->s_flags & MS_ACTIVE))
+		goto out;
+
+	/*
+	 * so now we have a nice long stream of locked
+	 * and up to date pages, lets wait on them
+	 */
+	for (i = 0; i < i_done; i++)
+		wait_on_page_writeback(pages[i]);
+
+	page_start = page_offset(pages[0]);
+	page_end = page_offset(pages[i_done - 1]) + PAGE_CACHE_SIZE;
+
+	lock_extent_bits(&BTRFS_I(inode)->io_tree,
+			 page_start, page_end - 1, 0, &cached_state,
+			 GFP_NOFS);
+	ordered = btrfs_lookup_first_ordered_extent(inode, page_end - 1);
+	if (ordered &&
+	    ordered->file_offset + ordered->len > page_start &&
+	    ordered->file_offset < page_end) {
+		btrfs_put_ordered_extent(ordered);
+		unlock_extent_cached(&BTRFS_I(inode)->io_tree,
+				     page_start, page_end - 1,
+				     &cached_state, GFP_NOFS);
+		for (i = 0; i < i_done; i++) {
+			unlock_page(pages[i]);
+			page_cache_release(pages[i]);
+		}
+		btrfs_wait_ordered_range(inode, page_start,
+					 page_end - page_start);
+		goto again;
+	}
+	if (ordered)
+		btrfs_put_ordered_extent(ordered);
+
+	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start,
+			  page_end - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
+			  EXTENT_DO_ACCOUNTING, 0, 0, &cached_state,
+			  GFP_NOFS);
+
+	if (i_done != num_pages) {
+		atomic_inc(&BTRFS_I(inode)->outstanding_extents);
+		btrfs_delalloc_release_space(inode,
+				     (num_pages - i_done) << PAGE_CACHE_SHIFT);
+	}
+
+
+	btrfs_set_extent_delalloc(inode, page_start, page_end - 1,
+				  &cached_state);
+
+	unlock_extent_cached(&BTRFS_I(inode)->io_tree,
+			     page_start, page_end - 1, &cached_state,
+			     GFP_NOFS);
+
+	for (i = 0; i < i_done; i++) {
+		clear_page_dirty_for_io(pages[i]);
+		ClearPageChecked(pages[i]);
+		set_page_extent_mapped(pages[i]);
+		set_page_dirty(pages[i]);
+		unlock_page(pages[i]);
+		page_cache_release(pages[i]);
+	}
+	return i_done;
+out:
+	for (i = 0; i < i_done; i++) {
+		unlock_page(pages[i]);
+		page_cache_release(pages[i]);
+	}
+	btrfs_delalloc_release_space(inode, num_pages << PAGE_CACHE_SHIFT);
+	return ret;
+
+}
+
+int btrfs_defrag_file(struct inode *inode, struct file *file,
+		      struct btrfs_ioctl_defrag_range_args *range,
+		      u64 newer_than, unsigned long max_to_defrag)
+{
+	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_super_block *disk_super;
+	struct file_ra_state *ra = NULL;
 	unsigned long last_index;
-	unsigned long ra_pages = root->fs_info->bdi.ra_pages;
-	unsigned long total_read = 0;
 	u64 features;
-	u64 page_start;
-	u64 page_end;
 	u64 last_len = 0;
 	u64 skip = 0;
 	u64 defrag_end = 0;
+	u64 newer_off = range->start;
+	int newer_left = 0;
 	unsigned long i;
 	int ret;
+	int defrag_count = 0;
 	int compress_type = BTRFS_COMPRESS_ZLIB;
+	int extent_thresh = range->extent_thresh;
+	int newer_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
+	u64 new_align = ~((u64)128 * 1024 - 1);
+	struct page **pages = NULL;
+
+	if (extent_thresh == 0)
+		extent_thresh = 256 * 1024;
 
 	if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) {
 		if (range->compress_type > BTRFS_COMPRESS_TYPES)
@@ -758,6 +1006,27 @@ static int btrfs_defrag_file(struct file *file,
 	if (inode->i_size == 0)
 		return 0;
 
+	/*
+	 * if we were not given a file, allocate a readahead
+	 * context
+	 */
+	if (!file) {
+		ra = kzalloc(sizeof(*ra), GFP_NOFS);
+		if (!ra)
+			return -ENOMEM;
+		file_ra_state_init(ra, inode->i_mapping);
+	} else {
+		ra = &file->f_ra;
+	}
+
+	pages = kmalloc(sizeof(struct page *) * newer_cluster,
+			GFP_NOFS);
+	if (!pages) {
+		ret = -ENOMEM;
+		goto out_ra;
+	}
+
+	/* find the last page to defrag */
 	if (range->start + range->len > range->start) {
 		last_index = min_t(u64, inode->i_size - 1,
 			 range->start + range->len - 1) >> PAGE_CACHE_SHIFT;
@@ -765,11 +1034,37 @@ static int btrfs_defrag_file(struct file *file,
 		last_index = (inode->i_size - 1) >> PAGE_CACHE_SHIFT;
 	}
 
-	i = range->start >> PAGE_CACHE_SHIFT;
-	while (i <= last_index) {
-		if (!should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT,
+	if (newer_than) {
+		ret = find_new_extents(root, inode, newer_than,
+				       &newer_off, 64 * 1024);
+		if (!ret) {
+			range->start = newer_off;
+			/*
+			 * we always align our defrag to help keep
+			 * the extents in the file evenly spaced
+			 */
+			i = (newer_off & new_align) >> PAGE_CACHE_SHIFT;
+			newer_left = newer_cluster;
+		} else
+			goto out_ra;
+	} else {
+		i = range->start >> PAGE_CACHE_SHIFT;
+	}
+	if (!max_to_defrag)
+		max_to_defrag = last_index - 1;
+
+	while (i <= last_index && defrag_count < max_to_defrag) {
+		/*
+		 * make sure we stop running if someone unmounts
+		 * the FS
+		 */
+		if (!(inode->i_sb->s_flags & MS_ACTIVE))
+			break;
+
+		if (!newer_than &&
+		    !should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT,
 					PAGE_CACHE_SIZE,
-					range->extent_thresh,
+					extent_thresh,
 					&last_len, &skip,
 					&defrag_end)) {
 			unsigned long next;
@@ -781,92 +1076,39 @@ static int btrfs_defrag_file(struct file *file,
 			i = max(i + 1, next);
 			continue;
 		}
-
-		if (total_read % ra_pages == 0) {
-			btrfs_force_ra(inode->i_mapping, &file->f_ra, file, i,
-				       min(last_index, i + ra_pages - 1));
-		}
-		total_read++;
-		mutex_lock(&inode->i_mutex);
 		if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
 			BTRFS_I(inode)->force_compress = compress_type;
 
-		ret  = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
-		if (ret)
-			goto err_unlock;
-again:
-		if (inode->i_size == 0 ||
-		    i > ((inode->i_size - 1) >> PAGE_CACHE_SHIFT)) {
-			ret = 0;
-			goto err_reservations;
-		}
-
-		page = grab_cache_page(inode->i_mapping, i);
-		if (!page) {
-			ret = -ENOMEM;
-			goto err_reservations;
-		}
-
-		if (!PageUptodate(page)) {
-			btrfs_readpage(NULL, page);
-			lock_page(page);
-			if (!PageUptodate(page)) {
-				unlock_page(page);
-				page_cache_release(page);
-				ret = -EIO;
-				goto err_reservations;
-			}
-		}
-
-		if (page->mapping != inode->i_mapping) {
-			unlock_page(page);
-			page_cache_release(page);
-			goto again;
-		}
+		btrfs_force_ra(inode->i_mapping, ra, file, i, newer_cluster);
 
-		wait_on_page_writeback(page);
+		ret = cluster_pages_for_defrag(inode, pages, i, newer_cluster);
+		if (ret < 0)
+			goto out_ra;
 
-		if (PageDirty(page)) {
-			btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
-			goto loop_unlock;
-		}
+		defrag_count += ret;
+		balance_dirty_pages_ratelimited_nr(inode->i_mapping, ret);
+		i += ret;
 
-		page_start = (u64)page->index << PAGE_CACHE_SHIFT;
-		page_end = page_start + PAGE_CACHE_SIZE - 1;
-		lock_extent(io_tree, page_start, page_end, GFP_NOFS);
+		if (newer_than) {
+			if (newer_off == (u64)-1)
+				break;
 
-		ordered = btrfs_lookup_ordered_extent(inode, page_start);
-		if (ordered) {
-			unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
-			unlock_page(page);
-			page_cache_release(page);
-			btrfs_start_ordered_extent(inode, ordered, 1);
-			btrfs_put_ordered_extent(ordered);
-			goto again;
+			newer_off = max(newer_off + 1,
+					(u64)i << PAGE_CACHE_SHIFT);
+
+			ret = find_new_extents(root, inode,
+					       newer_than, &newer_off,
+					       64 * 1024);
+			if (!ret) {
+				range->start = newer_off;
+				i = (newer_off & new_align) >> PAGE_CACHE_SHIFT;
+				newer_left = newer_cluster;
+			} else {
+				break;
+			}
+		} else {
+			i++;
 		}
-		set_page_extent_mapped(page);
-
-		/*
-		 * this makes sure page_mkwrite is called on the
-		 * page if it is dirtied again later
-		 */
-		clear_page_dirty_for_io(page);
-		clear_extent_bits(&BTRFS_I(inode)->io_tree, page_start,
-				  page_end, EXTENT_DIRTY | EXTENT_DELALLOC |
-				  EXTENT_DO_ACCOUNTING, GFP_NOFS);
-
-		btrfs_set_extent_delalloc(inode, page_start, page_end, NULL);
-		ClearPageChecked(page);
-		set_page_dirty(page);
-		unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
-
-loop_unlock:
-		unlock_page(page);
-		page_cache_release(page);
-		mutex_unlock(&inode->i_mutex);
-
-		balance_dirty_pages_ratelimited_nr(inode->i_mapping, 1);
-		i++;
 	}
 
 	if ((range->flags & BTRFS_DEFRAG_RANGE_START_IO))
@@ -898,12 +1140,14 @@ loop_unlock:
 		btrfs_set_super_incompat_flags(disk_super, features);
 	}
 
-	return 0;
+	if (!file)
+		kfree(ra);
+	return defrag_count;
 
-err_reservations:
-	btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
-err_unlock:
-	mutex_unlock(&inode->i_mutex);
+out_ra:
+	if (!file)
+		kfree(ra);
+	kfree(pages);
 	return ret;
 }
 
@@ -1129,7 +1373,7 @@ static noinline int btrfs_ioctl_subvol_getflags(struct file *file,
 	int ret = 0;
 	u64 flags = 0;
 
-	if (inode->i_ino != BTRFS_FIRST_FREE_OBJECTID)
+	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID)
 		return -EINVAL;
 
 	down_read(&root->fs_info->subvol_sem);
@@ -1156,7 +1400,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
 	if (root->fs_info->sb->s_flags & MS_RDONLY)
 		return -EROFS;
 
-	if (inode->i_ino != BTRFS_FIRST_FREE_OBJECTID)
+	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID)
 		return -EINVAL;
 
 	if (copy_from_user(&flags, arg, sizeof(flags)))
@@ -1279,7 +1523,6 @@ static noinline int copy_to_sk(struct btrfs_root *root,
 	int nritems;
 	int i;
 	int slot;
-	int found = 0;
 	int ret = 0;
 
 	leaf = path->nodes[0];
@@ -1326,7 +1569,7 @@ static noinline int copy_to_sk(struct btrfs_root *root,
 					   item_off, item_len);
 			*sk_offset += item_len;
 		}
-		found++;
+		(*num_found)++;
 
 		if (*num_found >= sk->nr_items)
 			break;
@@ -1345,7 +1588,6 @@ advance_key:
 	} else
 		ret = 1;
 overflow:
-	*num_found += found;
 	return ret;
 }
 
@@ -1402,7 +1644,7 @@ static noinline int search_ioctl(struct inode *inode,
 		}
 		ret = copy_to_sk(root, path, &key, sk, args->buf,
 				 &sk_offset, &num_found);
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		if (ret || num_found >= sk->nr_items)
 			break;
 
@@ -1509,7 +1751,7 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info,
 		if (key.offset == BTRFS_FIRST_FREE_OBJECTID)
 			break;
 
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		key.objectid = key.offset;
 		key.offset = (u64)-1;
 		dirid = key.objectid;
@@ -1639,7 +1881,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 			goto out_dput;
 	}
 
-	if (inode->i_ino != BTRFS_FIRST_FREE_OBJECTID) {
+	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
 		err = -EINVAL;
 		goto out_dput;
 	}
@@ -1757,7 +1999,10 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 			/* the rest are all set to zero by kzalloc */
 			range->len = (u64)-1;
 		}
-		ret = btrfs_defrag_file(file, range);
+		ret = btrfs_defrag_file(fdentry(file)->d_inode, file,
+					range, 0, 0);
+		if (ret > 0)
+			ret = 0;
 		kfree(range);
 		break;
 	default:
@@ -1809,6 +2054,80 @@ static long btrfs_ioctl_rm_dev(struct btrfs_root *root, void __user *arg)
 	return ret;
 }
 
+static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg)
+{
+	struct btrfs_ioctl_fs_info_args *fi_args;
+	struct btrfs_device *device;
+	struct btrfs_device *next;
+	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
+	int ret = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	fi_args = kzalloc(sizeof(*fi_args), GFP_KERNEL);
+	if (!fi_args)
+		return -ENOMEM;
+
+	fi_args->num_devices = fs_devices->num_devices;
+	memcpy(&fi_args->fsid, root->fs_info->fsid, sizeof(fi_args->fsid));
+
+	mutex_lock(&fs_devices->device_list_mutex);
+	list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) {
+		if (device->devid > fi_args->max_id)
+			fi_args->max_id = device->devid;
+	}
+	mutex_unlock(&fs_devices->device_list_mutex);
+
+	if (copy_to_user(arg, fi_args, sizeof(*fi_args)))
+		ret = -EFAULT;
+
+	kfree(fi_args);
+	return ret;
+}
+
+static long btrfs_ioctl_dev_info(struct btrfs_root *root, void __user *arg)
+{
+	struct btrfs_ioctl_dev_info_args *di_args;
+	struct btrfs_device *dev;
+	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
+	int ret = 0;
+	char *s_uuid = NULL;
+	char empty_uuid[BTRFS_UUID_SIZE] = {0};
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	di_args = memdup_user(arg, sizeof(*di_args));
+	if (IS_ERR(di_args))
+		return PTR_ERR(di_args);
+
+	if (memcmp(empty_uuid, di_args->uuid, BTRFS_UUID_SIZE) != 0)
+		s_uuid = di_args->uuid;
+
+	mutex_lock(&fs_devices->device_list_mutex);
+	dev = btrfs_find_device(root, di_args->devid, s_uuid, NULL);
+	mutex_unlock(&fs_devices->device_list_mutex);
+
+	if (!dev) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	di_args->devid = dev->devid;
+	di_args->bytes_used = dev->bytes_used;
+	di_args->total_bytes = dev->total_bytes;
+	memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid));
+	strncpy(di_args->path, dev->name, sizeof(di_args->path));
+
+out:
+	if (ret == 0 && copy_to_user(arg, di_args, sizeof(*di_args)))
+		ret = -EFAULT;
+
+	kfree(di_args);
+	return ret;
+}
+
 static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 				       u64 off, u64 olen, u64 destoff)
 {
@@ -1925,7 +2244,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	}
 
 	/* clone data */
-	key.objectid = src->i_ino;
+	key.objectid = btrfs_ino(src);
 	key.type = BTRFS_EXTENT_DATA_KEY;
 	key.offset = 0;
 
@@ -1952,7 +2271,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 
 		btrfs_item_key_to_cpu(leaf, &key, slot);
 		if (btrfs_key_type(&key) > BTRFS_EXTENT_DATA_KEY ||
-		    key.objectid != src->i_ino)
+		    key.objectid != btrfs_ino(src))
 			break;
 
 		if (btrfs_key_type(&key) == BTRFS_EXTENT_DATA_KEY) {
@@ -1988,14 +2307,14 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 				datal = btrfs_file_extent_ram_bytes(leaf,
 								    extent);
 			}
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 
 			if (key.offset + datal <= off ||
 			    key.offset >= off+len)
 				goto next;
 
 			memcpy(&new_key, &key, sizeof(new_key));
-			new_key.objectid = inode->i_ino;
+			new_key.objectid = btrfs_ino(inode);
 			if (off <= key.offset)
 				new_key.offset = key.offset + destoff - off;
 			else
@@ -2049,7 +2368,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 					ret = btrfs_inc_extent_ref(trans, root,
 							disko, diskl, 0,
 							root->root_key.objectid,
-							inode->i_ino,
+							btrfs_ino(inode),
 							new_key.offset - datao);
 					BUG_ON(ret);
 				}
@@ -2098,7 +2417,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 			}
 
 			btrfs_mark_buffer_dirty(leaf);
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 
 			inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 
@@ -2119,12 +2438,12 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 			btrfs_end_transaction(trans, root);
 		}
 next:
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		key.offset++;
 	}
 	ret = 0;
 out:
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	unlock_extent(&BTRFS_I(src)->io_tree, off, off+len, GFP_NOFS);
 out_unlock:
 	mutex_unlock(&src->i_mutex);
@@ -2177,12 +2496,10 @@ static long btrfs_ioctl_trans_start(struct file *file)
 	if (ret)
 		goto out;
 
-	mutex_lock(&root->fs_info->trans_mutex);
-	root->fs_info->open_ioctl_trans++;
-	mutex_unlock(&root->fs_info->trans_mutex);
+	atomic_inc(&root->fs_info->open_ioctl_trans);
 
 	ret = -ENOMEM;
-	trans = btrfs_start_ioctl_transaction(root, 0);
+	trans = btrfs_start_ioctl_transaction(root);
 	if (IS_ERR(trans))
 		goto out_drop;
 
@@ -2190,9 +2507,7 @@ static long btrfs_ioctl_trans_start(struct file *file)
 	return 0;
 
 out_drop:
-	mutex_lock(&root->fs_info->trans_mutex);
-	root->fs_info->open_ioctl_trans--;
-	mutex_unlock(&root->fs_info->trans_mutex);
+	atomic_dec(&root->fs_info->open_ioctl_trans);
 	mnt_drop_write(file->f_path.mnt);
 out:
 	return ret;
@@ -2426,9 +2741,7 @@ long btrfs_ioctl_trans_end(struct file *file)
 
 	btrfs_end_transaction(trans, root);
 
-	mutex_lock(&root->fs_info->trans_mutex);
-	root->fs_info->open_ioctl_trans--;
-	mutex_unlock(&root->fs_info->trans_mutex);
+	atomic_dec(&root->fs_info->open_ioctl_trans);
 
 	mnt_drop_write(file->f_path.mnt);
 	return 0;
@@ -2471,6 +2784,58 @@ static noinline long btrfs_ioctl_wait_sync(struct file *file, void __user *argp)
 	return btrfs_wait_for_commit(root, transid);
 }
 
+static long btrfs_ioctl_scrub(struct btrfs_root *root, void __user *arg)
+{
+	int ret;
+	struct btrfs_ioctl_scrub_args *sa;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	sa = memdup_user(arg, sizeof(*sa));
+	if (IS_ERR(sa))
+		return PTR_ERR(sa);
+
+	ret = btrfs_scrub_dev(root, sa->devid, sa->start, sa->end,
+			      &sa->progress, sa->flags & BTRFS_SCRUB_READONLY);
+
+	if (copy_to_user(arg, sa, sizeof(*sa)))
+		ret = -EFAULT;
+
+	kfree(sa);
+	return ret;
+}
+
+static long btrfs_ioctl_scrub_cancel(struct btrfs_root *root, void __user *arg)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return btrfs_scrub_cancel(root);
+}
+
+static long btrfs_ioctl_scrub_progress(struct btrfs_root *root,
+				       void __user *arg)
+{
+	struct btrfs_ioctl_scrub_args *sa;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	sa = memdup_user(arg, sizeof(*sa));
+	if (IS_ERR(sa))
+		return PTR_ERR(sa);
+
+	ret = btrfs_scrub_progress(root, sa->devid, &sa->progress);
+
+	if (copy_to_user(arg, sa, sizeof(*sa)))
+		ret = -EFAULT;
+
+	kfree(sa);
+	return ret;
+}
+
 long btrfs_ioctl(struct file *file, unsigned int
 		cmd, unsigned long arg)
 {
@@ -2510,6 +2875,10 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_add_dev(root, argp);
 	case BTRFS_IOC_RM_DEV:
 		return btrfs_ioctl_rm_dev(root, argp);
+	case BTRFS_IOC_FS_INFO:
+		return btrfs_ioctl_fs_info(root, argp);
+	case BTRFS_IOC_DEV_INFO:
+		return btrfs_ioctl_dev_info(root, argp);
 	case BTRFS_IOC_BALANCE:
 		return btrfs_balance(root->fs_info->dev_root);
 	case BTRFS_IOC_CLONE:
@@ -2533,6 +2902,12 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_start_sync(file, argp);
 	case BTRFS_IOC_WAIT_SYNC:
 		return btrfs_ioctl_wait_sync(file, argp);
+	case BTRFS_IOC_SCRUB:
+		return btrfs_ioctl_scrub(root, argp);
+	case BTRFS_IOC_SCRUB_CANCEL:
+		return btrfs_ioctl_scrub_cancel(root, argp);
+	case BTRFS_IOC_SCRUB_PROGRESS:
+		return btrfs_ioctl_scrub_progress(root, argp);
 	}
 
 	return -ENOTTY;
diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h
index 8fb382167b13..ad1ea789fcb4 100644
--- a/fs/btrfs/ioctl.h
+++ b/fs/btrfs/ioctl.h
@@ -32,6 +32,8 @@ struct btrfs_ioctl_vol_args {
 
 #define BTRFS_SUBVOL_CREATE_ASYNC	(1ULL << 0)
 #define BTRFS_SUBVOL_RDONLY		(1ULL << 1)
+#define BTRFS_FSID_SIZE 16
+#define BTRFS_UUID_SIZE 16
 
 #define BTRFS_SUBVOL_NAME_MAX 4039
 struct btrfs_ioctl_vol_args_v2 {
@@ -42,6 +44,71 @@ struct btrfs_ioctl_vol_args_v2 {
 	char name[BTRFS_SUBVOL_NAME_MAX + 1];
 };
 
+/*
+ * structure to report errors and progress to userspace, either as a
+ * result of a finished scrub, a canceled scrub or a progress inquiry
+ */
+struct btrfs_scrub_progress {
+	__u64 data_extents_scrubbed;	/* # of data extents scrubbed */
+	__u64 tree_extents_scrubbed;	/* # of tree extents scrubbed */
+	__u64 data_bytes_scrubbed;	/* # of data bytes scrubbed */
+	__u64 tree_bytes_scrubbed;	/* # of tree bytes scrubbed */
+	__u64 read_errors;		/* # of read errors encountered (EIO) */
+	__u64 csum_errors;		/* # of failed csum checks */
+	__u64 verify_errors;		/* # of occurences, where the metadata
+					 * of a tree block did not match the
+					 * expected values, like generation or
+					 * logical */
+	__u64 no_csum;			/* # of 4k data block for which no csum
+					 * is present, probably the result of
+					 * data written with nodatasum */
+	__u64 csum_discards;		/* # of csum for which no data was found
+					 * in the extent tree. */
+	__u64 super_errors;		/* # of bad super blocks encountered */
+	__u64 malloc_errors;		/* # of internal kmalloc errors. These
+					 * will likely cause an incomplete
+					 * scrub */
+	__u64 uncorrectable_errors;	/* # of errors where either no intact
+					 * copy was found or the writeback
+					 * failed */
+	__u64 corrected_errors;		/* # of errors corrected */
+	__u64 last_physical;		/* last physical address scrubbed. In
+					 * case a scrub was aborted, this can
+					 * be used to restart the scrub */
+	__u64 unverified_errors;	/* # of occurences where a read for a
+					 * full (64k) bio failed, but the re-
+					 * check succeeded for each 4k piece.
+					 * Intermittent error. */
+};
+
+#define BTRFS_SCRUB_READONLY	1
+struct btrfs_ioctl_scrub_args {
+	__u64 devid;				/* in */
+	__u64 start;				/* in */
+	__u64 end;				/* in */
+	__u64 flags;				/* in */
+	struct btrfs_scrub_progress progress;	/* out */
+	/* pad to 1k */
+	__u64 unused[(1024-32-sizeof(struct btrfs_scrub_progress))/8];
+};
+
+#define BTRFS_DEVICE_PATH_NAME_MAX 1024
+struct btrfs_ioctl_dev_info_args {
+	__u64 devid;				/* in/out */
+	__u8 uuid[BTRFS_UUID_SIZE];		/* in/out */
+	__u64 bytes_used;			/* out */
+	__u64 total_bytes;			/* out */
+	__u64 unused[379];			/* pad to 4k */
+	__u8 path[BTRFS_DEVICE_PATH_NAME_MAX];	/* out */
+};
+
+struct btrfs_ioctl_fs_info_args {
+	__u64 max_id;				/* out */
+	__u64 num_devices;			/* out */
+	__u8 fsid[BTRFS_FSID_SIZE];		/* out */
+	__u64 reserved[124];			/* pad to 1k */
+};
+
 #define BTRFS_INO_LOOKUP_PATH_MAX 4080
 struct btrfs_ioctl_ino_lookup_args {
 	__u64 treeid;
@@ -114,37 +181,6 @@ struct btrfs_ioctl_clone_range_args {
 #define BTRFS_DEFRAG_RANGE_COMPRESS 1
 #define BTRFS_DEFRAG_RANGE_START_IO 2
 
-struct btrfs_ioctl_defrag_range_args {
-	/* start of the defrag operation */
-	__u64 start;
-
-	/* number of bytes to defrag, use (u64)-1 to say all */
-	__u64 len;
-
-	/*
-	 * flags for the operation, which can include turning
-	 * on compression for this one defrag
-	 */
-	__u64 flags;
-
-	/*
-	 * any extent bigger than this will be considered
-	 * already defragged.  Use 0 to take the kernel default
-	 * Use 1 to say every single extent must be rewritten
-	 */
-	__u32 extent_thresh;
-
-	/*
-	 * which compression method to use if turning on compression
-	 * for this defrag operation.  If unspecified, zlib will
-	 * be used
-	 */
-	__u32 compress_type;
-
-	/* spare for later */
-	__u32 unused[4];
-};
-
 struct btrfs_ioctl_space_info {
 	__u64 flags;
 	__u64 total_bytes;
@@ -203,4 +239,13 @@ struct btrfs_ioctl_space_args {
 				   struct btrfs_ioctl_vol_args_v2)
 #define BTRFS_IOC_SUBVOL_GETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 25, __u64)
 #define BTRFS_IOC_SUBVOL_SETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 26, __u64)
+#define BTRFS_IOC_SCRUB _IOWR(BTRFS_IOCTL_MAGIC, 27, \
+			      struct btrfs_ioctl_scrub_args)
+#define BTRFS_IOC_SCRUB_CANCEL _IO(BTRFS_IOCTL_MAGIC, 28)
+#define BTRFS_IOC_SCRUB_PROGRESS _IOWR(BTRFS_IOCTL_MAGIC, 29, \
+				       struct btrfs_ioctl_scrub_args)
+#define BTRFS_IOC_DEV_INFO _IOWR(BTRFS_IOCTL_MAGIC, 30, \
+				 struct btrfs_ioctl_dev_info_args)
+#define BTRFS_IOC_FS_INFO _IOR(BTRFS_IOCTL_MAGIC, 31, \
+			       struct btrfs_ioctl_fs_info_args)
 #endif
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 6151f2ea38bb..66fa43dc3f0f 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -185,31 +185,6 @@ sleep:
 	return 0;
 }
 
-/*
- * Very quick trylock, this does not spin or schedule.  It returns
- * 1 with the spinlock held if it was able to take the lock, or it
- * returns zero if it was unable to take the lock.
- *
- * After this call, scheduling is not safe without first calling
- * btrfs_set_lock_blocking()
- */
-int btrfs_try_tree_lock(struct extent_buffer *eb)
-{
-	if (spin_trylock(&eb->lock)) {
-		if (test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags)) {
-			/*
-			 * we've got the spinlock, but the real owner is
-			 * blocking.  Drop the spinlock and return failure
-			 */
-			spin_unlock(&eb->lock);
-			return 0;
-		}
-		return 1;
-	}
-	/* someone else has the spinlock giveup */
-	return 0;
-}
-
 int btrfs_tree_unlock(struct extent_buffer *eb)
 {
 	/*
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index 6c4ce457168c..5c33a560a2f1 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -21,8 +21,6 @@
 
 int btrfs_tree_lock(struct extent_buffer *eb);
 int btrfs_tree_unlock(struct extent_buffer *eb);
-
-int btrfs_try_tree_lock(struct extent_buffer *eb);
 int btrfs_try_spin_lock(struct extent_buffer *eb);
 
 void btrfs_set_lock_blocking(struct extent_buffer *eb);
diff --git a/fs/btrfs/ref-cache.c b/fs/btrfs/ref-cache.c
index a97314cf6bd6..82d569cb6267 100644
--- a/fs/btrfs/ref-cache.c
+++ b/fs/btrfs/ref-cache.c
@@ -23,56 +23,6 @@
 #include "ref-cache.h"
 #include "transaction.h"
 
-/*
- * leaf refs are used to cache the information about which extents
- * a given leaf has references on.  This allows us to process that leaf
- * in btrfs_drop_snapshot without needing to read it back from disk.
- */
-
-/*
- * kmalloc a leaf reference struct and update the counters for the
- * total ref cache size
- */
-struct btrfs_leaf_ref *btrfs_alloc_leaf_ref(struct btrfs_root *root,
-					    int nr_extents)
-{
-	struct btrfs_leaf_ref *ref;
-	size_t size = btrfs_leaf_ref_size(nr_extents);
-
-	ref = kmalloc(size, GFP_NOFS);
-	if (ref) {
-		spin_lock(&root->fs_info->ref_cache_lock);
-		root->fs_info->total_ref_cache_size += size;
-		spin_unlock(&root->fs_info->ref_cache_lock);
-
-		memset(ref, 0, sizeof(*ref));
-		atomic_set(&ref->usage, 1);
-		INIT_LIST_HEAD(&ref->list);
-	}
-	return ref;
-}
-
-/*
- * free a leaf reference struct and update the counters for the
- * total ref cache size
- */
-void btrfs_free_leaf_ref(struct btrfs_root *root, struct btrfs_leaf_ref *ref)
-{
-	if (!ref)
-		return;
-	WARN_ON(atomic_read(&ref->usage) == 0);
-	if (atomic_dec_and_test(&ref->usage)) {
-		size_t size = btrfs_leaf_ref_size(ref->nritems);
-
-		BUG_ON(ref->in_tree);
-		kfree(ref);
-
-		spin_lock(&root->fs_info->ref_cache_lock);
-		root->fs_info->total_ref_cache_size -= size;
-		spin_unlock(&root->fs_info->ref_cache_lock);
-	}
-}
-
 static struct rb_node *tree_insert(struct rb_root *root, u64 bytenr,
 				   struct rb_node *node)
 {
@@ -116,117 +66,3 @@ static struct rb_node *tree_search(struct rb_root *root, u64 bytenr)
 	}
 	return NULL;
 }
-
-int btrfs_remove_leaf_refs(struct btrfs_root *root, u64 max_root_gen,
-			   int shared)
-{
-	struct btrfs_leaf_ref *ref = NULL;
-	struct btrfs_leaf_ref_tree *tree = root->ref_tree;
-
-	if (shared)
-		tree = &root->fs_info->shared_ref_tree;
-	if (!tree)
-		return 0;
-
-	spin_lock(&tree->lock);
-	while (!list_empty(&tree->list)) {
-		ref = list_entry(tree->list.next, struct btrfs_leaf_ref, list);
-		BUG_ON(ref->tree != tree);
-		if (ref->root_gen > max_root_gen)
-			break;
-		if (!xchg(&ref->in_tree, 0)) {
-			cond_resched_lock(&tree->lock);
-			continue;
-		}
-
-		rb_erase(&ref->rb_node, &tree->root);
-		list_del_init(&ref->list);
-
-		spin_unlock(&tree->lock);
-		btrfs_free_leaf_ref(root, ref);
-		cond_resched();
-		spin_lock(&tree->lock);
-	}
-	spin_unlock(&tree->lock);
-	return 0;
-}
-
-/*
- * find the leaf ref for a given extent.  This returns the ref struct with
- * a usage reference incremented
- */
-struct btrfs_leaf_ref *btrfs_lookup_leaf_ref(struct btrfs_root *root,
-					     u64 bytenr)
-{
-	struct rb_node *rb;
-	struct btrfs_leaf_ref *ref = NULL;
-	struct btrfs_leaf_ref_tree *tree = root->ref_tree;
-again:
-	if (tree) {
-		spin_lock(&tree->lock);
-		rb = tree_search(&tree->root, bytenr);
-		if (rb)
-			ref = rb_entry(rb, struct btrfs_leaf_ref, rb_node);
-		if (ref)
-			atomic_inc(&ref->usage);
-		spin_unlock(&tree->lock);
-		if (ref)
-			return ref;
-	}
-	if (tree != &root->fs_info->shared_ref_tree) {
-		tree = &root->fs_info->shared_ref_tree;
-		goto again;
-	}
-	return NULL;
-}
-
-/*
- * add a fully filled in leaf ref struct
- * remove all the refs older than a given root generation
- */
-int btrfs_add_leaf_ref(struct btrfs_root *root, struct btrfs_leaf_ref *ref,
-		       int shared)
-{
-	int ret = 0;
-	struct rb_node *rb;
-	struct btrfs_leaf_ref_tree *tree = root->ref_tree;
-
-	if (shared)
-		tree = &root->fs_info->shared_ref_tree;
-
-	spin_lock(&tree->lock);
-	rb = tree_insert(&tree->root, ref->bytenr, &ref->rb_node);
-	if (rb) {
-		ret = -EEXIST;
-	} else {
-		atomic_inc(&ref->usage);
-		ref->tree = tree;
-		ref->in_tree = 1;
-		list_add_tail(&ref->list, &tree->list);
-	}
-	spin_unlock(&tree->lock);
-	return ret;
-}
-
-/*
- * remove a single leaf ref from the tree.  This drops the ref held by the tree
- * only
- */
-int btrfs_remove_leaf_ref(struct btrfs_root *root, struct btrfs_leaf_ref *ref)
-{
-	struct btrfs_leaf_ref_tree *tree;
-
-	if (!xchg(&ref->in_tree, 0))
-		return 0;
-
-	tree = ref->tree;
-	spin_lock(&tree->lock);
-
-	rb_erase(&ref->rb_node, &tree->root);
-	list_del_init(&ref->list);
-
-	spin_unlock(&tree->lock);
-
-	btrfs_free_leaf_ref(root, ref);
-	return 0;
-}
diff --git a/fs/btrfs/ref-cache.h b/fs/btrfs/ref-cache.h
index e2a55cb2072b..24f7001f6387 100644
--- a/fs/btrfs/ref-cache.h
+++ b/fs/btrfs/ref-cache.h
@@ -49,28 +49,4 @@ static inline size_t btrfs_leaf_ref_size(int nr_extents)
 	return sizeof(struct btrfs_leaf_ref) +
 	       sizeof(struct btrfs_extent_info) * nr_extents;
 }
-
-static inline void btrfs_leaf_ref_tree_init(struct btrfs_leaf_ref_tree *tree)
-{
-	tree->root = RB_ROOT;
-	INIT_LIST_HEAD(&tree->list);
-	spin_lock_init(&tree->lock);
-}
-
-static inline int btrfs_leaf_ref_tree_empty(struct btrfs_leaf_ref_tree *tree)
-{
-	return RB_EMPTY_ROOT(&tree->root);
-}
-
-void btrfs_leaf_ref_tree_init(struct btrfs_leaf_ref_tree *tree);
-struct btrfs_leaf_ref *btrfs_alloc_leaf_ref(struct btrfs_root *root,
-					    int nr_extents);
-void btrfs_free_leaf_ref(struct btrfs_root *root, struct btrfs_leaf_ref *ref);
-struct btrfs_leaf_ref *btrfs_lookup_leaf_ref(struct btrfs_root *root,
-					     u64 bytenr);
-int btrfs_add_leaf_ref(struct btrfs_root *root, struct btrfs_leaf_ref *ref,
-		       int shared);
-int btrfs_remove_leaf_refs(struct btrfs_root *root, u64 max_root_gen,
-			   int shared);
-int btrfs_remove_leaf_ref(struct btrfs_root *root, struct btrfs_leaf_ref *ref);
 #endif
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index f340f7c99d09..5e0a3dc79a45 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -30,6 +30,7 @@
 #include "btrfs_inode.h"
 #include "async-thread.h"
 #include "free-space-cache.h"
+#include "inode-map.h"
 
 /*
  * backref_node, mapping_node and tree_block start with this
@@ -507,6 +508,7 @@ static int update_backref_cache(struct btrfs_trans_handle *trans,
 	return 1;
 }
 
+
 static int should_ignore_root(struct btrfs_root *root)
 {
 	struct btrfs_root *reloc_root;
@@ -529,7 +531,6 @@ static int should_ignore_root(struct btrfs_root *root)
 	 */
 	return 1;
 }
-
 /*
  * find reloc tree by address of tree root
  */
@@ -676,6 +677,8 @@ struct backref_node *build_backref_tree(struct reloc_control *rc,
 		err = -ENOMEM;
 		goto out;
 	}
+	path1->reada = 1;
+	path2->reada = 2;
 
 	node = alloc_backref_node(cache);
 	if (!node) {
@@ -961,7 +964,7 @@ again:
 			lower = upper;
 			upper = NULL;
 		}
-		btrfs_release_path(root, path2);
+		btrfs_release_path(path2);
 next:
 		if (ptr < end) {
 			ptr += btrfs_extent_inline_ref_size(key.type);
@@ -974,7 +977,7 @@ next:
 		if (ptr >= end)
 			path1->slots[0]++;
 	}
-	btrfs_release_path(rc->extent_root, path1);
+	btrfs_release_path(path1);
 
 	cur->checked = 1;
 	WARN_ON(exist);
@@ -1365,7 +1368,7 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
 	int ret;
 
 	if (!root->reloc_root)
-		return 0;
+		goto out;
 
 	reloc_root = root->reloc_root;
 	root_item = &reloc_root->root_item;
@@ -1387,6 +1390,8 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
 	ret = btrfs_update_root(trans, root->fs_info->tree_root,
 				&reloc_root->root_key, root_item);
 	BUG_ON(ret);
+
+out:
 	return 0;
 }
 
@@ -1409,9 +1414,9 @@ again:
 		prev = node;
 		entry = rb_entry(node, struct btrfs_inode, rb_node);
 
-		if (objectid < entry->vfs_inode.i_ino)
+		if (objectid < btrfs_ino(&entry->vfs_inode))
 			node = node->rb_left;
-		else if (objectid > entry->vfs_inode.i_ino)
+		else if (objectid > btrfs_ino(&entry->vfs_inode))
 			node = node->rb_right;
 		else
 			break;
@@ -1419,7 +1424,7 @@ again:
 	if (!node) {
 		while (prev) {
 			entry = rb_entry(prev, struct btrfs_inode, rb_node);
-			if (objectid <= entry->vfs_inode.i_ino) {
+			if (objectid <= btrfs_ino(&entry->vfs_inode)) {
 				node = prev;
 				break;
 			}
@@ -1434,7 +1439,7 @@ again:
 			return inode;
 		}
 
-		objectid = entry->vfs_inode.i_ino + 1;
+		objectid = btrfs_ino(&entry->vfs_inode) + 1;
 		if (cond_resched_lock(&root->inode_lock))
 			goto again;
 
@@ -1470,7 +1475,7 @@ static int get_new_location(struct inode *reloc_inode, u64 *new_bytenr,
 		return -ENOMEM;
 
 	bytenr -= BTRFS_I(reloc_inode)->index_cnt;
-	ret = btrfs_lookup_file_extent(NULL, root, path, reloc_inode->i_ino,
+	ret = btrfs_lookup_file_extent(NULL, root, path, btrfs_ino(reloc_inode),
 				       bytenr, 0);
 	if (ret < 0)
 		goto out;
@@ -1558,11 +1563,11 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 			if (first) {
 				inode = find_next_inode(root, key.objectid);
 				first = 0;
-			} else if (inode && inode->i_ino < key.objectid) {
+			} else if (inode && btrfs_ino(inode) < key.objectid) {
 				btrfs_add_delayed_iput(inode);
 				inode = find_next_inode(root, key.objectid);
 			}
-			if (inode && inode->i_ino == key.objectid) {
+			if (inode && btrfs_ino(inode) == key.objectid) {
 				end = key.offset +
 				      btrfs_file_extent_num_bytes(leaf, fi);
 				WARN_ON(!IS_ALIGNED(key.offset,
@@ -1749,7 +1754,7 @@ again:
 
 		btrfs_node_key_to_cpu(path->nodes[level], &key,
 				      path->slots[level]);
-		btrfs_release_path(src, path);
+		btrfs_release_path(path);
 
 		path->lowest_level = level;
 		ret = btrfs_search_slot(trans, src, &key, path, 0, 1);
@@ -1893,6 +1898,7 @@ static int invalidate_extent_cache(struct btrfs_root *root,
 	struct inode *inode = NULL;
 	u64 objectid;
 	u64 start, end;
+	u64 ino;
 
 	objectid = min_key->objectid;
 	while (1) {
@@ -1905,17 +1911,18 @@ static int invalidate_extent_cache(struct btrfs_root *root,
 		inode = find_next_inode(root, objectid);
 		if (!inode)
 			break;
+		ino = btrfs_ino(inode);
 
-		if (inode->i_ino > max_key->objectid) {
+		if (ino > max_key->objectid) {
 			iput(inode);
 			break;
 		}
 
-		objectid = inode->i_ino + 1;
+		objectid = ino + 1;
 		if (!S_ISREG(inode->i_mode))
 			continue;
 
-		if (unlikely(min_key->objectid == inode->i_ino)) {
+		if (unlikely(min_key->objectid == ino)) {
 			if (min_key->type > BTRFS_EXTENT_DATA_KEY)
 				continue;
 			if (min_key->type < BTRFS_EXTENT_DATA_KEY)
@@ -1928,7 +1935,7 @@ static int invalidate_extent_cache(struct btrfs_root *root,
 			start = 0;
 		}
 
-		if (unlikely(max_key->objectid == inode->i_ino)) {
+		if (unlikely(max_key->objectid == ino)) {
 			if (max_key->type < BTRFS_EXTENT_DATA_KEY)
 				continue;
 			if (max_key->type > BTRFS_EXTENT_DATA_KEY) {
@@ -1996,6 +2003,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->reada = 1;
 
 	reloc_root = root->reloc_root;
 	root_item = &reloc_root->root_item;
@@ -2136,10 +2144,11 @@ int prepare_to_merge(struct reloc_control *rc, int err)
 	u64 num_bytes = 0;
 	int ret;
 
-	mutex_lock(&root->fs_info->trans_mutex);
+	mutex_lock(&root->fs_info->reloc_mutex);
 	rc->merging_rsv_size += root->nodesize * (BTRFS_MAX_LEVEL - 1) * 2;
 	rc->merging_rsv_size += rc->nodes_relocated * 2;
-	mutex_unlock(&root->fs_info->trans_mutex);
+	mutex_unlock(&root->fs_info->reloc_mutex);
+
 again:
 	if (!err) {
 		num_bytes = rc->merging_rsv_size;
@@ -2149,7 +2158,7 @@ again:
 			err = ret;
 	}
 
-	trans = btrfs_join_transaction(rc->extent_root, 1);
+	trans = btrfs_join_transaction(rc->extent_root);
 	if (IS_ERR(trans)) {
 		if (!err)
 			btrfs_block_rsv_release(rc->extent_root,
@@ -2208,9 +2217,16 @@ int merge_reloc_roots(struct reloc_control *rc)
 	int ret;
 again:
 	root = rc->extent_root;
-	mutex_lock(&root->fs_info->trans_mutex);
+
+	/*
+	 * this serializes us with btrfs_record_root_in_transaction,
+	 * we have to make sure nobody is in the middle of
+	 * adding their roots to the list while we are
+	 * doing this splice
+	 */
+	mutex_lock(&root->fs_info->reloc_mutex);
 	list_splice_init(&rc->reloc_roots, &reloc_roots);
-	mutex_unlock(&root->fs_info->trans_mutex);
+	mutex_unlock(&root->fs_info->reloc_mutex);
 
 	while (!list_empty(&reloc_roots)) {
 		found = 1;
@@ -2496,7 +2512,7 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 			path->locks[upper->level] = 0;
 
 			slot = path->slots[upper->level];
-			btrfs_release_path(NULL, path);
+			btrfs_release_path(path);
 		} else {
 			ret = btrfs_bin_search(upper->eb, key, upper->level,
 					       &slot);
@@ -2737,7 +2753,7 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans,
 		} else {
 			path->lowest_level = node->level;
 			ret = btrfs_search_slot(trans, root, key, path, 0, 1);
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			if (ret > 0)
 				ret = 0;
 		}
@@ -2870,7 +2886,7 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
 	struct extent_map *em;
 	int ret = 0;
 
-	em = alloc_extent_map(GFP_NOFS);
+	em = alloc_extent_map();
 	if (!em)
 		return -ENOMEM;
 
@@ -3119,7 +3135,7 @@ static int add_tree_block(struct reloc_control *rc,
 #endif
 	}
 
-	btrfs_release_path(rc->extent_root, path);
+	btrfs_release_path(path);
 
 	BUG_ON(level == -1);
 
@@ -3220,7 +3236,7 @@ static int delete_block_group_cache(struct btrfs_fs_info *fs_info,
 	key.offset = 0;
 
 	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
-	if (!inode || IS_ERR(inode) || is_bad_inode(inode)) {
+	if (IS_ERR_OR_NULL(inode) || is_bad_inode(inode)) {
 		if (inode && !IS_ERR(inode))
 			iput(inode);
 		return -ENOENT;
@@ -3233,7 +3249,7 @@ truncate:
 		goto out;
 	}
 
-	trans = btrfs_join_transaction(root, 0);
+	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans)) {
 		btrfs_free_path(path);
 		ret = PTR_ERR(trans);
@@ -3297,6 +3313,7 @@ static int find_data_references(struct reloc_control *rc,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->reada = 1;
 
 	root = read_fs_root(rc->extent_root->fs_info, ref_root);
 	if (IS_ERR(root)) {
@@ -3505,7 +3522,7 @@ int add_data_references(struct reloc_control *rc,
 		}
 		path->slots[0]++;
 	}
-	btrfs_release_path(rc->extent_root, path);
+	btrfs_release_path(path);
 	if (err)
 		free_block_list(blocks);
 	return err;
@@ -3568,7 +3585,7 @@ next:
 					    EXTENT_DIRTY);
 
 		if (ret == 0 && start <= key.objectid) {
-			btrfs_release_path(rc->extent_root, path);
+			btrfs_release_path(path);
 			rc->search_start = end + 1;
 		} else {
 			rc->search_start = key.objectid + key.offset;
@@ -3576,24 +3593,26 @@ next:
 			return 0;
 		}
 	}
-	btrfs_release_path(rc->extent_root, path);
+	btrfs_release_path(path);
 	return ret;
 }
 
 static void set_reloc_control(struct reloc_control *rc)
 {
 	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
-	mutex_lock(&fs_info->trans_mutex);
+
+	mutex_lock(&fs_info->reloc_mutex);
 	fs_info->reloc_ctl = rc;
-	mutex_unlock(&fs_info->trans_mutex);
+	mutex_unlock(&fs_info->reloc_mutex);
 }
 
 static void unset_reloc_control(struct reloc_control *rc)
 {
 	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
-	mutex_lock(&fs_info->trans_mutex);
+
+	mutex_lock(&fs_info->reloc_mutex);
 	fs_info->reloc_ctl = NULL;
-	mutex_unlock(&fs_info->trans_mutex);
+	mutex_unlock(&fs_info->reloc_mutex);
 }
 
 static int check_extent_flags(u64 flags)
@@ -3642,7 +3661,7 @@ int prepare_to_relocate(struct reloc_control *rc)
 	rc->create_reloc_tree = 1;
 	set_reloc_control(rc);
 
-	trans = btrfs_join_transaction(rc->extent_root, 1);
+	trans = btrfs_join_transaction(rc->extent_root);
 	BUG_ON(IS_ERR(trans));
 	btrfs_commit_transaction(trans, rc->extent_root);
 	return 0;
@@ -3665,6 +3684,7 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->reada = 1;
 
 	ret = prepare_to_relocate(rc);
 	if (ret) {
@@ -3713,7 +3733,7 @@ restart:
 				flags = BTRFS_EXTENT_FLAG_DATA;
 
 			if (path_change) {
-				btrfs_release_path(rc->extent_root, path);
+				btrfs_release_path(path);
 
 				path->search_commit_root = 1;
 				path->skip_locking = 1;
@@ -3736,7 +3756,7 @@ restart:
 			   (flags & BTRFS_EXTENT_FLAG_DATA)) {
 			ret = add_data_references(rc, &key, path, &blocks);
 		} else {
-			btrfs_release_path(rc->extent_root, path);
+			btrfs_release_path(path);
 			ret = 0;
 		}
 		if (ret < 0) {
@@ -3799,7 +3819,7 @@ restart:
 		}
 	}
 
-	btrfs_release_path(rc->extent_root, path);
+	btrfs_release_path(path);
 	clear_extent_bits(&rc->processed_blocks, 0, (u64)-1, EXTENT_DIRTY,
 			  GFP_NOFS);
 
@@ -3831,7 +3851,7 @@ restart:
 	btrfs_block_rsv_release(rc->extent_root, rc->block_rsv, (u64)-1);
 
 	/* get rid of pinned extents */
-	trans = btrfs_join_transaction(rc->extent_root, 1);
+	trans = btrfs_join_transaction(rc->extent_root);
 	if (IS_ERR(trans))
 		err = PTR_ERR(trans);
 	else
@@ -3867,7 +3887,7 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans,
 	btrfs_set_inode_flags(leaf, item, BTRFS_INODE_NOCOMPRESS |
 					  BTRFS_INODE_PREALLOC);
 	btrfs_mark_buffer_dirty(leaf);
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 out:
 	btrfs_free_path(path);
 	return ret;
@@ -3897,7 +3917,7 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
 	if (IS_ERR(trans))
 		return ERR_CAST(trans);
 
-	err = btrfs_find_free_objectid(trans, root, objectid, &objectid);
+	err = btrfs_find_free_objectid(root, &objectid);
 	if (err)
 		goto out;
 
@@ -3935,7 +3955,7 @@ static struct reloc_control *alloc_reloc_control(void)
 	INIT_LIST_HEAD(&rc->reloc_roots);
 	backref_cache_init(&rc->backref_cache);
 	mapping_tree_init(&rc->reloc_root_tree);
-	extent_io_tree_init(&rc->processed_blocks, NULL, GFP_NOFS);
+	extent_io_tree_init(&rc->processed_blocks, NULL);
 	return rc;
 }
 
@@ -4090,6 +4110,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->reada = -1;
 
 	key.objectid = BTRFS_TREE_RELOC_OBJECTID;
 	key.type = BTRFS_ROOT_ITEM_KEY;
@@ -4109,7 +4130,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 		}
 		leaf = path->nodes[0];
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-		btrfs_release_path(root->fs_info->tree_root, path);
+		btrfs_release_path(path);
 
 		if (key.objectid != BTRFS_TREE_RELOC_OBJECTID ||
 		    key.type != BTRFS_ROOT_ITEM_KEY)
@@ -4141,7 +4162,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 
 		key.offset--;
 	}
-	btrfs_release_path(root->fs_info->tree_root, path);
+	btrfs_release_path(path);
 
 	if (list_empty(&reloc_roots))
 		goto out;
@@ -4156,7 +4177,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 
 	set_reloc_control(rc);
 
-	trans = btrfs_join_transaction(rc->extent_root, 1);
+	trans = btrfs_join_transaction(rc->extent_root);
 	if (IS_ERR(trans)) {
 		unset_reloc_control(rc);
 		err = PTR_ERR(trans);
@@ -4190,7 +4211,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 
 	unset_reloc_control(rc);
 
-	trans = btrfs_join_transaction(rc->extent_root, 1);
+	trans = btrfs_join_transaction(rc->extent_root);
 	if (IS_ERR(trans))
 		err = PTR_ERR(trans);
 	else
@@ -4242,7 +4263,7 @@ int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len)
 
 	disk_bytenr = file_pos + BTRFS_I(inode)->index_cnt;
 	ret = btrfs_lookup_csums_range(root->fs_info->csum_root, disk_bytenr,
-				       disk_bytenr + len - 1, &list);
+				       disk_bytenr + len - 1, &list, 0);
 
 	while (!list_empty(&list)) {
 		sums = list_entry(list.next, struct btrfs_ordered_sum, list);
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 6928bff62daa..ebe45443de06 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -22,53 +22,6 @@
 #include "print-tree.h"
 
 /*
- *  search forward for a root, starting with objectid 'search_start'
- *  if a root key is found, the objectid we find is filled into 'found_objectid'
- *  and 0 is returned.  < 0 is returned on error, 1 if there is nothing
- *  left in the tree.
- */
-int btrfs_search_root(struct btrfs_root *root, u64 search_start,
-		      u64 *found_objectid)
-{
-	struct btrfs_path *path;
-	struct btrfs_key search_key;
-	int ret;
-
-	root = root->fs_info->tree_root;
-	search_key.objectid = search_start;
-	search_key.type = (u8)-1;
-	search_key.offset = (u64)-1;
-
-	path = btrfs_alloc_path();
-	BUG_ON(!path);
-again:
-	ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
-	if (ret < 0)
-		goto out;
-	if (ret == 0) {
-		ret = 1;
-		goto out;
-	}
-	if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
-		ret = btrfs_next_leaf(root, path);
-		if (ret)
-			goto out;
-	}
-	btrfs_item_key_to_cpu(path->nodes[0], &search_key, path->slots[0]);
-	if (search_key.type != BTRFS_ROOT_ITEM_KEY) {
-		search_key.offset++;
-		btrfs_release_path(root, path);
-		goto again;
-	}
-	ret = 0;
-	*found_objectid = search_key.objectid;
-
-out:
-	btrfs_free_path(path);
-	return ret;
-}
-
-/*
  * lookup the root with the highest offset for a given objectid.  The key we do
  * find is copied into 'key'.  If we find something return 0, otherwise 1, < 0
  * on error.
@@ -230,7 +183,7 @@ again:
 
 		memcpy(&found_key, &key, sizeof(key));
 		key.offset++;
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		dead_root =
 			btrfs_read_fs_root_no_radix(root->fs_info->tree_root,
 						    &found_key);
@@ -292,7 +245,7 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
 		}
 
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-		btrfs_release_path(tree_root, path);
+		btrfs_release_path(path);
 
 		if (key.objectid != BTRFS_ORPHAN_OBJECTID ||
 		    key.type != BTRFS_ORPHAN_ITEM_KEY)
@@ -385,18 +338,22 @@ again:
 		*sequence = btrfs_root_ref_sequence(leaf, ref);
 
 		ret = btrfs_del_item(trans, tree_root, path);
-		BUG_ON(ret);
+		if (ret) {
+			err = ret;
+			goto out;
+		}
 	} else
 		err = -ENOENT;
 
 	if (key.type == BTRFS_ROOT_BACKREF_KEY) {
-		btrfs_release_path(tree_root, path);
+		btrfs_release_path(path);
 		key.objectid = ref_id;
 		key.type = BTRFS_ROOT_REF_KEY;
 		key.offset = root_id;
 		goto again;
 	}
 
+out:
 	btrfs_free_path(path);
 	return err;
 }
@@ -463,7 +420,7 @@ again:
 	btrfs_mark_buffer_dirty(leaf);
 
 	if (key.type == BTRFS_ROOT_BACKREF_KEY) {
-		btrfs_release_path(tree_root, path);
+		btrfs_release_path(path);
 		key.objectid = ref_id;
 		key.type = BTRFS_ROOT_REF_KEY;
 		key.offset = root_id;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
new file mode 100644
index 000000000000..a8d03d5efb5d
--- /dev/null
+++ b/fs/btrfs/scrub.c
@@ -0,0 +1,1395 @@
+/*
+ * Copyright (C) 2011 STRATO.  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 v2 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 021110-1307, USA.
+ */
+
+#include <linux/blkdev.h>
+#include "ctree.h"
+#include "volumes.h"
+#include "disk-io.h"
+#include "ordered-data.h"
+
+/*
+ * This is only the first step towards a full-features scrub. It reads all
+ * extent and super block and verifies the checksums. In case a bad checksum
+ * is found or the extent cannot be read, good data will be written back if
+ * any can be found.
+ *
+ * Future enhancements:
+ *  - To enhance the performance, better read-ahead strategies for the
+ *    extent-tree can be employed.
+ *  - In case an unrepairable extent is encountered, track which files are
+ *    affected and report them
+ *  - In case of a read error on files with nodatasum, map the file and read
+ *    the extent to trigger a writeback of the good copy
+ *  - track and record media errors, throw out bad devices
+ *  - add a mode to also read unallocated space
+ *  - make the prefetch cancellable
+ */
+
+struct scrub_bio;
+struct scrub_page;
+struct scrub_dev;
+static void scrub_bio_end_io(struct bio *bio, int err);
+static void scrub_checksum(struct btrfs_work *work);
+static int scrub_checksum_data(struct scrub_dev *sdev,
+			       struct scrub_page *spag, void *buffer);
+static int scrub_checksum_tree_block(struct scrub_dev *sdev,
+				     struct scrub_page *spag, u64 logical,
+				     void *buffer);
+static int scrub_checksum_super(struct scrub_bio *sbio, void *buffer);
+static int scrub_fixup_check(struct scrub_bio *sbio, int ix);
+static void scrub_fixup_end_io(struct bio *bio, int err);
+static int scrub_fixup_io(int rw, struct block_device *bdev, sector_t sector,
+			  struct page *page);
+static void scrub_fixup(struct scrub_bio *sbio, int ix);
+
+#define SCRUB_PAGES_PER_BIO	16	/* 64k per bio */
+#define SCRUB_BIOS_PER_DEV	16	/* 1 MB per device in flight */
+
+struct scrub_page {
+	u64			flags;  /* extent flags */
+	u64			generation;
+	u64			mirror_num;
+	int			have_csum;
+	u8			csum[BTRFS_CSUM_SIZE];
+};
+
+struct scrub_bio {
+	int			index;
+	struct scrub_dev	*sdev;
+	struct bio		*bio;
+	int			err;
+	u64			logical;
+	u64			physical;
+	struct scrub_page	spag[SCRUB_PAGES_PER_BIO];
+	u64			count;
+	int			next_free;
+	struct btrfs_work	work;
+};
+
+struct scrub_dev {
+	struct scrub_bio	*bios[SCRUB_BIOS_PER_DEV];
+	struct btrfs_device	*dev;
+	int			first_free;
+	int			curr;
+	atomic_t		in_flight;
+	spinlock_t		list_lock;
+	wait_queue_head_t	list_wait;
+	u16			csum_size;
+	struct list_head	csum_list;
+	atomic_t		cancel_req;
+	int			readonly;
+	/*
+	 * statistics
+	 */
+	struct btrfs_scrub_progress stat;
+	spinlock_t		stat_lock;
+};
+
+static void scrub_free_csums(struct scrub_dev *sdev)
+{
+	while (!list_empty(&sdev->csum_list)) {
+		struct btrfs_ordered_sum *sum;
+		sum = list_first_entry(&sdev->csum_list,
+				       struct btrfs_ordered_sum, list);
+		list_del(&sum->list);
+		kfree(sum);
+	}
+}
+
+static void scrub_free_bio(struct bio *bio)
+{
+	int i;
+	struct page *last_page = NULL;
+
+	if (!bio)
+		return;
+
+	for (i = 0; i < bio->bi_vcnt; ++i) {
+		if (bio->bi_io_vec[i].bv_page == last_page)
+			continue;
+		last_page = bio->bi_io_vec[i].bv_page;
+		__free_page(last_page);
+	}
+	bio_put(bio);
+}
+
+static noinline_for_stack void scrub_free_dev(struct scrub_dev *sdev)
+{
+	int i;
+
+	if (!sdev)
+		return;
+
+	for (i = 0; i < SCRUB_BIOS_PER_DEV; ++i) {
+		struct scrub_bio *sbio = sdev->bios[i];
+
+		if (!sbio)
+			break;
+
+		scrub_free_bio(sbio->bio);
+		kfree(sbio);
+	}
+
+	scrub_free_csums(sdev);
+	kfree(sdev);
+}
+
+static noinline_for_stack
+struct scrub_dev *scrub_setup_dev(struct btrfs_device *dev)
+{
+	struct scrub_dev *sdev;
+	int		i;
+	struct btrfs_fs_info *fs_info = dev->dev_root->fs_info;
+
+	sdev = kzalloc(sizeof(*sdev), GFP_NOFS);
+	if (!sdev)
+		goto nomem;
+	sdev->dev = dev;
+	for (i = 0; i < SCRUB_BIOS_PER_DEV; ++i) {
+		struct scrub_bio *sbio;
+
+		sbio = kzalloc(sizeof(*sbio), GFP_NOFS);
+		if (!sbio)
+			goto nomem;
+		sdev->bios[i] = sbio;
+
+		sbio->index = i;
+		sbio->sdev = sdev;
+		sbio->count = 0;
+		sbio->work.func = scrub_checksum;
+
+		if (i != SCRUB_BIOS_PER_DEV-1)
+			sdev->bios[i]->next_free = i + 1;
+		 else
+			sdev->bios[i]->next_free = -1;
+	}
+	sdev->first_free = 0;
+	sdev->curr = -1;
+	atomic_set(&sdev->in_flight, 0);
+	atomic_set(&sdev->cancel_req, 0);
+	sdev->csum_size = btrfs_super_csum_size(&fs_info->super_copy);
+	INIT_LIST_HEAD(&sdev->csum_list);
+
+	spin_lock_init(&sdev->list_lock);
+	spin_lock_init(&sdev->stat_lock);
+	init_waitqueue_head(&sdev->list_wait);
+	return sdev;
+
+nomem:
+	scrub_free_dev(sdev);
+	return ERR_PTR(-ENOMEM);
+}
+
+/*
+ * scrub_recheck_error gets called when either verification of the page
+ * failed or the bio failed to read, e.g. with EIO. In the latter case,
+ * recheck_error gets called for every page in the bio, even though only
+ * one may be bad
+ */
+static void scrub_recheck_error(struct scrub_bio *sbio, int ix)
+{
+	if (sbio->err) {
+		if (scrub_fixup_io(READ, sbio->sdev->dev->bdev,
+				   (sbio->physical + ix * PAGE_SIZE) >> 9,
+				   sbio->bio->bi_io_vec[ix].bv_page) == 0) {
+			if (scrub_fixup_check(sbio, ix) == 0)
+				return;
+		}
+	}
+
+	scrub_fixup(sbio, ix);
+}
+
+static int scrub_fixup_check(struct scrub_bio *sbio, int ix)
+{
+	int ret = 1;
+	struct page *page;
+	void *buffer;
+	u64 flags = sbio->spag[ix].flags;
+
+	page = sbio->bio->bi_io_vec[ix].bv_page;
+	buffer = kmap_atomic(page, KM_USER0);
+	if (flags & BTRFS_EXTENT_FLAG_DATA) {
+		ret = scrub_checksum_data(sbio->sdev,
+					  sbio->spag + ix, buffer);
+	} else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+		ret = scrub_checksum_tree_block(sbio->sdev,
+						sbio->spag + ix,
+						sbio->logical + ix * PAGE_SIZE,
+						buffer);
+	} else {
+		WARN_ON(1);
+	}
+	kunmap_atomic(buffer, KM_USER0);
+
+	return ret;
+}
+
+static void scrub_fixup_end_io(struct bio *bio, int err)
+{
+	complete((struct completion *)bio->bi_private);
+}
+
+static void scrub_fixup(struct scrub_bio *sbio, int ix)
+{
+	struct scrub_dev *sdev = sbio->sdev;
+	struct btrfs_fs_info *fs_info = sdev->dev->dev_root->fs_info;
+	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
+	struct btrfs_multi_bio *multi = NULL;
+	u64 logical = sbio->logical + ix * PAGE_SIZE;
+	u64 length;
+	int i;
+	int ret;
+	DECLARE_COMPLETION_ONSTACK(complete);
+
+	if ((sbio->spag[ix].flags & BTRFS_EXTENT_FLAG_DATA) &&
+	    (sbio->spag[ix].have_csum == 0)) {
+		/*
+		 * nodatasum, don't try to fix anything
+		 * FIXME: we can do better, open the inode and trigger a
+		 * writeback
+		 */
+		goto uncorrectable;
+	}
+
+	length = PAGE_SIZE;
+	ret = btrfs_map_block(map_tree, REQ_WRITE, logical, &length,
+			      &multi, 0);
+	if (ret || !multi || length < PAGE_SIZE) {
+		printk(KERN_ERR
+		       "scrub_fixup: btrfs_map_block failed us for %llu\n",
+		       (unsigned long long)logical);
+		WARN_ON(1);
+		return;
+	}
+
+	if (multi->num_stripes == 1)
+		/* there aren't any replicas */
+		goto uncorrectable;
+
+	/*
+	 * first find a good copy
+	 */
+	for (i = 0; i < multi->num_stripes; ++i) {
+		if (i == sbio->spag[ix].mirror_num)
+			continue;
+
+		if (scrub_fixup_io(READ, multi->stripes[i].dev->bdev,
+				   multi->stripes[i].physical >> 9,
+				   sbio->bio->bi_io_vec[ix].bv_page)) {
+			/* I/O-error, this is not a good copy */
+			continue;
+		}
+
+		if (scrub_fixup_check(sbio, ix) == 0)
+			break;
+	}
+	if (i == multi->num_stripes)
+		goto uncorrectable;
+
+	if (!sdev->readonly) {
+		/*
+		 * bi_io_vec[ix].bv_page now contains good data, write it back
+		 */
+		if (scrub_fixup_io(WRITE, sdev->dev->bdev,
+				   (sbio->physical + ix * PAGE_SIZE) >> 9,
+				   sbio->bio->bi_io_vec[ix].bv_page)) {
+			/* I/O-error, writeback failed, give up */
+			goto uncorrectable;
+		}
+	}
+
+	kfree(multi);
+	spin_lock(&sdev->stat_lock);
+	++sdev->stat.corrected_errors;
+	spin_unlock(&sdev->stat_lock);
+
+	if (printk_ratelimit())
+		printk(KERN_ERR "btrfs: fixed up at %llu\n",
+		       (unsigned long long)logical);
+	return;
+
+uncorrectable:
+	kfree(multi);
+	spin_lock(&sdev->stat_lock);
+	++sdev->stat.uncorrectable_errors;
+	spin_unlock(&sdev->stat_lock);
+
+	if (printk_ratelimit())
+		printk(KERN_ERR "btrfs: unable to fixup at %llu\n",
+			 (unsigned long long)logical);
+}
+
+static int scrub_fixup_io(int rw, struct block_device *bdev, sector_t sector,
+			 struct page *page)
+{
+	struct bio *bio = NULL;
+	int ret;
+	DECLARE_COMPLETION_ONSTACK(complete);
+
+	bio = bio_alloc(GFP_NOFS, 1);
+	bio->bi_bdev = bdev;
+	bio->bi_sector = sector;
+	bio_add_page(bio, page, PAGE_SIZE, 0);
+	bio->bi_end_io = scrub_fixup_end_io;
+	bio->bi_private = &complete;
+	submit_bio(rw, bio);
+
+	/* this will also unplug the queue */
+	wait_for_completion(&complete);
+
+	ret = !test_bit(BIO_UPTODATE, &bio->bi_flags);
+	bio_put(bio);
+	return ret;
+}
+
+static void scrub_bio_end_io(struct bio *bio, int err)
+{
+	struct scrub_bio *sbio = bio->bi_private;
+	struct scrub_dev *sdev = sbio->sdev;
+	struct btrfs_fs_info *fs_info = sdev->dev->dev_root->fs_info;
+
+	sbio->err = err;
+	sbio->bio = bio;
+
+	btrfs_queue_worker(&fs_info->scrub_workers, &sbio->work);
+}
+
+static void scrub_checksum(struct btrfs_work *work)
+{
+	struct scrub_bio *sbio = container_of(work, struct scrub_bio, work);
+	struct scrub_dev *sdev = sbio->sdev;
+	struct page *page;
+	void *buffer;
+	int i;
+	u64 flags;
+	u64 logical;
+	int ret;
+
+	if (sbio->err) {
+		for (i = 0; i < sbio->count; ++i)
+			scrub_recheck_error(sbio, i);
+
+		sbio->bio->bi_flags &= ~(BIO_POOL_MASK - 1);
+		sbio->bio->bi_flags |= 1 << BIO_UPTODATE;
+		sbio->bio->bi_phys_segments = 0;
+		sbio->bio->bi_idx = 0;
+
+		for (i = 0; i < sbio->count; i++) {
+			struct bio_vec *bi;
+			bi = &sbio->bio->bi_io_vec[i];
+			bi->bv_offset = 0;
+			bi->bv_len = PAGE_SIZE;
+		}
+
+		spin_lock(&sdev->stat_lock);
+		++sdev->stat.read_errors;
+		spin_unlock(&sdev->stat_lock);
+		goto out;
+	}
+	for (i = 0; i < sbio->count; ++i) {
+		page = sbio->bio->bi_io_vec[i].bv_page;
+		buffer = kmap_atomic(page, KM_USER0);
+		flags = sbio->spag[i].flags;
+		logical = sbio->logical + i * PAGE_SIZE;
+		ret = 0;
+		if (flags & BTRFS_EXTENT_FLAG_DATA) {
+			ret = scrub_checksum_data(sdev, sbio->spag + i, buffer);
+		} else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+			ret = scrub_checksum_tree_block(sdev, sbio->spag + i,
+							logical, buffer);
+		} else if (flags & BTRFS_EXTENT_FLAG_SUPER) {
+			BUG_ON(i);
+			(void)scrub_checksum_super(sbio, buffer);
+		} else {
+			WARN_ON(1);
+		}
+		kunmap_atomic(buffer, KM_USER0);
+		if (ret)
+			scrub_recheck_error(sbio, i);
+	}
+
+out:
+	scrub_free_bio(sbio->bio);
+	sbio->bio = NULL;
+	spin_lock(&sdev->list_lock);
+	sbio->next_free = sdev->first_free;
+	sdev->first_free = sbio->index;
+	spin_unlock(&sdev->list_lock);
+	atomic_dec(&sdev->in_flight);
+	wake_up(&sdev->list_wait);
+}
+
+static int scrub_checksum_data(struct scrub_dev *sdev,
+			       struct scrub_page *spag, void *buffer)
+{
+	u8 csum[BTRFS_CSUM_SIZE];
+	u32 crc = ~(u32)0;
+	int fail = 0;
+	struct btrfs_root *root = sdev->dev->dev_root;
+
+	if (!spag->have_csum)
+		return 0;
+
+	crc = btrfs_csum_data(root, buffer, crc, PAGE_SIZE);
+	btrfs_csum_final(crc, csum);
+	if (memcmp(csum, spag->csum, sdev->csum_size))
+		fail = 1;
+
+	spin_lock(&sdev->stat_lock);
+	++sdev->stat.data_extents_scrubbed;
+	sdev->stat.data_bytes_scrubbed += PAGE_SIZE;
+	if (fail)
+		++sdev->stat.csum_errors;
+	spin_unlock(&sdev->stat_lock);
+
+	return fail;
+}
+
+static int scrub_checksum_tree_block(struct scrub_dev *sdev,
+				     struct scrub_page *spag, u64 logical,
+				     void *buffer)
+{
+	struct btrfs_header *h;
+	struct btrfs_root *root = sdev->dev->dev_root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	u8 csum[BTRFS_CSUM_SIZE];
+	u32 crc = ~(u32)0;
+	int fail = 0;
+	int crc_fail = 0;
+
+	/*
+	 * we don't use the getter functions here, as we
+	 * a) don't have an extent buffer and
+	 * b) the page is already kmapped
+	 */
+	h = (struct btrfs_header *)buffer;
+
+	if (logical != le64_to_cpu(h->bytenr))
+		++fail;
+
+	if (spag->generation != le64_to_cpu(h->generation))
+		++fail;
+
+	if (memcmp(h->fsid, fs_info->fsid, BTRFS_UUID_SIZE))
+		++fail;
+
+	if (memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid,
+		   BTRFS_UUID_SIZE))
+		++fail;
+
+	crc = btrfs_csum_data(root, buffer + BTRFS_CSUM_SIZE, crc,
+			      PAGE_SIZE - BTRFS_CSUM_SIZE);
+	btrfs_csum_final(crc, csum);
+	if (memcmp(csum, h->csum, sdev->csum_size))
+		++crc_fail;
+
+	spin_lock(&sdev->stat_lock);
+	++sdev->stat.tree_extents_scrubbed;
+	sdev->stat.tree_bytes_scrubbed += PAGE_SIZE;
+	if (crc_fail)
+		++sdev->stat.csum_errors;
+	if (fail)
+		++sdev->stat.verify_errors;
+	spin_unlock(&sdev->stat_lock);
+
+	return fail || crc_fail;
+}
+
+static int scrub_checksum_super(struct scrub_bio *sbio, void *buffer)
+{
+	struct btrfs_super_block *s;
+	u64 logical;
+	struct scrub_dev *sdev = sbio->sdev;
+	struct btrfs_root *root = sdev->dev->dev_root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	u8 csum[BTRFS_CSUM_SIZE];
+	u32 crc = ~(u32)0;
+	int fail = 0;
+
+	s = (struct btrfs_super_block *)buffer;
+	logical = sbio->logical;
+
+	if (logical != le64_to_cpu(s->bytenr))
+		++fail;
+
+	if (sbio->spag[0].generation != le64_to_cpu(s->generation))
+		++fail;
+
+	if (memcmp(s->fsid, fs_info->fsid, BTRFS_UUID_SIZE))
+		++fail;
+
+	crc = btrfs_csum_data(root, buffer + BTRFS_CSUM_SIZE, crc,
+			      PAGE_SIZE - BTRFS_CSUM_SIZE);
+	btrfs_csum_final(crc, csum);
+	if (memcmp(csum, s->csum, sbio->sdev->csum_size))
+		++fail;
+
+	if (fail) {
+		/*
+		 * if we find an error in a super block, we just report it.
+		 * They will get written with the next transaction commit
+		 * anyway
+		 */
+		spin_lock(&sdev->stat_lock);
+		++sdev->stat.super_errors;
+		spin_unlock(&sdev->stat_lock);
+	}
+
+	return fail;
+}
+
+static int scrub_submit(struct scrub_dev *sdev)
+{
+	struct scrub_bio *sbio;
+	struct bio *bio;
+	int i;
+
+	if (sdev->curr == -1)
+		return 0;
+
+	sbio = sdev->bios[sdev->curr];
+
+	bio = bio_alloc(GFP_NOFS, sbio->count);
+	if (!bio)
+		goto nomem;
+
+	bio->bi_private = sbio;
+	bio->bi_end_io = scrub_bio_end_io;
+	bio->bi_bdev = sdev->dev->bdev;
+	bio->bi_sector = sbio->physical >> 9;
+
+	for (i = 0; i < sbio->count; ++i) {
+		struct page *page;
+		int ret;
+
+		page = alloc_page(GFP_NOFS);
+		if (!page)
+			goto nomem;
+
+		ret = bio_add_page(bio, page, PAGE_SIZE, 0);
+		if (!ret) {
+			__free_page(page);
+			goto nomem;
+		}
+	}
+
+	sbio->err = 0;
+	sdev->curr = -1;
+	atomic_inc(&sdev->in_flight);
+
+	submit_bio(READ, bio);
+
+	return 0;
+
+nomem:
+	scrub_free_bio(bio);
+
+	return -ENOMEM;
+}
+
+static int scrub_page(struct scrub_dev *sdev, u64 logical, u64 len,
+		      u64 physical, u64 flags, u64 gen, u64 mirror_num,
+		      u8 *csum, int force)
+{
+	struct scrub_bio *sbio;
+
+again:
+	/*
+	 * grab a fresh bio or wait for one to become available
+	 */
+	while (sdev->curr == -1) {
+		spin_lock(&sdev->list_lock);
+		sdev->curr = sdev->first_free;
+		if (sdev->curr != -1) {
+			sdev->first_free = sdev->bios[sdev->curr]->next_free;
+			sdev->bios[sdev->curr]->next_free = -1;
+			sdev->bios[sdev->curr]->count = 0;
+			spin_unlock(&sdev->list_lock);
+		} else {
+			spin_unlock(&sdev->list_lock);
+			wait_event(sdev->list_wait, sdev->first_free != -1);
+		}
+	}
+	sbio = sdev->bios[sdev->curr];
+	if (sbio->count == 0) {
+		sbio->physical = physical;
+		sbio->logical = logical;
+	} else if (sbio->physical + sbio->count * PAGE_SIZE != physical ||
+		   sbio->logical + sbio->count * PAGE_SIZE != logical) {
+		int ret;
+
+		ret = scrub_submit(sdev);
+		if (ret)
+			return ret;
+		goto again;
+	}
+	sbio->spag[sbio->count].flags = flags;
+	sbio->spag[sbio->count].generation = gen;
+	sbio->spag[sbio->count].have_csum = 0;
+	sbio->spag[sbio->count].mirror_num = mirror_num;
+	if (csum) {
+		sbio->spag[sbio->count].have_csum = 1;
+		memcpy(sbio->spag[sbio->count].csum, csum, sdev->csum_size);
+	}
+	++sbio->count;
+	if (sbio->count == SCRUB_PAGES_PER_BIO || force) {
+		int ret;
+
+		ret = scrub_submit(sdev);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int scrub_find_csum(struct scrub_dev *sdev, u64 logical, u64 len,
+			   u8 *csum)
+{
+	struct btrfs_ordered_sum *sum = NULL;
+	int ret = 0;
+	unsigned long i;
+	unsigned long num_sectors;
+	u32 sectorsize = sdev->dev->dev_root->sectorsize;
+
+	while (!list_empty(&sdev->csum_list)) {
+		sum = list_first_entry(&sdev->csum_list,
+				       struct btrfs_ordered_sum, list);
+		if (sum->bytenr > logical)
+			return 0;
+		if (sum->bytenr + sum->len > logical)
+			break;
+
+		++sdev->stat.csum_discards;
+		list_del(&sum->list);
+		kfree(sum);
+		sum = NULL;
+	}
+	if (!sum)
+		return 0;
+
+	num_sectors = sum->len / sectorsize;
+	for (i = 0; i < num_sectors; ++i) {
+		if (sum->sums[i].bytenr == logical) {
+			memcpy(csum, &sum->sums[i].sum, sdev->csum_size);
+			ret = 1;
+			break;
+		}
+	}
+	if (ret && i == num_sectors - 1) {
+		list_del(&sum->list);
+		kfree(sum);
+	}
+	return ret;
+}
+
+/* scrub extent tries to collect up to 64 kB for each bio */
+static int scrub_extent(struct scrub_dev *sdev, u64 logical, u64 len,
+			u64 physical, u64 flags, u64 gen, u64 mirror_num)
+{
+	int ret;
+	u8 csum[BTRFS_CSUM_SIZE];
+
+	while (len) {
+		u64 l = min_t(u64, len, PAGE_SIZE);
+		int have_csum = 0;
+
+		if (flags & BTRFS_EXTENT_FLAG_DATA) {
+			/* push csums to sbio */
+			have_csum = scrub_find_csum(sdev, logical, l, csum);
+			if (have_csum == 0)
+				++sdev->stat.no_csum;
+		}
+		ret = scrub_page(sdev, logical, l, physical, flags, gen,
+				 mirror_num, have_csum ? csum : NULL, 0);
+		if (ret)
+			return ret;
+		len -= l;
+		logical += l;
+		physical += l;
+	}
+	return 0;
+}
+
+static noinline_for_stack int scrub_stripe(struct scrub_dev *sdev,
+	struct map_lookup *map, int num, u64 base, u64 length)
+{
+	struct btrfs_path *path;
+	struct btrfs_fs_info *fs_info = sdev->dev->dev_root->fs_info;
+	struct btrfs_root *root = fs_info->extent_root;
+	struct btrfs_root *csum_root = fs_info->csum_root;
+	struct btrfs_extent_item *extent;
+	struct blk_plug plug;
+	u64 flags;
+	int ret;
+	int slot;
+	int i;
+	u64 nstripes;
+	int start_stripe;
+	struct extent_buffer *l;
+	struct btrfs_key key;
+	u64 physical;
+	u64 logical;
+	u64 generation;
+	u64 mirror_num;
+
+	u64 increment = map->stripe_len;
+	u64 offset;
+
+	nstripes = length;
+	offset = 0;
+	do_div(nstripes, map->stripe_len);
+	if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
+		offset = map->stripe_len * num;
+		increment = map->stripe_len * map->num_stripes;
+		mirror_num = 0;
+	} else if (map->type & BTRFS_BLOCK_GROUP_RAID10) {
+		int factor = map->num_stripes / map->sub_stripes;
+		offset = map->stripe_len * (num / map->sub_stripes);
+		increment = map->stripe_len * factor;
+		mirror_num = num % map->sub_stripes;
+	} else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
+		increment = map->stripe_len;
+		mirror_num = num % map->num_stripes;
+	} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
+		increment = map->stripe_len;
+		mirror_num = num % map->num_stripes;
+	} else {
+		increment = map->stripe_len;
+		mirror_num = 0;
+	}
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	path->reada = 2;
+	path->search_commit_root = 1;
+	path->skip_locking = 1;
+
+	/*
+	 * find all extents for each stripe and just read them to get
+	 * them into the page cache
+	 * FIXME: we can do better. build a more intelligent prefetching
+	 */
+	logical = base + offset;
+	physical = map->stripes[num].physical;
+	ret = 0;
+	for (i = 0; i < nstripes; ++i) {
+		key.objectid = logical;
+		key.type = BTRFS_EXTENT_ITEM_KEY;
+		key.offset = (u64)0;
+
+		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+		if (ret < 0)
+			goto out_noplug;
+
+		/*
+		 * we might miss half an extent here, but that doesn't matter,
+		 * as it's only the prefetch
+		 */
+		while (1) {
+			l = path->nodes[0];
+			slot = path->slots[0];
+			if (slot >= btrfs_header_nritems(l)) {
+				ret = btrfs_next_leaf(root, path);
+				if (ret == 0)
+					continue;
+				if (ret < 0)
+					goto out_noplug;
+
+				break;
+			}
+			btrfs_item_key_to_cpu(l, &key, slot);
+
+			if (key.objectid >= logical + map->stripe_len)
+				break;
+
+			path->slots[0]++;
+		}
+		btrfs_release_path(path);
+		logical += increment;
+		physical += map->stripe_len;
+		cond_resched();
+	}
+
+	/*
+	 * collect all data csums for the stripe to avoid seeking during
+	 * the scrub. This might currently (crc32) end up to be about 1MB
+	 */
+	start_stripe = 0;
+	blk_start_plug(&plug);
+again:
+	logical = base + offset + start_stripe * increment;
+	for (i = start_stripe; i < nstripes; ++i) {
+		ret = btrfs_lookup_csums_range(csum_root, logical,
+					       logical + map->stripe_len - 1,
+					       &sdev->csum_list, 1);
+		if (ret)
+			goto out;
+
+		logical += increment;
+		cond_resched();
+	}
+	/*
+	 * now find all extents for each stripe and scrub them
+	 */
+	logical = base + offset + start_stripe * increment;
+	physical = map->stripes[num].physical + start_stripe * map->stripe_len;
+	ret = 0;
+	for (i = start_stripe; i < nstripes; ++i) {
+		/*
+		 * canceled?
+		 */
+		if (atomic_read(&fs_info->scrub_cancel_req) ||
+		    atomic_read(&sdev->cancel_req)) {
+			ret = -ECANCELED;
+			goto out;
+		}
+		/*
+		 * check to see if we have to pause
+		 */
+		if (atomic_read(&fs_info->scrub_pause_req)) {
+			/* push queued extents */
+			scrub_submit(sdev);
+			wait_event(sdev->list_wait,
+				   atomic_read(&sdev->in_flight) == 0);
+			atomic_inc(&fs_info->scrubs_paused);
+			wake_up(&fs_info->scrub_pause_wait);
+			mutex_lock(&fs_info->scrub_lock);
+			while (atomic_read(&fs_info->scrub_pause_req)) {
+				mutex_unlock(&fs_info->scrub_lock);
+				wait_event(fs_info->scrub_pause_wait,
+				   atomic_read(&fs_info->scrub_pause_req) == 0);
+				mutex_lock(&fs_info->scrub_lock);
+			}
+			atomic_dec(&fs_info->scrubs_paused);
+			mutex_unlock(&fs_info->scrub_lock);
+			wake_up(&fs_info->scrub_pause_wait);
+			scrub_free_csums(sdev);
+			start_stripe = i;
+			goto again;
+		}
+
+		key.objectid = logical;
+		key.type = BTRFS_EXTENT_ITEM_KEY;
+		key.offset = (u64)0;
+
+		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+		if (ret < 0)
+			goto out;
+		if (ret > 0) {
+			ret = btrfs_previous_item(root, path, 0,
+						  BTRFS_EXTENT_ITEM_KEY);
+			if (ret < 0)
+				goto out;
+			if (ret > 0) {
+				/* there's no smaller item, so stick with the
+				 * larger one */
+				btrfs_release_path(path);
+				ret = btrfs_search_slot(NULL, root, &key,
+							path, 0, 0);
+				if (ret < 0)
+					goto out;
+			}
+		}
+
+		while (1) {
+			l = path->nodes[0];
+			slot = path->slots[0];
+			if (slot >= btrfs_header_nritems(l)) {
+				ret = btrfs_next_leaf(root, path);
+				if (ret == 0)
+					continue;
+				if (ret < 0)
+					goto out;
+
+				break;
+			}
+			btrfs_item_key_to_cpu(l, &key, slot);
+
+			if (key.objectid + key.offset <= logical)
+				goto next;
+
+			if (key.objectid >= logical + map->stripe_len)
+				break;
+
+			if (btrfs_key_type(&key) != BTRFS_EXTENT_ITEM_KEY)
+				goto next;
+
+			extent = btrfs_item_ptr(l, slot,
+						struct btrfs_extent_item);
+			flags = btrfs_extent_flags(l, extent);
+			generation = btrfs_extent_generation(l, extent);
+
+			if (key.objectid < logical &&
+			    (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)) {
+				printk(KERN_ERR
+				       "btrfs scrub: tree block %llu spanning "
+				       "stripes, ignored. logical=%llu\n",
+				       (unsigned long long)key.objectid,
+				       (unsigned long long)logical);
+				goto next;
+			}
+
+			/*
+			 * trim extent to this stripe
+			 */
+			if (key.objectid < logical) {
+				key.offset -= logical - key.objectid;
+				key.objectid = logical;
+			}
+			if (key.objectid + key.offset >
+			    logical + map->stripe_len) {
+				key.offset = logical + map->stripe_len -
+					     key.objectid;
+			}
+
+			ret = scrub_extent(sdev, key.objectid, key.offset,
+					   key.objectid - logical + physical,
+					   flags, generation, mirror_num);
+			if (ret)
+				goto out;
+
+next:
+			path->slots[0]++;
+		}
+		btrfs_release_path(path);
+		logical += increment;
+		physical += map->stripe_len;
+		spin_lock(&sdev->stat_lock);
+		sdev->stat.last_physical = physical;
+		spin_unlock(&sdev->stat_lock);
+	}
+	/* push queued extents */
+	scrub_submit(sdev);
+
+out:
+	blk_finish_plug(&plug);
+out_noplug:
+	btrfs_free_path(path);
+	return ret < 0 ? ret : 0;
+}
+
+static noinline_for_stack int scrub_chunk(struct scrub_dev *sdev,
+	u64 chunk_tree, u64 chunk_objectid, u64 chunk_offset, u64 length)
+{
+	struct btrfs_mapping_tree *map_tree =
+		&sdev->dev->dev_root->fs_info->mapping_tree;
+	struct map_lookup *map;
+	struct extent_map *em;
+	int i;
+	int ret = -EINVAL;
+
+	read_lock(&map_tree->map_tree.lock);
+	em = lookup_extent_mapping(&map_tree->map_tree, chunk_offset, 1);
+	read_unlock(&map_tree->map_tree.lock);
+
+	if (!em)
+		return -EINVAL;
+
+	map = (struct map_lookup *)em->bdev;
+	if (em->start != chunk_offset)
+		goto out;
+
+	if (em->len < length)
+		goto out;
+
+	for (i = 0; i < map->num_stripes; ++i) {
+		if (map->stripes[i].dev == sdev->dev) {
+			ret = scrub_stripe(sdev, map, i, chunk_offset, length);
+			if (ret)
+				goto out;
+		}
+	}
+out:
+	free_extent_map(em);
+
+	return ret;
+}
+
+static noinline_for_stack
+int scrub_enumerate_chunks(struct scrub_dev *sdev, u64 start, u64 end)
+{
+	struct btrfs_dev_extent *dev_extent = NULL;
+	struct btrfs_path *path;
+	struct btrfs_root *root = sdev->dev->dev_root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	u64 length;
+	u64 chunk_tree;
+	u64 chunk_objectid;
+	u64 chunk_offset;
+	int ret;
+	int slot;
+	struct extent_buffer *l;
+	struct btrfs_key key;
+	struct btrfs_key found_key;
+	struct btrfs_block_group_cache *cache;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	path->reada = 2;
+	path->search_commit_root = 1;
+	path->skip_locking = 1;
+
+	key.objectid = sdev->dev->devid;
+	key.offset = 0ull;
+	key.type = BTRFS_DEV_EXTENT_KEY;
+
+
+	while (1) {
+		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+		if (ret < 0)
+			break;
+		if (ret > 0) {
+			if (path->slots[0] >=
+			    btrfs_header_nritems(path->nodes[0])) {
+				ret = btrfs_next_leaf(root, path);
+				if (ret)
+					break;
+			}
+		}
+
+		l = path->nodes[0];
+		slot = path->slots[0];
+
+		btrfs_item_key_to_cpu(l, &found_key, slot);
+
+		if (found_key.objectid != sdev->dev->devid)
+			break;
+
+		if (btrfs_key_type(&found_key) != BTRFS_DEV_EXTENT_KEY)
+			break;
+
+		if (found_key.offset >= end)
+			break;
+
+		if (found_key.offset < key.offset)
+			break;
+
+		dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
+		length = btrfs_dev_extent_length(l, dev_extent);
+
+		if (found_key.offset + length <= start) {
+			key.offset = found_key.offset + length;
+			btrfs_release_path(path);
+			continue;
+		}
+
+		chunk_tree = btrfs_dev_extent_chunk_tree(l, dev_extent);
+		chunk_objectid = btrfs_dev_extent_chunk_objectid(l, dev_extent);
+		chunk_offset = btrfs_dev_extent_chunk_offset(l, dev_extent);
+
+		/*
+		 * get a reference on the corresponding block group to prevent
+		 * the chunk from going away while we scrub it
+		 */
+		cache = btrfs_lookup_block_group(fs_info, chunk_offset);
+		if (!cache) {
+			ret = -ENOENT;
+			break;
+		}
+		ret = scrub_chunk(sdev, chunk_tree, chunk_objectid,
+				  chunk_offset, length);
+		btrfs_put_block_group(cache);
+		if (ret)
+			break;
+
+		key.offset = found_key.offset + length;
+		btrfs_release_path(path);
+	}
+
+	btrfs_free_path(path);
+
+	/*
+	 * ret can still be 1 from search_slot or next_leaf,
+	 * that's not an error
+	 */
+	return ret < 0 ? ret : 0;
+}
+
+static noinline_for_stack int scrub_supers(struct scrub_dev *sdev)
+{
+	int	i;
+	u64	bytenr;
+	u64	gen;
+	int	ret;
+	struct btrfs_device *device = sdev->dev;
+	struct btrfs_root *root = device->dev_root;
+
+	gen = root->fs_info->last_trans_committed;
+
+	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
+		bytenr = btrfs_sb_offset(i);
+		if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->total_bytes)
+			break;
+
+		ret = scrub_page(sdev, bytenr, PAGE_SIZE, bytenr,
+				 BTRFS_EXTENT_FLAG_SUPER, gen, i, NULL, 1);
+		if (ret)
+			return ret;
+	}
+	wait_event(sdev->list_wait, atomic_read(&sdev->in_flight) == 0);
+
+	return 0;
+}
+
+/*
+ * get a reference count on fs_info->scrub_workers. start worker if necessary
+ */
+static noinline_for_stack int scrub_workers_get(struct btrfs_root *root)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+
+	mutex_lock(&fs_info->scrub_lock);
+	if (fs_info->scrub_workers_refcnt == 0) {
+		btrfs_init_workers(&fs_info->scrub_workers, "scrub",
+			   fs_info->thread_pool_size, &fs_info->generic_worker);
+		fs_info->scrub_workers.idle_thresh = 4;
+		btrfs_start_workers(&fs_info->scrub_workers, 1);
+	}
+	++fs_info->scrub_workers_refcnt;
+	mutex_unlock(&fs_info->scrub_lock);
+
+	return 0;
+}
+
+static noinline_for_stack void scrub_workers_put(struct btrfs_root *root)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+
+	mutex_lock(&fs_info->scrub_lock);
+	if (--fs_info->scrub_workers_refcnt == 0)
+		btrfs_stop_workers(&fs_info->scrub_workers);
+	WARN_ON(fs_info->scrub_workers_refcnt < 0);
+	mutex_unlock(&fs_info->scrub_lock);
+}
+
+
+int btrfs_scrub_dev(struct btrfs_root *root, u64 devid, u64 start, u64 end,
+		    struct btrfs_scrub_progress *progress, int readonly)
+{
+	struct scrub_dev *sdev;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	int ret;
+	struct btrfs_device *dev;
+
+	if (btrfs_fs_closing(root->fs_info))
+		return -EINVAL;
+
+	/*
+	 * check some assumptions
+	 */
+	if (root->sectorsize != PAGE_SIZE ||
+	    root->sectorsize != root->leafsize ||
+	    root->sectorsize != root->nodesize) {
+		printk(KERN_ERR "btrfs_scrub: size assumptions fail\n");
+		return -EINVAL;
+	}
+
+	ret = scrub_workers_get(root);
+	if (ret)
+		return ret;
+
+	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
+	dev = btrfs_find_device(root, devid, NULL, NULL);
+	if (!dev || dev->missing) {
+		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+		scrub_workers_put(root);
+		return -ENODEV;
+	}
+	mutex_lock(&fs_info->scrub_lock);
+
+	if (!dev->in_fs_metadata) {
+		mutex_unlock(&fs_info->scrub_lock);
+		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+		scrub_workers_put(root);
+		return -ENODEV;
+	}
+
+	if (dev->scrub_device) {
+		mutex_unlock(&fs_info->scrub_lock);
+		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+		scrub_workers_put(root);
+		return -EINPROGRESS;
+	}
+	sdev = scrub_setup_dev(dev);
+	if (IS_ERR(sdev)) {
+		mutex_unlock(&fs_info->scrub_lock);
+		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+		scrub_workers_put(root);
+		return PTR_ERR(sdev);
+	}
+	sdev->readonly = readonly;
+	dev->scrub_device = sdev;
+
+	atomic_inc(&fs_info->scrubs_running);
+	mutex_unlock(&fs_info->scrub_lock);
+	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+
+	down_read(&fs_info->scrub_super_lock);
+	ret = scrub_supers(sdev);
+	up_read(&fs_info->scrub_super_lock);
+
+	if (!ret)
+		ret = scrub_enumerate_chunks(sdev, start, end);
+
+	wait_event(sdev->list_wait, atomic_read(&sdev->in_flight) == 0);
+
+	atomic_dec(&fs_info->scrubs_running);
+	wake_up(&fs_info->scrub_pause_wait);
+
+	if (progress)
+		memcpy(progress, &sdev->stat, sizeof(*progress));
+
+	mutex_lock(&fs_info->scrub_lock);
+	dev->scrub_device = NULL;
+	mutex_unlock(&fs_info->scrub_lock);
+
+	scrub_free_dev(sdev);
+	scrub_workers_put(root);
+
+	return ret;
+}
+
+int btrfs_scrub_pause(struct btrfs_root *root)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+
+	mutex_lock(&fs_info->scrub_lock);
+	atomic_inc(&fs_info->scrub_pause_req);
+	while (atomic_read(&fs_info->scrubs_paused) !=
+	       atomic_read(&fs_info->scrubs_running)) {
+		mutex_unlock(&fs_info->scrub_lock);
+		wait_event(fs_info->scrub_pause_wait,
+			   atomic_read(&fs_info->scrubs_paused) ==
+			   atomic_read(&fs_info->scrubs_running));
+		mutex_lock(&fs_info->scrub_lock);
+	}
+	mutex_unlock(&fs_info->scrub_lock);
+
+	return 0;
+}
+
+int btrfs_scrub_continue(struct btrfs_root *root)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+
+	atomic_dec(&fs_info->scrub_pause_req);
+	wake_up(&fs_info->scrub_pause_wait);
+	return 0;
+}
+
+int btrfs_scrub_pause_super(struct btrfs_root *root)
+{
+	down_write(&root->fs_info->scrub_super_lock);
+	return 0;
+}
+
+int btrfs_scrub_continue_super(struct btrfs_root *root)
+{
+	up_write(&root->fs_info->scrub_super_lock);
+	return 0;
+}
+
+int btrfs_scrub_cancel(struct btrfs_root *root)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+
+	mutex_lock(&fs_info->scrub_lock);
+	if (!atomic_read(&fs_info->scrubs_running)) {
+		mutex_unlock(&fs_info->scrub_lock);
+		return -ENOTCONN;
+	}
+
+	atomic_inc(&fs_info->scrub_cancel_req);
+	while (atomic_read(&fs_info->scrubs_running)) {
+		mutex_unlock(&fs_info->scrub_lock);
+		wait_event(fs_info->scrub_pause_wait,
+			   atomic_read(&fs_info->scrubs_running) == 0);
+		mutex_lock(&fs_info->scrub_lock);
+	}
+	atomic_dec(&fs_info->scrub_cancel_req);
+	mutex_unlock(&fs_info->scrub_lock);
+
+	return 0;
+}
+
+int btrfs_scrub_cancel_dev(struct btrfs_root *root, struct btrfs_device *dev)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct scrub_dev *sdev;
+
+	mutex_lock(&fs_info->scrub_lock);
+	sdev = dev->scrub_device;
+	if (!sdev) {
+		mutex_unlock(&fs_info->scrub_lock);
+		return -ENOTCONN;
+	}
+	atomic_inc(&sdev->cancel_req);
+	while (dev->scrub_device) {
+		mutex_unlock(&fs_info->scrub_lock);
+		wait_event(fs_info->scrub_pause_wait,
+			   dev->scrub_device == NULL);
+		mutex_lock(&fs_info->scrub_lock);
+	}
+	mutex_unlock(&fs_info->scrub_lock);
+
+	return 0;
+}
+int btrfs_scrub_cancel_devid(struct btrfs_root *root, u64 devid)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_device *dev;
+	int ret;
+
+	/*
+	 * we have to hold the device_list_mutex here so the device
+	 * does not go away in cancel_dev. FIXME: find a better solution
+	 */
+	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	dev = btrfs_find_device(root, devid, NULL, NULL);
+	if (!dev) {
+		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+		return -ENODEV;
+	}
+	ret = btrfs_scrub_cancel_dev(root, dev);
+	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+
+	return ret;
+}
+
+int btrfs_scrub_progress(struct btrfs_root *root, u64 devid,
+			 struct btrfs_scrub_progress *progress)
+{
+	struct btrfs_device *dev;
+	struct scrub_dev *sdev = NULL;
+
+	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
+	dev = btrfs_find_device(root, devid, NULL, NULL);
+	if (dev)
+		sdev = dev->scrub_device;
+	if (sdev)
+		memcpy(progress, &sdev->stat, sizeof(*progress));
+	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+
+	return dev ? (sdev ? 0 : -ENOTCONN) : -ENODEV;
+}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index be4ffa12f3ef..0bb4ebbb71b7 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -41,6 +41,7 @@
 #include <linux/slab.h>
 #include <linux/cleancache.h>
 #include "compat.h"
+#include "delayed-inode.h"
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -160,7 +161,8 @@ enum {
 	Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
 	Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
 	Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed,
-	Opt_enospc_debug, Opt_subvolrootid, Opt_err,
+	Opt_enospc_debug, Opt_subvolrootid, Opt_defrag,
+	Opt_inode_cache, Opt_err,
 };
 
 static match_table_t tokens = {
@@ -191,6 +193,8 @@ static match_table_t tokens = {
 	{Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"},
 	{Opt_enospc_debug, "enospc_debug"},
 	{Opt_subvolrootid, "subvolrootid=%d"},
+	{Opt_defrag, "autodefrag"},
+	{Opt_inode_cache, "inode_cache"},
 	{Opt_err, NULL},
 };
 
@@ -359,6 +363,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			printk(KERN_INFO "btrfs: enabling disk space caching\n");
 			btrfs_set_opt(info->mount_opt, SPACE_CACHE);
 			break;
+		case Opt_inode_cache:
+			printk(KERN_INFO "btrfs: enabling inode map caching\n");
+			btrfs_set_opt(info->mount_opt, INODE_MAP_CACHE);
+			break;
 		case Opt_clear_cache:
 			printk(KERN_INFO "btrfs: force clearing of disk cache\n");
 			btrfs_set_opt(info->mount_opt, CLEAR_CACHE);
@@ -369,6 +377,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 		case Opt_enospc_debug:
 			btrfs_set_opt(info->mount_opt, ENOSPC_DEBUG);
 			break;
+		case Opt_defrag:
+			printk(KERN_INFO "btrfs: enabling auto defrag");
+			btrfs_set_opt(info->mount_opt, AUTO_DEFRAG);
+			break;
 		case Opt_err:
 			printk(KERN_INFO "btrfs: unrecognized mount option "
 			       "'%s'\n", p);
@@ -507,8 +519,10 @@ static struct dentry *get_default_root(struct super_block *sb,
 	 */
 	dir_id = btrfs_super_root_dir(&root->fs_info->super_copy);
 	di = btrfs_lookup_dir_item(NULL, root, path, dir_id, "default", 7, 0);
-	if (IS_ERR(di))
+	if (IS_ERR(di)) {
+		btrfs_free_path(path);
 		return ERR_CAST(di);
+	}
 	if (!di) {
 		/*
 		 * Ok the default dir item isn't there.  This is weird since
@@ -741,7 +755,7 @@ static int btrfs_set_super(struct super_block *s, void *data)
  *	  for multiple device setup.  Make sure to keep it in sync.
  */
 static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
-		const char *dev_name, void *data)
+		const char *device_name, void *data)
 {
 	struct block_device *bdev = NULL;
 	struct super_block *s;
@@ -764,7 +778,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	if (error)
 		return ERR_PTR(error);
 
-	error = btrfs_scan_one_device(dev_name, mode, fs_type, &fs_devices);
+	error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices);
 	if (error)
 		goto error_free_subvol_name;
 
@@ -811,7 +825,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	} else {
 		char b[BDEVNAME_SIZE];
 
-		s->s_flags = flags;
+		s->s_flags = flags | MS_NOSEC;
 		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
 		error = btrfs_fill_super(s, fs_devices, data,
 					 flags & MS_SILENT ? 1 : 0);
@@ -915,6 +929,32 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 	return 0;
 }
 
+/* Used to sort the devices by max_avail(descending sort) */
+static int btrfs_cmp_device_free_bytes(const void *dev_info1,
+				       const void *dev_info2)
+{
+	if (((struct btrfs_device_info *)dev_info1)->max_avail >
+	    ((struct btrfs_device_info *)dev_info2)->max_avail)
+		return -1;
+	else if (((struct btrfs_device_info *)dev_info1)->max_avail <
+		 ((struct btrfs_device_info *)dev_info2)->max_avail)
+		return 1;
+	else
+	return 0;
+}
+
+/*
+ * sort the devices by max_avail, in which max free extent size of each device
+ * is stored.(Descending Sort)
+ */
+static inline void btrfs_descending_sort_devices(
+					struct btrfs_device_info *devices,
+					size_t nr_devices)
+{
+	sort(devices, nr_devices, sizeof(struct btrfs_device_info),
+	     btrfs_cmp_device_free_bytes, NULL);
+}
+
 /*
  * The helper to calc the free space on the devices that can be used to store
  * file data.
@@ -1208,10 +1248,14 @@ static int __init init_btrfs_fs(void)
 	if (err)
 		goto free_extent_io;
 
-	err = btrfs_interface_init();
+	err = btrfs_delayed_inode_init();
 	if (err)
 		goto free_extent_map;
 
+	err = btrfs_interface_init();
+	if (err)
+		goto free_delayed_inode;
+
 	err = register_filesystem(&btrfs_fs_type);
 	if (err)
 		goto unregister_ioctl;
@@ -1221,6 +1265,8 @@ static int __init init_btrfs_fs(void)
 
 unregister_ioctl:
 	btrfs_interface_exit();
+free_delayed_inode:
+	btrfs_delayed_inode_exit();
 free_extent_map:
 	extent_map_exit();
 free_extent_io:
@@ -1237,6 +1283,7 @@ free_sysfs:
 static void __exit exit_btrfs_fs(void)
 {
 	btrfs_destroy_cachep();
+	btrfs_delayed_inode_exit();
 	extent_map_exit();
 	extent_io_exit();
 	btrfs_interface_exit();
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 4ce16ef702a3..daac9ae6d731 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -28,232 +28,9 @@
 #include "disk-io.h"
 #include "transaction.h"
 
-static ssize_t root_blocks_used_show(struct btrfs_root *root, char *buf)
-{
-	return snprintf(buf, PAGE_SIZE, "%llu\n",
-		(unsigned long long)btrfs_root_used(&root->root_item));
-}
-
-static ssize_t root_block_limit_show(struct btrfs_root *root, char *buf)
-{
-	return snprintf(buf, PAGE_SIZE, "%llu\n",
-		(unsigned long long)btrfs_root_limit(&root->root_item));
-}
-
-static ssize_t super_blocks_used_show(struct btrfs_fs_info *fs, char *buf)
-{
-
-	return snprintf(buf, PAGE_SIZE, "%llu\n",
-		(unsigned long long)btrfs_super_bytes_used(&fs->super_copy));
-}
-
-static ssize_t super_total_blocks_show(struct btrfs_fs_info *fs, char *buf)
-{
-	return snprintf(buf, PAGE_SIZE, "%llu\n",
-		(unsigned long long)btrfs_super_total_bytes(&fs->super_copy));
-}
-
-static ssize_t super_blocksize_show(struct btrfs_fs_info *fs, char *buf)
-{
-	return snprintf(buf, PAGE_SIZE, "%llu\n",
-		(unsigned long long)btrfs_super_sectorsize(&fs->super_copy));
-}
-
-/* this is for root attrs (subvols/snapshots) */
-struct btrfs_root_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct btrfs_root *, char *);
-	ssize_t (*store)(struct btrfs_root *, const char *, size_t);
-};
-
-#define ROOT_ATTR(name, mode, show, store) \
-static struct btrfs_root_attr btrfs_root_attr_##name = __ATTR(name, mode, \
-							      show, store)
-
-ROOT_ATTR(blocks_used,	0444,	root_blocks_used_show,	NULL);
-ROOT_ATTR(block_limit,	0644,	root_block_limit_show,	NULL);
-
-static struct attribute *btrfs_root_attrs[] = {
-	&btrfs_root_attr_blocks_used.attr,
-	&btrfs_root_attr_block_limit.attr,
-	NULL,
-};
-
-/* this is for super attrs (actual full fs) */
-struct btrfs_super_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct btrfs_fs_info *, char *);
-	ssize_t (*store)(struct btrfs_fs_info *, const char *, size_t);
-};
-
-#define SUPER_ATTR(name, mode, show, store) \
-static struct btrfs_super_attr btrfs_super_attr_##name = __ATTR(name, mode, \
-								show, store)
-
-SUPER_ATTR(blocks_used,		0444,	super_blocks_used_show,		NULL);
-SUPER_ATTR(total_blocks,	0444,	super_total_blocks_show,	NULL);
-SUPER_ATTR(blocksize,		0444,	super_blocksize_show,		NULL);
-
-static struct attribute *btrfs_super_attrs[] = {
-	&btrfs_super_attr_blocks_used.attr,
-	&btrfs_super_attr_total_blocks.attr,
-	&btrfs_super_attr_blocksize.attr,
-	NULL,
-};
-
-static ssize_t btrfs_super_attr_show(struct kobject *kobj,
-				    struct attribute *attr, char *buf)
-{
-	struct btrfs_fs_info *fs = container_of(kobj, struct btrfs_fs_info,
-						super_kobj);
-	struct btrfs_super_attr *a = container_of(attr,
-						  struct btrfs_super_attr,
-						  attr);
-
-	return a->show ? a->show(fs, buf) : 0;
-}
-
-static ssize_t btrfs_super_attr_store(struct kobject *kobj,
-				     struct attribute *attr,
-				     const char *buf, size_t len)
-{
-	struct btrfs_fs_info *fs = container_of(kobj, struct btrfs_fs_info,
-						super_kobj);
-	struct btrfs_super_attr *a = container_of(attr,
-						  struct btrfs_super_attr,
-						  attr);
-
-	return a->store ? a->store(fs, buf, len) : 0;
-}
-
-static ssize_t btrfs_root_attr_show(struct kobject *kobj,
-				    struct attribute *attr, char *buf)
-{
-	struct btrfs_root *root = container_of(kobj, struct btrfs_root,
-						root_kobj);
-	struct btrfs_root_attr *a = container_of(attr,
-						 struct btrfs_root_attr,
-						 attr);
-
-	return a->show ? a->show(root, buf) : 0;
-}
-
-static ssize_t btrfs_root_attr_store(struct kobject *kobj,
-				     struct attribute *attr,
-				     const char *buf, size_t len)
-{
-	struct btrfs_root *root = container_of(kobj, struct btrfs_root,
-						root_kobj);
-	struct btrfs_root_attr *a = container_of(attr,
-						 struct btrfs_root_attr,
-						 attr);
-	return a->store ? a->store(root, buf, len) : 0;
-}
-
-static void btrfs_super_release(struct kobject *kobj)
-{
-	struct btrfs_fs_info *fs = container_of(kobj, struct btrfs_fs_info,
-						super_kobj);
-	complete(&fs->kobj_unregister);
-}
-
-static void btrfs_root_release(struct kobject *kobj)
-{
-	struct btrfs_root *root = container_of(kobj, struct btrfs_root,
-						root_kobj);
-	complete(&root->kobj_unregister);
-}
-
-static const struct sysfs_ops btrfs_super_attr_ops = {
-	.show	= btrfs_super_attr_show,
-	.store	= btrfs_super_attr_store,
-};
-
-static const struct sysfs_ops btrfs_root_attr_ops = {
-	.show	= btrfs_root_attr_show,
-	.store	= btrfs_root_attr_store,
-};
-
-static struct kobj_type btrfs_root_ktype = {
-	.default_attrs	= btrfs_root_attrs,
-	.sysfs_ops	= &btrfs_root_attr_ops,
-	.release	= btrfs_root_release,
-};
-
-static struct kobj_type btrfs_super_ktype = {
-	.default_attrs	= btrfs_super_attrs,
-	.sysfs_ops	= &btrfs_super_attr_ops,
-	.release	= btrfs_super_release,
-};
-
 /* /sys/fs/btrfs/ entry */
 static struct kset *btrfs_kset;
 
-int btrfs_sysfs_add_super(struct btrfs_fs_info *fs)
-{
-	int error;
-	char *name;
-	char c;
-	int len = strlen(fs->sb->s_id) + 1;
-	int i;
-
-	name = kmalloc(len, GFP_NOFS);
-	if (!name) {
-		error = -ENOMEM;
-		goto fail;
-	}
-
-	for (i = 0; i < len; i++) {
-		c = fs->sb->s_id[i];
-		if (c == '/' || c == '\\')
-			c = '!';
-		name[i] = c;
-	}
-	name[len] = '\0';
-
-	fs->super_kobj.kset = btrfs_kset;
-	error = kobject_init_and_add(&fs->super_kobj, &btrfs_super_ktype,
-				     NULL, "%s", name);
-	kfree(name);
-	if (error)
-		goto fail;
-
-	return 0;
-
-fail:
-	printk(KERN_ERR "btrfs: sysfs creation for super failed\n");
-	return error;
-}
-
-int btrfs_sysfs_add_root(struct btrfs_root *root)
-{
-	int error;
-
-	error = kobject_init_and_add(&root->root_kobj, &btrfs_root_ktype,
-				     &root->fs_info->super_kobj,
-				     "%s", root->name);
-	if (error)
-		goto fail;
-
-	return 0;
-
-fail:
-	printk(KERN_ERR "btrfs: sysfs creation for root failed\n");
-	return error;
-}
-
-void btrfs_sysfs_del_root(struct btrfs_root *root)
-{
-	kobject_put(&root->root_kobj);
-	wait_for_completion(&root->kobj_unregister);
-}
-
-void btrfs_sysfs_del_super(struct btrfs_fs_info *fs)
-{
-	kobject_put(&fs->super_kobj);
-	wait_for_completion(&fs->kobj_unregister);
-}
-
 int btrfs_init_sysfs(void)
 {
 	btrfs_kset = kset_create_and_add("btrfs", NULL, fs_kobj);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index c571734d5e5a..51dcec86757f 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -27,6 +27,7 @@
 #include "transaction.h"
 #include "locking.h"
 #include "tree-log.h"
+#include "inode-map.h"
 
 #define BTRFS_ROOT_TRANS_TAG 0
 
@@ -34,6 +35,7 @@ static noinline void put_transaction(struct btrfs_transaction *transaction)
 {
 	WARN_ON(atomic_read(&transaction->use_count) == 0);
 	if (atomic_dec_and_test(&transaction->use_count)) {
+		BUG_ON(!list_empty(&transaction->list));
 		memset(transaction, 0, sizeof(*transaction));
 		kmem_cache_free(btrfs_transaction_cachep, transaction);
 	}
@@ -48,47 +50,72 @@ static noinline void switch_commit_root(struct btrfs_root *root)
 /*
  * either allocate a new transaction or hop into the existing one
  */
-static noinline int join_transaction(struct btrfs_root *root)
+static noinline int join_transaction(struct btrfs_root *root, int nofail)
 {
 	struct btrfs_transaction *cur_trans;
+
+	spin_lock(&root->fs_info->trans_lock);
+	if (root->fs_info->trans_no_join) {
+		if (!nofail) {
+			spin_unlock(&root->fs_info->trans_lock);
+			return -EBUSY;
+		}
+	}
+
 	cur_trans = root->fs_info->running_transaction;
-	if (!cur_trans) {
-		cur_trans = kmem_cache_alloc(btrfs_transaction_cachep,
-					     GFP_NOFS);
-		if (!cur_trans)
-			return -ENOMEM;
-		root->fs_info->generation++;
-		atomic_set(&cur_trans->num_writers, 1);
-		cur_trans->num_joined = 0;
-		cur_trans->transid = root->fs_info->generation;
-		init_waitqueue_head(&cur_trans->writer_wait);
-		init_waitqueue_head(&cur_trans->commit_wait);
-		cur_trans->in_commit = 0;
-		cur_trans->blocked = 0;
-		atomic_set(&cur_trans->use_count, 1);
-		cur_trans->commit_done = 0;
-		cur_trans->start_time = get_seconds();
-
-		cur_trans->delayed_refs.root = RB_ROOT;
-		cur_trans->delayed_refs.num_entries = 0;
-		cur_trans->delayed_refs.num_heads_ready = 0;
-		cur_trans->delayed_refs.num_heads = 0;
-		cur_trans->delayed_refs.flushing = 0;
-		cur_trans->delayed_refs.run_delayed_start = 0;
-		spin_lock_init(&cur_trans->delayed_refs.lock);
-
-		INIT_LIST_HEAD(&cur_trans->pending_snapshots);
-		list_add_tail(&cur_trans->list, &root->fs_info->trans_list);
-		extent_io_tree_init(&cur_trans->dirty_pages,
-				     root->fs_info->btree_inode->i_mapping,
-				     GFP_NOFS);
-		spin_lock(&root->fs_info->new_trans_lock);
-		root->fs_info->running_transaction = cur_trans;
-		spin_unlock(&root->fs_info->new_trans_lock);
-	} else {
+	if (cur_trans) {
+		atomic_inc(&cur_trans->use_count);
 		atomic_inc(&cur_trans->num_writers);
 		cur_trans->num_joined++;
+		spin_unlock(&root->fs_info->trans_lock);
+		return 0;
 	}
+	spin_unlock(&root->fs_info->trans_lock);
+
+	cur_trans = kmem_cache_alloc(btrfs_transaction_cachep, GFP_NOFS);
+	if (!cur_trans)
+		return -ENOMEM;
+	spin_lock(&root->fs_info->trans_lock);
+	if (root->fs_info->running_transaction) {
+		kmem_cache_free(btrfs_transaction_cachep, cur_trans);
+		cur_trans = root->fs_info->running_transaction;
+		atomic_inc(&cur_trans->use_count);
+		atomic_inc(&cur_trans->num_writers);
+		cur_trans->num_joined++;
+		spin_unlock(&root->fs_info->trans_lock);
+		return 0;
+	}
+	atomic_set(&cur_trans->num_writers, 1);
+	cur_trans->num_joined = 0;
+	init_waitqueue_head(&cur_trans->writer_wait);
+	init_waitqueue_head(&cur_trans->commit_wait);
+	cur_trans->in_commit = 0;
+	cur_trans->blocked = 0;
+	/*
+	 * One for this trans handle, one so it will live on until we
+	 * commit the transaction.
+	 */
+	atomic_set(&cur_trans->use_count, 2);
+	cur_trans->commit_done = 0;
+	cur_trans->start_time = get_seconds();
+
+	cur_trans->delayed_refs.root = RB_ROOT;
+	cur_trans->delayed_refs.num_entries = 0;
+	cur_trans->delayed_refs.num_heads_ready = 0;
+	cur_trans->delayed_refs.num_heads = 0;
+	cur_trans->delayed_refs.flushing = 0;
+	cur_trans->delayed_refs.run_delayed_start = 0;
+	spin_lock_init(&cur_trans->commit_lock);
+	spin_lock_init(&cur_trans->delayed_refs.lock);
+
+	INIT_LIST_HEAD(&cur_trans->pending_snapshots);
+	list_add_tail(&cur_trans->list, &root->fs_info->trans_list);
+	extent_io_tree_init(&cur_trans->dirty_pages,
+			     root->fs_info->btree_inode->i_mapping);
+	root->fs_info->generation++;
+	cur_trans->transid = root->fs_info->generation;
+	root->fs_info->running_transaction = cur_trans;
+	spin_unlock(&root->fs_info->trans_lock);
 
 	return 0;
 }
@@ -99,36 +126,82 @@ static noinline int join_transaction(struct btrfs_root *root)
  * to make sure the old root from before we joined the transaction is deleted
  * when the transaction commits
  */
-static noinline int record_root_in_trans(struct btrfs_trans_handle *trans,
-					 struct btrfs_root *root)
+static int record_root_in_trans(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root)
 {
 	if (root->ref_cows && root->last_trans < trans->transid) {
 		WARN_ON(root == root->fs_info->extent_root);
 		WARN_ON(root->commit_root != root->node);
 
+		/*
+		 * see below for in_trans_setup usage rules
+		 * we have the reloc mutex held now, so there
+		 * is only one writer in this function
+		 */
+		root->in_trans_setup = 1;
+
+		/* make sure readers find in_trans_setup before
+		 * they find our root->last_trans update
+		 */
+		smp_wmb();
+
+		spin_lock(&root->fs_info->fs_roots_radix_lock);
+		if (root->last_trans == trans->transid) {
+			spin_unlock(&root->fs_info->fs_roots_radix_lock);
+			return 0;
+		}
 		radix_tree_tag_set(&root->fs_info->fs_roots_radix,
 			   (unsigned long)root->root_key.objectid,
 			   BTRFS_ROOT_TRANS_TAG);
+		spin_unlock(&root->fs_info->fs_roots_radix_lock);
 		root->last_trans = trans->transid;
+
+		/* this is pretty tricky.  We don't want to
+		 * take the relocation lock in btrfs_record_root_in_trans
+		 * unless we're really doing the first setup for this root in
+		 * this transaction.
+		 *
+		 * Normally we'd use root->last_trans as a flag to decide
+		 * if we want to take the expensive mutex.
+		 *
+		 * But, we have to set root->last_trans before we
+		 * init the relocation root, otherwise, we trip over warnings
+		 * in ctree.c.  The solution used here is to flag ourselves
+		 * with root->in_trans_setup.  When this is 1, we're still
+		 * fixing up the reloc trees and everyone must wait.
+		 *
+		 * When this is zero, they can trust root->last_trans and fly
+		 * through btrfs_record_root_in_trans without having to take the
+		 * lock.  smp_wmb() makes sure that all the writes above are
+		 * done before we pop in the zero below
+		 */
 		btrfs_init_reloc_root(trans, root);
+		smp_wmb();
+		root->in_trans_setup = 0;
 	}
 	return 0;
 }
 
+
 int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root)
 {
 	if (!root->ref_cows)
 		return 0;
 
-	mutex_lock(&root->fs_info->trans_mutex);
-	if (root->last_trans == trans->transid) {
-		mutex_unlock(&root->fs_info->trans_mutex);
+	/*
+	 * see record_root_in_trans for comments about in_trans_setup usage
+	 * and barriers
+	 */
+	smp_rmb();
+	if (root->last_trans == trans->transid &&
+	    !root->in_trans_setup)
 		return 0;
-	}
 
+	mutex_lock(&root->fs_info->reloc_mutex);
 	record_root_in_trans(trans, root);
-	mutex_unlock(&root->fs_info->trans_mutex);
+	mutex_unlock(&root->fs_info->reloc_mutex);
+
 	return 0;
 }
 
@@ -140,21 +213,23 @@ static void wait_current_trans(struct btrfs_root *root)
 {
 	struct btrfs_transaction *cur_trans;
 
+	spin_lock(&root->fs_info->trans_lock);
 	cur_trans = root->fs_info->running_transaction;
 	if (cur_trans && cur_trans->blocked) {
 		DEFINE_WAIT(wait);
 		atomic_inc(&cur_trans->use_count);
+		spin_unlock(&root->fs_info->trans_lock);
 		while (1) {
 			prepare_to_wait(&root->fs_info->transaction_wait, &wait,
 					TASK_UNINTERRUPTIBLE);
 			if (!cur_trans->blocked)
 				break;
-			mutex_unlock(&root->fs_info->trans_mutex);
 			schedule();
-			mutex_lock(&root->fs_info->trans_mutex);
 		}
 		finish_wait(&root->fs_info->transaction_wait, &wait);
 		put_transaction(cur_trans);
+	} else {
+		spin_unlock(&root->fs_info->trans_lock);
 	}
 }
 
@@ -167,10 +242,16 @@ enum btrfs_trans_type {
 
 static int may_wait_transaction(struct btrfs_root *root, int type)
 {
-	if (!root->fs_info->log_root_recovering &&
-	    ((type == TRANS_START && !root->fs_info->open_ioctl_trans) ||
-	     type == TRANS_USERSPACE))
+	if (root->fs_info->log_root_recovering)
+		return 0;
+
+	if (type == TRANS_USERSPACE)
+		return 1;
+
+	if (type == TRANS_START &&
+	    !atomic_read(&root->fs_info->open_ioctl_trans))
 		return 1;
+
 	return 0;
 }
 
@@ -184,36 +265,44 @@ static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
 
 	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
 		return ERR_PTR(-EROFS);
+
+	if (current->journal_info) {
+		WARN_ON(type != TRANS_JOIN && type != TRANS_JOIN_NOLOCK);
+		h = current->journal_info;
+		h->use_count++;
+		h->orig_rsv = h->block_rsv;
+		h->block_rsv = NULL;
+		goto got_it;
+	}
 again:
 	h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
 	if (!h)
 		return ERR_PTR(-ENOMEM);
 
-	if (type != TRANS_JOIN_NOLOCK)
-		mutex_lock(&root->fs_info->trans_mutex);
 	if (may_wait_transaction(root, type))
 		wait_current_trans(root);
 
-	ret = join_transaction(root);
+	do {
+		ret = join_transaction(root, type == TRANS_JOIN_NOLOCK);
+		if (ret == -EBUSY)
+			wait_current_trans(root);
+	} while (ret == -EBUSY);
+
 	if (ret < 0) {
 		kmem_cache_free(btrfs_trans_handle_cachep, h);
-		if (type != TRANS_JOIN_NOLOCK)
-			mutex_unlock(&root->fs_info->trans_mutex);
 		return ERR_PTR(ret);
 	}
 
 	cur_trans = root->fs_info->running_transaction;
-	atomic_inc(&cur_trans->use_count);
-	if (type != TRANS_JOIN_NOLOCK)
-		mutex_unlock(&root->fs_info->trans_mutex);
 
 	h->transid = cur_trans->transid;
 	h->transaction = cur_trans;
 	h->blocks_used = 0;
-	h->block_group = 0;
 	h->bytes_reserved = 0;
 	h->delayed_ref_updates = 0;
+	h->use_count = 1;
 	h->block_rsv = NULL;
+	h->orig_rsv = NULL;
 
 	smp_mb();
 	if (cur_trans->blocked && may_wait_transaction(root, type)) {
@@ -241,11 +330,8 @@ again:
 		}
 	}
 
-	if (type != TRANS_JOIN_NOLOCK)
-		mutex_lock(&root->fs_info->trans_mutex);
-	record_root_in_trans(h, root);
-	if (type != TRANS_JOIN_NOLOCK)
-		mutex_unlock(&root->fs_info->trans_mutex);
+got_it:
+	btrfs_record_root_in_trans(h, root);
 
 	if (!current->journal_info && type != TRANS_USERSPACE)
 		current->journal_info = h;
@@ -257,22 +343,19 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
 {
 	return start_transaction(root, num_items, TRANS_START);
 }
-struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root,
-						   int num_blocks)
+struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root)
 {
 	return start_transaction(root, 0, TRANS_JOIN);
 }
 
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root,
-							  int num_blocks)
+struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root)
 {
 	return start_transaction(root, 0, TRANS_JOIN_NOLOCK);
 }
 
-struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *r,
-							 int num_blocks)
+struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root)
 {
-	return start_transaction(r, 0, TRANS_USERSPACE);
+	return start_transaction(root, 0, TRANS_USERSPACE);
 }
 
 /* wait for a transaction commit to be fully complete */
@@ -280,17 +363,13 @@ static noinline int wait_for_commit(struct btrfs_root *root,
 				    struct btrfs_transaction *commit)
 {
 	DEFINE_WAIT(wait);
-	mutex_lock(&root->fs_info->trans_mutex);
 	while (!commit->commit_done) {
 		prepare_to_wait(&commit->commit_wait, &wait,
 				TASK_UNINTERRUPTIBLE);
 		if (commit->commit_done)
 			break;
-		mutex_unlock(&root->fs_info->trans_mutex);
 		schedule();
-		mutex_lock(&root->fs_info->trans_mutex);
 	}
-	mutex_unlock(&root->fs_info->trans_mutex);
 	finish_wait(&commit->commit_wait, &wait);
 	return 0;
 }
@@ -300,102 +379,56 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
 	struct btrfs_transaction *cur_trans = NULL, *t;
 	int ret;
 
-	mutex_lock(&root->fs_info->trans_mutex);
-
 	ret = 0;
 	if (transid) {
 		if (transid <= root->fs_info->last_trans_committed)
-			goto out_unlock;
+			goto out;
 
 		/* find specified transaction */
+		spin_lock(&root->fs_info->trans_lock);
 		list_for_each_entry(t, &root->fs_info->trans_list, list) {
 			if (t->transid == transid) {
 				cur_trans = t;
+				atomic_inc(&cur_trans->use_count);
 				break;
 			}
 			if (t->transid > transid)
 				break;
 		}
+		spin_unlock(&root->fs_info->trans_lock);
 		ret = -EINVAL;
 		if (!cur_trans)
-			goto out_unlock;  /* bad transid */
+			goto out;  /* bad transid */
 	} else {
 		/* find newest transaction that is committing | committed */
+		spin_lock(&root->fs_info->trans_lock);
 		list_for_each_entry_reverse(t, &root->fs_info->trans_list,
 					    list) {
 			if (t->in_commit) {
 				if (t->commit_done)
-					goto out_unlock;
+					break;
 				cur_trans = t;
+				atomic_inc(&cur_trans->use_count);
 				break;
 			}
 		}
+		spin_unlock(&root->fs_info->trans_lock);
 		if (!cur_trans)
-			goto out_unlock;  /* nothing committing|committed */
+			goto out;  /* nothing committing|committed */
 	}
 
-	atomic_inc(&cur_trans->use_count);
-	mutex_unlock(&root->fs_info->trans_mutex);
-
 	wait_for_commit(root, cur_trans);
 
-	mutex_lock(&root->fs_info->trans_mutex);
 	put_transaction(cur_trans);
 	ret = 0;
-out_unlock:
-	mutex_unlock(&root->fs_info->trans_mutex);
+out:
 	return ret;
 }
 
-#if 0
-/*
- * rate limit against the drop_snapshot code.  This helps to slow down new
- * operations if the drop_snapshot code isn't able to keep up.
- */
-static void throttle_on_drops(struct btrfs_root *root)
-{
-	struct btrfs_fs_info *info = root->fs_info;
-	int harder_count = 0;
-
-harder:
-	if (atomic_read(&info->throttles)) {
-		DEFINE_WAIT(wait);
-		int thr;
-		thr = atomic_read(&info->throttle_gen);
-
-		do {
-			prepare_to_wait(&info->transaction_throttle,
-					&wait, TASK_UNINTERRUPTIBLE);
-			if (!atomic_read(&info->throttles)) {
-				finish_wait(&info->transaction_throttle, &wait);
-				break;
-			}
-			schedule();
-			finish_wait(&info->transaction_throttle, &wait);
-		} while (thr == atomic_read(&info->throttle_gen));
-		harder_count++;
-
-		if (root->fs_info->total_ref_cache_size > 1 * 1024 * 1024 &&
-		    harder_count < 2)
-			goto harder;
-
-		if (root->fs_info->total_ref_cache_size > 5 * 1024 * 1024 &&
-		    harder_count < 10)
-			goto harder;
-
-		if (root->fs_info->total_ref_cache_size > 10 * 1024 * 1024 &&
-		    harder_count < 20)
-			goto harder;
-	}
-}
-#endif
-
 void btrfs_throttle(struct btrfs_root *root)
 {
-	mutex_lock(&root->fs_info->trans_mutex);
-	if (!root->fs_info->open_ioctl_trans)
+	if (!atomic_read(&root->fs_info->open_ioctl_trans))
 		wait_current_trans(root);
-	mutex_unlock(&root->fs_info->trans_mutex);
 }
 
 static int should_end_transaction(struct btrfs_trans_handle *trans,
@@ -413,6 +446,7 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans,
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	int updates;
 
+	smp_mb();
 	if (cur_trans->blocked || cur_trans->delayed_refs.flushing)
 		return 1;
 
@@ -431,6 +465,11 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	struct btrfs_fs_info *info = root->fs_info;
 	int count = 0;
 
+	if (--trans->use_count) {
+		trans->block_rsv = trans->orig_rsv;
+		return 0;
+	}
+
 	while (count < 4) {
 		unsigned long cur = trans->delayed_ref_updates;
 		trans->delayed_ref_updates = 0;
@@ -453,9 +492,11 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 
 	btrfs_trans_release_metadata(trans, root);
 
-	if (lock && !root->fs_info->open_ioctl_trans &&
-	    should_end_transaction(trans, root))
+	if (lock && !atomic_read(&root->fs_info->open_ioctl_trans) &&
+	    should_end_transaction(trans, root)) {
 		trans->transaction->blocked = 1;
+		smp_wmb();
+	}
 
 	if (lock && cur_trans->blocked && !cur_trans->in_commit) {
 		if (throttle)
@@ -487,19 +528,40 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 int btrfs_end_transaction(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root)
 {
-	return __btrfs_end_transaction(trans, root, 0, 1);
+	int ret;
+
+	ret = __btrfs_end_transaction(trans, root, 0, 1);
+	if (ret)
+		return ret;
+	return 0;
 }
 
 int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root)
 {
-	return __btrfs_end_transaction(trans, root, 1, 1);
+	int ret;
+
+	ret = __btrfs_end_transaction(trans, root, 1, 1);
+	if (ret)
+		return ret;
+	return 0;
 }
 
 int btrfs_end_transaction_nolock(struct btrfs_trans_handle *trans,
 				 struct btrfs_root *root)
 {
-	return __btrfs_end_transaction(trans, root, 0, 0);
+	int ret;
+
+	ret = __btrfs_end_transaction(trans, root, 0, 0);
+	if (ret)
+		return ret;
+	return 0;
+}
+
+int btrfs_end_transaction_dmeta(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root)
+{
+	return __btrfs_end_transaction(trans, root, 1, 1);
 }
 
 /*
@@ -725,9 +787,9 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
  */
 int btrfs_add_dead_root(struct btrfs_root *root)
 {
-	mutex_lock(&root->fs_info->trans_mutex);
+	spin_lock(&root->fs_info->trans_lock);
 	list_add(&root->root_list, &root->fs_info->dead_roots);
-	mutex_unlock(&root->fs_info->trans_mutex);
+	spin_unlock(&root->fs_info->trans_lock);
 	return 0;
 }
 
@@ -743,6 +805,7 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
 	int ret;
 	int err = 0;
 
+	spin_lock(&fs_info->fs_roots_radix_lock);
 	while (1) {
 		ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix,
 						 (void **)gang, 0,
@@ -755,13 +818,20 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
 			radix_tree_tag_clear(&fs_info->fs_roots_radix,
 					(unsigned long)root->root_key.objectid,
 					BTRFS_ROOT_TRANS_TAG);
+			spin_unlock(&fs_info->fs_roots_radix_lock);
 
 			btrfs_free_log(trans, root);
 			btrfs_update_reloc_root(trans, root);
 			btrfs_orphan_commit_root(trans, root);
 
+			btrfs_save_ino_cache(root, trans);
+
 			if (root->commit_root != root->node) {
+				mutex_lock(&root->fs_commit_mutex);
 				switch_commit_root(root);
+				btrfs_unpin_free_ino(root);
+				mutex_unlock(&root->fs_commit_mutex);
+
 				btrfs_set_root_node(&root->root_item,
 						    root->node);
 			}
@@ -769,10 +839,12 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
 			err = btrfs_update_root(trans, fs_info->tree_root,
 						&root->root_key,
 						&root->root_item);
+			spin_lock(&fs_info->fs_roots_radix_lock);
 			if (err)
 				break;
 		}
 	}
+	spin_unlock(&fs_info->fs_roots_radix_lock);
 	return err;
 }
 
@@ -802,104 +874,13 @@ int btrfs_defrag_root(struct btrfs_root *root, int cacheonly)
 		btrfs_btree_balance_dirty(info->tree_root, nr);
 		cond_resched();
 
-		if (root->fs_info->closing || ret != -EAGAIN)
+		if (btrfs_fs_closing(root->fs_info) || ret != -EAGAIN)
 			break;
 	}
 	root->defrag_running = 0;
 	return ret;
 }
 
-#if 0
-/*
- * when dropping snapshots, we generate a ton of delayed refs, and it makes
- * sense not to join the transaction while it is trying to flush the current
- * queue of delayed refs out.
- *
- * This is used by the drop snapshot code only
- */
-static noinline int wait_transaction_pre_flush(struct btrfs_fs_info *info)
-{
-	DEFINE_WAIT(wait);
-
-	mutex_lock(&info->trans_mutex);
-	while (info->running_transaction &&
-	       info->running_transaction->delayed_refs.flushing) {
-		prepare_to_wait(&info->transaction_wait, &wait,
-				TASK_UNINTERRUPTIBLE);
-		mutex_unlock(&info->trans_mutex);
-
-		schedule();
-
-		mutex_lock(&info->trans_mutex);
-		finish_wait(&info->transaction_wait, &wait);
-	}
-	mutex_unlock(&info->trans_mutex);
-	return 0;
-}
-
-/*
- * Given a list of roots that need to be deleted, call btrfs_drop_snapshot on
- * all of them
- */
-int btrfs_drop_dead_root(struct btrfs_root *root)
-{
-	struct btrfs_trans_handle *trans;
-	struct btrfs_root *tree_root = root->fs_info->tree_root;
-	unsigned long nr;
-	int ret;
-
-	while (1) {
-		/*
-		 * we don't want to jump in and create a bunch of
-		 * delayed refs if the transaction is starting to close
-		 */
-		wait_transaction_pre_flush(tree_root->fs_info);
-		trans = btrfs_start_transaction(tree_root, 1);
-
-		/*
-		 * we've joined a transaction, make sure it isn't
-		 * closing right now
-		 */
-		if (trans->transaction->delayed_refs.flushing) {
-			btrfs_end_transaction(trans, tree_root);
-			continue;
-		}
-
-		ret = btrfs_drop_snapshot(trans, root);
-		if (ret != -EAGAIN)
-			break;
-
-		ret = btrfs_update_root(trans, tree_root,
-					&root->root_key,
-					&root->root_item);
-		if (ret)
-			break;
-
-		nr = trans->blocks_used;
-		ret = btrfs_end_transaction(trans, tree_root);
-		BUG_ON(ret);
-
-		btrfs_btree_balance_dirty(tree_root, nr);
-		cond_resched();
-	}
-	BUG_ON(ret);
-
-	ret = btrfs_del_root(trans, tree_root, &root->root_key);
-	BUG_ON(ret);
-
-	nr = trans->blocks_used;
-	ret = btrfs_end_transaction(trans, tree_root);
-	BUG_ON(ret);
-
-	free_extent_buffer(root->node);
-	free_extent_buffer(root->commit_root);
-	kfree(root);
-
-	btrfs_btree_balance_dirty(tree_root, nr);
-	return ret;
-}
-#endif
-
 /*
  * new snapshots need to be created at a very specific time in the
  * transaction commit.  This does the actual creation
@@ -930,7 +911,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	ret = btrfs_find_free_objectid(trans, tree_root, 0, &objectid);
+	ret = btrfs_find_free_objectid(tree_root, &objectid);
 	if (ret) {
 		pending->error = ret;
 		goto fail;
@@ -967,7 +948,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	BUG_ON(ret);
 	ret = btrfs_insert_dir_item(trans, parent_root,
 				dentry->d_name.name, dentry->d_name.len,
-				parent_inode->i_ino, &key,
+				parent_inode, &key,
 				BTRFS_FT_DIR, index);
 	BUG_ON(ret);
 
@@ -976,6 +957,15 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	ret = btrfs_update_inode(trans, parent_root, parent_inode);
 	BUG_ON(ret);
 
+	/*
+	 * pull in the delayed directory update
+	 * and the delayed inode item
+	 * otherwise we corrupt the FS during
+	 * snapshot
+	 */
+	ret = btrfs_run_delayed_items(trans, root);
+	BUG_ON(ret);
+
 	record_root_in_trans(trans, root);
 	btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
 	memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
@@ -1009,7 +999,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	 */
 	ret = btrfs_add_root_ref(trans, tree_root, objectid,
 				 parent_root->root_key.objectid,
-				 parent_inode->i_ino, index,
+				 btrfs_ino(parent_inode), index,
 				 dentry->d_name.name, dentry->d_name.len);
 	BUG_ON(ret);
 	dput(parent);
@@ -1066,20 +1056,20 @@ static void update_super_roots(struct btrfs_root *root)
 int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
 {
 	int ret = 0;
-	spin_lock(&info->new_trans_lock);
+	spin_lock(&info->trans_lock);
 	if (info->running_transaction)
 		ret = info->running_transaction->in_commit;
-	spin_unlock(&info->new_trans_lock);
+	spin_unlock(&info->trans_lock);
 	return ret;
 }
 
 int btrfs_transaction_blocked(struct btrfs_fs_info *info)
 {
 	int ret = 0;
-	spin_lock(&info->new_trans_lock);
+	spin_lock(&info->trans_lock);
 	if (info->running_transaction)
 		ret = info->running_transaction->blocked;
-	spin_unlock(&info->new_trans_lock);
+	spin_unlock(&info->trans_lock);
 	return ret;
 }
 
@@ -1103,9 +1093,7 @@ static void wait_current_trans_commit_start(struct btrfs_root *root,
 				    &wait);
 			break;
 		}
-		mutex_unlock(&root->fs_info->trans_mutex);
 		schedule();
-		mutex_lock(&root->fs_info->trans_mutex);
 		finish_wait(&root->fs_info->transaction_blocked_wait, &wait);
 	}
 }
@@ -1131,9 +1119,7 @@ static void wait_current_trans_commit_start_and_unblock(struct btrfs_root *root,
 				    &wait);
 			break;
 		}
-		mutex_unlock(&root->fs_info->trans_mutex);
 		schedule();
-		mutex_lock(&root->fs_info->trans_mutex);
 		finish_wait(&root->fs_info->transaction_wait,
 			    &wait);
 	}
@@ -1171,7 +1157,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 
 	INIT_DELAYED_WORK(&ac->work, do_async_commit);
 	ac->root = root;
-	ac->newtrans = btrfs_join_transaction(root, 0);
+	ac->newtrans = btrfs_join_transaction(root);
 	if (IS_ERR(ac->newtrans)) {
 		int err = PTR_ERR(ac->newtrans);
 		kfree(ac);
@@ -1179,23 +1165,22 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 	}
 
 	/* take transaction reference */
-	mutex_lock(&root->fs_info->trans_mutex);
 	cur_trans = trans->transaction;
 	atomic_inc(&cur_trans->use_count);
-	mutex_unlock(&root->fs_info->trans_mutex);
 
 	btrfs_end_transaction(trans, root);
 	schedule_delayed_work(&ac->work, 0);
 
 	/* wait for transaction to start and unblock */
-	mutex_lock(&root->fs_info->trans_mutex);
 	if (wait_for_unblock)
 		wait_current_trans_commit_start_and_unblock(root, cur_trans);
 	else
 		wait_current_trans_commit_start(root, cur_trans);
-	put_transaction(cur_trans);
-	mutex_unlock(&root->fs_info->trans_mutex);
 
+	if (current->journal_info == trans)
+		current->journal_info = NULL;
+
+	put_transaction(cur_trans);
 	return 0;
 }
 
@@ -1238,38 +1223,41 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	ret = btrfs_run_delayed_refs(trans, root, 0);
 	BUG_ON(ret);
 
-	mutex_lock(&root->fs_info->trans_mutex);
+	spin_lock(&cur_trans->commit_lock);
 	if (cur_trans->in_commit) {
+		spin_unlock(&cur_trans->commit_lock);
 		atomic_inc(&cur_trans->use_count);
-		mutex_unlock(&root->fs_info->trans_mutex);
 		btrfs_end_transaction(trans, root);
 
 		ret = wait_for_commit(root, cur_trans);
 		BUG_ON(ret);
 
-		mutex_lock(&root->fs_info->trans_mutex);
 		put_transaction(cur_trans);
-		mutex_unlock(&root->fs_info->trans_mutex);
 
 		return 0;
 	}
 
 	trans->transaction->in_commit = 1;
 	trans->transaction->blocked = 1;
+	spin_unlock(&cur_trans->commit_lock);
 	wake_up(&root->fs_info->transaction_blocked_wait);
 
+	spin_lock(&root->fs_info->trans_lock);
 	if (cur_trans->list.prev != &root->fs_info->trans_list) {
 		prev_trans = list_entry(cur_trans->list.prev,
 					struct btrfs_transaction, list);
 		if (!prev_trans->commit_done) {
 			atomic_inc(&prev_trans->use_count);
-			mutex_unlock(&root->fs_info->trans_mutex);
+			spin_unlock(&root->fs_info->trans_lock);
 
 			wait_for_commit(root, prev_trans);
 
-			mutex_lock(&root->fs_info->trans_mutex);
 			put_transaction(prev_trans);
+		} else {
+			spin_unlock(&root->fs_info->trans_lock);
 		}
+	} else {
+		spin_unlock(&root->fs_info->trans_lock);
 	}
 
 	if (now < cur_trans->start_time || now - cur_trans->start_time < 1)
@@ -1277,12 +1265,12 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 	do {
 		int snap_pending = 0;
+
 		joined = cur_trans->num_joined;
 		if (!list_empty(&trans->transaction->pending_snapshots))
 			snap_pending = 1;
 
 		WARN_ON(cur_trans != trans->transaction);
-		mutex_unlock(&root->fs_info->trans_mutex);
 
 		if (flush_on_commit || snap_pending) {
 			btrfs_start_delalloc_inodes(root, 1);
@@ -1290,6 +1278,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 			BUG_ON(ret);
 		}
 
+		ret = btrfs_run_delayed_items(trans, root);
+		BUG_ON(ret);
+
 		/*
 		 * rename don't use btrfs_join_transaction, so, once we
 		 * set the transaction to blocked above, we aren't going
@@ -1302,25 +1293,51 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 		prepare_to_wait(&cur_trans->writer_wait, &wait,
 				TASK_UNINTERRUPTIBLE);
 
-		smp_mb();
 		if (atomic_read(&cur_trans->num_writers) > 1)
 			schedule_timeout(MAX_SCHEDULE_TIMEOUT);
 		else if (should_grow)
 			schedule_timeout(1);
 
-		mutex_lock(&root->fs_info->trans_mutex);
 		finish_wait(&cur_trans->writer_wait, &wait);
 	} while (atomic_read(&cur_trans->num_writers) > 1 ||
 		 (should_grow && cur_trans->num_joined != joined));
 
+	/*
+	 * Ok now we need to make sure to block out any other joins while we
+	 * commit the transaction.  We could have started a join before setting
+	 * no_join so make sure to wait for num_writers to == 1 again.
+	 */
+	spin_lock(&root->fs_info->trans_lock);
+	root->fs_info->trans_no_join = 1;
+	spin_unlock(&root->fs_info->trans_lock);
+	wait_event(cur_trans->writer_wait,
+		   atomic_read(&cur_trans->num_writers) == 1);
+
+	/*
+	 * the reloc mutex makes sure that we stop
+	 * the balancing code from coming in and moving
+	 * extents around in the middle of the commit
+	 */
+	mutex_lock(&root->fs_info->reloc_mutex);
+
+	ret = btrfs_run_delayed_items(trans, root);
+	BUG_ON(ret);
+
 	ret = create_pending_snapshots(trans, root->fs_info);
 	BUG_ON(ret);
 
 	ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
 	BUG_ON(ret);
 
+	/*
+	 * make sure none of the code above managed to slip in a
+	 * delayed item
+	 */
+	btrfs_assert_delayed_root_empty(root);
+
 	WARN_ON(cur_trans != trans->transaction);
 
+	btrfs_scrub_pause(root);
 	/* btrfs_commit_tree_roots is responsible for getting the
 	 * various roots consistent with each other.  Every pointer
 	 * in the tree of tree roots has to point to the most up to date
@@ -1350,9 +1367,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	btrfs_prepare_extent_commit(trans, root);
 
 	cur_trans = root->fs_info->running_transaction;
-	spin_lock(&root->fs_info->new_trans_lock);
-	root->fs_info->running_transaction = NULL;
-	spin_unlock(&root->fs_info->new_trans_lock);
 
 	btrfs_set_root_node(&root->fs_info->tree_root->root_item,
 			    root->fs_info->tree_root->node);
@@ -1373,10 +1387,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	       sizeof(root->fs_info->super_copy));
 
 	trans->transaction->blocked = 0;
+	spin_lock(&root->fs_info->trans_lock);
+	root->fs_info->running_transaction = NULL;
+	root->fs_info->trans_no_join = 0;
+	spin_unlock(&root->fs_info->trans_lock);
+	mutex_unlock(&root->fs_info->reloc_mutex);
 
 	wake_up(&root->fs_info->transaction_wait);
 
-	mutex_unlock(&root->fs_info->trans_mutex);
 	ret = btrfs_write_and_wait_transaction(trans, root);
 	BUG_ON(ret);
 	write_ctree_super(trans, root, 0);
@@ -1389,21 +1407,22 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 	btrfs_finish_extent_commit(trans, root);
 
-	mutex_lock(&root->fs_info->trans_mutex);
-
 	cur_trans->commit_done = 1;
 
 	root->fs_info->last_trans_committed = cur_trans->transid;
 
 	wake_up(&cur_trans->commit_wait);
 
+	spin_lock(&root->fs_info->trans_lock);
 	list_del_init(&cur_trans->list);
+	spin_unlock(&root->fs_info->trans_lock);
+
 	put_transaction(cur_trans);
 	put_transaction(cur_trans);
 
 	trace_btrfs_transaction_commit(root);
 
-	mutex_unlock(&root->fs_info->trans_mutex);
+	btrfs_scrub_continue(root);
 
 	if (current->journal_info == trans)
 		current->journal_info = NULL;
@@ -1424,14 +1443,16 @@ int btrfs_clean_old_snapshots(struct btrfs_root *root)
 	LIST_HEAD(list);
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
-	mutex_lock(&fs_info->trans_mutex);
+	spin_lock(&fs_info->trans_lock);
 	list_splice_init(&fs_info->dead_roots, &list);
-	mutex_unlock(&fs_info->trans_mutex);
+	spin_unlock(&fs_info->trans_lock);
 
 	while (!list_empty(&list)) {
 		root = list_entry(list.next, struct btrfs_root, root_list);
 		list_del(&root->root_list);
 
+		btrfs_kill_all_delayed_nodes(root);
+
 		if (btrfs_header_backref_rev(root->node) <
 		    BTRFS_MIXED_BACKREF_REV)
 			btrfs_drop_snapshot(root, NULL, 0);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index e441acc6c584..02564e6230ac 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -28,10 +28,12 @@ struct btrfs_transaction {
 	 * transaction can end
 	 */
 	atomic_t num_writers;
+	atomic_t use_count;
 
 	unsigned long num_joined;
+
+	spinlock_t commit_lock;
 	int in_commit;
-	atomic_t use_count;
 	int commit_done;
 	int blocked;
 	struct list_head list;
@@ -45,13 +47,14 @@ struct btrfs_transaction {
 
 struct btrfs_trans_handle {
 	u64 transid;
-	u64 block_group;
 	u64 bytes_reserved;
+	unsigned long use_count;
 	unsigned long blocks_reserved;
 	unsigned long blocks_used;
 	unsigned long delayed_ref_updates;
 	struct btrfs_transaction *transaction;
 	struct btrfs_block_rsv *block_rsv;
+	struct btrfs_block_rsv *orig_rsv;
 };
 
 struct btrfs_pending_snapshot {
@@ -66,19 +69,6 @@ struct btrfs_pending_snapshot {
 	struct list_head list;
 };
 
-static inline void btrfs_set_trans_block_group(struct btrfs_trans_handle *trans,
-					       struct inode *inode)
-{
-	trans->block_group = BTRFS_I(inode)->block_group;
-}
-
-static inline void btrfs_update_inode_block_group(
-					  struct btrfs_trans_handle *trans,
-					  struct inode *inode)
-{
-	BTRFS_I(inode)->block_group = trans->block_group;
-}
-
 static inline void btrfs_set_inode_last_trans(struct btrfs_trans_handle *trans,
 					      struct inode *inode)
 {
@@ -92,20 +82,14 @@ int btrfs_end_transaction_nolock(struct btrfs_trans_handle *trans,
 				 struct btrfs_root *root);
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
 						   int num_items);
-struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root,
-						  int num_blocks);
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root,
-							  int num_blocks);
-struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *r,
-							 int num_blocks);
+struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root);
 int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid);
 int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root);
-int btrfs_commit_tree_roots(struct btrfs_trans_handle *trans,
-			    struct btrfs_root *root);
 
 int btrfs_add_dead_root(struct btrfs_root *root);
-int btrfs_drop_dead_root(struct btrfs_root *root);
 int btrfs_defrag_root(struct btrfs_root *root, int cacheonly);
 int btrfs_clean_old_snapshots(struct btrfs_root *root);
 int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
@@ -115,6 +99,8 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 				   int wait_for_unblock);
 int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root);
+int btrfs_end_transaction_dmeta(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root);
 int btrfs_should_end_transaction(struct btrfs_trans_handle *trans,
 				 struct btrfs_root *root);
 void btrfs_throttle(struct btrfs_root *root);
diff --git a/fs/btrfs/tree-defrag.c b/fs/btrfs/tree-defrag.c
index 992ab425599d..3b580ee8ab1d 100644
--- a/fs/btrfs/tree-defrag.c
+++ b/fs/btrfs/tree-defrag.c
@@ -97,7 +97,7 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 		ret = 0;
 		goto out;
 	}
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	wret = btrfs_search_slot(trans, root, &key, path, 0, 1);
 
 	if (wret < 0) {
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index f997ec0c1ba4..4ce8a9f41d1e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -333,13 +333,13 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 			goto insert;
 
 		if (item_size == 0) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			return 0;
 		}
 		dst_copy = kmalloc(item_size, GFP_NOFS);
 		src_copy = kmalloc(item_size, GFP_NOFS);
 		if (!dst_copy || !src_copy) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			kfree(dst_copy);
 			kfree(src_copy);
 			return -ENOMEM;
@@ -361,13 +361,13 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 		 * sync
 		 */
 		if (ret == 0) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			return 0;
 		}
 
 	}
 insert:
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	/* try to insert the key into the destination tree */
 	ret = btrfs_insert_empty_item(trans, root, path,
 				      key, item_size);
@@ -382,7 +382,6 @@ insert:
 		} else if (found_size < item_size) {
 			ret = btrfs_extend_item(trans, root, path,
 						item_size - found_size);
-			BUG_ON(ret);
 		}
 	} else if (ret) {
 		return ret;
@@ -438,7 +437,7 @@ insert:
 	}
 no_copy:
 	btrfs_mark_buffer_dirty(path->nodes[0]);
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	return 0;
 }
 
@@ -519,7 +518,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	 * file.  This must be done before the btrfs_drop_extents run
 	 * so we don't try to drop this extent.
 	 */
-	ret = btrfs_lookup_file_extent(trans, root, path, inode->i_ino,
+	ret = btrfs_lookup_file_extent(trans, root, path, btrfs_ino(inode),
 				       start, 0);
 
 	if (ret == 0 &&
@@ -544,11 +543,11 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		 * we don't have to do anything
 		 */
 		if (memcmp(&cmp1, &cmp2, sizeof(cmp1)) == 0) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			goto out;
 		}
 	}
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	saved_nbytes = inode_get_bytes(inode);
 	/* drop any overlapping extents */
@@ -590,6 +589,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 						ins.objectid, ins.offset,
 						0, root->root_key.objectid,
 						key->objectid, offset);
+				BUG_ON(ret);
 			} else {
 				/*
 				 * insert the extent pointer in the extent
@@ -600,7 +600,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 						key->objectid, offset, &ins);
 				BUG_ON(ret);
 			}
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 
 			if (btrfs_file_extent_compression(eb, item)) {
 				csum_start = ins.objectid;
@@ -614,7 +614,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 
 			ret = btrfs_lookup_csums_range(root->log_root,
 						csum_start, csum_end - 1,
-						&ordered_sums);
+						&ordered_sums, 0);
 			BUG_ON(ret);
 			while (!list_empty(&ordered_sums)) {
 				struct btrfs_ordered_sum *sums;
@@ -629,7 +629,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 				kfree(sums);
 			}
 		} else {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 		}
 	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
 		/* inline extents are easy, we just overwrite them */
@@ -675,10 +675,13 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 
 	read_extent_buffer(leaf, name, (unsigned long)(di + 1), name_len);
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	inode = read_one_inode(root, location.objectid);
-	BUG_ON(!inode);
+	if (!inode) {
+		kfree(name);
+		return -EIO;
+	}
 
 	ret = link_to_fixup_dir(trans, root, path, location.objectid);
 	BUG_ON(ret);
@@ -713,7 +716,7 @@ static noinline int inode_in_dir(struct btrfs_root *root,
 			goto out;
 	} else
 		goto out;
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	di = btrfs_lookup_dir_item(NULL, root, path, dirid, name, name_len, 0);
 	if (di && !IS_ERR(di)) {
@@ -724,7 +727,7 @@ static noinline int inode_in_dir(struct btrfs_root *root,
 		goto out;
 	match = 1;
 out:
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	return match;
 }
 
@@ -817,7 +820,10 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 		return -ENOENT;
 
 	inode = read_one_inode(root, key->objectid);
-	BUG_ON(!inode);
+	if (!inode) {
+		iput(dir);
+		return -EIO;
+	}
 
 	ref_ptr = btrfs_item_ptr_offset(eb, slot);
 	ref_end = ref_ptr + btrfs_item_size_nr(eb, slot);
@@ -832,7 +838,7 @@ again:
 	read_extent_buffer(eb, name, (unsigned long)(ref + 1), namelen);
 
 	/* if we already have a perfect match, we're done */
-	if (inode_in_dir(root, path, dir->i_ino, inode->i_ino,
+	if (inode_in_dir(root, path, btrfs_ino(dir), btrfs_ino(inode),
 			 btrfs_inode_ref_index(eb, ref),
 			 name, namelen)) {
 		goto out;
@@ -884,7 +890,7 @@ again:
 			if (!backref_in_log(log, key, victim_name,
 					    victim_name_len)) {
 				btrfs_inc_nlink(inode);
-				btrfs_release_path(root, path);
+				btrfs_release_path(path);
 
 				ret = btrfs_unlink_inode(trans, root, dir,
 							 inode, victim_name,
@@ -901,7 +907,7 @@ again:
 		 */
 		search_done = 1;
 	}
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 insert:
 	/* insert our name */
@@ -922,7 +928,7 @@ out:
 	BUG_ON(ret);
 
 out_nowrite:
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	iput(dir);
 	iput(inode);
 	return 0;
@@ -960,8 +966,9 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 	unsigned long ptr;
 	unsigned long ptr_end;
 	int name_len;
+	u64 ino = btrfs_ino(inode);
 
-	key.objectid = inode->i_ino;
+	key.objectid = ino;
 	key.type = BTRFS_INODE_REF_KEY;
 	key.offset = (u64)-1;
 
@@ -980,7 +987,7 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 		}
 		btrfs_item_key_to_cpu(path->nodes[0], &key,
 				      path->slots[0]);
-		if (key.objectid != inode->i_ino ||
+		if (key.objectid != ino ||
 		    key.type != BTRFS_INODE_REF_KEY)
 			break;
 		ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
@@ -999,9 +1006,9 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 		if (key.offset == 0)
 			break;
 		key.offset--;
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 	}
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	if (nlink != inode->i_nlink) {
 		inode->i_nlink = nlink;
 		btrfs_update_inode(trans, root, inode);
@@ -1011,10 +1018,10 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 	if (inode->i_nlink == 0) {
 		if (S_ISDIR(inode->i_mode)) {
 			ret = replay_dir_deletes(trans, root, NULL, path,
-						 inode->i_ino, 1);
+						 ino, 1);
 			BUG_ON(ret);
 		}
-		ret = insert_orphan_item(trans, root, inode->i_ino);
+		ret = insert_orphan_item(trans, root, ino);
 		BUG_ON(ret);
 	}
 	btrfs_free_path(path);
@@ -1050,11 +1057,13 @@ static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans,
 			break;
 
 		ret = btrfs_del_item(trans, root, path);
-		BUG_ON(ret);
+		if (ret)
+			goto out;
 
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		inode = read_one_inode(root, key.offset);
-		BUG_ON(!inode);
+		if (!inode)
+			return -EIO;
 
 		ret = fixup_inode_link_count(trans, root, inode);
 		BUG_ON(ret);
@@ -1068,8 +1077,10 @@ static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans,
 		 */
 		key.offset = (u64)-1;
 	}
-	btrfs_release_path(root, path);
-	return 0;
+	ret = 0;
+out:
+	btrfs_release_path(path);
+	return ret;
 }
 
 
@@ -1088,7 +1099,8 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans,
 	struct inode *inode;
 
 	inode = read_one_inode(root, objectid);
-	BUG_ON(!inode);
+	if (!inode)
+		return -EIO;
 
 	key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID;
 	btrfs_set_key_type(&key, BTRFS_ORPHAN_ITEM_KEY);
@@ -1096,7 +1108,7 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
 
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	if (ret == 0) {
 		btrfs_inc_nlink(inode);
 		btrfs_update_inode(trans, root, inode);
@@ -1175,7 +1187,8 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
 	int ret;
 
 	dir = read_one_inode(root, key->objectid);
-	BUG_ON(!dir);
+	if (!dir)
+		return -EIO;
 
 	name_len = btrfs_dir_name_len(eb, di);
 	name = kmalloc(name_len, GFP_NOFS);
@@ -1192,7 +1205,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
 		exists = 1;
 	else
 		exists = 0;
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	if (key->type == BTRFS_DIR_ITEM_KEY) {
 		dst_di = btrfs_lookup_dir_item(trans, root, path, key->objectid,
@@ -1205,7 +1218,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
 	} else {
 		BUG();
 	}
-	if (!dst_di || IS_ERR(dst_di)) {
+	if (IS_ERR_OR_NULL(dst_di)) {
 		/* we need a sequence number to insert, so we only
 		 * do inserts for the BTRFS_DIR_INDEX_KEY types
 		 */
@@ -1236,13 +1249,13 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
 	if (key->type == BTRFS_DIR_INDEX_KEY)
 		goto insert;
 out:
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	kfree(name);
 	iput(dir);
 	return 0;
 
 insert:
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	ret = insert_one_name(trans, root, path, key->objectid, key->offset,
 			      name, name_len, log_type, &log_key);
 
@@ -1363,7 +1376,7 @@ next:
 	*end_ret = found_end;
 	ret = 0;
 out:
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	return ret;
 }
 
@@ -1426,12 +1439,15 @@ again:
 						     dir_key->offset,
 						     name, name_len, 0);
 		}
-		if (!log_di || IS_ERR(log_di)) {
+		if (IS_ERR_OR_NULL(log_di)) {
 			btrfs_dir_item_key_to_cpu(eb, di, &location);
-			btrfs_release_path(root, path);
-			btrfs_release_path(log, log_path);
+			btrfs_release_path(path);
+			btrfs_release_path(log_path);
 			inode = read_one_inode(root, location.objectid);
-			BUG_ON(!inode);
+			if (!inode) {
+				kfree(name);
+				return -EIO;
+			}
 
 			ret = link_to_fixup_dir(trans, root,
 						path, location.objectid);
@@ -1453,7 +1469,7 @@ again:
 			ret = 0;
 			goto out;
 		}
-		btrfs_release_path(log, log_path);
+		btrfs_release_path(log_path);
 		kfree(name);
 
 		ptr = (unsigned long)(di + 1);
@@ -1461,8 +1477,8 @@ again:
 	}
 	ret = 0;
 out:
-	btrfs_release_path(root, path);
-	btrfs_release_path(log, log_path);
+	btrfs_release_path(path);
+	btrfs_release_path(log_path);
 	return ret;
 }
 
@@ -1550,7 +1566,7 @@ again:
 				break;
 			dir_key.offset = found_key.offset + 1;
 		}
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		if (range_end == (u64)-1)
 			break;
 		range_start = range_end + 1;
@@ -1561,11 +1577,11 @@ next_type:
 	if (key_type == BTRFS_DIR_LOG_ITEM_KEY) {
 		key_type = BTRFS_DIR_LOG_INDEX_KEY;
 		dir_key.type = BTRFS_DIR_INDEX_KEY;
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		goto again;
 	}
 out:
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	btrfs_free_path(log_path);
 	iput(dir);
 	return ret;
@@ -2093,7 +2109,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	 * the running transaction open, so a full commit can't hop
 	 * in and cause problems either.
 	 */
+	btrfs_scrub_pause_super(root);
 	write_ctree_super(trans, root->fs_info->tree_root, 1);
+	btrfs_scrub_continue_super(root);
 	ret = 0;
 
 	mutex_lock(&root->log_mutex);
@@ -2197,6 +2215,7 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 	int ret;
 	int err = 0;
 	int bytes_del = 0;
+	u64 dir_ino = btrfs_ino(dir);
 
 	if (BTRFS_I(dir)->logged_trans < trans->transid)
 		return 0;
@@ -2214,7 +2233,7 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 		goto out_unlock;
 	}
 
-	di = btrfs_lookup_dir_item(trans, log, path, dir->i_ino,
+	di = btrfs_lookup_dir_item(trans, log, path, dir_ino,
 				   name, name_len, -1);
 	if (IS_ERR(di)) {
 		err = PTR_ERR(di);
@@ -2225,8 +2244,8 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 		bytes_del += name_len;
 		BUG_ON(ret);
 	}
-	btrfs_release_path(log, path);
-	di = btrfs_lookup_dir_index_item(trans, log, path, dir->i_ino,
+	btrfs_release_path(path);
+	di = btrfs_lookup_dir_index_item(trans, log, path, dir_ino,
 					 index, name, name_len, -1);
 	if (IS_ERR(di)) {
 		err = PTR_ERR(di);
@@ -2244,10 +2263,10 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 	if (bytes_del) {
 		struct btrfs_key key;
 
-		key.objectid = dir->i_ino;
+		key.objectid = dir_ino;
 		key.offset = 0;
 		key.type = BTRFS_INODE_ITEM_KEY;
-		btrfs_release_path(log, path);
+		btrfs_release_path(path);
 
 		ret = btrfs_search_slot(trans, log, &key, path, 0, 1);
 		if (ret < 0) {
@@ -2269,7 +2288,7 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 			btrfs_mark_buffer_dirty(path->nodes[0]);
 		} else
 			ret = 0;
-		btrfs_release_path(log, path);
+		btrfs_release_path(path);
 	}
 fail:
 	btrfs_free_path(path);
@@ -2303,7 +2322,7 @@ int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
 	log = root->log_root;
 	mutex_lock(&BTRFS_I(inode)->log_mutex);
 
-	ret = btrfs_del_inode_ref(trans, log, name, name_len, inode->i_ino,
+	ret = btrfs_del_inode_ref(trans, log, name, name_len, btrfs_ino(inode),
 				  dirid, &index);
 	mutex_unlock(&BTRFS_I(inode)->log_mutex);
 	if (ret == -ENOSPC) {
@@ -2344,7 +2363,7 @@ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans,
 			      struct btrfs_dir_log_item);
 	btrfs_set_dir_log_end(path->nodes[0], item, last_offset);
 	btrfs_mark_buffer_dirty(path->nodes[0]);
-	btrfs_release_path(log, path);
+	btrfs_release_path(path);
 	return 0;
 }
 
@@ -2369,13 +2388,14 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 	int nritems;
 	u64 first_offset = min_offset;
 	u64 last_offset = (u64)-1;
+	u64 ino = btrfs_ino(inode);
 
 	log = root->log_root;
-	max_key.objectid = inode->i_ino;
+	max_key.objectid = ino;
 	max_key.offset = (u64)-1;
 	max_key.type = key_type;
 
-	min_key.objectid = inode->i_ino;
+	min_key.objectid = ino;
 	min_key.type = key_type;
 	min_key.offset = min_offset;
 
@@ -2388,18 +2408,17 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 	 * we didn't find anything from this transaction, see if there
 	 * is anything at all
 	 */
-	if (ret != 0 || min_key.objectid != inode->i_ino ||
-	    min_key.type != key_type) {
-		min_key.objectid = inode->i_ino;
+	if (ret != 0 || min_key.objectid != ino || min_key.type != key_type) {
+		min_key.objectid = ino;
 		min_key.type = key_type;
 		min_key.offset = (u64)-1;
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
 		if (ret < 0) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			return ret;
 		}
-		ret = btrfs_previous_item(root, path, inode->i_ino, key_type);
+		ret = btrfs_previous_item(root, path, ino, key_type);
 
 		/* if ret == 0 there are items for this type,
 		 * create a range to tell us the last key of this type.
@@ -2417,7 +2436,7 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 	}
 
 	/* go backward to find any previous key */
-	ret = btrfs_previous_item(root, path, inode->i_ino, key_type);
+	ret = btrfs_previous_item(root, path, ino, key_type);
 	if (ret == 0) {
 		struct btrfs_key tmp;
 		btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]);
@@ -2432,7 +2451,7 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 			}
 		}
 	}
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	/* find the first key from this transaction again */
 	ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
@@ -2452,8 +2471,7 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 		for (i = path->slots[0]; i < nritems; i++) {
 			btrfs_item_key_to_cpu(src, &min_key, i);
 
-			if (min_key.objectid != inode->i_ino ||
-			    min_key.type != key_type)
+			if (min_key.objectid != ino || min_key.type != key_type)
 				goto done;
 			ret = overwrite_item(trans, log, dst_path, src, i,
 					     &min_key);
@@ -2474,7 +2492,7 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 			goto done;
 		}
 		btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]);
-		if (tmp.objectid != inode->i_ino || tmp.type != key_type) {
+		if (tmp.objectid != ino || tmp.type != key_type) {
 			last_offset = (u64)-1;
 			goto done;
 		}
@@ -2490,8 +2508,8 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 		}
 	}
 done:
-	btrfs_release_path(root, path);
-	btrfs_release_path(log, dst_path);
+	btrfs_release_path(path);
+	btrfs_release_path(dst_path);
 
 	if (err == 0) {
 		*last_offset_ret = last_offset;
@@ -2500,8 +2518,7 @@ done:
 		 * is valid
 		 */
 		ret = insert_dir_log_key(trans, log, path, key_type,
-					 inode->i_ino, first_offset,
-					 last_offset);
+					 ino, first_offset, last_offset);
 		if (ret)
 			err = ret;
 	}
@@ -2587,10 +2604,11 @@ static int drop_objectid_items(struct btrfs_trans_handle *trans,
 			break;
 
 		ret = btrfs_del_item(trans, log, path);
-		BUG_ON(ret);
-		btrfs_release_path(log, path);
+		if (ret)
+			break;
+		btrfs_release_path(path);
 	}
-	btrfs_release_path(log, path);
+	btrfs_release_path(path);
 	return ret;
 }
 
@@ -2665,6 +2683,9 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 			extent = btrfs_item_ptr(src, start_slot + i,
 						struct btrfs_file_extent_item);
 
+			if (btrfs_file_extent_generation(src, extent) < trans->transid)
+				continue;
+
 			found_type = btrfs_file_extent_type(src, extent);
 			if (found_type == BTRFS_FILE_EXTENT_REG ||
 			    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
@@ -2689,14 +2710,14 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 				ret = btrfs_lookup_csums_range(
 						log->fs_info->csum_root,
 						ds + cs, ds + cs + cl - 1,
-						&ordered_sums);
+						&ordered_sums, 0);
 				BUG_ON(ret);
 			}
 		}
 	}
 
 	btrfs_mark_buffer_dirty(dst_path->nodes[0]);
-	btrfs_release_path(log, dst_path);
+	btrfs_release_path(dst_path);
 	kfree(ins_data);
 
 	/*
@@ -2745,6 +2766,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	int nritems;
 	int ins_start_slot = 0;
 	int ins_nr;
+	u64 ino = btrfs_ino(inode);
 
 	log = root->log_root;
 
@@ -2757,11 +2779,11 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 	}
 
-	min_key.objectid = inode->i_ino;
+	min_key.objectid = ino;
 	min_key.type = BTRFS_INODE_ITEM_KEY;
 	min_key.offset = 0;
 
-	max_key.objectid = inode->i_ino;
+	max_key.objectid = ino;
 
 	/* today the code can only do partial logging of directories */
 	if (!S_ISDIR(inode->i_mode))
@@ -2773,6 +2795,13 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 		max_key.type = (u8)-1;
 	max_key.offset = (u64)-1;
 
+	ret = btrfs_commit_inode_delayed_items(trans, inode);
+	if (ret) {
+		btrfs_free_path(path);
+		btrfs_free_path(dst_path);
+		return ret;
+	}
+
 	mutex_lock(&BTRFS_I(inode)->log_mutex);
 
 	/*
@@ -2784,8 +2813,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 
 		if (inode_only == LOG_INODE_EXISTS)
 			max_key_type = BTRFS_XATTR_ITEM_KEY;
-		ret = drop_objectid_items(trans, log, path,
-					  inode->i_ino, max_key_type);
+		ret = drop_objectid_items(trans, log, path, ino, max_key_type);
 	} else {
 		ret = btrfs_truncate_inode_items(trans, log, inode, 0, 0);
 	}
@@ -2803,7 +2831,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			break;
 again:
 		/* note, ins_nr might be > 0 here, cleanup outside the loop */
-		if (min_key.objectid != inode->i_ino)
+		if (min_key.objectid != ino)
 			break;
 		if (min_key.type > max_key.type)
 			break;
@@ -2845,7 +2873,7 @@ next_slot:
 			}
 			ins_nr = 0;
 		}
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 
 		if (min_key.offset < (u64)-1)
 			min_key.offset++;
@@ -2868,8 +2896,8 @@ next_slot:
 	}
 	WARN_ON(ins_nr);
 	if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->i_mode)) {
-		btrfs_release_path(root, path);
-		btrfs_release_path(log, dst_path);
+		btrfs_release_path(path);
+		btrfs_release_path(dst_path);
 		ret = log_directory_changes(trans, root, inode, path, dst_path);
 		if (ret) {
 			err = ret;
@@ -3136,7 +3164,7 @@ again:
 		}
 		btrfs_item_key_to_cpu(path->nodes[0], &found_key,
 				      path->slots[0]);
-		btrfs_release_path(log_root_tree, path);
+		btrfs_release_path(path);
 		if (found_key.objectid != BTRFS_TREE_LOG_OBJECTID)
 			break;
 
@@ -3149,7 +3177,7 @@ again:
 		tmp_key.offset = (u64)-1;
 
 		wc.replay_dest = btrfs_read_fs_root_no_name(fs_info, &tmp_key);
-		BUG_ON(!wc.replay_dest);
+		BUG_ON(IS_ERR_OR_NULL(wc.replay_dest));
 
 		wc.replay_dest->log_root = log;
 		btrfs_record_root_in_trans(trans, wc.replay_dest);
@@ -3171,7 +3199,7 @@ again:
 		if (found_key.offset == 0)
 			break;
 	}
-	btrfs_release_path(log_root_tree, path);
+	btrfs_release_path(path);
 
 	/* step one is to pin it all, step two is to replay just inodes */
 	if (wc.pin) {
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index 3dfae84c8cc8..2270ac58d746 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -38,7 +38,6 @@ int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root,
 			       const char *name, int name_len,
 			       struct inode *inode, u64 dirid);
-int btrfs_join_running_log_trans(struct btrfs_root *root);
 int btrfs_end_log_trans(struct btrfs_root *root);
 int btrfs_pin_log_trans(struct btrfs_root *root);
 int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/version.sh b/fs/btrfs/version.sh
deleted file mode 100644
index 1ca1952fd917..000000000000
--- a/fs/btrfs/version.sh
+++ /dev/null
@@ -1,43 +0,0 @@
-#!/bin/bash
-#
-# determine-version -- report a useful version for releases
-#
-# Copyright 2008, Aron Griffis <agriffis@n01se.net>
-# Copyright 2008, Oracle
-# Released under the GNU GPLv2
- 
-v="v0.16"
-
-which git &> /dev/null
-if [ $? == 0 ]; then
-    git branch >& /dev/null
-    if [ $? == 0 ]; then
-	    if head=`git rev-parse --verify HEAD 2>/dev/null`; then
-		if tag=`git describe --tags 2>/dev/null`; then
-		    v="$tag"
-		fi
-
-		# Are there uncommitted changes?
-		git update-index --refresh --unmerged > /dev/null
-		if git diff-index --name-only HEAD | \
-		    grep -v "^scripts/package" \
-		    | read dummy; then
-		    v="$v"-dirty
-		fi
-	    fi
-    fi
-fi
- 
-echo "#ifndef __BUILD_VERSION" > .build-version.h
-echo "#define __BUILD_VERSION" >> .build-version.h
-echo "#define BTRFS_BUILD_VERSION \"Btrfs $v\"" >> .build-version.h
-echo "#endif" >> .build-version.h
-
-diff -q version.h .build-version.h >& /dev/null
-
-if [ $? == 0 ]; then
-    rm .build-version.h
-    exit 0
-fi
-
-mv .build-version.h version.h
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c7367ae5a3e6..1efa56e18f9b 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -38,22 +38,9 @@ static int init_first_rw_device(struct btrfs_trans_handle *trans,
 				struct btrfs_device *device);
 static int btrfs_relocate_sys_chunks(struct btrfs_root *root);
 
-#define map_lookup_size(n) (sizeof(struct map_lookup) + \
-			    (sizeof(struct btrfs_bio_stripe) * (n)))
-
 static DEFINE_MUTEX(uuid_mutex);
 static LIST_HEAD(fs_uuids);
 
-void btrfs_lock_volumes(void)
-{
-	mutex_lock(&uuid_mutex);
-}
-
-void btrfs_unlock_volumes(void)
-{
-	mutex_unlock(&uuid_mutex);
-}
-
 static void lock_chunks(struct btrfs_root *root)
 {
 	mutex_lock(&root->fs_info->chunk_mutex);
@@ -363,7 +350,7 @@ static noinline int device_list_add(const char *path,
 		INIT_LIST_HEAD(&device->dev_alloc_list);
 
 		mutex_lock(&fs_devices->device_list_mutex);
-		list_add(&device->dev_list, &fs_devices->devices);
+		list_add_rcu(&device->dev_list, &fs_devices->devices);
 		mutex_unlock(&fs_devices->device_list_mutex);
 
 		device->fs_devices = fs_devices;
@@ -406,7 +393,7 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 	fs_devices->latest_trans = orig->latest_trans;
 	memcpy(fs_devices->fsid, orig->fsid, sizeof(fs_devices->fsid));
 
-	mutex_lock(&orig->device_list_mutex);
+	/* We have held the volume lock, it is safe to get the devices. */
 	list_for_each_entry(orig_dev, &orig->devices, dev_list) {
 		device = kzalloc(sizeof(*device), GFP_NOFS);
 		if (!device)
@@ -429,10 +416,8 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 		device->fs_devices = fs_devices;
 		fs_devices->num_devices++;
 	}
-	mutex_unlock(&orig->device_list_mutex);
 	return fs_devices;
 error:
-	mutex_unlock(&orig->device_list_mutex);
 	free_fs_devices(fs_devices);
 	return ERR_PTR(-ENOMEM);
 }
@@ -443,7 +428,7 @@ int btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices)
 
 	mutex_lock(&uuid_mutex);
 again:
-	mutex_lock(&fs_devices->device_list_mutex);
+	/* This is the initialized path, it is safe to release the devices. */
 	list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) {
 		if (device->in_fs_metadata)
 			continue;
@@ -463,7 +448,6 @@ again:
 		kfree(device->name);
 		kfree(device);
 	}
-	mutex_unlock(&fs_devices->device_list_mutex);
 
 	if (fs_devices->seed) {
 		fs_devices = fs_devices->seed;
@@ -474,6 +458,29 @@ again:
 	return 0;
 }
 
+static void __free_device(struct work_struct *work)
+{
+	struct btrfs_device *device;
+
+	device = container_of(work, struct btrfs_device, rcu_work);
+
+	if (device->bdev)
+		blkdev_put(device->bdev, device->mode);
+
+	kfree(device->name);
+	kfree(device);
+}
+
+static void free_device(struct rcu_head *head)
+{
+	struct btrfs_device *device;
+
+	device = container_of(head, struct btrfs_device, rcu);
+
+	INIT_WORK(&device->rcu_work, __free_device);
+	schedule_work(&device->rcu_work);
+}
+
 static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 {
 	struct btrfs_device *device;
@@ -481,20 +488,32 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 	if (--fs_devices->opened > 0)
 		return 0;
 
+	mutex_lock(&fs_devices->device_list_mutex);
 	list_for_each_entry(device, &fs_devices->devices, dev_list) {
-		if (device->bdev) {
-			blkdev_put(device->bdev, device->mode);
+		struct btrfs_device *new_device;
+
+		if (device->bdev)
 			fs_devices->open_devices--;
-		}
+
 		if (device->writeable) {
 			list_del_init(&device->dev_alloc_list);
 			fs_devices->rw_devices--;
 		}
 
-		device->bdev = NULL;
-		device->writeable = 0;
-		device->in_fs_metadata = 0;
+		new_device = kmalloc(sizeof(*new_device), GFP_NOFS);
+		BUG_ON(!new_device);
+		memcpy(new_device, device, sizeof(*new_device));
+		new_device->name = kstrdup(device->name, GFP_NOFS);
+		BUG_ON(device->name && !new_device->name);
+		new_device->bdev = NULL;
+		new_device->writeable = 0;
+		new_device->in_fs_metadata = 0;
+		list_replace_rcu(&device->dev_list, &new_device->dev_list);
+
+		call_rcu(&device->rcu, free_device);
 	}
+	mutex_unlock(&fs_devices->device_list_mutex);
+
 	WARN_ON(fs_devices->open_devices);
 	WARN_ON(fs_devices->rw_devices);
 	fs_devices->opened = 0;
@@ -597,6 +616,7 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 			list_add(&device->dev_alloc_list,
 				 &fs_devices->alloc_list);
 		}
+		brelse(bh);
 		continue;
 
 error_brelse:
@@ -669,12 +689,8 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	transid = btrfs_super_generation(disk_super);
 	if (disk_super->label[0])
 		printk(KERN_INFO "device label %s ", disk_super->label);
-	else {
-		/* FIXME, make a readl uuid parser */
-		printk(KERN_INFO "device fsid %llx-%llx ",
-		       *(unsigned long long *)disk_super->fsid,
-		       *(unsigned long long *)(disk_super->fsid + 8));
-	}
+	else
+		printk(KERN_INFO "device fsid %pU ", disk_super->fsid);
 	printk(KERN_CONT "devid %llu transid %llu %s\n",
 	       (unsigned long long)devid, (unsigned long long)transid, path);
 	ret = device_list_add(path, disk_super, devid, fs_devices_ret);
@@ -815,10 +831,7 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans,
 	/* we don't want to overwrite the superblock on the drive,
 	 * so we make sure to start at an offset of at least 1MB
 	 */
-	search_start = 1024 * 1024;
-
-	if (root->fs_info->alloc_start + num_bytes <= search_end)
-		search_start = max(root->fs_info->alloc_start, search_start);
+	search_start = max(root->fs_info->alloc_start, 1024ull * 1024);
 
 	max_hole_start = search_start;
 	max_hole_size = 0;
@@ -949,14 +962,14 @@ static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans,
 	if (ret > 0) {
 		ret = btrfs_previous_item(root, path, key.objectid,
 					  BTRFS_DEV_EXTENT_KEY);
-		BUG_ON(ret);
+		if (ret)
+			goto out;
 		leaf = path->nodes[0];
 		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
 		extent = btrfs_item_ptr(leaf, path->slots[0],
 					struct btrfs_dev_extent);
 		BUG_ON(found_key.offset > start || found_key.offset +
 		       btrfs_dev_extent_length(leaf, extent) < start);
-		ret = 0;
 	} else if (ret == 0) {
 		leaf = path->nodes[0];
 		extent = btrfs_item_ptr(leaf, path->slots[0],
@@ -967,8 +980,8 @@ static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans,
 	if (device->bytes_used > 0)
 		device->bytes_used -= btrfs_dev_extent_length(leaf, extent);
 	ret = btrfs_del_item(trans, root, path);
-	BUG_ON(ret);
 
+out:
 	btrfs_free_path(path);
 	return ret;
 }
@@ -1203,11 +1216,13 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	struct block_device *bdev;
 	struct buffer_head *bh = NULL;
 	struct btrfs_super_block *disk_super;
+	struct btrfs_fs_devices *cur_devices;
 	u64 all_avail;
 	u64 devid;
 	u64 num_devices;
 	u8 *dev_uuid;
 	int ret = 0;
+	bool clear_super = false;
 
 	mutex_lock(&uuid_mutex);
 	mutex_lock(&root->fs_info->volume_mutex);
@@ -1238,14 +1253,16 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 
 		device = NULL;
 		devices = &root->fs_info->fs_devices->devices;
-		mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
+		/*
+		 * It is safe to read the devices since the volume_mutex
+		 * is held.
+		 */
 		list_for_each_entry(tmp, devices, dev_list) {
 			if (tmp->in_fs_metadata && !tmp->bdev) {
 				device = tmp;
 				break;
 			}
 		}
-		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 		bdev = NULL;
 		bh = NULL;
 		disk_super = NULL;
@@ -1287,8 +1304,11 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	}
 
 	if (device->writeable) {
+		lock_chunks(root);
 		list_del_init(&device->dev_alloc_list);
+		unlock_chunks(root);
 		root->fs_info->fs_devices->rw_devices--;
+		clear_super = true;
 	}
 
 	ret = btrfs_shrink_device(device, 0);
@@ -1300,15 +1320,17 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		goto error_undo;
 
 	device->in_fs_metadata = 0;
+	btrfs_scrub_cancel_dev(root, device);
 
 	/*
 	 * the device list mutex makes sure that we don't change
 	 * the device list while someone else is writing out all
 	 * the device supers.
 	 */
+
+	cur_devices = device->fs_devices;
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
-	list_del_init(&device->dev_list);
-	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+	list_del_rcu(&device->dev_list);
 
 	device->fs_devices->num_devices--;
 
@@ -1322,34 +1344,36 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	if (device->bdev == root->fs_info->fs_devices->latest_bdev)
 		root->fs_info->fs_devices->latest_bdev = next_device->bdev;
 
-	if (device->bdev) {
-		blkdev_put(device->bdev, device->mode);
-		device->bdev = NULL;
+	if (device->bdev)
 		device->fs_devices->open_devices--;
-	}
+
+	call_rcu(&device->rcu, free_device);
+	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 
 	num_devices = btrfs_super_num_devices(&root->fs_info->super_copy) - 1;
 	btrfs_set_super_num_devices(&root->fs_info->super_copy, num_devices);
 
-	if (device->fs_devices->open_devices == 0) {
+	if (cur_devices->open_devices == 0) {
 		struct btrfs_fs_devices *fs_devices;
 		fs_devices = root->fs_info->fs_devices;
 		while (fs_devices) {
-			if (fs_devices->seed == device->fs_devices)
+			if (fs_devices->seed == cur_devices)
 				break;
 			fs_devices = fs_devices->seed;
 		}
-		fs_devices->seed = device->fs_devices->seed;
-		device->fs_devices->seed = NULL;
-		__btrfs_close_devices(device->fs_devices);
-		free_fs_devices(device->fs_devices);
+		fs_devices->seed = cur_devices->seed;
+		cur_devices->seed = NULL;
+		lock_chunks(root);
+		__btrfs_close_devices(cur_devices);
+		unlock_chunks(root);
+		free_fs_devices(cur_devices);
 	}
 
 	/*
 	 * at this point, the device is zero sized.  We want to
 	 * remove it from the devices list and zero out the old super
 	 */
-	if (device->writeable) {
+	if (clear_super) {
 		/* make sure this device isn't detected as part of
 		 * the FS anymore
 		 */
@@ -1358,8 +1382,6 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		sync_dirty_buffer(bh);
 	}
 
-	kfree(device->name);
-	kfree(device);
 	ret = 0;
 
 error_brelse:
@@ -1373,8 +1395,10 @@ out:
 	return ret;
 error_undo:
 	if (device->writeable) {
+		lock_chunks(root);
 		list_add(&device->dev_alloc_list,
 			 &root->fs_info->fs_devices->alloc_list);
+		unlock_chunks(root);
 		root->fs_info->fs_devices->rw_devices++;
 	}
 	goto error_brelse;
@@ -1414,7 +1438,12 @@ static int btrfs_prepare_sprout(struct btrfs_trans_handle *trans,
 	INIT_LIST_HEAD(&seed_devices->devices);
 	INIT_LIST_HEAD(&seed_devices->alloc_list);
 	mutex_init(&seed_devices->device_list_mutex);
-	list_splice_init(&fs_devices->devices, &seed_devices->devices);
+
+	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
+	list_splice_init_rcu(&fs_devices->devices, &seed_devices->devices,
+			      synchronize_rcu);
+	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+
 	list_splice_init(&fs_devices->alloc_list, &seed_devices->alloc_list);
 	list_for_each_entry(device, &seed_devices->devices, dev_list) {
 		device->fs_devices = seed_devices;
@@ -1475,7 +1504,7 @@ next_slot:
 				goto error;
 			leaf = path->nodes[0];
 			btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			continue;
 		}
 
@@ -1611,7 +1640,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	 * half setup
 	 */
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
-	list_add(&device->dev_list, &root->fs_info->fs_devices->devices);
+	list_add_rcu(&device->dev_list, &root->fs_info->fs_devices->devices);
 	list_add(&device->dev_alloc_list,
 		 &root->fs_info->fs_devices->alloc_list);
 	root->fs_info->fs_devices->num_devices++;
@@ -1769,10 +1798,9 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans,
 	BUG_ON(ret);
 
 	ret = btrfs_del_item(trans, root, path);
-	BUG_ON(ret);
 
 	btrfs_free_path(path);
-	return 0;
+	return ret;
 }
 
 static int btrfs_del_sys_chunk(struct btrfs_root *root, u64 chunk_objectid, u64
@@ -1947,7 +1975,7 @@ again:
 		chunk = btrfs_item_ptr(leaf, path->slots[0],
 				       struct btrfs_chunk);
 		chunk_type = btrfs_chunk_type(leaf, chunk);
-		btrfs_release_path(chunk_root, path);
+		btrfs_release_path(path);
 
 		if (chunk_type & BTRFS_BLOCK_GROUP_SYSTEM) {
 			ret = btrfs_relocate_chunk(chunk_root, chunk_tree,
@@ -2065,7 +2093,7 @@ int btrfs_balance(struct btrfs_root *dev_root)
 		if (found_key.offset == 0)
 			break;
 
-		btrfs_release_path(chunk_root, path);
+		btrfs_release_path(path);
 		ret = btrfs_relocate_chunk(chunk_root,
 					   chunk_root->root_key.objectid,
 					   found_key.objectid,
@@ -2137,7 +2165,7 @@ again:
 			goto done;
 		if (ret) {
 			ret = 0;
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			break;
 		}
 
@@ -2146,7 +2174,7 @@ again:
 		btrfs_item_key_to_cpu(l, &key, path->slots[0]);
 
 		if (key.objectid != device->devid) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			break;
 		}
 
@@ -2154,14 +2182,14 @@ again:
 		length = btrfs_dev_extent_length(l, dev_extent);
 
 		if (key.offset + length <= new_size) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			break;
 		}
 
 		chunk_tree = btrfs_dev_extent_chunk_tree(l, dev_extent);
 		chunk_objectid = btrfs_dev_extent_chunk_objectid(l, dev_extent);
 		chunk_offset = btrfs_dev_extent_chunk_offset(l, dev_extent);
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 
 		ret = btrfs_relocate_chunk(root, chunk_tree, chunk_objectid,
 					   chunk_offset);
@@ -2237,275 +2265,204 @@ static int btrfs_add_system_chunk(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
-static noinline u64 chunk_bytes_by_type(u64 type, u64 calc_size,
-					int num_stripes, int sub_stripes)
+/*
+ * sort the devices in descending order by max_avail, total_avail
+ */
+static int btrfs_cmp_device_info(const void *a, const void *b)
 {
-	if (type & (BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_DUP))
-		return calc_size;
-	else if (type & BTRFS_BLOCK_GROUP_RAID10)
-		return calc_size * (num_stripes / sub_stripes);
-	else
-		return calc_size * num_stripes;
-}
+	const struct btrfs_device_info *di_a = a;
+	const struct btrfs_device_info *di_b = b;
 
-/* Used to sort the devices by max_avail(descending sort) */
-int btrfs_cmp_device_free_bytes(const void *dev_info1, const void *dev_info2)
-{
-	if (((struct btrfs_device_info *)dev_info1)->max_avail >
-	    ((struct btrfs_device_info *)dev_info2)->max_avail)
+	if (di_a->max_avail > di_b->max_avail)
 		return -1;
-	else if (((struct btrfs_device_info *)dev_info1)->max_avail <
-		 ((struct btrfs_device_info *)dev_info2)->max_avail)
+	if (di_a->max_avail < di_b->max_avail)
 		return 1;
-	else
-		return 0;
+	if (di_a->total_avail > di_b->total_avail)
+		return -1;
+	if (di_a->total_avail < di_b->total_avail)
+		return 1;
+	return 0;
 }
 
-static int __btrfs_calc_nstripes(struct btrfs_fs_devices *fs_devices, u64 type,
-				 int *num_stripes, int *min_stripes,
-				 int *sub_stripes)
+static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *extent_root,
+			       struct map_lookup **map_ret,
+			       u64 *num_bytes_out, u64 *stripe_size_out,
+			       u64 start, u64 type)
 {
-	*num_stripes = 1;
-	*min_stripes = 1;
-	*sub_stripes = 0;
+	struct btrfs_fs_info *info = extent_root->fs_info;
+	struct btrfs_fs_devices *fs_devices = info->fs_devices;
+	struct list_head *cur;
+	struct map_lookup *map = NULL;
+	struct extent_map_tree *em_tree;
+	struct extent_map *em;
+	struct btrfs_device_info *devices_info = NULL;
+	u64 total_avail;
+	int num_stripes;	/* total number of stripes to allocate */
+	int sub_stripes;	/* sub_stripes info for map */
+	int dev_stripes;	/* stripes per dev */
+	int devs_max;		/* max devs to use */
+	int devs_min;		/* min devs needed */
+	int devs_increment;	/* ndevs has to be a multiple of this */
+	int ncopies;		/* how many copies to data has */
+	int ret;
+	u64 max_stripe_size;
+	u64 max_chunk_size;
+	u64 stripe_size;
+	u64 num_bytes;
+	int ndevs;
+	int i;
+	int j;
 
-	if (type & (BTRFS_BLOCK_GROUP_RAID0)) {
-		*num_stripes = fs_devices->rw_devices;
-		*min_stripes = 2;
-	}
-	if (type & (BTRFS_BLOCK_GROUP_DUP)) {
-		*num_stripes = 2;
-		*min_stripes = 2;
-	}
-	if (type & (BTRFS_BLOCK_GROUP_RAID1)) {
-		if (fs_devices->rw_devices < 2)
-			return -ENOSPC;
-		*num_stripes = 2;
-		*min_stripes = 2;
-	}
-	if (type & (BTRFS_BLOCK_GROUP_RAID10)) {
-		*num_stripes = fs_devices->rw_devices;
-		if (*num_stripes < 4)
-			return -ENOSPC;
-		*num_stripes &= ~(u32)1;
-		*sub_stripes = 2;
-		*min_stripes = 4;
+	if ((type & BTRFS_BLOCK_GROUP_RAID1) &&
+	    (type & BTRFS_BLOCK_GROUP_DUP)) {
+		WARN_ON(1);
+		type &= ~BTRFS_BLOCK_GROUP_DUP;
 	}
 
-	return 0;
-}
+	if (list_empty(&fs_devices->alloc_list))
+		return -ENOSPC;
 
-static u64 __btrfs_calc_stripe_size(struct btrfs_fs_devices *fs_devices,
-				    u64 proposed_size, u64 type,
-				    int num_stripes, int small_stripe)
-{
-	int min_stripe_size = 1 * 1024 * 1024;
-	u64 calc_size = proposed_size;
-	u64 max_chunk_size = calc_size;
-	int ncopies = 1;
+	sub_stripes = 1;
+	dev_stripes = 1;
+	devs_increment = 1;
+	ncopies = 1;
+	devs_max = 0;	/* 0 == as many as possible */
+	devs_min = 1;
 
-	if (type & (BTRFS_BLOCK_GROUP_RAID1 |
-		    BTRFS_BLOCK_GROUP_DUP |
-		    BTRFS_BLOCK_GROUP_RAID10))
+	/*
+	 * define the properties of each RAID type.
+	 * FIXME: move this to a global table and use it in all RAID
+	 * calculation code
+	 */
+	if (type & (BTRFS_BLOCK_GROUP_DUP)) {
+		dev_stripes = 2;
 		ncopies = 2;
+		devs_max = 1;
+	} else if (type & (BTRFS_BLOCK_GROUP_RAID0)) {
+		devs_min = 2;
+	} else if (type & (BTRFS_BLOCK_GROUP_RAID1)) {
+		devs_increment = 2;
+		ncopies = 2;
+		devs_max = 2;
+		devs_min = 2;
+	} else if (type & (BTRFS_BLOCK_GROUP_RAID10)) {
+		sub_stripes = 2;
+		devs_increment = 2;
+		ncopies = 2;
+		devs_min = 4;
+	} else {
+		devs_max = 1;
+	}
 
 	if (type & BTRFS_BLOCK_GROUP_DATA) {
-		max_chunk_size = 10 * calc_size;
-		min_stripe_size = 64 * 1024 * 1024;
+		max_stripe_size = 1024 * 1024 * 1024;
+		max_chunk_size = 10 * max_stripe_size;
 	} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
-		max_chunk_size = 256 * 1024 * 1024;
-		min_stripe_size = 32 * 1024 * 1024;
+		max_stripe_size = 256 * 1024 * 1024;
+		max_chunk_size = max_stripe_size;
 	} else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
-		calc_size = 8 * 1024 * 1024;
-		max_chunk_size = calc_size * 2;
-		min_stripe_size = 1 * 1024 * 1024;
+		max_stripe_size = 8 * 1024 * 1024;
+		max_chunk_size = 2 * max_stripe_size;
+	} else {
+		printk(KERN_ERR "btrfs: invalid chunk type 0x%llx requested\n",
+		       type);
+		BUG_ON(1);
 	}
 
 	/* we don't want a chunk larger than 10% of writeable space */
 	max_chunk_size = min(div_factor(fs_devices->total_rw_bytes, 1),
 			     max_chunk_size);
 
-	if (calc_size * num_stripes > max_chunk_size * ncopies) {
-		calc_size = max_chunk_size * ncopies;
-		do_div(calc_size, num_stripes);
-		do_div(calc_size, BTRFS_STRIPE_LEN);
-		calc_size *= BTRFS_STRIPE_LEN;
-	}
+	devices_info = kzalloc(sizeof(*devices_info) * fs_devices->rw_devices,
+			       GFP_NOFS);
+	if (!devices_info)
+		return -ENOMEM;
 
-	/* we don't want tiny stripes */
-	if (!small_stripe)
-		calc_size = max_t(u64, min_stripe_size, calc_size);
+	cur = fs_devices->alloc_list.next;
 
 	/*
-	 * we're about to do_div by the BTRFS_STRIPE_LEN so lets make sure
-	 * we end up with something bigger than a stripe
+	 * in the first pass through the devices list, we gather information
+	 * about the available holes on each device.
 	 */
-	calc_size = max_t(u64, calc_size, BTRFS_STRIPE_LEN);
-
-	do_div(calc_size, BTRFS_STRIPE_LEN);
-	calc_size *= BTRFS_STRIPE_LEN;
-
-	return calc_size;
-}
-
-static struct map_lookup *__shrink_map_lookup_stripes(struct map_lookup *map,
-						      int num_stripes)
-{
-	struct map_lookup *new;
-	size_t len = map_lookup_size(num_stripes);
-
-	BUG_ON(map->num_stripes < num_stripes);
-
-	if (map->num_stripes == num_stripes)
-		return map;
-
-	new = kmalloc(len, GFP_NOFS);
-	if (!new) {
-		/* just change map->num_stripes */
-		map->num_stripes = num_stripes;
-		return map;
-	}
-
-	memcpy(new, map, len);
-	new->num_stripes = num_stripes;
-	kfree(map);
-	return new;
-}
+	ndevs = 0;
+	while (cur != &fs_devices->alloc_list) {
+		struct btrfs_device *device;
+		u64 max_avail;
+		u64 dev_offset;
 
-/*
- * helper to allocate device space from btrfs_device_info, in which we stored
- * max free space information of every device. It is used when we can not
- * allocate chunks by default size.
- *
- * By this helper, we can allocate a new chunk as larger as possible.
- */
-static int __btrfs_alloc_tiny_space(struct btrfs_trans_handle *trans,
-				    struct btrfs_fs_devices *fs_devices,
-				    struct btrfs_device_info *devices,
-				    int nr_device, u64 type,
-				    struct map_lookup **map_lookup,
-				    int min_stripes, u64 *stripe_size)
-{
-	int i, index, sort_again = 0;
-	int min_devices = min_stripes;
-	u64 max_avail, min_free;
-	struct map_lookup *map = *map_lookup;
-	int ret;
+		device = list_entry(cur, struct btrfs_device, dev_alloc_list);
 
-	if (nr_device < min_stripes)
-		return -ENOSPC;
+		cur = cur->next;
 
-	btrfs_descending_sort_devices(devices, nr_device);
+		if (!device->writeable) {
+			printk(KERN_ERR
+			       "btrfs: read-only device in alloc_list\n");
+			WARN_ON(1);
+			continue;
+		}
 
-	max_avail = devices[0].max_avail;
-	if (!max_avail)
-		return -ENOSPC;
+		if (!device->in_fs_metadata)
+			continue;
 
-	for (i = 0; i < nr_device; i++) {
-		/*
-		 * if dev_offset = 0, it means the free space of this device
-		 * is less than what we need, and we didn't search max avail
-		 * extent on this device, so do it now.
+		if (device->total_bytes > device->bytes_used)
+			total_avail = device->total_bytes - device->bytes_used;
+		else
+			total_avail = 0;
+		/* avail is off by max(alloc_start, 1MB), but that is the same
+		 * for all devices, so it doesn't hurt the sorting later on
 		 */
-		if (!devices[i].dev_offset) {
-			ret = find_free_dev_extent(trans, devices[i].dev,
-						   max_avail,
-						   &devices[i].dev_offset,
-						   &devices[i].max_avail);
-			if (ret != 0 && ret != -ENOSPC)
-				return ret;
-			sort_again = 1;
-		}
-	}
 
-	/* we update the max avail free extent of each devices, sort again */
-	if (sort_again)
-		btrfs_descending_sort_devices(devices, nr_device);
-
-	if (type & BTRFS_BLOCK_GROUP_DUP)
-		min_devices = 1;
+		ret = find_free_dev_extent(trans, device,
+					   max_stripe_size * dev_stripes,
+					   &dev_offset, &max_avail);
+		if (ret && ret != -ENOSPC)
+			goto error;
 
-	if (!devices[min_devices - 1].max_avail)
-		return -ENOSPC;
+		if (ret == 0)
+			max_avail = max_stripe_size * dev_stripes;
 
-	max_avail = devices[min_devices - 1].max_avail;
-	if (type & BTRFS_BLOCK_GROUP_DUP)
-		do_div(max_avail, 2);
+		if (max_avail < BTRFS_STRIPE_LEN * dev_stripes)
+			continue;
 
-	max_avail = __btrfs_calc_stripe_size(fs_devices, max_avail, type,
-					     min_stripes, 1);
-	if (type & BTRFS_BLOCK_GROUP_DUP)
-		min_free = max_avail * 2;
-	else
-		min_free = max_avail;
+		devices_info[ndevs].dev_offset = dev_offset;
+		devices_info[ndevs].max_avail = max_avail;
+		devices_info[ndevs].total_avail = total_avail;
+		devices_info[ndevs].dev = device;
+		++ndevs;
+	}
 
-	if (min_free > devices[min_devices - 1].max_avail)
-		return -ENOSPC;
+	/*
+	 * now sort the devices by hole size / available space
+	 */
+	sort(devices_info, ndevs, sizeof(struct btrfs_device_info),
+	     btrfs_cmp_device_info, NULL);
 
-	map = __shrink_map_lookup_stripes(map, min_stripes);
-	*stripe_size = max_avail;
+	/* round down to number of usable stripes */
+	ndevs -= ndevs % devs_increment;
 
-	index = 0;
-	for (i = 0; i < min_stripes; i++) {
-		map->stripes[i].dev = devices[index].dev;
-		map->stripes[i].physical = devices[index].dev_offset;
-		if (type & BTRFS_BLOCK_GROUP_DUP) {
-			i++;
-			map->stripes[i].dev = devices[index].dev;
-			map->stripes[i].physical = devices[index].dev_offset +
-						   max_avail;
-		}
-		index++;
+	if (ndevs < devs_increment * sub_stripes || ndevs < devs_min) {
+		ret = -ENOSPC;
+		goto error;
 	}
-	*map_lookup = map;
-
-	return 0;
-}
 
-static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *extent_root,
-			       struct map_lookup **map_ret,
-			       u64 *num_bytes, u64 *stripe_size,
-			       u64 start, u64 type)
-{
-	struct btrfs_fs_info *info = extent_root->fs_info;
-	struct btrfs_device *device = NULL;
-	struct btrfs_fs_devices *fs_devices = info->fs_devices;
-	struct list_head *cur;
-	struct map_lookup *map;
-	struct extent_map_tree *em_tree;
-	struct extent_map *em;
-	struct btrfs_device_info *devices_info;
-	struct list_head private_devs;
-	u64 calc_size = 1024 * 1024 * 1024;
-	u64 min_free;
-	u64 avail;
-	u64 dev_offset;
-	int num_stripes;
-	int min_stripes;
-	int sub_stripes;
-	int min_devices;	/* the min number of devices we need */
-	int i;
-	int ret;
-	int index;
+	if (devs_max && ndevs > devs_max)
+		ndevs = devs_max;
+	/*
+	 * the primary goal is to maximize the number of stripes, so use as many
+	 * devices as possible, even if the stripes are not maximum sized.
+	 */
+	stripe_size = devices_info[ndevs-1].max_avail;
+	num_stripes = ndevs * dev_stripes;
 
-	if ((type & BTRFS_BLOCK_GROUP_RAID1) &&
-	    (type & BTRFS_BLOCK_GROUP_DUP)) {
-		WARN_ON(1);
-		type &= ~BTRFS_BLOCK_GROUP_DUP;
+	if (stripe_size * num_stripes > max_chunk_size * ncopies) {
+		stripe_size = max_chunk_size * ncopies;
+		do_div(stripe_size, num_stripes);
 	}
-	if (list_empty(&fs_devices->alloc_list))
-		return -ENOSPC;
-
-	ret = __btrfs_calc_nstripes(fs_devices, type, &num_stripes,
-				    &min_stripes, &sub_stripes);
-	if (ret)
-		return ret;
 
-	devices_info = kzalloc(sizeof(*devices_info) * fs_devices->rw_devices,
-			       GFP_NOFS);
-	if (!devices_info)
-		return -ENOMEM;
+	do_div(stripe_size, dev_stripes);
+	do_div(stripe_size, BTRFS_STRIPE_LEN);
+	stripe_size *= BTRFS_STRIPE_LEN;
 
 	map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
 	if (!map) {
@@ -2514,85 +2471,12 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	}
 	map->num_stripes = num_stripes;
 
-	cur = fs_devices->alloc_list.next;
-	index = 0;
-	i = 0;
-
-	calc_size = __btrfs_calc_stripe_size(fs_devices, calc_size, type,
-					     num_stripes, 0);
-
-	if (type & BTRFS_BLOCK_GROUP_DUP) {
-		min_free = calc_size * 2;
-		min_devices = 1;
-	} else {
-		min_free = calc_size;
-		min_devices = min_stripes;
-	}
-
-	INIT_LIST_HEAD(&private_devs);
-	while (index < num_stripes) {
-		device = list_entry(cur, struct btrfs_device, dev_alloc_list);
-		BUG_ON(!device->writeable);
-		if (device->total_bytes > device->bytes_used)
-			avail = device->total_bytes - device->bytes_used;
-		else
-			avail = 0;
-		cur = cur->next;
-
-		if (device->in_fs_metadata && avail >= min_free) {
-			ret = find_free_dev_extent(trans, device, min_free,
-						   &devices_info[i].dev_offset,
-						   &devices_info[i].max_avail);
-			if (ret == 0) {
-				list_move_tail(&device->dev_alloc_list,
-					       &private_devs);
-				map->stripes[index].dev = device;
-				map->stripes[index].physical =
-						devices_info[i].dev_offset;
-				index++;
-				if (type & BTRFS_BLOCK_GROUP_DUP) {
-					map->stripes[index].dev = device;
-					map->stripes[index].physical =
-						devices_info[i].dev_offset +
-						calc_size;
-					index++;
-				}
-			} else if (ret != -ENOSPC)
-				goto error;
-
-			devices_info[i].dev = device;
-			i++;
-		} else if (device->in_fs_metadata &&
-			   avail >= BTRFS_STRIPE_LEN) {
-			devices_info[i].dev = device;
-			devices_info[i].max_avail = avail;
-			i++;
-		}
-
-		if (cur == &fs_devices->alloc_list)
-			break;
-	}
-
-	list_splice(&private_devs, &fs_devices->alloc_list);
-	if (index < num_stripes) {
-		if (index >= min_stripes) {
-			num_stripes = index;
-			if (type & (BTRFS_BLOCK_GROUP_RAID10)) {
-				num_stripes /= sub_stripes;
-				num_stripes *= sub_stripes;
-			}
-
-			map = __shrink_map_lookup_stripes(map, num_stripes);
-		} else if (i >= min_devices) {
-			ret = __btrfs_alloc_tiny_space(trans, fs_devices,
-						       devices_info, i, type,
-						       &map, min_stripes,
-						       &calc_size);
-			if (ret)
-				goto error;
-		} else {
-			ret = -ENOSPC;
-			goto error;
+	for (i = 0; i < ndevs; ++i) {
+		for (j = 0; j < dev_stripes; ++j) {
+			int s = i * dev_stripes + j;
+			map->stripes[s].dev = devices_info[i].dev;
+			map->stripes[s].physical = devices_info[i].dev_offset +
+						   j * stripe_size;
 		}
 	}
 	map->sector_size = extent_root->sectorsize;
@@ -2603,20 +2487,21 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	map->sub_stripes = sub_stripes;
 
 	*map_ret = map;
-	*stripe_size = calc_size;
-	*num_bytes = chunk_bytes_by_type(type, calc_size,
-					 map->num_stripes, sub_stripes);
+	num_bytes = stripe_size * (num_stripes / ncopies);
 
-	trace_btrfs_chunk_alloc(info->chunk_root, map, start, *num_bytes);
+	*stripe_size_out = stripe_size;
+	*num_bytes_out = num_bytes;
 
-	em = alloc_extent_map(GFP_NOFS);
+	trace_btrfs_chunk_alloc(info->chunk_root, map, start, num_bytes);
+
+	em = alloc_extent_map();
 	if (!em) {
 		ret = -ENOMEM;
 		goto error;
 	}
 	em->bdev = (struct block_device *)map;
 	em->start = start;
-	em->len = *num_bytes;
+	em->len = num_bytes;
 	em->block_start = 0;
 	em->block_len = em->len;
 
@@ -2629,20 +2514,21 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_make_block_group(trans, extent_root, 0, type,
 				     BTRFS_FIRST_CHUNK_TREE_OBJECTID,
-				     start, *num_bytes);
+				     start, num_bytes);
 	BUG_ON(ret);
 
-	index = 0;
-	while (index < map->num_stripes) {
-		device = map->stripes[index].dev;
-		dev_offset = map->stripes[index].physical;
+	for (i = 0; i < map->num_stripes; ++i) {
+		struct btrfs_device *device;
+		u64 dev_offset;
+
+		device = map->stripes[i].dev;
+		dev_offset = map->stripes[i].physical;
 
 		ret = btrfs_alloc_dev_extent(trans, device,
 				info->chunk_root->root_key.objectid,
 				BTRFS_FIRST_CHUNK_TREE_OBJECTID,
-				start, dev_offset, calc_size);
+				start, dev_offset, stripe_size);
 		BUG_ON(ret);
-		index++;
 	}
 
 	kfree(devices_info);
@@ -2849,7 +2735,7 @@ int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
 
 void btrfs_mapping_init(struct btrfs_mapping_tree *tree)
 {
-	extent_map_tree_init(&tree->map_tree, GFP_NOFS);
+	extent_map_tree_init(&tree->map_tree);
 }
 
 void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree)
@@ -3499,7 +3385,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 		free_extent_map(em);
 	}
 
-	em = alloc_extent_map(GFP_NOFS);
+	em = alloc_extent_map();
 	if (!em)
 		return -ENOMEM;
 	num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
@@ -3688,15 +3574,6 @@ static int read_one_dev(struct btrfs_root *root,
 	return ret;
 }
 
-int btrfs_read_super_device(struct btrfs_root *root, struct extent_buffer *buf)
-{
-	struct btrfs_dev_item *dev_item;
-
-	dev_item = (struct btrfs_dev_item *)offsetof(struct btrfs_super_block,
-						     dev_item);
-	return read_one_dev(root, buf, dev_item);
-}
-
 int btrfs_read_sys_array(struct btrfs_root *root)
 {
 	struct btrfs_super_block *super_copy = &root->fs_info->super_copy;
@@ -3813,7 +3690,7 @@ again:
 	}
 	if (key.objectid == BTRFS_DEV_ITEMS_OBJECTID) {
 		key.objectid = 0;
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 		goto again;
 	}
 	ret = 0;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index cc2eadaf7a27..7c12d61ae7ae 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -85,7 +85,12 @@ struct btrfs_device {
 	/* physical drive uuid (or lvm uuid) */
 	u8 uuid[BTRFS_UUID_SIZE];
 
+	/* per-device scrub information */
+	struct scrub_dev *scrub_device;
+
 	struct btrfs_work work;
+	struct rcu_head rcu;
+	struct work_struct rcu_work;
 };
 
 struct btrfs_fs_devices {
@@ -144,6 +149,7 @@ struct btrfs_device_info {
 	struct btrfs_device *dev;
 	u64 dev_offset;
 	u64 max_avail;
+	u64 total_avail;
 };
 
 struct map_lookup {
@@ -157,20 +163,8 @@ struct map_lookup {
 	struct btrfs_bio_stripe stripes[];
 };
 
-/* Used to sort the devices by max_avail(descending sort) */
-int btrfs_cmp_device_free_bytes(const void *dev_info1, const void *dev_info2);
-
-/*
- * sort the devices by max_avail, in which max free extent size of each device
- * is stored.(Descending Sort)
- */
-static inline void btrfs_descending_sort_devices(
-					struct btrfs_device_info *devices,
-					size_t nr_devices)
-{
-	sort(devices, nr_devices, sizeof(struct btrfs_device_info),
-	     btrfs_cmp_device_free_bytes, NULL);
-}
+#define map_lookup_size(n) (sizeof(struct map_lookup) + \
+			    (sizeof(struct btrfs_bio_stripe) * (n)))
 
 int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
 				   u64 end, u64 *length);
@@ -196,7 +190,6 @@ void btrfs_mapping_init(struct btrfs_mapping_tree *tree);
 void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree);
 int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 		  int mirror_num, int async_submit);
-int btrfs_read_super_device(struct btrfs_root *root, struct extent_buffer *buf);
 int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		       fmode_t flags, void *holder);
 int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
@@ -209,8 +202,6 @@ int btrfs_add_device(struct btrfs_trans_handle *trans,
 int btrfs_rm_device(struct btrfs_root *root, char *device_path);
 int btrfs_cleanup_fs_uuids(void);
 int btrfs_num_copies(struct btrfs_mapping_tree *map_tree, u64 logical, u64 len);
-int btrfs_unplug_page(struct btrfs_mapping_tree *map_tree,
-		      u64 logical, struct page *page);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,
 		      struct btrfs_device *device, u64 new_size);
 struct btrfs_device *btrfs_find_device(struct btrfs_root *root, u64 devid,
@@ -218,8 +209,6 @@ struct btrfs_device *btrfs_find_device(struct btrfs_root *root, u64 devid,
 int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
 int btrfs_init_new_device(struct btrfs_root *root, char *path);
 int btrfs_balance(struct btrfs_root *dev_root);
-void btrfs_unlock_volumes(void);
-void btrfs_lock_volumes(void);
 int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset);
 int find_free_dev_extent(struct btrfs_trans_handle *trans,
 			 struct btrfs_device *device, u64 num_bytes,
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index cfd660550ded..5366fe452ab0 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -44,7 +44,7 @@ ssize_t __btrfs_getxattr(struct inode *inode, const char *name,
 		return -ENOMEM;
 
 	/* lookup the xattr by name */
-	di = btrfs_lookup_xattr(NULL, root, path, inode->i_ino, name,
+	di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), name,
 				strlen(name), 0);
 	if (!di) {
 		ret = -ENODATA;
@@ -103,7 +103,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 
 	/* first lets see if we already have this xattr */
-	di = btrfs_lookup_xattr(trans, root, path, inode->i_ino, name,
+	di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), name,
 				strlen(name), -1);
 	if (IS_ERR(di)) {
 		ret = PTR_ERR(di);
@@ -120,13 +120,13 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 
 		ret = btrfs_delete_one_dir_name(trans, root, path, di);
 		BUG_ON(ret);
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 
 		/* if we don't have a value then we are removing the xattr */
 		if (!value)
 			goto out;
 	} else {
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 
 		if (flags & XATTR_REPLACE) {
 			/* we couldn't find the attr to replace */
@@ -136,7 +136,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 	}
 
 	/* ok we have to create a completely new xattr */
-	ret = btrfs_insert_xattr_item(trans, root, path, inode->i_ino,
+	ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode),
 				      name, name_len, value, size);
 	BUG_ON(ret);
 out:
@@ -158,8 +158,6 @@ int __btrfs_setxattr(struct btrfs_trans_handle *trans,
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	btrfs_set_trans_block_group(trans, inode);
-
 	ret = do_setxattr(trans, inode, name, value, size, flags);
 	if (ret)
 		goto out;
@@ -190,7 +188,7 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 	 * NOTE: we set key.offset = 0; because we want to start with the
 	 * first xattr that we find and walk forward
 	 */
-	key.objectid = inode->i_ino;
+	key.objectid = btrfs_ino(inode);
 	btrfs_set_key_type(&key, BTRFS_XATTR_ITEM_KEY);
 	key.offset = 0;
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 698c6b2cc462..1a80b048ade8 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1902,10 +1902,8 @@ int __block_write_begin(struct page *page, loff_t pos, unsigned len,
 		if (!buffer_uptodate(*wait_bh))
 			err = -EIO;
 	}
-	if (unlikely(err)) {
+	if (unlikely(err))
 		page_zero_new_buffers(page, from, to);
-		ClearPageUptodate(page);
-	}
 	return err;
 }
 EXPORT_SYMBOL(__block_write_begin);
@@ -2382,6 +2380,7 @@ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 		ret = -EAGAIN;
 		goto out_unlock;
 	}
+	wait_on_page_writeback(page);
 	return 0;
 out_unlock:
 	unlock_page(page);
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 33da49dc3cc6..5a3953db8118 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -453,7 +453,7 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc)
 	int err;
 	struct inode *inode = page->mapping->host;
 	BUG_ON(!inode);
-	igrab(inode);
+	ihold(inode);
 	err = writepage_nounlock(page, wbc);
 	unlock_page(page);
 	iput(inode);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 1f72b00447c4..f605753c8fe9 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2940,14 +2940,12 @@ void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc)
 	while (!list_empty(&mdsc->cap_dirty)) {
 		ci = list_first_entry(&mdsc->cap_dirty, struct ceph_inode_info,
 				      i_dirty_item);
-		inode = igrab(&ci->vfs_inode);
+		inode = &ci->vfs_inode;
+		ihold(inode);
 		dout("flush_dirty_caps %p\n", inode);
 		spin_unlock(&mdsc->cap_dirty_lock);
-		if (inode) {
-			ceph_check_caps(ci, CHECK_CAPS_NODELAY|CHECK_CAPS_FLUSH,
-					NULL);
-			iput(inode);
-		}
+		ceph_check_caps(ci, CHECK_CAPS_NODELAY|CHECK_CAPS_FLUSH, NULL);
+		iput(inode);
 		spin_lock(&mdsc->cap_dirty_lock);
 	}
 	spin_unlock(&mdsc->cap_dirty_lock);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 33729e822bb9..ef8f08c343e8 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -308,7 +308,8 @@ more:
 		req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
 		if (IS_ERR(req))
 			return PTR_ERR(req);
-		req->r_inode = igrab(inode);
+		req->r_inode = inode;
+		ihold(inode);
 		req->r_dentry = dget(filp->f_dentry);
 		/* hints to request -> mds selection code */
 		req->r_direct_mode = USE_AUTH_MDS;
@@ -787,10 +788,12 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
 	err = ceph_mdsc_do_request(mdsc, dir, req);
-	if (err)
+	if (err) {
 		d_drop(dentry);
-	else if (!req->r_reply_info.head->is_dentry)
-		d_instantiate(dentry, igrab(old_dentry->d_inode));
+	} else if (!req->r_reply_info.head->is_dentry) {
+		ihold(old_dentry->d_inode);
+		d_instantiate(dentry, old_dentry->d_inode);
+	}
 	ceph_mdsc_put_request(req);
 	return err;
 }
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index a610d3d67488..f67b687550de 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -109,7 +109,7 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
 		err = ceph_mdsc_do_request(mdsc, NULL, req);
 		inode = req->r_target_inode;
 		if (inode)
-			igrab(inode);
+			ihold(inode);
 		ceph_mdsc_put_request(req);
 		if (!inode)
 			return ERR_PTR(-ESTALE);
@@ -167,7 +167,7 @@ static struct dentry *__cfh_to_dentry(struct super_block *sb,
 		err = ceph_mdsc_do_request(mdsc, NULL, req);
 		inode = req->r_target_inode;
 		if (inode)
-			igrab(inode);
+			ihold(inode);
 		ceph_mdsc_put_request(req);
 		if (!inode)
 			return ERR_PTR(err ? err : -ESTALE);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 203252d88d9f..9542f07d0b93 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -191,7 +191,8 @@ int ceph_open(struct inode *inode, struct file *file)
 		err = PTR_ERR(req);
 		goto out;
 	}
-	req->r_inode = igrab(inode);
+	req->r_inode = inode;
+	ihold(inode);
 	req->r_num_caps = 1;
 	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
 	if (!err)
@@ -282,7 +283,7 @@ int ceph_release(struct inode *inode, struct file *file)
 static int striped_read(struct inode *inode,
 			u64 off, u64 len,
 			struct page **pages, int num_pages,
-			int *checkeof, bool align_to_pages,
+			int *checkeof, bool o_direct,
 			unsigned long buf_align)
 {
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
@@ -307,7 +308,7 @@ static int striped_read(struct inode *inode,
 	io_align = off & ~PAGE_MASK;
 
 more:
-	if (align_to_pages)
+	if (o_direct)
 		page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
 	else
 		page_align = pos & ~PAGE_MASK;
@@ -317,10 +318,10 @@ more:
 				  ci->i_truncate_seq,
 				  ci->i_truncate_size,
 				  page_pos, pages_left, page_align);
-	hit_stripe = this_len < left;
-	was_short = ret >= 0 && ret < this_len;
 	if (ret == -ENOENT)
 		ret = 0;
+	hit_stripe = this_len < left;
+	was_short = ret >= 0 && ret < this_len;
 	dout("striped_read %llu~%u (read %u) got %d%s%s\n", pos, left, read,
 	     ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
 
@@ -345,20 +346,22 @@ more:
 	}
 
 	if (was_short) {
-		/* was original extent fully inside i_size? */
-		if (pos + left <= inode->i_size) {
-			dout("zero tail\n");
-			ceph_zero_page_vector_range(page_off + read, len - read,
+		/* did we bounce off eof? */
+		if (pos + left > inode->i_size)
+			*checkeof = 1;
+
+		/* zero trailing bytes (inside i_size) */
+		if (left > 0 && pos < inode->i_size) {
+			if (pos + left > inode->i_size)
+				left = inode->i_size - pos;
+
+			dout("zero tail %d\n", left);
+			ceph_zero_page_vector_range(page_off + read, left,
 						    pages);
-			read = len;
-			goto out;
+			read += left;
 		}
-
-		/* check i_size */
-		*checkeof = 1;
 	}
 
-out:
 	if (ret >= 0)
 		ret = read;
 	dout("striped_read returns %d\n", ret);
@@ -658,7 +661,7 @@ out:
 
 		/* hit EOF or hole? */
 		if (statret == 0 && *ppos < inode->i_size) {
-			dout("aio_read sync_read hit hole, reading more\n");
+			dout("aio_read sync_read hit hole, ppos %lld < size %lld, reading more\n", *ppos, inode->i_size);
 			read += ret;
 			base += ret;
 			len -= ret;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 70b6a4839c38..d8858e96ab18 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1101,10 +1101,10 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 				goto done;
 			}
 			req->r_dentry = dn;  /* may have spliced */
-			igrab(in);
+			ihold(in);
 		} else if (ceph_ino(in) == vino.ino &&
 			   ceph_snap(in) == vino.snap) {
-			igrab(in);
+			ihold(in);
 		} else {
 			dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
 			     dn, in, ceph_ino(in), ceph_snap(in),
@@ -1144,7 +1144,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 			goto done;
 		}
 		req->r_dentry = dn;  /* may have spliced */
-		igrab(in);
+		ihold(in);
 		rinfo->head->is_dentry = 1;  /* fool notrace handlers */
 	}
 
@@ -1328,7 +1328,7 @@ void ceph_queue_writeback(struct inode *inode)
 	if (queue_work(ceph_inode_to_client(inode)->wb_wq,
 		       &ceph_inode(inode)->i_wb_work)) {
 		dout("ceph_queue_writeback %p\n", inode);
-		igrab(inode);
+		ihold(inode);
 	} else {
 		dout("ceph_queue_writeback %p failed\n", inode);
 	}
@@ -1353,7 +1353,7 @@ void ceph_queue_invalidate(struct inode *inode)
 	if (queue_work(ceph_inode_to_client(inode)->pg_inv_wq,
 		       &ceph_inode(inode)->i_pg_inv_work)) {
 		dout("ceph_queue_invalidate %p\n", inode);
-		igrab(inode);
+		ihold(inode);
 	} else {
 		dout("ceph_queue_invalidate %p failed\n", inode);
 	}
@@ -1477,7 +1477,7 @@ void ceph_queue_vmtruncate(struct inode *inode)
 	if (queue_work(ceph_sb_to_client(inode->i_sb)->trunc_wq,
 		       &ci->i_vmtruncate_work)) {
 		dout("ceph_queue_vmtruncate %p\n", inode);
-		igrab(inode);
+		ihold(inode);
 	} else {
 		dout("ceph_queue_vmtruncate %p failed, pending=%d\n",
 		     inode, ci->i_truncate_pending);
@@ -1738,7 +1738,8 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 		__mark_inode_dirty(inode, inode_dirty_flags);
 
 	if (mask) {
-		req->r_inode = igrab(inode);
+		req->r_inode = inode;
+		ihold(inode);
 		req->r_inode_drop = release;
 		req->r_args.setattr.mask = cpu_to_le32(mask);
 		req->r_num_caps = 1;
@@ -1779,7 +1780,8 @@ int ceph_do_getattr(struct inode *inode, int mask)
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, USE_ANY_MDS);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
-	req->r_inode = igrab(inode);
+	req->r_inode = inode;
+	ihold(inode);
 	req->r_num_caps = 1;
 	req->r_args.getattr.mask = cpu_to_le32(mask);
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 8888c9ba68db..ef0b5f48e13a 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -73,7 +73,8 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 				       USE_AUTH_MDS);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
-	req->r_inode = igrab(inode);
+	req->r_inode = inode;
+	ihold(inode);
 	req->r_inode_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL;
 
 	req->r_args.setlayout.layout.fl_stripe_unit =
@@ -135,7 +136,8 @@ static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
 
 	if (IS_ERR(req))
 		return PTR_ERR(req);
-	req->r_inode = igrab(inode);
+	req->r_inode = inode;
+	ihold(inode);
 
 	req->r_args.setlayout.layout.fl_stripe_unit =
 			cpu_to_le32(l.stripe_unit);
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 476b329867d4..80576d05d687 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -23,7 +23,8 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
 	req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
-	req->r_inode = igrab(inode);
+	req->r_inode = inode;
+	ihold(inode);
 
 	/* mds requires start and length rather than start and end */
 	if (LLONG_MAX == fl->fl_end)
@@ -32,11 +33,10 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
 		length = fl->fl_end - fl->fl_start + 1;
 
 	dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
-	     "length: %llu, wait: %d, type`: %d", (int)lock_type,
+	     "length: %llu, wait: %d, type: %d", (int)lock_type,
 	     (int)operation, (u64)fl->fl_pid, fl->fl_start,
 	     length, wait, fl->fl_type);
 
-
 	req->r_args.filelock_change.rule = lock_type;
 	req->r_args.filelock_change.type = cmd;
 	req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid);
@@ -70,7 +70,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
 	}
 	ceph_mdsc_put_request(req);
 	dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
-	     "length: %llu, wait: %d, type`: %d, err code %d", (int)lock_type,
+	     "length: %llu, wait: %d, type: %d, err code %d", (int)lock_type,
 	     (int)operation, (u64)fl->fl_pid, fl->fl_start,
 	     length, wait, fl->fl_type, err);
 	return err;
@@ -109,16 +109,20 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 			dout("mds locked, locking locally");
 			err = posix_lock_file(file, fl, NULL);
 			if (err && (CEPH_MDS_OP_SETFILELOCK == op)) {
-				/* undo! This should only happen if the kernel detects
-				 * local deadlock. */
+				/* undo! This should only happen if
+				 * the kernel detects local
+				 * deadlock. */
 				ceph_lock_message(CEPH_LOCK_FCNTL, op, file,
 						  CEPH_LOCK_UNLOCK, 0, fl);
-				dout("got %d on posix_lock_file, undid lock", err);
+				dout("got %d on posix_lock_file, undid lock",
+				     err);
 			}
 		}
 
-	} else {
-		dout("mds returned error code %d", err);
+	} else if (err == -ERESTARTSYS) {
+		dout("undoing lock\n");
+		ceph_lock_message(CEPH_LOCK_FCNTL, op, file,
+				  CEPH_LOCK_UNLOCK, 0, fl);
 	}
 	return err;
 }
@@ -155,8 +159,11 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 					  file, CEPH_LOCK_UNLOCK, 0, fl);
 			dout("got %d on flock_lock_file_wait, undid lock", err);
 		}
-	} else {
-		dout("mds error code %d", err);
+	} else if (err == -ERESTARTSYS) {
+		dout("undoing lock\n");
+		ceph_lock_message(CEPH_LOCK_FLOCK,
+				  CEPH_MDS_OP_SETFILELOCK,
+				  file, CEPH_LOCK_UNLOCK, 0, fl);
 	}
 	return err;
 }
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 24067d68a554..54b14de2e729 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -722,7 +722,7 @@ static void flush_snaps(struct ceph_mds_client *mdsc)
 		ci = list_first_entry(&mdsc->snap_flush_list,
 				struct ceph_inode_info, i_snap_flush_item);
 		inode = &ci->vfs_inode;
-		igrab(inode);
+		ihold(inode);
 		spin_unlock(&mdsc->snap_flush_lock);
 		spin_lock(&inode->i_lock);
 		__ceph_flush_snaps(ci, &session, 0);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index f2b628696180..f42d730f1b66 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -665,7 +665,8 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
 		err = PTR_ERR(req);
 		goto out;
 	}
-	req->r_inode = igrab(inode);
+	req->r_inode = inode;
+	ihold(inode);
 	req->r_inode_drop = CEPH_CAP_XATTR_SHARED;
 	req->r_num_caps = 1;
 	req->r_args.setxattr.flags = cpu_to_le32(flags);
@@ -795,7 +796,8 @@ static int ceph_send_removexattr(struct dentry *dentry, const char *name)
 				       USE_AUTH_MDS);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
-	req->r_inode = igrab(inode);
+	req->r_inode = inode;
+	ihold(inode);
 	req->r_inode_drop = CEPH_CAP_XATTR_SHARED;
 	req->r_num_caps = 1;
 	req->r_path2 = kstrdup(name, GFP_NOFS);
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index 75c47cd8d086..f66cc1625150 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -7,6 +7,7 @@ config CIFS
 	select CRYPTO_MD5
 	select CRYPTO_HMAC
 	select CRYPTO_ARC4
+	select CRYPTO_ECB
 	select CRYPTO_DES
 	help
 	  This is the client VFS module for the Common Internet File System
@@ -148,33 +149,13 @@ config CIFS_FSCACHE
 
 config CIFS_ACL
 	  bool "Provide CIFS ACL support (EXPERIMENTAL)"
-	  depends on EXPERIMENTAL && CIFS_XATTR
+	  depends on EXPERIMENTAL && CIFS_XATTR && KEYS
 	  help
 	    Allows to fetch CIFS/NTFS ACL from the server.  The DACL blob
 	    is handed over to the application/caller.
 
-config CIFS_SMB2
-	bool "SMB2 network file system support (EXPERIMENTAL)"
-	depends on EXPERIMENTAL && INET && BROKEN
-	select NLS
-	select KEYS
-	select FSCACHE
-	select DNS_RESOLVER
-
-	help
-	  This enables experimental support for the SMB2 (Server Message Block
-	  version 2) protocol. The SMB2 protocol is the successor to the
-	  popular CIFS and SMB network file sharing protocols. SMB2 is the
-	  native file sharing mechanism for recent versions of Windows
-	  operating systems (since Vista).  SMB2 enablement will eventually
-	  allow users better performance, security and features, than would be
-	  possible with cifs. Note that smb2 mount options also are simpler
-	  (compared to cifs) due to protocol improvements.
-
-	  Unless you are a developer or tester, say N.
-
 config CIFS_NFSD_EXPORT
 	  bool "Allow nfsd to export CIFS file system (EXPERIMENTAL)"
-	  depends on CIFS && EXPERIMENTAL
+	  depends on CIFS && EXPERIMENTAL && BROKEN
 	  help
 	   Allows NFS server to export a CIFS mounted share (nfsd over cifs)
diff --git a/fs/cifs/README b/fs/cifs/README
index 4a3ca0e5ca24..c5c2c5e5f0f2 100644
--- a/fs/cifs/README
+++ b/fs/cifs/README
@@ -457,6 +457,9 @@ A partial list of the supported mount options follows:
 		otherwise - read from the server. All written data are stored
 		in the cache, but if the client doesn't have Exclusive Oplock,
 		it writes the data to the server.
+  rwpidforward  Forward pid of a process who opened a file to any read or write
+		operation on that file. This prevent applications like WINE
+		from failing on read and write if we use mandatory brlock style.
   acl   	Allow setfacl and getfacl to manage posix ACLs if server
 		supports them.  (default)
   noacl 	Do not allow setfacl and getfacl calls on this mount
diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c
index 53d57a3fe427..545509c3313b 100644
--- a/fs/cifs/cache.c
+++ b/fs/cifs/cache.c
@@ -92,7 +92,7 @@ static uint16_t cifs_server_get_key(const void *cookie_netfs_data,
 		break;
 
 	default:
-		cERROR(1, "CIFS: Unknown network family '%d'", sa->sa_family);
+		cERROR(1, "Unknown network family '%d'", sa->sa_family);
 		key_len = 0;
 		break;
 	}
@@ -146,13 +146,13 @@ static char *extract_sharename(const char *treename)
 static uint16_t cifs_super_get_key(const void *cookie_netfs_data, void *buffer,
 				   uint16_t maxbuf)
 {
-	const struct cifsTconInfo *tcon = cookie_netfs_data;
+	const struct cifs_tcon *tcon = cookie_netfs_data;
 	char *sharename;
 	uint16_t len;
 
 	sharename = extract_sharename(tcon->treeName);
 	if (IS_ERR(sharename)) {
-		cFYI(1, "CIFS: couldn't extract sharename\n");
+		cFYI(1, "%s: couldn't extract sharename\n", __func__);
 		sharename = NULL;
 		return 0;
 	}
@@ -173,7 +173,7 @@ cifs_fscache_super_get_aux(const void *cookie_netfs_data, void *buffer,
 			   uint16_t maxbuf)
 {
 	struct cifs_fscache_super_auxdata auxdata;
-	const struct cifsTconInfo *tcon = cookie_netfs_data;
+	const struct cifs_tcon *tcon = cookie_netfs_data;
 
 	memset(&auxdata, 0, sizeof(auxdata));
 	auxdata.resource_id = tcon->resource_id;
@@ -192,7 +192,7 @@ fscache_checkaux cifs_fscache_super_check_aux(void *cookie_netfs_data,
 					      uint16_t datalen)
 {
 	struct cifs_fscache_super_auxdata auxdata;
-	const struct cifsTconInfo *tcon = cookie_netfs_data;
+	const struct cifs_tcon *tcon = cookie_netfs_data;
 
 	if (datalen != sizeof(auxdata))
 		return FSCACHE_CHECKAUX_OBSOLETE;
@@ -302,7 +302,7 @@ static void cifs_fscache_inode_now_uncached(void *cookie_netfs_data)
 	pagevec_init(&pvec, 0);
 	first = 0;
 
-	cFYI(1, "cifs inode 0x%p now uncached", cifsi);
+	cFYI(1, "%s: cifs inode 0x%p now uncached", __func__, cifsi);
 
 	for (;;) {
 		nr_pages = pagevec_lookup(&pvec,
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 18f4272d9047..2fe3cf13b2e9 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -110,8 +110,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 	struct list_head *tmp1, *tmp2, *tmp3;
 	struct mid_q_entry *mid_entry;
 	struct TCP_Server_Info *server;
-	struct cifsSesInfo *ses;
-	struct cifsTconInfo *tcon;
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
 	int i, j;
 	__u32 dev_type;
 
@@ -152,7 +152,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 				    tcp_ses_list);
 		i++;
 		list_for_each(tmp2, &server->smb_ses_list) {
-			ses = list_entry(tmp2, struct cifsSesInfo,
+			ses = list_entry(tmp2, struct cifs_ses,
 					 smb_ses_list);
 			if ((ses->serverDomain == NULL) ||
 				(ses->serverOS == NULL) ||
@@ -171,7 +171,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 			seq_printf(m, "TCP status: %d\n\tLocal Users To "
 				   "Server: %d SecMode: 0x%x Req On Wire: %d",
 				   server->tcpStatus, server->srv_count,
-				   server->secMode,
+				   server->sec_mode,
 				   atomic_read(&server->inFlight));
 
 #ifdef CONFIG_CIFS_STATS2
@@ -183,7 +183,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 			seq_puts(m, "\n\tShares:");
 			j = 0;
 			list_for_each(tmp3, &ses->tcon_list) {
-				tcon = list_entry(tmp3, struct cifsTconInfo,
+				tcon = list_entry(tmp3, struct cifs_tcon,
 						  tcon_list);
 				++j;
 				dev_type = le32_to_cpu(tcon->fsDevInfo.DeviceType);
@@ -256,8 +256,8 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 	int rc;
 	struct list_head *tmp1, *tmp2, *tmp3;
 	struct TCP_Server_Info *server;
-	struct cifsSesInfo *ses;
-	struct cifsTconInfo *tcon;
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
 
 	rc = get_user(c, buffer);
 	if (rc)
@@ -273,11 +273,11 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 			server = list_entry(tmp1, struct TCP_Server_Info,
 					    tcp_ses_list);
 			list_for_each(tmp2, &server->smb_ses_list) {
-				ses = list_entry(tmp2, struct cifsSesInfo,
+				ses = list_entry(tmp2, struct cifs_ses,
 						 smb_ses_list);
 				list_for_each(tmp3, &ses->tcon_list) {
 					tcon = list_entry(tmp3,
-							  struct cifsTconInfo,
+							  struct cifs_tcon,
 							  tcon_list);
 					atomic_set(&tcon->num_smbs_sent, 0);
 					atomic_set(&tcon->num_writes, 0);
@@ -312,8 +312,8 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v)
 	int i;
 	struct list_head *tmp1, *tmp2, *tmp3;
 	struct TCP_Server_Info *server;
-	struct cifsSesInfo *ses;
-	struct cifsTconInfo *tcon;
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
 
 	seq_printf(m,
 			"Resources in use\nCIFS Session: %d\n",
@@ -346,11 +346,11 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v)
 		server = list_entry(tmp1, struct TCP_Server_Info,
 				    tcp_ses_list);
 		list_for_each(tmp2, &server->smb_ses_list) {
-			ses = list_entry(tmp2, struct cifsSesInfo,
+			ses = list_entry(tmp2, struct cifs_ses,
 					 smb_ses_list);
 			list_for_each(tmp3, &ses->tcon_list) {
 				tcon = list_entry(tmp3,
-						  struct cifsTconInfo,
+						  struct cifs_tcon,
 						  tcon_list);
 				i++;
 				seq_printf(m, "\n%d) %s", i, tcon->treeName);
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 2b68ac57d97d..8d8f28c94c0f 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -272,7 +272,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
 	struct dfs_info3_param *referrals = NULL;
 	unsigned int num_referrals = 0;
 	struct cifs_sb_info *cifs_sb;
-	struct cifsSesInfo *ses;
+	struct cifs_ses *ses;
 	char *full_path;
 	int xid, i;
 	int rc;
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index a9d5692e0c20..7260e11e21f8 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -41,6 +41,8 @@
 #define CIFS_MOUNT_MF_SYMLINKS	0x10000 /* Minshall+French Symlinks enabled */
 #define CIFS_MOUNT_MULTIUSER	0x20000 /* multiuser mount */
 #define CIFS_MOUNT_STRICT_IO	0x40000 /* strict cache mode */
+#define CIFS_MOUNT_RWPIDFORWARD	0x80000 /* use pid forwarding for rw */
+#define CIFS_MOUNT_POSIXACL	0x100000 /* mirror of MS_POSIXACL in mnt_cifs_flags */
 
 struct cifs_sb_info {
 	struct rb_root tlink_tree;
@@ -56,8 +58,6 @@ struct cifs_sb_info {
 	mode_t	mnt_file_mode;
 	mode_t	mnt_dir_mode;
 	unsigned int mnt_cifs_flags;
-	int	prepathlen;
-	char   *prepath; /* relative path under the share to mount to */
 	char   *mountdata; /* options received at mount time or via DFS refs */
 	struct backing_dev_info bdi;
 	struct delayed_work prune_tlinks;
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index 33d221394aca..2272fd5fe5b7 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -95,7 +95,7 @@ struct key_type cifs_spnego_key_type = {
 
 /* get a key struct with a SPNEGO security blob, suitable for session setup */
 struct key *
-cifs_get_spnego_key(struct cifsSesInfo *sesInfo)
+cifs_get_spnego_key(struct cifs_ses *sesInfo)
 {
 	struct TCP_Server_Info *server = sesInfo->server;
 	struct sockaddr_in *sa = (struct sockaddr_in *) &server->dstaddr;
diff --git a/fs/cifs/cifs_spnego.h b/fs/cifs/cifs_spnego.h
index e4041ec4d712..31bef9ee078b 100644
--- a/fs/cifs/cifs_spnego.h
+++ b/fs/cifs/cifs_spnego.h
@@ -41,7 +41,7 @@ struct cifs_spnego_msg {
 
 #ifdef __KERNEL__
 extern struct key_type cifs_spnego_key_type;
-extern struct key *cifs_get_spnego_key(struct cifsSesInfo *sesInfo);
+extern struct key *cifs_get_spnego_key(struct cifs_ses *sesInfo);
 #endif /* KERNEL */
 
 #endif /* _CIFS_SPNEGO_H */
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index f3c6fb9942ac..21de1d6d5849 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -38,7 +38,7 @@ static const struct cifs_sid sid_everyone = {
 	1, 1, {0, 0, 0, 0, 0, 1}, {0} };
 /* security id for Authenticated Users system group */
 static const struct cifs_sid sid_authusers = {
-	1, 1, {0, 0, 0, 0, 0, 5}, {11} };
+	1, 1, {0, 0, 0, 0, 0, 5}, {__constant_cpu_to_le32(11)} };
 /* group users */
 static const struct cifs_sid sid_user = {1, 2 , {0, 0, 0, 0, 0, 5}, {} };
 
@@ -74,8 +74,9 @@ shrink_idmap_tree(struct rb_root *root, int nr_to_scan, int *nr_rem,
  * Run idmap cache shrinker.
  */
 static int
-cifs_idmap_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask)
+cifs_idmap_shrinker(struct shrinker *shrink, struct shrink_control *sc)
 {
+	int nr_to_scan = sc->nr_to_scan;
 	int nr_del = 0;
 	int nr_rem = 0;
 	struct rb_root *root;
@@ -458,7 +459,8 @@ int compare_sids(const struct cifs_sid *ctsid, const struct cifs_sid *cwsid)
 	if (num_subauth) {
 		for (i = 0; i < num_subauth; ++i) {
 			if (ctsid->sub_auth[i] != cwsid->sub_auth[i]) {
-				if (ctsid->sub_auth[i] > cwsid->sub_auth[i])
+				if (le32_to_cpu(ctsid->sub_auth[i]) >
+					le32_to_cpu(cwsid->sub_auth[i]))
 					return 1;
 				else
 					return -1;
@@ -945,7 +947,7 @@ static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb,
 	int oplock = 0;
 	int xid, rc;
 	__u16 fid;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
 
 	if (IS_ERR(tlink))
@@ -1013,7 +1015,7 @@ static int set_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, const char *path,
 	int oplock = 0;
 	int xid, rc;
 	__u16 fid;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
 
 	if (IS_ERR(tlink))
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 45c3f78c8f81..5a0ee7f2af06 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -184,7 +184,7 @@ int cifs_verify_signature(struct smb_hdr *cifs_pdu,
 	if (cifs_pdu == NULL || server == NULL)
 		return -EINVAL;
 
-	if (cifs_pdu->Command == SMB_COM_NEGOTIATE)
+	if (!server->session_estab)
 		return 0;
 
 	if (cifs_pdu->Command == SMB_COM_LOCKING_ANDX) {
@@ -229,7 +229,7 @@ int cifs_verify_signature(struct smb_hdr *cifs_pdu,
 }
 
 /* first calculate 24 bytes ntlm response and then 16 byte session key */
-int setup_ntlm_response(struct cifsSesInfo *ses)
+int setup_ntlm_response(struct cifs_ses *ses)
 {
 	int rc = 0;
 	unsigned int temp_len = CIFS_SESS_KEY_SIZE + CIFS_AUTH_RESP_SIZE;
@@ -312,7 +312,7 @@ int calc_lanman_hash(const char *password, const char *cryptkey, bool encrypt,
  * Allocate domain name which gets freed when session struct is deallocated.
  */
 static int
-build_avpair_blob(struct cifsSesInfo *ses, const struct nls_table *nls_cp)
+build_avpair_blob(struct cifs_ses *ses, const struct nls_table *nls_cp)
 {
 	unsigned int dlen;
 	unsigned int wlen;
@@ -400,7 +400,7 @@ build_avpair_blob(struct cifsSesInfo *ses, const struct nls_table *nls_cp)
  * about target string i.e. for some, just user name might suffice.
  */
 static int
-find_domain_name(struct cifsSesInfo *ses, const struct nls_table *nls_cp)
+find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp)
 {
 	unsigned int attrsize;
 	unsigned int type;
@@ -445,7 +445,7 @@ find_domain_name(struct cifsSesInfo *ses, const struct nls_table *nls_cp)
 	return 0;
 }
 
-static int calc_ntlmv2_hash(struct cifsSesInfo *ses, char *ntlmv2_hash,
+static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
 			    const struct nls_table *nls_cp)
 {
 	int rc = 0;
@@ -527,7 +527,7 @@ calc_exit_2:
 }
 
 static int
-CalcNTLMv2_response(const struct cifsSesInfo *ses, char *ntlmv2_hash)
+CalcNTLMv2_response(const struct cifs_ses *ses, char *ntlmv2_hash)
 {
 	int rc;
 	unsigned int offset = CIFS_SESS_KEY_SIZE + 8;
@@ -563,7 +563,7 @@ CalcNTLMv2_response(const struct cifsSesInfo *ses, char *ntlmv2_hash)
 
 
 int
-setup_ntlmv2_rsp(struct cifsSesInfo *ses, const struct nls_table *nls_cp)
+setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 {
 	int rc;
 	int baselen;
@@ -649,7 +649,7 @@ setup_ntlmv2_rsp_ret:
 }
 
 int
-calc_seckey(struct cifsSesInfo *ses)
+calc_seckey(struct cifs_ses *ses)
 {
 	int rc;
 	struct crypto_blkcipher *tfm_arc4;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 493b74ca5648..35f9154615fa 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -104,52 +104,24 @@ cifs_sb_deactive(struct super_block *sb)
 }
 
 static int
-cifs_read_super(struct super_block *sb, void *data,
-		const char *devname, int silent)
+cifs_read_super(struct super_block *sb)
 {
 	struct inode *inode;
 	struct cifs_sb_info *cifs_sb;
 	int rc = 0;
 
-	/* BB should we make this contingent on mount parm? */
-	sb->s_flags |= MS_NODIRATIME | MS_NOATIME;
-	sb->s_fs_info = kzalloc(sizeof(struct cifs_sb_info), GFP_KERNEL);
 	cifs_sb = CIFS_SB(sb);
-	if (cifs_sb == NULL)
-		return -ENOMEM;
 
-	spin_lock_init(&cifs_sb->tlink_tree_lock);
-	cifs_sb->tlink_tree = RB_ROOT;
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL)
+		sb->s_flags |= MS_POSIXACL;
 
-	rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs", BDI_CAP_MAP_COPY);
-	if (rc) {
-		kfree(cifs_sb);
-		return rc;
-	}
-	cifs_sb->bdi.ra_pages = default_backing_dev_info.ra_pages;
-
-	/*
-	 * Copy mount params to sb for use in submounts. Better to do
-	 * the copy here and deal with the error before cleanup gets
-	 * complicated post-mount.
-	 */
-	if (data) {
-		cifs_sb->mountdata = kstrndup(data, PAGE_SIZE, GFP_KERNEL);
-		if (cifs_sb->mountdata == NULL) {
-			bdi_destroy(&cifs_sb->bdi);
-			kfree(sb->s_fs_info);
-			sb->s_fs_info = NULL;
-			return -ENOMEM;
-		}
-	}
+	if (cifs_sb_master_tcon(cifs_sb)->ses->capabilities & CAP_LARGE_FILES)
+		sb->s_maxbytes = MAX_LFS_FILESIZE;
+	else
+		sb->s_maxbytes = MAX_NON_LFS;
 
-	rc = cifs_mount(sb, cifs_sb, devname);
-
-	if (rc) {
-		if (!silent)
-			cERROR(1, "cifs_mount failed w/return code = %d", rc);
-		goto out_mount_failed;
-	}
+	/* BB FIXME fix time_gran to be larger for LANMAN sessions */
+	sb->s_time_gran = 100;
 
 	sb->s_magic = CIFS_MAGIC_NUMBER;
 	sb->s_op = &cifs_super_ops;
@@ -191,45 +163,14 @@ out_no_root:
 	if (inode)
 		iput(inode);
 
-	cifs_umount(sb, cifs_sb);
-
-out_mount_failed:
-	if (cifs_sb) {
-		if (cifs_sb->mountdata) {
-			kfree(cifs_sb->mountdata);
-			cifs_sb->mountdata = NULL;
-		}
-		unload_nls(cifs_sb->local_nls);
-		bdi_destroy(&cifs_sb->bdi);
-		kfree(cifs_sb);
-	}
 	return rc;
 }
 
-static void
-cifs_put_super(struct super_block *sb)
+static void cifs_kill_sb(struct super_block *sb)
 {
-	int rc = 0;
-	struct cifs_sb_info *cifs_sb;
-
-	cFYI(1, "In cifs_put_super");
-	cifs_sb = CIFS_SB(sb);
-	if (cifs_sb == NULL) {
-		cFYI(1, "Empty cifs superblock info passed to unmount");
-		return;
-	}
-
-	rc = cifs_umount(sb, cifs_sb);
-	if (rc)
-		cERROR(1, "cifs_umount failed with return code %d", rc);
-	if (cifs_sb->mountdata) {
-		kfree(cifs_sb->mountdata);
-		cifs_sb->mountdata = NULL;
-	}
-
-	unload_nls(cifs_sb->local_nls);
-	bdi_destroy(&cifs_sb->bdi);
-	kfree(cifs_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+	kill_anon_super(sb);
+	cifs_umount(cifs_sb);
 }
 
 static int
@@ -237,7 +178,7 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
-	struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	int rc = -EOPNOTSUPP;
 	int xid;
 
@@ -286,9 +227,6 @@ static int cifs_permission(struct inode *inode, int mask, unsigned int flags)
 {
 	struct cifs_sb_info *cifs_sb;
 
-	if (flags & IPERM_FLAG_RCU)
-		return -ECHILD;
-
 	cifs_sb = CIFS_SB(inode->i_sb);
 
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) {
@@ -381,6 +319,37 @@ cifs_show_address(struct seq_file *s, struct TCP_Server_Info *server)
 	}
 }
 
+static void
+cifs_show_security(struct seq_file *s, struct TCP_Server_Info *server)
+{
+	seq_printf(s, ",sec=");
+
+	switch (server->secType) {
+	case LANMAN:
+		seq_printf(s, "lanman");
+		break;
+	case NTLMv2:
+		seq_printf(s, "ntlmv2");
+		break;
+	case NTLM:
+		seq_printf(s, "ntlm");
+		break;
+	case Kerberos:
+		seq_printf(s, "krb5");
+		break;
+	case RawNTLMSSP:
+		seq_printf(s, "ntlmssp");
+		break;
+	default:
+		/* shouldn't ever happen */
+		seq_printf(s, "unknown");
+		break;
+	}
+
+	if (server->sec_mode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
+		seq_printf(s, "i");
+}
+
 /*
  * cifs_show_options() is for displaying mount options in /proc/mounts.
  * Not all settable options are displayed but most of the important
@@ -390,10 +359,12 @@ static int
 cifs_show_options(struct seq_file *s, struct vfsmount *m)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(m->mnt_sb);
-	struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	struct sockaddr *srcaddr;
 	srcaddr = (struct sockaddr *)&tcon->ses->server->srcaddr;
 
+	cifs_show_security(s, tcon->ses->server);
+
 	seq_printf(s, ",unc=%s", tcon->treeName);
 
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)
@@ -444,14 +415,20 @@ cifs_show_options(struct seq_file *s, struct vfsmount *m)
 		seq_printf(s, ",nocase");
 	if (tcon->retry)
 		seq_printf(s, ",hard");
-	if (cifs_sb->prepath)
-		seq_printf(s, ",prepath=%s", cifs_sb->prepath);
+	if (tcon->unix_ext)
+		seq_printf(s, ",unix");
+	else
+		seq_printf(s, ",nounix");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
 		seq_printf(s, ",posixpaths");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
 		seq_printf(s, ",setuids");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
 		seq_printf(s, ",serverino");
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
+		seq_printf(s, ",rwpidforward");
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL)
+		seq_printf(s, ",forcemand");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO)
 		seq_printf(s, ",directio");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
@@ -484,7 +461,7 @@ cifs_show_options(struct seq_file *s, struct vfsmount *m)
 static void cifs_umount_begin(struct super_block *sb)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 
 	if (cifs_sb == NULL)
 		return;
@@ -541,7 +518,6 @@ static int cifs_drop_inode(struct inode *inode)
 }
 
 static const struct super_operations cifs_super_ops = {
-	.put_super = cifs_put_super,
 	.statfs = cifs_statfs,
 	.alloc_inode = cifs_alloc_inode,
 	.destroy_inode = cifs_destroy_inode,
@@ -559,29 +535,194 @@ static const struct super_operations cifs_super_ops = {
 #endif
 };
 
+/*
+ * Get root dentry from superblock according to prefix path mount option.
+ * Return dentry with refcount + 1 on success and NULL otherwise.
+ */
+static struct dentry *
+cifs_get_root(struct smb_vol *vol, struct super_block *sb)
+{
+	int xid, rc;
+	struct inode *inode;
+	struct qstr name;
+	struct dentry *dparent = NULL, *dchild = NULL, *alias;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+	unsigned int i, full_len, len;
+	char *full_path = NULL, *pstart;
+	char sep;
+
+	full_path = cifs_build_path_to_root(vol, cifs_sb,
+					    cifs_sb_master_tcon(cifs_sb));
+	if (full_path == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	cFYI(1, "Get root dentry for %s", full_path);
+
+	xid = GetXid();
+	sep = CIFS_DIR_SEP(cifs_sb);
+	dparent = dget(sb->s_root);
+	full_len = strlen(full_path);
+	full_path[full_len] = sep;
+	pstart = full_path + 1;
+
+	for (i = 1, len = 0; i <= full_len; i++) {
+		if (full_path[i] != sep || !len) {
+			len++;
+			continue;
+		}
+
+		full_path[i] = 0;
+		cFYI(1, "get dentry for %s", pstart);
+
+		name.name = pstart;
+		name.len = len;
+		name.hash = full_name_hash(pstart, len);
+		dchild = d_lookup(dparent, &name);
+		if (dchild == NULL) {
+			cFYI(1, "not exists");
+			dchild = d_alloc(dparent, &name);
+			if (dchild == NULL) {
+				dput(dparent);
+				dparent = ERR_PTR(-ENOMEM);
+				goto out;
+			}
+		}
+
+		cFYI(1, "get inode");
+		if (dchild->d_inode == NULL) {
+			cFYI(1, "not exists");
+			inode = NULL;
+			if (cifs_sb_master_tcon(CIFS_SB(sb))->unix_ext)
+				rc = cifs_get_inode_info_unix(&inode, full_path,
+							      sb, xid);
+			else
+				rc = cifs_get_inode_info(&inode, full_path,
+							 NULL, sb, xid, NULL);
+			if (rc) {
+				dput(dchild);
+				dput(dparent);
+				dparent = ERR_PTR(rc);
+				goto out;
+			}
+			alias = d_materialise_unique(dchild, inode);
+			if (alias != NULL) {
+				dput(dchild);
+				if (IS_ERR(alias)) {
+					dput(dparent);
+					dparent = ERR_PTR(-EINVAL); /* XXX */
+					goto out;
+				}
+				dchild = alias;
+			}
+		}
+		cFYI(1, "parent %p, child %p", dparent, dchild);
+
+		dput(dparent);
+		dparent = dchild;
+		len = 0;
+		pstart = full_path + i + 1;
+		full_path[i] = sep;
+	}
+out:
+	_FreeXid(xid);
+	kfree(full_path);
+	return dparent;
+}
+
+static int cifs_set_super(struct super_block *sb, void *data)
+{
+	struct cifs_mnt_data *mnt_data = data;
+	sb->s_fs_info = mnt_data->cifs_sb;
+	return set_anon_super(sb, NULL);
+}
+
 static struct dentry *
 cifs_do_mount(struct file_system_type *fs_type,
-	    int flags, const char *dev_name, void *data)
+	      int flags, const char *dev_name, void *data)
 {
 	int rc;
 	struct super_block *sb;
-
-	sb = sget(fs_type, NULL, set_anon_super, NULL);
+	struct cifs_sb_info *cifs_sb;
+	struct smb_vol *volume_info;
+	struct cifs_mnt_data mnt_data;
+	struct dentry *root;
 
 	cFYI(1, "Devname: %s flags: %d ", dev_name, flags);
 
-	if (IS_ERR(sb))
-		return ERR_CAST(sb);
+	rc = cifs_setup_volume_info(&volume_info, (char *)data, dev_name);
+	if (rc)
+		return ERR_PTR(rc);
+
+	cifs_sb = kzalloc(sizeof(struct cifs_sb_info), GFP_KERNEL);
+	if (cifs_sb == NULL) {
+		root = ERR_PTR(-ENOMEM);
+		goto out_nls;
+	}
+
+	cifs_sb->mountdata = kstrndup(data, PAGE_SIZE, GFP_KERNEL);
+	if (cifs_sb->mountdata == NULL) {
+		root = ERR_PTR(-ENOMEM);
+		goto out_cifs_sb;
+	}
 
-	sb->s_flags = flags;
+	cifs_setup_cifs_sb(volume_info, cifs_sb);
 
-	rc = cifs_read_super(sb, data, dev_name, flags & MS_SILENT ? 1 : 0);
+	rc = cifs_mount(cifs_sb, volume_info);
 	if (rc) {
-		deactivate_locked_super(sb);
-		return ERR_PTR(rc);
+		if (!(flags & MS_SILENT))
+			cERROR(1, "cifs_mount failed w/return code = %d", rc);
+		root = ERR_PTR(rc);
+		goto out_mountdata;
+	}
+
+	mnt_data.vol = volume_info;
+	mnt_data.cifs_sb = cifs_sb;
+	mnt_data.flags = flags;
+
+	sb = sget(fs_type, cifs_match_super, cifs_set_super, &mnt_data);
+	if (IS_ERR(sb)) {
+		root = ERR_CAST(sb);
+		cifs_umount(cifs_sb);
+		goto out;
+	}
+
+	if (sb->s_root) {
+		cFYI(1, "Use existing superblock");
+		cifs_umount(cifs_sb);
+	} else {
+		sb->s_flags = flags;
+		/* BB should we make this contingent on mount parm? */
+		sb->s_flags |= MS_NODIRATIME | MS_NOATIME;
+
+		rc = cifs_read_super(sb);
+		if (rc) {
+			root = ERR_PTR(rc);
+			goto out_super;
+		}
+
+		sb->s_flags |= MS_ACTIVE;
 	}
-	sb->s_flags |= MS_ACTIVE;
-	return dget(sb->s_root);
+
+	root = cifs_get_root(volume_info, sb);
+	if (IS_ERR(root))
+		goto out_super;
+
+	cFYI(1, "dentry root is: %p", root);
+	goto out;
+
+out_super:
+	deactivate_locked_super(sb);
+out:
+	cifs_cleanup_volume_info(&volume_info);
+	return root;
+
+out_mountdata:
+	kfree(cifs_sb->mountdata);
+out_cifs_sb:
+	kfree(cifs_sb);
+out_nls:
+	unload_nls(volume_info->local_nls);
+	goto out;
 }
 
 static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
@@ -670,7 +811,7 @@ struct file_system_type cifs_fs_type = {
 	.owner = THIS_MODULE,
 	.name = "cifs",
 	.mount = cifs_do_mount,
-	.kill_sb = kill_anon_super,
+	.kill_sb = cifs_kill_sb,
 	/*  .fs_flags */
 };
 const struct inode_operations cifs_dir_inode_ops = {
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 64313f778ebf..0900e1658c96 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -129,5 +129,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
 extern const struct export_operations cifs_export_ops;
 #endif /* CIFS_NFSD_EXPORT */
 
-#define CIFS_VERSION   "1.72"
+#define CIFS_VERSION   "1.73"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 76b4517e74b0..6255fa812c7a 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -155,6 +155,81 @@ struct cifs_cred {
  *****************************************************************
  */
 
+struct smb_vol {
+	char *username;
+	char *password;
+	char *domainname;
+	char *UNC;
+	char *UNCip;
+	char *iocharset;  /* local code page for mapping to and from Unicode */
+	char source_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* clnt nb name */
+	char target_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* srvr nb name */
+	uid_t cred_uid;
+	uid_t linux_uid;
+	gid_t linux_gid;
+	mode_t file_mode;
+	mode_t dir_mode;
+	unsigned secFlg;
+	bool retry:1;
+	bool intr:1;
+	bool setuids:1;
+	bool override_uid:1;
+	bool override_gid:1;
+	bool dynperm:1;
+	bool noperm:1;
+	bool no_psx_acl:1; /* set if posix acl support should be disabled */
+	bool cifs_acl:1;
+	bool no_xattr:1;   /* set if xattr (EA) support should be disabled*/
+	bool server_ino:1; /* use inode numbers from server ie UniqueId */
+	bool direct_io:1;
+	bool strict_io:1; /* strict cache behavior */
+	bool remap:1;      /* set to remap seven reserved chars in filenames */
+	bool posix_paths:1; /* unset to not ask for posix pathnames. */
+	bool no_linux_ext:1;
+	bool sfu_emul:1;
+	bool nullauth:1;   /* attempt to authenticate with null user */
+	bool nocase:1;     /* request case insensitive filenames */
+	bool nobrl:1;      /* disable sending byte range locks to srv */
+	bool mand_lock:1;  /* send mandatory not posix byte range lock reqs */
+	bool seal:1;       /* request transport encryption on share */
+	bool nodfs:1;      /* Do not request DFS, even if available */
+	bool local_lease:1; /* check leases only on local system, not remote */
+	bool noblocksnd:1;
+	bool noautotune:1;
+	bool nostrictsync:1; /* do not force expensive SMBflush on every sync */
+	bool fsc:1;	/* enable fscache */
+	bool mfsymlinks:1; /* use Minshall+French Symlinks */
+	bool multiuser:1;
+	bool rwpidforward:1; /* pid forward for read/write operations */
+	unsigned int rsize;
+	unsigned int wsize;
+	bool sockopt_tcp_nodelay:1;
+	unsigned short int port;
+	unsigned long actimeo; /* attribute cache timeout (jiffies) */
+	char *prepath;
+	struct sockaddr_storage srcaddr; /* allow binding to a local IP */
+	struct nls_table *local_nls;
+};
+
+#define CIFS_MOUNT_MASK (CIFS_MOUNT_NO_PERM | CIFS_MOUNT_SET_UID | \
+			 CIFS_MOUNT_SERVER_INUM | CIFS_MOUNT_DIRECT_IO | \
+			 CIFS_MOUNT_NO_XATTR | CIFS_MOUNT_MAP_SPECIAL_CHR | \
+			 CIFS_MOUNT_UNX_EMUL | CIFS_MOUNT_NO_BRL | \
+			 CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_OVERR_UID | \
+			 CIFS_MOUNT_OVERR_GID | CIFS_MOUNT_DYNPERM | \
+			 CIFS_MOUNT_NOPOSIXBRL | CIFS_MOUNT_NOSSYNC | \
+			 CIFS_MOUNT_FSCACHE | CIFS_MOUNT_MF_SYMLINKS | \
+			 CIFS_MOUNT_MULTIUSER | CIFS_MOUNT_STRICT_IO)
+
+#define CIFS_MS_MASK (MS_RDONLY | MS_MANDLOCK | MS_NOEXEC | MS_NOSUID | \
+		      MS_NODEV | MS_SYNCHRONOUS)
+
+struct cifs_mnt_data {
+	struct cifs_sb_info *cifs_sb;
+	struct smb_vol *vol;
+	int flags;
+};
+
 struct TCP_Server_Info {
 	struct list_head tcp_ses_list;
 	struct list_head smb_ses_list;
@@ -179,7 +254,7 @@ struct TCP_Server_Info {
 	struct mutex srv_mutex;
 	struct task_struct *tsk;
 	char server_GUID[16];
-	char secMode;
+	char sec_mode;
 	bool session_estab; /* mark when very first sess is established */
 	u16 dialect; /* dialect index that server chose */
 	enum securityEnum secType;
@@ -254,7 +329,7 @@ static inline void cifs_set_net_ns(struct TCP_Server_Info *srv, struct net *net)
 /*
  * Session structure.  One of these for each uid session with a particular host
  */
-struct cifsSesInfo {
+struct cifs_ses {
 	struct list_head smb_ses_list;
 	struct list_head tcon_list;
 	struct mutex session_mutex;
@@ -294,11 +369,11 @@ struct cifsSesInfo {
  * there is one of these for each connection to a resource on a particular
  * session
  */
-struct cifsTconInfo {
+struct cifs_tcon {
 	struct list_head tcon_list;
 	int tc_count;
 	struct list_head openFileList;
-	struct cifsSesInfo *ses;	/* pointer to session associated with */
+	struct cifs_ses *ses;	/* pointer to session associated with */
 	char treeName[MAX_TREE_SIZE + 1]; /* UNC name of resource in ASCII */
 	char *nativeFileSystem;
 	char *password;		/* for share-level security */
@@ -380,12 +455,12 @@ struct tcon_link {
 #define TCON_LINK_IN_TREE	2
 	unsigned long		tl_time;
 	atomic_t		tl_count;
-	struct cifsTconInfo	*tl_tcon;
+	struct cifs_tcon	*tl_tcon;
 };
 
 extern struct tcon_link *cifs_sb_tlink(struct cifs_sb_info *cifs_sb);
 
-static inline struct cifsTconInfo *
+static inline struct cifs_tcon *
 tlink_tcon(struct tcon_link *tlink)
 {
 	return tlink->tl_tcon;
@@ -402,7 +477,7 @@ cifs_get_tlink(struct tcon_link *tlink)
 }
 
 /* This function is always expected to succeed */
-extern struct cifsTconInfo *cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb);
+extern struct cifs_tcon *cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb);
 
 /*
  * This info hangs off the cifsFileInfo structure, pointed to by llist.
@@ -455,6 +530,14 @@ struct cifsFileInfo {
 	struct work_struct oplock_break; /* work for oplock breaks */
 };
 
+struct cifs_io_parms {
+	__u16 netfid;
+	__u32 pid;
+	__u64 offset;
+	unsigned int length;
+	struct cifs_tcon *tcon;
+};
+
 /*
  * Take a reference on the file private data. Must be called with
  * cifs_file_list_lock held.
@@ -509,10 +592,30 @@ static inline char CIFS_DIR_SEP(const struct cifs_sb_info *cifs_sb)
 		return '\\';
 }
 
+static inline void
+convert_delimiter(char *path, char delim)
+{
+	int i;
+	char old_delim;
+
+	if (path == NULL)
+		return;
+
+	if (delim == '/')
+		old_delim = '\\';
+	else
+		old_delim = '/';
+
+	for (i = 0; path[i] != '\0'; i++) {
+		if (path[i] == old_delim)
+			path[i] = delim;
+	}
+}
+
 #ifdef CONFIG_CIFS_STATS
 #define cifs_stats_inc atomic_inc
 
-static inline void cifs_stats_bytes_written(struct cifsTconInfo *tcon,
+static inline void cifs_stats_bytes_written(struct cifs_tcon *tcon,
 					    unsigned int bytes)
 {
 	if (bytes) {
@@ -522,7 +625,7 @@ static inline void cifs_stats_bytes_written(struct cifsTconInfo *tcon,
 	}
 }
 
-static inline void cifs_stats_bytes_read(struct cifsTconInfo *tcon,
+static inline void cifs_stats_bytes_read(struct cifs_tcon *tcon,
 					 unsigned int bytes)
 {
 	spin_lock(&tcon->stat_lock);
@@ -543,9 +646,8 @@ struct mid_q_entry;
  * This is the prototype for the mid callback function. When creating one,
  * take special care to avoid deadlocks. Things to bear in mind:
  *
- * - it will be called by cifsd
- * - the GlobalMid_Lock will be held
- * - the mid will be removed from the pending_mid_q list
+ * - it will be called by cifsd, with no locks held
+ * - the mid will be removed from any lists
  */
 typedef void (mid_callback_t)(struct mid_q_entry *mid);
 
@@ -573,7 +675,7 @@ struct mid_q_entry {
 struct oplock_q_entry {
 	struct list_head qhead;
 	struct inode *pinode;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	__u16 netfid;
 };
 
@@ -656,6 +758,7 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param,
 #define   MID_RESPONSE_RECEIVED 4
 #define   MID_RETRY_NEEDED      8 /* session closed while this request out */
 #define   MID_RESPONSE_MALFORMED 0x10
+#define   MID_SHUTDOWN		 0x20
 
 /* Types of response buffer returned from SendReceive2 */
 #define   CIFS_NO_BUFFER        0    /* Response buffer not returned */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 6e69e06a30b3..257f312ede42 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -57,8 +57,9 @@ extern int init_cifs_idmap(void);
 extern void exit_cifs_idmap(void);
 extern void cifs_destroy_idmaptrees(void);
 extern char *build_path_from_dentry(struct dentry *);
-extern char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb,
-					struct cifsTconInfo *tcon);
+extern char *cifs_build_path_to_root(struct smb_vol *vol,
+				     struct cifs_sb_info *cifs_sb,
+				     struct cifs_tcon *tcon);
 extern char *build_wildcard_path_from_dentry(struct dentry *direntry);
 extern char *cifs_compose_mount_options(const char *sb_mountdata,
 		const char *fullpath, const struct dfs_info3_param *ref,
@@ -67,20 +68,22 @@ extern char *cifs_compose_mount_options(const char *sb_mountdata,
 extern struct mid_q_entry *AllocMidQEntry(const struct smb_hdr *smb_buffer,
 					struct TCP_Server_Info *server);
 extern void DeleteMidQEntry(struct mid_q_entry *midEntry);
-extern int cifs_call_async(struct TCP_Server_Info *server,
-			   struct smb_hdr *in_buf, mid_callback_t *callback,
-			   void *cbdata);
-extern int SendReceive(const unsigned int /* xid */ , struct cifsSesInfo *,
+extern int cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov,
+			   unsigned int nvec, mid_callback_t *callback,
+			   void *cbdata, bool ignore_pend);
+extern int SendReceive(const unsigned int /* xid */ , struct cifs_ses *,
 			struct smb_hdr * /* input */ ,
 			struct smb_hdr * /* out */ ,
 			int * /* bytes returned */ , const int long_op);
-extern int SendReceiveNoRsp(const unsigned int xid, struct cifsSesInfo *ses,
+extern int SendReceiveNoRsp(const unsigned int xid, struct cifs_ses *ses,
 			struct smb_hdr *in_buf, int flags);
-extern int SendReceive2(const unsigned int /* xid */ , struct cifsSesInfo *,
+extern int cifs_check_receive(struct mid_q_entry *mid,
+			struct TCP_Server_Info *server, bool log_error);
+extern int SendReceive2(const unsigned int /* xid */ , struct cifs_ses *,
 			struct kvec *, int /* nvec to send */,
 			int * /* type of buf returned */ , const int flags);
 extern int SendReceiveBlockingLock(const unsigned int xid,
-			struct cifsTconInfo *ptcon,
+			struct cifs_tcon *ptcon,
 			struct smb_hdr *in_buf ,
 			struct smb_hdr *out_buf,
 			int *bytes_returned);
@@ -99,14 +102,14 @@ extern int cifs_convert_address(struct sockaddr *dst, const char *src, int len);
 extern int cifs_set_port(struct sockaddr *addr, const unsigned short int port);
 extern int cifs_fill_sockaddr(struct sockaddr *dst, const char *src, int len,
 				const unsigned short int port);
-extern int map_smb_to_linux_error(struct smb_hdr *smb, int logErr);
+extern int map_smb_to_linux_error(struct smb_hdr *smb, bool logErr);
 extern void header_assemble(struct smb_hdr *, char /* command */ ,
-			    const struct cifsTconInfo *, int /* length of
+			    const struct cifs_tcon *, int /* length of
 			    fixed section (word count) in two byte units */);
 extern int small_smb_init_no_tc(const int smb_cmd, const int wct,
-				struct cifsSesInfo *ses,
+				struct cifs_ses *ses,
 				void **request_buf);
-extern int CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses,
+extern int CIFS_SessSetup(unsigned int xid, struct cifs_ses *ses,
 			     const struct nls_table *nls_cp);
 extern __u16 GetNextMid(struct TCP_Server_Info *server);
 extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
@@ -148,102 +151,108 @@ extern struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *, struct inode *,
 extern int set_cifs_acl(struct cifs_ntsd *, __u32, struct inode *,
 				const char *);
 
-extern int cifs_mount(struct super_block *, struct cifs_sb_info *,
-			const char *);
-extern int cifs_umount(struct super_block *, struct cifs_sb_info *);
+extern void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
+			       struct cifs_sb_info *cifs_sb);
+extern int cifs_match_super(struct super_block *, void *);
+extern void cifs_cleanup_volume_info(struct smb_vol **pvolume_info);
+extern int cifs_setup_volume_info(struct smb_vol **pvolume_info,
+				  char *mount_data, const char *devname);
+extern int cifs_mount(struct cifs_sb_info *, struct smb_vol *);
+extern void cifs_umount(struct cifs_sb_info *);
 extern void cifs_dfs_release_automount_timer(void);
 void cifs_proc_init(void);
 void cifs_proc_clean(void);
 
 extern int cifs_negotiate_protocol(unsigned int xid,
-				  struct cifsSesInfo *ses);
-extern int cifs_setup_session(unsigned int xid, struct cifsSesInfo *ses,
+				  struct cifs_ses *ses);
+extern int cifs_setup_session(unsigned int xid, struct cifs_ses *ses,
 			struct nls_table *nls_info);
-extern int CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses);
+extern int CIFSSMBNegotiate(unsigned int xid, struct cifs_ses *ses);
 
-extern int CIFSTCon(unsigned int xid, struct cifsSesInfo *ses,
-			const char *tree, struct cifsTconInfo *tcon,
+extern int CIFSTCon(unsigned int xid, struct cifs_ses *ses,
+			const char *tree, struct cifs_tcon *tcon,
 			const struct nls_table *);
 
-extern int CIFSFindFirst(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSFindFirst(const int xid, struct cifs_tcon *tcon,
 		const char *searchName, const struct nls_table *nls_codepage,
 		__u16 *searchHandle, struct cifs_search_info *psrch_inf,
 		int map, const char dirsep);
 
-extern int CIFSFindNext(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSFindNext(const int xid, struct cifs_tcon *tcon,
 		__u16 searchHandle, struct cifs_search_info *psrch_inf);
 
-extern int CIFSFindClose(const int, struct cifsTconInfo *tcon,
+extern int CIFSFindClose(const int, struct cifs_tcon *tcon,
 			const __u16 search_handle);
 
-extern int CIFSSMBQFileInfo(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBQFileInfo(const int xid, struct cifs_tcon *tcon,
 			u16 netfid, FILE_ALL_INFO *pFindData);
-extern int CIFSSMBQPathInfo(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBQPathInfo(const int xid, struct cifs_tcon *tcon,
 			const unsigned char *searchName,
 			FILE_ALL_INFO *findData,
 			int legacy /* whether to use old info level */,
 			const struct nls_table *nls_codepage, int remap);
-extern int SMBQueryInformation(const int xid, struct cifsTconInfo *tcon,
+extern int SMBQueryInformation(const int xid, struct cifs_tcon *tcon,
 			const unsigned char *searchName,
 			FILE_ALL_INFO *findData,
 			const struct nls_table *nls_codepage, int remap);
 
-extern int CIFSSMBUnixQFileInfo(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBUnixQFileInfo(const int xid, struct cifs_tcon *tcon,
 			u16 netfid, FILE_UNIX_BASIC_INFO *pFindData);
 extern int CIFSSMBUnixQPathInfo(const int xid,
-			struct cifsTconInfo *tcon,
+			struct cifs_tcon *tcon,
 			const unsigned char *searchName,
 			FILE_UNIX_BASIC_INFO *pFindData,
 			const struct nls_table *nls_codepage, int remap);
 
-extern int CIFSGetDFSRefer(const int xid, struct cifsSesInfo *ses,
+extern int CIFSGetDFSRefer(const int xid, struct cifs_ses *ses,
 			const unsigned char *searchName,
 			struct dfs_info3_param **target_nodes,
 			unsigned int *number_of_nodes_in_array,
 			const struct nls_table *nls_codepage, int remap);
 
-extern int get_dfs_path(int xid, struct cifsSesInfo *pSesInfo,
+extern int get_dfs_path(int xid, struct cifs_ses *pSesInfo,
 			const char *old_path,
 			const struct nls_table *nls_codepage,
 			unsigned int *pnum_referrals,
 			struct dfs_info3_param **preferrals,
 			int remap);
-extern void reset_cifs_unix_caps(int xid, struct cifsTconInfo *tcon,
-				 struct super_block *sb, struct smb_vol *vol);
-extern int CIFSSMBQFSInfo(const int xid, struct cifsTconInfo *tcon,
+extern void reset_cifs_unix_caps(int xid, struct cifs_tcon *tcon,
+				 struct cifs_sb_info *cifs_sb,
+				 struct smb_vol *vol);
+extern int CIFSSMBQFSInfo(const int xid, struct cifs_tcon *tcon,
 			struct kstatfs *FSData);
-extern int SMBOldQFSInfo(const int xid, struct cifsTconInfo *tcon,
+extern int SMBOldQFSInfo(const int xid, struct cifs_tcon *tcon,
 			struct kstatfs *FSData);
-extern int CIFSSMBSetFSUnixInfo(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBSetFSUnixInfo(const int xid, struct cifs_tcon *tcon,
 			__u64 cap);
 
 extern int CIFSSMBQFSAttributeInfo(const int xid,
-			struct cifsTconInfo *tcon);
-extern int CIFSSMBQFSDeviceInfo(const int xid, struct cifsTconInfo *tcon);
-extern int CIFSSMBQFSUnixInfo(const int xid, struct cifsTconInfo *tcon);
-extern int CIFSSMBQFSPosixInfo(const int xid, struct cifsTconInfo *tcon,
+			struct cifs_tcon *tcon);
+extern int CIFSSMBQFSDeviceInfo(const int xid, struct cifs_tcon *tcon);
+extern int CIFSSMBQFSUnixInfo(const int xid, struct cifs_tcon *tcon);
+extern int CIFSSMBQFSPosixInfo(const int xid, struct cifs_tcon *tcon,
 			struct kstatfs *FSData);
 
-extern int CIFSSMBSetPathInfo(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBSetPathInfo(const int xid, struct cifs_tcon *tcon,
 			const char *fileName, const FILE_BASIC_INFO *data,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
-extern int CIFSSMBSetFileInfo(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBSetFileInfo(const int xid, struct cifs_tcon *tcon,
 			const FILE_BASIC_INFO *data, __u16 fid,
 			__u32 pid_of_opener);
-extern int CIFSSMBSetFileDisposition(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBSetFileDisposition(const int xid, struct cifs_tcon *tcon,
 			bool delete_file, __u16 fid, __u32 pid_of_opener);
 #if 0
-extern int CIFSSMBSetAttrLegacy(int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBSetAttrLegacy(int xid, struct cifs_tcon *tcon,
 			char *fileName, __u16 dos_attributes,
 			const struct nls_table *nls_codepage);
 #endif /* possibly unneeded function */
-extern int CIFSSMBSetEOF(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBSetEOF(const int xid, struct cifs_tcon *tcon,
 			const char *fileName, __u64 size,
 			bool setAllocationSizeFlag,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
-extern int CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBSetFileSize(const int xid, struct cifs_tcon *tcon,
 			 __u64 size, __u16 fileHandle, __u32 opener_pid,
 			bool AllocSizeFlag);
 
@@ -257,120 +266,116 @@ struct cifs_unix_set_info_args {
 	dev_t	device;
 };
 
-extern int CIFSSMBUnixSetFileInfo(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBUnixSetFileInfo(const int xid, struct cifs_tcon *tcon,
 				  const struct cifs_unix_set_info_args *args,
 				  u16 fid, u32 pid_of_opener);
 
-extern int CIFSSMBUnixSetPathInfo(const int xid, struct cifsTconInfo *pTcon,
+extern int CIFSSMBUnixSetPathInfo(const int xid, struct cifs_tcon *pTcon,
 			char *fileName,
 			const struct cifs_unix_set_info_args *args,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
 
-extern int CIFSSMBMkDir(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBMkDir(const int xid, struct cifs_tcon *tcon,
 			const char *newName,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
-extern int CIFSSMBRmDir(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBRmDir(const int xid, struct cifs_tcon *tcon,
 			const char *name, const struct nls_table *nls_codepage,
 			int remap_special_chars);
-extern int CIFSPOSIXDelFile(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSPOSIXDelFile(const int xid, struct cifs_tcon *tcon,
 			const char *name, __u16 type,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
-extern int CIFSSMBDelFile(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBDelFile(const int xid, struct cifs_tcon *tcon,
 			const char *name,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
-extern int CIFSSMBRename(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBRename(const int xid, struct cifs_tcon *tcon,
 			const char *fromName, const char *toName,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
-extern int CIFSSMBRenameOpenFile(const int xid, struct cifsTconInfo *pTcon,
+extern int CIFSSMBRenameOpenFile(const int xid, struct cifs_tcon *pTcon,
 			int netfid, const char *target_name,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
 extern int CIFSCreateHardLink(const int xid,
-			struct cifsTconInfo *tcon,
+			struct cifs_tcon *tcon,
 			const char *fromName, const char *toName,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
 extern int CIFSUnixCreateHardLink(const int xid,
-			struct cifsTconInfo *tcon,
+			struct cifs_tcon *tcon,
 			const char *fromName, const char *toName,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
 extern int CIFSUnixCreateSymLink(const int xid,
-			struct cifsTconInfo *tcon,
+			struct cifs_tcon *tcon,
 			const char *fromName, const char *toName,
 			const struct nls_table *nls_codepage);
 extern int CIFSSMBUnixQuerySymLink(const int xid,
-			struct cifsTconInfo *tcon,
+			struct cifs_tcon *tcon,
 			const unsigned char *searchName, char **syminfo,
 			const struct nls_table *nls_codepage);
 #ifdef CONFIG_CIFS_SYMLINK_EXPERIMENTAL
 extern int CIFSSMBQueryReparseLinkInfo(const int xid,
-			struct cifsTconInfo *tcon,
+			struct cifs_tcon *tcon,
 			const unsigned char *searchName,
 			char *symlinkinfo, const int buflen, __u16 fid,
 			const struct nls_table *nls_codepage);
 #endif /* temporarily unused until cifs_symlink fixed */
-extern int CIFSSMBOpen(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBOpen(const int xid, struct cifs_tcon *tcon,
 			const char *fileName, const int disposition,
 			const int access_flags, const int omode,
 			__u16 *netfid, int *pOplock, FILE_ALL_INFO *,
 			const struct nls_table *nls_codepage, int remap);
-extern int SMBLegacyOpen(const int xid, struct cifsTconInfo *tcon,
+extern int SMBLegacyOpen(const int xid, struct cifs_tcon *tcon,
 			const char *fileName, const int disposition,
 			const int access_flags, const int omode,
 			__u16 *netfid, int *pOplock, FILE_ALL_INFO *,
 			const struct nls_table *nls_codepage, int remap);
-extern int CIFSPOSIXCreate(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSPOSIXCreate(const int xid, struct cifs_tcon *tcon,
 			u32 posix_flags, __u64 mode, __u16 *netfid,
 			FILE_UNIX_BASIC_INFO *pRetData,
 			__u32 *pOplock, const char *name,
 			const struct nls_table *nls_codepage, int remap);
-extern int CIFSSMBClose(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBClose(const int xid, struct cifs_tcon *tcon,
 			const int smb_file_id);
 
-extern int CIFSSMBFlush(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBFlush(const int xid, struct cifs_tcon *tcon,
 			const int smb_file_id);
 
-extern int CIFSSMBRead(const int xid, struct cifsTconInfo *tcon,
-			const int netfid, unsigned int count,
-			const __u64 lseek, unsigned int *nbytes, char **buf,
+extern int CIFSSMBRead(const int xid, struct cifs_io_parms *io_parms,
+			unsigned int *nbytes, char **buf,
 			int *return_buf_type);
-extern int CIFSSMBWrite(const int xid, struct cifsTconInfo *tcon,
-			const int netfid, const unsigned int count,
-			const __u64 lseek, unsigned int *nbytes,
-			const char *buf, const char __user *ubuf,
+extern int CIFSSMBWrite(const int xid, struct cifs_io_parms *io_parms,
+			unsigned int *nbytes, const char *buf,
+			const char __user *ubuf, const int long_op);
+extern int CIFSSMBWrite2(const int xid, struct cifs_io_parms *io_parms,
+			unsigned int *nbytes, struct kvec *iov, const int nvec,
 			const int long_op);
-extern int CIFSSMBWrite2(const int xid, struct cifsTconInfo *tcon,
-			const int netfid, const unsigned int count,
-			const __u64 offset, unsigned int *nbytes,
-			struct kvec *iov, const int nvec, const int long_op);
-extern int CIFSGetSrvInodeNumber(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSGetSrvInodeNumber(const int xid, struct cifs_tcon *tcon,
 			const unsigned char *searchName, __u64 *inode_number,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
 
-extern int CIFSSMBLock(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBLock(const int xid, struct cifs_tcon *tcon,
 			const __u16 netfid, const __u64 len,
 			const __u64 offset, const __u32 numUnlock,
 			const __u32 numLock, const __u8 lockType,
 			const bool waitFlag, const __u8 oplock_level);
-extern int CIFSSMBPosixLock(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBPosixLock(const int xid, struct cifs_tcon *tcon,
 			const __u16 smb_file_id, const int get_flag,
 			const __u64 len, struct file_lock *,
 			const __u16 lock_type, const bool waitFlag);
-extern int CIFSSMBTDis(const int xid, struct cifsTconInfo *tcon);
+extern int CIFSSMBTDis(const int xid, struct cifs_tcon *tcon);
 extern int CIFSSMBEcho(struct TCP_Server_Info *server);
-extern int CIFSSMBLogoff(const int xid, struct cifsSesInfo *ses);
+extern int CIFSSMBLogoff(const int xid, struct cifs_ses *ses);
 
-extern struct cifsSesInfo *sesInfoAlloc(void);
-extern void sesInfoFree(struct cifsSesInfo *);
-extern struct cifsTconInfo *tconInfoAlloc(void);
-extern void tconInfoFree(struct cifsTconInfo *);
+extern struct cifs_ses *sesInfoAlloc(void);
+extern void sesInfoFree(struct cifs_ses *);
+extern struct cifs_tcon *tconInfoAlloc(void);
+extern void tconInfoFree(struct cifs_tcon *);
 
 extern int cifs_sign_smb(struct smb_hdr *, struct TCP_Server_Info *, __u32 *);
 extern int cifs_sign_smb2(struct kvec *iov, int n_vec, struct TCP_Server_Info *,
@@ -379,51 +384,51 @@ extern int cifs_verify_signature(struct smb_hdr *,
 				 struct TCP_Server_Info *server,
 				__u32 expected_sequence_number);
 extern int SMBNTencrypt(unsigned char *, unsigned char *, unsigned char *);
-extern int setup_ntlm_response(struct cifsSesInfo *);
-extern int setup_ntlmv2_rsp(struct cifsSesInfo *, const struct nls_table *);
+extern int setup_ntlm_response(struct cifs_ses *);
+extern int setup_ntlmv2_rsp(struct cifs_ses *, const struct nls_table *);
 extern int cifs_crypto_shash_allocate(struct TCP_Server_Info *);
 extern void cifs_crypto_shash_release(struct TCP_Server_Info *);
-extern int calc_seckey(struct cifsSesInfo *);
+extern int calc_seckey(struct cifs_ses *);
 
 #ifdef CONFIG_CIFS_WEAK_PW_HASH
 extern int calc_lanman_hash(const char *password, const char *cryptkey,
 				bool encrypt, char *lnm_session_key);
 #endif /* CIFS_WEAK_PW_HASH */
 #ifdef CONFIG_CIFS_DNOTIFY_EXPERIMENTAL /* unused temporarily */
-extern int CIFSSMBNotify(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBNotify(const int xid, struct cifs_tcon *tcon,
 			const int notify_subdirs, const __u16 netfid,
 			__u32 filter, struct file *file, int multishot,
 			const struct nls_table *nls_codepage);
 #endif /* was needed for dnotify, and will be needed for inotify when VFS fix */
 extern int CIFSSMBCopy(int xid,
-			struct cifsTconInfo *source_tcon,
+			struct cifs_tcon *source_tcon,
 			const char *fromName,
 			const __u16 target_tid,
 			const char *toName, const int flags,
 			const struct nls_table *nls_codepage,
 			int remap_special_chars);
-extern ssize_t CIFSSMBQAllEAs(const int xid, struct cifsTconInfo *tcon,
+extern ssize_t CIFSSMBQAllEAs(const int xid, struct cifs_tcon *tcon,
 			const unsigned char *searchName,
 			const unsigned char *ea_name, char *EAData,
 			size_t bufsize, const struct nls_table *nls_codepage,
 			int remap_special_chars);
-extern int CIFSSMBSetEA(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBSetEA(const int xid, struct cifs_tcon *tcon,
 		const char *fileName, const char *ea_name,
 		const void *ea_value, const __u16 ea_value_len,
 		const struct nls_table *nls_codepage, int remap_special_chars);
-extern int CIFSSMBGetCIFSACL(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBGetCIFSACL(const int xid, struct cifs_tcon *tcon,
 			__u16 fid, struct cifs_ntsd **acl_inf, __u32 *buflen);
-extern int CIFSSMBSetCIFSACL(const int, struct cifsTconInfo *, __u16,
+extern int CIFSSMBSetCIFSACL(const int, struct cifs_tcon *, __u16,
 			struct cifs_ntsd *, __u32);
-extern int CIFSSMBGetPosixACL(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBGetPosixACL(const int xid, struct cifs_tcon *tcon,
 		const unsigned char *searchName,
 		char *acl_inf, const int buflen, const int acl_type,
 		const struct nls_table *nls_codepage, int remap_special_chars);
-extern int CIFSSMBSetPosixACL(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBSetPosixACL(const int xid, struct cifs_tcon *tcon,
 		const unsigned char *fileName,
 		const char *local_acl, const int buflen, const int acl_type,
 		const struct nls_table *nls_codepage, int remap_special_chars);
-extern int CIFSGetExtAttr(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSGetExtAttr(const int xid, struct cifs_tcon *tcon,
 			const int netfid, __u64 *pExtAttrBits, __u64 *pMask);
 extern void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb);
 extern bool CIFSCouldBeMFSymlink(const struct cifs_fattr *fattr);
@@ -434,4 +439,22 @@ extern int mdfour(unsigned char *, unsigned char *, int);
 extern int E_md4hash(const unsigned char *passwd, unsigned char *p16);
 extern int SMBencrypt(unsigned char *passwd, const unsigned char *c8,
 			unsigned char *p24);
+
+/* asynchronous write support */
+struct cifs_writedata {
+	struct kref			refcount;
+	enum writeback_sync_modes	sync_mode;
+	struct work_struct		work;
+	struct cifsFileInfo		*cfile;
+	__u64				offset;
+	unsigned int			bytes;
+	int				result;
+	unsigned int			nr_pages;
+	struct page			*pages[1];
+};
+
+int cifs_async_writev(struct cifs_writedata *wdata);
+struct cifs_writedata *cifs_writedata_alloc(unsigned int nr_pages);
+void cifs_writedata_release(struct kref *refcount);
+
 #endif			/* _CIFSPROTO_H */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 83df937b814e..1a9fe7f816d1 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -32,6 +32,7 @@
 #include <linux/vfs.h>
 #include <linux/slab.h>
 #include <linux/posix_acl_xattr.h>
+#include <linux/pagemap.h>
 #include <asm/uaccess.h>
 #include "cifspdu.h"
 #include "cifsglob.h"
@@ -84,7 +85,7 @@ static struct {
 
 /* Mark as invalid, all open files on tree connections since they
    were closed when session to server was lost */
-static void mark_open_files_invalid(struct cifsTconInfo *pTcon)
+static void mark_open_files_invalid(struct cifs_tcon *pTcon)
 {
 	struct cifsFileInfo *open_file = NULL;
 	struct list_head *tmp;
@@ -104,10 +105,10 @@ static void mark_open_files_invalid(struct cifsTconInfo *pTcon)
 
 /* reconnect the socket, tcon, and smb session if needed */
 static int
-cifs_reconnect_tcon(struct cifsTconInfo *tcon, int smb_command)
+cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command)
 {
 	int rc = 0;
-	struct cifsSesInfo *ses;
+	struct cifs_ses *ses;
 	struct TCP_Server_Info *server;
 	struct nls_table *nls_codepage;
 
@@ -226,7 +227,7 @@ out:
    SMB information in the SMB header.  If the return code is zero, this
    function must have filled in request_buf pointer */
 static int
-small_smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
+small_smb_init(int smb_command, int wct, struct cifs_tcon *tcon,
 		void **request_buf)
 {
 	int rc;
@@ -252,7 +253,7 @@ small_smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
 
 int
 small_smb_init_no_tc(const int smb_command, const int wct,
-		     struct cifsSesInfo *ses, void **request_buf)
+		     struct cifs_ses *ses, void **request_buf)
 {
 	int rc;
 	struct smb_hdr *buffer;
@@ -278,7 +279,7 @@ small_smb_init_no_tc(const int smb_command, const int wct,
 
 /* If the return code is zero, this function must fill in request_buf pointer */
 static int
-__smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
+__smb_init(int smb_command, int wct, struct cifs_tcon *tcon,
 			void **request_buf, void **response_buf)
 {
 	*request_buf = cifs_buf_get();
@@ -304,7 +305,7 @@ __smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
 
 /* If the return code is zero, this function must fill in request_buf pointer */
 static int
-smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
+smb_init(int smb_command, int wct, struct cifs_tcon *tcon,
 	 void **request_buf, void **response_buf)
 {
 	int rc;
@@ -317,7 +318,7 @@ smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
 }
 
 static int
-smb_init_no_reconnect(int smb_command, int wct, struct cifsTconInfo *tcon,
+smb_init_no_reconnect(int smb_command, int wct, struct cifs_tcon *tcon,
 			void **request_buf, void **response_buf)
 {
 	if (tcon->ses->need_reconnect || tcon->need_reconnect)
@@ -366,7 +367,7 @@ static inline void inc_rfc1001_len(void *pSMB, int count)
 }
 
 int
-CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
+CIFSSMBNegotiate(unsigned int xid, struct cifs_ses *ses)
 {
 	NEGOTIATE_REQ *pSMB;
 	NEGOTIATE_RSP *pSMBr;
@@ -450,7 +451,7 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
 			rc = -EOPNOTSUPP;
 			goto neg_err_exit;
 		}
-		server->secMode = (__u8)le16_to_cpu(rsp->SecurityMode);
+		server->sec_mode = (__u8)le16_to_cpu(rsp->SecurityMode);
 		server->maxReq = le16_to_cpu(rsp->MaxMpxCount);
 		server->maxBuf = min((__u32)le16_to_cpu(rsp->MaxBufSize),
 				(__u32)CIFSMaxBufSize + MAX_CIFS_HDR_SIZE);
@@ -504,7 +505,7 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
 				cpu_to_le16(CIFS_CRYPTO_KEY_SIZE)) {
 			memcpy(ses->server->cryptkey, rsp->EncryptionKey,
 				CIFS_CRYPTO_KEY_SIZE);
-		} else if (server->secMode & SECMODE_PW_ENCRYPT) {
+		} else if (server->sec_mode & SECMODE_PW_ENCRYPT) {
 			rc = -EIO; /* need cryptkey unless plain text */
 			goto neg_err_exit;
 		}
@@ -526,11 +527,11 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
 		goto neg_err_exit;
 	}
 	/* else wct == 17 NTLM */
-	server->secMode = pSMBr->SecurityMode;
-	if ((server->secMode & SECMODE_USER) == 0)
+	server->sec_mode = pSMBr->SecurityMode;
+	if ((server->sec_mode & SECMODE_USER) == 0)
 		cFYI(1, "share mode security");
 
-	if ((server->secMode & SECMODE_PW_ENCRYPT) == 0)
+	if ((server->sec_mode & SECMODE_PW_ENCRYPT) == 0)
 #ifdef CONFIG_CIFS_WEAK_PW_HASH
 		if ((secFlags & CIFSSEC_MAY_PLNTXT) == 0)
 #endif /* CIFS_WEAK_PW_HASH */
@@ -570,18 +571,10 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
 	if (pSMBr->EncryptionKeyLength == CIFS_CRYPTO_KEY_SIZE) {
 		memcpy(ses->server->cryptkey, pSMBr->u.EncryptionKey,
 		       CIFS_CRYPTO_KEY_SIZE);
-	} else if ((pSMBr->hdr.Flags2 & SMBFLG2_EXT_SEC)
-			&& (pSMBr->EncryptionKeyLength == 0)) {
+	} else if ((pSMBr->hdr.Flags2 & SMBFLG2_EXT_SEC ||
+			server->capabilities & CAP_EXTENDED_SECURITY) &&
+				(pSMBr->EncryptionKeyLength == 0)) {
 		/* decode security blob */
-	} else if (server->secMode & SECMODE_PW_ENCRYPT) {
-		rc = -EIO; /* no crypt key only if plain text pwd */
-		goto neg_err_exit;
-	}
-
-	/* BB might be helpful to save off the domain of server here */
-
-	if ((pSMBr->hdr.Flags2 & SMBFLG2_EXT_SEC) &&
-		(server->capabilities & CAP_EXTENDED_SECURITY)) {
 		count = get_bcc(&pSMBr->hdr);
 		if (count < 16) {
 			rc = -EIO;
@@ -624,6 +617,9 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
 			} else
 					rc = -EOPNOTSUPP;
 		}
+	} else if (server->sec_mode & SECMODE_PW_ENCRYPT) {
+		rc = -EIO; /* no crypt key only if plain text pwd */
+		goto neg_err_exit;
 	} else
 		server->capabilities &= ~CAP_EXTENDED_SECURITY;
 
@@ -634,27 +630,27 @@ signing_check:
 		/* MUST_SIGN already includes the MAY_SIGN FLAG
 		   so if this is zero it means that signing is disabled */
 		cFYI(1, "Signing disabled");
-		if (server->secMode & SECMODE_SIGN_REQUIRED) {
+		if (server->sec_mode & SECMODE_SIGN_REQUIRED) {
 			cERROR(1, "Server requires "
 				   "packet signing to be enabled in "
 				   "/proc/fs/cifs/SecurityFlags.");
 			rc = -EOPNOTSUPP;
 		}
-		server->secMode &=
+		server->sec_mode &=
 			~(SECMODE_SIGN_ENABLED | SECMODE_SIGN_REQUIRED);
 	} else if ((secFlags & CIFSSEC_MUST_SIGN) == CIFSSEC_MUST_SIGN) {
 		/* signing required */
 		cFYI(1, "Must sign - secFlags 0x%x", secFlags);
-		if ((server->secMode &
+		if ((server->sec_mode &
 			(SECMODE_SIGN_ENABLED | SECMODE_SIGN_REQUIRED)) == 0) {
 			cERROR(1, "signing required but server lacks support");
 			rc = -EOPNOTSUPP;
 		} else
-			server->secMode |= SECMODE_SIGN_REQUIRED;
+			server->sec_mode |= SECMODE_SIGN_REQUIRED;
 	} else {
 		/* signing optional ie CIFSSEC_MAY_SIGN */
-		if ((server->secMode & SECMODE_SIGN_REQUIRED) == 0)
-			server->secMode &=
+		if ((server->sec_mode & SECMODE_SIGN_REQUIRED) == 0)
+			server->sec_mode &=
 				~(SECMODE_SIGN_ENABLED | SECMODE_SIGN_REQUIRED);
 	}
 
@@ -666,7 +662,7 @@ neg_err_exit:
 }
 
 int
-CIFSSMBTDis(const int xid, struct cifsTconInfo *tcon)
+CIFSSMBTDis(const int xid, struct cifs_tcon *tcon)
 {
 	struct smb_hdr *smb_buffer;
 	int rc = 0;
@@ -725,6 +721,7 @@ CIFSSMBEcho(struct TCP_Server_Info *server)
 {
 	ECHO_REQ *smb;
 	int rc = 0;
+	struct kvec iov;
 
 	cFYI(1, "In echo request");
 
@@ -739,9 +736,10 @@ CIFSSMBEcho(struct TCP_Server_Info *server)
 	put_bcc(1, &smb->hdr);
 	smb->Data[0] = 'a';
 	inc_rfc1001_len(smb, 3);
+	iov.iov_base = smb;
+	iov.iov_len = be32_to_cpu(smb->hdr.smb_buf_length) + 4;
 
-	rc = cifs_call_async(server, (struct smb_hdr *)smb,
-				cifs_echo_callback, server);
+	rc = cifs_call_async(server, &iov, 1, cifs_echo_callback, server, true);
 	if (rc)
 		cFYI(1, "Echo request failed: %d", rc);
 
@@ -751,7 +749,7 @@ CIFSSMBEcho(struct TCP_Server_Info *server)
 }
 
 int
-CIFSSMBLogoff(const int xid, struct cifsSesInfo *ses)
+CIFSSMBLogoff(const int xid, struct cifs_ses *ses)
 {
 	LOGOFF_ANDX_REQ *pSMB;
 	int rc = 0;
@@ -778,7 +776,7 @@ CIFSSMBLogoff(const int xid, struct cifsSesInfo *ses)
 
 	pSMB->hdr.Mid = GetNextMid(ses->server);
 
-	if (ses->server->secMode &
+	if (ses->server->sec_mode &
 		   (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
 			pSMB->hdr.Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
 
@@ -798,7 +796,7 @@ session_already_dead:
 }
 
 int
-CIFSPOSIXDelFile(const int xid, struct cifsTconInfo *tcon, const char *fileName,
+CIFSPOSIXDelFile(const int xid, struct cifs_tcon *tcon, const char *fileName,
 		 __u16 type, const struct nls_table *nls_codepage, int remap)
 {
 	TRANSACTION2_SPI_REQ *pSMB = NULL;
@@ -873,7 +871,7 @@ PsxDelete:
 }
 
 int
-CIFSSMBDelFile(const int xid, struct cifsTconInfo *tcon, const char *fileName,
+CIFSSMBDelFile(const int xid, struct cifs_tcon *tcon, const char *fileName,
 	       const struct nls_table *nls_codepage, int remap)
 {
 	DELETE_FILE_REQ *pSMB = NULL;
@@ -918,7 +916,7 @@ DelFileRetry:
 }
 
 int
-CIFSSMBRmDir(const int xid, struct cifsTconInfo *tcon, const char *dirName,
+CIFSSMBRmDir(const int xid, struct cifs_tcon *tcon, const char *dirName,
 	     const struct nls_table *nls_codepage, int remap)
 {
 	DELETE_DIRECTORY_REQ *pSMB = NULL;
@@ -961,7 +959,7 @@ RmDirRetry:
 }
 
 int
-CIFSSMBMkDir(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBMkDir(const int xid, struct cifs_tcon *tcon,
 	     const char *name, const struct nls_table *nls_codepage, int remap)
 {
 	int rc = 0;
@@ -1004,7 +1002,7 @@ MkDirRetry:
 }
 
 int
-CIFSPOSIXCreate(const int xid, struct cifsTconInfo *tcon, __u32 posix_flags,
+CIFSPOSIXCreate(const int xid, struct cifs_tcon *tcon, __u32 posix_flags,
 		__u64 mode, __u16 *netfid, FILE_UNIX_BASIC_INFO *pRetData,
 		__u32 *pOplock, const char *name,
 		const struct nls_table *nls_codepage, int remap)
@@ -1170,7 +1168,7 @@ access_flags_to_smbopen_mode(const int access_flags)
 }
 
 int
-SMBLegacyOpen(const int xid, struct cifsTconInfo *tcon,
+SMBLegacyOpen(const int xid, struct cifs_tcon *tcon,
 	    const char *fileName, const int openDisposition,
 	    const int access_flags, const int create_options, __u16 *netfid,
 	    int *pOplock, FILE_ALL_INFO *pfile_info,
@@ -1277,7 +1275,7 @@ OldOpenRetry:
 }
 
 int
-CIFSSMBOpen(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBOpen(const int xid, struct cifs_tcon *tcon,
 	    const char *fileName, const int openDisposition,
 	    const int access_flags, const int create_options, __u16 *netfid,
 	    int *pOplock, FILE_ALL_INFO *pfile_info,
@@ -1379,8 +1377,7 @@ openRetry:
 }
 
 int
-CIFSSMBRead(const int xid, struct cifsTconInfo *tcon, const int netfid,
-	    const unsigned int count, const __u64 lseek, unsigned int *nbytes,
+CIFSSMBRead(const int xid, struct cifs_io_parms *io_parms, unsigned int *nbytes,
 	    char **buf, int *pbuf_type)
 {
 	int rc = -EACCES;
@@ -1390,13 +1387,18 @@ CIFSSMBRead(const int xid, struct cifsTconInfo *tcon, const int netfid,
 	int wct;
 	int resp_buf_type = 0;
 	struct kvec iov[1];
+	__u32 pid = io_parms->pid;
+	__u16 netfid = io_parms->netfid;
+	__u64 offset = io_parms->offset;
+	struct cifs_tcon *tcon = io_parms->tcon;
+	unsigned int count = io_parms->length;
 
 	cFYI(1, "Reading %d bytes on fid %d", count, netfid);
 	if (tcon->ses->capabilities & CAP_LARGE_FILES)
 		wct = 12;
 	else {
 		wct = 10; /* old style read */
-		if ((lseek >> 32) > 0)  {
+		if ((offset >> 32) > 0)  {
 			/* can not handle this big offset for old */
 			return -EIO;
 		}
@@ -1407,15 +1409,18 @@ CIFSSMBRead(const int xid, struct cifsTconInfo *tcon, const int netfid,
 	if (rc)
 		return rc;
 
+	pSMB->hdr.Pid = cpu_to_le16((__u16)pid);
+	pSMB->hdr.PidHigh = cpu_to_le16((__u16)(pid >> 16));
+
 	/* tcon and ses pointer are checked in smb_init */
 	if (tcon->ses->server == NULL)
 		return -ECONNABORTED;
 
 	pSMB->AndXCommand = 0xFF;       /* none */
 	pSMB->Fid = netfid;
-	pSMB->OffsetLow = cpu_to_le32(lseek & 0xFFFFFFFF);
+	pSMB->OffsetLow = cpu_to_le32(offset & 0xFFFFFFFF);
 	if (wct == 12)
-		pSMB->OffsetHigh = cpu_to_le32(lseek >> 32);
+		pSMB->OffsetHigh = cpu_to_le32(offset >> 32);
 
 	pSMB->Remaining = 0;
 	pSMB->MaxCount = cpu_to_le16(count & 0xFFFF);
@@ -1484,9 +1489,8 @@ CIFSSMBRead(const int xid, struct cifsTconInfo *tcon, const int netfid,
 
 
 int
-CIFSSMBWrite(const int xid, struct cifsTconInfo *tcon,
-	     const int netfid, const unsigned int count,
-	     const __u64 offset, unsigned int *nbytes, const char *buf,
+CIFSSMBWrite(const int xid, struct cifs_io_parms *io_parms,
+	     unsigned int *nbytes, const char *buf,
 	     const char __user *ubuf, const int long_op)
 {
 	int rc = -EACCES;
@@ -1495,6 +1499,11 @@ CIFSSMBWrite(const int xid, struct cifsTconInfo *tcon,
 	int bytes_returned, wct;
 	__u32 bytes_sent;
 	__u16 byte_count;
+	__u32 pid = io_parms->pid;
+	__u16 netfid = io_parms->netfid;
+	__u64 offset = io_parms->offset;
+	struct cifs_tcon *tcon = io_parms->tcon;
+	unsigned int count = io_parms->length;
 
 	*nbytes = 0;
 
@@ -1516,6 +1525,10 @@ CIFSSMBWrite(const int xid, struct cifsTconInfo *tcon,
 		      (void **) &pSMBr);
 	if (rc)
 		return rc;
+
+	pSMB->hdr.Pid = cpu_to_le16((__u16)pid);
+	pSMB->hdr.PidHigh = cpu_to_le16((__u16)(pid >> 16));
+
 	/* tcon and ses pointer are checked in smb_init */
 	if (tcon->ses->server == NULL)
 		return -ECONNABORTED;
@@ -1602,17 +1615,259 @@ CIFSSMBWrite(const int xid, struct cifsTconInfo *tcon,
 	return rc;
 }
 
+void
+cifs_writedata_release(struct kref *refcount)
+{
+	struct cifs_writedata *wdata = container_of(refcount,
+					struct cifs_writedata, refcount);
+
+	if (wdata->cfile)
+		cifsFileInfo_put(wdata->cfile);
+
+	kfree(wdata);
+}
+
+/*
+ * Write failed with a retryable error. Resend the write request. It's also
+ * possible that the page was redirtied so re-clean the page.
+ */
+static void
+cifs_writev_requeue(struct cifs_writedata *wdata)
+{
+	int i, rc;
+	struct inode *inode = wdata->cfile->dentry->d_inode;
+
+	for (i = 0; i < wdata->nr_pages; i++) {
+		lock_page(wdata->pages[i]);
+		clear_page_dirty_for_io(wdata->pages[i]);
+	}
+
+	do {
+		rc = cifs_async_writev(wdata);
+	} while (rc == -EAGAIN);
+
+	for (i = 0; i < wdata->nr_pages; i++) {
+		if (rc != 0)
+			SetPageError(wdata->pages[i]);
+		unlock_page(wdata->pages[i]);
+	}
+
+	mapping_set_error(inode->i_mapping, rc);
+	kref_put(&wdata->refcount, cifs_writedata_release);
+}
+
+static void
+cifs_writev_complete(struct work_struct *work)
+{
+	struct cifs_writedata *wdata = container_of(work,
+						struct cifs_writedata, work);
+	struct inode *inode = wdata->cfile->dentry->d_inode;
+	int i = 0;
+
+	if (wdata->result == 0) {
+		cifs_update_eof(CIFS_I(inode), wdata->offset, wdata->bytes);
+		cifs_stats_bytes_written(tlink_tcon(wdata->cfile->tlink),
+					 wdata->bytes);
+	} else if (wdata->sync_mode == WB_SYNC_ALL && wdata->result == -EAGAIN)
+		return cifs_writev_requeue(wdata);
+
+	for (i = 0; i < wdata->nr_pages; i++) {
+		struct page *page = wdata->pages[i];
+		if (wdata->result == -EAGAIN)
+			__set_page_dirty_nobuffers(page);
+		else if (wdata->result < 0)
+			SetPageError(page);
+		end_page_writeback(page);
+		page_cache_release(page);
+	}
+	if (wdata->result != -EAGAIN)
+		mapping_set_error(inode->i_mapping, wdata->result);
+	kref_put(&wdata->refcount, cifs_writedata_release);
+}
+
+struct cifs_writedata *
+cifs_writedata_alloc(unsigned int nr_pages)
+{
+	struct cifs_writedata *wdata;
+
+	/* this would overflow */
+	if (nr_pages == 0) {
+		cERROR(1, "%s: called with nr_pages == 0!", __func__);
+		return NULL;
+	}
+
+	/* writedata + number of page pointers */
+	wdata = kzalloc(sizeof(*wdata) +
+			sizeof(struct page *) * (nr_pages - 1), GFP_NOFS);
+	if (wdata != NULL) {
+		INIT_WORK(&wdata->work, cifs_writev_complete);
+		kref_init(&wdata->refcount);
+	}
+	return wdata;
+}
+
+/*
+ * Check the midState and signature on received buffer (if any), and queue the
+ * workqueue completion task.
+ */
+static void
+cifs_writev_callback(struct mid_q_entry *mid)
+{
+	struct cifs_writedata *wdata = mid->callback_data;
+	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
+	unsigned int written;
+	WRITE_RSP *smb = (WRITE_RSP *)mid->resp_buf;
+
+	switch (mid->midState) {
+	case MID_RESPONSE_RECEIVED:
+		wdata->result = cifs_check_receive(mid, tcon->ses->server, 0);
+		if (wdata->result != 0)
+			break;
+
+		written = le16_to_cpu(smb->CountHigh);
+		written <<= 16;
+		written += le16_to_cpu(smb->Count);
+		/*
+		 * Mask off high 16 bits when bytes written as returned
+		 * by the server is greater than bytes requested by the
+		 * client. OS/2 servers are known to set incorrect
+		 * CountHigh values.
+		 */
+		if (written > wdata->bytes)
+			written &= 0xFFFF;
+
+		if (written < wdata->bytes)
+			wdata->result = -ENOSPC;
+		else
+			wdata->bytes = written;
+		break;
+	case MID_REQUEST_SUBMITTED:
+	case MID_RETRY_NEEDED:
+		wdata->result = -EAGAIN;
+		break;
+	default:
+		wdata->result = -EIO;
+		break;
+	}
+
+	queue_work(system_nrt_wq, &wdata->work);
+	DeleteMidQEntry(mid);
+	atomic_dec(&tcon->ses->server->inFlight);
+	wake_up(&tcon->ses->server->request_q);
+}
+
+/* cifs_async_writev - send an async write, and set up mid to handle result */
+int
+cifs_async_writev(struct cifs_writedata *wdata)
+{
+	int i, rc = -EACCES;
+	WRITE_REQ *smb = NULL;
+	int wct;
+	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
+	struct inode *inode = wdata->cfile->dentry->d_inode;
+	struct kvec *iov = NULL;
+
+	if (tcon->ses->capabilities & CAP_LARGE_FILES) {
+		wct = 14;
+	} else {
+		wct = 12;
+		if (wdata->offset >> 32 > 0) {
+			/* can not handle big offset for old srv */
+			return -EIO;
+		}
+	}
+
+	rc = small_smb_init(SMB_COM_WRITE_ANDX, wct, tcon, (void **)&smb);
+	if (rc)
+		goto async_writev_out;
+
+	/* 1 iov per page + 1 for header */
+	iov = kzalloc((wdata->nr_pages + 1) * sizeof(*iov), GFP_NOFS);
+	if (iov == NULL) {
+		rc = -ENOMEM;
+		goto async_writev_out;
+	}
+
+	smb->hdr.Pid = cpu_to_le16((__u16)wdata->cfile->pid);
+	smb->hdr.PidHigh = cpu_to_le16((__u16)(wdata->cfile->pid >> 16));
+
+	smb->AndXCommand = 0xFF;	/* none */
+	smb->Fid = wdata->cfile->netfid;
+	smb->OffsetLow = cpu_to_le32(wdata->offset & 0xFFFFFFFF);
+	if (wct == 14)
+		smb->OffsetHigh = cpu_to_le32(wdata->offset >> 32);
+	smb->Reserved = 0xFFFFFFFF;
+	smb->WriteMode = 0;
+	smb->Remaining = 0;
+
+	smb->DataOffset =
+	    cpu_to_le16(offsetof(struct smb_com_write_req, Data) - 4);
+
+	/* 4 for RFC1001 length + 1 for BCC */
+	iov[0].iov_len = be32_to_cpu(smb->hdr.smb_buf_length) + 4 + 1;
+	iov[0].iov_base = smb;
+
+	/* marshal up the pages into iov array */
+	wdata->bytes = 0;
+	for (i = 0; i < wdata->nr_pages; i++) {
+		iov[i + 1].iov_len = min(inode->i_size -
+				      page_offset(wdata->pages[i]),
+					(loff_t)PAGE_CACHE_SIZE);
+		iov[i + 1].iov_base = kmap(wdata->pages[i]);
+		wdata->bytes += iov[i + 1].iov_len;
+	}
+
+	cFYI(1, "async write at %llu %u bytes", wdata->offset, wdata->bytes);
+
+	smb->DataLengthLow = cpu_to_le16(wdata->bytes & 0xFFFF);
+	smb->DataLengthHigh = cpu_to_le16(wdata->bytes >> 16);
+
+	if (wct == 14) {
+		inc_rfc1001_len(&smb->hdr, wdata->bytes + 1);
+		put_bcc(wdata->bytes + 1, &smb->hdr);
+	} else {
+		/* wct == 12 */
+		struct smb_com_writex_req *smbw =
+				(struct smb_com_writex_req *)smb;
+		inc_rfc1001_len(&smbw->hdr, wdata->bytes + 5);
+		put_bcc(wdata->bytes + 5, &smbw->hdr);
+		iov[0].iov_len += 4; /* pad bigger by four bytes */
+	}
+
+	kref_get(&wdata->refcount);
+	rc = cifs_call_async(tcon->ses->server, iov, wdata->nr_pages + 1,
+			     cifs_writev_callback, wdata, false);
+
+	if (rc == 0)
+		cifs_stats_inc(&tcon->num_writes);
+	else
+		kref_put(&wdata->refcount, cifs_writedata_release);
+
+	/* send is done, unmap pages */
+	for (i = 0; i < wdata->nr_pages; i++)
+		kunmap(wdata->pages[i]);
+
+async_writev_out:
+	cifs_small_buf_release(smb);
+	kfree(iov);
+	return rc;
+}
+
 int
-CIFSSMBWrite2(const int xid, struct cifsTconInfo *tcon,
-	     const int netfid, const unsigned int count,
-	     const __u64 offset, unsigned int *nbytes, struct kvec *iov,
-	     int n_vec, const int long_op)
+CIFSSMBWrite2(const int xid, struct cifs_io_parms *io_parms,
+	      unsigned int *nbytes, struct kvec *iov, int n_vec,
+	      const int long_op)
 {
 	int rc = -EACCES;
 	WRITE_REQ *pSMB = NULL;
 	int wct;
 	int smb_hdr_len;
 	int resp_buf_type = 0;
+	__u32 pid = io_parms->pid;
+	__u16 netfid = io_parms->netfid;
+	__u64 offset = io_parms->offset;
+	struct cifs_tcon *tcon = io_parms->tcon;
+	unsigned int count = io_parms->length;
 
 	*nbytes = 0;
 
@@ -1630,6 +1885,10 @@ CIFSSMBWrite2(const int xid, struct cifsTconInfo *tcon,
 	rc = small_smb_init(SMB_COM_WRITE_ANDX, wct, tcon, (void **) &pSMB);
 	if (rc)
 		return rc;
+
+	pSMB->hdr.Pid = cpu_to_le16((__u16)pid);
+	pSMB->hdr.PidHigh = cpu_to_le16((__u16)(pid >> 16));
+
 	/* tcon and ses pointer are checked in smb_init */
 	if (tcon->ses->server == NULL)
 		return -ECONNABORTED;
@@ -1705,7 +1964,7 @@ CIFSSMBWrite2(const int xid, struct cifsTconInfo *tcon,
 
 
 int
-CIFSSMBLock(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBLock(const int xid, struct cifs_tcon *tcon,
 	    const __u16 smb_file_id, const __u64 len,
 	    const __u64 offset, const __u32 numUnlock,
 	    const __u32 numLock, const __u8 lockType,
@@ -1775,7 +2034,7 @@ CIFSSMBLock(const int xid, struct cifsTconInfo *tcon,
 }
 
 int
-CIFSSMBPosixLock(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBPosixLock(const int xid, struct cifs_tcon *tcon,
 		const __u16 smb_file_id, const int get_flag, const __u64 len,
 		struct file_lock *pLockData, const __u16 lock_type,
 		const bool waitFlag)
@@ -1913,7 +2172,7 @@ plk_err_exit:
 
 
 int
-CIFSSMBClose(const int xid, struct cifsTconInfo *tcon, int smb_file_id)
+CIFSSMBClose(const int xid, struct cifs_tcon *tcon, int smb_file_id)
 {
 	int rc = 0;
 	CLOSE_REQ *pSMB = NULL;
@@ -1946,7 +2205,7 @@ CIFSSMBClose(const int xid, struct cifsTconInfo *tcon, int smb_file_id)
 }
 
 int
-CIFSSMBFlush(const int xid, struct cifsTconInfo *tcon, int smb_file_id)
+CIFSSMBFlush(const int xid, struct cifs_tcon *tcon, int smb_file_id)
 {
 	int rc = 0;
 	FLUSH_REQ *pSMB = NULL;
@@ -1967,7 +2226,7 @@ CIFSSMBFlush(const int xid, struct cifsTconInfo *tcon, int smb_file_id)
 }
 
 int
-CIFSSMBRename(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBRename(const int xid, struct cifs_tcon *tcon,
 	      const char *fromName, const char *toName,
 	      const struct nls_table *nls_codepage, int remap)
 {
@@ -2034,7 +2293,7 @@ renameRetry:
 	return rc;
 }
 
-int CIFSSMBRenameOpenFile(const int xid, struct cifsTconInfo *pTcon,
+int CIFSSMBRenameOpenFile(const int xid, struct cifs_tcon *pTcon,
 		int netfid, const char *target_name,
 		const struct nls_table *nls_codepage, int remap)
 {
@@ -2114,7 +2373,7 @@ int CIFSSMBRenameOpenFile(const int xid, struct cifsTconInfo *pTcon,
 }
 
 int
-CIFSSMBCopy(const int xid, struct cifsTconInfo *tcon, const char *fromName,
+CIFSSMBCopy(const int xid, struct cifs_tcon *tcon, const char *fromName,
 	    const __u16 target_tid, const char *toName, const int flags,
 	    const struct nls_table *nls_codepage, int remap)
 {
@@ -2182,7 +2441,7 @@ copyRetry:
 }
 
 int
-CIFSUnixCreateSymLink(const int xid, struct cifsTconInfo *tcon,
+CIFSUnixCreateSymLink(const int xid, struct cifs_tcon *tcon,
 		      const char *fromName, const char *toName,
 		      const struct nls_table *nls_codepage)
 {
@@ -2271,7 +2530,7 @@ createSymLinkRetry:
 }
 
 int
-CIFSUnixCreateHardLink(const int xid, struct cifsTconInfo *tcon,
+CIFSUnixCreateHardLink(const int xid, struct cifs_tcon *tcon,
 		       const char *fromName, const char *toName,
 		       const struct nls_table *nls_codepage, int remap)
 {
@@ -2356,7 +2615,7 @@ createHardLinkRetry:
 }
 
 int
-CIFSCreateHardLink(const int xid, struct cifsTconInfo *tcon,
+CIFSCreateHardLink(const int xid, struct cifs_tcon *tcon,
 		   const char *fromName, const char *toName,
 		   const struct nls_table *nls_codepage, int remap)
 {
@@ -2428,7 +2687,7 @@ winCreateHardLinkRetry:
 }
 
 int
-CIFSSMBUnixQuerySymLink(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBUnixQuerySymLink(const int xid, struct cifs_tcon *tcon,
 			const unsigned char *searchName, char **symlinkinfo,
 			const struct nls_table *nls_codepage)
 {
@@ -2533,7 +2792,7 @@ querySymLinkRetry:
  *	it is not compiled in by default until callers fixed up and more tested.
  */
 int
-CIFSSMBQueryReparseLinkInfo(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBQueryReparseLinkInfo(const int xid, struct cifs_tcon *tcon,
 			const unsigned char *searchName,
 			char *symlinkinfo, const int buflen, __u16 fid,
 			const struct nls_table *nls_codepage)
@@ -2771,7 +3030,7 @@ static __u16 ACL_to_cifs_posix(char *parm_data, const char *pACL,
 }
 
 int
-CIFSSMBGetPosixACL(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBGetPosixACL(const int xid, struct cifs_tcon *tcon,
 		   const unsigned char *searchName,
 		   char *acl_inf, const int buflen, const int acl_type,
 		   const struct nls_table *nls_codepage, int remap)
@@ -2859,7 +3118,7 @@ queryAclRetry:
 }
 
 int
-CIFSSMBSetPosixACL(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBSetPosixACL(const int xid, struct cifs_tcon *tcon,
 		   const unsigned char *fileName,
 		   const char *local_acl, const int buflen,
 		   const int acl_type,
@@ -2939,7 +3198,7 @@ setACLerrorExit:
 
 /* BB fix tabs in this function FIXME BB */
 int
-CIFSGetExtAttr(const int xid, struct cifsTconInfo *tcon,
+CIFSGetExtAttr(const int xid, struct cifs_tcon *tcon,
 	       const int netfid, __u64 *pExtAttrBits, __u64 *pMask)
 {
 	int rc = 0;
@@ -3032,7 +3291,7 @@ GetExtAttrOut:
  */
 static int
 smb_init_nttransact(const __u16 sub_command, const int setup_count,
-		   const int parm_len, struct cifsTconInfo *tcon,
+		   const int parm_len, struct cifs_tcon *tcon,
 		   void **ret_buf)
 {
 	int rc;
@@ -3115,7 +3374,7 @@ validate_ntransact(char *buf, char **ppparm, char **ppdata,
 
 /* Get Security Descriptor (by handle) from remote server for a file or dir */
 int
-CIFSSMBGetCIFSACL(const int xid, struct cifsTconInfo *tcon, __u16 fid,
+CIFSSMBGetCIFSACL(const int xid, struct cifs_tcon *tcon, __u16 fid,
 		  struct cifs_ntsd **acl_inf, __u32 *pbuflen)
 {
 	int rc = 0;
@@ -3207,7 +3466,7 @@ qsec_out:
 }
 
 int
-CIFSSMBSetCIFSACL(const int xid, struct cifsTconInfo *tcon, __u16 fid,
+CIFSSMBSetCIFSACL(const int xid, struct cifs_tcon *tcon, __u16 fid,
 			struct cifs_ntsd *pntsd, __u32 acllen)
 {
 	__u16 byte_count, param_count, data_count, param_offset, data_offset;
@@ -3273,7 +3532,7 @@ setCifsAclRetry:
 
 /* Legacy Query Path Information call for lookup to old servers such
    as Win9x/WinME */
-int SMBQueryInformation(const int xid, struct cifsTconInfo *tcon,
+int SMBQueryInformation(const int xid, struct cifs_tcon *tcon,
 			const unsigned char *searchName,
 			FILE_ALL_INFO *pFinfo,
 			const struct nls_table *nls_codepage, int remap)
@@ -3341,7 +3600,7 @@ QInfRetry:
 }
 
 int
-CIFSSMBQFileInfo(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBQFileInfo(const int xid, struct cifs_tcon *tcon,
 		 u16 netfid, FILE_ALL_INFO *pFindData)
 {
 	struct smb_t2_qfi_req *pSMB = NULL;
@@ -3408,7 +3667,7 @@ QFileInfoRetry:
 }
 
 int
-CIFSSMBQPathInfo(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBQPathInfo(const int xid, struct cifs_tcon *tcon,
 		 const unsigned char *searchName,
 		 FILE_ALL_INFO *pFindData,
 		 int legacy /* old style infolevel */,
@@ -3509,7 +3768,7 @@ QPathInfoRetry:
 }
 
 int
-CIFSSMBUnixQFileInfo(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBUnixQFileInfo(const int xid, struct cifs_tcon *tcon,
 		 u16 netfid, FILE_UNIX_BASIC_INFO *pFindData)
 {
 	struct smb_t2_qfi_req *pSMB = NULL;
@@ -3578,7 +3837,7 @@ UnixQFileInfoRetry:
 }
 
 int
-CIFSSMBUnixQPathInfo(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBUnixQPathInfo(const int xid, struct cifs_tcon *tcon,
 		     const unsigned char *searchName,
 		     FILE_UNIX_BASIC_INFO *pFindData,
 		     const struct nls_table *nls_codepage, int remap)
@@ -3664,7 +3923,7 @@ UnixQPathInfoRetry:
 
 /* xid, tcon, searchName and codepage are input parms, rest are returned */
 int
-CIFSFindFirst(const int xid, struct cifsTconInfo *tcon,
+CIFSFindFirst(const int xid, struct cifs_tcon *tcon,
 	      const char *searchName,
 	      const struct nls_table *nls_codepage,
 	      __u16 *pnetfid,
@@ -3812,7 +4071,7 @@ findFirstRetry:
 	return rc;
 }
 
-int CIFSFindNext(const int xid, struct cifsTconInfo *tcon,
+int CIFSFindNext(const int xid, struct cifs_tcon *tcon,
 		 __u16 searchHandle, struct cifs_search_info *psrch_inf)
 {
 	TRANSACTION2_FNEXT_REQ *pSMB = NULL;
@@ -3950,7 +4209,7 @@ FNext2_err_exit:
 }
 
 int
-CIFSFindClose(const int xid, struct cifsTconInfo *tcon,
+CIFSFindClose(const int xid, struct cifs_tcon *tcon,
 	      const __u16 searchHandle)
 {
 	int rc = 0;
@@ -3982,7 +4241,7 @@ CIFSFindClose(const int xid, struct cifsTconInfo *tcon,
 }
 
 int
-CIFSGetSrvInodeNumber(const int xid, struct cifsTconInfo *tcon,
+CIFSGetSrvInodeNumber(const int xid, struct cifs_tcon *tcon,
 		      const unsigned char *searchName,
 		      __u64 *inode_number,
 		      const struct nls_table *nls_codepage, int remap)
@@ -4184,7 +4443,7 @@ parse_DFS_referrals_exit:
 }
 
 int
-CIFSGetDFSRefer(const int xid, struct cifsSesInfo *ses,
+CIFSGetDFSRefer(const int xid, struct cifs_ses *ses,
 		const unsigned char *searchName,
 		struct dfs_info3_param **target_nodes,
 		unsigned int *num_of_nodes,
@@ -4233,7 +4492,7 @@ getDFSRetry:
 	}
 
 	if (ses->server) {
-		if (ses->server->secMode &
+		if (ses->server->sec_mode &
 		   (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
 			pSMB->hdr.Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
 	}
@@ -4298,7 +4557,7 @@ GetDFSRefExit:
 
 /* Query File System Info such as free space to old servers such as Win 9x */
 int
-SMBOldQFSInfo(const int xid, struct cifsTconInfo *tcon, struct kstatfs *FSData)
+SMBOldQFSInfo(const int xid, struct cifs_tcon *tcon, struct kstatfs *FSData)
 {
 /* level 0x01 SMB_QUERY_FILE_SYSTEM_INFO */
 	TRANSACTION2_QFSI_REQ *pSMB = NULL;
@@ -4377,7 +4636,7 @@ oldQFSInfoRetry:
 }
 
 int
-CIFSSMBQFSInfo(const int xid, struct cifsTconInfo *tcon, struct kstatfs *FSData)
+CIFSSMBQFSInfo(const int xid, struct cifs_tcon *tcon, struct kstatfs *FSData)
 {
 /* level 0x103 SMB_QUERY_FILE_SYSTEM_INFO */
 	TRANSACTION2_QFSI_REQ *pSMB = NULL;
@@ -4456,7 +4715,7 @@ QFSInfoRetry:
 }
 
 int
-CIFSSMBQFSAttributeInfo(const int xid, struct cifsTconInfo *tcon)
+CIFSSMBQFSAttributeInfo(const int xid, struct cifs_tcon *tcon)
 {
 /* level 0x105  SMB_QUERY_FILE_SYSTEM_INFO */
 	TRANSACTION2_QFSI_REQ *pSMB = NULL;
@@ -4526,7 +4785,7 @@ QFSAttributeRetry:
 }
 
 int
-CIFSSMBQFSDeviceInfo(const int xid, struct cifsTconInfo *tcon)
+CIFSSMBQFSDeviceInfo(const int xid, struct cifs_tcon *tcon)
 {
 /* level 0x104 SMB_QUERY_FILE_SYSTEM_INFO */
 	TRANSACTION2_QFSI_REQ *pSMB = NULL;
@@ -4597,7 +4856,7 @@ QFSDeviceRetry:
 }
 
 int
-CIFSSMBQFSUnixInfo(const int xid, struct cifsTconInfo *tcon)
+CIFSSMBQFSUnixInfo(const int xid, struct cifs_tcon *tcon)
 {
 /* level 0x200  SMB_QUERY_CIFS_UNIX_INFO */
 	TRANSACTION2_QFSI_REQ *pSMB = NULL;
@@ -4667,7 +4926,7 @@ QFSUnixRetry:
 }
 
 int
-CIFSSMBSetFSUnixInfo(const int xid, struct cifsTconInfo *tcon, __u64 cap)
+CIFSSMBSetFSUnixInfo(const int xid, struct cifs_tcon *tcon, __u64 cap)
 {
 /* level 0x200  SMB_SET_CIFS_UNIX_INFO */
 	TRANSACTION2_SETFSI_REQ *pSMB = NULL;
@@ -4741,7 +5000,7 @@ SETFSUnixRetry:
 
 
 int
-CIFSSMBQFSPosixInfo(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBQFSPosixInfo(const int xid, struct cifs_tcon *tcon,
 		   struct kstatfs *FSData)
 {
 /* level 0x201  SMB_QUERY_CIFS_POSIX_INFO */
@@ -4834,7 +5093,7 @@ QFSPosixRetry:
    in Samba which this routine can run into */
 
 int
-CIFSSMBSetEOF(const int xid, struct cifsTconInfo *tcon, const char *fileName,
+CIFSSMBSetEOF(const int xid, struct cifs_tcon *tcon, const char *fileName,
 	      __u64 size, bool SetAllocation,
 	      const struct nls_table *nls_codepage, int remap)
 {
@@ -4923,7 +5182,7 @@ SetEOFRetry:
 }
 
 int
-CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon, __u64 size,
+CIFSSMBSetFileSize(const int xid, struct cifs_tcon *tcon, __u64 size,
 		   __u16 fid, __u32 pid_of_opener, bool SetAllocation)
 {
 	struct smb_com_transaction2_sfi_req *pSMB  = NULL;
@@ -5005,7 +5264,7 @@ CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon, __u64 size,
    time and resort to the original setpathinfo level which takes the ancient
    DOS time format with 2 second granularity */
 int
-CIFSSMBSetFileInfo(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBSetFileInfo(const int xid, struct cifs_tcon *tcon,
 		    const FILE_BASIC_INFO *data, __u16 fid, __u32 pid_of_opener)
 {
 	struct smb_com_transaction2_sfi_req *pSMB  = NULL;
@@ -5067,7 +5326,7 @@ CIFSSMBSetFileInfo(const int xid, struct cifsTconInfo *tcon,
 }
 
 int
-CIFSSMBSetFileDisposition(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBSetFileDisposition(const int xid, struct cifs_tcon *tcon,
 			  bool delete_file, __u16 fid, __u32 pid_of_opener)
 {
 	struct smb_com_transaction2_sfi_req *pSMB  = NULL;
@@ -5123,7 +5382,7 @@ CIFSSMBSetFileDisposition(const int xid, struct cifsTconInfo *tcon,
 }
 
 int
-CIFSSMBSetPathInfo(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBSetPathInfo(const int xid, struct cifs_tcon *tcon,
 		   const char *fileName, const FILE_BASIC_INFO *data,
 		   const struct nls_table *nls_codepage, int remap)
 {
@@ -5207,7 +5466,7 @@ SetTimesRetry:
 	  handling it anyway and NT4 was what we thought it would be needed for
 	  Do not delete it until we prove whether needed for Win9x though */
 int
-CIFSSMBSetAttrLegacy(int xid, struct cifsTconInfo *tcon, char *fileName,
+CIFSSMBSetAttrLegacy(int xid, struct cifs_tcon *tcon, char *fileName,
 		__u16 dos_attrs, const struct nls_table *nls_codepage)
 {
 	SETATTR_REQ *pSMB = NULL;
@@ -5295,7 +5554,7 @@ cifs_fill_unix_set_info(FILE_UNIX_BASIC_INFO *data_offset,
 }
 
 int
-CIFSSMBUnixSetFileInfo(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBUnixSetFileInfo(const int xid, struct cifs_tcon *tcon,
 		       const struct cifs_unix_set_info_args *args,
 		       u16 fid, u32 pid_of_opener)
 {
@@ -5358,7 +5617,7 @@ CIFSSMBUnixSetFileInfo(const int xid, struct cifsTconInfo *tcon,
 }
 
 int
-CIFSSMBUnixSetPathInfo(const int xid, struct cifsTconInfo *tcon, char *fileName,
+CIFSSMBUnixSetPathInfo(const int xid, struct cifs_tcon *tcon, char *fileName,
 		       const struct cifs_unix_set_info_args *args,
 		       const struct nls_table *nls_codepage, int remap)
 {
@@ -5445,7 +5704,7 @@ setPermsRetry:
  * the data isn't copied to it, but the length is returned.
  */
 ssize_t
-CIFSSMBQAllEAs(const int xid, struct cifsTconInfo *tcon,
+CIFSSMBQAllEAs(const int xid, struct cifs_tcon *tcon,
 		const unsigned char *searchName, const unsigned char *ea_name,
 		char *EAData, size_t buf_size,
 		const struct nls_table *nls_codepage, int remap)
@@ -5626,7 +5885,7 @@ QAllEAsOut:
 }
 
 int
-CIFSSMBSetEA(const int xid, struct cifsTconInfo *tcon, const char *fileName,
+CIFSSMBSetEA(const int xid, struct cifs_tcon *tcon, const char *fileName,
 	     const char *ea_name, const void *ea_value,
 	     const __u16 ea_value_len, const struct nls_table *nls_codepage,
 	     int remap)
@@ -5753,7 +6012,7 @@ SetEARetry:
  *	incompatible for network fs clients, we could instead simply
  *	expose this config flag by adding a future cifs (and smb2) notify ioctl.
  */
-int CIFSSMBNotify(const int xid, struct cifsTconInfo *tcon,
+int CIFSSMBNotify(const int xid, struct cifs_tcon *tcon,
 		  const int notify_subdirs, const __u16 netfid,
 		  __u32 filter, struct file *pfile, int multishot,
 		  const struct nls_table *nls_codepage)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index da284e3cb653..7f540df52527 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -57,62 +57,6 @@
 
 extern mempool_t *cifs_req_poolp;
 
-struct smb_vol {
-	char *username;
-	char *password;
-	char *domainname;
-	char *UNC;
-	char *UNCip;
-	char *iocharset;  /* local code page for mapping to and from Unicode */
-	char source_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* clnt nb name */
-	char target_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* srvr nb name */
-	uid_t cred_uid;
-	uid_t linux_uid;
-	gid_t linux_gid;
-	mode_t file_mode;
-	mode_t dir_mode;
-	unsigned secFlg;
-	bool retry:1;
-	bool intr:1;
-	bool setuids:1;
-	bool override_uid:1;
-	bool override_gid:1;
-	bool dynperm:1;
-	bool noperm:1;
-	bool no_psx_acl:1; /* set if posix acl support should be disabled */
-	bool cifs_acl:1;
-	bool no_xattr:1;   /* set if xattr (EA) support should be disabled*/
-	bool server_ino:1; /* use inode numbers from server ie UniqueId */
-	bool direct_io:1;
-	bool strict_io:1; /* strict cache behavior */
-	bool remap:1;      /* set to remap seven reserved chars in filenames */
-	bool posix_paths:1; /* unset to not ask for posix pathnames. */
-	bool no_linux_ext:1;
-	bool sfu_emul:1;
-	bool nullauth:1;   /* attempt to authenticate with null user */
-	bool nocase:1;     /* request case insensitive filenames */
-	bool nobrl:1;      /* disable sending byte range locks to srv */
-	bool mand_lock:1;  /* send mandatory not posix byte range lock reqs */
-	bool seal:1;       /* request transport encryption on share */
-	bool nodfs:1;      /* Do not request DFS, even if available */
-	bool local_lease:1; /* check leases only on local system, not remote */
-	bool noblocksnd:1;
-	bool noautotune:1;
-	bool nostrictsync:1; /* do not force expensive SMBflush on every sync */
-	bool fsc:1;	/* enable fscache */
-	bool mfsymlinks:1; /* use Minshall+French Symlinks */
-	bool multiuser:1;
-	bool use_smb2:1; /* force smb2 use on mount instead of cifs */
-	unsigned int rsize;
-	unsigned int wsize;
-	bool sockopt_tcp_nodelay:1;
-	unsigned short int port;
-	unsigned long actimeo; /* attribute cache timeout (jiffies) */
-	char *prepath;
-	struct sockaddr_storage srcaddr; /* allow binding to a local IP */
-	struct nls_table *local_nls;
-};
-
 /* FIXME: should these be tunable? */
 #define TLINK_ERROR_EXPIRE	(1 * HZ)
 #define TLINK_IDLE_EXPIRE	(600 * HZ)
@@ -135,9 +79,10 @@ cifs_reconnect(struct TCP_Server_Info *server)
 {
 	int rc = 0;
 	struct list_head *tmp, *tmp2;
-	struct cifsSesInfo *ses;
-	struct cifsTconInfo *tcon;
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
 	struct mid_q_entry *mid_entry;
+	struct list_head retry_list;
 
 	spin_lock(&GlobalMid_Lock);
 	if (server->tcpStatus == CifsExiting) {
@@ -157,11 +102,11 @@ cifs_reconnect(struct TCP_Server_Info *server)
 	cFYI(1, "%s: marking sessions and tcons for reconnect", __func__);
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each(tmp, &server->smb_ses_list) {
-		ses = list_entry(tmp, struct cifsSesInfo, smb_ses_list);
+		ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
 		ses->need_reconnect = true;
 		ses->ipc_tid = 0;
 		list_for_each(tmp2, &ses->tcon_list) {
-			tcon = list_entry(tmp2, struct cifsTconInfo, tcon_list);
+			tcon = list_entry(tmp2, struct cifs_tcon, tcon_list);
 			tcon->need_reconnect = true;
 		}
 	}
@@ -189,18 +134,25 @@ cifs_reconnect(struct TCP_Server_Info *server)
 	mutex_unlock(&server->srv_mutex);
 
 	/* mark submitted MIDs for retry and issue callback */
-	cFYI(1, "%s: issuing mid callbacks", __func__);
+	INIT_LIST_HEAD(&retry_list);
+	cFYI(1, "%s: moving mids to private list", __func__);
 	spin_lock(&GlobalMid_Lock);
 	list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
 		mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
 		if (mid_entry->midState == MID_REQUEST_SUBMITTED)
 			mid_entry->midState = MID_RETRY_NEEDED;
+		list_move(&mid_entry->qhead, &retry_list);
+	}
+	spin_unlock(&GlobalMid_Lock);
+
+	cFYI(1, "%s: issuing mid callbacks", __func__);
+	list_for_each_safe(tmp, tmp2, &retry_list) {
+		mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
 		list_del_init(&mid_entry->qhead);
 		mid_entry->callback(mid_entry);
 	}
-	spin_unlock(&GlobalMid_Lock);
 
-	while (server->tcpStatus == CifsNeedReconnect) {
+	do {
 		try_to_freeze();
 
 		/* we should try only the port we connected to before */
@@ -215,7 +167,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
 				server->tcpStatus = CifsNeedNegotiate;
 			spin_unlock(&GlobalMid_Lock);
 		}
-	}
+	} while (server->tcpStatus == CifsNeedReconnect);
 
 	return rc;
 }
@@ -672,12 +624,12 @@ multi_t2_fnd:
 			mid_entry->when_received = jiffies;
 #endif
 			list_del_init(&mid_entry->qhead);
-			mid_entry->callback(mid_entry);
 			break;
 		}
 		spin_unlock(&GlobalMid_Lock);
 
 		if (mid_entry != NULL) {
+			mid_entry->callback(mid_entry);
 			/* Was previous buf put in mpx struct for multi-rsp? */
 			if (!isMultiRsp) {
 				/* smb buffer will be freed by user thread */
@@ -741,15 +693,25 @@ multi_t2_fnd:
 		cifs_small_buf_release(smallbuf);
 
 	if (!list_empty(&server->pending_mid_q)) {
+		struct list_head dispose_list;
+
+		INIT_LIST_HEAD(&dispose_list);
 		spin_lock(&GlobalMid_Lock);
 		list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
 			mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-			cFYI(1, "Clearing Mid 0x%x - issuing callback",
-					 mid_entry->mid);
+			cFYI(1, "Clearing mid 0x%x", mid_entry->mid);
+			mid_entry->midState = MID_SHUTDOWN;
+			list_move(&mid_entry->qhead, &dispose_list);
+		}
+		spin_unlock(&GlobalMid_Lock);
+
+		/* now walk dispose list and issue callbacks */
+		list_for_each_safe(tmp, tmp2, &dispose_list) {
+			mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
+			cFYI(1, "Callback mid 0x%x", mid_entry->mid);
 			list_del_init(&mid_entry->qhead);
 			mid_entry->callback(mid_entry);
 		}
-		spin_unlock(&GlobalMid_Lock);
 		/* 1/8th of sec is more than enough time for them to exit */
 		msleep(125);
 	}
@@ -822,7 +784,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 			 struct smb_vol *vol)
 {
 	char *value, *data, *end;
-	char *mountdata_copy, *options;
+	char *mountdata_copy = NULL, *options;
 	unsigned int  temp_len, i, j;
 	char separator[2];
 	short int override_uid = -1;
@@ -1062,13 +1024,6 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 				   (strnicmp(value, "1", 1) == 0)) {
 				/* this is the default */
 				continue;
-			} else if ((strnicmp(value, "smb2", 4) == 0) ||
-				   (strnicmp(value, "2", 1) == 0)) {
-#ifdef CONFIG_CIFS_SMB2
-				vol->use_smb2 = true;
-#else
-				cERROR(1, "smb2 support not enabled");
-#endif /* CONFIG_CIFS_SMB2 */
 			}
 		} else if ((strnicmp(data, "unc", 3) == 0)
 			   || (strnicmp(data, "target", 6) == 0)
@@ -1404,6 +1359,8 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 			vol->server_ino = 1;
 		} else if (strnicmp(data, "noserverino", 9) == 0) {
 			vol->server_ino = 0;
+		} else if (strnicmp(data, "rwpidforward", 4) == 0) {
+			vol->rwpidforward = 1;
 		} else if (strnicmp(data, "cifsacl", 7) == 0) {
 			vol->cifs_acl = 1;
 		} else if (strnicmp(data, "nocifsacl", 9) == 0) {
@@ -1434,7 +1391,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 				"/proc/fs/cifs/LookupCacheEnabled to 0\n");
 		} else if (strnicmp(data, "fsc", 3) == 0) {
 #ifndef CONFIG_CIFS_FSCACHE
-			cERROR(1, "FS-Cache support needs CONFIG_CIFS_FSCACHE"
+			cERROR(1, "FS-Cache support needs CONFIG_CIFS_FSCACHE "
 				  "kernel config option set");
 			goto cifs_parse_mount_err;
 #endif
@@ -1640,16 +1597,35 @@ match_security(struct TCP_Server_Info *server, struct smb_vol *vol)
 
 	/* now check if signing mode is acceptable */
 	if ((secFlags & CIFSSEC_MAY_SIGN) == 0 &&
-	    (server->secMode & SECMODE_SIGN_REQUIRED))
+	    (server->sec_mode & SECMODE_SIGN_REQUIRED))
 			return false;
 	else if (((secFlags & CIFSSEC_MUST_SIGN) == CIFSSEC_MUST_SIGN) &&
-		 (server->secMode &
+		 (server->sec_mode &
 		  (SECMODE_SIGN_ENABLED|SECMODE_SIGN_REQUIRED)) == 0)
 			return false;
 
 	return true;
 }
 
+static int match_server(struct TCP_Server_Info *server, struct sockaddr *addr,
+			 struct smb_vol *vol)
+{
+	if (!net_eq(cifs_net_ns(server), current->nsproxy->net_ns))
+		return 0;
+
+	if (!match_address(server, addr,
+			   (struct sockaddr *)&vol->srcaddr))
+		return 0;
+
+	if (!match_port(server, addr))
+		return 0;
+
+	if (!match_security(server, vol))
+		return 0;
+
+	return 1;
+}
+
 static struct TCP_Server_Info *
 cifs_find_tcp_session(struct sockaddr *addr, struct smb_vol *vol)
 {
@@ -1657,17 +1633,7 @@ cifs_find_tcp_session(struct sockaddr *addr, struct smb_vol *vol)
 
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
-		if (!net_eq(cifs_net_ns(server), current->nsproxy->net_ns))
-			continue;
-
-		if (!match_address(server, addr,
-				   (struct sockaddr *)&vol->srcaddr))
-			continue;
-
-		if (!match_port(server, addr))
-			continue;
-
-		if (!match_security(server, vol))
+		if (!match_server(server, addr, vol))
 			continue;
 
 		++server->srv_count;
@@ -1861,32 +1827,39 @@ out_err:
 	return ERR_PTR(rc);
 }
 
-static struct cifsSesInfo *
+static int match_session(struct cifs_ses *ses, struct smb_vol *vol)
+{
+	switch (ses->server->secType) {
+	case Kerberos:
+		if (vol->cred_uid != ses->cred_uid)
+			return 0;
+		break;
+	default:
+		/* anything else takes username/password */
+		if (ses->user_name == NULL)
+			return 0;
+		if (strncmp(ses->user_name, vol->username,
+			    MAX_USERNAME_SIZE))
+			return 0;
+		if (strlen(vol->username) != 0 &&
+		    ses->password != NULL &&
+		    strncmp(ses->password,
+			    vol->password ? vol->password : "",
+			    MAX_PASSWORD_SIZE))
+			return 0;
+	}
+	return 1;
+}
+
+static struct cifs_ses *
 cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb_vol *vol)
 {
-	struct cifsSesInfo *ses;
+	struct cifs_ses *ses;
 
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
-		switch (server->secType) {
-		case Kerberos:
-			if (vol->cred_uid != ses->cred_uid)
-				continue;
-			break;
-		default:
-			/* anything else takes username/password */
-			if (ses->user_name == NULL)
-				continue;
-			if (strncmp(ses->user_name, vol->username,
-				    MAX_USERNAME_SIZE))
-				continue;
-			if (strlen(vol->username) != 0 &&
-			    ses->password != NULL &&
-			    strncmp(ses->password,
-				    vol->password ? vol->password : "",
-				    MAX_PASSWORD_SIZE))
-				continue;
-		}
+		if (!match_session(ses, vol))
+			continue;
 		++ses->ses_count;
 		spin_unlock(&cifs_tcp_ses_lock);
 		return ses;
@@ -1896,7 +1869,7 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb_vol *vol)
 }
 
 static void
-cifs_put_smb_ses(struct cifsSesInfo *ses)
+cifs_put_smb_ses(struct cifs_ses *ses)
 {
 	int xid;
 	struct TCP_Server_Info *server = ses->server;
@@ -1922,11 +1895,11 @@ cifs_put_smb_ses(struct cifsSesInfo *ses)
 
 static bool warned_on_ntlm;  /* globals init to false automatically */
 
-static struct cifsSesInfo *
+static struct cifs_ses *
 cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info)
 {
 	int rc = -ENOMEM, xid;
-	struct cifsSesInfo *ses;
+	struct cifs_ses *ses;
 	struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr;
 	struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)&server->dstaddr;
 
@@ -2003,7 +1976,7 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info)
 		warned_on_ntlm = true;
 		cERROR(1, "default security mechanism requested.  The default "
 			"security mechanism will be upgraded from ntlm to "
-			"ntlmv2 in kernel release 2.6.41");
+			"ntlmv2 in kernel release 3.1");
 	}
 	ses->overrideSecFlg = volume_info->secFlg;
 
@@ -2029,20 +2002,26 @@ get_ses_fail:
 	return ERR_PTR(rc);
 }
 
-static struct cifsTconInfo *
-cifs_find_tcon(struct cifsSesInfo *ses, const char *unc)
+static int match_tcon(struct cifs_tcon *tcon, const char *unc)
+{
+	if (tcon->tidStatus == CifsExiting)
+		return 0;
+	if (strncmp(tcon->treeName, unc, MAX_TREE_SIZE))
+		return 0;
+	return 1;
+}
+
+static struct cifs_tcon *
+cifs_find_tcon(struct cifs_ses *ses, const char *unc)
 {
 	struct list_head *tmp;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each(tmp, &ses->tcon_list) {
-		tcon = list_entry(tmp, struct cifsTconInfo, tcon_list);
-		if (tcon->tidStatus == CifsExiting)
+		tcon = list_entry(tmp, struct cifs_tcon, tcon_list);
+		if (!match_tcon(tcon, unc))
 			continue;
-		if (strncmp(tcon->treeName, unc, MAX_TREE_SIZE))
-			continue;
-
 		++tcon->tc_count;
 		spin_unlock(&cifs_tcp_ses_lock);
 		return tcon;
@@ -2052,10 +2031,10 @@ cifs_find_tcon(struct cifsSesInfo *ses, const char *unc)
 }
 
 static void
-cifs_put_tcon(struct cifsTconInfo *tcon)
+cifs_put_tcon(struct cifs_tcon *tcon)
 {
 	int xid;
-	struct cifsSesInfo *ses = tcon->ses;
+	struct cifs_ses *ses = tcon->ses;
 
 	cFYI(1, "%s: tc_count=%d\n", __func__, tcon->tc_count);
 	spin_lock(&cifs_tcp_ses_lock);
@@ -2076,11 +2055,11 @@ cifs_put_tcon(struct cifsTconInfo *tcon)
 	cifs_put_smb_ses(ses);
 }
 
-static struct cifsTconInfo *
-cifs_get_tcon(struct cifsSesInfo *ses, struct smb_vol *volume_info)
+static struct cifs_tcon *
+cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 {
 	int rc, xid;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 
 	tcon = cifs_find_tcon(ses, volume_info->UNC);
 	if (tcon) {
@@ -2169,8 +2148,105 @@ cifs_put_tlink(struct tcon_link *tlink)
 	return;
 }
 
+static inline struct tcon_link *
+cifs_sb_master_tlink(struct cifs_sb_info *cifs_sb)
+{
+	return cifs_sb->master_tlink;
+}
+
+static int
+compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data)
+{
+	struct cifs_sb_info *old = CIFS_SB(sb);
+	struct cifs_sb_info *new = mnt_data->cifs_sb;
+
+	if ((sb->s_flags & CIFS_MS_MASK) != (mnt_data->flags & CIFS_MS_MASK))
+		return 0;
+
+	if ((old->mnt_cifs_flags & CIFS_MOUNT_MASK) !=
+	    (new->mnt_cifs_flags & CIFS_MOUNT_MASK))
+		return 0;
+
+	if (old->rsize != new->rsize)
+		return 0;
+
+	/*
+	 * We want to share sb only if we don't specify wsize or specified wsize
+	 * is greater or equal than existing one.
+	 */
+	if (new->wsize && new->wsize < old->wsize)
+		return 0;
+
+	if (old->mnt_uid != new->mnt_uid || old->mnt_gid != new->mnt_gid)
+		return 0;
+
+	if (old->mnt_file_mode != new->mnt_file_mode ||
+	    old->mnt_dir_mode != new->mnt_dir_mode)
+		return 0;
+
+	if (strcmp(old->local_nls->charset, new->local_nls->charset))
+		return 0;
+
+	if (old->actimeo != new->actimeo)
+		return 0;
+
+	return 1;
+}
+
+int
+cifs_match_super(struct super_block *sb, void *data)
+{
+	struct cifs_mnt_data *mnt_data = (struct cifs_mnt_data *)data;
+	struct smb_vol *volume_info;
+	struct cifs_sb_info *cifs_sb;
+	struct TCP_Server_Info *tcp_srv;
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
+	struct tcon_link *tlink;
+	struct sockaddr_storage addr;
+	int rc = 0;
+
+	memset(&addr, 0, sizeof(struct sockaddr_storage));
+
+	spin_lock(&cifs_tcp_ses_lock);
+	cifs_sb = CIFS_SB(sb);
+	tlink = cifs_get_tlink(cifs_sb_master_tlink(cifs_sb));
+	if (IS_ERR(tlink)) {
+		spin_unlock(&cifs_tcp_ses_lock);
+		return rc;
+	}
+	tcon = tlink_tcon(tlink);
+	ses = tcon->ses;
+	tcp_srv = ses->server;
+
+	volume_info = mnt_data->vol;
+
+	if (!volume_info->UNCip || !volume_info->UNC)
+		goto out;
+
+	rc = cifs_fill_sockaddr((struct sockaddr *)&addr,
+				volume_info->UNCip,
+				strlen(volume_info->UNCip),
+				volume_info->port);
+	if (!rc)
+		goto out;
+
+	if (!match_server(tcp_srv, (struct sockaddr *)&addr, volume_info) ||
+	    !match_session(ses, volume_info) ||
+	    !match_tcon(tcon, volume_info->UNC)) {
+		rc = 0;
+		goto out;
+	}
+
+	rc = compare_mount_options(sb, mnt_data);
+out:
+	cifs_put_tlink(tlink);
+	spin_unlock(&cifs_tcp_ses_lock);
+	return rc;
+}
+
 int
-get_dfs_path(int xid, struct cifsSesInfo *pSesInfo, const char *old_path,
+get_dfs_path(int xid, struct cifs_ses *pSesInfo, const char *old_path,
 	     const struct nls_table *nls_codepage, unsigned int *pnum_referrals,
 	     struct dfs_info3_param **preferrals, int remap)
 {
@@ -2469,8 +2545,8 @@ ip_connect(struct TCP_Server_Info *server)
 	return generic_ip_connect(server);
 }
 
-void reset_cifs_unix_caps(int xid, struct cifsTconInfo *tcon,
-			  struct super_block *sb, struct smb_vol *vol_info)
+void reset_cifs_unix_caps(int xid, struct cifs_tcon *tcon,
+			  struct cifs_sb_info *cifs_sb, struct smb_vol *vol_info)
 {
 	/* if we are reconnecting then should we check to see if
 	 * any requested capabilities changed locally e.g. via
@@ -2498,7 +2574,7 @@ void reset_cifs_unix_caps(int xid, struct cifsTconInfo *tcon,
 
 	if (!CIFSSMBQFSUnixInfo(xid, tcon)) {
 		__u64 cap = le64_to_cpu(tcon->fsUnixInfo.Capability);
-
+		cFYI(1, "unix caps which server supports %lld", cap);
 		/* check for reconnect case in which we do not
 		   want to change the mount behavior if we can avoid it */
 		if (vol_info == NULL) {
@@ -2516,33 +2592,31 @@ void reset_cifs_unix_caps(int xid, struct cifsTconInfo *tcon,
 			}
 		}
 
+		if (cap & CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)
+			cERROR(1, "per-share encryption not supported yet");
+
 		cap &= CIFS_UNIX_CAP_MASK;
 		if (vol_info && vol_info->no_psx_acl)
 			cap &= ~CIFS_UNIX_POSIX_ACL_CAP;
 		else if (CIFS_UNIX_POSIX_ACL_CAP & cap) {
 			cFYI(1, "negotiated posix acl support");
-			if (sb)
-				sb->s_flags |= MS_POSIXACL;
+			if (cifs_sb)
+				cifs_sb->mnt_cifs_flags |=
+					CIFS_MOUNT_POSIXACL;
 		}
 
 		if (vol_info && vol_info->posix_paths == 0)
 			cap &= ~CIFS_UNIX_POSIX_PATHNAMES_CAP;
 		else if (cap & CIFS_UNIX_POSIX_PATHNAMES_CAP) {
 			cFYI(1, "negotiate posix pathnames");
-			if (sb)
-				CIFS_SB(sb)->mnt_cifs_flags |=
+			if (cifs_sb)
+				cifs_sb->mnt_cifs_flags |=
 					CIFS_MOUNT_POSIX_PATHS;
 		}
 
-		/* We might be setting the path sep back to a different
-		form if we are reconnecting and the server switched its
-		posix path capability for this share */
-		if (sb && (CIFS_SB(sb)->prepathlen > 0))
-			CIFS_SB(sb)->prepath[0] = CIFS_DIR_SEP(CIFS_SB(sb));
-
-		if (sb && (CIFS_SB(sb)->rsize > 127 * 1024)) {
+		if (cifs_sb && (cifs_sb->rsize > 127 * 1024)) {
 			if ((cap & CIFS_UNIX_LARGE_READ_CAP) == 0) {
-				CIFS_SB(sb)->rsize = 127 * 1024;
+				cifs_sb->rsize = 127 * 1024;
 				cFYI(DBG2, "larger reads not supported by srv");
 			}
 		}
@@ -2564,6 +2638,10 @@ void reset_cifs_unix_caps(int xid, struct cifsTconInfo *tcon,
 			cFYI(1, "very large read cap");
 		if (cap & CIFS_UNIX_LARGE_WRITE_CAP)
 			cFYI(1, "very large write cap");
+		if (cap & CIFS_UNIX_TRANSPORT_ENCRYPTION_CAP)
+			cFYI(1, "transport encryption cap");
+		if (cap & CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)
+			cFYI(1, "mandatory transport encryption cap");
 #endif /* CIFS_DEBUG2 */
 		if (CIFSSMBSetFSUnixInfo(xid, tcon, cap)) {
 			if (vol_info == NULL) {
@@ -2580,31 +2658,14 @@ void reset_cifs_unix_caps(int xid, struct cifsTconInfo *tcon,
 	}
 }
 
-static void
-convert_delimiter(char *path, char delim)
-{
-	int i;
-	char old_delim;
-
-	if (path == NULL)
-		return;
-
-	if (delim == '/')
-		old_delim = '\\';
-	else
-		old_delim = '/';
-
-	for (i = 0; path[i] != '\0'; i++) {
-		if (path[i] == old_delim)
-			path[i] = delim;
-	}
-}
-
-static void setup_cifs_sb(struct smb_vol *pvolume_info,
-			  struct cifs_sb_info *cifs_sb)
+void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
+			struct cifs_sb_info *cifs_sb)
 {
 	INIT_DELAYED_WORK(&cifs_sb->prune_tlinks, cifs_prune_tlinks);
 
+	spin_lock_init(&cifs_sb->tlink_tree_lock);
+	cifs_sb->tlink_tree = RB_ROOT;
+
 	if (pvolume_info->rsize > CIFSMaxBufSize) {
 		cERROR(1, "rsize %d too large, using MaxBufSize",
 			pvolume_info->rsize);
@@ -2615,40 +2676,19 @@ static void setup_cifs_sb(struct smb_vol *pvolume_info,
 	else /* default */
 		cifs_sb->rsize = CIFSMaxBufSize;
 
-	if (pvolume_info->wsize > PAGEVEC_SIZE * PAGE_CACHE_SIZE) {
-		cERROR(1, "wsize %d too large, using 4096 instead",
-			  pvolume_info->wsize);
-		cifs_sb->wsize = 4096;
-	} else if (pvolume_info->wsize)
-		cifs_sb->wsize = pvolume_info->wsize;
-	else
-		cifs_sb->wsize = min_t(const int,
-					PAGEVEC_SIZE * PAGE_CACHE_SIZE,
-					127*1024);
-		/* old default of CIFSMaxBufSize was too small now
-		   that SMB Write2 can send multiple pages in kvec.
-		   RFC1001 does not describe what happens when frame
-		   bigger than 128K is sent so use that as max in
-		   conjunction with 52K kvec constraint on arch with 4K
-		   page size  */
-
 	if (cifs_sb->rsize < 2048) {
 		cifs_sb->rsize = 2048;
 		/* Windows ME may prefer this */
 		cFYI(1, "readsize set to minimum: 2048");
 	}
-	/* calculate prepath */
-	cifs_sb->prepath = pvolume_info->prepath;
-	if (cifs_sb->prepath) {
-		cifs_sb->prepathlen = strlen(cifs_sb->prepath);
-		/* we can not convert the / to \ in the path
-		separators in the prefixpath yet because we do not
-		know (until reset_cifs_unix_caps is called later)
-		whether POSIX PATH CAP is available. We normalize
-		the / to \ after reset_cifs_unix_caps is called */
-		pvolume_info->prepath = NULL;
-	} else
-		cifs_sb->prepathlen = 0;
+
+	/*
+	 * Temporarily set wsize for matching superblock. If we end up using
+	 * new sb then cifs_negotiate_wsize will later negotiate it downward
+	 * if needed.
+	 */
+	cifs_sb->wsize = pvolume_info->wsize;
+
 	cifs_sb->mnt_uid = pvolume_info->linux_uid;
 	cifs_sb->mnt_gid = pvolume_info->linux_gid;
 	cifs_sb->mnt_file_mode = pvolume_info->file_mode;
@@ -2657,6 +2697,7 @@ static void setup_cifs_sb(struct smb_vol *pvolume_info,
 		cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode);
 
 	cifs_sb->actimeo = pvolume_info->actimeo;
+	cifs_sb->local_nls = pvolume_info->local_nls;
 
 	if (pvolume_info->noperm)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_PERM;
@@ -2676,6 +2717,8 @@ static void setup_cifs_sb(struct smb_vol *pvolume_info,
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NOSSYNC;
 	if (pvolume_info->mand_lock)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NOPOSIXBRL;
+	if (pvolume_info->rwpidforward)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_RWPIDFORWARD;
 	if (pvolume_info->cifs_acl)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_ACL;
 	if (pvolume_info->override_uid)
@@ -2709,8 +2752,62 @@ static void setup_cifs_sb(struct smb_vol *pvolume_info,
 			   "mount option supported");
 }
 
+/*
+ * When the server supports very large writes via POSIX extensions, we can
+ * allow up to 2^24-1, minus the size of a WRITE_AND_X header, not including
+ * the RFC1001 length.
+ *
+ * Note that this might make for "interesting" allocation problems during
+ * writeback however as we have to allocate an array of pointers for the
+ * pages. A 16M write means ~32kb page array with PAGE_CACHE_SIZE == 4096.
+ */
+#define CIFS_MAX_WSIZE ((1<<24) - 1 - sizeof(WRITE_REQ) + 4)
+
+/*
+ * When the server doesn't allow large posix writes, only allow a wsize of
+ * 128k minus the size of the WRITE_AND_X header. That allows for a write up
+ * to the maximum size described by RFC1002.
+ */
+#define CIFS_MAX_RFC1002_WSIZE (128 * 1024 - sizeof(WRITE_REQ) + 4)
+
+/*
+ * The default wsize is 1M. find_get_pages seems to return a maximum of 256
+ * pages in a single call. With PAGE_CACHE_SIZE == 4k, this means we can fill
+ * a single wsize request with a single call.
+ */
+#define CIFS_DEFAULT_WSIZE (1024 * 1024)
+
+static unsigned int
+cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info)
+{
+	__u64 unix_cap = le64_to_cpu(tcon->fsUnixInfo.Capability);
+	struct TCP_Server_Info *server = tcon->ses->server;
+	unsigned int wsize = pvolume_info->wsize ? pvolume_info->wsize :
+				CIFS_DEFAULT_WSIZE;
+
+	/* can server support 24-bit write sizes? (via UNIX extensions) */
+	if (!tcon->unix_ext || !(unix_cap & CIFS_UNIX_LARGE_WRITE_CAP))
+		wsize = min_t(unsigned int, wsize, CIFS_MAX_RFC1002_WSIZE);
+
+	/*
+	 * no CAP_LARGE_WRITE_X or is signing enabled without CAP_UNIX set?
+	 * Limit it to max buffer offered by the server, minus the size of the
+	 * WRITEX header, not including the 4 byte RFC1001 length.
+	 */
+	if (!(server->capabilities & CAP_LARGE_WRITE_X) ||
+	    (!(server->capabilities & CAP_UNIX) &&
+	     (server->sec_mode & (SECMODE_SIGN_ENABLED|SECMODE_SIGN_REQUIRED))))
+		wsize = min_t(unsigned int, wsize,
+				server->maxBuf - sizeof(WRITE_REQ) + 4);
+
+	/* hard limit of CIFS_MAX_WSIZE */
+	wsize = min_t(unsigned int, wsize, CIFS_MAX_WSIZE);
+
+	return wsize;
+}
+
 static int
-is_path_accessible(int xid, struct cifsTconInfo *tcon,
+is_path_accessible(int xid, struct cifs_tcon *tcon,
 		   struct cifs_sb_info *cifs_sb, const char *full_path)
 {
 	int rc;
@@ -2733,8 +2830,8 @@ is_path_accessible(int xid, struct cifsTconInfo *tcon,
 	return rc;
 }
 
-static void
-cleanup_volume_info(struct smb_vol **pvolume_info)
+void
+cifs_cleanup_volume_info(struct smb_vol **pvolume_info)
 {
 	struct smb_vol *volume_info;
 
@@ -2764,24 +2861,13 @@ build_unc_path_to_root(const struct smb_vol *volume_info,
 	char *full_path;
 
 	int unc_len = strnlen(volume_info->UNC, MAX_TREE_SIZE + 1);
-	full_path = kmalloc(unc_len + cifs_sb->prepathlen + 1, GFP_KERNEL);
+	full_path = kmalloc(unc_len + 1, GFP_KERNEL);
 	if (full_path == NULL)
 		return ERR_PTR(-ENOMEM);
 
 	strncpy(full_path, volume_info->UNC, unc_len);
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) {
-		int i;
-		for (i = 0; i < unc_len; i++) {
-			if (full_path[i] == '\\')
-				full_path[i] = '/';
-		}
-	}
-
-	if (cifs_sb->prepathlen)
-		strncpy(full_path + unc_len, cifs_sb->prepath,
-				cifs_sb->prepathlen);
-
-	full_path[unc_len + cifs_sb->prepathlen] = 0; /* add trailing null */
+	full_path[unc_len] = 0; /* add trailing null */
+	convert_delimiter(full_path, CIFS_DIR_SEP(cifs_sb));
 	return full_path;
 }
 
@@ -2796,7 +2882,7 @@ build_unc_path_to_root(const struct smb_vol *volume_info,
  * determine whether there were referrals.
  */
 static int
-expand_dfs_referral(int xid, struct cifsSesInfo *pSesInfo,
+expand_dfs_referral(int xid, struct cifs_ses *pSesInfo,
 		    struct smb_vol *volume_info, struct cifs_sb_info *cifs_sb,
 		    int check_prefix)
 {
@@ -2840,40 +2926,13 @@ expand_dfs_referral(int xid, struct cifsSesInfo *pSesInfo,
 }
 #endif
 
-int
-cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
-		const char *devname)
+int cifs_setup_volume_info(struct smb_vol **pvolume_info, char *mount_data,
+			   const char *devname)
 {
-	int rc;
-	int xid;
 	struct smb_vol *volume_info;
-	struct cifsSesInfo *pSesInfo;
-	struct cifsTconInfo *tcon;
-	struct TCP_Server_Info *srvTcp;
-	char   *full_path;
-	struct tcon_link *tlink;
-#ifdef CONFIG_CIFS_DFS_UPCALL
-	int referral_walks_count = 0;
-try_mount_again:
-	/* cleanup activities if we're chasing a referral */
-	if (referral_walks_count) {
-		if (tcon)
-			cifs_put_tcon(tcon);
-		else if (pSesInfo)
-			cifs_put_smb_ses(pSesInfo);
-
-		cleanup_volume_info(&volume_info);
-		FreeXid(xid);
-	}
-#endif
-	rc = 0;
-	tcon = NULL;
-	pSesInfo = NULL;
-	srvTcp = NULL;
-	full_path = NULL;
-	tlink = NULL;
+	int rc = 0;
 
-	xid = GetXid();
+	*pvolume_info = NULL;
 
 	volume_info = kzalloc(sizeof(struct smb_vol), GFP_KERNEL);
 	if (!volume_info) {
@@ -2881,7 +2940,7 @@ try_mount_again:
 		goto out;
 	}
 
-	if (cifs_parse_mount_options(cifs_sb->mountdata, devname,
+	if (cifs_parse_mount_options(mount_data, devname,
 				     volume_info)) {
 		rc = -EINVAL;
 		goto out;
@@ -2889,7 +2948,11 @@ try_mount_again:
 
 	if (volume_info->nullauth) {
 		cFYI(1, "null user");
-		volume_info->username = "";
+		volume_info->username = kzalloc(1, GFP_KERNEL);
+		if (volume_info->username == NULL) {
+			rc = -ENOMEM;
+			goto out;
+		}
 	} else if (volume_info->username) {
 		/* BB fixme parse for domain name here */
 		cFYI(1, "Username: %s", volume_info->username);
@@ -2914,12 +2977,58 @@ try_mount_again:
 			goto out;
 		}
 	}
-	cifs_sb->local_nls = volume_info->local_nls;
+
+	*pvolume_info = volume_info;
+	return rc;
+out:
+	cifs_cleanup_volume_info(&volume_info);
+	return rc;
+}
+
+int
+cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
+{
+	int rc = 0;
+	int xid;
+	struct cifs_ses *pSesInfo;
+	struct cifs_tcon *tcon;
+	struct TCP_Server_Info *srvTcp;
+	char   *full_path;
+	struct tcon_link *tlink;
+#ifdef CONFIG_CIFS_DFS_UPCALL
+	int referral_walks_count = 0;
+
+	rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs", BDI_CAP_MAP_COPY);
+	if (rc)
+		return rc;
+
+	cifs_sb->bdi.ra_pages = default_backing_dev_info.ra_pages;
+
+try_mount_again:
+	/* cleanup activities if we're chasing a referral */
+	if (referral_walks_count) {
+		if (tcon)
+			cifs_put_tcon(tcon);
+		else if (pSesInfo)
+			cifs_put_smb_ses(pSesInfo);
+
+		cifs_cleanup_volume_info(&volume_info);
+		FreeXid(xid);
+	}
+#endif
+	tcon = NULL;
+	pSesInfo = NULL;
+	srvTcp = NULL;
+	full_path = NULL;
+	tlink = NULL;
+
+	xid = GetXid();
 
 	/* get a reference to a tcp session */
 	srvTcp = cifs_get_tcp_session(volume_info);
 	if (IS_ERR(srvTcp)) {
 		rc = PTR_ERR(srvTcp);
+		bdi_destroy(&cifs_sb->bdi);
 		goto out;
 	}
 
@@ -2931,15 +3040,6 @@ try_mount_again:
 		goto mount_fail_check;
 	}
 
-	setup_cifs_sb(volume_info, cifs_sb);
-	if (pSesInfo->capabilities & CAP_LARGE_FILES)
-		sb->s_maxbytes = MAX_LFS_FILESIZE;
-	else
-		sb->s_maxbytes = MAX_NON_LFS;
-
-	/* BB FIXME fix time_gran to be larger for LANMAN sessions */
-	sb->s_time_gran = 100;
-
 	/* search for existing tcon to this server share */
 	tcon = cifs_get_tcon(pSesInfo, volume_info);
 	if (IS_ERR(tcon)) {
@@ -2948,35 +3048,36 @@ try_mount_again:
 		goto remote_path_check;
 	}
 
-	/* do not care if following two calls succeed - informational */
-	if (!tcon->ipc) {
-		CIFSSMBQFSDeviceInfo(xid, tcon);
-		CIFSSMBQFSAttributeInfo(xid, tcon);
-	}
-
 	/* tell server which Unix caps we support */
-	if (tcon->ses->capabilities & CAP_UNIX)
+	if (tcon->ses->capabilities & CAP_UNIX) {
 		/* reset of caps checks mount to see if unix extensions
 		   disabled for just this mount */
-		reset_cifs_unix_caps(xid, tcon, sb, volume_info);
-	else
+		reset_cifs_unix_caps(xid, tcon, cifs_sb, volume_info);
+		if ((tcon->ses->server->tcpStatus == CifsNeedReconnect) &&
+		    (le64_to_cpu(tcon->fsUnixInfo.Capability) &
+		     CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)) {
+			rc = -EACCES;
+			goto mount_fail_check;
+		}
+	} else
 		tcon->unix_ext = 0; /* server does not support them */
 
-	/* convert forward to back slashes in prepath here if needed */
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) == 0)
-		convert_delimiter(cifs_sb->prepath, CIFS_DIR_SEP(cifs_sb));
+	/* do not care if following two calls succeed - informational */
+	if (!tcon->ipc) {
+		CIFSSMBQFSDeviceInfo(xid, tcon);
+		CIFSSMBQFSAttributeInfo(xid, tcon);
+	}
 
 	if ((tcon->unix_ext == 0) && (cifs_sb->rsize > (1024 * 127))) {
 		cifs_sb->rsize = 1024 * 127;
 		cFYI(DBG2, "no very large read support, rsize now 127K");
 	}
-	if (!(tcon->ses->capabilities & CAP_LARGE_WRITE_X))
-		cifs_sb->wsize = min(cifs_sb->wsize,
-			       (tcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE));
 	if (!(tcon->ses->capabilities & CAP_LARGE_READ_X))
 		cifs_sb->rsize = min(cifs_sb->rsize,
 			       (tcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE));
 
+	cifs_sb->wsize = cifs_negotiate_wsize(tcon, volume_info);
+
 remote_path_check:
 #ifdef CONFIG_CIFS_DFS_UPCALL
 	/*
@@ -2996,10 +3097,10 @@ remote_path_check:
 	}
 #endif
 
-	/* check if a whole path (including prepath) is not remote */
+	/* check if a whole path is not remote */
 	if (!rc && tcon) {
 		/* build_path_to_root works only when we have a valid tcon */
-		full_path = cifs_build_path_to_root(cifs_sb, tcon);
+		full_path = cifs_build_path_to_root(volume_info, cifs_sb, tcon);
 		if (full_path == NULL) {
 			rc = -ENOMEM;
 			goto mount_fail_check;
@@ -3025,10 +3126,6 @@ remote_path_check:
 			rc = -ELOOP;
 			goto mount_fail_check;
 		}
-		/* convert forward to back slashes in prepath here if needed */
-		if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) == 0)
-			convert_delimiter(cifs_sb->prepath,
-					CIFS_DIR_SEP(cifs_sb));
 
 		rc = expand_dfs_referral(xid, pSesInfo, volume_info, cifs_sb,
 					 true);
@@ -3078,6 +3175,7 @@ mount_fail_check:
 			cifs_put_smb_ses(pSesInfo);
 		else
 			cifs_put_tcp_session(srvTcp);
+		bdi_destroy(&cifs_sb->bdi);
 		goto out;
 	}
 
@@ -3087,14 +3185,17 @@ mount_fail_check:
 	password will be freed at unmount time) */
 out:
 	/* zero out password before freeing */
-	cleanup_volume_info(&volume_info);
 	FreeXid(xid);
 	return rc;
 }
 
+/*
+ * Issue a TREE_CONNECT request. Note that for IPC$ shares, that the tcon
+ * pointer may be NULL.
+ */
 int
-CIFSTCon(unsigned int xid, struct cifsSesInfo *ses,
-	 const char *tree, struct cifsTconInfo *tcon,
+CIFSTCon(unsigned int xid, struct cifs_ses *ses,
+	 const char *tree, struct cifs_tcon *tcon,
 	 const struct nls_table *nls_codepage)
 {
 	struct smb_hdr *smb_buffer;
@@ -3126,7 +3227,7 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses,
 	pSMB->AndXCommand = 0xFF;
 	pSMB->Flags = cpu_to_le16(TCON_EXTENDED_SECINFO);
 	bcc_ptr = &pSMB->Password[0];
-	if ((ses->server->secMode) & SECMODE_USER) {
+	if (!tcon || (ses->server->sec_mode & SECMODE_USER)) {
 		pSMB->PasswordLength = cpu_to_le16(1);	/* minimum */
 		*bcc_ptr = 0; /* password is null byte */
 		bcc_ptr++;              /* skip password */
@@ -3143,7 +3244,7 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses,
 		if ((global_secflags & CIFSSEC_MAY_LANMAN) &&
 		    (ses->server->secType == LANMAN))
 			calc_lanman_hash(tcon->password, ses->server->cryptkey,
-					 ses->server->secMode &
+					 ses->server->sec_mode &
 					    SECMODE_PW_ENCRYPT ? true : false,
 					 bcc_ptr);
 		else
@@ -3159,7 +3260,7 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses,
 		}
 	}
 
-	if (ses->server->secMode &
+	if (ses->server->sec_mode &
 			(SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
 		smb_buffer->Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
 
@@ -3249,13 +3350,12 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses,
 	return rc;
 }
 
-int
-cifs_umount(struct super_block *sb, struct cifs_sb_info *cifs_sb)
+void
+cifs_umount(struct cifs_sb_info *cifs_sb)
 {
 	struct rb_root *root = &cifs_sb->tlink_tree;
 	struct rb_node *node;
 	struct tcon_link *tlink;
-	char *tmp;
 
 	cancel_delayed_work_sync(&cifs_sb->prune_tlinks);
 
@@ -3272,15 +3372,13 @@ cifs_umount(struct super_block *sb, struct cifs_sb_info *cifs_sb)
 	}
 	spin_unlock(&cifs_sb->tlink_tree_lock);
 
-	tmp = cifs_sb->prepath;
-	cifs_sb->prepathlen = 0;
-	cifs_sb->prepath = NULL;
-	kfree(tmp);
-
-	return 0;
+	bdi_destroy(&cifs_sb->bdi);
+	kfree(cifs_sb->mountdata);
+	unload_nls(cifs_sb->local_nls);
+	kfree(cifs_sb);
 }
 
-int cifs_negotiate_protocol(unsigned int xid, struct cifsSesInfo *ses)
+int cifs_negotiate_protocol(unsigned int xid, struct cifs_ses *ses)
 {
 	int rc = 0;
 	struct TCP_Server_Info *server = ses->server;
@@ -3298,7 +3396,7 @@ int cifs_negotiate_protocol(unsigned int xid, struct cifsSesInfo *ses)
 	}
 	if (rc == 0) {
 		spin_lock(&GlobalMid_Lock);
-		if (server->tcpStatus != CifsExiting)
+		if (server->tcpStatus == CifsNeedNegotiate)
 			server->tcpStatus = CifsGood;
 		else
 			rc = -EHOSTDOWN;
@@ -3310,7 +3408,7 @@ int cifs_negotiate_protocol(unsigned int xid, struct cifsSesInfo *ses)
 }
 
 
-int cifs_setup_session(unsigned int xid, struct cifsSesInfo *ses,
+int cifs_setup_session(unsigned int xid, struct cifs_ses *ses,
 			struct nls_table *nls_info)
 {
 	int rc = 0;
@@ -3322,7 +3420,7 @@ int cifs_setup_session(unsigned int xid, struct cifsSesInfo *ses,
 		ses->capabilities &= (~CAP_UNIX);
 
 	cFYI(1, "Security Mode: 0x%x Capabilities: 0x%x TimeAdjust: %d",
-		 server->secMode, server->capabilities, server->timeAdj);
+		 server->sec_mode, server->capabilities, server->timeAdj);
 
 	rc = CIFS_SessSetup(xid, ses, nls_info);
 	if (rc) {
@@ -3354,12 +3452,12 @@ int cifs_setup_session(unsigned int xid, struct cifsSesInfo *ses,
 	return rc;
 }
 
-static struct cifsTconInfo *
+static struct cifs_tcon *
 cifs_construct_tcon(struct cifs_sb_info *cifs_sb, uid_t fsuid)
 {
-	struct cifsTconInfo *master_tcon = cifs_sb_master_tcon(cifs_sb);
-	struct cifsSesInfo *ses;
-	struct cifsTconInfo *tcon = NULL;
+	struct cifs_tcon *master_tcon = cifs_sb_master_tcon(cifs_sb);
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon = NULL;
 	struct smb_vol *vol_info;
 	char username[28]; /* big enough for "krb50x" + hex of ULONG_MAX 6+16 */
 			   /* We used to have this as MAX_USERNAME which is   */
@@ -3392,7 +3490,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, uid_t fsuid)
 
 	ses = cifs_get_smb_ses(master_tcon->ses->server, vol_info);
 	if (IS_ERR(ses)) {
-		tcon = (struct cifsTconInfo *)ses;
+		tcon = (struct cifs_tcon *)ses;
 		cifs_put_tcp_session(master_tcon->ses->server);
 		goto out;
 	}
@@ -3411,13 +3509,7 @@ out:
 	return tcon;
 }
 
-static inline struct tcon_link *
-cifs_sb_master_tlink(struct cifs_sb_info *cifs_sb)
-{
-	return cifs_sb->master_tlink;
-}
-
-struct cifsTconInfo *
+struct cifs_tcon *
 cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb)
 {
 	return tlink_tcon(cifs_sb_master_tlink(cifs_sb));
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 9ea65cf36714..81914df47ef1 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -50,12 +50,11 @@ build_path_from_dentry(struct dentry *direntry)
 {
 	struct dentry *temp;
 	int namelen;
-	int pplen;
 	int dfsplen;
 	char *full_path;
 	char dirsep;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
-	struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 
 	if (direntry == NULL)
 		return NULL;  /* not much we can do if dentry is freed and
@@ -63,13 +62,12 @@ build_path_from_dentry(struct dentry *direntry)
 		when the server crashed */
 
 	dirsep = CIFS_DIR_SEP(cifs_sb);
-	pplen = cifs_sb->prepathlen;
 	if (tcon->Flags & SMB_SHARE_IS_IN_DFS)
 		dfsplen = strnlen(tcon->treeName, MAX_TREE_SIZE + 1);
 	else
 		dfsplen = 0;
 cifs_bp_rename_retry:
-	namelen = pplen + dfsplen;
+	namelen = dfsplen;
 	for (temp = direntry; !IS_ROOT(temp);) {
 		namelen += (1 + temp->d_name.len);
 		temp = temp->d_parent;
@@ -100,7 +98,7 @@ cifs_bp_rename_retry:
 			return NULL;
 		}
 	}
-	if (namelen != pplen + dfsplen) {
+	if (namelen != dfsplen) {
 		cERROR(1, "did not end path lookup where expected namelen is %d",
 			namelen);
 		/* presumably this is only possible if racing with a rename
@@ -126,7 +124,6 @@ cifs_bp_rename_retry:
 			}
 		}
 	}
-	strncpy(full_path + dfsplen, CIFS_SB(direntry->d_sb)->prepath, pplen);
 	return full_path;
 }
 
@@ -152,7 +149,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
 	__u16 fileHandle;
 	struct cifs_sb_info *cifs_sb;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	char *full_path = NULL;
 	FILE_ALL_INFO *buf = NULL;
 	struct inode *newinode = NULL;
@@ -356,7 +353,8 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode,
 	int xid;
 	struct cifs_sb_info *cifs_sb;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
+	struct cifs_io_parms io_parms;
 	char *full_path = NULL;
 	struct inode *newinode = NULL;
 	int oplock = 0;
@@ -439,16 +437,19 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode,
 	 * timestamps in, but we can reuse it safely */
 
 	pdev = (struct win_dev *)buf;
+	io_parms.netfid = fileHandle;
+	io_parms.pid = current->tgid;
+	io_parms.tcon = pTcon;
+	io_parms.offset = 0;
+	io_parms.length = sizeof(struct win_dev);
 	if (S_ISCHR(mode)) {
 		memcpy(pdev->type, "IntxCHR", 8);
 		pdev->major =
 		      cpu_to_le64(MAJOR(device_number));
 		pdev->minor =
 		      cpu_to_le64(MINOR(device_number));
-		rc = CIFSSMBWrite(xid, pTcon,
-			fileHandle,
-			sizeof(struct win_dev),
-			0, &bytes_written, (char *)pdev,
+		rc = CIFSSMBWrite(xid, &io_parms,
+			&bytes_written, (char *)pdev,
 			NULL, 0);
 	} else if (S_ISBLK(mode)) {
 		memcpy(pdev->type, "IntxBLK", 8);
@@ -456,10 +457,8 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode,
 		      cpu_to_le64(MAJOR(device_number));
 		pdev->minor =
 		      cpu_to_le64(MINOR(device_number));
-		rc = CIFSSMBWrite(xid, pTcon,
-			fileHandle,
-			sizeof(struct win_dev),
-			0, &bytes_written, (char *)pdev,
+		rc = CIFSSMBWrite(xid, &io_parms,
+			&bytes_written, (char *)pdev,
 			NULL, 0);
 	} /* else if (S_ISFIFO) */
 	CIFSSMBClose(xid, pTcon, fileHandle);
@@ -486,7 +485,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 	bool posix_open = false;
 	struct cifs_sb_info *cifs_sb;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	struct cifsFileInfo *cfile;
 	struct inode *newInode = NULL;
 	char *full_path = NULL;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index c672afef0c09..bb71471a4d9d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -114,7 +114,7 @@ int cifs_posix_open(char *full_path, struct inode **pinode,
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct cifs_fattr fattr;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 
 	cFYI(1, "posix open %s", full_path);
 
@@ -168,7 +168,7 @@ posix_open_ret:
 
 static int
 cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb,
-	     struct cifsTconInfo *tcon, unsigned int f_flags, __u32 *poplock,
+	     struct cifs_tcon *tcon, unsigned int f_flags, __u32 *poplock,
 	     __u16 *pnetfid, int xid)
 {
 	int rc;
@@ -285,7 +285,7 @@ cifs_new_fileinfo(__u16 fileHandle, struct file *file,
 void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 {
 	struct inode *inode = cifs_file->dentry->d_inode;
-	struct cifsTconInfo *tcon = tlink_tcon(cifs_file->tlink);
+	struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink);
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct cifsLockInfo *li, *tmp;
@@ -343,7 +343,7 @@ int cifs_open(struct inode *inode, struct file *file)
 	int xid;
 	__u32 oplock;
 	struct cifs_sb_info *cifs_sb;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	struct tcon_link *tlink;
 	struct cifsFileInfo *pCifsFile = NULL;
 	char *full_path = NULL;
@@ -457,7 +457,7 @@ static int cifs_reopen_file(struct cifsFileInfo *pCifsFile, bool can_flush)
 	int xid;
 	__u32 oplock;
 	struct cifs_sb_info *cifs_sb;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	struct cifsInodeInfo *pCifsInode;
 	struct inode *inode;
 	char *full_path = NULL;
@@ -596,7 +596,7 @@ int cifs_closedir(struct inode *inode, struct file *file)
 	xid = GetXid();
 
 	if (pCFileStruct) {
-		struct cifsTconInfo *pTcon = tlink_tcon(pCFileStruct->tlink);
+		struct cifs_tcon *pTcon = tlink_tcon(pCFileStruct->tlink);
 
 		cFYI(1, "Freeing private data in close dir");
 		spin_lock(&cifs_file_list_lock);
@@ -653,7 +653,7 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock)
 	__u64 length;
 	bool wait_flag = false;
 	struct cifs_sb_info *cifs_sb;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	__u16 netfid;
 	__u8 lockType = LOCKING_ANDX_LARGE_FILES;
 	bool posix_locking = 0;
@@ -725,8 +725,8 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock)
 			else
 				posix_lock_type = CIFS_WRLCK;
 			rc = CIFSSMBPosixLock(xid, tcon, netfid, 1 /* get */,
-					length,	pfLock,
-					posix_lock_type, wait_flag);
+					length, pfLock, posix_lock_type,
+					wait_flag);
 			FreeXid(xid);
 			return rc;
 		}
@@ -797,8 +797,8 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock)
 			posix_lock_type = CIFS_UNLCK;
 
 		rc = CIFSSMBPosixLock(xid, tcon, netfid, 0 /* set */,
-				      length, pfLock,
-				      posix_lock_type, wait_flag);
+				      length, pfLock, posix_lock_type,
+				      wait_flag);
 	} else {
 		struct cifsFileInfo *fid = file->private_data;
 
@@ -857,7 +857,7 @@ cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
 		cifsi->server_eof = end_of_write;
 }
 
-static ssize_t cifs_write(struct cifsFileInfo *open_file,
+static ssize_t cifs_write(struct cifsFileInfo *open_file, __u32 pid,
 			  const char *write_data, size_t write_size,
 			  loff_t *poffset)
 {
@@ -865,10 +865,11 @@ static ssize_t cifs_write(struct cifsFileInfo *open_file,
 	unsigned int bytes_written = 0;
 	unsigned int total_written;
 	struct cifs_sb_info *cifs_sb;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	int xid;
 	struct dentry *dentry = open_file->dentry;
 	struct cifsInodeInfo *cifsi = CIFS_I(dentry->d_inode);
+	struct cifs_io_parms io_parms;
 
 	cifs_sb = CIFS_SB(dentry->d_sb);
 
@@ -901,8 +902,13 @@ static ssize_t cifs_write(struct cifsFileInfo *open_file,
 			/* iov[0] is reserved for smb header */
 			iov[1].iov_base = (char *)write_data + total_written;
 			iov[1].iov_len = len;
-			rc = CIFSSMBWrite2(xid, pTcon, open_file->netfid, len,
-					   *poffset, &bytes_written, iov, 1, 0);
+			io_parms.netfid = open_file->netfid;
+			io_parms.pid = pid;
+			io_parms.tcon = pTcon;
+			io_parms.offset = *poffset;
+			io_parms.length = len;
+			rc = CIFSSMBWrite2(xid, &io_parms, &bytes_written, iov,
+					   1, 0);
 		}
 		if (rc || (bytes_written == 0)) {
 			if (total_written)
@@ -1071,8 +1077,8 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to)
 
 	open_file = find_writable_file(CIFS_I(mapping->host), false);
 	if (open_file) {
-		bytes_written = cifs_write(open_file, write_data,
-					   to - from, &offset);
+		bytes_written = cifs_write(open_file, open_file->pid,
+					   write_data, to - from, &offset);
 		cifsFileInfo_put(open_file);
 		/* Does mm or vfs already set times? */
 		inode->i_atime = inode->i_mtime = current_fs_time(inode->i_sb);
@@ -1092,58 +1098,20 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to)
 static int cifs_writepages(struct address_space *mapping,
 			   struct writeback_control *wbc)
 {
-	unsigned int bytes_to_write;
-	unsigned int bytes_written;
-	struct cifs_sb_info *cifs_sb;
-	int done = 0;
-	pgoff_t end;
-	pgoff_t index;
-	int range_whole = 0;
-	struct kvec *iov;
-	int len;
-	int n_iov = 0;
-	pgoff_t next;
-	int nr_pages;
-	__u64 offset = 0;
-	struct cifsFileInfo *open_file;
-	struct cifsTconInfo *tcon;
-	struct cifsInodeInfo *cifsi = CIFS_I(mapping->host);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(mapping->host->i_sb);
+	bool done = false, scanned = false, range_whole = false;
+	pgoff_t end, index;
+	struct cifs_writedata *wdata;
 	struct page *page;
-	struct pagevec pvec;
 	int rc = 0;
-	int scanned = 0;
-	int xid;
-
-	cifs_sb = CIFS_SB(mapping->host->i_sb);
 
 	/*
-	 * If wsize is smaller that the page cache size, default to writing
+	 * If wsize is smaller than the page cache size, default to writing
 	 * one page at a time via cifs_writepage
 	 */
 	if (cifs_sb->wsize < PAGE_CACHE_SIZE)
 		return generic_writepages(mapping, wbc);
 
-	iov = kmalloc(32 * sizeof(struct kvec), GFP_KERNEL);
-	if (iov == NULL)
-		return generic_writepages(mapping, wbc);
-
-	/*
-	 * if there's no open file, then this is likely to fail too,
-	 * but it'll at least handle the return. Maybe it should be
-	 * a BUG() instead?
-	 */
-	open_file = find_writable_file(CIFS_I(mapping->host), false);
-	if (!open_file) {
-		kfree(iov);
-		return generic_writepages(mapping, wbc);
-	}
-
-	tcon = tlink_tcon(open_file->tlink);
-	cifsFileInfo_put(open_file);
-
-	xid = GetXid();
-
-	pagevec_init(&pvec, 0);
 	if (wbc->range_cyclic) {
 		index = mapping->writeback_index; /* Start from prev offset */
 		end = -1;
@@ -1151,24 +1119,49 @@ static int cifs_writepages(struct address_space *mapping,
 		index = wbc->range_start >> PAGE_CACHE_SHIFT;
 		end = wbc->range_end >> PAGE_CACHE_SHIFT;
 		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
-			range_whole = 1;
-		scanned = 1;
+			range_whole = true;
+		scanned = true;
 	}
 retry:
-	while (!done && (index <= end) &&
-	       (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
-			PAGECACHE_TAG_DIRTY,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1))) {
-		int first;
-		unsigned int i;
-
-		first = -1;
-		next = 0;
-		n_iov = 0;
-		bytes_to_write = 0;
-
-		for (i = 0; i < nr_pages; i++) {
-			page = pvec.pages[i];
+	while (!done && index <= end) {
+		unsigned int i, nr_pages, found_pages;
+		pgoff_t next = 0, tofind;
+		struct page **pages;
+
+		tofind = min((cifs_sb->wsize / PAGE_CACHE_SIZE) - 1,
+				end - index) + 1;
+
+		wdata = cifs_writedata_alloc((unsigned int)tofind);
+		if (!wdata) {
+			rc = -ENOMEM;
+			break;
+		}
+
+		/*
+		 * find_get_pages_tag seems to return a max of 256 on each
+		 * iteration, so we must call it several times in order to
+		 * fill the array or the wsize is effectively limited to
+		 * 256 * PAGE_CACHE_SIZE.
+		 */
+		found_pages = 0;
+		pages = wdata->pages;
+		do {
+			nr_pages = find_get_pages_tag(mapping, &index,
+							PAGECACHE_TAG_DIRTY,
+							tofind, pages);
+			found_pages += nr_pages;
+			tofind -= nr_pages;
+			pages += nr_pages;
+		} while (nr_pages && tofind && index <= end);
+
+		if (found_pages == 0) {
+			kref_put(&wdata->refcount, cifs_writedata_release);
+			break;
+		}
+
+		nr_pages = 0;
+		for (i = 0; i < found_pages; i++) {
+			page = wdata->pages[i];
 			/*
 			 * At this point we hold neither mapping->tree_lock nor
 			 * lock on the page itself: the page may be truncated or
@@ -1177,7 +1170,7 @@ retry:
 			 * mapping
 			 */
 
-			if (first < 0)
+			if (nr_pages == 0)
 				lock_page(page);
 			else if (!trylock_page(page))
 				break;
@@ -1188,7 +1181,7 @@ retry:
 			}
 
 			if (!wbc->range_cyclic && page->index > end) {
-				done = 1;
+				done = true;
 				unlock_page(page);
 				break;
 			}
@@ -1215,119 +1208,89 @@ retry:
 			set_page_writeback(page);
 
 			if (page_offset(page) >= mapping->host->i_size) {
-				done = 1;
+				done = true;
 				unlock_page(page);
 				end_page_writeback(page);
 				break;
 			}
 
-			/*
-			 * BB can we get rid of this?  pages are held by pvec
-			 */
-			page_cache_get(page);
+			wdata->pages[i] = page;
+			next = page->index + 1;
+			++nr_pages;
+		}
 
-			len = min(mapping->host->i_size - page_offset(page),
-				  (loff_t)PAGE_CACHE_SIZE);
+		/* reset index to refind any pages skipped */
+		if (nr_pages == 0)
+			index = wdata->pages[0]->index + 1;
 
-			/* reserve iov[0] for the smb header */
-			n_iov++;
-			iov[n_iov].iov_base = kmap(page);
-			iov[n_iov].iov_len = len;
-			bytes_to_write += len;
+		/* put any pages we aren't going to use */
+		for (i = nr_pages; i < found_pages; i++) {
+			page_cache_release(wdata->pages[i]);
+			wdata->pages[i] = NULL;
+		}
 
-			if (first < 0) {
-				first = i;
-				offset = page_offset(page);
-			}
-			next = page->index + 1;
-			if (bytes_to_write + PAGE_CACHE_SIZE > cifs_sb->wsize)
-				break;
+		/* nothing to write? */
+		if (nr_pages == 0) {
+			kref_put(&wdata->refcount, cifs_writedata_release);
+			continue;
 		}
-		if (n_iov) {
-retry_write:
-			open_file = find_writable_file(CIFS_I(mapping->host),
-							false);
-			if (!open_file) {
-				cERROR(1, "No writable handles for inode");
-				rc = -EBADF;
-			} else {
-				rc = CIFSSMBWrite2(xid, tcon, open_file->netfid,
-						   bytes_to_write, offset,
-						   &bytes_written, iov, n_iov,
-						   0);
-				cifsFileInfo_put(open_file);
-			}
 
-			cFYI(1, "Write2 rc=%d, wrote=%u", rc, bytes_written);
+		wdata->sync_mode = wbc->sync_mode;
+		wdata->nr_pages = nr_pages;
+		wdata->offset = page_offset(wdata->pages[0]);
 
-			/*
-			 * For now, treat a short write as if nothing got
-			 * written. A zero length write however indicates
-			 * ENOSPC or EFBIG. We have no way to know which
-			 * though, so call it ENOSPC for now. EFBIG would
-			 * get translated to AS_EIO anyway.
-			 *
-			 * FIXME: make it take into account the data that did
-			 *	  get written
-			 */
-			if (rc == 0) {
-				if (bytes_written == 0)
-					rc = -ENOSPC;
-				else if (bytes_written < bytes_to_write)
-					rc = -EAGAIN;
+		do {
+			if (wdata->cfile != NULL)
+				cifsFileInfo_put(wdata->cfile);
+			wdata->cfile = find_writable_file(CIFS_I(mapping->host),
+							  false);
+			if (!wdata->cfile) {
+				cERROR(1, "No writable handles for inode");
+				rc = -EBADF;
+				break;
 			}
+			rc = cifs_async_writev(wdata);
+		} while (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN);
 
-			/* retry on data-integrity flush */
-			if (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN)
-				goto retry_write;
-
-			/* fix the stats and EOF */
-			if (bytes_written > 0) {
-				cifs_stats_bytes_written(tcon, bytes_written);
-				cifs_update_eof(cifsi, offset, bytes_written);
-			}
+		for (i = 0; i < nr_pages; ++i)
+			unlock_page(wdata->pages[i]);
 
-			for (i = 0; i < n_iov; i++) {
-				page = pvec.pages[first + i];
-				/* on retryable write error, redirty page */
+		/* send failure -- clean up the mess */
+		if (rc != 0) {
+			for (i = 0; i < nr_pages; ++i) {
 				if (rc == -EAGAIN)
-					redirty_page_for_writepage(wbc, page);
-				else if (rc != 0)
-					SetPageError(page);
-				kunmap(page);
-				unlock_page(page);
-				end_page_writeback(page);
-				page_cache_release(page);
+					redirty_page_for_writepage(wbc,
+							   wdata->pages[i]);
+				else
+					SetPageError(wdata->pages[i]);
+				end_page_writeback(wdata->pages[i]);
+				page_cache_release(wdata->pages[i]);
 			}
-
 			if (rc != -EAGAIN)
 				mapping_set_error(mapping, rc);
-			else
-				rc = 0;
+		}
+		kref_put(&wdata->refcount, cifs_writedata_release);
 
-			if ((wbc->nr_to_write -= n_iov) <= 0)
-				done = 1;
-			index = next;
-		} else
-			/* Need to re-find the pages we skipped */
-			index = pvec.pages[0]->index + 1;
+		wbc->nr_to_write -= nr_pages;
+		if (wbc->nr_to_write <= 0)
+			done = true;
 
-		pagevec_release(&pvec);
+		index = next;
 	}
+
 	if (!scanned && !done) {
 		/*
 		 * We hit the last page and there is more work to be done: wrap
 		 * back to the start of the file
 		 */
-		scanned = 1;
+		scanned = true;
 		index = 0;
 		goto retry;
 	}
+
 	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
 		mapping->writeback_index = index;
 
-	FreeXid(xid);
-	kfree(iov);
 	return rc;
 }
 
@@ -1383,6 +1346,14 @@ static int cifs_write_end(struct file *file, struct address_space *mapping,
 {
 	int rc;
 	struct inode *inode = mapping->host;
+	struct cifsFileInfo *cfile = file->private_data;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb);
+	__u32 pid;
+
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
+		pid = cfile->pid;
+	else
+		pid = current->tgid;
 
 	cFYI(1, "write_end for page %p from pos %lld with %d bytes",
 		 page, pos, copied);
@@ -1406,8 +1377,7 @@ static int cifs_write_end(struct file *file, struct address_space *mapping,
 		/* BB check if anything else missing out of ppw
 		   such as updating last write time */
 		page_data = kmap(page);
-		rc = cifs_write(file->private_data, page_data + offset,
-				copied, &pos);
+		rc = cifs_write(cfile, pid, page_data + offset, copied, &pos);
 		/* if (rc < 0) should we set writebehind rc? */
 		kunmap(page);
 
@@ -1435,7 +1405,7 @@ int cifs_strict_fsync(struct file *file, int datasync)
 {
 	int xid;
 	int rc = 0;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	struct cifsFileInfo *smbfile = file->private_data;
 	struct inode *inode = file->f_path.dentry->d_inode;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
@@ -1465,7 +1435,7 @@ int cifs_fsync(struct file *file, int datasync)
 {
 	int xid;
 	int rc = 0;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	struct cifsFileInfo *smbfile = file->private_data;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
 
@@ -1556,9 +1526,11 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
 	struct iov_iter it;
 	struct inode *inode;
 	struct cifsFileInfo *open_file;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	struct cifs_sb_info *cifs_sb;
+	struct cifs_io_parms io_parms;
 	int xid, rc;
+	__u32 pid;
 
 	len = iov_length(iov, nr_segs);
 	if (!len)
@@ -1590,6 +1562,12 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
 
 	xid = GetXid();
 	open_file = file->private_data;
+
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
+		pid = open_file->pid;
+	else
+		pid = current->tgid;
+
 	pTcon = tlink_tcon(open_file->tlink);
 	inode = file->f_path.dentry->d_inode;
 
@@ -1616,9 +1594,13 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
 				if (rc != 0)
 					break;
 			}
-			rc = CIFSSMBWrite2(xid, pTcon, open_file->netfid,
-					   cur_len, *poffset, &written,
-					   to_send, npages, 0);
+			io_parms.netfid = open_file->netfid;
+			io_parms.pid = pid;
+			io_parms.tcon = pTcon;
+			io_parms.offset = *poffset;
+			io_parms.length = cur_len;
+			rc = CIFSSMBWrite2(xid, &io_parms, &written, to_send,
+					   npages, 0);
 		} while (rc == -EAGAIN);
 
 		for (i = 0; i < npages; i++)
@@ -1711,10 +1693,12 @@ cifs_iovec_read(struct file *file, const struct iovec *iov,
 	size_t len, cur_len;
 	int iov_offset = 0;
 	struct cifs_sb_info *cifs_sb;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	struct cifsFileInfo *open_file;
 	struct smb_com_read_rsp *pSMBr;
+	struct cifs_io_parms io_parms;
 	char *read_data;
+	__u32 pid;
 
 	if (!nr_segs)
 		return 0;
@@ -1729,6 +1713,11 @@ cifs_iovec_read(struct file *file, const struct iovec *iov,
 	open_file = file->private_data;
 	pTcon = tlink_tcon(open_file->tlink);
 
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
+		pid = open_file->pid;
+	else
+		pid = current->tgid;
+
 	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
 		cFYI(1, "attempting read on write only file instance");
 
@@ -1744,8 +1733,12 @@ cifs_iovec_read(struct file *file, const struct iovec *iov,
 				if (rc != 0)
 					break;
 			}
-			rc = CIFSSMBRead(xid, pTcon, open_file->netfid,
-					 cur_len, *poffset, &bytes_read,
+			io_parms.netfid = open_file->netfid;
+			io_parms.pid = pid;
+			io_parms.tcon = pTcon;
+			io_parms.offset = *poffset;
+			io_parms.length = len;
+			rc = CIFSSMBRead(xid, &io_parms, &bytes_read,
 					 &read_data, &buf_type);
 			pSMBr = (struct smb_com_read_rsp *)read_data;
 			if (read_data) {
@@ -1822,11 +1815,13 @@ static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size,
 	unsigned int total_read;
 	unsigned int current_read_size;
 	struct cifs_sb_info *cifs_sb;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	int xid;
 	char *current_offset;
 	struct cifsFileInfo *open_file;
+	struct cifs_io_parms io_parms;
 	int buf_type = CIFS_NO_BUFFER;
+	__u32 pid;
 
 	xid = GetXid();
 	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
@@ -1839,6 +1834,11 @@ static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size,
 	open_file = file->private_data;
 	pTcon = tlink_tcon(open_file->tlink);
 
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
+		pid = open_file->pid;
+	else
+		pid = current->tgid;
+
 	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
 		cFYI(1, "attempting read on write only file instance");
 
@@ -1861,11 +1861,13 @@ static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size,
 				if (rc != 0)
 					break;
 			}
-			rc = CIFSSMBRead(xid, pTcon,
-					 open_file->netfid,
-					 current_read_size, *poffset,
-					 &bytes_read, &current_offset,
-					 &buf_type);
+			io_parms.netfid = open_file->netfid;
+			io_parms.pid = pid;
+			io_parms.tcon = pTcon;
+			io_parms.offset = *poffset;
+			io_parms.length = current_read_size;
+			rc = CIFSSMBRead(xid, &io_parms, &bytes_read,
+					 &current_offset, &buf_type);
 		}
 		if (rc || (bytes_read == 0)) {
 			if (total_read) {
@@ -1996,13 +1998,15 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 	loff_t offset;
 	struct page *page;
 	struct cifs_sb_info *cifs_sb;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	unsigned int bytes_read = 0;
 	unsigned int read_size, i;
 	char *smb_read_data = NULL;
 	struct smb_com_read_rsp *pSMBr;
 	struct cifsFileInfo *open_file;
+	struct cifs_io_parms io_parms;
 	int buf_type = CIFS_NO_BUFFER;
+	__u32 pid;
 
 	xid = GetXid();
 	if (file->private_data == NULL) {
@@ -2024,6 +2028,11 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 		goto read_complete;
 
 	cFYI(DBG2, "rpages: num pages %d", num_pages);
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
+		pid = open_file->pid;
+	else
+		pid = current->tgid;
+
 	for (i = 0; i < num_pages; ) {
 		unsigned contig_pages;
 		struct page *tmp_page;
@@ -2065,12 +2074,13 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 				if (rc != 0)
 					break;
 			}
-
-			rc = CIFSSMBRead(xid, pTcon,
-					 open_file->netfid,
-					 read_size, offset,
-					 &bytes_read, &smb_read_data,
-					 &buf_type);
+			io_parms.netfid = open_file->netfid;
+			io_parms.pid = pid;
+			io_parms.tcon = pTcon;
+			io_parms.offset = offset;
+			io_parms.length = read_size;
+			rc = CIFSSMBRead(xid, &io_parms, &bytes_read,
+					 &smb_read_data, &buf_type);
 			/* BB more RC checks ? */
 			if (rc == -EAGAIN) {
 				if (smb_read_data) {
diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c
index 297a43d0ff7f..816696621ec9 100644
--- a/fs/cifs/fscache.c
+++ b/fs/cifs/fscache.c
@@ -28,32 +28,32 @@ void cifs_fscache_get_client_cookie(struct TCP_Server_Info *server)
 	server->fscache =
 		fscache_acquire_cookie(cifs_fscache_netfs.primary_index,
 				&cifs_fscache_server_index_def, server);
-	cFYI(1, "CIFS: get client cookie (0x%p/0x%p)", server,
-				server->fscache);
+	cFYI(1, "%s: (0x%p/0x%p)", __func__, server,
+			server->fscache);
 }
 
 void cifs_fscache_release_client_cookie(struct TCP_Server_Info *server)
 {
-	cFYI(1, "CIFS: release client cookie (0x%p/0x%p)", server,
-				server->fscache);
+	cFYI(1, "%s: (0x%p/0x%p)", __func__, server,
+			server->fscache);
 	fscache_relinquish_cookie(server->fscache, 0);
 	server->fscache = NULL;
 }
 
-void cifs_fscache_get_super_cookie(struct cifsTconInfo *tcon)
+void cifs_fscache_get_super_cookie(struct cifs_tcon *tcon)
 {
 	struct TCP_Server_Info *server = tcon->ses->server;
 
 	tcon->fscache =
 		fscache_acquire_cookie(server->fscache,
 				&cifs_fscache_super_index_def, tcon);
-	cFYI(1, "CIFS: get superblock cookie (0x%p/0x%p)",
-				server->fscache, tcon->fscache);
+	cFYI(1, "%s: (0x%p/0x%p)", __func__, server->fscache,
+			tcon->fscache);
 }
 
-void cifs_fscache_release_super_cookie(struct cifsTconInfo *tcon)
+void cifs_fscache_release_super_cookie(struct cifs_tcon *tcon)
 {
-	cFYI(1, "CIFS: releasing superblock cookie (0x%p)", tcon->fscache);
+	cFYI(1, "%s: (0x%p)", __func__, tcon->fscache);
 	fscache_relinquish_cookie(tcon->fscache, 0);
 	tcon->fscache = NULL;
 }
@@ -62,7 +62,7 @@ static void cifs_fscache_enable_inode_cookie(struct inode *inode)
 {
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
-	struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 
 	if (cifsi->fscache)
 		return;
@@ -70,8 +70,8 @@ static void cifs_fscache_enable_inode_cookie(struct inode *inode)
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE) {
 		cifsi->fscache = fscache_acquire_cookie(tcon->fscache,
 				&cifs_fscache_inode_object_def, cifsi);
-		cFYI(1, "CIFS: got FH cookie (0x%p/0x%p)", tcon->fscache,
-				cifsi->fscache);
+		cFYI(1, "%s: got FH cookie (0x%p/0x%p)", __func__,
+				tcon->fscache, cifsi->fscache);
 	}
 }
 
@@ -80,8 +80,7 @@ void cifs_fscache_release_inode_cookie(struct inode *inode)
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 
 	if (cifsi->fscache) {
-		cFYI(1, "CIFS releasing inode cookie (0x%p)",
-				cifsi->fscache);
+		cFYI(1, "%s: (0x%p)", __func__, cifsi->fscache);
 		fscache_relinquish_cookie(cifsi->fscache, 0);
 		cifsi->fscache = NULL;
 	}
@@ -92,8 +91,7 @@ static void cifs_fscache_disable_inode_cookie(struct inode *inode)
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 
 	if (cifsi->fscache) {
-		cFYI(1, "CIFS disabling inode cookie (0x%p)",
-				cifsi->fscache);
+		cFYI(1, "%s: (0x%p)", __func__, cifsi->fscache);
 		fscache_relinquish_cookie(cifsi->fscache, 1);
 		cifsi->fscache = NULL;
 	}
@@ -121,8 +119,8 @@ void cifs_fscache_reset_inode_cookie(struct inode *inode)
 					cifs_sb_master_tcon(cifs_sb)->fscache,
 					&cifs_fscache_inode_object_def,
 					cifsi);
-		cFYI(1, "CIFS: new cookie 0x%p oldcookie 0x%p",
-				cifsi->fscache, old);
+		cFYI(1, "%s: new cookie 0x%p oldcookie 0x%p",
+				__func__, cifsi->fscache, old);
 	}
 }
 
@@ -132,8 +130,8 @@ int cifs_fscache_release_page(struct page *page, gfp_t gfp)
 		struct inode *inode = page->mapping->host;
 		struct cifsInodeInfo *cifsi = CIFS_I(inode);
 
-		cFYI(1, "CIFS: fscache release page (0x%p/0x%p)",
-				page, cifsi->fscache);
+		cFYI(1, "%s: (0x%p/0x%p)", __func__, page,
+				cifsi->fscache);
 		if (!fscache_maybe_release_page(cifsi->fscache, page, gfp))
 			return 0;
 	}
@@ -144,8 +142,7 @@ int cifs_fscache_release_page(struct page *page, gfp_t gfp)
 static void cifs_readpage_from_fscache_complete(struct page *page, void *ctx,
 						int error)
 {
-	cFYI(1, "CFS: readpage_from_fscache_complete (0x%p/%d)",
-			page, error);
+	cFYI(1, "%s: (0x%p/%d)", __func__, page, error);
 	if (!error)
 		SetPageUptodate(page);
 	unlock_page(page);
@@ -158,7 +155,7 @@ int __cifs_readpage_from_fscache(struct inode *inode, struct page *page)
 {
 	int ret;
 
-	cFYI(1, "CIFS: readpage_from_fscache(fsc:%p, p:%p, i:0x%p",
+	cFYI(1, "%s: (fsc:%p, p:%p, i:0x%p", __func__,
 			CIFS_I(inode)->fscache, page, inode);
 	ret = fscache_read_or_alloc_page(CIFS_I(inode)->fscache, page,
 					 cifs_readpage_from_fscache_complete,
@@ -167,11 +164,11 @@ int __cifs_readpage_from_fscache(struct inode *inode, struct page *page)
 	switch (ret) {
 
 	case 0: /* page found in fscache, read submitted */
-		cFYI(1, "CIFS: readpage_from_fscache: submitted");
+		cFYI(1, "%s: submitted", __func__);
 		return ret;
 	case -ENOBUFS:	/* page won't be cached */
 	case -ENODATA:	/* page not in cache */
-		cFYI(1, "CIFS: readpage_from_fscache %d", ret);
+		cFYI(1, "%s: %d", __func__, ret);
 		return 1;
 
 	default:
@@ -190,7 +187,7 @@ int __cifs_readpages_from_fscache(struct inode *inode,
 {
 	int ret;
 
-	cFYI(1, "CIFS: __cifs_readpages_from_fscache (0x%p/%u/0x%p)",
+	cFYI(1, "%s: (0x%p/%u/0x%p)", __func__,
 			CIFS_I(inode)->fscache, *nr_pages, inode);
 	ret = fscache_read_or_alloc_pages(CIFS_I(inode)->fscache, mapping,
 					  pages, nr_pages,
@@ -199,12 +196,12 @@ int __cifs_readpages_from_fscache(struct inode *inode,
 					  mapping_gfp_mask(mapping));
 	switch (ret) {
 	case 0:	/* read submitted to the cache for all pages */
-		cFYI(1, "CIFS: readpages_from_fscache: submitted");
+		cFYI(1, "%s: submitted", __func__);
 		return ret;
 
 	case -ENOBUFS:	/* some pages are not cached and can't be */
 	case -ENODATA:	/* some pages are not cached */
-		cFYI(1, "CIFS: readpages_from_fscache: no page");
+		cFYI(1, "%s: no page", __func__);
 		return 1;
 
 	default:
@@ -218,7 +215,7 @@ void __cifs_readpage_to_fscache(struct inode *inode, struct page *page)
 {
 	int ret;
 
-	cFYI(1, "CIFS: readpage_to_fscache(fsc: %p, p: %p, i: %p",
+	cFYI(1, "%s: (fsc: %p, p: %p, i: %p)", __func__,
 			CIFS_I(inode)->fscache, page, inode);
 	ret = fscache_write_page(CIFS_I(inode)->fscache, page, GFP_KERNEL);
 	if (ret != 0)
@@ -230,7 +227,7 @@ void __cifs_fscache_invalidate_page(struct page *page, struct inode *inode)
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 	struct fscache_cookie *cookie = cifsi->fscache;
 
-	cFYI(1, "CIFS: fscache invalidatepage (0x%p/0x%p)", page, cookie);
+	cFYI(1, "%s: (0x%p/0x%p)", __func__, page, cookie);
 	fscache_wait_on_page_write(cookie, page);
 	fscache_uncache_page(cookie, page);
 }
diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h
index 31b88ec2341e..63539323e0b9 100644
--- a/fs/cifs/fscache.h
+++ b/fs/cifs/fscache.h
@@ -40,8 +40,8 @@ extern void cifs_fscache_unregister(void);
  */
 extern void cifs_fscache_get_client_cookie(struct TCP_Server_Info *);
 extern void cifs_fscache_release_client_cookie(struct TCP_Server_Info *);
-extern void cifs_fscache_get_super_cookie(struct cifsTconInfo *);
-extern void cifs_fscache_release_super_cookie(struct cifsTconInfo *);
+extern void cifs_fscache_get_super_cookie(struct cifs_tcon *);
+extern void cifs_fscache_release_super_cookie(struct cifs_tcon *);
 
 extern void cifs_fscache_release_inode_cookie(struct inode *);
 extern void cifs_fscache_set_inode_cookie(struct inode *, struct file *);
@@ -99,9 +99,9 @@ static inline void
 cifs_fscache_get_client_cookie(struct TCP_Server_Info *server) {}
 static inline void
 cifs_fscache_release_client_cookie(struct TCP_Server_Info *server) {}
-static inline void cifs_fscache_get_super_cookie(struct cifsTconInfo *tcon) {}
+static inline void cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) {}
 static inline void
-cifs_fscache_release_super_cookie(struct cifsTconInfo *tcon) {}
+cifs_fscache_release_super_cookie(struct cifs_tcon *tcon) {}
 
 static inline void cifs_fscache_release_inode_cookie(struct inode *inode) {}
 static inline void cifs_fscache_set_inode_cookie(struct inode *inode,
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index de02ed5e25c2..9b018c8334fa 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -295,7 +295,7 @@ int cifs_get_file_info_unix(struct file *filp)
 	struct inode *inode = filp->f_path.dentry->d_inode;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct cifsFileInfo *cfile = filp->private_data;
-	struct cifsTconInfo *tcon = tlink_tcon(cfile->tlink);
+	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 
 	xid = GetXid();
 	rc = CIFSSMBUnixQFileInfo(xid, tcon, cfile->netfid, &find_data);
@@ -318,7 +318,7 @@ int cifs_get_inode_info_unix(struct inode **pinode,
 	int rc;
 	FILE_UNIX_BASIC_INFO find_data;
 	struct cifs_fattr fattr;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	struct tcon_link *tlink;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 
@@ -373,7 +373,8 @@ cifs_sfu_type(struct cifs_fattr *fattr, const unsigned char *path,
 	int oplock = 0;
 	__u16 netfid;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
+	struct cifs_io_parms io_parms;
 	char buf[24];
 	unsigned int bytes_read;
 	char *pbuf;
@@ -405,9 +406,13 @@ cifs_sfu_type(struct cifs_fattr *fattr, const unsigned char *path,
 	if (rc == 0) {
 		int buf_type = CIFS_NO_BUFFER;
 			/* Read header */
-		rc = CIFSSMBRead(xid, tcon, netfid,
-				 24 /* length */, 0 /* offset */,
-				 &bytes_read, &pbuf, &buf_type);
+		io_parms.netfid = netfid;
+		io_parms.pid = current->tgid;
+		io_parms.tcon = tcon;
+		io_parms.offset = 0;
+		io_parms.length = 24;
+		rc = CIFSSMBRead(xid, &io_parms, &bytes_read, &pbuf,
+				 &buf_type);
 		if ((rc == 0) && (bytes_read >= 8)) {
 			if (memcmp("IntxBLK", pbuf, 8) == 0) {
 				cFYI(1, "Block device");
@@ -468,7 +473,7 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path,
 	char ea_value[4];
 	__u32 mode;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 
 	tlink = cifs_sb_tlink(cifs_sb);
 	if (IS_ERR(tlink))
@@ -502,7 +507,7 @@ static void
 cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
 		       struct cifs_sb_info *cifs_sb, bool adjust_tz)
 {
-	struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 
 	memset(fattr, 0, sizeof(*fattr));
 	fattr->cf_cifsattrs = le32_to_cpu(info->Attributes);
@@ -553,7 +558,7 @@ int cifs_get_file_info(struct file *filp)
 	struct inode *inode = filp->f_path.dentry->d_inode;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct cifsFileInfo *cfile = filp->private_data;
-	struct cifsTconInfo *tcon = tlink_tcon(cfile->tlink);
+	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 
 	xid = GetXid();
 	rc = CIFSSMBQFileInfo(xid, tcon, cfile->netfid, &find_data);
@@ -590,7 +595,7 @@ int cifs_get_inode_info(struct inode **pinode,
 	struct super_block *sb, int xid, const __u16 *pfid)
 {
 	int rc = 0, tmprc;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	struct tcon_link *tlink;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	char *buf = NULL;
@@ -735,10 +740,10 @@ static const struct inode_operations cifs_ipc_inode_ops = {
 	.lookup = cifs_lookup,
 };
 
-char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb,
-				struct cifsTconInfo *tcon)
+char *cifs_build_path_to_root(struct smb_vol *vol, struct cifs_sb_info *cifs_sb,
+			      struct cifs_tcon *tcon)
 {
-	int pplen = cifs_sb->prepathlen;
+	int pplen = vol->prepath ? strlen(vol->prepath) : 0;
 	int dfsplen;
 	char *full_path = NULL;
 
@@ -772,7 +777,7 @@ char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb,
 			}
 		}
 	}
-	strncpy(full_path + dfsplen, cifs_sb->prepath, pplen);
+	strncpy(full_path + dfsplen, vol->prepath, pplen);
 	full_path[dfsplen + pplen] = 0; /* add trailing null */
 	return full_path;
 }
@@ -884,19 +889,13 @@ struct inode *cifs_root_iget(struct super_block *sb)
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct inode *inode = NULL;
 	long rc;
-	char *full_path;
-	struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb);
-
-	full_path = cifs_build_path_to_root(cifs_sb, tcon);
-	if (full_path == NULL)
-		return ERR_PTR(-ENOMEM);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 
 	xid = GetXid();
 	if (tcon->unix_ext)
-		rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid);
+		rc = cifs_get_inode_info_unix(&inode, "", sb, xid);
 	else
-		rc = cifs_get_inode_info(&inode, full_path, NULL, sb,
-						xid, NULL);
+		rc = cifs_get_inode_info(&inode, "", NULL, sb, xid, NULL);
 
 	if (!inode) {
 		inode = ERR_PTR(rc);
@@ -922,7 +921,6 @@ struct inode *cifs_root_iget(struct super_block *sb)
 	}
 
 out:
-	kfree(full_path);
 	/* can not call macro FreeXid here since in a void func
 	 * TODO: This is no longer true
 	 */
@@ -943,7 +941,7 @@ cifs_set_file_info(struct inode *inode, struct iattr *attrs, int xid,
 	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct tcon_link *tlink = NULL;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	FILE_BASIC_INFO	info_buf;
 
 	if (attrs == NULL)
@@ -1061,7 +1059,7 @@ cifs_rename_pending_delete(char *full_path, struct dentry *dentry, int xid)
 	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct tcon_link *tlink;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	__u32 dosattr, origattr;
 	FILE_BASIC_INFO *info_buf = NULL;
 
@@ -1179,7 +1177,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry)
 	struct super_block *sb = dir->i_sb;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct tcon_link *tlink;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	struct iattr *attrs = NULL;
 	__u32 dosattr = 0, origattr = 0;
 
@@ -1277,7 +1275,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode)
 	int xid;
 	struct cifs_sb_info *cifs_sb;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	char *full_path = NULL;
 	struct inode *newinode = NULL;
 	struct cifs_fattr fattr;
@@ -1455,7 +1453,7 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
 	int xid;
 	struct cifs_sb_info *cifs_sb;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	char *full_path = NULL;
 	struct cifsInodeInfo *cifsInode;
 
@@ -1512,7 +1510,7 @@ cifs_do_rename(int xid, struct dentry *from_dentry, const char *fromPath,
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(from_dentry->d_sb);
 	struct tcon_link *tlink;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	__u16 srcfid;
 	int oplock, rc;
 
@@ -1564,7 +1562,7 @@ int cifs_rename(struct inode *source_dir, struct dentry *source_dentry,
 	char *toName = NULL;
 	struct cifs_sb_info *cifs_sb;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	FILE_UNIX_BASIC_INFO *info_buf_source = NULL;
 	FILE_UNIX_BASIC_INFO *info_buf_target;
 	int xid, rc, tmprc;
@@ -1794,7 +1792,7 @@ int cifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		 struct kstat *stat)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb);
-	struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	struct inode *inode = dentry->d_inode;
 	int rc;
 
@@ -1872,7 +1870,8 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
 	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct tcon_link *tlink = NULL;
-	struct cifsTconInfo *pTcon = NULL;
+	struct cifs_tcon *pTcon = NULL;
+	struct cifs_io_parms io_parms;
 
 	/*
 	 * To avoid spurious oplock breaks from server, in the case of
@@ -1894,8 +1893,14 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
 		cFYI(1, "SetFSize for attrs rc = %d", rc);
 		if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
 			unsigned int bytes_written;
-			rc = CIFSSMBWrite(xid, pTcon, nfid, 0, attrs->ia_size,
-					  &bytes_written, NULL, NULL, 1);
+
+			io_parms.netfid = nfid;
+			io_parms.pid = npid;
+			io_parms.tcon = pTcon;
+			io_parms.offset = 0;
+			io_parms.length = attrs->ia_size;
+			rc = CIFSSMBWrite(xid, &io_parms, &bytes_written,
+					  NULL, NULL, 1);
 			cFYI(1, "Wrt seteof rc %d", rc);
 		}
 	} else
@@ -1930,10 +1935,15 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
 					CIFS_MOUNT_MAP_SPECIAL_CHR);
 			if (rc == 0) {
 				unsigned int bytes_written;
-				rc = CIFSSMBWrite(xid, pTcon, netfid, 0,
-						  attrs->ia_size,
-						  &bytes_written, NULL,
-						  NULL, 1);
+
+				io_parms.netfid = netfid;
+				io_parms.pid = current->tgid;
+				io_parms.tcon = pTcon;
+				io_parms.offset = 0;
+				io_parms.length = attrs->ia_size;
+				rc = CIFSSMBWrite(xid, &io_parms,
+						  &bytes_written,
+						  NULL, NULL,  1);
 				cFYI(1, "wrt seteof rc %d", rc);
 				CIFSSMBClose(xid, pTcon, netfid);
 			}
@@ -1961,7 +1971,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct tcon_link *tlink;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	struct cifs_unix_set_info_args *args = NULL;
 	struct cifsFileInfo *open_file;
 
@@ -2247,7 +2257,7 @@ cifs_setattr(struct dentry *direntry, struct iattr *attrs)
 {
 	struct inode *inode = direntry->d_inode;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
-	struct cifsTconInfo *pTcon = cifs_sb_master_tcon(cifs_sb);
+	struct cifs_tcon *pTcon = cifs_sb_master_tcon(cifs_sb);
 
 	if (pTcon->unix_ext)
 		return cifs_setattr_unix(direntry, attrs);
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 0c98672d0122..4221b5e48a42 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -38,7 +38,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 	struct cifs_sb_info *cifs_sb;
 #ifdef CONFIG_CIFS_POSIX
 	struct cifsFileInfo *pSMBFile = filep->private_data;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 	__u64	ExtAttrBits = 0;
 	__u64	ExtAttrMask = 0;
 	__u64   caps;
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index ce417a9764a3..556b1a0b54de 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -175,7 +175,7 @@ CIFSFormatMFSymlink(u8 *buf, unsigned int buf_len, const char *link_str)
 }
 
 static int
-CIFSCreateMFSymLink(const int xid, struct cifsTconInfo *tcon,
+CIFSCreateMFSymLink(const int xid, struct cifs_tcon *tcon,
 		    const char *fromName, const char *toName,
 		    const struct nls_table *nls_codepage, int remap)
 {
@@ -184,6 +184,7 @@ CIFSCreateMFSymLink(const int xid, struct cifsTconInfo *tcon,
 	__u16 netfid = 0;
 	u8 *buf;
 	unsigned int bytes_written = 0;
+	struct cifs_io_parms io_parms;
 
 	buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL);
 	if (!buf)
@@ -203,10 +204,13 @@ CIFSCreateMFSymLink(const int xid, struct cifsTconInfo *tcon,
 		return rc;
 	}
 
-	rc = CIFSSMBWrite(xid, tcon, netfid,
-			  CIFS_MF_SYMLINK_FILE_SIZE /* length */,
-			  0 /* offset */,
-			  &bytes_written, buf, NULL, 0);
+	io_parms.netfid = netfid;
+	io_parms.pid = current->tgid;
+	io_parms.tcon = tcon;
+	io_parms.offset = 0;
+	io_parms.length = CIFS_MF_SYMLINK_FILE_SIZE;
+
+	rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, buf, NULL, 0);
 	CIFSSMBClose(xid, tcon, netfid);
 	kfree(buf);
 	if (rc != 0)
@@ -219,7 +223,7 @@ CIFSCreateMFSymLink(const int xid, struct cifsTconInfo *tcon,
 }
 
 static int
-CIFSQueryMFSymLink(const int xid, struct cifsTconInfo *tcon,
+CIFSQueryMFSymLink(const int xid, struct cifs_tcon *tcon,
 		   const unsigned char *searchName, char **symlinkinfo,
 		   const struct nls_table *nls_codepage, int remap)
 {
@@ -231,6 +235,7 @@ CIFSQueryMFSymLink(const int xid, struct cifsTconInfo *tcon,
 	unsigned int bytes_read = 0;
 	int buf_type = CIFS_NO_BUFFER;
 	unsigned int link_len = 0;
+	struct cifs_io_parms io_parms;
 	FILE_ALL_INFO file_info;
 
 	rc = CIFSSMBOpen(xid, tcon, searchName, FILE_OPEN, GENERIC_READ,
@@ -249,11 +254,13 @@ CIFSQueryMFSymLink(const int xid, struct cifsTconInfo *tcon,
 	if (!buf)
 		return -ENOMEM;
 	pbuf = buf;
+	io_parms.netfid = netfid;
+	io_parms.pid = current->tgid;
+	io_parms.tcon = tcon;
+	io_parms.offset = 0;
+	io_parms.length = CIFS_MF_SYMLINK_FILE_SIZE;
 
-	rc = CIFSSMBRead(xid, tcon, netfid,
-			 CIFS_MF_SYMLINK_FILE_SIZE /* length */,
-			 0 /* offset */,
-			 &bytes_read, &pbuf, &buf_type);
+	rc = CIFSSMBRead(xid, &io_parms, &bytes_read, &pbuf, &buf_type);
 	CIFSSMBClose(xid, tcon, netfid);
 	if (rc != 0) {
 		kfree(buf);
@@ -291,7 +298,8 @@ CIFSCheckMFSymlink(struct cifs_fattr *fattr,
 	int oplock = 0;
 	__u16 netfid = 0;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
+	struct cifs_io_parms io_parms;
 	u8 *buf;
 	char *pbuf;
 	unsigned int bytes_read = 0;
@@ -328,11 +336,13 @@ CIFSCheckMFSymlink(struct cifs_fattr *fattr,
 		goto out;
 	}
 	pbuf = buf;
+	io_parms.netfid = netfid;
+	io_parms.pid = current->tgid;
+	io_parms.tcon = pTcon;
+	io_parms.offset = 0;
+	io_parms.length = CIFS_MF_SYMLINK_FILE_SIZE;
 
-	rc = CIFSSMBRead(xid, pTcon, netfid,
-			 CIFS_MF_SYMLINK_FILE_SIZE /* length */,
-			 0 /* offset */,
-			 &bytes_read, &pbuf, &buf_type);
+	rc = CIFSSMBRead(xid, &io_parms, &bytes_read, &pbuf, &buf_type);
 	CIFSSMBClose(xid, pTcon, netfid);
 	if (rc != 0) {
 		kfree(buf);
@@ -370,7 +380,7 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
 	char *toName = NULL;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct tcon_link *tlink;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	struct cifsInodeInfo *cifsInode;
 
 	tlink = cifs_sb_tlink(cifs_sb);
@@ -445,7 +455,7 @@ cifs_follow_link(struct dentry *direntry, struct nameidata *nd)
 	char *target_path = NULL;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct tcon_link *tlink = NULL;
-	struct cifsTconInfo *tcon;
+	struct cifs_tcon *tcon;
 
 	xid = GetXid();
 
@@ -518,7 +528,7 @@ cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname)
 	int xid;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct tcon_link *tlink;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	char *full_path = NULL;
 	struct inode *newinode = NULL;
 
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 907531ac5888..03a1f491d39b 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -67,12 +67,12 @@ _FreeXid(unsigned int xid)
 	spin_unlock(&GlobalMid_Lock);
 }
 
-struct cifsSesInfo *
+struct cifs_ses *
 sesInfoAlloc(void)
 {
-	struct cifsSesInfo *ret_buf;
+	struct cifs_ses *ret_buf;
 
-	ret_buf = kzalloc(sizeof(struct cifsSesInfo), GFP_KERNEL);
+	ret_buf = kzalloc(sizeof(struct cifs_ses), GFP_KERNEL);
 	if (ret_buf) {
 		atomic_inc(&sesInfoAllocCount);
 		ret_buf->status = CifsNew;
@@ -85,7 +85,7 @@ sesInfoAlloc(void)
 }
 
 void
-sesInfoFree(struct cifsSesInfo *buf_to_free)
+sesInfoFree(struct cifs_ses *buf_to_free)
 {
 	if (buf_to_free == NULL) {
 		cFYI(1, "Null buffer passed to sesInfoFree");
@@ -105,11 +105,11 @@ sesInfoFree(struct cifsSesInfo *buf_to_free)
 	kfree(buf_to_free);
 }
 
-struct cifsTconInfo *
+struct cifs_tcon *
 tconInfoAlloc(void)
 {
-	struct cifsTconInfo *ret_buf;
-	ret_buf = kzalloc(sizeof(struct cifsTconInfo), GFP_KERNEL);
+	struct cifs_tcon *ret_buf;
+	ret_buf = kzalloc(sizeof(struct cifs_tcon), GFP_KERNEL);
 	if (ret_buf) {
 		atomic_inc(&tconInfoAllocCount);
 		ret_buf->tidStatus = CifsNew;
@@ -124,7 +124,7 @@ tconInfoAlloc(void)
 }
 
 void
-tconInfoFree(struct cifsTconInfo *buf_to_free)
+tconInfoFree(struct cifs_tcon *buf_to_free)
 {
 	if (buf_to_free == NULL) {
 		cFYI(1, "Null buffer passed to tconInfoFree");
@@ -295,11 +295,11 @@ __u16 GetNextMid(struct TCP_Server_Info *server)
    case it is responsbility of caller to set the mid */
 void
 header_assemble(struct smb_hdr *buffer, char smb_command /* command */ ,
-		const struct cifsTconInfo *treeCon, int word_count
+		const struct cifs_tcon *treeCon, int word_count
 		/* length of fixed section (word count) in two byte units  */)
 {
 	struct list_head *temp_item;
-	struct cifsSesInfo *ses;
+	struct cifs_ses *ses;
 	char *temp = (char *) buffer;
 
 	memset(temp, 0, 256); /* bigger than MAX_CIFS_HDR_SIZE */
@@ -359,7 +359,7 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ ,
 						 "did not match tcon uid");
 					spin_lock(&cifs_tcp_ses_lock);
 					list_for_each(temp_item, &treeCon->ses->server->smb_ses_list) {
-						ses = list_entry(temp_item, struct cifsSesInfo, smb_ses_list);
+						ses = list_entry(temp_item, struct cifs_ses, smb_ses_list);
 						if (ses->linux_uid == current_fsuid()) {
 							if (ses->server == treeCon->ses->server) {
 								cFYI(1, "found matching uid substitute right smb_uid");
@@ -380,7 +380,7 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ ,
 		if (treeCon->nocase)
 			buffer->Flags  |= SMBFLG_CASELESS;
 		if ((treeCon->ses) && (treeCon->ses->server))
-			if (treeCon->ses->server->secMode &
+			if (treeCon->ses->server->sec_mode &
 			  (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
 				buffer->Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
 	}
@@ -507,8 +507,8 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv)
 {
 	struct smb_com_lock_req *pSMB = (struct smb_com_lock_req *)buf;
 	struct list_head *tmp, *tmp1, *tmp2;
-	struct cifsSesInfo *ses;
-	struct cifsTconInfo *tcon;
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
 	struct cifsInodeInfo *pCifsInode;
 	struct cifsFileInfo *netfile;
 
@@ -566,9 +566,9 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv)
 	/* look up tcon based on tid & uid */
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each(tmp, &srv->smb_ses_list) {
-		ses = list_entry(tmp, struct cifsSesInfo, smb_ses_list);
+		ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
 		list_for_each(tmp1, &ses->tcon_list) {
-			tcon = list_entry(tmp1, struct cifsTconInfo, tcon_list);
+			tcon = list_entry(tmp1, struct cifs_tcon, tcon_list);
 			if (tcon->tid != buf->Tid)
 				continue;
 
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index 79b71c2c7c9d..73e47e84b61a 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -836,7 +836,7 @@ ntstatus_to_dos(__u32 ntstatus, __u8 *eclass, __u16 *ecode)
 }
 
 int
-map_smb_to_linux_error(struct smb_hdr *smb, int logErr)
+map_smb_to_linux_error(struct smb_hdr *smb, bool logErr)
 {
 	unsigned int i;
 	int rc = -EIO;	/* if transport error smb error may not be set */
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index f8e4cd2a7912..6751e745bbc6 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -195,7 +195,7 @@ int get_symlink_reparse_path(char *full_path, struct cifs_sb_info *cifs_sb,
 	int len;
 	int oplock = 0;
 	int rc;
-	struct cifsTconInfo *ptcon = cifs_sb_tcon(cifs_sb);
+	struct cifs_tcon *ptcon = cifs_sb_tcon(cifs_sb);
 	char *tmpbuffer;
 
 	rc = CIFSSMBOpen(xid, ptcon, full_path, FILE_OPEN, GENERIC_READ,
@@ -223,7 +223,7 @@ static int initiate_cifs_search(const int xid, struct file *file)
 	struct cifsFileInfo *cifsFile;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
 	struct tcon_link *tlink = NULL;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 
 	if (file->private_data == NULL) {
 		tlink = cifs_sb_tlink(cifs_sb);
@@ -496,7 +496,7 @@ static int cifs_save_resume_key(const char *current_entry,
    assume that they are located in the findfirst return buffer.*/
 /* We start counting in the buffer with entry 2 and increment for every
    entry (do not increment for . or .. entry) */
-static int find_cifs_entry(const int xid, struct cifsTconInfo *pTcon,
+static int find_cifs_entry(const int xid, struct cifs_tcon *pTcon,
 	struct file *file, char **ppCurrentEntry, int *num_to_ret)
 {
 	int rc = 0;
@@ -764,7 +764,7 @@ int cifs_readdir(struct file *file, void *direntry, filldir_t filldir)
 {
 	int rc = 0;
 	int xid, i;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	struct cifsFileInfo *cifsFile = NULL;
 	char *current_entry;
 	int num_to_fill = 0;
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 7dd462100378..3892ab817a36 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -37,13 +37,13 @@
  * the socket has been reestablished (so we know whether to use vc 0).
  * Called while holding the cifs_tcp_ses_lock, so do not block
  */
-static bool is_first_ses_reconnect(struct cifsSesInfo *ses)
+static bool is_first_ses_reconnect(struct cifs_ses *ses)
 {
 	struct list_head *tmp;
-	struct cifsSesInfo *tmp_ses;
+	struct cifs_ses *tmp_ses;
 
 	list_for_each(tmp, &ses->server->smb_ses_list) {
-		tmp_ses = list_entry(tmp, struct cifsSesInfo,
+		tmp_ses = list_entry(tmp, struct cifs_ses,
 				     smb_ses_list);
 		if (tmp_ses->need_reconnect == false)
 			return false;
@@ -61,11 +61,11 @@ static bool is_first_ses_reconnect(struct cifsSesInfo *ses)
  *	any vc but zero (some servers reset the connection on vcnum zero)
  *
  */
-static __le16 get_next_vcnum(struct cifsSesInfo *ses)
+static __le16 get_next_vcnum(struct cifs_ses *ses)
 {
 	__u16 vcnum = 0;
 	struct list_head *tmp;
-	struct cifsSesInfo *tmp_ses;
+	struct cifs_ses *tmp_ses;
 	__u16 max_vcs = ses->server->max_vcs;
 	__u16 i;
 	int free_vc_found = 0;
@@ -87,7 +87,7 @@ static __le16 get_next_vcnum(struct cifsSesInfo *ses)
 		free_vc_found = 1;
 
 		list_for_each(tmp, &ses->server->smb_ses_list) {
-			tmp_ses = list_entry(tmp, struct cifsSesInfo,
+			tmp_ses = list_entry(tmp, struct cifs_ses,
 					     smb_ses_list);
 			if (tmp_ses->vcnum == i) {
 				free_vc_found = 0;
@@ -114,7 +114,7 @@ get_vc_num_exit:
 	return cpu_to_le16(vcnum);
 }
 
-static __u32 cifs_ssetup_hdr(struct cifsSesInfo *ses, SESSION_SETUP_ANDX *pSMB)
+static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB)
 {
 	__u32 capabilities = 0;
 
@@ -136,7 +136,7 @@ static __u32 cifs_ssetup_hdr(struct cifsSesInfo *ses, SESSION_SETUP_ANDX *pSMB)
 	capabilities = CAP_LARGE_FILES | CAP_NT_SMBS | CAP_LEVEL_II_OPLOCKS |
 			CAP_LARGE_WRITE_X | CAP_LARGE_READ_X;
 
-	if (ses->server->secMode &
+	if (ses->server->sec_mode &
 	    (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
 		pSMB->req.hdr.Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
 
@@ -181,7 +181,7 @@ unicode_oslm_strings(char **pbcc_area, const struct nls_table *nls_cp)
 	*pbcc_area = bcc_ptr;
 }
 
-static void unicode_domain_string(char **pbcc_area, struct cifsSesInfo *ses,
+static void unicode_domain_string(char **pbcc_area, struct cifs_ses *ses,
 				   const struct nls_table *nls_cp)
 {
 	char *bcc_ptr = *pbcc_area;
@@ -204,7 +204,7 @@ static void unicode_domain_string(char **pbcc_area, struct cifsSesInfo *ses,
 }
 
 
-static void unicode_ssetup_strings(char **pbcc_area, struct cifsSesInfo *ses,
+static void unicode_ssetup_strings(char **pbcc_area, struct cifs_ses *ses,
 				   const struct nls_table *nls_cp)
 {
 	char *bcc_ptr = *pbcc_area;
@@ -236,7 +236,7 @@ static void unicode_ssetup_strings(char **pbcc_area, struct cifsSesInfo *ses,
 	*pbcc_area = bcc_ptr;
 }
 
-static void ascii_ssetup_strings(char **pbcc_area, struct cifsSesInfo *ses,
+static void ascii_ssetup_strings(char **pbcc_area, struct cifs_ses *ses,
 				 const struct nls_table *nls_cp)
 {
 	char *bcc_ptr = *pbcc_area;
@@ -276,7 +276,7 @@ static void ascii_ssetup_strings(char **pbcc_area, struct cifsSesInfo *ses,
 }
 
 static void
-decode_unicode_ssetup(char **pbcc_area, int bleft, struct cifsSesInfo *ses,
+decode_unicode_ssetup(char **pbcc_area, int bleft, struct cifs_ses *ses,
 		      const struct nls_table *nls_cp)
 {
 	int len;
@@ -310,7 +310,7 @@ decode_unicode_ssetup(char **pbcc_area, int bleft, struct cifsSesInfo *ses,
 }
 
 static int decode_ascii_ssetup(char **pbcc_area, __u16 bleft,
-			       struct cifsSesInfo *ses,
+			       struct cifs_ses *ses,
 			       const struct nls_table *nls_cp)
 {
 	int rc = 0;
@@ -364,7 +364,7 @@ static int decode_ascii_ssetup(char **pbcc_area, __u16 bleft,
 }
 
 static int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len,
-				    struct cifsSesInfo *ses)
+				    struct cifs_ses *ses)
 {
 	unsigned int tioffset; /* challenge message target info area */
 	unsigned int tilen; /* challenge message target info area length  */
@@ -411,7 +411,7 @@ static int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len,
 /* We do not malloc the blob, it is passed in pbuffer, because
    it is fixed size, and small, making this approach cleaner */
 static void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
-					 struct cifsSesInfo *ses)
+					 struct cifs_ses *ses)
 {
 	NEGOTIATE_MESSAGE *sec_blob = (NEGOTIATE_MESSAGE *)pbuffer;
 	__u32 flags;
@@ -424,7 +424,7 @@ static void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
 	flags = NTLMSSP_NEGOTIATE_56 |	NTLMSSP_REQUEST_TARGET |
 		NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE |
 		NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC;
-	if (ses->server->secMode &
+	if (ses->server->sec_mode &
 			(SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) {
 		flags |= NTLMSSP_NEGOTIATE_SIGN;
 		if (!ses->server->session_estab)
@@ -449,7 +449,7 @@ static void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
    This function returns the length of the data in the blob */
 static int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 					u16 *buflen,
-				   struct cifsSesInfo *ses,
+				   struct cifs_ses *ses,
 				   const struct nls_table *nls_cp)
 {
 	int rc;
@@ -464,10 +464,10 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 		NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_TARGET_INFO |
 		NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE |
 		NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC;
-	if (ses->server->secMode &
+	if (ses->server->sec_mode &
 	   (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
 		flags |= NTLMSSP_NEGOTIATE_SIGN;
-	if (ses->server->secMode & SECMODE_SIGN_REQUIRED)
+	if (ses->server->sec_mode & SECMODE_SIGN_REQUIRED)
 		flags |= NTLMSSP_NEGOTIATE_ALWAYS_SIGN;
 
 	tmp = pbuffer + sizeof(AUTHENTICATE_MESSAGE);
@@ -551,7 +551,7 @@ setup_ntlmv2_ret:
 }
 
 int
-CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses,
+CIFS_SessSetup(unsigned int xid, struct cifs_ses *ses,
 	       const struct nls_table *nls_cp)
 {
 	int rc = 0;
@@ -657,7 +657,7 @@ ssetup_ntlmssp_authenticate:
 		 */
 
 		rc = calc_lanman_hash(ses->password, ses->server->cryptkey,
-				 ses->server->secMode & SECMODE_PW_ENCRYPT ?
+				 ses->server->sec_mode & SECMODE_PW_ENCRYPT ?
 					true : false, lnm_session_key);
 
 		ses->flags |= CIFS_SES_LANMAN;
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index 1525d5e662b6..1c5b770c3141 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -90,12 +90,10 @@ smbhash(unsigned char *out, const unsigned char *in, unsigned char *key)
 	sg_init_one(&sgout, out, 8);
 
 	rc = crypto_blkcipher_encrypt(&desc, &sgout, &sgin, 8);
-	if (rc) {
+	if (rc)
 		cERROR(1, "could not encrypt crypt key rc: %d\n", rc);
-		crypto_free_blkcipher(tfm_des);
-		goto smbhash_err;
-	}
 
+	crypto_free_blkcipher(tfm_des);
 smbhash_err:
 	return rc;
 }
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index f2513fb8c391..147aa22c3c3a 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -295,7 +295,7 @@ static int wait_for_free_request(struct TCP_Server_Info *server,
 	return 0;
 }
 
-static int allocate_mid(struct cifsSesInfo *ses, struct smb_hdr *in_buf,
+static int allocate_mid(struct cifs_ses *ses, struct smb_hdr *in_buf,
 			struct mid_q_entry **ppmidQ)
 {
 	if (ses->server->tcpStatus == CifsExiting) {
@@ -342,22 +342,24 @@ wait_for_response(struct TCP_Server_Info *server, struct mid_q_entry *midQ)
  * the result. Caller is responsible for dealing with timeouts.
  */
 int
-cifs_call_async(struct TCP_Server_Info *server, struct smb_hdr *in_buf,
-		mid_callback_t *callback, void *cbdata)
+cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov,
+		unsigned int nvec, mid_callback_t *callback, void *cbdata,
+		bool ignore_pend)
 {
 	int rc;
 	struct mid_q_entry *mid;
+	struct smb_hdr *hdr = (struct smb_hdr *)iov[0].iov_base;
 
-	rc = wait_for_free_request(server, CIFS_ASYNC_OP);
+	rc = wait_for_free_request(server, ignore_pend ? CIFS_ASYNC_OP : 0);
 	if (rc)
 		return rc;
 
 	/* enable signing if server requires it */
-	if (server->secMode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
-		in_buf->Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
+	if (server->sec_mode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
+		hdr->Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
 
 	mutex_lock(&server->srv_mutex);
-	mid = AllocMidQEntry(in_buf, server);
+	mid = AllocMidQEntry(hdr, server);
 	if (mid == NULL) {
 		mutex_unlock(&server->srv_mutex);
 		return -ENOMEM;
@@ -368,7 +370,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_hdr *in_buf,
 	list_add_tail(&mid->qhead, &server->pending_mid_q);
 	spin_unlock(&GlobalMid_Lock);
 
-	rc = cifs_sign_smb(in_buf, server, &mid->sequence_number);
+	rc = cifs_sign_smb2(iov, nvec, server, &mid->sequence_number);
 	if (rc) {
 		mutex_unlock(&server->srv_mutex);
 		goto out_err;
@@ -380,7 +382,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_hdr *in_buf,
 #ifdef CONFIG_CIFS_STATS2
 	atomic_inc(&server->inSend);
 #endif
-	rc = smb_send(server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
+	rc = smb_sendv(server, iov, nvec);
 #ifdef CONFIG_CIFS_STATS2
 	atomic_dec(&server->inSend);
 	mid->when_sent = jiffies;
@@ -407,7 +409,7 @@ out_err:
  *
  */
 int
-SendReceiveNoRsp(const unsigned int xid, struct cifsSesInfo *ses,
+SendReceiveNoRsp(const unsigned int xid, struct cifs_ses *ses,
 		struct smb_hdr *in_buf, int flags)
 {
 	int rc;
@@ -424,7 +426,7 @@ SendReceiveNoRsp(const unsigned int xid, struct cifsSesInfo *ses,
 }
 
 static int
-sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
+cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
 {
 	int rc = 0;
 
@@ -432,28 +434,21 @@ sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
 		mid->mid, mid->midState);
 
 	spin_lock(&GlobalMid_Lock);
-	/* ensure that it's no longer on the pending_mid_q */
-	list_del_init(&mid->qhead);
-
 	switch (mid->midState) {
 	case MID_RESPONSE_RECEIVED:
 		spin_unlock(&GlobalMid_Lock);
 		return rc;
-	case MID_REQUEST_SUBMITTED:
-		/* socket is going down, reject all calls */
-		if (server->tcpStatus == CifsExiting) {
-			cERROR(1, "%s: canceling mid=%d cmd=0x%x state=%d",
-			       __func__, mid->mid, mid->command, mid->midState);
-			rc = -EHOSTDOWN;
-			break;
-		}
 	case MID_RETRY_NEEDED:
 		rc = -EAGAIN;
 		break;
 	case MID_RESPONSE_MALFORMED:
 		rc = -EIO;
 		break;
+	case MID_SHUTDOWN:
+		rc = -EHOSTDOWN;
+		break;
 	default:
+		list_del_init(&mid->qhead);
 		cERROR(1, "%s: invalid mid state mid=%d state=%d", __func__,
 			mid->mid, mid->midState);
 		rc = -EIO;
@@ -502,13 +497,31 @@ send_nt_cancel(struct TCP_Server_Info *server, struct smb_hdr *in_buf,
 }
 
 int
-SendReceive2(const unsigned int xid, struct cifsSesInfo *ses,
+cifs_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server,
+		   bool log_error)
+{
+	dump_smb(mid->resp_buf,
+		 min_t(u32, 92, be32_to_cpu(mid->resp_buf->smb_buf_length)));
+
+	/* convert the length into a more usable form */
+	if (server->sec_mode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) {
+		/* FIXME: add code to kill session */
+		if (cifs_verify_signature(mid->resp_buf, server,
+					  mid->sequence_number + 1) != 0)
+			cERROR(1, "Unexpected SMB signature");
+	}
+
+	/* BB special case reconnect tid and uid here? */
+	return map_smb_to_linux_error(mid->resp_buf, log_error);
+}
+
+int
+SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	     struct kvec *iov, int n_vec, int *pRespBufType /* ret */,
 	     const int flags)
 {
 	int rc = 0;
 	int long_op;
-	unsigned int receive_len;
 	struct mid_q_entry *midQ;
 	struct smb_hdr *in_buf = iov[0].iov_base;
 
@@ -598,61 +611,31 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses,
 
 	cifs_small_buf_release(in_buf);
 
-	rc = sync_mid_result(midQ, ses->server);
+	rc = cifs_sync_mid_result(midQ, ses->server);
 	if (rc != 0) {
 		atomic_dec(&ses->server->inFlight);
 		wake_up(&ses->server->request_q);
 		return rc;
 	}
 
-	receive_len = be32_to_cpu(midQ->resp_buf->smb_buf_length);
-
-	if (receive_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) {
-		cERROR(1, "Frame too large received.  Length: %d  Xid: %d",
-			receive_len, xid);
+	if (!midQ->resp_buf || midQ->midState != MID_RESPONSE_RECEIVED) {
 		rc = -EIO;
+		cFYI(1, "Bad MID state?");
 		goto out;
 	}
 
-	/* rcvd frame is ok */
-
-	if (midQ->resp_buf &&
-	    (midQ->midState == MID_RESPONSE_RECEIVED)) {
-
-		iov[0].iov_base = (char *)midQ->resp_buf;
-		if (midQ->largeBuf)
-			*pRespBufType = CIFS_LARGE_BUFFER;
-		else
-			*pRespBufType = CIFS_SMALL_BUFFER;
-		iov[0].iov_len = receive_len + 4;
-
-		dump_smb(midQ->resp_buf, 80);
-		/* convert the length into a more usable form */
-		if ((receive_len > 24) &&
-		    (ses->server->secMode & (SECMODE_SIGN_REQUIRED |
-					     SECMODE_SIGN_ENABLED))) {
-			rc = cifs_verify_signature(midQ->resp_buf,
-						ses->server,
-						midQ->sequence_number+1);
-			if (rc) {
-				cERROR(1, "Unexpected SMB signature");
-				/* BB FIXME add code to kill session */
-			}
-		}
-
-		/* BB special case reconnect tid and uid here? */
-		rc = map_smb_to_linux_error(midQ->resp_buf,
-					    flags & CIFS_LOG_ERROR);
+	iov[0].iov_base = (char *)midQ->resp_buf;
+	iov[0].iov_len = be32_to_cpu(midQ->resp_buf->smb_buf_length) + 4;
+	if (midQ->largeBuf)
+		*pRespBufType = CIFS_LARGE_BUFFER;
+	else
+		*pRespBufType = CIFS_SMALL_BUFFER;
 
-		if ((flags & CIFS_NO_RESP) == 0)
-			midQ->resp_buf = NULL;  /* mark it so buf will
-						   not be freed by
-						   delete_mid */
-	} else {
-		rc = -EIO;
-		cFYI(1, "Bad MID state?");
-	}
+	rc = cifs_check_receive(midQ, ses->server, flags & CIFS_LOG_ERROR);
 
+	/* mark it so buf will not be freed by delete_mid */
+	if ((flags & CIFS_NO_RESP) == 0)
+		midQ->resp_buf = NULL;
 out:
 	delete_mid(midQ);
 	atomic_dec(&ses->server->inFlight);
@@ -662,12 +645,11 @@ out:
 }
 
 int
-SendReceive(const unsigned int xid, struct cifsSesInfo *ses,
+SendReceive(const unsigned int xid, struct cifs_ses *ses,
 	    struct smb_hdr *in_buf, struct smb_hdr *out_buf,
 	    int *pbytes_returned, const int long_op)
 {
 	int rc = 0;
-	unsigned int receive_len;
 	struct mid_q_entry *midQ;
 
 	if (ses == NULL) {
@@ -750,54 +732,23 @@ SendReceive(const unsigned int xid, struct cifsSesInfo *ses,
 		spin_unlock(&GlobalMid_Lock);
 	}
 
-	rc = sync_mid_result(midQ, ses->server);
+	rc = cifs_sync_mid_result(midQ, ses->server);
 	if (rc != 0) {
 		atomic_dec(&ses->server->inFlight);
 		wake_up(&ses->server->request_q);
 		return rc;
 	}
 
-	receive_len = be32_to_cpu(midQ->resp_buf->smb_buf_length);
-
-	if (receive_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) {
-		cERROR(1, "Frame too large received.  Length: %d  Xid: %d",
-			receive_len, xid);
-		rc = -EIO;
-		goto out;
-	}
-
-	/* rcvd frame is ok */
-
-	if (midQ->resp_buf && out_buf
-	    && (midQ->midState == MID_RESPONSE_RECEIVED)) {
-		out_buf->smb_buf_length = cpu_to_be32(receive_len);
-		memcpy((char *)out_buf + 4,
-		       (char *)midQ->resp_buf + 4,
-		       receive_len);
-
-		dump_smb(out_buf, 92);
-		/* convert the length into a more usable form */
-		if ((receive_len > 24) &&
-		    (ses->server->secMode & (SECMODE_SIGN_REQUIRED |
-					     SECMODE_SIGN_ENABLED))) {
-			rc = cifs_verify_signature(out_buf,
-						ses->server,
-						midQ->sequence_number+1);
-			if (rc) {
-				cERROR(1, "Unexpected SMB signature");
-				/* BB FIXME add code to kill session */
-			}
-		}
-
-		*pbytes_returned = be32_to_cpu(out_buf->smb_buf_length);
-
-		/* BB special case reconnect tid and uid here? */
-		rc = map_smb_to_linux_error(out_buf, 0 /* no log */ );
-	} else {
+	if (!midQ->resp_buf || !out_buf ||
+	    midQ->midState != MID_RESPONSE_RECEIVED) {
 		rc = -EIO;
 		cERROR(1, "Bad MID state?");
+		goto out;
 	}
 
+	*pbytes_returned = be32_to_cpu(midQ->resp_buf->smb_buf_length);
+	memcpy(out_buf, midQ->resp_buf, *pbytes_returned + 4);
+	rc = cifs_check_receive(midQ, ses->server, 0);
 out:
 	delete_mid(midQ);
 	atomic_dec(&ses->server->inFlight);
@@ -810,12 +761,12 @@ out:
    blocking lock to return. */
 
 static int
-send_lock_cancel(const unsigned int xid, struct cifsTconInfo *tcon,
+send_lock_cancel(const unsigned int xid, struct cifs_tcon *tcon,
 			struct smb_hdr *in_buf,
 			struct smb_hdr *out_buf)
 {
 	int bytes_returned;
-	struct cifsSesInfo *ses = tcon->ses;
+	struct cifs_ses *ses = tcon->ses;
 	LOCK_REQ *pSMB = (LOCK_REQ *)in_buf;
 
 	/* We just modify the current in_buf to change
@@ -832,15 +783,14 @@ send_lock_cancel(const unsigned int xid, struct cifsTconInfo *tcon,
 }
 
 int
-SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon,
+SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 	    struct smb_hdr *in_buf, struct smb_hdr *out_buf,
 	    int *pbytes_returned)
 {
 	int rc = 0;
 	int rstart = 0;
-	unsigned int receive_len;
 	struct mid_q_entry *midQ;
-	struct cifsSesInfo *ses;
+	struct cifs_ses *ses;
 
 	if (tcon == NULL || tcon->ses == NULL) {
 		cERROR(1, "Null smb session");
@@ -957,50 +907,20 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon,
 		rstart = 1;
 	}
 
-	rc = sync_mid_result(midQ, ses->server);
+	rc = cifs_sync_mid_result(midQ, ses->server);
 	if (rc != 0)
 		return rc;
 
-	receive_len = be32_to_cpu(midQ->resp_buf->smb_buf_length);
-	if (receive_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) {
-		cERROR(1, "Frame too large received.  Length: %d  Xid: %d",
-			receive_len, xid);
-		rc = -EIO;
-		goto out;
-	}
-
 	/* rcvd frame is ok */
-
-	if ((out_buf == NULL) || (midQ->midState != MID_RESPONSE_RECEIVED)) {
+	if (out_buf == NULL || midQ->midState != MID_RESPONSE_RECEIVED) {
 		rc = -EIO;
 		cERROR(1, "Bad MID state?");
 		goto out;
 	}
 
-	out_buf->smb_buf_length = cpu_to_be32(receive_len);
-	memcpy((char *)out_buf + 4,
-	       (char *)midQ->resp_buf + 4,
-	       receive_len);
-
-	dump_smb(out_buf, 92);
-	/* convert the length into a more usable form */
-	if ((receive_len > 24) &&
-	    (ses->server->secMode & (SECMODE_SIGN_REQUIRED |
-				     SECMODE_SIGN_ENABLED))) {
-		rc = cifs_verify_signature(out_buf,
-					   ses->server,
-					   midQ->sequence_number+1);
-		if (rc) {
-			cERROR(1, "Unexpected SMB signature");
-			/* BB FIXME add code to kill session */
-		}
-	}
-
-	*pbytes_returned = be32_to_cpu(out_buf->smb_buf_length);
-
-	/* BB special case reconnect tid and uid here? */
-	rc = map_smb_to_linux_error(out_buf, 0 /* no log */ );
-
+	*pbytes_returned = be32_to_cpu(midQ->resp_buf->smb_buf_length);
+	memcpy(out_buf, midQ->resp_buf, *pbytes_returned + 4);
+	rc = cifs_check_receive(midQ, ses->server, 0);
 out:
 	delete_mid(midQ);
 	if (rstart && rc == -EACCES)
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 912995e013ec..2a22fb2989e4 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -49,7 +49,7 @@ int cifs_removexattr(struct dentry *direntry, const char *ea_name)
 	int xid;
 	struct cifs_sb_info *cifs_sb;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	struct super_block *sb;
 	char *full_path = NULL;
 
@@ -109,7 +109,7 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
 	int xid;
 	struct cifs_sb_info *cifs_sb;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	struct super_block *sb;
 	char *full_path;
 	struct cifs_ntsd *pacl;
@@ -240,7 +240,7 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
 	int xid;
 	struct cifs_sb_info *cifs_sb;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	struct super_block *sb;
 	char *full_path;
 
@@ -372,7 +372,7 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
 	int xid;
 	struct cifs_sb_info *cifs_sb;
 	struct tcon_link *tlink;
-	struct cifsTconInfo *pTcon;
+	struct cifs_tcon *pTcon;
 	struct super_block *sb;
 	char *full_path;
 
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index a46126fd5735..2b8dae4d121e 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -336,8 +336,6 @@ static int coda_rmdir(struct inode *dir, struct dentry *de)
 	int len = de->d_name.len;
 	int error;
 
-	dentry_unhash(de);
-
 	error = venus_rmdir(dir->i_sb, coda_i2f(dir), name, len);
 	if (!error) {
 		/* VFS may delete the child */
@@ -361,9 +359,6 @@ static int coda_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int new_length = new_dentry->d_name.len;
 	int error;
 
-	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	error = venus_rename(old_dir->i_sb, coda_i2f(old_dir),
 			     coda_i2f(new_dir), old_length, new_length,
 			     (const char *) old_name, (const char *)new_name);
diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c
index 6cbb3afb36dc..cb140ef293e4 100644
--- a/fs/coda/pioctl.c
+++ b/fs/coda/pioctl.c
@@ -43,8 +43,6 @@ const struct file_operations coda_ioctl_operations = {
 /* the coda pioctl inode ops */
 static int coda_ioctl_permission(struct inode *inode, int mask, unsigned int flags)
 {
-	if (flags & IPERM_FLAG_RCU)
-		return -ECHILD;
 	return (mask & MAY_EXEC) ? -EACCES : 0;
 }
 
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 9d17d350abc5..9a37a9b6de3a 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1359,8 +1359,6 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
 	struct module *subsys_owner = NULL, *dead_item_owner = NULL;
 	int ret;
 
-	dentry_unhash(dentry);
-
 	if (dentry->d_parent == configfs_sb->s_root)
 		return -EPERM;
 
diff --git a/fs/dcookies.c b/fs/dcookies.c
index a21cabdbd87b..dda0dc702d1b 100644
--- a/fs/dcookies.c
+++ b/fs/dcookies.c
@@ -178,6 +178,8 @@ SYSCALL_DEFINE(lookup_dcookie)(u64 cookie64, char __user * buf, size_t len)
 	/* FIXME: (deleted) ? */
 	path = d_path(&dcs->path, kbuf, PAGE_SIZE);
 
+	mutex_unlock(&dcookie_mutex);
+
 	if (IS_ERR(path)) {
 		err = PTR_ERR(path);
 		goto out_free;
@@ -194,6 +196,7 @@ SYSCALL_DEFINE(lookup_dcookie)(u64 cookie64, char __user * buf, size_t len)
 
 out_free:
 	kfree(kbuf);
+	return err;
 out:
 	mutex_unlock(&dcookie_mutex);
 	return err;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index b8d5c8091024..58609bde3b9f 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1024,25 +1024,25 @@ out:
 }
 
 /**
- * contains_ecryptfs_marker - check for the ecryptfs marker
+ * ecryptfs_validate_marker - check for the ecryptfs marker
  * @data: The data block in which to check
  *
- * Returns one if marker found; zero if not found
+ * Returns zero if marker found; -EINVAL if not found
  */
-static int contains_ecryptfs_marker(char *data)
+static int ecryptfs_validate_marker(char *data)
 {
 	u32 m_1, m_2;
 
 	m_1 = get_unaligned_be32(data);
 	m_2 = get_unaligned_be32(data + 4);
 	if ((m_1 ^ MAGIC_ECRYPTFS_MARKER) == m_2)
-		return 1;
+		return 0;
 	ecryptfs_printk(KERN_DEBUG, "m_1 = [0x%.8x]; m_2 = [0x%.8x]; "
 			"MAGIC_ECRYPTFS_MARKER = [0x%.8x]\n", m_1, m_2,
 			MAGIC_ECRYPTFS_MARKER);
 	ecryptfs_printk(KERN_DEBUG, "(m_1 ^ MAGIC_ECRYPTFS_MARKER) = "
 			"[0x%.8x]\n", (m_1 ^ MAGIC_ECRYPTFS_MARKER));
-	return 0;
+	return -EINVAL;
 }
 
 struct ecryptfs_flag_map_elem {
@@ -1201,27 +1201,19 @@ int ecryptfs_cipher_code_to_string(char *str, u8 cipher_code)
 	return rc;
 }
 
-int ecryptfs_read_and_validate_header_region(char *data,
-					     struct inode *ecryptfs_inode)
+int ecryptfs_read_and_validate_header_region(struct inode *inode)
 {
-	struct ecryptfs_crypt_stat *crypt_stat =
-		&(ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat);
+	u8 file_size[ECRYPTFS_SIZE_AND_MARKER_BYTES];
+	u8 *marker = file_size + ECRYPTFS_FILE_SIZE_BYTES;
 	int rc;
 
-	if (crypt_stat->extent_size == 0)
-		crypt_stat->extent_size = ECRYPTFS_DEFAULT_EXTENT_SIZE;
-	rc = ecryptfs_read_lower(data, 0, crypt_stat->extent_size,
-				 ecryptfs_inode);
-	if (rc < 0) {
-		printk(KERN_ERR "%s: Error reading header region; rc = [%d]\n",
-		       __func__, rc);
-		goto out;
-	}
-	if (!contains_ecryptfs_marker(data + ECRYPTFS_FILE_SIZE_BYTES)) {
-		rc = -EINVAL;
-	} else
-		rc = 0;
-out:
+	rc = ecryptfs_read_lower(file_size, 0, ECRYPTFS_SIZE_AND_MARKER_BYTES,
+				 inode);
+	if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES)
+		return rc >= 0 ? -EINVAL : rc;
+	rc = ecryptfs_validate_marker(marker);
+	if (!rc)
+		ecryptfs_i_size_init(file_size, inode);
 	return rc;
 }
 
@@ -1242,8 +1234,7 @@ ecryptfs_write_header_metadata(char *virt,
 	(*written) = 6;
 }
 
-struct kmem_cache *ecryptfs_header_cache_1;
-struct kmem_cache *ecryptfs_header_cache_2;
+struct kmem_cache *ecryptfs_header_cache;
 
 /**
  * ecryptfs_write_headers_virt
@@ -1496,11 +1487,9 @@ static int ecryptfs_read_headers_virt(char *page_virt,
 	crypt_stat->mount_crypt_stat = &ecryptfs_superblock_to_private(
 		ecryptfs_dentry->d_sb)->mount_crypt_stat;
 	offset = ECRYPTFS_FILE_SIZE_BYTES;
-	rc = contains_ecryptfs_marker(page_virt + offset);
-	if (rc == 0) {
-		rc = -EINVAL;
+	rc = ecryptfs_validate_marker(page_virt + offset);
+	if (rc)
 		goto out;
-	}
 	if (!(crypt_stat->flags & ECRYPTFS_I_SIZE_INITIALIZED))
 		ecryptfs_i_size_init(page_virt, ecryptfs_dentry->d_inode);
 	offset += MAGIC_ECRYPTFS_MARKER_SIZE_BYTES;
@@ -1567,20 +1556,21 @@ out:
 	return rc;
 }
 
-int ecryptfs_read_and_validate_xattr_region(char *page_virt,
-					    struct dentry *ecryptfs_dentry)
+int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry,
+					    struct inode *inode)
 {
+	u8 file_size[ECRYPTFS_SIZE_AND_MARKER_BYTES];
+	u8 *marker = file_size + ECRYPTFS_FILE_SIZE_BYTES;
 	int rc;
 
-	rc = ecryptfs_read_xattr_region(page_virt, ecryptfs_dentry->d_inode);
-	if (rc)
-		goto out;
-	if (!contains_ecryptfs_marker(page_virt	+ ECRYPTFS_FILE_SIZE_BYTES)) {
-		printk(KERN_WARNING "Valid data found in [%s] xattr, but "
-			"the marker is invalid\n", ECRYPTFS_XATTR_NAME);
-		rc = -EINVAL;
-	}
-out:
+	rc = ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry),
+				     ECRYPTFS_XATTR_NAME, file_size,
+				     ECRYPTFS_SIZE_AND_MARKER_BYTES);
+	if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES)
+		return rc >= 0 ? -EINVAL : rc;
+	rc = ecryptfs_validate_marker(marker);
+	if (!rc)
+		ecryptfs_i_size_init(file_size, inode);
 	return rc;
 }
 
@@ -1610,7 +1600,7 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
 	ecryptfs_copy_mount_wide_flags_to_inode_flags(crypt_stat,
 						      mount_crypt_stat);
 	/* Read the first page from the underlying file */
-	page_virt = kmem_cache_alloc(ecryptfs_header_cache_1, GFP_USER);
+	page_virt = kmem_cache_alloc(ecryptfs_header_cache, GFP_USER);
 	if (!page_virt) {
 		rc = -ENOMEM;
 		printk(KERN_ERR "%s: Unable to allocate page_virt\n",
@@ -1655,7 +1645,7 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
 out:
 	if (page_virt) {
 		memset(page_virt, 0, PAGE_CACHE_SIZE);
-		kmem_cache_free(ecryptfs_header_cache_1, page_virt);
+		kmem_cache_free(ecryptfs_header_cache, page_virt);
 	}
 	return rc;
 }
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index e70282775e2c..43c7c43b06f5 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -200,6 +200,8 @@ ecryptfs_get_key_payload_data(struct key *key)
 #define MAGIC_ECRYPTFS_MARKER 0x3c81b7f5
 #define MAGIC_ECRYPTFS_MARKER_SIZE_BYTES 8	/* 4*2 */
 #define ECRYPTFS_FILE_SIZE_BYTES (sizeof(u64))
+#define ECRYPTFS_SIZE_AND_MARKER_BYTES (ECRYPTFS_FILE_SIZE_BYTES \
+					+ MAGIC_ECRYPTFS_MARKER_SIZE_BYTES)
 #define ECRYPTFS_DEFAULT_CIPHER "aes"
 #define ECRYPTFS_DEFAULT_KEY_BYTES 16
 #define ECRYPTFS_DEFAULT_HASH "md5"
@@ -603,8 +605,7 @@ extern struct kmem_cache *ecryptfs_file_info_cache;
 extern struct kmem_cache *ecryptfs_dentry_info_cache;
 extern struct kmem_cache *ecryptfs_inode_info_cache;
 extern struct kmem_cache *ecryptfs_sb_info_cache;
-extern struct kmem_cache *ecryptfs_header_cache_1;
-extern struct kmem_cache *ecryptfs_header_cache_2;
+extern struct kmem_cache *ecryptfs_header_cache;
 extern struct kmem_cache *ecryptfs_xattr_cache;
 extern struct kmem_cache *ecryptfs_key_record_cache;
 extern struct kmem_cache *ecryptfs_key_sig_cache;
@@ -625,14 +626,9 @@ struct ecryptfs_open_req {
 	struct list_head kthread_ctl_list;
 };
 
-#define ECRYPTFS_INTERPOSE_FLAG_D_ADD                 0x00000001
-int ecryptfs_interpose(struct dentry *hidden_dentry,
-		       struct dentry *this_dentry, struct super_block *sb,
-		       u32 flags);
+struct inode *ecryptfs_get_inode(struct inode *lower_inode,
+				 struct super_block *sb);
 void ecryptfs_i_size_init(const char *page_virt, struct inode *inode);
-int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
-					struct dentry *lower_dentry,
-					struct inode *ecryptfs_dir_inode);
 int ecryptfs_decode_and_decrypt_filename(char **decrypted_name,
 					 size_t *decrypted_name_size,
 					 struct dentry *ecryptfs_dentry,
@@ -664,10 +660,9 @@ int ecryptfs_new_file_context(struct dentry *ecryptfs_dentry);
 void ecryptfs_write_crypt_stat_flags(char *page_virt,
 				     struct ecryptfs_crypt_stat *crypt_stat,
 				     size_t *written);
-int ecryptfs_read_and_validate_header_region(char *data,
-					     struct inode *ecryptfs_inode);
-int ecryptfs_read_and_validate_xattr_region(char *page_virt,
-					    struct dentry *ecryptfs_dentry);
+int ecryptfs_read_and_validate_header_region(struct inode *inode);
+int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry,
+					    struct inode *inode);
 u8 ecryptfs_code_for_cipher_string(char *cipher_name, size_t key_bytes);
 int ecryptfs_cipher_code_to_string(char *str, u8 cipher_code);
 void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat);
@@ -679,9 +674,6 @@ int
 ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat,
 			  unsigned char *src, struct dentry *ecryptfs_dentry);
 int ecryptfs_truncate(struct dentry *dentry, loff_t new_length);
-int ecryptfs_inode_test(struct inode *inode, void *candidate_lower_inode);
-int ecryptfs_inode_set(struct inode *inode, void *lower_inode);
-void ecryptfs_init_inode(struct inode *inode, struct inode *lower_inode);
 ssize_t
 ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name,
 			void *value, size_t size);
@@ -761,7 +753,7 @@ int ecryptfs_privileged_open(struct file **lower_file,
 			     struct dentry *lower_dentry,
 			     struct vfsmount *lower_mnt,
 			     const struct cred *cred);
-int ecryptfs_get_lower_file(struct dentry *ecryptfs_dentry);
+int ecryptfs_get_lower_file(struct dentry *dentry, struct inode *inode);
 void ecryptfs_put_lower_file(struct inode *inode);
 int
 ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 566e5472f78c..4ec9eb00a241 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -191,7 +191,7 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 				      | ECRYPTFS_ENCRYPTED);
 	}
 	mutex_unlock(&crypt_stat->cs_mutex);
-	rc = ecryptfs_get_lower_file(ecryptfs_dentry);
+	rc = ecryptfs_get_lower_file(ecryptfs_dentry, inode);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to initialize "
 			"the lower file for the dentry with name "
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 227b409b8406..7349ade17de6 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -51,6 +51,97 @@ static void unlock_dir(struct dentry *dir)
 	dput(dir);
 }
 
+static int ecryptfs_inode_test(struct inode *inode, void *lower_inode)
+{
+	if (ecryptfs_inode_to_lower(inode) == (struct inode *)lower_inode)
+		return 1;
+	return 0;
+}
+
+static int ecryptfs_inode_set(struct inode *inode, void *opaque)
+{
+	struct inode *lower_inode = opaque;
+
+	ecryptfs_set_inode_lower(inode, lower_inode);
+	fsstack_copy_attr_all(inode, lower_inode);
+	/* i_size will be overwritten for encrypted regular files */
+	fsstack_copy_inode_size(inode, lower_inode);
+	inode->i_ino = lower_inode->i_ino;
+	inode->i_version++;
+	inode->i_mapping->a_ops = &ecryptfs_aops;
+
+	if (S_ISLNK(inode->i_mode))
+		inode->i_op = &ecryptfs_symlink_iops;
+	else if (S_ISDIR(inode->i_mode))
+		inode->i_op = &ecryptfs_dir_iops;
+	else
+		inode->i_op = &ecryptfs_main_iops;
+
+	if (S_ISDIR(inode->i_mode))
+		inode->i_fop = &ecryptfs_dir_fops;
+	else if (special_file(inode->i_mode))
+		init_special_inode(inode, inode->i_mode, inode->i_rdev);
+	else
+		inode->i_fop = &ecryptfs_main_fops;
+
+	return 0;
+}
+
+static struct inode *__ecryptfs_get_inode(struct inode *lower_inode,
+					  struct super_block *sb)
+{
+	struct inode *inode;
+
+	if (lower_inode->i_sb != ecryptfs_superblock_to_lower(sb))
+		return ERR_PTR(-EXDEV);
+	if (!igrab(lower_inode))
+		return ERR_PTR(-ESTALE);
+	inode = iget5_locked(sb, (unsigned long)lower_inode,
+			     ecryptfs_inode_test, ecryptfs_inode_set,
+			     lower_inode);
+	if (!inode) {
+		iput(lower_inode);
+		return ERR_PTR(-EACCES);
+	}
+	if (!(inode->i_state & I_NEW))
+		iput(lower_inode);
+
+	return inode;
+}
+
+struct inode *ecryptfs_get_inode(struct inode *lower_inode,
+				 struct super_block *sb)
+{
+	struct inode *inode = __ecryptfs_get_inode(lower_inode, sb);
+
+	if (!IS_ERR(inode) && (inode->i_state & I_NEW))
+		unlock_new_inode(inode);
+
+	return inode;
+}
+
+/**
+ * ecryptfs_interpose
+ * @lower_dentry: Existing dentry in the lower filesystem
+ * @dentry: ecryptfs' dentry
+ * @sb: ecryptfs's super_block
+ *
+ * Interposes upper and lower dentries.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_interpose(struct dentry *lower_dentry,
+			      struct dentry *dentry, struct super_block *sb)
+{
+	struct inode *inode = ecryptfs_get_inode(lower_dentry->d_inode, sb);
+
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+	d_instantiate(dentry, inode);
+
+	return 0;
+}
+
 /**
  * ecryptfs_create_underlying_file
  * @lower_dir_inode: inode of the parent in the lower fs of the new file
@@ -129,7 +220,7 @@ ecryptfs_do_create(struct inode *directory_inode,
 		goto out_lock;
 	}
 	rc = ecryptfs_interpose(lower_dentry, ecryptfs_dentry,
-				directory_inode->i_sb, 0);
+				directory_inode->i_sb);
 	if (rc) {
 		ecryptfs_printk(KERN_ERR, "Failure in ecryptfs_interpose\n");
 		goto out_lock;
@@ -168,7 +259,8 @@ static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry)
 				"context; rc = [%d]\n", rc);
 		goto out;
 	}
-	rc = ecryptfs_get_lower_file(ecryptfs_dentry);
+	rc = ecryptfs_get_lower_file(ecryptfs_dentry,
+				     ecryptfs_dentry->d_inode);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to initialize "
 			"the lower file for the dentry with name "
@@ -215,102 +307,90 @@ out:
 	return rc;
 }
 
+static int ecryptfs_i_size_read(struct dentry *dentry, struct inode *inode)
+{
+	struct ecryptfs_crypt_stat *crypt_stat;
+	int rc;
+
+	rc = ecryptfs_get_lower_file(dentry, inode);
+	if (rc) {
+		printk(KERN_ERR "%s: Error attempting to initialize "
+			"the lower file for the dentry with name "
+			"[%s]; rc = [%d]\n", __func__,
+			dentry->d_name.name, rc);
+		return rc;
+	}
+
+	crypt_stat = &ecryptfs_inode_to_private(inode)->crypt_stat;
+	/* TODO: lock for crypt_stat comparison */
+	if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED))
+		ecryptfs_set_default_sizes(crypt_stat);
+
+	rc = ecryptfs_read_and_validate_header_region(inode);
+	ecryptfs_put_lower_file(inode);
+	if (rc) {
+		rc = ecryptfs_read_and_validate_xattr_region(dentry, inode);
+		if (!rc)
+			crypt_stat->flags |= ECRYPTFS_METADATA_IN_XATTR;
+	}
+
+	/* Must return 0 to allow non-eCryptfs files to be looked up, too */
+	return 0;
+}
+
 /**
- * ecryptfs_lookup_and_interpose_lower - Perform a lookup
+ * ecryptfs_lookup_interpose - Dentry interposition for a lookup
  */
-int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
-					struct dentry *lower_dentry,
-					struct inode *ecryptfs_dir_inode)
+static int ecryptfs_lookup_interpose(struct dentry *dentry,
+				     struct dentry *lower_dentry,
+				     struct inode *dir_inode)
 {
-	struct dentry *lower_dir_dentry;
+	struct inode *inode, *lower_inode = lower_dentry->d_inode;
+	struct ecryptfs_dentry_info *dentry_info;
 	struct vfsmount *lower_mnt;
-	struct inode *lower_inode;
-	struct ecryptfs_crypt_stat *crypt_stat;
-	char *page_virt = NULL;
-	int put_lower = 0, rc = 0;
-
-	lower_dir_dentry = lower_dentry->d_parent;
-	lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(
-				   ecryptfs_dentry->d_parent));
-	lower_inode = lower_dentry->d_inode;
-	fsstack_copy_attr_atime(ecryptfs_dir_inode, lower_dir_dentry->d_inode);
+	int rc = 0;
+
+	lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent));
+	fsstack_copy_attr_atime(dir_inode, lower_dentry->d_parent->d_inode);
 	BUG_ON(!lower_dentry->d_count);
-	ecryptfs_set_dentry_private(ecryptfs_dentry,
-				    kmem_cache_alloc(ecryptfs_dentry_info_cache,
-						     GFP_KERNEL));
-	if (!ecryptfs_dentry_to_private(ecryptfs_dentry)) {
-		rc = -ENOMEM;
+
+	dentry_info = kmem_cache_alloc(ecryptfs_dentry_info_cache, GFP_KERNEL);
+	ecryptfs_set_dentry_private(dentry, dentry_info);
+	if (!dentry_info) {
 		printk(KERN_ERR "%s: Out of memory whilst attempting "
 		       "to allocate ecryptfs_dentry_info struct\n",
 			__func__);
-		goto out_put;
+		dput(lower_dentry);
+		mntput(lower_mnt);
+		d_drop(dentry);
+		return -ENOMEM;
 	}
-	ecryptfs_set_dentry_lower(ecryptfs_dentry, lower_dentry);
-	ecryptfs_set_dentry_lower_mnt(ecryptfs_dentry, lower_mnt);
+	ecryptfs_set_dentry_lower(dentry, lower_dentry);
+	ecryptfs_set_dentry_lower_mnt(dentry, lower_mnt);
+
 	if (!lower_dentry->d_inode) {
 		/* We want to add because we couldn't find in lower */
-		d_add(ecryptfs_dentry, NULL);
-		goto out;
-	}
-	rc = ecryptfs_interpose(lower_dentry, ecryptfs_dentry,
-				ecryptfs_dir_inode->i_sb,
-				ECRYPTFS_INTERPOSE_FLAG_D_ADD);
-	if (rc) {
-		printk(KERN_ERR "%s: Error interposing; rc = [%d]\n",
-		       __func__, rc);
-		goto out;
-	}
-	if (S_ISDIR(lower_inode->i_mode))
-		goto out;
-	if (S_ISLNK(lower_inode->i_mode))
-		goto out;
-	if (special_file(lower_inode->i_mode))
-		goto out;
-	/* Released in this function */
-	page_virt = kmem_cache_zalloc(ecryptfs_header_cache_2, GFP_USER);
-	if (!page_virt) {
-		printk(KERN_ERR "%s: Cannot kmem_cache_zalloc() a page\n",
-		       __func__);
-		rc = -ENOMEM;
-		goto out;
+		d_add(dentry, NULL);
+		return 0;
 	}
-	rc = ecryptfs_get_lower_file(ecryptfs_dentry);
-	if (rc) {
-		printk(KERN_ERR "%s: Error attempting to initialize "
-			"the lower file for the dentry with name "
-			"[%s]; rc = [%d]\n", __func__,
-			ecryptfs_dentry->d_name.name, rc);
-		goto out_free_kmem;
+	inode = __ecryptfs_get_inode(lower_inode, dir_inode->i_sb);
+	if (IS_ERR(inode)) {
+		printk(KERN_ERR "%s: Error interposing; rc = [%ld]\n",
+		       __func__, PTR_ERR(inode));
+		return PTR_ERR(inode);
 	}
-	put_lower = 1;
-	crypt_stat = &ecryptfs_inode_to_private(
-					ecryptfs_dentry->d_inode)->crypt_stat;
-	/* TODO: lock for crypt_stat comparison */
-	if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED))
-			ecryptfs_set_default_sizes(crypt_stat);
-	rc = ecryptfs_read_and_validate_header_region(page_virt,
-						      ecryptfs_dentry->d_inode);
-	if (rc) {
-		memset(page_virt, 0, PAGE_CACHE_SIZE);
-		rc = ecryptfs_read_and_validate_xattr_region(page_virt,
-							     ecryptfs_dentry);
+	if (S_ISREG(inode->i_mode)) {
+		rc = ecryptfs_i_size_read(dentry, inode);
 		if (rc) {
-			rc = 0;
-			goto out_free_kmem;
+			make_bad_inode(inode);
+			return rc;
 		}
-		crypt_stat->flags |= ECRYPTFS_METADATA_IN_XATTR;
 	}
-	ecryptfs_i_size_init(page_virt, ecryptfs_dentry->d_inode);
-out_free_kmem:
-	kmem_cache_free(ecryptfs_header_cache_2, page_virt);
-	goto out;
-out_put:
-	dput(lower_dentry);
-	mntput(lower_mnt);
-	d_drop(ecryptfs_dentry);
-out:
-	if (put_lower)
-		ecryptfs_put_lower_file(ecryptfs_dentry->d_inode);
+
+	if (inode->i_state & I_NEW)
+		unlock_new_inode(inode);
+	d_add(dentry, inode);
+
 	return rc;
 }
 
@@ -353,12 +433,12 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 		goto out_d_drop;
 	}
 	if (lower_dentry->d_inode)
-		goto lookup_and_interpose;
+		goto interpose;
 	mount_crypt_stat = &ecryptfs_superblock_to_private(
 				ecryptfs_dentry->d_sb)->mount_crypt_stat;
 	if (!(mount_crypt_stat
 	    && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)))
-		goto lookup_and_interpose;
+		goto interpose;
 	dput(lower_dentry);
 	rc = ecryptfs_encrypt_and_encode_filename(
 		&encrypted_and_encoded_name, &encrypted_and_encoded_name_size,
@@ -381,9 +461,9 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 				encrypted_and_encoded_name);
 		goto out_d_drop;
 	}
-lookup_and_interpose:
-	rc = ecryptfs_lookup_and_interpose_lower(ecryptfs_dentry, lower_dentry,
-						 ecryptfs_dir_inode);
+interpose:
+	rc = ecryptfs_lookup_interpose(ecryptfs_dentry, lower_dentry,
+				       ecryptfs_dir_inode);
 	goto out;
 out_d_drop:
 	d_drop(ecryptfs_dentry);
@@ -411,7 +491,7 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
 		      lower_new_dentry);
 	if (rc || !lower_new_dentry->d_inode)
 		goto out_lock;
-	rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb, 0);
+	rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb);
 	if (rc)
 		goto out_lock;
 	fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
@@ -478,7 +558,7 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry,
 	kfree(encoded_symname);
 	if (rc || !lower_dentry->d_inode)
 		goto out_lock;
-	rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb, 0);
+	rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
 	if (rc)
 		goto out_lock;
 	fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
@@ -502,7 +582,7 @@ static int ecryptfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	rc = vfs_mkdir(lower_dir_dentry->d_inode, lower_dentry, mode);
 	if (rc || !lower_dentry->d_inode)
 		goto out;
-	rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb, 0);
+	rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
 	if (rc)
 		goto out;
 	fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
@@ -521,14 +601,14 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry)
 	struct dentry *lower_dir_dentry;
 	int rc;
 
-	dentry_unhash(dentry);
-
 	lower_dentry = ecryptfs_dentry_to_lower(dentry);
 	dget(dentry);
 	lower_dir_dentry = lock_parent(lower_dentry);
 	dget(lower_dentry);
 	rc = vfs_rmdir(lower_dir_dentry->d_inode, lower_dentry);
 	dput(lower_dentry);
+	if (!rc && dentry->d_inode)
+		clear_nlink(dentry->d_inode);
 	fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
 	dir->i_nlink = lower_dir_dentry->d_inode->i_nlink;
 	unlock_dir(lower_dir_dentry);
@@ -550,7 +630,7 @@ ecryptfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
 	rc = vfs_mknod(lower_dir_dentry->d_inode, lower_dentry, mode, dev);
 	if (rc || !lower_dentry->d_inode)
 		goto out;
-	rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb, 0);
+	rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
 	if (rc)
 		goto out;
 	fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
@@ -573,9 +653,6 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct dentry *lower_new_dir_dentry;
 	struct dentry *trap = NULL;
 
-	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry);
 	lower_new_dentry = ecryptfs_dentry_to_lower(new_dentry);
 	dget(lower_old_dentry);
@@ -753,7 +830,7 @@ static int truncate_upper(struct dentry *dentry, struct iattr *ia,
 		lower_ia->ia_valid &= ~ATTR_SIZE;
 		return 0;
 	}
-	rc = ecryptfs_get_lower_file(dentry);
+	rc = ecryptfs_get_lower_file(dentry, inode);
 	if (rc)
 		return rc;
 	crypt_stat = &ecryptfs_inode_to_private(dentry->d_inode)->crypt_stat;
@@ -909,7 +986,7 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 
 		mount_crypt_stat = &ecryptfs_superblock_to_private(
 			dentry->d_sb)->mount_crypt_stat;
-		rc = ecryptfs_get_lower_file(dentry);
+		rc = ecryptfs_get_lower_file(dentry, inode);
 		if (rc) {
 			mutex_unlock(&crypt_stat->cs_mutex);
 			goto out;
@@ -1082,21 +1159,6 @@ out:
 	return rc;
 }
 
-int ecryptfs_inode_test(struct inode *inode, void *candidate_lower_inode)
-{
-	if ((ecryptfs_inode_to_lower(inode)
-	     == (struct inode *)candidate_lower_inode))
-		return 1;
-	else
-		return 0;
-}
-
-int ecryptfs_inode_set(struct inode *inode, void *lower_inode)
-{
-	ecryptfs_init_inode(inode, (struct inode *)lower_inode);
-	return 0;
-}
-
 const struct inode_operations ecryptfs_symlink_iops = {
 	.readlink = ecryptfs_readlink,
 	.follow_link = ecryptfs_follow_link,
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 03e609c45012..27a7fefb83eb 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -599,8 +599,8 @@ struct ecryptfs_write_tag_70_packet_silly_stack {
 	struct mutex *tfm_mutex;
 	char *block_aligned_filename;
 	struct ecryptfs_auth_tok *auth_tok;
-	struct scatterlist src_sg;
-	struct scatterlist dst_sg;
+	struct scatterlist src_sg[2];
+	struct scatterlist dst_sg[2];
 	struct blkcipher_desc desc;
 	char iv[ECRYPTFS_MAX_IV_BYTES];
 	char hash[ECRYPTFS_TAG_70_DIGEST_SIZE];
@@ -816,23 +816,21 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 	memcpy(&s->block_aligned_filename[s->num_rand_bytes], filename,
 	       filename_size);
 	rc = virt_to_scatterlist(s->block_aligned_filename,
-				 s->block_aligned_filename_size, &s->src_sg, 1);
-	if (rc != 1) {
+				 s->block_aligned_filename_size, s->src_sg, 2);
+	if (rc < 1) {
 		printk(KERN_ERR "%s: Internal error whilst attempting to "
-		       "convert filename memory to scatterlist; "
-		       "expected rc = 1; got rc = [%d]. "
+		       "convert filename memory to scatterlist; rc = [%d]. "
 		       "block_aligned_filename_size = [%zd]\n", __func__, rc,
 		       s->block_aligned_filename_size);
 		goto out_release_free_unlock;
 	}
 	rc = virt_to_scatterlist(&dest[s->i], s->block_aligned_filename_size,
-				 &s->dst_sg, 1);
-	if (rc != 1) {
+				 s->dst_sg, 2);
+	if (rc < 1) {
 		printk(KERN_ERR "%s: Internal error whilst attempting to "
 		       "convert encrypted filename memory to scatterlist; "
-		       "expected rc = 1; got rc = [%d]. "
-		       "block_aligned_filename_size = [%zd]\n", __func__, rc,
-		       s->block_aligned_filename_size);
+		       "rc = [%d]. block_aligned_filename_size = [%zd]\n",
+		       __func__, rc, s->block_aligned_filename_size);
 		goto out_release_free_unlock;
 	}
 	/* The characters in the first block effectively do the job
@@ -855,7 +853,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		       mount_crypt_stat->global_default_fn_cipher_key_bytes);
 		goto out_release_free_unlock;
 	}
-	rc = crypto_blkcipher_encrypt_iv(&s->desc, &s->dst_sg, &s->src_sg,
+	rc = crypto_blkcipher_encrypt_iv(&s->desc, s->dst_sg, s->src_sg,
 					 s->block_aligned_filename_size);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to encrypt filename; "
@@ -891,8 +889,8 @@ struct ecryptfs_parse_tag_70_packet_silly_stack {
 	struct mutex *tfm_mutex;
 	char *decrypted_filename;
 	struct ecryptfs_auth_tok *auth_tok;
-	struct scatterlist src_sg;
-	struct scatterlist dst_sg;
+	struct scatterlist src_sg[2];
+	struct scatterlist dst_sg[2];
 	struct blkcipher_desc desc;
 	char fnek_sig_hex[ECRYPTFS_SIG_SIZE_HEX + 1];
 	char iv[ECRYPTFS_MAX_IV_BYTES];
@@ -1008,13 +1006,12 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 	}
 	mutex_lock(s->tfm_mutex);
 	rc = virt_to_scatterlist(&data[(*packet_size)],
-				 s->block_aligned_filename_size, &s->src_sg, 1);
-	if (rc != 1) {
+				 s->block_aligned_filename_size, s->src_sg, 2);
+	if (rc < 1) {
 		printk(KERN_ERR "%s: Internal error whilst attempting to "
 		       "convert encrypted filename memory to scatterlist; "
-		       "expected rc = 1; got rc = [%d]. "
-		       "block_aligned_filename_size = [%zd]\n", __func__, rc,
-		       s->block_aligned_filename_size);
+		       "rc = [%d]. block_aligned_filename_size = [%zd]\n",
+		       __func__, rc, s->block_aligned_filename_size);
 		goto out_unlock;
 	}
 	(*packet_size) += s->block_aligned_filename_size;
@@ -1028,13 +1025,12 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		goto out_unlock;
 	}
 	rc = virt_to_scatterlist(s->decrypted_filename,
-				 s->block_aligned_filename_size, &s->dst_sg, 1);
-	if (rc != 1) {
+				 s->block_aligned_filename_size, s->dst_sg, 2);
+	if (rc < 1) {
 		printk(KERN_ERR "%s: Internal error whilst attempting to "
 		       "convert decrypted filename memory to scatterlist; "
-		       "expected rc = 1; got rc = [%d]. "
-		       "block_aligned_filename_size = [%zd]\n", __func__, rc,
-		       s->block_aligned_filename_size);
+		       "rc = [%d]. block_aligned_filename_size = [%zd]\n",
+		       __func__, rc, s->block_aligned_filename_size);
 		goto out_free_unlock;
 	}
 	/* The characters in the first block effectively do the job of
@@ -1065,7 +1061,7 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		       mount_crypt_stat->global_default_fn_cipher_key_bytes);
 		goto out_free_unlock;
 	}
-	rc = crypto_blkcipher_decrypt_iv(&s->desc, &s->dst_sg, &s->src_sg,
+	rc = crypto_blkcipher_decrypt_iv(&s->desc, s->dst_sg, s->src_sg,
 					 s->block_aligned_filename_size);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to decrypt filename; "
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 89b93389af8e..9f1bb747d77d 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -135,12 +135,12 @@ static int ecryptfs_init_lower_file(struct dentry *dentry,
 	return rc;
 }
 
-int ecryptfs_get_lower_file(struct dentry *dentry)
+int ecryptfs_get_lower_file(struct dentry *dentry, struct inode *inode)
 {
-	struct ecryptfs_inode_info *inode_info =
-		ecryptfs_inode_to_private(dentry->d_inode);
+	struct ecryptfs_inode_info *inode_info;
 	int count, rc = 0;
 
+	inode_info = ecryptfs_inode_to_private(inode);
 	mutex_lock(&inode_info->lower_file_mutex);
 	count = atomic_inc_return(&inode_info->lower_file_count);
 	if (WARN_ON_ONCE(count < 1))
@@ -168,75 +168,6 @@ void ecryptfs_put_lower_file(struct inode *inode)
 	}
 }
 
-static struct inode *ecryptfs_get_inode(struct inode *lower_inode,
-		       struct super_block *sb)
-{
-	struct inode *inode;
-	int rc = 0;
-
-	if (lower_inode->i_sb != ecryptfs_superblock_to_lower(sb)) {
-		rc = -EXDEV;
-		goto out;
-	}
-	if (!igrab(lower_inode)) {
-		rc = -ESTALE;
-		goto out;
-	}
-	inode = iget5_locked(sb, (unsigned long)lower_inode,
-			     ecryptfs_inode_test, ecryptfs_inode_set,
-			     lower_inode);
-	if (!inode) {
-		rc = -EACCES;
-		iput(lower_inode);
-		goto out;
-	}
-	if (inode->i_state & I_NEW)
-		unlock_new_inode(inode);
-	else
-		iput(lower_inode);
-	if (S_ISLNK(lower_inode->i_mode))
-		inode->i_op = &ecryptfs_symlink_iops;
-	else if (S_ISDIR(lower_inode->i_mode))
-		inode->i_op = &ecryptfs_dir_iops;
-	if (S_ISDIR(lower_inode->i_mode))
-		inode->i_fop = &ecryptfs_dir_fops;
-	if (special_file(lower_inode->i_mode))
-		init_special_inode(inode, lower_inode->i_mode,
-				   lower_inode->i_rdev);
-	fsstack_copy_attr_all(inode, lower_inode);
-	/* This size will be overwritten for real files w/ headers and
-	 * other metadata */
-	fsstack_copy_inode_size(inode, lower_inode);
-	return inode;
-out:
-	return ERR_PTR(rc);
-}
-
-/**
- * ecryptfs_interpose
- * @lower_dentry: Existing dentry in the lower filesystem
- * @dentry: ecryptfs' dentry
- * @sb: ecryptfs's super_block
- * @flags: flags to govern behavior of interpose procedure
- *
- * Interposes upper and lower dentries.
- *
- * Returns zero on success; non-zero otherwise
- */
-int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
-		       struct super_block *sb, u32 flags)
-{
-	struct inode *lower_inode = lower_dentry->d_inode;
-	struct inode *inode = ecryptfs_get_inode(lower_inode, sb);
-	if (IS_ERR(inode))
-		return PTR_ERR(inode);
-	if (flags & ECRYPTFS_INTERPOSE_FLAG_D_ADD)
-		d_add(dentry, inode);
-	else
-		d_instantiate(dentry, inode);
-	return 0;
-}
-
 enum { ecryptfs_opt_sig, ecryptfs_opt_ecryptfs_sig,
        ecryptfs_opt_cipher, ecryptfs_opt_ecryptfs_cipher,
        ecryptfs_opt_ecryptfs_key_bytes,
@@ -704,13 +635,8 @@ static struct ecryptfs_cache_info {
 		.size = sizeof(struct ecryptfs_sb_info),
 	},
 	{
-		.cache = &ecryptfs_header_cache_1,
-		.name = "ecryptfs_headers_1",
-		.size = PAGE_CACHE_SIZE,
-	},
-	{
-		.cache = &ecryptfs_header_cache_2,
-		.name = "ecryptfs_headers_2",
+		.cache = &ecryptfs_header_cache,
+		.name = "ecryptfs_headers",
 		.size = PAGE_CACHE_SIZE,
 	},
 	{
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index 245b517bf1b6..dbd52d40df4c 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -93,22 +93,6 @@ static void ecryptfs_destroy_inode(struct inode *inode)
 }
 
 /**
- * ecryptfs_init_inode
- * @inode: The ecryptfs inode
- *
- * Set up the ecryptfs inode.
- */
-void ecryptfs_init_inode(struct inode *inode, struct inode *lower_inode)
-{
-	ecryptfs_set_inode_lower(inode, lower_inode);
-	inode->i_ino = lower_inode->i_ino;
-	inode->i_version++;
-	inode->i_op = &ecryptfs_main_iops;
-	inode->i_fop = &ecryptfs_main_fops;
-	inode->i_mapping->a_ops = &ecryptfs_aops;
-}
-
-/**
  * ecryptfs_statfs
  * @sb: The ecryptfs super block
  * @buf: The struct kstatfs to fill in with stats
diff --git a/fs/exec.c b/fs/exec.c
index ea5f748906a8..6075a1e727ae 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1093,6 +1093,7 @@ int flush_old_exec(struct linux_binprm * bprm)
 
 	bprm->mm = NULL;		/* We're using it now */
 
+	set_fs(USER_DS);
 	current->flags &= ~(PF_RANDOMIZE | PF_KTHREAD);
 	flush_thread();
 	current->personality &= ~bprm->per_clear;
@@ -1357,10 +1358,6 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 	if (retval)
 		return retval;
 
-	/* kernel module loader fixup */
-	/* so we don't try to load run modprobe in kernel space. */
-	set_fs(USER_DS);
-
 	retval = audit_bprm(bprm);
 	if (retval)
 		return retval;
@@ -1999,7 +1996,7 @@ static void wait_for_dump_helpers(struct file *file)
  * is a special value that we use to trap recursive
  * core dumps
  */
-static int umh_pipe_setup(struct subprocess_info *info)
+static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
 {
 	struct file *rp, *wp;
 	struct fdtable *fdt;
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 68b2e43d7c35..3451d23c3bae 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -3392,7 +3392,7 @@ int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode)
  * so would cause a commit on atime updates, which we don't bother doing.
  * We handle synchronous inodes at the highest possible level.
  */
-void ext3_dirty_inode(struct inode *inode)
+void ext3_dirty_inode(struct inode *inode, int flags)
 {
 	handle_t *current_handle = ext3_journal_current_handle();
 	handle_t *handle;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index a74b89c09f90..1921392cd708 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1813,7 +1813,7 @@ extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
 extern void ext4_evict_inode(struct inode *);
 extern void ext4_clear_inode(struct inode *);
 extern int  ext4_sync_inode(handle_t *, struct inode *);
-extern void ext4_dirty_inode(struct inode *);
+extern void ext4_dirty_inode(struct inode *, int);
 extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
 extern int ext4_can_truncate(struct inode *inode);
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 2e29abb30f76..095c36f3b612 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -125,7 +125,7 @@ struct ext4_ext_path {
  * positive retcode - signal for ext4_ext_walk_space(), see below
  * callback must return valid extent (passed or newly created)
  */
-typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *,
+typedef int (*ext_prepare_callback)(struct inode *, ext4_lblk_t,
 					struct ext4_ext_cache *,
 					struct ext4_extent *, void *);
 
@@ -133,8 +133,11 @@ typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *,
 #define EXT_BREAK      1
 #define EXT_REPEAT     2
 
-/* Maximum logical block in a file; ext4_extent's ee_block is __le32 */
-#define EXT_MAX_BLOCK	0xffffffff
+/*
+ * Maximum number of logical blocks in a file; ext4_extent's ee_block is
+ * __le32.
+ */
+#define EXT_MAX_BLOCKS	0xffffffff
 
 /*
  * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 5199bac7fc62..f815cc81e7a2 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1408,7 +1408,7 @@ got_index:
 
 /*
  * ext4_ext_next_allocated_block:
- * returns allocated block in subsequent extent or EXT_MAX_BLOCK.
+ * returns allocated block in subsequent extent or EXT_MAX_BLOCKS.
  * NOTE: it considers block number from index entry as
  * allocated block. Thus, index entries have to be consistent
  * with leaves.
@@ -1422,7 +1422,7 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path)
 	depth = path->p_depth;
 
 	if (depth == 0 && path->p_ext == NULL)
-		return EXT_MAX_BLOCK;
+		return EXT_MAX_BLOCKS;
 
 	while (depth >= 0) {
 		if (depth == path->p_depth) {
@@ -1439,12 +1439,12 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path)
 		depth--;
 	}
 
-	return EXT_MAX_BLOCK;
+	return EXT_MAX_BLOCKS;
 }
 
 /*
  * ext4_ext_next_leaf_block:
- * returns first allocated block from next leaf or EXT_MAX_BLOCK
+ * returns first allocated block from next leaf or EXT_MAX_BLOCKS
  */
 static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode,
 					struct ext4_ext_path *path)
@@ -1456,7 +1456,7 @@ static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode,
 
 	/* zero-tree has no leaf blocks at all */
 	if (depth == 0)
-		return EXT_MAX_BLOCK;
+		return EXT_MAX_BLOCKS;
 
 	/* go to index block */
 	depth--;
@@ -1469,7 +1469,7 @@ static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode,
 		depth--;
 	}
 
-	return EXT_MAX_BLOCK;
+	return EXT_MAX_BLOCKS;
 }
 
 /*
@@ -1677,13 +1677,13 @@ static unsigned int ext4_ext_check_overlap(struct inode *inode,
 	 */
 	if (b2 < b1) {
 		b2 = ext4_ext_next_allocated_block(path);
-		if (b2 == EXT_MAX_BLOCK)
+		if (b2 == EXT_MAX_BLOCKS)
 			goto out;
 	}
 
 	/* check for wrap through zero on extent logical start block*/
 	if (b1 + len1 < b1) {
-		len1 = EXT_MAX_BLOCK - b1;
+		len1 = EXT_MAX_BLOCKS - b1;
 		newext->ee_len = cpu_to_le16(len1);
 		ret = 1;
 	}
@@ -1767,7 +1767,7 @@ repeat:
 	fex = EXT_LAST_EXTENT(eh);
 	next = ext4_ext_next_leaf_block(inode, path);
 	if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block)
-	    && next != EXT_MAX_BLOCK) {
+	    && next != EXT_MAX_BLOCKS) {
 		ext_debug("next leaf block - %d\n", next);
 		BUG_ON(npath != NULL);
 		npath = ext4_ext_find_extent(inode, next, NULL);
@@ -1887,7 +1887,7 @@ static int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
 	BUG_ON(func == NULL);
 	BUG_ON(inode == NULL);
 
-	while (block < last && block != EXT_MAX_BLOCK) {
+	while (block < last && block != EXT_MAX_BLOCKS) {
 		num = last - block;
 		/* find extent for this block */
 		down_read(&EXT4_I(inode)->i_data_sem);
@@ -1958,7 +1958,7 @@ static int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
 			err = -EIO;
 			break;
 		}
-		err = func(inode, path, &cbex, ex, cbdata);
+		err = func(inode, next, &cbex, ex, cbdata);
 		ext4_ext_drop_refs(path);
 
 		if (err < 0)
@@ -2020,7 +2020,7 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
 	if (ex == NULL) {
 		/* there is no extent yet, so gap is [0;-] */
 		lblock = 0;
-		len = EXT_MAX_BLOCK;
+		len = EXT_MAX_BLOCKS;
 		ext_debug("cache gap(whole file):");
 	} else if (block < le32_to_cpu(ex->ee_block)) {
 		lblock = block;
@@ -2350,7 +2350,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 			 * never happen because at least one of the end points
 			 * needs to be on the edge of the extent.
 			 */
-			if (end == EXT_MAX_BLOCK) {
+			if (end == EXT_MAX_BLOCKS - 1) {
 				ext_debug("  bad truncate %u:%u\n",
 						start, end);
 				block = 0;
@@ -2398,7 +2398,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 			 * If this is a truncate, this condition
 			 * should never happen
 			 */
-			if (end == EXT_MAX_BLOCK) {
+			if (end == EXT_MAX_BLOCKS - 1) {
 				ext_debug("  bad truncate %u:%u\n",
 					start, end);
 				err = -EIO;
@@ -2478,7 +2478,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 		 * we need to remove it from the leaf
 		 */
 		if (num == 0) {
-			if (end != EXT_MAX_BLOCK) {
+			if (end != EXT_MAX_BLOCKS - 1) {
 				/*
 				 * For hole punching, we need to scoot all the
 				 * extents up when an extent is removed so that
@@ -3699,7 +3699,7 @@ void ext4_ext_truncate(struct inode *inode)
 
 	last_block = (inode->i_size + sb->s_blocksize - 1)
 			>> EXT4_BLOCK_SIZE_BITS(sb);
-	err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCK);
+	err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
 
 	/* In a multi-transaction truncate, we only make the final
 	 * transaction synchronous.
@@ -3914,14 +3914,13 @@ int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
 /*
  * Callback function called for each extent to gather FIEMAP information.
  */
-static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
+static int ext4_ext_fiemap_cb(struct inode *inode, ext4_lblk_t next,
 		       struct ext4_ext_cache *newex, struct ext4_extent *ex,
 		       void *data)
 {
 	__u64	logical;
 	__u64	physical;
 	__u64	length;
-	loff_t	size;
 	__u32	flags = 0;
 	int		ret = 0;
 	struct fiemap_extent_info *fieinfo = data;
@@ -4103,8 +4102,7 @@ found_delayed_extent:
 	if (ex && ext4_ext_is_uninitialized(ex))
 		flags |= FIEMAP_EXTENT_UNWRITTEN;
 
-	size = i_size_read(inode);
-	if (logical + length >= size)
+	if (next == EXT_MAX_BLOCKS)
 		flags |= FIEMAP_EXTENT_LAST;
 
 	ret = fiemap_fill_next_extent(fieinfo, logical, physical,
@@ -4347,8 +4345,8 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 
 		start_blk = start >> inode->i_sb->s_blocksize_bits;
 		last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits;
-		if (last_blk >= EXT_MAX_BLOCK)
-			last_blk = EXT_MAX_BLOCK-1;
+		if (last_blk >= EXT_MAX_BLOCKS)
+			last_blk = EXT_MAX_BLOCKS-1;
 		len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1;
 
 		/*
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 50d0e9c64584..e3126c051006 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2634,7 +2634,7 @@ static int ext4_writepage(struct page *page,
 	struct buffer_head *page_bufs = NULL;
 	struct inode *inode = page->mapping->host;
 
-	trace_ext4_writepage(inode, page);
+	trace_ext4_writepage(page);
 	size = i_size_read(inode);
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
@@ -5733,7 +5733,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
  * so would cause a commit on atime updates, which we don't bother doing.
  * We handle synchronous inodes at the highest possible level.
  */
-void ext4_dirty_inode(struct inode *inode)
+void ext4_dirty_inode(struct inode *inode, int flags)
 {
 	handle_t *handle;
 
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 859f2ae8864e..6ed859d56850 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3578,8 +3578,8 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 		free += next - bit;
 
 		trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit);
-		trace_ext4_mb_release_inode_pa(sb, pa->pa_inode, pa,
-					       grp_blk_start + bit, next - bit);
+		trace_ext4_mb_release_inode_pa(pa, grp_blk_start + bit,
+					       next - bit);
 		mb_free_blocks(pa->pa_inode, e4b, bit, next - bit);
 		bit = next + 1;
 	}
@@ -3608,7 +3608,7 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 	ext4_group_t group;
 	ext4_grpblk_t bit;
 
-	trace_ext4_mb_release_group_pa(sb, pa);
+	trace_ext4_mb_release_group_pa(pa);
 	BUG_ON(pa->pa_deleted == 0);
 	ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
 	BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
@@ -4448,7 +4448,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
  * @inode:		inode
  * @block:		start physical block to free
  * @count:		number of blocks to count
- * @metadata: 		Are these metadata blocks
+ * @flags:		flags used by ext4_free_blocks
  */
 void ext4_free_blocks(handle_t *handle, struct inode *inode,
 		      struct buffer_head *bh, ext4_fsblk_t block,
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 2b8304bf3c50..f57455a1b1b2 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -1002,12 +1002,12 @@ mext_check_arguments(struct inode *orig_inode,
 		return -EINVAL;
 	}
 
-	if ((orig_start > EXT_MAX_BLOCK) ||
-	    (donor_start > EXT_MAX_BLOCK) ||
-	    (*len > EXT_MAX_BLOCK) ||
-	    (orig_start + *len > EXT_MAX_BLOCK))  {
+	if ((orig_start >= EXT_MAX_BLOCKS) ||
+	    (donor_start >= EXT_MAX_BLOCKS) ||
+	    (*len > EXT_MAX_BLOCKS) ||
+	    (orig_start + *len >= EXT_MAX_BLOCKS))  {
 		ext4_debug("ext4 move extent: Can't handle over [%u] blocks "
-			"[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCK,
+			"[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCKS,
 			orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index cc5c157aa11d..9ea71aa864b3 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2243,6 +2243,12 @@ static void ext4_orphan_cleanup(struct super_block *sb,
  * in the vfs.  ext4 inode has 48 bits of i_block in fsblock units,
  * so that won't be a limiting factor.
  *
+ * However there is other limiting factor. We do store extents in the form
+ * of starting block and length, hence the resulting length of the extent
+ * covering maximum file size must fit into on-disk format containers as
+ * well. Given that length is always by 1 unit bigger than max unit (because
+ * we count 0 as well) we have to lower the s_maxbytes by one fs block.
+ *
  * Note, this does *not* consider any metadata overhead for vfs i_blocks.
  */
 static loff_t ext4_max_size(int blkbits, int has_huge_files)
@@ -2264,10 +2270,13 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files)
 		upper_limit <<= blkbits;
 	}
 
-	/* 32-bit extent-start container, ee_block */
-	res = 1LL << 32;
+	/*
+	 * 32-bit extent-start container, ee_block. We lower the maxbytes
+	 * by one fs block, so ee_len can cover the extent of maximum file
+	 * size
+	 */
+	res = (1LL << 32) - 1;
 	res <<= blkbits;
-	res -= 1;
 
 	/* Sanity check against vm- & vfs- imposed limits */
 	if (res > upper_limit)
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 7257752b6d5d..7018e1d8902d 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -102,7 +102,7 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr)
 		if (attr & ATTR_SYS)
 			inode->i_flags |= S_IMMUTABLE;
 		else
-			inode->i_flags &= S_IMMUTABLE;
+			inode->i_flags &= ~S_IMMUTABLE;
 	}
 
 	fat_save_attrs(inode, attr);
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index be15437c272e..3b222dafd15b 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -326,8 +326,6 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry)
 	struct fat_slot_info sinfo;
 	int err;
 
-	dentry_unhash(dentry);
-
 	lock_super(sb);
 	/*
 	 * Check whether the directory is not in use, then check
@@ -459,9 +457,6 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name,
 	old_inode = old_dentry->d_inode;
 	new_inode = new_dentry->d_inode;
 
-	if (new_inode && S_ISDIR(new_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	err = fat_scan(old_dir, old_name, &old_sinfo);
 	if (err) {
 		err = -EIO;
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index c61a6789f36c..20b4ea53fdc4 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -824,8 +824,6 @@ static int vfat_rmdir(struct inode *dir, struct dentry *dentry)
 	struct fat_slot_info sinfo;
 	int err;
 
-	dentry_unhash(dentry);
-
 	lock_super(sb);
 
 	err = fat_dir_empty(inode);
@@ -933,9 +931,6 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int err, is_dir, update_dotdot, corrupt = 0;
 	struct super_block *sb = old_dir->i_sb;
 
-	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	old_sinfo.bh = sinfo.bh = dotdot_bh = NULL;
 	old_inode = old_dentry->d_inode;
 	new_inode = new_dentry->d_inode;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 34591ee804b5..0f015a0468de 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1007,9 +1007,6 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode)
  * In short, make sure you hash any inodes _before_ you start marking
  * them dirty.
  *
- * This function *must* be atomic for the I_DIRTY_PAGES case -
- * set_page_dirty() is called under spinlock in several places.
- *
  * Note that for blockdevs, inode->dirtied_when represents the dirtying time of
  * the block-special inode (/dev/hda1) itself.  And the ->dirtied_when field of
  * the kernel-internal blockdev inode represents the dirtying time of the
@@ -1028,7 +1025,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	 */
 	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
 		if (sb->s_op->dirty_inode)
-			sb->s_op->dirty_inode(inode);
+			sb->s_op->dirty_inode(inode, flags);
 	}
 
 	/*
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 0d0e3faddcfa..d50160714595 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -667,8 +667,6 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	dentry_unhash(entry);
-
 	req->in.h.opcode = FUSE_RMDIR;
 	req->in.h.nodeid = get_node_id(dir);
 	req->in.numargs = 1;
@@ -694,9 +692,6 @@ static int fuse_rename(struct inode *olddir, struct dentry *oldent,
 	struct fuse_conn *fc = get_fuse_conn(olddir);
 	struct fuse_req *req = fuse_get_req(fc);
 
-	if (newent->d_inode && S_ISDIR(newent->d_inode->i_mode))
-		dentry_unhash(newent);
-
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index cc6ec4b2f0ff..38f84cd48b67 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -921,6 +921,8 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	if (sb->s_flags & MS_MANDLOCK)
 		goto err;
 
+	sb->s_flags &= ~MS_NOSEC;
+
 	if (!parse_fuse_opt((char *) data, &d, is_bdev))
 		goto err;
 
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 2792a790e50b..1c1336e7b3b2 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -663,14 +663,19 @@ static void glock_work_func(struct work_struct *work)
 		drop_ref = 1;
 	}
 	spin_lock(&gl->gl_spin);
-	if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
 	    gl->gl_state != LM_ST_UNLOCKED &&
 	    gl->gl_demote_state != LM_ST_EXCLUSIVE) {
 		unsigned long holdtime, now = jiffies;
+
 		holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
 		if (time_before(now, holdtime))
 			delay = holdtime - now;
-		set_bit(delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE, &gl->gl_flags);
+
+		if (!delay) {
+			clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags);
+			set_bit(GLF_DEMOTE, &gl->gl_flags);
+		}
 	}
 	run_queue(gl, 0);
 	spin_unlock(&gl->gl_spin);
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 1cb70cdba2c1..b4d70b13be92 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -253,9 +253,6 @@ static int hfs_remove(struct inode *dir, struct dentry *dentry)
 	struct inode *inode = dentry->d_inode;
 	int res;
 
-	if (S_ISDIR(inode->i_mode))
-		dentry_unhash(dentry);
-
 	if (S_ISDIR(inode->i_mode) && inode->i_size != 2)
 		return -ENOTEMPTY;
 	res = hfs_cat_delete(inode->i_ino, dir, &dentry->d_name);
@@ -286,9 +283,6 @@ static int hfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	/* Unlink destination if it already exists */
 	if (new_dentry->d_inode) {
-		if (S_ISDIR(new_dentry->d_inode->i_mode))
-			dentry_unhash(new_dentry);
-
 		res = hfs_remove(new_dir, new_dentry);
 		if (res)
 			return res;
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index b28835091dd0..4df5059c25da 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -370,8 +370,6 @@ static int hfsplus_rmdir(struct inode *dir, struct dentry *dentry)
 	struct inode *inode = dentry->d_inode;
 	int res;
 
-	dentry_unhash(dentry);
-
 	if (inode->i_size != 2)
 		return -ENOTEMPTY;
 
@@ -469,12 +467,10 @@ static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	/* Unlink destination if it already exists */
 	if (new_dentry->d_inode) {
-		if (S_ISDIR(new_dentry->d_inode->i_mode)) {
-			dentry_unhash(new_dentry);
+		if (S_ISDIR(new_dentry->d_inode->i_mode))
 			res = hfsplus_rmdir(new_dir, new_dentry);
-		} else {
+		else
 			res = hfsplus_unlink(new_dir, new_dentry);
-		}
 		if (res)
 			return res;
 	}
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index e6816b9e6903..2638c834ed28 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -683,8 +683,6 @@ int hostfs_rmdir(struct inode *ino, struct dentry *dentry)
 	char *file;
 	int err;
 
-	dentry_unhash(dentry);
-
 	if ((file = dentry_name(dentry)) == NULL)
 		return -ENOMEM;
 	err = do_rmdir(file);
@@ -738,9 +736,6 @@ int hostfs_rename(struct inode *from_ino, struct dentry *from,
 	char *from_name, *to_name;
 	int err;
 
-	if (to->d_inode && S_ISDIR(to->d_inode->i_mode))
-		dentry_unhash(to);
-
 	if ((from_name = dentry_name(from)) == NULL)
 		return -ENOMEM;
 	if ((to_name = dentry_name(to)) == NULL) {
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index ff0ce21c0867..acf95dab2aac 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -439,8 +439,6 @@ static int hpfs_rmdir(struct inode *dir, struct dentry *dentry)
 	int err;
 	int r;
 
-	dentry_unhash(dentry);
-
 	hpfs_adjust_length(name, &len);
 	hpfs_lock(dir->i_sb);
 	err = -ENOENT;
@@ -535,9 +533,6 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct fnode *fnode;
 	int err;
 
-	if (new_inode && S_ISDIR(new_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	if ((err = hpfs_chk_name(new_name, &new_len))) return err;
 	err = 0;
 	hpfs_adjust_length(old_name, &old_len);
diff --git a/fs/inode.c b/fs/inode.c
index 990d284877a1..43566d17d1b8 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1,9 +1,7 @@
 /*
- * linux/fs/inode.c
- *
  * (C) 1997 Linus Torvalds
+ * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation)
  */
-
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/dcache.h>
@@ -27,10 +25,11 @@
 #include <linux/prefetch.h>
 #include <linux/ima.h>
 #include <linux/cred.h>
+#include <linux/buffer_head.h> /* for inode_has_buffers */
 #include "internal.h"
 
 /*
- * inode locking rules.
+ * Inode locking rules:
  *
  * inode->i_lock protects:
  *   inode->i_state, inode->i_hash, __iget()
@@ -60,54 +59,11 @@
  *   inode_hash_lock
  */
 
-/*
- * This is needed for the following functions:
- *  - inode_has_buffers
- *  - invalidate_bdev
- *
- * FIXME: remove all knowledge of the buffer layer from this file
- */
-#include <linux/buffer_head.h>
-
-/*
- * New inode.c implementation.
- *
- * This implementation has the basic premise of trying
- * to be extremely low-overhead and SMP-safe, yet be
- * simple enough to be "obviously correct".
- *
- * Famous last words.
- */
-
-/* inode dynamic allocation 1999, Andrea Arcangeli <andrea@suse.de> */
-
-/* #define INODE_PARANOIA 1 */
-/* #define INODE_DEBUG 1 */
-
-/*
- * Inode lookup is no longer as critical as it used to be:
- * most of the lookups are going to be through the dcache.
- */
-#define I_HASHBITS	i_hash_shift
-#define I_HASHMASK	i_hash_mask
-
 static unsigned int i_hash_mask __read_mostly;
 static unsigned int i_hash_shift __read_mostly;
 static struct hlist_head *inode_hashtable __read_mostly;
 static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
 
-/*
- * Each inode can be on two separate lists. One is
- * the hash list of the inode, used for lookups. The
- * other linked list is the "type" list:
- *  "in_use" - valid inode, i_count > 0, i_nlink > 0
- *  "dirty"  - as "in_use" but also dirty
- *  "unused" - valid inode, i_count = 0
- *
- * A "dirty" list is maintained for each super block,
- * allowing for low-overhead inode sync() operations.
- */
-
 static LIST_HEAD(inode_lru);
 static DEFINE_SPINLOCK(inode_lru_lock);
 
@@ -424,8 +380,8 @@ static unsigned long hash(struct super_block *sb, unsigned long hashval)
 
 	tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) /
 			L1_CACHE_BYTES;
-	tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> I_HASHBITS);
-	return tmp & I_HASHMASK;
+	tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift);
+	return tmp & i_hash_mask;
 }
 
 /**
@@ -467,7 +423,14 @@ EXPORT_SYMBOL(remove_inode_hash);
 void end_writeback(struct inode *inode)
 {
 	might_sleep();
+	/*
+	 * We have to cycle tree_lock here because reclaim can be still in the
+	 * process of removing the last page (in __delete_from_page_cache())
+	 * and we must not free mapping under it.
+	 */
+	spin_lock_irq(&inode->i_data.tree_lock);
 	BUG_ON(inode->i_data.nrpages);
+	spin_unlock_irq(&inode->i_data.tree_lock);
 	BUG_ON(!list_empty(&inode->i_data.private_list));
 	BUG_ON(!(inode->i_state & I_FREEING));
 	BUG_ON(inode->i_state & I_CLEAR);
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 3db5ba4568fc..b3cc8586984e 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -974,7 +974,7 @@ out_no_inode:
 out_no_read:
 	printk(KERN_WARNING "%s: bread failed, dev=%s, iso_blknum=%d, block=%d\n",
 		__func__, s->s_id, iso_blknum, block);
-	goto out_freesbi;
+	goto out_freebh;
 out_bad_zone_size:
 	printk(KERN_WARNING "ISOFS: Bad logical zone size %ld\n",
 		sbi->s_log_zone_size);
@@ -989,6 +989,7 @@ out_unknown_format:
 
 out_freebh:
 	brelse(bh);
+	brelse(pri_bh);
 out_freesbi:
 	kfree(opt.iocharset);
 	kfree(sbi);
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 6a79fd0a1a32..2c62c5aae82f 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -97,10 +97,14 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
 
 	if (jh->b_jlist == BJ_None && !buffer_locked(bh) &&
 	    !buffer_dirty(bh) && !buffer_write_io_error(bh)) {
+		/*
+		 * Get our reference so that bh cannot be freed before
+		 * we unlock it
+		 */
+		get_bh(bh);
 		JBUFFER_TRACE(jh, "remove from checkpoint list");
 		ret = __jbd2_journal_remove_checkpoint(jh) + 1;
 		jbd_unlock_bh_state(bh);
-		jbd2_journal_remove_journal_head(bh);
 		BUFFER_TRACE(bh, "release");
 		__brelse(bh);
 	} else {
@@ -223,8 +227,8 @@ restart:
 			spin_lock(&journal->j_list_lock);
 			goto restart;
 		}
+		get_bh(bh);
 		if (buffer_locked(bh)) {
-			atomic_inc(&bh->b_count);
 			spin_unlock(&journal->j_list_lock);
 			jbd_unlock_bh_state(bh);
 			wait_on_buffer(bh);
@@ -243,7 +247,6 @@ restart:
 		 */
 		released = __jbd2_journal_remove_checkpoint(jh);
 		jbd_unlock_bh_state(bh);
-		jbd2_journal_remove_journal_head(bh);
 		__brelse(bh);
 	}
 
@@ -284,7 +287,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 	int ret = 0;
 
 	if (buffer_locked(bh)) {
-		atomic_inc(&bh->b_count);
+		get_bh(bh);
 		spin_unlock(&journal->j_list_lock);
 		jbd_unlock_bh_state(bh);
 		wait_on_buffer(bh);
@@ -316,12 +319,12 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		ret = 1;
 		if (unlikely(buffer_write_io_error(bh)))
 			ret = -EIO;
+		get_bh(bh);
 		J_ASSERT_JH(jh, !buffer_jbddirty(bh));
 		BUFFER_TRACE(bh, "remove from checkpoint");
 		__jbd2_journal_remove_checkpoint(jh);
 		spin_unlock(&journal->j_list_lock);
 		jbd_unlock_bh_state(bh);
-		jbd2_journal_remove_journal_head(bh);
 		__brelse(bh);
 	} else {
 		/*
@@ -554,7 +557,8 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
 /*
  * journal_clean_one_cp_list
  *
- * Find all the written-back checkpoint buffers in the given list and release them.
+ * Find all the written-back checkpoint buffers in the given list and
+ * release them.
  *
  * Called with the journal locked.
  * Called with j_list_lock held.
@@ -663,8 +667,8 @@ out:
  * checkpoint lists.
  *
  * The function returns 1 if it frees the transaction, 0 otherwise.
+ * The function can free jh and bh.
  *
- * This function is called with the journal locked.
  * This function is called with j_list_lock held.
  * This function is called with jbd_lock_bh_state(jh2bh(jh))
  */
@@ -684,13 +688,14 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 	}
 	journal = transaction->t_journal;
 
+	JBUFFER_TRACE(jh, "removing from transaction");
 	__buffer_unlink(jh);
 	jh->b_cp_transaction = NULL;
+	jbd2_journal_put_journal_head(jh);
 
 	if (transaction->t_checkpoint_list != NULL ||
 	    transaction->t_checkpoint_io_list != NULL)
 		goto out;
-	JBUFFER_TRACE(jh, "transaction has no more buffers");
 
 	/*
 	 * There is one special case to worry about: if we have just pulled the
@@ -701,10 +706,8 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 	 * The locking here around t_state is a bit sleazy.
 	 * See the comment at the end of jbd2_journal_commit_transaction().
 	 */
-	if (transaction->t_state != T_FINISHED) {
-		JBUFFER_TRACE(jh, "belongs to running/committing transaction");
+	if (transaction->t_state != T_FINISHED)
 		goto out;
-	}
 
 	/* OK, that was the last buffer for the transaction: we can now
 	   safely remove this transaction from the log */
@@ -723,7 +726,6 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 	wake_up(&journal->j_wait_logspace);
 	ret = 1;
 out:
-	JBUFFER_TRACE(jh, "exit");
 	return ret;
 }
 
@@ -742,6 +744,8 @@ void __jbd2_journal_insert_checkpoint(struct journal_head *jh,
 	J_ASSERT_JH(jh, buffer_dirty(jh2bh(jh)) || buffer_jbddirty(jh2bh(jh)));
 	J_ASSERT_JH(jh, jh->b_cp_transaction == NULL);
 
+	/* Get reference for checkpointing transaction */
+	jbd2_journal_grab_journal_head(jh2bh(jh));
 	jh->b_cp_transaction = transaction;
 
 	if (!transaction->t_checkpoint_list) {
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 7f21cf3aaf92..eef6979821a4 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -848,10 +848,16 @@ restart_loop:
 	while (commit_transaction->t_forget) {
 		transaction_t *cp_transaction;
 		struct buffer_head *bh;
+		int try_to_free = 0;
 
 		jh = commit_transaction->t_forget;
 		spin_unlock(&journal->j_list_lock);
 		bh = jh2bh(jh);
+		/*
+		 * Get a reference so that bh cannot be freed before we are
+		 * done with it.
+		 */
+		get_bh(bh);
 		jbd_lock_bh_state(bh);
 		J_ASSERT_JH(jh,	jh->b_transaction == commit_transaction);
 
@@ -914,28 +920,27 @@ restart_loop:
 			__jbd2_journal_insert_checkpoint(jh, commit_transaction);
 			if (is_journal_aborted(journal))
 				clear_buffer_jbddirty(bh);
-			JBUFFER_TRACE(jh, "refile for checkpoint writeback");
-			__jbd2_journal_refile_buffer(jh);
-			jbd_unlock_bh_state(bh);
 		} else {
 			J_ASSERT_BH(bh, !buffer_dirty(bh));
-			/* The buffer on BJ_Forget list and not jbddirty means
+			/*
+			 * The buffer on BJ_Forget list and not jbddirty means
 			 * it has been freed by this transaction and hence it
 			 * could not have been reallocated until this
 			 * transaction has committed. *BUT* it could be
 			 * reallocated once we have written all the data to
 			 * disk and before we process the buffer on BJ_Forget
-			 * list. */
-			JBUFFER_TRACE(jh, "refile or unfile freed buffer");
-			__jbd2_journal_refile_buffer(jh);
-			if (!jh->b_transaction) {
-				jbd_unlock_bh_state(bh);
-				 /* needs a brelse */
-				jbd2_journal_remove_journal_head(bh);
-				release_buffer_page(bh);
-			} else
-				jbd_unlock_bh_state(bh);
+			 * list.
+			 */
+			if (!jh->b_next_transaction)
+				try_to_free = 1;
 		}
+		JBUFFER_TRACE(jh, "refile or unfile buffer");
+		__jbd2_journal_refile_buffer(jh);
+		jbd_unlock_bh_state(bh);
+		if (try_to_free)
+			release_buffer_page(bh);	/* Drops bh reference */
+		else
+			__brelse(bh);
 		cond_resched_lock(&journal->j_list_lock);
 	}
 	spin_unlock(&journal->j_list_lock);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 9a7826990304..0dfa5b598e68 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -2078,10 +2078,9 @@ static void journal_free_journal_head(struct journal_head *jh)
  * When a buffer has its BH_JBD bit set it is immune from being released by
  * core kernel code, mainly via ->b_count.
  *
- * A journal_head may be detached from its buffer_head when the journal_head's
- * b_transaction, b_cp_transaction and b_next_transaction pointers are NULL.
- * Various places in JBD call jbd2_journal_remove_journal_head() to indicate that the
- * journal_head can be dropped if needed.
+ * A journal_head is detached from its buffer_head when the journal_head's
+ * b_jcount reaches zero. Running transaction (b_transaction) and checkpoint
+ * transaction (b_cp_transaction) hold their references to b_jcount.
  *
  * Various places in the kernel want to attach a journal_head to a buffer_head
  * _before_ attaching the journal_head to a transaction.  To protect the
@@ -2094,17 +2093,16 @@ static void journal_free_journal_head(struct journal_head *jh)
  *	(Attach a journal_head if needed.  Increments b_jcount)
  *	struct journal_head *jh = jbd2_journal_add_journal_head(bh);
  *	...
+ *      (Get another reference for transaction)
+ *	jbd2_journal_grab_journal_head(bh);
  *	jh->b_transaction = xxx;
+ *	(Put original reference)
  *	jbd2_journal_put_journal_head(jh);
- *
- * Now, the journal_head's b_jcount is zero, but it is safe from being released
- * because it has a non-zero b_transaction.
  */
 
 /*
  * Give a buffer_head a journal_head.
  *
- * Doesn't need the journal lock.
  * May sleep.
  */
 struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh)
@@ -2168,61 +2166,29 @@ static void __journal_remove_journal_head(struct buffer_head *bh)
 	struct journal_head *jh = bh2jh(bh);
 
 	J_ASSERT_JH(jh, jh->b_jcount >= 0);
-
-	get_bh(bh);
-	if (jh->b_jcount == 0) {
-		if (jh->b_transaction == NULL &&
-				jh->b_next_transaction == NULL &&
-				jh->b_cp_transaction == NULL) {
-			J_ASSERT_JH(jh, jh->b_jlist == BJ_None);
-			J_ASSERT_BH(bh, buffer_jbd(bh));
-			J_ASSERT_BH(bh, jh2bh(jh) == bh);
-			BUFFER_TRACE(bh, "remove journal_head");
-			if (jh->b_frozen_data) {
-				printk(KERN_WARNING "%s: freeing "
-						"b_frozen_data\n",
-						__func__);
-				jbd2_free(jh->b_frozen_data, bh->b_size);
-			}
-			if (jh->b_committed_data) {
-				printk(KERN_WARNING "%s: freeing "
-						"b_committed_data\n",
-						__func__);
-				jbd2_free(jh->b_committed_data, bh->b_size);
-			}
-			bh->b_private = NULL;
-			jh->b_bh = NULL;	/* debug, really */
-			clear_buffer_jbd(bh);
-			__brelse(bh);
-			journal_free_journal_head(jh);
-		} else {
-			BUFFER_TRACE(bh, "journal_head was locked");
-		}
+	J_ASSERT_JH(jh, jh->b_transaction == NULL);
+	J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
+	J_ASSERT_JH(jh, jh->b_cp_transaction == NULL);
+	J_ASSERT_JH(jh, jh->b_jlist == BJ_None);
+	J_ASSERT_BH(bh, buffer_jbd(bh));
+	J_ASSERT_BH(bh, jh2bh(jh) == bh);
+	BUFFER_TRACE(bh, "remove journal_head");
+	if (jh->b_frozen_data) {
+		printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__);
+		jbd2_free(jh->b_frozen_data, bh->b_size);
 	}
+	if (jh->b_committed_data) {
+		printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__);
+		jbd2_free(jh->b_committed_data, bh->b_size);
+	}
+	bh->b_private = NULL;
+	jh->b_bh = NULL;	/* debug, really */
+	clear_buffer_jbd(bh);
+	journal_free_journal_head(jh);
 }
 
 /*
- * jbd2_journal_remove_journal_head(): if the buffer isn't attached to a transaction
- * and has a zero b_jcount then remove and release its journal_head.   If we did
- * see that the buffer is not used by any transaction we also "logically"
- * decrement ->b_count.
- *
- * We in fact take an additional increment on ->b_count as a convenience,
- * because the caller usually wants to do additional things with the bh
- * after calling here.
- * The caller of jbd2_journal_remove_journal_head() *must* run __brelse(bh) at some
- * time.  Once the caller has run __brelse(), the buffer is eligible for
- * reaping by try_to_free_buffers().
- */
-void jbd2_journal_remove_journal_head(struct buffer_head *bh)
-{
-	jbd_lock_bh_journal_head(bh);
-	__journal_remove_journal_head(bh);
-	jbd_unlock_bh_journal_head(bh);
-}
-
-/*
- * Drop a reference on the passed journal_head.  If it fell to zero then try to
+ * Drop a reference on the passed journal_head.  If it fell to zero then
  * release the journal_head from the buffer_head.
  */
 void jbd2_journal_put_journal_head(struct journal_head *jh)
@@ -2232,11 +2198,12 @@ void jbd2_journal_put_journal_head(struct journal_head *jh)
 	jbd_lock_bh_journal_head(bh);
 	J_ASSERT_JH(jh, jh->b_jcount > 0);
 	--jh->b_jcount;
-	if (!jh->b_jcount && !jh->b_transaction) {
+	if (!jh->b_jcount) {
 		__journal_remove_journal_head(bh);
+		jbd_unlock_bh_journal_head(bh);
 		__brelse(bh);
-	}
-	jbd_unlock_bh_journal_head(bh);
+	} else
+		jbd_unlock_bh_journal_head(bh);
 }
 
 /*
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 3eec82d32fd4..2d7109414cdd 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -30,6 +30,7 @@
 #include <linux/module.h>
 
 static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh);
+static void __jbd2_journal_unfile_buffer(struct journal_head *jh);
 
 /*
  * jbd2_get_transaction: obtain a new transaction_t object.
@@ -764,7 +765,6 @@ repeat:
 	if (!jh->b_transaction) {
 		JBUFFER_TRACE(jh, "no transaction");
 		J_ASSERT_JH(jh, !jh->b_next_transaction);
-		jh->b_transaction = transaction;
 		JBUFFER_TRACE(jh, "file as BJ_Reserved");
 		spin_lock(&journal->j_list_lock);
 		__jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
@@ -814,7 +814,6 @@ out:
  * int jbd2_journal_get_write_access() - notify intent to modify a buffer for metadata (not data) update.
  * @handle: transaction to add buffer modifications to
  * @bh:     bh to be used for metadata writes
- * @credits: variable that will receive credits for the buffer
  *
  * Returns an error code or 0 on success.
  *
@@ -896,8 +895,6 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
 		 * committed and so it's safe to clear the dirty bit.
 		 */
 		clear_buffer_dirty(jh2bh(jh));
-		jh->b_transaction = transaction;
-
 		/* first access by this transaction */
 		jh->b_modified = 0;
 
@@ -932,7 +929,6 @@ out:
  *     non-rewindable consequences
  * @handle: transaction
  * @bh: buffer to undo
- * @credits: store the number of taken credits here (if not NULL)
  *
  * Sometimes there is a need to distinguish between metadata which has
  * been committed to disk and that which has not.  The ext3fs code uses
@@ -1232,8 +1228,6 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 			__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
 		} else {
 			__jbd2_journal_unfile_buffer(jh);
-			jbd2_journal_remove_journal_head(bh);
-			__brelse(bh);
 			if (!buffer_jbd(bh)) {
 				spin_unlock(&journal->j_list_lock);
 				jbd_unlock_bh_state(bh);
@@ -1556,19 +1550,32 @@ void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
 		mark_buffer_dirty(bh);	/* Expose it to the VM */
 }
 
-void __jbd2_journal_unfile_buffer(struct journal_head *jh)
+/*
+ * Remove buffer from all transactions.
+ *
+ * Called with bh_state lock and j_list_lock
+ *
+ * jh and bh may be already freed when this function returns.
+ */
+static void __jbd2_journal_unfile_buffer(struct journal_head *jh)
 {
 	__jbd2_journal_temp_unlink_buffer(jh);
 	jh->b_transaction = NULL;
+	jbd2_journal_put_journal_head(jh);
 }
 
 void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh)
 {
-	jbd_lock_bh_state(jh2bh(jh));
+	struct buffer_head *bh = jh2bh(jh);
+
+	/* Get reference so that buffer cannot be freed before we unlock it */
+	get_bh(bh);
+	jbd_lock_bh_state(bh);
 	spin_lock(&journal->j_list_lock);
 	__jbd2_journal_unfile_buffer(jh);
 	spin_unlock(&journal->j_list_lock);
-	jbd_unlock_bh_state(jh2bh(jh));
+	jbd_unlock_bh_state(bh);
+	__brelse(bh);
 }
 
 /*
@@ -1595,8 +1602,6 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
 		if (jh->b_jlist == BJ_None) {
 			JBUFFER_TRACE(jh, "remove from checkpoint list");
 			__jbd2_journal_remove_checkpoint(jh);
-			jbd2_journal_remove_journal_head(bh);
-			__brelse(bh);
 		}
 	}
 	spin_unlock(&journal->j_list_lock);
@@ -1659,7 +1664,6 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal,
 		/*
 		 * We take our own ref against the journal_head here to avoid
 		 * having to add tons of locking around each instance of
-		 * jbd2_journal_remove_journal_head() and
 		 * jbd2_journal_put_journal_head().
 		 */
 		jh = jbd2_journal_grab_journal_head(bh);
@@ -1697,10 +1701,9 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
 	int may_free = 1;
 	struct buffer_head *bh = jh2bh(jh);
 
-	__jbd2_journal_unfile_buffer(jh);
-
 	if (jh->b_cp_transaction) {
 		JBUFFER_TRACE(jh, "on running+cp transaction");
+		__jbd2_journal_temp_unlink_buffer(jh);
 		/*
 		 * We don't want to write the buffer anymore, clear the
 		 * bit so that we don't confuse checks in
@@ -1711,8 +1714,7 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
 		may_free = 0;
 	} else {
 		JBUFFER_TRACE(jh, "on running transaction");
-		jbd2_journal_remove_journal_head(bh);
-		__brelse(bh);
+		__jbd2_journal_unfile_buffer(jh);
 	}
 	return may_free;
 }
@@ -1990,6 +1992,8 @@ void __jbd2_journal_file_buffer(struct journal_head *jh,
 
 	if (jh->b_transaction)
 		__jbd2_journal_temp_unlink_buffer(jh);
+	else
+		jbd2_journal_grab_journal_head(bh);
 	jh->b_transaction = transaction;
 
 	switch (jlist) {
@@ -2041,9 +2045,10 @@ void jbd2_journal_file_buffer(struct journal_head *jh,
  * already started to be used by a subsequent transaction, refile the
  * buffer on that transaction's metadata list.
  *
- * Called under journal->j_list_lock
- *
+ * Called under j_list_lock
  * Called under jbd_lock_bh_state(jh2bh(jh))
+ *
+ * jh and bh may be already free when this function returns
  */
 void __jbd2_journal_refile_buffer(struct journal_head *jh)
 {
@@ -2067,6 +2072,11 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh)
 
 	was_dirty = test_clear_buffer_jbddirty(bh);
 	__jbd2_journal_temp_unlink_buffer(jh);
+	/*
+	 * We set b_transaction here because b_next_transaction will inherit
+	 * our jh reference and thus __jbd2_journal_file_buffer() must not
+	 * take a new one.
+	 */
 	jh->b_transaction = jh->b_next_transaction;
 	jh->b_next_transaction = NULL;
 	if (buffer_freed(bh))
@@ -2083,30 +2093,21 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh)
 }
 
 /*
- * For the unlocked version of this call, also make sure that any
- * hanging journal_head is cleaned up if necessary.
- *
- * __jbd2_journal_refile_buffer is usually called as part of a single locked
- * operation on a buffer_head, in which the caller is probably going to
- * be hooking the journal_head onto other lists.  In that case it is up
- * to the caller to remove the journal_head if necessary.  For the
- * unlocked jbd2_journal_refile_buffer call, the caller isn't going to be
- * doing anything else to the buffer so we need to do the cleanup
- * ourselves to avoid a jh leak.
- *
- * *** The journal_head may be freed by this call! ***
+ * __jbd2_journal_refile_buffer() with necessary locking added. We take our
+ * bh reference so that we can safely unlock bh.
+ *
+ * The jh and bh may be freed by this call.
  */
 void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh)
 {
 	struct buffer_head *bh = jh2bh(jh);
 
+	/* Get reference so that buffer cannot be freed before we unlock it */
+	get_bh(bh);
 	jbd_lock_bh_state(bh);
 	spin_lock(&journal->j_list_lock);
-
 	__jbd2_journal_refile_buffer(jh);
 	jbd_unlock_bh_state(bh);
-	jbd2_journal_remove_journal_head(bh);
-
 	spin_unlock(&journal->j_list_lock);
 	__brelse(bh);
 }
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 05f73328b28b..4bca6a2e5c07 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -75,7 +75,6 @@ static struct dentry *jffs2_lookup(struct inode *dir_i, struct dentry *target,
 				   struct nameidata *nd)
 {
 	struct jffs2_inode_info *dir_f;
-	struct jffs2_sb_info *c;
 	struct jffs2_full_dirent *fd = NULL, *fd_list;
 	uint32_t ino = 0;
 	struct inode *inode = NULL;
@@ -86,7 +85,6 @@ static struct dentry *jffs2_lookup(struct inode *dir_i, struct dentry *target,
 		return ERR_PTR(-ENAMETOOLONG);
 
 	dir_f = JFFS2_INODE_INFO(dir_i);
-	c = JFFS2_SB_INFO(dir_i->i_sb);
 
 	mutex_lock(&dir_f->sem);
 
@@ -119,7 +117,6 @@ static struct dentry *jffs2_lookup(struct inode *dir_i, struct dentry *target,
 static int jffs2_readdir(struct file *filp, void *dirent, filldir_t filldir)
 {
 	struct jffs2_inode_info *f;
-	struct jffs2_sb_info *c;
 	struct inode *inode = filp->f_path.dentry->d_inode;
 	struct jffs2_full_dirent *fd;
 	unsigned long offset, curofs;
@@ -127,7 +124,6 @@ static int jffs2_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	D1(printk(KERN_DEBUG "jffs2_readdir() for dir_i #%lu\n", filp->f_path.dentry->d_inode->i_ino));
 
 	f = JFFS2_INODE_INFO(inode);
-	c = JFFS2_SB_INFO(inode->i_sb);
 
 	offset = filp->f_pos;
 
@@ -609,8 +605,6 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry)
 	int ret;
 	uint32_t now = get_seconds();
 
-	dentry_unhash(dentry);
-
 	for (fd = f->dents ; fd; fd = fd->next) {
 		if (fd->ino)
 			return -ENOTEMPTY;
@@ -786,9 +780,6 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 	uint8_t type;
 	uint32_t now;
 
-	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	/* The VFS will check for us and prevent trying to rename a
 	 * file over a directory and vice versa, but if it's a directory,
 	 * the VFS can't check whether the victim is empty. The filesystem
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index e896e67767eb..46ad619b6124 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -357,7 +357,7 @@ error:
 	return ERR_PTR(ret);
 }
 
-void jffs2_dirty_inode(struct inode *inode)
+void jffs2_dirty_inode(struct inode *inode, int flags)
 {
 	struct iattr iattr;
 
diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h
index 00bae7cc2e48..65c6c43ca482 100644
--- a/fs/jffs2/os-linux.h
+++ b/fs/jffs2/os-linux.h
@@ -172,7 +172,7 @@ int jffs2_setattr (struct dentry *, struct iattr *);
 int jffs2_do_setattr (struct inode *, struct iattr *);
 struct inode *jffs2_iget(struct super_block *, unsigned long);
 void jffs2_evict_inode (struct inode *);
-void jffs2_dirty_inode(struct inode *inode);
+void jffs2_dirty_inode(struct inode *inode, int flags);
 struct inode *jffs2_new_inode (struct inode *dir_i, int mode,
 			       struct jffs2_raw_inode *ri);
 int jffs2_statfs (struct dentry *, struct kstatfs *);
diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c
index b632dddcb482..8d8cd3419d02 100644
--- a/fs/jffs2/scan.c
+++ b/fs/jffs2/scan.c
@@ -94,7 +94,7 @@ int jffs2_scan_medium(struct jffs2_sb_info *c)
 	uint32_t buf_size = 0;
 	struct jffs2_summary *s = NULL; /* summary info collected by the scan process */
 #ifndef __ECOS
-	size_t pointlen;
+	size_t pointlen, try_size;
 
 	if (c->mtd->point) {
 		ret = c->mtd->point(c->mtd, 0, c->mtd->size, &pointlen,
@@ -113,18 +113,21 @@ int jffs2_scan_medium(struct jffs2_sb_info *c)
 		/* For NAND it's quicker to read a whole eraseblock at a time,
 		   apparently */
 		if (jffs2_cleanmarker_oob(c))
-			buf_size = c->sector_size;
+			try_size = c->sector_size;
 		else
-			buf_size = PAGE_SIZE;
+			try_size = PAGE_SIZE;
 
-		/* Respect kmalloc limitations */
-		if (buf_size > 128*1024)
-			buf_size = 128*1024;
+		D1(printk(KERN_DEBUG "Trying to allocate readbuf of %zu "
+			"bytes\n", try_size));
 
-		D1(printk(KERN_DEBUG "Allocating readbuf of %d bytes\n", buf_size));
-		flashbuf = kmalloc(buf_size, GFP_KERNEL);
+		flashbuf = mtd_kmalloc_up_to(c->mtd, &try_size);
 		if (!flashbuf)
 			return -ENOMEM;
+
+		D1(printk(KERN_DEBUG "Allocated readbuf of %zu bytes\n",
+			try_size));
+
+		buf_size = (uint32_t)try_size;
 	}
 
 	if (jffs2_sum_active()) {
diff --git a/fs/jfs/file.c b/fs/jfs/file.c
index c5ce6c1d1ff4..2f3f531f3606 100644
--- a/fs/jfs/file.c
+++ b/fs/jfs/file.c
@@ -66,9 +66,9 @@ static int jfs_open(struct inode *inode, struct file *file)
 		struct jfs_inode_info *ji = JFS_IP(inode);
 		spin_lock_irq(&ji->ag_lock);
 		if (ji->active_ag == -1) {
-			ji->active_ag = ji->agno;
-			atomic_inc(
-			    &JFS_SBI(inode->i_sb)->bmap->db_active[ji->agno]);
+			struct jfs_sb_info *jfs_sb = JFS_SBI(inode->i_sb);
+			ji->active_ag = BLKTOAG(addressPXD(&ji->ixpxd), jfs_sb);
+			atomic_inc( &jfs_sb->bmap->db_active[ji->active_ag]);
 		}
 		spin_unlock_irq(&ji->ag_lock);
 	}
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index eddbb373209e..109655904bbc 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -173,7 +173,7 @@ void jfs_evict_inode(struct inode *inode)
 	dquot_drop(inode);
 }
 
-void jfs_dirty_inode(struct inode *inode)
+void jfs_dirty_inode(struct inode *inode, int flags)
 {
 	static int noisy = 5;
 
diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
index ed53a4740168..b78b2f978f04 100644
--- a/fs/jfs/jfs_imap.c
+++ b/fs/jfs/jfs_imap.c
@@ -397,7 +397,7 @@ int diRead(struct inode *ip)
 	release_metapage(mp);
 
 	/* set the ag for the inode */
-	JFS_IP(ip)->agno = BLKTOAG(agstart, sbi);
+	JFS_IP(ip)->agstart = agstart;
 	JFS_IP(ip)->active_ag = -1;
 
 	return (rc);
@@ -901,7 +901,7 @@ int diFree(struct inode *ip)
 
 	/* get the allocation group for this ino.
 	 */
-	agno = JFS_IP(ip)->agno;
+	agno = BLKTOAG(JFS_IP(ip)->agstart, JFS_SBI(ip->i_sb));
 
 	/* Lock the AG specific inode map information
 	 */
@@ -1315,12 +1315,11 @@ int diFree(struct inode *ip)
 static inline void
 diInitInode(struct inode *ip, int iagno, int ino, int extno, struct iag * iagp)
 {
-	struct jfs_sb_info *sbi = JFS_SBI(ip->i_sb);
 	struct jfs_inode_info *jfs_ip = JFS_IP(ip);
 
 	ip->i_ino = (iagno << L2INOSPERIAG) + ino;
 	jfs_ip->ixpxd = iagp->inoext[extno];
-	jfs_ip->agno = BLKTOAG(le64_to_cpu(iagp->agstart), sbi);
+	jfs_ip->agstart = le64_to_cpu(iagp->agstart);
 	jfs_ip->active_ag = -1;
 }
 
@@ -1379,7 +1378,7 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip)
 	 */
 
 	/* get the ag number of this iag */
-	agno = JFS_IP(pip)->agno;
+	agno = BLKTOAG(JFS_IP(pip)->agstart, JFS_SBI(pip->i_sb));
 
 	if (atomic_read(&JFS_SBI(pip->i_sb)->bmap->db_active[agno])) {
 		/*
@@ -2921,10 +2920,9 @@ int diExtendFS(struct inode *ipimap, struct inode *ipbmap)
 			continue;
 		}
 
-		/* agstart that computes to the same ag is treated as same; */
 		agstart = le64_to_cpu(iagp->agstart);
-		/* iagp->agstart = agstart & ~(mp->db_agsize - 1); */
 		n = agstart >> mp->db_agl2size;
+		iagp->agstart = cpu_to_le64((s64)n << mp->db_agl2size);
 
 		/* compute backed inodes */
 		numinos = (EXTSPERIAG - le32_to_cpu(iagp->nfreeexts))
diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h
index 1439f119ec83..584a4a1a6e81 100644
--- a/fs/jfs/jfs_incore.h
+++ b/fs/jfs/jfs_incore.h
@@ -50,8 +50,9 @@ struct jfs_inode_info {
 	short	btindex;	/* btpage entry index*/
 	struct inode *ipimap;	/* inode map			*/
 	unsigned long cflag;	/* commit flags		*/
+	u64	agstart;	/* agstart of the containing IAG */
 	u16	bxflag;		/* xflag of pseudo buffer?	*/
-	unchar	agno;		/* ag number			*/
+	unchar	pad;
 	signed char active_ag;	/* ag currently allocating from	*/
 	lid_t	blid;		/* lid of pseudo buffer?	*/
 	lid_t	atlhead;	/* anonymous tlock list head	*/
diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h
index 155e91eff07d..ec2fb8b945fc 100644
--- a/fs/jfs/jfs_inode.h
+++ b/fs/jfs/jfs_inode.h
@@ -28,7 +28,7 @@ extern struct inode *jfs_iget(struct super_block *, unsigned long);
 extern int jfs_commit_inode(struct inode *, int);
 extern int jfs_write_inode(struct inode *, struct writeback_control *);
 extern void jfs_evict_inode(struct inode *);
-extern void jfs_dirty_inode(struct inode *);
+extern void jfs_dirty_inode(struct inode *, int);
 extern void jfs_truncate(struct inode *);
 extern void jfs_truncate_nolock(struct inode *, loff_t);
 extern void jfs_free_zero_link(struct inode *);
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 278e3fb40b71..583636f745e5 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1123,7 +1123,7 @@ int lmLogOpen(struct super_block *sb)
 	bdev = blkdev_get_by_dev(sbi->logdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
 				 log);
 	if (IS_ERR(bdev)) {
-		rc = -PTR_ERR(bdev);
+		rc = PTR_ERR(bdev);
 		goto free;
 	}
 
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 865df16a6cf3..eaaf2b511e89 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -360,8 +360,6 @@ static int jfs_rmdir(struct inode *dip, struct dentry *dentry)
 
 	jfs_info("jfs_rmdir: dip:0x%p name:%s", dip, dentry->d_name.name);
 
-	dentry_unhash(dentry);
-
 	/* Init inode for quota operations. */
 	dquot_initialize(dip);
 	dquot_initialize(ip);
@@ -1097,9 +1095,6 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	jfs_info("jfs_rename: %s %s", old_dentry->d_name.name,
 		 new_dentry->d_name.name);
 
-	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	dquot_initialize(old_dir);
 	dquot_initialize(new_dir);
 
diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c
index 8ea5efb5a34e..8d0c1c7c0820 100644
--- a/fs/jfs/resize.c
+++ b/fs/jfs/resize.c
@@ -80,7 +80,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize)
 	int log_formatted = 0;
 	struct inode *iplist[1];
 	struct jfs_superblock *j_sb, *j_sb2;
-	uint old_agsize;
+	s64 old_agsize;
 	int agsizechanged = 0;
 	struct buffer_head *bh, *bh2;
 
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index adb45ec9038c..e374050a911c 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -708,7 +708,13 @@ static void nlmclnt_unlock_callback(struct rpc_task *task, void *data)
 
 	if (task->tk_status < 0) {
 		dprintk("lockd: unlock failed (err = %d)\n", -task->tk_status);
-		goto retry_rebind;
+		switch (task->tk_status) {
+		case -EACCES:
+		case -EIO:
+			goto die;
+		default:
+			goto retry_rebind;
+		}
 	}
 	if (status == NLM_LCK_DENIED_GRACE_PERIOD) {
 		rpc_delay(task, NLMCLNT_GRACE_WAIT);
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index f34c9cde9e94..1afae26cf236 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -273,8 +273,6 @@ static int logfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = dentry->d_inode;
 
-	dentry_unhash(dentry);
-
 	if (!logfs_empty_dir(inode))
 		return -ENOTEMPTY;
 
@@ -557,13 +555,6 @@ static int logfs_symlink(struct inode *dir, struct dentry *dentry,
 	return __logfs_create(dir, dentry, inode, target, destlen);
 }
 
-static int logfs_permission(struct inode *inode, int mask, unsigned int flags)
-{
-	if (flags & IPERM_FLAG_RCU)
-		return -ECHILD;
-	return generic_permission(inode, mask, flags, NULL);
-}
-
 static int logfs_link(struct dentry *old_dentry, struct inode *dir,
 		struct dentry *dentry)
 {
@@ -624,9 +615,6 @@ static int logfs_rename_cross(struct inode *old_dir, struct dentry *old_dentry,
 	loff_t pos;
 	int err;
 
-	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	/* 1. locate source dd */
 	err = logfs_get_dd(old_dir, old_dentry, &dd, &pos);
 	if (err)
@@ -825,7 +813,6 @@ const struct inode_operations logfs_dir_iops = {
 	.mknod		= logfs_mknod,
 	.rename		= logfs_rename,
 	.rmdir		= logfs_rmdir,
-	.permission	= logfs_permission,
 	.symlink	= logfs_symlink,
 	.unlink		= logfs_unlink,
 };
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index f60aed8db9c4..6e6777f1b4b2 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -168,8 +168,6 @@ static int minix_rmdir(struct inode * dir, struct dentry *dentry)
 	struct inode * inode = dentry->d_inode;
 	int err = -ENOTEMPTY;
 
-	dentry_unhash(dentry);
-
 	if (minix_empty_dir(inode)) {
 		err = minix_unlink(dir, dentry);
 		if (!err) {
@@ -192,9 +190,6 @@ static int minix_rename(struct inode * old_dir, struct dentry *old_dentry,
 	struct minix_dir_entry * old_de;
 	int err = -ENOENT;
 
-	if (new_inode && S_ISDIR(new_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	old_de = minix_find_entry(old_dentry, &old_page);
 	if (!old_de)
 		goto out;
diff --git a/fs/namei.c b/fs/namei.c
index 2358b326b221..0223c41fb114 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -238,7 +238,8 @@ int generic_permission(struct inode *inode, int mask, unsigned int flags,
 
 	/*
 	 * Read/write DACs are always overridable.
-	 * Executable DACs are overridable if at least one exec bit is set.
+	 * Executable DACs are overridable for all directories and
+	 * for non-directories that have least one exec bit set.
 	 */
 	if (!(mask & MAY_EXEC) || execute_ok(inode))
 		if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE))
@@ -812,6 +813,11 @@ static int follow_automount(struct path *path, unsigned flags,
 	if (!mnt) /* mount collision */
 		return 0;
 
+	if (!*need_mntput) {
+		/* lock_mount() may release path->mnt on error */
+		mntget(path->mnt);
+		*need_mntput = true;
+	}
 	err = finish_automount(mnt, path);
 
 	switch (err) {
@@ -819,12 +825,9 @@ static int follow_automount(struct path *path, unsigned flags,
 		/* Someone else made a mount here whilst we were busy */
 		return 0;
 	case 0:
-		dput(path->dentry);
-		if (*need_mntput)
-			mntput(path->mnt);
+		path_put(path);
 		path->mnt = mnt;
 		path->dentry = dget(mnt->mnt_root);
-		*need_mntput = true;
 		return 0;
 	default:
 		return err;
@@ -844,9 +847,10 @@ static int follow_automount(struct path *path, unsigned flags,
  */
 static int follow_managed(struct path *path, unsigned flags)
 {
+	struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */
 	unsigned managed;
 	bool need_mntput = false;
-	int ret;
+	int ret = 0;
 
 	/* Given that we're not holding a lock here, we retain the value in a
 	 * local variable for each dentry as we look at it so that we don't see
@@ -861,7 +865,7 @@ static int follow_managed(struct path *path, unsigned flags)
 			BUG_ON(!path->dentry->d_op->d_manage);
 			ret = path->dentry->d_op->d_manage(path->dentry, false);
 			if (ret < 0)
-				return ret == -EISDIR ? 0 : ret;
+				break;
 		}
 
 		/* Transit to a mounted filesystem. */
@@ -887,14 +891,19 @@ static int follow_managed(struct path *path, unsigned flags)
 		if (managed & DCACHE_NEED_AUTOMOUNT) {
 			ret = follow_automount(path, flags, &need_mntput);
 			if (ret < 0)
-				return ret == -EISDIR ? 0 : ret;
+				break;
 			continue;
 		}
 
 		/* We didn't change the current path point */
 		break;
 	}
-	return 0;
+
+	if (need_mntput && path->mnt == mnt)
+		mntput(path->mnt);
+	if (ret == -EISDIR)
+		ret = 0;
+	return ret;
 }
 
 int follow_down_one(struct path *path)
@@ -919,12 +928,11 @@ static inline bool managed_dentry_might_block(struct dentry *dentry)
 }
 
 /*
- * Skip to top of mountpoint pile in rcuwalk mode.  We abort the rcu-walk if we
- * meet a managed dentry and we're not walking to "..".  True is returned to
- * continue, false to abort.
+ * Try to skip to top of mountpoint pile in rcuwalk mode.  Fail if
+ * we meet a managed dentry that would need blocking.
  */
 static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
-			       struct inode **inode, bool reverse_transit)
+			       struct inode **inode)
 {
 	for (;;) {
 		struct vfsmount *mounted;
@@ -933,8 +941,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 		 * that wants to block transit.
 		 */
 		*inode = path->dentry->d_inode;
-		if (!reverse_transit &&
-		     unlikely(managed_dentry_might_block(path->dentry)))
+		if (unlikely(managed_dentry_might_block(path->dentry)))
 			return false;
 
 		if (!d_mountpoint(path->dentry))
@@ -947,16 +954,24 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 		path->dentry = mounted->mnt_root;
 		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
 	}
-
-	if (unlikely(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
-		return reverse_transit;
 	return true;
 }
 
-static int follow_dotdot_rcu(struct nameidata *nd)
+static void follow_mount_rcu(struct nameidata *nd)
 {
-	struct inode *inode = nd->inode;
+	while (d_mountpoint(nd->path.dentry)) {
+		struct vfsmount *mounted;
+		mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry, 1);
+		if (!mounted)
+			break;
+		nd->path.mnt = mounted;
+		nd->path.dentry = mounted->mnt_root;
+		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
+	}
+}
 
+static int follow_dotdot_rcu(struct nameidata *nd)
+{
 	set_root_rcu(nd);
 
 	while (1) {
@@ -972,7 +987,6 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 			seq = read_seqcount_begin(&parent->d_seq);
 			if (read_seqcount_retry(&old->d_seq, nd->seq))
 				goto failed;
-			inode = parent->d_inode;
 			nd->path.dentry = parent;
 			nd->seq = seq;
 			break;
@@ -980,10 +994,9 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 		if (!follow_up_rcu(&nd->path))
 			break;
 		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
-		inode = nd->path.dentry->d_inode;
 	}
-	__follow_mount_rcu(nd, &nd->path, &inode, true);
-	nd->inode = inode;
+	follow_mount_rcu(nd);
+	nd->inode = nd->path.dentry->d_inode;
 	return 0;
 
 failed:
@@ -999,9 +1012,6 @@ failed:
  * Follow down to the covering mount currently visible to userspace.  At each
  * point, the filesystem owning that dentry may be queried as to whether the
  * caller is permitted to proceed or not.
- *
- * Care must be taken as namespace_sem may be held (indicated by mounting_here
- * being true).
  */
 int follow_down(struct path *path)
 {
@@ -1157,8 +1167,11 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
 		}
 		path->mnt = mnt;
 		path->dentry = dentry;
-		if (likely(__follow_mount_rcu(nd, path, inode, false)))
-			return 0;
+		if (unlikely(!__follow_mount_rcu(nd, path, inode)))
+			goto unlazy;
+		if (unlikely(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
+			goto unlazy;
+		return 0;
 unlazy:
 		if (unlazy_walk(nd, dentry))
 			return -ECHILD;
@@ -2572,6 +2585,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 	if (error)
 		goto out;
 
+	shrink_dcache_parent(dentry);
 	error = dir->i_op->rmdir(dir, dentry);
 	if (error)
 		goto out;
@@ -2616,6 +2630,10 @@ static long do_rmdir(int dfd, const char __user *pathname)
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto exit2;
+	if (!dentry->d_inode) {
+		error = -ENOENT;
+		goto exit3;
+	}
 	error = mnt_want_write(nd.path.mnt);
 	if (error)
 		goto exit3;
@@ -2704,8 +2722,9 @@ static long do_unlinkat(int dfd, const char __user *pathname)
 		if (nd.last.name[nd.last.len])
 			goto slashes;
 		inode = dentry->d_inode;
-		if (inode)
-			ihold(inode);
+		if (!inode)
+			goto slashes;
+		ihold(inode);
 		error = mnt_want_write(nd.path.mnt);
 		if (error)
 			goto exit2;
@@ -2986,6 +3005,8 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
 	if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry))
 		goto out;
 
+	if (target)
+		shrink_dcache_parent(new_dentry);
 	error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
 	if (error)
 		goto out;
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index e3e646b06404..9c51f621e901 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -1033,8 +1033,11 @@ static int ncp_rmdir(struct inode *dir, struct dentry *dentry)
 	DPRINTK("ncp_rmdir: removing %s/%s\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 
+	/*
+	 * fail with EBUSY if there are still references to this
+	 * directory.
+	 */
 	dentry_unhash(dentry);
-
 	error = -EBUSY;
 	if (!d_unhashed(dentry))
 		goto out;
@@ -1141,8 +1144,16 @@ static int ncp_rename(struct inode *old_dir, struct dentry *old_dentry,
 		old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
 		new_dentry->d_parent->d_name.name, new_dentry->d_name.name);
 
-	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
+	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode)) {
+		/*
+		 * fail with EBUSY if there are still references to this
+		 * directory.
+		 */
 		dentry_unhash(new_dentry);
+		error = -EBUSY;
+		if (!d_unhashed(new_dentry))
+			goto out;
+	}
 
 	ncp_age_dentry(server, old_dentry);
 	ncp_age_dentry(server, new_dentry);
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index ba306658a6db..81515545ba75 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -87,6 +87,16 @@ config NFS_V4_1
 config PNFS_FILE_LAYOUT
 	tristate
 
+config PNFS_OBJLAYOUT
+	tristate "Provide support for the pNFS Objects Layout Driver for NFSv4.1 pNFS (EXPERIMENTAL)"
+	depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD
+	help
+	  Say M here if you want your pNFS client to support the Objects Layout Driver.
+	  Requires the SCSI osd initiator library (SCSI_OSD_INITIATOR) and
+	  upper level driver (SCSI_OSD_ULD).
+
+	  If unsure, say N.
+
 config ROOT_NFS
 	bool "Root file system on NFS"
 	depends on NFS_FS=y && IP_PNP
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 4776ff9e3814..6a34f7dd0e6f 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -15,9 +15,11 @@ nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
 			   delegation.o idmap.o \
 			   callback.o callback_xdr.o callback_proc.o \
 			   nfs4namespace.o
-nfs-$(CONFIG_NFS_V4_1)	+= pnfs.o
+nfs-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
 nfs-$(CONFIG_SYSCTL) += sysctl.o
 nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
 nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o
+
+obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index 46d93ce7311b..b257383bb565 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -167,6 +167,23 @@ extern unsigned nfs4_callback_layoutrecall(
 
 extern void nfs4_check_drain_bc_complete(struct nfs4_session *ses);
 extern void nfs4_cb_take_slot(struct nfs_client *clp);
+
+struct cb_devicenotifyitem {
+	uint32_t		cbd_notify_type;
+	uint32_t		cbd_layout_type;
+	struct nfs4_deviceid	cbd_dev_id;
+	uint32_t		cbd_immediate;
+};
+
+struct cb_devicenotifyargs {
+	int				 ndevs;
+	struct cb_devicenotifyitem	 *devs;
+};
+
+extern __be32 nfs4_callback_devicenotify(
+	struct cb_devicenotifyargs *args,
+	void *dummy, struct cb_process_state *cps);
+
 #endif /* CONFIG_NFS_V4_1 */
 extern int check_gss_callback_principal(struct nfs_client *, struct svc_rqst *);
 extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 2f41dccea18e..d4d1954e9bb9 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -139,7 +139,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	spin_lock(&ino->i_lock);
 	if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
 	    mark_matching_lsegs_invalid(lo, &free_me_list,
-					args->cbl_range.iomode))
+					&args->cbl_range))
 		rv = NFS4ERR_DELAY;
 	else
 		rv = NFS4ERR_NOMATCHING_LAYOUT;
@@ -184,7 +184,7 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 		ino = lo->plh_inode;
 		spin_lock(&ino->i_lock);
 		set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
-		if (mark_matching_lsegs_invalid(lo, &free_me_list, range.iomode))
+		if (mark_matching_lsegs_invalid(lo, &free_me_list, &range))
 			rv = NFS4ERR_DELAY;
 		list_del_init(&lo->plh_bulk_recall);
 		spin_unlock(&ino->i_lock);
@@ -241,6 +241,53 @@ static void pnfs_recall_all_layouts(struct nfs_client *clp)
 	do_callback_layoutrecall(clp, &args);
 }
 
+__be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args,
+				  void *dummy, struct cb_process_state *cps)
+{
+	int i;
+	__be32 res = 0;
+	struct nfs_client *clp = cps->clp;
+	struct nfs_server *server = NULL;
+
+	dprintk("%s: -->\n", __func__);
+
+	if (!clp) {
+		res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
+		goto out;
+	}
+
+	for (i = 0; i < args->ndevs; i++) {
+		struct cb_devicenotifyitem *dev = &args->devs[i];
+
+		if (!server ||
+		    server->pnfs_curr_ld->id != dev->cbd_layout_type) {
+			rcu_read_lock();
+			list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
+				if (server->pnfs_curr_ld &&
+				    server->pnfs_curr_ld->id == dev->cbd_layout_type) {
+					rcu_read_unlock();
+					goto found;
+				}
+			rcu_read_unlock();
+			dprintk("%s: layout type %u not found\n",
+				__func__, dev->cbd_layout_type);
+			continue;
+		}
+
+	found:
+		if (dev->cbd_notify_type == NOTIFY_DEVICEID4_CHANGE)
+			dprintk("%s: NOTIFY_DEVICEID4_CHANGE not supported, "
+				"deleting instead\n", __func__);
+		nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id);
+	}
+
+out:
+	kfree(args->devs);
+	dprintk("%s: exit with status = %u\n",
+		__func__, be32_to_cpu(res));
+	return res;
+}
+
 int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, const nfs4_stateid *stateid)
 {
 	if (delegation == NULL)
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 00ecf62ce7c1..c6c86a77e043 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -25,6 +25,7 @@
 
 #if defined(CONFIG_NFS_V4_1)
 #define CB_OP_LAYOUTRECALL_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
+#define CB_OP_DEVICENOTIFY_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 #define CB_OP_SEQUENCE_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ + \
 					4 + 1 + 3)
 #define CB_OP_RECALLANY_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
@@ -284,6 +285,93 @@ out:
 	return status;
 }
 
+static
+__be32 decode_devicenotify_args(struct svc_rqst *rqstp,
+				struct xdr_stream *xdr,
+				struct cb_devicenotifyargs *args)
+{
+	__be32 *p;
+	__be32 status = 0;
+	u32 tmp;
+	int n, i;
+	args->ndevs = 0;
+
+	/* Num of device notifications */
+	p = read_buf(xdr, sizeof(uint32_t));
+	if (unlikely(p == NULL)) {
+		status = htonl(NFS4ERR_BADXDR);
+		goto out;
+	}
+	n = ntohl(*p++);
+	if (n <= 0)
+		goto out;
+
+	args->devs = kmalloc(n * sizeof(*args->devs), GFP_KERNEL);
+	if (!args->devs) {
+		status = htonl(NFS4ERR_DELAY);
+		goto out;
+	}
+
+	/* Decode each dev notification */
+	for (i = 0; i < n; i++) {
+		struct cb_devicenotifyitem *dev = &args->devs[i];
+
+		p = read_buf(xdr, (4 * sizeof(uint32_t)) + NFS4_DEVICEID4_SIZE);
+		if (unlikely(p == NULL)) {
+			status = htonl(NFS4ERR_BADXDR);
+			goto err;
+		}
+
+		tmp = ntohl(*p++);	/* bitmap size */
+		if (tmp != 1) {
+			status = htonl(NFS4ERR_INVAL);
+			goto err;
+		}
+		dev->cbd_notify_type = ntohl(*p++);
+		if (dev->cbd_notify_type != NOTIFY_DEVICEID4_CHANGE &&
+		    dev->cbd_notify_type != NOTIFY_DEVICEID4_DELETE) {
+			status = htonl(NFS4ERR_INVAL);
+			goto err;
+		}
+
+		tmp = ntohl(*p++);	/* opaque size */
+		if (((dev->cbd_notify_type == NOTIFY_DEVICEID4_CHANGE) &&
+		     (tmp != NFS4_DEVICEID4_SIZE + 8)) ||
+		    ((dev->cbd_notify_type == NOTIFY_DEVICEID4_DELETE) &&
+		     (tmp != NFS4_DEVICEID4_SIZE + 4))) {
+			status = htonl(NFS4ERR_INVAL);
+			goto err;
+		}
+		dev->cbd_layout_type = ntohl(*p++);
+		memcpy(dev->cbd_dev_id.data, p, NFS4_DEVICEID4_SIZE);
+		p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
+
+		if (dev->cbd_layout_type == NOTIFY_DEVICEID4_CHANGE) {
+			p = read_buf(xdr, sizeof(uint32_t));
+			if (unlikely(p == NULL)) {
+				status = htonl(NFS4ERR_BADXDR);
+				goto err;
+			}
+			dev->cbd_immediate = ntohl(*p++);
+		} else {
+			dev->cbd_immediate = 0;
+		}
+
+		args->ndevs++;
+
+		dprintk("%s: type %d layout 0x%x immediate %d\n",
+			__func__, dev->cbd_notify_type, dev->cbd_layout_type,
+			dev->cbd_immediate);
+	}
+out:
+	dprintk("%s: status %d ndevs %d\n",
+		__func__, ntohl(status), args->ndevs);
+	return status;
+err:
+	kfree(args->devs);
+	goto out;
+}
+
 static __be32 decode_sessionid(struct xdr_stream *xdr,
 				 struct nfs4_sessionid *sid)
 {
@@ -639,10 +727,10 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
 	case OP_CB_RECALL_ANY:
 	case OP_CB_RECALL_SLOT:
 	case OP_CB_LAYOUTRECALL:
+	case OP_CB_NOTIFY_DEVICEID:
 		*op = &callback_ops[op_nr];
 		break;
 
-	case OP_CB_NOTIFY_DEVICEID:
 	case OP_CB_NOTIFY:
 	case OP_CB_PUSH_DELEG:
 	case OP_CB_RECALLABLE_OBJ_AVAIL:
@@ -849,6 +937,12 @@ static struct callback_op callback_ops[] = {
 			(callback_decode_arg_t)decode_layoutrecall_args,
 		.res_maxsize = CB_OP_LAYOUTRECALL_RES_MAXSZ,
 	},
+	[OP_CB_NOTIFY_DEVICEID] = {
+		.process_op = (callback_process_op_t)nfs4_callback_devicenotify,
+		.decode_args =
+			(callback_decode_arg_t)decode_devicenotify_args,
+		.res_maxsize = CB_OP_DEVICENOTIFY_RES_MAXSZ,
+	},
 	[OP_CB_SEQUENCE] = {
 		.process_op = (callback_process_op_t)nfs4_callback_sequence,
 		.decode_args = (callback_decode_arg_t)decode_cb_sequence_args,
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 139be9647d80..b3dc2b88b65b 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -290,6 +290,8 @@ static void nfs_free_client(struct nfs_client *clp)
 	if (clp->cl_machine_cred != NULL)
 		put_rpccred(clp->cl_machine_cred);
 
+	nfs4_deviceid_purge_client(clp);
+
 	kfree(clp->cl_hostname);
 	kfree(clp);
 
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index bbbc6bf5cb2e..dd25c2aec375 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -21,25 +21,13 @@
 #include "delegation.h"
 #include "internal.h"
 
-static void nfs_do_free_delegation(struct nfs_delegation *delegation)
-{
-	kfree(delegation);
-}
-
-static void nfs_free_delegation_callback(struct rcu_head *head)
-{
-	struct nfs_delegation *delegation = container_of(head, struct nfs_delegation, rcu);
-
-	nfs_do_free_delegation(delegation);
-}
-
 static void nfs_free_delegation(struct nfs_delegation *delegation)
 {
 	if (delegation->cred) {
 		put_rpccred(delegation->cred);
 		delegation->cred = NULL;
 	}
-	call_rcu(&delegation->rcu, nfs_free_delegation_callback);
+	kfree_rcu(delegation, rcu);
 }
 
 /**
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 424e47773a84..ededdbd0db38 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -512,12 +512,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 				struct page **xdr_pages, struct page *page, unsigned int buflen)
 {
 	struct xdr_stream stream;
-	struct xdr_buf buf = {
-		.pages = xdr_pages,
-		.page_len = buflen,
-		.buflen = buflen,
-		.len = buflen,
-	};
+	struct xdr_buf buf;
 	struct page *scratch;
 	struct nfs_cache_array *array;
 	unsigned int count = 0;
@@ -527,7 +522,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 	if (scratch == NULL)
 		return -ENOMEM;
 
-	xdr_init_decode(&stream, &buf, NULL);
+	xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen);
 	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
 	do {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 57bb31ad7a5e..6f4850deb272 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -256,7 +256,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 
 	nfs_attr_check_mountpoint(sb, fattr);
 
-	if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0 && (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0)
+	if (((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) &&
+	    !nfs_attr_use_mounted_on_fileid(fattr))
 		goto out_no_inode;
 	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0)
 		goto out_no_inode;
@@ -1294,12 +1295,17 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		if (new_isize != cur_isize) {
 			/* Do we perhaps have any outstanding writes, or has
 			 * the file grown beyond our last write? */
-			if (nfsi->npages == 0 || new_isize > cur_isize) {
+			if ((nfsi->npages == 0 && !test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) ||
+			     new_isize > cur_isize) {
 				i_size_write(inode, new_isize);
 				invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
 			}
-			dprintk("NFS: isize change on server for file %s/%ld\n",
-					inode->i_sb->s_id, inode->i_ino);
+			dprintk("NFS: isize change on server for file %s/%ld "
+					"(%Ld to %Ld)\n",
+					inode->i_sb->s_id,
+					inode->i_ino,
+					(long long)cur_isize,
+					(long long)new_isize);
 		}
 	} else
 		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
@@ -1424,9 +1430,10 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
  */
 void nfs4_evict_inode(struct inode *inode)
 {
-	pnfs_destroy_layout(NFS_I(inode));
 	truncate_inode_pages(&inode->i_data, 0);
 	end_writeback(inode);
+	pnfs_return_layout(inode);
+	pnfs_destroy_layout(NFS_I(inode));
 	/* If we are holding a delegation, return it! */
 	nfs_inode_return_delegation_noreclaim(inode);
 	/* First call standard NFS clear_inode() code */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 2df6ca7b5898..2a55347a2daa 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -45,6 +45,17 @@ static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct
 		fattr->valid |= NFS_ATTR_FATTR_MOUNTPOINT;
 }
 
+static inline int nfs_attr_use_mounted_on_fileid(struct nfs_fattr *fattr)
+{
+	if (((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) == 0) ||
+	    (((fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) &&
+	     ((fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) == 0)))
+		return 0;
+
+	fattr->fileid = fattr->mounted_on_fileid;
+	return 1;
+}
+
 struct nfs_clone_mount {
 	const struct super_block *sb;
 	const struct dentry *dentry;
@@ -310,6 +321,7 @@ extern int nfs_migrate_page(struct address_space *,
 #endif
 
 /* nfs4proc.c */
+extern void __nfs4_read_done_cb(struct nfs_read_data *);
 extern void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data);
 extern int nfs4_init_client(struct nfs_client *clp,
 			    const struct rpc_timeout *timeparms,
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index be79dc9f386d..0bafcc91c27f 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -30,6 +30,7 @@
  */
 
 #include <linux/nfs_fs.h>
+#include <linux/nfs_page.h>
 
 #include "internal.h"
 #include "nfs4filelayout.h"
@@ -421,6 +422,7 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 			struct nfs4_deviceid *id,
 			gfp_t gfp_flags)
 {
+	struct nfs4_deviceid_node *d;
 	struct nfs4_file_layout_dsaddr *dsaddr;
 	int status = -EINVAL;
 	struct nfs_server *nfss = NFS_SERVER(lo->plh_inode);
@@ -428,7 +430,7 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 	dprintk("--> %s\n", __func__);
 
 	if (fl->pattern_offset > lgr->range.offset) {
-		dprintk("%s pattern_offset %lld to large\n",
+		dprintk("%s pattern_offset %lld too large\n",
 				__func__, fl->pattern_offset);
 		goto out;
 	}
@@ -440,12 +442,14 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 	}
 
 	/* find and reference the deviceid */
-	dsaddr = nfs4_fl_find_get_deviceid(id);
-	if (dsaddr == NULL) {
+	d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode)->pnfs_curr_ld,
+				   NFS_SERVER(lo->plh_inode)->nfs_client, id);
+	if (d == NULL) {
 		dsaddr = get_device_info(lo->plh_inode, id, gfp_flags);
 		if (dsaddr == NULL)
 			goto out;
-	}
+	} else
+		dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
 	fl->dsaddr = dsaddr;
 
 	if (fl->first_stripe_index < 0 ||
@@ -507,12 +511,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 			 gfp_t gfp_flags)
 {
 	struct xdr_stream stream;
-	struct xdr_buf buf = {
-		.pages =  lgr->layoutp->pages,
-		.page_len =  lgr->layoutp->len,
-		.buflen =  lgr->layoutp->len,
-		.len = lgr->layoutp->len,
-	};
+	struct xdr_buf buf;
 	struct page *scratch;
 	__be32 *p;
 	uint32_t nfl_util;
@@ -524,7 +523,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 	if (!scratch)
 		return -ENOMEM;
 
-	xdr_init_decode(&stream, &buf, NULL);
+	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len);
 	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
 	/* 20 = ufl_util (4), first_stripe_index (4), pattern_offset (8),
@@ -535,7 +534,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 
 	memcpy(id, p, sizeof(*id));
 	p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
-	print_deviceid(id);
+	nfs4_print_deviceid(id);
 
 	nfl_util = be32_to_cpup(p++);
 	if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS)
@@ -554,13 +553,18 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 		__func__, nfl_util, fl->num_fh, fl->first_stripe_index,
 		fl->pattern_offset);
 
-	if (!fl->num_fh)
+	/* Note that a zero value for num_fh is legal for STRIPE_SPARSE.
+	 * Futher checking is done in filelayout_check_layout */
+	if (fl->num_fh < 0 || fl->num_fh >
+	    max(NFS4_PNFS_MAX_STRIPE_CNT, NFS4_PNFS_MAX_MULTI_CNT))
 		goto out_err;
 
-	fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *),
-			       gfp_flags);
-	if (!fl->fh_array)
-		goto out_err;
+	if (fl->num_fh > 0) {
+		fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *),
+				       gfp_flags);
+		if (!fl->fh_array)
+			goto out_err;
+	}
 
 	for (i = 0; i < fl->num_fh; i++) {
 		/* Do we want to use a mempool here? */
@@ -653,16 +657,20 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
 /*
  * filelayout_pg_test(). Called by nfs_can_coalesce_requests()
  *
- * return 1 :  coalesce page
- * return 0 :  don't coalesce page
+ * return true  : coalesce page
+ * return false : don't coalesce page
  */
-int
+bool
 filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		   struct nfs_page *req)
 {
 	u64 p_stripe, r_stripe;
 	u32 stripe_unit;
 
+	if (!pnfs_generic_pg_test(pgio, prev, req) ||
+	    !nfs_generic_pg_test(pgio, prev, req))
+		return false;
+
 	if (!pgio->pg_lseg)
 		return 1;
 	p_stripe = (u64)prev->wb_index << PAGE_CACHE_SHIFT;
@@ -860,6 +868,12 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 	return -ENOMEM;
 }
 
+static void
+filelayout_free_deveiceid_node(struct nfs4_deviceid_node *d)
+{
+	nfs4_fl_free_deviceid(container_of(d, struct nfs4_file_layout_dsaddr, id_node));
+}
+
 static struct pnfs_layoutdriver_type filelayout_type = {
 	.id			= LAYOUT_NFSV4_1_FILES,
 	.name			= "LAYOUT_NFSV4_1_FILES",
@@ -872,6 +886,7 @@ static struct pnfs_layoutdriver_type filelayout_type = {
 	.commit_pagelist	= filelayout_commit_pagelist,
 	.read_pagelist		= filelayout_read_pagelist,
 	.write_pagelist		= filelayout_write_pagelist,
+	.free_deviceid_node	= filelayout_free_deveiceid_node,
 };
 
 static int __init nfs4filelayout_init(void)
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
index 2b461d77b43a..cebe01e3795e 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/nfs4filelayout.h
@@ -59,9 +59,7 @@ struct nfs4_pnfs_ds {
 #define NFS4_DEVICE_ID_NEG_ENTRY	0x00000001
 
 struct nfs4_file_layout_dsaddr {
-	struct hlist_node		node;
-	struct nfs4_deviceid		deviceid;
-	atomic_t			ref;
+	struct nfs4_deviceid_node	id_node;
 	unsigned long			flags;
 	u32				stripe_count;
 	u8				*stripe_indices;
@@ -95,14 +93,12 @@ extern struct nfs_fh *
 nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
 
 extern void print_ds(struct nfs4_pnfs_ds *ds);
-extern void print_deviceid(struct nfs4_deviceid *dev_id);
 u32 nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset);
 u32 nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j);
 struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg,
 					u32 ds_idx);
-extern struct nfs4_file_layout_dsaddr *
-nfs4_fl_find_get_deviceid(struct nfs4_deviceid *dev_id);
 extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
+extern void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
 struct nfs4_file_layout_dsaddr *
 get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags);
 
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index db07c7af1395..3b7bf1377264 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -37,30 +37,6 @@
 #define NFSDBG_FACILITY		NFSDBG_PNFS_LD
 
 /*
- * Device ID RCU cache. A device ID is unique per client ID and layout type.
- */
-#define NFS4_FL_DEVICE_ID_HASH_BITS	5
-#define NFS4_FL_DEVICE_ID_HASH_SIZE	(1 << NFS4_FL_DEVICE_ID_HASH_BITS)
-#define NFS4_FL_DEVICE_ID_HASH_MASK	(NFS4_FL_DEVICE_ID_HASH_SIZE - 1)
-
-static inline u32
-nfs4_fl_deviceid_hash(struct nfs4_deviceid *id)
-{
-	unsigned char *cptr = (unsigned char *)id->data;
-	unsigned int nbytes = NFS4_DEVICEID4_SIZE;
-	u32 x = 0;
-
-	while (nbytes--) {
-		x *= 37;
-		x += *cptr++;
-	}
-	return x & NFS4_FL_DEVICE_ID_HASH_MASK;
-}
-
-static struct hlist_head filelayout_deviceid_cache[NFS4_FL_DEVICE_ID_HASH_SIZE];
-static DEFINE_SPINLOCK(filelayout_deviceid_lock);
-
-/*
  * Data server cache
  *
  * Data servers can be mapped to different device ids.
@@ -89,27 +65,6 @@ print_ds(struct nfs4_pnfs_ds *ds)
 		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
 }
 
-void
-print_ds_list(struct nfs4_file_layout_dsaddr *dsaddr)
-{
-	int i;
-
-	ifdebug(FACILITY) {
-		printk("%s dsaddr->ds_num %d\n", __func__,
-		       dsaddr->ds_num);
-		for (i = 0; i < dsaddr->ds_num; i++)
-			print_ds(dsaddr->ds_list[i]);
-	}
-}
-
-void print_deviceid(struct nfs4_deviceid *id)
-{
-	u32 *p = (u32 *)id;
-
-	dprintk("%s: device id= [%x%x%x%x]\n", __func__,
-		p[0], p[1], p[2], p[3]);
-}
-
 /* nfs4_ds_cache_lock is held */
 static struct nfs4_pnfs_ds *
 _data_server_lookup_locked(u32 ip_addr, u32 port)
@@ -201,13 +156,13 @@ destroy_ds(struct nfs4_pnfs_ds *ds)
 	kfree(ds);
 }
 
-static void
+void
 nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 {
 	struct nfs4_pnfs_ds *ds;
 	int i;
 
-	print_deviceid(&dsaddr->deviceid);
+	nfs4_print_deviceid(&dsaddr->id_node.deviceid);
 
 	for (i = 0; i < dsaddr->ds_num; i++) {
 		ds = dsaddr->ds_list[i];
@@ -353,12 +308,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 	u8 max_stripe_index;
 	struct nfs4_file_layout_dsaddr *dsaddr = NULL;
 	struct xdr_stream stream;
-	struct xdr_buf buf = {
-		.pages = pdev->pages,
-		.page_len = pdev->pglen,
-		.buflen = pdev->pglen,
-		.len = pdev->pglen,
-	};
+	struct xdr_buf buf;
 	struct page *scratch;
 
 	/* set up xdr stream */
@@ -366,7 +316,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 	if (!scratch)
 		goto out_err;
 
-	xdr_init_decode(&stream, &buf, NULL);
+	xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
 	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
 	/* Get the stripe count (number of stripe index) */
@@ -431,8 +381,10 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 	dsaddr->stripe_indices = stripe_indices;
 	stripe_indices = NULL;
 	dsaddr->ds_num = num;
-
-	memcpy(&dsaddr->deviceid, &pdev->dev_id, sizeof(pdev->dev_id));
+	nfs4_init_deviceid_node(&dsaddr->id_node,
+				NFS_SERVER(ino)->pnfs_curr_ld,
+				NFS_SERVER(ino)->nfs_client,
+				&pdev->dev_id);
 
 	for (i = 0; i < dsaddr->ds_num; i++) {
 		int j;
@@ -505,8 +457,8 @@ out_err:
 static struct nfs4_file_layout_dsaddr *
 decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_flags)
 {
-	struct nfs4_file_layout_dsaddr *d, *new;
-	long hash;
+	struct nfs4_deviceid_node *d;
+	struct nfs4_file_layout_dsaddr *n, *new;
 
 	new = decode_device(inode, dev, gfp_flags);
 	if (!new) {
@@ -515,20 +467,13 @@ decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_fl
 		return NULL;
 	}
 
-	spin_lock(&filelayout_deviceid_lock);
-	d = nfs4_fl_find_get_deviceid(&new->deviceid);
-	if (d) {
-		spin_unlock(&filelayout_deviceid_lock);
+	d = nfs4_insert_deviceid_node(&new->id_node);
+	n = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
+	if (n != new) {
 		nfs4_fl_free_deviceid(new);
-		return d;
+		return n;
 	}
 
-	INIT_HLIST_NODE(&new->node);
-	atomic_set(&new->ref, 1);
-	hash = nfs4_fl_deviceid_hash(&new->deviceid);
-	hlist_add_head_rcu(&new->node, &filelayout_deviceid_cache[hash]);
-	spin_unlock(&filelayout_deviceid_lock);
-
 	return new;
 }
 
@@ -600,35 +545,7 @@ out_free:
 void
 nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 {
-	if (atomic_dec_and_lock(&dsaddr->ref, &filelayout_deviceid_lock)) {
-		hlist_del_rcu(&dsaddr->node);
-		spin_unlock(&filelayout_deviceid_lock);
-
-		synchronize_rcu();
-		nfs4_fl_free_deviceid(dsaddr);
-	}
-}
-
-struct nfs4_file_layout_dsaddr *
-nfs4_fl_find_get_deviceid(struct nfs4_deviceid *id)
-{
-	struct nfs4_file_layout_dsaddr *d;
-	struct hlist_node *n;
-	long hash = nfs4_fl_deviceid_hash(id);
-
-
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(d, n, &filelayout_deviceid_cache[hash], node) {
-		if (!memcmp(&d->deviceid, id, sizeof(*id))) {
-			if (!atomic_inc_not_zero(&d->ref))
-				goto fail;
-			rcu_read_unlock();
-			return d;
-		}
-	}
-fail:
-	rcu_read_unlock();
-	return NULL;
+	nfs4_put_deviceid_node(&dsaddr->id_node);
 }
 
 /*
@@ -676,15 +593,15 @@ static void
 filelayout_mark_devid_negative(struct nfs4_file_layout_dsaddr *dsaddr,
 			       int err, u32 ds_addr)
 {
-	u32 *p = (u32 *)&dsaddr->deviceid;
+	u32 *p = (u32 *)&dsaddr->id_node.deviceid;
 
 	printk(KERN_ERR "NFS: data server %x connection error %d."
 		" Deviceid [%x%x%x%x] marked out of use.\n",
 		ds_addr, err, p[0], p[1], p[2], p[3]);
 
-	spin_lock(&filelayout_deviceid_lock);
+	spin_lock(&nfs4_ds_cache_lock);
 	dsaddr->flags |= NFS4_DEVICE_ID_NEG_ENTRY;
-	spin_unlock(&filelayout_deviceid_lock);
+	spin_unlock(&nfs4_ds_cache_lock);
 }
 
 struct nfs4_pnfs_ds *
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index cf1b339c3937..5879b23e0c99 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -267,9 +267,11 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 				break;
 			nfs4_schedule_stateid_recovery(server, state);
 			goto wait_on_recovery;
+		case -NFS4ERR_EXPIRED:
+			if (state != NULL)
+				nfs4_schedule_stateid_recovery(server, state);
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_STALE_CLIENTID:
-		case -NFS4ERR_EXPIRED:
 			nfs4_schedule_lease_recovery(clp);
 			goto wait_on_recovery;
 #if defined(CONFIG_NFS_V4_1)
@@ -2263,12 +2265,14 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
 	return nfs4_map_errors(status);
 }
 
+static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr);
 /*
  * Get locations and (maybe) other attributes of a referral.
  * Note that we'll actually follow the referral later when
  * we detect fsid mismatch in inode revalidation
  */
-static int nfs4_get_referral(struct inode *dir, const struct qstr *name, struct nfs_fattr *fattr, struct nfs_fh *fhandle)
+static int nfs4_get_referral(struct inode *dir, const struct qstr *name,
+			     struct nfs_fattr *fattr, struct nfs_fh *fhandle)
 {
 	int status = -ENOMEM;
 	struct page *page = NULL;
@@ -2286,15 +2290,16 @@ static int nfs4_get_referral(struct inode *dir, const struct qstr *name, struct
 		goto out;
 	/* Make sure server returned a different fsid for the referral */
 	if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &locations->fattr.fsid)) {
-		dprintk("%s: server did not return a different fsid for a referral at %s\n", __func__, name->name);
+		dprintk("%s: server did not return a different fsid for"
+			" a referral at %s\n", __func__, name->name);
 		status = -EIO;
 		goto out;
 	}
+	/* Fixup attributes for the nfs_lookup() call to nfs_fhget() */
+	nfs_fixup_referral_attributes(&locations->fattr);
 
+	/* replace the lookup nfs_fattr with the locations nfs_fattr */
 	memcpy(fattr, &locations->fattr, sizeof(struct nfs_fattr));
-	fattr->valid |= NFS_ATTR_FATTR_V4_REFERRAL;
-	if (!fattr->mode)
-		fattr->mode = S_IFDIR;
 	memset(fhandle, 0, sizeof(struct nfs_fh));
 out:
 	if (page)
@@ -2361,6 +2366,9 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	struct nfs4_state *state = NULL;
 	int status;
 
+	if (pnfs_ld_layoutret_on_setattr(inode))
+		pnfs_return_layout(inode);
+
 	nfs_fattr_init(fattr);
 	
 	/* Search for an existing open(O_WRITE) file */
@@ -3175,6 +3183,11 @@ static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 	return err;
 }
 
+void __nfs4_read_done_cb(struct nfs_read_data *data)
+{
+	nfs_invalidate_atime(data->inode);
+}
+
 static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data)
 {
 	struct nfs_server *server = NFS_SERVER(data->inode);
@@ -3184,7 +3197,7 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data)
 		return -EAGAIN;
 	}
 
-	nfs_invalidate_atime(data->inode);
+	__nfs4_read_done_cb(data);
 	if (task->tk_status > 0)
 		renew_lease(server, data->timestamp);
 	return 0;
@@ -3198,7 +3211,8 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data)
 	if (!nfs4_sequence_done(task, &data->res.seq_res))
 		return -EAGAIN;
 
-	return data->read_done_cb(task, data);
+	return data->read_done_cb ? data->read_done_cb(task, data) :
+				    nfs4_read_done_cb(task, data);
 }
 
 static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message *msg)
@@ -3243,7 +3257,8 @@ static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data)
 {
 	if (!nfs4_sequence_done(task, &data->res.seq_res))
 		return -EAGAIN;
-	return data->write_done_cb(task, data);
+	return data->write_done_cb ? data->write_done_cb(task, data) :
+		nfs4_write_done_cb(task, data);
 }
 
 /* Reset the the nfs_write_data to send the write to the MDS. */
@@ -3670,9 +3685,11 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 				break;
 			nfs4_schedule_stateid_recovery(server, state);
 			goto wait_on_recovery;
+		case -NFS4ERR_EXPIRED:
+			if (state != NULL)
+				nfs4_schedule_stateid_recovery(server, state);
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_STALE_CLIENTID:
-		case -NFS4ERR_EXPIRED:
 			nfs4_schedule_lease_recovery(clp);
 			goto wait_on_recovery;
 #if defined(CONFIG_NFS_V4_1)
@@ -4543,6 +4560,7 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
 			case -ESTALE:
 				goto out;
 			case -NFS4ERR_EXPIRED:
+				nfs4_schedule_stateid_recovery(server, state);
 			case -NFS4ERR_STALE_CLIENTID:
 			case -NFS4ERR_STALE_STATEID:
 				nfs4_schedule_lease_recovery(server->nfs_client);
@@ -4652,11 +4670,15 @@ static size_t nfs4_xattr_list_nfs4_acl(struct dentry *dentry, char *list,
 	return len;
 }
 
+/*
+ * nfs_fhget will use either the mounted_on_fileid or the fileid
+ */
 static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr)
 {
-	if (!((fattr->valid & NFS_ATTR_FATTR_FILEID) &&
-		(fattr->valid & NFS_ATTR_FATTR_FSID) &&
-		(fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)))
+	if (!(((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) ||
+	       (fattr->valid & NFS_ATTR_FATTR_FILEID)) &&
+	      (fattr->valid & NFS_ATTR_FATTR_FSID) &&
+	      (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)))
 		return;
 
 	fattr->valid |= NFS_ATTR_FATTR_TYPE | NFS_ATTR_FATTR_MODE |
@@ -4671,7 +4693,6 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
 	struct nfs_server *server = NFS_SERVER(dir);
 	u32 bitmask[2] = {
 		[0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS,
-		[1] = FATTR4_WORD1_MOUNTED_ON_FILEID,
 	};
 	struct nfs4_fs_locations_arg args = {
 		.dir_fh = NFS_FH(dir),
@@ -4690,11 +4711,18 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
 	int status;
 
 	dprintk("%s: start\n", __func__);
+
+	/* Ask for the fileid of the absent filesystem if mounted_on_fileid
+	 * is not supported */
+	if (NFS_SERVER(dir)->attr_bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)
+		bitmask[1] |= FATTR4_WORD1_MOUNTED_ON_FILEID;
+	else
+		bitmask[0] |= FATTR4_WORD0_FILEID;
+
 	nfs_fattr_init(&fs_locations->fattr);
 	fs_locations->server = server;
 	fs_locations->nlocations = 0;
 	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
-	nfs_fixup_referral_attributes(&fs_locations->fattr);
 	dprintk("%s: returned status = %d\n", __func__, status);
 	return status;
 }
@@ -5083,7 +5111,6 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
 	if (mxresp_sz == 0)
 		mxresp_sz = NFS_MAX_FILE_IO_SIZE;
 	/* Fore channel attributes */
-	args->fc_attrs.headerpadsz = 0;
 	args->fc_attrs.max_rqst_sz = mxrqst_sz;
 	args->fc_attrs.max_resp_sz = mxresp_sz;
 	args->fc_attrs.max_ops = NFS4_MAX_OPS;
@@ -5096,7 +5123,6 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
 		args->fc_attrs.max_ops, args->fc_attrs.max_reqs);
 
 	/* Back channel attributes */
-	args->bc_attrs.headerpadsz = 0;
 	args->bc_attrs.max_rqst_sz = PAGE_SIZE;
 	args->bc_attrs.max_resp_sz = PAGE_SIZE;
 	args->bc_attrs.max_resp_sz_cached = 0;
@@ -5116,8 +5142,6 @@ static int nfs4_verify_fore_channel_attrs(struct nfs41_create_session_args *args
 	struct nfs4_channel_attrs *sent = &args->fc_attrs;
 	struct nfs4_channel_attrs *rcvd = &session->fc_attrs;
 
-	if (rcvd->headerpadsz > sent->headerpadsz)
-		return -EINVAL;
 	if (rcvd->max_resp_sz > sent->max_resp_sz)
 		return -EINVAL;
 	/*
@@ -5666,6 +5690,88 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp)
 	return status;
 }
 
+static void
+nfs4_layoutreturn_prepare(struct rpc_task *task, void *calldata)
+{
+	struct nfs4_layoutreturn *lrp = calldata;
+
+	dprintk("--> %s\n", __func__);
+	if (nfs41_setup_sequence(lrp->clp->cl_session, &lrp->args.seq_args,
+				&lrp->res.seq_res, 0, task))
+		return;
+	rpc_call_start(task);
+}
+
+static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
+{
+	struct nfs4_layoutreturn *lrp = calldata;
+	struct nfs_server *server;
+	struct pnfs_layout_hdr *lo = NFS_I(lrp->args.inode)->layout;
+
+	dprintk("--> %s\n", __func__);
+
+	if (!nfs4_sequence_done(task, &lrp->res.seq_res))
+		return;
+
+	server = NFS_SERVER(lrp->args.inode);
+	if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
+		nfs_restart_rpc(task, lrp->clp);
+		return;
+	}
+	spin_lock(&lo->plh_inode->i_lock);
+	if (task->tk_status == 0) {
+		if (lrp->res.lrs_present) {
+			pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+		} else
+			BUG_ON(!list_empty(&lo->plh_segs));
+	}
+	lo->plh_block_lgets--;
+	spin_unlock(&lo->plh_inode->i_lock);
+	dprintk("<-- %s\n", __func__);
+}
+
+static void nfs4_layoutreturn_release(void *calldata)
+{
+	struct nfs4_layoutreturn *lrp = calldata;
+
+	dprintk("--> %s\n", __func__);
+	put_layout_hdr(NFS_I(lrp->args.inode)->layout);
+	kfree(calldata);
+	dprintk("<-- %s\n", __func__);
+}
+
+static const struct rpc_call_ops nfs4_layoutreturn_call_ops = {
+	.rpc_call_prepare = nfs4_layoutreturn_prepare,
+	.rpc_call_done = nfs4_layoutreturn_done,
+	.rpc_release = nfs4_layoutreturn_release,
+};
+
+int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
+{
+	struct rpc_task *task;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTRETURN],
+		.rpc_argp = &lrp->args,
+		.rpc_resp = &lrp->res,
+	};
+	struct rpc_task_setup task_setup_data = {
+		.rpc_client = lrp->clp->cl_rpcclient,
+		.rpc_message = &msg,
+		.callback_ops = &nfs4_layoutreturn_call_ops,
+		.callback_data = lrp,
+	};
+	int status;
+
+	dprintk("--> %s\n", __func__);
+	task = rpc_run_task(&task_setup_data);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+	status = task->tk_status;
+	dprintk("<-- %s status=%d\n", __func__, status);
+	rpc_put_task(task);
+	return status;
+}
+
 static int
 _nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev)
 {
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 036f5adc9e1f..e97dd219f84f 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1466,7 +1466,10 @@ static int nfs4_reclaim_lease(struct nfs_client *clp)
 #ifdef CONFIG_NFS_V4_1
 void nfs4_schedule_session_recovery(struct nfs4_session *session)
 {
-	nfs4_schedule_lease_recovery(session->clp);
+	struct nfs_client *clp = session->clp;
+
+	set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+	nfs4_schedule_lease_recovery(clp);
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_session_recovery);
 
@@ -1549,6 +1552,7 @@ static int nfs4_reset_session(struct nfs_client *clp)
 		status = nfs4_recovery_handle_error(clp, status);
 		goto out;
 	}
+	clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
 	/* create_session negotiated new slot table */
 	clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index c3ccd2c46834..6870bc61ceec 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -255,7 +255,7 @@ static int nfs4_stat_to_errno(int);
 #define decode_fs_locations_maxsz \
 				(0)
 #define encode_secinfo_maxsz	(op_encode_hdr_maxsz + nfs4_name_maxsz)
-#define decode_secinfo_maxsz	(op_decode_hdr_maxsz + 4 + (NFS_MAX_SECFLAVORS * (16 + GSS_OID_MAX_LEN)))
+#define decode_secinfo_maxsz	(op_decode_hdr_maxsz + 1 + ((NFS_MAX_SECFLAVORS * (16 + GSS_OID_MAX_LEN)) / 4))
 
 #if defined(CONFIG_NFS_V4_1)
 #define NFS4_MAX_MACHINE_NAME_LEN (64)
@@ -338,7 +338,11 @@ static int nfs4_stat_to_errno(int);
 				1 /* layoutupdate4 layout type */ + \
 				1 /* NULL filelayout layoutupdate4 payload */)
 #define decode_layoutcommit_maxsz (op_decode_hdr_maxsz + 3)
-
+#define encode_layoutreturn_maxsz (8 + op_encode_hdr_maxsz + \
+				encode_stateid_maxsz + \
+				1 /* FIXME: opaque lrf_body always empty at the moment */)
+#define decode_layoutreturn_maxsz (op_decode_hdr_maxsz + \
+				1 + decode_stateid_maxsz)
 #else /* CONFIG_NFS_V4_1 */
 #define encode_sequence_maxsz	0
 #define decode_sequence_maxsz	0
@@ -760,7 +764,14 @@ static int nfs4_stat_to_errno(int);
 				decode_putfh_maxsz + \
 				decode_layoutcommit_maxsz + \
 				decode_getattr_maxsz)
-
+#define NFS4_enc_layoutreturn_sz (compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
+				encode_putfh_maxsz + \
+				encode_layoutreturn_maxsz)
+#define NFS4_dec_layoutreturn_sz (compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
+				decode_putfh_maxsz + \
+				decode_layoutreturn_maxsz)
 
 const u32 nfs41_maxwrite_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
 				      compound_encode_hdr_maxsz +
@@ -1714,7 +1725,7 @@ static void encode_create_session(struct xdr_stream *xdr,
 	*p++ = cpu_to_be32(args->flags);			/*flags */
 
 	/* Fore Channel */
-	*p++ = cpu_to_be32(args->fc_attrs.headerpadsz);	/* header padding size */
+	*p++ = cpu_to_be32(0);				/* header padding size */
 	*p++ = cpu_to_be32(args->fc_attrs.max_rqst_sz);	/* max req size */
 	*p++ = cpu_to_be32(args->fc_attrs.max_resp_sz);	/* max resp size */
 	*p++ = cpu_to_be32(max_resp_sz_cached);		/* Max resp sz cached */
@@ -1723,7 +1734,7 @@ static void encode_create_session(struct xdr_stream *xdr,
 	*p++ = cpu_to_be32(0);				/* rdmachannel_attrs */
 
 	/* Back Channel */
-	*p++ = cpu_to_be32(args->fc_attrs.headerpadsz);	/* header padding size */
+	*p++ = cpu_to_be32(0);				/* header padding size */
 	*p++ = cpu_to_be32(args->bc_attrs.max_rqst_sz);	/* max req size */
 	*p++ = cpu_to_be32(args->bc_attrs.max_resp_sz);	/* max resp size */
 	*p++ = cpu_to_be32(args->bc_attrs.max_resp_sz_cached);	/* Max resp sz cached */
@@ -1864,6 +1875,7 @@ encode_layoutget(struct xdr_stream *xdr,
 
 static int
 encode_layoutcommit(struct xdr_stream *xdr,
+		    struct inode *inode,
 		    const struct nfs4_layoutcommit_args *args,
 		    struct compound_hdr *hdr)
 {
@@ -1872,7 +1884,7 @@ encode_layoutcommit(struct xdr_stream *xdr,
 	dprintk("%s: lbw: %llu type: %d\n", __func__, args->lastbytewritten,
 		NFS_SERVER(args->inode)->pnfs_curr_ld->id);
 
-	p = reserve_space(xdr, 48 + NFS4_STATEID_SIZE);
+	p = reserve_space(xdr, 44 + NFS4_STATEID_SIZE);
 	*p++ = cpu_to_be32(OP_LAYOUTCOMMIT);
 	/* Only whole file layouts */
 	p = xdr_encode_hyper(p, 0); /* offset */
@@ -1883,12 +1895,49 @@ encode_layoutcommit(struct xdr_stream *xdr,
 	p = xdr_encode_hyper(p, args->lastbytewritten);
 	*p++ = cpu_to_be32(0); /* Never send time_modify_changed */
 	*p++ = cpu_to_be32(NFS_SERVER(args->inode)->pnfs_curr_ld->id);/* type */
-	*p++ = cpu_to_be32(0); /* no file layout payload */
+
+	if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit)
+		NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit(
+			NFS_I(inode)->layout, xdr, args);
+	else {
+		p = reserve_space(xdr, 4);
+		*p = cpu_to_be32(0); /* no layout-type payload */
+	}
 
 	hdr->nops++;
 	hdr->replen += decode_layoutcommit_maxsz;
 	return 0;
 }
+
+static void
+encode_layoutreturn(struct xdr_stream *xdr,
+		    const struct nfs4_layoutreturn_args *args,
+		    struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	p = reserve_space(xdr, 20);
+	*p++ = cpu_to_be32(OP_LAYOUTRETURN);
+	*p++ = cpu_to_be32(0);		/* reclaim. always 0 for now */
+	*p++ = cpu_to_be32(args->layout_type);
+	*p++ = cpu_to_be32(IOMODE_ANY);
+	*p = cpu_to_be32(RETURN_FILE);
+	p = reserve_space(xdr, 16 + NFS4_STATEID_SIZE);
+	p = xdr_encode_hyper(p, 0);
+	p = xdr_encode_hyper(p, NFS4_MAX_UINT64);
+	spin_lock(&args->inode->i_lock);
+	xdr_encode_opaque_fixed(p, &args->stateid.data, NFS4_STATEID_SIZE);
+	spin_unlock(&args->inode->i_lock);
+	if (NFS_SERVER(args->inode)->pnfs_curr_ld->encode_layoutreturn) {
+		NFS_SERVER(args->inode)->pnfs_curr_ld->encode_layoutreturn(
+			NFS_I(args->inode)->layout, xdr, args);
+	} else {
+		p = reserve_space(xdr, 4);
+		*p = cpu_to_be32(0);
+	}
+	hdr->nops++;
+	hdr->replen += decode_layoutreturn_maxsz;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /*
@@ -2706,10 +2755,12 @@ static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req,
 /*
  *  Encode LAYOUTCOMMIT request
  */
-static int nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req,
-				     struct xdr_stream *xdr,
-				     struct nfs4_layoutcommit_args *args)
+static void nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req,
+				      struct xdr_stream *xdr,
+				      struct nfs4_layoutcommit_args *args)
 {
+	struct nfs4_layoutcommit_data *data =
+		container_of(args, struct nfs4_layoutcommit_data, args);
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2717,10 +2768,27 @@ static int nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req,
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, NFS_FH(args->inode), &hdr);
-	encode_layoutcommit(xdr, args, &hdr);
+	encode_layoutcommit(xdr, data->args.inode, args, &hdr);
 	encode_getfattr(xdr, args->bitmask, &hdr);
 	encode_nops(&hdr);
-	return 0;
+}
+
+/*
+ * Encode LAYOUTRETURN request
+ */
+static void nfs4_xdr_enc_layoutreturn(struct rpc_rqst *req,
+				      struct xdr_stream *xdr,
+				      struct nfs4_layoutreturn_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, NFS_FH(args->inode), &hdr);
+	encode_layoutreturn(xdr, args, &hdr);
+	encode_nops(&hdr);
 }
 #endif /* CONFIG_NFS_V4_1 */
 
@@ -3030,7 +3098,7 @@ out_overflow:
 	return -EIO;
 }
 
-static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap)
+static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap, int32_t *res)
 {
 	__be32 *p;
 
@@ -3041,7 +3109,7 @@ static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap)
 		if (unlikely(!p))
 			goto out_overflow;
 		bitmap[0] &= ~FATTR4_WORD0_RDATTR_ERROR;
-		return -be32_to_cpup(p);
+		*res = -be32_to_cpup(p);
 	}
 	return 0;
 out_overflow:
@@ -4002,6 +4070,7 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
 	int status;
 	umode_t fmode = 0;
 	uint32_t type;
+	int32_t err;
 
 	status = decode_attr_type(xdr, bitmap, &type);
 	if (status < 0)
@@ -4027,13 +4096,12 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
 		goto xdr_error;
 	fattr->valid |= status;
 
-	status = decode_attr_error(xdr, bitmap);
-	if (status == -NFS4ERR_WRONGSEC) {
-		nfs_fixup_secinfo_attributes(fattr, fh);
-		status = 0;
-	}
+	err = 0;
+	status = decode_attr_error(xdr, bitmap, &err);
 	if (status < 0)
 		goto xdr_error;
+	if (err == -NFS4ERR_WRONGSEC)
+		nfs_fixup_secinfo_attributes(fattr, fh);
 
 	status = decode_attr_filehandle(xdr, bitmap, fh);
 	if (status < 0)
@@ -4929,12 +4997,14 @@ static int decode_chan_attrs(struct xdr_stream *xdr,
 			     struct nfs4_channel_attrs *attrs)
 {
 	__be32 *p;
-	u32 nr_attrs;
+	u32 nr_attrs, val;
 
 	p = xdr_inline_decode(xdr, 28);
 	if (unlikely(!p))
 		goto out_overflow;
-	attrs->headerpadsz = be32_to_cpup(p++);
+	val = be32_to_cpup(p++);	/* headerpadsz */
+	if (val)
+		return -EINVAL;		/* no support for header padding yet */
 	attrs->max_rqst_sz = be32_to_cpup(p++);
 	attrs->max_resp_sz = be32_to_cpup(p++);
 	attrs->max_resp_sz_cached = be32_to_cpup(p++);
@@ -5203,6 +5273,27 @@ out_overflow:
 	return -EIO;
 }
 
+static int decode_layoutreturn(struct xdr_stream *xdr,
+			       struct nfs4_layoutreturn_res *res)
+{
+	__be32 *p;
+	int status;
+
+	status = decode_op_hdr(xdr, OP_LAYOUTRETURN);
+	if (status)
+		return status;
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	res->lrs_present = be32_to_cpup(p);
+	if (res->lrs_present)
+		status = decode_stateid(xdr, &res->stateid);
+	return status;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
 static int decode_layoutcommit(struct xdr_stream *xdr,
 			       struct rpc_rqst *req,
 			       struct nfs4_layoutcommit_res *res)
@@ -6320,6 +6411,30 @@ out:
 }
 
 /*
+ * Decode LAYOUTRETURN response
+ */
+static int nfs4_xdr_dec_layoutreturn(struct rpc_rqst *rqstp,
+				     struct xdr_stream *xdr,
+				     struct nfs4_layoutreturn_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_layoutreturn(xdr, res);
+out:
+	return status;
+}
+
+/*
  * Decode LAYOUTCOMMIT response
  */
 static int nfs4_xdr_dec_layoutcommit(struct rpc_rqst *rqstp,
@@ -6547,6 +6662,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(GETDEVICEINFO,	enc_getdeviceinfo,	dec_getdeviceinfo),
 	PROC(LAYOUTGET,		enc_layoutget,		dec_layoutget),
 	PROC(LAYOUTCOMMIT,	enc_layoutcommit,	dec_layoutcommit),
+	PROC(LAYOUTRETURN,	enc_layoutreturn,	dec_layoutreturn),
 #endif /* CONFIG_NFS_V4_1 */
 };
 
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index c541093a5bf2..c4744e1d513c 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -87,7 +87,7 @@
 #define NFS_ROOT		"/tftpboot/%s"
 
 /* Default NFSROOT mount options. */
-#define NFS_DEF_OPTIONS		"udp"
+#define NFS_DEF_OPTIONS		"vers=2,udp,rsize=4096,wsize=4096"
 
 /* Parameters passed from the kernel command line */
 static char nfs_root_parms[256] __initdata = "";
diff --git a/fs/nfs/objlayout/Kbuild b/fs/nfs/objlayout/Kbuild
new file mode 100644
index 000000000000..ed30ea072bb8
--- /dev/null
+++ b/fs/nfs/objlayout/Kbuild
@@ -0,0 +1,5 @@
+#
+# Makefile for the pNFS Objects Layout Driver kernel module
+#
+objlayoutdriver-y := objio_osd.o pnfs_osd_xdr_cli.o objlayout.o
+obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayoutdriver.o
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
new file mode 100644
index 000000000000..8ff2ea3f10ef
--- /dev/null
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -0,0 +1,1059 @@
+/*
+ *  pNFS Objects layout implementation over open-osd initiator library
+ *
+ *  Copyright (C) 2009 Panasas Inc. [year of first publication]
+ *  All rights reserved.
+ *
+ *  Benny Halevy <bhalevy@panasas.com>
+ *  Boaz Harrosh <bharrosh@panasas.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
+ *  See the file COPYING included with this distribution for more details.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the Panasas company nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <scsi/osd_initiator.h>
+
+#include "objlayout.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+#define _LLU(x) ((unsigned long long)x)
+
+enum { BIO_MAX_PAGES_KMALLOC =
+		(PAGE_SIZE - sizeof(struct bio)) / sizeof(struct bio_vec),
+};
+
+struct objio_dev_ent {
+	struct nfs4_deviceid_node id_node;
+	struct osd_dev *od;
+};
+
+static void
+objio_free_deviceid_node(struct nfs4_deviceid_node *d)
+{
+	struct objio_dev_ent *de = container_of(d, struct objio_dev_ent, id_node);
+
+	dprintk("%s: free od=%p\n", __func__, de->od);
+	osduld_put_device(de->od);
+	kfree(de);
+}
+
+static struct objio_dev_ent *_dev_list_find(const struct nfs_server *nfss,
+	const struct nfs4_deviceid *d_id)
+{
+	struct nfs4_deviceid_node *d;
+	struct objio_dev_ent *de;
+
+	d = nfs4_find_get_deviceid(nfss->pnfs_curr_ld, nfss->nfs_client, d_id);
+	if (!d)
+		return NULL;
+
+	de = container_of(d, struct objio_dev_ent, id_node);
+	return de;
+}
+
+static struct objio_dev_ent *
+_dev_list_add(const struct nfs_server *nfss,
+	const struct nfs4_deviceid *d_id, struct osd_dev *od,
+	gfp_t gfp_flags)
+{
+	struct nfs4_deviceid_node *d;
+	struct objio_dev_ent *de = kzalloc(sizeof(*de), gfp_flags);
+	struct objio_dev_ent *n;
+
+	if (!de) {
+		dprintk("%s: -ENOMEM od=%p\n", __func__, od);
+		return NULL;
+	}
+
+	dprintk("%s: Adding od=%p\n", __func__, od);
+	nfs4_init_deviceid_node(&de->id_node,
+				nfss->pnfs_curr_ld,
+				nfss->nfs_client,
+				d_id);
+	de->od = od;
+
+	d = nfs4_insert_deviceid_node(&de->id_node);
+	n = container_of(d, struct objio_dev_ent, id_node);
+	if (n != de) {
+		dprintk("%s: Race with other n->od=%p\n", __func__, n->od);
+		objio_free_deviceid_node(&de->id_node);
+		de = n;
+	}
+
+	return de;
+}
+
+struct caps_buffers {
+	u8 caps_key[OSD_CRYPTO_KEYID_SIZE];
+	u8 creds[OSD_CAP_LEN];
+};
+
+struct objio_segment {
+	struct pnfs_layout_segment lseg;
+
+	struct pnfs_osd_object_cred *comps;
+
+	unsigned mirrors_p1;
+	unsigned stripe_unit;
+	unsigned group_width;	/* Data stripe_units without integrity comps */
+	u64 group_depth;
+	unsigned group_count;
+
+	unsigned max_io_size;
+
+	unsigned comps_index;
+	unsigned num_comps;
+	/* variable length */
+	struct objio_dev_ent *ods[];
+};
+
+static inline struct objio_segment *
+OBJIO_LSEG(struct pnfs_layout_segment *lseg)
+{
+	return container_of(lseg, struct objio_segment, lseg);
+}
+
+struct objio_state;
+typedef ssize_t (*objio_done_fn)(struct objio_state *ios);
+
+struct objio_state {
+	/* Generic layer */
+	struct objlayout_io_state ol_state;
+
+	struct objio_segment *layout;
+
+	struct kref kref;
+	objio_done_fn done;
+	void *private;
+
+	unsigned long length;
+	unsigned numdevs; /* Actually used devs in this IO */
+	/* A per-device variable array of size numdevs */
+	struct _objio_per_comp {
+		struct bio *bio;
+		struct osd_request *or;
+		unsigned long length;
+		u64 offset;
+		unsigned dev;
+	} per_dev[];
+};
+
+/* Send and wait for a get_device_info of devices in the layout,
+   then look them up with the osd_initiator library */
+static struct objio_dev_ent *_device_lookup(struct pnfs_layout_hdr *pnfslay,
+				struct objio_segment *objio_seg, unsigned comp,
+				gfp_t gfp_flags)
+{
+	struct pnfs_osd_deviceaddr *deviceaddr;
+	struct nfs4_deviceid *d_id;
+	struct objio_dev_ent *ode;
+	struct osd_dev *od;
+	struct osd_dev_info odi;
+	int err;
+
+	d_id = &objio_seg->comps[comp].oc_object_id.oid_device_id;
+
+	ode = _dev_list_find(NFS_SERVER(pnfslay->plh_inode), d_id);
+	if (ode)
+		return ode;
+
+	err = objlayout_get_deviceinfo(pnfslay, d_id, &deviceaddr, gfp_flags);
+	if (unlikely(err)) {
+		dprintk("%s: objlayout_get_deviceinfo dev(%llx:%llx) =>%d\n",
+			__func__, _DEVID_LO(d_id), _DEVID_HI(d_id), err);
+		return ERR_PTR(err);
+	}
+
+	odi.systemid_len = deviceaddr->oda_systemid.len;
+	if (odi.systemid_len > sizeof(odi.systemid)) {
+		err = -EINVAL;
+		goto out;
+	} else if (odi.systemid_len)
+		memcpy(odi.systemid, deviceaddr->oda_systemid.data,
+		       odi.systemid_len);
+	odi.osdname_len	 = deviceaddr->oda_osdname.len;
+	odi.osdname	 = (u8 *)deviceaddr->oda_osdname.data;
+
+	if (!odi.osdname_len && !odi.systemid_len) {
+		dprintk("%s: !odi.osdname_len && !odi.systemid_len\n",
+			__func__);
+		err = -ENODEV;
+		goto out;
+	}
+
+	od = osduld_info_lookup(&odi);
+	if (unlikely(IS_ERR(od))) {
+		err = PTR_ERR(od);
+		dprintk("%s: osduld_info_lookup => %d\n", __func__, err);
+		goto out;
+	}
+
+	ode = _dev_list_add(NFS_SERVER(pnfslay->plh_inode), d_id, od,
+			    gfp_flags);
+
+out:
+	dprintk("%s: return=%d\n", __func__, err);
+	objlayout_put_deviceinfo(deviceaddr);
+	return err ? ERR_PTR(err) : ode;
+}
+
+static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay,
+	struct objio_segment *objio_seg,
+	gfp_t gfp_flags)
+{
+	unsigned i;
+	int err;
+
+	/* lookup all devices */
+	for (i = 0; i < objio_seg->num_comps; i++) {
+		struct objio_dev_ent *ode;
+
+		ode = _device_lookup(pnfslay, objio_seg, i, gfp_flags);
+		if (unlikely(IS_ERR(ode))) {
+			err = PTR_ERR(ode);
+			goto out;
+		}
+		objio_seg->ods[i] = ode;
+	}
+	err = 0;
+
+out:
+	dprintk("%s: return=%d\n", __func__, err);
+	return err;
+}
+
+static int _verify_data_map(struct pnfs_osd_layout *layout)
+{
+	struct pnfs_osd_data_map *data_map = &layout->olo_map;
+	u64 stripe_length;
+	u32 group_width;
+
+/* FIXME: Only raid0 for now. if not go through MDS */
+	if (data_map->odm_raid_algorithm != PNFS_OSD_RAID_0) {
+		printk(KERN_ERR "Only RAID_0 for now\n");
+		return -ENOTSUPP;
+	}
+	if (0 != (data_map->odm_num_comps % (data_map->odm_mirror_cnt + 1))) {
+		printk(KERN_ERR "Data Map wrong, num_comps=%u mirrors=%u\n",
+			  data_map->odm_num_comps, data_map->odm_mirror_cnt);
+		return -EINVAL;
+	}
+
+	if (data_map->odm_group_width)
+		group_width = data_map->odm_group_width;
+	else
+		group_width = data_map->odm_num_comps /
+						(data_map->odm_mirror_cnt + 1);
+
+	stripe_length = (u64)data_map->odm_stripe_unit * group_width;
+	if (stripe_length >= (1ULL << 32)) {
+		printk(KERN_ERR "Total Stripe length(0x%llx)"
+			  " >= 32bit is not supported\n", _LLU(stripe_length));
+		return -ENOTSUPP;
+	}
+
+	if (0 != (data_map->odm_stripe_unit & ~PAGE_MASK)) {
+		printk(KERN_ERR "Stripe Unit(0x%llx)"
+			  " must be Multples of PAGE_SIZE(0x%lx)\n",
+			  _LLU(data_map->odm_stripe_unit), PAGE_SIZE);
+		return -ENOTSUPP;
+	}
+
+	return 0;
+}
+
+static void copy_single_comp(struct pnfs_osd_object_cred *cur_comp,
+			     struct pnfs_osd_object_cred *src_comp,
+			     struct caps_buffers *caps_p)
+{
+	WARN_ON(src_comp->oc_cap_key.cred_len > sizeof(caps_p->caps_key));
+	WARN_ON(src_comp->oc_cap.cred_len > sizeof(caps_p->creds));
+
+	*cur_comp = *src_comp;
+
+	memcpy(caps_p->caps_key, src_comp->oc_cap_key.cred,
+	       sizeof(caps_p->caps_key));
+	cur_comp->oc_cap_key.cred = caps_p->caps_key;
+
+	memcpy(caps_p->creds, src_comp->oc_cap.cred,
+	       sizeof(caps_p->creds));
+	cur_comp->oc_cap.cred = caps_p->creds;
+}
+
+int objio_alloc_lseg(struct pnfs_layout_segment **outp,
+	struct pnfs_layout_hdr *pnfslay,
+	struct pnfs_layout_range *range,
+	struct xdr_stream *xdr,
+	gfp_t gfp_flags)
+{
+	struct objio_segment *objio_seg;
+	struct pnfs_osd_xdr_decode_layout_iter iter;
+	struct pnfs_osd_layout layout;
+	struct pnfs_osd_object_cred *cur_comp, src_comp;
+	struct caps_buffers *caps_p;
+	int err;
+
+	err = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr);
+	if (unlikely(err))
+		return err;
+
+	err = _verify_data_map(&layout);
+	if (unlikely(err))
+		return err;
+
+	objio_seg = kzalloc(sizeof(*objio_seg) +
+			    sizeof(objio_seg->ods[0]) * layout.olo_num_comps +
+			    sizeof(*objio_seg->comps) * layout.olo_num_comps +
+			    sizeof(struct caps_buffers) * layout.olo_num_comps,
+			    gfp_flags);
+	if (!objio_seg)
+		return -ENOMEM;
+
+	objio_seg->comps = (void *)(objio_seg->ods + layout.olo_num_comps);
+	cur_comp = objio_seg->comps;
+	caps_p = (void *)(cur_comp + layout.olo_num_comps);
+	while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err))
+		copy_single_comp(cur_comp++, &src_comp, caps_p++);
+	if (unlikely(err))
+		goto err;
+
+	objio_seg->num_comps = layout.olo_num_comps;
+	objio_seg->comps_index = layout.olo_comps_index;
+	err = objio_devices_lookup(pnfslay, objio_seg, gfp_flags);
+	if (err)
+		goto err;
+
+	objio_seg->mirrors_p1 = layout.olo_map.odm_mirror_cnt + 1;
+	objio_seg->stripe_unit = layout.olo_map.odm_stripe_unit;
+	if (layout.olo_map.odm_group_width) {
+		objio_seg->group_width = layout.olo_map.odm_group_width;
+		objio_seg->group_depth = layout.olo_map.odm_group_depth;
+		objio_seg->group_count = layout.olo_map.odm_num_comps /
+						objio_seg->mirrors_p1 /
+						objio_seg->group_width;
+	} else {
+		objio_seg->group_width = layout.olo_map.odm_num_comps /
+						objio_seg->mirrors_p1;
+		objio_seg->group_depth = -1;
+		objio_seg->group_count = 1;
+	}
+
+	/* Cache this calculation it will hit for every page */
+	objio_seg->max_io_size = (BIO_MAX_PAGES_KMALLOC * PAGE_SIZE -
+				  objio_seg->stripe_unit) *
+				 objio_seg->group_width;
+
+	*outp = &objio_seg->lseg;
+	return 0;
+
+err:
+	kfree(objio_seg);
+	dprintk("%s: Error: return %d\n", __func__, err);
+	*outp = NULL;
+	return err;
+}
+
+void objio_free_lseg(struct pnfs_layout_segment *lseg)
+{
+	int i;
+	struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
+
+	for (i = 0; i < objio_seg->num_comps; i++) {
+		if (!objio_seg->ods[i])
+			break;
+		nfs4_put_deviceid_node(&objio_seg->ods[i]->id_node);
+	}
+	kfree(objio_seg);
+}
+
+int objio_alloc_io_state(struct pnfs_layout_segment *lseg,
+			 struct objlayout_io_state **outp,
+			 gfp_t gfp_flags)
+{
+	struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
+	struct objio_state *ios;
+	const unsigned first_size = sizeof(*ios) +
+				objio_seg->num_comps * sizeof(ios->per_dev[0]);
+	const unsigned sec_size = objio_seg->num_comps *
+						sizeof(ios->ol_state.ioerrs[0]);
+
+	ios = kzalloc(first_size + sec_size, gfp_flags);
+	if (unlikely(!ios))
+		return -ENOMEM;
+
+	ios->layout = objio_seg;
+	ios->ol_state.ioerrs = ((void *)ios) + first_size;
+	ios->ol_state.num_comps = objio_seg->num_comps;
+
+	*outp = &ios->ol_state;
+	return 0;
+}
+
+void objio_free_io_state(struct objlayout_io_state *ol_state)
+{
+	struct objio_state *ios = container_of(ol_state, struct objio_state,
+					       ol_state);
+
+	kfree(ios);
+}
+
+enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
+{
+	switch (oep) {
+	case OSD_ERR_PRI_NO_ERROR:
+		return (enum pnfs_osd_errno)0;
+
+	case OSD_ERR_PRI_CLEAR_PAGES:
+		BUG_ON(1);
+		return 0;
+
+	case OSD_ERR_PRI_RESOURCE:
+		return PNFS_OSD_ERR_RESOURCE;
+	case OSD_ERR_PRI_BAD_CRED:
+		return PNFS_OSD_ERR_BAD_CRED;
+	case OSD_ERR_PRI_NO_ACCESS:
+		return PNFS_OSD_ERR_NO_ACCESS;
+	case OSD_ERR_PRI_UNREACHABLE:
+		return PNFS_OSD_ERR_UNREACHABLE;
+	case OSD_ERR_PRI_NOT_FOUND:
+		return PNFS_OSD_ERR_NOT_FOUND;
+	case OSD_ERR_PRI_NO_SPACE:
+		return PNFS_OSD_ERR_NO_SPACE;
+	default:
+		WARN_ON(1);
+		/* fallthrough */
+	case OSD_ERR_PRI_EIO:
+		return PNFS_OSD_ERR_EIO;
+	}
+}
+
+static void _clear_bio(struct bio *bio)
+{
+	struct bio_vec *bv;
+	unsigned i;
+
+	__bio_for_each_segment(bv, bio, i, 0) {
+		unsigned this_count = bv->bv_len;
+
+		if (likely(PAGE_SIZE == this_count))
+			clear_highpage(bv->bv_page);
+		else
+			zero_user(bv->bv_page, bv->bv_offset, this_count);
+	}
+}
+
+static int _io_check(struct objio_state *ios, bool is_write)
+{
+	enum osd_err_priority oep = OSD_ERR_PRI_NO_ERROR;
+	int lin_ret = 0;
+	int i;
+
+	for (i = 0; i <  ios->numdevs; i++) {
+		struct osd_sense_info osi;
+		struct osd_request *or = ios->per_dev[i].or;
+		unsigned dev;
+		int ret;
+
+		if (!or)
+			continue;
+
+		ret = osd_req_decode_sense(or, &osi);
+		if (likely(!ret))
+			continue;
+
+		if (OSD_ERR_PRI_CLEAR_PAGES == osi.osd_err_pri) {
+			/* start read offset passed endof file */
+			BUG_ON(is_write);
+			_clear_bio(ios->per_dev[i].bio);
+			dprintk("%s: start read offset passed end of file "
+				"offset=0x%llx, length=0x%lx\n", __func__,
+				_LLU(ios->per_dev[i].offset),
+				ios->per_dev[i].length);
+
+			continue; /* we recovered */
+		}
+		dev = ios->per_dev[i].dev;
+		objlayout_io_set_result(&ios->ol_state, dev,
+					&ios->layout->comps[dev].oc_object_id,
+					osd_pri_2_pnfs_err(osi.osd_err_pri),
+					ios->per_dev[i].offset,
+					ios->per_dev[i].length,
+					is_write);
+
+		if (osi.osd_err_pri >= oep) {
+			oep = osi.osd_err_pri;
+			lin_ret = ret;
+		}
+	}
+
+	return lin_ret;
+}
+
+/*
+ * Common IO state helpers.
+ */
+static void _io_free(struct objio_state *ios)
+{
+	unsigned i;
+
+	for (i = 0; i < ios->numdevs; i++) {
+		struct _objio_per_comp *per_dev = &ios->per_dev[i];
+
+		if (per_dev->or) {
+			osd_end_request(per_dev->or);
+			per_dev->or = NULL;
+		}
+
+		if (per_dev->bio) {
+			bio_put(per_dev->bio);
+			per_dev->bio = NULL;
+		}
+	}
+}
+
+struct osd_dev *_io_od(struct objio_state *ios, unsigned dev)
+{
+	unsigned min_dev = ios->layout->comps_index;
+	unsigned max_dev = min_dev + ios->layout->num_comps;
+
+	BUG_ON(dev < min_dev || max_dev <= dev);
+	return ios->layout->ods[dev - min_dev]->od;
+}
+
+struct _striping_info {
+	u64 obj_offset;
+	u64 group_length;
+	unsigned dev;
+	unsigned unit_off;
+};
+
+static void _calc_stripe_info(struct objio_state *ios, u64 file_offset,
+			      struct _striping_info *si)
+{
+	u32	stripe_unit = ios->layout->stripe_unit;
+	u32	group_width = ios->layout->group_width;
+	u64	group_depth = ios->layout->group_depth;
+	u32	U = stripe_unit * group_width;
+
+	u64	T = U * group_depth;
+	u64	S = T * ios->layout->group_count;
+	u64	M = div64_u64(file_offset, S);
+
+	/*
+	G = (L - (M * S)) / T
+	H = (L - (M * S)) % T
+	*/
+	u64	LmodU = file_offset - M * S;
+	u32	G = div64_u64(LmodU, T);
+	u64	H = LmodU - G * T;
+
+	u32	N = div_u64(H, U);
+
+	div_u64_rem(file_offset, stripe_unit, &si->unit_off);
+	si->obj_offset = si->unit_off + (N * stripe_unit) +
+				  (M * group_depth * stripe_unit);
+
+	/* "H - (N * U)" is just "H % U" so it's bound to u32 */
+	si->dev = (u32)(H - (N * U)) / stripe_unit + G * group_width;
+	si->dev *= ios->layout->mirrors_p1;
+
+	si->group_length = T - H;
+}
+
+static int _add_stripe_unit(struct objio_state *ios,  unsigned *cur_pg,
+		unsigned pgbase, struct _objio_per_comp *per_dev, int cur_len,
+		gfp_t gfp_flags)
+{
+	unsigned pg = *cur_pg;
+	struct request_queue *q =
+			osd_request_queue(_io_od(ios, per_dev->dev));
+
+	per_dev->length += cur_len;
+
+	if (per_dev->bio == NULL) {
+		unsigned stripes = ios->layout->num_comps /
+						     ios->layout->mirrors_p1;
+		unsigned pages_in_stripe = stripes *
+				      (ios->layout->stripe_unit / PAGE_SIZE);
+		unsigned bio_size = (ios->ol_state.nr_pages + pages_in_stripe) /
+				    stripes;
+
+		if (BIO_MAX_PAGES_KMALLOC < bio_size)
+			bio_size = BIO_MAX_PAGES_KMALLOC;
+
+		per_dev->bio = bio_kmalloc(gfp_flags, bio_size);
+		if (unlikely(!per_dev->bio)) {
+			dprintk("Faild to allocate BIO size=%u\n", bio_size);
+			return -ENOMEM;
+		}
+	}
+
+	while (cur_len > 0) {
+		unsigned pglen = min_t(unsigned, PAGE_SIZE - pgbase, cur_len);
+		unsigned added_len;
+
+		BUG_ON(ios->ol_state.nr_pages <= pg);
+		cur_len -= pglen;
+
+		added_len = bio_add_pc_page(q, per_dev->bio,
+					ios->ol_state.pages[pg], pglen, pgbase);
+		if (unlikely(pglen != added_len))
+			return -ENOMEM;
+		pgbase = 0;
+		++pg;
+	}
+	BUG_ON(cur_len);
+
+	*cur_pg = pg;
+	return 0;
+}
+
+static int _prepare_one_group(struct objio_state *ios, u64 length,
+			      struct _striping_info *si, unsigned *last_pg,
+			      gfp_t gfp_flags)
+{
+	unsigned stripe_unit = ios->layout->stripe_unit;
+	unsigned mirrors_p1 = ios->layout->mirrors_p1;
+	unsigned devs_in_group = ios->layout->group_width * mirrors_p1;
+	unsigned dev = si->dev;
+	unsigned first_dev = dev - (dev % devs_in_group);
+	unsigned max_comp = ios->numdevs ? ios->numdevs - mirrors_p1 : 0;
+	unsigned cur_pg = *last_pg;
+	int ret = 0;
+
+	while (length) {
+		struct _objio_per_comp *per_dev = &ios->per_dev[dev];
+		unsigned cur_len, page_off = 0;
+
+		if (!per_dev->length) {
+			per_dev->dev = dev;
+			if (dev < si->dev) {
+				per_dev->offset = si->obj_offset + stripe_unit -
+								   si->unit_off;
+				cur_len = stripe_unit;
+			} else if (dev == si->dev) {
+				per_dev->offset = si->obj_offset;
+				cur_len = stripe_unit - si->unit_off;
+				page_off = si->unit_off & ~PAGE_MASK;
+				BUG_ON(page_off &&
+				      (page_off != ios->ol_state.pgbase));
+			} else { /* dev > si->dev */
+				per_dev->offset = si->obj_offset - si->unit_off;
+				cur_len = stripe_unit;
+			}
+
+			if (max_comp < dev)
+				max_comp = dev;
+		} else {
+			cur_len = stripe_unit;
+		}
+		if (cur_len >= length)
+			cur_len = length;
+
+		ret = _add_stripe_unit(ios, &cur_pg, page_off , per_dev,
+				       cur_len, gfp_flags);
+		if (unlikely(ret))
+			goto out;
+
+		dev += mirrors_p1;
+		dev = (dev % devs_in_group) + first_dev;
+
+		length -= cur_len;
+		ios->length += cur_len;
+	}
+out:
+	ios->numdevs = max_comp + mirrors_p1;
+	*last_pg = cur_pg;
+	return ret;
+}
+
+static int _io_rw_pagelist(struct objio_state *ios, gfp_t gfp_flags)
+{
+	u64 length = ios->ol_state.count;
+	u64 offset = ios->ol_state.offset;
+	struct _striping_info si;
+	unsigned last_pg = 0;
+	int ret = 0;
+
+	while (length) {
+		_calc_stripe_info(ios, offset, &si);
+
+		if (length < si.group_length)
+			si.group_length = length;
+
+		ret = _prepare_one_group(ios, si.group_length, &si, &last_pg, gfp_flags);
+		if (unlikely(ret))
+			goto out;
+
+		offset += si.group_length;
+		length -= si.group_length;
+	}
+
+out:
+	if (!ios->length)
+		return ret;
+
+	return 0;
+}
+
+static ssize_t _sync_done(struct objio_state *ios)
+{
+	struct completion *waiting = ios->private;
+
+	complete(waiting);
+	return 0;
+}
+
+static void _last_io(struct kref *kref)
+{
+	struct objio_state *ios = container_of(kref, struct objio_state, kref);
+
+	ios->done(ios);
+}
+
+static void _done_io(struct osd_request *or, void *p)
+{
+	struct objio_state *ios = p;
+
+	kref_put(&ios->kref, _last_io);
+}
+
+static ssize_t _io_exec(struct objio_state *ios)
+{
+	DECLARE_COMPLETION_ONSTACK(wait);
+	ssize_t status = 0; /* sync status */
+	unsigned i;
+	objio_done_fn saved_done_fn = ios->done;
+	bool sync = ios->ol_state.sync;
+
+	if (sync) {
+		ios->done = _sync_done;
+		ios->private = &wait;
+	}
+
+	kref_init(&ios->kref);
+
+	for (i = 0; i < ios->numdevs; i++) {
+		struct osd_request *or = ios->per_dev[i].or;
+
+		if (!or)
+			continue;
+
+		kref_get(&ios->kref);
+		osd_execute_request_async(or, _done_io, ios);
+	}
+
+	kref_put(&ios->kref, _last_io);
+
+	if (sync) {
+		wait_for_completion(&wait);
+		status = saved_done_fn(ios);
+	}
+
+	return status;
+}
+
+/*
+ * read
+ */
+static ssize_t _read_done(struct objio_state *ios)
+{
+	ssize_t status;
+	int ret = _io_check(ios, false);
+
+	_io_free(ios);
+
+	if (likely(!ret))
+		status = ios->length;
+	else
+		status = ret;
+
+	objlayout_read_done(&ios->ol_state, status, ios->ol_state.sync);
+	return status;
+}
+
+static int _read_mirrors(struct objio_state *ios, unsigned cur_comp)
+{
+	struct osd_request *or = NULL;
+	struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp];
+	unsigned dev = per_dev->dev;
+	struct pnfs_osd_object_cred *cred =
+			&ios->layout->comps[dev];
+	struct osd_obj_id obj = {
+		.partition = cred->oc_object_id.oid_partition_id,
+		.id = cred->oc_object_id.oid_object_id,
+	};
+	int ret;
+
+	or = osd_start_request(_io_od(ios, dev), GFP_KERNEL);
+	if (unlikely(!or)) {
+		ret = -ENOMEM;
+		goto err;
+	}
+	per_dev->or = or;
+
+	osd_req_read(or, &obj, per_dev->offset, per_dev->bio, per_dev->length);
+
+	ret = osd_finalize_request(or, 0, cred->oc_cap.cred, NULL);
+	if (ret) {
+		dprintk("%s: Faild to osd_finalize_request() => %d\n",
+			__func__, ret);
+		goto err;
+	}
+
+	dprintk("%s:[%d] dev=%d obj=0x%llx start=0x%llx length=0x%lx\n",
+		__func__, cur_comp, dev, obj.id, _LLU(per_dev->offset),
+		per_dev->length);
+
+err:
+	return ret;
+}
+
+static ssize_t _read_exec(struct objio_state *ios)
+{
+	unsigned i;
+	int ret;
+
+	for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) {
+		if (!ios->per_dev[i].length)
+			continue;
+		ret = _read_mirrors(ios, i);
+		if (unlikely(ret))
+			goto err;
+	}
+
+	ios->done = _read_done;
+	return _io_exec(ios); /* In sync mode exec returns the io status */
+
+err:
+	_io_free(ios);
+	return ret;
+}
+
+ssize_t objio_read_pagelist(struct objlayout_io_state *ol_state)
+{
+	struct objio_state *ios = container_of(ol_state, struct objio_state,
+					       ol_state);
+	int ret;
+
+	ret = _io_rw_pagelist(ios, GFP_KERNEL);
+	if (unlikely(ret))
+		return ret;
+
+	return _read_exec(ios);
+}
+
+/*
+ * write
+ */
+static ssize_t _write_done(struct objio_state *ios)
+{
+	ssize_t status;
+	int ret = _io_check(ios, true);
+
+	_io_free(ios);
+
+	if (likely(!ret)) {
+		/* FIXME: should be based on the OSD's persistence model
+		 * See OSD2r05 Section 4.13 Data persistence model */
+		ios->ol_state.committed = NFS_FILE_SYNC;
+		status = ios->length;
+	} else {
+		status = ret;
+	}
+
+	objlayout_write_done(&ios->ol_state, status, ios->ol_state.sync);
+	return status;
+}
+
+static int _write_mirrors(struct objio_state *ios, unsigned cur_comp)
+{
+	struct _objio_per_comp *master_dev = &ios->per_dev[cur_comp];
+	unsigned dev = ios->per_dev[cur_comp].dev;
+	unsigned last_comp = cur_comp + ios->layout->mirrors_p1;
+	int ret;
+
+	for (; cur_comp < last_comp; ++cur_comp, ++dev) {
+		struct osd_request *or = NULL;
+		struct pnfs_osd_object_cred *cred =
+					&ios->layout->comps[dev];
+		struct osd_obj_id obj = {
+			.partition = cred->oc_object_id.oid_partition_id,
+			.id = cred->oc_object_id.oid_object_id,
+		};
+		struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp];
+		struct bio *bio;
+
+		or = osd_start_request(_io_od(ios, dev), GFP_NOFS);
+		if (unlikely(!or)) {
+			ret = -ENOMEM;
+			goto err;
+		}
+		per_dev->or = or;
+
+		if (per_dev != master_dev) {
+			bio = bio_kmalloc(GFP_NOFS,
+					  master_dev->bio->bi_max_vecs);
+			if (unlikely(!bio)) {
+				dprintk("Faild to allocate BIO size=%u\n",
+					master_dev->bio->bi_max_vecs);
+				ret = -ENOMEM;
+				goto err;
+			}
+
+			__bio_clone(bio, master_dev->bio);
+			bio->bi_bdev = NULL;
+			bio->bi_next = NULL;
+			per_dev->bio = bio;
+			per_dev->dev = dev;
+			per_dev->length = master_dev->length;
+			per_dev->offset =  master_dev->offset;
+		} else {
+			bio = master_dev->bio;
+			bio->bi_rw |= REQ_WRITE;
+		}
+
+		osd_req_write(or, &obj, per_dev->offset, bio, per_dev->length);
+
+		ret = osd_finalize_request(or, 0, cred->oc_cap.cred, NULL);
+		if (ret) {
+			dprintk("%s: Faild to osd_finalize_request() => %d\n",
+				__func__, ret);
+			goto err;
+		}
+
+		dprintk("%s:[%d] dev=%d obj=0x%llx start=0x%llx length=0x%lx\n",
+			__func__, cur_comp, dev, obj.id, _LLU(per_dev->offset),
+			per_dev->length);
+	}
+
+err:
+	return ret;
+}
+
+static ssize_t _write_exec(struct objio_state *ios)
+{
+	unsigned i;
+	int ret;
+
+	for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) {
+		if (!ios->per_dev[i].length)
+			continue;
+		ret = _write_mirrors(ios, i);
+		if (unlikely(ret))
+			goto err;
+	}
+
+	ios->done = _write_done;
+	return _io_exec(ios); /* In sync mode exec returns the io->status */
+
+err:
+	_io_free(ios);
+	return ret;
+}
+
+ssize_t objio_write_pagelist(struct objlayout_io_state *ol_state, bool stable)
+{
+	struct objio_state *ios = container_of(ol_state, struct objio_state,
+					       ol_state);
+	int ret;
+
+	/* TODO: ios->stable = stable; */
+	ret = _io_rw_pagelist(ios, GFP_NOFS);
+	if (unlikely(ret))
+		return ret;
+
+	return _write_exec(ios);
+}
+
+static bool objio_pg_test(struct nfs_pageio_descriptor *pgio,
+			  struct nfs_page *prev, struct nfs_page *req)
+{
+	if (!pnfs_generic_pg_test(pgio, prev, req))
+		return false;
+
+	if (pgio->pg_lseg == NULL)
+		return true;
+
+	return pgio->pg_count + req->wb_bytes <=
+			OBJIO_LSEG(pgio->pg_lseg)->max_io_size;
+}
+
+static struct pnfs_layoutdriver_type objlayout_type = {
+	.id = LAYOUT_OSD2_OBJECTS,
+	.name = "LAYOUT_OSD2_OBJECTS",
+	.flags                   = PNFS_LAYOUTRET_ON_SETATTR,
+
+	.alloc_layout_hdr        = objlayout_alloc_layout_hdr,
+	.free_layout_hdr         = objlayout_free_layout_hdr,
+
+	.alloc_lseg              = objlayout_alloc_lseg,
+	.free_lseg               = objlayout_free_lseg,
+
+	.read_pagelist           = objlayout_read_pagelist,
+	.write_pagelist          = objlayout_write_pagelist,
+	.pg_test                 = objio_pg_test,
+
+	.free_deviceid_node	 = objio_free_deviceid_node,
+
+	.encode_layoutcommit	 = objlayout_encode_layoutcommit,
+	.encode_layoutreturn     = objlayout_encode_layoutreturn,
+};
+
+MODULE_DESCRIPTION("pNFS Layout Driver for OSD2 objects");
+MODULE_AUTHOR("Benny Halevy <bhalevy@panasas.com>");
+MODULE_LICENSE("GPL");
+
+static int __init
+objlayout_init(void)
+{
+	int ret = pnfs_register_layoutdriver(&objlayout_type);
+
+	if (ret)
+		printk(KERN_INFO
+			"%s: Registering OSD pNFS Layout Driver failed: error=%d\n",
+			__func__, ret);
+	else
+		printk(KERN_INFO "%s: Registered OSD pNFS Layout Driver\n",
+			__func__);
+	return ret;
+}
+
+static void __exit
+objlayout_exit(void)
+{
+	pnfs_unregister_layoutdriver(&objlayout_type);
+	printk(KERN_INFO "%s: Unregistered OSD pNFS Layout Driver\n",
+	       __func__);
+}
+
+module_init(objlayout_init);
+module_exit(objlayout_exit);
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
new file mode 100644
index 000000000000..1d06f8e2adea
--- /dev/null
+++ b/fs/nfs/objlayout/objlayout.c
@@ -0,0 +1,712 @@
+/*
+ *  pNFS Objects layout driver high level definitions
+ *
+ *  Copyright (C) 2007 Panasas Inc. [year of first publication]
+ *  All rights reserved.
+ *
+ *  Benny Halevy <bhalevy@panasas.com>
+ *  Boaz Harrosh <bharrosh@panasas.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
+ *  See the file COPYING included with this distribution for more details.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the Panasas company nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <scsi/osd_initiator.h>
+#include "objlayout.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+/*
+ * Create a objlayout layout structure for the given inode and return it.
+ */
+struct pnfs_layout_hdr *
+objlayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
+{
+	struct objlayout *objlay;
+
+	objlay = kzalloc(sizeof(struct objlayout), gfp_flags);
+	if (objlay) {
+		spin_lock_init(&objlay->lock);
+		INIT_LIST_HEAD(&objlay->err_list);
+	}
+	dprintk("%s: Return %p\n", __func__, objlay);
+	return &objlay->pnfs_layout;
+}
+
+/*
+ * Free an objlayout layout structure
+ */
+void
+objlayout_free_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+	struct objlayout *objlay = OBJLAYOUT(lo);
+
+	dprintk("%s: objlay %p\n", __func__, objlay);
+
+	WARN_ON(!list_empty(&objlay->err_list));
+	kfree(objlay);
+}
+
+/*
+ * Unmarshall layout and store it in pnfslay.
+ */
+struct pnfs_layout_segment *
+objlayout_alloc_lseg(struct pnfs_layout_hdr *pnfslay,
+		     struct nfs4_layoutget_res *lgr,
+		     gfp_t gfp_flags)
+{
+	int status = -ENOMEM;
+	struct xdr_stream stream;
+	struct xdr_buf buf = {
+		.pages =  lgr->layoutp->pages,
+		.page_len =  lgr->layoutp->len,
+		.buflen =  lgr->layoutp->len,
+		.len = lgr->layoutp->len,
+	};
+	struct page *scratch;
+	struct pnfs_layout_segment *lseg;
+
+	dprintk("%s: Begin pnfslay %p\n", __func__, pnfslay);
+
+	scratch = alloc_page(gfp_flags);
+	if (!scratch)
+		goto err_nofree;
+
+	xdr_init_decode(&stream, &buf, NULL);
+	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
+
+	status = objio_alloc_lseg(&lseg, pnfslay, &lgr->range, &stream, gfp_flags);
+	if (unlikely(status)) {
+		dprintk("%s: objio_alloc_lseg Return err %d\n", __func__,
+			status);
+		goto err;
+	}
+
+	__free_page(scratch);
+
+	dprintk("%s: Return %p\n", __func__, lseg);
+	return lseg;
+
+err:
+	__free_page(scratch);
+err_nofree:
+	dprintk("%s: Err Return=>%d\n", __func__, status);
+	return ERR_PTR(status);
+}
+
+/*
+ * Free a layout segement
+ */
+void
+objlayout_free_lseg(struct pnfs_layout_segment *lseg)
+{
+	dprintk("%s: freeing layout segment %p\n", __func__, lseg);
+
+	if (unlikely(!lseg))
+		return;
+
+	objio_free_lseg(lseg);
+}
+
+/*
+ * I/O Operations
+ */
+static inline u64
+end_offset(u64 start, u64 len)
+{
+	u64 end;
+
+	end = start + len;
+	return end >= start ? end : NFS4_MAX_UINT64;
+}
+
+/* last octet in a range */
+static inline u64
+last_byte_offset(u64 start, u64 len)
+{
+	u64 end;
+
+	BUG_ON(!len);
+	end = start + len;
+	return end > start ? end - 1 : NFS4_MAX_UINT64;
+}
+
+static struct objlayout_io_state *
+objlayout_alloc_io_state(struct pnfs_layout_hdr *pnfs_layout_type,
+			struct page **pages,
+			unsigned pgbase,
+			loff_t offset,
+			size_t count,
+			struct pnfs_layout_segment *lseg,
+			void *rpcdata,
+			gfp_t gfp_flags)
+{
+	struct objlayout_io_state *state;
+	u64 lseg_end_offset;
+
+	dprintk("%s: allocating io_state\n", __func__);
+	if (objio_alloc_io_state(lseg, &state, gfp_flags))
+		return NULL;
+
+	BUG_ON(offset < lseg->pls_range.offset);
+	lseg_end_offset = end_offset(lseg->pls_range.offset,
+				     lseg->pls_range.length);
+	BUG_ON(offset >= lseg_end_offset);
+	if (offset + count > lseg_end_offset) {
+		count = lseg->pls_range.length -
+				(offset - lseg->pls_range.offset);
+		dprintk("%s: truncated count %Zd\n", __func__, count);
+	}
+
+	if (pgbase > PAGE_SIZE) {
+		pages += pgbase >> PAGE_SHIFT;
+		pgbase &= ~PAGE_MASK;
+	}
+
+	INIT_LIST_HEAD(&state->err_list);
+	state->lseg = lseg;
+	state->rpcdata = rpcdata;
+	state->pages = pages;
+	state->pgbase = pgbase;
+	state->nr_pages = (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	state->offset = offset;
+	state->count = count;
+	state->sync = 0;
+
+	return state;
+}
+
+static void
+objlayout_free_io_state(struct objlayout_io_state *state)
+{
+	dprintk("%s: freeing io_state\n", __func__);
+	if (unlikely(!state))
+		return;
+
+	objio_free_io_state(state);
+}
+
+/*
+ * I/O done common code
+ */
+static void
+objlayout_iodone(struct objlayout_io_state *state)
+{
+	dprintk("%s: state %p status\n", __func__, state);
+
+	if (likely(state->status >= 0)) {
+		objlayout_free_io_state(state);
+	} else {
+		struct objlayout *objlay = OBJLAYOUT(state->lseg->pls_layout);
+
+		spin_lock(&objlay->lock);
+		objlay->delta_space_valid = OBJ_DSU_INVALID;
+		list_add(&objlay->err_list, &state->err_list);
+		spin_unlock(&objlay->lock);
+	}
+}
+
+/*
+ * objlayout_io_set_result - Set an osd_error code on a specific osd comp.
+ *
+ * The @index component IO failed (error returned from target). Register
+ * the error for later reporting at layout-return.
+ */
+void
+objlayout_io_set_result(struct objlayout_io_state *state, unsigned index,
+			struct pnfs_osd_objid *pooid, int osd_error,
+			u64 offset, u64 length, bool is_write)
+{
+	struct pnfs_osd_ioerr *ioerr = &state->ioerrs[index];
+
+	BUG_ON(index >= state->num_comps);
+	if (osd_error) {
+		ioerr->oer_component = *pooid;
+		ioerr->oer_comp_offset = offset;
+		ioerr->oer_comp_length = length;
+		ioerr->oer_iswrite = is_write;
+		ioerr->oer_errno = osd_error;
+
+		dprintk("%s: err[%d]: errno=%d is_write=%d dev(%llx:%llx) "
+			"par=0x%llx obj=0x%llx offset=0x%llx length=0x%llx\n",
+			__func__, index, ioerr->oer_errno,
+			ioerr->oer_iswrite,
+			_DEVID_LO(&ioerr->oer_component.oid_device_id),
+			_DEVID_HI(&ioerr->oer_component.oid_device_id),
+			ioerr->oer_component.oid_partition_id,
+			ioerr->oer_component.oid_object_id,
+			ioerr->oer_comp_offset,
+			ioerr->oer_comp_length);
+	} else {
+		/* User need not call if no error is reported */
+		ioerr->oer_errno = 0;
+	}
+}
+
+/* Function scheduled on rpc workqueue to call ->nfs_readlist_complete().
+ * This is because the osd completion is called with ints-off from
+ * the block layer
+ */
+static void _rpc_read_complete(struct work_struct *work)
+{
+	struct rpc_task *task;
+	struct nfs_read_data *rdata;
+
+	dprintk("%s enter\n", __func__);
+	task = container_of(work, struct rpc_task, u.tk_work);
+	rdata = container_of(task, struct nfs_read_data, task);
+
+	pnfs_ld_read_done(rdata);
+}
+
+void
+objlayout_read_done(struct objlayout_io_state *state, ssize_t status, bool sync)
+{
+	int eof = state->eof;
+	struct nfs_read_data *rdata;
+
+	state->status = status;
+	dprintk("%s: Begin status=%zd eof=%d\n", __func__, status, eof);
+	rdata = state->rpcdata;
+	rdata->task.tk_status = status;
+	if (status >= 0) {
+		rdata->res.count = status;
+		rdata->res.eof = eof;
+	}
+	objlayout_iodone(state);
+	/* must not use state after this point */
+
+	if (sync)
+		pnfs_ld_read_done(rdata);
+	else {
+		INIT_WORK(&rdata->task.u.tk_work, _rpc_read_complete);
+		schedule_work(&rdata->task.u.tk_work);
+	}
+}
+
+/*
+ * Perform sync or async reads.
+ */
+enum pnfs_try_status
+objlayout_read_pagelist(struct nfs_read_data *rdata)
+{
+	loff_t offset = rdata->args.offset;
+	size_t count = rdata->args.count;
+	struct objlayout_io_state *state;
+	ssize_t status = 0;
+	loff_t eof;
+
+	dprintk("%s: Begin inode %p offset %llu count %d\n",
+		__func__, rdata->inode, offset, (int)count);
+
+	eof = i_size_read(rdata->inode);
+	if (unlikely(offset + count > eof)) {
+		if (offset >= eof) {
+			status = 0;
+			rdata->res.count = 0;
+			rdata->res.eof = 1;
+			goto out;
+		}
+		count = eof - offset;
+	}
+
+	state = objlayout_alloc_io_state(NFS_I(rdata->inode)->layout,
+					 rdata->args.pages, rdata->args.pgbase,
+					 offset, count,
+					 rdata->lseg, rdata,
+					 GFP_KERNEL);
+	if (unlikely(!state)) {
+		status = -ENOMEM;
+		goto out;
+	}
+
+	state->eof = state->offset + state->count >= eof;
+
+	status = objio_read_pagelist(state);
+ out:
+	dprintk("%s: Return status %Zd\n", __func__, status);
+	rdata->pnfs_error = status;
+	return PNFS_ATTEMPTED;
+}
+
+/* Function scheduled on rpc workqueue to call ->nfs_writelist_complete().
+ * This is because the osd completion is called with ints-off from
+ * the block layer
+ */
+static void _rpc_write_complete(struct work_struct *work)
+{
+	struct rpc_task *task;
+	struct nfs_write_data *wdata;
+
+	dprintk("%s enter\n", __func__);
+	task = container_of(work, struct rpc_task, u.tk_work);
+	wdata = container_of(task, struct nfs_write_data, task);
+
+	pnfs_ld_write_done(wdata);
+}
+
+void
+objlayout_write_done(struct objlayout_io_state *state, ssize_t status,
+		     bool sync)
+{
+	struct nfs_write_data *wdata;
+
+	dprintk("%s: Begin\n", __func__);
+	wdata = state->rpcdata;
+	state->status = status;
+	wdata->task.tk_status = status;
+	if (status >= 0) {
+		wdata->res.count = status;
+		wdata->verf.committed = state->committed;
+		dprintk("%s: Return status %d committed %d\n",
+			__func__, wdata->task.tk_status,
+			wdata->verf.committed);
+	} else
+		dprintk("%s: Return status %d\n",
+			__func__, wdata->task.tk_status);
+	objlayout_iodone(state);
+	/* must not use state after this point */
+
+	if (sync)
+		pnfs_ld_write_done(wdata);
+	else {
+		INIT_WORK(&wdata->task.u.tk_work, _rpc_write_complete);
+		schedule_work(&wdata->task.u.tk_work);
+	}
+}
+
+/*
+ * Perform sync or async writes.
+ */
+enum pnfs_try_status
+objlayout_write_pagelist(struct nfs_write_data *wdata,
+			 int how)
+{
+	struct objlayout_io_state *state;
+	ssize_t status;
+
+	dprintk("%s: Begin inode %p offset %llu count %u\n",
+		__func__, wdata->inode, wdata->args.offset, wdata->args.count);
+
+	state = objlayout_alloc_io_state(NFS_I(wdata->inode)->layout,
+					 wdata->args.pages,
+					 wdata->args.pgbase,
+					 wdata->args.offset,
+					 wdata->args.count,
+					 wdata->lseg, wdata,
+					 GFP_NOFS);
+	if (unlikely(!state)) {
+		status = -ENOMEM;
+		goto out;
+	}
+
+	state->sync = how & FLUSH_SYNC;
+
+	status = objio_write_pagelist(state, how & FLUSH_STABLE);
+ out:
+	dprintk("%s: Return status %Zd\n", __func__, status);
+	wdata->pnfs_error = status;
+	return PNFS_ATTEMPTED;
+}
+
+void
+objlayout_encode_layoutcommit(struct pnfs_layout_hdr *pnfslay,
+			      struct xdr_stream *xdr,
+			      const struct nfs4_layoutcommit_args *args)
+{
+	struct objlayout *objlay = OBJLAYOUT(pnfslay);
+	struct pnfs_osd_layoutupdate lou;
+	__be32 *start;
+
+	dprintk("%s: Begin\n", __func__);
+
+	spin_lock(&objlay->lock);
+	lou.dsu_valid = (objlay->delta_space_valid == OBJ_DSU_VALID);
+	lou.dsu_delta = objlay->delta_space_used;
+	objlay->delta_space_used = 0;
+	objlay->delta_space_valid = OBJ_DSU_INIT;
+	lou.olu_ioerr_flag = !list_empty(&objlay->err_list);
+	spin_unlock(&objlay->lock);
+
+	start = xdr_reserve_space(xdr, 4);
+
+	BUG_ON(pnfs_osd_xdr_encode_layoutupdate(xdr, &lou));
+
+	*start = cpu_to_be32((xdr->p - start - 1) * 4);
+
+	dprintk("%s: Return delta_space_used %lld err %d\n", __func__,
+		lou.dsu_delta, lou.olu_ioerr_flag);
+}
+
+static int
+err_prio(u32 oer_errno)
+{
+	switch (oer_errno) {
+	case 0:
+		return 0;
+
+	case PNFS_OSD_ERR_RESOURCE:
+		return OSD_ERR_PRI_RESOURCE;
+	case PNFS_OSD_ERR_BAD_CRED:
+		return OSD_ERR_PRI_BAD_CRED;
+	case PNFS_OSD_ERR_NO_ACCESS:
+		return OSD_ERR_PRI_NO_ACCESS;
+	case PNFS_OSD_ERR_UNREACHABLE:
+		return OSD_ERR_PRI_UNREACHABLE;
+	case PNFS_OSD_ERR_NOT_FOUND:
+		return OSD_ERR_PRI_NOT_FOUND;
+	case PNFS_OSD_ERR_NO_SPACE:
+		return OSD_ERR_PRI_NO_SPACE;
+	default:
+		WARN_ON(1);
+		/* fallthrough */
+	case PNFS_OSD_ERR_EIO:
+		return OSD_ERR_PRI_EIO;
+	}
+}
+
+static void
+merge_ioerr(struct pnfs_osd_ioerr *dest_err,
+	    const struct pnfs_osd_ioerr *src_err)
+{
+	u64 dest_end, src_end;
+
+	if (!dest_err->oer_errno) {
+		*dest_err = *src_err;
+		/* accumulated device must be blank */
+		memset(&dest_err->oer_component.oid_device_id, 0,
+			sizeof(dest_err->oer_component.oid_device_id));
+
+		return;
+	}
+
+	if (dest_err->oer_component.oid_partition_id !=
+				src_err->oer_component.oid_partition_id)
+		dest_err->oer_component.oid_partition_id = 0;
+
+	if (dest_err->oer_component.oid_object_id !=
+				src_err->oer_component.oid_object_id)
+		dest_err->oer_component.oid_object_id = 0;
+
+	if (dest_err->oer_comp_offset > src_err->oer_comp_offset)
+		dest_err->oer_comp_offset = src_err->oer_comp_offset;
+
+	dest_end = end_offset(dest_err->oer_comp_offset,
+			      dest_err->oer_comp_length);
+	src_end =  end_offset(src_err->oer_comp_offset,
+			      src_err->oer_comp_length);
+	if (dest_end < src_end)
+		dest_end = src_end;
+
+	dest_err->oer_comp_length = dest_end - dest_err->oer_comp_offset;
+
+	if ((src_err->oer_iswrite == dest_err->oer_iswrite) &&
+	    (err_prio(src_err->oer_errno) > err_prio(dest_err->oer_errno))) {
+			dest_err->oer_errno = src_err->oer_errno;
+	} else if (src_err->oer_iswrite) {
+		dest_err->oer_iswrite = true;
+		dest_err->oer_errno = src_err->oer_errno;
+	}
+}
+
+static void
+encode_accumulated_error(struct objlayout *objlay, __be32 *p)
+{
+	struct objlayout_io_state *state, *tmp;
+	struct pnfs_osd_ioerr accumulated_err = {.oer_errno = 0};
+
+	list_for_each_entry_safe(state, tmp, &objlay->err_list, err_list) {
+		unsigned i;
+
+		for (i = 0; i < state->num_comps; i++) {
+			struct pnfs_osd_ioerr *ioerr = &state->ioerrs[i];
+
+			if (!ioerr->oer_errno)
+				continue;
+
+			printk(KERN_ERR "%s: err[%d]: errno=%d is_write=%d "
+				"dev(%llx:%llx) par=0x%llx obj=0x%llx "
+				"offset=0x%llx length=0x%llx\n",
+				__func__, i, ioerr->oer_errno,
+				ioerr->oer_iswrite,
+				_DEVID_LO(&ioerr->oer_component.oid_device_id),
+				_DEVID_HI(&ioerr->oer_component.oid_device_id),
+				ioerr->oer_component.oid_partition_id,
+				ioerr->oer_component.oid_object_id,
+				ioerr->oer_comp_offset,
+				ioerr->oer_comp_length);
+
+			merge_ioerr(&accumulated_err, ioerr);
+		}
+		list_del(&state->err_list);
+		objlayout_free_io_state(state);
+	}
+
+	pnfs_osd_xdr_encode_ioerr(p, &accumulated_err);
+}
+
+void
+objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay,
+			      struct xdr_stream *xdr,
+			      const struct nfs4_layoutreturn_args *args)
+{
+	struct objlayout *objlay = OBJLAYOUT(pnfslay);
+	struct objlayout_io_state *state, *tmp;
+	__be32 *start;
+
+	dprintk("%s: Begin\n", __func__);
+	start = xdr_reserve_space(xdr, 4);
+	BUG_ON(!start);
+
+	spin_lock(&objlay->lock);
+
+	list_for_each_entry_safe(state, tmp, &objlay->err_list, err_list) {
+		__be32 *last_xdr = NULL, *p;
+		unsigned i;
+		int res = 0;
+
+		for (i = 0; i < state->num_comps; i++) {
+			struct pnfs_osd_ioerr *ioerr = &state->ioerrs[i];
+
+			if (!ioerr->oer_errno)
+				continue;
+
+			dprintk("%s: err[%d]: errno=%d is_write=%d "
+				"dev(%llx:%llx) par=0x%llx obj=0x%llx "
+				"offset=0x%llx length=0x%llx\n",
+				__func__, i, ioerr->oer_errno,
+				ioerr->oer_iswrite,
+				_DEVID_LO(&ioerr->oer_component.oid_device_id),
+				_DEVID_HI(&ioerr->oer_component.oid_device_id),
+				ioerr->oer_component.oid_partition_id,
+				ioerr->oer_component.oid_object_id,
+				ioerr->oer_comp_offset,
+				ioerr->oer_comp_length);
+
+			p = pnfs_osd_xdr_ioerr_reserve_space(xdr);
+			if (unlikely(!p)) {
+				res = -E2BIG;
+				break; /* accumulated_error */
+			}
+
+			last_xdr = p;
+			pnfs_osd_xdr_encode_ioerr(p, &state->ioerrs[i]);
+		}
+
+		/* TODO: use xdr_write_pages */
+		if (unlikely(res)) {
+			/* no space for even one error descriptor */
+			BUG_ON(!last_xdr);
+
+			/* we've encountered a situation with lots and lots of
+			 * errors and no space to encode them all. Use the last
+			 * available slot to report the union of all the
+			 * remaining errors.
+			 */
+			encode_accumulated_error(objlay, last_xdr);
+			goto loop_done;
+		}
+		list_del(&state->err_list);
+		objlayout_free_io_state(state);
+	}
+loop_done:
+	spin_unlock(&objlay->lock);
+
+	*start = cpu_to_be32((xdr->p - start - 1) * 4);
+	dprintk("%s: Return\n", __func__);
+}
+
+
+/*
+ * Get Device Info API for io engines
+ */
+struct objlayout_deviceinfo {
+	struct page *page;
+	struct pnfs_osd_deviceaddr da; /* This must be last */
+};
+
+/* Initialize and call nfs_getdeviceinfo, then decode and return a
+ * "struct pnfs_osd_deviceaddr *" Eventually objlayout_put_deviceinfo()
+ * should be called.
+ */
+int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay,
+	struct nfs4_deviceid *d_id, struct pnfs_osd_deviceaddr **deviceaddr,
+	gfp_t gfp_flags)
+{
+	struct objlayout_deviceinfo *odi;
+	struct pnfs_device pd;
+	struct super_block *sb;
+	struct page *page, **pages;
+	u32 *p;
+	int err;
+
+	page = alloc_page(gfp_flags);
+	if (!page)
+		return -ENOMEM;
+
+	pages = &page;
+	pd.pages = pages;
+
+	memcpy(&pd.dev_id, d_id, sizeof(*d_id));
+	pd.layout_type = LAYOUT_OSD2_OBJECTS;
+	pd.pages = &page;
+	pd.pgbase = 0;
+	pd.pglen = PAGE_SIZE;
+	pd.mincount = 0;
+
+	sb = pnfslay->plh_inode->i_sb;
+	err = nfs4_proc_getdeviceinfo(NFS_SERVER(pnfslay->plh_inode), &pd);
+	dprintk("%s nfs_getdeviceinfo returned %d\n", __func__, err);
+	if (err)
+		goto err_out;
+
+	p = page_address(page);
+	odi = kzalloc(sizeof(*odi), gfp_flags);
+	if (!odi) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+	pnfs_osd_xdr_decode_deviceaddr(&odi->da, p);
+	odi->page = page;
+	*deviceaddr = &odi->da;
+	return 0;
+
+err_out:
+	__free_page(page);
+	return err;
+}
+
+void objlayout_put_deviceinfo(struct pnfs_osd_deviceaddr *deviceaddr)
+{
+	struct objlayout_deviceinfo *odi = container_of(deviceaddr,
+						struct objlayout_deviceinfo,
+						da);
+
+	__free_page(odi->page);
+	kfree(odi);
+}
diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h
new file mode 100644
index 000000000000..a8244c8e042d
--- /dev/null
+++ b/fs/nfs/objlayout/objlayout.h
@@ -0,0 +1,187 @@
+/*
+ *  Data types and function declerations for interfacing with the
+ *  pNFS standard object layout driver.
+ *
+ *  Copyright (C) 2007 Panasas Inc. [year of first publication]
+ *  All rights reserved.
+ *
+ *  Benny Halevy <bhalevy@panasas.com>
+ *  Boaz Harrosh <bharrosh@panasas.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
+ *  See the file COPYING included with this distribution for more details.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the Panasas company nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _OBJLAYOUT_H
+#define _OBJLAYOUT_H
+
+#include <linux/nfs_fs.h>
+#include <linux/pnfs_osd_xdr.h>
+#include "../pnfs.h"
+
+/*
+ * per-inode layout
+ */
+struct objlayout {
+	struct pnfs_layout_hdr pnfs_layout;
+
+	 /* for layout_commit */
+	enum osd_delta_space_valid_enum {
+		OBJ_DSU_INIT = 0,
+		OBJ_DSU_VALID,
+		OBJ_DSU_INVALID,
+	} delta_space_valid;
+	s64 delta_space_used;  /* consumed by write ops */
+
+	 /* for layout_return */
+	spinlock_t lock;
+	struct list_head err_list;
+};
+
+static inline struct objlayout *
+OBJLAYOUT(struct pnfs_layout_hdr *lo)
+{
+	return container_of(lo, struct objlayout, pnfs_layout);
+}
+
+/*
+ * per-I/O operation state
+ * embedded in objects provider io_state data structure
+ */
+struct objlayout_io_state {
+	struct pnfs_layout_segment *lseg;
+
+	struct page **pages;
+	unsigned pgbase;
+	unsigned nr_pages;
+	unsigned long count;
+	loff_t offset;
+	bool sync;
+
+	void *rpcdata;
+	int status;             /* res */
+	int eof;                /* res */
+	int committed;          /* res */
+
+	/* Error reporting (layout_return) */
+	struct list_head err_list;
+	unsigned num_comps;
+	/* Pointer to array of error descriptors of size num_comps.
+	 * It should contain as many entries as devices in the osd_layout
+	 * that participate in the I/O. It is up to the io_engine to allocate
+	 * needed space and set num_comps.
+	 */
+	struct pnfs_osd_ioerr *ioerrs;
+};
+
+/*
+ * Raid engine I/O API
+ */
+extern int objio_alloc_lseg(struct pnfs_layout_segment **outp,
+	struct pnfs_layout_hdr *pnfslay,
+	struct pnfs_layout_range *range,
+	struct xdr_stream *xdr,
+	gfp_t gfp_flags);
+extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
+
+extern int objio_alloc_io_state(
+	struct pnfs_layout_segment *lseg,
+	struct objlayout_io_state **outp,
+	gfp_t gfp_flags);
+extern void objio_free_io_state(struct objlayout_io_state *state);
+
+extern ssize_t objio_read_pagelist(struct objlayout_io_state *ol_state);
+extern ssize_t objio_write_pagelist(struct objlayout_io_state *ol_state,
+				    bool stable);
+
+/*
+ * callback API
+ */
+extern void objlayout_io_set_result(struct objlayout_io_state *state,
+			unsigned index, struct pnfs_osd_objid *pooid,
+			int osd_error, u64 offset, u64 length, bool is_write);
+
+static inline void
+objlayout_add_delta_space_used(struct objlayout_io_state *state, s64 space_used)
+{
+	struct objlayout *objlay = OBJLAYOUT(state->lseg->pls_layout);
+
+	/* If one of the I/Os errored out and the delta_space_used was
+	 * invalid we render the complete report as invalid. Protocol mandate
+	 * the DSU be accurate or not reported.
+	 */
+	spin_lock(&objlay->lock);
+	if (objlay->delta_space_valid != OBJ_DSU_INVALID) {
+		objlay->delta_space_valid = OBJ_DSU_VALID;
+		objlay->delta_space_used += space_used;
+	}
+	spin_unlock(&objlay->lock);
+}
+
+extern void objlayout_read_done(struct objlayout_io_state *state,
+				ssize_t status, bool sync);
+extern void objlayout_write_done(struct objlayout_io_state *state,
+				 ssize_t status, bool sync);
+
+extern int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay,
+	struct nfs4_deviceid *d_id, struct pnfs_osd_deviceaddr **deviceaddr,
+	gfp_t gfp_flags);
+extern void objlayout_put_deviceinfo(struct pnfs_osd_deviceaddr *deviceaddr);
+
+/*
+ * exported generic objects function vectors
+ */
+
+extern struct pnfs_layout_hdr *objlayout_alloc_layout_hdr(struct inode *, gfp_t gfp_flags);
+extern void objlayout_free_layout_hdr(struct pnfs_layout_hdr *);
+
+extern struct pnfs_layout_segment *objlayout_alloc_lseg(
+	struct pnfs_layout_hdr *,
+	struct nfs4_layoutget_res *,
+	gfp_t gfp_flags);
+extern void objlayout_free_lseg(struct pnfs_layout_segment *);
+
+extern enum pnfs_try_status objlayout_read_pagelist(
+	struct nfs_read_data *);
+
+extern enum pnfs_try_status objlayout_write_pagelist(
+	struct nfs_write_data *,
+	int how);
+
+extern void objlayout_encode_layoutcommit(
+	struct pnfs_layout_hdr *,
+	struct xdr_stream *,
+	const struct nfs4_layoutcommit_args *);
+
+extern void objlayout_encode_layoutreturn(
+	struct pnfs_layout_hdr *,
+	struct xdr_stream *,
+	const struct nfs4_layoutreturn_args *);
+
+#endif /* _OBJLAYOUT_H */
diff --git a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
new file mode 100644
index 000000000000..16fc758e9123
--- /dev/null
+++ b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
@@ -0,0 +1,412 @@
+/*
+ *  Object-Based pNFS Layout XDR layer
+ *
+ *  Copyright (C) 2007 Panasas Inc. [year of first publication]
+ *  All rights reserved.
+ *
+ *  Benny Halevy <bhalevy@panasas.com>
+ *  Boaz Harrosh <bharrosh@panasas.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
+ *  See the file COPYING included with this distribution for more details.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the Panasas company nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/pnfs_osd_xdr.h>
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+/*
+ * The following implementation is based on RFC5664
+ */
+
+/*
+ * struct pnfs_osd_objid {
+ *	struct nfs4_deviceid	oid_device_id;
+ *	u64			oid_partition_id;
+ *	u64			oid_object_id;
+ * }; // xdr size 32 bytes
+ */
+static __be32 *
+_osd_xdr_decode_objid(__be32 *p, struct pnfs_osd_objid *objid)
+{
+	p = xdr_decode_opaque_fixed(p, objid->oid_device_id.data,
+				    sizeof(objid->oid_device_id.data));
+
+	p = xdr_decode_hyper(p, &objid->oid_partition_id);
+	p = xdr_decode_hyper(p, &objid->oid_object_id);
+	return p;
+}
+/*
+ * struct pnfs_osd_opaque_cred {
+ *	u32 cred_len;
+ *	void *cred;
+ * }; // xdr size [variable]
+ * The return pointers are from the xdr buffer
+ */
+static int
+_osd_xdr_decode_opaque_cred(struct pnfs_osd_opaque_cred *opaque_cred,
+			    struct xdr_stream *xdr)
+{
+	__be32 *p = xdr_inline_decode(xdr, 1);
+
+	if (!p)
+		return -EINVAL;
+
+	opaque_cred->cred_len = be32_to_cpu(*p++);
+
+	p = xdr_inline_decode(xdr, opaque_cred->cred_len);
+	if (!p)
+		return -EINVAL;
+
+	opaque_cred->cred = p;
+	return 0;
+}
+
+/*
+ * struct pnfs_osd_object_cred {
+ *	struct pnfs_osd_objid		oc_object_id;
+ *	u32				oc_osd_version;
+ *	u32				oc_cap_key_sec;
+ *	struct pnfs_osd_opaque_cred	oc_cap_key
+ *	struct pnfs_osd_opaque_cred	oc_cap;
+ * }; // xdr size 32 + 4 + 4 + [variable] + [variable]
+ */
+static int
+_osd_xdr_decode_object_cred(struct pnfs_osd_object_cred *comp,
+			    struct xdr_stream *xdr)
+{
+	__be32 *p = xdr_inline_decode(xdr, 32 + 4 + 4);
+	int ret;
+
+	if (!p)
+		return -EIO;
+
+	p = _osd_xdr_decode_objid(p, &comp->oc_object_id);
+	comp->oc_osd_version = be32_to_cpup(p++);
+	comp->oc_cap_key_sec = be32_to_cpup(p);
+
+	ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap_key, xdr);
+	if (unlikely(ret))
+		return ret;
+
+	ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap, xdr);
+	return ret;
+}
+
+/*
+ * struct pnfs_osd_data_map {
+ *	u32	odm_num_comps;
+ *	u64	odm_stripe_unit;
+ *	u32	odm_group_width;
+ *	u32	odm_group_depth;
+ *	u32	odm_mirror_cnt;
+ *	u32	odm_raid_algorithm;
+ * }; // xdr size 4 + 8 + 4 + 4 + 4 + 4
+ */
+static inline int
+_osd_data_map_xdr_sz(void)
+{
+	return 4 + 8 + 4 + 4 + 4 + 4;
+}
+
+static __be32 *
+_osd_xdr_decode_data_map(__be32 *p, struct pnfs_osd_data_map *data_map)
+{
+	data_map->odm_num_comps = be32_to_cpup(p++);
+	p = xdr_decode_hyper(p, &data_map->odm_stripe_unit);
+	data_map->odm_group_width = be32_to_cpup(p++);
+	data_map->odm_group_depth = be32_to_cpup(p++);
+	data_map->odm_mirror_cnt = be32_to_cpup(p++);
+	data_map->odm_raid_algorithm = be32_to_cpup(p++);
+	dprintk("%s: odm_num_comps=%u odm_stripe_unit=%llu odm_group_width=%u "
+		"odm_group_depth=%u odm_mirror_cnt=%u odm_raid_algorithm=%u\n",
+		__func__,
+		data_map->odm_num_comps,
+		(unsigned long long)data_map->odm_stripe_unit,
+		data_map->odm_group_width,
+		data_map->odm_group_depth,
+		data_map->odm_mirror_cnt,
+		data_map->odm_raid_algorithm);
+	return p;
+}
+
+int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout,
+	struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr)
+{
+	__be32 *p;
+
+	memset(iter, 0, sizeof(*iter));
+
+	p = xdr_inline_decode(xdr, _osd_data_map_xdr_sz() + 4 + 4);
+	if (unlikely(!p))
+		return -EINVAL;
+
+	p = _osd_xdr_decode_data_map(p, &layout->olo_map);
+	layout->olo_comps_index = be32_to_cpup(p++);
+	layout->olo_num_comps = be32_to_cpup(p++);
+	iter->total_comps = layout->olo_num_comps;
+	return 0;
+}
+
+bool pnfs_osd_xdr_decode_layout_comp(struct pnfs_osd_object_cred *comp,
+	struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr,
+	int *err)
+{
+	BUG_ON(iter->decoded_comps > iter->total_comps);
+	if (iter->decoded_comps == iter->total_comps)
+		return false;
+
+	*err = _osd_xdr_decode_object_cred(comp, xdr);
+	if (unlikely(*err)) {
+		dprintk("%s: _osd_xdr_decode_object_cred=>%d decoded_comps=%d "
+			"total_comps=%d\n", __func__, *err,
+			iter->decoded_comps, iter->total_comps);
+		return false; /* stop the loop */
+	}
+	dprintk("%s: dev(%llx:%llx) par=0x%llx obj=0x%llx "
+		"key_len=%u cap_len=%u\n",
+		__func__,
+		_DEVID_LO(&comp->oc_object_id.oid_device_id),
+		_DEVID_HI(&comp->oc_object_id.oid_device_id),
+		comp->oc_object_id.oid_partition_id,
+		comp->oc_object_id.oid_object_id,
+		comp->oc_cap_key.cred_len, comp->oc_cap.cred_len);
+
+	iter->decoded_comps++;
+	return true;
+}
+
+/*
+ * Get Device Information Decoding
+ *
+ * Note: since Device Information is currently done synchronously, all
+ *       variable strings fields are left inside the rpc buffer and are only
+ *       pointed to by the pnfs_osd_deviceaddr members. So the read buffer
+ *       should not be freed while the returned information is in use.
+ */
+/*
+ *struct nfs4_string {
+ *	unsigned int len;
+ *	char *data;
+ *}; // size [variable]
+ * NOTE: Returned string points to inside the XDR buffer
+ */
+static __be32 *
+__read_u8_opaque(__be32 *p, struct nfs4_string *str)
+{
+	str->len = be32_to_cpup(p++);
+	str->data = (char *)p;
+
+	p += XDR_QUADLEN(str->len);
+	return p;
+}
+
+/*
+ * struct pnfs_osd_targetid {
+ *	u32			oti_type;
+ *	struct nfs4_string	oti_scsi_device_id;
+ * };// size 4 + [variable]
+ */
+static __be32 *
+__read_targetid(__be32 *p, struct pnfs_osd_targetid* targetid)
+{
+	u32 oti_type;
+
+	oti_type = be32_to_cpup(p++);
+	targetid->oti_type = oti_type;
+
+	switch (oti_type) {
+	case OBJ_TARGET_SCSI_NAME:
+	case OBJ_TARGET_SCSI_DEVICE_ID:
+		p = __read_u8_opaque(p, &targetid->oti_scsi_device_id);
+	}
+
+	return p;
+}
+
+/*
+ * struct pnfs_osd_net_addr {
+ *	struct nfs4_string	r_netid;
+ *	struct nfs4_string	r_addr;
+ * };
+ */
+static __be32 *
+__read_net_addr(__be32 *p, struct pnfs_osd_net_addr* netaddr)
+{
+	p = __read_u8_opaque(p, &netaddr->r_netid);
+	p = __read_u8_opaque(p, &netaddr->r_addr);
+
+	return p;
+}
+
+/*
+ * struct pnfs_osd_targetaddr {
+ *	u32				ota_available;
+ *	struct pnfs_osd_net_addr	ota_netaddr;
+ * };
+ */
+static __be32 *
+__read_targetaddr(__be32 *p, struct pnfs_osd_targetaddr *targetaddr)
+{
+	u32 ota_available;
+
+	ota_available = be32_to_cpup(p++);
+	targetaddr->ota_available = ota_available;
+
+	if (ota_available)
+		p = __read_net_addr(p, &targetaddr->ota_netaddr);
+
+
+	return p;
+}
+
+/*
+ * struct pnfs_osd_deviceaddr {
+ *	struct pnfs_osd_targetid	oda_targetid;
+ *	struct pnfs_osd_targetaddr	oda_targetaddr;
+ *	u8				oda_lun[8];
+ *	struct nfs4_string		oda_systemid;
+ *	struct pnfs_osd_object_cred	oda_root_obj_cred;
+ *	struct nfs4_string		oda_osdname;
+ * };
+ */
+
+/* We need this version for the pnfs_osd_xdr_decode_deviceaddr which does
+ * not have an xdr_stream
+ */
+static __be32 *
+__read_opaque_cred(__be32 *p,
+			      struct pnfs_osd_opaque_cred *opaque_cred)
+{
+	opaque_cred->cred_len = be32_to_cpu(*p++);
+	opaque_cred->cred = p;
+	return p + XDR_QUADLEN(opaque_cred->cred_len);
+}
+
+static __be32 *
+__read_object_cred(__be32 *p, struct pnfs_osd_object_cred *comp)
+{
+	p = _osd_xdr_decode_objid(p, &comp->oc_object_id);
+	comp->oc_osd_version = be32_to_cpup(p++);
+	comp->oc_cap_key_sec = be32_to_cpup(p++);
+
+	p = __read_opaque_cred(p, &comp->oc_cap_key);
+	p = __read_opaque_cred(p, &comp->oc_cap);
+	return p;
+}
+
+void pnfs_osd_xdr_decode_deviceaddr(
+	struct pnfs_osd_deviceaddr *deviceaddr, __be32 *p)
+{
+	p = __read_targetid(p, &deviceaddr->oda_targetid);
+
+	p = __read_targetaddr(p, &deviceaddr->oda_targetaddr);
+
+	p = xdr_decode_opaque_fixed(p, deviceaddr->oda_lun,
+				    sizeof(deviceaddr->oda_lun));
+
+	p = __read_u8_opaque(p, &deviceaddr->oda_systemid);
+
+	p = __read_object_cred(p, &deviceaddr->oda_root_obj_cred);
+
+	p = __read_u8_opaque(p, &deviceaddr->oda_osdname);
+
+	/* libosd likes this terminated in dbg. It's last, so no problems */
+	deviceaddr->oda_osdname.data[deviceaddr->oda_osdname.len] = 0;
+}
+
+/*
+ * struct pnfs_osd_layoutupdate {
+ *	u32	dsu_valid;
+ *	s64	dsu_delta;
+ *	u32	olu_ioerr_flag;
+ * }; xdr size 4 + 8 + 4
+ */
+int
+pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr,
+				 struct pnfs_osd_layoutupdate *lou)
+{
+	__be32 *p = xdr_reserve_space(xdr,  4 + 8 + 4);
+
+	if (!p)
+		return -E2BIG;
+
+	*p++ = cpu_to_be32(lou->dsu_valid);
+	if (lou->dsu_valid)
+		p = xdr_encode_hyper(p, lou->dsu_delta);
+	*p++ = cpu_to_be32(lou->olu_ioerr_flag);
+	return 0;
+}
+
+/*
+ * struct pnfs_osd_objid {
+ *	struct nfs4_deviceid	oid_device_id;
+ *	u64			oid_partition_id;
+ *	u64			oid_object_id;
+ * }; // xdr size 32 bytes
+ */
+static inline __be32 *
+pnfs_osd_xdr_encode_objid(__be32 *p, struct pnfs_osd_objid *object_id)
+{
+	p = xdr_encode_opaque_fixed(p, &object_id->oid_device_id.data,
+				    sizeof(object_id->oid_device_id.data));
+	p = xdr_encode_hyper(p, object_id->oid_partition_id);
+	p = xdr_encode_hyper(p, object_id->oid_object_id);
+
+	return p;
+}
+
+/*
+ * struct pnfs_osd_ioerr {
+ *	struct pnfs_osd_objid	oer_component;
+ *	u64			oer_comp_offset;
+ *	u64			oer_comp_length;
+ *	u32			oer_iswrite;
+ *	u32			oer_errno;
+ * }; // xdr size 32 + 24 bytes
+ */
+void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr)
+{
+	p = pnfs_osd_xdr_encode_objid(p, &ioerr->oer_component);
+	p = xdr_encode_hyper(p, ioerr->oer_comp_offset);
+	p = xdr_encode_hyper(p, ioerr->oer_comp_length);
+	*p++ = cpu_to_be32(ioerr->oer_iswrite);
+	*p   = cpu_to_be32(ioerr->oer_errno);
+}
+
+__be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr)
+{
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, 32 + 24);
+	if (unlikely(!p))
+		dprintk("%s: out of xdr space\n", __func__);
+
+	return p;
+}
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index c80add6e2213..009855716286 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -204,6 +204,22 @@ nfs_wait_on_request(struct nfs_page *req)
 			TASK_UNINTERRUPTIBLE);
 }
 
+bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req)
+{
+	/*
+	 * FIXME: ideally we should be able to coalesce all requests
+	 * that are not block boundary aligned, but currently this
+	 * is problematic for the case of bsize < PAGE_CACHE_SIZE,
+	 * since nfs_flush_multi and nfs_pagein_multi assume you
+	 * can have only one struct nfs_page.
+	 */
+	if (desc->pg_bsize < PAGE_SIZE)
+		return 0;
+
+	return desc->pg_count + req->wb_bytes <= desc->pg_bsize;
+}
+EXPORT_SYMBOL_GPL(nfs_generic_pg_test);
+
 /**
  * nfs_pageio_init - initialise a page io descriptor
  * @desc: pointer to descriptor
@@ -229,6 +245,8 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_ioflags = io_flags;
 	desc->pg_error = 0;
 	desc->pg_lseg = NULL;
+	desc->pg_test = nfs_generic_pg_test;
+	pnfs_pageio_init(desc, inode);
 }
 
 /**
@@ -242,29 +260,23 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
  *
  * Return 'true' if this is the case, else return 'false'.
  */
-static int nfs_can_coalesce_requests(struct nfs_page *prev,
-				     struct nfs_page *req,
-				     struct nfs_pageio_descriptor *pgio)
+static bool nfs_can_coalesce_requests(struct nfs_page *prev,
+				      struct nfs_page *req,
+				      struct nfs_pageio_descriptor *pgio)
 {
 	if (req->wb_context->cred != prev->wb_context->cred)
-		return 0;
+		return false;
 	if (req->wb_lock_context->lockowner != prev->wb_lock_context->lockowner)
-		return 0;
+		return false;
 	if (req->wb_context->state != prev->wb_context->state)
-		return 0;
+		return false;
 	if (req->wb_index != (prev->wb_index + 1))
-		return 0;
+		return false;
 	if (req->wb_pgbase != 0)
-		return 0;
+		return false;
 	if (prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE)
-		return 0;
-	/*
-	 * Non-whole file layouts need to check that req is inside of
-	 * pgio->pg_lseg.
-	 */
-	if (pgio->pg_test && !pgio->pg_test(pgio, prev, req))
-		return 0;
-	return 1;
+		return false;
+	return pgio->pg_test(pgio, prev, req);
 }
 
 /**
@@ -278,31 +290,18 @@ static int nfs_can_coalesce_requests(struct nfs_page *prev,
 static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
 				     struct nfs_page *req)
 {
-	size_t newlen = req->wb_bytes;
-
 	if (desc->pg_count != 0) {
 		struct nfs_page *prev;
 
-		/*
-		 * FIXME: ideally we should be able to coalesce all requests
-		 * that are not block boundary aligned, but currently this
-		 * is problematic for the case of bsize < PAGE_CACHE_SIZE,
-		 * since nfs_flush_multi and nfs_pagein_multi assume you
-		 * can have only one struct nfs_page.
-		 */
-		if (desc->pg_bsize < PAGE_SIZE)
-			return 0;
-		newlen += desc->pg_count;
-		if (newlen > desc->pg_bsize)
-			return 0;
 		prev = nfs_list_entry(desc->pg_list.prev);
 		if (!nfs_can_coalesce_requests(prev, req, desc))
 			return 0;
-	} else
+	} else {
 		desc->pg_base = req->wb_pgbase;
+	}
 	nfs_list_remove_request(req);
 	nfs_list_add_request(req, &desc->pg_list);
-	desc->pg_count = newlen;
+	desc->pg_count += req->wb_bytes;
 	return 1;
 }
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index f57f5281a520..29c0ca7fc347 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -177,13 +177,28 @@ get_layout_hdr(struct pnfs_layout_hdr *lo)
 	atomic_inc(&lo->plh_refcount);
 }
 
+static struct pnfs_layout_hdr *
+pnfs_alloc_layout_hdr(struct inode *ino, gfp_t gfp_flags)
+{
+	struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld;
+	return ld->alloc_layout_hdr ? ld->alloc_layout_hdr(ino, gfp_flags) :
+		kzalloc(sizeof(struct pnfs_layout_hdr), gfp_flags);
+}
+
+static void
+pnfs_free_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+	struct pnfs_layoutdriver_type *ld = NFS_SERVER(lo->plh_inode)->pnfs_curr_ld;
+	return ld->alloc_layout_hdr ? ld->free_layout_hdr(lo) : kfree(lo);
+}
+
 static void
 destroy_layout_hdr(struct pnfs_layout_hdr *lo)
 {
 	dprintk("%s: freeing layout cache %p\n", __func__, lo);
 	BUG_ON(!list_empty(&lo->plh_layouts));
 	NFS_I(lo->plh_inode)->layout = NULL;
-	kfree(lo);
+	pnfs_free_layout_hdr(lo);
 }
 
 static void
@@ -228,7 +243,7 @@ put_lseg_common(struct pnfs_layout_segment *lseg)
 {
 	struct inode *inode = lseg->pls_layout->plh_inode;
 
-	BUG_ON(test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
+	WARN_ON(test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
 	list_del_init(&lseg->pls_list);
 	if (list_empty(&lseg->pls_layout->plh_segs)) {
 		set_bit(NFS_LAYOUT_DESTROYED, &lseg->pls_layout->plh_flags);
@@ -261,11 +276,72 @@ put_lseg(struct pnfs_layout_segment *lseg)
 }
 EXPORT_SYMBOL_GPL(put_lseg);
 
+static inline u64
+end_offset(u64 start, u64 len)
+{
+	u64 end;
+
+	end = start + len;
+	return end >= start ? end : NFS4_MAX_UINT64;
+}
+
+/* last octet in a range */
+static inline u64
+last_byte_offset(u64 start, u64 len)
+{
+	u64 end;
+
+	BUG_ON(!len);
+	end = start + len;
+	return end > start ? end - 1 : NFS4_MAX_UINT64;
+}
+
+/*
+ * is l2 fully contained in l1?
+ *   start1                             end1
+ *   [----------------------------------)
+ *           start2           end2
+ *           [----------------)
+ */
+static inline int
+lo_seg_contained(struct pnfs_layout_range *l1,
+		 struct pnfs_layout_range *l2)
+{
+	u64 start1 = l1->offset;
+	u64 end1 = end_offset(start1, l1->length);
+	u64 start2 = l2->offset;
+	u64 end2 = end_offset(start2, l2->length);
+
+	return (start1 <= start2) && (end1 >= end2);
+}
+
+/*
+ * is l1 and l2 intersecting?
+ *   start1                             end1
+ *   [----------------------------------)
+ *                              start2           end2
+ *                              [----------------)
+ */
+static inline int
+lo_seg_intersecting(struct pnfs_layout_range *l1,
+		    struct pnfs_layout_range *l2)
+{
+	u64 start1 = l1->offset;
+	u64 end1 = end_offset(start1, l1->length);
+	u64 start2 = l2->offset;
+	u64 end2 = end_offset(start2, l2->length);
+
+	return (end1 == NFS4_MAX_UINT64 || end1 > start2) &&
+	       (end2 == NFS4_MAX_UINT64 || end2 > start1);
+}
+
 static bool
-should_free_lseg(u32 lseg_iomode, u32 recall_iomode)
+should_free_lseg(struct pnfs_layout_range *lseg_range,
+		 struct pnfs_layout_range *recall_range)
 {
-	return (recall_iomode == IOMODE_ANY ||
-		lseg_iomode == recall_iomode);
+	return (recall_range->iomode == IOMODE_ANY ||
+		lseg_range->iomode == recall_range->iomode) &&
+	       lo_seg_intersecting(lseg_range, recall_range);
 }
 
 /* Returns 1 if lseg is removed from list, 0 otherwise */
@@ -296,7 +372,7 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
 int
 mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 			    struct list_head *tmp_list,
-			    u32 iomode)
+			    struct pnfs_layout_range *recall_range)
 {
 	struct pnfs_layout_segment *lseg, *next;
 	int invalid = 0, removed = 0;
@@ -309,7 +385,8 @@ mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 		return 0;
 	}
 	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
-		if (should_free_lseg(lseg->pls_range.iomode, iomode)) {
+		if (!recall_range ||
+		    should_free_lseg(&lseg->pls_range, recall_range)) {
 			dprintk("%s: freeing lseg %p iomode %d "
 				"offset %llu length %llu\n", __func__,
 				lseg, lseg->pls_range.iomode, lseg->pls_range.offset,
@@ -358,7 +435,7 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
 	lo = nfsi->layout;
 	if (lo) {
 		lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
-		mark_matching_lsegs_invalid(lo, &tmp_list, IOMODE_ANY);
+		mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
 	}
 	spin_unlock(&nfsi->vfs_inode.i_lock);
 	pnfs_free_lseg_list(&tmp_list);
@@ -467,7 +544,7 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
 static struct pnfs_layout_segment *
 send_layoutget(struct pnfs_layout_hdr *lo,
 	   struct nfs_open_context *ctx,
-	   u32 iomode,
+	   struct pnfs_layout_range *range,
 	   gfp_t gfp_flags)
 {
 	struct inode *ino = lo->plh_inode;
@@ -499,11 +576,11 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 			goto out_err_free;
 	}
 
-	lgp->args.minlength = NFS4_MAX_UINT64;
+	lgp->args.minlength = PAGE_CACHE_SIZE;
+	if (lgp->args.minlength > range->length)
+		lgp->args.minlength = range->length;
 	lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
-	lgp->args.range.iomode = iomode;
-	lgp->args.range.offset = 0;
-	lgp->args.range.length = NFS4_MAX_UINT64;
+	lgp->args.range = *range;
 	lgp->args.type = server->pnfs_curr_ld->id;
 	lgp->args.inode = ino;
 	lgp->args.ctx = get_nfs_open_context(ctx);
@@ -518,7 +595,7 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 	nfs4_proc_layoutget(lgp);
 	if (!lseg) {
 		/* remember that LAYOUTGET failed and suspend trying */
-		set_bit(lo_fail_bit(iomode), &lo->plh_flags);
+		set_bit(lo_fail_bit(range->iomode), &lo->plh_flags);
 	}
 
 	/* free xdr pages */
@@ -542,6 +619,56 @@ out_err_free:
 	return NULL;
 }
 
+/* Initiates a LAYOUTRETURN(FILE) */
+int
+_pnfs_return_layout(struct inode *ino)
+{
+	struct pnfs_layout_hdr *lo = NULL;
+	struct nfs_inode *nfsi = NFS_I(ino);
+	LIST_HEAD(tmp_list);
+	struct nfs4_layoutreturn *lrp;
+	nfs4_stateid stateid;
+	int status = 0;
+
+	dprintk("--> %s\n", __func__);
+
+	spin_lock(&ino->i_lock);
+	lo = nfsi->layout;
+	if (!lo) {
+		spin_unlock(&ino->i_lock);
+		dprintk("%s: no layout to return\n", __func__);
+		return status;
+	}
+	stateid = nfsi->layout->plh_stateid;
+	/* Reference matched in nfs4_layoutreturn_release */
+	get_layout_hdr(lo);
+	mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
+	lo->plh_block_lgets++;
+	spin_unlock(&ino->i_lock);
+	pnfs_free_lseg_list(&tmp_list);
+
+	WARN_ON(test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags));
+
+	lrp = kzalloc(sizeof(*lrp), GFP_KERNEL);
+	if (unlikely(lrp == NULL)) {
+		status = -ENOMEM;
+		set_bit(NFS_LAYOUT_RW_FAILED, &lo->plh_flags);
+		set_bit(NFS_LAYOUT_RO_FAILED, &lo->plh_flags);
+		put_layout_hdr(lo);
+		goto out;
+	}
+
+	lrp->args.stateid = stateid;
+	lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id;
+	lrp->args.inode = ino;
+	lrp->clp = NFS_SERVER(ino)->nfs_client;
+
+	status = nfs4_proc_layoutreturn(lrp);
+out:
+	dprintk("<-- %s status: %d\n", __func__, status);
+	return status;
+}
+
 bool pnfs_roc(struct inode *ino)
 {
 	struct pnfs_layout_hdr *lo;
@@ -625,10 +752,23 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier)
  * are seen first.
  */
 static s64
-cmp_layout(u32 iomode1, u32 iomode2)
+cmp_layout(struct pnfs_layout_range *l1,
+	   struct pnfs_layout_range *l2)
 {
+	s64 d;
+
+	/* high offset > low offset */
+	d = l1->offset - l2->offset;
+	if (d)
+		return d;
+
+	/* short length > long length */
+	d = l2->length - l1->length;
+	if (d)
+		return d;
+
 	/* read > read/write */
-	return (int)(iomode2 == IOMODE_READ) - (int)(iomode1 == IOMODE_READ);
+	return (int)(l1->iomode == IOMODE_READ) - (int)(l2->iomode == IOMODE_READ);
 }
 
 static void
@@ -636,13 +776,12 @@ pnfs_insert_layout(struct pnfs_layout_hdr *lo,
 		   struct pnfs_layout_segment *lseg)
 {
 	struct pnfs_layout_segment *lp;
-	int found = 0;
 
 	dprintk("%s:Begin\n", __func__);
 
 	assert_spin_locked(&lo->plh_inode->i_lock);
 	list_for_each_entry(lp, &lo->plh_segs, pls_list) {
-		if (cmp_layout(lp->pls_range.iomode, lseg->pls_range.iomode) > 0)
+		if (cmp_layout(&lseg->pls_range, &lp->pls_range) > 0)
 			continue;
 		list_add_tail(&lseg->pls_list, &lp->pls_list);
 		dprintk("%s: inserted lseg %p "
@@ -652,16 +791,14 @@ pnfs_insert_layout(struct pnfs_layout_hdr *lo,
 			lseg->pls_range.offset, lseg->pls_range.length,
 			lp, lp->pls_range.iomode, lp->pls_range.offset,
 			lp->pls_range.length);
-		found = 1;
-		break;
-	}
-	if (!found) {
-		list_add_tail(&lseg->pls_list, &lo->plh_segs);
-		dprintk("%s: inserted lseg %p "
-			"iomode %d offset %llu length %llu at tail\n",
-			__func__, lseg, lseg->pls_range.iomode,
-			lseg->pls_range.offset, lseg->pls_range.length);
+		goto out;
 	}
+	list_add_tail(&lseg->pls_list, &lo->plh_segs);
+	dprintk("%s: inserted lseg %p "
+		"iomode %d offset %llu length %llu at tail\n",
+		__func__, lseg, lseg->pls_range.iomode,
+		lseg->pls_range.offset, lseg->pls_range.length);
+out:
 	get_layout_hdr(lo);
 
 	dprintk("%s:Return\n", __func__);
@@ -672,7 +809,7 @@ alloc_init_layout_hdr(struct inode *ino, gfp_t gfp_flags)
 {
 	struct pnfs_layout_hdr *lo;
 
-	lo = kzalloc(sizeof(struct pnfs_layout_hdr), gfp_flags);
+	lo = pnfs_alloc_layout_hdr(ino, gfp_flags);
 	if (!lo)
 		return NULL;
 	atomic_set(&lo->plh_refcount, 1);
@@ -705,7 +842,7 @@ pnfs_find_alloc_layout(struct inode *ino, gfp_t gfp_flags)
 	if (likely(nfsi->layout == NULL))	/* Won the race? */
 		nfsi->layout = new;
 	else
-		kfree(new);
+		pnfs_free_layout_hdr(new);
 	return nfsi->layout;
 }
 
@@ -721,16 +858,28 @@ pnfs_find_alloc_layout(struct inode *ino, gfp_t gfp_flags)
  * READ		RW	true
  */
 static int
-is_matching_lseg(struct pnfs_layout_segment *lseg, u32 iomode)
+is_matching_lseg(struct pnfs_layout_range *ls_range,
+		 struct pnfs_layout_range *range)
 {
-	return (iomode != IOMODE_RW || lseg->pls_range.iomode == IOMODE_RW);
+	struct pnfs_layout_range range1;
+
+	if ((range->iomode == IOMODE_RW &&
+	     ls_range->iomode != IOMODE_RW) ||
+	    !lo_seg_intersecting(ls_range, range))
+		return 0;
+
+	/* range1 covers only the first byte in the range */
+	range1 = *range;
+	range1.length = 1;
+	return lo_seg_contained(ls_range, &range1);
 }
 
 /*
  * lookup range in layout
  */
 static struct pnfs_layout_segment *
-pnfs_find_lseg(struct pnfs_layout_hdr *lo, u32 iomode)
+pnfs_find_lseg(struct pnfs_layout_hdr *lo,
+		struct pnfs_layout_range *range)
 {
 	struct pnfs_layout_segment *lseg, *ret = NULL;
 
@@ -739,11 +888,11 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo, u32 iomode)
 	assert_spin_locked(&lo->plh_inode->i_lock);
 	list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
 		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) &&
-		    is_matching_lseg(lseg, iomode)) {
+		    is_matching_lseg(&lseg->pls_range, range)) {
 			ret = get_lseg(lseg);
 			break;
 		}
-		if (cmp_layout(iomode, lseg->pls_range.iomode) > 0)
+		if (lseg->pls_range.offset > range->offset)
 			break;
 	}
 
@@ -759,9 +908,17 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo, u32 iomode)
 struct pnfs_layout_segment *
 pnfs_update_layout(struct inode *ino,
 		   struct nfs_open_context *ctx,
+		   loff_t pos,
+		   u64 count,
 		   enum pnfs_iomode iomode,
 		   gfp_t gfp_flags)
 {
+	struct pnfs_layout_range arg = {
+		.iomode = iomode,
+		.offset = pos,
+		.length = count,
+	};
+	unsigned pg_offset;
 	struct nfs_inode *nfsi = NFS_I(ino);
 	struct nfs_client *clp = NFS_SERVER(ino)->nfs_client;
 	struct pnfs_layout_hdr *lo;
@@ -789,7 +946,7 @@ pnfs_update_layout(struct inode *ino,
 		goto out_unlock;
 
 	/* Check to see if the layout for the given range already exists */
-	lseg = pnfs_find_lseg(lo, iomode);
+	lseg = pnfs_find_lseg(lo, &arg);
 	if (lseg)
 		goto out_unlock;
 
@@ -811,7 +968,14 @@ pnfs_update_layout(struct inode *ino,
 		spin_unlock(&clp->cl_lock);
 	}
 
-	lseg = send_layoutget(lo, ctx, iomode, gfp_flags);
+	pg_offset = arg.offset & ~PAGE_CACHE_MASK;
+	if (pg_offset) {
+		arg.offset -= pg_offset;
+		arg.length += pg_offset;
+	}
+	arg.length = PAGE_CACHE_ALIGN(arg.length);
+
+	lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
 	if (!lseg && first) {
 		spin_lock(&clp->cl_lock);
 		list_del_init(&lo->plh_layouts);
@@ -838,17 +1002,6 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 	struct nfs_client *clp = NFS_SERVER(ino)->nfs_client;
 	int status = 0;
 
-	/* Verify we got what we asked for.
-	 * Note that because the xdr parsing only accepts a single
-	 * element array, this can fail even if the server is behaving
-	 * correctly.
-	 */
-	if (lgp->args.range.iomode > res->range.iomode ||
-	    res->range.offset != 0 ||
-	    res->range.length != NFS4_MAX_UINT64) {
-		status = -EINVAL;
-		goto out;
-	}
 	/* Inject layout blob into I/O device driver */
 	lseg = NFS_SERVER(ino)->pnfs_curr_ld->alloc_lseg(lo, res, lgp->gfp_flags);
 	if (!lseg || IS_ERR(lseg)) {
@@ -895,51 +1048,77 @@ out_forget_reply:
 	goto out;
 }
 
-static int pnfs_read_pg_test(struct nfs_pageio_descriptor *pgio,
-			     struct nfs_page *prev,
-			     struct nfs_page *req)
-{
-	if (pgio->pg_count == prev->wb_bytes) {
-		/* This is first coelesce call for a series of nfs_pages */
-		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
-						   prev->wb_context,
-						   IOMODE_READ,
-						   GFP_KERNEL);
-	}
-	return NFS_SERVER(pgio->pg_inode)->pnfs_curr_ld->pg_test(pgio, prev, req);
-}
-
-void
-pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode)
+bool
+pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
+		     struct nfs_page *req)
 {
-	struct pnfs_layoutdriver_type *ld;
+	enum pnfs_iomode access_type;
+	gfp_t gfp_flags;
 
-	ld = NFS_SERVER(inode)->pnfs_curr_ld;
-	pgio->pg_test = (ld && ld->pg_test) ? pnfs_read_pg_test : NULL;
-}
+	/* We assume that pg_ioflags == 0 iff we're reading a page */
+	if (pgio->pg_ioflags == 0) {
+		access_type = IOMODE_READ;
+		gfp_flags = GFP_KERNEL;
+	} else {
+		access_type = IOMODE_RW;
+		gfp_flags = GFP_NOFS;
+	}
 
-static int pnfs_write_pg_test(struct nfs_pageio_descriptor *pgio,
-			      struct nfs_page *prev,
-			      struct nfs_page *req)
-{
-	if (pgio->pg_count == prev->wb_bytes) {
+	if (pgio->pg_lseg == NULL) {
+		if (pgio->pg_count != prev->wb_bytes)
+			return true;
 		/* This is first coelesce call for a series of nfs_pages */
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   prev->wb_context,
-						   IOMODE_RW,
-						   GFP_NOFS);
+						   req_offset(prev),
+						   pgio->pg_count,
+						   access_type,
+						   gfp_flags);
+		if (pgio->pg_lseg == NULL)
+			return true;
 	}
-	return NFS_SERVER(pgio->pg_inode)->pnfs_curr_ld->pg_test(pgio, prev, req);
+
+	/*
+	 * Test if a nfs_page is fully contained in the pnfs_layout_range.
+	 * Note that this test makes several assumptions:
+	 * - that the previous nfs_page in the struct nfs_pageio_descriptor
+	 *   is known to lie within the range.
+	 *   - that the nfs_page being tested is known to be contiguous with the
+	 *   previous nfs_page.
+	 *   - Layout ranges are page aligned, so we only have to test the
+	 *   start offset of the request.
+	 *
+	 * Please also note that 'end_offset' is actually the offset of the
+	 * first byte that lies outside the pnfs_layout_range. FIXME?
+	 *
+	 */
+	return req_offset(req) < end_offset(pgio->pg_lseg->pls_range.offset,
+					 pgio->pg_lseg->pls_range.length);
 }
+EXPORT_SYMBOL_GPL(pnfs_generic_pg_test);
 
-void
-pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode)
+/*
+ * Called by non rpc-based layout drivers
+ */
+int
+pnfs_ld_write_done(struct nfs_write_data *data)
 {
-	struct pnfs_layoutdriver_type *ld;
+	int status;
 
-	ld = NFS_SERVER(inode)->pnfs_curr_ld;
-	pgio->pg_test = (ld && ld->pg_test) ? pnfs_write_pg_test : NULL;
+	if (!data->pnfs_error) {
+		pnfs_set_layoutcommit(data);
+		data->mds_ops->rpc_call_done(&data->task, data);
+		data->mds_ops->rpc_release(data);
+		return 0;
+	}
+
+	dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__,
+		data->pnfs_error);
+	status = nfs_initiate_write(data, NFS_CLIENT(data->inode),
+				    data->mds_ops, NFS_FILE_SYNC);
+	return status ? : -EAGAIN;
 }
+EXPORT_SYMBOL_GPL(pnfs_ld_write_done);
 
 enum pnfs_try_status
 pnfs_try_to_write_data(struct nfs_write_data *wdata,
@@ -966,6 +1145,29 @@ pnfs_try_to_write_data(struct nfs_write_data *wdata,
 }
 
 /*
+ * Called by non rpc-based layout drivers
+ */
+int
+pnfs_ld_read_done(struct nfs_read_data *data)
+{
+	int status;
+
+	if (!data->pnfs_error) {
+		__nfs4_read_done_cb(data);
+		data->mds_ops->rpc_call_done(&data->task, data);
+		data->mds_ops->rpc_release(data);
+		return 0;
+	}
+
+	dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__,
+		data->pnfs_error);
+	status = nfs_initiate_read(data, NFS_CLIENT(data->inode),
+				   data->mds_ops);
+	return status ? : -EAGAIN;
+}
+EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
+
+/*
  * Call the appropriate parallel I/O subsystem read function.
  */
 enum pnfs_try_status
@@ -1009,7 +1211,7 @@ void
 pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 {
 	struct nfs_inode *nfsi = NFS_I(wdata->inode);
-	loff_t end_pos = wdata->args.offset + wdata->res.count;
+	loff_t end_pos = wdata->mds_offset + wdata->res.count;
 	bool mark_as_dirty = false;
 
 	spin_lock(&nfsi->vfs_inode.i_lock);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 0c015bad9e7a..96bf4e6f45be 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -30,6 +30,7 @@
 #ifndef FS_NFS_PNFS_H
 #define FS_NFS_PNFS_H
 
+#include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
 
 enum {
@@ -64,17 +65,29 @@ enum {
 	NFS_LAYOUT_DESTROYED,		/* no new use of layout allowed */
 };
 
+enum layoutdriver_policy_flags {
+	/* Should the pNFS client commit and return the layout upon a setattr */
+	PNFS_LAYOUTRET_ON_SETATTR	= 1 << 0,
+};
+
+struct nfs4_deviceid_node;
+
 /* Per-layout driver specific registration structure */
 struct pnfs_layoutdriver_type {
 	struct list_head pnfs_tblid;
 	const u32 id;
 	const char *name;
 	struct module *owner;
+	unsigned flags;
+
+	struct pnfs_layout_hdr * (*alloc_layout_hdr) (struct inode *inode, gfp_t gfp_flags);
+	void (*free_layout_hdr) (struct pnfs_layout_hdr *);
+
 	struct pnfs_layout_segment * (*alloc_lseg) (struct pnfs_layout_hdr *layoutid, struct nfs4_layoutget_res *lgr, gfp_t gfp_flags);
 	void (*free_lseg) (struct pnfs_layout_segment *lseg);
 
 	/* test for nfs page cache coalescing */
-	int (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *);
+	bool (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *);
 
 	/* Returns true if layoutdriver wants to divert this request to
 	 * driver's commit routine.
@@ -89,6 +102,16 @@ struct pnfs_layoutdriver_type {
 	 */
 	enum pnfs_try_status (*read_pagelist) (struct nfs_read_data *nfs_data);
 	enum pnfs_try_status (*write_pagelist) (struct nfs_write_data *nfs_data, int how);
+
+	void (*free_deviceid_node) (struct nfs4_deviceid_node *);
+
+	void (*encode_layoutreturn) (struct pnfs_layout_hdr *layoutid,
+				     struct xdr_stream *xdr,
+				     const struct nfs4_layoutreturn_args *args);
+
+	void (*encode_layoutcommit) (struct pnfs_layout_hdr *layoutid,
+				     struct xdr_stream *xdr,
+				     const struct nfs4_layoutcommit_args *args);
 };
 
 struct pnfs_layout_hdr {
@@ -120,21 +143,22 @@ extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
 extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
 				   struct pnfs_device *dev);
 extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp);
+extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
 
 /* pnfs.c */
 void get_layout_hdr(struct pnfs_layout_hdr *lo);
 void put_lseg(struct pnfs_layout_segment *lseg);
 struct pnfs_layout_segment *
 pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx,
-		   enum pnfs_iomode access_type, gfp_t gfp_flags);
+		   loff_t pos, u64 count, enum pnfs_iomode access_type,
+		   gfp_t gfp_flags);
 void set_pnfs_layoutdriver(struct nfs_server *, u32 id);
 void unset_pnfs_layoutdriver(struct nfs_server *);
 enum pnfs_try_status pnfs_try_to_write_data(struct nfs_write_data *,
 					     const struct rpc_call_ops *, int);
 enum pnfs_try_status pnfs_try_to_read_data(struct nfs_read_data *,
 					    const struct rpc_call_ops *);
-void pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *);
-void pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *);
+bool pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req);
 int pnfs_layout_process(struct nfs4_layoutget *lgp);
 void pnfs_free_lseg_list(struct list_head *tmp_list);
 void pnfs_destroy_layout(struct nfs_inode *);
@@ -148,13 +172,38 @@ int pnfs_choose_layoutget_stateid(nfs4_stateid *dst,
 				  struct nfs4_state *open_state);
 int mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,
-				u32 iomode);
+				struct pnfs_layout_range *recall_range);
 bool pnfs_roc(struct inode *ino);
 void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
 bool pnfs_roc_drain(struct inode *ino, u32 *barrier);
 void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
+int _pnfs_return_layout(struct inode *);
+int pnfs_ld_write_done(struct nfs_write_data *);
+int pnfs_ld_read_done(struct nfs_read_data *);
+
+/* pnfs_dev.c */
+struct nfs4_deviceid_node {
+	struct hlist_node		node;
+	struct hlist_node		tmpnode;
+	const struct pnfs_layoutdriver_type *ld;
+	const struct nfs_client		*nfs_client;
+	struct nfs4_deviceid		deviceid;
+	atomic_t			ref;
+};
+
+void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id);
+struct nfs4_deviceid_node *nfs4_find_get_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
+struct nfs4_deviceid_node *nfs4_unhash_put_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
+void nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
+void nfs4_init_deviceid_node(struct nfs4_deviceid_node *,
+			     const struct pnfs_layoutdriver_type *,
+			     const struct nfs_client *,
+			     const struct nfs4_deviceid *);
+struct nfs4_deviceid_node *nfs4_insert_deviceid_node(struct nfs4_deviceid_node *);
+bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *);
+void nfs4_deviceid_purge_client(const struct nfs_client *);
 
 static inline int lo_fail_bit(u32 iomode)
 {
@@ -223,6 +272,36 @@ static inline void pnfs_clear_request_commit(struct nfs_page *req)
 		put_lseg(req->wb_commit_lseg);
 }
 
+/* Should the pNFS client commit and return the layout upon a setattr */
+static inline bool
+pnfs_ld_layoutret_on_setattr(struct inode *inode)
+{
+	if (!pnfs_enabled_sb(NFS_SERVER(inode)))
+		return false;
+	return NFS_SERVER(inode)->pnfs_curr_ld->flags &
+		PNFS_LAYOUTRET_ON_SETATTR;
+}
+
+static inline int pnfs_return_layout(struct inode *ino)
+{
+	struct nfs_inode *nfsi = NFS_I(ino);
+	struct nfs_server *nfss = NFS_SERVER(ino);
+
+	if (pnfs_enabled_sb(nfss) && nfsi->layout)
+		return _pnfs_return_layout(ino);
+
+	return 0;
+}
+
+static inline void pnfs_pageio_init(struct nfs_pageio_descriptor *pgio,
+				    struct inode *inode)
+{
+	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
+
+	if (ld)
+		pgio->pg_test = ld->pg_test;
+}
+
 #else  /* CONFIG_NFS_V4_1 */
 
 static inline void pnfs_destroy_all_layouts(struct nfs_client *clp)
@@ -245,7 +324,8 @@ static inline void put_lseg(struct pnfs_layout_segment *lseg)
 
 static inline struct pnfs_layout_segment *
 pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx,
-		   enum pnfs_iomode access_type, gfp_t gfp_flags)
+		   loff_t pos, u64 count, enum pnfs_iomode access_type,
+		   gfp_t gfp_flags)
 {
 	return NULL;
 }
@@ -264,6 +344,17 @@ pnfs_try_to_write_data(struct nfs_write_data *data,
 	return PNFS_NOT_ATTEMPTED;
 }
 
+static inline int pnfs_return_layout(struct inode *ino)
+{
+	return 0;
+}
+
+static inline bool
+pnfs_ld_layoutret_on_setattr(struct inode *inode)
+{
+	return false;
+}
+
 static inline bool
 pnfs_roc(struct inode *ino)
 {
@@ -294,16 +385,9 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s)
 {
 }
 
-static inline void
-pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *ino)
-{
-	pgio->pg_test = NULL;
-}
-
-static inline void
-pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *ino)
+static inline void pnfs_pageio_init(struct nfs_pageio_descriptor *pgio,
+				    struct inode *inode)
 {
-	pgio->pg_test = NULL;
 }
 
 static inline void
@@ -331,6 +415,10 @@ static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 {
 	return 0;
 }
+
+static inline void nfs4_deviceid_purge_client(struct nfs_client *ncl)
+{
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 #endif /* FS_NFS_PNFS_H */
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
new file mode 100644
index 000000000000..f0f8e1e22f6c
--- /dev/null
+++ b/fs/nfs/pnfs_dev.c
@@ -0,0 +1,277 @@
+/*
+ *  Device operations for the pnfs client.
+ *
+ *  Copyright (c) 2002
+ *  The Regents of the University of Michigan
+ *  All Rights Reserved
+ *
+ *  Dean Hildebrand <dhildebz@umich.edu>
+ *  Garth Goodson   <Garth.Goodson@netapp.com>
+ *
+ *  Permission is granted to use, copy, create derivative works, and
+ *  redistribute this software and such derivative works for any purpose,
+ *  so long as the name of the University of Michigan is not used in
+ *  any advertising or publicity pertaining to the use or distribution
+ *  of this software without specific, written prior authorization. If
+ *  the above copyright notice or any other identification of the
+ *  University of Michigan is included in any copy of any portion of
+ *  this software, then the disclaimer below must also be included.
+ *
+ *  This software is provided as is, without representation or warranty
+ *  of any kind either express or implied, including without limitation
+ *  the implied warranties of merchantability, fitness for a particular
+ *  purpose, or noninfringement.  The Regents of the University of
+ *  Michigan shall not be liable for any damages, including special,
+ *  indirect, incidental, or consequential damages, with respect to any
+ *  claim arising out of or in connection with the use of the software,
+ *  even if it has been or is hereafter advised of the possibility of
+ *  such damages.
+ */
+
+#include "pnfs.h"
+
+#define NFSDBG_FACILITY		NFSDBG_PNFS
+
+/*
+ * Device ID RCU cache. A device ID is unique per server and layout type.
+ */
+#define NFS4_DEVICE_ID_HASH_BITS	5
+#define NFS4_DEVICE_ID_HASH_SIZE	(1 << NFS4_DEVICE_ID_HASH_BITS)
+#define NFS4_DEVICE_ID_HASH_MASK	(NFS4_DEVICE_ID_HASH_SIZE - 1)
+
+static struct hlist_head nfs4_deviceid_cache[NFS4_DEVICE_ID_HASH_SIZE];
+static DEFINE_SPINLOCK(nfs4_deviceid_lock);
+
+void
+nfs4_print_deviceid(const struct nfs4_deviceid *id)
+{
+	u32 *p = (u32 *)id;
+
+	dprintk("%s: device id= [%x%x%x%x]\n", __func__,
+		p[0], p[1], p[2], p[3]);
+}
+EXPORT_SYMBOL_GPL(nfs4_print_deviceid);
+
+static inline u32
+nfs4_deviceid_hash(const struct nfs4_deviceid *id)
+{
+	unsigned char *cptr = (unsigned char *)id->data;
+	unsigned int nbytes = NFS4_DEVICEID4_SIZE;
+	u32 x = 0;
+
+	while (nbytes--) {
+		x *= 37;
+		x += *cptr++;
+	}
+	return x & NFS4_DEVICE_ID_HASH_MASK;
+}
+
+static struct nfs4_deviceid_node *
+_lookup_deviceid(const struct pnfs_layoutdriver_type *ld,
+		 const struct nfs_client *clp, const struct nfs4_deviceid *id,
+		 long hash)
+{
+	struct nfs4_deviceid_node *d;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node)
+		if (d->ld == ld && d->nfs_client == clp &&
+		    !memcmp(&d->deviceid, id, sizeof(*id))) {
+			if (atomic_read(&d->ref))
+				return d;
+			else
+				continue;
+		}
+	return NULL;
+}
+
+/*
+ * Lookup a deviceid in cache and get a reference count on it if found
+ *
+ * @clp nfs_client associated with deviceid
+ * @id deviceid to look up
+ */
+struct nfs4_deviceid_node *
+_find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
+		   const struct nfs_client *clp, const struct nfs4_deviceid *id,
+		   long hash)
+{
+	struct nfs4_deviceid_node *d;
+
+	rcu_read_lock();
+	d = _lookup_deviceid(ld, clp, id, hash);
+	if (d && !atomic_inc_not_zero(&d->ref))
+		d = NULL;
+	rcu_read_unlock();
+	return d;
+}
+
+struct nfs4_deviceid_node *
+nfs4_find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
+		       const struct nfs_client *clp, const struct nfs4_deviceid *id)
+{
+	return _find_get_deviceid(ld, clp, id, nfs4_deviceid_hash(id));
+}
+EXPORT_SYMBOL_GPL(nfs4_find_get_deviceid);
+
+/*
+ * Unhash and put deviceid
+ *
+ * @clp nfs_client associated with deviceid
+ * @id the deviceid to unhash
+ *
+ * @ret the unhashed node, if found and dereferenced to zero, NULL otherwise.
+ */
+struct nfs4_deviceid_node *
+nfs4_unhash_put_deviceid(const struct pnfs_layoutdriver_type *ld,
+			 const struct nfs_client *clp, const struct nfs4_deviceid *id)
+{
+	struct nfs4_deviceid_node *d;
+
+	spin_lock(&nfs4_deviceid_lock);
+	rcu_read_lock();
+	d = _lookup_deviceid(ld, clp, id, nfs4_deviceid_hash(id));
+	rcu_read_unlock();
+	if (!d) {
+		spin_unlock(&nfs4_deviceid_lock);
+		return NULL;
+	}
+	hlist_del_init_rcu(&d->node);
+	spin_unlock(&nfs4_deviceid_lock);
+	synchronize_rcu();
+
+	/* balance the initial ref set in pnfs_insert_deviceid */
+	if (atomic_dec_and_test(&d->ref))
+		return d;
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(nfs4_unhash_put_deviceid);
+
+/*
+ * Delete a deviceid from cache
+ *
+ * @clp struct nfs_client qualifying the deviceid
+ * @id deviceid to delete
+ */
+void
+nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *ld,
+		     const struct nfs_client *clp, const struct nfs4_deviceid *id)
+{
+	struct nfs4_deviceid_node *d;
+
+	d = nfs4_unhash_put_deviceid(ld, clp, id);
+	if (!d)
+		return;
+	d->ld->free_deviceid_node(d);
+}
+EXPORT_SYMBOL_GPL(nfs4_delete_deviceid);
+
+void
+nfs4_init_deviceid_node(struct nfs4_deviceid_node *d,
+			const struct pnfs_layoutdriver_type *ld,
+			const struct nfs_client *nfs_client,
+			const struct nfs4_deviceid *id)
+{
+	INIT_HLIST_NODE(&d->node);
+	INIT_HLIST_NODE(&d->tmpnode);
+	d->ld = ld;
+	d->nfs_client = nfs_client;
+	d->deviceid = *id;
+	atomic_set(&d->ref, 1);
+}
+EXPORT_SYMBOL_GPL(nfs4_init_deviceid_node);
+
+/*
+ * Uniquely initialize and insert a deviceid node into cache
+ *
+ * @new new deviceid node
+ *      Note that the caller must set up the following members:
+ *        new->ld
+ *        new->nfs_client
+ *        new->deviceid
+ *
+ * @ret the inserted node, if none found, otherwise, the found entry.
+ */
+struct nfs4_deviceid_node *
+nfs4_insert_deviceid_node(struct nfs4_deviceid_node *new)
+{
+	struct nfs4_deviceid_node *d;
+	long hash;
+
+	spin_lock(&nfs4_deviceid_lock);
+	hash = nfs4_deviceid_hash(&new->deviceid);
+	d = _find_get_deviceid(new->ld, new->nfs_client, &new->deviceid, hash);
+	if (d) {
+		spin_unlock(&nfs4_deviceid_lock);
+		return d;
+	}
+
+	hlist_add_head_rcu(&new->node, &nfs4_deviceid_cache[hash]);
+	spin_unlock(&nfs4_deviceid_lock);
+	atomic_inc(&new->ref);
+
+	return new;
+}
+EXPORT_SYMBOL_GPL(nfs4_insert_deviceid_node);
+
+/*
+ * Dereference a deviceid node and delete it when its reference count drops
+ * to zero.
+ *
+ * @d deviceid node to put
+ *
+ * @ret true iff the node was deleted
+ */
+bool
+nfs4_put_deviceid_node(struct nfs4_deviceid_node *d)
+{
+	if (!atomic_dec_and_lock(&d->ref, &nfs4_deviceid_lock))
+		return false;
+	hlist_del_init_rcu(&d->node);
+	spin_unlock(&nfs4_deviceid_lock);
+	synchronize_rcu();
+	d->ld->free_deviceid_node(d);
+	return true;
+}
+EXPORT_SYMBOL_GPL(nfs4_put_deviceid_node);
+
+static void
+_deviceid_purge_client(const struct nfs_client *clp, long hash)
+{
+	struct nfs4_deviceid_node *d;
+	struct hlist_node *n;
+	HLIST_HEAD(tmp);
+
+	spin_lock(&nfs4_deviceid_lock);
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node)
+		if (d->nfs_client == clp && atomic_read(&d->ref)) {
+			hlist_del_init_rcu(&d->node);
+			hlist_add_head(&d->tmpnode, &tmp);
+		}
+	rcu_read_unlock();
+	spin_unlock(&nfs4_deviceid_lock);
+
+	if (hlist_empty(&tmp))
+		return;
+
+	synchronize_rcu();
+	while (!hlist_empty(&tmp)) {
+		d = hlist_entry(tmp.first, struct nfs4_deviceid_node, tmpnode);
+		hlist_del(&d->tmpnode);
+		if (atomic_dec_and_test(&d->ref))
+			d->ld->free_deviceid_node(d);
+	}
+}
+
+void
+nfs4_deviceid_purge_client(const struct nfs_client *clp)
+{
+	long h;
+
+	if (!(clp->cl_exchange_flags & EXCHGID4_FLAG_USE_PNFS_MDS))
+		return;
+	for (h = 0; h < NFS4_DEVICE_ID_HASH_SIZE; h++)
+		_deviceid_purge_client(clp, h);
+}
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 2bcf0dc306a1..20a7f952e244 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -288,7 +288,9 @@ static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc)
 	atomic_set(&req->wb_complete, requests);
 
 	BUG_ON(desc->pg_lseg != NULL);
-	lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_READ, GFP_KERNEL);
+	lseg = pnfs_update_layout(desc->pg_inode, req->wb_context,
+				  req_offset(req), desc->pg_count,
+				  IOMODE_READ, GFP_KERNEL);
 	ClearPageError(page);
 	offset = 0;
 	nbytes = desc->pg_count;
@@ -351,7 +353,9 @@ static int nfs_pagein_one(struct nfs_pageio_descriptor *desc)
 	}
 	req = nfs_list_entry(data->pages.next);
 	if ((!lseg) && list_is_singular(&data->pages))
-		lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_READ, GFP_KERNEL);
+		lseg = pnfs_update_layout(desc->pg_inode, req->wb_context,
+					  req_offset(req), desc->pg_count,
+					  IOMODE_READ, GFP_KERNEL);
 
 	ret = nfs_read_rpcsetup(req, data, &nfs_read_full_ops, desc->pg_count,
 				0, lseg);
@@ -660,7 +664,6 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	if (ret == 0)
 		goto read_complete; /* all pages were read */
 
-	pnfs_pageio_init_read(&pgio, inode);
 	if (rsize < PAGE_CACHE_SIZE)
 		nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0);
 	else
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index e288f06d3fa7..ce40e5c568ba 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -63,6 +63,7 @@
 #include "iostat.h"
 #include "internal.h"
 #include "fscache.h"
+#include "pnfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -732,6 +733,28 @@ static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt)
 
 	return 0;
 }
+#ifdef CONFIG_NFS_V4_1
+void show_sessions(struct seq_file *m, struct nfs_server *server)
+{
+	if (nfs4_has_session(server->nfs_client))
+		seq_printf(m, ",sessions");
+}
+#else
+void show_sessions(struct seq_file *m, struct nfs_server *server) {}
+#endif
+
+#ifdef CONFIG_NFS_V4_1
+void show_pnfs(struct seq_file *m, struct nfs_server *server)
+{
+	seq_printf(m, ",pnfs=");
+	if (server->pnfs_curr_ld)
+		seq_printf(m, "%s", server->pnfs_curr_ld->name);
+	else
+		seq_printf(m, "not configured");
+}
+#else  /* CONFIG_NFS_V4_1 */
+void show_pnfs(struct seq_file *m, struct nfs_server *server) {}
+#endif /* CONFIG_NFS_V4_1 */
 
 static int nfs_show_devname(struct seq_file *m, struct vfsmount *mnt)
 {
@@ -792,6 +815,8 @@ static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt)
 		seq_printf(m, "bm0=0x%x", nfss->attr_bitmask[0]);
 		seq_printf(m, ",bm1=0x%x", nfss->attr_bitmask[1]);
 		seq_printf(m, ",acl=0x%x", nfss->acl_bitmask);
+		show_sessions(m, nfss);
+		show_pnfs(m, nfss);
 	}
 #endif
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 49c715b4ac92..e268e3b23497 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -939,7 +939,9 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc)
 	atomic_set(&req->wb_complete, requests);
 
 	BUG_ON(desc->pg_lseg);
-	lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_RW, GFP_NOFS);
+	lseg = pnfs_update_layout(desc->pg_inode, req->wb_context,
+				  req_offset(req), desc->pg_count,
+				  IOMODE_RW, GFP_NOFS);
 	ClearPageError(page);
 	offset = 0;
 	nbytes = desc->pg_count;
@@ -1013,7 +1015,9 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc)
 	}
 	req = nfs_list_entry(data->pages.next);
 	if ((!lseg) && list_is_singular(&data->pages))
-		lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_RW, GFP_NOFS);
+		lseg = pnfs_update_layout(desc->pg_inode, req->wb_context,
+					  req_offset(req), desc->pg_count,
+					  IOMODE_RW, GFP_NOFS);
 
 	if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
 	    (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit))
@@ -1032,8 +1036,6 @@ static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
 {
 	size_t wsize = NFS_SERVER(inode)->wsize;
 
-	pnfs_pageio_init_write(pgio, inode);
-
 	if (wsize < PAGE_CACHE_SIZE)
 		nfs_pageio_init(pgio, inode, nfs_flush_multi, wsize, ioflags);
 	else
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 18b3e8975fe0..fbb2a5ef5817 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -82,6 +82,7 @@ config NFSD_V4
 	select NFSD_V3
 	select FS_POSIX_ACL
 	select SUNRPC_GSS
+	select CRYPTO
 	help
 	  This option enables support in your system's NFS server for
 	  version 4 of the NFS protocol (RFC 3530).
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index ad000aeb21a2..b9566e46219f 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1354,12 +1354,6 @@ exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp)
 	if (IS_ERR(exp))
 		return nfserrno(PTR_ERR(exp));
 	rv = fh_compose(fhp, exp, exp->ex_path.dentry, NULL);
-	if (rv)
-		goto out;
-	rv = check_nfsd_access(exp, rqstp);
-	if (rv)
-		fh_put(fhp);
-out:
 	exp_put(exp);
 	return rv;
 }
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 2247fc91d5e9..9095f3c21df9 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -245,7 +245,7 @@ nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
 	}
 
 	/* Now create the file and set attributes */
-	nfserr = nfsd_create_v3(rqstp, dirfhp, argp->name, argp->len,
+	nfserr = do_nfsd_create(rqstp, dirfhp, argp->name, argp->len,
 				attr, newfhp,
 				argp->createmode, argp->verf, NULL, NULL);
 
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index ad48faca20fc..08c6e36ab2eb 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -842,7 +842,7 @@ out:
 	return rv;
 }
 
-__be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen)
+static __be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen)
 {
 	struct svc_fh	fh;
 	int err;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 5fcb1396a7e3..3a6dbd70b34b 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -196,9 +196,9 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
 
 		/*
 		 * Note: create modes (UNCHECKED,GUARDED...) are the same
-		 * in NFSv4 as in v3.
+		 * in NFSv4 as in v3 except EXCLUSIVE4_1.
 		 */
-		status = nfsd_create_v3(rqstp, current_fh, open->op_fname.data,
+		status = do_nfsd_create(rqstp, current_fh, open->op_fname.data,
 					open->op_fname.len, &open->op_iattr,
 					&resfh, open->op_createmode,
 					(u32 *)open->op_verf.data,
@@ -403,7 +403,7 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen;
 	memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval,
 	       putfh->pf_fhlen);
-	return fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
+	return fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS);
 }
 
 static __be32
@@ -762,6 +762,9 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	__be32 err;
 
 	fh_init(&resfh, NFS4_FHSIZE);
+	err = fh_verify(rqstp, &cstate->current_fh, S_IFDIR, NFSD_MAY_EXEC);
+	if (err)
+		return err;
 	err = nfsd_lookup_dentry(rqstp, &cstate->current_fh,
 				    secinfo->si_name, secinfo->si_namelen,
 				    &exp, &dentry);
@@ -986,6 +989,9 @@ enum nfsd4_op_flags {
 	ALLOWED_WITHOUT_FH = 1 << 0,	/* No current filehandle required */
 	ALLOWED_ON_ABSENT_FS = 1 << 1,	/* ops processed on absent fs */
 	ALLOWED_AS_FIRST_OP = 1 << 2,	/* ops reqired first in compound */
+	/* For rfc 5661 section 2.6.3.1.1: */
+	OP_HANDLES_WRONGSEC = 1 << 3,
+	OP_IS_PUTFH_LIKE = 1 << 4,
 };
 
 struct nfsd4_operation {
@@ -1031,6 +1037,44 @@ static __be32 nfs41_check_op_ordering(struct nfsd4_compoundargs *args)
 	return nfs_ok;
 }
 
+static inline struct nfsd4_operation *OPDESC(struct nfsd4_op *op)
+{
+	return &nfsd4_ops[op->opnum];
+}
+
+static bool need_wrongsec_check(struct svc_rqst *rqstp)
+{
+	struct nfsd4_compoundres *resp = rqstp->rq_resp;
+	struct nfsd4_compoundargs *argp = rqstp->rq_argp;
+	struct nfsd4_op *this = &argp->ops[resp->opcnt - 1];
+	struct nfsd4_op *next = &argp->ops[resp->opcnt];
+	struct nfsd4_operation *thisd;
+	struct nfsd4_operation *nextd;
+
+	thisd = OPDESC(this);
+	/*
+	 * Most ops check wronsec on our own; only the putfh-like ops
+	 * have special rules.
+	 */
+	if (!(thisd->op_flags & OP_IS_PUTFH_LIKE))
+		return false;
+	/*
+	 * rfc 5661 2.6.3.1.1.6: don't bother erroring out a
+	 * put-filehandle operation if we're not going to use the
+	 * result:
+	 */
+	if (argp->opcnt == resp->opcnt)
+		return false;
+
+	nextd = OPDESC(next);
+	/*
+	 * Rest of 2.6.3.1.1: certain operations will return WRONGSEC
+	 * errors themselves as necessary; others should check for them
+	 * now:
+	 */
+	return !(nextd->op_flags & OP_HANDLES_WRONGSEC);
+}
+
 /*
  * COMPOUND call.
  */
@@ -1108,7 +1152,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			goto encode_op;
 		}
 
-		opdesc = &nfsd4_ops[op->opnum];
+		opdesc = OPDESC(op);
 
 		if (!cstate->current_fh.fh_dentry) {
 			if (!(opdesc->op_flags & ALLOWED_WITHOUT_FH)) {
@@ -1126,6 +1170,9 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 		else
 			BUG_ON(op->status == nfs_ok);
 
+		if (!op->status && need_wrongsec_check(rqstp))
+			op->status = check_nfsd_access(cstate->current_fh.fh_export, rqstp);
+
 encode_op:
 		/* Only from SEQUENCE */
 		if (resp->cstate.status == nfserr_replay_cache) {
@@ -1217,10 +1264,12 @@ static struct nfsd4_operation nfsd4_ops[] = {
 	},
 	[OP_LOOKUP] = {
 		.op_func = (nfsd4op_func)nfsd4_lookup,
+		.op_flags = OP_HANDLES_WRONGSEC,
 		.op_name = "OP_LOOKUP",
 	},
 	[OP_LOOKUPP] = {
 		.op_func = (nfsd4op_func)nfsd4_lookupp,
+		.op_flags = OP_HANDLES_WRONGSEC,
 		.op_name = "OP_LOOKUPP",
 	},
 	[OP_NVERIFY] = {
@@ -1229,6 +1278,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
 	},
 	[OP_OPEN] = {
 		.op_func = (nfsd4op_func)nfsd4_open,
+		.op_flags = OP_HANDLES_WRONGSEC,
 		.op_name = "OP_OPEN",
 	},
 	[OP_OPEN_CONFIRM] = {
@@ -1241,17 +1291,20 @@ static struct nfsd4_operation nfsd4_ops[] = {
 	},
 	[OP_PUTFH] = {
 		.op_func = (nfsd4op_func)nfsd4_putfh,
-		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
+				| OP_IS_PUTFH_LIKE,
 		.op_name = "OP_PUTFH",
 	},
 	[OP_PUTPUBFH] = {
 		.op_func = (nfsd4op_func)nfsd4_putrootfh,
-		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
+				| OP_IS_PUTFH_LIKE,
 		.op_name = "OP_PUTPUBFH",
 	},
 	[OP_PUTROOTFH] = {
 		.op_func = (nfsd4op_func)nfsd4_putrootfh,
-		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
+				| OP_IS_PUTFH_LIKE,
 		.op_name = "OP_PUTROOTFH",
 	},
 	[OP_READ] = {
@@ -1281,15 +1334,18 @@ static struct nfsd4_operation nfsd4_ops[] = {
 	},
 	[OP_RESTOREFH] = {
 		.op_func = (nfsd4op_func)nfsd4_restorefh,
-		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
+				| OP_IS_PUTFH_LIKE,
 		.op_name = "OP_RESTOREFH",
 	},
 	[OP_SAVEFH] = {
 		.op_func = (nfsd4op_func)nfsd4_savefh,
+		.op_flags = OP_HANDLES_WRONGSEC,
 		.op_name = "OP_SAVEFH",
 	},
 	[OP_SECINFO] = {
 		.op_func = (nfsd4op_func)nfsd4_secinfo,
+		.op_flags = OP_HANDLES_WRONGSEC,
 		.op_name = "OP_SECINFO",
 	},
 	[OP_SETATTR] = {
@@ -1353,6 +1409,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
 	},
 	[OP_SECINFO_NO_NAME] = {
 		.op_func = (nfsd4op_func)nfsd4_secinfo_no_name,
+		.op_flags = OP_HANDLES_WRONGSEC,
 		.op_name = "OP_SECINFO_NO_NAME",
 	},
 };
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4cf04e11c66c..e98f3c2e9492 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1519,6 +1519,9 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 	bool confirm_me = false;
 	int status = 0;
 
+	if (cr_ses->flags & ~SESSION4_FLAG_MASK_A)
+		return nfserr_inval;
+
 	nfs4_lock_state();
 	unconf = find_unconfirmed_client(&cr_ses->clientid);
 	conf = find_confirmed_client(&cr_ses->clientid);
@@ -1637,8 +1640,9 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
 		return nfserr_badsession;
 
 	status = nfsd4_map_bcts_dir(&bcts->dir);
-	nfsd4_new_conn(rqstp, cstate->session, bcts->dir);
-	return nfs_ok;
+	if (!status)
+		nfsd4_new_conn(rqstp, cstate->session, bcts->dir);
+	return status;
 }
 
 static bool nfsd4_compound_in_session(struct nfsd4_session *session, struct nfs4_sessionid *sid)
@@ -1725,6 +1729,13 @@ static void nfsd4_sequence_check_conn(struct nfsd4_conn *new, struct nfsd4_sessi
 	return;
 }
 
+static bool nfsd4_session_too_many_ops(struct svc_rqst *rqstp, struct nfsd4_session *session)
+{
+	struct nfsd4_compoundargs *args = rqstp->rq_argp;
+
+	return args->opcnt > session->se_fchannel.maxops;
+}
+
 __be32
 nfsd4_sequence(struct svc_rqst *rqstp,
 	       struct nfsd4_compound_state *cstate,
@@ -1753,6 +1764,10 @@ nfsd4_sequence(struct svc_rqst *rqstp,
 	if (!session)
 		goto out;
 
+	status = nfserr_too_many_ops;
+	if (nfsd4_session_too_many_ops(rqstp, session))
+		goto out;
+
 	status = nfserr_badslot;
 	if (seq->slotid >= session->se_fchannel.maxreqs)
 		goto out;
@@ -1808,6 +1823,8 @@ out:
 __be32
 nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_reclaim_complete *rc)
 {
+	int status = 0;
+
 	if (rc->rca_one_fs) {
 		if (!cstate->current_fh.fh_dentry)
 			return nfserr_nofilehandle;
@@ -1817,9 +1834,14 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
 		 */
 		 return nfs_ok;
 	}
+
 	nfs4_lock_state();
-	if (is_client_expired(cstate->session->se_client)) {
-		nfs4_unlock_state();
+	status = nfserr_complete_already;
+	if (cstate->session->se_client->cl_firststate)
+		goto out;
+
+	status = nfserr_stale_clientid;
+	if (is_client_expired(cstate->session->se_client))
 		/*
 		 * The following error isn't really legal.
 		 * But we only get here if the client just explicitly
@@ -1827,11 +1849,13 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
 		 * error it gets back on an operation for the dead
 		 * client.
 		 */
-		return nfserr_stale_clientid;
-	}
+		goto out;
+
+	status = nfs_ok;
 	nfsd4_create_clid_dir(cstate->session->se_client);
+out:
 	nfs4_unlock_state();
-	return nfs_ok;
+	return status;
 }
 
 __be32
@@ -2462,7 +2486,7 @@ find_delegation_file(struct nfs4_file *fp, stateid_t *stid)
 	return NULL;
 }
 
-int share_access_to_flags(u32 share_access)
+static int share_access_to_flags(u32 share_access)
 {
 	share_access &= ~NFS4_SHARE_WANT_MASK;
 
@@ -2882,7 +2906,7 @@ out:
 	return status;
 }
 
-struct lock_manager nfsd4_manager = {
+static struct lock_manager nfsd4_manager = {
 };
 
 static void
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index c6766af00d98..990181103214 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -424,15 +424,12 @@ nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access
 static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, struct nfsd4_bind_conn_to_session *bcts)
 {
 	DECODE_HEAD;
-	u32 dummy;
 
 	READ_BUF(NFS4_MAX_SESSIONID_LEN + 8);
 	COPYMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN);
 	READ32(bcts->dir);
-	/* XXX: Perhaps Tom Tucker could help us figure out how we
-	 * should be using ctsa_use_conn_in_rdma_mode: */
-	READ32(dummy);
-
+	/* XXX: skipping ctsa_use_conn_in_rdma_mode.  Perhaps Tom Tucker
+	 * could help us figure out we should be using it. */
 	DECODE_TAIL;
 }
 
@@ -588,8 +585,6 @@ nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt)
 	READ_BUF(lockt->lt_owner.len);
 	READMEM(lockt->lt_owner.data, lockt->lt_owner.len);
 
-	if (argp->minorversion && !zero_clientid(&lockt->lt_clientid))
-		return nfserr_inval;
 	DECODE_TAIL;
 }
 
@@ -3120,7 +3115,7 @@ nfsd4_encode_destroy_session(struct nfsd4_compoundres *resp, int nfserr,
 	return nfserr;
 }
 
-__be32
+static __be32
 nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr,
 		      struct nfsd4_sequence *seq)
 {
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 1f5eae40f34e..2b1449dd2f49 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -13,6 +13,7 @@
 #include <linux/lockd/lockd.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/gss_api.h>
+#include <linux/sunrpc/gss_krb5_enctypes.h>
 
 #include "idmap.h"
 #include "nfsd.h"
@@ -189,18 +190,10 @@ static struct file_operations export_features_operations = {
 	.release	= single_release,
 };
 
-#ifdef CONFIG_SUNRPC_GSS
+#if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE)
 static int supported_enctypes_show(struct seq_file *m, void *v)
 {
-	struct gss_api_mech *k5mech;
-
-	k5mech = gss_mech_get_by_name("krb5");
-	if (k5mech == NULL)
-		goto out;
-	if (k5mech->gm_upcall_enctypes != NULL)
-		seq_printf(m, k5mech->gm_upcall_enctypes);
-	gss_mech_put(k5mech);
-out:
+	seq_printf(m, KRB5_SUPPORTED_ENCTYPES);
 	return 0;
 }
 
@@ -215,7 +208,7 @@ static struct file_operations supported_enctypes_ops = {
 	.llseek		= seq_lseek,
 	.release	= single_release,
 };
-#endif /* CONFIG_SUNRPC_GSS */
+#endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */
 
 extern int nfsd_pool_stats_open(struct inode *inode, struct file *file);
 extern int nfsd_pool_stats_release(struct inode *inode, struct file *file);
@@ -1427,9 +1420,9 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
 		[NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO},
 		[NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO},
-#ifdef CONFIG_SUNRPC_GSS
+#if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE)
 		[NFSD_SupportedEnctypes] = {"supported_krb5_enctypes", &supported_enctypes_ops, S_IRUGO},
-#endif /* CONFIG_SUNRPC_GSS */
+#endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */
 #ifdef CONFIG_NFSD_V4
 		[NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Gracetime] = {"nfsv4gracetime", &transaction_ops, S_IWUSR|S_IRUSR},
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 55c8e63af0be..90c6aa6d5e0f 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -344,7 +344,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
 	 * which clients virtually always use auth_sys for,
 	 * even while using RPCSEC_GSS for NFS.
 	 */
-	if (access & NFSD_MAY_LOCK)
+	if (access & NFSD_MAY_LOCK || access & NFSD_MAY_BYPASS_GSS)
 		goto skip_pseudoflavor_check;
 	/*
 	 * Clients may expect to be able to use auth_sys during mount,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 129f3c9f62d5..fd0acca5370a 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -181,16 +181,10 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	struct svc_export	*exp;
 	struct dentry		*dparent;
 	struct dentry		*dentry;
-	__be32			err;
 	int			host_err;
 
 	dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);
 
-	/* Obtain dentry and export. */
-	err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
-	if (err)
-		return err;
-
 	dparent = fhp->fh_dentry;
 	exp  = fhp->fh_export;
 	exp_get(exp);
@@ -254,6 +248,9 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
 	struct dentry		*dentry;
 	__be32 err;
 
+	err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
+	if (err)
+		return err;
 	err = nfsd_lookup_dentry(rqstp, fhp, name, len, &exp, &dentry);
 	if (err)
 		return err;
@@ -699,7 +696,15 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor
 }
 #endif /* CONFIG_NFSD_V3 */
 
+static int nfsd_open_break_lease(struct inode *inode, int access)
+{
+	unsigned int mode;
 
+	if (access & NFSD_MAY_NOT_BREAK_LEASE)
+		return 0;
+	mode = (access & NFSD_MAY_WRITE) ? O_WRONLY : O_RDONLY;
+	return break_lease(inode, mode | O_NONBLOCK);
+}
 
 /*
  * Open an existing file or directory.
@@ -747,12 +752,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	if (!inode->i_fop)
 		goto out;
 
-	/*
-	 * Check to see if there are any leases on this file.
-	 * This may block while leases are broken.
-	 */
-	if (!(access & NFSD_MAY_NOT_BREAK_LEASE))
-		host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? O_WRONLY : 0));
+	host_err = nfsd_open_break_lease(inode, access);
 	if (host_err) /* NOMEM or WOULDBLOCK */
 		goto out_nfserr;
 
@@ -877,13 +877,11 @@ static __be32
 nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
               loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
 {
-	struct inode *inode;
 	mm_segment_t	oldfs;
 	__be32		err;
 	int		host_err;
 
 	err = nfserr_perm;
-	inode = file->f_path.dentry->d_inode;
 
 	if (file->f_op->splice_read && rqstp->rq_splice_ok) {
 		struct splice_desc sd = {
@@ -1340,11 +1338,18 @@ out_nfserr:
 }
 
 #ifdef CONFIG_NFSD_V3
+
+static inline int nfsd_create_is_exclusive(int createmode)
+{
+	return createmode == NFS3_CREATE_EXCLUSIVE
+	       || createmode == NFS4_CREATE_EXCLUSIVE4_1;
+}
+
 /*
- * NFSv3 version of nfsd_create
+ * NFSv3 and NFSv4 version of nfsd_create
  */
 __be32
-nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
+do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		char *fname, int flen, struct iattr *iap,
 		struct svc_fh *resfhp, int createmode, u32 *verifier,
 	        int *truncp, int *created)
@@ -1396,7 +1401,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (err)
 		goto out;
 
-	if (createmode == NFS3_CREATE_EXCLUSIVE) {
+	if (nfsd_create_is_exclusive(createmode)) {
 		/* solaris7 gets confused (bugid 4218508) if these have
 		 * the high bit set, so just clear the high bits. If this is
 		 * ever changed to use different attrs for storing the
@@ -1437,6 +1442,11 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			    && dchild->d_inode->i_atime.tv_sec == v_atime
 			    && dchild->d_inode->i_size  == 0 )
 				break;
+		case NFS4_CREATE_EXCLUSIVE4_1:
+			if (   dchild->d_inode->i_mtime.tv_sec == v_mtime
+			    && dchild->d_inode->i_atime.tv_sec == v_atime
+			    && dchild->d_inode->i_size  == 0 )
+				goto set_attr;
 			 /* fallthru */
 		case NFS3_CREATE_GUARDED:
 			err = nfserr_exist;
@@ -1455,7 +1465,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 
 	nfsd_check_ignore_resizing(iap);
 
-	if (createmode == NFS3_CREATE_EXCLUSIVE) {
+	if (nfsd_create_is_exclusive(createmode)) {
 		/* Cram the verifier into atime/mtime */
 		iap->ia_valid = ATTR_MTIME|ATTR_ATIME
 			| ATTR_MTIME_SET|ATTR_ATIME_SET;
@@ -1653,8 +1663,10 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 	if (!dold->d_inode)
 		goto out_drop_write;
 	host_err = nfsd_break_lease(dold->d_inode);
-	if (host_err)
+	if (host_err) {
+		err = nfserrno(host_err);
 		goto out_drop_write;
+	}
 	host_err = vfs_link(dold, dirp, dnew);
 	if (!host_err) {
 		err = nfserrno(commit_metadata(ffhp));
@@ -2034,7 +2046,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
 	struct inode	*inode = dentry->d_inode;
 	int		err;
 
-	if (acc == NFSD_MAY_NOP)
+	if ((acc & NFSD_MAY_MASK) == NFSD_MAY_NOP)
 		return 0;
 #if 0
 	dprintk("nfsd: permission 0x%x%s%s%s%s%s%s%s mode 0%o%s%s%s\n",
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 9a370a5e36b7..e0bbac04d1dd 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -17,10 +17,14 @@
 #define NFSD_MAY_SATTR		8
 #define NFSD_MAY_TRUNC		16
 #define NFSD_MAY_LOCK		32
+#define NFSD_MAY_MASK		63
+
+/* extra hints to permission and open routines: */
 #define NFSD_MAY_OWNER_OVERRIDE	64
 #define NFSD_MAY_LOCAL_ACCESS	128 /* IRIX doing local access check on device special file*/
 #define NFSD_MAY_BYPASS_GSS_ON_ROOT 256
 #define NFSD_MAY_NOT_BREAK_LEASE 512
+#define NFSD_MAY_BYPASS_GSS	1024
 
 #define NFSD_MAY_CREATE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE)
 #define NFSD_MAY_REMOVE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
@@ -54,7 +58,7 @@ __be32		nfsd_create(struct svc_rqst *, struct svc_fh *,
 				int type, dev_t rdev, struct svc_fh *res);
 #ifdef CONFIG_NFSD_V3
 __be32		nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *);
-__be32		nfsd_create_v3(struct svc_rqst *, struct svc_fh *,
+__be32		do_nfsd_create(struct svc_rqst *, struct svc_fh *,
 				char *name, int len, struct iattr *attrs,
 				struct svc_fh *res, int createmode,
 				u32 *verifier, int *truncp, int *created);
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index 7eafe468a29c..b2e3ff347620 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -1346,6 +1346,11 @@ static void nilfs_btree_shrink(struct nilfs_bmap *btree,
 	path[level].bp_bh = NULL;
 }
 
+static void nilfs_btree_nop(struct nilfs_bmap *btree,
+			    struct nilfs_btree_path *path,
+			    int level, __u64 *keyp, __u64 *ptrp)
+{
+}
 
 static int nilfs_btree_prepare_delete(struct nilfs_bmap *btree,
 				      struct nilfs_btree_path *path,
@@ -1356,20 +1361,19 @@ static int nilfs_btree_prepare_delete(struct nilfs_bmap *btree,
 	struct buffer_head *bh;
 	struct nilfs_btree_node *node, *parent, *sib;
 	__u64 sibptr;
-	int pindex, level, ncmin, ncmax, ncblk, ret;
+	int pindex, dindex, level, ncmin, ncmax, ncblk, ret;
 
 	ret = 0;
 	stats->bs_nblocks = 0;
 	ncmin = NILFS_BTREE_NODE_NCHILDREN_MIN(nilfs_btree_node_size(btree));
 	ncblk = nilfs_btree_nchildren_per_block(btree);
 
-	for (level = NILFS_BTREE_LEVEL_NODE_MIN;
+	for (level = NILFS_BTREE_LEVEL_NODE_MIN, dindex = path[level].bp_index;
 	     level < nilfs_btree_height(btree) - 1;
 	     level++) {
 		node = nilfs_btree_get_nonroot_node(path, level);
 		path[level].bp_oldreq.bpr_ptr =
-			nilfs_btree_node_get_ptr(node, path[level].bp_index,
-						 ncblk);
+			nilfs_btree_node_get_ptr(node, dindex, ncblk);
 		ret = nilfs_bmap_prepare_end_ptr(btree,
 						 &path[level].bp_oldreq, dat);
 		if (ret < 0)
@@ -1383,6 +1387,7 @@ static int nilfs_btree_prepare_delete(struct nilfs_bmap *btree,
 
 		parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax);
 		pindex = path[level + 1].bp_index;
+		dindex = pindex;
 
 		if (pindex > 0) {
 			/* left sibling */
@@ -1421,6 +1426,14 @@ static int nilfs_btree_prepare_delete(struct nilfs_bmap *btree,
 				path[level].bp_sib_bh = bh;
 				path[level].bp_op = nilfs_btree_concat_right;
 				stats->bs_nblocks++;
+				/*
+				 * When merging right sibling node
+				 * into the current node, pointer to
+				 * the right sibling node must be
+				 * terminated instead.  The adjustment
+				 * below is required for that.
+				 */
+				dindex = pindex + 1;
 				/* continue; */
 			}
 		} else {
@@ -1431,29 +1444,31 @@ static int nilfs_btree_prepare_delete(struct nilfs_bmap *btree,
 			    NILFS_BTREE_ROOT_NCHILDREN_MAX) {
 				path[level].bp_op = nilfs_btree_shrink;
 				stats->bs_nblocks += 2;
+				level++;
+				path[level].bp_op = nilfs_btree_nop;
+				goto shrink_root_child;
 			} else {
 				path[level].bp_op = nilfs_btree_do_delete;
 				stats->bs_nblocks++;
+				goto out;
 			}
-
-			goto out;
-
 		}
 	}
 
+	/* child of the root node is deleted */
+	path[level].bp_op = nilfs_btree_do_delete;
+	stats->bs_nblocks++;
+
+shrink_root_child:
 	node = nilfs_btree_get_root(btree);
 	path[level].bp_oldreq.bpr_ptr =
-		nilfs_btree_node_get_ptr(node, path[level].bp_index,
+		nilfs_btree_node_get_ptr(node, dindex,
 					 NILFS_BTREE_ROOT_NCHILDREN_MAX);
 
 	ret = nilfs_bmap_prepare_end_ptr(btree, &path[level].bp_oldreq, dat);
 	if (ret < 0)
 		goto err_out_child_node;
 
-	/* child of the root node is deleted */
-	path[level].bp_op = nilfs_btree_do_delete;
-	stats->bs_nblocks++;
-
 	/* success */
  out:
 	*levelp = level;
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 587f18432832..b9b45fc2903e 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -801,12 +801,7 @@ out_err:
 
 int nilfs_permission(struct inode *inode, int mask, unsigned int flags)
 {
-	struct nilfs_root *root;
-
-	if (flags & IPERM_FLAG_RCU)
-		return -ECHILD;
-
-	root = NILFS_I(inode)->i_root;
+	struct nilfs_root *root = NILFS_I(inode)->i_root;
 	if ((mask & MAY_WRITE) && root &&
 	    root->cno != NILFS_CPTREE_CURRENT_CNO)
 		return -EROFS; /* snapshot is not writable */
@@ -917,7 +912,7 @@ int nilfs_mark_inode_dirty(struct inode *inode)
  * construction. This function can be called both as a single operation
  * and as a part of indivisible file operations.
  */
-void nilfs_dirty_inode(struct inode *inode)
+void nilfs_dirty_inode(struct inode *inode, int flags)
 {
 	struct nilfs_transaction_info ti;
 	struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 1102a5fbb744..546849b3e88f 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -334,8 +334,6 @@ static int nilfs_rmdir(struct inode *dir, struct dentry *dentry)
 	struct nilfs_transaction_info ti;
 	int err;
 
-	dentry_unhash(dentry);
-
 	err = nilfs_transaction_begin(dir->i_sb, &ti, 0);
 	if (err)
 		return err;
@@ -371,9 +369,6 @@ static int nilfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct nilfs_transaction_info ti;
 	int err;
 
-	if (new_inode && S_ISDIR(new_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	err = nilfs_transaction_begin(old_dir->i_sb, &ti, 1);
 	if (unlikely(err))
 		return err;
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index a9c6a531f80c..f02b9ad43a21 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -269,7 +269,7 @@ int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh);
 extern int nilfs_inode_dirty(struct inode *);
 int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty);
 extern int nilfs_mark_inode_dirty(struct inode *);
-extern void nilfs_dirty_inode(struct inode *);
+extern void nilfs_dirty_inode(struct inode *, int flags);
 int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		 __u64 start, __u64 len);
 
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 141646e88fb5..bb24ab6c282f 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -2573,7 +2573,7 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb,
 	sci->sc_watermark = NILFS_SC_DEFAULT_WATERMARK;
 
 	if (nilfs->ns_interval)
-		sci->sc_interval = nilfs->ns_interval;
+		sci->sc_interval = HZ * nilfs->ns_interval;
 	if (nilfs->ns_watermark)
 		sci->sc_watermark = nilfs->ns_watermark;
 	return sci;
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 4c5488468c14..cd9427023d2e 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -368,7 +368,7 @@ static int ocfs2_find_victim_alloc_group(struct inode *inode,
 					 int *vict_bit,
 					 struct buffer_head **ret_bh)
 {
-	int ret, i, blocks_per_unit = 1;
+	int ret, i, bits_per_unit = 0;
 	u64 blkno;
 	char namebuf[40];
 
@@ -398,14 +398,14 @@ static int ocfs2_find_victim_alloc_group(struct inode *inode,
 	rec = &(cl->cl_recs[0]);
 
 	if (type == GLOBAL_BITMAP_SYSTEM_INODE)
-		blocks_per_unit <<= (osb->s_clustersize_bits -
-						inode->i_sb->s_blocksize_bits);
+		bits_per_unit = osb->s_clustersize_bits -
+					inode->i_sb->s_blocksize_bits;
 	/*
 	 * 'vict_blkno' was out of the valid range.
 	 */
 	if ((vict_blkno < le64_to_cpu(rec->c_blkno)) ||
-	    (vict_blkno >= (le32_to_cpu(ac_dinode->id1.bitmap1.i_total) *
-				blocks_per_unit))) {
+	    (vict_blkno >= (le32_to_cpu(ac_dinode->id1.bitmap1.i_total) <<
+				bits_per_unit))) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -441,8 +441,8 @@ static int ocfs2_find_victim_alloc_group(struct inode *inode,
 						le16_to_cpu(bg->bg_bits))) {
 
 				*ret_bh = gd_bh;
-				*vict_bit = (vict_blkno - blkno) /
-							blocks_per_unit;
+				*vict_bit = (vict_blkno - blkno) >>
+							bits_per_unit;
 				mlog(0, "find the victim group: #%llu, "
 				     "total_bits: %u, vict_bit: %u\n",
 				     blkno, le16_to_cpu(bg->bg_bits),
@@ -472,12 +472,24 @@ static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
 	int ret, goal_bit = 0;
 
 	struct buffer_head *gd_bh = NULL;
-	struct ocfs2_group_desc *bg;
+	struct ocfs2_group_desc *bg = NULL;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	int c_to_b = 1 << (osb->s_clustersize_bits -
 					inode->i_sb->s_blocksize_bits);
 
 	/*
+	 * make goal become cluster aligned.
+	 */
+	range->me_goal = ocfs2_block_to_cluster_start(inode->i_sb,
+						      range->me_goal);
+	/*
+	 * moving goal is not allowd to start with a group desc blok(#0 blk)
+	 * let's compromise to the latter cluster.
+	 */
+	if (range->me_goal == le64_to_cpu(bg->bg_blkno))
+		range->me_goal += c_to_b;
+
+	/*
 	 * validate goal sits within global_bitmap, and return the victim
 	 * group desc
 	 */
@@ -491,19 +503,6 @@ static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
 	bg = (struct ocfs2_group_desc *)gd_bh->b_data;
 
 	/*
-	 * make goal become cluster aligned.
-	 */
-	if (range->me_goal % c_to_b)
-		range->me_goal = range->me_goal / c_to_b * c_to_b;
-
-	/*
-	 * moving goal is not allowd to start with a group desc blok(#0 blk)
-	 * let's compromise to the latter cluster.
-	 */
-	if (range->me_goal == le64_to_cpu(bg->bg_blkno))
-		range->me_goal += c_to_b;
-
-	/*
 	 * movement is not gonna cross two groups.
 	 */
 	if ((le16_to_cpu(bg->bg_bits) - goal_bit) * osb->s_clustersize <
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index cdbaf5e97308..56f61027236b 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1072,7 +1072,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 
 	sb->s_magic = OCFS2_SUPER_MAGIC;
 
-	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+	sb->s_flags = (sb->s_flags & ~(MS_POSIXACL | MS_NOSEC)) |
 		((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
 
 	/* Hard readonly mode only if: bdev_read_only, MS_RDONLY,
diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c
index c368360c35a1..3b8d3979e03b 100644
--- a/fs/omfs/dir.c
+++ b/fs/omfs/dir.c
@@ -241,11 +241,9 @@ static int omfs_remove(struct inode *dir, struct dentry *dentry)
 	int ret;
 
 
-	if (S_ISDIR(inode->i_mode)) {
-		dentry_unhash(dentry);
-		if (!omfs_dir_is_empty(inode))
-			return -ENOTEMPTY;
-	}
+	if (S_ISDIR(inode->i_mode) &&
+	    !omfs_dir_is_empty(inode))
+		return -ENOTEMPTY;
 
 	ret = omfs_delete_entry(dentry);
 	if (ret)
@@ -382,9 +380,6 @@ static int omfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int err;
 
 	if (new_inode) {
-		if (S_ISDIR(new_inode->i_mode))
-			dentry_unhash(new_dentry);
-
 		/* overwriting existing file/dir */
 		err = omfs_remove(new_dir, new_dentry);
 		if (err)
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index d738a7e493dd..2c6d95257a4d 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -4,7 +4,6 @@
  * Released under GPL v2.
  */
 
-#include <linux/version.h>
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 8ed4d3433199..d545e97d99c3 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -255,11 +255,7 @@ ssize_t part_discard_alignment_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
-	struct gendisk *disk = dev_to_disk(dev);
-
-	return sprintf(buf, "%u\n",
-			queue_limit_discard_alignment(&disk->queue->limits,
-							p->start_sect));
+	return sprintf(buf, "%u\n", p->discard_alignment);
 }
 
 ssize_t part_stat_show(struct device *dev,
@@ -453,6 +449,8 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	p->start_sect = start;
 	p->alignment_offset =
 		queue_limit_alignment_offset(&disk->queue->limits, start);
+	p->discard_alignment =
+		queue_limit_discard_alignment(&disk->queue->limits, start);
 	p->nr_sects = len;
 	p->partno = partno;
 	p->policy = get_disk_ro(disk);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 4ede550517a6..8a84210ca080 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -83,6 +83,9 @@
 #include <linux/pid_namespace.h>
 #include <linux/fs_struct.h>
 #include <linux/slab.h>
+#ifdef CONFIG_HARDWALL
+#include <asm/hardwall.h>
+#endif
 #include "internal.h"
 
 /* NOTE:
@@ -2166,11 +2169,7 @@ static const struct file_operations proc_fd_operations = {
  */
 static int proc_fd_permission(struct inode *inode, int mask, unsigned int flags)
 {
-	int rv;
-
-	if (flags & IPERM_FLAG_RCU)
-		return -ECHILD;
-	rv = generic_permission(inode, mask, flags, NULL);
+	int rv = generic_permission(inode, mask, flags, NULL);
 	if (rv == 0)
 		return 0;
 	if (task_pid(current) == proc_pid(inode))
@@ -2842,6 +2841,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_TASK_IO_ACCOUNTING
 	INF("io",	S_IRUGO, proc_tgid_io_accounting),
 #endif
+#ifdef CONFIG_HARDWALL
+	INF("hardwall",   S_IRUGO, proc_pid_hardwall),
+#endif
 };
 
 static int proc_tgid_base_readdir(struct file * filp,
@@ -3181,6 +3183,9 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_TASK_IO_ACCOUNTING
 	INF("io",	S_IRUGO, proc_tid_io_accounting),
 #endif
+#ifdef CONFIG_HARDWALL
+	INF("hardwall",   S_IRUGO, proc_pid_hardwall),
+#endif
 };
 
 static int proc_tid_base_readdir(struct file * filp,
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 781dec5bd682..be177f702acb 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -38,18 +38,21 @@ static struct dentry *proc_ns_instantiate(struct inode *dir,
 	struct inode *inode;
 	struct proc_inode *ei;
 	struct dentry *error = ERR_PTR(-ENOENT);
+	void *ns;
 
 	inode = proc_pid_make_inode(dir->i_sb, task);
 	if (!inode)
 		goto out;
 
+	ns = ns_ops->get(task);
+	if (!ns)
+		goto out_iput;
+
 	ei = PROC_I(inode);
 	inode->i_mode = S_IFREG|S_IRUSR;
 	inode->i_fop  = &ns_file_operations;
 	ei->ns_ops    = ns_ops;
-	ei->ns	      = ns_ops->get(task);
-	if (!ei->ns)
-		goto out_iput;
+	ei->ns	      = ns;
 
 	dentry->d_op = &pid_dentry_operations;
 	d_add(dentry, inode);
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index f50133c11c24..d167de365a8d 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -304,9 +304,6 @@ static int proc_sys_permission(struct inode *inode, int mask,unsigned int flags)
 	struct ctl_table *table;
 	int error;
 
-	if (flags & IPERM_FLAG_RCU)
-		return -ECHILD;
-
 	/* Executable files are not allowed under /proc/sys/ */
 	if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
 		return -EACCES;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index a9000e9cfee5..d6c3b416529b 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -28,11 +28,12 @@ static int proc_test_super(struct super_block *sb, void *data)
 
 static int proc_set_super(struct super_block *sb, void *data)
 {
-	struct pid_namespace *ns;
-
-	ns = (struct pid_namespace *)data;
-	sb->s_fs_info = get_pid_ns(ns);
-	return set_anon_super(sb, NULL);
+	int err = set_anon_super(sb, NULL);
+	if (!err) {
+		struct pid_namespace *ns = (struct pid_namespace *)data;
+		sb->s_fs_info = get_pid_ns(ns);
+	}
+	return err;
 }
 
 static struct dentry *proc_mount(struct file_system_type *fs_type,
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 76c8164d5651..118662690cdf 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -831,8 +831,6 @@ static int reiserfs_rmdir(struct inode *dir, struct dentry *dentry)
 	INITIALIZE_PATH(path);
 	struct reiserfs_dir_entry de;
 
-	dentry_unhash(dentry);
-
 	/* we will be doing 2 balancings and update 2 stat data, we change quotas
 	 * of the owner of the directory and of the owner of the parent directory.
 	 * The quota structure is possibly deleted only on last iput => outside
@@ -1227,9 +1225,6 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	unsigned long savelink = 1;
 	struct timespec ctime;
 
-	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	/* three balancings: (1) old name removal, (2) new name insertion
 	   and (3) maybe "save" link insertion
 	   stat data updates: (1) old directory,
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index b216ff6be1c9..aa91089162cb 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -568,7 +568,7 @@ static void destroy_inodecache(void)
 }
 
 /* we don't mark inodes dirty, we just log them */
-static void reiserfs_dirty_inode(struct inode *inode)
+static void reiserfs_dirty_inode(struct inode *inode, int flags)
 {
 	struct reiserfs_transaction_handle th;
 
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 50f1abccd1cd..d78089690965 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -98,7 +98,6 @@ static int xattr_rmdir(struct inode *dir, struct dentry *dentry)
 
 	reiserfs_mutex_lock_nested_safe(&dentry->d_inode->i_mutex,
 					I_MUTEX_CHILD, dir->i_sb);
-	dentry_unhash(dentry);
 	error = dir->i_op->rmdir(dir, dentry);
 	if (!error)
 		dentry->d_inode->i_flags |= S_DEAD;
@@ -955,8 +954,6 @@ static int xattr_mount_check(struct super_block *s)
 
 int reiserfs_permission(struct inode *inode, int mask, unsigned int flags)
 {
-	if (flags & IPERM_FLAG_RCU)
-		return -ECHILD;
 	/*
 	 * We don't do permission checks on the internal objects.
 	 * Permissions are determined by the "owning" object.
diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c
index f0511e816967..eed99428f104 100644
--- a/fs/romfs/mmap-nommu.c
+++ b/fs/romfs/mmap-nommu.c
@@ -27,14 +27,18 @@ static unsigned long romfs_get_unmapped_area(struct file *file,
 {
 	struct inode *inode = file->f_mapping->host;
 	struct mtd_info *mtd = inode->i_sb->s_mtd;
-	unsigned long isize, offset;
+	unsigned long isize, offset, maxpages, lpages;
 
 	if (!mtd)
 		goto cant_map_directly;
 
+	/* the mapping mustn't extend beyond the EOF */
+	lpages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	isize = i_size_read(inode);
 	offset = pgoff << PAGE_SHIFT;
-	if (offset > isize || len > isize || offset > isize - len)
+
+	maxpages = (isize + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if ((pgoff >= maxpages) || (maxpages - pgoff < lpages))
 		return (unsigned long) -EINVAL;
 
 	/* we need to call down to the MTD layer to do the actual mapping */
diff --git a/fs/squashfs/export.c b/fs/squashfs/export.c
index 730c56248c9b..5e1101ff276f 100644
--- a/fs/squashfs/export.c
+++ b/fs/squashfs/export.c
@@ -147,7 +147,7 @@ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb,
 	 * table[0] points to the first inode lookup table metadata block,
 	 * this should be less than lookup_table_start
 	 */
-	if (!IS_ERR(table) && table[0] >= lookup_table_start) {
+	if (!IS_ERR(table) && le64_to_cpu(table[0]) >= lookup_table_start) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}
diff --git a/fs/squashfs/fragment.c b/fs/squashfs/fragment.c
index 1516a6490bfb..0ed6edbc5c71 100644
--- a/fs/squashfs/fragment.c
+++ b/fs/squashfs/fragment.c
@@ -90,7 +90,7 @@ __le64 *squashfs_read_fragment_index_table(struct super_block *sb,
 	 * table[0] points to the first fragment table metadata block, this
 	 * should be less than fragment_table_start
 	 */
-	if (!IS_ERR(table) && table[0] >= fragment_table_start) {
+	if (!IS_ERR(table) && le64_to_cpu(table[0]) >= fragment_table_start) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}
diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c
index a70858e0fb44..d38ea3dab951 100644
--- a/fs/squashfs/id.c
+++ b/fs/squashfs/id.c
@@ -93,7 +93,7 @@ __le64 *squashfs_read_id_index_table(struct super_block *sb,
 	 * table[0] points to the first id lookup table metadata block, this
 	 * should be less than id_table_start
 	 */
-	if (!IS_ERR(table) && table[0] >= id_table_start) {
+	if (!IS_ERR(table) && le64_to_cpu(table[0]) >= id_table_start) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 6f26abee3597..7438850c62d0 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -245,7 +245,7 @@ allocate_id_index_table:
 		msblk->id_table = NULL;
 		goto failed_mount;
 	}
-	next_table = msblk->id_table[0];
+	next_table = le64_to_cpu(msblk->id_table[0]);
 
 	/* Handle inode lookup table */
 	lookup_table_start = le64_to_cpu(sblk->lookup_table_start);
@@ -261,7 +261,7 @@ allocate_id_index_table:
 		msblk->inode_lookup_table = NULL;
 		goto failed_mount;
 	}
-	next_table = msblk->inode_lookup_table[0];
+	next_table = le64_to_cpu(msblk->inode_lookup_table[0]);
 
 	sb->s_export_op = &squashfs_export_ops;
 
@@ -286,7 +286,7 @@ handle_fragments:
 		msblk->fragment_index = NULL;
 		goto failed_mount;
 	}
-	next_table = msblk->fragment_index[0];
+	next_table = le64_to_cpu(msblk->fragment_index[0]);
 
 check_directory_table:
 	/* Sanity check directory_table */
diff --git a/fs/super.c b/fs/super.c
index c75593953c52..ab3d672db0de 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -822,7 +822,7 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 	} else {
 		char b[BDEVNAME_SIZE];
 
-		s->s_flags = flags;
+		s->s_flags = flags | MS_NOSEC;
 		s->s_mode = mode;
 		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
 		sb_set_blocksize(s, block_size(bdev));
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 266895783b47..e34f0d99ea4e 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -95,6 +95,14 @@ static int sysfs_set_super(struct super_block *sb, void *data)
 	return error;
 }
 
+static void free_sysfs_super_info(struct sysfs_super_info *info)
+{
+	int type;
+	for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++)
+		kobj_ns_drop(type, info->ns[type]);
+	kfree(info);
+}
+
 static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
 {
@@ -108,11 +116,11 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 		return ERR_PTR(-ENOMEM);
 
 	for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++)
-		info->ns[type] = kobj_ns_current(type);
+		info->ns[type] = kobj_ns_grab_current(type);
 
 	sb = sget(fs_type, sysfs_test_super, sysfs_set_super, info);
 	if (IS_ERR(sb) || sb->s_fs_info != info)
-		kfree(info);
+		free_sysfs_super_info(info);
 	if (IS_ERR(sb))
 		return ERR_CAST(sb);
 	if (!sb->s_root) {
@@ -131,12 +139,11 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 static void sysfs_kill_sb(struct super_block *sb)
 {
 	struct sysfs_super_info *info = sysfs_info(sb);
-
 	/* Remove the superblock from fs_supers/s_instances
 	 * so we can't find it, before freeing sysfs_super_info.
 	 */
 	kill_anon_super(sb);
-	kfree(info);
+	free_sysfs_super_info(info);
 }
 
 static struct file_system_type sysfs_fs_type = {
@@ -145,28 +152,6 @@ static struct file_system_type sysfs_fs_type = {
 	.kill_sb	= sysfs_kill_sb,
 };
 
-void sysfs_exit_ns(enum kobj_ns_type type, const void *ns)
-{
-	struct super_block *sb;
-
-	mutex_lock(&sysfs_mutex);
-	spin_lock(&sb_lock);
-	list_for_each_entry(sb, &sysfs_fs_type.fs_supers, s_instances) {
-		struct sysfs_super_info *info = sysfs_info(sb);
-		/*
-		 * If we see a superblock on the fs_supers/s_instances
-		 * list the unmount has not completed and sb->s_fs_info
-		 * points to a valid struct sysfs_super_info.
-		 */
-		/* Ignore superblocks with the wrong ns */
-		if (info->ns[type] != ns)
-			continue;
-		info->ns[type] = NULL;
-	}
-	spin_unlock(&sb_lock);
-	mutex_unlock(&sysfs_mutex);
-}
-
 int __init sysfs_init(void)
 {
 	int err = -ENOMEM;
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index 3d28af31d863..2ed2404f3113 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -136,7 +136,7 @@ struct sysfs_addrm_cxt {
  * instance).
  */
 struct sysfs_super_info {
-	const void *ns[KOBJ_NS_TYPES];
+	void *ns[KOBJ_NS_TYPES];
 };
 #define sysfs_info(SB) ((struct sysfs_super_info *)(SB->s_fs_info))
 extern struct sysfs_dirent sysfs_root;
diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c
index e2cc6756f3b1..e474fbcf8bde 100644
--- a/fs/sysv/namei.c
+++ b/fs/sysv/namei.c
@@ -196,8 +196,6 @@ static int sysv_rmdir(struct inode * dir, struct dentry * dentry)
 	struct inode *inode = dentry->d_inode;
 	int err = -ENOTEMPTY;
 
-	dentry_unhash(dentry);
-
 	if (sysv_empty_dir(inode)) {
 		err = sysv_unlink(dir, dentry);
 		if (!err) {
@@ -224,9 +222,6 @@ static int sysv_rename(struct inode * old_dir, struct dentry * old_dentry,
 	struct sysv_dir_entry * old_de;
 	int err = -ENOENT;
 
-	if (new_inode && S_ISDIR(new_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	old_de = sysv_find_entry(old_dentry, &old_page);
 	if (!old_de)
 		goto out;
diff --git a/fs/timerfd.c b/fs/timerfd.c
index f67acbdda5e8..dffeb3795af1 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -61,7 +61,9 @@ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr)
 
 /*
  * Called when the clock was set to cancel the timers in the cancel
- * list.
+ * list. This will wake up processes waiting on these timers. The
+ * wake-up requires ctx->ticks to be non zero, therefore we increment
+ * it before calling wake_up_locked().
  */
 void timerfd_clock_was_set(void)
 {
@@ -76,6 +78,7 @@ void timerfd_clock_was_set(void)
 		spin_lock_irqsave(&ctx->wqh.lock, flags);
 		if (ctx->moffs.tv64 != moffs.tv64) {
 			ctx->moffs.tv64 = KTIME_MAX;
+			ctx->ticks++;
 			wake_up_locked(&ctx->wqh);
 		}
 		spin_unlock_irqrestore(&ctx->wqh.lock, flags);
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index c2b80943560d..ef5abd38f0bf 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -656,8 +656,6 @@ static int ubifs_rmdir(struct inode *dir, struct dentry *dentry)
 	struct ubifs_inode *dir_ui = ubifs_inode(dir);
 	struct ubifs_budget_req req = { .mod_dent = 1, .dirtied_ino = 2 };
 
-	dentry_unhash(dentry);
-
 	/*
 	 * Budget request settings: deletion direntry, deletion inode and
 	 * changing the parent inode. If budgeting fails, go ahead anyway
@@ -978,9 +976,6 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			.dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) };
 	struct timespec time;
 
-	if (new_inode && S_ISDIR(new_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	/*
 	 * Budget request settings: deletion direntry, new direntry, removing
 	 * the old inode, and changing old and new parent directory inodes.
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index 166951e0dcd3..3be645e012c9 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -581,6 +581,7 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len)
 	ubifs_assert(wbuf->size % c->min_io_size == 0);
 	ubifs_assert(mutex_is_locked(&wbuf->io_mutex));
 	ubifs_assert(!c->ro_media && !c->ro_mount);
+	ubifs_assert(!c->space_fixup);
 	if (c->leb_size - wbuf->offs >= c->max_write_size)
 		ubifs_assert(!((wbuf->offs + wbuf->size) % c->max_write_size));
 
@@ -759,6 +760,7 @@ int ubifs_write_node(struct ubifs_info *c, void *buf, int len, int lnum,
 	ubifs_assert(lnum >= 0 && lnum < c->leb_cnt && offs >= 0);
 	ubifs_assert(offs % c->min_io_size == 0 && offs < c->leb_size);
 	ubifs_assert(!c->ro_media && !c->ro_mount);
+	ubifs_assert(!c->space_fixup);
 
 	if (c->ro_error)
 		return -EROFS;
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 34b1679e6e3a..cef0460f4c54 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -669,6 +669,7 @@ out_free:
 
 out_release:
 	release_head(c, BASEHD);
+	kfree(dent);
 out_ro:
 	ubifs_ro_mode(c, err);
 	if (last_reference)
diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c
index bd644bf587a8..a5422fffbd69 100644
--- a/fs/ubifs/orphan.c
+++ b/fs/ubifs/orphan.c
@@ -674,7 +674,7 @@ static int kill_orphans(struct ubifs_info *c)
 		if (IS_ERR(sleb)) {
 			if (PTR_ERR(sleb) == -EUCLEAN)
 				sleb = ubifs_recover_leb(c, lnum, 0,
-							 c->sbuf, 0);
+							 c->sbuf, -1);
 			if (IS_ERR(sleb)) {
 				err = PTR_ERR(sleb);
 				break;
diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c
index 731d9e2e7b50..783d8e0beb76 100644
--- a/fs/ubifs/recovery.c
+++ b/fs/ubifs/recovery.c
@@ -564,19 +564,15 @@ static int fix_unclean_leb(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
 }
 
 /**
- * drop_last_node - drop the last node or group of nodes.
+ * drop_last_group - drop the last group of nodes.
  * @sleb: scanned LEB information
  * @offs: offset of dropped nodes is returned here
- * @grouped: non-zero if whole group of nodes have to be dropped
  *
  * This is a helper function for 'ubifs_recover_leb()' which drops the last
- * node of the scanned LEB or the last group of nodes if @grouped is not zero.
- * This function returns %1 if a node was dropped and %0 otherwise.
+ * group of nodes of the scanned LEB.
  */
-static int drop_last_node(struct ubifs_scan_leb *sleb, int *offs, int grouped)
+static void drop_last_group(struct ubifs_scan_leb *sleb, int *offs)
 {
-	int dropped = 0;
-
 	while (!list_empty(&sleb->nodes)) {
 		struct ubifs_scan_node *snod;
 		struct ubifs_ch *ch;
@@ -585,17 +581,40 @@ static int drop_last_node(struct ubifs_scan_leb *sleb, int *offs, int grouped)
 				  list);
 		ch = snod->node;
 		if (ch->group_type != UBIFS_IN_NODE_GROUP)
-			return dropped;
-		dbg_rcvry("dropping node at %d:%d", sleb->lnum, snod->offs);
+			break;
+
+		dbg_rcvry("dropping grouped node at %d:%d",
+			  sleb->lnum, snod->offs);
+		*offs = snod->offs;
+		list_del(&snod->list);
+		kfree(snod);
+		sleb->nodes_cnt -= 1;
+	}
+}
+
+/**
+ * drop_last_node - drop the last node.
+ * @sleb: scanned LEB information
+ * @offs: offset of dropped nodes is returned here
+ * @grouped: non-zero if whole group of nodes have to be dropped
+ *
+ * This is a helper function for 'ubifs_recover_leb()' which drops the last
+ * node of the scanned LEB.
+ */
+static void drop_last_node(struct ubifs_scan_leb *sleb, int *offs)
+{
+	struct ubifs_scan_node *snod;
+
+	if (!list_empty(&sleb->nodes)) {
+		snod = list_entry(sleb->nodes.prev, struct ubifs_scan_node,
+				  list);
+
+		dbg_rcvry("dropping last node at %d:%d", sleb->lnum, snod->offs);
 		*offs = snod->offs;
 		list_del(&snod->list);
 		kfree(snod);
 		sleb->nodes_cnt -= 1;
-		dropped = 1;
-		if (!grouped)
-			break;
 	}
-	return dropped;
 }
 
 /**
@@ -604,7 +623,8 @@ static int drop_last_node(struct ubifs_scan_leb *sleb, int *offs, int grouped)
  * @lnum: LEB number
  * @offs: offset
  * @sbuf: LEB-sized buffer to use
- * @grouped: nodes may be grouped for recovery
+ * @jhead: journal head number this LEB belongs to (%-1 if the LEB does not
+ *         belong to any journal head)
  *
  * This function does a scan of a LEB, but caters for errors that might have
  * been caused by the unclean unmount from which we are attempting to recover.
@@ -612,13 +632,14 @@ static int drop_last_node(struct ubifs_scan_leb *sleb, int *offs, int grouped)
  * found, and a negative error code in case of failure.
  */
 struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
-					 int offs, void *sbuf, int grouped)
+					 int offs, void *sbuf, int jhead)
 {
 	int ret = 0, err, len = c->leb_size - offs, start = offs, min_io_unit;
+	int grouped = jhead == -1 ? 0 : c->jheads[jhead].grouped;
 	struct ubifs_scan_leb *sleb;
 	void *buf = sbuf + offs;
 
-	dbg_rcvry("%d:%d", lnum, offs);
+	dbg_rcvry("%d:%d, jhead %d, grouped %d", lnum, offs, jhead, grouped);
 
 	sleb = ubifs_start_scan(c, lnum, offs, sbuf);
 	if (IS_ERR(sleb))
@@ -635,7 +656,7 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
 		 * Scan quietly until there is an error from which we cannot
 		 * recover
 		 */
-		ret = ubifs_scan_a_node(c, buf, len, lnum, offs, 0);
+		ret = ubifs_scan_a_node(c, buf, len, lnum, offs, 1);
 		if (ret == SCANNED_A_NODE) {
 			/* A valid node, and not a padding node */
 			struct ubifs_ch *ch = buf;
@@ -695,59 +716,62 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
 		 * If nodes are grouped, always drop the incomplete group at
 		 * the end.
 		 */
-		drop_last_node(sleb, &offs, 1);
+		drop_last_group(sleb, &offs);
 
-	/*
-	 * While we are in the middle of the same min. I/O unit keep dropping
-	 * nodes. So basically, what we want is to make sure that the last min.
-	 * I/O unit where we saw the corruption is dropped completely with all
-	 * the uncorrupted node which may possibly sit there.
-	 *
-	 * In other words, let's name the min. I/O unit where the corruption
-	 * starts B, and the previous min. I/O unit A. The below code tries to
-	 * deal with a situation when half of B contains valid nodes or the end
-	 * of a valid node, and the second half of B contains corrupted data or
-	 * garbage. This means that UBIFS had been writing to B just before the
-	 * power cut happened. I do not know how realistic is this scenario
-	 * that half of the min. I/O unit had been written successfully and the
-	 * other half not, but this is possible in our 'failure mode emulation'
-	 * infrastructure at least.
-	 *
-	 * So what is the problem, why we need to drop those nodes? Whey can't
-	 * we just clean-up the second half of B by putting a padding node
-	 * there? We can, and this works fine with one exception which was
-	 * reproduced with power cut emulation testing and happens extremely
-	 * rarely. The description follows, but it is worth noting that that is
-	 * only about the GC head, so we could do this trick only if the bud
-	 * belongs to the GC head, but it does not seem to be worth an
-	 * additional "if" statement.
-	 *
-	 * So, imagine the file-system is full, we run GC which is moving valid
-	 * nodes from LEB X to LEB Y (obviously, LEB Y is the current GC head
-	 * LEB). The @c->gc_lnum is -1, which means that GC will retain LEB X
-	 * and will try to continue. Imagine that LEB X is currently the
-	 * dirtiest LEB, and the amount of used space in LEB Y is exactly the
-	 * same as amount of free space in LEB X.
-	 *
-	 * And a power cut happens when nodes are moved from LEB X to LEB Y. We
-	 * are here trying to recover LEB Y which is the GC head LEB. We find
-	 * the min. I/O unit B as described above. Then we clean-up LEB Y by
-	 * padding min. I/O unit. And later 'ubifs_rcvry_gc_commit()' function
-	 * fails, because it cannot find a dirty LEB which could be GC'd into
-	 * LEB Y! Even LEB X does not match because the amount of valid nodes
-	 * there does not fit the free space in LEB Y any more! And this is
-	 * because of the padding node which we added to LEB Y. The
-	 * user-visible effect of this which I once observed and analysed is
-	 * that we cannot mount the file-system with -ENOSPC error.
-	 *
-	 * So obviously, to make sure that situation does not happen we should
-	 * free min. I/O unit B in LEB Y completely and the last used min. I/O
-	 * unit in LEB Y should be A. This is basically what the below code
-	 * tries to do.
-	 */
-	while (min_io_unit == round_down(offs, c->min_io_size) &&
-	       min_io_unit != offs &&
-	       drop_last_node(sleb, &offs, grouped));
+	if (jhead == GCHD) {
+		/*
+		 * If this LEB belongs to the GC head then while we are in the
+		 * middle of the same min. I/O unit keep dropping nodes. So
+		 * basically, what we want is to make sure that the last min.
+		 * I/O unit where we saw the corruption is dropped completely
+		 * with all the uncorrupted nodes which may possibly sit there.
+		 *
+		 * In other words, let's name the min. I/O unit where the
+		 * corruption starts B, and the previous min. I/O unit A. The
+		 * below code tries to deal with a situation when half of B
+		 * contains valid nodes or the end of a valid node, and the
+		 * second half of B contains corrupted data or garbage. This
+		 * means that UBIFS had been writing to B just before the power
+		 * cut happened. I do not know how realistic is this scenario
+		 * that half of the min. I/O unit had been written successfully
+		 * and the other half not, but this is possible in our 'failure
+		 * mode emulation' infrastructure at least.
+		 *
+		 * So what is the problem, why we need to drop those nodes? Why
+		 * can't we just clean-up the second half of B by putting a
+		 * padding node there? We can, and this works fine with one
+		 * exception which was reproduced with power cut emulation
+		 * testing and happens extremely rarely.
+		 *
+		 * Imagine the file-system is full, we run GC which starts
+		 * moving valid nodes from LEB X to LEB Y (obviously, LEB Y is
+		 * the current GC head LEB). The @c->gc_lnum is -1, which means
+		 * that GC will retain LEB X and will try to continue. Imagine
+		 * that LEB X is currently the dirtiest LEB, and the amount of
+		 * used space in LEB Y is exactly the same as amount of free
+		 * space in LEB X.
+		 *
+		 * And a power cut happens when nodes are moved from LEB X to
+		 * LEB Y. We are here trying to recover LEB Y which is the GC
+		 * head LEB. We find the min. I/O unit B as described above.
+		 * Then we clean-up LEB Y by padding min. I/O unit. And later
+		 * 'ubifs_rcvry_gc_commit()' function fails, because it cannot
+		 * find a dirty LEB which could be GC'd into LEB Y! Even LEB X
+		 * does not match because the amount of valid nodes there does
+		 * not fit the free space in LEB Y any more! And this is
+		 * because of the padding node which we added to LEB Y. The
+		 * user-visible effect of this which I once observed and
+		 * analysed is that we cannot mount the file-system with
+		 * -ENOSPC error.
+		 *
+		 * So obviously, to make sure that situation does not happen we
+		 * should free min. I/O unit B in LEB Y completely and the last
+		 * used min. I/O unit in LEB Y should be A. This is basically
+		 * what the below code tries to do.
+		 */
+		while (offs > min_io_unit)
+			drop_last_node(sleb, &offs);
+	}
 
 	buf = sbuf + offs;
 	len = c->leb_size - offs;
@@ -881,7 +905,7 @@ struct ubifs_scan_leb *ubifs_recover_log_leb(struct ubifs_info *c, int lnum,
 		}
 		ubifs_scan_destroy(sleb);
 	}
-	return ubifs_recover_leb(c, lnum, offs, sbuf, 0);
+	return ubifs_recover_leb(c, lnum, offs, sbuf, -1);
 }
 
 /**
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index 6617280d1679..5e97161ce4d3 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -557,8 +557,7 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b)
 		 * these LEBs could possibly be written to at the power cut
 		 * time.
 		 */
-		sleb = ubifs_recover_leb(c, lnum, offs, c->sbuf,
-					 b->bud->jhead != GCHD);
+		sleb = ubifs_recover_leb(c, lnum, offs, c->sbuf, b->bud->jhead);
 	else
 		sleb = ubifs_scan(c, lnum, offs, c->sbuf, 0);
 	if (IS_ERR(sleb))
diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c
index 46961c003236..9e1d05666fed 100644
--- a/fs/ubifs/shrinker.c
+++ b/fs/ubifs/shrinker.c
@@ -277,13 +277,18 @@ static int kick_a_thread(void)
 	return 0;
 }
 
-int ubifs_shrinker(struct shrinker *shrink, int nr, gfp_t gfp_mask)
+int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc)
 {
+	int nr = sc->nr_to_scan;
 	int freed, contention = 0;
 	long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt);
 
 	if (nr == 0)
-		return clean_zn_cnt;
+		/*
+		 * Due to the way UBIFS updates the clean znode counter it may
+		 * temporarily be negative.
+		 */
+		return clean_zn_cnt >= 0 ? clean_zn_cnt : 1;
 
 	if (!clean_zn_cnt) {
 		/*
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 6db0bdaa9f74..529be0582029 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -382,7 +382,7 @@ done:
 	end_writeback(inode);
 }
 
-static void ubifs_dirty_inode(struct inode *inode)
+static void ubifs_dirty_inode(struct inode *inode, int flags)
 {
 	struct ubifs_inode *ui = ubifs_inode(inode);
 
@@ -811,15 +811,18 @@ static int alloc_wbufs(struct ubifs_info *c)
 
 		c->jheads[i].wbuf.sync_callback = &bud_wbuf_callback;
 		c->jheads[i].wbuf.jhead = i;
+		c->jheads[i].grouped = 1;
 	}
 
 	c->jheads[BASEHD].wbuf.dtype = UBI_SHORTTERM;
 	/*
 	 * Garbage Collector head likely contains long-term data and
-	 * does not need to be synchronized by timer.
+	 * does not need to be synchronized by timer. Also GC head nodes are
+	 * not grouped.
 	 */
 	c->jheads[GCHD].wbuf.dtype = UBI_LONGTERM;
 	c->jheads[GCHD].wbuf.no_timer = 1;
+	c->jheads[GCHD].grouped = 0;
 
 	return 0;
 }
@@ -1284,12 +1287,25 @@ static int mount_ubifs(struct ubifs_info *c)
 	if ((c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY)) != 0) {
 		ubifs_msg("recovery needed");
 		c->need_recovery = 1;
-		if (!c->ro_mount) {
-			err = ubifs_recover_inl_heads(c, c->sbuf);
-			if (err)
-				goto out_master;
-		}
-	} else if (!c->ro_mount) {
+	}
+
+	if (c->need_recovery && !c->ro_mount) {
+		err = ubifs_recover_inl_heads(c, c->sbuf);
+		if (err)
+			goto out_master;
+	}
+
+	err = ubifs_lpt_init(c, 1, !c->ro_mount);
+	if (err)
+		goto out_master;
+
+	if (!c->ro_mount && c->space_fixup) {
+		err = ubifs_fixup_free_space(c);
+		if (err)
+			goto out_master;
+	}
+
+	if (!c->ro_mount) {
 		/*
 		 * Set the "dirty" flag so that if we reboot uncleanly we
 		 * will notice this immediately on the next mount.
@@ -1297,13 +1313,9 @@ static int mount_ubifs(struct ubifs_info *c)
 		c->mst_node->flags |= cpu_to_le32(UBIFS_MST_DIRTY);
 		err = ubifs_write_master(c);
 		if (err)
-			goto out_master;
+			goto out_lpt;
 	}
 
-	err = ubifs_lpt_init(c, 1, !c->ro_mount);
-	if (err)
-		goto out_lpt;
-
 	err = dbg_check_idx_size(c, c->bi.old_idx_sz);
 	if (err)
 		goto out_lpt;
@@ -1396,12 +1408,6 @@ static int mount_ubifs(struct ubifs_info *c)
 	} else
 		ubifs_assert(c->lst.taken_empty_lebs > 0);
 
-	if (!c->ro_mount && c->space_fixup) {
-		err = ubifs_fixup_free_space(c);
-		if (err)
-			goto out_infos;
-	}
-
 	err = dbg_check_filesystem(c);
 	if (err)
 		goto out_infos;
@@ -1842,7 +1848,6 @@ static void ubifs_put_super(struct super_block *sb)
 	bdi_destroy(&c->bdi);
 	ubi_close_volume(c->ubi);
 	mutex_unlock(&c->umount_mutex);
-	kfree(c);
 }
 
 static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data)
@@ -1965,61 +1970,65 @@ static struct ubi_volume_desc *open_ubi(const char *name, int mode)
 	return ERR_PTR(-EINVAL);
 }
 
-static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
+static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi)
 {
-	struct ubi_volume_desc *ubi = sb->s_fs_info;
 	struct ubifs_info *c;
-	struct inode *root;
-	int err;
 
 	c = kzalloc(sizeof(struct ubifs_info), GFP_KERNEL);
-	if (!c)
-		return -ENOMEM;
+	if (c) {
+		spin_lock_init(&c->cnt_lock);
+		spin_lock_init(&c->cs_lock);
+		spin_lock_init(&c->buds_lock);
+		spin_lock_init(&c->space_lock);
+		spin_lock_init(&c->orphan_lock);
+		init_rwsem(&c->commit_sem);
+		mutex_init(&c->lp_mutex);
+		mutex_init(&c->tnc_mutex);
+		mutex_init(&c->log_mutex);
+		mutex_init(&c->mst_mutex);
+		mutex_init(&c->umount_mutex);
+		mutex_init(&c->bu_mutex);
+		mutex_init(&c->write_reserve_mutex);
+		init_waitqueue_head(&c->cmt_wq);
+		c->buds = RB_ROOT;
+		c->old_idx = RB_ROOT;
+		c->size_tree = RB_ROOT;
+		c->orph_tree = RB_ROOT;
+		INIT_LIST_HEAD(&c->infos_list);
+		INIT_LIST_HEAD(&c->idx_gc);
+		INIT_LIST_HEAD(&c->replay_list);
+		INIT_LIST_HEAD(&c->replay_buds);
+		INIT_LIST_HEAD(&c->uncat_list);
+		INIT_LIST_HEAD(&c->empty_list);
+		INIT_LIST_HEAD(&c->freeable_list);
+		INIT_LIST_HEAD(&c->frdi_idx_list);
+		INIT_LIST_HEAD(&c->unclean_leb_list);
+		INIT_LIST_HEAD(&c->old_buds);
+		INIT_LIST_HEAD(&c->orph_list);
+		INIT_LIST_HEAD(&c->orph_new);
+		c->no_chk_data_crc = 1;
+
+		c->highest_inum = UBIFS_FIRST_INO;
+		c->lhead_lnum = c->ltail_lnum = UBIFS_LOG_LNUM;
+
+		ubi_get_volume_info(ubi, &c->vi);
+		ubi_get_device_info(c->vi.ubi_num, &c->di);
+	}
+	return c;
+}
 
-	spin_lock_init(&c->cnt_lock);
-	spin_lock_init(&c->cs_lock);
-	spin_lock_init(&c->buds_lock);
-	spin_lock_init(&c->space_lock);
-	spin_lock_init(&c->orphan_lock);
-	init_rwsem(&c->commit_sem);
-	mutex_init(&c->lp_mutex);
-	mutex_init(&c->tnc_mutex);
-	mutex_init(&c->log_mutex);
-	mutex_init(&c->mst_mutex);
-	mutex_init(&c->umount_mutex);
-	mutex_init(&c->bu_mutex);
-	mutex_init(&c->write_reserve_mutex);
-	init_waitqueue_head(&c->cmt_wq);
-	c->buds = RB_ROOT;
-	c->old_idx = RB_ROOT;
-	c->size_tree = RB_ROOT;
-	c->orph_tree = RB_ROOT;
-	INIT_LIST_HEAD(&c->infos_list);
-	INIT_LIST_HEAD(&c->idx_gc);
-	INIT_LIST_HEAD(&c->replay_list);
-	INIT_LIST_HEAD(&c->replay_buds);
-	INIT_LIST_HEAD(&c->uncat_list);
-	INIT_LIST_HEAD(&c->empty_list);
-	INIT_LIST_HEAD(&c->freeable_list);
-	INIT_LIST_HEAD(&c->frdi_idx_list);
-	INIT_LIST_HEAD(&c->unclean_leb_list);
-	INIT_LIST_HEAD(&c->old_buds);
-	INIT_LIST_HEAD(&c->orph_list);
-	INIT_LIST_HEAD(&c->orph_new);
-	c->no_chk_data_crc = 1;
+static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct ubifs_info *c = sb->s_fs_info;
+	struct inode *root;
+	int err;
 
 	c->vfs_sb = sb;
-	c->highest_inum = UBIFS_FIRST_INO;
-	c->lhead_lnum = c->ltail_lnum = UBIFS_LOG_LNUM;
-
-	ubi_get_volume_info(ubi, &c->vi);
-	ubi_get_device_info(c->vi.ubi_num, &c->di);
-
 	/* Re-open the UBI device in read-write mode */
 	c->ubi = ubi_open_volume(c->vi.ubi_num, c->vi.vol_id, UBI_READWRITE);
 	if (IS_ERR(c->ubi)) {
 		err = PTR_ERR(c->ubi);
-		goto out_free;
+		goto out;
 	}
 
 	/*
@@ -2085,24 +2094,29 @@ out_bdi:
 	bdi_destroy(&c->bdi);
 out_close:
 	ubi_close_volume(c->ubi);
-out_free:
-	kfree(c);
+out:
 	return err;
 }
 
 static int sb_test(struct super_block *sb, void *data)
 {
-	dev_t *dev = data;
+	struct ubifs_info *c1 = data;
 	struct ubifs_info *c = sb->s_fs_info;
 
-	return c->vi.cdev == *dev;
+	return c->vi.cdev == c1->vi.cdev;
+}
+
+static int sb_set(struct super_block *sb, void *data)
+{
+	sb->s_fs_info = data;
+	return set_anon_super(sb, NULL);
 }
 
 static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
 			const char *name, void *data)
 {
 	struct ubi_volume_desc *ubi;
-	struct ubi_volume_info vi;
+	struct ubifs_info *c;
 	struct super_block *sb;
 	int err;
 
@@ -2119,19 +2133,25 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
 			name, (int)PTR_ERR(ubi));
 		return ERR_CAST(ubi);
 	}
-	ubi_get_volume_info(ubi, &vi);
 
-	dbg_gen("opened ubi%d_%d", vi.ubi_num, vi.vol_id);
+	c = alloc_ubifs_info(ubi);
+	if (!c) {
+		err = -ENOMEM;
+		goto out_close;
+	}
+
+	dbg_gen("opened ubi%d_%d", c->vi.ubi_num, c->vi.vol_id);
 
-	sb = sget(fs_type, &sb_test, &set_anon_super, &vi.cdev);
+	sb = sget(fs_type, sb_test, sb_set, c);
 	if (IS_ERR(sb)) {
 		err = PTR_ERR(sb);
+		kfree(c);
 		goto out_close;
 	}
 
 	if (sb->s_root) {
 		struct ubifs_info *c1 = sb->s_fs_info;
-
+		kfree(c);
 		/* A new mount point for already mounted UBIFS */
 		dbg_gen("this ubi volume is already mounted");
 		if (!!(flags & MS_RDONLY) != c1->ro_mount) {
@@ -2140,11 +2160,6 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
 		}
 	} else {
 		sb->s_flags = flags;
-		/*
-		 * Pass 'ubi' to 'fill_super()' in sb->s_fs_info where it is
-		 * replaced by 'c'.
-		 */
-		sb->s_fs_info = ubi;
 		err = ubifs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
 		if (err)
 			goto out_deact;
@@ -2164,11 +2179,18 @@ out_close:
 	return ERR_PTR(err);
 }
 
+static void kill_ubifs_super(struct super_block *s)
+{
+	struct ubifs_info *c = s->s_fs_info;
+	kill_anon_super(s);
+	kfree(c);
+}
+
 static struct file_system_type ubifs_fs_type = {
 	.name    = "ubifs",
 	.owner   = THIS_MODULE,
 	.mount   = ubifs_mount,
-	.kill_sb = kill_anon_super,
+	.kill_sb = kill_ubifs_super,
 };
 
 /*
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 8119b1fd8d94..91b4213dde84 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -2876,12 +2876,13 @@ static void tnc_destroy_cnext(struct ubifs_info *c)
  */
 void ubifs_tnc_close(struct ubifs_info *c)
 {
-	long clean_freed;
-
 	tnc_destroy_cnext(c);
 	if (c->zroot.znode) {
-		clean_freed = ubifs_destroy_tnc_subtree(c->zroot.znode);
-		atomic_long_sub(clean_freed, &ubifs_clean_zn_cnt);
+		long n;
+
+		ubifs_destroy_tnc_subtree(c->zroot.znode);
+		n = atomic_long_read(&c->clean_zn_cnt);
+		atomic_long_sub(n, &ubifs_clean_zn_cnt);
 	}
 	kfree(c->gap_lebs);
 	kfree(c->ilebs);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 93d1412a06f0..f79983d6f860 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -722,12 +722,14 @@ struct ubifs_bud {
  * struct ubifs_jhead - journal head.
  * @wbuf: head's write-buffer
  * @buds_list: list of bud LEBs belonging to this journal head
+ * @grouped: non-zero if UBIFS groups nodes when writing to this journal head
  *
  * Note, the @buds list is protected by the @c->buds_lock.
  */
 struct ubifs_jhead {
 	struct ubifs_wbuf wbuf;
 	struct list_head buds_list;
+	unsigned int grouped:1;
 };
 
 /**
@@ -1614,7 +1616,7 @@ int ubifs_tnc_start_commit(struct ubifs_info *c, struct ubifs_zbranch *zroot);
 int ubifs_tnc_end_commit(struct ubifs_info *c);
 
 /* shrinker.c */
-int ubifs_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask);
+int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc);
 
 /* commit.c */
 int ubifs_bg_thread(void *info);
@@ -1742,7 +1744,7 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum);
 int ubifs_recover_master_node(struct ubifs_info *c);
 int ubifs_write_rcvrd_mst_node(struct ubifs_info *c);
 struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
-					 int offs, void *sbuf, int grouped);
+					 int offs, void *sbuf, int jhead);
 struct ubifs_scan_leb *ubifs_recover_log_leb(struct ubifs_info *c, int lnum,
 					     int offs, void *sbuf);
 int ubifs_recover_inl_heads(const struct ubifs_info *c, void *sbuf);
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 4d76594c2a8f..f1dce848ef96 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -783,8 +783,6 @@ static int udf_rmdir(struct inode *dir, struct dentry *dentry)
 	struct fileIdentDesc *fi, cfi;
 	struct kernel_lb_addr tloc;
 
-	dentry_unhash(dentry);
-
 	retval = -ENOENT;
 	fi = udf_find_entry(dir, &dentry->d_name, &fibh, &cfi);
 	if (!fi)
@@ -1083,9 +1081,6 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct kernel_lb_addr tloc;
 	struct udf_inode_info *old_iinfo = UDF_I(old_inode);
 
-	if (new_inode && S_ISDIR(new_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	ofi = udf_find_entry(old_dir, &old_dentry->d_name, &ofibh, &ocfi);
 	if (ofi) {
 		if (ofibh.sbh != ofibh.ebh)
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 953ebdfc5bf7..29309e25417f 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -258,8 +258,6 @@ static int ufs_rmdir (struct inode * dir, struct dentry *dentry)
 	struct inode * inode = dentry->d_inode;
 	int err= -ENOTEMPTY;
 
-	dentry_unhash(dentry);
-
 	lock_ufs(dir->i_sb);
 	if (ufs_empty_dir (inode)) {
 		err = ufs_unlink(dir, dentry);
@@ -284,9 +282,6 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct ufs_dir_entry *old_de;
 	int err = -ENOENT;
 
-	if (new_inode && S_ISDIR(new_inode->i_mode))
-		dentry_unhash(new_dentry);
-
 	old_de = ufs_find_entry(old_dir, &old_dentry->d_name, &old_page);
 	if (!old_de)
 		goto out;
diff --git a/fs/xattr.c b/fs/xattr.c
index f1ef94974dea..f060663ab70c 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -46,18 +46,22 @@ xattr_permission(struct inode *inode, const char *name, int mask)
 		return 0;
 
 	/*
-	 * The trusted.* namespace can only be accessed by a privileged user.
+	 * The trusted.* namespace can only be accessed by privileged users.
 	 */
-	if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN))
-		return (capable(CAP_SYS_ADMIN) ? 0 : -EPERM);
+	if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) {
+		if (!capable(CAP_SYS_ADMIN))
+			return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
+		return 0;
+	}
 
-	/* In user.* namespace, only regular files and directories can have
+	/*
+	 * In the user.* namespace, only regular files and directories can have
 	 * extended attributes. For sticky directories, only the owner and
-	 * privileged user can write attributes.
+	 * privileged users can write attributes.
 	 */
 	if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) {
 		if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
-			return -EPERM;
+			return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
 		if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) &&
 		    (mask & MAY_WRITE) && !inode_owner_or_capable(inode))
 			return -EPERM;
@@ -87,7 +91,11 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
 {
 	struct inode *inode = dentry->d_inode;
 	int error = -EOPNOTSUPP;
+	int issec = !strncmp(name, XATTR_SECURITY_PREFIX,
+				   XATTR_SECURITY_PREFIX_LEN);
 
+	if (issec)
+		inode->i_flags &= ~S_NOSEC;
 	if (inode->i_op->setxattr) {
 		error = inode->i_op->setxattr(dentry, name, value, size, flags);
 		if (!error) {
@@ -95,8 +103,7 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
 			security_inode_post_setxattr(dentry, name, value,
 						     size, flags);
 		}
-	} else if (!strncmp(name, XATTR_SECURITY_PREFIX,
-				XATTR_SECURITY_PREFIX_LEN)) {
+	} else if (issec) {
 		const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
 		error = security_inode_setsecurity(inode, suffix, value,
 						   size, flags);
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index f4213ba1ff85..7f782af286bf 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -131,19 +131,34 @@ xfs_file_fsync(
 {
 	struct inode		*inode = file->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	int			error = 0;
 	int			log_flushed = 0;
 
 	trace_xfs_file_fsync(ip);
 
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+	if (XFS_FORCED_SHUTDOWN(mp))
 		return -XFS_ERROR(EIO);
 
 	xfs_iflags_clear(ip, XFS_ITRUNCATED);
 
 	xfs_ioend_wait(ip);
 
+	if (mp->m_flags & XFS_MOUNT_BARRIER) {
+		/*
+		 * If we have an RT and/or log subvolume we need to make sure
+		 * to flush the write cache the device used for file data
+		 * first.  This is to ensure newly written file data make
+		 * it to disk before logging the new inode size in case of
+		 * an extending write.
+		 */
+		if (XFS_IS_REALTIME_INODE(ip))
+			xfs_blkdev_issue_flush(mp->m_rtdev_targp);
+		else if (mp->m_logdev_targp != mp->m_ddev_targp)
+			xfs_blkdev_issue_flush(mp->m_ddev_targp);
+	}
+
 	/*
 	 * We always need to make sure that the required inode state is safe on
 	 * disk.  The inode might be clean but we still might need to force the
@@ -175,9 +190,9 @@ xfs_file_fsync(
 		 * updates.  The sync transaction will also force the log.
 		 */
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
-		tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_FSYNC_TS);
+		tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
 		error = xfs_trans_reserve(tp, 0,
-				XFS_FSYNC_TS_LOG_RES(ip->i_mount), 0, 0, 0);
+				XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
 		if (error) {
 			xfs_trans_cancel(tp, 0);
 			return -error;
@@ -209,28 +224,25 @@ xfs_file_fsync(
 		 * force the log.
 		 */
 		if (xfs_ipincount(ip)) {
-			error = _xfs_log_force_lsn(ip->i_mount,
+			error = _xfs_log_force_lsn(mp,
 					ip->i_itemp->ili_last_lsn,
 					XFS_LOG_SYNC, &log_flushed);
 		}
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 	}
 
-	if (ip->i_mount->m_flags & XFS_MOUNT_BARRIER) {
-		/*
-		 * If the log write didn't issue an ordered tag we need
-		 * to flush the disk cache for the data device now.
-		 */
-		if (!log_flushed)
-			xfs_blkdev_issue_flush(ip->i_mount->m_ddev_targp);
-
-		/*
-		 * If this inode is on the RT dev we need to flush that
-		 * cache as well.
-		 */
-		if (XFS_IS_REALTIME_INODE(ip))
-			xfs_blkdev_issue_flush(ip->i_mount->m_rtdev_targp);
-	}
+	/*
+	 * If we only have a single device, and the log force about was
+	 * a no-op we might have to flush the data device cache here.
+	 * This can only happen for fdatasync/O_DSYNC if we were overwriting
+	 * an already allocated file and thus do not have any metadata to
+	 * commit.
+	 */
+	if ((mp->m_flags & XFS_MOUNT_BARRIER) &&
+	    mp->m_logdev_targp == mp->m_ddev_targp &&
+	    !XFS_IS_REALTIME_INODE(ip) &&
+	    !log_flushed)
+		xfs_blkdev_issue_flush(mp->m_ddev_targp);
 
 	return -error;
 }
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index dd21784525a8..d44d92cd12b1 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -182,7 +182,7 @@ xfs_vn_mknod(
 	if (IS_POSIXACL(dir)) {
 		default_acl = xfs_get_acl(dir, ACL_TYPE_DEFAULT);
 		if (IS_ERR(default_acl))
-			return -PTR_ERR(default_acl);
+			return PTR_ERR(default_acl);
 
 		if (!default_acl)
 			mode &= ~current_umask();
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 98b9c91fcdf1..a1a881e68a9a 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -627,68 +627,6 @@ xfs_blkdev_put(
 		blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 }
 
-/*
- * Try to write out the superblock using barriers.
- */
-STATIC int
-xfs_barrier_test(
-	xfs_mount_t	*mp)
-{
-	xfs_buf_t	*sbp = xfs_getsb(mp, 0);
-	int		error;
-
-	XFS_BUF_UNDONE(sbp);
-	XFS_BUF_UNREAD(sbp);
-	XFS_BUF_UNDELAYWRITE(sbp);
-	XFS_BUF_WRITE(sbp);
-	XFS_BUF_UNASYNC(sbp);
-	XFS_BUF_ORDERED(sbp);
-
-	xfsbdstrat(mp, sbp);
-	error = xfs_buf_iowait(sbp);
-
-	/*
-	 * Clear all the flags we set and possible error state in the
-	 * buffer.  We only did the write to try out whether barriers
-	 * worked and shouldn't leave any traces in the superblock
-	 * buffer.
-	 */
-	XFS_BUF_DONE(sbp);
-	XFS_BUF_ERROR(sbp, 0);
-	XFS_BUF_UNORDERED(sbp);
-
-	xfs_buf_relse(sbp);
-	return error;
-}
-
-STATIC void
-xfs_mountfs_check_barriers(xfs_mount_t *mp)
-{
-	int error;
-
-	if (mp->m_logdev_targp != mp->m_ddev_targp) {
-		xfs_notice(mp,
-		  "Disabling barriers, not supported with external log device");
-		mp->m_flags &= ~XFS_MOUNT_BARRIER;
-		return;
-	}
-
-	if (xfs_readonly_buftarg(mp->m_ddev_targp)) {
-		xfs_notice(mp,
-			"Disabling barriers, underlying device is readonly");
-		mp->m_flags &= ~XFS_MOUNT_BARRIER;
-		return;
-	}
-
-	error = xfs_barrier_test(mp);
-	if (error) {
-		xfs_notice(mp,
-			"Disabling barriers, trial barrier write failed");
-		mp->m_flags &= ~XFS_MOUNT_BARRIER;
-		return;
-	}
-}
-
 void
 xfs_blkdev_issue_flush(
 	xfs_buftarg_t		*buftarg)
@@ -925,7 +863,8 @@ xfs_fs_inode_init_once(
  */
 STATIC void
 xfs_fs_dirty_inode(
-	struct inode	*inode)
+	struct inode	*inode,
+	int		flags)
 {
 	barrier();
 	XFS_I(inode)->i_update_core = 1;
@@ -1239,14 +1178,6 @@ xfs_fs_remount(
 		switch (token) {
 		case Opt_barrier:
 			mp->m_flags |= XFS_MOUNT_BARRIER;
-
-			/*
-			 * Test if barriers are actually working if we can,
-			 * else delay this check until the filesystem is
-			 * marked writeable.
-			 */
-			if (!(mp->m_flags & XFS_MOUNT_RDONLY))
-				xfs_mountfs_check_barriers(mp);
 			break;
 		case Opt_nobarrier:
 			mp->m_flags &= ~XFS_MOUNT_BARRIER;
@@ -1281,8 +1212,6 @@ xfs_fs_remount(
 	/* ro -> rw */
 	if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & MS_RDONLY)) {
 		mp->m_flags &= ~XFS_MOUNT_RDONLY;
-		if (mp->m_flags & XFS_MOUNT_BARRIER)
-			xfs_mountfs_check_barriers(mp);
 
 		/*
 		 * If this is the first remount to writeable state we
@@ -1464,9 +1393,6 @@ xfs_fs_fill_super(
 	if (error)
 		goto out_free_sb;
 
-	if (mp->m_flags & XFS_MOUNT_BARRIER)
-		xfs_mountfs_check_barriers(mp);
-
 	error = xfs_filestream_mount(mp);
 	if (error)
 		goto out_free_sb;
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index c86375378810..01d2072fb6d4 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -490,6 +490,13 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
 	args.whichfork = XFS_ATTR_FORK;
 
 	/*
+	 * we have no control over the attribute names that userspace passes us
+	 * to remove, so we have to allow the name lookup prior to attribute
+	 * removal to fail.
+	 */
+	args.op_flags = XFS_DA_OP_OKNOENT;
+
+	/*
 	 * Attach the dquots to the inode.
 	 */
 	error = xfs_qm_dqattach(dp, 0);
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index cb9b6d1469f7..3631783b2b53 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -253,16 +253,21 @@ xfs_iget_cache_hit(
 			rcu_read_lock();
 			spin_lock(&ip->i_flags_lock);
 
-			ip->i_flags &= ~XFS_INEW;
-			ip->i_flags |= XFS_IRECLAIMABLE;
-			__xfs_inode_set_reclaim_tag(pag, ip);
+			ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM);
+			ASSERT(ip->i_flags & XFS_IRECLAIMABLE);
 			trace_xfs_iget_reclaim_fail(ip);
 			goto out_error;
 		}
 
 		spin_lock(&pag->pag_ici_lock);
 		spin_lock(&ip->i_flags_lock);
-		ip->i_flags &= ~(XFS_IRECLAIMABLE | XFS_IRECLAIM);
+
+		/*
+		 * Clear the per-lifetime state in the inode as we are now
+		 * effectively a new inode and need to return to the initial
+		 * state before reuse occurs.
+		 */
+		ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS;
 		ip->i_flags |= XFS_INEW;
 		__xfs_inode_clear_reclaim_tag(mp, pag, ip);
 		inode->i_state = I_NEW;
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 3ae6d58e5473..964cfea77686 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -384,6 +384,16 @@ static inline void xfs_ifunlock(xfs_inode_t *ip)
 #define XFS_IDIRTY_RELEASE	0x0040	/* dirty release already seen */
 
 /*
+ * Per-lifetime flags need to be reset when re-using a reclaimable inode during
+ * inode lookup. Thi prevents unintended behaviour on the new inode from
+ * ocurring.
+ */
+#define XFS_IRECLAIM_RESET_FLAGS	\
+	(XFS_IRECLAIMABLE | XFS_IRECLAIM | \
+	 XFS_IDIRTY_RELEASE | XFS_ITRUNCATED | \
+	 XFS_IFILESTREAM);
+
+/*
  * Flags for inode locking.
  * Bit ranges:	1<<1  - 1<<16-1 -- iolock/ilock modes (bitfield)
  *		1<<16 - 1<<32-1 -- lockdep annotation (integers)
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 211930246f20..41d5b8f2bf92 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1372,8 +1372,17 @@ xlog_sync(xlog_t		*log,
 	XFS_BUF_ASYNC(bp);
 	bp->b_flags |= XBF_LOG_BUFFER;
 
-	if (log->l_mp->m_flags & XFS_MOUNT_BARRIER)
+	if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) {
+		/*
+		 * If we have an external log device, flush the data device
+		 * before flushing the log to make sure all meta data
+		 * written back from the AIL actually made it to disk
+		 * before writing out the new log tail LSN in the log buffer.
+		 */
+		if (log->l_mp->m_logdev_targp != log->l_mp->m_ddev_targp)
+			xfs_blkdev_issue_flush(log->l_mp->m_ddev_targp);
 		XFS_BUF_ORDERED(bp);
+	}
 
 	ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1);
 	ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize);
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index b7a5fe7c52c8..619720705bc6 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -960,8 +960,11 @@ xfs_release(
 		 * be exposed to that problem.
 		 */
 		truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED);
-		if (truncated && VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0)
-			xfs_flush_pages(ip, 0, -1, XBF_ASYNC, FI_NONE);
+		if (truncated) {
+			xfs_iflags_clear(ip, XFS_IDIRTY_RELEASE);
+			if (VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0)
+				xfs_flush_pages(ip, 0, -1, XBF_ASYNC, FI_NONE);
+		}
 	}
 
 	if (ip->i_d.di_nlink == 0)
diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index a3252a5ead66..a756bc8d866d 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -98,6 +98,9 @@ acpi_os_table_override(struct acpi_table_header *existing_table,
 /*
  * Spinlock primitives
  */
+acpi_status
+acpi_os_create_lock(acpi_spinlock *out_handle);
+
 void acpi_os_delete_lock(acpi_spinlock handle);
 
 acpi_cpu_flags acpi_os_acquire_lock(acpi_spinlock handle);
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index f6ad63d25b73..2ed0a8486c19 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -47,7 +47,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20110316
+#define ACPI_CA_VERSION                 0x20110413
 
 #include "actypes.h"
 #include "actbl.h"
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 64f838beaabf..b67231bef632 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -501,8 +501,9 @@ typedef u64 acpi_integer;
 #define ACPI_STATE_D1                   (u8) 1
 #define ACPI_STATE_D2                   (u8) 2
 #define ACPI_STATE_D3                   (u8) 3
-#define ACPI_D_STATES_MAX               ACPI_STATE_D3
-#define ACPI_D_STATE_COUNT              4
+#define ACPI_STATE_D3_COLD              (u8) 4
+#define ACPI_D_STATES_MAX               ACPI_STATE_D3_COLD
+#define ACPI_D_STATE_COUNT              5
 
 #define ACPI_STATE_C0                   (u8) 0
 #define ACPI_STATE_C1                   (u8) 1
@@ -712,8 +713,24 @@ typedef u8 acpi_adr_space_type;
 #define ACPI_ADR_SPACE_CMOS             (acpi_adr_space_type) 5
 #define ACPI_ADR_SPACE_PCI_BAR_TARGET   (acpi_adr_space_type) 6
 #define ACPI_ADR_SPACE_IPMI             (acpi_adr_space_type) 7
-#define ACPI_ADR_SPACE_DATA_TABLE       (acpi_adr_space_type) 8
-#define ACPI_ADR_SPACE_FIXED_HARDWARE   (acpi_adr_space_type) 127
+
+#define ACPI_NUM_PREDEFINED_REGIONS     8
+
+/*
+ * Special Address Spaces
+ *
+ * Note: A Data Table region is a special type of operation region
+ * that has its own AML opcode. However, internally, the AML
+ * interpreter simply creates an operation region with an an address
+ * space type of ACPI_ADR_SPACE_DATA_TABLE.
+ */
+#define ACPI_ADR_SPACE_DATA_TABLE       (acpi_adr_space_type) 0x7E	/* Internal to ACPICA only */
+#define ACPI_ADR_SPACE_FIXED_HARDWARE   (acpi_adr_space_type) 0x7F
+
+/* Values for _REG connection code */
+
+#define ACPI_REG_DISCONNECT             0
+#define ACPI_REG_CONNECT                1
 
 /*
  * bit_register IDs
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 55192ac0cede..ba4928cae473 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -310,14 +310,7 @@ static inline int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
 
 /* in processor_core.c */
 void acpi_processor_set_pdc(acpi_handle handle);
-#ifdef CONFIG_SMP
 int acpi_get_cpuid(acpi_handle, int type, u32 acpi_id);
-#else
-static inline int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
-{
-	return -1;
-}
-#endif
 
 /* in processor_throttling.c */
 int acpi_processor_tstate_has_changed(struct acpi_processor *pr);
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 91784841e407..dfb0ec666c94 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -162,46 +162,6 @@ extern void warn_slowpath_null(const char *file, const int line);
 	unlikely(__ret_warn_once);				\
 })
 
-#ifdef CONFIG_PRINTK
-
-#define WARN_ON_RATELIMIT(condition, state)			\
-		WARN_ON((condition) && __ratelimit(state))
-
-#define __WARN_RATELIMIT(condition, state, format...)		\
-({								\
-	int rtn = 0;						\
-	if (unlikely(__ratelimit(state)))			\
-		rtn = WARN(condition, format);			\
-	rtn;							\
-})
-
-#define WARN_RATELIMIT(condition, format...)			\
-({								\
-	static DEFINE_RATELIMIT_STATE(_rs,			\
-				      DEFAULT_RATELIMIT_INTERVAL,	\
-				      DEFAULT_RATELIMIT_BURST);	\
-	__WARN_RATELIMIT(condition, &_rs, format);		\
-})
-
-#else
-
-#define WARN_ON_RATELIMIT(condition, state)			\
-	WARN_ON(condition)
-
-#define __WARN_RATELIMIT(condition, state, format...)		\
-({								\
-	int rtn = WARN(condition, format);			\
-	rtn;							\
-})
-
-#define WARN_RATELIMIT(condition, format...)			\
-({								\
-	int rtn = WARN(condition, format);			\
-	rtn;							\
-})
-
-#endif
-
 /*
  * WARN_ON_SMP() is for cases that the warning is either
  * meaningless for !SMP or may even cause failures.
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index ff5c66080c8c..d494001b1226 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -35,9 +35,9 @@
  * platform data and other tables.
  */
 
-static inline int gpio_is_valid(int number)
+static inline bool gpio_is_valid(int number)
 {
-	return ((unsigned)number) < ARCH_NR_GPIOS;
+	return number >= 0 && number < ARCH_NR_GPIOS;
 }
 
 struct device;
@@ -170,16 +170,6 @@ extern int __gpio_cansleep(unsigned gpio);
 
 extern int __gpio_to_irq(unsigned gpio);
 
-#define GPIOF_DIR_OUT	(0 << 0)
-#define GPIOF_DIR_IN	(1 << 0)
-
-#define GPIOF_INIT_LOW	(0 << 1)
-#define GPIOF_INIT_HIGH	(1 << 1)
-
-#define GPIOF_IN		(GPIOF_DIR_IN)
-#define GPIOF_OUT_INIT_LOW	(GPIOF_DIR_OUT | GPIOF_INIT_LOW)
-#define GPIOF_OUT_INIT_HIGH	(GPIOF_DIR_OUT | GPIOF_INIT_HIGH)
-
 /**
  * struct gpio - a structure describing a GPIO with configuration
  * @gpio:	the GPIO number
@@ -193,8 +183,8 @@ struct gpio {
 };
 
 extern int gpio_request_one(unsigned gpio, unsigned long flags, const char *label);
-extern int gpio_request_array(struct gpio *array, size_t num);
-extern void gpio_free_array(struct gpio *array, size_t num);
+extern int gpio_request_array(const struct gpio *array, size_t num);
+extern void gpio_free_array(const struct gpio *array, size_t num);
 
 #ifdef CONFIG_GPIO_SYSFS
 
@@ -212,7 +202,7 @@ extern void gpio_unexport(unsigned gpio);
 
 #else	/* !CONFIG_GPIOLIB */
 
-static inline int gpio_is_valid(int number)
+static inline bool gpio_is_valid(int number)
 {
 	/* only non-negative numbers are valid */
 	return number >= 0;
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index e9b8e5926bef..76bff2bff15e 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -88,7 +88,7 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
 	pmd_t pmd = *pmdp;
 	pmd_clear(mm, address, pmdp);
 	return pmd;
-})
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index 33d524704883..4f76959397fa 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -681,9 +681,13 @@ __SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \
 __SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
 #define __NR_syncfs 267
 __SYSCALL(__NR_syncfs, sys_syncfs)
+#define __NR_setns 268
+__SYSCALL(__NR_setns, sys_setns)
+#define __NR_sendmmsg 269
+__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
 
 #undef __NR_syscalls
-#define __NR_syscalls 268
+#define __NR_syscalls 270
 
 /*
  * All syscalls below here should go away really,
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 9573e0ce3120..33d12f87f0e0 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -520,6 +520,8 @@ struct drm_connector {
 	uint32_t encoder_ids[DRM_CONNECTOR_MAX_ENCODER];
 	uint32_t force_encoder_id;
 	struct drm_encoder *encoder; /* currently active encoder */
+
+	int null_edid_counter; /* needed to workaround some HW bugs where we get all 0s */
 };
 
 /**
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index f04b2a3b0f49..e08f344c6cff 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -467,6 +467,17 @@
 	{0x1002, 0x9614, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9615, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9616, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9640, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9641, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9642, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9643, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9644, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9645, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+	{0x1002, 0x9648, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+	{0x1002, 0x964a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x964e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+	{0x1002, 0x964f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
 	{0x1002, 0x9710, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9711, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9712, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index a2e910e01293..1deb2a73c2da 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -150,8 +150,7 @@ extern int ec_read(u8 addr, u8 *val);
 extern int ec_write(u8 addr, u8 val);
 extern int ec_transaction(u8 command,
                           const u8 *wdata, unsigned wdata_len,
-                          u8 *rdata, unsigned rdata_len,
-			  int force_poll);
+                          u8 *rdata, unsigned rdata_len);
 
 #if defined(CONFIG_ACPI_WMI) || defined(CONFIG_ACPI_WMI_MODULE)
 
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 96c038e43d66..ee456c79b0e6 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -34,4 +34,17 @@ static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint)
 }
 #endif
 
+#ifndef CONFIG_ARCH_HAS_ATOMIC_OR
+static inline void atomic_or(int i, atomic_t *v)
+{
+	int old;
+	int new;
+
+	do {
+		old = atomic_read(v);
+		new = old | i;
+	} while (atomic_cmpxchg(v, old, new) != old);
+}
+#endif /* #ifndef CONFIG_ARCH_HAS_ATOMIC_OR */
+
 #endif /* _LINUX_ATOMIC_H */
diff --git a/include/linux/basic_mmio_gpio.h b/include/linux/basic_mmio_gpio.h
index 1ae12710d732..98999cf107ce 100644
--- a/include/linux/basic_mmio_gpio.h
+++ b/include/linux/basic_mmio_gpio.h
@@ -16,6 +16,7 @@
 #include <linux/gpio.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
+#include <linux/spinlock_types.h>
 
 struct bgpio_pdata {
 	int base;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 2a7cea53ca0d..6395692b2e7a 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -167,7 +167,7 @@ enum rq_flag_bits {
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
 	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_DISCARD | \
-	 REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
+	 REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE)
 #define REQ_CLONE_MASK		REQ_COMMON_MASK
 
 #define REQ_RAHEAD		(1 << __REQ_RAHEAD)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ae9091a68480..1a23722e8878 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1282,8 +1282,8 @@ queue_max_integrity_segments(struct request_queue *q)
 #define blk_get_integrity(a)			(0)
 #define blk_integrity_compare(a, b)		(0)
 #define blk_integrity_register(a, b)		(0)
-#define blk_integrity_unregister(a)		do { } while (0);
-#define blk_queue_max_integrity_segments(a, b)	do { } while (0);
+#define blk_integrity_unregister(a)		do { } while (0)
+#define blk_queue_max_integrity_segments(a, b)	do { } while (0)
 #define queue_max_integrity_segments(a)		(0)
 #define blk_integrity_merge_rq(a, b, c)		(0)
 #define blk_integrity_merge_bio(a, b, c)	(0)
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index b22fb0d3db0f..8c7c2de7631a 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -169,7 +169,8 @@ extern void blk_trace_shutdown(struct request_queue *);
 extern int do_blk_trace_setup(struct request_queue *q, char *name,
 			      dev_t dev, struct block_device *bdev,
 			      struct blk_user_trace_setup *buts);
-extern void __trace_note_message(struct blk_trace *, const char *fmt, ...);
+extern __attribute__((format(printf, 2, 3)))
+void __trace_note_message(struct blk_trace *, const char *fmt, ...);
 
 /**
  * blk_add_trace_msg - Add a (simple) message to the blktrace stream
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index d4646b48dc4a..18a1baf31f2d 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -188,6 +188,7 @@ struct clocksource {
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 	/* Watchdog related data, used by the framework */
 	struct list_head wd_list;
+	cycle_t cs_last;
 	cycle_t wd_last;
 #endif
 } ____cacheline_aligned;
diff --git a/include/linux/compat.h b/include/linux/compat.h
index ddcb7db38e67..846bb1792572 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -467,6 +467,8 @@ asmlinkage long compat_sys_setsockopt(int fd, int level, int optname,
 				      char __user *optval, unsigned int optlen);
 asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg,
 				   unsigned flags);
+asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg,
+				    unsigned vlen, unsigned int flags);
 asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg,
 				   unsigned int flags);
 asmlinkage long compat_sys_recv(int fd, void __user *buf, size_t len,
diff --git a/include/linux/cred.h b/include/linux/cred.h
index be16b61283cc..82607992f308 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -1,4 +1,4 @@
-/* Credentials management - see Documentation/credentials.txt
+/* Credentials management - see Documentation/security/credentials.txt
  *
  * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 32a4423710f5..4427e0454051 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -191,6 +191,12 @@ struct dm_target {
 
 	/* Used to provide an error string from the ctr */
 	char *error;
+
+	/*
+	 * Set if this target needs to receive discards regardless of
+	 * whether or not its underlying devices have support.
+	 */
+	unsigned discards_supported:1;
 };
 
 /* Each target can link one of these into the table */
diff --git a/include/linux/device.h b/include/linux/device.h
index c66111affca9..e4f62d8896b7 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -530,7 +530,6 @@ struct device_dma_parameters {
  * @dma_mem:	Internal for coherent mem override.
  * @archdata:	For arch-specific additions.
  * @of_node:	Associated device tree node.
- * @of_match:	Matching of_device_id from driver.
  * @devt:	For creating the sysfs "dev".
  * @devres_lock: Spinlock to protect the resource of the device.
  * @devres_head: The resources list of the device.
@@ -654,13 +653,13 @@ static inline int device_is_registered(struct device *dev)
 
 static inline void device_enable_async_suspend(struct device *dev)
 {
-	if (!dev->power.in_suspend)
+	if (!dev->power.is_prepared)
 		dev->power.async_suspend = true;
 }
 
 static inline void device_disable_async_suspend(struct device *dev)
 {
-	if (!dev->power.in_suspend)
+	if (!dev->power.is_prepared)
 		dev->power.async_suspend = false;
 }
 
diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h
index 0b0d9c39ed67..7aad1f440867 100644
--- a/include/linux/device_cgroup.h
+++ b/include/linux/device_cgroup.h
@@ -2,8 +2,16 @@
 #include <linux/fs.h>
 
 #ifdef CONFIG_CGROUP_DEVICE
-extern int devcgroup_inode_permission(struct inode *inode, int mask);
+extern int __devcgroup_inode_permission(struct inode *inode, int mask);
 extern int devcgroup_inode_mknod(int mode, dev_t dev);
+static inline int devcgroup_inode_permission(struct inode *inode, int mask)
+{
+	if (likely(!inode->i_rdev))
+		return 0;
+	if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode))
+		return 0;
+	return __devcgroup_inode_permission(inode, mask);
+}
 #else
 static inline int devcgroup_inode_permission(struct inode *inode, int mask)
 { return 0; }
diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h
index 5c9186b93fff..f4b0aa3126f5 100644
--- a/include/linux/dm-io.h
+++ b/include/linux/dm-io.h
@@ -69,8 +69,7 @@ struct dm_io_request {
  *
  * Create/destroy may block.
  */
-struct dm_io_client *dm_io_client_create(unsigned num_pages);
-int dm_io_client_resize(unsigned num_pages, struct dm_io_client *client);
+struct dm_io_client *dm_io_client_create(void);
 void dm_io_client_destroy(struct dm_io_client *client);
 
 /*
diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h
index 5db216311695..298d587e349b 100644
--- a/include/linux/dm-kcopyd.h
+++ b/include/linux/dm-kcopyd.h
@@ -25,8 +25,7 @@
  * To use kcopyd you must first create a dm_kcopyd_client object.
  */
 struct dm_kcopyd_client;
-int dm_kcopyd_client_create(unsigned num_pages,
-			    struct dm_kcopyd_client **result);
+struct dm_kcopyd_client *dm_kcopyd_client_create(void);
 void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc);
 
 /*
diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h
index 5619f8522738..bbd8661b3473 100644
--- a/include/linux/dma_remapping.h
+++ b/include/linux/dma_remapping.h
@@ -9,8 +9,12 @@
 #define VTD_PAGE_MASK		(((u64)-1) << VTD_PAGE_SHIFT)
 #define VTD_PAGE_ALIGN(addr)	(((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK)
 
+#define VTD_STRIDE_SHIFT        (9)
+#define VTD_STRIDE_MASK         (((u64)-1) << VTD_STRIDE_SHIFT)
+
 #define DMA_PTE_READ (1)
 #define DMA_PTE_WRITE (2)
+#define DMA_PTE_LARGE_PAGE (1 << 7)
 #define DMA_PTE_SNP (1 << 11)
 
 #define CONTEXT_TT_MULTI_LEVEL	0
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
index 6998d9376ef9..4bfe0a2f7d50 100644
--- a/include/linux/dw_dmac.h
+++ b/include/linux/dw_dmac.h
@@ -3,6 +3,7 @@
  * AVR32 systems.)
  *
  * Copyright (C) 2007 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
  *
  * 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
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 33fa1203024e..e376270cd26e 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -299,6 +299,7 @@ extern void efi_initialize_iomem_resources(struct resource *code_resource,
 		struct resource *data_resource, struct resource *bss_resource);
 extern unsigned long efi_get_time(void);
 extern int efi_set_rtc_mmss(unsigned long nowtime);
+extern void efi_reserve_boot_services(void);
 extern struct efi_memory_map memmap;
 
 /**
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index c6a850ab2ec5..439b173c5882 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -268,7 +268,7 @@ struct ethtool_pauseparam {
 	__u32	cmd;	/* ETHTOOL_{G,S}PAUSEPARAM */
 
 	/* If the link is being auto-negotiated (via ethtool_cmd.autoneg
-	 * being true) the user may set 'autonet' here non-zero to have the
+	 * being true) the user may set 'autoneg' here non-zero to have the
 	 * pause parameters be auto-negotiated too.  In such a case, the
 	 * {rx,tx}_pause values below determine what capabilities are
 	 * advertised.
@@ -811,7 +811,7 @@ bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported);
  * @get_tx_csum: Deprecated as redundant. Report whether transmit checksums
  *	are turned on or off.
  * @set_tx_csum: Deprecated in favour of generic netdev features.  Turn
- *	transmit checksums on or off.  Returns a egative error code or zero.
+ *	transmit checksums on or off.  Returns a negative error code or zero.
  * @get_sg: Deprecated as redundant.  Report whether scatter-gather is
  *	enabled.  
  * @set_sg: Deprecated in favour of generic netdev features.  Turn
@@ -1087,7 +1087,7 @@ struct ethtool_ops {
 /* The following are all involved in forcing a particular link
  * mode for the device for setting things.  When getting the
  * devices settings, these indicate the current mode and whether
- * it was foced up into this mode or autonegotiated.
+ * it was forced up into this mode or autonegotiated.
  */
 
 /* The forced speed, 10Mb, 100Mb, gigabit, 2.5Gb, 10GbE. */
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 85c1d302c12e..5e06acf95d0f 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -909,7 +909,7 @@ extern int  ext3_setattr (struct dentry *, struct iattr *);
 extern void ext3_evict_inode (struct inode *);
 extern int  ext3_sync_inode (handle_t *, struct inode *);
 extern void ext3_discard_reservation (struct inode *);
-extern void ext3_dirty_inode(struct inode *);
+extern void ext3_dirty_inode(struct inode *, int);
 extern int ext3_change_inode_journal_flag(struct inode *, int);
 extern int ext3_get_inode_loc(struct inode *, struct ext3_iloc *);
 extern int ext3_can_truncate(struct inode *inode);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 241609346dfb..b5b979247863 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -208,6 +208,7 @@ struct inodes_stat_t {
 #define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
 #define MS_I_VERSION	(1<<23) /* Update inode I_version field */
 #define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_NOSEC	(1<<28)
 #define MS_BORN		(1<<29)
 #define MS_ACTIVE	(1<<30)
 #define MS_NOUSER	(1<<31)
@@ -237,6 +238,7 @@ struct inodes_stat_t {
 #define S_PRIVATE	512	/* Inode is fs-internal */
 #define S_IMA		1024	/* Inode has an associated IMA struct */
 #define S_AUTOMOUNT	2048	/* Automount/referral quasi-directory */
+#define S_NOSEC		4096	/* no suid or xattr security attributes */
 
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system
@@ -273,6 +275,7 @@ struct inodes_stat_t {
 #define IS_PRIVATE(inode)	((inode)->i_flags & S_PRIVATE)
 #define IS_IMA(inode)		((inode)->i_flags & S_IMA)
 #define IS_AUTOMOUNT(inode)	((inode)->i_flags & S_AUTOMOUNT)
+#define IS_NOSEC(inode)		((inode)->i_flags & S_NOSEC)
 
 /* the read-only stuff doesn't really belong here, but any other place is
    probably as bad and I don't want to create yet another include file. */
@@ -636,6 +639,7 @@ struct address_space {
 	struct prio_tree_root	i_mmap;		/* tree of private and shared mappings */
 	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
 	struct mutex		i_mmap_mutex;	/* protect tree, count, list */
+	/* Protected by tree_lock together with the radix tree */
 	unsigned long		nrpages;	/* number of total pages */
 	pgoff_t			writeback_index;/* writeback starts here */
 	const struct address_space_operations *a_ops;	/* methods */
@@ -741,9 +745,13 @@ struct inode {
 
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	unsigned int		i_flags;
+	unsigned long		i_state;
+#ifdef CONFIG_SECURITY
+	void			*i_security;
+#endif
 	struct mutex		i_mutex;
 
-	unsigned long		i_state;
+
 	unsigned long		dirtied_when;	/* jiffies of first dirtying */
 
 	struct hlist_node	i_hash;
@@ -795,9 +803,6 @@ struct inode {
 	atomic_t		i_readcount; /* struct files open RO */
 #endif
 	atomic_t		i_writecount;
-#ifdef CONFIG_SECURITY
-	void			*i_security;
-#endif
 #ifdef CONFIG_FS_POSIX_ACL
 	struct posix_acl	*i_acl;
 	struct posix_acl	*i_default_acl;
@@ -1618,7 +1623,7 @@ struct super_operations {
    	struct inode *(*alloc_inode)(struct super_block *sb);
 	void (*destroy_inode)(struct inode *);
 
-   	void (*dirty_inode) (struct inode *);
+   	void (*dirty_inode) (struct inode *, int flags);
 	int (*write_inode) (struct inode *, struct writeback_control *wbc);
 	int (*drop_inode) (struct inode *);
 	void (*evict_inode) (struct inode *);
@@ -2582,5 +2587,16 @@ int __init get_filesystem_list(char *buf);
 #define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
 					    (flag & __FMODE_NONOTIFY)))
 
+static inline int is_sxid(mode_t mode)
+{
+	return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
+}
+
+static inline void inode_has_no_xattr(struct inode *inode)
+{
+	if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC))
+		inode->i_flags |= S_NOSEC;
+}
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_FS_H */
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index b5a550a39a70..59d3ef100eb9 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -16,6 +16,11 @@ struct trace_print_flags {
 	const char		*name;
 };
 
+struct trace_print_flags_u64 {
+	unsigned long long	mask;
+	const char		*name;
+};
+
 const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
 				   unsigned long flags,
 				   const struct trace_print_flags *flag_array);
@@ -23,6 +28,13 @@ const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
 const char *ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 				     const struct trace_print_flags *symbol_array);
 
+#if BITS_PER_LONG == 32
+const char *ftrace_print_symbols_seq_u64(struct trace_seq *p,
+					 unsigned long long val,
+					 const struct trace_print_flags_u64
+								 *symbol_array);
+#endif
+
 const char *ftrace_print_hex_seq(struct trace_seq *p,
 				 const unsigned char *buf, int len);
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index b78956b3c2e7..300d7582006e 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -100,6 +100,7 @@ struct hd_struct {
 	sector_t start_sect;
 	sector_t nr_sects;
 	sector_t alignment_offset;
+	unsigned int discard_alignment;
 	struct device __dev;
 	struct kobject *holder_dir;
 	int policy, partno;
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index 32720baf70f1..17b5a0d80e42 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -3,6 +3,17 @@
 
 /* see Documentation/gpio.txt */
 
+/* make these flag values available regardless of GPIO kconfig options */
+#define GPIOF_DIR_OUT	(0 << 0)
+#define GPIOF_DIR_IN	(1 << 0)
+
+#define GPIOF_INIT_LOW	(0 << 1)
+#define GPIOF_INIT_HIGH	(1 << 1)
+
+#define GPIOF_IN		(GPIOF_DIR_IN)
+#define GPIOF_OUT_INIT_LOW	(GPIOF_DIR_OUT | GPIOF_INIT_LOW)
+#define GPIOF_OUT_INIT_HIGH	(GPIOF_DIR_OUT | GPIOF_INIT_HIGH)
+
 #ifdef CONFIG_GENERIC_GPIO
 #include <asm/gpio.h>
 
@@ -25,9 +36,9 @@ struct gpio_chip;
  * warning when something is wrongly called.
  */
 
-static inline int gpio_is_valid(int number)
+static inline bool gpio_is_valid(int number)
 {
-	return 0;
+	return false;
 }
 
 static inline int gpio_request(unsigned gpio, const char *label)
@@ -41,7 +52,7 @@ static inline int gpio_request_one(unsigned gpio,
 	return -ENOSYS;
 }
 
-static inline int gpio_request_array(struct gpio *array, size_t num)
+static inline int gpio_request_array(const struct gpio *array, size_t num)
 {
 	return -ENOSYS;
 }
@@ -54,7 +65,7 @@ static inline void gpio_free(unsigned gpio)
 	WARN_ON(1);
 }
 
-static inline void gpio_free_array(struct gpio *array, size_t num)
+static inline void gpio_free_array(const struct gpio *array, size_t num)
 {
 	might_sleep();
 
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 51932e5acf7c..fd0dc30c9f15 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -135,6 +135,7 @@ struct hrtimer_sleeper {
  * @cpu_base:		per cpu clock base
  * @index:		clock type index for per_cpu support when moving a
  *			timer to a base on another cpu.
+ * @clockid:		clock id for per_cpu support
  * @active:		red black tree root node for the active timers
  * @resolution:		the resolution of the clock, in nanoseconds
  * @get_time:		function to retrieve the current time of the clock
diff --git a/include/linux/i2c/adp8870.h b/include/linux/i2c/adp8870.h
new file mode 100644
index 000000000000..624dceccbd5b
--- /dev/null
+++ b/include/linux/i2c/adp8870.h
@@ -0,0 +1,153 @@
+/*
+ * Definitions and platform data for Analog Devices
+ * Backlight drivers ADP8870
+ *
+ * Copyright 2009-2010 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#ifndef __LINUX_I2C_ADP8870_H
+#define __LINUX_I2C_ADP8870_H
+
+#define ID_ADP8870		8870
+
+#define ADP8870_MAX_BRIGHTNESS	0x7F
+#define FLAG_OFFT_SHIFT 8
+
+/*
+ * LEDs subdevice platform data
+ */
+
+#define ADP8870_LED_DIS_BLINK	(0 << FLAG_OFFT_SHIFT)
+#define ADP8870_LED_OFFT_600ms	(1 << FLAG_OFFT_SHIFT)
+#define ADP8870_LED_OFFT_1200ms	(2 << FLAG_OFFT_SHIFT)
+#define ADP8870_LED_OFFT_1800ms	(3 << FLAG_OFFT_SHIFT)
+
+#define ADP8870_LED_ONT_200ms	0
+#define ADP8870_LED_ONT_600ms	1
+#define ADP8870_LED_ONT_800ms	2
+#define ADP8870_LED_ONT_1200ms	3
+
+#define ADP8870_LED_D7		(7)
+#define ADP8870_LED_D6		(6)
+#define ADP8870_LED_D5		(5)
+#define ADP8870_LED_D4		(4)
+#define ADP8870_LED_D3		(3)
+#define ADP8870_LED_D2		(2)
+#define ADP8870_LED_D1		(1)
+
+/*
+ * Backlight subdevice platform data
+ */
+
+#define ADP8870_BL_D7		(1 << 6)
+#define ADP8870_BL_D6		(1 << 5)
+#define ADP8870_BL_D5		(1 << 4)
+#define ADP8870_BL_D4		(1 << 3)
+#define ADP8870_BL_D3		(1 << 2)
+#define ADP8870_BL_D2		(1 << 1)
+#define ADP8870_BL_D1		(1 << 0)
+
+#define ADP8870_FADE_T_DIS	0	/* Fade Timer Disabled */
+#define ADP8870_FADE_T_300ms	1	/* 0.3 Sec */
+#define ADP8870_FADE_T_600ms	2
+#define ADP8870_FADE_T_900ms	3
+#define ADP8870_FADE_T_1200ms	4
+#define ADP8870_FADE_T_1500ms	5
+#define ADP8870_FADE_T_1800ms	6
+#define ADP8870_FADE_T_2100ms	7
+#define ADP8870_FADE_T_2400ms	8
+#define ADP8870_FADE_T_2700ms	9
+#define ADP8870_FADE_T_3000ms	10
+#define ADP8870_FADE_T_3500ms	11
+#define ADP8870_FADE_T_4000ms	12
+#define ADP8870_FADE_T_4500ms	13
+#define ADP8870_FADE_T_5000ms	14
+#define ADP8870_FADE_T_5500ms	15	/* 5.5 Sec */
+
+#define ADP8870_FADE_LAW_LINEAR	0
+#define ADP8870_FADE_LAW_SQUARE	1
+#define ADP8870_FADE_LAW_CUBIC1	2
+#define ADP8870_FADE_LAW_CUBIC2	3
+
+#define ADP8870_BL_AMBL_FILT_80ms	0	/* Light sensor filter time */
+#define ADP8870_BL_AMBL_FILT_160ms	1
+#define ADP8870_BL_AMBL_FILT_320ms	2
+#define ADP8870_BL_AMBL_FILT_640ms	3
+#define ADP8870_BL_AMBL_FILT_1280ms	4
+#define ADP8870_BL_AMBL_FILT_2560ms	5
+#define ADP8870_BL_AMBL_FILT_5120ms	6
+#define ADP8870_BL_AMBL_FILT_10240ms	7	/* 10.24 sec */
+
+/*
+ * Blacklight current 0..30mA
+ */
+#define ADP8870_BL_CUR_mA(I)		((I * 127) / 30)
+
+/*
+ * L2 comparator current 0..1106uA
+ */
+#define ADP8870_L2_COMP_CURR_uA(I)	((I * 255) / 1106)
+
+/*
+ * L3 comparator current 0..551uA
+ */
+#define ADP8870_L3_COMP_CURR_uA(I)	((I * 255) / 551)
+
+/*
+ * L4 comparator current 0..275uA
+ */
+#define ADP8870_L4_COMP_CURR_uA(I)	((I * 255) / 275)
+
+/*
+ * L5 comparator current 0..138uA
+ */
+#define ADP8870_L5_COMP_CURR_uA(I)	((I * 255) / 138)
+
+struct adp8870_backlight_platform_data {
+	u8 bl_led_assign;	/* 1 = Backlight 0 = Individual LED */
+	u8 pwm_assign;		/* 1 = Enables PWM mode */
+
+	u8 bl_fade_in;		/* Backlight Fade-In Timer */
+	u8 bl_fade_out;		/* Backlight Fade-Out Timer */
+	u8 bl_fade_law;		/* fade-on/fade-off transfer characteristic */
+
+	u8 en_ambl_sens;	/* 1 = enable ambient light sensor */
+	u8 abml_filt;		/* Light sensor filter time */
+
+	u8 l1_daylight_max;	/* use BL_CUR_mA(I) 0 <= I <= 30 mA */
+	u8 l1_daylight_dim;	/* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */
+	u8 l2_bright_max;	/* use BL_CUR_mA(I) 0 <= I <= 30 mA */
+	u8 l2_bright_dim;	/* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */
+	u8 l3_office_max;	/* use BL_CUR_mA(I) 0 <= I <= 30 mA */
+	u8 l3_office_dim;	/* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */
+	u8 l4_indoor_max;	/* use BL_CUR_mA(I) 0 <= I <= 30 mA */
+	u8 l4_indor_dim;	/* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */
+	u8 l5_dark_max;		/* use BL_CUR_mA(I) 0 <= I <= 30 mA */
+	u8 l5_dark_dim;		/* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */
+
+	u8 l2_trip;		/* use L2_COMP_CURR_uA(I) 0 <= I <= 1106 uA */
+	u8 l2_hyst;		/* use L2_COMP_CURR_uA(I) 0 <= I <= 1106 uA */
+	u8 l3_trip;		/* use L3_COMP_CURR_uA(I) 0 <= I <= 551 uA */
+	u8 l3_hyst;		/* use L3_COMP_CURR_uA(I) 0 <= I <= 551 uA */
+	u8 l4_trip;		/* use L4_COMP_CURR_uA(I) 0 <= I <= 275 uA */
+	u8 l4_hyst;		/* use L4_COMP_CURR_uA(I) 0 <= I <= 275 uA */
+	u8 l5_trip;		/* use L5_COMP_CURR_uA(I) 0 <= I <= 138 uA */
+	u8 l5_hyst;		/* use L6_COMP_CURR_uA(I) 0 <= I <= 138 uA */
+
+	/**
+	 * Independent Current Sinks / LEDS
+	 * Sinks not assigned to the Backlight can be exposed to
+	 * user space using the LEDS CLASS interface
+	 */
+
+	int num_leds;
+	struct led_info	*leds;
+	u8 led_fade_in;		/* LED Fade-In Timer */
+	u8 led_fade_out;	/* LED Fade-Out Timer */
+	u8 led_fade_law;	/* fade-on/fade-off transfer characteristic */
+	u8 led_on_time;
+};
+
+#endif /* __LINUX_I2C_ADP8870_H */
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index b2eee5879883..bf56b6f78270 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1003,8 +1003,12 @@ struct ieee80211_ht_info {
 #define WLAN_CAPABILITY_ESS		(1<<0)
 #define WLAN_CAPABILITY_IBSS		(1<<1)
 
-/* A mesh STA sets the ESS and IBSS capability bits to zero */
-#define WLAN_CAPABILITY_IS_MBSS(cap)	\
+/*
+ * A mesh STA sets the ESS and IBSS capability bits to zero.
+ * however, this holds true for p2p probe responses (in the p2p_find
+ * phase) as well.
+ */
+#define WLAN_CAPABILITY_IS_STA_BSS(cap)	\
 	(!((cap) & (WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_IBSS)))
 
 #define WLAN_CAPABILITY_CF_POLLABLE	(1<<2)
diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h
index 0f1325d98295..0065ffd3226b 100644
--- a/include/linux/if_ether.h
+++ b/include/linux/if_ether.h
@@ -132,10 +132,6 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb)
 
 int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr);
 
-#ifdef CONFIG_SYSCTL
-extern struct ctl_table ether_table[];
-#endif
-
 int mac_pton(const char *s, u8 *mac);
 extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len);
 
diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h
index 72bfa5a034dd..7b318630139f 100644
--- a/include/linux/if_packet.h
+++ b/include/linux/if_packet.h
@@ -62,6 +62,7 @@ struct tpacket_auxdata {
 	__u16		tp_mac;
 	__u16		tp_net;
 	__u16		tp_vlan_tci;
+	__u16		tp_padding;
 };
 
 /* Rx ring - header status */
@@ -70,6 +71,7 @@ struct tpacket_auxdata {
 #define TP_STATUS_COPY		0x2
 #define TP_STATUS_LOSING	0x4
 #define TP_STATUS_CSUMNOTREADY	0x8
+#define TP_STATUS_VLAN_VALID   0x10 /* auxdata has valid tp_vlan_tci */
 
 /* Tx ring - header status */
 #define TP_STATUS_AVAILABLE	0x0
@@ -100,6 +102,7 @@ struct tpacket2_hdr {
 	__u32		tp_sec;
 	__u32		tp_nsec;
 	__u16		tp_vlan_tci;
+	__u16		tp_padding;
 };
 
 #define TPACKET2_HDRLEN		(TPACKET_ALIGN(sizeof(struct tpacket2_hdr)) + sizeof(struct sockaddr_ll))
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index dc01681fbb42..affa27380b72 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -225,7 +225,7 @@ static inline int vlan_hwaccel_receive_skb(struct sk_buff *skb,
 }
 
 /**
- * __vlan_put_tag - regular VLAN tag inserting
+ * vlan_insert_tag - regular VLAN tag inserting
  * @skb: skbuff to tag
  * @vlan_tci: VLAN TCI to insert
  *
@@ -234,8 +234,10 @@ static inline int vlan_hwaccel_receive_skb(struct sk_buff *skb,
  *
  * Following the skb_unshare() example, in case of error, the calling function
  * doesn't have to worry about freeing the original skb.
+ *
+ * Does not change skb->protocol so this function can be used during receive.
  */
-static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci)
+static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, u16 vlan_tci)
 {
 	struct vlan_ethhdr *veth;
 
@@ -255,8 +257,25 @@ static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci)
 	/* now, the TCI */
 	veth->h_vlan_TCI = htons(vlan_tci);
 
-	skb->protocol = htons(ETH_P_8021Q);
+	return skb;
+}
 
+/**
+ * __vlan_put_tag - regular VLAN tag inserting
+ * @skb: skbuff to tag
+ * @vlan_tci: VLAN TCI to insert
+ *
+ * Inserts the VLAN tag into @skb as part of the payload
+ * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
+ *
+ * Following the skb_unshare() example, in case of error, the calling function
+ * doesn't have to worry about freeing the original skb.
+ */
+static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci)
+{
+	skb = vlan_insert_tag(skb, vlan_tci);
+	if (skb)
+		skb->protocol = htons(ETH_P_8021Q);
 	return skb;
 }
 
diff --git a/include/linux/input/sh_keysc.h b/include/linux/input/sh_keysc.h
index 649dc7f12925..5d253cd93691 100644
--- a/include/linux/input/sh_keysc.h
+++ b/include/linux/input/sh_keysc.h
@@ -1,7 +1,7 @@
 #ifndef __SH_KEYSC_H__
 #define __SH_KEYSC_H__
 
-#define SH_KEYSC_MAXKEYS 49
+#define SH_KEYSC_MAXKEYS 64
 
 struct sh_keysc_info {
 	enum { SH_KEYSC_MODE_1, SH_KEYSC_MODE_2, SH_KEYSC_MODE_3,
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 6c12989839d9..f6efed0039ed 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -414,6 +414,7 @@ enum
 	TASKLET_SOFTIRQ,
 	SCHED_SOFTIRQ,
 	HRTIMER_SOFTIRQ,
+	RCU_SOFTIRQ,    /* Preferable RCU should always be the last softirq */
 
 	NR_SOFTIRQS
 };
diff --git a/include/linux/irqreturn.h b/include/linux/irqreturn.h
index 819acaaac3f5..714ba08dc092 100644
--- a/include/linux/irqreturn.h
+++ b/include/linux/irqreturn.h
@@ -8,9 +8,9 @@
  * @IRQ_WAKE_THREAD	handler requests to wake the handler thread
  */
 enum irqreturn {
-	IRQ_NONE,
-	IRQ_HANDLED,
-	IRQ_WAKE_THREAD,
+	IRQ_NONE		= (0 << 0),
+	IRQ_HANDLED		= (1 << 0),
+	IRQ_WAKE_THREAD		= (1 << 1),
 };
 
 typedef enum irqreturn irqreturn_t;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 4ecb7b16b278..d087c2e7b2aa 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1024,7 +1024,6 @@ struct journal_s
 
 /* Filing buffers */
 extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *);
-extern void __jbd2_journal_unfile_buffer(struct journal_head *);
 extern void __jbd2_journal_refile_buffer(struct journal_head *);
 extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *);
 extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int);
@@ -1165,7 +1164,6 @@ extern void	   jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_in
  */
 struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh);
 struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh);
-void jbd2_journal_remove_journal_head(struct buffer_head *bh);
 void jbd2_journal_put_journal_head(struct journal_head *jh);
 
 /*
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index fb0e7329fee1..953352a88336 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -671,8 +671,8 @@ struct sysinfo {
 
 #ifdef __CHECKER__
 #define BUILD_BUG_ON_NOT_POWER_OF_2(n)
-#define BUILD_BUG_ON_ZERO(e)
-#define BUILD_BUG_ON_NULL(e)
+#define BUILD_BUG_ON_ZERO(e) (0)
+#define BUILD_BUG_ON_NULL(e) ((void*)0)
 #define BUILD_BUG_ON(condition)
 #else /* __CHECKER__ */
 
diff --git a/include/linux/key.h b/include/linux/key.h
index ef19b99aff98..6ea4eebd3467 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -9,7 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  *
  *
- * See Documentation/keys.txt for information on keys/keyrings.
+ * See Documentation/security/keys.txt for information on keys/keyrings.
  */
 
 #ifndef _LINUX_KEY_H
diff --git a/include/linux/kmod.h b/include/linux/kmod.h
index d4a5c84c503d..0da38cf7db7b 100644
--- a/include/linux/kmod.h
+++ b/include/linux/kmod.h
@@ -45,7 +45,7 @@ static inline int request_module_nowait(const char *name, ...) { return -ENOSYS;
 #endif
 
 
-struct key;
+struct cred;
 struct file;
 
 enum umh_wait {
@@ -62,7 +62,7 @@ struct subprocess_info {
 	char **envp;
 	enum umh_wait wait;
 	int retval;
-	int (*init)(struct subprocess_info *info);
+	int (*init)(struct subprocess_info *info, struct cred *new);
 	void (*cleanup)(struct subprocess_info *info);
 	void *data;
 };
@@ -73,7 +73,7 @@ struct subprocess_info *call_usermodehelper_setup(char *path, char **argv,
 
 /* Set various pieces of state into the subprocess_info structure */
 void call_usermodehelper_setfns(struct subprocess_info *info,
-		    int (*init)(struct subprocess_info *info),
+		    int (*init)(struct subprocess_info *info, struct cred *new),
 		    void (*cleanup)(struct subprocess_info *info),
 		    void *data);
 
@@ -87,7 +87,7 @@ void call_usermodehelper_freeinfo(struct subprocess_info *info);
 static inline int
 call_usermodehelper_fns(char *path, char **argv, char **envp,
 			enum umh_wait wait,
-			int (*init)(struct subprocess_info *info),
+			int (*init)(struct subprocess_info *info, struct cred *new),
 			void (*cleanup)(struct subprocess_info *), void *data)
 {
 	struct subprocess_info *info;
diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h
index 2a0d7d651dc3..ee0c952188de 100644
--- a/include/linux/kmsg_dump.h
+++ b/include/linux/kmsg_dump.h
@@ -12,6 +12,7 @@
 #ifndef _LINUX_KMSG_DUMP_H
 #define _LINUX_KMSG_DUMP_H
 
+#include <linux/errno.h>
 #include <linux/list.h>
 
 enum kmsg_dump_reason {
diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h
index 82cb5bf461fb..f66b065a8b5f 100644
--- a/include/linux/kobject_ns.h
+++ b/include/linux/kobject_ns.h
@@ -32,15 +32,17 @@ enum kobj_ns_type {
 
 /*
  * Callbacks so sysfs can determine namespaces
- *   @current_ns: return calling task's namespace
+ *   @grab_current_ns: return a new reference to calling task's namespace
  *   @netlink_ns: return namespace to which a sock belongs (right?)
  *   @initial_ns: return the initial namespace (i.e. init_net_ns)
+ *   @drop_ns: drops a reference to namespace
  */
 struct kobj_ns_type_operations {
 	enum kobj_ns_type type;
-	const void *(*current_ns)(void);
+	void *(*grab_current_ns)(void);
 	const void *(*netlink_ns)(struct sock *sk);
 	const void *(*initial_ns)(void);
+	void (*drop_ns)(void *);
 };
 
 int kobj_ns_type_register(const struct kobj_ns_type_operations *ops);
@@ -48,9 +50,9 @@ int kobj_ns_type_registered(enum kobj_ns_type type);
 const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent);
 const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj);
 
-const void *kobj_ns_current(enum kobj_ns_type type);
+void *kobj_ns_grab_current(enum kobj_ns_type type);
 const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk);
 const void *kobj_ns_initial(enum kobj_ns_type type);
-void kobj_ns_exit(enum kobj_ns_type type, const void *ns);
+void kobj_ns_drop(enum kobj_ns_type type, void *ns);
 
 #endif /* _LINUX_KOBJECT_NS_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 9724a38ee69d..50940da6adf3 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -84,6 +84,7 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
 
 extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
 extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
+extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm);
 
 static inline
 int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
@@ -246,6 +247,11 @@ static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 	return NULL;
 }
 
+static inline struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
+{
+	return NULL;
+}
+
 static inline int mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *mem)
 {
 	return 1;
diff --git a/include/linux/mfd/max8997-private.h b/include/linux/mfd/max8997-private.h
index 69d1010e2e51..5ff2400ad46c 100644
--- a/include/linux/mfd/max8997-private.h
+++ b/include/linux/mfd/max8997-private.h
@@ -311,10 +311,6 @@ enum max8997_irq {
 	MAX8997_IRQ_NR,
 };
 
-#define MAX8997_REG_BUCK1DVS(x)	(MAX8997_REG_BUCK1DVS1 + (x) - 1)
-#define MAX8997_REG_BUCK2DVS(x)	(MAX8997_REG_BUCK2DVS1 + (x) - 1)
-#define MAX8997_REG_BUCK5DVS(x)	(MAX8997_REG_BUCK5DVS1 + (x) - 1)
-
 #define MAX8997_NUM_GPIO	12
 struct max8997_dev {
 	struct device *dev;
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
new file mode 100644
index 000000000000..8bb85b930c07
--- /dev/null
+++ b/include/linux/mfd/tps65910.h
@@ -0,0 +1,800 @@
+/*
+ * tps65910.h  --  TI TPS6591x
+ *
+ * Copyright 2010-2011 Texas Instruments Inc.
+ *
+ * Author: Graeme Gregory <gg@slimlogic.co.uk>
+ * Author: Jorge Eduardo Candelaria <jedu@slimlogic.co.uk>
+ * Author: Arnaud Deconinck <a-deconinck@ti.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.
+ *
+ */
+
+#ifndef __LINUX_MFD_TPS65910_H
+#define __LINUX_MFD_TPS65910_H
+
+/* TPS chip id list */
+#define TPS65910			0
+#define TPS65911			1
+
+/* TPS regulator type list */
+#define REGULATOR_LDO			0
+#define REGULATOR_DCDC			1
+
+/*
+ * List of registers for component TPS65910
+ *
+ */
+
+#define TPS65910_SECONDS				0x0
+#define TPS65910_MINUTES				0x1
+#define TPS65910_HOURS					0x2
+#define TPS65910_DAYS					0x3
+#define TPS65910_MONTHS					0x4
+#define TPS65910_YEARS					0x5
+#define TPS65910_WEEKS					0x6
+#define TPS65910_ALARM_SECONDS				0x8
+#define TPS65910_ALARM_MINUTES				0x9
+#define TPS65910_ALARM_HOURS				0xA
+#define TPS65910_ALARM_DAYS				0xB
+#define TPS65910_ALARM_MONTHS				0xC
+#define TPS65910_ALARM_YEARS				0xD
+#define TPS65910_RTC_CTRL				0x10
+#define TPS65910_RTC_STATUS				0x11
+#define TPS65910_RTC_INTERRUPTS				0x12
+#define TPS65910_RTC_COMP_LSB				0x13
+#define TPS65910_RTC_COMP_MSB				0x14
+#define TPS65910_RTC_RES_PROG				0x15
+#define TPS65910_RTC_RESET_STATUS			0x16
+#define TPS65910_BCK1					0x17
+#define TPS65910_BCK2					0x18
+#define TPS65910_BCK3					0x19
+#define TPS65910_BCK4					0x1A
+#define TPS65910_BCK5					0x1B
+#define TPS65910_PUADEN					0x1C
+#define TPS65910_REF					0x1D
+#define TPS65910_VRTC					0x1E
+#define TPS65910_VIO					0x20
+#define TPS65910_VDD1					0x21
+#define TPS65910_VDD1_OP				0x22
+#define TPS65910_VDD1_SR				0x23
+#define TPS65910_VDD2					0x24
+#define TPS65910_VDD2_OP				0x25
+#define TPS65910_VDD2_SR				0x26
+#define TPS65910_VDD3					0x27
+#define TPS65910_VDIG1					0x30
+#define TPS65910_VDIG2					0x31
+#define TPS65910_VAUX1					0x32
+#define TPS65910_VAUX2					0x33
+#define TPS65910_VAUX33					0x34
+#define TPS65910_VMMC					0x35
+#define TPS65910_VPLL					0x36
+#define TPS65910_VDAC					0x37
+#define TPS65910_THERM					0x38
+#define TPS65910_BBCH					0x39
+#define TPS65910_DCDCCTRL				0x3E
+#define TPS65910_DEVCTRL				0x3F
+#define TPS65910_DEVCTRL2				0x40
+#define TPS65910_SLEEP_KEEP_LDO_ON			0x41
+#define TPS65910_SLEEP_KEEP_RES_ON			0x42
+#define TPS65910_SLEEP_SET_LDO_OFF			0x43
+#define TPS65910_SLEEP_SET_RES_OFF			0x44
+#define TPS65910_EN1_LDO_ASS				0x45
+#define TPS65910_EN1_SMPS_ASS				0x46
+#define TPS65910_EN2_LDO_ASS				0x47
+#define TPS65910_EN2_SMPS_ASS				0x48
+#define TPS65910_EN3_LDO_ASS				0x49
+#define TPS65910_SPARE					0x4A
+#define TPS65910_INT_STS				0x50
+#define TPS65910_INT_MSK				0x51
+#define TPS65910_INT_STS2				0x52
+#define TPS65910_INT_MSK2				0x53
+#define TPS65910_INT_STS3				0x54
+#define TPS65910_INT_MSK3				0x55
+#define TPS65910_GPIO0					0x60
+#define TPS65910_GPIO1					0x61
+#define TPS65910_GPIO2					0x62
+#define TPS65910_GPIO3					0x63
+#define TPS65910_GPIO4					0x64
+#define TPS65910_GPIO5					0x65
+#define TPS65910_GPIO6					0x66
+#define TPS65910_GPIO7					0x67
+#define TPS65910_GPIO8					0x68
+#define TPS65910_JTAGVERNUM				0x80
+#define TPS65910_MAX_REGISTER				0x80
+
+/*
+ * List of registers specific to TPS65911
+ */
+#define TPS65911_VDDCTRL				0x27
+#define TPS65911_VDDCTRL_OP				0x28
+#define TPS65911_VDDCTRL_SR				0x29
+#define TPS65911_LDO1					0x30
+#define TPS65911_LDO2					0x31
+#define TPS65911_LDO5					0x32
+#define TPS65911_LDO8					0x33
+#define TPS65911_LDO7					0x34
+#define TPS65911_LDO6					0x35
+#define TPS65911_LDO4					0x36
+#define TPS65911_LDO3					0x37
+#define TPS65911_VMBCH					0x6A
+#define TPS65911_VMBCH2					0x6B
+
+/*
+ * List of register bitfields for component TPS65910
+ *
+ */
+
+
+/*Register BCK1  (0x80) register.RegisterDescription */
+#define BCK1_BCKUP_MASK					0xFF
+#define BCK1_BCKUP_SHIFT				0
+
+
+/*Register BCK2  (0x80) register.RegisterDescription */
+#define BCK2_BCKUP_MASK					0xFF
+#define BCK2_BCKUP_SHIFT				0
+
+
+/*Register BCK3  (0x80) register.RegisterDescription */
+#define BCK3_BCKUP_MASK					0xFF
+#define BCK3_BCKUP_SHIFT				0
+
+
+/*Register BCK4  (0x80) register.RegisterDescription */
+#define BCK4_BCKUP_MASK					0xFF
+#define BCK4_BCKUP_SHIFT				0
+
+
+/*Register BCK5  (0x80) register.RegisterDescription */
+#define BCK5_BCKUP_MASK					0xFF
+#define BCK5_BCKUP_SHIFT				0
+
+
+/*Register PUADEN  (0x80) register.RegisterDescription */
+#define PUADEN_EN3P_MASK				0x80
+#define PUADEN_EN3P_SHIFT				7
+#define PUADEN_I2CCTLP_MASK				0x40
+#define PUADEN_I2CCTLP_SHIFT				6
+#define PUADEN_I2CSRP_MASK				0x20
+#define PUADEN_I2CSRP_SHIFT				5
+#define PUADEN_PWRONP_MASK				0x10
+#define PUADEN_PWRONP_SHIFT				4
+#define PUADEN_SLEEPP_MASK				0x08
+#define PUADEN_SLEEPP_SHIFT				3
+#define PUADEN_PWRHOLDP_MASK				0x04
+#define PUADEN_PWRHOLDP_SHIFT				2
+#define PUADEN_BOOT1P_MASK				0x02
+#define PUADEN_BOOT1P_SHIFT				1
+#define PUADEN_BOOT0P_MASK				0x01
+#define PUADEN_BOOT0P_SHIFT				0
+
+
+/*Register REF	(0x80) register.RegisterDescription */
+#define REF_VMBCH_SEL_MASK				0x0C
+#define REF_VMBCH_SEL_SHIFT				2
+#define REF_ST_MASK					0x03
+#define REF_ST_SHIFT					0
+
+
+/*Register VRTC  (0x80) register.RegisterDescription */
+#define VRTC_VRTC_OFFMASK_MASK				0x08
+#define VRTC_VRTC_OFFMASK_SHIFT				3
+#define VRTC_ST_MASK					0x03
+#define VRTC_ST_SHIFT					0
+
+
+/*Register VIO	(0x80) register.RegisterDescription */
+#define VIO_ILMAX_MASK					0xC0
+#define VIO_ILMAX_SHIFT					6
+#define VIO_SEL_MASK					0x0C
+#define VIO_SEL_SHIFT					2
+#define VIO_ST_MASK					0x03
+#define VIO_ST_SHIFT					0
+
+
+/*Register VDD1  (0x80) register.RegisterDescription */
+#define VDD1_VGAIN_SEL_MASK				0xC0
+#define VDD1_VGAIN_SEL_SHIFT				6
+#define VDD1_ILMAX_MASK					0x20
+#define VDD1_ILMAX_SHIFT				5
+#define VDD1_TSTEP_MASK					0x1C
+#define VDD1_TSTEP_SHIFT				2
+#define VDD1_ST_MASK					0x03
+#define VDD1_ST_SHIFT					0
+
+
+/*Register VDD1_OP  (0x80) register.RegisterDescription */
+#define VDD1_OP_CMD_MASK				0x80
+#define VDD1_OP_CMD_SHIFT				7
+#define VDD1_OP_SEL_MASK				0x7F
+#define VDD1_OP_SEL_SHIFT				0
+
+
+/*Register VDD1_SR  (0x80) register.RegisterDescription */
+#define VDD1_SR_SEL_MASK				0x7F
+#define VDD1_SR_SEL_SHIFT				0
+
+
+/*Register VDD2  (0x80) register.RegisterDescription */
+#define VDD2_VGAIN_SEL_MASK				0xC0
+#define VDD2_VGAIN_SEL_SHIFT				6
+#define VDD2_ILMAX_MASK					0x20
+#define VDD2_ILMAX_SHIFT				5
+#define VDD2_TSTEP_MASK					0x1C
+#define VDD2_TSTEP_SHIFT				2
+#define VDD2_ST_MASK					0x03
+#define VDD2_ST_SHIFT					0
+
+
+/*Register VDD2_OP  (0x80) register.RegisterDescription */
+#define VDD2_OP_CMD_MASK				0x80
+#define VDD2_OP_CMD_SHIFT				7
+#define VDD2_OP_SEL_MASK				0x7F
+#define VDD2_OP_SEL_SHIFT				0
+
+/*Register VDD2_SR  (0x80) register.RegisterDescription */
+#define VDD2_SR_SEL_MASK				0x7F
+#define VDD2_SR_SEL_SHIFT				0
+
+
+/*Registers VDD1, VDD2 voltage values definitions */
+#define VDD1_2_NUM_VOLTS				73
+#define VDD1_2_MIN_VOLT					6000
+#define VDD1_2_OFFSET					125
+
+
+/*Register VDD3  (0x80) register.RegisterDescription */
+#define VDD3_CKINEN_MASK				0x04
+#define VDD3_CKINEN_SHIFT				2
+#define VDD3_ST_MASK					0x03
+#define VDD3_ST_SHIFT					0
+#define VDDCTRL_MIN_VOLT				6000
+#define VDDCTRL_OFFSET					125
+
+/*Registers VDIG (0x80) to VDAC register.RegisterDescription */
+#define LDO_SEL_MASK					0x0C
+#define LDO_SEL_SHIFT					2
+#define LDO_ST_MASK					0x03
+#define LDO_ST_SHIFT					0
+#define LDO_ST_ON_BIT					0x01
+#define LDO_ST_MODE_BIT					0x02	
+
+
+/* Registers LDO1 to LDO8 in tps65910 */
+#define LDO1_SEL_MASK					0xFC
+#define LDO3_SEL_MASK					0x7C
+#define LDO_MIN_VOLT					1000
+#define LDO_MAX_VOLT					3300;
+
+
+/*Register VDIG1  (0x80) register.RegisterDescription */
+#define VDIG1_SEL_MASK					0x0C
+#define VDIG1_SEL_SHIFT					2
+#define VDIG1_ST_MASK					0x03
+#define VDIG1_ST_SHIFT					0
+
+
+/*Register VDIG2  (0x80) register.RegisterDescription */
+#define VDIG2_SEL_MASK					0x0C
+#define VDIG2_SEL_SHIFT					2
+#define VDIG2_ST_MASK					0x03
+#define VDIG2_ST_SHIFT					0
+
+
+/*Register VAUX1  (0x80) register.RegisterDescription */
+#define VAUX1_SEL_MASK					0x0C
+#define VAUX1_SEL_SHIFT					2
+#define VAUX1_ST_MASK					0x03
+#define VAUX1_ST_SHIFT					0
+
+
+/*Register VAUX2  (0x80) register.RegisterDescription */
+#define VAUX2_SEL_MASK					0x0C
+#define VAUX2_SEL_SHIFT					2
+#define VAUX2_ST_MASK					0x03
+#define VAUX2_ST_SHIFT					0
+
+
+/*Register VAUX33  (0x80) register.RegisterDescription */
+#define VAUX33_SEL_MASK					0x0C
+#define VAUX33_SEL_SHIFT				2
+#define VAUX33_ST_MASK					0x03
+#define VAUX33_ST_SHIFT					0
+
+
+/*Register VMMC  (0x80) register.RegisterDescription */
+#define VMMC_SEL_MASK					0x0C
+#define VMMC_SEL_SHIFT					2
+#define VMMC_ST_MASK					0x03
+#define VMMC_ST_SHIFT					0
+
+
+/*Register VPLL  (0x80) register.RegisterDescription */
+#define VPLL_SEL_MASK					0x0C
+#define VPLL_SEL_SHIFT					2
+#define VPLL_ST_MASK					0x03
+#define VPLL_ST_SHIFT					0
+
+
+/*Register VDAC  (0x80) register.RegisterDescription */
+#define VDAC_SEL_MASK					0x0C
+#define VDAC_SEL_SHIFT					2
+#define VDAC_ST_MASK					0x03
+#define VDAC_ST_SHIFT					0
+
+
+/*Register THERM  (0x80) register.RegisterDescription */
+#define THERM_THERM_HD_MASK				0x20
+#define THERM_THERM_HD_SHIFT				5
+#define THERM_THERM_TS_MASK				0x10
+#define THERM_THERM_TS_SHIFT				4
+#define THERM_THERM_HDSEL_MASK				0x0C
+#define THERM_THERM_HDSEL_SHIFT				2
+#define THERM_RSVD1_MASK				0x02
+#define THERM_RSVD1_SHIFT				1
+#define THERM_THERM_STATE_MASK				0x01
+#define THERM_THERM_STATE_SHIFT				0
+
+
+/*Register BBCH  (0x80) register.RegisterDescription */
+#define BBCH_BBSEL_MASK					0x06
+#define BBCH_BBSEL_SHIFT				1
+#define BBCH_BBCHEN_MASK				0x01
+#define BBCH_BBCHEN_SHIFT				0
+
+
+/*Register DCDCCTRL  (0x80) register.RegisterDescription */
+#define DCDCCTRL_VDD2_PSKIP_MASK			0x20
+#define DCDCCTRL_VDD2_PSKIP_SHIFT			5
+#define DCDCCTRL_VDD1_PSKIP_MASK			0x10
+#define DCDCCTRL_VDD1_PSKIP_SHIFT			4
+#define DCDCCTRL_VIO_PSKIP_MASK				0x08
+#define DCDCCTRL_VIO_PSKIP_SHIFT			3
+#define DCDCCTRL_DCDCCKEXT_MASK				0x04
+#define DCDCCTRL_DCDCCKEXT_SHIFT			2
+#define DCDCCTRL_DCDCCKSYNC_MASK			0x03
+#define DCDCCTRL_DCDCCKSYNC_SHIFT			0
+
+
+/*Register DEVCTRL  (0x80) register.RegisterDescription */
+#define DEVCTRL_RTC_PWDN_MASK				0x40
+#define DEVCTRL_RTC_PWDN_SHIFT				6
+#define DEVCTRL_CK32K_CTRL_MASK				0x20
+#define DEVCTRL_CK32K_CTRL_SHIFT			5
+#define DEVCTRL_SR_CTL_I2C_SEL_MASK			0x10
+#define DEVCTRL_SR_CTL_I2C_SEL_SHIFT			4
+#define DEVCTRL_DEV_OFF_RST_MASK			0x08
+#define DEVCTRL_DEV_OFF_RST_SHIFT			3
+#define DEVCTRL_DEV_ON_MASK				0x04
+#define DEVCTRL_DEV_ON_SHIFT				2
+#define DEVCTRL_DEV_SLP_MASK				0x02
+#define DEVCTRL_DEV_SLP_SHIFT				1
+#define DEVCTRL_DEV_OFF_MASK				0x01
+#define DEVCTRL_DEV_OFF_SHIFT				0
+
+
+/*Register DEVCTRL2  (0x80) register.RegisterDescription */
+#define DEVCTRL2_TSLOT_LENGTH_MASK			0x30
+#define DEVCTRL2_TSLOT_LENGTH_SHIFT			4
+#define DEVCTRL2_SLEEPSIG_POL_MASK			0x08
+#define DEVCTRL2_SLEEPSIG_POL_SHIFT			3
+#define DEVCTRL2_PWON_LP_OFF_MASK			0x04
+#define DEVCTRL2_PWON_LP_OFF_SHIFT			2
+#define DEVCTRL2_PWON_LP_RST_MASK			0x02
+#define DEVCTRL2_PWON_LP_RST_SHIFT			1
+#define DEVCTRL2_IT_POL_MASK				0x01
+#define DEVCTRL2_IT_POL_SHIFT				0
+
+
+/*Register SLEEP_KEEP_LDO_ON  (0x80) register.RegisterDescription */
+#define SLEEP_KEEP_LDO_ON_VDAC_KEEPON_MASK		0x80
+#define SLEEP_KEEP_LDO_ON_VDAC_KEEPON_SHIFT		7
+#define SLEEP_KEEP_LDO_ON_VPLL_KEEPON_MASK		0x40
+#define SLEEP_KEEP_LDO_ON_VPLL_KEEPON_SHIFT		6
+#define SLEEP_KEEP_LDO_ON_VAUX33_KEEPON_MASK		0x20
+#define SLEEP_KEEP_LDO_ON_VAUX33_KEEPON_SHIFT		5
+#define SLEEP_KEEP_LDO_ON_VAUX2_KEEPON_MASK		0x10
+#define SLEEP_KEEP_LDO_ON_VAUX2_KEEPON_SHIFT		4
+#define SLEEP_KEEP_LDO_ON_VAUX1_KEEPON_MASK		0x08
+#define SLEEP_KEEP_LDO_ON_VAUX1_KEEPON_SHIFT		3
+#define SLEEP_KEEP_LDO_ON_VDIG2_KEEPON_MASK		0x04
+#define SLEEP_KEEP_LDO_ON_VDIG2_KEEPON_SHIFT		2
+#define SLEEP_KEEP_LDO_ON_VDIG1_KEEPON_MASK		0x02
+#define SLEEP_KEEP_LDO_ON_VDIG1_KEEPON_SHIFT		1
+#define SLEEP_KEEP_LDO_ON_VMMC_KEEPON_MASK		0x01
+#define SLEEP_KEEP_LDO_ON_VMMC_KEEPON_SHIFT		0
+
+
+/*Register SLEEP_KEEP_RES_ON  (0x80) register.RegisterDescription */
+#define SLEEP_KEEP_RES_ON_THERM_KEEPON_MASK		0x80
+#define SLEEP_KEEP_RES_ON_THERM_KEEPON_SHIFT		7
+#define SLEEP_KEEP_RES_ON_CLKOUT32K_KEEPON_MASK		0x40
+#define SLEEP_KEEP_RES_ON_CLKOUT32K_KEEPON_SHIFT	6
+#define SLEEP_KEEP_RES_ON_VRTC_KEEPON_MASK		0x20
+#define SLEEP_KEEP_RES_ON_VRTC_KEEPON_SHIFT		5
+#define SLEEP_KEEP_RES_ON_I2CHS_KEEPON_MASK		0x10
+#define SLEEP_KEEP_RES_ON_I2CHS_KEEPON_SHIFT		4
+#define SLEEP_KEEP_RES_ON_VDD3_KEEPON_MASK		0x08
+#define SLEEP_KEEP_RES_ON_VDD3_KEEPON_SHIFT		3
+#define SLEEP_KEEP_RES_ON_VDD2_KEEPON_MASK		0x04
+#define SLEEP_KEEP_RES_ON_VDD2_KEEPON_SHIFT		2
+#define SLEEP_KEEP_RES_ON_VDD1_KEEPON_MASK		0x02
+#define SLEEP_KEEP_RES_ON_VDD1_KEEPON_SHIFT		1
+#define SLEEP_KEEP_RES_ON_VIO_KEEPON_MASK		0x01
+#define SLEEP_KEEP_RES_ON_VIO_KEEPON_SHIFT		0
+
+
+/*Register SLEEP_SET_LDO_OFF  (0x80) register.RegisterDescription */
+#define SLEEP_SET_LDO_OFF_VDAC_SETOFF_MASK		0x80
+#define SLEEP_SET_LDO_OFF_VDAC_SETOFF_SHIFT		7
+#define SLEEP_SET_LDO_OFF_VPLL_SETOFF_MASK		0x40
+#define SLEEP_SET_LDO_OFF_VPLL_SETOFF_SHIFT		6
+#define SLEEP_SET_LDO_OFF_VAUX33_SETOFF_MASK		0x20
+#define SLEEP_SET_LDO_OFF_VAUX33_SETOFF_SHIFT		5
+#define SLEEP_SET_LDO_OFF_VAUX2_SETOFF_MASK		0x10
+#define SLEEP_SET_LDO_OFF_VAUX2_SETOFF_SHIFT		4
+#define SLEEP_SET_LDO_OFF_VAUX1_SETOFF_MASK		0x08
+#define SLEEP_SET_LDO_OFF_VAUX1_SETOFF_SHIFT		3
+#define SLEEP_SET_LDO_OFF_VDIG2_SETOFF_MASK		0x04
+#define SLEEP_SET_LDO_OFF_VDIG2_SETOFF_SHIFT		2
+#define SLEEP_SET_LDO_OFF_VDIG1_SETOFF_MASK		0x02
+#define SLEEP_SET_LDO_OFF_VDIG1_SETOFF_SHIFT		1
+#define SLEEP_SET_LDO_OFF_VMMC_SETOFF_MASK		0x01
+#define SLEEP_SET_LDO_OFF_VMMC_SETOFF_SHIFT		0
+
+
+/*Register SLEEP_SET_RES_OFF  (0x80) register.RegisterDescription */
+#define SLEEP_SET_RES_OFF_DEFAULT_VOLT_MASK		0x80
+#define SLEEP_SET_RES_OFF_DEFAULT_VOLT_SHIFT		7
+#define SLEEP_SET_RES_OFF_RSVD_MASK			0x60
+#define SLEEP_SET_RES_OFF_RSVD_SHIFT			5
+#define SLEEP_SET_RES_OFF_SPARE_SETOFF_MASK		0x10
+#define SLEEP_SET_RES_OFF_SPARE_SETOFF_SHIFT		4
+#define SLEEP_SET_RES_OFF_VDD3_SETOFF_MASK		0x08
+#define SLEEP_SET_RES_OFF_VDD3_SETOFF_SHIFT		3
+#define SLEEP_SET_RES_OFF_VDD2_SETOFF_MASK		0x04
+#define SLEEP_SET_RES_OFF_VDD2_SETOFF_SHIFT		2
+#define SLEEP_SET_RES_OFF_VDD1_SETOFF_MASK		0x02
+#define SLEEP_SET_RES_OFF_VDD1_SETOFF_SHIFT		1
+#define SLEEP_SET_RES_OFF_VIO_SETOFF_MASK		0x01
+#define SLEEP_SET_RES_OFF_VIO_SETOFF_SHIFT		0
+
+
+/*Register EN1_LDO_ASS	(0x80) register.RegisterDescription */
+#define EN1_LDO_ASS_VDAC_EN1_MASK			0x80
+#define EN1_LDO_ASS_VDAC_EN1_SHIFT			7
+#define EN1_LDO_ASS_VPLL_EN1_MASK			0x40
+#define EN1_LDO_ASS_VPLL_EN1_SHIFT			6
+#define EN1_LDO_ASS_VAUX33_EN1_MASK			0x20
+#define EN1_LDO_ASS_VAUX33_EN1_SHIFT			5
+#define EN1_LDO_ASS_VAUX2_EN1_MASK			0x10
+#define EN1_LDO_ASS_VAUX2_EN1_SHIFT			4
+#define EN1_LDO_ASS_VAUX1_EN1_MASK			0x08
+#define EN1_LDO_ASS_VAUX1_EN1_SHIFT			3
+#define EN1_LDO_ASS_VDIG2_EN1_MASK			0x04
+#define EN1_LDO_ASS_VDIG2_EN1_SHIFT			2
+#define EN1_LDO_ASS_VDIG1_EN1_MASK			0x02
+#define EN1_LDO_ASS_VDIG1_EN1_SHIFT			1
+#define EN1_LDO_ASS_VMMC_EN1_MASK			0x01
+#define EN1_LDO_ASS_VMMC_EN1_SHIFT			0
+
+
+/*Register EN1_SMPS_ASS  (0x80) register.RegisterDescription */
+#define EN1_SMPS_ASS_RSVD_MASK				0xE0
+#define EN1_SMPS_ASS_RSVD_SHIFT				5
+#define EN1_SMPS_ASS_SPARE_EN1_MASK			0x10
+#define EN1_SMPS_ASS_SPARE_EN1_SHIFT			4
+#define EN1_SMPS_ASS_VDD3_EN1_MASK			0x08
+#define EN1_SMPS_ASS_VDD3_EN1_SHIFT			3
+#define EN1_SMPS_ASS_VDD2_EN1_MASK			0x04
+#define EN1_SMPS_ASS_VDD2_EN1_SHIFT			2
+#define EN1_SMPS_ASS_VDD1_EN1_MASK			0x02
+#define EN1_SMPS_ASS_VDD1_EN1_SHIFT			1
+#define EN1_SMPS_ASS_VIO_EN1_MASK			0x01
+#define EN1_SMPS_ASS_VIO_EN1_SHIFT			0
+
+
+/*Register EN2_LDO_ASS	(0x80) register.RegisterDescription */
+#define EN2_LDO_ASS_VDAC_EN2_MASK			0x80
+#define EN2_LDO_ASS_VDAC_EN2_SHIFT			7
+#define EN2_LDO_ASS_VPLL_EN2_MASK			0x40
+#define EN2_LDO_ASS_VPLL_EN2_SHIFT			6
+#define EN2_LDO_ASS_VAUX33_EN2_MASK			0x20
+#define EN2_LDO_ASS_VAUX33_EN2_SHIFT			5
+#define EN2_LDO_ASS_VAUX2_EN2_MASK			0x10
+#define EN2_LDO_ASS_VAUX2_EN2_SHIFT			4
+#define EN2_LDO_ASS_VAUX1_EN2_MASK			0x08
+#define EN2_LDO_ASS_VAUX1_EN2_SHIFT			3
+#define EN2_LDO_ASS_VDIG2_EN2_MASK			0x04
+#define EN2_LDO_ASS_VDIG2_EN2_SHIFT			2
+#define EN2_LDO_ASS_VDIG1_EN2_MASK			0x02
+#define EN2_LDO_ASS_VDIG1_EN2_SHIFT			1
+#define EN2_LDO_ASS_VMMC_EN2_MASK			0x01
+#define EN2_LDO_ASS_VMMC_EN2_SHIFT			0
+
+
+/*Register EN2_SMPS_ASS  (0x80) register.RegisterDescription */
+#define EN2_SMPS_ASS_RSVD_MASK				0xE0
+#define EN2_SMPS_ASS_RSVD_SHIFT				5
+#define EN2_SMPS_ASS_SPARE_EN2_MASK			0x10
+#define EN2_SMPS_ASS_SPARE_EN2_SHIFT			4
+#define EN2_SMPS_ASS_VDD3_EN2_MASK			0x08
+#define EN2_SMPS_ASS_VDD3_EN2_SHIFT			3
+#define EN2_SMPS_ASS_VDD2_EN2_MASK			0x04
+#define EN2_SMPS_ASS_VDD2_EN2_SHIFT			2
+#define EN2_SMPS_ASS_VDD1_EN2_MASK			0x02
+#define EN2_SMPS_ASS_VDD1_EN2_SHIFT			1
+#define EN2_SMPS_ASS_VIO_EN2_MASK			0x01
+#define EN2_SMPS_ASS_VIO_EN2_SHIFT			0
+
+
+/*Register EN3_LDO_ASS	(0x80) register.RegisterDescription */
+#define EN3_LDO_ASS_VDAC_EN3_MASK			0x80
+#define EN3_LDO_ASS_VDAC_EN3_SHIFT			7
+#define EN3_LDO_ASS_VPLL_EN3_MASK			0x40
+#define EN3_LDO_ASS_VPLL_EN3_SHIFT			6
+#define EN3_LDO_ASS_VAUX33_EN3_MASK			0x20
+#define EN3_LDO_ASS_VAUX33_EN3_SHIFT			5
+#define EN3_LDO_ASS_VAUX2_EN3_MASK			0x10
+#define EN3_LDO_ASS_VAUX2_EN3_SHIFT			4
+#define EN3_LDO_ASS_VAUX1_EN3_MASK			0x08
+#define EN3_LDO_ASS_VAUX1_EN3_SHIFT			3
+#define EN3_LDO_ASS_VDIG2_EN3_MASK			0x04
+#define EN3_LDO_ASS_VDIG2_EN3_SHIFT			2
+#define EN3_LDO_ASS_VDIG1_EN3_MASK			0x02
+#define EN3_LDO_ASS_VDIG1_EN3_SHIFT			1
+#define EN3_LDO_ASS_VMMC_EN3_MASK			0x01
+#define EN3_LDO_ASS_VMMC_EN3_SHIFT			0
+
+
+/*Register SPARE  (0x80) register.RegisterDescription */
+#define SPARE_SPARE_MASK				0xFF
+#define SPARE_SPARE_SHIFT				0
+
+
+/*Register INT_STS  (0x80) register.RegisterDescription */
+#define INT_STS_RTC_PERIOD_IT_MASK			0x80
+#define INT_STS_RTC_PERIOD_IT_SHIFT			7
+#define INT_STS_RTC_ALARM_IT_MASK			0x40
+#define INT_STS_RTC_ALARM_IT_SHIFT			6
+#define INT_STS_HOTDIE_IT_MASK				0x20
+#define INT_STS_HOTDIE_IT_SHIFT				5
+#define INT_STS_PWRHOLD_IT_MASK				0x10
+#define INT_STS_PWRHOLD_IT_SHIFT			4
+#define INT_STS_PWRON_LP_IT_MASK			0x08
+#define INT_STS_PWRON_LP_IT_SHIFT			3
+#define INT_STS_PWRON_IT_MASK				0x04
+#define INT_STS_PWRON_IT_SHIFT				2
+#define INT_STS_VMBHI_IT_MASK				0x02
+#define INT_STS_VMBHI_IT_SHIFT				1
+#define INT_STS_VMBDCH_IT_MASK				0x01
+#define INT_STS_VMBDCH_IT_SHIFT				0
+
+
+/*Register INT_MSK  (0x80) register.RegisterDescription */
+#define INT_MSK_RTC_PERIOD_IT_MSK_MASK			0x80
+#define INT_MSK_RTC_PERIOD_IT_MSK_SHIFT			7
+#define INT_MSK_RTC_ALARM_IT_MSK_MASK			0x40
+#define INT_MSK_RTC_ALARM_IT_MSK_SHIFT			6
+#define INT_MSK_HOTDIE_IT_MSK_MASK			0x20
+#define INT_MSK_HOTDIE_IT_MSK_SHIFT			5
+#define INT_MSK_PWRHOLD_IT_MSK_MASK			0x10
+#define INT_MSK_PWRHOLD_IT_MSK_SHIFT			4
+#define INT_MSK_PWRON_LP_IT_MSK_MASK			0x08
+#define INT_MSK_PWRON_LP_IT_MSK_SHIFT			3
+#define INT_MSK_PWRON_IT_MSK_MASK			0x04
+#define INT_MSK_PWRON_IT_MSK_SHIFT			2
+#define INT_MSK_VMBHI_IT_MSK_MASK			0x02
+#define INT_MSK_VMBHI_IT_MSK_SHIFT			1
+#define INT_MSK_VMBDCH_IT_MSK_MASK			0x01
+#define INT_MSK_VMBDCH_IT_MSK_SHIFT			0
+
+
+/*Register INT_STS2  (0x80) register.RegisterDescription */
+#define INT_STS2_GPIO3_F_IT_MASK			0x80
+#define INT_STS2_GPIO3_F_IT_SHIFT			7
+#define INT_STS2_GPIO3_R_IT_MASK			0x40
+#define INT_STS2_GPIO3_R_IT_SHIFT			6
+#define INT_STS2_GPIO2_F_IT_MASK			0x20
+#define INT_STS2_GPIO2_F_IT_SHIFT			5
+#define INT_STS2_GPIO2_R_IT_MASK			0x10
+#define INT_STS2_GPIO2_R_IT_SHIFT			4
+#define INT_STS2_GPIO1_F_IT_MASK			0x08
+#define INT_STS2_GPIO1_F_IT_SHIFT			3
+#define INT_STS2_GPIO1_R_IT_MASK			0x04
+#define INT_STS2_GPIO1_R_IT_SHIFT			2
+#define INT_STS2_GPIO0_F_IT_MASK			0x02
+#define INT_STS2_GPIO0_F_IT_SHIFT			1
+#define INT_STS2_GPIO0_R_IT_MASK			0x01
+#define INT_STS2_GPIO0_R_IT_SHIFT			0
+
+
+/*Register INT_MSK2  (0x80) register.RegisterDescription */
+#define INT_MSK2_GPIO3_F_IT_MSK_MASK			0x80
+#define INT_MSK2_GPIO3_F_IT_MSK_SHIFT			7
+#define INT_MSK2_GPIO3_R_IT_MSK_MASK			0x40
+#define INT_MSK2_GPIO3_R_IT_MSK_SHIFT			6
+#define INT_MSK2_GPIO2_F_IT_MSK_MASK			0x20
+#define INT_MSK2_GPIO2_F_IT_MSK_SHIFT			5
+#define INT_MSK2_GPIO2_R_IT_MSK_MASK			0x10
+#define INT_MSK2_GPIO2_R_IT_MSK_SHIFT			4
+#define INT_MSK2_GPIO1_F_IT_MSK_MASK			0x08
+#define INT_MSK2_GPIO1_F_IT_MSK_SHIFT			3
+#define INT_MSK2_GPIO1_R_IT_MSK_MASK			0x04
+#define INT_MSK2_GPIO1_R_IT_MSK_SHIFT			2
+#define INT_MSK2_GPIO0_F_IT_MSK_MASK			0x02
+#define INT_MSK2_GPIO0_F_IT_MSK_SHIFT			1
+#define INT_MSK2_GPIO0_R_IT_MSK_MASK			0x01
+#define INT_MSK2_GPIO0_R_IT_MSK_SHIFT			0
+
+
+/*Register INT_STS3  (0x80) register.RegisterDescription */
+#define INT_STS3_GPIO5_F_IT_MASK			0x08
+#define INT_STS3_GPIO5_F_IT_SHIFT			3
+#define INT_STS3_GPIO5_R_IT_MASK			0x04
+#define INT_STS3_GPIO5_R_IT_SHIFT			2
+#define INT_STS3_GPIO4_F_IT_MASK			0x02
+#define INT_STS3_GPIO4_F_IT_SHIFT			1
+#define INT_STS3_GPIO4_R_IT_MASK			0x01
+#define INT_STS3_GPIO4_R_IT_SHIFT			0
+
+
+/*Register INT_MSK3  (0x80) register.RegisterDescription */
+#define INT_MSK3_GPIO5_F_IT_MSK_MASK			0x08
+#define INT_MSK3_GPIO5_F_IT_MSK_SHIFT			3
+#define INT_MSK3_GPIO5_R_IT_MSK_MASK			0x04
+#define INT_MSK3_GPIO5_R_IT_MSK_SHIFT			2
+#define INT_MSK3_GPIO4_F_IT_MSK_MASK			0x02
+#define INT_MSK3_GPIO4_F_IT_MSK_SHIFT			1
+#define INT_MSK3_GPIO4_R_IT_MSK_MASK			0x01
+#define INT_MSK3_GPIO4_R_IT_MSK_SHIFT			0
+
+
+/*Register GPIO  (0x80) register.RegisterDescription */
+#define GPIO_DEB_MASK                           0x10
+#define GPIO_DEB_SHIFT                          4
+#define GPIO_PUEN_MASK                          0x08
+#define GPIO_PUEN_SHIFT                         3
+#define GPIO_CFG_MASK                           0x04
+#define GPIO_CFG_SHIFT                          2
+#define GPIO_STS_MASK                           0x02
+#define GPIO_STS_SHIFT                          1
+#define GPIO_SET_MASK                           0x01
+#define GPIO_SET_SHIFT                          0
+
+
+/*Register JTAGVERNUM  (0x80) register.RegisterDescription */
+#define JTAGVERNUM_VERNUM_MASK				0x0F
+#define JTAGVERNUM_VERNUM_SHIFT				0
+
+
+/* Register VDDCTRL (0x27) bit definitions */
+#define VDDCTRL_ST_MASK                                  0x03
+#define VDDCTRL_ST_SHIFT                                 0
+
+
+/*Register VDDCTRL_OP  (0x28) bit definitios */
+#define VDDCTRL_OP_CMD_MASK                              0x80
+#define VDDCTRL_OP_CMD_SHIFT                             7
+#define VDDCTRL_OP_SEL_MASK                              0x7F
+#define VDDCTRL_OP_SEL_SHIFT                             0
+
+
+/*Register VDDCTRL_SR  (0x29) bit definitions */
+#define VDDCTRL_SR_SEL_MASK                              0x7F
+#define VDDCTRL_SR_SEL_SHIFT                             0
+
+
+/* IRQ Definitions */
+#define TPS65910_IRQ_VBAT_VMBDCH			0
+#define TPS65910_IRQ_VBAT_VMHI				1
+#define TPS65910_IRQ_PWRON				2
+#define TPS65910_IRQ_PWRON_LP				3
+#define TPS65910_IRQ_PWRHOLD				4
+#define TPS65910_IRQ_HOTDIE				5
+#define TPS65910_IRQ_RTC_ALARM				6
+#define TPS65910_IRQ_RTC_PERIOD				7
+#define TPS65910_IRQ_GPIO_R				8
+#define TPS65910_IRQ_GPIO_F				9
+#define TPS65910_NUM_IRQ				10
+
+#define TPS65911_IRQ_VBAT_VMBDCH			0
+#define TPS65911_IRQ_VBAT_VMBDCH2L			1
+#define TPS65911_IRQ_VBAT_VMBDCH2H			2
+#define TPS65911_IRQ_VBAT_VMHI				3
+#define TPS65911_IRQ_PWRON				4
+#define TPS65911_IRQ_PWRON_LP				5
+#define TPS65911_IRQ_PWRHOLD_F				6
+#define TPS65911_IRQ_PWRHOLD_R				7
+#define TPS65911_IRQ_HOTDIE				8
+#define TPS65911_IRQ_RTC_ALARM				9
+#define TPS65911_IRQ_RTC_PERIOD				10
+#define TPS65911_IRQ_GPIO0_R				11
+#define TPS65911_IRQ_GPIO0_F				12
+#define TPS65911_IRQ_GPIO1_R				13
+#define TPS65911_IRQ_GPIO1_F				14
+#define TPS65911_IRQ_GPIO2_R				15
+#define TPS65911_IRQ_GPIO2_F				16
+#define TPS65911_IRQ_GPIO3_R				17
+#define TPS65911_IRQ_GPIO3_F				18
+#define TPS65911_IRQ_GPIO4_R				19
+#define TPS65911_IRQ_GPIO4_F				20
+#define TPS65911_IRQ_GPIO5_R				21
+#define TPS65911_IRQ_GPIO5_F				22
+#define TPS65911_IRQ_WTCHDG				23
+#define TPS65911_IRQ_PWRDN				24
+
+#define TPS65911_NUM_IRQ				25
+
+
+/* GPIO Register Definitions */
+#define TPS65910_GPIO_DEB				BIT(2)
+#define TPS65910_GPIO_PUEN				BIT(3)
+#define TPS65910_GPIO_CFG				BIT(2)
+#define TPS65910_GPIO_STS				BIT(1)
+#define TPS65910_GPIO_SET				BIT(0)
+
+/**
+ * struct tps65910_board
+ * Board platform data may be used to initialize regulators.
+ */
+
+struct tps65910_board {
+	int gpio_base;
+	int irq;
+	int irq_base;
+	int vmbch_threshold;
+	int vmbch2_threshold;
+	struct regulator_init_data *tps65910_pmic_init_data;
+};
+
+/**
+ * struct tps65910 - tps65910 sub-driver chip access routines
+ */
+
+struct tps65910 {
+	struct device *dev;
+	struct i2c_client *i2c_client;
+	struct mutex io_mutex;
+	unsigned int id;
+	int (*read)(struct tps65910 *tps65910, u8 reg, int size, void *dest);
+	int (*write)(struct tps65910 *tps65910, u8 reg, int size, void *src);
+
+	/* Client devices */
+	struct tps65910_pmic *pmic;
+	struct tps65910_rtc *rtc;
+	struct tps65910_power *power;
+
+	/* GPIO Handling */
+	struct gpio_chip gpio;
+
+	/* IRQ Handling */
+	struct mutex irq_lock;
+	int chip_irq;
+	int irq_base;
+	int irq_num;
+	u32 irq_mask;
+};
+
+struct tps65910_platform_data {
+	int irq;
+	int irq_base;
+};
+
+int tps65910_set_bits(struct tps65910 *tps65910, u8 reg, u8 mask);
+int tps65910_clear_bits(struct tps65910 *tps65910, u8 reg, u8 mask);
+void tps65910_gpio_init(struct tps65910 *tps65910, int gpio_base);
+int tps65910_irq_init(struct tps65910 *tps65910, int irq,
+		struct tps65910_platform_data *pdata);
+
+static inline int tps65910_chip_id(struct tps65910 *tps65910)
+{
+	return tps65910->id;
+}
+
+#endif /*  __LINUX_MFD_TPS65910_H */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 2a78aae78c69..027935c86c68 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -264,6 +264,8 @@ struct mm_struct {
 
 	struct linux_binfmt *binfmt;
 
+	cpumask_var_t cpu_vm_mask_var;
+
 	/* Architecture-specific MM context */
 	mm_context_t context;
 
@@ -311,10 +313,18 @@ struct mm_struct {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	pgtable_t pmd_huge_pte; /* protected by page_table_lock */
 #endif
-
-	cpumask_var_t cpu_vm_mask_var;
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	struct cpumask cpumask_allocation;
+#endif
 };
 
+static inline void mm_init_cpumask(struct mm_struct *mm)
+{
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	mm->cpu_vm_mask_var = &mm->cpumask_allocation;
+#endif
+}
+
 /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
 static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
 {
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 29312bdf119f..9f7c3ebcbbad 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -647,6 +647,13 @@ typedef struct pglist_data {
 #endif
 #define nid_page_nr(nid, pagenr) 	pgdat_page_nr(NODE_DATA(nid),(pagenr))
 
+#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
+
+#define node_end_pfn(nid) ({\
+	pg_data_t *__pgdat = NODE_DATA(nid);\
+	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;\
+})
+
 #include <linux/memory_hotplug.h>
 
 extern struct mutex zonelists_mutex;
@@ -1051,12 +1058,14 @@ static inline struct mem_section *__pfn_to_section(unsigned long pfn)
 	return __nr_to_section(pfn_to_section_nr(pfn));
 }
 
+#ifndef CONFIG_HAVE_ARCH_PFN_VALID
 static inline int pfn_valid(unsigned long pfn)
 {
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
 	return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
 }
+#endif
 
 static inline int pfn_present(unsigned long pfn)
 {
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index 9d5306bad117..2541fb848daa 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -322,9 +322,12 @@ static inline uint32_t mtd_mod_by_ws(uint64_t sz, struct mtd_info *mtd)
 
 	/* Kernel-side ioctl definitions */
 
-extern int add_mtd_device(struct mtd_info *mtd);
-extern int del_mtd_device (struct mtd_info *mtd);
+struct mtd_partition;
 
+extern int mtd_device_register(struct mtd_info *master,
+			       const struct mtd_partition *parts,
+			       int nr_parts);
+extern int mtd_device_unregister(struct mtd_info *master);
 extern struct mtd_info *get_mtd_device(struct mtd_info *mtd, int num);
 extern int __get_mtd_device(struct mtd_info *mtd);
 extern void __put_mtd_device(struct mtd_info *mtd);
@@ -348,15 +351,9 @@ int default_mtd_writev(struct mtd_info *mtd, const struct kvec *vecs,
 int default_mtd_readv(struct mtd_info *mtd, struct kvec *vecs,
 		      unsigned long count, loff_t from, size_t *retlen);
 
-#ifdef CONFIG_MTD_PARTITIONS
+void *mtd_kmalloc_up_to(const struct mtd_info *mtd, size_t *size);
+
 void mtd_erase_callback(struct erase_info *instr);
-#else
-static inline void mtd_erase_callback(struct erase_info *instr)
-{
-	if (instr->callback)
-		instr->callback(instr);
-}
-#endif
 
 /*
  * Debugging macro and defines
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index d44192740f6f..c2b9ac4fbc4a 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -237,9 +237,9 @@ typedef enum {
  * If passed additionally to NAND_USE_FLASH_BBT then BBT code will not touch
  * the OOB area.
  */
-#define NAND_USE_FLASH_BBT_NO_OOB	0x00100000
+#define NAND_USE_FLASH_BBT_NO_OOB	0x00800000
 /* Create an empty BBT with no vendor information if the BBT is available */
-#define NAND_CREATE_EMPTY_BBT		0x00200000
+#define NAND_CREATE_EMPTY_BBT		0x01000000
 
 /* Options set by nand scan */
 /* Nand scan has allocated controller struct */
diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h
index 4a0a8ba90a72..3a6f0372fc96 100644
--- a/include/linux/mtd/partitions.h
+++ b/include/linux/mtd/partitions.h
@@ -16,7 +16,7 @@
  * Partition definition structure:
  *
  * An array of struct partition is passed along with a MTD object to
- * add_mtd_partitions() to create them.
+ * mtd_device_register() to create them.
  *
  * For each partition, these fields are available:
  * name: string that will be used to label the partition's MTD device.
@@ -49,9 +49,6 @@ struct mtd_partition {
 
 struct mtd_info;
 
-int add_mtd_partitions(struct mtd_info *, const struct mtd_partition *, int);
-int del_mtd_partitions(struct mtd_info *);
-
 /*
  * Functions dealing with the various ways of partitioning the space
  */
@@ -73,14 +70,17 @@ extern int parse_mtd_partitions(struct mtd_info *master, const char **types,
 struct device;
 struct device_node;
 
+#ifdef CONFIG_MTD_OF_PARTS
 int __devinit of_mtd_parse_partitions(struct device *dev,
                                       struct device_node *node,
                                       struct mtd_partition **pparts);
-
-#ifdef CONFIG_MTD_PARTITIONS
-static inline int mtd_has_partitions(void) { return 1; }
 #else
-static inline int mtd_has_partitions(void) { return 0; }
+static inline int of_mtd_parse_partitions(struct device *dev,
+					  struct device_node *node,
+					  struct mtd_partition **pparts)
+{
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_MTD_CMDLINE_PARTS
diff --git a/include/linux/mtd/physmap.h b/include/linux/mtd/physmap.h
index 49b959029417..e5f21d293c70 100644
--- a/include/linux/mtd/physmap.h
+++ b/include/linux/mtd/physmap.h
@@ -19,6 +19,7 @@
 #include <linux/mtd/partitions.h>
 
 struct map_info;
+struct platform_device;
 
 struct physmap_flash_data {
 	unsigned int		width;
@@ -37,8 +38,6 @@ struct physmap_flash_data {
 void physmap_configure(unsigned long addr, unsigned long size,
 		int bankwidth, void (*set_vpp)(struct map_info *, int) );
 
-#ifdef CONFIG_MTD_PARTITIONS
-
 /*
  * Machines that wish to do flash partition may want to call this function in
  * their setup routine.
@@ -50,6 +49,4 @@ void physmap_configure(unsigned long addr, unsigned long size,
  */
 void physmap_set_partitions(struct mtd_partition *parts, int num_parts);
 
-#endif /* defined(CONFIG_MTD_PARTITIONS) */
-
 #endif /* __LINUX_MTD_PHYSMAP__ */
diff --git a/include/linux/net.h b/include/linux/net.h
index 1da55e9b6f01..b29923006b11 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -289,11 +289,5 @@ extern int kernel_sock_shutdown(struct socket *sock,
 	MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto) \
 		     "-type-" __stringify(type))
 
-#ifdef CONFIG_SYSCTL
-#include <linux/sysctl.h>
-#include <linux/ratelimit.h>
-extern struct ratelimit_state net_ratelimit_state;
-#endif
-
 #endif /* __KERNEL__ */
 #endif	/* _LINUX_NET_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ca333e79e10f..54b8b4d7b68f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2555,7 +2555,7 @@ extern void netdev_class_remove_file(struct class_attribute *class_attr);
 
 extern struct kobj_ns_type_operations net_ns_type_operations;
 
-extern char *netdev_drivername(const struct net_device *dev, char *buffer, int len);
+extern const char *netdev_drivername(const struct net_device *dev);
 
 extern void linkwatch_run_queue(void);
 
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 7fa95df60146..857f5026ced6 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -13,6 +13,7 @@
 #endif
 #include <linux/types.h>
 #include <linux/compiler.h>
+#include <linux/sysctl.h>
 
 /* Responses from hook functions. */
 #define NF_DROP 0
diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h
index a0196ac79051..ac3c822eb39a 100644
--- a/include/linux/netfilter/ipset/ip_set_ahash.h
+++ b/include/linux/netfilter/ipset/ip_set_ahash.h
@@ -839,7 +839,7 @@ type_pf_tdel(struct ip_set *set, void *value, u32 timeout)
 	struct htable *t = h->table;
 	const struct type_pf_elem *d = value;
 	struct hbucket *n;
-	int i, ret = 0;
+	int i;
 	struct type_pf_elem *data;
 	u32 key;
 
@@ -850,7 +850,7 @@ type_pf_tdel(struct ip_set *set, void *value, u32 timeout)
 		if (!type_pf_data_equal(data, d))
 			continue;
 		if (type_pf_data_expired(data))
-			ret = -IPSET_ERR_EXIST;
+			return -IPSET_ERR_EXIST;
 		if (i != n->pos - 1)
 			/* Not last one */
 			type_pf_data_copy(data, ahash_tdata(n, n->pos - 1));
diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h
index 9f30c5f2ec1c..bcdd40ad39ed 100644
--- a/include/linux/netfilter/ipset/ip_set_timeout.h
+++ b/include/linux/netfilter/ipset/ip_set_timeout.h
@@ -45,7 +45,7 @@ ip_set_timeout_test(unsigned long timeout)
 {
 	return timeout != IPSET_ELEM_UNSET &&
 	       (timeout == IPSET_ELEM_PERMANENT ||
-		time_after(timeout, jiffies));
+		time_is_after_jiffies(timeout));
 }
 
 static inline bool
@@ -53,7 +53,7 @@ ip_set_timeout_expired(unsigned long timeout)
 {
 	return timeout != IPSET_ELEM_UNSET &&
 	       timeout != IPSET_ELEM_PERMANENT &&
-	       time_before(timeout, jiffies);
+	       time_is_before_jiffies(timeout);
 }
 
 static inline unsigned long
@@ -64,7 +64,7 @@ ip_set_timeout_set(u32 timeout)
 	if (!timeout)
 		return IPSET_ELEM_PERMANENT;
 
-	t = timeout * HZ + jiffies;
+	t = msecs_to_jiffies(timeout * 1000) + jiffies;
 	if (t == IPSET_ELEM_UNSET || t == IPSET_ELEM_PERMANENT)
 		/* Bingo! */
 		t++;
@@ -75,7 +75,8 @@ ip_set_timeout_set(u32 timeout)
 static inline u32
 ip_set_timeout_get(unsigned long timeout)
 {
-	return timeout == IPSET_ELEM_PERMANENT ? 0 : (timeout - jiffies)/HZ;
+	return timeout == IPSET_ELEM_PERMANENT ? 0 : 
+		jiffies_to_msecs(timeout - jiffies)/1000;
 }
 
 #else
@@ -89,14 +90,14 @@ static inline bool
 ip_set_timeout_test(unsigned long timeout)
 {
 	return timeout == IPSET_ELEM_PERMANENT ||
-	       time_after(timeout, jiffies);
+	       time_is_after_jiffies(timeout);
 }
 
 static inline bool
 ip_set_timeout_expired(unsigned long timeout)
 {
 	return timeout != IPSET_ELEM_PERMANENT &&
-	       time_before(timeout, jiffies);
+	       time_is_before_jiffies(timeout);
 }
 
 static inline unsigned long
@@ -107,7 +108,7 @@ ip_set_timeout_set(u32 timeout)
 	if (!timeout)
 		return IPSET_ELEM_PERMANENT;
 
-	t = timeout * HZ + jiffies;
+	t = msecs_to_jiffies(timeout * 1000) + jiffies;
 	if (t == IPSET_ELEM_PERMANENT)
 		/* Bingo! :-) */
 		t++;
@@ -118,7 +119,8 @@ ip_set_timeout_set(u32 timeout)
 static inline u32
 ip_set_timeout_get(unsigned long timeout)
 {
-	return timeout == IPSET_ELEM_PERMANENT ? 0 : (timeout - jiffies)/HZ;
+	return timeout == IPSET_ELEM_PERMANENT ? 0 :
+		jiffies_to_msecs(timeout - jiffies)/1000;
 }
 #endif /* ! IP_SET_BITMAP_TIMEOUT */
 
diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h
index 50cdc2559a5a..0d3dd66322ec 100644
--- a/include/linux/netfilter/nf_conntrack_common.h
+++ b/include/linux/netfilter/nf_conntrack_common.h
@@ -18,6 +18,9 @@ enum ip_conntrack_info {
 	/* >= this indicates reply direction */
 	IP_CT_IS_REPLY,
 
+	IP_CT_ESTABLISHED_REPLY = IP_CT_ESTABLISHED + IP_CT_IS_REPLY,
+	IP_CT_RELATED_REPLY = IP_CT_RELATED + IP_CT_IS_REPLY,
+	IP_CT_NEW_REPLY = IP_CT_NEW + IP_CT_IS_REPLY,	
 	/* Number of distinct IP_CT types (no NEW in reply dirn). */
 	IP_CT_NUMBER = IP_CT_IS_REPLY * 2 - 1
 };
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 178fafe0ff93..504b289ba680 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -562,6 +562,7 @@ enum {
 	NFSPROC4_CLNT_LAYOUTGET,
 	NFSPROC4_CLNT_GETDEVICEINFO,
 	NFSPROC4_CLNT_LAYOUTCOMMIT,
+	NFSPROC4_CLNT_LAYOUTRETURN,
 };
 
 /* nfs41 types */
@@ -570,9 +571,11 @@ struct nfs4_sessionid {
 };
 
 /* Create Session Flags */
-#define SESSION4_PERSIST	 0x001
-#define SESSION4_BACK_CHAN 	 0x002
-#define SESSION4_RDMA		 0x004
+#define SESSION4_PERSIST	0x001
+#define SESSION4_BACK_CHAN	0x002
+#define SESSION4_RDMA		0x004
+
+#define SESSION4_FLAG_MASK_A	0x007
 
 enum state_protect_how4 {
 	SP4_NONE	= 0,
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index 91af2e49fa3a..25311b3bedf8 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -68,7 +68,7 @@ struct nfs_pageio_descriptor {
 	int 			pg_ioflags;
 	int			pg_error;
 	struct pnfs_layout_segment *pg_lseg;
-	int			(*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *);
+	bool			(*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *);
 };
 
 #define NFS_WBACK_BUSY(req)	(test_bit(PG_BUSY,&(req)->wb_flags))
@@ -92,6 +92,9 @@ extern	int nfs_pageio_add_request(struct nfs_pageio_descriptor *,
 				   struct nfs_page *);
 extern	void nfs_pageio_complete(struct nfs_pageio_descriptor *desc);
 extern	void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *, pgoff_t);
+extern bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
+				struct nfs_page *prev,
+				struct nfs_page *req);
 extern  int nfs_wait_on_request(struct nfs_page *);
 extern	void nfs_unlock_request(struct nfs_page *req);
 extern	int nfs_set_page_tag_locked(struct nfs_page *req);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 7e371f7df9c4..00848d86ffb2 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -158,7 +158,6 @@ struct nfs_seqid;
 
 /* nfs41 sessions channel attributes */
 struct nfs4_channel_attrs {
-	u32			headerpadsz;
 	u32			max_rqst_sz;
 	u32			max_resp_sz;
 	u32			max_resp_sz_cached;
@@ -269,6 +268,27 @@ struct nfs4_layoutcommit_data {
 	struct nfs4_layoutcommit_res res;
 };
 
+struct nfs4_layoutreturn_args {
+	__u32   layout_type;
+	struct inode *inode;
+	nfs4_stateid stateid;
+	struct nfs4_sequence_args seq_args;
+};
+
+struct nfs4_layoutreturn_res {
+	struct nfs4_sequence_res seq_res;
+	u32 lrs_present;
+	nfs4_stateid stateid;
+};
+
+struct nfs4_layoutreturn {
+	struct nfs4_layoutreturn_args args;
+	struct nfs4_layoutreturn_res res;
+	struct rpc_cred *cred;
+	struct nfs_client *clp;
+	int rpc_status;
+};
+
 /*
  * Arguments to the open call.
  */
@@ -1087,6 +1107,7 @@ struct nfs_read_data {
 	const struct rpc_call_ops *mds_ops;
 	int (*read_done_cb) (struct rpc_task *task, struct nfs_read_data *data);
 	__u64			mds_offset;
+	int			pnfs_error;
 	struct page		*page_array[NFS_PAGEVEC_SIZE];
 };
 
@@ -1112,6 +1133,7 @@ struct nfs_write_data {
 	unsigned long		timestamp;	/* For lease renewal */
 #endif
 	__u64			mds_offset;	/* Filelayout dense stripe */
+	int			pnfs_error;
 	struct page		*page_array[NFS_PAGEVEC_SIZE];
 };
 
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 79a6700b7162..6081493db68f 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -308,7 +308,7 @@ static inline void SetPageUptodate(struct page *page)
 {
 #ifdef CONFIG_S390
 	if (!test_and_set_bit(PG_uptodate, &page->flags))
-		page_set_storage_key(page_to_pfn(page), PAGE_DEFAULT_KEY, 0);
+		page_set_storage_key(page_to_phys(page), PAGE_DEFAULT_KEY, 0);
 #else
 	/*
 	 * Memory barrier must be issued before setting the PG_uptodate bit,
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 24787b751286..f8910e155566 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -1537,6 +1537,7 @@
 #define PCI_DEVICE_ID_RICOH_RL5C476	0x0476
 #define PCI_DEVICE_ID_RICOH_RL5C478	0x0478
 #define PCI_DEVICE_ID_RICOH_R5C822	0x0822
+#define PCI_DEVICE_ID_RICOH_R5CE823	0xe823
 #define PCI_DEVICE_ID_RICOH_R5C832	0x0832
 #define PCI_DEVICE_ID_RICOH_R5C843	0x0843
 
@@ -2483,6 +2484,7 @@
 #define PCI_DEVICE_ID_INTEL_COUGARPOINT_LPC_MAX	0x1c5f
 #define PCI_DEVICE_ID_INTEL_PATSBURG_LPC_0	0x1d40
 #define PCI_DEVICE_ID_INTEL_PATSBURG_LPC_1	0x1d41
+#define PCI_DEVICE_ID_INTEL_PANTHERPOINT_XHCI	0x1e31
 #define PCI_DEVICE_ID_INTEL_PANTHERPOINT_LPC_MIN	0x1e40
 #define PCI_DEVICE_ID_INTEL_PANTHERPOINT_LPC_MAX	0x1e5f
 #define PCI_DEVICE_ID_INTEL_DH89XXCC_LPC_MIN	0x2310
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 8b97308e65df..9ca008f0c542 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -259,6 +259,9 @@ extern void __bad_size_call_parameter(void);
  * Special handling for cmpxchg_double.  cmpxchg_double is passed two
  * percpu variables.  The first has to be aligned to a double word
  * boundary and the second has to follow directly thereafter.
+ * We enforce this on all architectures even if they don't support
+ * a double cmpxchg instruction, since it's a cheap requirement, and it
+ * avoids breaking the requirement for architectures with the instruction.
  */
 #define __pcpu_double_call_return_bool(stem, pcp1, pcp2, ...)		\
 ({									\
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3412684ce5d5..e0786e35f247 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -137,14 +137,14 @@ enum perf_event_sample_format {
  *
  * struct read_format {
  *	{ u64		value;
- *	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
- *	  { u64		time_running; } && PERF_FORMAT_RUNNING
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		id;           } && PERF_FORMAT_ID
  *	} && !PERF_FORMAT_GROUP
  *
  *	{ u64		nr;
- *	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
- *	  { u64		time_running; } && PERF_FORMAT_RUNNING
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		value;
  *	    { u64	id;           } && PERF_FORMAT_ID
  *	  }		cntr[nr];
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 3160648ccdda..411e4f4be52b 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -425,7 +425,8 @@ struct dev_pm_info {
 	pm_message_t		power_state;
 	unsigned int		can_wakeup:1;
 	unsigned int		async_suspend:1;
-	unsigned int		in_suspend:1;	/* Owned by the PM core */
+	bool			is_prepared:1;	/* Owned by the PM core */
+	bool			is_suspended:1;	/* Ditto */
 	spinlock_t		lock;
 #ifdef CONFIG_PM_SLEEP
 	struct list_head	entry;
diff --git a/include/linux/pm_qos_params.h b/include/linux/pm_qos_params.h
index 77cbddb3784c..a7d87f911cab 100644
--- a/include/linux/pm_qos_params.h
+++ b/include/linux/pm_qos_params.h
@@ -16,6 +16,10 @@
 #define PM_QOS_NUM_CLASSES 4
 #define PM_QOS_DEFAULT_VALUE -1
 
+#define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
+#define PM_QOS_NETWORK_LAT_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
+#define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE	0
+
 struct pm_qos_request_list {
 	struct plist_node list;
 	int pm_qos_class;
diff --git a/include/linux/pnfs_osd_xdr.h b/include/linux/pnfs_osd_xdr.h
new file mode 100644
index 000000000000..76efbdd01622
--- /dev/null
+++ b/include/linux/pnfs_osd_xdr.h
@@ -0,0 +1,345 @@
+/*
+ *  pNFS-osd on-the-wire data structures
+ *
+ *  Copyright (C) 2007 Panasas Inc. [year of first publication]
+ *  All rights reserved.
+ *
+ *  Benny Halevy <bhalevy@panasas.com>
+ *  Boaz Harrosh <bharrosh@panasas.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
+ *  See the file COPYING included with this distribution for more details.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the Panasas company nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef __PNFS_OSD_XDR_H__
+#define __PNFS_OSD_XDR_H__
+
+#include <linux/nfs_fs.h>
+#include <linux/nfs_page.h>
+#include <scsi/osd_protocol.h>
+
+#define PNFS_OSD_OSDNAME_MAXSIZE 256
+
+/*
+ * draft-ietf-nfsv4-minorversion-22
+ * draft-ietf-nfsv4-pnfs-obj-12
+ */
+
+/* Layout Structure */
+
+enum pnfs_osd_raid_algorithm4 {
+	PNFS_OSD_RAID_0		= 1,
+	PNFS_OSD_RAID_4		= 2,
+	PNFS_OSD_RAID_5		= 3,
+	PNFS_OSD_RAID_PQ	= 4     /* Reed-Solomon P+Q */
+};
+
+/*   struct pnfs_osd_data_map4 {
+ *       uint32_t                    odm_num_comps;
+ *       length4                     odm_stripe_unit;
+ *       uint32_t                    odm_group_width;
+ *       uint32_t                    odm_group_depth;
+ *       uint32_t                    odm_mirror_cnt;
+ *       pnfs_osd_raid_algorithm4    odm_raid_algorithm;
+ *   };
+ */
+struct pnfs_osd_data_map {
+	u32	odm_num_comps;
+	u64	odm_stripe_unit;
+	u32	odm_group_width;
+	u32	odm_group_depth;
+	u32	odm_mirror_cnt;
+	u32	odm_raid_algorithm;
+};
+
+/*   struct pnfs_osd_objid4 {
+ *       deviceid4       oid_device_id;
+ *       uint64_t        oid_partition_id;
+ *       uint64_t        oid_object_id;
+ *   };
+ */
+struct pnfs_osd_objid {
+	struct nfs4_deviceid	oid_device_id;
+	u64			oid_partition_id;
+	u64			oid_object_id;
+};
+
+/* For printout. I use:
+ * kprint("dev(%llx:%llx)", _DEVID_LO(pointer), _DEVID_HI(pointer));
+ * BE style
+ */
+#define _DEVID_LO(oid_device_id) \
+	(unsigned long long)be64_to_cpup((__be64 *)(oid_device_id)->data)
+
+#define _DEVID_HI(oid_device_id) \
+	(unsigned long long)be64_to_cpup(((__be64 *)(oid_device_id)->data) + 1)
+
+static inline int
+pnfs_osd_objid_xdr_sz(void)
+{
+	return (NFS4_DEVICEID4_SIZE / 4) + 2 + 2;
+}
+
+enum pnfs_osd_version {
+	PNFS_OSD_MISSING              = 0,
+	PNFS_OSD_VERSION_1            = 1,
+	PNFS_OSD_VERSION_2            = 2
+};
+
+struct pnfs_osd_opaque_cred {
+	u32 cred_len;
+	void *cred;
+};
+
+enum pnfs_osd_cap_key_sec {
+	PNFS_OSD_CAP_KEY_SEC_NONE     = 0,
+	PNFS_OSD_CAP_KEY_SEC_SSV      = 1,
+};
+
+/*   struct pnfs_osd_object_cred4 {
+ *       pnfs_osd_objid4         oc_object_id;
+ *       pnfs_osd_version4       oc_osd_version;
+ *       pnfs_osd_cap_key_sec4   oc_cap_key_sec;
+ *       opaque                  oc_capability_key<>;
+ *       opaque                  oc_capability<>;
+ *   };
+ */
+struct pnfs_osd_object_cred {
+	struct pnfs_osd_objid		oc_object_id;
+	u32				oc_osd_version;
+	u32				oc_cap_key_sec;
+	struct pnfs_osd_opaque_cred	oc_cap_key;
+	struct pnfs_osd_opaque_cred	oc_cap;
+};
+
+/*   struct pnfs_osd_layout4 {
+ *       pnfs_osd_data_map4      olo_map;
+ *       uint32_t                olo_comps_index;
+ *       pnfs_osd_object_cred4   olo_components<>;
+ *   };
+ */
+struct pnfs_osd_layout {
+	struct pnfs_osd_data_map	olo_map;
+	u32				olo_comps_index;
+	u32				olo_num_comps;
+	struct pnfs_osd_object_cred	*olo_comps;
+};
+
+/* Device Address */
+enum pnfs_osd_targetid_type {
+	OBJ_TARGET_ANON = 1,
+	OBJ_TARGET_SCSI_NAME = 2,
+	OBJ_TARGET_SCSI_DEVICE_ID = 3,
+};
+
+/*   union pnfs_osd_targetid4 switch (pnfs_osd_targetid_type4 oti_type) {
+ *       case OBJ_TARGET_SCSI_NAME:
+ *           string              oti_scsi_name<>;
+ *
+ *       case OBJ_TARGET_SCSI_DEVICE_ID:
+ *           opaque              oti_scsi_device_id<>;
+ *
+ *       default:
+ *           void;
+ *   };
+ *
+ *   union pnfs_osd_targetaddr4 switch (bool ota_available) {
+ *       case TRUE:
+ *           netaddr4            ota_netaddr;
+ *       case FALSE:
+ *           void;
+ *   };
+ *
+ *   struct pnfs_osd_deviceaddr4 {
+ *       pnfs_osd_targetid4      oda_targetid;
+ *       pnfs_osd_targetaddr4    oda_targetaddr;
+ *       uint64_t                oda_lun;
+ *       opaque                  oda_systemid<>;
+ *       pnfs_osd_object_cred4   oda_root_obj_cred;
+ *       opaque                  oda_osdname<>;
+ *   };
+ */
+struct pnfs_osd_targetid {
+	u32				oti_type;
+	struct nfs4_string		oti_scsi_device_id;
+};
+
+enum { PNFS_OSD_TARGETID_MAX = 1 + PNFS_OSD_OSDNAME_MAXSIZE / 4 };
+
+/*   struct netaddr4 {
+ *       // see struct rpcb in RFC1833
+ *       string r_netid<>;    // network id
+ *       string r_addr<>;     // universal address
+ *   };
+ */
+struct pnfs_osd_net_addr {
+	struct nfs4_string	r_netid;
+	struct nfs4_string	r_addr;
+};
+
+struct pnfs_osd_targetaddr {
+	u32				ota_available;
+	struct pnfs_osd_net_addr	ota_netaddr;
+};
+
+enum {
+	NETWORK_ID_MAX = 16 / 4,
+	UNIVERSAL_ADDRESS_MAX = 64 / 4,
+	PNFS_OSD_TARGETADDR_MAX = 3 +  NETWORK_ID_MAX + UNIVERSAL_ADDRESS_MAX,
+};
+
+struct pnfs_osd_deviceaddr {
+	struct pnfs_osd_targetid	oda_targetid;
+	struct pnfs_osd_targetaddr	oda_targetaddr;
+	u8				oda_lun[8];
+	struct nfs4_string		oda_systemid;
+	struct pnfs_osd_object_cred	oda_root_obj_cred;
+	struct nfs4_string		oda_osdname;
+};
+
+enum {
+	ODA_OSDNAME_MAX = PNFS_OSD_OSDNAME_MAXSIZE / 4,
+	PNFS_OSD_DEVICEADDR_MAX =
+		PNFS_OSD_TARGETID_MAX + PNFS_OSD_TARGETADDR_MAX +
+		2 /*oda_lun*/ +
+		1 + OSD_SYSTEMID_LEN +
+		1 + ODA_OSDNAME_MAX,
+};
+
+/* LAYOUTCOMMIT: layoutupdate */
+
+/*   union pnfs_osd_deltaspaceused4 switch (bool dsu_valid) {
+ *       case TRUE:
+ *           int64_t     dsu_delta;
+ *       case FALSE:
+ *           void;
+ *   };
+ *
+ *   struct pnfs_osd_layoutupdate4 {
+ *       pnfs_osd_deltaspaceused4    olu_delta_space_used;
+ *       bool                        olu_ioerr_flag;
+ *   };
+ */
+struct pnfs_osd_layoutupdate {
+	u32	dsu_valid;
+	s64	dsu_delta;
+	u32	olu_ioerr_flag;
+};
+
+/* LAYOUTRETURN: I/O Rrror Report */
+
+enum pnfs_osd_errno {
+	PNFS_OSD_ERR_EIO		= 1,
+	PNFS_OSD_ERR_NOT_FOUND		= 2,
+	PNFS_OSD_ERR_NO_SPACE		= 3,
+	PNFS_OSD_ERR_BAD_CRED		= 4,
+	PNFS_OSD_ERR_NO_ACCESS		= 5,
+	PNFS_OSD_ERR_UNREACHABLE	= 6,
+	PNFS_OSD_ERR_RESOURCE		= 7
+};
+
+/*   struct pnfs_osd_ioerr4 {
+ *       pnfs_osd_objid4     oer_component;
+ *       length4             oer_comp_offset;
+ *       length4             oer_comp_length;
+ *       bool                oer_iswrite;
+ *       pnfs_osd_errno4     oer_errno;
+ *   };
+ */
+struct pnfs_osd_ioerr {
+	struct pnfs_osd_objid	oer_component;
+	u64			oer_comp_offset;
+	u64			oer_comp_length;
+	u32			oer_iswrite;
+	u32			oer_errno;
+};
+
+/* OSD XDR API */
+/* Layout helpers */
+/* Layout decoding is done in two parts:
+ * 1. First Call pnfs_osd_xdr_decode_layout_map to read in only the header part
+ *    of the layout. @iter members need not be initialized.
+ *    Returned:
+ *             @layout members are set. (@layout->olo_comps set to NULL).
+ *
+ *             Zero on success, or negative error if passed xdr is broken.
+ *
+ * 2. 2nd Call pnfs_osd_xdr_decode_layout_comp() in a loop until it returns
+ *    false, to decode the next component.
+ *    Returned:
+ *       true if there is more to decode or false if we are done or error.
+ *
+ * Example:
+ *	struct pnfs_osd_xdr_decode_layout_iter iter;
+ *	struct pnfs_osd_layout layout;
+ *	struct pnfs_osd_object_cred comp;
+ *	int status;
+ *
+ *	status = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr);
+ *	if (unlikely(status))
+ *		goto err;
+ *	while(pnfs_osd_xdr_decode_layout_comp(&comp, &iter, xdr, &status)) {
+ *		// All of @comp strings point to inside the xdr_buffer
+ *		// or scrach buffer. Copy them out to user memory eg.
+ *		copy_single_comp(dest_comp++, &comp);
+ *	}
+ *	if (unlikely(status))
+ *		goto err;
+ */
+
+struct pnfs_osd_xdr_decode_layout_iter {
+	unsigned total_comps;
+	unsigned decoded_comps;
+};
+
+extern int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout,
+	struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr);
+
+extern bool pnfs_osd_xdr_decode_layout_comp(struct pnfs_osd_object_cred *comp,
+	struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr,
+	int *err);
+
+/* Device Info helpers */
+
+/* Note: All strings inside @deviceaddr point to space inside @p.
+ * @p should stay valid while @deviceaddr is in use.
+ */
+extern void pnfs_osd_xdr_decode_deviceaddr(
+	struct pnfs_osd_deviceaddr *deviceaddr, __be32 *p);
+
+/* layoutupdate (layout_commit) xdr helpers */
+extern int
+pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr,
+				 struct pnfs_osd_layoutupdate *lou);
+
+/* osd_ioerror encoding/decoding (layout_return) */
+/* Client */
+extern __be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr);
+extern void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr);
+
+#endif /* __PNFS_OSD_XDR_H__ */
diff --git a/arch/arm/mach-s5p6442/include/mach/dma.h b/include/linux/power/isp1704_charger.h
index 81209eb1409b..68096a6aa2d7 100644
--- a/arch/arm/mach-s5p6442/include/mach/dma.h
+++ b/include/linux/power/isp1704_charger.h
@@ -1,6 +1,7 @@
 /*
- * Copyright (C) 2010 Samsung Electronics Co. Ltd.
- *	Jaswinder Singh <jassi.brar@samsung.com>
+ * ISP1704 USB Charger Detection driver
+ *
+ * Copyright (C) 2011 Nokia Corporation
  *
  * 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
@@ -14,13 +15,15 @@
  *
  * 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.
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
-#ifndef __MACH_DMA_H
-#define __MACH_DMA_H
 
-/* This platform uses the common S3C DMA API driver for PL330 */
-#include <plat/s3c-dma-pl330.h>
+#ifndef __ISP1704_CHARGER_H
+#define __ISP1704_CHARGER_H
+
+struct isp1704_charger_data {
+	void		(*set_power)(bool on);
+};
 
-#endif /* __MACH_DMA_H */
+#endif
diff --git a/include/linux/power/max8903_charger.h b/include/linux/power/max8903_charger.h
new file mode 100644
index 000000000000..24f51db8a83f
--- /dev/null
+++ b/include/linux/power/max8903_charger.h
@@ -0,0 +1,57 @@
+/*
+ * max8903_charger.h - Maxim 8903 USB/Adapter Charger Driver
+ *
+ * Copyright (C) 2011 Samsung Electronics
+ * MyungJoo Ham <myungjoo.ham@samsung.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.
+ *
+ * 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
+ *
+ */
+
+#ifndef __MAX8903_CHARGER_H__
+#define __MAX8903_CHARGER_H__
+
+struct max8903_pdata {
+	/*
+	 * GPIOs
+	 * cen, chg, flt, and usus are optional.
+	 * dok, dcm, and uok are not optional depending on the status of
+	 * dc_valid and usb_valid.
+	 */
+	int cen;	/* Charger Enable input */
+	int dok;	/* DC(Adapter) Power OK output */
+	int uok;	/* USB Power OK output */
+	int chg;	/* Charger status output */
+	int flt;	/* Fault output */
+	int dcm;	/* Current-Limit Mode input (1: DC, 2: USB) */
+	int usus;	/* USB Suspend Input (1: suspended) */
+
+	/*
+	 * DC(Adapter/TA) is wired
+	 * When dc_valid is true,
+	 *	dok and dcm should be valid.
+	 *
+	 * At least one of dc_valid or usb_valid should be true.
+	 */
+	bool dc_valid;
+	/*
+	 * USB is wired
+	 * When usb_valid is true,
+	 *	uok should be valid.
+	 */
+	bool usb_valid;
+};
+
+#endif /* __MAX8903_CHARGER_H__ */
diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h
index 03ff67b0cdf5..2f007157fab9 100644
--- a/include/linux/ratelimit.h
+++ b/include/linux/ratelimit.h
@@ -41,4 +41,44 @@ extern struct ratelimit_state printk_ratelimit_state;
 extern int ___ratelimit(struct ratelimit_state *rs, const char *func);
 #define __ratelimit(state) ___ratelimit(state, __func__)
 
+#ifdef CONFIG_PRINTK
+
+#define WARN_ON_RATELIMIT(condition, state)			\
+		WARN_ON((condition) && __ratelimit(state))
+
+#define __WARN_RATELIMIT(condition, state, format...)		\
+({								\
+	int rtn = 0;						\
+	if (unlikely(__ratelimit(state)))			\
+		rtn = WARN(condition, format);			\
+	rtn;							\
+})
+
+#define WARN_RATELIMIT(condition, format...)			\
+({								\
+	static DEFINE_RATELIMIT_STATE(_rs,			\
+				      DEFAULT_RATELIMIT_INTERVAL,	\
+				      DEFAULT_RATELIMIT_BURST);	\
+	__WARN_RATELIMIT(condition, &_rs, format);		\
+})
+
+#else
+
+#define WARN_ON_RATELIMIT(condition, state)			\
+	WARN_ON(condition)
+
+#define __WARN_RATELIMIT(condition, state, format...)		\
+({								\
+	int rtn = WARN(condition, format);			\
+	rtn;							\
+})
+
+#define WARN_RATELIMIT(condition, format...)			\
+({								\
+	int rtn = WARN(condition, format);			\
+	rtn;							\
+})
+
+#endif
+
 #endif /* _LINUX_RATELIMIT_H */
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index c4c4fc45f856..ce3127a75c88 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -68,6 +68,8 @@ struct regulator_state {
  *
  * @min_uV: Smallest voltage consumers may set.
  * @max_uV: Largest voltage consumers may set.
+ * @uV_offset: Offset applied to voltages from consumer to compensate for
+ *             voltage drops.
  *
  * @min_uA: Smallest consumers consumers may set.
  * @max_uA: Largest current consumers may set.
@@ -99,6 +101,8 @@ struct regulation_constraints {
 	int min_uV;
 	int max_uV;
 
+	int uV_offset;
+
 	/* current output range (inclusive) - for current control */
 	int min_uA;
 	int max_uA;
@@ -160,8 +164,6 @@ struct regulator_consumer_supply {
  * @supply_regulator: Parent regulator.  Specified using the regulator name
  *                    as it appears in the name field in sysfs, which can
  *                    be explicitly set using the constraints field 'name'.
- * @supply_regulator_dev: Parent regulator (if any) - DEPRECATED in favour
- *                        of supply_regulator.
  *
  * @constraints: Constraints.  These must be specified for the regulator to
  *               be usable.
@@ -173,7 +175,6 @@ struct regulator_consumer_supply {
  */
 struct regulator_init_data {
 	const char *supply_regulator;        /* or NULL for system supply */
-	struct device *supply_regulator_dev; /* or NULL for system supply */
 
 	struct regulation_constraints constraints;
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 483c1ed5bc4d..a837b20ba190 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1547,7 +1547,7 @@ struct task_struct {
 #ifdef CONFIG_TRACING
 	/* state flags for use by tracers */
 	unsigned long trace;
-	/* bitmask of trace recursion */
+	/* bitmask and counter of trace recursion */
 	unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
@@ -2195,7 +2195,6 @@ static inline void mmdrop(struct mm_struct * mm)
 	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
 		__mmdrop(mm);
 }
-extern int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm);
 
 /* mmput gets rid of the mappings and all user-space */
 extern void mmput(struct mm_struct *);
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index e9811892844f..c6db9fb33c44 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -28,6 +28,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/preempt.h>
+#include <asm/processor.h>
 
 typedef struct {
 	unsigned sequence;
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 2b7fec840517..aa08fa8fd79b 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -3,6 +3,7 @@
 
 #include <linux/swap.h>
 #include <linux/mempolicy.h>
+#include <linux/pagemap.h>
 #include <linux/percpu_counter.h>
 
 /* inode in-kernel data */
@@ -45,7 +46,27 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode)
 	return container_of(inode, struct shmem_inode_info, vfs_inode);
 }
 
+/*
+ * Functions in mm/shmem.c called directly from elsewhere:
+ */
 extern int init_tmpfs(void);
 extern int shmem_fill_super(struct super_block *sb, void *data, int silent);
+extern struct file *shmem_file_setup(const char *name,
+					loff_t size, unsigned long flags);
+extern int shmem_zero_setup(struct vm_area_struct *);
+extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
+extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
+					pgoff_t index, gfp_t gfp_mask);
+extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end);
+extern int shmem_unuse(swp_entry_t entry, struct page *page);
+extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff,
+					struct page **pagep, swp_entry_t *ent);
+
+static inline struct page *shmem_read_mapping_page(
+				struct address_space *mapping, pgoff_t index)
+{
+	return shmem_read_mapping_page_gfp(mapping, index,
+					mapping_gfp_mask(mapping));
+}
 
 #endif
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e8b78ce14474..c0a4f3ab0cc0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1256,6 +1256,11 @@ static inline void skb_reserve(struct sk_buff *skb, int len)
 	skb->tail += len;
 }
 
+static inline void skb_reset_mac_len(struct sk_buff *skb)
+{
+	skb->mac_len = skb->network_header - skb->mac_header;
+}
+
 #ifdef NET_SKBUFF_DATA_USES_OFFSET
 static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
 {
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 7ad824d510a2..8cc38d3bab0c 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -85,12 +85,15 @@ int smp_call_function_any(const struct cpumask *mask,
  * Generic and arch helpers
  */
 #ifdef CONFIG_USE_GENERIC_SMP_HELPERS
+void __init call_function_init(void);
 void generic_smp_call_function_single_interrupt(void);
 void generic_smp_call_function_interrupt(void);
 void ipi_call_lock(void);
 void ipi_call_unlock(void);
 void ipi_call_lock_irq(void);
 void ipi_call_unlock_irq(void);
+#else
+static inline void call_function_init(void) { }
 #endif
 
 /*
@@ -134,7 +137,7 @@ static inline void smp_send_reschedule(int cpu) { }
 #define smp_prepare_boot_cpu()			do {} while (0)
 #define smp_call_function_many(mask, func, info, wait) \
 			(up_smp_call_function(func, info))
-static inline void init_call_single_data(void) { }
+static inline void call_function_init(void) { }
 
 static inline int
 smp_call_function_any(const struct cpumask *mask, smp_call_func_t func,
diff --git a/include/linux/sunrpc/gss_krb5_enctypes.h b/include/linux/sunrpc/gss_krb5_enctypes.h
new file mode 100644
index 000000000000..ec6234eee89c
--- /dev/null
+++ b/include/linux/sunrpc/gss_krb5_enctypes.h
@@ -0,0 +1,4 @@
+/*
+ * Dumb way to share this static piece of information with nfsd
+ */
+#define KRB5_SUPPORTED_ENCTYPES "18,17,16,23,3,1,2"
diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h
index 77e624883393..c68a147939a6 100644
--- a/include/linux/sunrpc/msg_prot.h
+++ b/include/linux/sunrpc/msg_prot.h
@@ -145,6 +145,7 @@ typedef __be32	rpc_fraghdr;
 #define RPCBIND_NETID_TCP	"tcp"
 #define RPCBIND_NETID_UDP6	"udp6"
 #define RPCBIND_NETID_TCP6	"tcp6"
+#define RPCBIND_NETID_LOCAL	"local"
 
 /*
  * Note that RFC 1833 does not put any size restrictions on the
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index f73c482ec9c6..fe2d8e6b923b 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -84,7 +84,8 @@ struct rpc_task {
 #endif
 	unsigned char		tk_priority : 2,/* Task priority */
 				tk_garb_retry : 2,
-				tk_cred_retry : 2;
+				tk_cred_retry : 2,
+				tk_rebind_retry : 2;
 };
 #define tk_xprt			tk_client->cl_xprt
 
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 04dba23c59f2..85c50b40759d 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -28,6 +28,7 @@ struct svc_sock {
 	/* private TCP part */
 	u32			sk_reclen;	/* length of record */
 	u32			sk_tcplen;	/* current read length */
+	struct page *		sk_pages[RPCSVC_MAXPAGES];	/* received data */
 };
 
 /*
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index fc84b7a19ca3..a20970ef9e4e 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -216,6 +216,8 @@ extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
 extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages,
 		unsigned int base, unsigned int len);
 extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p);
+extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
+		struct page **pages, unsigned int len);
 extern void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen);
 extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern void xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index a0f998c07c65..81cce3b3ee66 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -141,7 +141,8 @@ enum xprt_transports {
 	XPRT_TRANSPORT_UDP	= IPPROTO_UDP,
 	XPRT_TRANSPORT_TCP	= IPPROTO_TCP,
 	XPRT_TRANSPORT_BC_TCP	= IPPROTO_TCP | XPRT_TRANSPORT_BC,
-	XPRT_TRANSPORT_RDMA	= 256
+	XPRT_TRANSPORT_RDMA	= 256,
+	XPRT_TRANSPORT_LOCAL	= 257,
 };
 
 struct rpc_xprt {
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 384eb5fe530b..a273468f8285 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -300,16 +300,6 @@ static inline void scan_unevictable_unregister_node(struct node *node)
 extern int kswapd_run(int nid);
 extern void kswapd_stop(int nid);
 
-#ifdef CONFIG_MMU
-/* linux/mm/shmem.c */
-extern int shmem_unuse(swp_entry_t entry, struct page *page);
-#endif /* CONFIG_MMU */
-
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff,
-					struct page **pagep, swp_entry_t *ent);
-#endif
-
 #ifdef CONFIG_SWAP
 /* linux/mm/page_io.c */
 extern int swap_readpage(struct page *);
@@ -358,6 +348,7 @@ struct backing_dev_info;
 extern struct mm_struct *swap_token_mm;
 extern void grab_swap_token(struct mm_struct *);
 extern void __put_swap_token(struct mm_struct *);
+extern void disable_swap_token(struct mem_cgroup *memcg);
 
 static inline int has_swap_token(struct mm_struct *mm)
 {
@@ -370,11 +361,6 @@ static inline void put_swap_token(struct mm_struct *mm)
 		__put_swap_token(mm);
 }
 
-static inline void disable_swap_token(void)
-{
-	put_swap_token(swap_token_mm);
-}
-
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 extern void
 mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout);
@@ -500,7 +486,7 @@ static inline int has_swap_token(struct mm_struct *mm)
 	return 0;
 }
 
-static inline void disable_swap_token(void)
+static inline void disable_swap_token(struct mem_cgroup *memcg)
 {
 }
 
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 8c0e349f4a6c..445702c60d04 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -24,6 +24,7 @@ extern int swiotlb_force;
 
 extern void swiotlb_init(int verbose);
 extern void swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
+extern unsigned long swioltb_nr_tbl(void);
 
 /*
  * Enumeration for sync targets
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index c3acda60eee0..e2696d76a599 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -177,9 +177,6 @@ struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
 struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd);
 void sysfs_put(struct sysfs_dirent *sd);
 
-/* Called to clear a ns tag when it is no longer valid */
-void sysfs_exit_ns(enum kobj_ns_type type, const void *tag);
-
 int __must_check sysfs_init(void);
 
 #else /* CONFIG_SYSFS */
@@ -338,10 +335,6 @@ static inline void sysfs_put(struct sysfs_dirent *sd)
 {
 }
 
-static inline void sysfs_exit_ns(int type, const void *tag)
-{
-}
-
 static inline int __must_check sysfs_init(void)
 {
 	return 0;
diff --git a/include/linux/topology.h b/include/linux/topology.h
index b91a40e847d2..fc839bfa7935 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -60,7 +60,7 @@ int arch_update_cpu_topology(void);
  * (in whatever arch specific measurement units returned by node_distance())
  * then switch on zone reclaim on boot.
  */
-#define RECLAIM_DISTANCE 20
+#define RECLAIM_DISTANCE 30
 #endif
 #ifndef PENALTY_FOR_NODE_WITH_CPUS
 #define PENALTY_FOR_NODE_WITH_CPUS	(1)
diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h
index 5b07792ccb46..ff7dc08696a8 100644
--- a/include/linux/tty_ldisc.h
+++ b/include/linux/tty_ldisc.h
@@ -76,7 +76,7 @@
  * 	tty device.  It is solely the responsibility of the line
  * 	discipline to handle poll requests.
  *
- * unsigned int (*receive_buf)(struct tty_struct *, const unsigned char *cp,
+ * void	(*receive_buf)(struct tty_struct *, const unsigned char *cp,
  * 		       char *fp, int count);
  *
  * 	This function is called by the low-level tty driver to send
@@ -84,8 +84,7 @@
  * 	processing.  <cp> is a pointer to the buffer of input
  * 	character received by the device.  <fp> is a pointer to a
  * 	pointer of flag bytes which indicate whether a character was
- * 	received with a parity error, etc. Returns the amount of bytes
- * 	received.
+ * 	received with a parity error, etc.
  * 
  * void	(*write_wakeup)(struct tty_struct *);
  *
@@ -141,8 +140,8 @@ struct tty_ldisc_ops {
 	/*
 	 * The following routines are called from below.
 	 */
-	unsigned int (*receive_buf)(struct tty_struct *,
-			const unsigned char *cp, char *fp, int count);
+	void	(*receive_buf)(struct tty_struct *, const unsigned char *cp,
+			       char *fp, int count);
 	void	(*write_wakeup)(struct tty_struct *);
 	void	(*dcd_change)(struct tty_struct *, unsigned int,
 				struct pps_event_time *);
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index d512d98dfb7d..5ca0951e1855 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -93,8 +93,8 @@ static inline unsigned long __copy_from_user_nocache(void *to,
  * Safely read from address @src to the buffer at @dst.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-extern long probe_kernel_read(void *dst, void *src, size_t size);
-extern long __probe_kernel_read(void *dst, void *src, size_t size);
+extern long probe_kernel_read(void *dst, const void *src, size_t size);
+extern long __probe_kernel_read(void *dst, const void *src, size_t size);
 
 /*
  * probe_kernel_write(): safely attempt to write to a location
@@ -105,7 +105,7 @@ extern long __probe_kernel_read(void *dst, void *src, size_t size);
  * Safely write to address @dst from the buffer at @src.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-extern long notrace probe_kernel_write(void *dst, void *src, size_t size);
-extern long notrace __probe_kernel_write(void *dst, void *src, size_t size);
+extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
+extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size);
 
 #endif		/* __LINUX_UACCESS_H__ */
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index 71693d4a4fe1..17df3600bcef 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -62,7 +62,9 @@
 	US_FLAG(NO_READ_DISC_INFO,	0x00040000)		\
 		/* cannot handle READ_DISC_INFO */		\
 	US_FLAG(NO_READ_CAPACITY_16,	0x00080000)		\
-		/* cannot handle READ_CAPACITY_16 */
+		/* cannot handle READ_CAPACITY_16 */		\
+	US_FLAG(INITIAL_READ10,	0x00100000)			\
+		/* Initial READ(10) (and others) must be retried */
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };
diff --git a/include/linux/uts.h b/include/linux/uts.h
index 73eb1ed36ec4..6ddbd86377de 100644
--- a/include/linux/uts.h
+++ b/include/linux/uts.h
@@ -9,7 +9,7 @@
 #endif
 
 #ifndef UTS_NODENAME
-#define UTS_NODENAME "(none)"	/* set by sethostname() */
+#define UTS_NODENAME CONFIG_DEFAULT_HOSTNAME /* set by sethostname() */
 #endif
 
 #ifndef UTS_DOMAINNAME
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index aff5b4f74041..710885749605 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -51,6 +51,13 @@ struct virtqueue {
  *	This re-enables callbacks; it returns "false" if there are pending
  *	buffers in the queue, to detect a possible race between the driver
  *	checking for more work, and enabling callbacks.
+ * virtqueue_enable_cb_delayed: restart callbacks after disable_cb.
+ *	vq: the struct virtqueue we're talking about.
+ *	This re-enables callbacks but hints to the other side to delay
+ *	interrupts until most of the available buffers have been processed;
+ *	it returns "false" if there are many pending buffers in the queue,
+ *	to detect a possible race between the driver checking for more work,
+ *	and enabling callbacks.
  * virtqueue_detach_unused_buf: detach first unused buffer
  * 	vq: the struct virtqueue we're talking about.
  * 	Returns NULL or the "data" token handed to add_buf
@@ -86,6 +93,8 @@ void virtqueue_disable_cb(struct virtqueue *vq);
 
 bool virtqueue_enable_cb(struct virtqueue *vq);
 
+bool virtqueue_enable_cb_delayed(struct virtqueue *vq);
+
 void *virtqueue_detach_unused_buf(struct virtqueue *vq);
 
 /**
diff --git a/include/linux/virtio_9p.h b/include/linux/virtio_9p.h
index e68b439b2860..277c4ad44e84 100644
--- a/include/linux/virtio_9p.h
+++ b/include/linux/virtio_9p.h
@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_9P_H
 #define _LINUX_VIRTIO_9P_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
diff --git a/include/linux/virtio_balloon.h b/include/linux/virtio_balloon.h
index a50ecd1b81a2..652dc8bea921 100644
--- a/include/linux/virtio_balloon.h
+++ b/include/linux/virtio_balloon.h
@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_BALLOON_H
 #define _LINUX_VIRTIO_BALLOON_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
 
diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h
index 167720d695ed..e0edb40ca7aa 100644
--- a/include/linux/virtio_blk.h
+++ b/include/linux/virtio_blk.h
@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_BLK_H
 #define _LINUX_VIRTIO_BLK_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 800617b4ddd5..39c88c5ad19d 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_CONFIG_H
 #define _LINUX_VIRTIO_CONFIG_H
 /* This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
- * anyone can use the definitions to implement compatible drivers/servers. */
+ * anyone can use the definitions to implement compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 
 /* Virtio devices use a standardized configuration space to define their
  * features and pass configuration information, but each implementation can
diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h
index e4d333543a33..bdf4b0034739 100644
--- a/include/linux/virtio_console.h
+++ b/include/linux/virtio_console.h
@@ -5,7 +5,31 @@
 #include <linux/virtio_config.h>
 /*
  * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
- * anyone can use the definitions to implement compatible drivers/servers.
+ * anyone can use the definitions to implement compatible drivers/servers:
+ *
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
  *
  * Copyright (C) Red Hat, Inc., 2009, 2010, 2011
  * Copyright (C) Amit Shah <amit.shah@redhat.com>, 2009, 2010, 2011
diff --git a/include/linux/virtio_ids.h b/include/linux/virtio_ids.h
index 06660c0a78d7..85bb0bb66ffc 100644
--- a/include/linux/virtio_ids.h
+++ b/include/linux/virtio_ids.h
@@ -5,7 +5,29 @@
  *
  * This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
- */
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 
 #define VIRTIO_ID_NET		1 /* virtio net */
 #define VIRTIO_ID_BLOCK		2 /* virtio block */
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 085e42298ce5..136040bba3e3 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_NET_H
 #define _LINUX_VIRTIO_NET_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
diff --git a/include/linux/virtio_pci.h b/include/linux/virtio_pci.h
index 9a3d7c48c622..ea66f3f60d63 100644
--- a/include/linux/virtio_pci.h
+++ b/include/linux/virtio_pci.h
@@ -11,6 +11,29 @@
  *
  * This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
  */
 
 #ifndef _LINUX_VIRTIO_PCI_H
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index e4d144b132b5..4a32cb6da425 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -7,6 +7,29 @@
  * This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
  *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
  * Copyright Rusty Russell IBM Corporation 2007. */
 #include <linux/types.h>
 
@@ -29,6 +52,12 @@
 /* We support indirect buffer descriptors */
 #define VIRTIO_RING_F_INDIRECT_DESC	28
 
+/* The Guest publishes the used index for which it expects an interrupt
+ * at the end of the avail ring. Host should ignore the avail->flags field. */
+/* The Host publishes the avail index for which it expects a kick
+ * at the end of the used ring. Guest should ignore the used->flags field. */
+#define VIRTIO_RING_F_EVENT_IDX		29
+
 /* Virtio ring descriptors: 16 bytes.  These can chain together via "next". */
 struct vring_desc {
 	/* Address (guest-physical). */
@@ -83,6 +112,7 @@ struct vring {
  *	__u16 avail_flags;
  *	__u16 avail_idx;
  *	__u16 available[num];
+ *	__u16 used_event_idx;
  *
  *	// Padding to the next align boundary.
  *	char pad[];
@@ -91,8 +121,14 @@ struct vring {
  *	__u16 used_flags;
  *	__u16 used_idx;
  *	struct vring_used_elem used[num];
+ *	__u16 avail_event_idx;
  * };
  */
+/* We publish the used event index at the end of the available ring, and vice
+ * versa. They are at the end for backwards compatibility. */
+#define vring_used_event(vr) ((vr)->avail->ring[(vr)->num])
+#define vring_avail_event(vr) (*(__u16 *)&(vr)->used->ring[(vr)->num])
+
 static inline void vring_init(struct vring *vr, unsigned int num, void *p,
 			      unsigned long align)
 {
@@ -107,7 +143,21 @@ static inline unsigned vring_size(unsigned int num, unsigned long align)
 {
 	return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (2 + num)
 		 + align - 1) & ~(align - 1))
-		+ sizeof(__u16) * 2 + sizeof(struct vring_used_elem) * num;
+		+ sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num;
+}
+
+/* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */
+/* Assuming a given event_idx value from the other size, if
+ * we have just incremented index from old to new_idx,
+ * should we trigger an event? */
+static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old)
+{
+	/* Note: Xen has similar logic for notification hold-off
+	 * in include/xen/interface/io/ring.h with req_event and req_prod
+	 * corresponding to event_idx + 1 and new_idx respectively.
+	 * Note also that req_event and req_prod in Xen start at 1,
+	 * event indexes in virtio start at 0. */
+	return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old);
 }
 
 #ifdef __KERNEL__
diff --git a/include/media/m5mols.h b/include/media/m5mols.h
new file mode 100644
index 000000000000..2d7e7ca2313d
--- /dev/null
+++ b/include/media/m5mols.h
@@ -0,0 +1,35 @@
+/*
+ * Driver header for M-5MOLS 8M Pixel camera sensor with ISP
+ *
+ * Copyright (C) 2011 Samsung Electronics Co., Ltd.
+ * Author: HeungJun Kim, riverful.kim@samsung.com
+ *
+ * Copyright (C) 2009 Samsung Electronics Co., Ltd.
+ * Author: Dongsoo Nathaniel Kim, dongsoo45.kim@samsung.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.
+ */
+
+#ifndef MEDIA_M5MOLS_H
+#define MEDIA_M5MOLS_H
+
+/**
+ * struct m5mols_platform_data - platform data for M-5MOLS driver
+ * @irq:	GPIO getting the irq pin of M-5MOLS
+ * @gpio_reset:	GPIO driving the reset pin of M-5MOLS
+ * @reset_polarity: active state for gpio_rst pin, 0 or 1
+ * @set_power:	an additional callback to the board setup code
+ *		to be called after enabling and before disabling
+ *		the sensor's supply regulators
+ */
+struct m5mols_platform_data {
+	int irq;
+	int gpio_reset;
+	u8 reset_polarity;
+	int (*set_power)(struct device *dev, int on);
+};
+
+#endif	/* MEDIA_M5MOLS_H */
diff --git a/include/media/v4l2-dev.h b/include/media/v4l2-dev.h
index 93e96fb93452..c7c40f1d2624 100644
--- a/include/media/v4l2-dev.h
+++ b/include/media/v4l2-dev.h
@@ -128,8 +128,8 @@ struct video_device
 	struct mutex *lock;
 };
 
-#define media_entity_to_video_device(entity) \
-	container_of(entity, struct video_device, entity)
+#define media_entity_to_video_device(__e) \
+	container_of(__e, struct video_device, entity)
 /* dev to video-device */
 #define to_video_device(cd) container_of(cd, struct video_device, dev)
 
diff --git a/include/media/videobuf-dvb.h b/include/media/videobuf-dvb.h
index 07cf4b9d0a65..bf365721d6b0 100644
--- a/include/media/videobuf-dvb.h
+++ b/include/media/videobuf-dvb.h
@@ -4,6 +4,9 @@
 #include <dvb_net.h>
 #include <dvb_frontend.h>
 
+#ifndef _VIDEOBUF_DVB_H_
+#define	_VIDEOBUF_DVB_H_
+
 struct videobuf_dvb {
 	/* filling that the job of the driver */
 	char                       *name;
@@ -54,6 +57,7 @@ void videobuf_dvb_dealloc_frontends(struct videobuf_dvb_frontends *f);
 struct videobuf_dvb_frontend * videobuf_dvb_get_frontend(struct videobuf_dvb_frontends *f, int id);
 int videobuf_dvb_find_frontend(struct videobuf_dvb_frontends *f, struct dvb_frontend *p);
 
+#endif			/* _VIDEOBUF_DVB_H_ */
 
 /*
  * Local variables:
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4fff432aeade..481f856c650f 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -797,7 +797,8 @@ struct netns_ipvs {
 	struct list_head	rs_table[IP_VS_RTAB_SIZE];
 	/* ip_vs_app */
 	struct list_head	app_list;
-
+	/* ip_vs_ftp */
+	struct ip_vs_app	*ftp_app;
 	/* ip_vs_proto */
 	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
 	struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index dcc8f5749d3f..aef430d779bd 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -7,6 +7,7 @@
 #include <asm/atomic.h>
 #include <linux/workqueue.h>
 #include <linux/list.h>
+#include <linux/sysctl.h>
 
 #include <net/netns/core.h>
 #include <net/netns/mib.h>
@@ -34,8 +35,11 @@ struct netns_ipvs;
 #define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)
 
 struct net {
+	atomic_t		passive;	/* To decided when the network
+						 * namespace should be freed.
+						 */
 	atomic_t		count;		/* To decided when the network
-						 *  namespace should be freed.
+						 *  namespace should be shut down.
 						 */
 #ifdef NETNS_REFCNT_DEBUG
 	atomic_t		use_count;	/* To track references we
@@ -153,6 +157,9 @@ int net_eq(const struct net *net1, const struct net *net2)
 {
 	return net1 == net2;
 }
+
+extern void net_drop_ns(void *);
+
 #else
 
 static inline struct net *get_net(struct net *net)
@@ -174,6 +181,8 @@ int net_eq(const struct net *net1, const struct net *net2)
 {
 	return 1;
 }
+
+#define net_drop_ns NULL
 #endif
 
 
diff --git a/include/net/net_ratelimit.h b/include/net/net_ratelimit.h
new file mode 100644
index 000000000000..7727b4247daf
--- /dev/null
+++ b/include/net/net_ratelimit.h
@@ -0,0 +1,8 @@
+#ifndef _LINUX_NET_RATELIMIT_H
+#define _LINUX_NET_RATELIMIT_H
+
+#include <linux/ratelimit.h>
+
+extern struct ratelimit_state net_ratelimit_state;
+
+#endif	/* _LINUX_NET_RATELIMIT_H */
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index c7c42e7acc31..5d4f8e586e32 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -307,6 +307,12 @@ static inline int nf_ct_is_untracked(const struct nf_conn *ct)
 	return test_bit(IPS_UNTRACKED_BIT, &ct->status);
 }
 
+/* Packet is received from loopback */
+static inline bool nf_is_loopback_packet(const struct sk_buff *skb)
+{
+	return skb->dev && skb->skb_iif && skb->dev->flags & IFF_LOOPBACK;
+}
+
 extern int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp);
 extern unsigned int nf_conntrack_htable_size;
 extern unsigned int nf_conntrack_max;
diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index 2b447646ce4b..dd6847e5d6e4 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -107,6 +107,7 @@ typedef enum {
 	SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */
 	SCTP_CMD_SEND_MSG,	 /* Send the whole use message */
 	SCTP_CMD_SEND_NEXT_ASCONF, /* Send the next ASCONF after ACK */
+	SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/
 	SCTP_CMD_LAST
 } sctp_verb_t;
 
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 795f4886e111..7df327a6d564 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1993,7 +1993,7 @@ void sctp_assoc_clean_asconf_ack_cache(const struct sctp_association *asoc);
 struct sctp_chunk *sctp_assoc_lookup_asconf_ack(
 					const struct sctp_association *asoc,
 					__be32 serial);
-
+void sctp_asconf_queue_teardown(struct sctp_association *asoc);
 
 int sctp_cmp_addr_exact(const union sctp_addr *ss1,
 			const union sctp_addr *ss2);
diff --git a/include/net/sock.h b/include/net/sock.h
index f2046e404a61..c0b938cb4b1a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -178,7 +178,6 @@ struct sock_common {
   *	@sk_dst_cache: destination cache
   *	@sk_dst_lock: destination cache lock
   *	@sk_policy: flow policy
-  *	@sk_rmem_alloc: receive queue bytes committed
   *	@sk_receive_queue: incoming packets
   *	@sk_wmem_alloc: transmit queue bytes committed
   *	@sk_write_queue: Packet sending queue
diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h
index 8f6bb9c7f3eb..ee866060f8a4 100644
--- a/include/scsi/libsas.h
+++ b/include/scsi/libsas.h
@@ -604,6 +604,7 @@ struct sas_domain_function_template {
 	int (*lldd_clear_aca)(struct domain_device *, u8 *lun);
 	int (*lldd_clear_task_set)(struct domain_device *, u8 *lun);
 	int (*lldd_I_T_nexus_reset)(struct domain_device *);
+	int (*lldd_ata_soft_reset)(struct domain_device *);
 	int (*lldd_lu_reset)(struct domain_device *, u8 *lun);
 	int (*lldd_query_task)(struct sas_task *);
 
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index d6e7994aa634..81dd12edc38c 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -9,6 +9,7 @@
 #define MSG_SIMPLE_TAG	0x20
 #define MSG_HEAD_TAG	0x21
 #define MSG_ORDERED_TAG	0x22
+#define MSG_ACA_TAG	0x24	/* unsupported */
 
 #define SCSI_NO_TAG	(-1)    /* identify no tag in use */
 
diff --git a/include/sound/soc.h b/include/sound/soc.h
index f1de3e0c75bc..3a4bd3a3c68d 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -248,8 +248,7 @@ typedef int (*hw_write_t)(void *,const char* ,int);
 extern struct snd_ac97_bus_ops soc_ac97_ops;
 
 enum snd_soc_control_type {
-	SND_SOC_CUSTOM = 1,
-	SND_SOC_I2C,
+	SND_SOC_I2C = 1,
 	SND_SOC_SPI,
 };
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 1d3b5b2f0dbc..561ac99def5a 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -98,6 +98,7 @@ enum transport_state_table {
 	TRANSPORT_REMOVE	= 14,
 	TRANSPORT_FREE		= 15,
 	TRANSPORT_NEW_CMD_MAP	= 16,
+	TRANSPORT_FREE_CMD_INTR = 17,
 };
 
 /* Used for struct se_cmd->se_cmd_flags */
diff --git a/include/target/target_core_fabric_ops.h b/include/target/target_core_fabric_ops.h
index dc78f77f9450..747e1404dca0 100644
--- a/include/target/target_core_fabric_ops.h
+++ b/include/target/target_core_fabric_ops.h
@@ -77,7 +77,6 @@ struct target_core_fabric_ops {
 	u16 (*set_fabric_sense_len)(struct se_cmd *, u32);
 	u16 (*get_fabric_sense_len)(void);
 	int (*is_state_remove)(struct se_cmd *);
-	u64 (*pack_lun)(unsigned int);
 	/*
 	 * fabric module calls for target_core_fabric_configfs.c
 	 */
diff --git a/include/target/target_core_transport.h b/include/target/target_core_transport.h
index 59aa464f6ee2..24a1c6cb83c3 100644
--- a/include/target/target_core_transport.h
+++ b/include/target/target_core_transport.h
@@ -172,6 +172,7 @@ extern int transport_generic_handle_cdb_map(struct se_cmd *);
 extern int transport_generic_handle_data(struct se_cmd *);
 extern void transport_new_cmd_failure(struct se_cmd *);
 extern int transport_generic_handle_tmr(struct se_cmd *);
+extern void transport_generic_free_cmd_intr(struct se_cmd *);
 extern void __transport_stop_task_timer(struct se_task *, unsigned long *);
 extern unsigned char transport_asciihex_to_binaryhex(unsigned char val[2]);
 extern int transport_generic_map_mem_to_cmd(struct se_cmd *cmd, struct scatterlist *, u32,
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index f445cff66ab7..4114129f0794 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -28,7 +28,7 @@ struct extent_buffer;
 		{ BTRFS_SHARED_DATA_REF_KEY, 	"SHARED_DATA_REF" })
 
 #define __show_root_type(obj)						\
-	__print_symbolic(obj,						\
+	__print_symbolic_u64(obj,					\
 		{ BTRFS_ROOT_TREE_OBJECTID, 	"ROOT_TREE"	},	\
 		{ BTRFS_EXTENT_TREE_OBJECTID, 	"EXTENT_TREE"	},	\
 		{ BTRFS_CHUNK_TREE_OBJECTID, 	"CHUNK_TREE"	},	\
@@ -125,7 +125,7 @@ DEFINE_EVENT(btrfs__inode, btrfs_inode_evict,
 );
 
 #define __show_map_type(type)						\
-	__print_symbolic(type,						\
+	__print_symbolic_u64(type,					\
 		{ EXTENT_MAP_LAST_BYTE, "LAST_BYTE" 	},		\
 		{ EXTENT_MAP_HOLE, 	"HOLE" 		},		\
 		{ EXTENT_MAP_INLINE, 	"INLINE" 	},		\
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index e09592d2f916..5ce2b2f5f524 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -26,7 +26,7 @@ TRACE_EVENT(ext4_free_inode,
 		__field(	umode_t, mode			)
 		__field(	uid_t,	uid			)
 		__field(	gid_t,	gid			)
-		__field(	blkcnt_t, blocks		)
+		__field(	__u64, blocks			)
 	),
 
 	TP_fast_assign(
@@ -40,9 +40,8 @@ TRACE_EVENT(ext4_free_inode,
 
 	TP_printk("dev %d,%d ino %lu mode 0%o uid %u gid %u blocks %llu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino,
-		  __entry->mode, __entry->uid, __entry->gid,
-		  (unsigned long long) __entry->blocks)
+		  (unsigned long) __entry->ino, __entry->mode,
+		  __entry->uid, __entry->gid, __entry->blocks)
 );
 
 TRACE_EVENT(ext4_request_inode,
@@ -178,7 +177,7 @@ TRACE_EVENT(ext4_begin_ordered_truncate,
 	TP_printk("dev %d,%d ino %lu new_size %lld",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  (long long) __entry->new_size)
+		  __entry->new_size)
 );
 
 DECLARE_EVENT_CLASS(ext4__write_begin,
@@ -204,7 +203,7 @@ DECLARE_EVENT_CLASS(ext4__write_begin,
 		__entry->flags	= flags;
 	),
 
-	TP_printk("dev %d,%d ino %lu pos %llu len %u flags %u",
+	TP_printk("dev %d,%d ino %lu pos %lld len %u flags %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->pos, __entry->len, __entry->flags)
@@ -248,7 +247,7 @@ DECLARE_EVENT_CLASS(ext4__write_end,
 		__entry->copied	= copied;
 	),
 
-	TP_printk("dev %d,%d ino %lu pos %llu len %u copied %u",
+	TP_printk("dev %d,%d ino %lu pos %lld len %u copied %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->pos, __entry->len, __entry->copied)
@@ -286,29 +285,6 @@ DEFINE_EVENT(ext4__write_end, ext4_da_write_end,
 	TP_ARGS(inode, pos, len, copied)
 );
 
-TRACE_EVENT(ext4_writepage,
-	TP_PROTO(struct inode *inode, struct page *page),
-
-	TP_ARGS(inode, page),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	pgoff_t, index			)
-
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->index	= page->index;
-	),
-
-	TP_printk("dev %d,%d ino %lu page_index %lu",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino, __entry->index)
-);
-
 TRACE_EVENT(ext4_da_writepages,
 	TP_PROTO(struct inode *inode, struct writeback_control *wbc),
 
@@ -341,7 +317,7 @@ TRACE_EVENT(ext4_da_writepages,
 	),
 
 	TP_printk("dev %d,%d ino %lu nr_to_write %ld pages_skipped %ld "
-		  "range_start %llu range_end %llu sync_mode %d"
+		  "range_start %lld range_end %lld sync_mode %d"
 		  "for_kupdate %d range_cyclic %d writeback_index %lu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino, __entry->nr_to_write,
@@ -449,7 +425,14 @@ DECLARE_EVENT_CLASS(ext4__page_op,
 	TP_printk("dev %d,%d ino %lu page_index %lu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  __entry->index)
+		  (unsigned long) __entry->index)
+);
+
+DEFINE_EVENT(ext4__page_op, ext4_writepage,
+
+	TP_PROTO(struct page *page),
+
+	TP_ARGS(page)
 );
 
 DEFINE_EVENT(ext4__page_op, ext4_readpage,
@@ -489,7 +472,7 @@ TRACE_EVENT(ext4_invalidatepage,
 	TP_printk("dev %d,%d ino %lu page_index %lu offset %lu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  __entry->index, __entry->offset)
+		  (unsigned long) __entry->index, __entry->offset)
 );
 
 TRACE_EVENT(ext4_discard_blocks,
@@ -562,12 +545,10 @@ DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_group_pa,
 );
 
 TRACE_EVENT(ext4_mb_release_inode_pa,
-	TP_PROTO(struct super_block *sb,
-		 struct inode *inode,
-		 struct ext4_prealloc_space *pa,
+	TP_PROTO(struct ext4_prealloc_space *pa,
 		 unsigned long long block, unsigned int count),
 
-	TP_ARGS(sb, inode, pa, block, count),
+	TP_ARGS(pa, block, count),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
@@ -578,8 +559,8 @@ TRACE_EVENT(ext4_mb_release_inode_pa,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= sb->s_dev;
-		__entry->ino		= inode->i_ino;
+		__entry->dev		= pa->pa_inode->i_sb->s_dev;
+		__entry->ino		= pa->pa_inode->i_ino;
 		__entry->block		= block;
 		__entry->count		= count;
 	),
@@ -591,10 +572,9 @@ TRACE_EVENT(ext4_mb_release_inode_pa,
 );
 
 TRACE_EVENT(ext4_mb_release_group_pa,
-	TP_PROTO(struct super_block *sb,
-		 struct ext4_prealloc_space *pa),
+	TP_PROTO(struct ext4_prealloc_space *pa),
 
-	TP_ARGS(sb, pa),
+	TP_ARGS(pa),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
@@ -604,7 +584,7 @@ TRACE_EVENT(ext4_mb_release_group_pa,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= sb->s_dev;
+		__entry->dev		= pa->pa_inode->i_sb->s_dev;
 		__entry->pa_pstart	= pa->pa_pstart;
 		__entry->pa_len		= pa->pa_len;
 	),
@@ -666,10 +646,10 @@ TRACE_EVENT(ext4_request_blocks,
 		__field(	ino_t,	ino			)
 		__field(	unsigned int, flags		)
 		__field(	unsigned int, len		)
-		__field(	__u64,  logical			)
+		__field(	__u32,  logical			)
+		__field(	__u32,	lleft			)
+		__field(	__u32,	lright			)
 		__field(	__u64,	goal			)
-		__field(	__u64,	lleft			)
-		__field(	__u64,	lright			)
 		__field(	__u64,	pleft			)
 		__field(	__u64,	pright			)
 	),
@@ -687,17 +667,13 @@ TRACE_EVENT(ext4_request_blocks,
 		__entry->pright	= ar->pright;
 	),
 
-	TP_printk("dev %d,%d ino %lu flags %u len %u lblk %llu goal %llu "
-		  "lleft %llu lright %llu pleft %llu pright %llu ",
+	TP_printk("dev %d,%d ino %lu flags %u len %u lblk %u goal %llu "
+		  "lleft %u lright %u pleft %llu pright %llu ",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino,
-		  __entry->flags, __entry->len,
-		  (unsigned long long) __entry->logical,
-		  (unsigned long long) __entry->goal,
-		  (unsigned long long) __entry->lleft,
-		  (unsigned long long) __entry->lright,
-		  (unsigned long long) __entry->pleft,
-		  (unsigned long long) __entry->pright)
+		  (unsigned long) __entry->ino, __entry->flags,
+		  __entry->len, __entry->logical, __entry->goal,
+		  __entry->lleft, __entry->lright, __entry->pleft,
+		  __entry->pright)
 );
 
 TRACE_EVENT(ext4_allocate_blocks,
@@ -711,10 +687,10 @@ TRACE_EVENT(ext4_allocate_blocks,
 		__field(	__u64,	block			)
 		__field(	unsigned int, flags		)
 		__field(	unsigned int, len		)
-		__field(	__u64,  logical			)
+		__field(	__u32,  logical			)
+		__field(	__u32,	lleft			)
+		__field(	__u32,	lright			)
 		__field(	__u64,	goal			)
-		__field(	__u64,	lleft			)
-		__field(	__u64,	lright			)
 		__field(	__u64,	pleft			)
 		__field(	__u64,	pright			)
 	),
@@ -733,17 +709,13 @@ TRACE_EVENT(ext4_allocate_blocks,
 		__entry->pright	= ar->pright;
 	),
 
-	TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %llu "
-		  "goal %llu lleft %llu lright %llu pleft %llu pright %llu",
+	TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %u "
+		  "goal %llu lleft %u lright %u pleft %llu pright %llu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino,
-		  __entry->flags, __entry->len, __entry->block,
-		  (unsigned long long) __entry->logical,
-		  (unsigned long long) __entry->goal,
-		  (unsigned long long) __entry->lleft,
-		  (unsigned long long) __entry->lright,
-		  (unsigned long long) __entry->pleft,
-		  (unsigned long long) __entry->pright)
+		  (unsigned long) __entry->ino, __entry->flags,
+		  __entry->len, __entry->block, __entry->logical,
+		  __entry->goal,  __entry->lleft, __entry->lright,
+		  __entry->pleft, __entry->pright)
 );
 
 TRACE_EVENT(ext4_free_blocks,
@@ -755,10 +727,10 @@ TRACE_EVENT(ext4_free_blocks,
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
-		__field(      umode_t, mode			)
+		__field(	umode_t, mode			)
 		__field(	__u64,	block			)
 		__field(	unsigned long,	count		)
-		__field(	 int,	flags			)
+		__field(	int,	flags			)
 	),
 
 	TP_fast_assign(
@@ -798,7 +770,7 @@ TRACE_EVENT(ext4_sync_file_enter,
 		__entry->parent		= dentry->d_parent->d_inode->i_ino;
 	),
 
-	TP_printk("dev %d,%d ino %ld parent %ld datasync %d ",
+	TP_printk("dev %d,%d ino %lu parent %lu datasync %d ",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  (unsigned long) __entry->parent, __entry->datasync)
@@ -821,7 +793,7 @@ TRACE_EVENT(ext4_sync_file_exit,
 		__entry->dev		= inode->i_sb->s_dev;
 	),
 
-	TP_printk("dev %d,%d ino %ld ret %d",
+	TP_printk("dev %d,%d ino %lu ret %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->ret)
@@ -1005,7 +977,7 @@ DECLARE_EVENT_CLASS(ext4__mballoc,
 		__entry->result_len	= len;
 	),
 
-	TP_printk("dev %d,%d inode %lu extent %u/%d/%u ",
+	TP_printk("dev %d,%d inode %lu extent %u/%d/%d ",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->result_group, __entry->result_start,
@@ -1093,7 +1065,7 @@ TRACE_EVENT(ext4_da_update_reserve_space,
 		  "allocated_meta_blocks %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  __entry->mode,  (unsigned long long) __entry->i_blocks,
+		  __entry->mode, __entry->i_blocks,
 		  __entry->used_blocks, __entry->reserved_data_blocks,
 		  __entry->reserved_meta_blocks, __entry->allocated_meta_blocks)
 );
@@ -1127,7 +1099,7 @@ TRACE_EVENT(ext4_da_reserve_space,
 		  "reserved_data_blocks %d reserved_meta_blocks %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  __entry->mode, (unsigned long long) __entry->i_blocks,
+		  __entry->mode, __entry->i_blocks,
 		  __entry->md_needed, __entry->reserved_data_blocks,
 		  __entry->reserved_meta_blocks)
 );
@@ -1164,7 +1136,7 @@ TRACE_EVENT(ext4_da_release_space,
 		  "allocated_meta_blocks %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  __entry->mode, (unsigned long long) __entry->i_blocks,
+		  __entry->mode, __entry->i_blocks,
 		  __entry->freed_blocks, __entry->reserved_data_blocks,
 		  __entry->reserved_meta_blocks, __entry->allocated_meta_blocks)
 );
@@ -1239,14 +1211,15 @@ TRACE_EVENT(ext4_direct_IO_enter,
 		__entry->rw	= rw;
 	),
 
-	TP_printk("dev %d,%d ino %lu pos %llu len %lu rw %d",
+	TP_printk("dev %d,%d ino %lu pos %lld len %lu rw %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  (unsigned long long) __entry->pos, __entry->len, __entry->rw)
+		  __entry->pos, __entry->len, __entry->rw)
 );
 
 TRACE_EVENT(ext4_direct_IO_exit,
-	TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, int rw, int ret),
+	TP_PROTO(struct inode *inode, loff_t offset, unsigned long len,
+		 int rw, int ret),
 
 	TP_ARGS(inode, offset, len, rw, ret),
 
@@ -1268,10 +1241,10 @@ TRACE_EVENT(ext4_direct_IO_exit,
 		__entry->ret	= ret;
 	),
 
-	TP_printk("dev %d,%d ino %lu pos %llu len %lu rw %d ret %d",
+	TP_printk("dev %d,%d ino %lu pos %lld len %lu rw %d ret %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  (unsigned long long) __entry->pos, __entry->len,
+		  __entry->pos, __entry->len,
 		  __entry->rw, __entry->ret)
 );
 
@@ -1296,15 +1269,15 @@ TRACE_EVENT(ext4_fallocate_enter,
 		__entry->mode	= mode;
 	),
 
-	TP_printk("dev %d,%d ino %ld pos %llu len %llu mode %d",
+	TP_printk("dev %d,%d ino %lu pos %lld len %lld mode %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino,
-		  (unsigned long long) __entry->pos,
-		  (unsigned long long) __entry->len, __entry->mode)
+		  (unsigned long) __entry->ino, __entry->pos,
+		  __entry->len, __entry->mode)
 );
 
 TRACE_EVENT(ext4_fallocate_exit,
-	TP_PROTO(struct inode *inode, loff_t offset, unsigned int max_blocks, int ret),
+	TP_PROTO(struct inode *inode, loff_t offset,
+		 unsigned int max_blocks, int ret),
 
 	TP_ARGS(inode, offset, max_blocks, ret),
 
@@ -1312,7 +1285,7 @@ TRACE_EVENT(ext4_fallocate_exit,
 		__field(	ino_t,	ino			)
 		__field(	dev_t,	dev			)
 		__field(	loff_t,	pos			)
-		__field(	unsigned,	blocks		)
+		__field(	unsigned int,	blocks		)
 		__field(	int, 	ret			)
 	),
 
@@ -1324,10 +1297,10 @@ TRACE_EVENT(ext4_fallocate_exit,
 		__entry->ret	= ret;
 	),
 
-	TP_printk("dev %d,%d ino %ld pos %llu blocks %d ret %d",
+	TP_printk("dev %d,%d ino %lu pos %lld blocks %u ret %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  (unsigned long long) __entry->pos, __entry->blocks,
+		  __entry->pos, __entry->blocks,
 		  __entry->ret)
 );
 
@@ -1350,7 +1323,7 @@ TRACE_EVENT(ext4_unlink_enter,
 		__entry->dev		= dentry->d_inode->i_sb->s_dev;
 	),
 
-	TP_printk("dev %d,%d ino %ld size %lld parent %ld",
+	TP_printk("dev %d,%d ino %lu size %lld parent %lu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino, __entry->size,
 		  (unsigned long) __entry->parent)
@@ -1373,7 +1346,7 @@ TRACE_EVENT(ext4_unlink_exit,
 		__entry->ret		= ret;
 	),
 
-	TP_printk("dev %d,%d ino %ld ret %d",
+	TP_printk("dev %d,%d ino %lu ret %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->ret)
@@ -1387,7 +1360,7 @@ DECLARE_EVENT_CLASS(ext4__truncate,
 	TP_STRUCT__entry(
 		__field(	ino_t,  	ino		)
 		__field(	dev_t,  	dev		)
-		__field(	blkcnt_t,	blocks		)
+		__field(	__u64,		blocks		)
 	),
 
 	TP_fast_assign(
@@ -1396,9 +1369,9 @@ DECLARE_EVENT_CLASS(ext4__truncate,
 		__entry->blocks	= inode->i_blocks;
 	),
 
-	TP_printk("dev %d,%d ino %lu blocks %lu",
+	TP_printk("dev %d,%d ino %lu blocks %llu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino, (unsigned long) __entry->blocks)
+		  (unsigned long) __entry->ino, __entry->blocks)
 );
 
 DEFINE_EVENT(ext4__truncate, ext4_truncate_enter,
@@ -1417,7 +1390,7 @@ DEFINE_EVENT(ext4__truncate, ext4_truncate_exit,
 
 DECLARE_EVENT_CLASS(ext4__map_blocks_enter,
 	TP_PROTO(struct inode *inode, ext4_lblk_t lblk,
-		 unsigned len, unsigned flags),
+		 unsigned int len, unsigned int flags),
 
 	TP_ARGS(inode, lblk, len, flags),
 
@@ -1425,8 +1398,8 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_enter,
 		__field(	ino_t,  	ino		)
 		__field(	dev_t,  	dev		)
 		__field(	ext4_lblk_t,	lblk		)
-		__field(	unsigned,	len		)
-		__field(	unsigned,	flags		)
+		__field(	unsigned int,	len		)
+		__field(	unsigned int,	flags		)
 	),
 
 	TP_fast_assign(
@@ -1440,7 +1413,7 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_enter,
 	TP_printk("dev %d,%d ino %lu lblk %u len %u flags %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  (unsigned) __entry->lblk, __entry->len, __entry->flags)
+		  __entry->lblk, __entry->len, __entry->flags)
 );
 
 DEFINE_EVENT(ext4__map_blocks_enter, ext4_ext_map_blocks_enter,
@@ -1459,7 +1432,7 @@ DEFINE_EVENT(ext4__map_blocks_enter, ext4_ind_map_blocks_enter,
 
 DECLARE_EVENT_CLASS(ext4__map_blocks_exit,
 	TP_PROTO(struct inode *inode, ext4_lblk_t lblk,
-		 ext4_fsblk_t pblk, unsigned len, int ret),
+		 ext4_fsblk_t pblk, unsigned int len, int ret),
 
 	TP_ARGS(inode, lblk, pblk, len, ret),
 
@@ -1468,7 +1441,7 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_exit,
 		__field(	dev_t,		dev		)
 		__field(	ext4_lblk_t,	lblk		)
 		__field(	ext4_fsblk_t,	pblk		)
-		__field(	unsigned,	len		)
+		__field(	unsigned int,	len		)
 		__field(	int,		ret		)
 	),
 
@@ -1484,7 +1457,7 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_exit,
 	TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u ret %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  (unsigned) __entry->lblk, (unsigned long long) __entry->pblk,
+		  __entry->lblk, __entry->pblk,
 		  __entry->len, __entry->ret)
 );
 
@@ -1524,7 +1497,7 @@ TRACE_EVENT(ext4_ext_load_extent,
 	TP_printk("dev %d,%d ino %lu lblk %u pblk %llu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  (unsigned) __entry->lblk, (unsigned long long) __entry->pblk)
+		  __entry->lblk, __entry->pblk)
 );
 
 TRACE_EVENT(ext4_load_inode,
diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h
index ae045ca7d356..1c09820df585 100644
--- a/include/trace/events/irq.h
+++ b/include/trace/events/irq.h
@@ -20,7 +20,8 @@ struct softirq_action;
 			 softirq_name(BLOCK_IOPOLL),	\
 			 softirq_name(TASKLET),		\
 			 softirq_name(SCHED),		\
-			 softirq_name(HRTIMER))
+			 softirq_name(HRTIMER),		\
+			 softirq_name(RCU))
 
 /**
  * irq_handler_entry - called immediately before the irq action handler
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index 5f247f5ffc56..f99645d05a8f 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -12,22 +12,24 @@
 TRACE_EVENT(net_dev_xmit,
 
 	TP_PROTO(struct sk_buff *skb,
-		 int rc),
+		 int rc,
+		 struct net_device *dev,
+		 unsigned int skb_len),
 
-	TP_ARGS(skb, rc),
+	TP_ARGS(skb, rc, dev, skb_len),
 
 	TP_STRUCT__entry(
 		__field(	void *,		skbaddr		)
 		__field(	unsigned int,	len		)
 		__field(	int,		rc		)
-		__string(	name,		skb->dev->name	)
+		__string(	name,		dev->name	)
 	),
 
 	TP_fast_assign(
 		__entry->skbaddr = skb;
-		__entry->len = skb->len;
+		__entry->len = skb_len;
 		__entry->rc = rc;
-		__assign_str(name, skb->dev->name);
+		__assign_str(name, dev->name);
 	),
 
 	TP_printk("dev=%s skbaddr=%p len=%u rc=%d",
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index ea422aaa23e1..b2c33bd955fa 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -6,6 +6,8 @@
 
 #include <linux/types.h>
 #include <linux/tracepoint.h>
+#include <linux/mm.h>
+#include <linux/memcontrol.h>
 #include "gfpflags.h"
 
 #define RECLAIM_WB_ANON		0x0001u
@@ -310,6 +312,87 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
 		show_reclaim_flags(__entry->reclaim_flags))
 );
 
+TRACE_EVENT(replace_swap_token,
+	TP_PROTO(struct mm_struct *old_mm,
+		 struct mm_struct *new_mm),
+
+	TP_ARGS(old_mm, new_mm),
+
+	TP_STRUCT__entry(
+		__field(struct mm_struct*,	old_mm)
+		__field(unsigned int,		old_prio)
+		__field(struct mm_struct*,	new_mm)
+		__field(unsigned int,		new_prio)
+	),
+
+	TP_fast_assign(
+		__entry->old_mm   = old_mm;
+		__entry->old_prio = old_mm ? old_mm->token_priority : 0;
+		__entry->new_mm   = new_mm;
+		__entry->new_prio = new_mm->token_priority;
+	),
+
+	TP_printk("old_token_mm=%p old_prio=%u new_token_mm=%p new_prio=%u",
+		  __entry->old_mm, __entry->old_prio,
+		  __entry->new_mm, __entry->new_prio)
+);
+
+DECLARE_EVENT_CLASS(put_swap_token_template,
+	TP_PROTO(struct mm_struct *swap_token_mm),
+
+	TP_ARGS(swap_token_mm),
+
+	TP_STRUCT__entry(
+		__field(struct mm_struct*, swap_token_mm)
+	),
+
+	TP_fast_assign(
+		__entry->swap_token_mm = swap_token_mm;
+	),
+
+	TP_printk("token_mm=%p", __entry->swap_token_mm)
+);
+
+DEFINE_EVENT(put_swap_token_template, put_swap_token,
+	TP_PROTO(struct mm_struct *swap_token_mm),
+	TP_ARGS(swap_token_mm)
+);
+
+DEFINE_EVENT_CONDITION(put_swap_token_template, disable_swap_token,
+	TP_PROTO(struct mm_struct *swap_token_mm),
+	TP_ARGS(swap_token_mm),
+	TP_CONDITION(swap_token_mm != NULL)
+);
+
+TRACE_EVENT_CONDITION(update_swap_token_priority,
+	TP_PROTO(struct mm_struct *mm,
+		 unsigned int old_prio,
+		 struct mm_struct *swap_token_mm),
+
+	TP_ARGS(mm, old_prio, swap_token_mm),
+
+	TP_CONDITION(mm->token_priority != old_prio),
+
+	TP_STRUCT__entry(
+		__field(struct mm_struct*, mm)
+		__field(unsigned int, old_prio)
+		__field(unsigned int, new_prio)
+		__field(struct mm_struct*, swap_token_mm)
+		__field(unsigned int, swap_token_prio)
+	),
+
+	TP_fast_assign(
+		__entry->mm		= mm;
+		__entry->old_prio	= old_prio;
+		__entry->new_prio	= mm->token_priority;
+		__entry->swap_token_mm	= swap_token_mm;
+		__entry->swap_token_prio = swap_token_mm ? swap_token_mm->token_priority : 0;
+	),
+
+	TP_printk("mm=%p old_prio=%u new_prio=%u swap_token_mm=%p token_prio=%u",
+		  __entry->mm, __entry->old_prio, __entry->new_prio,
+		  __entry->swap_token_mm, __entry->swap_token_prio)
+);
 
 #endif /* _TRACE_VMSCAN_H */
 
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 3e68366d485a..533c49f48047 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -205,6 +205,19 @@
 		ftrace_print_symbols_seq(p, value, symbols);		\
 	})
 
+#undef __print_symbolic_u64
+#if BITS_PER_LONG == 32
+#define __print_symbolic_u64(value, symbol_array...)			\
+	({								\
+		static const struct trace_print_flags_u64 symbols[] =	\
+			{ symbol_array, { -1, NULL } };			\
+		ftrace_print_symbols_seq_u64(p, value, symbols);	\
+	})
+#else
+#define __print_symbolic_u64(value, symbol_array...)			\
+			__print_symbolic(value, symbol_array)
+#endif
+
 #undef __print_hex
 #define __print_hex(buf, buf_len) ftrace_print_hex_seq(p, buf, buf_len)
 
diff --git a/init/Kconfig b/init/Kconfig
index ebafac4231ee..412c21b00d51 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -19,7 +19,6 @@ config DEFCONFIG_LIST
 config CONSTRUCTORS
 	bool
 	depends on !UML
-	default y
 
 config HAVE_IRQ_WORK
 	bool
@@ -204,6 +203,15 @@ config KERNEL_LZO
 
 endchoice
 
+config DEFAULT_HOSTNAME
+	string "Default hostname"
+	default "(none)"
+	help
+	  This option determines the default system hostname before userspace
+	  calls sethostname(2). The kernel traditionally uses "(none)" here,
+	  but you may wish to use a different default here to make a minimal
+	  system more usable with less configuration.
+
 config SWAP
 	bool "Support for paging of anonymous memory (swap)"
 	depends on MMU && BLOCK
diff --git a/init/calibrate.c b/init/calibrate.c
index cfd7000c9d71..aae2f40fea4c 100644
--- a/init/calibrate.c
+++ b/init/calibrate.c
@@ -93,9 +93,6 @@ static unsigned long __cpuinit calibrate_delay_direct(void)
 		 * If the upper limit and lower limit of the timer_rate is
 		 * >= 12.5% apart, redo calibration.
 		 */
-		printk(KERN_DEBUG "calibrate_delay_direct() timer_rate_max=%lu "
-			    "timer_rate_min=%lu pre_start=%lu pre_end=%lu\n",
-			  timer_rate_max, timer_rate_min, pre_start, pre_end);
 		if (start >= post_end)
 			printk(KERN_NOTICE "calibrate_delay_direct() ignoring "
 					"timer_rate as we had a TSC wrap around"
@@ -248,30 +245,32 @@ recalibrate:
 
 void __cpuinit calibrate_delay(void)
 {
+	unsigned long lpj;
 	static bool printed;
 
 	if (preset_lpj) {
-		loops_per_jiffy = preset_lpj;
+		lpj = preset_lpj;
 		if (!printed)
 			pr_info("Calibrating delay loop (skipped) "
 				"preset value.. ");
 	} else if ((!printed) && lpj_fine) {
-		loops_per_jiffy = lpj_fine;
+		lpj = lpj_fine;
 		pr_info("Calibrating delay loop (skipped), "
 			"value calculated using timer frequency.. ");
-	} else if ((loops_per_jiffy = calibrate_delay_direct()) != 0) {
+	} else if ((lpj = calibrate_delay_direct()) != 0) {
 		if (!printed)
 			pr_info("Calibrating delay using timer "
 				"specific routine.. ");
 	} else {
 		if (!printed)
 			pr_info("Calibrating delay loop... ");
-		loops_per_jiffy = calibrate_delay_converge();
+		lpj = calibrate_delay_converge();
 	}
 	if (!printed)
 		pr_cont("%lu.%02lu BogoMIPS (lpj=%lu)\n",
-			loops_per_jiffy/(500000/HZ),
-			(loops_per_jiffy/(5000/HZ)) % 100, loops_per_jiffy);
+			lpj/(500000/HZ),
+			(lpj/(5000/HZ)) % 100, lpj);
 
+	loops_per_jiffy = lpj;
 	printed = true;
 }
diff --git a/init/main.c b/init/main.c
index d2f1e086bf33..d7211faed2ad 100644
--- a/init/main.c
+++ b/init/main.c
@@ -487,6 +487,7 @@ asmlinkage void __init start_kernel(void)
 	printk(KERN_NOTICE "%s", linux_banner);
 	setup_arch(&command_line);
 	mm_init_owner(&init_mm, &init_task);
+	mm_init_cpumask(&init_mm);
 	setup_command_line(command_line);
 	setup_nr_cpu_ids();
 	setup_per_cpu_areas();
@@ -510,7 +511,6 @@ asmlinkage void __init start_kernel(void)
 	sort_main_extable();
 	trap_init();
 	mm_init();
-	BUG_ON(mm_init_cpumask(&init_mm, 0));
 
 	/*
 	 * Set up the scheduler prior starting any interrupts (such as the
@@ -542,6 +542,7 @@ asmlinkage void __init start_kernel(void)
 	timekeeping_init();
 	time_init();
 	profile_init();
+	call_function_init();
 	if (!irqs_disabled())
 		printk(KERN_CRIT "start_kernel(): bug: interrupts were "
 				 "enabled early\n");
diff --git a/kernel/cred.c b/kernel/cred.c
index e12c8af793f8..174fa84eca30 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -1,4 +1,4 @@
-/* Task credentials management - see Documentation/credentials.txt
+/* Task credentials management - see Documentation/security/credentials.txt
  *
  * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c09767f7db3e..9efe7108ccaf 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5028,6 +5028,14 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
 	else
 		perf_event_output(event, nmi, data, regs);
 
+	if (event->fasync && event->pending_kill) {
+		if (nmi) {
+			event->pending_wakeup = 1;
+			irq_work_queue(&event->pending);
+		} else
+			perf_event_wakeup(event);
+	}
+
 	return ret;
 }
 
@@ -7394,26 +7402,12 @@ static int __perf_cgroup_move(void *info)
 	return 0;
 }
 
-static void perf_cgroup_move(struct task_struct *task)
+static void
+perf_cgroup_attach_task(struct cgroup *cgrp, struct task_struct *task)
 {
 	task_function_call(task, __perf_cgroup_move, task);
 }
 
-static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-		struct cgroup *old_cgrp, struct task_struct *task,
-		bool threadgroup)
-{
-	perf_cgroup_move(task);
-	if (threadgroup) {
-		struct task_struct *c;
-		rcu_read_lock();
-		list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
-			perf_cgroup_move(c);
-		}
-		rcu_read_unlock();
-	}
-}
-
 static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
 		struct cgroup *old_cgrp, struct task_struct *task)
 {
@@ -7425,7 +7419,7 @@ static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
 	if (!(task->flags & PF_EXITING))
 		return;
 
-	perf_cgroup_move(task);
+	perf_cgroup_attach_task(cgrp, task);
 }
 
 struct cgroup_subsys perf_subsys = {
@@ -7434,6 +7428,6 @@ struct cgroup_subsys perf_subsys = {
 	.create		= perf_cgroup_create,
 	.destroy	= perf_cgroup_destroy,
 	.exit		= perf_cgroup_exit,
-	.attach		= perf_cgroup_attach,
+	.attach_task	= perf_cgroup_attach_task,
 };
 #endif /* CONFIG_CGROUP_PERF */
diff --git a/kernel/exit.c b/kernel/exit.c
index 20a406471525..f2b321bae440 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -561,29 +561,28 @@ void exit_files(struct task_struct *tsk)
 
 #ifdef CONFIG_MM_OWNER
 /*
- * Task p is exiting and it owned mm, lets find a new owner for it
+ * A task is exiting.   If it owned this mm, find a new owner for the mm.
  */
-static inline int
-mm_need_new_owner(struct mm_struct *mm, struct task_struct *p)
-{
-	/*
-	 * If there are other users of the mm and the owner (us) is exiting
-	 * we need to find a new owner to take on the responsibility.
-	 */
-	if (atomic_read(&mm->mm_users) <= 1)
-		return 0;
-	if (mm->owner != p)
-		return 0;
-	return 1;
-}
-
 void mm_update_next_owner(struct mm_struct *mm)
 {
 	struct task_struct *c, *g, *p = current;
 
 retry:
-	if (!mm_need_new_owner(mm, p))
+	/*
+	 * If the exiting or execing task is not the owner, it's
+	 * someone else's problem.
+	 */
+	if (mm->owner != p)
 		return;
+	/*
+	 * The current owner is exiting/execing and there are no other
+	 * candidates.  Do not leave the mm pointing to a possibly
+	 * freed task structure.
+	 */
+	if (atomic_read(&mm->mm_users) <= 1) {
+		mm->owner = NULL;
+		return;
+	}
 
 	read_lock(&tasklist_lock);
 	/*
diff --git a/kernel/fork.c b/kernel/fork.c
index ca406d916713..0276c30401a0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -484,20 +484,6 @@ static void mm_init_aio(struct mm_struct *mm)
 #endif
 }
 
-int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm)
-{
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	if (!alloc_cpumask_var(&mm->cpu_vm_mask_var, GFP_KERNEL))
-		return -ENOMEM;
-
-	if (oldmm)
-		cpumask_copy(mm_cpumask(mm), mm_cpumask(oldmm));
-	else
-		memset(mm_cpumask(mm), 0, cpumask_size());
-#endif
-	return 0;
-}
-
 static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 {
 	atomic_set(&mm->mm_users, 1);
@@ -538,17 +524,8 @@ struct mm_struct * mm_alloc(void)
 		return NULL;
 
 	memset(mm, 0, sizeof(*mm));
-	mm = mm_init(mm, current);
-	if (!mm)
-		return NULL;
-
-	if (mm_init_cpumask(mm, NULL)) {
-		mm_free_pgd(mm);
-		free_mm(mm);
-		return NULL;
-	}
-
-	return mm;
+	mm_init_cpumask(mm);
+	return mm_init(mm, current);
 }
 
 /*
@@ -559,7 +536,6 @@ struct mm_struct * mm_alloc(void)
 void __mmdrop(struct mm_struct *mm)
 {
 	BUG_ON(mm == &init_mm);
-	free_cpumask_var(mm->cpu_vm_mask_var);
 	mm_free_pgd(mm);
 	destroy_context(mm);
 	mmu_notifier_mm_destroy(mm);
@@ -753,6 +729,7 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 		goto fail_nomem;
 
 	memcpy(mm, oldmm, sizeof(*mm));
+	mm_init_cpumask(mm);
 
 	/* Initializing for Swap token stuff */
 	mm->token_priority = 0;
@@ -765,9 +742,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 
-	if (mm_init_cpumask(mm, oldmm))
-		goto fail_nocpumask;
-
 	if (init_new_context(tsk, mm))
 		goto fail_nocontext;
 
@@ -794,9 +768,6 @@ fail_nomem:
 	return NULL;
 
 fail_nocontext:
-	free_cpumask_var(mm->cpu_vm_mask_var);
-
-fail_nocpumask:
 	/*
 	 * If init_new_context() failed, we cannot use mmput() to free the mm
 	 * because it calls destroy_context()
@@ -1591,6 +1562,13 @@ void __init proc_caches_init(void)
 	fs_cachep = kmem_cache_create("fs_cache",
 			sizeof(struct fs_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
+	/*
+	 * FIXME! The "sizeof(struct mm_struct)" currently includes the
+	 * whole struct cpumask for the OFFSTACK case. We could change
+	 * this to *only* allocate as much of it as required by the
+	 * maximum number of CPU's we can ever have.  The cpumask_allocation
+	 * is at the end of the structure, exactly for that reason.
+	 */
 	mm_cachep = kmem_cache_create("mm_struct",
 			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index b8cadf70b1fb..5bf924d80b5c 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -2,7 +2,8 @@ menu "GCOV-based kernel profiling"
 
 config GCOV_KERNEL
 	bool "Enable gcov-based kernel profiling"
-	depends on DEBUG_FS && CONSTRUCTORS
+	depends on DEBUG_FS
+	select CONSTRUCTORS
 	default n
 	---help---
 	This option enables gcov-based code profiling (e.g. for code coverage
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 90cb55f6d7eb..470d08c82bbe 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -133,12 +133,6 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 		switch (res) {
 		case IRQ_WAKE_THREAD:
 			/*
-			 * Set result to handled so the spurious check
-			 * does not trigger.
-			 */
-			res = IRQ_HANDLED;
-
-			/*
 			 * Catch drivers which return WAKE_THREAD but
 			 * did not set up a thread function
 			 */
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 886e80347b32..4c60a50e66b2 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -257,13 +257,11 @@ int __init early_irq_init(void)
 	count = ARRAY_SIZE(irq_desc);
 
 	for (i = 0; i < count; i++) {
-		desc[i].irq_data.irq = i;
-		desc[i].irq_data.chip = &no_irq_chip;
 		desc[i].kstat_irqs = alloc_percpu(unsigned int);
-		irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS);
-		alloc_masks(desc + i, GFP_KERNEL, node);
-		desc_smp_init(desc + i, node);
+		alloc_masks(&desc[i], GFP_KERNEL, node);
+		raw_spin_lock_init(&desc[i].lock);
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
+		desc_set_defaults(i, &desc[i], node);
 	}
 	return arch_early_irq_init();
 }
@@ -346,6 +344,12 @@ irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node)
 	if (!cnt)
 		return -EINVAL;
 
+	if (irq >= 0) {
+		if (from > irq)
+			return -EINVAL;
+		from = irq;
+	}
+
 	mutex_lock(&sparse_irq_lock);
 
 	start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS,
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index f7ce0021e1c4..0a7840aeb0fb 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -491,6 +491,9 @@ int irq_set_irq_wake(unsigned int irq, unsigned int on)
 	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
 	int ret = 0;
 
+	if (!desc)
+		return -EINVAL;
+
 	/* wakeup-capable irqs can be shared between drivers that
 	 * don't need to have the same sleep mode behaviors.
 	 */
@@ -723,13 +726,16 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
  * context. So we need to disable bh here to avoid deadlocks and other
  * side effects.
  */
-static void
+static irqreturn_t
 irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
 {
+	irqreturn_t ret;
+
 	local_bh_disable();
-	action->thread_fn(action->irq, action->dev_id);
+	ret = action->thread_fn(action->irq, action->dev_id);
 	irq_finalize_oneshot(desc, action, false);
 	local_bh_enable();
+	return ret;
 }
 
 /*
@@ -737,10 +743,14 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
  * preemtible - many of them need to sleep and wait for slow busses to
  * complete.
  */
-static void irq_thread_fn(struct irq_desc *desc, struct irqaction *action)
+static irqreturn_t irq_thread_fn(struct irq_desc *desc,
+		struct irqaction *action)
 {
-	action->thread_fn(action->irq, action->dev_id);
+	irqreturn_t ret;
+
+	ret = action->thread_fn(action->irq, action->dev_id);
 	irq_finalize_oneshot(desc, action, false);
+	return ret;
 }
 
 /*
@@ -753,7 +763,8 @@ static int irq_thread(void *data)
 	};
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
-	void (*handler_fn)(struct irq_desc *desc, struct irqaction *action);
+	irqreturn_t (*handler_fn)(struct irq_desc *desc,
+			struct irqaction *action);
 	int wake;
 
 	if (force_irqthreads & test_bit(IRQTF_FORCED_THREAD,
@@ -783,8 +794,12 @@ static int irq_thread(void *data)
 			desc->istate |= IRQS_PENDING;
 			raw_spin_unlock_irq(&desc->lock);
 		} else {
+			irqreturn_t action_ret;
+
 			raw_spin_unlock_irq(&desc->lock);
-			handler_fn(desc, action);
+			action_ret = handler_fn(desc, action);
+			if (!noirqdebug)
+				note_interrupt(action->irq, desc, action_ret);
 		}
 
 		wake = atomic_dec_and_test(&desc->threads_active);
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index dfbd550401b2..aa57d5da18c1 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -167,6 +167,13 @@ out:
 		  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
 }
 
+static inline int bad_action_ret(irqreturn_t action_ret)
+{
+	if (likely(action_ret <= (IRQ_HANDLED | IRQ_WAKE_THREAD)))
+		return 0;
+	return 1;
+}
+
 /*
  * If 99,900 of the previous 100,000 interrupts have not been handled
  * then assume that the IRQ is stuck in some manner. Drop a diagnostic
@@ -182,7 +189,7 @@ __report_bad_irq(unsigned int irq, struct irq_desc *desc,
 	struct irqaction *action;
 	unsigned long flags;
 
-	if (action_ret != IRQ_HANDLED && action_ret != IRQ_NONE) {
+	if (bad_action_ret(action_ret)) {
 		printk(KERN_ERR "irq event %d: bogus return value %x\n",
 				irq, action_ret);
 	} else {
@@ -201,10 +208,11 @@ __report_bad_irq(unsigned int irq, struct irq_desc *desc,
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	action = desc->action;
 	while (action) {
-		printk(KERN_ERR "[<%p>]", action->handler);
-		print_symbol(" (%s)",
-			(unsigned long)action->handler);
-		printk("\n");
+		printk(KERN_ERR "[<%p>] %pf", action->handler, action->handler);
+		if (action->thread_fn)
+			printk(KERN_CONT " threaded [<%p>] %pf",
+					action->thread_fn, action->thread_fn);
+		printk(KERN_CONT "\n");
 		action = action->next;
 	}
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
@@ -262,7 +270,16 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
 	if (desc->istate & IRQS_POLL_INPROGRESS)
 		return;
 
-	if (unlikely(action_ret != IRQ_HANDLED)) {
+	/* we get here again via the threaded handler */
+	if (action_ret == IRQ_WAKE_THREAD)
+		return;
+
+	if (bad_action_ret(action_ret)) {
+		report_bad_irq(irq, desc, action_ret);
+		return;
+	}
+
+	if (unlikely(action_ret == IRQ_NONE)) {
 		/*
 		 * If we are seeing only the odd spurious IRQ caused by
 		 * bus asynchronicity then don't eventually trigger an error,
@@ -274,8 +291,6 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		else
 			desc->irqs_unhandled++;
 		desc->last_unhandled = jiffies;
-		if (unlikely(action_ret != IRQ_NONE))
-			report_bad_irq(irq, desc, action_ret);
 	}
 
 	if (unlikely(try_misrouted_irq(irq, desc, action_ret))) {
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 74d1c099fbd1..fa27e750dbc0 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -105,9 +105,12 @@ static int __jump_label_text_reserved(struct jump_entry *iter_start,
 }
 
 static void __jump_label_update(struct jump_label_key *key,
-		struct jump_entry *entry, int enable)
+				struct jump_entry *entry,
+				struct jump_entry *stop, int enable)
 {
-	for (; entry->key == (jump_label_t)(unsigned long)key; entry++) {
+	for (; (entry < stop) &&
+	      (entry->key == (jump_label_t)(unsigned long)key);
+	      entry++) {
 		/*
 		 * entry->code set to 0 invalidates module init text sections
 		 * kernel_text_address() verifies we are not in core kernel
@@ -181,7 +184,11 @@ static void __jump_label_mod_update(struct jump_label_key *key, int enable)
 	struct jump_label_mod *mod = key->next;
 
 	while (mod) {
-		__jump_label_update(key, mod->entries, enable);
+		struct module *m = mod->mod;
+
+		__jump_label_update(key, mod->entries,
+				    m->jump_entries + m->num_jump_entries,
+				    enable);
 		mod = mod->next;
 	}
 }
@@ -245,7 +252,8 @@ static int jump_label_add_module(struct module *mod)
 		key->next = jlm;
 
 		if (jump_label_enabled(key))
-			__jump_label_update(key, iter, JUMP_LABEL_ENABLE);
+			__jump_label_update(key, iter, iter_stop,
+					    JUMP_LABEL_ENABLE);
 	}
 
 	return 0;
@@ -371,7 +379,7 @@ static void jump_label_update(struct jump_label_key *key, int enable)
 
 	/* if there are no users, entry can be NULL */
 	if (entry)
-		__jump_label_update(key, entry, enable);
+		__jump_label_update(key, entry, __stop___jump_table, enable);
 
 #ifdef CONFIG_MODULES
 	__jump_label_mod_update(key, enable);
diff --git a/kernel/kmod.c b/kernel/kmod.c
index ad6a81c58b44..47613dfb7b28 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -156,12 +156,6 @@ static int ____call_usermodehelper(void *data)
 	 */
 	set_user_nice(current, 0);
 
-	if (sub_info->init) {
-		retval = sub_info->init(sub_info);
-		if (retval)
-			goto fail;
-	}
-
 	retval = -ENOMEM;
 	new = prepare_kernel_cred(current);
 	if (!new)
@@ -173,6 +167,14 @@ static int ____call_usermodehelper(void *data)
 					     new->cap_inheritable);
 	spin_unlock(&umh_sysctl_lock);
 
+	if (sub_info->init) {
+		retval = sub_info->init(sub_info, new);
+		if (retval) {
+			abort_creds(new);
+			goto fail;
+		}
+	}
+
 	commit_creds(new);
 
 	retval = kernel_execve(sub_info->path,
@@ -388,7 +390,7 @@ EXPORT_SYMBOL(call_usermodehelper_setup);
  * context in which call_usermodehelper_exec is called.
  */
 void call_usermodehelper_setfns(struct subprocess_info *info,
-		    int (*init)(struct subprocess_info *info),
+		    int (*init)(struct subprocess_info *info, struct cred *new),
 		    void (*cleanup)(struct subprocess_info *info),
 		    void *data)
 {
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 63437d065ac8..298c9276dfdb 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -3426,7 +3426,7 @@ int lock_is_held(struct lockdep_map *lock)
 	int ret = 0;
 
 	if (unlikely(current->lockdep_recursion))
-		return ret;
+		return 1; /* avoid false negative lockdep_assert_held() */
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index beb184689af9..6824ca7d4d0c 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -40,6 +40,7 @@
 #include <linux/string.h>
 #include <linux/platform_device.h>
 #include <linux/init.h>
+#include <linux/kernel.h>
 
 #include <linux/uaccess.h>
 
@@ -53,11 +54,17 @@ enum pm_qos_type {
 	PM_QOS_MIN		/* return the smallest value */
 };
 
+/*
+ * Note: The lockless read path depends on the CPU accessing
+ * target_value atomically.  Atomic access is only guaranteed on all CPU
+ * types linux supports for 32 bit quantites
+ */
 struct pm_qos_object {
 	struct plist_head requests;
 	struct blocking_notifier_head *notifiers;
 	struct miscdevice pm_qos_power_miscdev;
 	char *name;
+	s32 target_value;	/* Do not change to 64 bit */
 	s32 default_value;
 	enum pm_qos_type type;
 };
@@ -70,7 +77,8 @@ static struct pm_qos_object cpu_dma_pm_qos = {
 	.requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests, pm_qos_lock),
 	.notifiers = &cpu_dma_lat_notifier,
 	.name = "cpu_dma_latency",
-	.default_value = 2000 * USEC_PER_SEC,
+	.target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
+	.default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
 	.type = PM_QOS_MIN,
 };
 
@@ -79,7 +87,8 @@ static struct pm_qos_object network_lat_pm_qos = {
 	.requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests, pm_qos_lock),
 	.notifiers = &network_lat_notifier,
 	.name = "network_latency",
-	.default_value = 2000 * USEC_PER_SEC,
+	.target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
+	.default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
 	.type = PM_QOS_MIN
 };
 
@@ -89,7 +98,8 @@ static struct pm_qos_object network_throughput_pm_qos = {
 	.requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests, pm_qos_lock),
 	.notifiers = &network_throughput_notifier,
 	.name = "network_throughput",
-	.default_value = 0,
+	.target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
+	.default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
 	.type = PM_QOS_MAX,
 };
 
@@ -135,6 +145,16 @@ static inline int pm_qos_get_value(struct pm_qos_object *o)
 	}
 }
 
+static inline s32 pm_qos_read_value(struct pm_qos_object *o)
+{
+	return o->target_value;
+}
+
+static inline void pm_qos_set_value(struct pm_qos_object *o, s32 value)
+{
+	o->target_value = value;
+}
+
 static void update_target(struct pm_qos_object *o, struct plist_node *node,
 			  int del, int value)
 {
@@ -159,6 +179,7 @@ static void update_target(struct pm_qos_object *o, struct plist_node *node,
 		plist_add(node, &o->requests);
 	}
 	curr_value = pm_qos_get_value(o);
+	pm_qos_set_value(o, curr_value);
 	spin_unlock_irqrestore(&pm_qos_lock, flags);
 
 	if (prev_value != curr_value)
@@ -193,18 +214,11 @@ static int find_pm_qos_object_by_minor(int minor)
  * pm_qos_request - returns current system wide qos expectation
  * @pm_qos_class: identification of which qos value is requested
  *
- * This function returns the current target value in an atomic manner.
+ * This function returns the current target value.
  */
 int pm_qos_request(int pm_qos_class)
 {
-	unsigned long flags;
-	int value;
-
-	spin_lock_irqsave(&pm_qos_lock, flags);
-	value = pm_qos_get_value(pm_qos_array[pm_qos_class]);
-	spin_unlock_irqrestore(&pm_qos_lock, flags);
-
-	return value;
+	return pm_qos_read_value(pm_qos_array[pm_qos_class]);
 }
 EXPORT_SYMBOL_GPL(pm_qos_request);
 
@@ -404,24 +418,36 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
 		size_t count, loff_t *f_pos)
 {
 	s32 value;
-	int x;
-	char ascii_value[11];
 	struct pm_qos_request_list *pm_qos_req;
 
 	if (count == sizeof(s32)) {
 		if (copy_from_user(&value, buf, sizeof(s32)))
 			return -EFAULT;
-	} else if (count == 11) { /* len('0x12345678/0') */
-		if (copy_from_user(ascii_value, buf, 11))
+	} else if (count <= 11) { /* ASCII perhaps? */
+		char ascii_value[11];
+		unsigned long int ulval;
+		int ret;
+
+		if (copy_from_user(ascii_value, buf, count))
 			return -EFAULT;
-		if (strlen(ascii_value) != 10)
-			return -EINVAL;
-		x = sscanf(ascii_value, "%x", &value);
-		if (x != 1)
+
+		if (count > 10) {
+			if (ascii_value[10] == '\n')
+				ascii_value[10] = '\0';
+			else
+				return -EINVAL;
+		} else {
+			ascii_value[count] = '\0';
+		}
+		ret = strict_strtoul(ascii_value, 16, &ulval);
+		if (ret) {
+			pr_debug("%s, 0x%lx, 0x%x\n", ascii_value, ulval, ret);
 			return -EINVAL;
-		pr_debug("%s, %d, 0x%x\n", ascii_value, x, value);
-	} else
+		}
+		value = (s32)lower_32_bits(ulval);
+	} else {
 		return -EINVAL;
+	}
 
 	pm_qos_req = filp->private_data;
 	pm_qos_update_request(pm_qos_req, value);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index f9bec56d8825..8f7b1db1ece1 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -25,7 +25,6 @@
 #include <linux/gfp.h>
 #include <linux/syscore_ops.h>
 #include <scsi/scsi_scan.h>
-#include <asm/suspend.h>
 
 #include "power.h"
 
@@ -55,10 +54,9 @@ static int hibernation_mode = HIBERNATION_SHUTDOWN;
 static const struct platform_hibernation_ops *hibernation_ops;
 
 /**
- * hibernation_set_ops - set the global hibernate operations
- * @ops: the hibernation operations to use in subsequent hibernation transitions
+ * hibernation_set_ops - Set the global hibernate operations.
+ * @ops: Hibernation operations to use in subsequent hibernation transitions.
  */
-
 void hibernation_set_ops(const struct platform_hibernation_ops *ops)
 {
 	if (ops && !(ops->begin && ops->end &&  ops->pre_snapshot
@@ -115,10 +113,9 @@ static int hibernation_test(int level) { return 0; }
 #endif /* !CONFIG_PM_DEBUG */
 
 /**
- *	platform_begin - tell the platform driver that we're starting
- *	hibernation
+ * platform_begin - Call platform to start hibernation.
+ * @platform_mode: Whether or not to use the platform driver.
  */
-
 static int platform_begin(int platform_mode)
 {
 	return (platform_mode && hibernation_ops) ?
@@ -126,10 +123,9 @@ static int platform_begin(int platform_mode)
 }
 
 /**
- *	platform_end - tell the platform driver that we've entered the
- *	working state
+ * platform_end - Call platform to finish transition to the working state.
+ * @platform_mode: Whether or not to use the platform driver.
  */
-
 static void platform_end(int platform_mode)
 {
 	if (platform_mode && hibernation_ops)
@@ -137,8 +133,11 @@ static void platform_end(int platform_mode)
 }
 
 /**
- *	platform_pre_snapshot - prepare the machine for hibernation using the
- *	platform driver if so configured and return an error code if it fails
+ * platform_pre_snapshot - Call platform to prepare the machine for hibernation.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver to prepare the system for creating a hibernate image,
+ * if so configured, and return an error code if that fails.
  */
 
 static int platform_pre_snapshot(int platform_mode)
@@ -148,10 +147,14 @@ static int platform_pre_snapshot(int platform_mode)
 }
 
 /**
- *	platform_leave - prepare the machine for switching to the normal mode
- *	of operation using the platform driver (called with interrupts disabled)
+ * platform_leave - Call platform to prepare a transition to the working state.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver prepare to prepare the machine for switching to the
+ * normal mode of operation.
+ *
+ * This routine is called on one CPU with interrupts disabled.
  */
-
 static void platform_leave(int platform_mode)
 {
 	if (platform_mode && hibernation_ops)
@@ -159,10 +162,14 @@ static void platform_leave(int platform_mode)
 }
 
 /**
- *	platform_finish - switch the machine to the normal mode of operation
- *	using the platform driver (must be called after platform_prepare())
+ * platform_finish - Call platform to switch the system to the working state.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver to switch the machine to the normal mode of
+ * operation.
+ *
+ * This routine must be called after platform_prepare().
  */
-
 static void platform_finish(int platform_mode)
 {
 	if (platform_mode && hibernation_ops)
@@ -170,11 +177,15 @@ static void platform_finish(int platform_mode)
 }
 
 /**
- *	platform_pre_restore - prepare the platform for the restoration from a
- *	hibernation image.  If the restore fails after this function has been
- *	called, platform_restore_cleanup() must be called.
+ * platform_pre_restore - Prepare for hibernate image restoration.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver to prepare the system for resume from a hibernation
+ * image.
+ *
+ * If the restore fails after this function has been called,
+ * platform_restore_cleanup() must be called.
  */
-
 static int platform_pre_restore(int platform_mode)
 {
 	return (platform_mode && hibernation_ops) ?
@@ -182,12 +193,16 @@ static int platform_pre_restore(int platform_mode)
 }
 
 /**
- *	platform_restore_cleanup - switch the platform to the normal mode of
- *	operation after a failing restore.  If platform_pre_restore() has been
- *	called before the failing restore, this function must be called too,
- *	regardless of the result of platform_pre_restore().
+ * platform_restore_cleanup - Switch to the working state after failing restore.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver to switch the system to the normal mode of operation
+ * after a failing restore.
+ *
+ * If platform_pre_restore() has been called before the failing restore, this
+ * function must be called too, regardless of the result of
+ * platform_pre_restore().
  */
-
 static void platform_restore_cleanup(int platform_mode)
 {
 	if (platform_mode && hibernation_ops)
@@ -195,10 +210,9 @@ static void platform_restore_cleanup(int platform_mode)
 }
 
 /**
- *	platform_recover - recover the platform from a failure to suspend
- *	devices.
+ * platform_recover - Recover from a failure to suspend devices.
+ * @platform_mode: Whether or not to use the platform driver.
  */
-
 static void platform_recover(int platform_mode)
 {
 	if (platform_mode && hibernation_ops && hibernation_ops->recover)
@@ -206,13 +220,12 @@ static void platform_recover(int platform_mode)
 }
 
 /**
- *	swsusp_show_speed - print the time elapsed between two events.
- *	@start: Starting event.
- *	@stop: Final event.
- *	@nr_pages -	number of pages processed between @start and @stop
- *	@msg -		introductory message to print
+ * swsusp_show_speed - Print time elapsed between two events during hibernation.
+ * @start: Starting event.
+ * @stop: Final event.
+ * @nr_pages: Number of memory pages processed between @start and @stop.
+ * @msg: Additional diagnostic message to print.
  */
-
 void swsusp_show_speed(struct timeval *start, struct timeval *stop,
 			unsigned nr_pages, char *msg)
 {
@@ -235,25 +248,18 @@ void swsusp_show_speed(struct timeval *start, struct timeval *stop,
 }
 
 /**
- *	create_image - freeze devices that need to be frozen with interrupts
- *	off, create the hibernation image and thaw those devices.  Control
- *	reappears in this routine after a restore.
+ * create_image - Create a hibernation image.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Execute device drivers' .freeze_noirq() callbacks, create a hibernation image
+ * and execute the drivers' .thaw_noirq() callbacks.
+ *
+ * Control reappears in this routine after the subsequent restore.
  */
-
 static int create_image(int platform_mode)
 {
 	int error;
 
-	error = arch_prepare_suspend();
-	if (error)
-		return error;
-
-	/* At this point, dpm_suspend_start() has been called, but *not*
-	 * dpm_suspend_noirq(). We *must* call dpm_suspend_noirq() now.
-	 * Otherwise, drivers for some devices (e.g. interrupt controllers)
-	 * become desynchronized with the actual state of the hardware
-	 * at resume time, and evil weirdness ensues.
-	 */
 	error = dpm_suspend_noirq(PMSG_FREEZE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
@@ -297,9 +303,6 @@ static int create_image(int platform_mode)
 
  Power_up:
 	syscore_resume();
-	/* NOTE:  dpm_resume_noirq() is just a resume() for devices
-	 * that suspended with irqs off ... no overall powerup.
-	 */
 
  Enable_irqs:
 	local_irq_enable();
@@ -317,14 +320,11 @@ static int create_image(int platform_mode)
 }
 
 /**
- *	hibernation_snapshot - quiesce devices and create the hibernation
- *	snapshot image.
- *	@platform_mode - if set, use the platform driver, if available, to
- *			 prepare the platform firmware for the power transition.
+ * hibernation_snapshot - Quiesce devices and create a hibernation image.
+ * @platform_mode: If set, use platform driver to prepare for the transition.
  *
- *	Must be called with pm_mutex held
+ * This routine must be called with pm_mutex held.
  */
-
 int hibernation_snapshot(int platform_mode)
 {
 	pm_message_t msg = PMSG_RECOVER;
@@ -384,13 +384,14 @@ int hibernation_snapshot(int platform_mode)
 }
 
 /**
- *	resume_target_kernel - prepare devices that need to be suspended with
- *	interrupts off, restore the contents of highmem that have not been
- *	restored yet from the image and run the low level code that will restore
- *	the remaining contents of memory and switch to the just restored target
- *	kernel.
+ * resume_target_kernel - Restore system state from a hibernation image.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Execute device drivers' .freeze_noirq() callbacks, restore the contents of
+ * highmem that have not been restored yet from the image and run the low-level
+ * code that will restore the remaining contents of memory and switch to the
+ * just restored target kernel.
  */
-
 static int resume_target_kernel(bool platform_mode)
 {
 	int error;
@@ -416,24 +417,26 @@ static int resume_target_kernel(bool platform_mode)
 	if (error)
 		goto Enable_irqs;
 
-	/* We'll ignore saved state, but this gets preempt count (etc) right */
 	save_processor_state();
 	error = restore_highmem();
 	if (!error) {
 		error = swsusp_arch_resume();
 		/*
 		 * The code below is only ever reached in case of a failure.
-		 * Otherwise execution continues at place where
-		 * swsusp_arch_suspend() was called
+		 * Otherwise, execution continues at the place where
+		 * swsusp_arch_suspend() was called.
 		 */
 		BUG_ON(!error);
-		/* This call to restore_highmem() undos the previous one */
+		/*
+		 * This call to restore_highmem() reverts the changes made by
+		 * the previous one.
+		 */
 		restore_highmem();
 	}
 	/*
 	 * The only reason why swsusp_arch_resume() can fail is memory being
 	 * very tight, so we have to free it as soon as we can to avoid
-	 * subsequent failures
+	 * subsequent failures.
 	 */
 	swsusp_free();
 	restore_processor_state();
@@ -456,14 +459,12 @@ static int resume_target_kernel(bool platform_mode)
 }
 
 /**
- *	hibernation_restore - quiesce devices and restore the hibernation
- *	snapshot image.  If successful, control returns in hibernation_snaphot()
- *	@platform_mode - if set, use the platform driver, if available, to
- *			 prepare the platform firmware for the transition.
+ * hibernation_restore - Quiesce devices and restore from a hibernation image.
+ * @platform_mode: If set, use platform driver to prepare for the transition.
  *
- *	Must be called with pm_mutex held
+ * This routine must be called with pm_mutex held.  If it is successful, control
+ * reappears in the restored target kernel in hibernation_snaphot().
  */
-
 int hibernation_restore(int platform_mode)
 {
 	int error;
@@ -483,10 +484,8 @@ int hibernation_restore(int platform_mode)
 }
 
 /**
- *	hibernation_platform_enter - enter the hibernation state using the
- *	platform driver (if available)
+ * hibernation_platform_enter - Power off the system using the platform driver.
  */
-
 int hibernation_platform_enter(void)
 {
 	int error;
@@ -557,12 +556,12 @@ int hibernation_platform_enter(void)
 }
 
 /**
- *	power_down - Shut the machine down for hibernation.
+ * power_down - Shut the machine down for hibernation.
  *
- *	Use the platform driver, if configured so; otherwise try
- *	to power off or reboot.
+ * Use the platform driver, if configured, to put the system into the sleep
+ * state corresponding to hibernation, or try to power it off or reboot,
+ * depending on the value of hibernation_mode.
  */
-
 static void power_down(void)
 {
 	switch (hibernation_mode) {
@@ -599,9 +598,8 @@ static int prepare_processes(void)
 }
 
 /**
- *	hibernate - The granpappy of the built-in hibernation management
+ * hibernate - Carry out system hibernation, including saving the image.
  */
-
 int hibernate(void)
 {
 	int error;
@@ -679,17 +677,20 @@ int hibernate(void)
 
 
 /**
- *	software_resume - Resume from a saved image.
+ * software_resume - Resume from a saved hibernation image.
  *
- *	Called as a late_initcall (so all devices are discovered and
- *	initialized), we call swsusp to see if we have a saved image or not.
- *	If so, we quiesce devices, the restore the saved image. We will
- *	return above (in hibernate() ) if everything goes well.
- *	Otherwise, we fail gracefully and return to the normally
- *	scheduled program.
+ * This routine is called as a late initcall, when all devices have been
+ * discovered and initialized already.
  *
+ * The image reading code is called to see if there is a hibernation image
+ * available for reading.  If that is the case, devices are quiesced and the
+ * contents of memory is restored from the saved image.
+ *
+ * If this is successful, control reappears in the restored target kernel in
+ * hibernation_snaphot() which returns to hibernate().  Otherwise, the routine
+ * attempts to recover gracefully and make the kernel return to the normal mode
+ * of operation.
  */
-
 static int software_resume(void)
 {
 	int error;
@@ -819,21 +820,17 @@ static const char * const hibernation_modes[] = {
 	[HIBERNATION_TESTPROC]	= "testproc",
 };
 
-/**
- *	disk - Control hibernation mode
- *
- *	Suspend-to-disk can be handled in several ways. We have a few options
- *	for putting the system to sleep - using the platform driver (e.g. ACPI
- *	or other hibernation_ops), powering off the system or rebooting the
- *	system (for testing) as well as the two test modes.
+/*
+ * /sys/power/disk - Control hibernation mode.
  *
- *	The system can support 'platform', and that is known a priori (and
- *	encoded by the presence of hibernation_ops). However, the user may
- *	choose 'shutdown' or 'reboot' as alternatives, as well as one fo the
- *	test modes, 'test' or 'testproc'.
+ * Hibernation can be handled in several ways.  There are a few different ways
+ * to put the system into the sleep state: using the platform driver (e.g. ACPI
+ * or other hibernation_ops), powering it off or rebooting it (for testing
+ * mostly), or using one of the two available test modes.
  *
- *	show() will display what the mode is currently set to.
- *	store() will accept one of
+ * The sysfs file /sys/power/disk provides an interface for selecting the
+ * hibernation mode to use.  Reading from this file causes the available modes
+ * to be printed.  There are 5 modes that can be supported:
  *
  *	'platform'
  *	'shutdown'
@@ -841,8 +838,14 @@ static const char * const hibernation_modes[] = {
  *	'test'
  *	'testproc'
  *
- *	It will only change to 'platform' if the system
- *	supports it (as determined by having hibernation_ops).
+ * If a platform hibernation driver is in use, 'platform' will be supported
+ * and will be used by default.  Otherwise, 'shutdown' will be used by default.
+ * The selected option (i.e. the one corresponding to the current value of
+ * hibernation_mode) is enclosed by a square bracket.
+ *
+ * To select a given hibernation mode it is necessary to write the mode's
+ * string representation (as returned by reading from /sys/power/disk) back
+ * into /sys/power/disk.
  */
 
 static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
@@ -875,7 +878,6 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
 	return buf-start;
 }
 
-
 static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
 			  const char *buf, size_t n)
 {
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 7d02d33be699..42ddbc6f0de6 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -113,8 +113,10 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 		if (error)
 			pm_notifier_call_chain(PM_POST_RESTORE);
 	}
-	if (error)
+	if (error) {
+		free_basic_memory_bitmaps();
 		atomic_inc(&snapshot_device_available);
+	}
 	data->frozen = 0;
 	data->ready = 0;
 	data->platform_support = 0;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index f07d2f03181a..7e59ffb3d0ba 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -36,7 +36,7 @@
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/nmi.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/completion.h>
@@ -87,6 +87,8 @@ static struct rcu_state *rcu_state;
 int rcu_scheduler_active __read_mostly;
 EXPORT_SYMBOL_GPL(rcu_scheduler_active);
 
+#ifdef CONFIG_RCU_BOOST
+
 /*
  * Control variables for per-CPU and per-rcu_node kthreads.  These
  * handle all flavors of RCU.
@@ -95,12 +97,14 @@ static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
-static DEFINE_PER_CPU(wait_queue_head_t, rcu_cpu_wq);
 DEFINE_PER_CPU(char, rcu_cpu_has_work);
 static char rcu_kthreads_spawnable;
 
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
 static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
-static void invoke_rcu_cpu_kthread(void);
+static void invoke_rcu_core(void);
+static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
 
 #define RCU_KTHREAD_PRIO 1	/* RT priority for per-CPU kthreads. */
 
@@ -163,7 +167,7 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 #ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = 1,
-	.dynticks = 1,
+	.dynticks = ATOMIC_INIT(1),
 };
 #endif /* #ifdef CONFIG_NO_HZ */
 
@@ -322,13 +326,25 @@ void rcu_enter_nohz(void)
 	unsigned long flags;
 	struct rcu_dynticks *rdtp;
 
-	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
-	rdtp->dynticks++;
-	rdtp->dynticks_nesting--;
-	WARN_ON_ONCE(rdtp->dynticks & 0x1);
+	if (--rdtp->dynticks_nesting) {
+		local_irq_restore(flags);
+		return;
+	}
+	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+	smp_mb__before_atomic_inc();  /* See above. */
+	atomic_inc(&rdtp->dynticks);
+	smp_mb__after_atomic_inc();  /* Force ordering with next sojourn. */
+	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
 	local_irq_restore(flags);
+
+	/* If the interrupt queued a callback, get out of dyntick mode. */
+	if (in_irq() &&
+	    (__get_cpu_var(rcu_sched_data).nxtlist ||
+	     __get_cpu_var(rcu_bh_data).nxtlist ||
+	     rcu_preempt_needs_cpu(smp_processor_id())))
+		set_need_resched();
 }
 
 /*
@@ -344,11 +360,16 @@ void rcu_exit_nohz(void)
 
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
-	rdtp->dynticks++;
-	rdtp->dynticks_nesting++;
-	WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
+	if (rdtp->dynticks_nesting++) {
+		local_irq_restore(flags);
+		return;
+	}
+	smp_mb__before_atomic_inc();  /* Force ordering w/previous sojourn. */
+	atomic_inc(&rdtp->dynticks);
+	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
+	smp_mb__after_atomic_inc();  /* See above. */
+	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
 	local_irq_restore(flags);
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 }
 
 /**
@@ -362,11 +383,15 @@ void rcu_nmi_enter(void)
 {
 	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
 
-	if (rdtp->dynticks & 0x1)
+	if (rdtp->dynticks_nmi_nesting == 0 &&
+	    (atomic_read(&rdtp->dynticks) & 0x1))
 		return;
-	rdtp->dynticks_nmi++;
-	WARN_ON_ONCE(!(rdtp->dynticks_nmi & 0x1));
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+	rdtp->dynticks_nmi_nesting++;
+	smp_mb__before_atomic_inc();  /* Force delay from prior write. */
+	atomic_inc(&rdtp->dynticks);
+	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
+	smp_mb__after_atomic_inc();  /* See above. */
+	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
 }
 
 /**
@@ -380,11 +405,14 @@ void rcu_nmi_exit(void)
 {
 	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
 
-	if (rdtp->dynticks & 0x1)
+	if (rdtp->dynticks_nmi_nesting == 0 ||
+	    --rdtp->dynticks_nmi_nesting != 0)
 		return;
-	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-	rdtp->dynticks_nmi++;
-	WARN_ON_ONCE(rdtp->dynticks_nmi & 0x1);
+	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+	smp_mb__before_atomic_inc();  /* See above. */
+	atomic_inc(&rdtp->dynticks);
+	smp_mb__after_atomic_inc();  /* Force delay to next write. */
+	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
 }
 
 /**
@@ -395,13 +423,7 @@ void rcu_nmi_exit(void)
  */
 void rcu_irq_enter(void)
 {
-	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
-
-	if (rdtp->dynticks_nesting++)
-		return;
-	rdtp->dynticks++;
-	WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+	rcu_exit_nohz();
 }
 
 /**
@@ -413,18 +435,7 @@ void rcu_irq_enter(void)
  */
 void rcu_irq_exit(void)
 {
-	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
-
-	if (--rdtp->dynticks_nesting)
-		return;
-	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-	rdtp->dynticks++;
-	WARN_ON_ONCE(rdtp->dynticks & 0x1);
-
-	/* If the interrupt queued a callback, get out of dyntick mode. */
-	if (__this_cpu_read(rcu_sched_data.nxtlist) ||
-	    __this_cpu_read(rcu_bh_data.nxtlist))
-		set_need_resched();
+	rcu_enter_nohz();
 }
 
 #ifdef CONFIG_SMP
@@ -436,19 +447,8 @@ void rcu_irq_exit(void)
  */
 static int dyntick_save_progress_counter(struct rcu_data *rdp)
 {
-	int ret;
-	int snap;
-	int snap_nmi;
-
-	snap = rdp->dynticks->dynticks;
-	snap_nmi = rdp->dynticks->dynticks_nmi;
-	smp_mb();	/* Order sampling of snap with end of grace period. */
-	rdp->dynticks_snap = snap;
-	rdp->dynticks_nmi_snap = snap_nmi;
-	ret = ((snap & 0x1) == 0) && ((snap_nmi & 0x1) == 0);
-	if (ret)
-		rdp->dynticks_fqs++;
-	return ret;
+	rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
+	return 0;
 }
 
 /*
@@ -459,16 +459,11 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
  */
 static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 {
-	long curr;
-	long curr_nmi;
-	long snap;
-	long snap_nmi;
+	unsigned long curr;
+	unsigned long snap;
 
-	curr = rdp->dynticks->dynticks;
-	snap = rdp->dynticks_snap;
-	curr_nmi = rdp->dynticks->dynticks_nmi;
-	snap_nmi = rdp->dynticks_nmi_snap;
-	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+	curr = (unsigned long)atomic_add_return(0, &rdp->dynticks->dynticks);
+	snap = (unsigned long)rdp->dynticks_snap;
 
 	/*
 	 * If the CPU passed through or entered a dynticks idle phase with
@@ -478,8 +473,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 * read-side critical section that started before the beginning
 	 * of the current RCU grace period.
 	 */
-	if ((curr != snap || (curr & 0x1) == 0) &&
-	    (curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) {
+	if ((curr & 0x1) == 0 || ULONG_CMP_GE(curr, snap + 2)) {
 		rdp->dynticks_fqs++;
 		return 1;
 	}
@@ -908,6 +902,12 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	unsigned long gp_duration;
 
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
+
+	/*
+	 * Ensure that all grace-period and pre-grace-period activity
+	 * is seen before the assignment to rsp->completed.
+	 */
+	smp_mb(); /* See above block comment. */
 	gp_duration = jiffies - rsp->gp_start;
 	if (gp_duration > rsp->gp_max)
 		rsp->gp_max = gp_duration;
@@ -1093,14 +1093,8 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 	int need_report = 0;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp;
-	struct task_struct *t;
 
-	/* Stop the CPU's kthread. */
-	t = per_cpu(rcu_cpu_kthread_task, cpu);
-	if (t != NULL) {
-		per_cpu(rcu_cpu_kthread_task, cpu) = NULL;
-		kthread_stop(t);
-	}
+	rcu_stop_cpu_kthread(cpu);
 
 	/* Exclude any attempts to start a new grace period. */
 	raw_spin_lock_irqsave(&rsp->onofflock, flags);
@@ -1236,7 +1230,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	/* Re-raise the RCU softirq if there are callbacks remaining. */
 	if (cpu_has_callbacks_ready_to_invoke(rdp))
-		invoke_rcu_cpu_kthread();
+		invoke_rcu_core();
 }
 
 /*
@@ -1282,7 +1276,7 @@ void rcu_check_callbacks(int cpu, int user)
 	}
 	rcu_preempt_check_callbacks(cpu);
 	if (rcu_pending(cpu))
-		invoke_rcu_cpu_kthread();
+		invoke_rcu_core();
 }
 
 #ifdef CONFIG_SMP
@@ -1447,33 +1441,20 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 
 	/* If there are callbacks ready, invoke them. */
-	rcu_do_batch(rsp, rdp);
+	if (cpu_has_callbacks_ready_to_invoke(rdp))
+		invoke_rcu_callbacks(rsp, rdp);
 }
 
 /*
  * Do softirq processing for the current CPU.
  */
-static void rcu_process_callbacks(void)
+static void rcu_process_callbacks(struct softirq_action *unused)
 {
-	/*
-	 * Memory references from any prior RCU read-side critical sections
-	 * executed by the interrupted code must be seen before any RCU
-	 * grace-period manipulations below.
-	 */
-	smp_mb(); /* See above block comment. */
-
 	__rcu_process_callbacks(&rcu_sched_state,
 				&__get_cpu_var(rcu_sched_data));
 	__rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
 	rcu_preempt_process_callbacks();
 
-	/*
-	 * Memory references from any later RCU read-side critical sections
-	 * executed by the interrupted code must be seen after any RCU
-	 * grace-period manipulations above.
-	 */
-	smp_mb(); /* See above block comment. */
-
 	/* If we are last CPU on way to dyntick-idle mode, accelerate it. */
 	rcu_needs_cpu_flush();
 }
@@ -1484,341 +1465,20 @@ static void rcu_process_callbacks(void)
  * the current CPU with interrupts disabled, the rcu_cpu_kthread_task
  * cannot disappear out from under us.
  */
-static void invoke_rcu_cpu_kthread(void)
+static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__this_cpu_write(rcu_cpu_has_work, 1);
-	if (__this_cpu_read(rcu_cpu_kthread_task) == NULL) {
-		local_irq_restore(flags);
+	if (likely(!rsp->boost)) {
+		rcu_do_batch(rsp, rdp);
 		return;
 	}
-	wake_up(&__get_cpu_var(rcu_cpu_wq));
-	local_irq_restore(flags);
-}
-
-/*
- * Wake up the specified per-rcu_node-structure kthread.
- * Because the per-rcu_node kthreads are immortal, we don't need
- * to do anything to keep them alive.
- */
-static void invoke_rcu_node_kthread(struct rcu_node *rnp)
-{
-	struct task_struct *t;
-
-	t = rnp->node_kthread_task;
-	if (t != NULL)
-		wake_up_process(t);
+	invoke_rcu_callbacks_kthread();
 }
 
-/*
- * Set the specified CPU's kthread to run RT or not, as specified by
- * the to_rt argument.  The CPU-hotplug locks are held, so the task
- * is not going away.
- */
-static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
+static void invoke_rcu_core(void)
 {
-	int policy;
-	struct sched_param sp;
-	struct task_struct *t;
-
-	t = per_cpu(rcu_cpu_kthread_task, cpu);
-	if (t == NULL)
-		return;
-	if (to_rt) {
-		policy = SCHED_FIFO;
-		sp.sched_priority = RCU_KTHREAD_PRIO;
-	} else {
-		policy = SCHED_NORMAL;
-		sp.sched_priority = 0;
-	}
-	sched_setscheduler_nocheck(t, policy, &sp);
+	raise_softirq(RCU_SOFTIRQ);
 }
 
-/*
- * Timer handler to initiate the waking up of per-CPU kthreads that
- * have yielded the CPU due to excess numbers of RCU callbacks.
- * We wake up the per-rcu_node kthread, which in turn will wake up
- * the booster kthread.
- */
-static void rcu_cpu_kthread_timer(unsigned long arg)
-{
-	unsigned long flags;
-	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg);
-	struct rcu_node *rnp = rdp->mynode;
-
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	rnp->wakemask |= rdp->grpmask;
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	invoke_rcu_node_kthread(rnp);
-}
-
-/*
- * Drop to non-real-time priority and yield, but only after posting a
- * timer that will cause us to regain our real-time priority if we
- * remain preempted.  Either way, we restore our real-time priority
- * before returning.
- */
-static void rcu_yield(void (*f)(unsigned long), unsigned long arg)
-{
-	struct sched_param sp;
-	struct timer_list yield_timer;
-
-	setup_timer_on_stack(&yield_timer, f, arg);
-	mod_timer(&yield_timer, jiffies + 2);
-	sp.sched_priority = 0;
-	sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp);
-	set_user_nice(current, 19);
-	schedule();
-	sp.sched_priority = RCU_KTHREAD_PRIO;
-	sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
-	del_timer(&yield_timer);
-}
-
-/*
- * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU.
- * This can happen while the corresponding CPU is either coming online
- * or going offline.  We cannot wait until the CPU is fully online
- * before starting the kthread, because the various notifier functions
- * can wait for RCU grace periods.  So we park rcu_cpu_kthread() until
- * the corresponding CPU is online.
- *
- * Return 1 if the kthread needs to stop, 0 otherwise.
- *
- * Caller must disable bh.  This function can momentarily enable it.
- */
-static int rcu_cpu_kthread_should_stop(int cpu)
-{
-	while (cpu_is_offline(cpu) ||
-	       !cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)) ||
-	       smp_processor_id() != cpu) {
-		if (kthread_should_stop())
-			return 1;
-		per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
-		per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id();
-		local_bh_enable();
-		schedule_timeout_uninterruptible(1);
-		if (!cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)))
-			set_cpus_allowed_ptr(current, cpumask_of(cpu));
-		local_bh_disable();
-	}
-	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
-	return 0;
-}
-
-/*
- * Per-CPU kernel thread that invokes RCU callbacks.  This replaces the
- * earlier RCU softirq.
- */
-static int rcu_cpu_kthread(void *arg)
-{
-	int cpu = (int)(long)arg;
-	unsigned long flags;
-	int spincnt = 0;
-	unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu);
-	wait_queue_head_t *wqp = &per_cpu(rcu_cpu_wq, cpu);
-	char work;
-	char *workp = &per_cpu(rcu_cpu_has_work, cpu);
-
-	for (;;) {
-		*statusp = RCU_KTHREAD_WAITING;
-		wait_event_interruptible(*wqp,
-					 *workp != 0 || kthread_should_stop());
-		local_bh_disable();
-		if (rcu_cpu_kthread_should_stop(cpu)) {
-			local_bh_enable();
-			break;
-		}
-		*statusp = RCU_KTHREAD_RUNNING;
-		per_cpu(rcu_cpu_kthread_loops, cpu)++;
-		local_irq_save(flags);
-		work = *workp;
-		*workp = 0;
-		local_irq_restore(flags);
-		if (work)
-			rcu_process_callbacks();
-		local_bh_enable();
-		if (*workp != 0)
-			spincnt++;
-		else
-			spincnt = 0;
-		if (spincnt > 10) {
-			*statusp = RCU_KTHREAD_YIELDING;
-			rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu);
-			spincnt = 0;
-		}
-	}
-	*statusp = RCU_KTHREAD_STOPPED;
-	return 0;
-}
-
-/*
- * Spawn a per-CPU kthread, setting up affinity and priority.
- * Because the CPU hotplug lock is held, no other CPU will be attempting
- * to manipulate rcu_cpu_kthread_task.  There might be another CPU
- * attempting to access it during boot, but the locking in kthread_bind()
- * will enforce sufficient ordering.
- */
-static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
-{
-	struct sched_param sp;
-	struct task_struct *t;
-
-	if (!rcu_kthreads_spawnable ||
-	    per_cpu(rcu_cpu_kthread_task, cpu) != NULL)
-		return 0;
-	t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu);
-	if (IS_ERR(t))
-		return PTR_ERR(t);
-	kthread_bind(t, cpu);
-	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
-	WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
-	per_cpu(rcu_cpu_kthread_task, cpu) = t;
-	wake_up_process(t);
-	sp.sched_priority = RCU_KTHREAD_PRIO;
-	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
-	return 0;
-}
-
-/*
- * Per-rcu_node kthread, which is in charge of waking up the per-CPU
- * kthreads when needed.  We ignore requests to wake up kthreads
- * for offline CPUs, which is OK because force_quiescent_state()
- * takes care of this case.
- */
-static int rcu_node_kthread(void *arg)
-{
-	int cpu;
-	unsigned long flags;
-	unsigned long mask;
-	struct rcu_node *rnp = (struct rcu_node *)arg;
-	struct sched_param sp;
-	struct task_struct *t;
-
-	for (;;) {
-		rnp->node_kthread_status = RCU_KTHREAD_WAITING;
-		wait_event_interruptible(rnp->node_wq, rnp->wakemask != 0);
-		rnp->node_kthread_status = RCU_KTHREAD_RUNNING;
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		mask = rnp->wakemask;
-		rnp->wakemask = 0;
-		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
-		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) {
-			if ((mask & 0x1) == 0)
-				continue;
-			preempt_disable();
-			t = per_cpu(rcu_cpu_kthread_task, cpu);
-			if (!cpu_online(cpu) || t == NULL) {
-				preempt_enable();
-				continue;
-			}
-			per_cpu(rcu_cpu_has_work, cpu) = 1;
-			sp.sched_priority = RCU_KTHREAD_PRIO;
-			sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
-			preempt_enable();
-		}
-	}
-	/* NOTREACHED */
-	rnp->node_kthread_status = RCU_KTHREAD_STOPPED;
-	return 0;
-}
-
-/*
- * Set the per-rcu_node kthread's affinity to cover all CPUs that are
- * served by the rcu_node in question.  The CPU hotplug lock is still
- * held, so the value of rnp->qsmaskinit will be stable.
- *
- * We don't include outgoingcpu in the affinity set, use -1 if there is
- * no outgoing CPU.  If there are no CPUs left in the affinity set,
- * this function allows the kthread to execute on any CPU.
- */
-static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
-{
-	cpumask_var_t cm;
-	int cpu;
-	unsigned long mask = rnp->qsmaskinit;
-
-	if (rnp->node_kthread_task == NULL)
-		return;
-	if (!alloc_cpumask_var(&cm, GFP_KERNEL))
-		return;
-	cpumask_clear(cm);
-	for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1)
-		if ((mask & 0x1) && cpu != outgoingcpu)
-			cpumask_set_cpu(cpu, cm);
-	if (cpumask_weight(cm) == 0) {
-		cpumask_setall(cm);
-		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++)
-			cpumask_clear_cpu(cpu, cm);
-		WARN_ON_ONCE(cpumask_weight(cm) == 0);
-	}
-	set_cpus_allowed_ptr(rnp->node_kthread_task, cm);
-	rcu_boost_kthread_setaffinity(rnp, cm);
-	free_cpumask_var(cm);
-}
-
-/*
- * Spawn a per-rcu_node kthread, setting priority and affinity.
- * Called during boot before online/offline can happen, or, if
- * during runtime, with the main CPU-hotplug locks held.  So only
- * one of these can be executing at a time.
- */
-static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
-						struct rcu_node *rnp)
-{
-	unsigned long flags;
-	int rnp_index = rnp - &rsp->node[0];
-	struct sched_param sp;
-	struct task_struct *t;
-
-	if (!rcu_kthreads_spawnable ||
-	    rnp->qsmaskinit == 0)
-		return 0;
-	if (rnp->node_kthread_task == NULL) {
-		t = kthread_create(rcu_node_kthread, (void *)rnp,
-				   "rcun%d", rnp_index);
-		if (IS_ERR(t))
-			return PTR_ERR(t);
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		rnp->node_kthread_task = t;
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		wake_up_process(t);
-		sp.sched_priority = 99;
-		sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
-	}
-	return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index);
-}
-
-/*
- * Spawn all kthreads -- called as soon as the scheduler is running.
- */
-static int __init rcu_spawn_kthreads(void)
-{
-	int cpu;
-	struct rcu_node *rnp;
-
-	rcu_kthreads_spawnable = 1;
-	for_each_possible_cpu(cpu) {
-		init_waitqueue_head(&per_cpu(rcu_cpu_wq, cpu));
-		per_cpu(rcu_cpu_has_work, cpu) = 0;
-		if (cpu_online(cpu))
-			(void)rcu_spawn_one_cpu_kthread(cpu);
-	}
-	rnp = rcu_get_root(rcu_state);
-	init_waitqueue_head(&rnp->node_wq);
-	rcu_init_boost_waitqueue(rnp);
-	(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-	if (NUM_RCU_NODES > 1)
-		rcu_for_each_leaf_node(rcu_state, rnp) {
-			init_waitqueue_head(&rnp->node_wq);
-			rcu_init_boost_waitqueue(rnp);
-			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-		}
-	return 0;
-}
-early_initcall(rcu_spawn_kthreads);
-
 static void
 __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	   struct rcu_state *rsp)
@@ -2218,26 +1878,13 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
 	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
 
-static void __cpuinit rcu_online_cpu(int cpu)
+static void __cpuinit rcu_prepare_cpu(int cpu)
 {
 	rcu_init_percpu_data(cpu, &rcu_sched_state, 0);
 	rcu_init_percpu_data(cpu, &rcu_bh_state, 0);
 	rcu_preempt_init_percpu_data(cpu);
 }
 
-static void __cpuinit rcu_online_kthreads(int cpu)
-{
-	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
-	struct rcu_node *rnp = rdp->mynode;
-
-	/* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */
-	if (rcu_kthreads_spawnable) {
-		(void)rcu_spawn_one_cpu_kthread(cpu);
-		if (rnp->node_kthread_task == NULL)
-			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-	}
-}
-
 /*
  * Handle CPU online/offline notification events.
  */
@@ -2251,8 +1898,8 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		rcu_online_cpu(cpu);
-		rcu_online_kthreads(cpu);
+		rcu_prepare_cpu(cpu);
+		rcu_prepare_kthreads(cpu);
 		break;
 	case CPU_ONLINE:
 	case CPU_DOWN_FAILED:
@@ -2402,6 +2049,7 @@ void __init rcu_init(void)
 	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
 	__rcu_init_preempt();
+	 open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
 	/*
 	 * We don't need protection against CPU-hotplug here because
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 257664815d5d..01b2ccda26fb 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,11 +84,9 @@
  * Dynticks per-CPU state.
  */
 struct rcu_dynticks {
-	int dynticks_nesting;	/* Track nesting level, sort of. */
-	int dynticks;		/* Even value for dynticks-idle, else odd. */
-	int dynticks_nmi;	/* Even value for either dynticks-idle or */
-				/*  not in nmi handler, else odd.  So this */
-				/*  remains even for nmi from irq handler. */
+	int dynticks_nesting;	/* Track irq/process nesting level. */
+	int dynticks_nmi_nesting; /* Track NMI nesting level. */
+	atomic_t dynticks;	/* Even value for dynticks-idle, else odd. */
 };
 
 /* RCU's kthread states for tracing. */
@@ -121,7 +119,9 @@ struct rcu_node {
 				/*  elements that need to drain to allow the */
 				/*  current expedited grace period to */
 				/*  complete (only for TREE_PREEMPT_RCU). */
-	unsigned long wakemask; /* CPUs whose kthread needs to be awakened. */
+	atomic_t wakemask;	/* CPUs whose kthread needs to be awakened. */
+				/*  Since this has meaning only for leaf */
+				/*  rcu_node structures, 32 bits suffices. */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask & expmask. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
@@ -159,9 +159,6 @@ struct rcu_node {
 	struct task_struct *boost_kthread_task;
 				/* kthread that takes care of priority */
 				/*  boosting for this rcu_node structure. */
-	wait_queue_head_t boost_wq;
-				/* Wait queue on which to park the boost */
-				/*  kthread. */
 	unsigned int boost_kthread_status;
 				/* State of boost_kthread_task for tracing. */
 	unsigned long n_tasks_boosted;
@@ -188,9 +185,6 @@ struct rcu_node {
 				/* kthread that takes care of this rcu_node */
 				/*  structure, for example, awakening the */
 				/*  per-CPU kthreads as needed. */
-	wait_queue_head_t node_wq;
-				/* Wait queue on which to park the per-node */
-				/*  kthread. */
 	unsigned int node_kthread_status;
 				/* State of node_kthread_task for tracing. */
 } ____cacheline_internodealigned_in_smp;
@@ -284,7 +278,6 @@ struct rcu_data {
 	/* 3) dynticks interface. */
 	struct rcu_dynticks *dynticks;	/* Shared per-CPU dynticks state. */
 	int dynticks_snap;		/* Per-GP tracking for dynticks. */
-	int dynticks_nmi_snap;		/* Per-GP tracking for dynticks_nmi. */
 #endif /* #ifdef CONFIG_NO_HZ */
 
 	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
@@ -337,6 +330,16 @@ struct rcu_data {
 						/*  scheduling clock irq */
 						/*  before ratting on them. */
 
+#define rcu_wait(cond)							\
+do {									\
+	for (;;) {							\
+		set_current_state(TASK_INTERRUPTIBLE);			\
+		if (cond)						\
+			break;						\
+		schedule();						\
+	}								\
+	__set_current_state(TASK_RUNNING);				\
+} while (0)
 
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
@@ -366,6 +369,7 @@ struct rcu_state {
 						/*  period because */
 						/*  force_quiescent_state() */
 						/*  was running. */
+	u8	boost;				/* Subject to priority boost. */
 	unsigned long gpnum;			/* Current gp number. */
 	unsigned long completed;		/* # of last completed gp. */
 
@@ -423,6 +427,7 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
 				      unsigned long flags);
+static void rcu_stop_cpu_kthread(int cpu);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static void rcu_print_task_stall(struct rcu_node *rnp);
@@ -446,13 +451,20 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
 static void rcu_preempt_send_cbs_to_online(void);
 static void __init __rcu_init_preempt(void);
 static void rcu_needs_cpu_flush(void);
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
+static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
+static void invoke_rcu_callbacks_kthread(void);
+#ifdef CONFIG_RCU_BOOST
+static void rcu_preempt_do_callbacks(void);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
 					  cpumask_var_t cm);
-static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
 static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 						 struct rcu_node *rnp,
 						 int rnp_index);
+static void invoke_rcu_node_kthread(struct rcu_node *rnp);
+static void rcu_yield(void (*f)(unsigned long), unsigned long arg);
+#endif /* #ifdef CONFIG_RCU_BOOST */
+static void rcu_cpu_kthread_setrt(int cpu, int to_rt);
+static void __cpuinit rcu_prepare_kthreads(int cpu);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 3f6559a5f5cd..14dc7dd00902 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -602,6 +602,15 @@ static void rcu_preempt_process_callbacks(void)
 				&__get_cpu_var(rcu_preempt_data));
 }
 
+#ifdef CONFIG_RCU_BOOST
+
+static void rcu_preempt_do_callbacks(void)
+{
+	rcu_do_batch(&rcu_preempt_state, &__get_cpu_var(rcu_preempt_data));
+}
+
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
 /*
  * Queue a preemptible-RCU callback for invocation after a grace period.
  */
@@ -1196,8 +1205,7 @@ static int rcu_boost_kthread(void *arg)
 
 	for (;;) {
 		rnp->boost_kthread_status = RCU_KTHREAD_WAITING;
-		wait_event_interruptible(rnp->boost_wq, rnp->boost_tasks ||
-							rnp->exp_tasks);
+		rcu_wait(rnp->boost_tasks || rnp->exp_tasks);
 		rnp->boost_kthread_status = RCU_KTHREAD_RUNNING;
 		more2boost = rcu_boost(rnp);
 		if (more2boost)
@@ -1250,6 +1258,23 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 }
 
 /*
+ * Wake up the per-CPU kthread to invoke RCU callbacks.
+ */
+static void invoke_rcu_callbacks_kthread(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__this_cpu_write(rcu_cpu_has_work, 1);
+	if (__this_cpu_read(rcu_cpu_kthread_task) == NULL) {
+		local_irq_restore(flags);
+		return;
+	}
+	wake_up_process(__this_cpu_read(rcu_cpu_kthread_task));
+	local_irq_restore(flags);
+}
+
+/*
  * Set the affinity of the boost kthread.  The CPU-hotplug locks are
  * held, so no one should be messing with the existence of the boost
  * kthread.
@@ -1275,14 +1300,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 }
 
 /*
- * Initialize the RCU-boost waitqueue.
- */
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
-{
-	init_waitqueue_head(&rnp->boost_wq);
-}
-
-/*
  * Create an RCU-boost kthread for the specified node if one does not
  * already exist.  We only create this kthread for preemptible RCU.
  * Returns zero if all is well, a negated errno otherwise.
@@ -1297,6 +1314,7 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 
 	if (&rcu_preempt_state != rsp)
 		return 0;
+	rsp->boost = 1;
 	if (rnp->boost_kthread_task != NULL)
 		return 0;
 	t = kthread_create(rcu_boost_kthread, (void *)rnp,
@@ -1306,12 +1324,376 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	wake_up_process(t);
 	sp.sched_priority = RCU_KTHREAD_PRIO;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+	wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
 	return 0;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Stop the RCU's per-CPU kthread when its CPU goes offline,.
+ */
+static void rcu_stop_cpu_kthread(int cpu)
+{
+	struct task_struct *t;
+
+	/* Stop the CPU's kthread. */
+	t = per_cpu(rcu_cpu_kthread_task, cpu);
+	if (t != NULL) {
+		per_cpu(rcu_cpu_kthread_task, cpu) = NULL;
+		kthread_stop(t);
+	}
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+static void rcu_kthread_do_work(void)
+{
+	rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data));
+	rcu_do_batch(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
+	rcu_preempt_do_callbacks();
+}
+
+/*
+ * Wake up the specified per-rcu_node-structure kthread.
+ * Because the per-rcu_node kthreads are immortal, we don't need
+ * to do anything to keep them alive.
+ */
+static void invoke_rcu_node_kthread(struct rcu_node *rnp)
+{
+	struct task_struct *t;
+
+	t = rnp->node_kthread_task;
+	if (t != NULL)
+		wake_up_process(t);
+}
+
+/*
+ * Set the specified CPU's kthread to run RT or not, as specified by
+ * the to_rt argument.  The CPU-hotplug locks are held, so the task
+ * is not going away.
+ */
+static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
+{
+	int policy;
+	struct sched_param sp;
+	struct task_struct *t;
+
+	t = per_cpu(rcu_cpu_kthread_task, cpu);
+	if (t == NULL)
+		return;
+	if (to_rt) {
+		policy = SCHED_FIFO;
+		sp.sched_priority = RCU_KTHREAD_PRIO;
+	} else {
+		policy = SCHED_NORMAL;
+		sp.sched_priority = 0;
+	}
+	sched_setscheduler_nocheck(t, policy, &sp);
+}
+
+/*
+ * Timer handler to initiate the waking up of per-CPU kthreads that
+ * have yielded the CPU due to excess numbers of RCU callbacks.
+ * We wake up the per-rcu_node kthread, which in turn will wake up
+ * the booster kthread.
+ */
+static void rcu_cpu_kthread_timer(unsigned long arg)
+{
+	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg);
+	struct rcu_node *rnp = rdp->mynode;
+
+	atomic_or(rdp->grpmask, &rnp->wakemask);
+	invoke_rcu_node_kthread(rnp);
+}
+
+/*
+ * Drop to non-real-time priority and yield, but only after posting a
+ * timer that will cause us to regain our real-time priority if we
+ * remain preempted.  Either way, we restore our real-time priority
+ * before returning.
+ */
+static void rcu_yield(void (*f)(unsigned long), unsigned long arg)
+{
+	struct sched_param sp;
+	struct timer_list yield_timer;
+
+	setup_timer_on_stack(&yield_timer, f, arg);
+	mod_timer(&yield_timer, jiffies + 2);
+	sp.sched_priority = 0;
+	sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp);
+	set_user_nice(current, 19);
+	schedule();
+	sp.sched_priority = RCU_KTHREAD_PRIO;
+	sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
+	del_timer(&yield_timer);
+}
+
+/*
+ * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU.
+ * This can happen while the corresponding CPU is either coming online
+ * or going offline.  We cannot wait until the CPU is fully online
+ * before starting the kthread, because the various notifier functions
+ * can wait for RCU grace periods.  So we park rcu_cpu_kthread() until
+ * the corresponding CPU is online.
+ *
+ * Return 1 if the kthread needs to stop, 0 otherwise.
+ *
+ * Caller must disable bh.  This function can momentarily enable it.
+ */
+static int rcu_cpu_kthread_should_stop(int cpu)
+{
+	while (cpu_is_offline(cpu) ||
+	       !cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)) ||
+	       smp_processor_id() != cpu) {
+		if (kthread_should_stop())
+			return 1;
+		per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
+		per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id();
+		local_bh_enable();
+		schedule_timeout_uninterruptible(1);
+		if (!cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)))
+			set_cpus_allowed_ptr(current, cpumask_of(cpu));
+		local_bh_disable();
+	}
+	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
+	return 0;
+}
+
+/*
+ * Per-CPU kernel thread that invokes RCU callbacks.  This replaces the
+ * earlier RCU softirq.
+ */
+static int rcu_cpu_kthread(void *arg)
+{
+	int cpu = (int)(long)arg;
+	unsigned long flags;
+	int spincnt = 0;
+	unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu);
+	char work;
+	char *workp = &per_cpu(rcu_cpu_has_work, cpu);
+
+	for (;;) {
+		*statusp = RCU_KTHREAD_WAITING;
+		rcu_wait(*workp != 0 || kthread_should_stop());
+		local_bh_disable();
+		if (rcu_cpu_kthread_should_stop(cpu)) {
+			local_bh_enable();
+			break;
+		}
+		*statusp = RCU_KTHREAD_RUNNING;
+		per_cpu(rcu_cpu_kthread_loops, cpu)++;
+		local_irq_save(flags);
+		work = *workp;
+		*workp = 0;
+		local_irq_restore(flags);
+		if (work)
+			rcu_kthread_do_work();
+		local_bh_enable();
+		if (*workp != 0)
+			spincnt++;
+		else
+			spincnt = 0;
+		if (spincnt > 10) {
+			*statusp = RCU_KTHREAD_YIELDING;
+			rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu);
+			spincnt = 0;
+		}
+	}
+	*statusp = RCU_KTHREAD_STOPPED;
+	return 0;
+}
+
+/*
+ * Spawn a per-CPU kthread, setting up affinity and priority.
+ * Because the CPU hotplug lock is held, no other CPU will be attempting
+ * to manipulate rcu_cpu_kthread_task.  There might be another CPU
+ * attempting to access it during boot, but the locking in kthread_bind()
+ * will enforce sufficient ordering.
+ *
+ * Please note that we cannot simply refuse to wake up the per-CPU
+ * kthread because kthreads are created in TASK_UNINTERRUPTIBLE state,
+ * which can result in softlockup complaints if the task ends up being
+ * idle for more than a couple of minutes.
+ *
+ * However, please note also that we cannot bind the per-CPU kthread to its
+ * CPU until that CPU is fully online.  We also cannot wait until the
+ * CPU is fully online before we create its per-CPU kthread, as this would
+ * deadlock the system when CPU notifiers tried waiting for grace
+ * periods.  So we bind the per-CPU kthread to its CPU only if the CPU
+ * is online.  If its CPU is not yet fully online, then the code in
+ * rcu_cpu_kthread() will wait until it is fully online, and then do
+ * the binding.
+ */
+static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
+{
+	struct sched_param sp;
+	struct task_struct *t;
+
+	if (!rcu_kthreads_spawnable ||
+	    per_cpu(rcu_cpu_kthread_task, cpu) != NULL)
+		return 0;
+	t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu);
+	if (IS_ERR(t))
+		return PTR_ERR(t);
+	if (cpu_online(cpu))
+		kthread_bind(t, cpu);
+	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
+	WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
+	sp.sched_priority = RCU_KTHREAD_PRIO;
+	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+	per_cpu(rcu_cpu_kthread_task, cpu) = t;
+	wake_up_process(t); /* Get to TASK_INTERRUPTIBLE quickly. */
+	return 0;
+}
+
+/*
+ * Per-rcu_node kthread, which is in charge of waking up the per-CPU
+ * kthreads when needed.  We ignore requests to wake up kthreads
+ * for offline CPUs, which is OK because force_quiescent_state()
+ * takes care of this case.
+ */
+static int rcu_node_kthread(void *arg)
+{
+	int cpu;
+	unsigned long flags;
+	unsigned long mask;
+	struct rcu_node *rnp = (struct rcu_node *)arg;
+	struct sched_param sp;
+	struct task_struct *t;
+
+	for (;;) {
+		rnp->node_kthread_status = RCU_KTHREAD_WAITING;
+		rcu_wait(atomic_read(&rnp->wakemask) != 0);
+		rnp->node_kthread_status = RCU_KTHREAD_RUNNING;
+		raw_spin_lock_irqsave(&rnp->lock, flags);
+		mask = atomic_xchg(&rnp->wakemask, 0);
+		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
+		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) {
+			if ((mask & 0x1) == 0)
+				continue;
+			preempt_disable();
+			t = per_cpu(rcu_cpu_kthread_task, cpu);
+			if (!cpu_online(cpu) || t == NULL) {
+				preempt_enable();
+				continue;
+			}
+			per_cpu(rcu_cpu_has_work, cpu) = 1;
+			sp.sched_priority = RCU_KTHREAD_PRIO;
+			sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+			preempt_enable();
+		}
+	}
+	/* NOTREACHED */
+	rnp->node_kthread_status = RCU_KTHREAD_STOPPED;
+	return 0;
+}
+
+/*
+ * Set the per-rcu_node kthread's affinity to cover all CPUs that are
+ * served by the rcu_node in question.  The CPU hotplug lock is still
+ * held, so the value of rnp->qsmaskinit will be stable.
+ *
+ * We don't include outgoingcpu in the affinity set, use -1 if there is
+ * no outgoing CPU.  If there are no CPUs left in the affinity set,
+ * this function allows the kthread to execute on any CPU.
+ */
+static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
+{
+	cpumask_var_t cm;
+	int cpu;
+	unsigned long mask = rnp->qsmaskinit;
+
+	if (rnp->node_kthread_task == NULL)
+		return;
+	if (!alloc_cpumask_var(&cm, GFP_KERNEL))
+		return;
+	cpumask_clear(cm);
+	for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1)
+		if ((mask & 0x1) && cpu != outgoingcpu)
+			cpumask_set_cpu(cpu, cm);
+	if (cpumask_weight(cm) == 0) {
+		cpumask_setall(cm);
+		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++)
+			cpumask_clear_cpu(cpu, cm);
+		WARN_ON_ONCE(cpumask_weight(cm) == 0);
+	}
+	set_cpus_allowed_ptr(rnp->node_kthread_task, cm);
+	rcu_boost_kthread_setaffinity(rnp, cm);
+	free_cpumask_var(cm);
+}
+
+/*
+ * Spawn a per-rcu_node kthread, setting priority and affinity.
+ * Called during boot before online/offline can happen, or, if
+ * during runtime, with the main CPU-hotplug locks held.  So only
+ * one of these can be executing at a time.
+ */
+static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
+						struct rcu_node *rnp)
+{
+	unsigned long flags;
+	int rnp_index = rnp - &rsp->node[0];
+	struct sched_param sp;
+	struct task_struct *t;
+
+	if (!rcu_kthreads_spawnable ||
+	    rnp->qsmaskinit == 0)
+		return 0;
+	if (rnp->node_kthread_task == NULL) {
+		t = kthread_create(rcu_node_kthread, (void *)rnp,
+				   "rcun%d", rnp_index);
+		if (IS_ERR(t))
+			return PTR_ERR(t);
+		raw_spin_lock_irqsave(&rnp->lock, flags);
+		rnp->node_kthread_task = t;
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		sp.sched_priority = 99;
+		sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+		wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
+	}
+	return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index);
+}
+
+/*
+ * Spawn all kthreads -- called as soon as the scheduler is running.
+ */
+static int __init rcu_spawn_kthreads(void)
+{
+	int cpu;
+	struct rcu_node *rnp;
+
+	rcu_kthreads_spawnable = 1;
+	for_each_possible_cpu(cpu) {
+		per_cpu(rcu_cpu_has_work, cpu) = 0;
+		if (cpu_online(cpu))
+			(void)rcu_spawn_one_cpu_kthread(cpu);
+	}
+	rnp = rcu_get_root(rcu_state);
+	(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+	if (NUM_RCU_NODES > 1) {
+		rcu_for_each_leaf_node(rcu_state, rnp)
+			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+	}
+	return 0;
+}
+early_initcall(rcu_spawn_kthreads);
+
+static void __cpuinit rcu_prepare_kthreads(int cpu)
+{
+	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
+	struct rcu_node *rnp = rdp->mynode;
+
+	/* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */
+	if (rcu_kthreads_spawnable) {
+		(void)rcu_spawn_one_cpu_kthread(cpu);
+		if (rnp->node_kthread_task == NULL)
+			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+	}
+}
+
 #else /* #ifdef CONFIG_RCU_BOOST */
 
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
@@ -1319,24 +1701,33 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
-static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
-					  cpumask_var_t cm)
+static void invoke_rcu_callbacks_kthread(void)
 {
+	WARN_ON_ONCE(1);
 }
 
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 {
 }
 
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
+#ifdef CONFIG_HOTPLUG_CPU
+
+static void rcu_stop_cpu_kthread(int cpu)
 {
 }
 
-static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
-						 struct rcu_node *rnp,
-						 int rnp_index)
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
+{
+}
+
+static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
+{
+}
+
+static void __cpuinit rcu_prepare_kthreads(int cpu)
 {
-	return 0;
 }
 
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
@@ -1513,14 +1904,13 @@ static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
  *
  * Because it is not legal to invoke rcu_process_callbacks() with irqs
  * disabled, we do one pass of force_quiescent_state(), then do a
- * invoke_rcu_cpu_kthread() to cause rcu_process_callbacks() to be invoked
+ * invoke_rcu_core() to cause rcu_process_callbacks() to be invoked
  * later.  The per-cpu rcu_dyntick_drain variable controls the sequencing.
  */
 int rcu_needs_cpu(int cpu)
 {
 	int c = 0;
 	int snap;
-	int snap_nmi;
 	int thatcpu;
 
 	/* Check for being in the holdoff period. */
@@ -1531,10 +1921,10 @@ int rcu_needs_cpu(int cpu)
 	for_each_online_cpu(thatcpu) {
 		if (thatcpu == cpu)
 			continue;
-		snap = per_cpu(rcu_dynticks, thatcpu).dynticks;
-		snap_nmi = per_cpu(rcu_dynticks, thatcpu).dynticks_nmi;
+		snap = atomic_add_return(0, &per_cpu(rcu_dynticks,
+						     thatcpu).dynticks);
 		smp_mb(); /* Order sampling of snap with end of grace period. */
-		if (((snap & 0x1) != 0) || ((snap_nmi & 0x1) != 0)) {
+		if ((snap & 0x1) != 0) {
 			per_cpu(rcu_dyntick_drain, cpu) = 0;
 			per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
 			return rcu_needs_cpu_quick_check(cpu);
@@ -1565,7 +1955,7 @@ int rcu_needs_cpu(int cpu)
 
 	/* If RCU callbacks are still pending, RCU still needs this CPU. */
 	if (c)
-		invoke_rcu_cpu_kthread();
+		invoke_rcu_core();
 	return c;
 }
 
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index aa0fd72b4bc7..4e144876dc68 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -46,6 +46,8 @@
 #define RCU_TREE_NONCORE
 #include "rcutree.h"
 
+#ifdef CONFIG_RCU_BOOST
+
 DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_cpu);
 DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
@@ -58,6 +60,8 @@ static char convert_kthread_status(unsigned int kthread_status)
 	return "SRWOY"[kthread_status];
 }
 
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
 static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 {
 	if (!rdp->beenonline)
@@ -69,14 +73,14 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->passed_quiesc, rdp->passed_quiesc_completed,
 		   rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
-	seq_printf(m, " dt=%d/%d dn=%d df=%lu",
-		   rdp->dynticks->dynticks,
+	seq_printf(m, " dt=%d/%d/%d df=%lu",
+		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
-		   rdp->dynticks->dynticks_nmi,
+		   rdp->dynticks->dynticks_nmi_nesting,
 		   rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
-	seq_printf(m, " ql=%ld qs=%c%c%c%c kt=%d/%c/%d ktl=%x b=%ld",
+	seq_printf(m, " ql=%ld qs=%c%c%c%c",
 		   rdp->qlen,
 		   ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
 			rdp->nxttail[RCU_NEXT_TAIL]],
@@ -84,13 +88,16 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 			rdp->nxttail[RCU_NEXT_READY_TAIL]],
 		   ".W"[rdp->nxttail[RCU_DONE_TAIL] !=
 			rdp->nxttail[RCU_WAIT_TAIL]],
-		   ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]],
+		   ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]);
+#ifdef CONFIG_RCU_BOOST
+	seq_printf(m, " kt=%d/%c/%d ktl=%x",
 		   per_cpu(rcu_cpu_has_work, rdp->cpu),
 		   convert_kthread_status(per_cpu(rcu_cpu_kthread_status,
 					  rdp->cpu)),
 		   per_cpu(rcu_cpu_kthread_cpu, rdp->cpu),
-		   per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff,
-		   rdp->blimit);
+		   per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff);
+#endif /* #ifdef CONFIG_RCU_BOOST */
+	seq_printf(m, " b=%ld", rdp->blimit);
 	seq_printf(m, " ci=%lu co=%lu ca=%lu\n",
 		   rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted);
 }
@@ -141,24 +148,27 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
 	seq_printf(m, ",%d,%d,%d,%lu",
-		   rdp->dynticks->dynticks,
+		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
-		   rdp->dynticks->dynticks_nmi,
+		   rdp->dynticks->dynticks_nmi_nesting,
 		   rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
-	seq_printf(m, ",%ld,\"%c%c%c%c\",%d,\"%c\",%ld", rdp->qlen,
+	seq_printf(m, ",%ld,\"%c%c%c%c\"", rdp->qlen,
 		   ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
 			rdp->nxttail[RCU_NEXT_TAIL]],
 		   ".R"[rdp->nxttail[RCU_WAIT_TAIL] !=
 			rdp->nxttail[RCU_NEXT_READY_TAIL]],
 		   ".W"[rdp->nxttail[RCU_DONE_TAIL] !=
 			rdp->nxttail[RCU_WAIT_TAIL]],
-		   ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]],
+		   ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]);
+#ifdef CONFIG_RCU_BOOST
+	seq_printf(m, ",%d,\"%c\"",
 		   per_cpu(rcu_cpu_has_work, rdp->cpu),
 		   convert_kthread_status(per_cpu(rcu_cpu_kthread_status,
-					  rdp->cpu)),
-		   rdp->blimit);
+					  rdp->cpu)));
+#endif /* #ifdef CONFIG_RCU_BOOST */
+	seq_printf(m, ",%ld", rdp->blimit);
 	seq_printf(m, ",%lu,%lu,%lu\n",
 		   rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted);
 }
@@ -167,9 +177,13 @@ static int show_rcudata_csv(struct seq_file *m, void *unused)
 {
 	seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",");
 #ifdef CONFIG_NO_HZ
-	seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
+	seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\",");
 #endif /* #ifdef CONFIG_NO_HZ */
-	seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n");
+	seq_puts(m, "\"of\",\"ri\",\"ql\",\"qs\"");
+#ifdef CONFIG_RCU_BOOST
+	seq_puts(m, "\"kt\",\"ktl\"");
+#endif /* #ifdef CONFIG_RCU_BOOST */
+	seq_puts(m, ",\"b\",\"ci\",\"co\",\"ca\"\n");
 #ifdef CONFIG_TREE_PREEMPT_RCU
 	seq_puts(m, "\"rcu_preempt:\"\n");
 	PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data_csv, m);
diff --git a/kernel/sched.c b/kernel/sched.c
index fd18f395a1bf..59252754fbe0 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -605,10 +605,10 @@ static inline int cpu_of(struct rq *rq)
 /*
  * Return the group to which this tasks belongs.
  *
- * We use task_subsys_state_check() and extend the RCU verification
- * with lockdep_is_held(&p->pi_lock) because cpu_cgroup_attach()
- * holds that lock for each task it moves into the cgroup. Therefore
- * by holding that lock, we pin the task to the current cgroup.
+ * We use task_subsys_state_check() and extend the RCU verification with
+ * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each
+ * task it moves into the cgroup. Therefore by holding either of those locks,
+ * we pin the task to the current cgroup.
  */
 static inline struct task_group *task_group(struct task_struct *p)
 {
@@ -616,7 +616,8 @@ static inline struct task_group *task_group(struct task_struct *p)
 	struct cgroup_subsys_state *css;
 
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
-			lockdep_is_held(&p->pi_lock));
+			lockdep_is_held(&p->pi_lock) ||
+			lockdep_is_held(&task_rq(p)->lock));
 	tg = container_of(css, struct task_group, css);
 
 	return autogroup_task_group(p, tg);
@@ -2200,6 +2201,16 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 			!(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
 
 #ifdef CONFIG_LOCKDEP
+	/*
+	 * The caller should hold either p->pi_lock or rq->lock, when changing
+	 * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
+	 *
+	 * sched_move_task() holds both and thus holding either pins the cgroup,
+	 * see set_task_rq().
+	 *
+	 * Furthermore, all task_rq users should acquire both locks, see
+	 * task_rq_lock().
+	 */
 	WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
 				      lockdep_is_held(&task_rq(p)->lock)));
 #endif
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 08e937496b24..b03cd89fee20 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1096,7 +1096,7 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
 	 * to move current somewhere else, making room for our non-migratable
 	 * task.
 	 */
-	if (p->prio == rq->curr->prio && !need_resched())
+	if (p->prio == rq->curr->prio && !test_tsk_need_resched(rq->curr))
 		check_preempt_equal_prio(rq, p);
 #endif
 }
@@ -1239,6 +1239,10 @@ static int find_lowest_rq(struct task_struct *task)
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
 
+	/* Make sure the mask is initialized first */
+	if (unlikely(!lowest_mask))
+		return -1;
+
 	if (task->rt.nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */
 
diff --git a/kernel/signal.c b/kernel/signal.c
index 86c32b884f8e..ff7678603328 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2365,7 +2365,7 @@ int sigprocmask(int how, sigset_t *set, sigset_t *oldset)
 /**
  *  sys_rt_sigprocmask - change the list of currently blocked signals
  *  @how: whether to add, remove, or set signals
- *  @set: stores pending signals
+ *  @nset: stores pending signals
  *  @oset: previous value of signal mask if non-null
  *  @sigsetsize: size of sigset_t type
  */
diff --git a/kernel/smp.c b/kernel/smp.c
index 73a195193558..fb67dfa8394e 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -74,7 +74,7 @@ static struct notifier_block __cpuinitdata hotplug_cfd_notifier = {
 	.notifier_call		= hotplug_cfd,
 };
 
-static int __cpuinit init_call_single_data(void)
+void __init call_function_init(void)
 {
 	void *cpu = (void *)(long)smp_processor_id();
 	int i;
@@ -88,10 +88,7 @@ static int __cpuinit init_call_single_data(void)
 
 	hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu);
 	register_cpu_notifier(&hotplug_cfd_notifier);
-
-	return 0;
 }
-early_initcall(init_call_single_data);
 
 /*
  * csd_lock/csd_unlock used to serialize access to per-cpu csd resources
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 13960170cad4..40cf63ddd4b3 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -58,7 +58,7 @@ DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
 char *softirq_to_name[NR_SOFTIRQS] = {
 	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
-	"TASKLET", "SCHED", "HRTIMER"
+	"TASKLET", "SCHED", "HRTIMER", "RCU"
 };
 
 /*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4fc92445a29c..f175d98bd355 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -938,6 +938,12 @@ static struct ctl_table kern_table[] = {
 	},
 #endif
 #ifdef CONFIG_PERF_EVENTS
+	/*
+	 * User-space scripts rely on the existence of this file
+	 * as a feature check for perf_events being enabled.
+	 *
+	 * So it's an ABI, do not remove!
+	 */
 	{
 		.procname	= "perf_event_paranoid",
 		.data		= &sysctl_perf_event_paranoid,
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 9ffea360a778..fc0f22005417 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -285,16 +285,18 @@ ret:
 static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd)
 {
 	struct listener_list *listeners;
-	struct listener *s, *tmp;
+	struct listener *s, *tmp, *s2;
 	unsigned int cpu;
 
 	if (!cpumask_subset(mask, cpu_possible_mask))
 		return -EINVAL;
 
+	s = NULL;
 	if (isadd == REGISTER) {
 		for_each_cpu(cpu, mask) {
-			s = kmalloc_node(sizeof(struct listener), GFP_KERNEL,
-					 cpu_to_node(cpu));
+			if (!s)
+				s = kmalloc_node(sizeof(struct listener),
+						 GFP_KERNEL, cpu_to_node(cpu));
 			if (!s)
 				goto cleanup;
 			s->pid = pid;
@@ -303,9 +305,16 @@ static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd)
 
 			listeners = &per_cpu(listener_array, cpu);
 			down_write(&listeners->sem);
+			list_for_each_entry_safe(s2, tmp, &listeners->list, list) {
+				if (s2->pid == pid)
+					goto next_cpu;
+			}
 			list_add(&s->list, &listeners->list);
+			s = NULL;
+next_cpu:
 			up_write(&listeners->sem);
 		}
+		kfree(s);
 		return 0;
 	}
 
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 2d966244ea60..59f369f98a04 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -42,15 +42,75 @@ static struct alarm_base {
 	clockid_t		base_clockid;
 } alarm_bases[ALARM_NUMTYPE];
 
+/* freezer delta & lock used to handle clock_nanosleep triggered wakeups */
+static ktime_t freezer_delta;
+static DEFINE_SPINLOCK(freezer_delta_lock);
+
 #ifdef CONFIG_RTC_CLASS
 /* rtc timer and device for setting alarm wakeups at suspend */
 static struct rtc_timer		rtctimer;
 static struct rtc_device	*rtcdev;
-#endif
+static DEFINE_SPINLOCK(rtcdev_lock);
 
-/* freezer delta & lock used to handle clock_nanosleep triggered wakeups */
-static ktime_t freezer_delta;
-static DEFINE_SPINLOCK(freezer_delta_lock);
+/**
+ * has_wakealarm - check rtc device has wakealarm ability
+ * @dev: current device
+ * @name_ptr: name to be returned
+ *
+ * This helper function checks to see if the rtc device can wake
+ * from suspend.
+ */
+static int has_wakealarm(struct device *dev, void *name_ptr)
+{
+	struct rtc_device *candidate = to_rtc_device(dev);
+
+	if (!candidate->ops->set_alarm)
+		return 0;
+	if (!device_may_wakeup(candidate->dev.parent))
+		return 0;
+
+	*(const char **)name_ptr = dev_name(dev);
+	return 1;
+}
+
+/**
+ * alarmtimer_get_rtcdev - Return selected rtcdevice
+ *
+ * This function returns the rtc device to use for wakealarms.
+ * If one has not already been chosen, it checks to see if a
+ * functional rtc device is available.
+ */
+static struct rtc_device *alarmtimer_get_rtcdev(void)
+{
+	struct device *dev;
+	char *str;
+	unsigned long flags;
+	struct rtc_device *ret;
+
+	spin_lock_irqsave(&rtcdev_lock, flags);
+	if (!rtcdev) {
+		/* Find an rtc device and init the rtc_timer */
+		dev = class_find_device(rtc_class, NULL, &str, has_wakealarm);
+		/* If we have a device then str is valid. See has_wakealarm() */
+		if (dev) {
+			rtcdev = rtc_class_open(str);
+			/*
+			 * Drop the reference we got in class_find_device,
+			 * rtc_open takes its own.
+			 */
+			put_device(dev);
+			rtc_timer_init(&rtctimer, NULL, NULL);
+		}
+	}
+	ret = rtcdev;
+	spin_unlock_irqrestore(&rtcdev_lock, flags);
+
+	return ret;
+}
+#else
+#define alarmtimer_get_rtcdev() (0)
+#define rtcdev (0)
+#endif
 
 
 /**
@@ -166,6 +226,7 @@ static int alarmtimer_suspend(struct device *dev)
 	struct rtc_time tm;
 	ktime_t min, now;
 	unsigned long flags;
+	struct rtc_device *rtc;
 	int i;
 
 	spin_lock_irqsave(&freezer_delta_lock, flags);
@@ -173,8 +234,9 @@ static int alarmtimer_suspend(struct device *dev)
 	freezer_delta = ktime_set(0, 0);
 	spin_unlock_irqrestore(&freezer_delta_lock, flags);
 
+	rtc = rtcdev;
 	/* If we have no rtcdev, just return */
-	if (!rtcdev)
+	if (!rtc)
 		return 0;
 
 	/* Find the soonest timer to expire*/
@@ -199,12 +261,12 @@ static int alarmtimer_suspend(struct device *dev)
 	WARN_ON(min.tv64 < NSEC_PER_SEC);
 
 	/* Setup an rtc timer to fire that far in the future */
-	rtc_timer_cancel(rtcdev, &rtctimer);
-	rtc_read_time(rtcdev, &tm);
+	rtc_timer_cancel(rtc, &rtctimer);
+	rtc_read_time(rtc, &tm);
 	now = rtc_tm_to_ktime(tm);
 	now = ktime_add(now, min);
 
-	rtc_timer_start(rtcdev, &rtctimer, now, ktime_set(0, 0));
+	rtc_timer_start(rtc, &rtctimer, now, ktime_set(0, 0));
 
 	return 0;
 }
@@ -322,6 +384,9 @@ static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp)
 {
 	clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid;
 
+	if (!alarmtimer_get_rtcdev())
+		return -ENOTSUPP;
+
 	return hrtimer_get_res(baseid, tp);
 }
 
@@ -336,6 +401,9 @@ static int alarm_clock_get(clockid_t which_clock, struct timespec *tp)
 {
 	struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
 
+	if (!alarmtimer_get_rtcdev())
+		return -ENOTSUPP;
+
 	*tp = ktime_to_timespec(base->gettime());
 	return 0;
 }
@@ -351,6 +419,9 @@ static int alarm_timer_create(struct k_itimer *new_timer)
 	enum  alarmtimer_type type;
 	struct alarm_base *base;
 
+	if (!alarmtimer_get_rtcdev())
+		return -ENOTSUPP;
+
 	if (!capable(CAP_WAKE_ALARM))
 		return -EPERM;
 
@@ -385,6 +456,9 @@ static void alarm_timer_get(struct k_itimer *timr,
  */
 static int alarm_timer_del(struct k_itimer *timr)
 {
+	if (!rtcdev)
+		return -ENOTSUPP;
+
 	alarm_cancel(&timr->it.alarmtimer);
 	return 0;
 }
@@ -402,6 +476,9 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
 				struct itimerspec *new_setting,
 				struct itimerspec *old_setting)
 {
+	if (!rtcdev)
+		return -ENOTSUPP;
+
 	/* Save old values */
 	old_setting->it_interval =
 			ktime_to_timespec(timr->it.alarmtimer.period);
@@ -541,6 +618,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 	int ret = 0;
 	struct restart_block *restart;
 
+	if (!alarmtimer_get_rtcdev())
+		return -ENOTSUPP;
+
 	if (!capable(CAP_WAKE_ALARM))
 		return -EPERM;
 
@@ -638,65 +718,3 @@ static int __init alarmtimer_init(void)
 }
 device_initcall(alarmtimer_init);
 
-#ifdef CONFIG_RTC_CLASS
-/**
- * has_wakealarm - check rtc device has wakealarm ability
- * @dev: current device
- * @name_ptr: name to be returned
- *
- * This helper function checks to see if the rtc device can wake
- * from suspend.
- */
-static int __init has_wakealarm(struct device *dev, void *name_ptr)
-{
-	struct rtc_device *candidate = to_rtc_device(dev);
-
-	if (!candidate->ops->set_alarm)
-		return 0;
-	if (!device_may_wakeup(candidate->dev.parent))
-		return 0;
-
-	*(const char **)name_ptr = dev_name(dev);
-	return 1;
-}
-
-/**
- * alarmtimer_init_late - Late initializing of alarmtimer code
- *
- * This function locates a rtc device to use for wakealarms.
- * Run as late_initcall to make sure rtc devices have been
- * registered.
- */
-static int __init alarmtimer_init_late(void)
-{
-	struct device *dev;
-	char *str;
-
-	/* Find an rtc device and init the rtc_timer */
-	dev = class_find_device(rtc_class, NULL, &str, has_wakealarm);
-	/* If we have a device then str is valid. See has_wakealarm() */
-	if (dev) {
-		rtcdev = rtc_class_open(str);
-		/*
-		 * Drop the reference we got in class_find_device,
-		 * rtc_open takes its own.
-		 */
-		put_device(dev);
-	}
-	if (!rtcdev) {
-		printk(KERN_WARNING "No RTC device found, ALARM timers will"
-			" not wake from suspend");
-	}
-	rtc_timer_init(&rtctimer, NULL, NULL);
-
-	return 0;
-}
-#else
-static int __init alarmtimer_init_late(void)
-{
-	printk(KERN_WARNING "Kernel not built with RTC support, ALARM timers"
-		" will not wake from suspend");
-	return 0;
-}
-#endif
-late_initcall(alarmtimer_init_late);
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index c027d4f602f1..e4c699dfa4e8 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -182,7 +182,10 @@ void clockevents_register_device(struct clock_event_device *dev)
 	unsigned long flags;
 
 	BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
-	BUG_ON(!dev->cpumask);
+	if (!dev->cpumask) {
+		WARN_ON(num_possible_cpus() > 1);
+		dev->cpumask = cpumask_of(smp_processor_id());
+	}
 
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 1c95fd677328..e0980f0d9a0a 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -185,7 +185,6 @@ static struct clocksource *watchdog;
 static struct timer_list watchdog_timer;
 static DECLARE_WORK(watchdog_work, clocksource_watchdog_work);
 static DEFINE_SPINLOCK(watchdog_lock);
-static cycle_t watchdog_last;
 static int watchdog_running;
 
 static int clocksource_watchdog_kthread(void *data);
@@ -254,11 +253,6 @@ static void clocksource_watchdog(unsigned long data)
 	if (!watchdog_running)
 		goto out;
 
-	wdnow = watchdog->read(watchdog);
-	wd_nsec = clocksource_cyc2ns((wdnow - watchdog_last) & watchdog->mask,
-				     watchdog->mult, watchdog->shift);
-	watchdog_last = wdnow;
-
 	list_for_each_entry(cs, &watchdog_list, wd_list) {
 
 		/* Clocksource already marked unstable? */
@@ -268,19 +262,28 @@ static void clocksource_watchdog(unsigned long data)
 			continue;
 		}
 
+		local_irq_disable();
 		csnow = cs->read(cs);
+		wdnow = watchdog->read(watchdog);
+		local_irq_enable();
 
 		/* Clocksource initialized ? */
 		if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) {
 			cs->flags |= CLOCK_SOURCE_WATCHDOG;
-			cs->wd_last = csnow;
+			cs->wd_last = wdnow;
+			cs->cs_last = csnow;
 			continue;
 		}
 
-		/* Check the deviation from the watchdog clocksource. */
-		cs_nsec = clocksource_cyc2ns((csnow - cs->wd_last) &
+		wd_nsec = clocksource_cyc2ns((wdnow - cs->wd_last) & watchdog->mask,
+					     watchdog->mult, watchdog->shift);
+
+		cs_nsec = clocksource_cyc2ns((csnow - cs->cs_last) &
 					     cs->mask, cs->mult, cs->shift);
-		cs->wd_last = csnow;
+		cs->cs_last = csnow;
+		cs->wd_last = wdnow;
+
+		/* Check the deviation from the watchdog clocksource. */
 		if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
 			clocksource_unstable(cs, cs_nsec - wd_nsec);
 			continue;
@@ -318,7 +321,6 @@ static inline void clocksource_start_watchdog(void)
 		return;
 	init_timer(&watchdog_timer);
 	watchdog_timer.function = clocksource_watchdog;
-	watchdog_last = watchdog->read(watchdog);
 	watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
 	add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask));
 	watchdog_running = 1;
diff --git a/kernel/timer.c b/kernel/timer.c
index fd6198692b57..8cff36119e4d 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -749,16 +749,15 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
 	unsigned long expires_limit, mask;
 	int bit;
 
-	expires_limit = expires;
-
 	if (timer->slack >= 0) {
 		expires_limit = expires + timer->slack;
 	} else {
-		unsigned long now = jiffies;
+		long delta = expires - jiffies;
+
+		if (delta < 256)
+			return expires;
 
-		/* No slack, if already expired else auto slack 0.4% */
-		if (time_after(expires, now))
-			expires_limit = expires + (expires - now)/256;
+		expires_limit = expires + delta / 256;
 	}
 	mask = expires ^ expires_limit;
 	if (mask == 0)
@@ -795,6 +794,8 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
  */
 int mod_timer(struct timer_list *timer, unsigned long expires)
 {
+	expires = apply_slack(timer, expires);
+
 	/*
 	 * This is a common optimization triggered by the
 	 * networking code - if the timer is re-modified
@@ -803,8 +804,6 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
 	if (timer_pending(timer) && timer->expires == expires)
 		return 1;
 
-	expires = apply_slack(timer, expires);
-
 	return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);
 }
 EXPORT_SYMBOL(mod_timer);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index d017c2c82c44..908038f57440 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -109,12 +109,18 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
 static void ftrace_global_list_func(unsigned long ip,
 				    unsigned long parent_ip)
 {
-	struct ftrace_ops *op = rcu_dereference_raw(ftrace_global_list); /*see above*/
+	struct ftrace_ops *op;
+
+	if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT)))
+		return;
 
+	trace_recursion_set(TRACE_GLOBAL_BIT);
+	op = rcu_dereference_raw(ftrace_global_list); /*see above*/
 	while (op != &ftrace_list_end) {
 		op->func(ip, parent_ip);
 		op = rcu_dereference_raw(op->next); /*see above*/
 	};
+	trace_recursion_clear(TRACE_GLOBAL_BIT);
 }
 
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip)
@@ -1638,12 +1644,12 @@ static void ftrace_startup_enable(int command)
 	ftrace_run_update_code(command);
 }
 
-static void ftrace_startup(struct ftrace_ops *ops, int command)
+static int ftrace_startup(struct ftrace_ops *ops, int command)
 {
 	bool hash_enable = true;
 
 	if (unlikely(ftrace_disabled))
-		return;
+		return -ENODEV;
 
 	ftrace_start_up++;
 	command |= FTRACE_ENABLE_CALLS;
@@ -1662,6 +1668,8 @@ static void ftrace_startup(struct ftrace_ops *ops, int command)
 		ftrace_hash_rec_enable(ops, 1);
 
 	ftrace_startup_enable(command);
+
+	return 0;
 }
 
 static void ftrace_shutdown(struct ftrace_ops *ops, int command)
@@ -2501,7 +2509,7 @@ static void __enable_ftrace_function_probe(void)
 
 	ret = __register_ftrace_function(&trace_probe_ops);
 	if (!ret)
-		ftrace_startup(&trace_probe_ops, 0);
+		ret = ftrace_startup(&trace_probe_ops, 0);
 
 	ftrace_probe_registered = 1;
 }
@@ -2732,7 +2740,7 @@ static int ftrace_process_regex(struct ftrace_hash *hash,
 {
 	char *func, *command, *next = buff;
 	struct ftrace_func_command *p;
-	int ret;
+	int ret = -EINVAL;
 
 	func = strsep(&next, ":");
 
@@ -3322,6 +3330,7 @@ static int ftrace_process_locs(struct module *mod,
 {
 	unsigned long *p;
 	unsigned long addr;
+	unsigned long flags;
 
 	mutex_lock(&ftrace_lock);
 	p = start;
@@ -3338,7 +3347,13 @@ static int ftrace_process_locs(struct module *mod,
 		ftrace_record_ip(addr);
 	}
 
+	/*
+	 * Disable interrupts to prevent interrupts from executing
+	 * code that is being modified.
+	 */
+	local_irq_save(flags);
 	ftrace_update_code(mod);
+	local_irq_restore(flags);
 	mutex_unlock(&ftrace_lock);
 
 	return 0;
@@ -3466,7 +3481,11 @@ device_initcall(ftrace_nodyn_init);
 static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
 static inline void ftrace_startup_enable(int command) { }
 /* Keep as macros so we do not need to define the commands */
-# define ftrace_startup(ops, command)	do { } while (0)
+# define ftrace_startup(ops, command)			\
+	({						\
+		(ops)->flags |= FTRACE_OPS_FL_ENABLED;	\
+		0;					\
+	})
 # define ftrace_shutdown(ops, command)	do { } while (0)
 # define ftrace_startup_sysctl()	do { } while (0)
 # define ftrace_shutdown_sysctl()	do { } while (0)
@@ -3484,6 +3503,10 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
 {
 	struct ftrace_ops *op;
 
+	if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT)))
+		return;
+
+	trace_recursion_set(TRACE_INTERNAL_BIT);
 	/*
 	 * Some of the ops may be dynamically allocated,
 	 * they must be freed after a synchronize_sched().
@@ -3496,6 +3519,7 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
 		op = rcu_dereference_raw(op->next);
 	};
 	preempt_enable_notrace();
+	trace_recursion_clear(TRACE_INTERNAL_BIT);
 }
 
 static void clear_ftrace_swapper(void)
@@ -3799,7 +3823,7 @@ int register_ftrace_function(struct ftrace_ops *ops)
 
 	ret = __register_ftrace_function(ops);
 	if (!ret)
-		ftrace_startup(ops, 0);
+		ret = ftrace_startup(ops, 0);
 
 
  out_unlock:
@@ -4045,7 +4069,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	ftrace_graph_return = retfunc;
 	ftrace_graph_entry = entryfunc;
 
-	ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
+	ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
 
 out:
 	mutex_unlock(&ftrace_lock);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 0ef7b4b2a1f7..b0c7aa407943 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2216,7 +2216,7 @@ static noinline void trace_recursive_fail(void)
 
 	printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
 		    "HC[%lu]:SC[%lu]:NMI[%lu]\n",
-		    current->trace_recursion,
+		    trace_recursion_buffer(),
 		    hardirq_count() >> HARDIRQ_SHIFT,
 		    softirq_count() >> SOFTIRQ_SHIFT,
 		    in_nmi());
@@ -2226,9 +2226,9 @@ static noinline void trace_recursive_fail(void)
 
 static inline int trace_recursive_lock(void)
 {
-	current->trace_recursion++;
+	trace_recursion_inc();
 
-	if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
+	if (likely(trace_recursion_buffer() < TRACE_RECURSIVE_DEPTH))
 		return 0;
 
 	trace_recursive_fail();
@@ -2238,9 +2238,9 @@ static inline int trace_recursive_lock(void)
 
 static inline void trace_recursive_unlock(void)
 {
-	WARN_ON_ONCE(!current->trace_recursion);
+	WARN_ON_ONCE(!trace_recursion_buffer());
 
-	current->trace_recursion--;
+	trace_recursion_dec();
 }
 
 #else
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6b69c4bd306f..229f8591f61d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -784,4 +784,19 @@ extern const char *__stop___trace_bprintk_fmt[];
 	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
 #include "trace_entries.h"
 
+/* Only current can touch trace_recursion */
+#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
+#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
+
+/* Ring buffer has the 10 LSB bits to count */
+#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
+
+/* for function tracing recursion */
+#define TRACE_INTERNAL_BIT		(1<<11)
+#define TRACE_GLOBAL_BIT		(1<<12)
+
+#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (bit); } while (0)
+#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(bit); } while (0)
+#define trace_recursion_test(bit)	((current)->trace_recursion & (bit))
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 2fe110341359..686ec399f2a8 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1657,7 +1657,12 @@ static struct ftrace_ops trace_ops __initdata  =
 
 static __init void event_trace_self_test_with_function(void)
 {
-	register_ftrace_function(&trace_ops);
+	int ret;
+	ret = register_ftrace_function(&trace_ops);
+	if (WARN_ON(ret < 0)) {
+		pr_info("Failed to enable function tracer for event tests\n");
+		return;
+	}
 	pr_info("Running tests again, along with the function tracer\n");
 	event_trace_self_tests();
 	unregister_ftrace_function(&trace_ops);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index f925c45f0afa..27d13b36b8be 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1870,8 +1870,12 @@ fs_initcall(init_kprobe_trace);
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 
-static int kprobe_trace_selftest_target(int a1, int a2, int a3,
-					int a4, int a5, int a6)
+/*
+ * The "__used" keeps gcc from removing the function symbol
+ * from the kallsyms table.
+ */
+static __used int kprobe_trace_selftest_target(int a1, int a2, int a3,
+					       int a4, int a5, int a6)
 {
 	return a1 + a2 + a3 + a4 + a5 + a6;
 }
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index cf535ccedc86..e37de492a9e1 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -353,6 +353,33 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 }
 EXPORT_SYMBOL(ftrace_print_symbols_seq);
 
+#if BITS_PER_LONG == 32
+const char *
+ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val,
+			 const struct trace_print_flags_u64 *symbol_array)
+{
+	int i;
+	const char *ret = p->buffer + p->len;
+
+	for (i = 0;  symbol_array[i].name; i++) {
+
+		if (val != symbol_array[i].mask)
+			continue;
+
+		trace_seq_puts(p, symbol_array[i].name);
+		break;
+	}
+
+	if (!p->len)
+		trace_seq_printf(p, "0x%llx", val);
+
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL(ftrace_print_symbols_seq_u64);
+#endif
+
 const char *
 ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
 {
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index dff763b7baf1..1f06468a10d7 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -240,13 +240,10 @@ static const char **find_next(void *v, loff_t *pos)
 	const char **fmt = v;
 	int start_index;
 
-	if (!fmt)
-		fmt = __start___trace_bprintk_fmt + *pos;
-
 	start_index = __stop___trace_bprintk_fmt - __start___trace_bprintk_fmt;
 
 	if (*pos < start_index)
-		return fmt;
+		return __start___trace_bprintk_fmt + *pos;
 
 	return find_next_mod_format(start_index, v, fmt, pos);
 }
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 7daa4b072e9f..3d0c56ad4792 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -415,15 +415,13 @@ static void watchdog_nmi_disable(int cpu) { return; }
 #endif /* CONFIG_HARDLOCKUP_DETECTOR */
 
 /* prepare/enable/disable routines */
-static int watchdog_prepare_cpu(int cpu)
+static void watchdog_prepare_cpu(int cpu)
 {
 	struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);
 
 	WARN_ON(per_cpu(softlockup_watchdog, cpu));
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer->function = watchdog_timer_fn;
-
-	return 0;
 }
 
 static int watchdog_enable(int cpu)
@@ -542,17 +540,16 @@ static int __cpuinit
 cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
 	int hotcpu = (unsigned long)hcpu;
-	int err = 0;
 
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		err = watchdog_prepare_cpu(hotcpu);
+		watchdog_prepare_cpu(hotcpu);
 		break;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
 		if (watchdog_enabled)
-			err = watchdog_enable(hotcpu);
+			watchdog_enable(hotcpu);
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 28afa4c5333c..dd373c8ee943 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -697,7 +697,7 @@ config DEBUG_BUGVERBOSE
 	bool "Verbose BUG() reporting (adds 70K)" if DEBUG_KERNEL && EXPERT
 	depends on BUG
 	depends on ARM || AVR32 || M32R || M68K || SPARC32 || SPARC64 || \
-		   FRV || SUPERH || GENERIC_BUG || BLACKFIN || MN10300
+		   FRV || SUPERH || GENERIC_BUG || BLACKFIN || MN10300 || TILE
 	default y
 	help
 	  Say Y here to make BUG() panics output the file name and line number
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 41baf02924e6..3f3b68199d74 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -572,7 +572,7 @@ EXPORT_SYMBOL(bitmap_scnlistprintf);
 
 /**
  * __bitmap_parselist - convert list format ASCII string to bitmap
- * @bp: read nul-terminated user string from this buffer
+ * @buf: read nul-terminated user string from this buffer
  * @buflen: buffer size in bytes.  If string is smaller than this
  *    then it must be terminated with a \0.
  * @is_user: location of buffer, 0 indicates kernel space
diff --git a/lib/kobject.c b/lib/kobject.c
index 82dc34c095c2..640bd98a4c8a 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -948,14 +948,14 @@ const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj)
 }
 
 
-const void *kobj_ns_current(enum kobj_ns_type type)
+void *kobj_ns_grab_current(enum kobj_ns_type type)
 {
-	const void *ns = NULL;
+	void *ns = NULL;
 
 	spin_lock(&kobj_ns_type_lock);
 	if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) &&
 	    kobj_ns_ops_tbl[type])
-		ns = kobj_ns_ops_tbl[type]->current_ns();
+		ns = kobj_ns_ops_tbl[type]->grab_current_ns();
 	spin_unlock(&kobj_ns_type_lock);
 
 	return ns;
@@ -987,23 +987,15 @@ const void *kobj_ns_initial(enum kobj_ns_type type)
 	return ns;
 }
 
-/*
- * kobj_ns_exit - invalidate a namespace tag
- *
- * @type: the namespace type (i.e. KOBJ_NS_TYPE_NET)
- * @ns: the actual namespace being invalidated
- *
- * This is called when a tag is no longer valid.  For instance,
- * when a network namespace exits, it uses this helper to
- * make sure no sb's sysfs_info points to the now-invalidated
- * netns.
- */
-void kobj_ns_exit(enum kobj_ns_type type, const void *ns)
+void kobj_ns_drop(enum kobj_ns_type type, void *ns)
 {
-	sysfs_exit_ns(type, ns);
+	spin_lock(&kobj_ns_type_lock);
+	if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) &&
+	    kobj_ns_ops_tbl[type] && kobj_ns_ops_tbl[type]->drop_ns)
+		kobj_ns_ops_tbl[type]->drop_ns(ns);
+	spin_unlock(&kobj_ns_type_lock);
 }
 
-
 EXPORT_SYMBOL(kobject_get);
 EXPORT_SYMBOL(kobject_put);
 EXPORT_SYMBOL(kobject_del);
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 619313ed6c46..507a22fab738 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -144,7 +144,7 @@ static void init_shared_classes(void)
 
 #define HARDIRQ_ENTER()				\
 	local_irq_disable();			\
-	irq_enter();				\
+	__irq_enter();				\
 	WARN_ON(!in_irq());
 
 #define HARDIRQ_EXIT()				\
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 93ca08b8a451..99093b396145 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -110,6 +110,11 @@ setup_io_tlb_npages(char *str)
 __setup("swiotlb=", setup_io_tlb_npages);
 /* make io_tlb_overflow tunable too? */
 
+unsigned long swioltb_nr_tbl(void)
+{
+	return io_tlb_nslabs;
+}
+
 /* Note that this doesn't work with highmem page */
 static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
 				      volatile void *address)
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index c11205688fb4..4365df31a1d5 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -666,6 +666,8 @@ char *ip6_compressed_string(char *p, const char *addr)
 			colonpos = i;
 		}
 	}
+	if (longest == 1)		/* don't compress a single 0 */
+		colonpos = -1;
 
 	/* emit address */
 	for (i = 0; i < range; i++) {
@@ -826,7 +828,7 @@ int kptr_restrict __read_mostly;
  *       IPv4 uses dot-separated decimal with leading 0's (010.123.045.006)
  * - '[Ii]4[hnbl]' IPv4 addresses in host, network, big or little endian order
  * - 'I6c' for IPv6 addresses printed as specified by
- *       http://tools.ietf.org/html/draft-ietf-6man-text-addr-representation-00
+ *       http://tools.ietf.org/html/rfc5952
  * - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form
  *       "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
  *       Options for %pU are:
diff --git a/mm/compaction.c b/mm/compaction.c
index 021a2960ef9e..6cc604bd5649 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -144,9 +144,20 @@ static void isolate_freepages(struct zone *zone,
 	int nr_freepages = cc->nr_freepages;
 	struct list_head *freelist = &cc->freepages;
 
+	/*
+	 * Initialise the free scanner. The starting point is where we last
+	 * scanned from (or the end of the zone if starting). The low point
+	 * is the end of the pageblock the migration scanner is using.
+	 */
 	pfn = cc->free_pfn;
 	low_pfn = cc->migrate_pfn + pageblock_nr_pages;
-	high_pfn = low_pfn;
+
+	/*
+	 * Take care that if the migration scanner is at the end of the zone
+	 * that the free scanner does not accidentally move to the next zone
+	 * in the next isolation cycle.
+	 */
+	high_pfn = min(low_pfn, pfn);
 
 	/*
 	 * Isolate free pages until enough are available to migrate the
@@ -240,11 +251,18 @@ static bool too_many_isolated(struct zone *zone)
 	return isolated > (inactive + active) / 2;
 }
 
+/* possible outcome of isolate_migratepages */
+typedef enum {
+	ISOLATE_ABORT,		/* Abort compaction now */
+	ISOLATE_NONE,		/* No pages isolated, continue scanning */
+	ISOLATE_SUCCESS,	/* Pages isolated, migrate */
+} isolate_migrate_t;
+
 /*
  * Isolate all pages that can be migrated from the block pointed to by
  * the migrate scanner within compact_control.
  */
-static unsigned long isolate_migratepages(struct zone *zone,
+static isolate_migrate_t isolate_migratepages(struct zone *zone,
 					struct compact_control *cc)
 {
 	unsigned long low_pfn, end_pfn;
@@ -261,7 +279,7 @@ static unsigned long isolate_migratepages(struct zone *zone,
 	/* Do not cross the free scanner or scan within a memory hole */
 	if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) {
 		cc->migrate_pfn = end_pfn;
-		return 0;
+		return ISOLATE_NONE;
 	}
 
 	/*
@@ -270,10 +288,14 @@ static unsigned long isolate_migratepages(struct zone *zone,
 	 * delay for some time until fewer pages are isolated
 	 */
 	while (unlikely(too_many_isolated(zone))) {
+		/* async migration should just abort */
+		if (!cc->sync)
+			return ISOLATE_ABORT;
+
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 		if (fatal_signal_pending(current))
-			return 0;
+			return ISOLATE_ABORT;
 	}
 
 	/* Time to isolate some pages for migration */
@@ -358,7 +380,7 @@ static unsigned long isolate_migratepages(struct zone *zone,
 
 	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
 
-	return cc->nr_migratepages;
+	return ISOLATE_SUCCESS;
 }
 
 /*
@@ -420,13 +442,6 @@ static int compact_finished(struct zone *zone,
 	if (cc->free_pfn <= cc->migrate_pfn)
 		return COMPACT_COMPLETE;
 
-	/* Compaction run is not finished if the watermark is not met */
-	watermark = low_wmark_pages(zone);
-	watermark += (1 << cc->order);
-
-	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
-		return COMPACT_CONTINUE;
-
 	/*
 	 * order == -1 is expected when compacting via
 	 * /proc/sys/vm/compact_memory
@@ -434,6 +449,13 @@ static int compact_finished(struct zone *zone,
 	if (cc->order == -1)
 		return COMPACT_CONTINUE;
 
+	/* Compaction run is not finished if the watermark is not met */
+	watermark = low_wmark_pages(zone);
+	watermark += (1 << cc->order);
+
+	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
+		return COMPACT_CONTINUE;
+
 	/* Direct compactor: Is a suitable page free? */
 	for (order = cc->order; order < MAX_ORDER; order++) {
 		/* Job done if page is free of the right migratetype */
@@ -461,6 +483,13 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 	unsigned long watermark;
 
 	/*
+	 * order == -1 is expected when compacting via
+	 * /proc/sys/vm/compact_memory
+	 */
+	if (order == -1)
+		return COMPACT_CONTINUE;
+
+	/*
 	 * Watermarks for order-0 must be met for compaction. Note the 2UL.
 	 * This is because during migration, copies of pages need to be
 	 * allocated and for a short time, the footprint is higher
@@ -470,17 +499,11 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 		return COMPACT_SKIPPED;
 
 	/*
-	 * order == -1 is expected when compacting via
-	 * /proc/sys/vm/compact_memory
-	 */
-	if (order == -1)
-		return COMPACT_CONTINUE;
-
-	/*
 	 * fragmentation index determines if allocation failures are due to
 	 * low memory or external fragmentation
 	 *
-	 * index of -1 implies allocations might succeed dependingon watermarks
+	 * index of -1000 implies allocations might succeed depending on
+	 * watermarks
 	 * index towards 0 implies failure is due to lack of memory
 	 * index towards 1000 implies failure is due to fragmentation
 	 *
@@ -490,7 +513,8 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 	if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
 		return COMPACT_SKIPPED;
 
-	if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0))
+	if (fragindex == -1000 && zone_watermark_ok(zone, order, watermark,
+	    0, 0))
 		return COMPACT_PARTIAL;
 
 	return COMPACT_CONTINUE;
@@ -522,8 +546,15 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		unsigned long nr_migrate, nr_remaining;
 		int err;
 
-		if (!isolate_migratepages(zone, cc))
+		switch (isolate_migratepages(zone, cc)) {
+		case ISOLATE_ABORT:
+			ret = COMPACT_PARTIAL;
+			goto out;
+		case ISOLATE_NONE:
 			continue;
+		case ISOLATE_SUCCESS:
+			;
+		}
 
 		nr_migrate = cc->nr_migratepages;
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
@@ -547,6 +578,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 
 	}
 
+out:
 	/* Release free pages and check accounting */
 	cc->nr_freepages -= release_freepages(&cc->freepages);
 	VM_BUG_ON(cc->nr_freepages != 0);
diff --git a/mm/filemap.c b/mm/filemap.c
index bcdc393b6580..a8251a8d3457 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1982,16 +1982,26 @@ static int __remove_suid(struct dentry *dentry, int kill)
 int file_remove_suid(struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry;
-	int killsuid = should_remove_suid(dentry);
-	int killpriv = security_inode_need_killpriv(dentry);
+	struct inode *inode = dentry->d_inode;
+	int killsuid;
+	int killpriv;
 	int error = 0;
 
+	/* Fast path for nothing security related */
+	if (IS_NOSEC(inode))
+		return 0;
+
+	killsuid = should_remove_suid(dentry);
+	killpriv = security_inode_need_killpriv(dentry);
+
 	if (killpriv < 0)
 		return killpriv;
 	if (killpriv)
 		error = security_inode_killpriv(dentry);
 	if (!error && killsuid)
 		error = __remove_suid(dentry, killsuid);
+	if (!error && (inode->i_sb->s_flags & MS_NOSEC))
+		inode->i_flags |= S_NOSEC;
 
 	return error;
 }
@@ -2327,7 +2337,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
 repeat:
 	page = find_lock_page(mapping, index);
 	if (page)
-		return page;
+		goto found;
 
 	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask);
 	if (!page)
@@ -2340,6 +2350,8 @@ repeat:
 			goto repeat;
 		return NULL;
 	}
+found:
+	wait_on_page_writeback(page);
 	return page;
 }
 EXPORT_SYMBOL(grab_cache_page_write_begin);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 615d9743a3cb..81532f297fd2 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2234,11 +2234,8 @@ static void khugepaged_loop(void)
 	while (likely(khugepaged_enabled())) {
 #ifndef CONFIG_NUMA
 		hpage = khugepaged_alloc_hugepage();
-		if (unlikely(!hpage)) {
-			count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
+		if (unlikely(!hpage))
 			break;
-		}
-		count_vm_event(THP_COLLAPSE_ALLOC);
 #else
 		if (IS_ERR(hpage)) {
 			khugepaged_alloc_sleep();
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f33bb319b73f..bfcf153bc829 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1033,10 +1033,10 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	 */
 	chg = vma_needs_reservation(h, vma, addr);
 	if (chg < 0)
-		return ERR_PTR(chg);
+		return ERR_PTR(-VM_FAULT_OOM);
 	if (chg)
 		if (hugetlb_get_quota(inode->i_mapping, chg))
-			return ERR_PTR(-ENOSPC);
+			return ERR_PTR(-VM_FAULT_SIGBUS);
 
 	spin_lock(&hugetlb_lock);
 	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
@@ -1111,6 +1111,14 @@ static void __init gather_bootmem_prealloc(void)
 		WARN_ON(page_count(page) != 1);
 		prep_compound_huge_page(page, h->order);
 		prep_new_huge_page(h, page, page_to_nid(page));
+		/*
+		 * If we had gigantic hugepages allocated at boot time, we need
+		 * to restore the 'stolen' pages to totalram_pages in order to
+		 * fix confusing memory reports from free(1) and another
+		 * side-effects, like CommitLimit going negative.
+		 */
+		if (h->order > (MAX_ORDER - 1))
+			totalram_pages += 1 << h->order;
 	}
 }
 
diff --git a/mm/ksm.c b/mm/ksm.c
index d708b3ef2260..9a68b0cf0a1c 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1302,6 +1302,12 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page)
 		slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list);
 		ksm_scan.mm_slot = slot;
 		spin_unlock(&ksm_mmlist_lock);
+		/*
+		 * Although we tested list_empty() above, a racing __ksm_exit
+		 * of the last mm on the list may have removed it since then.
+		 */
+		if (slot == &ksm_mm_head)
+			return NULL;
 next_mm:
 		ksm_scan.address = 0;
 		ksm_scan.rmap_list = &slot->rmap_list;
diff --git a/mm/maccess.c b/mm/maccess.c
index e2b6f5634e0d..4cee182ab5f3 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -15,10 +15,10 @@
  * happens, handle that and return -EFAULT.
  */
 
-long __weak probe_kernel_read(void *dst, void *src, size_t size)
+long __weak probe_kernel_read(void *dst, const void *src, size_t size)
     __attribute__((alias("__probe_kernel_read")));
 
-long __probe_kernel_read(void *dst, void *src, size_t size)
+long __probe_kernel_read(void *dst, const void *src, size_t size)
 {
 	long ret;
 	mm_segment_t old_fs = get_fs();
@@ -43,10 +43,10 @@ EXPORT_SYMBOL_GPL(probe_kernel_read);
  * Safely write to address @dst from the buffer at @src.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-long __weak probe_kernel_write(void *dst, void *src, size_t size)
+long __weak probe_kernel_write(void *dst, const void *src, size_t size)
     __attribute__((alias("__probe_kernel_write")));
 
-long __probe_kernel_write(void *dst, void *src, size_t size)
+long __probe_kernel_write(void *dst, const void *src, size_t size)
 {
 	long ret;
 	mm_segment_t old_fs = get_fs();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index bd9052a5d3ad..ddffc74cdebe 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -35,6 +35,7 @@
 #include <linux/limits.h>
 #include <linux/mutex.h>
 #include <linux/rbtree.h>
+#include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
@@ -359,7 +360,7 @@ enum charge_type {
 static void mem_cgroup_get(struct mem_cgroup *mem);
 static void mem_cgroup_put(struct mem_cgroup *mem);
 static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem);
-static void drain_all_stock_async(void);
+static void drain_all_stock_async(struct mem_cgroup *mem);
 
 static struct mem_cgroup_per_zone *
 mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
@@ -735,7 +736,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 				struct mem_cgroup, css);
 }
 
-static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
+struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 {
 	struct mem_cgroup *mem = NULL;
 
@@ -1663,15 +1664,21 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 	excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT;
 
 	/* If memsw_is_minimum==1, swap-out is of-no-use. */
-	if (root_mem->memsw_is_minimum)
+	if (!check_soft && root_mem->memsw_is_minimum)
 		noswap = true;
 
 	while (1) {
 		victim = mem_cgroup_select_victim(root_mem);
 		if (victim == root_mem) {
 			loop++;
-			if (loop >= 1)
-				drain_all_stock_async();
+			/*
+			 * We are not draining per cpu cached charges during
+			 * soft limit reclaim  because global reclaim doesn't
+			 * care about charges. It tries to free some memory and
+			 * charges will not give any.
+			 */
+			if (!check_soft && loop >= 1)
+				drain_all_stock_async(root_mem);
 			if (loop >= 2) {
 				/*
 				 * If we have not been able to reclaim
@@ -1934,9 +1941,11 @@ struct memcg_stock_pcp {
 	struct mem_cgroup *cached; /* this never be root cgroup */
 	unsigned int nr_pages;
 	struct work_struct work;
+	unsigned long flags;
+#define FLUSHING_CACHED_CHARGE	(0)
 };
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
-static atomic_t memcg_drain_count;
+static DEFINE_MUTEX(percpu_charge_mutex);
 
 /*
  * Try to consume stocked charge on this cpu. If success, one page is consumed
@@ -1984,6 +1993,7 @@ static void drain_local_stock(struct work_struct *dummy)
 {
 	struct memcg_stock_pcp *stock = &__get_cpu_var(memcg_stock);
 	drain_stock(stock);
+	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
 }
 
 /*
@@ -2008,26 +2018,45 @@ static void refill_stock(struct mem_cgroup *mem, unsigned int nr_pages)
  * expects some charges will be back to res_counter later but cannot wait for
  * it.
  */
-static void drain_all_stock_async(void)
+static void drain_all_stock_async(struct mem_cgroup *root_mem)
 {
-	int cpu;
-	/* This function is for scheduling "drain" in asynchronous way.
-	 * The result of "drain" is not directly handled by callers. Then,
-	 * if someone is calling drain, we don't have to call drain more.
-	 * Anyway, WORK_STRUCT_PENDING check in queue_work_on() will catch if
-	 * there is a race. We just do loose check here.
+	int cpu, curcpu;
+	/*
+	 * If someone calls draining, avoid adding more kworker runs.
 	 */
-	if (atomic_read(&memcg_drain_count))
+	if (!mutex_trylock(&percpu_charge_mutex))
 		return;
 	/* Notify other cpus that system-wide "drain" is running */
-	atomic_inc(&memcg_drain_count);
 	get_online_cpus();
+	/*
+	 * Get a hint for avoiding draining charges on the current cpu,
+	 * which must be exhausted by our charging.  It is not required that
+	 * this be a precise check, so we use raw_smp_processor_id() instead of
+	 * getcpu()/putcpu().
+	 */
+	curcpu = raw_smp_processor_id();
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
-		schedule_work_on(cpu, &stock->work);
+		struct mem_cgroup *mem;
+
+		if (cpu == curcpu)
+			continue;
+
+		mem = stock->cached;
+		if (!mem)
+			continue;
+		if (mem != root_mem) {
+			if (!root_mem->use_hierarchy)
+				continue;
+			/* check whether "mem" is under tree of "root_mem" */
+			if (!css_is_ancestor(&mem->css, &root_mem->css))
+				continue;
+		}
+		if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
+			schedule_work_on(cpu, &stock->work);
 	}
  	put_online_cpus();
-	atomic_dec(&memcg_drain_count);
+	mutex_unlock(&percpu_charge_mutex);
 	/* We don't wait for flush_work */
 }
 
@@ -2035,9 +2064,9 @@ static void drain_all_stock_async(void)
 static void drain_all_stock_sync(void)
 {
 	/* called when force_empty is called */
-	atomic_inc(&memcg_drain_count);
+	mutex_lock(&percpu_charge_mutex);
 	schedule_on_each_cpu(drain_local_stock);
-	atomic_dec(&memcg_drain_count);
+	mutex_unlock(&percpu_charge_mutex);
 }
 
 /*
@@ -4640,6 +4669,7 @@ static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "numa_stat",
 		.open = mem_control_numa_stat_open,
+		.mode = S_IRUGO,
 	},
 #endif
 };
@@ -5414,18 +5444,16 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
 				struct cgroup *old_cont,
 				struct task_struct *p)
 {
-	struct mm_struct *mm;
+	struct mm_struct *mm = get_task_mm(p);
 
-	if (!mc.to)
-		/* no need to move charge */
-		return;
-
-	mm = get_task_mm(p);
 	if (mm) {
-		mem_cgroup_move_charge(mm);
+		if (mc.to)
+			mem_cgroup_move_charge(mm);
+		put_swap_token(mm);
 		mmput(mm);
 	}
-	mem_cgroup_clear_mc();
+	if (mc.to)
+		mem_cgroup_clear_mc();
 }
 #else	/* !CONFIG_MMU */
 static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 5c8f7e08928d..740c4f52059c 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -52,6 +52,7 @@
 #include <linux/swapops.h>
 #include <linux/hugetlb.h>
 #include <linux/memory_hotplug.h>
+#include <linux/mm_inline.h>
 #include "internal.h"
 
 int sysctl_memory_failure_early_kill __read_mostly = 0;
@@ -390,10 +391,11 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	struct task_struct *tsk;
 	struct anon_vma *av;
 
-	read_lock(&tasklist_lock);
 	av = page_lock_anon_vma(page);
 	if (av == NULL)	/* Not actually mapped anymore */
-		goto out;
+		return;
+
+	read_lock(&tasklist_lock);
 	for_each_process (tsk) {
 		struct anon_vma_chain *vmac;
 
@@ -407,9 +409,8 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 				add_to_kill(tsk, page, vma, to_kill, tkc);
 		}
 	}
-	page_unlock_anon_vma(av);
-out:
 	read_unlock(&tasklist_lock);
+	page_unlock_anon_vma(av);
 }
 
 /*
@@ -423,17 +424,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	struct prio_tree_iter iter;
 	struct address_space *mapping = page->mapping;
 
-	/*
-	 * A note on the locking order between the two locks.
-	 * We don't rely on this particular order.
-	 * If you have some other code that needs a different order
-	 * feel free to switch them around. Or add a reverse link
-	 * from mm_struct to task_struct, then this could be all
-	 * done without taking tasklist_lock and looping over all tasks.
-	 */
-
-	read_lock(&tasklist_lock);
 	mutex_lock(&mapping->i_mmap_mutex);
+	read_lock(&tasklist_lock);
 	for_each_process(tsk) {
 		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
 
@@ -453,8 +445,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 				add_to_kill(tsk, page, vma, to_kill, tkc);
 		}
 	}
-	mutex_unlock(&mapping->i_mmap_mutex);
 	read_unlock(&tasklist_lock);
+	mutex_unlock(&mapping->i_mmap_mutex);
 }
 
 /*
@@ -1468,7 +1460,8 @@ int soft_offline_page(struct page *page, int flags)
 	put_page(page);
 	if (!ret) {
 		LIST_HEAD(pagelist);
-
+		inc_zone_page_state(page, NR_ISOLATED_ANON +
+					    page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
 		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
 								0, true);
diff --git a/mm/memory.c b/mm/memory.c
index 6953d3926e01..40b7531ee8ba 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1112,11 +1112,13 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	int force_flush = 0;
 	int rss[NR_MM_COUNTERS];
 	spinlock_t *ptl;
+	pte_t *start_pte;
 	pte_t *pte;
 
 again:
 	init_rss_vec(rss);
-	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	pte = start_pte;
 	arch_enter_lazy_mmu_mode();
 	do {
 		pte_t ptent = *pte;
@@ -1196,7 +1198,7 @@ again:
 
 	add_mm_rss_vec(mm, rss);
 	arch_leave_lazy_mmu_mode();
-	pte_unmap_unlock(pte - 1, ptl);
+	pte_unmap_unlock(start_pte, ptl);
 
 	/*
 	 * mmu_gather ran out of room to batch pages, we break out of
@@ -1296,7 +1298,7 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb,
 
 /**
  * unmap_vmas - unmap a range of memory covered by a list of vma's
- * @tlbp: address of the caller's struct mmu_gather
+ * @tlb: address of the caller's struct mmu_gather
  * @vma: the starting vma
  * @start_addr: virtual address at which to start unmapping
  * @end_addr: virtual address at which to end unmapping
@@ -2796,30 +2798,6 @@ void unmap_mapping_range(struct address_space *mapping,
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
-int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
-{
-	struct address_space *mapping = inode->i_mapping;
-
-	/*
-	 * If the underlying filesystem is not going to provide
-	 * a way to truncate a range of blocks (punch a hole) -
-	 * we should return failure right now.
-	 */
-	if (!inode->i_op->truncate_range)
-		return -ENOSYS;
-
-	mutex_lock(&inode->i_mutex);
-	down_write(&inode->i_alloc_sem);
-	unmap_mapping_range(mapping, offset, (end - offset), 1);
-	truncate_inode_pages_range(mapping, offset, end);
-	unmap_mapping_range(mapping, offset, (end - offset), 1);
-	inode->i_op->truncate_range(inode, offset, end);
-	up_write(&inode->i_alloc_sem);
-	mutex_unlock(&inode->i_mutex);
-
-	return 0;
-}
-
 /*
  * We enter with non-exclusive mmap_sem (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9f646374e32f..c46887b5a11e 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -494,6 +494,14 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 	/* init node's zones as empty zones, we don't have any present pages.*/
 	free_area_init_node(nid, zones_size, start_pfn, zholes_size);
 
+	/*
+	 * The node we allocated has no zone fallback lists. For avoiding
+	 * to access not-initialized zonelist, build here.
+	 */
+	mutex_lock(&zonelists_mutex);
+	build_all_zonelists(NULL);
+	mutex_unlock(&zonelists_mutex);
+
 	return pgdat;
 }
 
@@ -515,7 +523,7 @@ int mem_online_node(int nid)
 
 	lock_memory_hotplug();
 	pgdat = hotadd_new_pgdat(nid, 0);
-	if (pgdat) {
+	if (!pgdat) {
 		ret = -ENOMEM;
 		goto out;
 	}
diff --git a/mm/migrate.c b/mm/migrate.c
index e4a5c912983d..666e4e677414 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -288,7 +288,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	 */
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	__inc_zone_page_state(newpage, NR_FILE_PAGES);
-	if (PageSwapBacked(page)) {
+	if (!PageSwapCache(page) && PageSwapBacked(page)) {
 		__dec_zone_page_state(page, NR_SHMEM);
 		__inc_zone_page_state(newpage, NR_SHMEM);
 	}
diff --git a/mm/mmap.c b/mm/mmap.c
index bbdc9af5e117..d49736ff8a8d 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -906,14 +906,7 @@ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma)
 	if (anon_vma)
 		return anon_vma;
 try_prev:
-	/*
-	 * It is potentially slow to have to call find_vma_prev here.
-	 * But it's only on the first write fault on the vma, not
-	 * every time, and we could devise a way to avoid it later
-	 * (e.g. stash info in next's anon_vma_node when assigning
-	 * an anon_vma, or when trying vma_merge).  Another time.
-	 */
-	BUG_ON(find_vma_prev(vma->vm_mm, vma->vm_start, &near) != vma);
+	near = vma->vm_prev;
 	if (!near)
 		goto none;
 
@@ -2044,9 +2037,10 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 		return -EINVAL;
 
 	/* Find the first overlapping VMA */
-	vma = find_vma_prev(mm, start, &prev);
+	vma = find_vma(mm, start);
 	if (!vma)
 		return 0;
+	prev = vma->vm_prev;
 	/* we have  start < vma->vm_end  */
 
 	/* if it doesn't overlap, we have nothing.. */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a4e1db3f1981..4e8985acdab8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2247,10 +2247,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 
 	if (should_fail_alloc_page(gfp_mask, order))
 		return NULL;
-#ifndef CONFIG_ZONE_DMA
-	if (WARN_ON_ONCE(gfp_mask & __GFP_DMA))
-		return NULL;
-#endif
 
 	/*
 	 * Check the zones suitable for the gfp_mask contain at least one
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 74ccff61d1be..53bffc6c293e 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -162,13 +162,13 @@ static void free_page_cgroup(void *addr)
 }
 #endif
 
-static int __meminit init_section_page_cgroup(unsigned long pfn)
+static int __meminit init_section_page_cgroup(unsigned long pfn, int nid)
 {
 	struct page_cgroup *base, *pc;
 	struct mem_section *section;
 	unsigned long table_size;
 	unsigned long nr;
-	int nid, index;
+	int index;
 
 	nr = pfn_to_section_nr(pfn);
 	section = __nr_to_section(nr);
@@ -176,7 +176,6 @@ static int __meminit init_section_page_cgroup(unsigned long pfn)
 	if (section->page_cgroup)
 		return 0;
 
-	nid = page_to_nid(pfn_to_page(pfn));
 	table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
 	base = alloc_page_cgroup(table_size, nid);
 
@@ -196,7 +195,11 @@ static int __meminit init_section_page_cgroup(unsigned long pfn)
 		pc = base + index;
 		init_page_cgroup(pc, nr);
 	}
-
+	/*
+	 * The passed "pfn" may not be aligned to SECTION.  For the calculation
+	 * we need to apply a mask.
+	 */
+	pfn &= PAGE_SECTION_MASK;
 	section->page_cgroup = base - pfn;
 	total_usage += table_size;
 	return 0;
@@ -225,10 +228,20 @@ int __meminit online_page_cgroup(unsigned long start_pfn,
 	start = start_pfn & ~(PAGES_PER_SECTION - 1);
 	end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
 
+	if (nid == -1) {
+		/*
+		 * In this case, "nid" already exists and contains valid memory.
+		 * "start_pfn" passed to us is a pfn which is an arg for
+		 * online__pages(), and start_pfn should exist.
+		 */
+		nid = pfn_to_nid(start_pfn);
+		VM_BUG_ON(!node_state(nid, N_ONLINE));
+	}
+
 	for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
 		if (!pfn_present(pfn))
 			continue;
-		fail = init_section_page_cgroup(pfn);
+		fail = init_section_page_cgroup(pfn, nid);
 	}
 	if (!fail)
 		return 0;
@@ -284,25 +297,47 @@ static int __meminit page_cgroup_callback(struct notifier_block *self,
 void __init page_cgroup_init(void)
 {
 	unsigned long pfn;
-	int fail = 0;
+	int nid;
 
 	if (mem_cgroup_disabled())
 		return;
 
-	for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) {
-		if (!pfn_present(pfn))
-			continue;
-		fail = init_section_page_cgroup(pfn);
-	}
-	if (fail) {
-		printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
-		panic("Out of memory");
-	} else {
-		hotplug_memory_notifier(page_cgroup_callback, 0);
+	for_each_node_state(nid, N_HIGH_MEMORY) {
+		unsigned long start_pfn, end_pfn;
+
+		start_pfn = node_start_pfn(nid);
+		end_pfn = node_end_pfn(nid);
+		/*
+		 * start_pfn and end_pfn may not be aligned to SECTION and the
+		 * page->flags of out of node pages are not initialized.  So we
+		 * scan [start_pfn, the biggest section's pfn < end_pfn) here.
+		 */
+		for (pfn = start_pfn;
+		     pfn < end_pfn;
+                     pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) {
+
+			if (!pfn_valid(pfn))
+				continue;
+			/*
+			 * Nodes's pfns can be overlapping.
+			 * We know some arch can have a nodes layout such as
+			 * -------------pfn-------------->
+			 * N0 | N1 | N2 | N0 | N1 | N2|....
+			 */
+			if (pfn_to_nid(pfn) != nid)
+				continue;
+			if (init_section_page_cgroup(pfn, nid))
+				goto oom;
+		}
 	}
+	hotplug_memory_notifier(page_cgroup_callback, 0);
 	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
-	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you don't"
-	" want memory cgroups\n");
+	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you "
+			 "don't want memory cgroups\n");
+	return;
+oom:
+	printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
+	panic("Out of memory");
 }
 
 void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
diff --git a/mm/rmap.c b/mm/rmap.c
index 3a39b518a653..23295f65ae43 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -38,9 +38,8 @@
  *                           in arch-dependent flush_dcache_mmap_lock,
  *                           within inode_wb_list_lock in __sync_single_inode)
  *
- * (code doesn't rely on that order so it could be switched around)
- * ->tasklist_lock
- *   anon_vma->mutex      (memory_failure, collect_procs_anon)
+ * anon_vma->mutex,mapping->i_mutex      (memory_failure, collect_procs_anon)
+ *   ->tasklist_lock
  *     pte map lock
  */
 
@@ -112,9 +111,9 @@ static inline void anon_vma_free(struct anon_vma *anon_vma)
 	kmem_cache_free(anon_vma_cachep, anon_vma);
 }
 
-static inline struct anon_vma_chain *anon_vma_chain_alloc(void)
+static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp)
 {
-	return kmem_cache_alloc(anon_vma_chain_cachep, GFP_KERNEL);
+	return kmem_cache_alloc(anon_vma_chain_cachep, gfp);
 }
 
 static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain)
@@ -159,7 +158,7 @@ int anon_vma_prepare(struct vm_area_struct *vma)
 		struct mm_struct *mm = vma->vm_mm;
 		struct anon_vma *allocated;
 
-		avc = anon_vma_chain_alloc();
+		avc = anon_vma_chain_alloc(GFP_KERNEL);
 		if (!avc)
 			goto out_enomem;
 
@@ -200,6 +199,32 @@ int anon_vma_prepare(struct vm_area_struct *vma)
 	return -ENOMEM;
 }
 
+/*
+ * This is a useful helper function for locking the anon_vma root as
+ * we traverse the vma->anon_vma_chain, looping over anon_vma's that
+ * have the same vma.
+ *
+ * Such anon_vma's should have the same root, so you'd expect to see
+ * just a single mutex_lock for the whole traversal.
+ */
+static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma)
+{
+	struct anon_vma *new_root = anon_vma->root;
+	if (new_root != root) {
+		if (WARN_ON_ONCE(root))
+			mutex_unlock(&root->mutex);
+		root = new_root;
+		mutex_lock(&root->mutex);
+	}
+	return root;
+}
+
+static inline void unlock_anon_vma_root(struct anon_vma *root)
+{
+	if (root)
+		mutex_unlock(&root->mutex);
+}
+
 static void anon_vma_chain_link(struct vm_area_struct *vma,
 				struct anon_vma_chain *avc,
 				struct anon_vma *anon_vma)
@@ -208,13 +233,11 @@ static void anon_vma_chain_link(struct vm_area_struct *vma,
 	avc->anon_vma = anon_vma;
 	list_add(&avc->same_vma, &vma->anon_vma_chain);
 
-	anon_vma_lock(anon_vma);
 	/*
 	 * It's critical to add new vmas to the tail of the anon_vma,
 	 * see comment in huge_memory.c:__split_huge_page().
 	 */
 	list_add_tail(&avc->same_anon_vma, &anon_vma->head);
-	anon_vma_unlock(anon_vma);
 }
 
 /*
@@ -224,13 +247,24 @@ static void anon_vma_chain_link(struct vm_area_struct *vma,
 int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 {
 	struct anon_vma_chain *avc, *pavc;
+	struct anon_vma *root = NULL;
 
 	list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
-		avc = anon_vma_chain_alloc();
-		if (!avc)
-			goto enomem_failure;
-		anon_vma_chain_link(dst, avc, pavc->anon_vma);
+		struct anon_vma *anon_vma;
+
+		avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN);
+		if (unlikely(!avc)) {
+			unlock_anon_vma_root(root);
+			root = NULL;
+			avc = anon_vma_chain_alloc(GFP_KERNEL);
+			if (!avc)
+				goto enomem_failure;
+		}
+		anon_vma = pavc->anon_vma;
+		root = lock_anon_vma_root(root, anon_vma);
+		anon_vma_chain_link(dst, avc, anon_vma);
 	}
+	unlock_anon_vma_root(root);
 	return 0;
 
  enomem_failure:
@@ -263,7 +297,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	anon_vma = anon_vma_alloc();
 	if (!anon_vma)
 		goto out_error;
-	avc = anon_vma_chain_alloc();
+	avc = anon_vma_chain_alloc(GFP_KERNEL);
 	if (!avc)
 		goto out_error_free_anon_vma;
 
@@ -280,7 +314,9 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	get_anon_vma(anon_vma->root);
 	/* Mark this anon_vma as the one where our new (COWed) pages go. */
 	vma->anon_vma = anon_vma;
+	anon_vma_lock(anon_vma);
 	anon_vma_chain_link(vma, avc, anon_vma);
+	anon_vma_unlock(anon_vma);
 
 	return 0;
 
@@ -291,36 +327,43 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	return -ENOMEM;
 }
 
-static void anon_vma_unlink(struct anon_vma_chain *anon_vma_chain)
-{
-	struct anon_vma *anon_vma = anon_vma_chain->anon_vma;
-	int empty;
-
-	/* If anon_vma_fork fails, we can get an empty anon_vma_chain. */
-	if (!anon_vma)
-		return;
-
-	anon_vma_lock(anon_vma);
-	list_del(&anon_vma_chain->same_anon_vma);
-
-	/* We must garbage collect the anon_vma if it's empty */
-	empty = list_empty(&anon_vma->head);
-	anon_vma_unlock(anon_vma);
-
-	if (empty)
-		put_anon_vma(anon_vma);
-}
-
 void unlink_anon_vmas(struct vm_area_struct *vma)
 {
 	struct anon_vma_chain *avc, *next;
+	struct anon_vma *root = NULL;
 
 	/*
 	 * Unlink each anon_vma chained to the VMA.  This list is ordered
 	 * from newest to oldest, ensuring the root anon_vma gets freed last.
 	 */
 	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
-		anon_vma_unlink(avc);
+		struct anon_vma *anon_vma = avc->anon_vma;
+
+		root = lock_anon_vma_root(root, anon_vma);
+		list_del(&avc->same_anon_vma);
+
+		/*
+		 * Leave empty anon_vmas on the list - we'll need
+		 * to free them outside the lock.
+		 */
+		if (list_empty(&anon_vma->head))
+			continue;
+
+		list_del(&avc->same_vma);
+		anon_vma_chain_free(avc);
+	}
+	unlock_anon_vma_root(root);
+
+	/*
+	 * Iterate the list once more, it now only contains empty and unlinked
+	 * anon_vmas, destroy them. Could not do before due to __put_anon_vma()
+	 * needing to acquire the anon_vma->root->mutex.
+	 */
+	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
+		struct anon_vma *anon_vma = avc->anon_vma;
+
+		put_anon_vma(anon_vma);
+
 		list_del(&avc->same_vma);
 		anon_vma_chain_free(avc);
 	}
@@ -352,6 +395,11 @@ void __init anon_vma_init(void)
  * The page might have been remapped to a different anon_vma or the anon_vma
  * returned may already be freed (and even reused).
  *
+ * In case it was remapped to a different anon_vma, the new anon_vma will be a
+ * child of the old anon_vma, and the anon_vma lifetime rules will therefore
+ * ensure that any anon_vma obtained from the page will still be valid for as
+ * long as we observe page_mapped() [ hence all those page_mapped() tests ].
+ *
  * All users of this function must be very careful when walking the anon_vma
  * chain and verify that the page in question is indeed mapped in it
  * [ something equivalent to page_mapped_in_vma() ].
@@ -405,6 +453,7 @@ out:
 struct anon_vma *page_lock_anon_vma(struct page *page)
 {
 	struct anon_vma *anon_vma = NULL;
+	struct anon_vma *root_anon_vma;
 	unsigned long anon_mapping;
 
 	rcu_read_lock();
@@ -415,13 +464,15 @@ struct anon_vma *page_lock_anon_vma(struct page *page)
 		goto out;
 
 	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
-	if (mutex_trylock(&anon_vma->root->mutex)) {
+	root_anon_vma = ACCESS_ONCE(anon_vma->root);
+	if (mutex_trylock(&root_anon_vma->mutex)) {
 		/*
-		 * If we observe a !0 refcount, then holding the lock ensures
-		 * the anon_vma will not go away, see __put_anon_vma().
+		 * If the page is still mapped, then this anon_vma is still
+		 * its anon_vma, and holding the mutex ensures that it will
+		 * not go away, see anon_vma_free().
 		 */
-		if (!atomic_read(&anon_vma->refcount)) {
-			anon_vma_unlock(anon_vma);
+		if (!page_mapped(page)) {
+			mutex_unlock(&root_anon_vma->mutex);
 			anon_vma = NULL;
 		}
 		goto out;
@@ -1014,7 +1065,7 @@ void do_page_add_anon_rmap(struct page *page,
 		return;
 
 	VM_BUG_ON(!PageLocked(page));
-	VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+	/* address might be in next vma when migration races vma_adjust */
 	if (first)
 		__page_set_anon_rmap(page, vma, address, exclusive);
 	else
@@ -1709,7 +1760,7 @@ void hugepage_add_anon_rmap(struct page *page,
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(!anon_vma);
-	BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+	/* address might be in next vma when migration races vma_adjust */
 	first = atomic_inc_and_test(&page->_mapcount);
 	if (first)
 		__hugepage_set_anon_rmap(page, vma, address, 0);
diff --git a/mm/shmem.c b/mm/shmem.c
index 1acfb2687bfa..fcedf5464eb7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -539,7 +539,7 @@ static void shmem_free_pages(struct list_head *next)
 	} while (next);
 }
 
-static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
+void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	unsigned long idx;
@@ -562,6 +562,8 @@ static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
 	spinlock_t *punch_lock;
 	unsigned long upper_limit;
 
+	truncate_inode_pages_range(inode->i_mapping, start, end);
+
 	inode->i_ctime = inode->i_mtime = CURRENT_TIME;
 	idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	if (idx >= info->next_index)
@@ -738,16 +740,8 @@ done2:
 		 * lowered next_index.  Also, though shmem_getpage checks
 		 * i_size before adding to cache, no recheck after: so fix the
 		 * narrow window there too.
-		 *
-		 * Recalling truncate_inode_pages_range and unmap_mapping_range
-		 * every time for punch_hole (which never got a chance to clear
-		 * SHMEM_PAGEIN at the start of vmtruncate_range) is expensive,
-		 * yet hardly ever necessary: try to optimize them out later.
 		 */
 		truncate_inode_pages_range(inode->i_mapping, start, end);
-		if (punch_hole)
-			unmap_mapping_range(inode->i_mapping, start,
-							end - start, 1);
 	}
 
 	spin_lock(&info->lock);
@@ -766,22 +760,23 @@ done2:
 		shmem_free_pages(pages_to_free.next);
 	}
 }
+EXPORT_SYMBOL_GPL(shmem_truncate_range);
 
-static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
+static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = dentry->d_inode;
-	loff_t newsize = attr->ia_size;
 	int error;
 
 	error = inode_change_ok(inode, attr);
 	if (error)
 		return error;
 
-	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)
-					&& newsize != inode->i_size) {
+	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
+		loff_t oldsize = inode->i_size;
+		loff_t newsize = attr->ia_size;
 		struct page *page = NULL;
 
-		if (newsize < inode->i_size) {
+		if (newsize < oldsize) {
 			/*
 			 * If truncating down to a partial page, then
 			 * if that page is already allocated, hold it
@@ -810,12 +805,19 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
 				spin_unlock(&info->lock);
 			}
 		}
-
-		/* XXX(truncate): truncate_setsize should be called last */
-		truncate_setsize(inode, newsize);
+		if (newsize != oldsize) {
+			i_size_write(inode, newsize);
+			inode->i_ctime = inode->i_mtime = CURRENT_TIME;
+		}
+		if (newsize < oldsize) {
+			loff_t holebegin = round_up(newsize, PAGE_SIZE);
+			unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
+			shmem_truncate_range(inode, newsize, (loff_t)-1);
+			/* unmap again to remove racily COWed private pages */
+			unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
+		}
 		if (page)
 			page_cache_release(page);
-		shmem_truncate_range(inode, newsize, (loff_t)-1);
 	}
 
 	setattr_copy(inode, attr);
@@ -832,7 +834,6 @@ static void shmem_evict_inode(struct inode *inode)
 	struct shmem_xattr *xattr, *nxattr;
 
 	if (inode->i_mapping->a_ops == &shmem_aops) {
-		truncate_inode_pages(inode->i_mapping, 0);
 		shmem_unacct_size(info->flags, inode->i_size);
 		inode->i_size = 0;
 		shmem_truncate_range(inode, 0, (loff_t)-1);
@@ -1114,8 +1115,8 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 		delete_from_page_cache(page);
 		shmem_swp_set(info, entry, swap.val);
 		shmem_swp_unmap(entry);
-		spin_unlock(&info->lock);
 		swap_shmem_alloc(swap);
+		spin_unlock(&info->lock);
 		BUG_ON(page_mapped(page));
 		swap_writepage(page, wbc);
 		return 0;
@@ -2706,7 +2707,7 @@ static const struct file_operations shmem_file_operations = {
 };
 
 static const struct inode_operations shmem_inode_operations = {
-	.setattr	= shmem_notify_change,
+	.setattr	= shmem_setattr,
 	.truncate_range	= shmem_truncate_range,
 #ifdef CONFIG_TMPFS_XATTR
 	.setxattr	= shmem_setxattr,
@@ -2739,7 +2740,7 @@ static const struct inode_operations shmem_dir_inode_operations = {
 	.removexattr	= shmem_removexattr,
 #endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
-	.setattr	= shmem_notify_change,
+	.setattr	= shmem_setattr,
 	.check_acl	= generic_check_acl,
 #endif
 };
@@ -2752,7 +2753,7 @@ static const struct inode_operations shmem_special_inode_operations = {
 	.removexattr	= shmem_removexattr,
 #endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
-	.setattr	= shmem_notify_change,
+	.setattr	= shmem_setattr,
 	.check_acl	= generic_check_acl,
 #endif
 };
@@ -2908,6 +2909,12 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
 	return 0;
 }
 
+void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
+{
+	truncate_inode_pages_range(inode->i_mapping, start, end);
+}
+EXPORT_SYMBOL_GPL(shmem_truncate_range);
+
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 /**
  * mem_cgroup_get_shmem_target - find a page or entry assigned to the shmem file
@@ -3028,3 +3035,26 @@ int shmem_zero_setup(struct vm_area_struct *vma)
 	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }
+
+/**
+ * shmem_read_mapping_page_gfp - read into page cache, using specified page allocation flags.
+ * @mapping:	the page's address_space
+ * @index:	the page index
+ * @gfp:	the page allocator flags to use if allocating
+ *
+ * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)",
+ * with any new page allocations done using the specified allocation flags.
+ * But read_cache_page_gfp() uses the ->readpage() method: which does not
+ * suit tmpfs, since it may have pages in swapcache, and needs to find those
+ * for itself; although drivers/gpu/drm i915 and ttm rely upon this support.
+ *
+ * Provide a stub for those callers to start using now, then later
+ * flesh it out to call shmem_getpage() with additional gfp mask, when
+ * shmem_file_splice_read() is added and shmem_readpage() is removed.
+ */
+struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
+					 pgoff_t index, gfp_t gfp)
+{
+	return read_cache_page_gfp(mapping, index, gfp);
+}
+EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp);
diff --git a/mm/slab.c b/mm/slab.c
index bcfa4987c8ae..d96e223de775 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3604,13 +3604,14 @@ free_done:
  * Release an obj back to its cache. If the obj has a constructed state, it must
  * be in this state _before_ it is released.  Called with disabled ints.
  */
-static inline void __cache_free(struct kmem_cache *cachep, void *objp)
+static inline void __cache_free(struct kmem_cache *cachep, void *objp,
+    void *caller)
 {
 	struct array_cache *ac = cpu_cache_get(cachep);
 
 	check_irq_off();
 	kmemleak_free_recursive(objp, cachep->flags);
-	objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0));
+	objp = cache_free_debugcheck(cachep, objp, caller);
 
 	kmemcheck_slab_free(cachep, objp, obj_size(cachep));
 
@@ -3801,7 +3802,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 	debug_check_no_locks_freed(objp, obj_size(cachep));
 	if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
 		debug_check_no_obj_freed(objp, obj_size(cachep));
-	__cache_free(cachep, objp);
+	__cache_free(cachep, objp, __builtin_return_address(0));
 	local_irq_restore(flags);
 
 	trace_kmem_cache_free(_RET_IP_, objp);
@@ -3831,7 +3832,7 @@ void kfree(const void *objp)
 	c = virt_to_cache(objp);
 	debug_check_no_locks_freed(objp, obj_size(c));
 	debug_check_no_obj_freed(objp, obj_size(c));
-	__cache_free(c, (void *)objp);
+	__cache_free(c, (void *)objp, __builtin_return_address(0));
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(kfree);
diff --git a/mm/slub.c b/mm/slub.c
index 7be0223531b0..35f351f26193 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2320,16 +2320,12 @@ static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)
 	BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE <
 			SLUB_PAGE_SHIFT * sizeof(struct kmem_cache_cpu));
 
-#ifdef CONFIG_CMPXCHG_LOCAL
 	/*
-	 * Must align to double word boundary for the double cmpxchg instructions
-	 * to work.
+	 * Must align to double word boundary for the double cmpxchg
+	 * instructions to work; see __pcpu_double_call_return_bool().
 	 */
-	s->cpu_slab = __alloc_percpu(sizeof(struct kmem_cache_cpu), 2 * sizeof(void *));
-#else
-	/* Regular alignment is sufficient */
-	s->cpu_slab = alloc_percpu(struct kmem_cache_cpu);
-#endif
+	s->cpu_slab = __alloc_percpu(sizeof(struct kmem_cache_cpu),
+				     2 * sizeof(void *));
 
 	if (!s->cpu_slab)
 		return 0;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index d537d29e9b7b..ff8dc1a18cb4 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -14,7 +14,7 @@
 #include <linux/vmalloc.h>
 #include <linux/pagemap.h>
 #include <linux/namei.h>
-#include <linux/shm.h>
+#include <linux/shmem_fs.h>
 #include <linux/blkdev.h>
 #include <linux/random.h>
 #include <linux/writeback.h>
diff --git a/mm/thrash.c b/mm/thrash.c
index 2372d4ed5dd8..fabf2d0f5169 100644
--- a/mm/thrash.c
+++ b/mm/thrash.c
@@ -21,14 +21,40 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/swap.h>
+#include <linux/memcontrol.h>
+
+#include <trace/events/vmscan.h>
+
+#define TOKEN_AGING_INTERVAL	(0xFF)
 
 static DEFINE_SPINLOCK(swap_token_lock);
 struct mm_struct *swap_token_mm;
+struct mem_cgroup *swap_token_memcg;
 static unsigned int global_faults;
+static unsigned int last_aging;
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm)
+{
+	struct mem_cgroup *memcg;
+
+	memcg = try_get_mem_cgroup_from_mm(mm);
+	if (memcg)
+		css_put(mem_cgroup_css(memcg));
+
+	return memcg;
+}
+#else
+static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm)
+{
+	return NULL;
+}
+#endif
 
 void grab_swap_token(struct mm_struct *mm)
 {
 	int current_interval;
+	unsigned int old_prio = mm->token_priority;
 
 	global_faults++;
 
@@ -38,40 +64,81 @@ void grab_swap_token(struct mm_struct *mm)
 		return;
 
 	/* First come first served */
-	if (swap_token_mm == NULL) {
-		mm->token_priority = mm->token_priority + 2;
-		swap_token_mm = mm;
-		goto out;
+	if (!swap_token_mm)
+		goto replace_token;
+
+	if ((global_faults - last_aging) > TOKEN_AGING_INTERVAL) {
+		swap_token_mm->token_priority /= 2;
+		last_aging = global_faults;
 	}
 
-	if (mm != swap_token_mm) {
-		if (current_interval < mm->last_interval)
-			mm->token_priority++;
-		else {
-			if (likely(mm->token_priority > 0))
-				mm->token_priority--;
-		}
-		/* Check if we deserve the token */
-		if (mm->token_priority > swap_token_mm->token_priority) {
-			mm->token_priority += 2;
-			swap_token_mm = mm;
-		}
-	} else {
-		/* Token holder came in again! */
+	if (mm == swap_token_mm) {
 		mm->token_priority += 2;
+		goto update_priority;
+	}
+
+	if (current_interval < mm->last_interval)
+		mm->token_priority++;
+	else {
+		if (likely(mm->token_priority > 0))
+			mm->token_priority--;
 	}
 
+	/* Check if we deserve the token */
+	if (mm->token_priority > swap_token_mm->token_priority)
+		goto replace_token;
+
+update_priority:
+	trace_update_swap_token_priority(mm, old_prio, swap_token_mm);
+
 out:
 	mm->faultstamp = global_faults;
 	mm->last_interval = current_interval;
 	spin_unlock(&swap_token_lock);
+	return;
+
+replace_token:
+	mm->token_priority += 2;
+	trace_replace_swap_token(swap_token_mm, mm);
+	swap_token_mm = mm;
+	swap_token_memcg = swap_token_memcg_from_mm(mm);
+	last_aging = global_faults;
+	goto out;
 }
 
 /* Called on process exit. */
 void __put_swap_token(struct mm_struct *mm)
 {
 	spin_lock(&swap_token_lock);
-	if (likely(mm == swap_token_mm))
+	if (likely(mm == swap_token_mm)) {
+		trace_put_swap_token(swap_token_mm);
 		swap_token_mm = NULL;
+		swap_token_memcg = NULL;
+	}
 	spin_unlock(&swap_token_lock);
 }
+
+static bool match_memcg(struct mem_cgroup *a, struct mem_cgroup *b)
+{
+	if (!a)
+		return true;
+	if (!b)
+		return true;
+	if (a == b)
+		return true;
+	return false;
+}
+
+void disable_swap_token(struct mem_cgroup *memcg)
+{
+	/* memcg reclaim don't disable unrelated mm token. */
+	if (match_memcg(memcg, swap_token_memcg)) {
+		spin_lock(&swap_token_lock);
+		if (match_memcg(memcg, swap_token_memcg)) {
+			trace_disable_swap_token(swap_token_mm);
+			swap_token_mm = NULL;
+			swap_token_memcg = NULL;
+		}
+		spin_unlock(&swap_token_lock);
+	}
+}
diff --git a/mm/truncate.c b/mm/truncate.c
index 3a29a6180212..e13f22efaad7 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -304,6 +304,11 @@ EXPORT_SYMBOL(truncate_inode_pages_range);
  * @lstart: offset from which to truncate
  *
  * Called under (and serialised by) inode->i_mutex.
+ *
+ * Note: When this function returns, there can be a page in the process of
+ * deletion (inside __delete_from_page_cache()) in the specified range.  Thus
+ * mapping->nrpages can be non-zero when this function returns even after
+ * truncation of the whole mapping.
  */
 void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
 {
@@ -603,3 +608,27 @@ int vmtruncate(struct inode *inode, loff_t offset)
 	return 0;
 }
 EXPORT_SYMBOL(vmtruncate);
+
+int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
+{
+	struct address_space *mapping = inode->i_mapping;
+
+	/*
+	 * If the underlying filesystem is not going to provide
+	 * a way to truncate a range of blocks (punch a hole) -
+	 * we should return failure right now.
+	 */
+	if (!inode->i_op->truncate_range)
+		return -ENOSYS;
+
+	mutex_lock(&inode->i_mutex);
+	down_write(&inode->i_alloc_sem);
+	unmap_mapping_range(mapping, offset, (end - offset), 1);
+	inode->i_op->truncate_range(inode, offset, end);
+	/* unmap again to remove racily COWed private pages */
+	unmap_mapping_range(mapping, offset, (end - offset), 1);
+	up_write(&inode->i_alloc_sem);
+	mutex_unlock(&inode->i_mutex);
+
+	return 0;
+}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index faa0a088f9cc..4f49535d4cd3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1124,8 +1124,20 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 					nr_lumpy_dirty++;
 				scan++;
 			} else {
-				/* the page is freed already. */
-				if (!page_count(cursor_page))
+				/*
+				 * Check if the page is freed already.
+				 *
+				 * We can't use page_count() as that
+				 * requires compound_head and we don't
+				 * have a pin on the page here. If a
+				 * page is tail, we may or may not
+				 * have isolated the head, so assume
+				 * it's not free, it'd be tricky to
+				 * track the head status without a
+				 * page pin.
+				 */
+				if (!PageTail(cursor_page) &&
+				    !atomic_read(&cursor_page->_count))
 					continue;
 				break;
 			}
@@ -1983,14 +1995,13 @@ restart:
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
+static void shrink_zones(int priority, struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
-	unsigned long total_scanned = 0;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask), sc->nodemask) {
@@ -2005,19 +2016,23 @@ static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
 				continue;
 			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;	/* Let kswapd poll it */
+			/*
+			 * This steals pages from memory cgroups over softlimit
+			 * and returns the number of reclaimed pages and
+			 * scanned pages. This works for global memory pressure
+			 * and balancing, not for a memcg's limit.
+			 */
+			nr_soft_scanned = 0;
+			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+						sc->order, sc->gfp_mask,
+						&nr_soft_scanned);
+			sc->nr_reclaimed += nr_soft_reclaimed;
+			sc->nr_scanned += nr_soft_scanned;
+			/* need some check for avoid more shrink_zone() */
 		}
 
-		nr_soft_scanned = 0;
-		nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
-							sc->order, sc->gfp_mask,
-							&nr_soft_scanned);
-		sc->nr_reclaimed += nr_soft_reclaimed;
-		total_scanned += nr_soft_scanned;
-
 		shrink_zone(priority, zone, sc);
 	}
-
-	return total_scanned;
 }
 
 static bool zone_reclaimable(struct zone *zone)
@@ -2081,8 +2096,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
 		sc->nr_scanned = 0;
 		if (!priority)
-			disable_swap_token();
-		total_scanned += shrink_zones(priority, zonelist, sc);
+			disable_swap_token(sc->mem_cgroup);
+		shrink_zones(priority, zonelist, sc);
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
@@ -2407,7 +2422,7 @@ loop_again:
 
 		/* The swap token gets in the way of swapout... */
 		if (!priority)
-			disable_swap_token();
+			disable_swap_token(NULL);
 
 		all_zones_ok = 1;
 		balanced = 0;
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index b2274d1fd605..917ecb93ea28 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -46,8 +46,6 @@ int vlan_net_id __read_mostly;
 
 const char vlan_fullname[] = "802.1Q VLAN Support";
 const char vlan_version[] = DRV_VERSION;
-static const char vlan_copyright[] = "Ben Greear <greearb@candelatech.com>";
-static const char vlan_buggyright[] = "David S. Miller <davem@redhat.com>";
 
 /* End of global variables definitions. */
 
@@ -207,7 +205,7 @@ int register_vlan_dev(struct net_device *dev)
 	grp->nr_vlans++;
 
 	if (ngrp) {
-		if (ops->ndo_vlan_rx_register)
+		if (ops->ndo_vlan_rx_register && (real_dev->features & NETIF_F_HW_VLAN_RX))
 			ops->ndo_vlan_rx_register(real_dev, ngrp);
 		rcu_assign_pointer(real_dev->vlgrp, ngrp);
 	}
@@ -673,8 +671,7 @@ static int __init vlan_proto_init(void)
 {
 	int err;
 
-	pr_info("%s v%s %s\n", vlan_fullname, vlan_version, vlan_copyright);
-	pr_info("All bugs added by %s\n", vlan_buggyright);
+	pr_info("%s v%s\n", vlan_fullname, vlan_version);
 
 	err = register_pernet_subsys(&vlan_net_ops);
 	if (err < 0)
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 41495dc2a4c9..fcc684678af6 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -23,6 +23,31 @@ bool vlan_do_receive(struct sk_buff **skbp)
 		return false;
 
 	skb->dev = vlan_dev;
+	if (skb->pkt_type == PACKET_OTHERHOST) {
+		/* Our lower layer thinks this is not local, let's make sure.
+		 * This allows the VLAN to have a different MAC than the
+		 * underlying device, and still route correctly. */
+		if (!compare_ether_addr(eth_hdr(skb)->h_dest,
+					vlan_dev->dev_addr))
+			skb->pkt_type = PACKET_HOST;
+	}
+
+	if (!(vlan_dev_info(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR)) {
+		unsigned int offset = skb->data - skb_mac_header(skb);
+
+		/*
+		 * vlan_insert_tag expect skb->data pointing to mac header.
+		 * So change skb->data before calling it and change back to
+		 * original position later
+		 */
+		skb_push(skb, offset);
+		skb = *skbp = vlan_insert_tag(skb, skb->vlan_tci);
+		if (!skb)
+			return false;
+		skb_pull(skb, offset + VLAN_HLEN);
+		skb_reset_mac_len(skb);
+	}
+
 	skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci);
 	skb->vlan_tci = 0;
 
@@ -31,22 +56,8 @@ bool vlan_do_receive(struct sk_buff **skbp)
 	u64_stats_update_begin(&rx_stats->syncp);
 	rx_stats->rx_packets++;
 	rx_stats->rx_bytes += skb->len;
-
-	switch (skb->pkt_type) {
-	case PACKET_BROADCAST:
-		break;
-	case PACKET_MULTICAST:
+	if (skb->pkt_type == PACKET_MULTICAST)
 		rx_stats->rx_multicast++;
-		break;
-	case PACKET_OTHERHOST:
-		/* Our lower layer thinks this is not local, let's make sure.
-		 * This allows the VLAN to have a different MAC than the
-		 * underlying device, and still route correctly. */
-		if (!compare_ether_addr(eth_hdr(skb)->h_dest,
-					vlan_dev->dev_addr))
-			skb->pkt_type = PACKET_HOST;
-		break;
-	}
 	u64_stats_update_end(&rx_stats->syncp);
 
 	return true;
@@ -89,18 +100,13 @@ gro_result_t vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp,
 }
 EXPORT_SYMBOL(vlan_gro_frags);
 
-static struct sk_buff *vlan_check_reorder_header(struct sk_buff *skb)
+static struct sk_buff *vlan_reorder_header(struct sk_buff *skb)
 {
-	if (vlan_dev_info(skb->dev)->flags & VLAN_FLAG_REORDER_HDR) {
-		if (skb_cow(skb, skb_headroom(skb)) < 0)
-			skb = NULL;
-		if (skb) {
-			/* Lifted from Gleb's VLAN code... */
-			memmove(skb->data - ETH_HLEN,
-				skb->data - VLAN_ETH_HLEN, 12);
-			skb->mac_header += VLAN_HLEN;
-		}
-	}
+	if (skb_cow(skb, skb_headroom(skb)) < 0)
+		return NULL;
+	memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN);
+	skb->mac_header += VLAN_HLEN;
+	skb_reset_mac_len(skb);
 	return skb;
 }
 
@@ -161,7 +167,7 @@ struct sk_buff *vlan_untag(struct sk_buff *skb)
 	skb_pull_rcsum(skb, VLAN_HLEN);
 	vlan_set_encap_proto(skb, vhdr);
 
-	skb = vlan_check_reorder_header(skb);
+	skb = vlan_reorder_header(skb);
 	if (unlikely(!skb))
 		goto err_free;
 
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index f247f5bff88d..7ea5cf9ea08a 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -165,7 +165,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
 		u64_stats_update_begin(&stats->syncp);
 		stats->tx_packets++;
 		stats->tx_bytes += len;
-		u64_stats_update_begin(&stats->syncp);
+		u64_stats_update_end(&stats->syncp);
 	} else {
 		this_cpu_inc(vlan_dev_info(dev)->vlan_pcpu_stats->tx_dropped);
 	}
diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c
index f7fa67c78766..f49da5814bc3 100644
--- a/net/atm/atm_sysfs.c
+++ b/net/atm/atm_sysfs.c
@@ -59,6 +59,14 @@ static ssize_t show_atmaddress(struct device *cdev,
 	return pos - buf;
 }
 
+static ssize_t show_atmindex(struct device *cdev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct atm_dev *adev = to_atm_dev(cdev);
+
+	return sprintf(buf, "%d\n", adev->number);
+}
+
 static ssize_t show_carrier(struct device *cdev,
 			    struct device_attribute *attr, char *buf)
 {
@@ -99,6 +107,7 @@ static ssize_t show_link_rate(struct device *cdev,
 
 static DEVICE_ATTR(address, S_IRUGO, show_address, NULL);
 static DEVICE_ATTR(atmaddress, S_IRUGO, show_atmaddress, NULL);
+static DEVICE_ATTR(atmindex, S_IRUGO, show_atmindex, NULL);
 static DEVICE_ATTR(carrier, S_IRUGO, show_carrier, NULL);
 static DEVICE_ATTR(type, S_IRUGO, show_type, NULL);
 static DEVICE_ATTR(link_rate, S_IRUGO, show_link_rate, NULL);
@@ -106,6 +115,7 @@ static DEVICE_ATTR(link_rate, S_IRUGO, show_link_rate, NULL);
 static struct device_attribute *atm_attrs[] = {
 	&dev_attr_atmaddress,
 	&dev_attr_address,
+	&dev_attr_atmindex,
 	&dev_attr_carrier,
 	&dev_attr_type,
 	&dev_attr_link_rate,
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index f13ddbf858ba..77930aa522e3 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -477,14 +477,16 @@ static void hci_setup_event_mask(struct hci_dev *hdev)
 	 * command otherwise */
 	u8 events[8] = { 0xff, 0xff, 0xfb, 0xff, 0x00, 0x00, 0x00, 0x00 };
 
-	/* Events for 1.2 and newer controllers */
-	if (hdev->lmp_ver > 1) {
-		events[4] |= 0x01; /* Flow Specification Complete */
-		events[4] |= 0x02; /* Inquiry Result with RSSI */
-		events[4] |= 0x04; /* Read Remote Extended Features Complete */
-		events[5] |= 0x08; /* Synchronous Connection Complete */
-		events[5] |= 0x10; /* Synchronous Connection Changed */
-	}
+	/* CSR 1.1 dongles does not accept any bitfield so don't try to set
+	 * any event mask for pre 1.2 devices */
+	if (hdev->lmp_ver <= 1)
+		return;
+
+	events[4] |= 0x01; /* Flow Specification Complete */
+	events[4] |= 0x02; /* Inquiry Result with RSSI */
+	events[4] |= 0x04; /* Read Remote Extended Features Complete */
+	events[5] |= 0x08; /* Synchronous Connection Complete */
+	events[5] |= 0x10; /* Synchronous Connection Changed */
 
 	if (hdev->features[3] & LMP_RSSI_INQ)
 		events[4] |= 0x04; /* Inquiry Result with RSSI */
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index a86f9ba4f05c..e64a1c2df238 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -906,7 +906,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, bdaddr
 		if (c->psm == psm) {
 			/* Exact match. */
 			if (!bacmp(&bt_sk(sk)->src, src)) {
-				read_unlock_bh(&chan_list_lock);
+				read_unlock(&chan_list_lock);
 				return c;
 			}
 
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 18dc9888d8c2..8248303f44e8 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -413,6 +413,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __us
 			break;
 		}
 
+		memset(&cinfo, 0, sizeof(cinfo));
 		cinfo.hci_handle = chan->conn->hcon->handle;
 		memcpy(cinfo.dev_class, chan->conn->hcon->dev_class, 3);
 
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 386cfaffd4b7..1b10727ce523 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -788,6 +788,7 @@ static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __u
 
 		l2cap_sk = rfcomm_pi(sk)->dlc->session->sock->sk;
 
+		memset(&cinfo, 0, sizeof(cinfo));
 		cinfo.hci_handle = conn->hcon->handle;
 		memcpy(cinfo.dev_class, conn->hcon->dev_class, 3);
 
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 42fdffd1d76c..cb4fb7837e5c 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -369,6 +369,15 @@ static void __sco_sock_close(struct sock *sk)
 
 	case BT_CONNECTED:
 	case BT_CONFIG:
+		if (sco_pi(sk)->conn) {
+			sk->sk_state = BT_DISCONN;
+			sco_sock_set_timer(sk, SCO_DISCONN_TIMEOUT);
+			hci_conn_put(sco_pi(sk)->conn->hcon);
+			sco_pi(sk)->conn->hcon = NULL;
+		} else
+			sco_chan_del(sk, ECONNRESET);
+		break;
+
 	case BT_CONNECT:
 	case BT_DISCONN:
 		sco_chan_del(sk, ECONNRESET);
@@ -819,7 +828,9 @@ static void sco_chan_del(struct sock *sk, int err)
 		conn->sk = NULL;
 		sco_pi(sk)->conn = NULL;
 		sco_conn_unlock(conn);
-		hci_conn_put(conn->hcon);
+
+		if (conn->hcon)
+			hci_conn_put(conn->hcon);
 	}
 
 	sk->sk_state = BT_CLOSED;
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index a6b2f86378c7..c188c803c09c 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -243,6 +243,7 @@ int br_netpoll_enable(struct net_bridge_port *p)
 		goto out;
 
 	np->dev = p->dev;
+	strlcpy(np->dev_name, p->dev->name, IFNAMSIZ);
 
 	err = __netpoll_setup(np);
 	if (err) {
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 2f14eafdeeab..29b9812c8da0 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1424,7 +1424,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
 	switch (ih->type) {
 	case IGMP_HOST_MEMBERSHIP_REPORT:
 	case IGMPV2_HOST_MEMBERSHIP_REPORT:
-		BR_INPUT_SKB_CB(skb2)->mrouters_only = 1;
+		BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
 		err = br_ip4_multicast_add_group(br, port, ih->group);
 		break;
 	case IGMPV3_HOST_MEMBERSHIP_REPORT:
@@ -1543,7 +1543,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
 			goto out;
 		}
 		mld = (struct mld_msg *)skb_transport_header(skb2);
-		BR_INPUT_SKB_CB(skb2)->mrouters_only = 1;
+		BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
 		err = br_ip6_multicast_add_group(br, port, &mld->mld_mca);
 		break;
 	    }
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 3fa123185e89..56149ec36d7f 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -104,10 +104,16 @@ static void fake_update_pmtu(struct dst_entry *dst, u32 mtu)
 {
 }
 
+static u32 *fake_cow_metrics(struct dst_entry *dst, unsigned long old)
+{
+	return NULL;
+}
+
 static struct dst_ops fake_dst_ops = {
 	.family =		AF_INET,
 	.protocol =		cpu_to_be16(ETH_P_IP),
 	.update_pmtu =		fake_update_pmtu,
+	.cow_metrics =		fake_cow_metrics,
 };
 
 /*
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 1a92b369c820..2b5ca1a0054d 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1883,14 +1883,13 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt,
 	struct xt_target *wt;
 	void *dst = NULL;
 	int off, pad = 0;
-	unsigned int size_kern, entry_offset, match_size = mwt->match_size;
+	unsigned int size_kern, match_size = mwt->match_size;
 
 	strlcpy(name, mwt->u.name, sizeof(name));
 
 	if (state->buf_kern_start)
 		dst = state->buf_kern_start + state->buf_kern_offset;
 
-	entry_offset = (unsigned char *) mwt - base;
 	switch (compat_mwt) {
 	case EBT_COMPAT_MATCH:
 		match = try_then_request_module(xt_find_match(NFPROTO_BRIDGE,
@@ -1933,6 +1932,9 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt,
 		size_kern = wt->targetsize;
 		module_put(wt->me);
 		break;
+
+	default:
+		return -EINVAL;
 	}
 
 	state->buf_kern_offset += match_size + off;
diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c
index 3a66b8c10e09..c23979e79dfa 100644
--- a/net/caif/cfmuxl.c
+++ b/net/caif/cfmuxl.c
@@ -255,7 +255,7 @@ static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
 
 		if (cfsrvl_phyid_match(layer, phyid) && layer->ctrlcmd) {
 
-			if ((ctrl == _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND ||
+			if ((ctrl == _CAIF_CTRLCMD_PHYIF_DOWN_IND ||
 				ctrl == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND) &&
 					layer->id != 0) {
 
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 649ebacaf6bc..adbb424403d4 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -139,17 +139,14 @@ static void close_work(struct work_struct *work)
 	struct chnl_net *dev = NULL;
 	struct list_head *list_node;
 	struct list_head *_tmp;
-	/* May be called with or without RTNL lock held */
-	int islocked = rtnl_is_locked();
-	if (!islocked)
-		rtnl_lock();
+
+	rtnl_lock();
 	list_for_each_safe(list_node, _tmp, &chnl_net_list) {
 		dev = list_entry(list_node, struct chnl_net, list_field);
 		if (dev->state == CAIF_SHUTDOWN)
 			dev_close(dev->netdev);
 	}
-	if (!islocked)
-		rtnl_unlock();
+	rtnl_unlock();
 }
 static DECLARE_WORK(close_worker, close_work);
 
diff --git a/net/can/proc.c b/net/can/proc.c
index f4265cc9c3fb..0016f7339699 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -204,12 +204,11 @@ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list,
 
 	hlist_for_each_entry_rcu(r, n, rx_list, list) {
 		char *fmt = (r->can_id & CAN_EFF_FLAG)?
-			"   %-5s  %08X  %08x  %08x  %08x  %8ld  %s\n" :
-			"   %-5s     %03X    %08x  %08lx  %08lx  %8ld  %s\n";
+			"   %-5s  %08x  %08x  %pK  %pK  %8ld  %s\n" :
+			"   %-5s     %03x    %08x  %pK  %pK  %8ld  %s\n";
 
 		seq_printf(m, fmt, DNAME(dev), r->can_id, r->mask,
-				(unsigned long)r->func, (unsigned long)r->data,
-				r->matches, r->ident);
+				r->func, r->data, r->matches, r->ident);
 	}
 }
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 6ea2b892f44b..9cb627a4073a 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1144,6 +1144,13 @@ static void handle_osds_timeout(struct work_struct *work)
 			      round_jiffies_relative(delay));
 }
 
+static void complete_request(struct ceph_osd_request *req)
+{
+	if (req->r_safe_callback)
+		req->r_safe_callback(req, NULL);
+	complete_all(&req->r_safe_completion);  /* fsync waiter */
+}
+
 /*
  * handle osd op reply.  either call the callback if it is specified,
  * or do the completion to wake up the waiting thread.
@@ -1226,11 +1233,8 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
 	else
 		complete_all(&req->r_completion);
 
-	if (flags & CEPH_OSD_FLAG_ONDISK) {
-		if (req->r_safe_callback)
-			req->r_safe_callback(req, msg);
-		complete_all(&req->r_safe_completion);  /* fsync waiter */
-	}
+	if (flags & CEPH_OSD_FLAG_ONDISK)
+		complete_request(req);
 
 done:
 	dout("req=%p req->r_linger=%d\n", req, req->r_linger);
@@ -1732,6 +1736,7 @@ int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
 		__cancel_request(req);
 		__unregister_request(osdc, req);
 		mutex_unlock(&osdc->request_mutex);
+		complete_request(req);
 		dout("wait_request tid %llu canceled/timed out\n", req->r_tid);
 		return rc;
 	}
diff --git a/net/core/dev.c b/net/core/dev.c
index c7e305d13b71..9c58c1ec41a9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2096,6 +2096,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int rc = NETDEV_TX_OK;
+	unsigned int skb_len;
 
 	if (likely(!skb->next)) {
 		u32 features;
@@ -2146,8 +2147,9 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			}
 		}
 
+		skb_len = skb->len;
 		rc = ops->ndo_start_xmit(skb, dev);
-		trace_net_dev_xmit(skb, rc);
+		trace_net_dev_xmit(skb, rc, dev, skb_len);
 		if (rc == NETDEV_TX_OK)
 			txq_trans_update(txq);
 		return rc;
@@ -2167,8 +2169,9 @@ gso:
 		if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
 			skb_dst_drop(nskb);
 
+		skb_len = nskb->len;
 		rc = ops->ndo_start_xmit(nskb, dev);
-		trace_net_dev_xmit(nskb, rc);
+		trace_net_dev_xmit(nskb, rc, dev, skb_len);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
 				goto out_kfree_gso_skb;
@@ -3111,7 +3114,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
 
 	skb_reset_network_header(skb);
 	skb_reset_transport_header(skb);
-	skb->mac_len = skb->network_header - skb->mac_header;
+	skb_reset_mac_len(skb);
 
 	pt_prev = NULL;
 
@@ -6175,6 +6178,11 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 		oldsd->output_queue = NULL;
 		oldsd->output_queue_tailp = &oldsd->output_queue;
 	}
+	/* Append NAPI poll list from offline CPU. */
+	if (!list_empty(&oldsd->poll_list)) {
+		list_splice_init(&oldsd->poll_list, &sd->poll_list);
+		raise_softirq_irqoff(NET_RX_SOFTIRQ);
+	}
 
 	raise_softirq_irqoff(NET_TX_SOFTIRQ);
 	local_irq_enable();
@@ -6261,29 +6269,23 @@ err_name:
 /**
  *	netdev_drivername - network driver for the device
  *	@dev: network device
- *	@buffer: buffer for resulting name
- *	@len: size of buffer
  *
  *	Determine network driver for device.
  */
-char *netdev_drivername(const struct net_device *dev, char *buffer, int len)
+const char *netdev_drivername(const struct net_device *dev)
 {
 	const struct device_driver *driver;
 	const struct device *parent;
-
-	if (len <= 0 || !buffer)
-		return buffer;
-	buffer[0] = 0;
+	const char *empty = "";
 
 	parent = dev->dev.parent;
-
 	if (!parent)
-		return buffer;
+		return empty;
 
 	driver = parent->driver;
 	if (driver && driver->name)
-		strlcpy(buffer, driver->name, len);
-	return buffer;
+		return driver->name;
+	return empty;
 }
 
 static int __netdev_printk(const char *level, const struct net_device *dev,
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 84e7304532e6..fd14116ad7f0 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -233,6 +233,29 @@ static int ethtool_set_feature_compat(struct net_device *dev,
 	return 1;
 }
 
+static int ethtool_set_flags_compat(struct net_device *dev,
+	int (*legacy_set)(struct net_device *, u32),
+	struct ethtool_set_features_block *features, u32 mask)
+{
+	u32 value;
+
+	if (!legacy_set)
+		return 0;
+
+	if (!(features[0].valid & mask))
+		return 0;
+
+	value = dev->features & ~features[0].valid;
+	value |= features[0].requested;
+
+	features[0].valid &= ~mask;
+
+	if (legacy_set(dev, value & mask) < 0)
+		netdev_info(dev, "Legacy flags change failed\n");
+
+	return 1;
+}
+
 static int ethtool_set_features_compat(struct net_device *dev,
 	struct ethtool_set_features_block *features)
 {
@@ -249,7 +272,7 @@ static int ethtool_set_features_compat(struct net_device *dev,
 		features, NETIF_F_ALL_TSO);
 	compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_rx_csum,
 		features, NETIF_F_RXCSUM);
-	compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_flags,
+	compat |= ethtool_set_flags_compat(dev, dev->ethtool_ops->set_flags,
 		features, flags_dup_features);
 
 	return compat;
diff --git a/net/core/filter.c b/net/core/filter.c
index 0e3622f1dcb1..36f975fa87cb 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -38,6 +38,7 @@
 #include <asm/unaligned.h>
 #include <linux/filter.h>
 #include <linux/reciprocal_div.h>
+#include <linux/ratelimit.h>
 
 /* No hurry in this branch */
 static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 11b98bc2aa8f..33d2a1fba131 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1179,9 +1179,14 @@ static void remove_queue_kobjects(struct net_device *net)
 #endif
 }
 
-static const void *net_current_ns(void)
+static void *net_grab_current_ns(void)
 {
-	return current->nsproxy->net_ns;
+	struct net *ns = current->nsproxy->net_ns;
+#ifdef CONFIG_NET_NS
+	if (ns)
+		atomic_inc(&ns->passive);
+#endif
+	return ns;
 }
 
 static const void *net_initial_ns(void)
@@ -1196,22 +1201,13 @@ static const void *net_netlink_ns(struct sock *sk)
 
 struct kobj_ns_type_operations net_ns_type_operations = {
 	.type = KOBJ_NS_TYPE_NET,
-	.current_ns = net_current_ns,
+	.grab_current_ns = net_grab_current_ns,
 	.netlink_ns = net_netlink_ns,
 	.initial_ns = net_initial_ns,
+	.drop_ns = net_drop_ns,
 };
 EXPORT_SYMBOL_GPL(net_ns_type_operations);
 
-static void net_kobj_ns_exit(struct net *net)
-{
-	kobj_ns_exit(KOBJ_NS_TYPE_NET, net);
-}
-
-static struct pernet_operations kobj_net_ops = {
-	.exit = net_kobj_ns_exit,
-};
-
-
 #ifdef CONFIG_HOTPLUG
 static int netdev_uevent(struct device *d, struct kobj_uevent_env *env)
 {
@@ -1339,6 +1335,5 @@ EXPORT_SYMBOL(netdev_class_remove_file);
 int netdev_kobject_init(void)
 {
 	kobj_ns_type_register(&net_ns_type_operations);
-	register_pernet_subsys(&kobj_net_ops);
 	return class_register(&net_class);
 }
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 6c6b86d0da15..ea489db1bc23 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -128,6 +128,7 @@ static __net_init int setup_net(struct net *net)
 	LIST_HEAD(net_exit_list);
 
 	atomic_set(&net->count, 1);
+	atomic_set(&net->passive, 1);
 
 #ifdef NETNS_REFCNT_DEBUG
 	atomic_set(&net->use_count, 0);
@@ -210,6 +211,13 @@ static void net_free(struct net *net)
 	kmem_cache_free(net_cachep, net);
 }
 
+void net_drop_ns(void *p)
+{
+	struct net *ns = p;
+	if (ns && atomic_dec_and_test(&ns->passive))
+		net_free(ns);
+}
+
 struct net *copy_net_ns(unsigned long flags, struct net *old_net)
 {
 	struct net *net;
@@ -230,7 +238,7 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net)
 	}
 	mutex_unlock(&net_mutex);
 	if (rv < 0) {
-		net_free(net);
+		net_drop_ns(net);
 		return ERR_PTR(rv);
 	}
 	return net;
@@ -286,7 +294,7 @@ static void cleanup_net(struct work_struct *work)
 	/* Finally it is safe to free my network namespace structure */
 	list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) {
 		list_del_init(&net->exit_list);
-		net_free(net);
+		net_drop_ns(net);
 	}
 }
 static DECLARE_WORK(net_cleanup_work, cleanup_net);
@@ -310,19 +318,17 @@ struct net *get_net_ns_by_fd(int fd)
 	struct file *file;
 	struct net *net;
 
-	net = ERR_PTR(-EINVAL);
 	file = proc_ns_fget(fd);
-	if (!file)
-		goto out;
+	if (IS_ERR(file))
+		return ERR_CAST(file);
 
 	ei = PROC_I(file->f_dentry->d_inode);
-	if (ei->ns_ops != &netns_operations)
-		goto out;
+	if (ei->ns_ops == &netns_operations)
+		net = get_net(ei->ns);
+	else
+		net = ERR_PTR(-EINVAL);
 
-	net = get_net(ei->ns);
-out:
-	if (file)
-		fput(file);
+	fput(file);
 	return net;
 }
 
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 2d7d6d473781..18d9cbda3a39 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -792,6 +792,13 @@ int netpoll_setup(struct netpoll *np)
 		return -ENODEV;
 	}
 
+	if (ndev->master) {
+		printk(KERN_ERR "%s: %s is a slave device, aborting.\n",
+		       np->name, np->dev_name);
+		err = -EBUSY;
+		goto put;
+	}
+
 	if (!netif_running(ndev)) {
 		unsigned long atmost, atleast;
 
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index a829e3f60aeb..77a65f031488 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -17,6 +17,7 @@
 
 #include <net/ip.h>
 #include <net/sock.h>
+#include <net/net_ratelimit.h>
 
 #ifdef CONFIG_RPS
 static int rps_sock_flow_sysctl(ctl_table *table, int write,
diff --git a/net/core/utils.c b/net/core/utils.c
index 2012bc797f9c..386e263f6066 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -27,6 +27,7 @@
 #include <linux/ratelimit.h>
 
 #include <net/sock.h>
+#include <net/net_ratelimit.h>
 
 #include <asm/byteorder.h>
 #include <asm/system.h>
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index ed0eab39f531..02548b292b53 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -44,7 +44,7 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 pid,
 	pr_debug("%s\n", __func__);
 
 	if (!buf)
-		goto out;
+		return -EMSGSIZE;
 
 	hdr = genlmsg_put(msg, 0, seq, &nl802154_family, flags,
 		IEEE802154_LIST_PHY);
@@ -65,6 +65,7 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 pid,
 				pages * sizeof(uint32_t), buf);
 
 	mutex_unlock(&phy->pib_lock);
+	kfree(buf);
 	return genlmsg_end(msg, hdr);
 
 nla_put_failure:
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index cc1463156cd0..eae1f676f870 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -465,6 +465,9 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (addr_len < sizeof(struct sockaddr_in))
 		goto out;
 
+	if (addr->sin_family != AF_INET)
+		goto out;
+
 	chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
 
 	/* Not specified by any standard per-se, however it breaks too
@@ -673,6 +676,7 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags)
 
 	lock_sock(sk2);
 
+	sock_rps_record_flow(sk2);
 	WARN_ON(!((1 << sk2->sk_state) &
 		  (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE)));
 
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 6ffe94ca5bc9..3267d3898437 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -437,7 +437,7 @@ static int valid_cc(const void *bc, int len, int cc)
 			return 0;
 		if (cc == len)
 			return 1;
-		if (op->yes < 4)
+		if (op->yes < 4 || op->yes & 3)
 			return 0;
 		len -= op->yes;
 		bc  += op->yes;
@@ -447,11 +447,11 @@ static int valid_cc(const void *bc, int len, int cc)
 
 static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
 {
-	const unsigned char *bc = bytecode;
+	const void *bc = bytecode;
 	int  len = bytecode_len;
 
 	while (len > 0) {
-		struct inet_diag_bc_op *op = (struct inet_diag_bc_op *)bc;
+		const struct inet_diag_bc_op *op = bc;
 
 //printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len);
 		switch (op->code) {
@@ -462,22 +462,20 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
 		case INET_DIAG_BC_S_LE:
 		case INET_DIAG_BC_D_GE:
 		case INET_DIAG_BC_D_LE:
-			if (op->yes < 4 || op->yes > len + 4)
-				return -EINVAL;
 		case INET_DIAG_BC_JMP:
-			if (op->no < 4 || op->no > len + 4)
+			if (op->no < 4 || op->no > len + 4 || op->no & 3)
 				return -EINVAL;
 			if (op->no < len &&
 			    !valid_cc(bytecode, bytecode_len, len - op->no))
 				return -EINVAL;
 			break;
 		case INET_DIAG_BC_NOP:
-			if (op->yes < 4 || op->yes > len + 4)
-				return -EINVAL;
 			break;
 		default:
 			return -EINVAL;
 		}
+		if (op->yes < 4 || op->yes > len + 4 || op->yes & 3)
+			return -EINVAL;
 		bc  += op->yes;
 		len -= op->yes;
 	}
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 9df4e635fb5f..ce616d92cc54 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -154,11 +154,9 @@ void __init inet_initpeers(void)
 /* Called with or without local BH being disabled. */
 static void unlink_from_unused(struct inet_peer *p)
 {
-	if (!list_empty(&p->unused)) {
-		spin_lock_bh(&unused_peers.lock);
-		list_del_init(&p->unused);
-		spin_unlock_bh(&unused_peers.lock);
-	}
+	spin_lock_bh(&unused_peers.lock);
+	list_del_init(&p->unused);
+	spin_unlock_bh(&unused_peers.lock);
 }
 
 static int addr_compare(const struct inetpeer_addr *a,
@@ -205,6 +203,20 @@ static int addr_compare(const struct inetpeer_addr *a,
 	u;							\
 })
 
+static bool atomic_add_unless_return(atomic_t *ptr, int a, int u, int *newv)
+{
+	int cur, old = atomic_read(ptr);
+
+	while (old != u) {
+		*newv = old + a;
+		cur = atomic_cmpxchg(ptr, old, *newv);
+		if (cur == old)
+			return true;
+		old = cur;
+	}
+	return false;
+}
+
 /*
  * Called with rcu_read_lock()
  * Because we hold no lock against a writer, its quite possible we fall
@@ -213,7 +225,8 @@ static int addr_compare(const struct inetpeer_addr *a,
  * We exit from this function if number of links exceeds PEER_MAXDEPTH
  */
 static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr,
-				    struct inet_peer_base *base)
+				    struct inet_peer_base *base,
+				    int *newrefcnt)
 {
 	struct inet_peer *u = rcu_dereference(base->root);
 	int count = 0;
@@ -226,7 +239,7 @@ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr,
 			 * distinction between an unused entry (refcnt=0) and
 			 * a freed one.
 			 */
-			if (unlikely(!atomic_add_unless(&u->refcnt, 1, -1)))
+			if (!atomic_add_unless_return(&u->refcnt, 1, -1, newrefcnt))
 				u = NULL;
 			return u;
 		}
@@ -465,22 +478,23 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create)
 	struct inet_peer_base *base = family_to_base(daddr->family);
 	struct inet_peer *p;
 	unsigned int sequence;
-	int invalidated;
+	int invalidated, newrefcnt = 0;
 
 	/* Look up for the address quickly, lockless.
 	 * Because of a concurrent writer, we might not find an existing entry.
 	 */
 	rcu_read_lock();
 	sequence = read_seqbegin(&base->lock);
-	p = lookup_rcu(daddr, base);
+	p = lookup_rcu(daddr, base, &newrefcnt);
 	invalidated = read_seqretry(&base->lock, sequence);
 	rcu_read_unlock();
 
 	if (p) {
-		/* The existing node has been found.
+found:		/* The existing node has been found.
 		 * Remove the entry from unused list if it was there.
 		 */
-		unlink_from_unused(p);
+		if (newrefcnt == 1)
+			unlink_from_unused(p);
 		return p;
 	}
 
@@ -494,11 +508,9 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create)
 	write_seqlock_bh(&base->lock);
 	p = lookup(daddr, stack, base);
 	if (p != peer_avl_empty) {
-		atomic_inc(&p->refcnt);
+		newrefcnt = atomic_inc_return(&p->refcnt);
 		write_sequnlock_bh(&base->lock);
-		/* Remove the entry from unused list if it was there. */
-		unlink_from_unused(p);
-		return p;
+		goto found;
 	}
 	p = create ? kmem_cache_alloc(peer_cachep, GFP_ATOMIC) : NULL;
 	if (p) {
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index c3118e1cd3bb..ec93335901dd 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <asm/uaccess.h>
+#include <asm/unaligned.h>
 #include <linux/skbuff.h>
 #include <linux/ip.h>
 #include <linux/icmp.h>
@@ -350,7 +351,7 @@ int ip_options_compile(struct net *net,
 				goto error;
 			}
 			if (optptr[2] <= optlen) {
-				__be32 *timeptr = NULL;
+				unsigned char *timeptr = NULL;
 				if (optptr[2]+3 > optptr[1]) {
 					pp_ptr = optptr + 2;
 					goto error;
@@ -359,7 +360,7 @@ int ip_options_compile(struct net *net,
 				      case IPOPT_TS_TSONLY:
 					opt->ts = optptr - iph;
 					if (skb)
-						timeptr = (__be32*)&optptr[optptr[2]-1];
+						timeptr = &optptr[optptr[2]-1];
 					opt->ts_needtime = 1;
 					optptr[2] += 4;
 					break;
@@ -371,7 +372,7 @@ int ip_options_compile(struct net *net,
 					opt->ts = optptr - iph;
 					if (rt)  {
 						memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
-						timeptr = (__be32*)&optptr[optptr[2]+3];
+						timeptr = &optptr[optptr[2]+3];
 					}
 					opt->ts_needaddr = 1;
 					opt->ts_needtime = 1;
@@ -389,7 +390,7 @@ int ip_options_compile(struct net *net,
 						if (inet_addr_type(net, addr) == RTN_UNICAST)
 							break;
 						if (skb)
-							timeptr = (__be32*)&optptr[optptr[2]+3];
+							timeptr = &optptr[optptr[2]+3];
 					}
 					opt->ts_needtime = 1;
 					optptr[2] += 8;
@@ -403,10 +404,10 @@ int ip_options_compile(struct net *net,
 				}
 				if (timeptr) {
 					struct timespec tv;
-					__be32  midtime;
+					u32  midtime;
 					getnstimeofday(&tv);
-					midtime = htonl((tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC);
-					memcpy(timeptr, &midtime, sizeof(__be32));
+					midtime = (tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC;
+					put_unaligned_be32(midtime, timeptr);
 					opt->is_changed = 1;
 				}
 			} else {
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 98af3697c718..a8024eaa0e87 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -799,7 +799,9 @@ static int __ip_append_data(struct sock *sk,
 	int csummode = CHECKSUM_NONE;
 	struct rtable *rt = (struct rtable *)cork->dst;
 
-	exthdrlen = transhdrlen ? rt->dst.header_len : 0;
+	skb = skb_peek_tail(queue);
+
+	exthdrlen = !skb ? rt->dst.header_len : 0;
 	length += exthdrlen;
 	transhdrlen += exthdrlen;
 	mtu = cork->fragsize;
@@ -825,8 +827,6 @@ static int __ip_append_data(struct sock *sk,
 	    !exthdrlen)
 		csummode = CHECKSUM_PARTIAL;
 
-	skb = skb_peek_tail(queue);
-
 	cork->length += length;
 	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index d2c1311cb28d..5c9b9d963918 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -203,7 +203,8 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
 	else
 		pmsg->outdev_name[0] = '\0';
 
-	if (entry->indev && entry->skb->dev) {
+	if (entry->indev && entry->skb->dev &&
+	    entry->skb->mac_header != entry->skb->network_header) {
 		pmsg->hw_type = entry->skb->dev->type;
 		pmsg->hw_addrlen = dev_parse_header(entry->skb,
 						    pmsg->hw_addr);
@@ -402,7 +403,8 @@ ipq_dev_drop(int ifindex)
 static inline void
 __ipq_rcv_skb(struct sk_buff *skb)
 {
-	int status, type, pid, flags, nlmsglen, skblen;
+	int status, type, pid, flags;
+	unsigned int nlmsglen, skblen;
 	struct nlmsghdr *nlh;
 
 	skblen = skb->len;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 764743843503..24e556e83a3b 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -566,7 +566,7 @@ check_entry(const struct ipt_entry *e, const char *name)
 	const struct xt_entry_target *t;
 
 	if (!ip_checkentry(&e->ip)) {
-		duprintf("ip check failed %p %s.\n", e, par->match->name);
+		duprintf("ip check failed %p %s.\n", e, name);
 		return -EINVAL;
 	}
 
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index d609ac3cb9a4..5c9e97c79017 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -307,7 +307,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	 * error messages (RELATED) and information requests (see below) */
 	if (ip_hdr(skb)->protocol == IPPROTO_ICMP &&
 	    (ctinfo == IP_CT_RELATED ||
-	     ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY))
+	     ctinfo == IP_CT_RELATED_REPLY))
 		return XT_CONTINUE;
 
 	/* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO,
@@ -321,12 +321,12 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
 			ct->mark = hash;
 			break;
 		case IP_CT_RELATED:
-		case IP_CT_RELATED+IP_CT_IS_REPLY:
+		case IP_CT_RELATED_REPLY:
 			/* FIXME: we don't handle expectations at the
 			 * moment.  they can arrive on a different node than
 			 * the master connection (e.g. FTP passive mode) */
 		case IP_CT_ESTABLISHED:
-		case IP_CT_ESTABLISHED+IP_CT_IS_REPLY:
+		case IP_CT_ESTABLISHED_REPLY:
 			break;
 		default:
 			break;
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index d2ed9dc74ebc..9931152a78b5 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -60,7 +60,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	nat = nfct_nat(ct);
 
 	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
-			    ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY));
+			    ctinfo == IP_CT_RELATED_REPLY));
 
 	/* Source address is 0.0.0.0 - locally generated packet that is
 	 * probably not supposed to be masqueraded.
diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c
index af6e9c778345..2b57e52c746c 100644
--- a/net/ipv4/netfilter/ipt_ecn.c
+++ b/net/ipv4/netfilter/ipt_ecn.c
@@ -25,7 +25,8 @@ MODULE_LICENSE("GPL");
 static inline bool match_ip(const struct sk_buff *skb,
 			    const struct ipt_ecn_info *einfo)
 {
-	return (ip_hdr(skb)->tos & IPT_ECN_IP_MASK) == einfo->ip_ect;
+	return ((ip_hdr(skb)->tos & IPT_ECN_IP_MASK) == einfo->ip_ect) ^
+	       !!(einfo->invert & IPT_ECN_OP_MATCH_IP);
 }
 
 static inline bool match_tcp(const struct sk_buff *skb,
@@ -76,8 +77,6 @@ static bool ecn_mt(const struct sk_buff *skb, struct xt_action_param *par)
 			return false;
 
 	if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR)) {
-		if (ip_hdr(skb)->protocol != IPPROTO_TCP)
-			return false;
 		if (!match_tcp(skb, info, &par->hotdrop))
 			return false;
 	}
@@ -97,7 +96,7 @@ static int ecn_mt_check(const struct xt_mtchk_param *par)
 		return -EINVAL;
 
 	if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) &&
-	    ip->proto != IPPROTO_TCP) {
+	    (ip->proto != IPPROTO_TCP || ip->invflags & IPT_INV_PROTO)) {
 		pr_info("cannot match TCP bits in rule for non-tcp packets\n");
 		return -EINVAL;
 	}
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 5a03c02af999..de9da21113a1 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -101,7 +101,7 @@ static unsigned int ipv4_confirm(unsigned int hooknum,
 
 	/* This is where we call the helper: as the packet goes out. */
 	ct = nf_ct_get(skb, &ctinfo);
-	if (!ct || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)
+	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
 		goto out;
 
 	help = nfct_help(ct);
@@ -121,7 +121,9 @@ static unsigned int ipv4_confirm(unsigned int hooknum,
 		return ret;
 	}
 
-	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status)) {
+	/* adjust seqs for loopback traffic only in outgoing direction */
+	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
+	    !nf_is_loopback_packet(skb)) {
 		typeof(nf_nat_seq_adjust_hook) seq_adjust;
 
 		seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook);
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index 7404bde95994..ab5b27a2916f 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -160,7 +160,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 	/* Update skb to refer to this connection */
 	skb->nfct = &nf_ct_tuplehash_to_ctrack(h)->ct_general;
 	skb->nfctinfo = *ctinfo;
-	return -NF_ACCEPT;
+	return NF_ACCEPT;
 }
 
 /* Small and modified version of icmp_rcv */
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 9c71b2755ce3..3346de5d94d0 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -433,7 +433,7 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct,
 
 	/* Must be RELATED */
 	NF_CT_ASSERT(skb->nfctinfo == IP_CT_RELATED ||
-		     skb->nfctinfo == IP_CT_RELATED+IP_CT_IS_REPLY);
+		     skb->nfctinfo == IP_CT_RELATED_REPLY);
 
 	/* Redirects on non-null nats must be dropped, else they'll
 	   start talking to each other without our translation, and be
diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c
index 99cfa28b6d38..ebc5f8894f99 100644
--- a/net/ipv4/netfilter/nf_nat_helper.c
+++ b/net/ipv4/netfilter/nf_nat_helper.c
@@ -160,7 +160,7 @@ static void nf_nat_csum(struct sk_buff *skb, const struct iphdr *iph, void *data
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL) {
 		if (!(rt->rt_flags & RTCF_LOCAL) &&
-		    skb->dev->features & NETIF_F_V4_CSUM) {
+		    (!skb->dev || skb->dev->features & NETIF_F_V4_CSUM)) {
 			skb->ip_summed = CHECKSUM_PARTIAL;
 			skb->csum_start = skb_headroom(skb) +
 					  skb_network_offset(skb) +
diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c
index 21c30426480b..733c9abc1cbd 100644
--- a/net/ipv4/netfilter/nf_nat_rule.c
+++ b/net/ipv4/netfilter/nf_nat_rule.c
@@ -53,7 +53,7 @@ ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par)
 
 	/* Connection must be valid and new. */
 	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
-			    ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY));
+			    ctinfo == IP_CT_RELATED_REPLY));
 	NF_CT_ASSERT(par->out != NULL);
 
 	return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_SRC);
diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c
index 7317bdf1d457..483b76d042da 100644
--- a/net/ipv4/netfilter/nf_nat_standalone.c
+++ b/net/ipv4/netfilter/nf_nat_standalone.c
@@ -116,7 +116,7 @@ nf_nat_fn(unsigned int hooknum,
 
 	switch (ctinfo) {
 	case IP_CT_RELATED:
-	case IP_CT_RELATED+IP_CT_IS_REPLY:
+	case IP_CT_RELATED_REPLY:
 		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
 			if (!nf_nat_icmp_reply_translation(ct, ctinfo,
 							   hooknum, skb))
@@ -144,7 +144,7 @@ nf_nat_fn(unsigned int hooknum,
 	default:
 		/* ESTABLISHED */
 		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
-			     ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY));
+			     ctinfo == IP_CT_ESTABLISHED_REPLY);
 	}
 
 	return nf_nat_packet(ct, ctinfo, hooknum, skb);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 9aaa67165f42..39b403f854c6 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -41,7 +41,6 @@
 #include <linux/proc_fs.h>
 #include <net/sock.h>
 #include <net/ping.h>
-#include <net/icmp.h>
 #include <net/udp.h>
 #include <net/route.h>
 #include <net/inet_common.h>
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 52b0b956508b..aa13ef105110 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1316,6 +1316,23 @@ reject_redirect:
 	;
 }
 
+static bool peer_pmtu_expired(struct inet_peer *peer)
+{
+	unsigned long orig = ACCESS_ONCE(peer->pmtu_expires);
+
+	return orig &&
+	       time_after_eq(jiffies, orig) &&
+	       cmpxchg(&peer->pmtu_expires, orig, 0) == orig;
+}
+
+static bool peer_pmtu_cleaned(struct inet_peer *peer)
+{
+	unsigned long orig = ACCESS_ONCE(peer->pmtu_expires);
+
+	return orig &&
+	       cmpxchg(&peer->pmtu_expires, orig, 0) == orig;
+}
+
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
 {
 	struct rtable *rt = (struct rtable *)dst;
@@ -1331,14 +1348,8 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
 						rt_genid(dev_net(dst->dev)));
 			rt_del(hash, rt);
 			ret = NULL;
-		} else if (rt->peer &&
-			   rt->peer->pmtu_expires &&
-			   time_after_eq(jiffies, rt->peer->pmtu_expires)) {
-			unsigned long orig = rt->peer->pmtu_expires;
-
-			if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig)
-				dst_metric_set(dst, RTAX_MTU,
-					       rt->peer->pmtu_orig);
+		} else if (rt->peer && peer_pmtu_expired(rt->peer)) {
+			dst_metric_set(dst, RTAX_MTU, rt->peer->pmtu_orig);
 		}
 	}
 	return ret;
@@ -1531,8 +1542,10 @@ unsigned short ip_rt_frag_needed(struct net *net, const struct iphdr *iph,
 
 static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer)
 {
-	unsigned long expires = peer->pmtu_expires;
+	unsigned long expires = ACCESS_ONCE(peer->pmtu_expires);
 
+	if (!expires)
+		return;
 	if (time_before(jiffies, expires)) {
 		u32 orig_dst_mtu = dst_mtu(dst);
 		if (peer->pmtu_learned < orig_dst_mtu) {
@@ -1555,10 +1568,11 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 		rt_bind_peer(rt, rt->rt_dst, 1);
 	peer = rt->peer;
 	if (peer) {
+		unsigned long pmtu_expires = ACCESS_ONCE(peer->pmtu_expires);
+
 		if (mtu < ip_rt_min_pmtu)
 			mtu = ip_rt_min_pmtu;
-		if (!peer->pmtu_expires || mtu < peer->pmtu_learned) {
-			unsigned long pmtu_expires;
+		if (!pmtu_expires || mtu < peer->pmtu_learned) {
 
 			pmtu_expires = jiffies + ip_rt_mtu_expires;
 			if (!pmtu_expires)
@@ -1612,13 +1626,14 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 			rt_bind_peer(rt, rt->rt_dst, 0);
 
 		peer = rt->peer;
-		if (peer && peer->pmtu_expires)
+		if (peer) {
 			check_peer_pmtu(dst, peer);
 
-		if (peer && peer->redirect_learned.a4 &&
-		    peer->redirect_learned.a4 != rt->rt_gateway) {
-			if (check_peer_redir(dst, peer))
-				return NULL;
+			if (peer->redirect_learned.a4 &&
+			    peer->redirect_learned.a4 != rt->rt_gateway) {
+				if (check_peer_redir(dst, peer))
+					return NULL;
+			}
 		}
 
 		rt->rt_peer_genid = rt_peer_genid();
@@ -1649,14 +1664,8 @@ static void ipv4_link_failure(struct sk_buff *skb)
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
 
 	rt = skb_rtable(skb);
-	if (rt &&
-	    rt->peer &&
-	    rt->peer->pmtu_expires) {
-		unsigned long orig = rt->peer->pmtu_expires;
-
-		if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig)
-			dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig);
-	}
+	if (rt && rt->peer && peer_pmtu_cleaned(rt->peer))
+		dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig);
 }
 
 static int ip_rt_bug(struct sk_buff *skb)
@@ -1770,8 +1779,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
 			       sizeof(u32) * RTAX_MAX);
 		dst_init_metrics(&rt->dst, peer->metrics, false);
 
-		if (peer->pmtu_expires)
-			check_peer_pmtu(&rt->dst, peer);
+		check_peer_pmtu(&rt->dst, peer);
 		if (peer->redirect_learned.a4 &&
 		    peer->redirect_learned.a4 != rt->rt_gateway) {
 			rt->rt_gateway = peer->redirect_learned.a4;
@@ -1894,9 +1902,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 
 	hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
 	rth = rt_intern_hash(hash, rth, skb, dev->ifindex);
-	err = 0;
-	if (IS_ERR(rth))
-		err = PTR_ERR(rth);
+	return IS_ERR(rth) ? PTR_ERR(rth) : 0;
 
 e_nobufs:
 	return -ENOBUFS;
@@ -2775,7 +2781,8 @@ static int rt_fill_info(struct net *net,
 	struct rtable *rt = skb_rtable(skb);
 	struct rtmsg *r;
 	struct nlmsghdr *nlh;
-	long expires;
+	long expires = 0;
+	const struct inet_peer *peer = rt->peer;
 	u32 id = 0, ts = 0, tsage = 0, error;
 
 	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags);
@@ -2823,15 +2830,16 @@ static int rt_fill_info(struct net *net,
 		NLA_PUT_BE32(skb, RTA_MARK, rt->rt_mark);
 
 	error = rt->dst.error;
-	expires = (rt->peer && rt->peer->pmtu_expires) ?
-		rt->peer->pmtu_expires - jiffies : 0;
-	if (rt->peer) {
+	if (peer) {
 		inet_peer_refcheck(rt->peer);
-		id = atomic_read(&rt->peer->ip_id_count) & 0xffff;
-		if (rt->peer->tcp_ts_stamp) {
-			ts = rt->peer->tcp_ts;
-			tsage = get_seconds() - rt->peer->tcp_ts_stamp;
+		id = atomic_read(&peer->ip_id_count) & 0xffff;
+		if (peer->tcp_ts_stamp) {
+			ts = peer->tcp_ts;
+			tsage = get_seconds() - peer->tcp_ts_stamp;
 		}
+		expires = ACCESS_ONCE(peer->pmtu_expires);
+		if (expires)
+			expires -= jiffies;
 	}
 
 	if (rt_is_input_route(rt)) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a7d6671e33b8..708dc203b034 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1589,6 +1589,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 			goto discard;
 
 		if (nsk != sk) {
+			sock_rps_save_rxhash(nsk, skb->rxhash);
 			if (tcp_child_process(sk, nsk, skb)) {
 				rsk = nsk;
 				goto reset;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index b7919f901fbf..d450a2f9fc06 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -272,6 +272,10 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
 	if (addr_len < SIN6_LEN_RFC2133)
 		return -EINVAL;
+
+	if (addr->sin6_family != AF_INET6)
+		return -EINVAL;
+
 	addr_type = ipv6_addr_type(&addr->sin6_addr);
 	if ((addr_type & IPV6_ADDR_MULTICAST) && sock->type == SOCK_STREAM)
 		return -EINVAL;
diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c
index 413ab0754e1f..249394863284 100644
--- a/net/ipv6/netfilter/ip6_queue.c
+++ b/net/ipv6/netfilter/ip6_queue.c
@@ -204,7 +204,8 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
 	else
 		pmsg->outdev_name[0] = '\0';
 
-	if (entry->indev && entry->skb->dev) {
+	if (entry->indev && entry->skb->dev &&
+	    entry->skb->mac_header != entry->skb->network_header) {
 		pmsg->hw_type = entry->skb->dev->type;
 		pmsg->hw_addrlen = dev_parse_header(entry->skb, pmsg->hw_addr);
 	}
@@ -403,7 +404,8 @@ ipq_dev_drop(int ifindex)
 static inline void
 __ipq_rcv_skb(struct sk_buff *skb)
 {
-	int status, type, pid, flags, nlmsglen, skblen;
+	int status, type, pid, flags;
+	unsigned int nlmsglen, skblen;
 	struct nlmsghdr *nlh;
 
 	skblen = skb->len;
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index c8af58b22562..4111050a9fc5 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -160,7 +160,7 @@ static unsigned int ipv6_confirm(unsigned int hooknum,
 
 	/* This is where we call the helper: as the packet goes out. */
 	ct = nf_ct_get(skb, &ctinfo);
-	if (!ct || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)
+	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
 		goto out;
 
 	help = nfct_help(ct);
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index 1df3c8b6bf47..7c05e7eacbc6 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -177,7 +177,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
 	/* Update skb to refer to this connection */
 	skb->nfct = &nf_ct_tuplehash_to_ctrack(h)->ct_general;
 	skb->nfctinfo = *ctinfo;
-	return -NF_ACCEPT;
+	return NF_ACCEPT;
 }
 
 static int
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d1fd28711ba5..87551ca568cd 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1644,6 +1644,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 		 * the new socket..
 		 */
 		if(nsk != sk) {
+			sock_rps_save_rxhash(nsk, skb->rxhash);
 			if (tcp_child_process(sk, nsk, skb))
 				goto reset;
 			if (opt_skb)
diff --git a/net/irda/iriap.c b/net/irda/iriap.c
index 36477538cea8..f876eed7d4aa 100644
--- a/net/irda/iriap.c
+++ b/net/irda/iriap.c
@@ -87,6 +87,8 @@ static inline void iriap_start_watchdog_timer(struct iriap_cb *self,
 			 iriap_watchdog_timer_expired);
 }
 
+static struct lock_class_key irias_objects_key;
+
 /*
  * Function iriap_init (void)
  *
@@ -114,6 +116,9 @@ int __init iriap_init(void)
 		return -ENOMEM;
 	}
 
+	lockdep_set_class_and_name(&irias_objects->hb_spinlock, &irias_objects_key,
+				   "irias_objects");
+
 	/*
 	 *  Register some default services for IrLMP
 	 */
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index a15c01524959..7f9124914b13 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -54,7 +54,7 @@
 #include <asm/atomic.h>
 #include <asm/ebcdic.h>
 #include <asm/io.h>
-#include <asm/s390_ext.h>
+#include <asm/irq.h>
 #include <asm/smp.h>
 
 /*
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index b8dbae82fab8..76130134bfa6 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -258,7 +258,7 @@ static int l2tp_dfs_seq_open(struct inode *inode, struct file *file)
 	 */
 	pd->net = get_net_ns_by_pid(current->pid);
 	if (IS_ERR(pd->net)) {
-		rc = -PTR_ERR(pd->net);
+		rc = PTR_ERR(pd->net);
 		goto err_free_pd;
 	}
 
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 421eaa6b0c2b..56c24cabf26d 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -965,6 +965,10 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata)
 
 	mutex_lock(&sdata->u.ibss.mtx);
 
+	sdata->u.ibss.state = IEEE80211_IBSS_MLME_SEARCH;
+	memset(sdata->u.ibss.bssid, 0, ETH_ALEN);
+	sdata->u.ibss.ssid_len = 0;
+
 	active_ibss = ieee80211_sta_active_ibss(sdata);
 
 	if (!active_ibss && !is_zero_ether_addr(ifibss->bssid)) {
@@ -999,8 +1003,6 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata)
 	kfree_skb(skb);
 
 	skb_queue_purge(&sdata->skb_queue);
-	memset(sdata->u.ibss.bssid, 0, ETH_ALEN);
-	sdata->u.ibss.ssid_len = 0;
 
 	del_timer_sync(&sdata->u.ibss.timer);
 
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 2025af52b195..090b0ec1e056 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -775,9 +775,6 @@ struct ieee80211_local {
 
 	int tx_headroom; /* required headroom for hardware/radiotap */
 
-	/* count for keys needing tailroom space allocation */
-	int crypto_tx_tailroom_needed_cnt;
-
 	/* Tasklet and skb queue to process calls from IRQ mode. All frames
 	 * added to skb_queue will be processed, but frames in
 	 * skb_queue_unreliable may be dropped if the total length of these
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 49d4f869e0bc..dee30aea9ab3 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1145,6 +1145,10 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 				+ IEEE80211_ENCRYPT_HEADROOM;
 	ndev->needed_tailroom = IEEE80211_ENCRYPT_TAILROOM;
 
+	ret = dev_alloc_name(ndev, ndev->name);
+	if (ret < 0)
+		goto fail;
+
 	ieee80211_assign_perm_addr(local, ndev, type);
 	memcpy(ndev->dev_addr, ndev->perm_addr, ETH_ALEN);
 	SET_NETDEV_DEV(ndev, wiphy_dev(local->hw.wiphy));
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 31afd712930d..f825e2f0a57e 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -101,11 +101,6 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 
 	if (!ret) {
 		key->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE;
-
-		if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
-		      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)))
-			key->local->crypto_tx_tailroom_needed_cnt--;
-
 		return 0;
 	}
 
@@ -161,10 +156,6 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key)
 			  key->conf.keyidx, sta ? sta->addr : bcast_addr, ret);
 
 	key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE;
-
-	if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
-	      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)))
-		key->local->crypto_tx_tailroom_needed_cnt++;
 }
 
 void ieee80211_key_removed(struct ieee80211_key_conf *key_conf)
@@ -403,10 +394,8 @@ static void __ieee80211_key_destroy(struct ieee80211_key *key)
 		ieee80211_aes_key_free(key->u.ccmp.tfm);
 	if (key->conf.cipher == WLAN_CIPHER_SUITE_AES_CMAC)
 		ieee80211_aes_cmac_key_free(key->u.aes_cmac.tfm);
-	if (key->local) {
+	if (key->local)
 		ieee80211_debugfs_key_remove(key);
-		key->local->crypto_tx_tailroom_needed_cnt--;
-	}
 
 	kfree(key);
 }
@@ -468,8 +457,6 @@ int ieee80211_key_link(struct ieee80211_key *key,
 
 	ieee80211_debugfs_key_add(key);
 
-	key->local->crypto_tx_tailroom_needed_cnt++;
-
 	ret = ieee80211_key_enable_hw_accel(key);
 
 	mutex_unlock(&sdata->local->key_mtx);
@@ -511,12 +498,8 @@ void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata)
 
 	mutex_lock(&sdata->local->key_mtx);
 
-	sdata->local->crypto_tx_tailroom_needed_cnt = 0;
-
-	list_for_each_entry(key, &sdata->key_list, list) {
-		sdata->local->crypto_tx_tailroom_needed_cnt++;
+	list_for_each_entry(key, &sdata->key_list, list)
 		ieee80211_key_enable_hw_accel(key);
-	}
 
 	mutex_unlock(&sdata->local->key_mtx);
 }
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 4f6b2675e41d..d595265d6c22 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1089,6 +1089,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 		local->hw.conf.flags &= ~IEEE80211_CONF_PS;
 		config_changed |= IEEE80211_CONF_CHANGE_PS;
 	}
+	local->ps_sdata = NULL;
 
 	ieee80211_hw_config(local, config_changed);
 
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 27af6723cb5e..58ffa7d069c7 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -15,7 +15,6 @@
 #include <linux/if_arp.h>
 #include <linux/rtnetlink.h>
 #include <linux/pm_qos_params.h>
-#include <linux/slab.h>
 #include <net/sch_generic.h>
 #include <linux/slab.h>
 #include <net/mac80211.h>
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 64e0f7587e6d..3104c844b544 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1480,7 +1480,12 @@ static int ieee80211_skb_resize(struct ieee80211_local *local,
 {
 	int tail_need = 0;
 
-	if (may_encrypt && local->crypto_tx_tailroom_needed_cnt) {
+	/*
+	 * This could be optimised, devices that do full hardware
+	 * crypto (including TKIP MMIC) need no tailroom... But we
+	 * have no drivers for such devices currently.
+	 */
+	if (may_encrypt) {
 		tail_need = IEEE80211_ENCRYPT_TAILROOM;
 		tail_need -= skb_tailroom(skb);
 		tail_need = max_t(int, tail_need, 0);
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 72d1ac611fdc..42aa64b6b0b1 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -767,7 +767,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
 	if (!attr[IPSET_ATTR_SETNAME]) {
 		for (i = 0; i < ip_set_max; i++) {
 			if (ip_set_list[i] != NULL && ip_set_list[i]->ref) {
-				ret = IPSET_ERR_BUSY;
+				ret = -IPSET_ERR_BUSY;
 				goto out;
 			}
 		}
@@ -815,7 +815,7 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb,
 	ip_set_id_t i;
 
 	if (unlikely(protocol_failed(attr)))
-		return -EPROTO;
+		return -IPSET_ERR_PROTOCOL;
 
 	if (!attr[IPSET_ATTR_SETNAME]) {
 		for (i = 0; i < ip_set_max; i++)
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 4743e5402522..565a7c5b8818 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -146,8 +146,9 @@ hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
 {
 	const struct ip_set_hash *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_ipportnet4_elem data =
-		{ .cidr = h->nets[0].cidr || HOST_MASK };
+	struct hash_ipportnet4_elem data = {
+		.cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK
+	};
 
 	if (data.cidr == 0)
 		return -EINVAL;
@@ -394,8 +395,9 @@ hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
 {
 	const struct ip_set_hash *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_ipportnet6_elem data =
-		{ .cidr = h->nets[0].cidr || HOST_MASK };
+	struct hash_ipportnet6_elem data = {
+		.cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK
+	};
 
 	if (data.cidr == 0)
 		return -EINVAL;
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index c4db202b7da4..2aeeabcd5a21 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -131,7 +131,9 @@ hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb,
 {
 	const struct ip_set_hash *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_net4_elem data = { .cidr = h->nets[0].cidr || HOST_MASK };
+	struct hash_net4_elem data = {
+		.cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK
+	};
 
 	if (data.cidr == 0)
 		return -EINVAL;
@@ -296,7 +298,9 @@ hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb,
 {
 	const struct ip_set_hash *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_net6_elem data = { .cidr = h->nets[0].cidr || HOST_MASK };
+	struct hash_net6_elem data = {
+		.cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK
+	};
 
 	if (data.cidr == 0)
 		return -EINVAL;
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index d2a40362dd3a..e50d9bb8820b 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -144,7 +144,8 @@ hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	const struct ip_set_hash *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netport4_elem data = {
-		.cidr = h->nets[0].cidr || HOST_MASK };
+		.cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK
+	};
 
 	if (data.cidr == 0)
 		return -EINVAL;
@@ -357,7 +358,8 @@ hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb,
 	const struct ip_set_hash *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netport6_elem data = {
-		.cidr = h->nets[0].cidr || HOST_MASK };
+		.cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK
+	};
 
 	if (data.cidr == 0)
 		return -EINVAL;
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index bf28ac2fc99b..782db275ac53 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -776,8 +776,16 @@ static void ip_vs_conn_expire(unsigned long data)
 		if (cp->control)
 			ip_vs_control_del(cp);
 
-		if (cp->flags & IP_VS_CONN_F_NFCT)
+		if (cp->flags & IP_VS_CONN_F_NFCT) {
 			ip_vs_conn_drop_conntrack(cp);
+			/* Do not access conntracks during subsys cleanup
+			 * because nf_conntrack_find_get can not be used after
+			 * conntrack cleanup for the net.
+			 */
+			smp_rmb();
+			if (ipvs->enable)
+				ip_vs_conn_drop_conntrack(cp);
+		}
 
 		ip_vs_pe_put(cp->pe);
 		kfree(cp->pe_data);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index bfa808f4da13..24c28d238dcb 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1772,7 +1772,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 		.owner		= THIS_MODULE,
 		.pf		= PF_INET,
 		.hooknum	= NF_INET_LOCAL_IN,
-		.priority	= 99,
+		.priority	= NF_IP_PRI_NAT_SRC - 2,
 	},
 	/* After packet filtering, forward packet through VS/DR, VS/TUN,
 	 * or VS/NAT(change destination), so that filtering rules can be
@@ -1782,7 +1782,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 		.owner		= THIS_MODULE,
 		.pf		= PF_INET,
 		.hooknum	= NF_INET_LOCAL_IN,
-		.priority	= 101,
+		.priority	= NF_IP_PRI_NAT_SRC - 1,
 	},
 	/* Before ip_vs_in, change source only for VS/NAT */
 	{
@@ -1790,7 +1790,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 		.owner		= THIS_MODULE,
 		.pf		= PF_INET,
 		.hooknum	= NF_INET_LOCAL_OUT,
-		.priority	= -99,
+		.priority	= NF_IP_PRI_NAT_DST + 1,
 	},
 	/* After mangle, schedule and forward local requests */
 	{
@@ -1798,7 +1798,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 		.owner		= THIS_MODULE,
 		.pf		= PF_INET,
 		.hooknum	= NF_INET_LOCAL_OUT,
-		.priority	= -98,
+		.priority	= NF_IP_PRI_NAT_DST + 2,
 	},
 	/* After packet filtering (but before ip_vs_out_icmp), catch icmp
 	 * destined for 0.0.0.0/0, which is for incoming IPVS connections */
@@ -1824,7 +1824,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 		.owner		= THIS_MODULE,
 		.pf		= PF_INET6,
 		.hooknum	= NF_INET_LOCAL_IN,
-		.priority	= 99,
+		.priority	= NF_IP6_PRI_NAT_SRC - 2,
 	},
 	/* After packet filtering, forward packet through VS/DR, VS/TUN,
 	 * or VS/NAT(change destination), so that filtering rules can be
@@ -1834,7 +1834,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 		.owner		= THIS_MODULE,
 		.pf		= PF_INET6,
 		.hooknum	= NF_INET_LOCAL_IN,
-		.priority	= 101,
+		.priority	= NF_IP6_PRI_NAT_SRC - 1,
 	},
 	/* Before ip_vs_in, change source only for VS/NAT */
 	{
@@ -1842,7 +1842,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 		.owner		= THIS_MODULE,
 		.pf		= PF_INET,
 		.hooknum	= NF_INET_LOCAL_OUT,
-		.priority	= -99,
+		.priority	= NF_IP6_PRI_NAT_DST + 1,
 	},
 	/* After mangle, schedule and forward local requests */
 	{
@@ -1850,7 +1850,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 		.owner		= THIS_MODULE,
 		.pf		= PF_INET6,
 		.hooknum	= NF_INET_LOCAL_OUT,
-		.priority	= -98,
+		.priority	= NF_IP6_PRI_NAT_DST + 2,
 	},
 	/* After packet filtering (but before ip_vs_out_icmp), catch icmp
 	 * destined for 0.0.0.0/0, which is for incoming IPVS connections */
@@ -1945,6 +1945,7 @@ static void __net_exit __ip_vs_dev_cleanup(struct net *net)
 {
 	EnterFunction(2);
 	net_ipvs(net)->enable = 0;	/* Disable packet reception */
+	smp_wmb();
 	__ip_vs_sync_cleanup(net);
 	LeaveFunction(2);
 }
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 6b5dd6ddaae9..af63553fa332 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -411,25 +411,35 @@ static struct ip_vs_app ip_vs_ftp = {
 static int __net_init __ip_vs_ftp_init(struct net *net)
 {
 	int i, ret;
-	struct ip_vs_app *app = &ip_vs_ftp;
+	struct ip_vs_app *app;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	app = kmemdup(&ip_vs_ftp, sizeof(struct ip_vs_app), GFP_KERNEL);
+	if (!app)
+		return -ENOMEM;
+	INIT_LIST_HEAD(&app->a_list);
+	INIT_LIST_HEAD(&app->incs_list);
+	ipvs->ftp_app = app;
 
 	ret = register_ip_vs_app(net, app);
 	if (ret)
-		return ret;
+		goto err_exit;
 
 	for (i=0; i<IP_VS_APP_MAX_PORTS; i++) {
 		if (!ports[i])
 			continue;
 		ret = register_ip_vs_app_inc(net, app, app->protocol, ports[i]);
 		if (ret)
-			break;
+			goto err_unreg;
 		pr_info("%s: loaded support on port[%d] = %d\n",
 			app->name, i, ports[i]);
 	}
+	return 0;
 
-	if (ret)
-		unregister_ip_vs_app(net, app);
-
+err_unreg:
+	unregister_ip_vs_app(net, app);
+err_exit:
+	kfree(ipvs->ftp_app);
 	return ret;
 }
 /*
@@ -437,9 +447,10 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
  */
 static void __ip_vs_ftp_exit(struct net *net)
 {
-	struct ip_vs_app *app = &ip_vs_ftp;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	unregister_ip_vs_app(net, app);
+	unregister_ip_vs_app(net, ipvs->ftp_app);
+	kfree(ipvs->ftp_app);
 }
 
 static struct pernet_operations ip_vs_ftp_ops = {
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 2e1c11f78419..f7af8b866017 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -850,7 +850,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 
 	/* It exists; we have (non-exclusive) reference. */
 	if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) {
-		*ctinfo = IP_CT_ESTABLISHED + IP_CT_IS_REPLY;
+		*ctinfo = IP_CT_ESTABLISHED_REPLY;
 		/* Please set reply bit if this packet OK */
 		*set_reply = 1;
 	} else {
@@ -922,6 +922,9 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 			ret = -ret;
 			goto out;
 		}
+		/* ICMP[v6] protocol trackers may assign one conntrack. */
+		if (skb->nfct)
+			goto out;
 	}
 
 	ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
@@ -1143,7 +1146,7 @@ static void nf_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb)
 	/* This ICMP is in reverse direction to the packet which caused it */
 	ct = nf_ct_get(skb, &ctinfo);
 	if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL)
-		ctinfo = IP_CT_RELATED + IP_CT_IS_REPLY;
+		ctinfo = IP_CT_RELATED_REPLY;
 	else
 		ctinfo = IP_CT_RELATED;
 
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index e17cb7c7dd8f..6f5801eac999 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -368,7 +368,7 @@ static int help(struct sk_buff *skb,
 
 	/* Until there's been traffic both ways, don't look in packets. */
 	if (ctinfo != IP_CT_ESTABLISHED &&
-	    ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) {
+	    ctinfo != IP_CT_ESTABLISHED_REPLY) {
 		pr_debug("ftp: Conntrackinfo = %u\n", ctinfo);
 		return NF_ACCEPT;
 	}
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 18b2ce5c8ced..f03c2d4539f6 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -571,10 +571,9 @@ static int h245_help(struct sk_buff *skb, unsigned int protoff,
 	int ret;
 
 	/* Until there's been traffic both ways, don't look in packets. */
-	if (ctinfo != IP_CT_ESTABLISHED &&
-	    ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) {
+	if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY)
 		return NF_ACCEPT;
-	}
+
 	pr_debug("nf_ct_h245: skblen = %u\n", skb->len);
 
 	spin_lock_bh(&nf_h323_lock);
@@ -1125,10 +1124,9 @@ static int q931_help(struct sk_buff *skb, unsigned int protoff,
 	int ret;
 
 	/* Until there's been traffic both ways, don't look in packets. */
-	if (ctinfo != IP_CT_ESTABLISHED &&
-	    ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) {
+	if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY)
 		return NF_ACCEPT;
-	}
+
 	pr_debug("nf_ct_q931: skblen = %u\n", skb->len);
 
 	spin_lock_bh(&nf_h323_lock);
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index b394aa318776..4f9390b98697 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -125,8 +125,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 		return NF_ACCEPT;
 
 	/* Until there's been traffic both ways, don't look in packets. */
-	if (ctinfo != IP_CT_ESTABLISHED &&
-	    ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY)
+	if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY)
 		return NF_ACCEPT;
 
 	/* Not a full tcp header? */
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index 088944824e13..2fd4565144de 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -519,8 +519,7 @@ conntrack_pptp_help(struct sk_buff *skb, unsigned int protoff,
 	u_int16_t msg;
 
 	/* don't do any tracking before tcp handshake complete */
-	if (ctinfo != IP_CT_ESTABLISHED &&
-	    ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY)
+	if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY)
 		return NF_ACCEPT;
 
 	nexthdr_off = protoff;
diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c
index d9e27734b2a2..8501823b3f9b 100644
--- a/net/netfilter/nf_conntrack_sane.c
+++ b/net/netfilter/nf_conntrack_sane.c
@@ -78,7 +78,7 @@ static int help(struct sk_buff *skb,
 	ct_sane_info = &nfct_help(ct)->help.ct_sane_info;
 	/* Until there's been traffic both ways, don't look in packets. */
 	if (ctinfo != IP_CT_ESTABLISHED &&
-	    ctinfo != IP_CT_ESTABLISHED+IP_CT_IS_REPLY)
+	    ctinfo != IP_CT_ESTABLISHED_REPLY)
 		return NF_ACCEPT;
 
 	/* Not a full tcp header? */
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index cb5a28581782..93faf6a3a637 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1423,7 +1423,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff,
 	typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust;
 
 	if (ctinfo != IP_CT_ESTABLISHED &&
-	    ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY)
+	    ctinfo != IP_CT_ESTABLISHED_REPLY)
 		return NF_ACCEPT;
 
 	/* No Data ? */
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index e0ee010935e7..2e7ccbb43ddb 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -456,7 +456,8 @@ __build_packet_message(struct nfulnl_instance *inst,
 	if (skb->mark)
 		NLA_PUT_BE32(inst->skb, NFULA_MARK, htonl(skb->mark));
 
-	if (indev && skb->dev) {
+	if (indev && skb->dev &&
+	    skb->mac_header != skb->network_header) {
 		struct nfulnl_msg_packet_hw phw;
 		int len = dev_parse_header(skb, phw.hw_addr);
 		if (len > 0) {
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index b83123f12b42..fdd2fafe0a14 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -335,7 +335,8 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
 	if (entskb->mark)
 		NLA_PUT_BE32(skb, NFQA_MARK, htonl(entskb->mark));
 
-	if (indev && entskb->dev) {
+	if (indev && entskb->dev &&
+	    entskb->mac_header != entskb->network_header) {
 		struct nfqnl_msg_packet_hw phw;
 		int len = dev_parse_header(entskb, phw.hw_addr);
 		if (len) {
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 9cc46356b577..fe39f7e913df 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -143,9 +143,9 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 	ct = nf_ct_get(skb, &ctinfo);
 	if (ct && !nf_ct_is_untracked(ct) &&
 	    ((iph->protocol != IPPROTO_ICMP &&
-	      ctinfo == IP_CT_IS_REPLY + IP_CT_ESTABLISHED) ||
+	      ctinfo == IP_CT_ESTABLISHED_REPLY) ||
 	     (iph->protocol == IPPROTO_ICMP &&
-	      ctinfo == IP_CT_IS_REPLY + IP_CT_RELATED)) &&
+	      ctinfo == IP_CT_RELATED_REPLY)) &&
 	    (ct->status & IPS_SRC_NAT_DONE)) {
 
 		daddr = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 925f715686a5..c0c3cda19712 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -798,7 +798,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 			getnstimeofday(&ts);
 		h.h2->tp_sec = ts.tv_sec;
 		h.h2->tp_nsec = ts.tv_nsec;
-		h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
+		if (vlan_tx_tag_present(skb)) {
+			h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
+			status |= TP_STATUS_VLAN_VALID;
+		} else {
+			h.h2->tp_vlan_tci = 0;
+		}
+		h.h2->tp_padding = 0;
 		hdrlen = sizeof(*h.h2);
 		break;
 	default:
@@ -1725,8 +1731,13 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 		aux.tp_snaplen = skb->len;
 		aux.tp_mac = 0;
 		aux.tp_net = skb_network_offset(skb);
-		aux.tp_vlan_tci = vlan_tx_tag_get(skb);
-
+		if (vlan_tx_tag_present(skb)) {
+			aux.tp_vlan_tci = vlan_tx_tag_get(skb);
+			aux.tp_status |= TP_STATUS_VLAN_VALID;
+		} else {
+			aux.tp_vlan_tci = 0;
+		}
+		aux.tp_padding = 0;
 		put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux);
 	}
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index b1721d71c27c..b4c680900d7a 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -251,9 +251,8 @@ static void dev_watchdog(unsigned long arg)
 			}
 
 			if (some_queue_timedout) {
-				char drivername[64];
 				WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n",
-				       dev->name, netdev_drivername(dev, drivername, 64), i);
+				       dev->name, netdev_drivername(dev), i);
 				dev->netdev_ops->ndo_tx_timeout(dev);
 			}
 			if (!mod_timer(&dev->watchdog_timer,
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 525f97c467e9..4a62888f2e43 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -444,15 +444,7 @@ void sctp_association_free(struct sctp_association *asoc)
 
 	asoc->peer.transport_count = 0;
 
-	/* Free any cached ASCONF_ACK chunk. */
-	sctp_assoc_free_asconf_acks(asoc);
-
-	/* Free the ASCONF queue. */
-	sctp_assoc_free_asconf_queue(asoc);
-
-	/* Free any cached ASCONF chunk. */
-	if (asoc->addip_last_asconf)
-		sctp_chunk_free(asoc->addip_last_asconf);
+	sctp_asconf_queue_teardown(asoc);
 
 	/* AUTH - Free the endpoint shared keys */
 	sctp_auth_destroy_keys(&asoc->endpoint_shared_keys);
@@ -1646,3 +1638,16 @@ struct sctp_chunk *sctp_assoc_lookup_asconf_ack(
 
 	return NULL;
 }
+
+void sctp_asconf_queue_teardown(struct sctp_association *asoc)
+{
+	/* Free any cached ASCONF_ACK chunk. */
+	sctp_assoc_free_asconf_acks(asoc);
+
+	/* Free the ASCONF queue. */
+	sctp_assoc_free_asconf_queue(asoc);
+
+	/* Free any cached ASCONF chunk. */
+	if (asoc->addip_last_asconf)
+		sctp_chunk_free(asoc->addip_last_asconf);
+}
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index d612ca1ca6c0..534c2e5feb05 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1670,6 +1670,9 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 		case SCTP_CMD_SEND_NEXT_ASCONF:
 			sctp_cmd_send_asconf(asoc);
 			break;
+		case SCTP_CMD_PURGE_ASCONF_QUEUE:
+			sctp_asconf_queue_teardown(asoc);
+			break;
 		default:
 			pr_warn("Impossible command: %u, %p\n",
 				cmd->verb, cmd->obj.ptr);
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 7f4a4f8368ee..a297283154d5 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1718,11 +1718,21 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(const struct sctp_endpoint *ep,
 		return SCTP_DISPOSITION_CONSUME;
 	}
 
-	/* For now, fail any unsent/unacked data.  Consider the optional
-	 * choice of resending of this data.
+	/* For now, stop pending T3-rtx and SACK timers, fail any unsent/unacked
+	 * data. Consider the optional choice of resending of this data.
 	 */
+	sctp_add_cmd_sf(commands, SCTP_CMD_T3_RTX_TIMERS_STOP, SCTP_NULL());
+	sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
+			SCTP_TO(SCTP_EVENT_TIMEOUT_SACK));
 	sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_OUTQUEUE, SCTP_NULL());
 
+	/* Stop pending T4-rto timer, teardown ASCONF queue, ASCONF-ACK queue
+	 * and ASCONF-ACK cache.
+	 */
+	sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
+			SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
+	sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_ASCONF_QUEUE, SCTP_NULL());
+
 	repl = sctp_make_cookie_ack(new_asoc, chunk);
 	if (!repl)
 		goto nomem;
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 339ba64cce1e..5daf6cc4faea 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -577,13 +577,13 @@ retry:
 	}
 	inode = &gss_msg->inode->vfs_inode;
 	for (;;) {
-		prepare_to_wait(&gss_msg->waitqueue, &wait, TASK_INTERRUPTIBLE);
+		prepare_to_wait(&gss_msg->waitqueue, &wait, TASK_KILLABLE);
 		spin_lock(&inode->i_lock);
 		if (gss_msg->ctx != NULL || gss_msg->msg.errno < 0) {
 			break;
 		}
 		spin_unlock(&inode->i_lock);
-		if (signalled()) {
+		if (fatal_signal_pending(current)) {
 			err = -ERESTARTSYS;
 			goto out_intr;
 		}
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index 0a9a2ec2e469..c3b75333b821 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -43,6 +43,7 @@
 #include <linux/sunrpc/gss_krb5.h>
 #include <linux/sunrpc/xdr.h>
 #include <linux/crypto.h>
+#include <linux/sunrpc/gss_krb5_enctypes.h>
 
 #ifdef RPC_DEBUG
 # define RPCDBG_FACILITY	RPCDBG_AUTH
@@ -750,7 +751,7 @@ static struct gss_api_mech gss_kerberos_mech = {
 	.gm_ops		= &gss_kerberos_ops,
 	.gm_pf_num	= ARRAY_SIZE(gss_kerberos_pfs),
 	.gm_pfs		= gss_kerberos_pfs,
-	.gm_upcall_enctypes = "18,17,16,23,3,1,2",
+	.gm_upcall_enctypes = KRB5_SUPPORTED_ENCTYPES,
 };
 
 static int __init init_kerberos_module(void)
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 8d83f9d48713..8c9141583d6f 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -13,10 +13,6 @@
  *	and need to be refreshed, or when a packet was damaged in transit.
  *	This may be have to be moved to the VFS layer.
  *
- *  NB: BSD uses a more intelligent approach to guessing when a request
- *  or reply has been lost by keeping the RTO estimate for each procedure.
- *  We currently make do with a constant timeout value.
- *
  *  Copyright (C) 1992,1993 Rick Sladkey <jrs@world.std.com>
  *  Copyright (C) 1995,1996 Olaf Kirch <okir@monad.swb.de>
  */
@@ -32,7 +28,9 @@
 #include <linux/slab.h>
 #include <linux/utsname.h>
 #include <linux/workqueue.h>
+#include <linux/in.h>
 #include <linux/in6.h>
+#include <linux/un.h>
 
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
@@ -298,22 +296,27 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 	 * up a string representation of the passed-in address.
 	 */
 	if (args->servername == NULL) {
+		struct sockaddr_un *sun =
+				(struct sockaddr_un *)args->address;
+		struct sockaddr_in *sin =
+				(struct sockaddr_in *)args->address;
+		struct sockaddr_in6 *sin6 =
+				(struct sockaddr_in6 *)args->address;
+
 		servername[0] = '\0';
 		switch (args->address->sa_family) {
-		case AF_INET: {
-			struct sockaddr_in *sin =
-					(struct sockaddr_in *)args->address;
+		case AF_LOCAL:
+			snprintf(servername, sizeof(servername), "%s",
+				 sun->sun_path);
+			break;
+		case AF_INET:
 			snprintf(servername, sizeof(servername), "%pI4",
 				 &sin->sin_addr.s_addr);
 			break;
-		}
-		case AF_INET6: {
-			struct sockaddr_in6 *sin =
-					(struct sockaddr_in6 *)args->address;
+		case AF_INET6:
 			snprintf(servername, sizeof(servername), "%pI6",
-				 &sin->sin6_addr);
+				 &sin6->sin6_addr);
 			break;
-		}
 		default:
 			/* caller wants default server name, but
 			 * address family isn't recognized. */
@@ -1058,7 +1061,7 @@ call_allocate(struct rpc_task *task)
 
 	dprintk("RPC: %5u rpc_buffer allocation failed\n", task->tk_pid);
 
-	if (RPC_IS_ASYNC(task) || !signalled()) {
+	if (RPC_IS_ASYNC(task) || !fatal_signal_pending(current)) {
 		task->tk_action = call_allocate;
 		rpc_delay(task, HZ>>4);
 		return;
@@ -1172,6 +1175,9 @@ call_bind_status(struct rpc_task *task)
 			status = -EOPNOTSUPP;
 			break;
 		}
+		if (task->tk_rebind_retry == 0)
+			break;
+		task->tk_rebind_retry--;
 		rpc_delay(task, 3*HZ);
 		goto retry_timeout;
 	case -ETIMEDOUT:
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index c652e4cc9fe9..9a80a922c527 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -16,6 +16,7 @@
 
 #include <linux/types.h>
 #include <linux/socket.h>
+#include <linux/un.h>
 #include <linux/in.h>
 #include <linux/in6.h>
 #include <linux/kernel.h>
@@ -32,6 +33,8 @@
 # define RPCDBG_FACILITY	RPCDBG_BIND
 #endif
 
+#define RPCBIND_SOCK_PATHNAME	"/var/run/rpcbind.sock"
+
 #define RPCBIND_PROGRAM		(100000u)
 #define RPCBIND_PORT		(111u)
 
@@ -158,20 +161,69 @@ static void rpcb_map_release(void *data)
 	kfree(map);
 }
 
-static const struct sockaddr_in rpcb_inaddr_loopback = {
-	.sin_family		= AF_INET,
-	.sin_addr.s_addr	= htonl(INADDR_LOOPBACK),
-	.sin_port		= htons(RPCBIND_PORT),
-};
+/*
+ * Returns zero on success, otherwise a negative errno value
+ * is returned.
+ */
+static int rpcb_create_local_unix(void)
+{
+	static const struct sockaddr_un rpcb_localaddr_rpcbind = {
+		.sun_family		= AF_LOCAL,
+		.sun_path		= RPCBIND_SOCK_PATHNAME,
+	};
+	struct rpc_create_args args = {
+		.net		= &init_net,
+		.protocol	= XPRT_TRANSPORT_LOCAL,
+		.address	= (struct sockaddr *)&rpcb_localaddr_rpcbind,
+		.addrsize	= sizeof(rpcb_localaddr_rpcbind),
+		.servername	= "localhost",
+		.program	= &rpcb_program,
+		.version	= RPCBVERS_2,
+		.authflavor	= RPC_AUTH_NULL,
+	};
+	struct rpc_clnt *clnt, *clnt4;
+	int result = 0;
+
+	/*
+	 * Because we requested an RPC PING at transport creation time,
+	 * this works only if the user space portmapper is rpcbind, and
+	 * it's listening on AF_LOCAL on the named socket.
+	 */
+	clnt = rpc_create(&args);
+	if (IS_ERR(clnt)) {
+		dprintk("RPC:       failed to create AF_LOCAL rpcbind "
+				"client (errno %ld).\n", PTR_ERR(clnt));
+		result = -PTR_ERR(clnt);
+		goto out;
+	}
+
+	clnt4 = rpc_bind_new_program(clnt, &rpcb_program, RPCBVERS_4);
+	if (IS_ERR(clnt4)) {
+		dprintk("RPC:       failed to bind second program to "
+				"rpcbind v4 client (errno %ld).\n",
+				PTR_ERR(clnt4));
+		clnt4 = NULL;
+	}
+
+	/* Protected by rpcb_create_local_mutex */
+	rpcb_local_clnt = clnt;
+	rpcb_local_clnt4 = clnt4;
 
-static DEFINE_MUTEX(rpcb_create_local_mutex);
+out:
+	return result;
+}
 
 /*
  * Returns zero on success, otherwise a negative errno value
  * is returned.
  */
-static int rpcb_create_local(void)
+static int rpcb_create_local_net(void)
 {
+	static const struct sockaddr_in rpcb_inaddr_loopback = {
+		.sin_family		= AF_INET,
+		.sin_addr.s_addr	= htonl(INADDR_LOOPBACK),
+		.sin_port		= htons(RPCBIND_PORT),
+	};
 	struct rpc_create_args args = {
 		.net		= &init_net,
 		.protocol	= XPRT_TRANSPORT_TCP,
@@ -186,13 +238,6 @@ static int rpcb_create_local(void)
 	struct rpc_clnt *clnt, *clnt4;
 	int result = 0;
 
-	if (rpcb_local_clnt)
-		return result;
-
-	mutex_lock(&rpcb_create_local_mutex);
-	if (rpcb_local_clnt)
-		goto out;
-
 	clnt = rpc_create(&args);
 	if (IS_ERR(clnt)) {
 		dprintk("RPC:       failed to create local rpcbind "
@@ -214,10 +259,34 @@ static int rpcb_create_local(void)
 		clnt4 = NULL;
 	}
 
+	/* Protected by rpcb_create_local_mutex */
 	rpcb_local_clnt = clnt;
 	rpcb_local_clnt4 = clnt4;
 
 out:
+	return result;
+}
+
+/*
+ * Returns zero on success, otherwise a negative errno value
+ * is returned.
+ */
+static int rpcb_create_local(void)
+{
+	static DEFINE_MUTEX(rpcb_create_local_mutex);
+	int result = 0;
+
+	if (rpcb_local_clnt)
+		return result;
+
+	mutex_lock(&rpcb_create_local_mutex);
+	if (rpcb_local_clnt)
+		goto out;
+
+	if (rpcb_create_local_unix() != 0)
+		result = rpcb_create_local_net();
+
+out:
 	mutex_unlock(&rpcb_create_local_mutex);
 	return result;
 }
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 6b43ee7221d5..a27406b1654f 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -792,6 +792,7 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta
 	/* Initialize retry counters */
 	task->tk_garb_retry = 2;
 	task->tk_cred_retry = 2;
+	task->tk_rebind_retry = 2;
 
 	task->tk_priority = task_setup_data->priority - RPC_PRIORITY_LOW;
 	task->tk_owner = current->tgid;
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 08e05a8ce025..2b90292e9505 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -942,6 +942,8 @@ static void svc_unregister(const struct svc_serv *serv)
 			if (progp->pg_vers[i]->vs_hidden)
 				continue;
 
+			dprintk("svc: attempting to unregister %sv%u\n",
+				progp->pg_name, i);
 			__svc_unregister(progp->pg_prog, i, progp->pg_name);
 		}
 	}
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index b7d435c3f19e..af04f779ce9f 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -387,6 +387,33 @@ static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr,
 	return len;
 }
 
+static int svc_partial_recvfrom(struct svc_rqst *rqstp,
+				struct kvec *iov, int nr,
+				int buflen, unsigned int base)
+{
+	size_t save_iovlen;
+	void __user *save_iovbase;
+	unsigned int i;
+	int ret;
+
+	if (base == 0)
+		return svc_recvfrom(rqstp, iov, nr, buflen);
+
+	for (i = 0; i < nr; i++) {
+		if (iov[i].iov_len > base)
+			break;
+		base -= iov[i].iov_len;
+	}
+	save_iovlen = iov[i].iov_len;
+	save_iovbase = iov[i].iov_base;
+	iov[i].iov_len -= base;
+	iov[i].iov_base += base;
+	ret = svc_recvfrom(rqstp, &iov[i], nr - i, buflen);
+	iov[i].iov_len = save_iovlen;
+	iov[i].iov_base = save_iovbase;
+	return ret;
+}
+
 /*
  * Set socket snd and rcv buffer lengths
  */
@@ -409,7 +436,6 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
 	lock_sock(sock->sk);
 	sock->sk->sk_sndbuf = snd * 2;
 	sock->sk->sk_rcvbuf = rcv * 2;
-	sock->sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK;
 	sock->sk->sk_write_space(sock->sk);
 	release_sock(sock->sk);
 #endif
@@ -884,6 +910,56 @@ failed:
 	return NULL;
 }
 
+static unsigned int svc_tcp_restore_pages(struct svc_sock *svsk, struct svc_rqst *rqstp)
+{
+	unsigned int i, len, npages;
+
+	if (svsk->sk_tcplen <= sizeof(rpc_fraghdr))
+		return 0;
+	len = svsk->sk_tcplen - sizeof(rpc_fraghdr);
+	npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	for (i = 0; i < npages; i++) {
+		if (rqstp->rq_pages[i] != NULL)
+			put_page(rqstp->rq_pages[i]);
+		BUG_ON(svsk->sk_pages[i] == NULL);
+		rqstp->rq_pages[i] = svsk->sk_pages[i];
+		svsk->sk_pages[i] = NULL;
+	}
+	rqstp->rq_arg.head[0].iov_base = page_address(rqstp->rq_pages[0]);
+	return len;
+}
+
+static void svc_tcp_save_pages(struct svc_sock *svsk, struct svc_rqst *rqstp)
+{
+	unsigned int i, len, npages;
+
+	if (svsk->sk_tcplen <= sizeof(rpc_fraghdr))
+		return;
+	len = svsk->sk_tcplen - sizeof(rpc_fraghdr);
+	npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	for (i = 0; i < npages; i++) {
+		svsk->sk_pages[i] = rqstp->rq_pages[i];
+		rqstp->rq_pages[i] = NULL;
+	}
+}
+
+static void svc_tcp_clear_pages(struct svc_sock *svsk)
+{
+	unsigned int i, len, npages;
+
+	if (svsk->sk_tcplen <= sizeof(rpc_fraghdr))
+		goto out;
+	len = svsk->sk_tcplen - sizeof(rpc_fraghdr);
+	npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	for (i = 0; i < npages; i++) {
+		BUG_ON(svsk->sk_pages[i] == NULL);
+		put_page(svsk->sk_pages[i]);
+		svsk->sk_pages[i] = NULL;
+	}
+out:
+	svsk->sk_tcplen = 0;
+}
+
 /*
  * Receive data.
  * If we haven't gotten the record length yet, get the next four bytes.
@@ -893,31 +969,15 @@ failed:
 static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
 {
 	struct svc_serv	*serv = svsk->sk_xprt.xpt_server;
+	unsigned int want;
 	int len;
 
-	if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags))
-		/* sndbuf needs to have room for one request
-		 * per thread, otherwise we can stall even when the
-		 * network isn't a bottleneck.
-		 *
-		 * We count all threads rather than threads in a
-		 * particular pool, which provides an upper bound
-		 * on the number of threads which will access the socket.
-		 *
-		 * rcvbuf just needs to be able to hold a few requests.
-		 * Normally they will be removed from the queue
-		 * as soon a a complete request arrives.
-		 */
-		svc_sock_setbufsize(svsk->sk_sock,
-				    (serv->sv_nrthreads+3) * serv->sv_max_mesg,
-				    3 * serv->sv_max_mesg);
-
 	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 
 	if (svsk->sk_tcplen < sizeof(rpc_fraghdr)) {
-		int		want = sizeof(rpc_fraghdr) - svsk->sk_tcplen;
 		struct kvec	iov;
 
+		want = sizeof(rpc_fraghdr) - svsk->sk_tcplen;
 		iov.iov_base = ((char *) &svsk->sk_reclen) + svsk->sk_tcplen;
 		iov.iov_len  = want;
 		if ((len = svc_recvfrom(rqstp, &iov, 1, want)) < 0)
@@ -927,7 +987,7 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
 		if (len < want) {
 			dprintk("svc: short recvfrom while reading record "
 				"length (%d of %d)\n", len, want);
-			goto err_again; /* record header not complete */
+			return -EAGAIN;
 		}
 
 		svsk->sk_reclen = ntohl(svsk->sk_reclen);
@@ -954,83 +1014,75 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
 		}
 	}
 
-	/* Check whether enough data is available */
-	len = svc_recv_available(svsk);
-	if (len < 0)
-		goto error;
+	if (svsk->sk_reclen < 8)
+		goto err_delete; /* client is nuts. */
 
-	if (len < svsk->sk_reclen) {
-		dprintk("svc: incomplete TCP record (%d of %d)\n",
-			len, svsk->sk_reclen);
-		goto err_again;	/* record not complete */
-	}
 	len = svsk->sk_reclen;
-	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 
 	return len;
- error:
-	if (len == -EAGAIN)
-		dprintk("RPC: TCP recv_record got EAGAIN\n");
+error:
+	dprintk("RPC: TCP recv_record got %d\n", len);
 	return len;
- err_delete:
+err_delete:
 	set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
- err_again:
 	return -EAGAIN;
 }
 
-static int svc_process_calldir(struct svc_sock *svsk, struct svc_rqst *rqstp,
-			       struct rpc_rqst **reqpp, struct kvec *vec)
+static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
 {
+	struct rpc_xprt *bc_xprt = svsk->sk_xprt.xpt_bc_xprt;
 	struct rpc_rqst *req = NULL;
-	u32 *p;
-	u32 xid;
-	u32 calldir;
-	int len;
-
-	len = svc_recvfrom(rqstp, vec, 1, 8);
-	if (len < 0)
-		goto error;
+	struct kvec *src, *dst;
+	__be32 *p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
+	__be32 xid;
+	__be32 calldir;
 
-	p = (u32 *)rqstp->rq_arg.head[0].iov_base;
 	xid = *p++;
 	calldir = *p;
 
-	if (calldir == 0) {
-		/* REQUEST is the most common case */
-		vec[0] = rqstp->rq_arg.head[0];
-	} else {
-		/* REPLY */
-		struct rpc_xprt *bc_xprt = svsk->sk_xprt.xpt_bc_xprt;
-
-		if (bc_xprt)
-			req = xprt_lookup_rqst(bc_xprt, xid);
-
-		if (!req) {
-			printk(KERN_NOTICE
-				"%s: Got unrecognized reply: "
-				"calldir 0x%x xpt_bc_xprt %p xid %08x\n",
-				__func__, ntohl(calldir),
-				bc_xprt, xid);
-			vec[0] = rqstp->rq_arg.head[0];
-			goto out;
-		}
+	if (bc_xprt)
+		req = xprt_lookup_rqst(bc_xprt, xid);
 
-		memcpy(&req->rq_private_buf, &req->rq_rcv_buf,
-		       sizeof(struct xdr_buf));
-		/* copy the xid and call direction */
-		memcpy(req->rq_private_buf.head[0].iov_base,
-		       rqstp->rq_arg.head[0].iov_base, 8);
-		vec[0] = req->rq_private_buf.head[0];
+	if (!req) {
+		printk(KERN_NOTICE
+			"%s: Got unrecognized reply: "
+			"calldir 0x%x xpt_bc_xprt %p xid %08x\n",
+			__func__, ntohl(calldir),
+			bc_xprt, xid);
+		return -EAGAIN;
 	}
- out:
-	vec[0].iov_base += 8;
-	vec[0].iov_len -= 8;
-	len = svsk->sk_reclen - 8;
- error:
-	*reqpp = req;
-	return len;
+
+	memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf));
+	/*
+	 * XXX!: cheating for now!  Only copying HEAD.
+	 * But we know this is good enough for now (in fact, for any
+	 * callback reply in the forseeable future).
+	 */
+	dst = &req->rq_private_buf.head[0];
+	src = &rqstp->rq_arg.head[0];
+	if (dst->iov_len < src->iov_len)
+		return -EAGAIN; /* whatever; just giving up. */
+	memcpy(dst->iov_base, src->iov_base, src->iov_len);
+	xprt_complete_rqst(req->rq_task, svsk->sk_reclen);
+	rqstp->rq_arg.len = 0;
+	return 0;
 }
 
+static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len)
+{
+	int i = 0;
+	int t = 0;
+
+	while (t < len) {
+		vec[i].iov_base = page_address(pages[i]);
+		vec[i].iov_len = PAGE_SIZE;
+		i++;
+		t += PAGE_SIZE;
+	}
+	return i;
+}
+
+
 /*
  * Receive data from a TCP socket.
  */
@@ -1041,8 +1093,10 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 	struct svc_serv	*serv = svsk->sk_xprt.xpt_server;
 	int		len;
 	struct kvec *vec;
-	int pnum, vlen;
-	struct rpc_rqst *req = NULL;
+	unsigned int want, base;
+	__be32 *p;
+	__be32 calldir;
+	int pnum;
 
 	dprintk("svc: tcp_recv %p data %d conn %d close %d\n",
 		svsk, test_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags),
@@ -1053,87 +1107,73 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 	if (len < 0)
 		goto error;
 
+	base = svc_tcp_restore_pages(svsk, rqstp);
+	want = svsk->sk_reclen - base;
+
 	vec = rqstp->rq_vec;
-	vec[0] = rqstp->rq_arg.head[0];
-	vlen = PAGE_SIZE;
 
-	/*
-	 * We have enough data for the whole tcp record. Let's try and read the
-	 * first 8 bytes to get the xid and the call direction. We can use this
-	 * to figure out if this is a call or a reply to a callback. If
-	 * sk_reclen is < 8 (xid and calldir), then this is a malformed packet.
-	 * In that case, don't bother with the calldir and just read the data.
-	 * It will be rejected in svc_process.
-	 */
-	if (len >= 8) {
-		len = svc_process_calldir(svsk, rqstp, &req, vec);
-		if (len < 0)
-			goto err_again;
-		vlen -= 8;
-	}
+	pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0],
+						svsk->sk_reclen);
 
-	pnum = 1;
-	while (vlen < len) {
-		vec[pnum].iov_base = (req) ?
-			page_address(req->rq_private_buf.pages[pnum - 1]) :
-			page_address(rqstp->rq_pages[pnum]);
-		vec[pnum].iov_len = PAGE_SIZE;
-		pnum++;
-		vlen += PAGE_SIZE;
-	}
 	rqstp->rq_respages = &rqstp->rq_pages[pnum];
 
 	/* Now receive data */
-	len = svc_recvfrom(rqstp, vec, pnum, len);
-	if (len < 0)
-		goto err_again;
-
-	/*
-	 * Account for the 8 bytes we read earlier
-	 */
-	len += 8;
-
-	if (req) {
-		xprt_complete_rqst(req->rq_task, len);
-		len = 0;
-		goto out;
+	len = svc_partial_recvfrom(rqstp, vec, pnum, want, base);
+	if (len >= 0)
+		svsk->sk_tcplen += len;
+	if (len != want) {
+		if (len < 0 && len != -EAGAIN)
+			goto err_other;
+		svc_tcp_save_pages(svsk, rqstp);
+		dprintk("svc: incomplete TCP record (%d of %d)\n",
+			svsk->sk_tcplen, svsk->sk_reclen);
+		goto err_noclose;
 	}
-	dprintk("svc: TCP complete record (%d bytes)\n", len);
-	rqstp->rq_arg.len = len;
+
+	rqstp->rq_arg.len = svsk->sk_reclen;
 	rqstp->rq_arg.page_base = 0;
-	if (len <= rqstp->rq_arg.head[0].iov_len) {
-		rqstp->rq_arg.head[0].iov_len = len;
+	if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len) {
+		rqstp->rq_arg.head[0].iov_len = rqstp->rq_arg.len;
 		rqstp->rq_arg.page_len = 0;
-	} else {
-		rqstp->rq_arg.page_len = len - rqstp->rq_arg.head[0].iov_len;
-	}
+	} else
+		rqstp->rq_arg.page_len = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len;
 
 	rqstp->rq_xprt_ctxt   = NULL;
 	rqstp->rq_prot	      = IPPROTO_TCP;
 
-out:
+	p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
+	calldir = p[1];
+	if (calldir)
+		len = receive_cb_reply(svsk, rqstp);
+
 	/* Reset TCP read info */
 	svsk->sk_reclen = 0;
 	svsk->sk_tcplen = 0;
+	/* If we have more data, signal svc_xprt_enqueue() to try again */
+	if (svc_recv_available(svsk) > sizeof(rpc_fraghdr))
+		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
+
+	if (len < 0)
+		goto error;
 
 	svc_xprt_copy_addrs(rqstp, &svsk->sk_xprt);
 	if (serv->sv_stats)
 		serv->sv_stats->nettcpcnt++;
 
-	return len;
+	dprintk("svc: TCP complete record (%d bytes)\n", rqstp->rq_arg.len);
+	return rqstp->rq_arg.len;
 
-err_again:
-	if (len == -EAGAIN) {
-		dprintk("RPC: TCP recvfrom got EAGAIN\n");
-		return len;
-	}
 error:
-	if (len != -EAGAIN) {
-		printk(KERN_NOTICE "%s: recvfrom returned errno %d\n",
-		       svsk->sk_xprt.xpt_server->sv_name, -len);
-		set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
-	}
+	if (len != -EAGAIN)
+		goto err_other;
+	dprintk("RPC: TCP recvfrom got EAGAIN\n");
 	return -EAGAIN;
+err_other:
+	printk(KERN_NOTICE "%s: recvfrom returned errno %d\n",
+	       svsk->sk_xprt.xpt_server->sv_name, -len);
+	set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
+err_noclose:
+	return -EAGAIN;	/* record not complete */
 }
 
 /*
@@ -1304,18 +1344,10 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
 
 		svsk->sk_reclen = 0;
 		svsk->sk_tcplen = 0;
+		memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages));
 
 		tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;
 
-		/* initialise setting must have enough space to
-		 * receive and respond to one request.
-		 * svc_tcp_recvfrom will re-adjust if necessary
-		 */
-		svc_sock_setbufsize(svsk->sk_sock,
-				    3 * svsk->sk_xprt.xpt_server->sv_max_mesg,
-				    3 * svsk->sk_xprt.xpt_server->sv_max_mesg);
-
-		set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
 		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 		if (sk->sk_state != TCP_ESTABLISHED)
 			set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
@@ -1379,8 +1411,14 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	/* Initialize the socket */
 	if (sock->type == SOCK_DGRAM)
 		svc_udp_init(svsk, serv);
-	else
+	else {
+		/* initialise setting must have enough space to
+		 * receive and respond to one request.
+		 */
+		svc_sock_setbufsize(svsk->sk_sock, 4 * serv->sv_max_mesg,
+					4 * serv->sv_max_mesg);
 		svc_tcp_init(svsk, serv);
+	}
 
 	dprintk("svc: svc_setup_socket created %p (inet %p)\n",
 				svsk, svsk->sk_sk);
@@ -1562,8 +1600,10 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt)
 
 	svc_sock_detach(xprt);
 
-	if (!test_bit(XPT_LISTENER, &xprt->xpt_flags))
+	if (!test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
+		svc_tcp_clear_pages(svsk);
 		kernel_sock_shutdown(svsk->sk_sock, SHUT_RDWR);
+	}
 }
 
 /*
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 679cd674b81d..f008c14ad34c 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -638,6 +638,25 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p)
 }
 EXPORT_SYMBOL_GPL(xdr_init_decode);
 
+/**
+ * xdr_init_decode - Initialize an xdr_stream for decoding data.
+ * @xdr: pointer to xdr_stream struct
+ * @buf: pointer to XDR buffer from which to decode data
+ * @pages: list of pages to decode into
+ * @len: length in bytes of buffer in pages
+ */
+void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
+			   struct page **pages, unsigned int len)
+{
+	memset(buf, 0, sizeof(*buf));
+	buf->pages =  pages;
+	buf->page_len =  len;
+	buf->buflen =  len;
+	buf->len = len;
+	xdr_init_decode(xdr, buf, NULL);
+}
+EXPORT_SYMBOL_GPL(xdr_init_decode_pages);
+
 static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes)
 {
 	__be32 *p = xdr->p;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index bf005d3c65ef..72abb7358933 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/types.h>
+#include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/capability.h>
@@ -28,6 +29,7 @@
 #include <linux/in.h>
 #include <linux/net.h>
 #include <linux/mm.h>
+#include <linux/un.h>
 #include <linux/udp.h>
 #include <linux/tcp.h>
 #include <linux/sunrpc/clnt.h>
@@ -45,6 +47,9 @@
 #include <net/tcp.h>
 
 #include "sunrpc.h"
+
+static void xs_close(struct rpc_xprt *xprt);
+
 /*
  * xprtsock tunables
  */
@@ -261,6 +266,11 @@ static inline struct sockaddr *xs_addr(struct rpc_xprt *xprt)
 	return (struct sockaddr *) &xprt->addr;
 }
 
+static inline struct sockaddr_un *xs_addr_un(struct rpc_xprt *xprt)
+{
+	return (struct sockaddr_un *) &xprt->addr;
+}
+
 static inline struct sockaddr_in *xs_addr_in(struct rpc_xprt *xprt)
 {
 	return (struct sockaddr_in *) &xprt->addr;
@@ -276,23 +286,34 @@ static void xs_format_common_peer_addresses(struct rpc_xprt *xprt)
 	struct sockaddr *sap = xs_addr(xprt);
 	struct sockaddr_in6 *sin6;
 	struct sockaddr_in *sin;
+	struct sockaddr_un *sun;
 	char buf[128];
 
-	(void)rpc_ntop(sap, buf, sizeof(buf));
-	xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL);
-
 	switch (sap->sa_family) {
+	case AF_LOCAL:
+		sun = xs_addr_un(xprt);
+		strlcpy(buf, sun->sun_path, sizeof(buf));
+		xprt->address_strings[RPC_DISPLAY_ADDR] =
+						kstrdup(buf, GFP_KERNEL);
+		break;
 	case AF_INET:
+		(void)rpc_ntop(sap, buf, sizeof(buf));
+		xprt->address_strings[RPC_DISPLAY_ADDR] =
+						kstrdup(buf, GFP_KERNEL);
 		sin = xs_addr_in(xprt);
 		snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr));
 		break;
 	case AF_INET6:
+		(void)rpc_ntop(sap, buf, sizeof(buf));
+		xprt->address_strings[RPC_DISPLAY_ADDR] =
+						kstrdup(buf, GFP_KERNEL);
 		sin6 = xs_addr_in6(xprt);
 		snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr);
 		break;
 	default:
 		BUG();
 	}
+
 	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
 }
 
@@ -495,6 +516,70 @@ static int xs_nospace(struct rpc_task *task)
 	return ret;
 }
 
+/*
+ * Construct a stream transport record marker in @buf.
+ */
+static inline void xs_encode_stream_record_marker(struct xdr_buf *buf)
+{
+	u32 reclen = buf->len - sizeof(rpc_fraghdr);
+	rpc_fraghdr *base = buf->head[0].iov_base;
+	*base = cpu_to_be32(RPC_LAST_STREAM_FRAGMENT | reclen);
+}
+
+/**
+ * xs_local_send_request - write an RPC request to an AF_LOCAL socket
+ * @task: RPC task that manages the state of an RPC request
+ *
+ * Return values:
+ *        0:	The request has been sent
+ *   EAGAIN:	The socket was blocked, please call again later to
+ *		complete the request
+ * ENOTCONN:	Caller needs to invoke connect logic then call again
+ *    other:	Some other error occured, the request was not sent
+ */
+static int xs_local_send_request(struct rpc_task *task)
+{
+	struct rpc_rqst *req = task->tk_rqstp;
+	struct rpc_xprt *xprt = req->rq_xprt;
+	struct sock_xprt *transport =
+				container_of(xprt, struct sock_xprt, xprt);
+	struct xdr_buf *xdr = &req->rq_snd_buf;
+	int status;
+
+	xs_encode_stream_record_marker(&req->rq_snd_buf);
+
+	xs_pktdump("packet data:",
+			req->rq_svec->iov_base, req->rq_svec->iov_len);
+
+	status = xs_sendpages(transport->sock, NULL, 0,
+						xdr, req->rq_bytes_sent);
+	dprintk("RPC:       %s(%u) = %d\n",
+			__func__, xdr->len - req->rq_bytes_sent, status);
+	if (likely(status >= 0)) {
+		req->rq_bytes_sent += status;
+		req->rq_xmit_bytes_sent += status;
+		if (likely(req->rq_bytes_sent >= req->rq_slen)) {
+			req->rq_bytes_sent = 0;
+			return 0;
+		}
+		status = -EAGAIN;
+	}
+
+	switch (status) {
+	case -EAGAIN:
+		status = xs_nospace(task);
+		break;
+	default:
+		dprintk("RPC:       sendmsg returned unrecognized error %d\n",
+			-status);
+	case -EPIPE:
+		xs_close(xprt);
+		status = -ENOTCONN;
+	}
+
+	return status;
+}
+
 /**
  * xs_udp_send_request - write an RPC request to a UDP socket
  * @task: address of RPC task that manages the state of an RPC request
@@ -574,13 +659,6 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt)
 		kernel_sock_shutdown(sock, SHUT_WR);
 }
 
-static inline void xs_encode_tcp_record_marker(struct xdr_buf *buf)
-{
-	u32 reclen = buf->len - sizeof(rpc_fraghdr);
-	rpc_fraghdr *base = buf->head[0].iov_base;
-	*base = htonl(RPC_LAST_STREAM_FRAGMENT | reclen);
-}
-
 /**
  * xs_tcp_send_request - write an RPC request to a TCP socket
  * @task: address of RPC task that manages the state of an RPC request
@@ -603,7 +681,7 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	struct xdr_buf *xdr = &req->rq_snd_buf;
 	int status;
 
-	xs_encode_tcp_record_marker(&req->rq_snd_buf);
+	xs_encode_stream_record_marker(&req->rq_snd_buf);
 
 	xs_pktdump("packet data:",
 				req->rq_svec->iov_base,
@@ -785,6 +863,88 @@ static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
 	return (struct rpc_xprt *) sk->sk_user_data;
 }
 
+static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
+{
+	struct xdr_skb_reader desc = {
+		.skb		= skb,
+		.offset		= sizeof(rpc_fraghdr),
+		.count		= skb->len - sizeof(rpc_fraghdr),
+	};
+
+	if (xdr_partial_copy_from_skb(xdr, 0, &desc, xdr_skb_read_bits) < 0)
+		return -1;
+	if (desc.count)
+		return -1;
+	return 0;
+}
+
+/**
+ * xs_local_data_ready - "data ready" callback for AF_LOCAL sockets
+ * @sk: socket with data to read
+ * @len: how much data to read
+ *
+ * Currently this assumes we can read the whole reply in a single gulp.
+ */
+static void xs_local_data_ready(struct sock *sk, int len)
+{
+	struct rpc_task *task;
+	struct rpc_xprt *xprt;
+	struct rpc_rqst *rovr;
+	struct sk_buff *skb;
+	int err, repsize, copied;
+	u32 _xid;
+	__be32 *xp;
+
+	read_lock_bh(&sk->sk_callback_lock);
+	dprintk("RPC:       %s...\n", __func__);
+	xprt = xprt_from_sock(sk);
+	if (xprt == NULL)
+		goto out;
+
+	skb = skb_recv_datagram(sk, 0, 1, &err);
+	if (skb == NULL)
+		goto out;
+
+	if (xprt->shutdown)
+		goto dropit;
+
+	repsize = skb->len - sizeof(rpc_fraghdr);
+	if (repsize < 4) {
+		dprintk("RPC:       impossible RPC reply size %d\n", repsize);
+		goto dropit;
+	}
+
+	/* Copy the XID from the skb... */
+	xp = skb_header_pointer(skb, sizeof(rpc_fraghdr), sizeof(_xid), &_xid);
+	if (xp == NULL)
+		goto dropit;
+
+	/* Look up and lock the request corresponding to the given XID */
+	spin_lock(&xprt->transport_lock);
+	rovr = xprt_lookup_rqst(xprt, *xp);
+	if (!rovr)
+		goto out_unlock;
+	task = rovr->rq_task;
+
+	copied = rovr->rq_private_buf.buflen;
+	if (copied > repsize)
+		copied = repsize;
+
+	if (xs_local_copy_to_xdr(&rovr->rq_private_buf, skb)) {
+		dprintk("RPC:       sk_buff copy failed\n");
+		goto out_unlock;
+	}
+
+	xprt_complete_rqst(task, copied);
+
+ out_unlock:
+	spin_unlock(&xprt->transport_lock);
+ dropit:
+	skb_free_datagram(sk, skb);
+ out:
+	read_unlock_bh(&sk->sk_callback_lock);
+}
+
 /**
  * xs_udp_data_ready - "data ready" callback for UDP sockets
  * @sk: socket with data to read
@@ -1344,7 +1504,6 @@ static void xs_tcp_state_change(struct sock *sk)
 	case TCP_CLOSE_WAIT:
 		/* The server initiated a shutdown of the socket */
 		xprt_force_disconnect(xprt);
-	case TCP_SYN_SENT:
 		xprt->connect_cookie++;
 	case TCP_CLOSING:
 		/*
@@ -1571,11 +1730,31 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock)
 	return err;
 }
 
+/*
+ * We don't support autobind on AF_LOCAL sockets
+ */
+static void xs_local_rpcbind(struct rpc_task *task)
+{
+	xprt_set_bound(task->tk_xprt);
+}
+
+static void xs_local_set_port(struct rpc_xprt *xprt, unsigned short port)
+{
+}
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key xs_key[2];
 static struct lock_class_key xs_slock_key[2];
 
+static inline void xs_reclassify_socketu(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+
+	BUG_ON(sock_owned_by_user(sk));
+	sock_lock_init_class_and_name(sk, "slock-AF_LOCAL-RPC",
+		&xs_slock_key[1], "sk_lock-AF_LOCAL-RPC", &xs_key[1]);
+}
+
 static inline void xs_reclassify_socket4(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
@@ -1597,6 +1776,9 @@ static inline void xs_reclassify_socket6(struct socket *sock)
 static inline void xs_reclassify_socket(int family, struct socket *sock)
 {
 	switch (family) {
+	case AF_LOCAL:
+		xs_reclassify_socketu(sock);
+		break;
 	case AF_INET:
 		xs_reclassify_socket4(sock);
 		break;
@@ -1606,6 +1788,10 @@ static inline void xs_reclassify_socket(int family, struct socket *sock)
 	}
 }
 #else
+static inline void xs_reclassify_socketu(struct socket *sock)
+{
+}
+
 static inline void xs_reclassify_socket4(struct socket *sock)
 {
 }
@@ -1644,6 +1830,94 @@ out:
 	return ERR_PTR(err);
 }
 
+static int xs_local_finish_connecting(struct rpc_xprt *xprt,
+				      struct socket *sock)
+{
+	struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
+									xprt);
+
+	if (!transport->inet) {
+		struct sock *sk = sock->sk;
+
+		write_lock_bh(&sk->sk_callback_lock);
+
+		xs_save_old_callbacks(transport, sk);
+
+		sk->sk_user_data = xprt;
+		sk->sk_data_ready = xs_local_data_ready;
+		sk->sk_write_space = xs_udp_write_space;
+		sk->sk_error_report = xs_error_report;
+		sk->sk_allocation = GFP_ATOMIC;
+
+		xprt_clear_connected(xprt);
+
+		/* Reset to new socket */
+		transport->sock = sock;
+		transport->inet = sk;
+
+		write_unlock_bh(&sk->sk_callback_lock);
+	}
+
+	/* Tell the socket layer to start connecting... */
+	xprt->stat.connect_count++;
+	xprt->stat.connect_start = jiffies;
+	return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, 0);
+}
+
+/**
+ * xs_local_setup_socket - create AF_LOCAL socket, connect to a local endpoint
+ * @xprt: RPC transport to connect
+ * @transport: socket transport to connect
+ * @create_sock: function to create a socket of the correct type
+ *
+ * Invoked by a work queue tasklet.
+ */
+static void xs_local_setup_socket(struct work_struct *work)
+{
+	struct sock_xprt *transport =
+		container_of(work, struct sock_xprt, connect_worker.work);
+	struct rpc_xprt *xprt = &transport->xprt;
+	struct socket *sock;
+	int status = -EIO;
+
+	if (xprt->shutdown)
+		goto out;
+
+	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
+	status = __sock_create(xprt->xprt_net, AF_LOCAL,
+					SOCK_STREAM, 0, &sock, 1);
+	if (status < 0) {
+		dprintk("RPC:       can't create AF_LOCAL "
+			"transport socket (%d).\n", -status);
+		goto out;
+	}
+	xs_reclassify_socketu(sock);
+
+	dprintk("RPC:       worker connecting xprt %p via AF_LOCAL to %s\n",
+			xprt, xprt->address_strings[RPC_DISPLAY_ADDR]);
+
+	status = xs_local_finish_connecting(xprt, sock);
+	switch (status) {
+	case 0:
+		dprintk("RPC:       xprt %p connected to %s\n",
+				xprt, xprt->address_strings[RPC_DISPLAY_ADDR]);
+		xprt_set_connected(xprt);
+		break;
+	case -ENOENT:
+		dprintk("RPC:       xprt %p: socket %s does not exist\n",
+				xprt, xprt->address_strings[RPC_DISPLAY_ADDR]);
+		break;
+	default:
+		printk(KERN_ERR "%s: unhandled error (%d) connecting to %s\n",
+				__func__, -status,
+				xprt->address_strings[RPC_DISPLAY_ADDR]);
+	}
+
+out:
+	xprt_clear_connecting(xprt);
+	xprt_wake_pending_tasks(xprt, status);
+}
+
 static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 {
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
@@ -1758,6 +2032,7 @@ static void xs_tcp_reuse_connection(struct sock_xprt *transport)
 static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 {
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+	int ret = -ENOTCONN;
 
 	if (!transport->inet) {
 		struct sock *sk = sock->sk;
@@ -1789,12 +2064,22 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 	}
 
 	if (!xprt_bound(xprt))
-		return -ENOTCONN;
+		goto out;
 
 	/* Tell the socket layer to start connecting... */
 	xprt->stat.connect_count++;
 	xprt->stat.connect_start = jiffies;
-	return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK);
+	ret = kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK);
+	switch (ret) {
+	case 0:
+	case -EINPROGRESS:
+		/* SYN_SENT! */
+		xprt->connect_cookie++;
+		if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
+			xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
+	}
+out:
+	return ret;
 }
 
 /**
@@ -1917,6 +2202,32 @@ static void xs_connect(struct rpc_task *task)
 }
 
 /**
+ * xs_local_print_stats - display AF_LOCAL socket-specifc stats
+ * @xprt: rpc_xprt struct containing statistics
+ * @seq: output file
+ *
+ */
+static void xs_local_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
+{
+	long idle_time = 0;
+
+	if (xprt_connected(xprt))
+		idle_time = (long)(jiffies - xprt->last_used) / HZ;
+
+	seq_printf(seq, "\txprt:\tlocal %lu %lu %lu %ld %lu %lu %lu "
+			"%llu %llu\n",
+			xprt->stat.bind_count,
+			xprt->stat.connect_count,
+			xprt->stat.connect_time,
+			idle_time,
+			xprt->stat.sends,
+			xprt->stat.recvs,
+			xprt->stat.bad_xids,
+			xprt->stat.req_u,
+			xprt->stat.bklog_u);
+}
+
+/**
  * xs_udp_print_stats - display UDP socket-specifc stats
  * @xprt: rpc_xprt struct containing statistics
  * @seq: output file
@@ -2014,10 +2325,7 @@ static int bc_sendto(struct rpc_rqst *req)
 	unsigned long headoff;
 	unsigned long tailoff;
 
-	/*
-	 * Set up the rpc header and record marker stuff
-	 */
-	xs_encode_tcp_record_marker(xbufp);
+	xs_encode_stream_record_marker(xbufp);
 
 	tailoff = (unsigned long)xbufp->tail[0].iov_base & ~PAGE_MASK;
 	headoff = (unsigned long)xbufp->head[0].iov_base & ~PAGE_MASK;
@@ -2089,6 +2397,21 @@ static void bc_destroy(struct rpc_xprt *xprt)
 {
 }
 
+static struct rpc_xprt_ops xs_local_ops = {
+	.reserve_xprt		= xprt_reserve_xprt,
+	.release_xprt		= xs_tcp_release_xprt,
+	.rpcbind		= xs_local_rpcbind,
+	.set_port		= xs_local_set_port,
+	.connect		= xs_connect,
+	.buf_alloc		= rpc_malloc,
+	.buf_free		= rpc_free,
+	.send_request		= xs_local_send_request,
+	.set_retrans_timeout	= xprt_set_retrans_timeout_def,
+	.close			= xs_close,
+	.destroy		= xs_destroy,
+	.print_stats		= xs_local_print_stats,
+};
+
 static struct rpc_xprt_ops xs_udp_ops = {
 	.set_buffer_size	= xs_udp_set_buffer_size,
 	.reserve_xprt		= xprt_reserve_xprt_cong,
@@ -2150,6 +2473,8 @@ static int xs_init_anyaddr(const int family, struct sockaddr *sap)
 	};
 
 	switch (family) {
+	case AF_LOCAL:
+		break;
 	case AF_INET:
 		memcpy(sap, &sin, sizeof(sin));
 		break;
@@ -2197,6 +2522,70 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args,
 	return xprt;
 }
 
+static const struct rpc_timeout xs_local_default_timeout = {
+	.to_initval = 10 * HZ,
+	.to_maxval = 10 * HZ,
+	.to_retries = 2,
+};
+
+/**
+ * xs_setup_local - Set up transport to use an AF_LOCAL socket
+ * @args: rpc transport creation arguments
+ *
+ * AF_LOCAL is a "tpi_cots_ord" transport, just like TCP
+ */
+static struct rpc_xprt *xs_setup_local(struct xprt_create *args)
+{
+	struct sockaddr_un *sun = (struct sockaddr_un *)args->dstaddr;
+	struct sock_xprt *transport;
+	struct rpc_xprt *xprt;
+	struct rpc_xprt *ret;
+
+	xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries);
+	if (IS_ERR(xprt))
+		return xprt;
+	transport = container_of(xprt, struct sock_xprt, xprt);
+
+	xprt->prot = 0;
+	xprt->tsh_size = sizeof(rpc_fraghdr) / sizeof(u32);
+	xprt->max_payload = RPC_MAX_FRAGMENT_SIZE;
+
+	xprt->bind_timeout = XS_BIND_TO;
+	xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
+	xprt->idle_timeout = XS_IDLE_DISC_TO;
+
+	xprt->ops = &xs_local_ops;
+	xprt->timeout = &xs_local_default_timeout;
+
+	switch (sun->sun_family) {
+	case AF_LOCAL:
+		if (sun->sun_path[0] != '/') {
+			dprintk("RPC:       bad AF_LOCAL address: %s\n",
+					sun->sun_path);
+			ret = ERR_PTR(-EINVAL);
+			goto out_err;
+		}
+		xprt_set_bound(xprt);
+		INIT_DELAYED_WORK(&transport->connect_worker,
+					xs_local_setup_socket);
+		xs_format_peer_addresses(xprt, "local", RPCBIND_NETID_LOCAL);
+		break;
+	default:
+		ret = ERR_PTR(-EAFNOSUPPORT);
+		goto out_err;
+	}
+
+	dprintk("RPC:       set up xprt to %s via AF_LOCAL\n",
+			xprt->address_strings[RPC_DISPLAY_ADDR]);
+
+	if (try_module_get(THIS_MODULE))
+		return xprt;
+	ret = ERR_PTR(-EINVAL);
+out_err:
+	xprt_free(xprt);
+	return ret;
+}
+
 static const struct rpc_timeout xs_udp_default_timeout = {
 	.to_initval = 5 * HZ,
 	.to_maxval = 30 * HZ,
@@ -2438,6 +2827,14 @@ out_err:
 	return ret;
 }
 
+static struct xprt_class	xs_local_transport = {
+	.list		= LIST_HEAD_INIT(xs_local_transport.list),
+	.name		= "named UNIX socket",
+	.owner		= THIS_MODULE,
+	.ident		= XPRT_TRANSPORT_LOCAL,
+	.setup		= xs_setup_local,
+};
+
 static struct xprt_class	xs_udp_transport = {
 	.list		= LIST_HEAD_INIT(xs_udp_transport.list),
 	.name		= "udp",
@@ -2473,6 +2870,7 @@ int init_socket_xprt(void)
 		sunrpc_table_header = register_sysctl_table(sunrpc_table);
 #endif
 
+	xprt_register_transport(&xs_local_transport);
 	xprt_register_transport(&xs_udp_transport);
 	xprt_register_transport(&xs_tcp_transport);
 	xprt_register_transport(&xs_bc_tcp_transport);
@@ -2493,6 +2891,7 @@ void cleanup_socket_xprt(void)
 	}
 #endif
 
+	xprt_unregister_transport(&xs_local_transport);
 	xprt_unregister_transport(&xs_udp_transport);
 	xprt_unregister_transport(&xs_tcp_transport);
 	xprt_unregister_transport(&xs_bc_tcp_transport);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ec83f413a7ed..98fa8eb6cc4b 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3406,12 +3406,12 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 	i = 0;
 	if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) {
 		nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) {
-			if (request->ssids[i].ssid_len > IEEE80211_MAX_SSID_LEN) {
+			if (nla_len(attr) > IEEE80211_MAX_SSID_LEN) {
 				err = -EINVAL;
 				goto out_free;
 			}
-			memcpy(request->ssids[i].ssid, nla_data(attr), nla_len(attr));
 			request->ssids[i].ssid_len = nla_len(attr);
+			memcpy(request->ssids[i].ssid, nla_data(attr), nla_len(attr));
 			i++;
 		}
 	}
@@ -3572,14 +3572,13 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) {
 		nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS],
 				    tmp) {
-			if (request->ssids[i].ssid_len >
-			    IEEE80211_MAX_SSID_LEN) {
+			if (nla_len(attr) > IEEE80211_MAX_SSID_LEN) {
 				err = -EINVAL;
 				goto out_free;
 			}
+			request->ssids[i].ssid_len = nla_len(attr);
 			memcpy(request->ssids[i].ssid, nla_data(attr),
 			       nla_len(attr));
-			request->ssids[i].ssid_len = nla_len(attr);
 			i++;
 		}
 	}
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 73a441d237b5..7a6c67667d70 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -267,13 +267,35 @@ static bool is_bss(struct cfg80211_bss *a,
 	return memcmp(ssidie + 2, ssid, ssid_len) == 0;
 }
 
+static bool is_mesh_bss(struct cfg80211_bss *a)
+{
+	const u8 *ie;
+
+	if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability))
+		return false;
+
+	ie = cfg80211_find_ie(WLAN_EID_MESH_ID,
+			      a->information_elements,
+			      a->len_information_elements);
+	if (!ie)
+		return false;
+
+	ie = cfg80211_find_ie(WLAN_EID_MESH_CONFIG,
+			      a->information_elements,
+			      a->len_information_elements);
+	if (!ie)
+		return false;
+
+	return true;
+}
+
 static bool is_mesh(struct cfg80211_bss *a,
 		    const u8 *meshid, size_t meshidlen,
 		    const u8 *meshcfg)
 {
 	const u8 *ie;
 
-	if (!WLAN_CAPABILITY_IS_MBSS(a->capability))
+	if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability))
 		return false;
 
 	ie = cfg80211_find_ie(WLAN_EID_MESH_ID,
@@ -311,7 +333,7 @@ static int cmp_bss(struct cfg80211_bss *a,
 	if (a->channel != b->channel)
 		return b->channel->center_freq - a->channel->center_freq;
 
-	if (WLAN_CAPABILITY_IS_MBSS(a->capability | b->capability)) {
+	if (is_mesh_bss(a) && is_mesh_bss(b)) {
 		r = cmp_ies(WLAN_EID_MESH_ID,
 			    a->information_elements,
 			    a->len_information_elements,
@@ -457,7 +479,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 		    struct cfg80211_internal_bss *res)
 {
 	struct cfg80211_internal_bss *found = NULL;
-	const u8 *meshid, *meshcfg;
 
 	/*
 	 * The reference to "res" is donated to this function.
@@ -470,22 +491,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 
 	res->ts = jiffies;
 
-	if (WLAN_CAPABILITY_IS_MBSS(res->pub.capability)) {
-		/* must be mesh, verify */
-		meshid = cfg80211_find_ie(WLAN_EID_MESH_ID,
-					  res->pub.information_elements,
-					  res->pub.len_information_elements);
-		meshcfg = cfg80211_find_ie(WLAN_EID_MESH_CONFIG,
-					   res->pub.information_elements,
-					   res->pub.len_information_elements);
-		if (!meshid || !meshcfg ||
-		    meshcfg[1] != sizeof(struct ieee80211_meshconf_ie)) {
-			/* bogus mesh */
-			kref_put(&res->ref, bss_release);
-			return NULL;
-		}
-	}
-
 	spin_lock_bh(&dev->bss_lock);
 
 	found = rb_find_bss(dev, res);
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
index 47f1b8638df9..b11ea692bd7d 100644
--- a/net/xfrm/xfrm_replay.c
+++ b/net/xfrm/xfrm_replay.c
@@ -265,7 +265,7 @@ static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq)
 			bitnr = bitnr & 0x1F;
 			replay_esn->bmp[nr] |= (1U << bitnr);
 		} else {
-			nr = replay_esn->replay_window >> 5;
+			nr = (replay_esn->replay_window - 1) >> 5;
 			for (i = 0; i <= nr; i++)
 				replay_esn->bmp[i] = 0;
 
@@ -471,7 +471,7 @@ static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq)
 			bitnr = bitnr & 0x1F;
 			replay_esn->bmp[nr] |= (1U << bitnr);
 		} else {
-			nr = replay_esn->replay_window >> 5;
+			nr = (replay_esn->replay_window - 1) >> 5;
 			for (i = 0; i <= nr; i++)
 				replay_esn->bmp[i] = 0;
 
diff --git a/scripts/Makefile.asm-generic b/scripts/Makefile.asm-generic
index 490122c3e2aa..40caf3c26cd5 100644
--- a/scripts/Makefile.asm-generic
+++ b/scripts/Makefile.asm-generic
@@ -17,6 +17,7 @@ quiet_cmd_wrap = WRAP    $@
 cmd_wrap = echo "\#include <asm-generic/$*.h>" >$@
 
 all: $(patsubst %, $(obj)/%, $(generic-y))
+	@:
 
 $(obj)/%.h:
 	$(call cmd,wrap)
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 8657f99bfb2b..b0aa2c680593 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -1943,6 +1943,11 @@ sub process {
 			WARN("LINUX_VERSION_CODE should be avoided, code should be for the version to which it is merged\n" . $herecurr);
 		}
 
+# check for uses of printk_ratelimit
+		if ($line =~ /\bprintk_ratelimit\s*\(/) {
+			WARN("Prefer printk_ratelimited or pr_<level>_ratelimited to printk_ratelimit\n" . $herecurr);
+		}
+
 # printk should use KERN_* levels.  Note that follow on printk's on the
 # same line do not need a level, so we use the current block context
 # to try and find and validate the current printk.  In summary the current
diff --git a/scripts/depmod.sh b/scripts/depmod.sh
new file mode 100755
index 000000000000..3b029cba2baf
--- /dev/null
+++ b/scripts/depmod.sh
@@ -0,0 +1,48 @@
+#!/bin/sh
+#
+# A depmod wrapper used by the toplevel Makefile
+
+if test $# -ne 2; then
+	echo "Usage: $0 /sbin/depmod <kernelrelease>" >&2
+	exit 1
+fi
+DEPMOD=$1
+KERNELRELEASE=$2
+
+if ! "$DEPMOD" -V 2>/dev/null | grep -q module-init-tools; then
+	echo "Warning: you may need to install module-init-tools" >&2
+	echo "See http://www.codemonkey.org.uk/docs/post-halloween-2.6.txt" >&2
+	sleep 1
+fi
+
+if ! test -r System.map -a -x "$DEPMOD"; then
+	exit 0
+fi
+# older versions of depmod require the version string to start with three
+# numbers, so we cheat with a symlink here
+depmod_hack_needed=true
+mkdir -p .tmp_depmod/lib/modules/$KERNELRELEASE
+if "$DEPMOD" -b .tmp_depmod $KERNELRELEASE 2>/dev/null; then
+	if test -e .tmp_depmod/lib/modules/$KERNELRELEASE/modules.dep -o \
+		-e .tmp_depmod/lib/modules/$KERNELRELEASE/modules.dep.bin; then
+		depmod_hack_needed=false
+	fi
+fi
+if $depmod_hack_needed; then
+	symlink="$INSTALL_MOD_PATH/lib/modules/99.98.$KERNELRELEASE"
+	ln -s "$KERNELRELEASE" "$symlink"
+	KERNELRELEASE=99.98.$KERNELRELEASE
+fi
+
+set -- -ae -F System.map
+if test -n "$INSTALL_MOD_PATH"; then
+	set -- "$@" -b "$INSTALL_MOD_PATH"
+fi
+"$DEPMOD" "$@" "$KERNELRELEASE"
+ret=$?
+
+if $depmod_hack_needed; then
+	rm -f "$symlink"
+fi
+
+exit $ret
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index 4be60364a405..f40a6af6bf40 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -43,6 +43,7 @@
 #undef ELF_R_INFO
 #undef Elf_r_info
 #undef ELF_ST_BIND
+#undef ELF_ST_TYPE
 #undef fn_ELF_R_SYM
 #undef fn_ELF_R_INFO
 #undef uint_t
@@ -76,6 +77,7 @@
 # define ELF_R_INFO		ELF64_R_INFO
 # define Elf_r_info		Elf64_r_info
 # define ELF_ST_BIND		ELF64_ST_BIND
+# define ELF_ST_TYPE		ELF64_ST_TYPE
 # define fn_ELF_R_SYM		fn_ELF64_R_SYM
 # define fn_ELF_R_INFO		fn_ELF64_R_INFO
 # define uint_t			uint64_t
@@ -108,6 +110,7 @@
 # define ELF_R_INFO		ELF32_R_INFO
 # define Elf_r_info		Elf32_r_info
 # define ELF_ST_BIND		ELF32_ST_BIND
+# define ELF_ST_TYPE		ELF32_ST_TYPE
 # define fn_ELF_R_SYM		fn_ELF32_R_SYM
 # define fn_ELF_R_INFO		fn_ELF32_R_INFO
 # define uint_t			uint32_t
@@ -427,6 +430,11 @@ static unsigned find_secsym_ndx(unsigned const txtndx,
 		if (txtndx == w2(symp->st_shndx)
 			/* avoid STB_WEAK */
 		    && (STB_LOCAL == st_bind || STB_GLOBAL == st_bind)) {
+			/* function symbols on ARM have quirks, avoid them */
+			if (w2(ehdr->e_machine) == EM_ARM
+			    && ELF_ST_TYPE(symp->st_info) == STT_FUNC)
+				continue;
+
 			*recvalp = _w(symp->st_value);
 			return symp - sym0;
 		}
diff --git a/scripts/selinux/README b/scripts/selinux/README
index a936315ba2c8..4d020ecb7524 100644
--- a/scripts/selinux/README
+++ b/scripts/selinux/README
@@ -1,2 +1,2 @@
-Please see Documentation/SELinux.txt for information on
+Please see Documentation/security/SELinux.txt for information on
 installing a dummy SELinux policy.
diff --git a/scripts/tags.sh b/scripts/tags.sh
index bd6185d529cf..75c5d24f1993 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -132,7 +132,7 @@ exuberant()
 	--regex-asm='/^ENTRY\(([^)]*)\).*/\1/'                  \
 	--regex-c='/^SYSCALL_DEFINE[[:digit:]]?\(([^,)]*).*/sys_\1/' \
 	--regex-c++='/^TRACE_EVENT\(([^,)]*).*/trace_\1/'		\
-	--regex-c++='/^DEFINE_EVENT\(([^,)]*).*/trace_\1/'
+	--regex-c++='/^DEFINE_EVENT\([^,)]*, *([^,)]*).*/trace_\1/'
 
 	all_kconfigs | xargs $1 -a                              \
 	--langdef=kconfig --language-force=kconfig              \
@@ -152,7 +152,9 @@ emacs()
 {
 	all_sources | xargs $1 -a                               \
 	--regex='/^ENTRY(\([^)]*\)).*/\1/'                      \
-	--regex='/^SYSCALL_DEFINE[0-9]?(\([^,)]*\).*/sys_\1/'
+	--regex='/^SYSCALL_DEFINE[0-9]?(\([^,)]*\).*/sys_\1/'   \
+	--regex='/^TRACE_EVENT(\([^,)]*\).*/trace_\1/'		\
+	--regex='/^DEFINE_EVENT([^,)]*, *\([^,)]*\).*/trace_\1/'
 
 	all_kconfigs | xargs $1 -a                              \
 	--regex='/^[ \t]*\(\(menu\)*config\)[ \t]+\([a-zA-Z0-9_]+\)/\3/'
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index ae3a698415e6..3d2fd141dff7 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -593,7 +593,8 @@ static int apparmor_setprocattr(struct task_struct *task, char *name,
 			sa.aad.op = OP_SETPROCATTR;
 			sa.aad.info = name;
 			sa.aad.error = -EINVAL;
-			return aa_audit(AUDIT_APPARMOR_DENIED, NULL, GFP_KERNEL,
+			return aa_audit(AUDIT_APPARMOR_DENIED,
+					__aa_current_profile(), GFP_KERNEL,
 					&sa, NULL);
 		}
 	} else if (strcmp(name, "exec") == 0) {
@@ -611,7 +612,7 @@ static int apparmor_setprocattr(struct task_struct *task, char *name,
 static int apparmor_task_setrlimit(struct task_struct *task,
 		unsigned int resource, struct rlimit *new_rlim)
 {
-	struct aa_profile *profile = aa_current_profile();
+	struct aa_profile *profile = __aa_current_profile();
 	int error = 0;
 
 	if (!unconfined(profile))
diff --git a/security/apparmor/match.c b/security/apparmor/match.c
index 06d764ccbbe5..94de6b4907c8 100644
--- a/security/apparmor/match.c
+++ b/security/apparmor/match.c
@@ -194,7 +194,7 @@ void aa_dfa_free_kref(struct kref *kref)
  * @flags: flags controlling what type of accept tables are acceptable
  *
  * Unpack a dfa that has been serialized.  To find information on the dfa
- * format look in Documentation/apparmor.txt
+ * format look in Documentation/security/apparmor.txt
  * Assumes the dfa @blob stream has been aligned on a 8 byte boundary
  *
  * Returns: an unpacked dfa ready for matching or ERR_PTR on failure
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index e33aaf7e5744..d6d9a57b5652 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -12,8 +12,8 @@
  * published by the Free Software Foundation, version 2 of the
  * License.
  *
- * AppArmor uses a serialized binary format for loading policy.
- * To find policy format documentation look in Documentation/apparmor.txt
+ * AppArmor uses a serialized binary format for loading policy. To find
+ * policy format documentation look in Documentation/security/apparmor.txt
  * All policy is validated before it is used.
  */
 
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index cd1f779fa51d..1be68269e1c2 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -474,17 +474,11 @@ struct cgroup_subsys devices_subsys = {
 	.subsys_id = devices_subsys_id,
 };
 
-int devcgroup_inode_permission(struct inode *inode, int mask)
+int __devcgroup_inode_permission(struct inode *inode, int mask)
 {
 	struct dev_cgroup *dev_cgroup;
 	struct dev_whitelist_item *wh;
 
-	dev_t device = inode->i_rdev;
-	if (!device)
-		return 0;
-	if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode))
-		return 0;
-
 	rcu_read_lock();
 
 	dev_cgroup = task_devcgroup(current);
diff --git a/security/keys/encrypted.c b/security/keys/encrypted.c
index 69907a58a683..b1cba5bf0a5e 100644
--- a/security/keys/encrypted.c
+++ b/security/keys/encrypted.c
@@ -8,7 +8,7 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation, version 2 of the License.
  *
- * See Documentation/keys-trusted-encrypted.txt
+ * See Documentation/security/keys-trusted-encrypted.txt
  */
 
 #include <linux/uaccess.h>
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index b18a71745901..82465328c39b 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -8,7 +8,7 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  *
- * See Documentation/keys-request-key.txt
+ * See Documentation/security/keys-request-key.txt
  */
 
 #include <linux/module.h>
@@ -71,9 +71,8 @@ EXPORT_SYMBOL(complete_request_key);
  * This is called in context of freshly forked kthread before kernel_execve(),
  * so we can simply install the desired session_keyring at this point.
  */
-static int umh_keys_init(struct subprocess_info *info)
+static int umh_keys_init(struct subprocess_info *info, struct cred *cred)
 {
-	struct cred *cred = (struct cred*)current_cred();
 	struct key *keyring = info->data;
 
 	return install_session_keyring_to_cred(cred, keyring);
@@ -470,7 +469,7 @@ static struct key *construct_key_and_link(struct key_type *type,
 	} else if (ret == -EINPROGRESS) {
 		ret = 0;
 	} else {
-		key = ERR_PTR(ret);
+		goto couldnt_alloc_key;
 	}
 
 	key_put(dest_keyring);
@@ -480,6 +479,7 @@ static struct key *construct_key_and_link(struct key_type *type,
 construction_failed:
 	key_negate_and_link(key, key_negative_timeout, NULL, NULL);
 	key_put(key);
+couldnt_alloc_key:
 	key_put(dest_keyring);
 	kleave(" = %d", ret);
 	return ERR_PTR(ret);
diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
index f6337c9082eb..6cff37529b80 100644
--- a/security/keys/request_key_auth.c
+++ b/security/keys/request_key_auth.c
@@ -8,7 +8,7 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  *
- * See Documentation/keys-request-key.txt
+ * See Documentation/security/keys-request-key.txt
  */
 
 #include <linux/module.h>
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index c99b9368368c..0c33e2ea1f3c 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -8,7 +8,7 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation, version 2 of the License.
  *
- * See Documentation/keys-trusted-encrypted.txt
+ * See Documentation/security/keys-trusted-encrypted.txt
  */
 
 #include <linux/uaccess.h>
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index a0d38459d650..20219ef5439a 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -1476,7 +1476,6 @@ static int inode_has_perm(const struct cred *cred,
 			  unsigned flags)
 {
 	struct inode_security_struct *isec;
-	struct common_audit_data ad;
 	u32 sid;
 
 	validate_creds(cred);
@@ -1487,15 +1486,21 @@ static int inode_has_perm(const struct cred *cred,
 	sid = cred_sid(cred);
 	isec = inode->i_security;
 
-	if (!adp) {
-		adp = &ad;
-		COMMON_AUDIT_DATA_INIT(&ad, INODE);
-		ad.u.inode = inode;
-	}
-
 	return avc_has_perm_flags(sid, isec->sid, isec->sclass, perms, adp, flags);
 }
 
+static int inode_has_perm_noadp(const struct cred *cred,
+				struct inode *inode,
+				u32 perms,
+				unsigned flags)
+{
+	struct common_audit_data ad;
+
+	COMMON_AUDIT_DATA_INIT(&ad, INODE);
+	ad.u.inode = inode;
+	return inode_has_perm(cred, inode, perms, &ad, flags);
+}
+
 /* Same as inode_has_perm, but pass explicit audit data containing
    the dentry to help the auditing code to more easily generate the
    pathname if needed. */
@@ -2122,8 +2127,8 @@ static inline void flush_unauthorized_files(const struct cred *cred,
 						struct tty_file_private, list);
 			file = file_priv->file;
 			inode = file->f_path.dentry->d_inode;
-			if (inode_has_perm(cred, inode,
-					   FILE__READ | FILE__WRITE, NULL, 0)) {
+			if (inode_has_perm_noadp(cred, inode,
+					   FILE__READ | FILE__WRITE, 0)) {
 				drop_tty = 1;
 			}
 		}
@@ -3228,7 +3233,7 @@ static int selinux_dentry_open(struct file *file, const struct cred *cred)
 	 * new inode label or new policy.
 	 * This check is not redundant - do not remove.
 	 */
-	return inode_has_perm(cred, inode, open_file_to_av(file), NULL, 0);
+	return inode_has_perm_noadp(cred, inode, open_file_to_av(file), 0);
 }
 
 /* task security operations */
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 77d44138864f..35459340019e 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -29,6 +29,7 @@
 #include <linux/audit.h>
 #include <linux/uaccess.h>
 #include <linux/kobject.h>
+#include <linux/ctype.h>
 
 /* selinuxfs pseudo filesystem for exporting the security policy API.
    Based on the proc code and the fs/nfsd/nfsctl.c code. */
@@ -751,6 +752,14 @@ out:
 	return length;
 }
 
+static inline int hexcode_to_int(int code) {
+	if (code == '\0' || !isxdigit(code))
+		return -1;
+	if (isdigit(code))
+		return code - '0';
+	return tolower(code) - 'a' + 10;
+}
+
 static ssize_t sel_write_create(struct file *file, char *buf, size_t size)
 {
 	char *scon = NULL, *tcon = NULL;
@@ -785,8 +794,34 @@ static ssize_t sel_write_create(struct file *file, char *buf, size_t size)
 	nargs = sscanf(buf, "%s %s %hu %s", scon, tcon, &tclass, namebuf);
 	if (nargs < 3 || nargs > 4)
 		goto out;
-	if (nargs == 4)
+	if (nargs == 4) {
+		/*
+		 * If and when the name of new object to be queried contains
+		 * either whitespace or multibyte characters, they shall be
+		 * encoded based on the percentage-encoding rule.
+		 * If not encoded, the sscanf logic picks up only left-half
+		 * of the supplied name; splitted by a whitespace unexpectedly.
+		 */
+		char   *r, *w;
+		int     c1, c2;
+
+		r = w = namebuf;
+		do {
+			c1 = *r++;
+			if (c1 == '+')
+				c1 = ' ';
+			else if (c1 == '%') {
+				if ((c1 = hexcode_to_int(*r++)) < 0)
+					goto out;
+				if ((c2 = hexcode_to_int(*r++)) < 0)
+					goto out;
+				c1 = (c1 << 4) | c2;
+			}
+			*w++ = c1;
+		} while (c1 != '\0');
+
 		objname = namebuf;
+	}
 
 	length = security_context_to_sid(scon, strlen(scon) + 1, &ssid);
 	if (length)
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index 102e9ec1b77a..d246aca3f4fb 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -3222,6 +3222,9 @@ static int filename_trans_write(struct policydb *p, void *fp)
 	__le32 buf[1];
 	int rc;
 
+	if (p->policyvers < POLICYDB_VERSION_FILENAME_TRANS)
+		return 0;
+
 	nel = 0;
 	rc = hashtab_map(p->filename_trans, hashtab_cnt, &nel);
 	if (rc)
diff --git a/security/tomoyo/mount.c b/security/tomoyo/mount.c
index 162a864dba24..9fc2e15841c9 100644
--- a/security/tomoyo/mount.c
+++ b/security/tomoyo/mount.c
@@ -138,7 +138,7 @@ static int tomoyo_mount_acl(struct tomoyo_request_info *r, char *dev_name,
 	}
 	if (need_dev) {
 		/* Get mount point or device file. */
-		if (kern_path(dev_name, LOOKUP_FOLLOW, &path)) {
+		if (!dev_name || kern_path(dev_name, LOOKUP_FOLLOW, &path)) {
 			error = -ENOENT;
 			goto out;
 		}
diff --git a/sound/core/control.c b/sound/core/control.c
index 5d98194bcad5..f8c5be464510 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -704,13 +704,12 @@ static int snd_ctl_elem_list(struct snd_card *card,
 	struct snd_ctl_elem_list list;
 	struct snd_kcontrol *kctl;
 	struct snd_ctl_elem_id *dst, *id;
-	unsigned int offset, space, first, jidx;
+	unsigned int offset, space, jidx;
 	
 	if (copy_from_user(&list, _list, sizeof(list)))
 		return -EFAULT;
 	offset = list.offset;
 	space = list.space;
-	first = 0;
 	/* try limit maximum space */
 	if (space > 16384)
 		return -ENOMEM;
diff --git a/sound/core/init.c b/sound/core/init.c
index 30ecad41403c..2c041bb36ab3 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -342,7 +342,6 @@ static const struct file_operations snd_shutdown_f_ops =
 int snd_card_disconnect(struct snd_card *card)
 {
 	struct snd_monitor_file *mfile;
-	struct file *file;
 	int err;
 
 	if (!card)
@@ -366,8 +365,6 @@ int snd_card_disconnect(struct snd_card *card)
 	
 	spin_lock(&card->files_lock);
 	list_for_each_entry(mfile, &card->files_list, list) {
-		file = mfile->file;
-
 		/* it's critical part, use endless loop */
 		/* we have no room to fail */
 		mfile->disconnected_f_op = mfile->file->f_op;
diff --git a/sound/core/misc.c b/sound/core/misc.c
index 2c41825c836e..eb9fe2e1d291 100644
--- a/sound/core/misc.c
+++ b/sound/core/misc.c
@@ -58,26 +58,6 @@ static const char *sanity_file_name(const char *path)
 	else
 		return path;
 }
-
-/* print file and line with a certain printk prefix */
-static int print_snd_pfx(unsigned int level, const char *path, int line,
-			 const char *format)
-{
-	const char *file = sanity_file_name(path);
-	char tmp[] = "<0>";
-	const char *pfx = level ? KERN_DEBUG : KERN_DEFAULT;
-	int ret = 0;
-
-	if (format[0] == '<' && format[2] == '>') {
-		tmp[1] = format[1];
-		pfx = tmp;
-		ret = 1;
-	}
-	printk("%sALSA %s:%d: ", pfx, file, line);
-	return ret;
-}
-#else
-#define print_snd_pfx(level, path, line, format)	0
 #endif
 
 #if defined(CONFIG_SND_DEBUG) || defined(CONFIG_SND_VERBOSE_PRINTK)
@@ -85,15 +65,29 @@ void __snd_printk(unsigned int level, const char *path, int line,
 		  const char *format, ...)
 {
 	va_list args;
-	
+#ifdef CONFIG_SND_VERBOSE_PRINTK
+	struct va_format vaf;
+	char verbose_fmt[] = KERN_DEFAULT "ALSA %s:%d %pV";
+#endif
+
 #ifdef CONFIG_SND_DEBUG	
 	if (debug < level)
 		return;
 #endif
+
 	va_start(args, format);
-	if (print_snd_pfx(level, path, line, format))
-		format += 3; /* skip the printk level-prefix */
+#ifdef CONFIG_SND_VERBOSE_PRINTK
+	vaf.fmt = format;
+	vaf.va = &args;
+	if (format[0] == '<' && format[2] == '>') {
+		memcpy(verbose_fmt, format, 3);
+		vaf.fmt = format + 3;
+	} else if (level)
+		memcpy(verbose_fmt, KERN_DEBUG, 3);
+	printk(verbose_fmt, sanity_file_name(path), line, &vaf);
+#else
 	vprintk(format, args);
+#endif
 	va_end(args);
 }
 EXPORT_SYMBOL_GPL(__snd_printk);
diff --git a/sound/core/oss/linear.c b/sound/core/oss/linear.c
index 13b3f6f49fae..2045697f449d 100644
--- a/sound/core/oss/linear.c
+++ b/sound/core/oss/linear.c
@@ -90,11 +90,8 @@ static snd_pcm_sframes_t linear_transfer(struct snd_pcm_plugin *plugin,
 			       struct snd_pcm_plugin_channel *dst_channels,
 			       snd_pcm_uframes_t frames)
 {
-	struct linear_priv *data;
-
 	if (snd_BUG_ON(!plugin || !src_channels || !dst_channels))
 		return -ENXIO;
-	data = (struct linear_priv *)plugin->extra_data;
 	if (frames == 0)
 		return 0;
 #ifdef CONFIG_SND_DEBUG
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index abfeff1611ce..f1341308beda 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -1756,8 +1756,18 @@ static int wait_for_avail(struct snd_pcm_substream *substream,
 	wait_queue_t wait;
 	int err = 0;
 	snd_pcm_uframes_t avail = 0;
-	long tout;
-
+	long wait_time, tout;
+
+	if (runtime->no_period_wakeup)
+		wait_time = MAX_SCHEDULE_TIMEOUT;
+	else {
+		wait_time = 10;
+		if (runtime->rate) {
+			long t = runtime->period_size * 2 / runtime->rate;
+			wait_time = max(t, wait_time);
+		}
+		wait_time = msecs_to_jiffies(wait_time * 1000);
+	}
 	init_waitqueue_entry(&wait, current);
 	add_wait_queue(&runtime->tsleep, &wait);
 	for (;;) {
@@ -1765,9 +1775,8 @@ static int wait_for_avail(struct snd_pcm_substream *substream,
 			err = -ERESTARTSYS;
 			break;
 		}
-		set_current_state(TASK_INTERRUPTIBLE);
 		snd_pcm_stream_unlock_irq(substream);
-		tout = schedule_timeout(msecs_to_jiffies(10000));
+		tout = schedule_timeout_interruptible(wait_time);
 		snd_pcm_stream_lock_irq(substream);
 		switch (runtime->status->state) {
 		case SNDRV_PCM_STATE_SUSPENDED:
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 1a07750f3836..1c6be91dfb98 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -1481,11 +1481,20 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream,
 			break; /* all drained */
 		init_waitqueue_entry(&wait, current);
 		add_wait_queue(&to_check->sleep, &wait);
-		set_current_state(TASK_INTERRUPTIBLE);
 		snd_pcm_stream_unlock_irq(substream);
 		up_read(&snd_pcm_link_rwsem);
 		snd_power_unlock(card);
-		tout = schedule_timeout(10 * HZ);
+		if (runtime->no_period_wakeup)
+			tout = MAX_SCHEDULE_TIMEOUT;
+		else {
+			tout = 10;
+			if (runtime->rate) {
+				long t = runtime->period_size * 2 / runtime->rate;
+				tout = max(t, tout);
+			}
+			tout = msecs_to_jiffies(tout * 1000);
+		}
+		tout = schedule_timeout_interruptible(tout);
 		snd_power_lock(card);
 		down_read(&snd_pcm_link_rwsem);
 		snd_pcm_stream_lock_irq(substream);
@@ -1518,13 +1527,11 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream,
 static int snd_pcm_drop(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime;
-	struct snd_card *card;
 	int result = 0;
 	
 	if (PCM_RUNTIME_CHECK(substream))
 		return -ENXIO;
 	runtime = substream->runtime;
-	card = substream->pcm->card;
 
 	if (runtime->status->state == SNDRV_PCM_STATE_OPEN ||
 	    runtime->status->state == SNDRV_PCM_STATE_DISCONNECTED ||
@@ -2056,7 +2063,6 @@ static int snd_pcm_open_file(struct file *file,
 {
 	struct snd_pcm_file *pcm_file;
 	struct snd_pcm_substream *substream;
-	struct snd_pcm_str *str;
 	int err;
 
 	if (rpcm_file)
@@ -2073,7 +2079,6 @@ static int snd_pcm_open_file(struct file *file,
 	}
 	pcm_file->substream = substream;
 	if (substream->ref_count == 1) {
-		str = substream->pstr;
 		substream->file = pcm_file;
 		substream->pcm_release = pcm_release_private;
 	}
@@ -3015,11 +3020,9 @@ static const struct vm_operations_struct snd_pcm_vm_ops_status =
 static int snd_pcm_mmap_status(struct snd_pcm_substream *substream, struct file *file,
 			       struct vm_area_struct *area)
 {
-	struct snd_pcm_runtime *runtime;
 	long size;
 	if (!(area->vm_flags & VM_READ))
 		return -EINVAL;
-	runtime = substream->runtime;
 	size = area->vm_end - area->vm_start;
 	if (size != PAGE_ALIGN(sizeof(struct snd_pcm_mmap_status)))
 		return -EINVAL;
@@ -3054,11 +3057,9 @@ static const struct vm_operations_struct snd_pcm_vm_ops_control =
 static int snd_pcm_mmap_control(struct snd_pcm_substream *substream, struct file *file,
 				struct vm_area_struct *area)
 {
-	struct snd_pcm_runtime *runtime;
 	long size;
 	if (!(area->vm_flags & VM_READ))
 		return -EINVAL;
-	runtime = substream->runtime;
 	size = area->vm_end - area->vm_start;
 	if (size != PAGE_ALIGN(sizeof(struct snd_pcm_mmap_control)))
 		return -EINVAL;
diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c
index e7a8e9e4edb2..f9077361c119 100644
--- a/sound/core/seq/seq_queue.c
+++ b/sound/core/seq/seq_queue.c
@@ -467,13 +467,11 @@ int snd_seq_queue_timer_open(int queueid)
 int snd_seq_queue_timer_close(int queueid)
 {
 	struct snd_seq_queue *queue;
-	struct snd_seq_timer *tmr;
 	int result = 0;
 
 	queue = queueptr(queueid);
 	if (queue == NULL)
 		return -EINVAL;
-	tmr = queue->timer;
 	snd_seq_timer_close(queue);
 	queuefree(queue);
 	return result;
diff --git a/sound/firewire/isight.c b/sound/firewire/isight.c
index 86ee16ca365e..440030818db7 100644
--- a/sound/firewire/isight.c
+++ b/sound/firewire/isight.c
@@ -209,6 +209,7 @@ static void isight_packet(struct fw_iso_context *context, u32 cycle,
 		isight->packet_index = -1;
 		return;
 	}
+	fw_iso_context_queue_flush(isight->context);
 
 	if (++index >= QUEUE_LENGTH)
 		index = 0;
diff --git a/sound/pci/asihpi/asihpi.c b/sound/pci/asihpi/asihpi.c
index 2ca6f4f85b41..e3569bdd3b64 100644
--- a/sound/pci/asihpi/asihpi.c
+++ b/sound/pci/asihpi/asihpi.c
@@ -27,7 +27,6 @@
 #include "hpioctl.h"
 
 #include <linux/pci.h>
-#include <linux/version.h>
 #include <linux/init.h>
 #include <linux/jiffies.h>
 #include <linux/slab.h>
diff --git a/sound/pci/asihpi/hpidspcd.c b/sound/pci/asihpi/hpidspcd.c
index fb311d8c05bf..5c6ea113d219 100644
--- a/sound/pci/asihpi/hpidspcd.c
+++ b/sound/pci/asihpi/hpidspcd.c
@@ -60,7 +60,7 @@ struct code_header {
 	    HPI_VER_MINOR(HPI_VER) * 100 + HPI_VER_RELEASE(HPI_VER)))
 
 /***********************************************************************/
-#include "linux/pci.h"
+#include <linux/pci.h>
 /*-------------------------------------------------------------------*/
 short hpi_dsp_code_open(u32 adapter, struct dsp_code *ps_dsp_code,
 	u32 *pos_error_code)
diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c
index 5e619a84da06..15f0161ce4a2 100644
--- a/sound/pci/emu10k1/emu10k1_main.c
+++ b/sound/pci/emu10k1/emu10k1_main.c
@@ -1440,6 +1440,14 @@ static struct snd_emu_chip_details emu_chip_details[] = {
 	 .ca0102_chip = 1,
 	 .spk71 = 1,
 	 .emu_model = EMU_MODEL_EMU0404}, /* EMU 0404 */
+	/* EMU0404 PCIe */
+	{.vendor = 0x1102, .device = 0x0008, .subsystem = 0x40051102,
+	 .driver = "Audigy2", .name = "E-mu 0404 PCIe [MAEM8984]",
+	 .id = "EMU0404",
+	 .emu10k2_chip = 1,
+	 .ca0108_chip = 1,
+	 .spk71 = 1,
+	 .emu_model = EMU_MODEL_EMU0404}, /* EMU 0404 PCIe ver_03 */
 	/* Note that all E-mu cards require kernel 2.6 or newer. */
 	{.vendor = 0x1102, .device = 0x0008,
 	 .driver = "Audigy2", .name = "SB Audigy 2 Value [Unknown]",
diff --git a/sound/pci/fm801.c b/sound/pci/fm801.c
index eacd4901a308..a7ec7030cf87 100644
--- a/sound/pci/fm801.c
+++ b/sound/pci/fm801.c
@@ -1234,9 +1234,12 @@ static int __devinit snd_fm801_create(struct snd_card *card,
 	sprintf(chip->tea.bus_info, "PCI:%s", pci_name(pci));
 	if ((tea575x_tuner & TUNER_TYPE_MASK) > 0 &&
 	    (tea575x_tuner & TUNER_TYPE_MASK) < 4) {
-		if (snd_tea575x_init(&chip->tea))
+		if (snd_tea575x_init(&chip->tea)) {
 			snd_printk(KERN_ERR "TEA575x radio not found\n");
-	} else if ((tea575x_tuner & TUNER_TYPE_MASK) == 0)
+			snd_fm801_free(chip);
+			return -ENODEV;
+		}
+	} else if ((tea575x_tuner & TUNER_TYPE_MASK) == 0) {
 		/* autodetect tuner connection */
 		for (tea575x_tuner = 1; tea575x_tuner <= 3; tea575x_tuner++) {
 			chip->tea575x_tuner = tea575x_tuner;
@@ -1246,6 +1249,12 @@ static int __devinit snd_fm801_create(struct snd_card *card,
 				break;
 			}
 		}
+		if (tea575x_tuner == 4) {
+			snd_printk(KERN_ERR "TEA575x radio not found\n");
+			snd_fm801_free(chip);
+			return -ENODEV;
+		}
+	}
 	strlcpy(chip->tea.card, snd_fm801_tea575x_gpios[(tea575x_tuner & TUNER_TYPE_MASK) - 1].name, sizeof(chip->tea.card));
 #endif
 
diff --git a/sound/pci/hda/hda_beep.h b/sound/pci/hda/hda_beep.h
index f1de1bac042c..55f0647458c7 100644
--- a/sound/pci/hda/hda_beep.h
+++ b/sound/pci/hda/hda_beep.h
@@ -50,7 +50,12 @@ int snd_hda_enable_beep_device(struct hda_codec *codec, int enable);
 int snd_hda_attach_beep_device(struct hda_codec *codec, int nid);
 void snd_hda_detach_beep_device(struct hda_codec *codec);
 #else
-#define snd_hda_attach_beep_device(...)		0
-#define snd_hda_detach_beep_device(...)
+static inline int snd_hda_attach_beep_device(struct hda_codec *codec, int nid)
+{
+	return 0;
+}
+static inline void snd_hda_detach_beep_device(struct hda_codec *codec)
+{
+}
 #endif
 #endif
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index 8edd998509f7..45b4a8d70e08 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -4719,7 +4719,7 @@ int snd_hda_parse_pin_def_config(struct hda_codec *codec,
 			   cfg->dig_out_pins[0], cfg->dig_out_pins[1]);
 	snd_printd("   inputs:");
 	for (i = 0; i < cfg->num_inputs; i++) {
-		snd_printdd(" %s=0x%x",
+		snd_printd(" %s=0x%x",
 			    hda_get_autocfg_input_label(codec, cfg, i),
 			    cfg->inputs[i].pin);
 	}
diff --git a/sound/pci/hda/hda_eld.c b/sound/pci/hda/hda_eld.c
index 74b0560289c0..b05f7be9dc1b 100644
--- a/sound/pci/hda/hda_eld.c
+++ b/sound/pci/hda/hda_eld.c
@@ -312,23 +312,6 @@ out_fail:
 	return -EINVAL;
 }
 
-static int hdmi_eld_valid(struct hda_codec *codec, hda_nid_t nid)
-{
-	int eldv;
-	int present;
-
-	present = snd_hda_pin_sense(codec, nid);
-	eldv    = (present & AC_PINSENSE_ELDV);
-	present = (present & AC_PINSENSE_PRESENCE);
-
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-	printk(KERN_INFO "HDMI: sink_present = %d, eld_valid = %d\n",
-			!!present, !!eldv);
-#endif
-
-	return eldv && present;
-}
-
 int snd_hdmi_get_eld_size(struct hda_codec *codec, hda_nid_t nid)
 {
 	return snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_HDMI_DIP_SIZE,
@@ -343,7 +326,7 @@ int snd_hdmi_get_eld(struct hdmi_eld *eld,
 	int size;
 	unsigned char *buf;
 
-	if (!hdmi_eld_valid(codec, nid))
+	if (!eld->eld_valid)
 		return -ENOENT;
 
 	size = snd_hdmi_get_eld_size(codec, nid);
@@ -477,6 +460,8 @@ static void hdmi_print_eld_info(struct snd_info_entry *entry,
 
 	snd_iprintf(buffer, "monitor_present\t\t%d\n", e->monitor_present);
 	snd_iprintf(buffer, "eld_valid\t\t%d\n", e->eld_valid);
+	if (!e->eld_valid)
+		return;
 	snd_iprintf(buffer, "monitor_name\t\t%s\n", e->monitor_name);
 	snd_iprintf(buffer, "connection_type\t\t%s\n",
 				eld_connection_type_names[e->conn_type]);
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 43a036716d25..486f6deb3eee 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -391,6 +391,7 @@ struct azx {
 
 	/* chip type specific */
 	int driver_type;
+	unsigned int driver_caps;
 	int playback_streams;
 	int playback_index_offset;
 	int capture_streams;
@@ -464,6 +465,34 @@ enum {
 	AZX_NUM_DRIVERS, /* keep this as last entry */
 };
 
+/* driver quirks (capabilities) */
+/* bits 0-7 are used for indicating driver type */
+#define AZX_DCAPS_NO_TCSEL	(1 << 8)	/* No Intel TCSEL bit */
+#define AZX_DCAPS_NO_MSI	(1 << 9)	/* No MSI support */
+#define AZX_DCAPS_ATI_SNOOP	(1 << 10)	/* ATI snoop enable */
+#define AZX_DCAPS_NVIDIA_SNOOP	(1 << 11)	/* Nvidia snoop enable */
+#define AZX_DCAPS_SCH_SNOOP	(1 << 12)	/* SCH/PCH snoop enable */
+#define AZX_DCAPS_RIRB_DELAY	(1 << 13)	/* Long delay in read loop */
+#define AZX_DCAPS_RIRB_PRE_DELAY (1 << 14)	/* Put a delay before read */
+#define AZX_DCAPS_CTX_WORKAROUND (1 << 15)	/* X-Fi workaround */
+#define AZX_DCAPS_POSFIX_LPIB	(1 << 16)	/* Use LPIB as default */
+#define AZX_DCAPS_POSFIX_VIA	(1 << 17)	/* Use VIACOMBO as default */
+#define AZX_DCAPS_NO_64BIT	(1 << 18)	/* No 64bit address */
+#define AZX_DCAPS_SYNC_WRITE	(1 << 19)	/* sync each cmd write */
+
+/* quirks for ATI SB / AMD Hudson */
+#define AZX_DCAPS_PRESET_ATI_SB \
+	(AZX_DCAPS_ATI_SNOOP | AZX_DCAPS_NO_TCSEL | \
+	 AZX_DCAPS_SYNC_WRITE | AZX_DCAPS_POSFIX_LPIB)
+
+/* quirks for ATI/AMD HDMI */
+#define AZX_DCAPS_PRESET_ATI_HDMI \
+	(AZX_DCAPS_NO_TCSEL | AZX_DCAPS_SYNC_WRITE | AZX_DCAPS_POSFIX_LPIB)
+
+/* quirks for Nvidia */
+#define AZX_DCAPS_PRESET_NVIDIA \
+	(AZX_DCAPS_NVIDIA_SNOOP | AZX_DCAPS_RIRB_DELAY | AZX_DCAPS_NO_MSI)
+
 static char *driver_short_names[] __devinitdata = {
 	[AZX_DRIVER_ICH] = "HDA Intel",
 	[AZX_DRIVER_PCH] = "HDA Intel PCH",
@@ -566,7 +595,7 @@ static void azx_init_cmd_io(struct azx *chip)
 	/* reset the rirb hw write pointer */
 	azx_writew(chip, RIRBWP, ICH6_RIRBWP_RST);
 	/* set N=1, get RIRB response interrupt for new entry */
-	if (chip->driver_type == AZX_DRIVER_CTX)
+	if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND)
 		azx_writew(chip, RINTCNT, 0xc0);
 	else
 		azx_writew(chip, RINTCNT, 1);
@@ -1056,19 +1085,24 @@ static void azx_init_pci(struct azx *chip)
 	 * codecs.
 	 * The PCI register TCSEL is defined in the Intel manuals.
 	 */
-	if (chip->driver_type != AZX_DRIVER_ATI &&
-	    chip->driver_type != AZX_DRIVER_ATIHDMI)
+	if (!(chip->driver_caps & AZX_DCAPS_NO_TCSEL)) {
+		snd_printdd(SFX "Clearing TCSEL\n");
 		update_pci_byte(chip->pci, ICH6_PCIREG_TCSEL, 0x07, 0);
+	}
 
-	switch (chip->driver_type) {
-	case AZX_DRIVER_ATI:
-		/* For ATI SB450 azalia HD audio, we need to enable snoop */
+	/* For ATI SB450/600/700/800/900 and AMD Hudson azalia HD audio,
+	 * we need to enable snoop.
+	 */
+	if (chip->driver_caps & AZX_DCAPS_ATI_SNOOP) {
+		snd_printdd(SFX "Enabling ATI snoop\n");
 		update_pci_byte(chip->pci,
 				ATI_SB450_HDAUDIO_MISC_CNTR2_ADDR, 
 				0x07, ATI_SB450_HDAUDIO_ENABLE_SNOOP);
-		break;
-	case AZX_DRIVER_NVIDIA:
-		/* For NVIDIA HDA, enable snoop */
+	}
+
+	/* For NVIDIA HDA, enable snoop */
+	if (chip->driver_caps & AZX_DCAPS_NVIDIA_SNOOP) {
+		snd_printdd(SFX "Enabling Nvidia snoop\n");
 		update_pci_byte(chip->pci,
 				NVIDIA_HDA_TRANSREG_ADDR,
 				0x0f, NVIDIA_HDA_ENABLE_COHBITS);
@@ -1078,9 +1112,10 @@ static void azx_init_pci(struct azx *chip)
 		update_pci_byte(chip->pci,
 				NVIDIA_HDA_OSTRM_COH,
 				0x01, NVIDIA_HDA_ENABLE_COHBIT);
-		break;
-	case AZX_DRIVER_SCH:
-	case AZX_DRIVER_PCH:
+	}
+
+	/* Enable SCH/PCH snoop if needed */
+	if (chip->driver_caps & AZX_DCAPS_SCH_SNOOP) {
 		pci_read_config_word(chip->pci, INTEL_SCH_HDA_DEVC, &snoop);
 		if (snoop & INTEL_SCH_HDA_DEVC_NOSNOOP) {
 			pci_write_config_word(chip->pci, INTEL_SCH_HDA_DEVC,
@@ -1091,14 +1126,6 @@ static void azx_init_pci(struct azx *chip)
 				(snoop & INTEL_SCH_HDA_DEVC_NOSNOOP)
 				? "Failed" : "OK");
 		}
-		break;
-	default:
-		/* AMD Hudson needs the similar snoop, as it seems... */
-		if (chip->pci->vendor == PCI_VENDOR_ID_AMD)
-			update_pci_byte(chip->pci,
-				ATI_SB450_HDAUDIO_MISC_CNTR2_ADDR,
-				0x07, ATI_SB450_HDAUDIO_ENABLE_SNOOP);
-		break;
         }
 }
 
@@ -1152,7 +1179,7 @@ static irqreturn_t azx_interrupt(int irq, void *dev_id)
 	status = azx_readb(chip, RIRBSTS);
 	if (status & RIRB_INT_MASK) {
 		if (status & RIRB_INT_RESPONSE) {
-			if (chip->driver_type == AZX_DRIVER_CTX)
+			if (chip->driver_caps & AZX_DCAPS_RIRB_PRE_DELAY)
 				udelay(80);
 			azx_update_rirb(chip);
 		}
@@ -1421,8 +1448,10 @@ static int __devinit azx_codec_create(struct azx *chip, const char *model)
 	if (err < 0)
 		return err;
 
-	if (chip->driver_type == AZX_DRIVER_NVIDIA)
+	if (chip->driver_caps & AZX_DCAPS_RIRB_DELAY) {
+		snd_printd(SFX "Enable delay in RIRB handling\n");
 		chip->bus->needs_damn_long_delay = 1;
+	}
 
 	codecs = 0;
 	max_slots = azx_max_codecs[chip->driver_type];
@@ -1457,9 +1486,8 @@ static int __devinit azx_codec_create(struct azx *chip, const char *model)
 	 * sequence like the pin-detection.  It seems that forcing the synced
 	 * access works around the stall.  Grrr...
 	 */
-	if (chip->pci->vendor == PCI_VENDOR_ID_AMD ||
-	    chip->pci->vendor == PCI_VENDOR_ID_ATI) {
-		snd_printk(KERN_INFO SFX "Enable sync_write for AMD chipset\n");
+	if (chip->driver_caps & AZX_DCAPS_SYNC_WRITE) {
+		snd_printd(SFX "Enable sync_write for stable communication\n");
 		chip->bus->sync_write = 1;
 		chip->bus->allow_bus_reset = 1;
 	}
@@ -1720,7 +1748,7 @@ static int azx_pcm_prepare(struct snd_pcm_substream *substream)
 
 	stream_tag = azx_dev->stream_tag;
 	/* CA-IBG chips need the playback stream starting from 1 */
-	if (chip->driver_type == AZX_DRIVER_CTX &&
+	if ((chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND) &&
 	    stream_tag > chip->capture_streams)
 		stream_tag -= chip->capture_streams;
 	return snd_hda_codec_prepare(apcm->codec, hinfo, stream_tag,
@@ -2365,20 +2393,14 @@ static int __devinit check_position_fix(struct azx *chip, int fix)
 	}
 
 	/* Check VIA/ATI HD Audio Controller exist */
-	switch (chip->driver_type) {
-	case AZX_DRIVER_VIA:
-		/* Use link position directly, avoid any transfer problem. */
+	if (chip->driver_caps & AZX_DCAPS_POSFIX_VIA) {
+		snd_printd(SFX "Using VIACOMBO position fix\n");
 		return POS_FIX_VIACOMBO;
-	case AZX_DRIVER_ATI:
-		/* ATI chipsets don't work well with position-buffer */
+	}
+	if (chip->driver_caps & AZX_DCAPS_POSFIX_LPIB) {
+		snd_printd(SFX "Using LPIB position fix\n");
 		return POS_FIX_LPIB;
-	case AZX_DRIVER_GENERIC:
-		/* AMD chipsets also don't work with position-buffer */
-		if (chip->pci->vendor == PCI_VENDOR_ID_AMD)
-			return POS_FIX_LPIB;
-		break;
 	}
-
 	return POS_FIX_AUTO;
 }
 
@@ -2460,8 +2482,8 @@ static void __devinit check_msi(struct azx *chip)
 	}
 
 	/* NVidia chipsets seem to cause troubles with MSI */
-	if (chip->driver_type == AZX_DRIVER_NVIDIA) {
-		printk(KERN_INFO "hda_intel: Disable MSI for Nvidia chipset\n");
+	if (chip->driver_caps & AZX_DCAPS_NO_MSI) {
+		printk(KERN_INFO "hda_intel: Disabling MSI\n");
 		chip->msi = 0;
 	}
 }
@@ -2471,7 +2493,7 @@ static void __devinit check_msi(struct azx *chip)
  * constructor
  */
 static int __devinit azx_create(struct snd_card *card, struct pci_dev *pci,
-				int dev, int driver_type,
+				int dev, unsigned int driver_caps,
 				struct azx **rchip)
 {
 	struct azx *chip;
@@ -2499,7 +2521,8 @@ static int __devinit azx_create(struct snd_card *card, struct pci_dev *pci,
 	chip->card = card;
 	chip->pci = pci;
 	chip->irq = -1;
-	chip->driver_type = driver_type;
+	chip->driver_caps = driver_caps;
+	chip->driver_type = driver_caps & 0xff;
 	check_msi(chip);
 	chip->dev_index = dev;
 	INIT_WORK(&chip->irq_pending_work, azx_irq_pending_work);
@@ -2563,8 +2586,7 @@ static int __devinit azx_create(struct snd_card *card, struct pci_dev *pci,
 	snd_printdd(SFX "chipset global capabilities = 0x%x\n", gcap);
 
 	/* disable SB600 64bit support for safety */
-	if ((chip->driver_type == AZX_DRIVER_ATI) ||
-	    (chip->driver_type == AZX_DRIVER_ATIHDMI)) {
+	if (chip->pci->vendor == PCI_VENDOR_ID_ATI) {
 		struct pci_dev *p_smbus;
 		p_smbus = pci_get_device(PCI_VENDOR_ID_ATI,
 					 PCI_DEVICE_ID_ATI_SBX00_SMBUS,
@@ -2574,19 +2596,13 @@ static int __devinit azx_create(struct snd_card *card, struct pci_dev *pci,
 				gcap &= ~ICH6_GCAP_64OK;
 			pci_dev_put(p_smbus);
 		}
-	} else {
-		/* FIXME: not sure whether this is really needed, but
-		 * Hudson isn't stable enough for allowing everything...
-		 * let's check later again.
-		 */
-		if (chip->pci->vendor == PCI_VENDOR_ID_AMD)
-			gcap &= ~ICH6_GCAP_64OK;
 	}
 
-	/* disable 64bit DMA address for Teradici */
-	/* it does not work with device 6549:1200 subsys e4a2:040b */
-	if (chip->driver_type == AZX_DRIVER_TERA)
+	/* disable 64bit DMA address on some devices */
+	if (chip->driver_caps & AZX_DCAPS_NO_64BIT) {
+		snd_printd(SFX "Disabling 64bit DMA\n");
 		gcap &= ~ICH6_GCAP_64OK;
+	}
 
 	/* allow 64bit DMA address if supported by H/W */
 	if ((gcap & ICH6_GCAP_64OK) && !pci_set_dma_mask(pci, DMA_BIT_MASK(64)))
@@ -2788,38 +2804,62 @@ static void __devexit azx_remove(struct pci_dev *pci)
 /* PCI IDs */
 static DEFINE_PCI_DEVICE_TABLE(azx_ids) = {
 	/* CPT */
-	{ PCI_DEVICE(0x8086, 0x1c20), .driver_data = AZX_DRIVER_PCH },
+	{ PCI_DEVICE(0x8086, 0x1c20),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_SCH_SNOOP },
 	/* PBG */
-	{ PCI_DEVICE(0x8086, 0x1d20), .driver_data = AZX_DRIVER_PCH },
+	{ PCI_DEVICE(0x8086, 0x1d20),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_SCH_SNOOP },
 	/* Panther Point */
-	{ PCI_DEVICE(0x8086, 0x1e20), .driver_data = AZX_DRIVER_PCH },
+	{ PCI_DEVICE(0x8086, 0x1e20),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_SCH_SNOOP },
 	/* SCH */
-	{ PCI_DEVICE(0x8086, 0x811b), .driver_data = AZX_DRIVER_SCH },
+	{ PCI_DEVICE(0x8086, 0x811b),
+	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_SCH_SNOOP },
 	/* Generic Intel */
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_ANY_ID),
 	  .class = PCI_CLASS_MULTIMEDIA_HD_AUDIO << 8,
 	  .class_mask = 0xffffff,
 	  .driver_data = AZX_DRIVER_ICH },
-	/* ATI SB 450/600 */
-	{ PCI_DEVICE(0x1002, 0x437b), .driver_data = AZX_DRIVER_ATI },
-	{ PCI_DEVICE(0x1002, 0x4383), .driver_data = AZX_DRIVER_ATI },
+	/* ATI SB 450/600/700/800/900 */
+	{ PCI_DEVICE(0x1002, 0x437b),
+	  .driver_data = AZX_DRIVER_ATI | AZX_DCAPS_PRESET_ATI_SB },
+	{ PCI_DEVICE(0x1002, 0x4383),
+	  .driver_data = AZX_DRIVER_ATI | AZX_DCAPS_PRESET_ATI_SB },
+	/* AMD Hudson */
+	{ PCI_DEVICE(0x1022, 0x780d),
+	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB },
 	/* ATI HDMI */
-	{ PCI_DEVICE(0x1002, 0x793b), .driver_data = AZX_DRIVER_ATIHDMI },
-	{ PCI_DEVICE(0x1002, 0x7919), .driver_data = AZX_DRIVER_ATIHDMI },
-	{ PCI_DEVICE(0x1002, 0x960f), .driver_data = AZX_DRIVER_ATIHDMI },
-	{ PCI_DEVICE(0x1002, 0x970f), .driver_data = AZX_DRIVER_ATIHDMI },
-	{ PCI_DEVICE(0x1002, 0xaa00), .driver_data = AZX_DRIVER_ATIHDMI },
-	{ PCI_DEVICE(0x1002, 0xaa08), .driver_data = AZX_DRIVER_ATIHDMI },
-	{ PCI_DEVICE(0x1002, 0xaa10), .driver_data = AZX_DRIVER_ATIHDMI },
-	{ PCI_DEVICE(0x1002, 0xaa18), .driver_data = AZX_DRIVER_ATIHDMI },
-	{ PCI_DEVICE(0x1002, 0xaa20), .driver_data = AZX_DRIVER_ATIHDMI },
-	{ PCI_DEVICE(0x1002, 0xaa28), .driver_data = AZX_DRIVER_ATIHDMI },
-	{ PCI_DEVICE(0x1002, 0xaa30), .driver_data = AZX_DRIVER_ATIHDMI },
-	{ PCI_DEVICE(0x1002, 0xaa38), .driver_data = AZX_DRIVER_ATIHDMI },
-	{ PCI_DEVICE(0x1002, 0xaa40), .driver_data = AZX_DRIVER_ATIHDMI },
-	{ PCI_DEVICE(0x1002, 0xaa48), .driver_data = AZX_DRIVER_ATIHDMI },
+	{ PCI_DEVICE(0x1002, 0x793b),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0x7919),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0x960f),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0x970f),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0xaa00),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0xaa08),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0xaa10),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0xaa18),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0xaa20),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0xaa28),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0xaa30),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0xaa38),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0xaa40),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0xaa48),
+	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
 	/* VIA VT8251/VT8237A */
-	{ PCI_DEVICE(0x1106, 0x3288), .driver_data = AZX_DRIVER_VIA },
+	{ PCI_DEVICE(0x1106, 0x3288),
+	  .driver_data = AZX_DRIVER_VIA | AZX_DCAPS_POSFIX_VIA },
 	/* SIS966 */
 	{ PCI_DEVICE(0x1039, 0x7502), .driver_data = AZX_DRIVER_SIS },
 	/* ULI M5461 */
@@ -2828,9 +2868,10 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID),
 	  .class = PCI_CLASS_MULTIMEDIA_HD_AUDIO << 8,
 	  .class_mask = 0xffffff,
-	  .driver_data = AZX_DRIVER_NVIDIA },
+	  .driver_data = AZX_DRIVER_NVIDIA | AZX_DCAPS_PRESET_NVIDIA },
 	/* Teradici */
-	{ PCI_DEVICE(0x6549, 0x1200), .driver_data = AZX_DRIVER_TERA },
+	{ PCI_DEVICE(0x6549, 0x1200),
+	  .driver_data = AZX_DRIVER_TERA | AZX_DCAPS_NO_64BIT },
 	/* Creative X-Fi (CA0110-IBG) */
 #if !defined(CONFIG_SND_CTXFI) && !defined(CONFIG_SND_CTXFI_MODULE)
 	/* the following entry conflicts with snd-ctxfi driver,
@@ -2840,10 +2881,13 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_CREATIVE, PCI_ANY_ID),
 	  .class = PCI_CLASS_MULTIMEDIA_HD_AUDIO << 8,
 	  .class_mask = 0xffffff,
-	  .driver_data = AZX_DRIVER_CTX },
+	  .driver_data = AZX_DRIVER_CTX | AZX_DCAPS_CTX_WORKAROUND |
+	  AZX_DCAPS_RIRB_PRE_DELAY },
 #else
 	/* this entry seems still valid -- i.e. without emu20kx chip */
-	{ PCI_DEVICE(0x1102, 0x0009), .driver_data = AZX_DRIVER_CTX },
+	{ PCI_DEVICE(0x1102, 0x0009),
+	  .driver_data = AZX_DRIVER_CTX | AZX_DCAPS_CTX_WORKAROUND |
+	  AZX_DCAPS_RIRB_PRE_DELAY },
 #endif
 	/* Vortex86MX */
 	{ PCI_DEVICE(0x17f3, 0x3010), .driver_data = AZX_DRIVER_GENERIC },
@@ -2853,11 +2897,11 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_ATI, PCI_ANY_ID),
 	  .class = PCI_CLASS_MULTIMEDIA_HD_AUDIO << 8,
 	  .class_mask = 0xffffff,
-	  .driver_data = AZX_DRIVER_GENERIC },
+	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_ANY_ID),
 	  .class = PCI_CLASS_MULTIMEDIA_HD_AUDIO << 8,
 	  .class_mask = 0xffffff,
-	  .driver_data = AZX_DRIVER_GENERIC },
+	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, azx_ids);
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index f1b3875c57df..d694e9d4921d 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -506,9 +506,11 @@ static void ad198x_power_eapd_write(struct hda_codec *codec, hda_nid_t front,
 				hda_nid_t hp)
 {
 	struct ad198x_spec *spec = codec->spec;
-	snd_hda_codec_write(codec, front, 0, AC_VERB_SET_EAPD_BTLENABLE,
+	if (snd_hda_query_pin_caps(codec, front) & AC_PINCAP_EAPD)
+		snd_hda_codec_write(codec, front, 0, AC_VERB_SET_EAPD_BTLENABLE,
 			    !spec->inv_eapd ? 0x00 : 0x02);
-	snd_hda_codec_write(codec, hp, 0, AC_VERB_SET_EAPD_BTLENABLE,
+	if (snd_hda_query_pin_caps(codec, hp) & AC_PINCAP_EAPD)
+		snd_hda_codec_write(codec, hp, 0, AC_VERB_SET_EAPD_BTLENABLE,
 			    !spec->inv_eapd ? 0x00 : 0x02);
 }
 
@@ -524,6 +526,10 @@ static void ad198x_power_eapd(struct hda_codec *codec)
 	case 0x11d4184a:
 	case 0x11d4194a:
 	case 0x11d4194b:
+	case 0x11d41988:
+	case 0x11d4198b:
+	case 0x11d4989a:
+	case 0x11d4989b:
 		ad198x_power_eapd_write(codec, 0x12, 0x11);
 		break;
 	case 0x11d41981:
@@ -533,12 +539,6 @@ static void ad198x_power_eapd(struct hda_codec *codec)
 	case 0x11d41986:
 		ad198x_power_eapd_write(codec, 0x1b, 0x1a);
 		break;
-	case 0x11d41988:
-	case 0x11d4198b:
-	case 0x11d4989a:
-	case 0x11d4989b:
-		ad198x_power_eapd_write(codec, 0x29, 0x22);
-		break;
 	}
 }
 
@@ -3159,6 +3159,7 @@ static const struct snd_pci_quirk ad1988_cfg_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x81ec, "Asus P5B-DLX", AD1988_6STACK_DIG),
 	SND_PCI_QUIRK(0x1043, 0x81f6, "Asus M2N-SLI", AD1988_6STACK_DIG),
 	SND_PCI_QUIRK(0x1043, 0x8277, "Asus P5K-E/WIFI-AP", AD1988_6STACK_DIG),
+	SND_PCI_QUIRK(0x1043, 0x82c0, "Asus M3N-HT Deluxe", AD1988_6STACK_DIG),
 	SND_PCI_QUIRK(0x1043, 0x8311, "Asus P5Q-Premium/Pro", AD1988_6STACK_DIG),
 	{}
 };
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index 4f37477d3c71..694b9daf691f 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -3098,8 +3098,11 @@ static const struct snd_pci_quirk cxt5066_cfg_tbl[] = {
  	SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo Thinkpad", CXT5066_THINKPAD),
 	SND_PCI_QUIRK(0x17aa, 0x21da, "Lenovo X220", CXT5066_THINKPAD),
 	SND_PCI_QUIRK(0x17aa, 0x21db, "Lenovo X220-tablet", CXT5066_THINKPAD),
+	SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo U350", CXT5066_ASUS),
 	SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo G560", CXT5066_ASUS),
+	SND_PCI_QUIRK(0x17aa, 0x3938, "Lenovo G565", CXT5066_AUTO),
 	SND_PCI_QUIRK_VENDOR(0x17aa, "Lenovo", CXT5066_IDEAPAD), /* Fallback for Lenovos without dock mic */
+	SND_PCI_QUIRK(0x1b0a, 0x2092, "CyberpowerPC Gamer Xplorer N57001", CXT5066_AUTO),
 	{}
 };
 
@@ -3433,7 +3436,9 @@ static void cx_auto_parse_output(struct hda_codec *codec)
 			break;
 		}
 	}
-	if (spec->auto_mute && cfg->line_out_pins[0] &&
+	if (spec->auto_mute &&
+	    cfg->line_out_pins[0] &&
+	    cfg->line_out_type != AUTO_PIN_SPEAKER_OUT &&
 	    cfg->line_out_pins[0] != cfg->hp_pins[0] &&
 	    cfg->line_out_pins[0] != cfg->speaker_pins[0]) {
 		for (i = 0; i < cfg->line_outs; i++) {
@@ -3481,25 +3486,32 @@ static void cx_auto_update_speakers(struct hda_codec *codec)
 {
 	struct conexant_spec *spec = codec->spec;
 	struct auto_pin_cfg *cfg = &spec->autocfg;
-	int on;
+	int on = 1;
 
-	if (!spec->auto_mute)
-		on = 0;
-	else
-		on = spec->hp_present | spec->line_present;
+	/* turn on HP EAPD when HP jacks are present */
+	if (spec->auto_mute)
+		on = spec->hp_present;
 	cx_auto_turn_eapd(codec, cfg->hp_outs, cfg->hp_pins, on);
-	do_automute(codec, cfg->speaker_outs, cfg->speaker_pins, !on);
+	/* mute speakers in auto-mode if HP or LO jacks are plugged */
+	if (spec->auto_mute)
+		on = !(spec->hp_present ||
+		       (spec->detect_line && spec->line_present));
+	do_automute(codec, cfg->speaker_outs, cfg->speaker_pins, on);
 
 	/* toggle line-out mutes if needed, too */
 	/* if LO is a copy of either HP or Speaker, don't need to handle it */
 	if (cfg->line_out_pins[0] == cfg->hp_pins[0] ||
 	    cfg->line_out_pins[0] == cfg->speaker_pins[0])
 		return;
-	if (!spec->automute_lines || !spec->auto_mute)
-		on = 0;
-	else
-		on = spec->hp_present;
-	do_automute(codec, cfg->line_outs, cfg->line_out_pins, !on);
+	if (spec->auto_mute) {
+		/* mute LO in auto-mode when HP jack is present */
+		if (cfg->line_out_type == AUTO_PIN_SPEAKER_OUT ||
+		    spec->automute_lines)
+			on = !spec->hp_present;
+		else
+			on = 1;
+	}
+	do_automute(codec, cfg->line_outs, cfg->line_out_pins, on);
 }
 
 static void cx_auto_hp_automute(struct hda_codec *codec)
@@ -3696,13 +3708,14 @@ static int cx_auto_mux_enum_update(struct hda_codec *codec,
 {
 	struct conexant_spec *spec = codec->spec;
 	hda_nid_t adc;
+	int changed = 1;
 
 	if (!imux->num_items)
 		return 0;
 	if (idx >= imux->num_items)
 		idx = imux->num_items - 1;
 	if (spec->cur_mux[0] == idx)
-		return 0;
+		changed = 0;
 	adc = spec->imux_info[idx].adc;
 	select_input_connection(codec, spec->imux_info[idx].adc,
 				spec->imux_info[idx].pin);
@@ -3715,7 +3728,7 @@ static int cx_auto_mux_enum_update(struct hda_codec *codec,
 					   spec->cur_adc_format);
 	}
 	spec->cur_mux[0] = idx;
-	return 1;
+	return changed;
 }
 
 static int cx_auto_mux_enum_put(struct snd_kcontrol *kcontrol,
@@ -3789,7 +3802,7 @@ static void cx_auto_check_auto_mic(struct hda_codec *codec)
 	int pset[INPUT_PIN_ATTR_NORMAL + 1];
 	int i;
 
-	for (i = 0; i < INPUT_PIN_ATTR_NORMAL; i++)
+	for (i = 0; i < ARRAY_SIZE(pset); i++)
 		pset[i] = -1;
 	for (i = 0; i < spec->private_imux.num_items; i++) {
 		hda_nid_t pin = spec->imux_info[i].pin;
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 322901873222..bd0ae697f9c4 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -48,8 +48,8 @@ MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info");
  *
  * The HDA correspondence of pipes/ports are converter/pin nodes.
  */
-#define MAX_HDMI_CVTS	3
-#define MAX_HDMI_PINS	3
+#define MAX_HDMI_CVTS	4
+#define MAX_HDMI_PINS	4
 
 struct hdmi_spec {
 	int num_cvts;
@@ -78,10 +78,6 @@ struct hdmi_spec {
 	 */
 	struct hda_multi_out multiout;
 	const struct hda_pcm_stream *pcm_playback;
-
-	/* misc flags */
-	/* PD bit indicates only the update, not the current state */
-	unsigned int old_pin_detect:1;
 };
 
 
@@ -300,13 +296,6 @@ static int hda_node_index(hda_nid_t *nids, hda_nid_t nid)
 	return -EINVAL;
 }
 
-static void hdmi_get_show_eld(struct hda_codec *codec, hda_nid_t pin_nid,
-			      struct hdmi_eld *eld)
-{
-	if (!snd_hdmi_get_eld(eld, codec, pin_nid))
-		snd_hdmi_show_eld(eld);
-}
-
 #ifdef BE_PARANOID
 static void hdmi_get_dip_index(struct hda_codec *codec, hda_nid_t pin_nid,
 				int *packet_index, int *byte_index)
@@ -694,35 +683,20 @@ static void hdmi_present_sense(struct hda_codec *codec, hda_nid_t pin_nid,
 static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res)
 {
 	struct hdmi_spec *spec = codec->spec;
-	int tag = res >> AC_UNSOL_RES_TAG_SHIFT;
-	int pind = !!(res & AC_UNSOL_RES_PD);
+	int pin_nid = res >> AC_UNSOL_RES_TAG_SHIFT;
+	int pd = !!(res & AC_UNSOL_RES_PD);
 	int eldv = !!(res & AC_UNSOL_RES_ELDV);
 	int index;
 
 	printk(KERN_INFO
 		"HDMI hot plug event: Pin=%d Presence_Detect=%d ELD_Valid=%d\n",
-		tag, pind, eldv);
+		pin_nid, pd, eldv);
 
-	index = hda_node_index(spec->pin, tag);
+	index = hda_node_index(spec->pin, pin_nid);
 	if (index < 0)
 		return;
 
-	if (spec->old_pin_detect) {
-		if (pind)
-			hdmi_present_sense(codec, tag, &spec->sink_eld[index]);
-		pind = spec->sink_eld[index].monitor_present;
-	}
-
-	spec->sink_eld[index].monitor_present = pind;
-	spec->sink_eld[index].eld_valid = eldv;
-
-	if (pind && eldv) {
-		hdmi_get_show_eld(codec, spec->pin[index],
-				  &spec->sink_eld[index]);
-		/* TODO: do real things about ELD */
-	}
-
-	snd_hda_input_jack_report(codec, tag);
+	hdmi_present_sense(codec, pin_nid, &spec->sink_eld[index]);
 }
 
 static void hdmi_non_intrinsic_event(struct hda_codec *codec, unsigned int res)
@@ -903,13 +877,33 @@ static int hdmi_read_pin_conn(struct hda_codec *codec, hda_nid_t pin_nid)
 static void hdmi_present_sense(struct hda_codec *codec, hda_nid_t pin_nid,
 			       struct hdmi_eld *eld)
 {
+	/*
+	 * Always execute a GetPinSense verb here, even when called from
+	 * hdmi_intrinsic_event; for some NVIDIA HW, the unsolicited
+	 * response's PD bit is not the real PD value, but indicates that
+	 * the real PD value changed. An older version of the HD-audio
+	 * specification worked this way. Hence, we just ignore the data in
+	 * the unsolicited response to avoid custom WARs.
+	 */
 	int present = snd_hda_pin_sense(codec, pin_nid);
 
+	memset(eld, 0, sizeof(*eld));
+
 	eld->monitor_present	= !!(present & AC_PINSENSE_PRESENCE);
-	eld->eld_valid		= !!(present & AC_PINSENSE_ELDV);
+	if (eld->monitor_present)
+		eld->eld_valid	= !!(present & AC_PINSENSE_ELDV);
+	else
+		eld->eld_valid	= 0;
 
-	if (present & AC_PINSENSE_ELDV)
-		hdmi_get_show_eld(codec, pin_nid, eld);
+	printk(KERN_INFO
+		"HDMI status: Pin=%d Presence_Detect=%d ELD_Valid=%d\n",
+		pin_nid, eld->monitor_present, eld->eld_valid);
+
+	if (eld->eld_valid)
+		if (!snd_hdmi_get_eld(eld, codec, pin_nid))
+			snd_hdmi_show_eld(eld);
+
+	snd_hda_input_jack_report(codec, pin_nid);
 }
 
 static int hdmi_add_pin(struct hda_codec *codec, hda_nid_t pin_nid)
@@ -927,7 +921,6 @@ static int hdmi_add_pin(struct hda_codec *codec, hda_nid_t pin_nid)
 				     SND_JACK_VIDEOOUT, NULL);
 	if (err < 0)
 		return err;
-	snd_hda_input_jack_report(codec, pin_nid);
 
 	hdmi_present_sense(codec, pin_nid, &spec->sink_eld[spec->num_pins]);
 
@@ -1034,6 +1027,7 @@ static char *generic_hdmi_pcm_names[MAX_HDMI_CVTS] = {
 	"HDMI 0",
 	"HDMI 1",
 	"HDMI 2",
+	"HDMI 3",
 };
 
 /*
@@ -1490,18 +1484,6 @@ static const struct hda_codec_ops nvhdmi_patch_ops_2ch = {
 	.free = generic_hdmi_free,
 };
 
-static int patch_nvhdmi_8ch_89(struct hda_codec *codec)
-{
-	struct hdmi_spec *spec;
-	int err = patch_generic_hdmi(codec);
-
-	if (err < 0)
-		return err;
-	spec = codec->spec;
-	spec->old_pin_detect = 1;
-	return 0;
-}
-
 static int patch_nvhdmi_2ch(struct hda_codec *codec)
 {
 	struct hdmi_spec *spec;
@@ -1515,7 +1497,6 @@ static int patch_nvhdmi_2ch(struct hda_codec *codec)
 	spec->multiout.num_dacs = 0;  /* no analog */
 	spec->multiout.max_channels = 2;
 	spec->multiout.dig_out_nid = nvhdmi_master_con_nid_7x;
-	spec->old_pin_detect = 1;
 	spec->num_cvts = 1;
 	spec->cvt[0] = nvhdmi_master_con_nid_7x;
 	spec->pcm_playback = &nvhdmi_pcm_playback_2ch;
@@ -1658,28 +1639,28 @@ static const struct hda_codec_preset snd_hda_preset_hdmi[] = {
 { .id = 0x10de0005, .name = "MCP77/78 HDMI",	.patch = patch_nvhdmi_8ch_7x },
 { .id = 0x10de0006, .name = "MCP77/78 HDMI",	.patch = patch_nvhdmi_8ch_7x },
 { .id = 0x10de0007, .name = "MCP79/7A HDMI",	.patch = patch_nvhdmi_8ch_7x },
-{ .id = 0x10de000a, .name = "GPU 0a HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de000b, .name = "GPU 0b HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de000c, .name = "MCP89 HDMI",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de000d, .name = "GPU 0d HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de0010, .name = "GPU 10 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de0011, .name = "GPU 11 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de0012, .name = "GPU 12 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de0013, .name = "GPU 13 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de0014, .name = "GPU 14 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de0015, .name = "GPU 15 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de0016, .name = "GPU 16 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
+{ .id = 0x10de000a, .name = "GPU 0a HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de000b, .name = "GPU 0b HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de000c, .name = "MCP89 HDMI",	.patch = patch_generic_hdmi },
+{ .id = 0x10de000d, .name = "GPU 0d HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0010, .name = "GPU 10 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0011, .name = "GPU 11 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0012, .name = "GPU 12 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0013, .name = "GPU 13 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0014, .name = "GPU 14 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0015, .name = "GPU 15 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0016, .name = "GPU 16 HDMI/DP",	.patch = patch_generic_hdmi },
 /* 17 is known to be absent */
-{ .id = 0x10de0018, .name = "GPU 18 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de0019, .name = "GPU 19 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de001a, .name = "GPU 1a HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de001b, .name = "GPU 1b HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de001c, .name = "GPU 1c HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de0040, .name = "GPU 40 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de0041, .name = "GPU 41 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de0042, .name = "GPU 42 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de0043, .name = "GPU 43 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
-{ .id = 0x10de0044, .name = "GPU 44 HDMI/DP",	.patch = patch_nvhdmi_8ch_89 },
+{ .id = 0x10de0018, .name = "GPU 18 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0019, .name = "GPU 19 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de001a, .name = "GPU 1a HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de001b, .name = "GPU 1b HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de001c, .name = "GPU 1c HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0040, .name = "GPU 40 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0041, .name = "GPU 41 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0042, .name = "GPU 42 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0043, .name = "GPU 43 HDMI/DP",	.patch = patch_generic_hdmi },
+{ .id = 0x10de0044, .name = "GPU 44 HDMI/DP",	.patch = patch_generic_hdmi },
 { .id = 0x10de0067, .name = "MCP67 HDMI",	.patch = patch_nvhdmi_2ch },
 { .id = 0x10de8001, .name = "MCP73 HDMI",	.patch = patch_nvhdmi_2ch },
 { .id = 0x80860054, .name = "IbexPeak HDMI",	.patch = patch_generic_hdmi },
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 7a4e10002f56..d21191dcfe88 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -1141,6 +1141,13 @@ static void update_speakers(struct hda_codec *codec)
 	struct alc_spec *spec = codec->spec;
 	int on;
 
+	/* Control HP pins/amps depending on master_mute state;
+	 * in general, HP pins/amps control should be enabled in all cases,
+	 * but currently set only for master_mute, just to be safe
+	 */
+	do_automute(codec, ARRAY_SIZE(spec->autocfg.hp_pins),
+		    spec->autocfg.hp_pins, spec->master_mute, true);
+
 	if (!spec->automute)
 		on = 0;
 	else
@@ -4876,7 +4883,6 @@ static const struct snd_pci_quirk alc880_cfg_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0xe309, "ULI", ALC880_3ST_DIG),
 	SND_PCI_QUIRK(0x1025, 0xe310, "ULI", ALC880_3ST),
 	SND_PCI_QUIRK(0x1039, 0x1234, NULL, ALC880_6ST_DIG),
-	SND_PCI_QUIRK(0x103c, 0x2a09, "HP", ALC880_5ST),
 	SND_PCI_QUIRK(0x1043, 0x10b3, "ASUS W1V", ALC880_ASUS_W1V),
 	SND_PCI_QUIRK(0x1043, 0x10c2, "ASUS W6A", ALC880_ASUS_DIG),
 	SND_PCI_QUIRK(0x1043, 0x10c3, "ASUS Wxx", ALC880_ASUS_DIG),
@@ -6201,11 +6207,6 @@ static const struct snd_kcontrol_new alc260_input_mixer[] = {
 /* update HP, line and mono out pins according to the master switch */
 static void alc260_hp_master_update(struct hda_codec *codec)
 {
-	struct alc_spec *spec = codec->spec;
-
-	/* change HP pins */
-	do_automute(codec, ARRAY_SIZE(spec->autocfg.hp_pins),
-		    spec->autocfg.hp_pins, spec->master_mute, true);
 	update_speakers(codec);
 }
 
@@ -11924,7 +11925,7 @@ static const struct hda_verb alc262_nec_verbs[] = {
  *  0x1b = port replicator headphone out
  */
 
-#define ALC_HP_EVENT	0x37
+#define ALC_HP_EVENT	ALC880_HP_EVENT
 
 static const struct hda_verb alc262_fujitsu_unsol_verbs[] = {
 	{0x14, AC_VERB_SET_UNSOLICITED_ENABLE, AC_USRSP_EN | ALC_HP_EVENT},
@@ -12598,6 +12599,7 @@ static const struct hda_verb alc262_toshiba_rx1_unsol_verbs[] = {
  */
 enum {
 	PINFIX_FSC_H270,
+	PINFIX_HP_Z200,
 };
 
 static const struct alc_fixup alc262_fixups[] = {
@@ -12610,9 +12612,17 @@ static const struct alc_fixup alc262_fixups[] = {
 			{ }
 		}
 	},
+	[PINFIX_HP_Z200] = {
+		.type = ALC_FIXUP_PINS,
+		.v.pins = (const struct alc_pincfg[]) {
+			{ 0x16, 0x99130120 }, /* internal speaker */
+			{ }
+		}
+	},
 };
 
 static const struct snd_pci_quirk alc262_fixup_tbl[] = {
+	SND_PCI_QUIRK(0x103c, 0x170b, "HP Z200", PINFIX_HP_Z200),
 	SND_PCI_QUIRK(0x1734, 0x1147, "FSC Celsius H270", PINFIX_FSC_H270),
 	{}
 };
@@ -12729,6 +12739,8 @@ static const struct snd_pci_quirk alc262_cfg_tbl[] = {
 			   ALC262_HP_BPC),
 	SND_PCI_QUIRK_MASK(0x103c, 0xff00, 0x1500, "HP z series",
 			   ALC262_HP_BPC),
+	SND_PCI_QUIRK(0x103c, 0x170b, "HP Z200",
+			   ALC262_AUTO),
 	SND_PCI_QUIRK_MASK(0x103c, 0xff00, 0x1700, "HP xw series",
 			   ALC262_HP_BPC),
 	SND_PCI_QUIRK(0x103c, 0x2800, "HP D7000", ALC262_HP_BPC_D7000_WL),
@@ -13314,9 +13326,8 @@ static void alc268_acer_lc_setup(struct hda_codec *codec)
 	struct alc_spec *spec = codec->spec;
 	spec->autocfg.hp_pins[0] = 0x15;
 	spec->autocfg.speaker_pins[0] = 0x14;
-	spec->automute_mixer_nid[0] = 0x0f;
 	spec->automute = 1;
-	spec->automute_mode = ALC_AUTOMUTE_MIXER;
+	spec->automute_mode = ALC_AUTOMUTE_AMP;
 	spec->ext_mic.pin = 0x18;
 	spec->ext_mic.mux_idx = 0;
 	spec->int_mic.pin = 0x12;
@@ -13860,6 +13871,7 @@ static const struct snd_pci_quirk alc268_cfg_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x015b, "Acer Aspire One",
 						ALC268_ACER_ASPIRE_ONE),
 	SND_PCI_QUIRK(0x1028, 0x0253, "Dell OEM", ALC268_DELL),
+	SND_PCI_QUIRK(0x1028, 0x02b0, "Dell Inspiron 910", ALC268_AUTO),
 	SND_PCI_QUIRK_MASK(0x1028, 0xfff0, 0x02b0,
 			"Dell Inspiron Mini9/Vostro A90", ALC268_DELL),
 	/* almost compatible with toshiba but with optional digital outs;
@@ -13870,7 +13882,6 @@ static const struct snd_pci_quirk alc268_cfg_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1205, "ASUS W7J", ALC268_3ST),
 	SND_PCI_QUIRK(0x1170, 0x0040, "ZEPTO", ALC268_ZEPTO),
 	SND_PCI_QUIRK(0x14c0, 0x0025, "COMPAL IFL90/JFL-92", ALC268_TOSHIBA),
-	SND_PCI_QUIRK(0x152d, 0x0763, "Diverse (CPR2000)", ALC268_ACER),
 	SND_PCI_QUIRK(0x152d, 0x0771, "Quanta IL1", ALC267_QUANTA_IL1),
 	{}
 };
diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index 605c99e1e520..f43bb0eaed8b 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -745,12 +745,23 @@ static int via_independent_hp_put(struct snd_kcontrol *kcontrol,
 	struct via_spec *spec = codec->spec;
 	hda_nid_t nid = kcontrol->private_value;
 	unsigned int pinsel = ucontrol->value.enumerated.item[0];
+	unsigned int parm0, parm1;
 	/* Get Independent Mode index of headphone pin widget */
 	spec->hp_independent_mode = spec->hp_independent_mode_index == pinsel
 		? 1 : 0;
-	if (spec->codec_type == VT1718S)
+	if (spec->codec_type == VT1718S) {
 		snd_hda_codec_write(codec, nid, 0,
 				    AC_VERB_SET_CONNECT_SEL, pinsel ? 2 : 0);
+		/* Set correct mute switch for MW3 */
+		parm0 = spec->hp_independent_mode ?
+			       AMP_IN_UNMUTE(0) : AMP_IN_MUTE(0);
+		parm1 = spec->hp_independent_mode ?
+			       AMP_IN_MUTE(1) : AMP_IN_UNMUTE(1);
+		snd_hda_codec_write(codec, 0x1b, 0,
+				    AC_VERB_SET_AMP_GAIN_MUTE, parm0);
+		snd_hda_codec_write(codec, 0x1b, 0,
+				    AC_VERB_SET_AMP_GAIN_MUTE, parm1);
+	}
 	else
 		snd_hda_codec_write(codec, nid, 0,
 				    AC_VERB_SET_CONNECT_SEL, pinsel);
@@ -832,10 +843,13 @@ static int via_hp_build(struct hda_codec *codec)
 	knew->subdevice = HDA_SUBDEV_NID_FLAG | nid;
 	knew->private_value = nid;
 
-	knew = via_clone_control(spec, &via_hp_mixer[1]);
-	if (knew == NULL)
-		return -ENOMEM;
-	knew->subdevice = side_mute_channel(spec);
+	nid = side_mute_channel(spec);
+	if (nid) {
+		knew = via_clone_control(spec, &via_hp_mixer[1]);
+		if (knew == NULL)
+			return -ENOMEM;
+		knew->subdevice = nid;
+	}
 
 	return 0;
 }
@@ -4280,9 +4294,6 @@ static const struct hda_verb vt1718S_volume_init_verbs[] = {
 	{0x21, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(2)},
 	{0x21, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(3)},
 	{0x21, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(5)},
-
-	/* Setup default input of Front HP to MW9 */
-	{0x28, AC_VERB_SET_CONNECT_SEL, 0x1},
 	/* PW9 PW10 Output enable */
 	{0x2d, AC_VERB_SET_PIN_WIDGET_CONTROL, AC_PINCTL_OUT_EN},
 	{0x2e, AC_VERB_SET_PIN_WIDGET_CONTROL, AC_PINCTL_OUT_EN},
@@ -4291,10 +4302,10 @@ static const struct hda_verb vt1718S_volume_init_verbs[] = {
 	/* Enable Boost Volume backdoor */
 	{0x1, 0xf88, 0x8},
 	/* MW0/1/2/3/4: un-mute index 0 (AOWx), mute index 1 (MW9) */
-	{0x18, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)},
+	{0x18, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(0)},
 	{0x19, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)},
 	{0x1a, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)},
-	{0x1b, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)},
+	{0x1b, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(0)},
 	{0x1c, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)},
 	{0x18, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(1)},
 	{0x19, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(1)},
@@ -4304,8 +4315,6 @@ static const struct hda_verb vt1718S_volume_init_verbs[] = {
 	/* set MUX1 = 2 (AOW4), MUX2 = 1 (AOW3) */
 	{0x34, AC_VERB_SET_CONNECT_SEL, 0x2},
 	{0x35, AC_VERB_SET_CONNECT_SEL, 0x1},
-	/* Unmute MW4's index 0 */
-	{0x1c, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)},
 	{ }
 };
 
@@ -4453,6 +4462,19 @@ static int vt1718S_auto_create_multi_out_ctls(struct via_spec *spec,
 			if (err < 0)
 				return err;
 		} else if (i == AUTO_SEQ_FRONT) {
+			/* add control to mixer index 0 */
+			err = via_add_control(spec, VIA_CTL_WIDGET_VOL,
+					      "Master Front Playback Volume",
+					      HDA_COMPOSE_AMP_VAL(0x21, 3, 5,
+								  HDA_INPUT));
+			if (err < 0)
+				return err;
+			err = via_add_control(spec, VIA_CTL_WIDGET_MUTE,
+					      "Master Front Playback Switch",
+					      HDA_COMPOSE_AMP_VAL(0x21, 3, 5,
+								  HDA_INPUT));
+			if (err < 0)
+				return err;
 			/* Front */
 			sprintf(name, "%s Playback Volume", chname[i]);
 			err = via_add_control(
diff --git a/sound/pci/lola/lola.c b/sound/pci/lola/lola.c
index 34b24286d279..2692e5ae5f2d 100644
--- a/sound/pci/lola/lola.c
+++ b/sound/pci/lola/lola.c
@@ -445,7 +445,7 @@ static void lola_reset_setups(struct lola *chip)
 	lola_setup_all_analog_gains(chip, PLAY, false); /* output, update */
 }
 
-static int lola_parse_tree(struct lola *chip)
+static int __devinit lola_parse_tree(struct lola *chip)
 {
 	unsigned int val;
 	int nid, err;
diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index 949691a876d3..3f08afc0f0d3 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -521,6 +521,7 @@ MODULE_SUPPORTED_DEVICE("{{RME HDSPM-MADI}}");
 #define HDSPM_DMA_AREA_KILOBYTES (HDSPM_DMA_AREA_BYTES/1024)
 
 /* revisions >= 230 indicate AES32 card */
+#define HDSPM_MADI_OLD_REV	207
 #define HDSPM_MADI_REV		210
 #define HDSPM_RAYDAT_REV	211
 #define HDSPM_AIO_REV		212
@@ -1143,7 +1144,7 @@ static int hdspm_external_sample_rate(struct hdspm *hdspm)
 
 		/* if wordclock has synced freq and wordclock is valid */
 		if ((status2 & HDSPM_wcLock) != 0 &&
-				(status & HDSPM_SelSyncRef0) == 0) {
+				(status2 & HDSPM_SelSyncRef0) == 0) {
 
 			rate_bits = status2 & HDSPM_wcFreqMask;
 
@@ -1639,12 +1640,14 @@ static int snd_hdspm_midi_input_read (struct hdspm_midi *hmidi)
 		}
 	}
 	hmidi->pending = 0;
+	spin_unlock_irqrestore(&hmidi->lock, flags);
 
+	spin_lock_irqsave(&hmidi->hdspm->lock, flags);
 	hmidi->hdspm->control_register |= hmidi->ie;
 	hdspm_write(hmidi->hdspm, HDSPM_controlRegister,
 		    hmidi->hdspm->control_register);
+	spin_unlock_irqrestore(&hmidi->hdspm->lock, flags);
 
-	spin_unlock_irqrestore (&hmidi->lock, flags);
 	return snd_hdspm_midi_output_write (hmidi);
 }
 
@@ -6377,6 +6380,7 @@ static int __devinit snd_hdspm_create(struct snd_card *card,
 
 	switch (hdspm->firmware_rev) {
 	case HDSPM_MADI_REV:
+	case HDSPM_MADI_OLD_REV:
 		hdspm->io_type = MADI;
 		hdspm->card_name = "RME MADI";
 		hdspm->midiPorts = 3;
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index 7fbfa051f6e1..eda955b15834 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -848,9 +848,10 @@ int atmel_ssc_set_audio(int ssc_id)
 	if (IS_ERR(ssc))
 		pr_warn("Unable to parent ASoC SSC DAI on SSC: %ld\n",
 			PTR_ERR(ssc));
-	else
+	else {
 		ssc_pdev->dev.parent = &(ssc->pdev->dev);
-	ssc_free(ssc);
+		ssc_free(ssc);
+	}
 
 	ret = platform_device_add(ssc_pdev);
 	if (ret < 0)
diff --git a/sound/soc/atmel/sam9g20_wm8731.c b/sound/soc/atmel/sam9g20_wm8731.c
index 28afbbf69ce0..95572d290c27 100644
--- a/sound/soc/atmel/sam9g20_wm8731.c
+++ b/sound/soc/atmel/sam9g20_wm8731.c
@@ -146,7 +146,7 @@ static int at91sam9g20ek_wm8731_init(struct snd_soc_pcm_runtime *rtd)
 			"at91sam9g20ek_wm8731 "
 			": at91sam9g20ek_wm8731_init() called\n");
 
-	ret = snd_soc_dai_set_sysclk(codec_dai, WM8731_SYSCLK_XTAL,
+	ret = snd_soc_dai_set_sysclk(codec_dai, WM8731_SYSCLK_MCLK,
 		MCLK_RATE, SND_SOC_CLOCK_IN);
 	if (ret < 0) {
 		printk(KERN_ERR "Failed to set WM8731 SYSCLK: %d\n", ret);
diff --git a/sound/soc/blackfin/bf5xx-ad1836.c b/sound/soc/blackfin/bf5xx-ad1836.c
index ea4951cf5526..f79d1655e035 100644
--- a/sound/soc/blackfin/bf5xx-ad1836.c
+++ b/sound/soc/blackfin/bf5xx-ad1836.c
@@ -75,7 +75,7 @@ static struct snd_soc_dai_link bf5xx_ad1836_dai[] = {
 		.cpu_dai_name = "bfin-tdm.0",
 		.codec_dai_name = "ad1836-hifi",
 		.platform_name = "bfin-tdm-pcm-audio",
-		.codec_name = "ad1836.0",
+		.codec_name = "spi0.4",
 		.ops = &bf5xx_ad1836_ops,
 	},
 	{
@@ -84,7 +84,7 @@ static struct snd_soc_dai_link bf5xx_ad1836_dai[] = {
 		.cpu_dai_name = "bfin-tdm.1",
 		.codec_dai_name = "ad1836-hifi",
 		.platform_name = "bfin-tdm-pcm-audio",
-		.codec_name = "ad1836.0",
+		.codec_name = "spi0.4",
 		.ops = &bf5xx_ad1836_ops,
 	},
 };
diff --git a/sound/soc/codecs/ad1836.c b/sound/soc/codecs/ad1836.c
index ab63d52e36e1..754c496412bd 100644
--- a/sound/soc/codecs/ad1836.c
+++ b/sound/soc/codecs/ad1836.c
@@ -145,22 +145,22 @@ static int ad1836_hw_params(struct snd_pcm_substream *substream,
 	/* bit size */
 	switch (params_format(params)) {
 	case SNDRV_PCM_FORMAT_S16_LE:
-		word_len = 3;
+		word_len = AD1836_WORD_LEN_16;
 		break;
 	case SNDRV_PCM_FORMAT_S20_3LE:
-		word_len = 1;
+		word_len = AD1836_WORD_LEN_20;
 		break;
 	case SNDRV_PCM_FORMAT_S24_LE:
 	case SNDRV_PCM_FORMAT_S32_LE:
-		word_len = 0;
+		word_len = AD1836_WORD_LEN_24;
 		break;
 	}
 
-	snd_soc_update_bits(codec, AD1836_DAC_CTRL1,
-		AD1836_DAC_WORD_LEN_MASK, word_len);
+	snd_soc_update_bits(codec, AD1836_DAC_CTRL1, AD1836_DAC_WORD_LEN_MASK,
+		word_len << AD1836_DAC_WORD_LEN_OFFSET);
 
-	snd_soc_update_bits(codec, AD1836_ADC_CTRL2,
-		AD1836_ADC_WORD_LEN_MASK, word_len);
+	snd_soc_update_bits(codec, AD1836_ADC_CTRL2, AD1836_ADC_WORD_LEN_MASK,
+		word_len << AD1836_ADC_WORD_OFFSET);
 
 	return 0;
 }
diff --git a/sound/soc/codecs/ad1836.h b/sound/soc/codecs/ad1836.h
index 845596717fdf..9d6a3f8f8aaf 100644
--- a/sound/soc/codecs/ad1836.h
+++ b/sound/soc/codecs/ad1836.h
@@ -25,6 +25,7 @@
 #define AD1836_DAC_SERFMT_PCK256       (0x4 << 5)
 #define AD1836_DAC_SERFMT_PCK128       (0x5 << 5)
 #define AD1836_DAC_WORD_LEN_MASK       0x18
+#define AD1836_DAC_WORD_LEN_OFFSET     3
 
 #define AD1836_DAC_CTRL2               1
 #define AD1836_DACL1_MUTE              0
@@ -51,6 +52,7 @@
 #define AD1836_ADCL2_MUTE 		2
 #define AD1836_ADCR2_MUTE 		3
 #define AD1836_ADC_WORD_LEN_MASK       0x30
+#define AD1836_ADC_WORD_OFFSET         5
 #define AD1836_ADC_SERFMT_MASK	       (7 << 6)
 #define AD1836_ADC_SERFMT_PCK256       (0x4 << 6)
 #define AD1836_ADC_SERFMT_PCK128       (0x5 << 6)
@@ -60,4 +62,8 @@
 
 #define AD1836_NUM_REGS                16
 
+#define AD1836_WORD_LEN_24 0x0
+#define AD1836_WORD_LEN_20 0x1
+#define AD1836_WORD_LEN_16 0x2
+
 #endif
diff --git a/sound/soc/codecs/cx20442.c b/sound/soc/codecs/cx20442.c
index f8c663dcff02..d68ea532cc7f 100644
--- a/sound/soc/codecs/cx20442.c
+++ b/sound/soc/codecs/cx20442.c
@@ -262,14 +262,14 @@ static int v253_hangup(struct tty_struct *tty)
 }
 
 /* Line discipline .receive_buf() */
-static unsigned int v253_receive(struct tty_struct *tty,
-				 const unsigned char *cp, char *fp, int count)
+static void v253_receive(struct tty_struct *tty,
+				const unsigned char *cp, char *fp, int count)
 {
 	struct snd_soc_codec *codec = tty->disc_data;
 	struct cx20442_priv *cx20442;
 
 	if (!codec)
-		return count;
+		return;
 
 	cx20442 = snd_soc_codec_get_drvdata(codec);
 
@@ -281,8 +281,6 @@ static unsigned int v253_receive(struct tty_struct *tty,
 		codec->hw_write = (hw_write_t)tty->ops->write;
 		codec->card->pop_time = 1;
 	}
-
-	return count;
 }
 
 /* Line discipline .write_wakeup() */
diff --git a/sound/soc/codecs/wm1250-ev1.c b/sound/soc/codecs/wm1250-ev1.c
index 14d0716bf009..bcc208967917 100644
--- a/sound/soc/codecs/wm1250-ev1.c
+++ b/sound/soc/codecs/wm1250-ev1.c
@@ -22,7 +22,7 @@ SND_SOC_DAPM_ADC("ADC", "wm1250-ev1 Capture", SND_SOC_NOPM, 0, 0),
 SND_SOC_DAPM_DAC("DAC", "wm1250-ev1 Playback", SND_SOC_NOPM, 0, 0),
 
 SND_SOC_DAPM_INPUT("WM1250 Input"),
-SND_SOC_DAPM_INPUT("WM1250 Output"),
+SND_SOC_DAPM_OUTPUT("WM1250 Output"),
 };
 
 static const struct snd_soc_dapm_route wm1250_ev1_dapm_routes[] = {
diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c
index 6dec7cee2cb4..2dc964b55e4f 100644
--- a/sound/soc/codecs/wm8731.c
+++ b/sound/soc/codecs/wm8731.c
@@ -198,7 +198,7 @@ static int wm8731_check_osc(struct snd_soc_dapm_widget *source,
 {
 	struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(source->codec);
 
-	return wm8731->sysclk_type == WM8731_SYSCLK_MCLK;
+	return wm8731->sysclk_type == WM8731_SYSCLK_XTAL;
 }
 
 static const struct snd_soc_dapm_route wm8731_intercon[] = {
diff --git a/sound/soc/codecs/wm8804.c b/sound/soc/codecs/wm8804.c
index 6785688f8806..9a5e67c5a6bd 100644
--- a/sound/soc/codecs/wm8804.c
+++ b/sound/soc/codecs/wm8804.c
@@ -680,20 +680,25 @@ static struct snd_soc_dai_ops wm8804_dai_ops = {
 #define WM8804_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_3LE | \
 			SNDRV_PCM_FMTBIT_S24_LE)
 
+#define WM8804_RATES (SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_44100 | \
+		      SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_64000 | \
+		      SNDRV_PCM_RATE_88200 | SNDRV_PCM_RATE_96000 | \
+		      SNDRV_PCM_RATE_176400 | SNDRV_PCM_RATE_192000)
+
 static struct snd_soc_dai_driver wm8804_dai = {
 	.name = "wm8804-spdif",
 	.playback = {
 		.stream_name = "Playback",
 		.channels_min = 2,
 		.channels_max = 2,
-		.rates = SNDRV_PCM_RATE_8000_192000,
+		.rates = WM8804_RATES,
 		.formats = WM8804_FORMATS,
 	},
 	.capture = {
 		.stream_name = "Capture",
 		.channels_min = 2,
 		.channels_max = 2,
-		.rates = SNDRV_PCM_RATE_8000_192000,
+		.rates = WM8804_RATES,
 		.formats = WM8804_FORMATS,
 	},
 	.ops = &wm8804_dai_ops,
diff --git a/sound/soc/codecs/wm8915.c b/sound/soc/codecs/wm8915.c
index ccc9bd832794..e2ab4fac2819 100644
--- a/sound/soc/codecs/wm8915.c
+++ b/sound/soc/codecs/wm8915.c
@@ -19,7 +19,6 @@
 #include <linux/gcd.h>
 #include <linux/gpio.h>
 #include <linux/i2c.h>
-#include <linux/delay.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
 #include <linux/workqueue.h>
@@ -1840,7 +1839,7 @@ static int wm8915_set_sysclk(struct snd_soc_dai *dai,
 	int old;
 
 	/* Disable SYSCLK while we reconfigure */
-	old = snd_soc_read(codec, WM8915_AIF_CLOCKING_1);
+	old = snd_soc_read(codec, WM8915_AIF_CLOCKING_1) & WM8915_SYSCLK_ENA;
 	snd_soc_update_bits(codec, WM8915_AIF_CLOCKING_1,
 			    WM8915_SYSCLK_ENA, 0);
 
@@ -2039,6 +2038,7 @@ static int wm8915_set_fll(struct snd_soc_codec *codec, int fll_id, int source,
 		break;
 	case WM8915_FLL_MCLK2:
 		reg = 1;
+		break;
 	case WM8915_FLL_DACLRCLK1:
 		reg = 2;
 		break;
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index f90ae427242b..5e05eed96c38 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -1999,12 +1999,12 @@ static int wm8962_put_hp_sw(struct snd_kcontrol *kcontrol,
 		return 0;
 
 	/* If the left PGA is enabled hit that VU bit... */
-	if (reg_cache[WM8962_PWR_MGMT_2] & WM8962_HPOUTL_PGA_ENA)
+	if (snd_soc_read(codec, WM8962_PWR_MGMT_2) & WM8962_HPOUTL_PGA_ENA)
 		return snd_soc_write(codec, WM8962_HPOUTL_VOLUME,
 				     reg_cache[WM8962_HPOUTL_VOLUME]);
 
 	/* ...otherwise the right.  The VU is stereo. */
-	if (reg_cache[WM8962_PWR_MGMT_2] & WM8962_HPOUTR_PGA_ENA)
+	if (snd_soc_read(codec, WM8962_PWR_MGMT_2) & WM8962_HPOUTR_PGA_ENA)
 		return snd_soc_write(codec, WM8962_HPOUTR_VOLUME,
 				     reg_cache[WM8962_HPOUTR_VOLUME]);
 
diff --git a/sound/soc/codecs/wm8991.c b/sound/soc/codecs/wm8991.c
index 3c2ee1bb73cd..6af23d06870f 100644
--- a/sound/soc/codecs/wm8991.c
+++ b/sound/soc/codecs/wm8991.c
@@ -13,7 +13,6 @@
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-#include <linux/version.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/delay.h>
diff --git a/sound/soc/codecs/wm_hubs.c b/sound/soc/codecs/wm_hubs.c
index e55b298c14a0..9e370d14ad88 100644
--- a/sound/soc/codecs/wm_hubs.c
+++ b/sound/soc/codecs/wm_hubs.c
@@ -215,23 +215,23 @@ static const struct snd_kcontrol_new analogue_snd_controls[] = {
 SOC_SINGLE_TLV("IN1L Volume", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 0, 31, 0,
 	       inpga_tlv),
 SOC_SINGLE("IN1L Switch", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN1L ZC Switch", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN1L ZC Switch", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 6, 1, 0),
 
 SOC_SINGLE_TLV("IN1R Volume", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 0, 31, 0,
 	       inpga_tlv),
 SOC_SINGLE("IN1R Switch", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN1R ZC Switch", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN1R ZC Switch", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 6, 1, 0),
 
 
 SOC_SINGLE_TLV("IN2L Volume", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 0, 31, 0,
 	       inpga_tlv),
 SOC_SINGLE("IN2L Switch", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN2L ZC Switch", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN2L ZC Switch", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 6, 1, 0),
 
 SOC_SINGLE_TLV("IN2R Volume", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 0, 31, 0,
 	       inpga_tlv),
 SOC_SINGLE("IN2R Switch", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN2R ZC Switch", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN2R ZC Switch", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 6, 1, 0),
 
 SOC_SINGLE_TLV("MIXINL IN2L Volume", WM8993_INPUT_MIXER3, 7, 1, 0,
 	       inmix_sw_tlv),
diff --git a/sound/soc/fsl/fsl_dma.c b/sound/soc/fsl/fsl_dma.c
index 15dac0f20cd8..6680c0b4d203 100644
--- a/sound/soc/fsl/fsl_dma.c
+++ b/sound/soc/fsl/fsl_dma.c
@@ -310,7 +310,7 @@ static int fsl_dma_new(struct snd_card *card, struct snd_soc_dai *dai,
 	 * should allocate a DMA buffer only for the streams that are valid.
 	 */
 
-	if (dai->driver->playback.channels_min) {
+	if (pcm->streams[0].substream) {
 		ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, card->dev,
 			fsl_dma_hardware.buffer_bytes_max,
 			&pcm->streams[0].substream->dma_buffer);
@@ -320,13 +320,13 @@ static int fsl_dma_new(struct snd_card *card, struct snd_soc_dai *dai,
 		}
 	}
 
-	if (dai->driver->capture.channels_min) {
+	if (pcm->streams[1].substream) {
 		ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, card->dev,
 			fsl_dma_hardware.buffer_bytes_max,
 			&pcm->streams[1].substream->dma_buffer);
 		if (ret) {
-			snd_dma_free_pages(&pcm->streams[0].substream->dma_buffer);
 			dev_err(card->dev, "can't alloc capture dma buffer\n");
+			snd_dma_free_pages(&pcm->streams[0].substream->dma_buffer);
 			return ret;
 		}
 	}
@@ -449,7 +449,8 @@ static int fsl_dma_open(struct snd_pcm_substream *substream)
 	dma_private->ld_buf_phys = ld_buf_phys;
 	dma_private->dma_buf_phys = substream->dma_buffer.addr;
 
-	ret = request_irq(dma_private->irq, fsl_dma_isr, 0, "DMA", dma_private);
+	ret = request_irq(dma_private->irq, fsl_dma_isr, 0, "fsldma-audio",
+			  dma_private);
 	if (ret) {
 		dev_err(dev, "can't register ISR for IRQ %u (ret=%i)\n",
 			dma_private->irq, ret);
diff --git a/sound/soc/imx/Kconfig b/sound/soc/imx/Kconfig
index d8f130d39dd9..bb699bb55a50 100644
--- a/sound/soc/imx/Kconfig
+++ b/sound/soc/imx/Kconfig
@@ -11,9 +11,6 @@ menuconfig SND_IMX_SOC
 
 if SND_IMX_SOC
 
-config SND_MXC_SOC_SSI
-	tristate
-
 config SND_MXC_SOC_FIQ
 	tristate
 
@@ -24,7 +21,6 @@ config SND_MXC_SOC_WM1133_EV1
 	tristate "Audio on the the i.MX31ADS with WM1133-EV1 fitted"
 	depends on MACH_MX31ADS_WM1133_EV1 && EXPERIMENTAL
 	select SND_SOC_WM8350
-	select SND_MXC_SOC_SSI
 	select SND_MXC_SOC_FIQ
 	help
 	  Enable support for audio on the i.MX31ADS with the WM1133-EV1
@@ -34,7 +30,6 @@ config SND_SOC_MX27VIS_AIC32X4
 	tristate "SoC audio support for Visstrim M10 boards"
 	depends on MACH_IMX27_VISSTRIM_M10
 	select SND_SOC_TVL320AIC32X4
-	select SND_MXC_SOC_SSI
 	select SND_MXC_SOC_MX2
 	help
 	  Say Y if you want to add support for SoC audio on Visstrim SM10
@@ -44,7 +39,6 @@ config SND_SOC_PHYCORE_AC97
 	tristate "SoC Audio support for Phytec phyCORE (and phyCARD) boards"
 	depends on MACH_PCM043 || MACH_PCA100
 	select SND_SOC_WM9712
-	select SND_MXC_SOC_SSI
 	select SND_MXC_SOC_FIQ
 	help
 	  Say Y if you want to add support for SoC audio on Phytec phyCORE
@@ -57,7 +51,6 @@ config SND_SOC_EUKREA_TLV320
 		|| MACH_EUKREA_MBIMXSD35_BASEBOARD \
 		|| MACH_EUKREA_MBIMXSD51_BASEBOARD
 	select SND_SOC_TLV320AIC23
-	select SND_MXC_SOC_SSI
 	select SND_MXC_SOC_FIQ
 	help
 	  Enable I2S based access to the TLV320AIC23B codec attached
diff --git a/sound/soc/imx/imx-pcm-dma-mx2.c b/sound/soc/imx/imx-pcm-dma-mx2.c
index aab7765f401a..4173b3d87f97 100644
--- a/sound/soc/imx/imx-pcm-dma-mx2.c
+++ b/sound/soc/imx/imx-pcm-dma-mx2.c
@@ -337,3 +337,5 @@ static void __exit snd_imx_pcm_exit(void)
 	platform_driver_unregister(&imx_pcm_driver);
 }
 module_exit(snd_imx_pcm_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:imx-pcm-audio");
diff --git a/sound/soc/imx/imx-ssi.c b/sound/soc/imx/imx-ssi.c
index 5b13feca7537..61fceb09cdb5 100644
--- a/sound/soc/imx/imx-ssi.c
+++ b/sound/soc/imx/imx-ssi.c
@@ -774,4 +774,4 @@ module_exit(imx_ssi_exit);
 MODULE_AUTHOR("Sascha Hauer, <s.hauer@pengutronix.de>");
 MODULE_DESCRIPTION("i.MX I2S/ac97 SoC Interface");
 MODULE_LICENSE("GPL");
-
+MODULE_ALIAS("platform:imx-ssi");
diff --git a/sound/soc/pxa/pxa2xx-pcm.c b/sound/soc/pxa/pxa2xx-pcm.c
index 2ce0b2d891d5..fab20a54e863 100644
--- a/sound/soc/pxa/pxa2xx-pcm.c
+++ b/sound/soc/pxa/pxa2xx-pcm.c
@@ -95,14 +95,14 @@ static int pxa2xx_soc_pcm_new(struct snd_card *card, struct snd_soc_dai *dai,
 	if (!card->dev->coherent_dma_mask)
 		card->dev->coherent_dma_mask = DMA_BIT_MASK(32);
 
-	if (dai->driver->playback.channels_min) {
+	if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) {
 		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm,
 			SNDRV_PCM_STREAM_PLAYBACK);
 		if (ret)
 			goto out;
 	}
 
-	if (dai->driver->capture.channels_min) {
+	if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) {
 		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm,
 			SNDRV_PCM_STREAM_CAPTURE);
 		if (ret)
diff --git a/sound/soc/pxa/raumfeld.c b/sound/soc/pxa/raumfeld.c
index 2afabaf59491..1a591f1ebfbd 100644
--- a/sound/soc/pxa/raumfeld.c
+++ b/sound/soc/pxa/raumfeld.c
@@ -151,13 +151,13 @@ static struct snd_soc_ops raumfeld_cs4270_ops = {
 	.hw_params = raumfeld_cs4270_hw_params,
 };
 
-static int raumfeld_line_suspend(struct snd_soc_card *card)
+static int raumfeld_analog_suspend(struct snd_soc_card *card)
 {
 	raumfeld_enable_audio(false);
 	return 0;
 }
 
-static int raumfeld_line_resume(struct snd_soc_card *card)
+static int raumfeld_analog_resume(struct snd_soc_card *card)
 {
 	raumfeld_enable_audio(true);
 	return 0;
@@ -225,32 +225,53 @@ static struct snd_soc_ops raumfeld_ak4104_ops = {
 	.hw_params = raumfeld_ak4104_hw_params,
 };
 
-static struct snd_soc_dai_link raumfeld_dai[] = {
+#define DAI_LINK_CS4270		\
+{							\
+	.name		= "CS4270",			\
+	.stream_name	= "CS4270",			\
+	.cpu_dai_name	= "pxa-ssp-dai.0",		\
+	.platform_name	= "pxa-pcm-audio",		\
+	.codec_dai_name	= "cs4270-hifi",		\
+	.codec_name	= "cs4270-codec.0-0048",	\
+	.ops		= &raumfeld_cs4270_ops,		\
+}
+
+#define DAI_LINK_AK4104		\
+{							\
+	.name		= "ak4104",			\
+	.stream_name	= "Playback",			\
+	.cpu_dai_name	= "pxa-ssp-dai.1",		\
+	.codec_dai_name	= "ak4104-hifi",		\
+	.platform_name	= "pxa-pcm-audio",		\
+	.ops		= &raumfeld_ak4104_ops,		\
+	.codec_name	= "spi0.0",			\
+}
+
+static struct snd_soc_dai_link snd_soc_raumfeld_connector_dai[] =
 {
-	.name		= "ak4104",
-	.stream_name	= "Playback",
-	.cpu_dai_name	= "pxa-ssp-dai.1",
-	.codec_dai_name	= "ak4104-hifi",
-	.platform_name	= "pxa-pcm-audio",
-	.ops		= &raumfeld_ak4104_ops,
-	.codec_name	= "ak4104-codec.0",
-},
+	DAI_LINK_CS4270,
+	DAI_LINK_AK4104,
+};
+
+static struct snd_soc_dai_link snd_soc_raumfeld_speaker_dai[] =
 {
-	.name		= "CS4270",
-	.stream_name	= "CS4270",
-	.cpu_dai_name	= "pxa-ssp-dai.0",
-	.platform_name	= "pxa-pcm-audio",
-	.codec_dai_name	= "cs4270-hifi",
-	.codec_name	= "cs4270-codec.0-0048",
-	.ops		= &raumfeld_cs4270_ops,
-},};
-
-static struct snd_soc_card snd_soc_raumfeld = {
-	.name		= "Raumfeld",
-	.dai_link	= raumfeld_dai,
-	.suspend_post	= raumfeld_line_suspend,
-	.resume_pre	= raumfeld_line_resume,
-	.num_links	= ARRAY_SIZE(raumfeld_dai),
+	DAI_LINK_CS4270,
+};
+
+static struct snd_soc_card snd_soc_raumfeld_connector = {
+	.name		= "Raumfeld Connector",
+	.dai_link	= snd_soc_raumfeld_connector_dai,
+	.num_links	= ARRAY_SIZE(snd_soc_raumfeld_connector_dai),
+	.suspend_post	= raumfeld_analog_suspend,
+	.resume_pre	= raumfeld_analog_resume,
+};
+
+static struct snd_soc_card snd_soc_raumfeld_speaker = {
+	.name		= "Raumfeld Speaker",
+	.dai_link	= snd_soc_raumfeld_speaker_dai,
+	.num_links	= ARRAY_SIZE(snd_soc_raumfeld_speaker_dai),
+	.suspend_post	= raumfeld_analog_suspend,
+	.resume_pre	= raumfeld_analog_resume,
 };
 
 static struct platform_device *raumfeld_audio_device;
@@ -271,22 +292,25 @@ static int __init raumfeld_audio_init(void)
 
 	set_max9485_clk(MAX9485_MCLK_FREQ_122880);
 
-	/* Register LINE and SPDIF */
+	/* Register analog device */
 	raumfeld_audio_device = platform_device_alloc("soc-audio", 0);
 	if (!raumfeld_audio_device)
 		return -ENOMEM;
 
-	platform_set_drvdata(raumfeld_audio_device,
-			     &snd_soc_raumfeld);
-	ret = platform_device_add(raumfeld_audio_device);
-
-	/* no S/PDIF on Speakers */
 	if (machine_is_raumfeld_speaker())
+		platform_set_drvdata(raumfeld_audio_device,
+				     &snd_soc_raumfeld_speaker);
+
+	if (machine_is_raumfeld_connector())
+		platform_set_drvdata(raumfeld_audio_device,
+				     &snd_soc_raumfeld_connector);
+
+	ret = platform_device_add(raumfeld_audio_device);
+	if (ret < 0)
 		return ret;
 
 	raumfeld_enable_audio(true);
-
-	return ret;
+	return 0;
 }
 
 static void __exit raumfeld_audio_exit(void)
diff --git a/sound/soc/samsung/Kconfig b/sound/soc/samsung/Kconfig
index 459566bfcd35..d155cbb58e1c 100644
--- a/sound/soc/samsung/Kconfig
+++ b/sound/soc/samsung/Kconfig
@@ -1,6 +1,6 @@
 config SND_SOC_SAMSUNG
 	tristate "ASoC support for Samsung"
-	depends on ARCH_S3C2410 || ARCH_S3C64XX || ARCH_S5PC100 || ARCH_S5PV210 || ARCH_S5P64X0 || ARCH_S5P6442 || ARCH_EXYNOS4
+	depends on ARCH_S3C2410 || ARCH_S3C64XX || ARCH_S5PC100 || ARCH_S5PV210 || ARCH_S5P64X0 || ARCH_EXYNOS4
 	select S3C64XX_DMA if ARCH_S3C64XX
 	select S3C2410_DMA if ARCH_S3C2410
 	help
@@ -55,7 +55,7 @@ config SND_SOC_SAMSUNG_JIVE_WM8750
 
 config SND_SOC_SAMSUNG_SMDK_WM8580
 	tristate "SoC I2S Audio support for WM8580 on SMDK"
-	depends on SND_SOC_SAMSUNG && (MACH_SMDK6410 || MACH_SMDKC100 || MACH_SMDK6440 || MACH_SMDK6450 || MACH_SMDK6442 || MACH_SMDKV210 || MACH_SMDKC110)
+	depends on SND_SOC_SAMSUNG && (MACH_SMDK6410 || MACH_SMDKC100 || MACH_SMDK6440 || MACH_SMDK6450 || MACH_SMDKV210 || MACH_SMDKC110)
 	select SND_SOC_WM8580
 	select SND_SAMSUNG_I2S
 	help
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index ffa09b3b2caa..992a732b5211 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -191,7 +191,7 @@ static inline bool tx_active(struct i2s_dai *i2s)
 	if (!i2s)
 		return false;
 
-	active = readl(i2s->addr + I2SMOD);
+	active = readl(i2s->addr + I2SCON);
 
 	if (is_secondary(i2s))
 		active &= CON_TXSDMA_ACTIVE;
@@ -223,7 +223,7 @@ static inline bool rx_active(struct i2s_dai *i2s)
 	if (!i2s)
 		return false;
 
-	active = readl(i2s->addr + I2SMOD) & CON_RXDMA_ACTIVE;
+	active = readl(i2s->addr + I2SCON) & CON_RXDMA_ACTIVE;
 
 	return active ? true : false;
 }
diff --git a/sound/soc/samsung/smdk_wm8580.c b/sound/soc/samsung/smdk_wm8580.c
index 8aacf23d6f3a..3d26f6607aa4 100644
--- a/sound/soc/samsung/smdk_wm8580.c
+++ b/sound/soc/samsung/smdk_wm8580.c
@@ -249,7 +249,7 @@ static int __init smdk_audio_init(void)
 	int ret;
 	char *str;
 
-	if (machine_is_smdkc100() || machine_is_smdk6442()
+	if (machine_is_smdkc100()
 			|| machine_is_smdkv210() || machine_is_smdkc110()) {
 		smdk.num_links = 3;
 		/* Secondary is at offset SAMSUNG_I2S_SECOFF from Primary */
diff --git a/sound/soc/soc-cache.c b/sound/soc/soc-cache.c
index 06b7b81a1601..039b9532b270 100644
--- a/sound/soc/soc-cache.c
+++ b/sound/soc/soc-cache.c
@@ -409,9 +409,6 @@ int snd_soc_codec_set_cache_io(struct snd_soc_codec *codec,
 	codec->bulk_write_raw = snd_soc_hw_bulk_write_raw;
 
 	switch (control) {
-	case SND_SOC_CUSTOM:
-		break;
-
 	case SND_SOC_I2C:
 #if defined(CONFIG_I2C) || (defined(CONFIG_I2C_MODULE) && defined(MODULE))
 		codec->hw_write = (hw_write_t)i2c_master_send;
@@ -466,6 +463,9 @@ static bool snd_soc_set_cache_val(void *base, unsigned int idx,
 static unsigned int snd_soc_get_cache_val(const void *base, unsigned int idx,
 		unsigned int word_size)
 {
+	if (!base)
+		return -1;
+
 	switch (word_size) {
 	case 1: {
 		const u8 *cache = base;
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index bb7cd5812945..d75043ed7fc0 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1306,10 +1306,6 @@ static int soc_bind_dai_link(struct snd_soc_card *card, int num)
 	/* no, then find CPU DAI from registered DAIs*/
 	list_for_each_entry(cpu_dai, &dai_list, list) {
 		if (!strcmp(cpu_dai->name, dai_link->cpu_dai_name)) {
-
-			if (!try_module_get(cpu_dai->dev->driver->owner))
-				return -ENODEV;
-
 			rtd->cpu_dai = cpu_dai;
 			goto find_codec;
 		}
@@ -1622,11 +1618,15 @@ static int soc_probe_dai_link(struct snd_soc_card *card, int num)
 
 	/* probe the cpu_dai */
 	if (!cpu_dai->probed) {
+		if (!try_module_get(cpu_dai->dev->driver->owner))
+			return -ENODEV;
+
 		if (cpu_dai->driver->probe) {
 			ret = cpu_dai->driver->probe(cpu_dai);
 			if (ret < 0) {
 				printk(KERN_ERR "asoc: failed to probe CPU DAI %s\n",
 						cpu_dai->name);
+				module_put(cpu_dai->dev->driver->owner);
 				return ret;
 			}
 		}
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 456617e63789..32ab7fc4579a 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -325,6 +325,7 @@ static int dapm_connect_mixer(struct snd_soc_dapm_context *dapm,
 }
 
 static int dapm_is_shared_kcontrol(struct snd_soc_dapm_context *dapm,
+	struct snd_soc_dapm_widget *kcontrolw,
 	const struct snd_kcontrol_new *kcontrol_new,
 	struct snd_kcontrol **kcontrol)
 {
@@ -334,6 +335,8 @@ static int dapm_is_shared_kcontrol(struct snd_soc_dapm_context *dapm,
 	*kcontrol = NULL;
 
 	list_for_each_entry(w, &dapm->card->widgets, list) {
+		if (w == kcontrolw || w->dapm != kcontrolw->dapm)
+			continue;
 		for (i = 0; i < w->num_kcontrols; i++) {
 			if (&w->kcontrol_news[i] == kcontrol_new) {
 				if (w->kcontrols)
@@ -347,9 +350,9 @@ static int dapm_is_shared_kcontrol(struct snd_soc_dapm_context *dapm,
 }
 
 /* create new dapm mixer control */
-static int dapm_new_mixer(struct snd_soc_dapm_context *dapm,
-	struct snd_soc_dapm_widget *w)
+static int dapm_new_mixer(struct snd_soc_dapm_widget *w)
 {
+	struct snd_soc_dapm_context *dapm = w->dapm;
 	int i, ret = 0;
 	size_t name_len, prefix_len;
 	struct snd_soc_dapm_path *path;
@@ -447,9 +450,9 @@ static int dapm_new_mixer(struct snd_soc_dapm_context *dapm,
 }
 
 /* create new dapm mux control */
-static int dapm_new_mux(struct snd_soc_dapm_context *dapm,
-	struct snd_soc_dapm_widget *w)
+static int dapm_new_mux(struct snd_soc_dapm_widget *w)
 {
+	struct snd_soc_dapm_context *dapm = w->dapm;
 	struct snd_soc_dapm_path *path = NULL;
 	struct snd_kcontrol *kcontrol;
 	struct snd_card *card = dapm->card->snd_card;
@@ -468,7 +471,7 @@ static int dapm_new_mux(struct snd_soc_dapm_context *dapm,
 		return -EINVAL;
 	}
 
-	shared = dapm_is_shared_kcontrol(dapm, &w->kcontrol_news[0],
+	shared = dapm_is_shared_kcontrol(dapm, w, &w->kcontrol_news[0],
 					 &kcontrol);
 	if (kcontrol) {
 		wlist = kcontrol->private_data;
@@ -532,8 +535,7 @@ static int dapm_new_mux(struct snd_soc_dapm_context *dapm,
 }
 
 /* create new dapm volume control */
-static int dapm_new_pga(struct snd_soc_dapm_context *dapm,
-	struct snd_soc_dapm_widget *w)
+static int dapm_new_pga(struct snd_soc_dapm_widget *w)
 {
 	if (w->num_kcontrols)
 		dev_err(w->dapm->dev,
@@ -1110,7 +1112,7 @@ static int dapm_power_widgets(struct snd_soc_dapm_context *dapm, int event)
 	trace_snd_soc_dapm_start(card);
 
 	list_for_each_entry(d, &card->dapm_list, list)
-		if (d->n_widgets)
+		if (d->n_widgets || d->codec == NULL)
 			d->dev_power = 0;
 
 	/* Check which widgets we need to power and store them in
@@ -1823,13 +1825,13 @@ int snd_soc_dapm_new_widgets(struct snd_soc_dapm_context *dapm)
 		case snd_soc_dapm_mixer:
 		case snd_soc_dapm_mixer_named_ctl:
 			w->power_check = dapm_generic_check_power;
-			dapm_new_mixer(dapm, w);
+			dapm_new_mixer(w);
 			break;
 		case snd_soc_dapm_mux:
 		case snd_soc_dapm_virt_mux:
 		case snd_soc_dapm_value_mux:
 			w->power_check = dapm_generic_check_power;
-			dapm_new_mux(dapm, w);
+			dapm_new_mux(w);
 			break;
 		case snd_soc_dapm_adc:
 		case snd_soc_dapm_aif_out:
@@ -1842,7 +1844,7 @@ int snd_soc_dapm_new_widgets(struct snd_soc_dapm_context *dapm)
 		case snd_soc_dapm_pga:
 		case snd_soc_dapm_out_drv:
 			w->power_check = dapm_generic_check_power;
-			dapm_new_pga(dapm, w);
+			dapm_new_pga(w);
 			break;
 		case snd_soc_dapm_input:
 		case snd_soc_dapm_output:
diff --git a/sound/usb/6fire/firmware.c b/sound/usb/6fire/firmware.c
index d47beffedb0f..1e3ae3327dd3 100644
--- a/sound/usb/6fire/firmware.c
+++ b/sound/usb/6fire/firmware.c
@@ -227,6 +227,7 @@ static int usb6fire_fw_ezusb_upload(
 	ret = usb6fire_fw_ihex_init(fw, rec);
 	if (ret < 0) {
 		kfree(rec);
+		release_firmware(fw);
 		snd_printk(KERN_ERR PREFIX "error validating ezusb "
 				"firmware %s.\n", fwname);
 		return ret;
@@ -269,7 +270,6 @@ static int usb6fire_fw_ezusb_upload(
 	data = 0x00; /* resume ezusb cpu */
 	ret = usb6fire_fw_ezusb_write(device, 0xa0, 0xe600, &data, 1);
 	if (ret < 0) {
-		release_firmware(fw);
 		snd_printk(KERN_ERR PREFIX "unable to upload ezusb "
 				"firmware %s: end message.\n", fwname);
 		return ret;
diff --git a/sound/usb/6fire/pcm.c b/sound/usb/6fire/pcm.c
index b137b25865cc..d144cdb2f159 100644
--- a/sound/usb/6fire/pcm.c
+++ b/sound/usb/6fire/pcm.c
@@ -395,12 +395,12 @@ static int usb6fire_pcm_open(struct snd_pcm_substream *alsa_sub)
 	alsa_rt->hw = pcm_hw;
 
 	if (alsa_sub->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		if (rt->rate >= 0)
+		if (rt->rate < ARRAY_SIZE(rates))
 			alsa_rt->hw.rates = rates_alsaid[rt->rate];
 		alsa_rt->hw.channels_max = OUT_N_CHANNELS;
 		sub = &rt->playback;
 	} else if (alsa_sub->stream == SNDRV_PCM_STREAM_CAPTURE) {
-		if (rt->rate >= 0)
+		if (rt->rate < ARRAY_SIZE(rates))
 			alsa_rt->hw.rates = rates_alsaid[rt->rate];
 		alsa_rt->hw.channels_max = IN_N_CHANNELS;
 		sub = &rt->capture;
diff --git a/sound/usb/card.c b/sound/usb/card.c
index a90662af2d6b..220c6167dd86 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -48,6 +48,7 @@
 #include <linux/usb/audio.h>
 #include <linux/usb/audio-v2.h>
 
+#include <sound/control.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/pcm.h>
@@ -492,14 +493,6 @@ static void *snd_usb_audio_probe(struct usb_device *dev,
 		}
 	}
 
-	chip->txfr_quirk = 0;
-	err = 1; /* continue */
-	if (quirk && quirk->ifnum != QUIRK_NO_INTERFACE) {
-		/* need some special handlings */
-		if ((err = snd_usb_create_quirk(chip, intf, &usb_audio_driver, quirk)) < 0)
-			goto __error;
-	}
-
 	/*
 	 * For devices with more than one control interface, we assume the
 	 * first contains the audio controls. We might need a more specific
@@ -508,6 +501,14 @@ static void *snd_usb_audio_probe(struct usb_device *dev,
 	if (!chip->ctrl_intf)
 		chip->ctrl_intf = alts;
 
+	chip->txfr_quirk = 0;
+	err = 1; /* continue */
+	if (quirk && quirk->ifnum != QUIRK_NO_INTERFACE) {
+		/* need some special handlings */
+		if ((err = snd_usb_create_quirk(chip, intf, &usb_audio_driver, quirk)) < 0)
+			goto __error;
+	}
+
 	if (err > 0) {
 		/* create normal USB audio interfaces */
 		if (snd_usb_create_streams(chip, ifnum) < 0 ||
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index eab06edcc9b7..c22fa76e363a 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -86,16 +86,6 @@ struct mixer_build {
 	const struct usbmix_selector_map *selector_map;
 };
 
-enum {
-	USB_MIXER_BOOLEAN,
-	USB_MIXER_INV_BOOLEAN,
-	USB_MIXER_S8,
-	USB_MIXER_U8,
-	USB_MIXER_S16,
-	USB_MIXER_U16,
-};
-
-
 /*E-mu 0202/0404/0204 eXtension Unit(XU) control*/
 enum {
 	USB_XU_CLOCK_RATE 		= 0xe301,
@@ -535,20 +525,21 @@ static int check_matrix_bitmap(unsigned char *bmap, int ich, int och, int num_ou
  * if failed, give up and free the control instance.
  */
 
-static int add_control_to_empty(struct mixer_build *state, struct snd_kcontrol *kctl)
+int snd_usb_mixer_add_control(struct usb_mixer_interface *mixer,
+			      struct snd_kcontrol *kctl)
 {
 	struct usb_mixer_elem_info *cval = kctl->private_data;
 	int err;
 
-	while (snd_ctl_find_id(state->chip->card, &kctl->id))
+	while (snd_ctl_find_id(mixer->chip->card, &kctl->id))
 		kctl->id.index++;
-	if ((err = snd_ctl_add(state->chip->card, kctl)) < 0) {
+	if ((err = snd_ctl_add(mixer->chip->card, kctl)) < 0) {
 		snd_printd(KERN_ERR "cannot add control (err = %d)\n", err);
 		return err;
 	}
 	cval->elem_id = &kctl->id;
-	cval->next_id_elem = state->mixer->id_elems[cval->id];
-	state->mixer->id_elems[cval->id] = cval;
+	cval->next_id_elem = mixer->id_elems[cval->id];
+	mixer->id_elems[cval->id] = cval;
 	return 0;
 }
 
@@ -984,6 +975,9 @@ static struct snd_kcontrol_new usb_feature_unit_ctl_ro = {
 	.put = NULL,
 };
 
+/* This symbol is exported in order to allow the mixer quirks to
+ * hook up to the standard feature unit control mechanism */
+struct snd_kcontrol_new *snd_usb_feature_unit_ctl = &usb_feature_unit_ctl;
 
 /*
  * build a feature control
@@ -1176,7 +1170,7 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
 
 	snd_printdd(KERN_INFO "[%d] FU [%s] ch = %d, val = %d/%d/%d\n",
 		    cval->id, kctl->id.name, cval->channels, cval->min, cval->max, cval->res);
-	add_control_to_empty(state, kctl);
+	snd_usb_mixer_add_control(state->mixer, kctl);
 }
 
 
@@ -1340,7 +1334,7 @@ static void build_mixer_unit_ctl(struct mixer_build *state,
 
 	snd_printdd(KERN_INFO "[%d] MU [%s] ch = %d, val = %d/%d\n",
 		    cval->id, kctl->id.name, cval->channels, cval->min, cval->max);
-	add_control_to_empty(state, kctl);
+	snd_usb_mixer_add_control(state->mixer, kctl);
 }
 
 
@@ -1641,7 +1635,7 @@ static int build_audio_procunit(struct mixer_build *state, int unitid, void *raw
 
 		snd_printdd(KERN_INFO "[%d] PU [%s] ch = %d, val = %d/%d\n",
 			    cval->id, kctl->id.name, cval->channels, cval->min, cval->max);
-		if ((err = add_control_to_empty(state, kctl)) < 0)
+		if ((err = snd_usb_mixer_add_control(state->mixer, kctl)) < 0)
 			return err;
 	}
 	return 0;
@@ -1858,7 +1852,7 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid, void
 
 	snd_printdd(KERN_INFO "[%d] SU [%s] items = %d\n",
 		    cval->id, kctl->id.name, desc->bNrInPins);
-	if ((err = add_control_to_empty(state, kctl)) < 0)
+	if ((err = snd_usb_mixer_add_control(state->mixer, kctl)) < 0)
 		return err;
 
 	return 0;
diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h
index b4a2c8165e4b..ae1a14dcfe82 100644
--- a/sound/usb/mixer.h
+++ b/sound/usb/mixer.h
@@ -24,7 +24,16 @@ struct usb_mixer_interface {
 	u8 xonar_u1_status;
 };
 
-#define MAX_CHANNELS	10	/* max logical channels */
+#define MAX_CHANNELS	16	/* max logical channels */
+
+enum {
+	USB_MIXER_BOOLEAN,
+	USB_MIXER_INV_BOOLEAN,
+	USB_MIXER_S8,
+	USB_MIXER_U8,
+	USB_MIXER_S16,
+	USB_MIXER_U16,
+};
 
 struct usb_mixer_elem_info {
 	struct usb_mixer_interface *mixer;
@@ -55,4 +64,7 @@ int snd_usb_mixer_set_ctl_value(struct usb_mixer_elem_info *cval,
 void snd_usb_mixer_inactivate(struct usb_mixer_interface *mixer);
 int snd_usb_mixer_activate(struct usb_mixer_interface *mixer);
 
+int snd_usb_mixer_add_control(struct usb_mixer_interface *mixer,
+			      struct snd_kcontrol *kctl);
+
 #endif /* __USBMIXER_H */
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index 9146cffa6ede..3d0f4873112b 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -40,6 +40,8 @@
 #include "mixer_quirks.h"
 #include "helper.h"
 
+extern struct snd_kcontrol_new *snd_usb_feature_unit_ctl;
+
 /*
  * Sound Blaster remote control configuration
  *
@@ -492,6 +494,69 @@ static int snd_nativeinstruments_create_mixer(struct usb_mixer_interface *mixer,
 	return err;
 }
 
+/* M-Audio FastTrack Ultra quirks */
+
+/* private_free callback */
+static void usb_mixer_elem_free(struct snd_kcontrol *kctl)
+{
+	kfree(kctl->private_data);
+	kctl->private_data = NULL;
+}
+
+static int snd_maudio_ftu_create_ctl(struct usb_mixer_interface *mixer,
+				     int in, int out, const char *name)
+{
+	struct usb_mixer_elem_info *cval;
+	struct snd_kcontrol *kctl;
+
+	cval = kzalloc(sizeof(*cval), GFP_KERNEL);
+	if (!cval)
+		return -ENOMEM;
+
+	cval->id = 5;
+	cval->mixer = mixer;
+	cval->val_type = USB_MIXER_S16;
+	cval->channels = 1;
+	cval->control = out + 1;
+	cval->cmask = 1 << in;
+
+	kctl = snd_ctl_new1(snd_usb_feature_unit_ctl, cval);
+	if (!kctl) {
+		kfree(cval);
+		return -ENOMEM;
+	}
+
+	snprintf(kctl->id.name, sizeof(kctl->id.name), name);
+	kctl->private_free = usb_mixer_elem_free;
+	return snd_usb_mixer_add_control(mixer, kctl);
+}
+
+static int snd_maudio_ftu_create_mixer(struct usb_mixer_interface *mixer)
+{
+	char name[64];
+	int in, out, err;
+
+	for (out = 0; out < 8; out++) {
+		for (in = 0; in < 8; in++) {
+			snprintf(name, sizeof(name),
+				 "AIn%d - Out%d Capture Volume", in  + 1, out + 1);
+			err = snd_maudio_ftu_create_ctl(mixer, in, out, name);
+			if (err < 0)
+				return err;
+		}
+
+		for (in = 8; in < 16; in++) {
+			snprintf(name, sizeof(name),
+				 "DIn%d - Out%d Playback Volume", in - 7, out + 1);
+			err = snd_maudio_ftu_create_ctl(mixer, in, out, name);
+			if (err < 0)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
 void snd_emuusb_set_samplerate(struct snd_usb_audio *chip,
 			       unsigned char samplerate_id)
 {
@@ -533,6 +598,11 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer)
 					      snd_audigy2nx_proc_read);
 		break;
 
+	case USB_ID(0x0763, 0x2080): /* M-Audio Fast Track Ultra */
+	case USB_ID(0x0763, 0x2081): /* M-Audio Fast Track Ultra 8R */
+		err = snd_maudio_ftu_create_mixer(mixer);
+		break;
+
 	case USB_ID(0x0b05, 0x1739):
 	case USB_ID(0x0b05, 0x1743):
 		err = snd_xonar_u1_controls_create(mixer);
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 78792a8900c3..0b2ae8e1c02d 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -1988,7 +1988,7 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 		.data = & (const struct snd_usb_audio_quirk[]) {
 			{
 				.ifnum = 0,
-				.type = QUIRK_IGNORE_INTERFACE
+				.type = QUIRK_AUDIO_STANDARD_MIXER,
 			},
 			{
 				.ifnum = 1,
@@ -2055,7 +2055,7 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 		.data = & (const struct snd_usb_audio_quirk[]) {
 			{
 				.ifnum = 0,
-				.type = QUIRK_IGNORE_INTERFACE
+				.type = QUIRK_AUDIO_STANDARD_MIXER,
 			},
 			{
 				.ifnum = 1,
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index bd13d7257240..090e1930dfdc 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -19,6 +19,7 @@
 #include <linux/usb.h>
 #include <linux/usb/audio.h>
 
+#include <sound/control.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/pcm.h>
@@ -263,6 +264,20 @@ static int create_uaxx_quirk(struct snd_usb_audio *chip,
 }
 
 /*
+ * Create a standard mixer for the specified interface.
+ */
+static int create_standard_mixer_quirk(struct snd_usb_audio *chip,
+				       struct usb_interface *iface,
+				       struct usb_driver *driver,
+				       const struct snd_usb_audio_quirk *quirk)
+{
+	if (quirk->ifnum < 0)
+		return 0;
+
+	return snd_usb_create_mixer(chip, quirk->ifnum, 0);
+}
+
+/*
  * audio-interface quirks
  *
  * returns zero if no standard audio/MIDI parsing is needed.
@@ -294,7 +309,8 @@ int snd_usb_create_quirk(struct snd_usb_audio *chip,
 		[QUIRK_AUDIO_STANDARD_INTERFACE] = create_standard_audio_quirk,
 		[QUIRK_AUDIO_FIXED_ENDPOINT] = create_fixed_stream_quirk,
 		[QUIRK_AUDIO_EDIROL_UAXX] = create_uaxx_quirk,
-		[QUIRK_AUDIO_ALIGN_TRANSFER] = create_align_transfer_quirk
+		[QUIRK_AUDIO_ALIGN_TRANSFER] = create_align_transfer_quirk,
+		[QUIRK_AUDIO_STANDARD_MIXER] = create_standard_mixer_quirk,
 	};
 
 	if (quirk->type < QUIRK_TYPE_COUNT) {
@@ -387,7 +403,7 @@ static int snd_usb_cm106_boot_quirk(struct usb_device *dev)
 static int snd_usb_cm6206_boot_quirk(struct usb_device *dev)
 {
 	int err, reg;
-	int val[] = {0x200c, 0x3000, 0xf800, 0x143f, 0x0000, 0x3000};
+	int val[] = {0x2004, 0x3000, 0xf800, 0x143f, 0x0000, 0x3000};
 
 	for (reg = 0; reg < ARRAY_SIZE(val); reg++) {
 		err = snd_usb_cm106_write_int_reg(dev, reg, val[reg]);
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index 32f2a97f2f14..1e79986b5777 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -84,6 +84,7 @@ enum quirk_type {
 	QUIRK_AUDIO_FIXED_ENDPOINT,
 	QUIRK_AUDIO_EDIROL_UAXX,
 	QUIRK_AUDIO_ALIGN_TRANSFER,
+	QUIRK_AUDIO_STANDARD_MIXER,
 
 	QUIRK_TYPE_COUNT
 };
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 1455413ec7a7..940257b5774e 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -215,11 +215,13 @@ LIB_FILE=$(OUTPUT)libperf.a
 LIB_H += ../../include/linux/perf_event.h
 LIB_H += ../../include/linux/rbtree.h
 LIB_H += ../../include/linux/list.h
+LIB_H += ../../include/linux/const.h
 LIB_H += ../../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
 LIB_H += util/include/linux/bitops.h
 LIB_H += util/include/linux/compiler.h
+LIB_H += util/include/linux/const.h
 LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
 LIB_H += util/include/linux/list.h
@@ -631,7 +633,7 @@ prefix_SQ = $(subst ','\'',$(prefix))
 
 SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
 
-LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive $(EXTLIBS)
+LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
 
 ALL_CFLAGS += $(BASIC_CFLAGS)
 ALL_CFLAGS += $(ARCH_CFLAGS)
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index e18eb7ed30ae..7b139e1e7e86 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -8,8 +8,6 @@
 #include "builtin.h"
 
 #include "util/util.h"
-
-#include "util/util.h"
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0974f957b8fa..8e2c85798185 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -823,6 +823,16 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 
 	symbol__init();
 
+	if (symbol_conf.kptr_restrict)
+		pr_warning(
+"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
+"check /proc/sys/kernel/kptr_restrict.\n\n"
+"Samples in kernel functions may not be resolved if a suitable vmlinux\n"
+"file is not found in the buildid cache or in the vmlinux path.\n\n"
+"Samples in kernel modules won't be resolved at all.\n\n"
+"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
+"even with a suitable vmlinux or kallsyms file.\n\n");
+
 	if (no_buildid_cache || no_buildid)
 		disable_buildid_cache();
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 498c6f70a747..287a173523a7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -116,6 +116,9 @@ static int process_sample_event(union perf_event *event,
 	if (al.filtered || (hide_unresolved && al.sym == NULL))
 		return 0;
 
+	if (al.map != NULL)
+		al.map->dso->hit = 1;
+
 	if (perf_session__add_hist_entry(session, &al, sample, evsel)) {
 		pr_debug("problem incrementing symbol period, skipping event\n");
 		return -1;
@@ -249,6 +252,8 @@ static int __cmd_report(void)
 	u64 nr_samples;
 	struct perf_session *session;
 	struct perf_evsel *pos;
+	struct map *kernel_map;
+	struct kmap *kernel_kmap;
 	const char *help = "For a higher level overview, try: perf report --sort comm,dso";
 
 	signal(SIGINT, sig_handler);
@@ -268,6 +273,24 @@ static int __cmd_report(void)
 	if (ret)
 		goto out_delete;
 
+	kernel_map = session->host_machine.vmlinux_maps[MAP__FUNCTION];
+	kernel_kmap = map__kmap(kernel_map);
+	if (kernel_map == NULL ||
+	    (kernel_map->dso->hit &&
+	     (kernel_kmap->ref_reloc_sym == NULL ||
+	      kernel_kmap->ref_reloc_sym->addr == 0))) {
+		const struct dso *kdso = kernel_map->dso;
+
+		ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) were restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict before running 'perf record'.\n\n%s\n\n"
+"Samples in kernel modules can't be resolved as well.\n\n",
+			    RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION]) ?
+"As no suitable kallsyms nor vmlinux was found, kernel samples\n"
+"can't be resolved." :
+"If some relocation was applied (e.g. kexec) symbols may be misresolved.");
+	}
+
 	if (dump_trace) {
 		perf_session__fprintf_nr_events(session, stdout);
 		goto out_delete;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 974f6d3f4e53..22747de7234b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -10,7 +10,6 @@
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/trace-event.h"
-#include "util/parse-options.h"
 #include "util/util.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index b67186228c89..2da9162262b0 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -474,7 +474,7 @@ static int test__basic_mmap(void)
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
-	int sample_size = perf_sample_size(attr.sample_type);
+	int sample_size = __perf_evsel__sample_size(attr.sample_type);
 
 	for (i = 0; i < nsyscalls; ++i) {
 		char name[64];
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 2d7934e9de38..f2f3f4937aa2 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -62,8 +62,6 @@
 #include <linux/unistd.h>
 #include <linux/types.h>
 
-#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
-
 static struct perf_top top = {
 	.count_filter		= 5,
 	.delay_secs		= 2,
@@ -82,6 +80,8 @@ static bool			use_tui, use_stdio;
 
 static int			default_interval		=      0;
 
+static bool			kptr_restrict_warned;
+static bool			vmlinux_warned;
 static bool			inherit				=  false;
 static int			realtime_prio			=      0;
 static bool			group				=  false;
@@ -740,7 +740,22 @@ static void perf_event__process_sample(const union perf_event *event,
 	    al.filtered)
 		return;
 
+	if (!kptr_restrict_warned &&
+	    symbol_conf.kptr_restrict &&
+	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
+		ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict.\n\n"
+"Kernel%s samples will not be resolved.\n",
+			  !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
+			  " modules" : "");
+		if (use_browser <= 0)
+			sleep(5);
+		kptr_restrict_warned = true;
+	}
+
 	if (al.sym == NULL) {
+		const char *msg = "Kernel samples will not be resolved.\n";
 		/*
 		 * As we do lazy loading of symtabs we only will know if the
 		 * specified vmlinux file is invalid when we actually have a
@@ -752,12 +767,20 @@ static void perf_event__process_sample(const union perf_event *event,
 		 * --hide-kernel-symbols, even if the user specifies an
 		 * invalid --vmlinux ;-)
 		 */
-		if (al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
+		if (!kptr_restrict_warned && !vmlinux_warned &&
+		    al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
 		    RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
-			ui__warning("The %s file can't be used\n",
-				    symbol_conf.vmlinux_name);
-			exit_browser(0);
-			exit(1);
+			if (symbol_conf.vmlinux_name) {
+				ui__warning("The %s file can't be used.\n%s",
+					    symbol_conf.vmlinux_name, msg);
+			} else {
+				ui__warning("A vmlinux file was not found.\n%s",
+					    msg);
+			}
+
+			if (use_browser <= 0)
+				sleep(5);
+			vmlinux_warned = true;
 		}
 
 		return;
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 26d4d3fd6deb..ad73300f7bac 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -23,12 +23,7 @@ if test -d ../../.git -o -f ../../.git &&
 then
 	VN=$(echo "$VN" | sed -e 's/-/./g');
 else
-	eval $(grep '^VERSION[[:space:]]*=' ../../Makefile|tr -d ' ')
-	eval $(grep '^PATCHLEVEL[[:space:]]*=' ../../Makefile|tr -d ' ')
-	eval $(grep '^SUBLEVEL[[:space:]]*=' ../../Makefile|tr -d ' ')
-	eval $(grep '^EXTRAVERSION[[:space:]]*=' ../../Makefile|tr -d ' ')
-
-	VN="${VERSION}.${PATCHLEVEL}.${SUBLEVEL}${EXTRAVERSION}"
+	VN=$(MAKEFLAGS= make -sC ../.. kernelversion)
 fi
 
 VN=$(expr "$VN" : v*'\(.*\)')
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 6635fcd11ca5..3c1b8a632101 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -35,22 +35,6 @@ const char *perf_event__name(unsigned int id)
 	return perf_event__names[id];
 }
 
-int perf_sample_size(u64 sample_type)
-{
-	u64 mask = sample_type & PERF_SAMPLE_MASK;
-	int size = 0;
-	int i;
-
-	for (i = 0; i < 64; i++) {
-		if (mask & (1ULL << i))
-			size++;
-	}
-
-	size *= sizeof(u64);
-
-	return size;
-}
-
 static struct perf_sample synth_sample = {
 	.pid	   = -1,
 	.tid	   = -1,
@@ -553,9 +537,18 @@ static int perf_event__process_kernel_mmap(union perf_event *event,
 			goto out_problem;
 
 		perf_event__set_kernel_mmap_len(event, machine->vmlinux_maps);
-		perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
-							 symbol_name,
-							 event->mmap.pgoff);
+
+		/*
+		 * Avoid using a zero address (kptr_restrict) for the ref reloc
+		 * symbol. Effectively having zero here means that at record
+		 * time /proc/sys/kernel/kptr_restrict was non zero.
+		 */
+		if (event->mmap.pgoff != 0) {
+			perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
+								 symbol_name,
+								 event->mmap.pgoff);
+		}
+
 		if (machine__is_default_guest(machine)) {
 			/*
 			 * preload dso of guest kernel and modules
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index c08332871408..1d7f66488a88 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -82,8 +82,6 @@ struct perf_sample {
 	struct ip_callchain *callchain;
 };
 
-int perf_sample_size(u64 sample_type);
-
 #define BUILD_ID_SIZE 20
 
 struct build_id_event {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 50aa34879c33..b021ea9265c3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -12,7 +12,6 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "util.h"
-#include "debug.h"
 
 #include <sys/mman.h>
 
@@ -257,19 +256,15 @@ int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel,
+static int __perf_evlist__mmap(struct perf_evlist *evlist,
 			       int idx, int prot, int mask, int fd)
 {
 	evlist->mmap[idx].prev = 0;
 	evlist->mmap[idx].mask = mask;
 	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
 				      MAP_SHARED, fd, 0);
-	if (evlist->mmap[idx].base == MAP_FAILED) {
-		if (evlist->cpus->map[idx] == -1 && evsel->attr.inherit)
-			ui__warning("Inherit is not allowed on per-task "
-				    "events using mmap.\n");
+	if (evlist->mmap[idx].base == MAP_FAILED)
 		return -1;
-	}
 
 	perf_evlist__add_pollfd(evlist, fd);
 	return 0;
@@ -289,7 +284,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 
 				if (output == -1) {
 					output = fd;
-					if (__perf_evlist__mmap(evlist, evsel, cpu,
+					if (__perf_evlist__mmap(evlist, cpu,
 								prot, mask, output) < 0)
 						goto out_unmap;
 				} else {
@@ -329,7 +324,7 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 
 			if (output == -1) {
 				output = fd;
-				if (__perf_evlist__mmap(evlist, evsel, thread,
+				if (__perf_evlist__mmap(evlist, thread,
 							prot, mask, output) < 0)
 					goto out_unmap;
 			} else {
@@ -460,33 +455,46 @@ int perf_evlist__set_filters(struct perf_evlist *evlist)
 	return 0;
 }
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist)
+bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist)
 {
-	struct perf_evsel *pos;
-	u64 type = 0;
-
-	list_for_each_entry(pos, &evlist->entries, node) {
-		if (!type)
-			type = pos->attr.sample_type;
-		else if (type != pos->attr.sample_type)
-			die("non matching sample_type");
+	struct perf_evsel *pos, *first;
+
+	pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+	list_for_each_entry_continue(pos, &evlist->entries, node) {
+		if (first->attr.sample_type != pos->attr.sample_type)
+			return false;
 	}
 
-	return type;
+	return true;
 }
 
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
+u64 perf_evlist__sample_type(const struct perf_evlist *evlist)
+{
+	struct perf_evsel *first;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return first->attr.sample_type;
+}
+
+bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist)
 {
-	bool value = false, first = true;
-	struct perf_evsel *pos;
-
-	list_for_each_entry(pos, &evlist->entries, node) {
-		if (first) {
-			value = pos->attr.sample_id_all;
-			first = false;
-		} else if (value != pos->attr.sample_id_all)
-			die("non matching sample_id_all");
+	struct perf_evsel *pos, *first;
+
+	pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+	list_for_each_entry_continue(pos, &evlist->entries, node) {
+		if (first->attr.sample_id_all != pos->attr.sample_id_all)
+			return false;
 	}
 
-	return value;
+	return true;
+}
+
+bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
+{
+	struct perf_evsel *first;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return first->attr.sample_id_all;
 }
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 0a1ef1f051f0..b2b862374f37 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -66,7 +66,9 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
 void perf_evlist__delete_maps(struct perf_evlist *evlist);
 int perf_evlist__set_filters(struct perf_evlist *evlist);
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist);
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist);
+u64 perf_evlist__sample_type(const struct perf_evlist *evlist);
+bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist);
 
+bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
+bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ee0fe0dffa71..0239eb87b232 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,6 +15,22 @@
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
+int __perf_evsel__sample_size(u64 sample_type)
+{
+	u64 mask = sample_type & PERF_SAMPLE_MASK;
+	int size = 0;
+	int i;
+
+	for (i = 0; i < 64; i++) {
+		if (mask & (1ULL << i))
+			size++;
+	}
+
+	size *= sizeof(u64);
+
+	return size;
+}
+
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
@@ -35,7 +51,17 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
+	int cpu, thread;
 	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
+
+	if (evsel->fd) {
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			for (thread = 0; thread < nthreads; thread++) {
+				FD(evsel, cpu, thread) = -1;
+			}
+		}
+	}
+
 	return evsel->fd != NULL ? 0 : -ENOMEM;
 }
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index f79bb2c09a6c..7e9366e4490b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -149,4 +149,11 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
 	return __perf_evsel__read(evsel, ncpus, nthreads, true);
 }
 
+int __perf_evsel__sample_size(u64 sample_type);
+
+static inline int perf_evsel__sample_size(struct perf_evsel *evsel)
+{
+	return __perf_evsel__sample_size(evsel->attr.sample_type);
+}
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 0717bebc7649..afb0849fe530 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -193,9 +193,13 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 	     *linkname = malloc(size), *targetname;
 	int len, err = -1;
 
-	if (is_kallsyms)
+	if (is_kallsyms) {
+		if (symbol_conf.kptr_restrict) {
+			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
+			return 0;
+		}
 		realname = (char *)name;
-	else
+	} else
 		realname = realpath(name, NULL);
 
 	if (realname == NULL || filename == NULL || linkname == NULL)
diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h
new file mode 100644
index 000000000000..1b476c9ae649
--- /dev/null
+++ b/tools/perf/util/include/linux/const.h
@@ -0,0 +1 @@
+#include "../../../../include/linux/const.h"
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 69436b3200a4..a9ac0504aabd 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -674,7 +674,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	struct perf_evlist *evlist = &pevlist->evlist;
 	union perf_event *event;
 	int sample_id_all = 1, cpu;
-	static char *kwlist[] = {"sample_id_all", NULL, NULL};
+	static char *kwlist[] = {"cpu", "sample_id_all", NULL, NULL};
 	int err;
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
@@ -692,16 +692,14 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 
 		first = list_entry(evlist->entries.next, struct perf_evsel, node);
 		err = perf_event__parse_sample(event, first->attr.sample_type,
-					       perf_sample_size(first->attr.sample_type),
+					       perf_evsel__sample_size(first),
 					       sample_id_all, &pevent->sample);
-		if (err) {
-			pr_err("Can't parse sample, err = %d\n", err);
-			goto end;
-		}
-
+		if (err)
+			return PyErr_Format(PyExc_OSError,
+					    "perf: can't parse sample, err=%d", err);
 		return pyevent;
 	}
-end:
+
 	Py_INCREF(Py_None);
 	return Py_None;
 }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 64500fc78799..f5a8fbdd3f76 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -58,6 +58,16 @@ static int perf_session__open(struct perf_session *self, bool force)
 		goto out_close;
 	}
 
+	if (!perf_evlist__valid_sample_type(self->evlist)) {
+		pr_err("non matching sample_type");
+		goto out_close;
+	}
+
+	if (!perf_evlist__valid_sample_id_all(self->evlist)) {
+		pr_err("non matching sample_id_all");
+		goto out_close;
+	}
+
 	self->size = input_stat.st_size;
 	return 0;
 
@@ -97,7 +107,7 @@ out:
 void perf_session__update_sample_type(struct perf_session *self)
 {
 	self->sample_type = perf_evlist__sample_type(self->evlist);
-	self->sample_size = perf_sample_size(self->sample_type);
+	self->sample_size = __perf_evsel__sample_size(self->sample_type);
 	self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
 	perf_session__id_header_size(self);
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 516876dfbe52..eec196329fd9 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -676,9 +676,30 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
 	return count + moved;
 }
 
+static bool symbol__restricted_filename(const char *filename,
+					const char *restricted_filename)
+{
+	bool restricted = false;
+
+	if (symbol_conf.kptr_restrict) {
+		char *r = realpath(filename, NULL);
+
+		if (r != NULL) {
+			restricted = strcmp(r, restricted_filename) == 0;
+			free(r);
+			return restricted;
+		}
+	}
+
+	return restricted;
+}
+
 int dso__load_kallsyms(struct dso *dso, const char *filename,
 		       struct map *map, symbol_filter_t filter)
 {
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return -1;
+
 	if (dso__load_all_kallsyms(dso, filename, map) < 0)
 		return -1;
 
@@ -1790,6 +1811,9 @@ static int machine__create_modules(struct machine *machine)
 		modules = path;
 	}
 
+	if (symbol__restricted_filename(path, "/proc/modules"))
+		return -1;
+
 	file = fopen(modules, "r");
 	if (file == NULL)
 		return -1;
@@ -2239,6 +2263,9 @@ static u64 machine__get_kernel_start_addr(struct machine *machine)
 		}
 	}
 
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return 0;
+
 	if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
 		return 0;
 
@@ -2410,6 +2437,25 @@ static int setup_list(struct strlist **list, const char *list_str,
 	return 0;
 }
 
+static bool symbol__read_kptr_restrict(void)
+{
+	bool value = false;
+
+	if (geteuid() != 0) {
+		FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
+		if (fp != NULL) {
+			char line[8];
+
+			if (fgets(line, sizeof(line), fp) != NULL)
+				value = atoi(line) != 0;
+
+			fclose(fp);
+		}
+	}
+
+	return value;
+}
+
 int symbol__init(void)
 {
 	const char *symfs;
@@ -2456,6 +2502,8 @@ int symbol__init(void)
 	if (symfs != symbol_conf.symfs)
 		free((void *)symfs);
 
+	symbol_conf.kptr_restrict = symbol__read_kptr_restrict();
+
 	symbol_conf.initialized = true;
 	return 0;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 242de0101a86..325ee36a9d29 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -75,7 +75,8 @@ struct symbol_conf {
 			use_callchain,
 			exclude_other,
 			show_cpu_utilization,
-			initialized;
+			initialized,
+			kptr_restrict;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 1e88485c16a0..0a7ed5b5e281 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -2187,6 +2187,7 @@ static const struct flag flags[] = {
 	{ "TASKLET_SOFTIRQ", 6 },
 	{ "SCHED_SOFTIRQ", 7 },
 	{ "HRTIMER_SOFTIRQ", 8 },
+	{ "RCU_SOFTIRQ", 9 },
 
 	{ "HRTIMER_NORESTART", 0 },
 	{ "HRTIMER_RESTART", 1 },
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 1fd29b2daa92..cef28e6632b9 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -788,7 +788,7 @@ sub wait_for_input
 
 sub reboot_to {
     if ($reboot_type eq "grub") {
-	run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch; reboot)'";
+	run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch && reboot)'";
 	return;
     }
 
@@ -1480,7 +1480,7 @@ sub process_config_ignore {
 	or dodie "Failed to read $config";
 
     while (<IN>) {
-	if (/^(.*?(CONFIG\S*)(=.*| is not set))/) {
+	if (/^((CONFIG\S*)=.*)/) {
 	    $config_ignore{$2} = $1;
 	}
     }
@@ -1638,7 +1638,7 @@ sub run_config_bisect {
 	if (!$found) {
 	    # try the other half
 	    doprint "Top half produced no set configs, trying bottom half\n";
-	    @tophalf = @start_list[$half .. $#start_list];
+	    @tophalf = @start_list[$half + 1 .. $#start_list];
 	    create_config @tophalf;
 	    read_current_config \%current_config;
 	    foreach my $config (@tophalf) {
@@ -1690,7 +1690,7 @@ sub run_config_bisect {
 	# remove half the configs we are looking at and see if
 	# they are good.
 	$half = int($#start_list / 2);
-    } while ($half > 0);
+    } while ($#start_list > 0);
 
     # we found a single config, try it again unless we are running manually
 
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index df0c6d2c3860..74d3331bdaf9 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -198,6 +198,14 @@ const struct option longopts[] = {
 		.val = 'h',
 	},
 	{
+		.name = "event-idx",
+		.val = 'E',
+	},
+	{
+		.name = "no-event-idx",
+		.val = 'e',
+	},
+	{
 		.name = "indirect",
 		.val = 'I',
 	},
@@ -211,13 +219,17 @@ const struct option longopts[] = {
 
 static void help()
 {
-	fprintf(stderr, "Usage: virtio_test [--help] [--no-indirect]\n");
+	fprintf(stderr, "Usage: virtio_test [--help]"
+		" [--no-indirect]"
+		" [--no-event-idx]"
+		"\n");
 }
 
 int main(int argc, char **argv)
 {
 	struct vdev_info dev;
-	unsigned long long features = 1ULL << VIRTIO_RING_F_INDIRECT_DESC;
+	unsigned long long features = (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
+		(1ULL << VIRTIO_RING_F_EVENT_IDX);
 	int o;
 
 	for (;;) {
@@ -228,6 +240,9 @@ int main(int argc, char **argv)
 		case '?':
 			help();
 			exit(2);
+		case 'e':
+			features &= ~(1ULL << VIRTIO_RING_F_EVENT_IDX);
+			break;
 		case 'h':
 			help();
 			goto done;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 22cdb960660a..96ebc0679415 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -467,12 +467,8 @@ static struct kvm *kvm_create_vm(void)
 		if (!kvm->buses[i])
 			goto out_err;
 	}
-	spin_lock_init(&kvm->mmu_lock);
-
-	r = kvm_init_mmu_notifier(kvm);
-	if (r)
-		goto out_err;
 
+	spin_lock_init(&kvm->mmu_lock);
 	kvm->mm = current->mm;
 	atomic_inc(&kvm->mm->mm_count);
 	kvm_eventfd_init(kvm);
@@ -480,6 +476,11 @@ static struct kvm *kvm_create_vm(void)
 	mutex_init(&kvm->irq_lock);
 	mutex_init(&kvm->slots_lock);
 	atomic_set(&kvm->users_count, 1);
+
+	r = kvm_init_mmu_notifier(kvm);
+	if (r)
+		goto out_err;
+
 	raw_spin_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
 	raw_spin_unlock(&kvm_lock);
@@ -651,7 +652,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	/* We can read the guest memory with __xxx_user() later on. */
 	if (user_alloc &&
 	    ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
-	     !access_ok(VERIFY_WRITE, mem->userspace_addr, mem->memory_size)))
+	     !access_ok(VERIFY_WRITE,
+			(void __user *)(unsigned long)mem->userspace_addr,
+			mem->memory_size)))
 		goto out;
 	if (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
 		goto out;