Merge commit 'v2.6.34-rc1' into perf/urgent

Conflicts:
	tools/perf/util/probe-event.c

Merge reason: Pick up -rc1 and resolve the conflict as well.

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

99 files changed, 3651 insertions, 820 deletions

diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node
new file mode 100644
index 00000000000..49b82cad700
--- /dev/null
+++ b/Documentation/ABI/stable/sysfs-devices-node
@@ -0,0 +1,7 @@
+What:		/sys/devices/system/node/nodeX
+Date:		October 2002
+Contact:	Linux Memory Management list <linux-mm@kvack.org>
+Description:
+		When CONFIG_NUMA is enabled, this is a directory containing
+		information on node X such as what CPUs are local to the
+		node.
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index d2f90334bb9..4873c759d53 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -128,3 +128,17 @@ Description:
 		preferred request size for workloads where sustained
 		throughput is desired.  If no optimal I/O size is
 		reported this file contains 0.
+
+What:		/sys/block/<disk>/queue/nomerges
+Date:		January 2010
+Contact:
+Description:
+		Standard I/O elevator operations include attempts to
+		merge contiguous I/Os. For known random I/O loads these
+		attempts will always fail and result in extra cycles
+		being spent in the kernel. This allows one to turn off
+		this behavior on one of two ways: When set to 1, complex
+		merge checks are disabled, but the simple one-shot merges
+		with the previous I/O request are enabled. When set to 2,
+		all merge tries are disabled. The default value is 0 -
+		which enables all types of merge tries.
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb
index a07c0f366f9..a986e9bbba3 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb
+++ b/Documentation/ABI/testing/sysfs-bus-usb
@@ -159,3 +159,14 @@ Description:
 		device.  This is useful to ensure auto probing won't
 		match the driver to the device.  For example:
 		# echo "046d c315" > /sys/bus/usb/drivers/foo/remove_id
+
+What:		/sys/bus/usb/device/.../avoid_reset
+Date:		December 2009
+Contact:	Oliver Neukum <oliver@neukum.org>
+Description:
+		Writing 1 to this file tells the kernel that this
+		device will morph into another mode when it is reset.
+		Drivers will not use reset for error handling for
+		such devices.
+Users:
+		usb_modeswitch
diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power
new file mode 100644
index 00000000000..6123c523bfd
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-power
@@ -0,0 +1,79 @@
+What:		/sys/devices/.../power/
+Date:		January 2009
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../power directory contains attributes
+		allowing the user space to check and modify some power
+		management related properties of given device.
+
+What:		/sys/devices/.../power/wakeup
+Date:		January 2009
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../power/wakeup attribute allows the user
+		space to check if the device is enabled to wake up the system
+		from sleep states, such as the memory sleep state (suspend to
+		RAM) and hibernation (suspend to disk), and to enable or disable
+		it to do that as desired.
+
+		Some devices support "wakeup" events, which are hardware signals
+		used to activate the system from a sleep state.  Such devices
+		have one of the following two values for the sysfs power/wakeup
+		file:
+
+		+ "enabled\n" to issue the events;
+		+ "disabled\n" not to do so;
+
+		In that cases the user space can change the setting represented
+		by the contents of this file by writing either "enabled", or
+		"disabled" to it.
+
+		For the devices that are not capable of generating system wakeup
+		events this file contains "\n".  In that cases the user space
+		cannot modify the contents of this file and the device cannot be
+		enabled to wake up the system.
+
+What:		/sys/devices/.../power/control
+Date:		January 2009
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../power/control attribute allows the user
+		space to control the run-time power management of the device.
+
+		All devices have one of the following two values for the
+		power/control file:
+
+		+ "auto\n" to allow the device to be power managed at run time;
+		+ "on\n" to prevent the device from being power managed;
+
+		The default for all devices is "auto", which means that they may
+		be subject to automatic power management, depending on their
+		drivers.  Changing this attribute to "on" prevents the driver
+		from power managing the device at run time.  Doing that while
+		the device is suspended causes it to be woken up.
+
+What:		/sys/devices/.../power/async
+Date:		January 2009
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../async attribute allows the user space to
+		enable or diasble the device's suspend and resume callbacks to
+		be executed asynchronously (ie. in separate threads, in parallel
+		with the main suspend/resume thread) during system-wide power
+		transitions (eg. suspend to RAM, hibernation).
+
+		All devices have one of the following two values for the
+		power/async file:
+
+		+ "enabled\n" to permit the asynchronous suspend/resume;
+		+ "disabled\n" to forbid it;
+
+		The value of this attribute may be changed by writing either
+		"enabled", or "disabled" to it.
+
+		It generally is unsafe to permit the asynchronous suspend/resume
+		of a device unless it is certain that all of the PM dependencies
+		of the device are known to the PM core.  However, for some
+		devices this attribute is set to "enabled" by bus type code or
+		device drivers and in that cases it should be safe to leave the
+		default value.
diff --git a/Documentation/ABI/testing/sysfs-platform-asus-laptop b/Documentation/ABI/testing/sysfs-platform-asus-laptop
index a1cb660c50c..1d775390e85 100644
--- a/Documentation/ABI/testing/sysfs-platform-asus-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-asus-laptop
@@ -1,4 +1,4 @@
-What:		/sys/devices/platform/asus-laptop/display
+What:		/sys/devices/platform/asus_laptop/display
 Date:		January 2007
 KernelVersion:	2.6.20
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
@@ -13,7 +13,7 @@ Description:
 		Ex: - 0 (0000b) means no display
 		    - 3 (0011b) CRT+LCD.
 
-What:		/sys/devices/platform/asus-laptop/gps
+What:		/sys/devices/platform/asus_laptop/gps
 Date:		January 2007
 KernelVersion:	2.6.20
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
@@ -21,7 +21,7 @@ Description:
 		Control the gps device. 1 means on, 0 means off.
 Users:		Lapsus
 
-What:		/sys/devices/platform/asus-laptop/ledd
+What:		/sys/devices/platform/asus_laptop/ledd
 Date:		January 2007
 KernelVersion:	2.6.20
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
@@ -29,11 +29,11 @@ Description:
 		Some models like the W1N have a LED display that can be
 		used to display several informations.
 		To control the LED display, use the following :
-		    echo 0x0T000DDD > /sys/devices/platform/asus-laptop/
+		    echo 0x0T000DDD > /sys/devices/platform/asus_laptop/
 		where T control the 3 letters display, and DDD the 3 digits display.
 		The DDD table can be found in Documentation/laptops/asus-laptop.txt
 
-What:		/sys/devices/platform/asus-laptop/bluetooth
+What:		/sys/devices/platform/asus_laptop/bluetooth
 Date:		January 2007
 KernelVersion:	2.6.20
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
@@ -42,7 +42,7 @@ Description:
 		This may control the led, the device or both.
 Users:		Lapsus
 
-What:		/sys/devices/platform/asus-laptop/wlan
+What:		/sys/devices/platform/asus_laptop/wlan
 Date:		January 2007
 KernelVersion:	2.6.20
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
diff --git a/Documentation/ABI/testing/sysfs-platform-eeepc-laptop b/Documentation/ABI/testing/sysfs-platform-eeepc-laptop
index 7445dfb321b..5b026c69587 100644
--- a/Documentation/ABI/testing/sysfs-platform-eeepc-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-eeepc-laptop
@@ -1,4 +1,4 @@
-What:		/sys/devices/platform/eeepc-laptop/disp
+What:		/sys/devices/platform/eeepc/disp
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
@@ -9,21 +9,21 @@ Description:
 		- 3 = LCD+CRT
 		If you run X11, you should use xrandr instead.
 
-What:		/sys/devices/platform/eeepc-laptop/camera
+What:		/sys/devices/platform/eeepc/camera
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
 Description:
 		Control the camera. 1 means on, 0 means off.
 
-What:		/sys/devices/platform/eeepc-laptop/cardr
+What:		/sys/devices/platform/eeepc/cardr
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
 Description:
 		Control the card reader. 1 means on, 0 means off.
 
-What:		/sys/devices/platform/eeepc-laptop/cpufv
+What:		/sys/devices/platform/eeepc/cpufv
 Date:		Jun 2009
 KernelVersion:	2.6.31
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
@@ -42,7 +42,7 @@ Description:
 		    `------------ Availables modes
 		For example, 0x301 means: mode 1 selected, 3 available modes.
 
-What:		/sys/devices/platform/eeepc-laptop/available_cpufv
+What:		/sys/devices/platform/eeepc/available_cpufv
 Date:		Jun 2009
 KernelVersion:	2.6.31
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index dcff4d0623a..d6a801f45b4 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -101,3 +101,16 @@ Description:
 
 		CAUTION: Using it will cause your machine's real-time (CMOS)
 		clock to be set to a random invalid time after a resume.
+
+What:		/sys/power/pm_async
+Date:		January 2009
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/power/pm_async file controls the switch allowing the
+		user space to enable or disable asynchronous suspend and resume
+		of devices.  If enabled, this feature will cause some device
+		drivers' suspend and resume callbacks to be executed in parallel
+		with each other and with the main suspend thread.  It is enabled
+		if this file contains "1", which is the default.  It may be
+		disabled by writing "0" to this file, in which case all devices
+		will be suspended and resumed synchronously.
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index f9a6e2c75f1..1b2dd4fc3db 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -45,7 +45,7 @@
      </sect1>
 
      <sect1><title>Atomic and pointer manipulation</title>
-!Iarch/x86/include/asm/atomic_32.h
+!Iarch/x86/include/asm/atomic.h
 !Iarch/x86/include/asm/unaligned.h
      </sect1>
 
diff --git a/Documentation/DocBook/deviceiobook.tmpl b/Documentation/DocBook/deviceiobook.tmpl
index 3ed88126ab8..c1ed6a49e59 100644
--- a/Documentation/DocBook/deviceiobook.tmpl
+++ b/Documentation/DocBook/deviceiobook.tmpl
@@ -316,7 +316,7 @@ CPU B:  spin_unlock_irqrestore(&amp;dev_lock, flags)
 
   <chapter id="pubfunctions">
      <title>Public Functions Provided</title>
-!Iarch/x86/include/asm/io_32.h
+!Iarch/x86/include/asm/io.h
 !Elib/iomap.c
   </chapter>
 
diff --git a/Documentation/DocBook/mac80211.tmpl b/Documentation/DocBook/mac80211.tmpl
index f3f37f141db..affb15a344a 100644
--- a/Documentation/DocBook/mac80211.tmpl
+++ b/Documentation/DocBook/mac80211.tmpl
@@ -144,7 +144,7 @@ usage should require reading the full document.
         this though and the recommendation to allow only a single
         interface in STA mode at first!
       </para>
-!Finclude/net/mac80211.h ieee80211_if_init_conf
+!Finclude/net/mac80211.h ieee80211_vif
     </chapter>
 
     <chapter id="rx-tx">
@@ -234,7 +234,6 @@ usage should require reading the full document.
       <title>Multiple queues and QoS support</title>
       <para>TBD</para>
 !Finclude/net/mac80211.h ieee80211_tx_queue_params
-!Finclude/net/mac80211.h ieee80211_tx_queue_stats
     </chapter>
 
     <chapter id="AP">
diff --git a/Documentation/DocBook/v4l/io.xml b/Documentation/DocBook/v4l/io.xml
index f92f24323b2..e870330cbf7 100644
--- a/Documentation/DocBook/v4l/io.xml
+++ b/Documentation/DocBook/v4l/io.xml
@@ -589,7 +589,8 @@ number of a video input as in &v4l2-input; field
 	    <entry></entry>
 	    <entry>A place holder for future extensions and custom
 (driver defined) buffer types
-<constant>V4L2_BUF_TYPE_PRIVATE</constant> and higher.</entry>
+<constant>V4L2_BUF_TYPE_PRIVATE</constant> and higher. Applications
+should set this to 0.</entry>
 	  </row>
 	</tbody>
       </tgroup>
diff --git a/Documentation/DocBook/v4l/vidioc-qbuf.xml b/Documentation/DocBook/v4l/vidioc-qbuf.xml
index 18708177815..b843bd7b389 100644
--- a/Documentation/DocBook/v4l/vidioc-qbuf.xml
+++ b/Documentation/DocBook/v4l/vidioc-qbuf.xml
@@ -54,12 +54,10 @@ to enqueue an empty (capturing) or filled (output) buffer in the
 driver's incoming queue. The semantics depend on the selected I/O
 method.</para>
 
-    <para>To enqueue a <link linkend="mmap">memory mapped</link>
-buffer applications set the <structfield>type</structfield> field of a
-&v4l2-buffer; to the same buffer type as previously &v4l2-format;
-<structfield>type</structfield> and &v4l2-requestbuffers;
-<structfield>type</structfield>, the <structfield>memory</structfield>
-field to <constant>V4L2_MEMORY_MMAP</constant> and the
+    <para>To enqueue a buffer applications set the <structfield>type</structfield>
+field of a &v4l2-buffer; to the same buffer type as was previously used
+with &v4l2-format; <structfield>type</structfield> and &v4l2-requestbuffers;
+<structfield>type</structfield>. Applications must also set the
 <structfield>index</structfield> field. Valid index numbers range from
 zero to the number of buffers allocated with &VIDIOC-REQBUFS;
 (&v4l2-requestbuffers; <structfield>count</structfield>) minus one. The
@@ -70,8 +68,19 @@ intended for output (<structfield>type</structfield> is
 <constant>V4L2_BUF_TYPE_VBI_OUTPUT</constant>) applications must also
 initialize the <structfield>bytesused</structfield>,
 <structfield>field</structfield> and
-<structfield>timestamp</structfield> fields. See <xref
-	linkend="buffer" /> for details. When
+<structfield>timestamp</structfield> fields, see <xref
+linkend="buffer" /> for details.
+Applications must also set <structfield>flags</structfield> to 0. If a driver
+supports capturing from specific video inputs and you want to specify a video
+input, then <structfield>flags</structfield> should be set to
+<constant>V4L2_BUF_FLAG_INPUT</constant> and the field
+<structfield>input</structfield> must be initialized to the desired input.
+The <structfield>reserved</structfield> field must be set to 0.
+</para>
+
+    <para>To enqueue a <link linkend="mmap">memory mapped</link>
+buffer applications set the <structfield>memory</structfield>
+field to <constant>V4L2_MEMORY_MMAP</constant>. When
 <constant>VIDIOC_QBUF</constant> is called with a pointer to this
 structure the driver sets the
 <constant>V4L2_BUF_FLAG_MAPPED</constant> and
@@ -81,14 +90,10 @@ structure the driver sets the
 &EINVAL;.</para>
 
     <para>To enqueue a <link linkend="userp">user pointer</link>
-buffer applications set the <structfield>type</structfield> field of a
-&v4l2-buffer; to the same buffer type as previously &v4l2-format;
-<structfield>type</structfield> and &v4l2-requestbuffers;
-<structfield>type</structfield>, the <structfield>memory</structfield>
-field to <constant>V4L2_MEMORY_USERPTR</constant> and the
+buffer applications set the <structfield>memory</structfield>
+field to <constant>V4L2_MEMORY_USERPTR</constant>, the
 <structfield>m.userptr</structfield> field to the address of the
-buffer and <structfield>length</structfield> to its size. When the
-buffer is intended for output additional fields must be set as above.
+buffer and <structfield>length</structfield> to its size.
 When <constant>VIDIOC_QBUF</constant> is called with a pointer to this
 structure the driver sets the <constant>V4L2_BUF_FLAG_QUEUED</constant>
 flag and clears the <constant>V4L2_BUF_FLAG_MAPPED</constant> and
@@ -96,13 +101,14 @@ flag and clears the <constant>V4L2_BUF_FLAG_MAPPED</constant> and
 <structfield>flags</structfield> field, or it returns an error code.
 This ioctl locks the memory pages of the buffer in physical memory,
 they cannot be swapped out to disk. Buffers remain locked until
-dequeued, until the &VIDIOC-STREAMOFF; or &VIDIOC-REQBUFS; ioctl are
+dequeued, until the &VIDIOC-STREAMOFF; or &VIDIOC-REQBUFS; ioctl is
 called, or until the device is closed.</para>
 
     <para>Applications call the <constant>VIDIOC_DQBUF</constant>
 ioctl to dequeue a filled (capturing) or displayed (output) buffer
 from the driver's outgoing queue. They just set the
-<structfield>type</structfield> and <structfield>memory</structfield>
+<structfield>type</structfield>, <structfield>memory</structfield>
+and <structfield>reserved</structfield>
 fields of a &v4l2-buffer; as above, when <constant>VIDIOC_DQBUF</constant>
 is called with a pointer to this structure the driver fills the
 remaining fields or returns an error code.</para>
diff --git a/Documentation/DocBook/v4l/vidioc-querybuf.xml b/Documentation/DocBook/v4l/vidioc-querybuf.xml
index d834993e619..e649805a490 100644
--- a/Documentation/DocBook/v4l/vidioc-querybuf.xml
+++ b/Documentation/DocBook/v4l/vidioc-querybuf.xml
@@ -54,12 +54,13 @@ buffer at any time after buffers have been allocated with the
 &VIDIOC-REQBUFS; ioctl.</para>
 
     <para>Applications set the <structfield>type</structfield> field
-    of a &v4l2-buffer; to the same buffer type as previously
+    of a &v4l2-buffer; to the same buffer type as was previously used with
 &v4l2-format; <structfield>type</structfield> and &v4l2-requestbuffers;
 <structfield>type</structfield>, and the <structfield>index</structfield>
     field. Valid index numbers range from zero
 to the number of buffers allocated with &VIDIOC-REQBUFS;
     (&v4l2-requestbuffers; <structfield>count</structfield>) minus one.
+The <structfield>reserved</structfield> field should to set to 0.
 After calling <constant>VIDIOC_QUERYBUF</constant> with a pointer to
     this structure drivers return an error code or fill the rest of
 the structure.</para>
@@ -68,8 +69,8 @@ the structure.</para>
 <constant>V4L2_BUF_FLAG_MAPPED</constant>,
 <constant>V4L2_BUF_FLAG_QUEUED</constant> and
 <constant>V4L2_BUF_FLAG_DONE</constant> flags will be valid. The
-<structfield>memory</structfield> field will be set to
-<constant>V4L2_MEMORY_MMAP</constant>, the <structfield>m.offset</structfield>
+<structfield>memory</structfield> field will be set to the current
+I/O method, the <structfield>m.offset</structfield>
 contains the offset of the buffer from the start of the device memory,
 the <structfield>length</structfield> field its size. The driver may
 or may not set the remaining fields and flags, they are meaningless in
diff --git a/Documentation/DocBook/v4l/vidioc-reqbufs.xml b/Documentation/DocBook/v4l/vidioc-reqbufs.xml
index bab38084454..1c081637207 100644
--- a/Documentation/DocBook/v4l/vidioc-reqbufs.xml
+++ b/Documentation/DocBook/v4l/vidioc-reqbufs.xml
@@ -54,23 +54,23 @@ I/O. Memory mapped buffers are located in device memory and must be
 allocated with this ioctl before they can be mapped into the
 application's address space. User buffers are allocated by
 applications themselves, and this ioctl is merely used to switch the
-driver into user pointer I/O mode.</para>
+driver into user pointer I/O mode and to setup some internal structures.</para>
 
-    <para>To allocate device buffers applications initialize three
-fields of a <structname>v4l2_requestbuffers</structname> structure.
+    <para>To allocate device buffers applications initialize all
+fields of the <structname>v4l2_requestbuffers</structname> structure.
 They set the <structfield>type</structfield> field to the respective
 stream or buffer type, the <structfield>count</structfield> field to
-the desired number of buffers, and <structfield>memory</structfield>
-must be set to <constant>V4L2_MEMORY_MMAP</constant>. When the ioctl
-is called with a pointer to this structure the driver attempts to
-allocate the requested number of buffers and stores the actual number
+the desired number of buffers, <structfield>memory</structfield>
+must be set to the requested I/O method and the reserved array
+must be zeroed. When the ioctl
+is called with a pointer to this structure the driver will attempt to allocate
+the requested number of buffers and it stores the actual number
 allocated in the <structfield>count</structfield> field. It can be
 smaller than the number requested, even zero, when the driver runs out
-of free memory. A larger number is possible when the driver requires
-more buffers to function correctly.<footnote>
-	<para>For example video output requires at least two buffers,
+of free memory. A larger number is also possible when the driver requires
+more buffers to function correctly. For example video output requires at least two buffers,
 one displayed and one filled by the application.</para>
-	</footnote> When memory mapping I/O is not supported the ioctl
+    <para>When the I/O method is not supported the ioctl
 returns an &EINVAL;.</para>
 
     <para>Applications can call <constant>VIDIOC_REQBUFS</constant>
@@ -81,14 +81,6 @@ in progress, an implicit &VIDIOC-STREAMOFF;. <!-- mhs: I see no
 reason why munmap()ping one or even all buffers must imply
 streamoff.--></para>
 
-    <para>To negotiate user pointer I/O, applications initialize only
-the <structfield>type</structfield> field and set
-<structfield>memory</structfield> to
-<constant>V4L2_MEMORY_USERPTR</constant>. When the ioctl is called
-with a pointer to this structure the driver prepares for user pointer
-I/O, when this I/O method is not supported the ioctl returns an
-&EINVAL;.</para>
-
     <table pgwide="1" frame="none" id="v4l2-requestbuffers">
       <title>struct <structname>v4l2_requestbuffers</structname></title>
       <tgroup cols="3">
@@ -97,9 +89,7 @@ I/O, when this I/O method is not supported the ioctl returns an
 	  <row>
 	    <entry>__u32</entry>
 	    <entry><structfield>count</structfield></entry>
-	    <entry>The number of buffers requested or granted. This
-field is only used when <structfield>memory</structfield> is set to
-<constant>V4L2_MEMORY_MMAP</constant>.</entry>
+	    <entry>The number of buffers requested or granted.</entry>
 	  </row>
 	  <row>
 	    <entry>&v4l2-buf-type;</entry>
@@ -120,7 +110,7 @@ as the &v4l2-format; <structfield>type</structfield> field. See <xref
 	    <entry><structfield>reserved</structfield>[2]</entry>
 	    <entry>A place holder for future extensions and custom
 (driver defined) buffer types <constant>V4L2_BUF_TYPE_PRIVATE</constant> and
-higher.</entry>
+higher. This array should be zeroed by applications.</entry>
 	  </row>
 	</tbody>
       </tgroup>
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index 8495fc97039..f5395af88a4 100644
--- a/Documentation/HOWTO
+++ b/Documentation/HOWTO
@@ -221,8 +221,8 @@ branches.  These different branches are:
   - main 2.6.x kernel tree
   - 2.6.x.y -stable kernel tree
   - 2.6.x -git kernel patches
-  - 2.6.x -mm kernel patches
   - subsystem specific kernel trees and patches
+  - the 2.6.x -next kernel tree for integration tests
 
 2.6.x kernel tree
 -----------------
@@ -232,7 +232,7 @@ process is as follows:
   - As soon as a new kernel is released a two weeks window is open,
     during this period of time maintainers can submit big diffs to
     Linus, usually the patches that have already been included in the
-    -mm kernel for a few weeks.  The preferred way to submit big changes
+    -next kernel for a few weeks.  The preferred way to submit big changes
     is using git (the kernel's source management tool, more information
     can be found at http://git.or.cz/) but plain patches are also just
     fine.
@@ -293,84 +293,43 @@ daily and represent the current state of Linus' tree.  They are more
 experimental than -rc kernels since they are generated automatically
 without even a cursory glance to see if they are sane.
 
-2.6.x -mm kernel patches
-------------------------
-These are experimental kernel patches released by Andrew Morton.  Andrew
-takes all of the different subsystem kernel trees and patches and mushes
-them together, along with a lot of patches that have been plucked from
-the linux-kernel mailing list.  This tree serves as a proving ground for
-new features and patches.  Once a patch has proved its worth in -mm for
-a while Andrew or the subsystem maintainer pushes it on to Linus for
-inclusion in mainline.
-
-It is heavily encouraged that all new patches get tested in the -mm tree
-before they are sent to Linus for inclusion in the main kernel tree.  Code
-which does not make an appearance in -mm before the opening of the merge
-window will prove hard to merge into the mainline.
-
-These kernels are not appropriate for use on systems that are supposed
-to be stable and they are more risky to run than any of the other
-branches.
-
-If you wish to help out with the kernel development process, please test
-and use these kernel releases and provide feedback to the linux-kernel
-mailing list if you have any problems, and if everything works properly.
-
-In addition to all the other experimental patches, these kernels usually
-also contain any changes in the mainline -git kernels available at the
-time of release.
-
-The -mm kernels are not released on a fixed schedule, but usually a few
--mm kernels are released in between each -rc kernel (1 to 3 is common).
-
 Subsystem Specific kernel trees and patches
 -------------------------------------------
-A number of the different kernel subsystem developers expose their
-development trees so that others can see what is happening in the
-different areas of the kernel.  These trees are pulled into the -mm
-kernel releases as described above.
-
-Here is a list of some of the different kernel trees available:
-  git trees:
-    - Kbuild development tree, Sam Ravnborg <sam@ravnborg.org>
-	git.kernel.org:/pub/scm/linux/kernel/git/sam/kbuild.git
-
-    - ACPI development tree, Len Brown <len.brown@intel.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6.git
-
-    - Block development tree, Jens Axboe <jens.axboe@oracle.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/axboe/linux-2.6-block.git
-
-    - DRM development tree, Dave Airlie <airlied@linux.ie>
-	git.kernel.org:/pub/scm/linux/kernel/git/airlied/drm-2.6.git
-
-    - ia64 development tree, Tony Luck <tony.luck@intel.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/aegl/linux-2.6.git
-
-    - infiniband, Roland Dreier <rolandd@cisco.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband.git
-
-    - libata, Jeff Garzik <jgarzik@pobox.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/libata-dev.git
-
-    - network drivers, Jeff Garzik <jgarzik@pobox.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6.git
-
-    - pcmcia, Dominik Brodowski <linux@dominikbrodowski.net>
-	git.kernel.org:/pub/scm/linux/kernel/git/brodo/pcmcia-2.6.git
-
-    - SCSI, James Bottomley <James.Bottomley@hansenpartnership.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6.git
-
-    - x86, Ingo Molnar <mingo@elte.hu>
-	git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git
-
-  quilt trees:
-    - USB, Driver Core, and I2C, Greg Kroah-Hartman <gregkh@suse.de>
-	kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
+The maintainers of the various kernel subsystems --- and also many
+kernel subsystem developers --- expose their current state of
+development in source repositories.  That way, others can see what is
+happening in the different areas of the kernel.  In areas where
+development is rapid, a developer may be asked to base his submissions
+onto such a subsystem kernel tree so that conflicts between the
+submission and other already ongoing work are avoided.
+
+Most of these repositories are git trees, but there are also other SCMs
+in use, or patch queues being published as quilt series.  Addresses of
+these subsystem repositories are listed in the MAINTAINERS file.  Many
+of them can be browsed at http://git.kernel.org/.
+
+Before a proposed patch is committed to such a subsystem tree, it is
+subject to review which primarily happens on mailing lists (see the
+respective section below).  For several kernel subsystems, this review
+process is tracked with the tool patchwork.  Patchwork offers a web
+interface which shows patch postings, any comments on a patch or
+revisions to it, and maintainers can mark patches as under review,
+accepted, or rejected.  Most of these patchwork sites are listed at
+http://patchwork.kernel.org/ or http://patchwork.ozlabs.org/.
+
+2.6.x -next kernel tree for integration tests
+---------------------------------------------
+Before updates from subsystem trees are merged into the mainline 2.6.x
+tree, they need to be integration-tested.  For this purpose, a special
+testing repository exists into which virtually all subsystem trees are
+pulled on an almost daily basis:
+	http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git
+	http://linux.f-seidel.de/linux-next/pmwiki/
+
+This way, the -next kernel gives a summary outlook onto what will be
+expected to go into the mainline kernel at the next merge period.
+Adventurous testers are very welcome to runtime-test the -next kernel.
 
-  Other kernel trees can be found listed at http://git.kernel.org/ and in
-  the MAINTAINERS file.
 
 Bug Reporting
 -------------
diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX
index 9bb62f7b89c..71b6f500ddb 100644
--- a/Documentation/RCU/00-INDEX
+++ b/Documentation/RCU/00-INDEX
@@ -6,16 +6,22 @@ checklist.txt
 	- Review Checklist for RCU Patches
 listRCU.txt
 	- Using RCU to Protect Read-Mostly Linked Lists
+lockdep.txt
+	- RCU and lockdep checking
 NMI-RCU.txt
 	- Using RCU to Protect Dynamic NMI Handlers
+rcubarrier.txt
+	- RCU and Unloadable Modules
+rculist_nulls.txt
+	- RCU list primitives for use with SLAB_DESTROY_BY_RCU
 rcuref.txt
 	- Reference-count design for elements of lists/arrays protected by RCU
 rcu.txt
 	- RCU Concepts
-rcubarrier.txt
-	- Unloading modules that use RCU callbacks
 RTFP.txt
 	- List of RCU papers (bibliography) going back to 1980.
+stallwarn.txt
+	- RCU CPU stall warnings (CONFIG_RCU_CPU_STALL_DETECTOR)
 torture.txt
 	- RCU Torture Test Operation (CONFIG_RCU_TORTURE_TEST)
 trace.txt
diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt
index d2b85237c76..5aea459e3dd 100644
--- a/Documentation/RCU/RTFP.txt
+++ b/Documentation/RCU/RTFP.txt
@@ -25,10 +25,10 @@ to be referencing the data structure.  However, this mechanism was not
 optimized for modern computer systems, which is not surprising given
 that these overheads were not so expensive in the mid-80s.  Nonetheless,
 passive serialization appears to be the first deferred-destruction
-mechanism to be used in production.  Furthermore, the relevant patent has
-lapsed, so this approach may be used in non-GPL software, if desired.
-(In contrast, use of RCU is permitted only in software licensed under
-GPL.  Sorry!!!)
+mechanism to be used in production.  Furthermore, the relevant patent
+has lapsed, so this approach may be used in non-GPL software, if desired.
+(In contrast, implementation of RCU is permitted only in software licensed
+under either GPL or LGPL.  Sorry!!!)
 
 In 1990, Pugh [Pugh90] noted that explicitly tracking which threads
 were reading a given data structure permitted deferred free to operate
@@ -150,6 +150,18 @@ preemptible RCU [PaulEMcKenney2007PreemptibleRCU], and the three-part
 LWN "What is RCU?" series [PaulEMcKenney2007WhatIsRCUFundamentally,
 PaulEMcKenney2008WhatIsRCUUsage, and PaulEMcKenney2008WhatIsRCUAPI].
 
+2008 saw a journal paper on real-time RCU [DinakarGuniguntala2008IBMSysJ],
+a history of how Linux changed RCU more than RCU changed Linux
+[PaulEMcKenney2008RCUOSR], and a design overview of hierarchical RCU
+[PaulEMcKenney2008HierarchicalRCU].
+
+2009 introduced user-level RCU algorithms [PaulEMcKenney2009MaliciousURCU],
+which Mathieu Desnoyers is now maintaining [MathieuDesnoyers2009URCU]
+[MathieuDesnoyersPhD].  TINY_RCU [PaulEMcKenney2009BloatWatchRCU] made
+its appearance, as did expedited RCU [PaulEMcKenney2009expeditedRCU].
+The problem of resizeable RCU-protected hash tables may now be on a path
+to a solution [JoshTriplett2009RPHash].
+
 Bibtex Entries
 
 @article{Kung80
@@ -730,6 +742,11 @@ Revised:
 "
 }
 
+#
+#	"What is RCU?" LWN series.
+#
+########################################################################
+
 @article{DinakarGuniguntala2008IBMSysJ
 ,author="D. Guniguntala and P. E. McKenney and J. Triplett and J. Walpole"
 ,title="The read-copy-update mechanism for supporting real-time applications on shared-memory multiprocessor systems with {Linux}"
@@ -820,3 +837,39 @@ Revised:
 	Uniprocessor assumptions allow simplified RCU implementation.
 "
 }
+
+@unpublished{PaulEMcKenney2009expeditedRCU
+,Author="Paul E. McKenney"
+,Title="[{PATCH} -tip 0/3] expedited 'big hammer' {RCU} grace periods"
+,month="June"
+,day="25"
+,year="2009"
+,note="Available:
+\url{http://lkml.org/lkml/2009/6/25/306}
+[Viewed August 16, 2009]"
+,annotation="
+	First posting of expedited RCU to be accepted into -tip.
+"
+}
+
+@unpublished{JoshTriplett2009RPHash
+,Author="Josh Triplett"
+,Title="Scalable concurrent hash tables via relativistic programming"
+,month="September"
+,year="2009"
+,note="Linux Plumbers Conference presentation"
+,annotation="
+	RP fun with hash tables.
+"
+}
+
+@phdthesis{MathieuDesnoyersPhD
+, title  = "Low-Impact Operating System Tracing"
+, author = "Mathieu Desnoyers"
+, school = "Ecole Polytechnique de Montr\'{e}al"
+, month  = "December"
+, year   = 2009
+,note="Available:
+\url{http://www.lttng.org/pub/thesis/desnoyers-dissertation-2009-12.pdf}
+[Viewed December 9, 2009]"
+}
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 51525a30e8b..cbc180f9019 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -8,13 +8,12 @@ would cause.  This list is based on experiences reviewing such patches
 over a rather long period of time, but improvements are always welcome!
 
 0.	Is RCU being applied to a read-mostly situation?  If the data
-	structure is updated more than about 10% of the time, then
-	you should strongly consider some other approach, unless
-	detailed performance measurements show that RCU is nonetheless
-	the right tool for the job.  Yes, you might think of RCU
-	as simply cutting overhead off of the readers and imposing it
-	on the writers.  That is exactly why normal uses of RCU will
-	do much more reading than updating.
+	structure is updated more than about 10% of the time, then you
+	should strongly consider some other approach, unless detailed
+	performance measurements show that RCU is nonetheless the right
+	tool for the job.  Yes, RCU does reduce read-side overhead by
+	increasing write-side overhead, which is exactly why normal uses
+	of RCU will do much more reading than updating.
 
 	Another exception is where performance is not an issue, and RCU
 	provides a simpler implementation.  An example of this situation
@@ -35,13 +34,13 @@ over a rather long period of time, but improvements are always welcome!
 
 	If you choose #b, be prepared to describe how you have handled
 	memory barriers on weakly ordered machines (pretty much all of
-	them -- even x86 allows reads to be reordered), and be prepared
-	to explain why this added complexity is worthwhile.  If you
-	choose #c, be prepared to explain how this single task does not
-	become a major bottleneck on big multiprocessor machines (for
-	example, if the task is updating information relating to itself
-	that other tasks can read, there by definition can be no
-	bottleneck).
+	them -- even x86 allows later loads to be reordered to precede
+	earlier stores), and be prepared to explain why this added
+	complexity is worthwhile.  If you choose #c, be prepared to
+	explain how this single task does not become a major bottleneck on
+	big multiprocessor machines (for example, if the task is updating
+	information relating to itself that other tasks can read, there
+	by definition can be no bottleneck).
 
 2.	Do the RCU read-side critical sections make proper use of
 	rcu_read_lock() and friends?  These primitives are needed
@@ -51,8 +50,10 @@ over a rather long period of time, but improvements are always welcome!
 	actuarial risk of your kernel.
 
 	As a rough rule of thumb, any dereference of an RCU-protected
-	pointer must be covered by rcu_read_lock() or rcu_read_lock_bh()
-	or by the appropriate update-side lock.
+	pointer must be covered by rcu_read_lock(), rcu_read_lock_bh(),
+	rcu_read_lock_sched(), or by the appropriate update-side lock.
+	Disabling of preemption can serve as rcu_read_lock_sched(), but
+	is less readable.
 
 3.	Does the update code tolerate concurrent accesses?
 
@@ -62,25 +63,27 @@ over a rather long period of time, but improvements are always welcome!
 	of ways to handle this concurrency, depending on the situation:
 
 	a.	Use the RCU variants of the list and hlist update
-		primitives to add, remove, and replace elements on an
-		RCU-protected list.  Alternatively, use the RCU-protected
-		trees that have been added to the Linux kernel.
+		primitives to add, remove, and replace elements on
+		an RCU-protected list.	Alternatively, use the other
+		RCU-protected data structures that have been added to
+		the Linux kernel.
 
 		This is almost always the best approach.
 
 	b.	Proceed as in (a) above, but also maintain per-element
 		locks (that are acquired by both readers and writers)
 		that guard per-element state.  Of course, fields that
-		the readers refrain from accessing can be guarded by the
-		update-side lock.
+		the readers refrain from accessing can be guarded by
+		some other lock acquired only by updaters, if desired.
 
 		This works quite well, also.
 
 	c.	Make updates appear atomic to readers.  For example,
-		pointer updates to properly aligned fields will appear
-		atomic, as will individual atomic primitives.  Operations
-		performed under a lock and sequences of multiple atomic
-		primitives will -not- appear to be atomic.
+		pointer updates to properly aligned fields will
+		appear atomic, as will individual atomic primitives.
+		Sequences of perations performed under a lock will -not-
+		appear to be atomic to RCU readers, nor will sequences
+		of multiple atomic primitives.
 
 		This can work, but is starting to get a bit tricky.
 
@@ -98,9 +101,9 @@ over a rather long period of time, but improvements are always welcome!
 		a new structure containing updated values.
 
 4.	Weakly ordered CPUs pose special challenges.  Almost all CPUs
-	are weakly ordered -- even i386 CPUs allow reads to be reordered.
-	RCU code must take all of the following measures to prevent
-	memory-corruption problems:
+	are weakly ordered -- even x86 CPUs allow later loads to be
+	reordered to precede earlier stores.  RCU code must take all of
+	the following measures to prevent memory-corruption problems:
 
 	a.	Readers must maintain proper ordering of their memory
 		accesses.  The rcu_dereference() primitive ensures that
@@ -113,14 +116,25 @@ over a rather long period of time, but improvements are always welcome!
 		The rcu_dereference() primitive is also an excellent
 		documentation aid, letting the person reading the code
 		know exactly which pointers are protected by RCU.
-
-		The rcu_dereference() primitive is used by the various
-		"_rcu()" list-traversal primitives, such as the
-		list_for_each_entry_rcu().  Note that it is perfectly
-		legal (if redundant) for update-side code to use
-		rcu_dereference() and the "_rcu()" list-traversal
-		primitives.  This is particularly useful in code
-		that is common to readers and updaters.
+		Please note that compilers can also reorder code, and
+		they are becoming increasingly aggressive about doing
+		just that.  The rcu_dereference() primitive therefore
+		also prevents destructive compiler optimizations.
+
+		The rcu_dereference() primitive is used by the
+		various "_rcu()" list-traversal primitives, such
+		as the list_for_each_entry_rcu().  Note that it is
+		perfectly legal (if redundant) for update-side code to
+		use rcu_dereference() and the "_rcu()" list-traversal
+		primitives.  This is particularly useful in code that
+		is common to readers and updaters.  However, lockdep
+		will complain if you access rcu_dereference() outside
+		of an RCU read-side critical section.  See lockdep.txt
+		to learn what to do about this.
+
+		Of course, neither rcu_dereference() nor the "_rcu()"
+		list-traversal primitives can substitute for a good
+		concurrency design coordinating among multiple updaters.
 
 	b.	If the list macros are being used, the list_add_tail_rcu()
 		and list_add_rcu() primitives must be used in order
@@ -135,11 +149,14 @@ over a rather long period of time, but improvements are always welcome!
 		readers.  Similarly, if the hlist macros are being used,
 		the hlist_del_rcu() primitive is required.
 
-		The list_replace_rcu() primitive may be used to
-		replace an old structure with a new one in an
-		RCU-protected list.
+		The list_replace_rcu() and hlist_replace_rcu() primitives
+		may be used to replace an old structure with a new one
+		in their respective types of RCU-protected lists.
+
+	d.	Rules similar to (4b) and (4c) apply to the "hlist_nulls"
+		type of RCU-protected linked lists.
 
-	d.	Updates must ensure that initialization of a given
+	e.	Updates must ensure that initialization of a given
 		structure happens before pointers to that structure are
 		publicized.  Use the rcu_assign_pointer() primitive
 		when publicizing a pointer to a structure that can
@@ -151,16 +168,31 @@ over a rather long period of time, but improvements are always welcome!
 	it cannot block.
 
 6.	Since synchronize_rcu() can block, it cannot be called from
-	any sort of irq context.  Ditto for synchronize_sched() and
-	synchronize_srcu().
-
-7.	If the updater uses call_rcu(), then the corresponding readers
-	must use rcu_read_lock() and rcu_read_unlock().  If the updater
-	uses call_rcu_bh(), then the corresponding readers must use
-	rcu_read_lock_bh() and rcu_read_unlock_bh().  If the updater
-	uses call_rcu_sched(), then the corresponding readers must
-	disable preemption.  Mixing things up will result in confusion
-	and broken kernels.
+	any sort of irq context.  The same rule applies for
+	synchronize_rcu_bh(), synchronize_sched(), synchronize_srcu(),
+	synchronize_rcu_expedited(), synchronize_rcu_bh_expedited(),
+	synchronize_sched_expedite(), and synchronize_srcu_expedited().
+
+	The expedited forms of these primitives have the same semantics
+	as the non-expedited forms, but expediting is both expensive
+	and unfriendly to real-time workloads.	Use of the expedited
+	primitives should be restricted to rare configuration-change
+	operations that would not normally be undertaken while a real-time
+	workload is running.
+
+7.	If the updater uses call_rcu() or synchronize_rcu(), then the
+	corresponding readers must use rcu_read_lock() and
+	rcu_read_unlock().  If the updater uses call_rcu_bh() or
+	synchronize_rcu_bh(), then the corresponding readers must
+	use rcu_read_lock_bh() and rcu_read_unlock_bh().  If the
+	updater uses call_rcu_sched() or synchronize_sched(), then
+	the corresponding readers must disable preemption, possibly
+	by calling rcu_read_lock_sched() and rcu_read_unlock_sched().
+	If the updater uses synchronize_srcu(), the the corresponding
+	readers must use srcu_read_lock() and srcu_read_unlock(),
+	and with the same srcu_struct.	The rules for the expedited
+	primitives are the same as for their non-expedited counterparts.
+	Mixing things up will result in confusion and broken kernels.
 
 	One exception to this rule: rcu_read_lock() and rcu_read_unlock()
 	may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
@@ -212,6 +244,8 @@ over a rather long period of time, but improvements are always welcome!
 	e.	Periodically invoke synchronize_rcu(), permitting a limited
 		number of updates per grace period.
 
+	The same cautions apply to call_rcu_bh() and call_rcu_sched().
+
 9.	All RCU list-traversal primitives, which include
 	rcu_dereference(), list_for_each_entry_rcu(),
 	list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
@@ -219,7 +253,9 @@ over a rather long period of time, but improvements are always welcome!
 	must be protected by appropriate update-side locks.  RCU
 	read-side critical sections are delimited by rcu_read_lock()
 	and rcu_read_unlock(), or by similar primitives such as
-	rcu_read_lock_bh() and rcu_read_unlock_bh().
+	rcu_read_lock_bh() and rcu_read_unlock_bh(), in which case
+	the matching rcu_dereference() primitive must be used in order
+	to keep lockdep happy, in this case, rcu_dereference_bh().
 
 	The reason that it is permissible to use RCU list-traversal
 	primitives when the update-side lock is held is that doing so
@@ -229,7 +265,8 @@ over a rather long period of time, but improvements are always welcome!
 10.	Conversely, if you are in an RCU read-side critical section,
 	and you don't hold the appropriate update-side lock, you -must-
 	use the "_rcu()" variants of the list macros.  Failing to do so
-	will break Alpha and confuse people reading your code.
+	will break Alpha, cause aggressive compilers to generate bad code,
+	and confuse people trying to read your code.
 
 11.	Note that synchronize_rcu() -only- guarantees to wait until
 	all currently executing rcu_read_lock()-protected RCU read-side
@@ -239,15 +276,21 @@ over a rather long period of time, but improvements are always welcome!
 	rcu_read_lock()-protected read-side critical sections, do -not-
 	use synchronize_rcu().
 
-	If you want to wait for some of these other things, you might
-	instead need to use synchronize_irq() or synchronize_sched().
+	Similarly, disabling preemption is not an acceptable substitute
+	for rcu_read_lock().  Code that attempts to use preemption
+	disabling where it should be using rcu_read_lock() will break
+	in real-time kernel builds.
+
+	If you want to wait for interrupt handlers, NMI handlers, and
+	code under the influence of preempt_disable(), you instead
+	need to use synchronize_irq() or synchronize_sched().
 
 12.	Any lock acquired by an RCU callback must be acquired elsewhere
 	with softirq disabled, e.g., via spin_lock_irqsave(),
 	spin_lock_bh(), etc.  Failing to disable irq on a given
-	acquisition of that lock will result in deadlock as soon as the
-	RCU callback happens to interrupt that acquisition's critical
-	section.
+	acquisition of that lock will result in deadlock as soon as
+	the RCU softirq handler happens to run your RCU callback while
+	interrupting that acquisition's critical section.
 
 13.	RCU callbacks can be and are executed in parallel.  In many cases,
 	the callback code simply wrappers around kfree(), so that this
@@ -265,29 +308,30 @@ over a rather long period of time, but improvements are always welcome!
 	not the case, a self-spawning RCU callback would prevent the
 	victim CPU from ever going offline.)
 
-14.	SRCU (srcu_read_lock(), srcu_read_unlock(), and synchronize_srcu())
-	may only be invoked from process context.  Unlike other forms of
-	RCU, it -is- permissible to block in an SRCU read-side critical
-	section (demarked by srcu_read_lock() and srcu_read_unlock()),
-	hence the "SRCU": "sleepable RCU".  Please note that if you
-	don't need to sleep in read-side critical sections, you should
-	be using RCU rather than SRCU, because RCU is almost always
-	faster and easier to use than is SRCU.
+14.	SRCU (srcu_read_lock(), srcu_read_unlock(), srcu_dereference(),
+	synchronize_srcu(), and synchronize_srcu_expedited()) may only
+	be invoked from process context.  Unlike other forms of RCU, it
+	-is- permissible to block in an SRCU read-side critical section
+	(demarked by srcu_read_lock() and srcu_read_unlock()), hence the
+	"SRCU": "sleepable RCU".  Please note that if you don't need
+	to sleep in read-side critical sections, you should be using
+	RCU rather than SRCU, because RCU is almost always faster and
+	easier to use than is SRCU.
 
 	Also unlike other forms of RCU, explicit initialization
 	and cleanup is required via init_srcu_struct() and
 	cleanup_srcu_struct().	These are passed a "struct srcu_struct"
 	that defines the scope of a given SRCU domain.	Once initialized,
 	the srcu_struct is passed to srcu_read_lock(), srcu_read_unlock()
-	and synchronize_srcu().  A given synchronize_srcu() waits only
-	for SRCU read-side critical sections governed by srcu_read_lock()
-	and srcu_read_unlock() calls that have been passd the same
-	srcu_struct.  This property is what makes sleeping read-side
-	critical sections tolerable -- a given subsystem delays only
-	its own updates, not those of other subsystems using SRCU.
-	Therefore, SRCU is less prone to OOM the system than RCU would
-	be if RCU's read-side critical sections were permitted to
-	sleep.
+	synchronize_srcu(), and synchronize_srcu_expedited().  A given
+	synchronize_srcu() waits only for SRCU read-side critical
+	sections governed by srcu_read_lock() and srcu_read_unlock()
+	calls that have been passed the same srcu_struct.  This property
+	is what makes sleeping read-side critical sections tolerable --
+	a given subsystem delays only its own updates, not those of other
+	subsystems using SRCU.	Therefore, SRCU is less prone to OOM the
+	system than RCU would be if RCU's read-side critical sections
+	were permitted to sleep.
 
 	The ability to sleep in read-side critical sections does not
 	come for free.	First, corresponding srcu_read_lock() and
@@ -311,12 +355,12 @@ over a rather long period of time, but improvements are always welcome!
 	destructive operation, and -only- -then- invoke call_rcu(),
 	synchronize_rcu(), or friends.
 
-	Because these primitives only wait for pre-existing readers,
-	it is the caller's responsibility to guarantee safety to
-	any subsequent readers.
+	Because these primitives only wait for pre-existing readers, it
+	is the caller's responsibility to guarantee that any subsequent
+	readers will execute safely.
 
-16.	The various RCU read-side primitives do -not- contain memory
-	barriers.  The CPU (and in some cases, the compiler) is free
-	to reorder code into and out of RCU read-side critical sections.
-	It is the responsibility of the RCU update-side primitives to
-	deal with this.
+16.	The various RCU read-side primitives do -not- necessarily contain
+	memory barriers.  You should therefore plan for the CPU
+	and the compiler to freely reorder code into and out of RCU
+	read-side critical sections.  It is the responsibility of the
+	RCU update-side primitives to deal with this.
diff --git a/Documentation/RCU/lockdep.txt b/Documentation/RCU/lockdep.txt
new file mode 100644
index 00000000000..fe24b58627b
--- /dev/null
+++ b/Documentation/RCU/lockdep.txt
@@ -0,0 +1,67 @@
+RCU and lockdep checking
+
+All flavors of RCU have lockdep checking available, so that lockdep is
+aware of when each task enters and leaves any flavor of RCU read-side
+critical section.  Each flavor of RCU is tracked separately (but note
+that this is not the case in 2.6.32 and earlier).  This allows lockdep's
+tracking to include RCU state, which can sometimes help when debugging
+deadlocks and the like.
+
+In addition, RCU provides the following primitives that check lockdep's
+state:
+
+	rcu_read_lock_held() for normal RCU.
+	rcu_read_lock_bh_held() for RCU-bh.
+	rcu_read_lock_sched_held() for RCU-sched.
+	srcu_read_lock_held() for SRCU.
+
+These functions are conservative, and will therefore return 1 if they
+aren't certain (for example, if CONFIG_DEBUG_LOCK_ALLOC is not set).
+This prevents things like WARN_ON(!rcu_read_lock_held()) from giving false
+positives when lockdep is disabled.
+
+In addition, a separate kernel config parameter CONFIG_PROVE_RCU enables
+checking of rcu_dereference() primitives:
+
+	rcu_dereference(p):
+		Check for RCU read-side critical section.
+	rcu_dereference_bh(p):
+		Check for RCU-bh read-side critical section.
+	rcu_dereference_sched(p):
+		Check for RCU-sched read-side critical section.
+	srcu_dereference(p, sp):
+		Check for SRCU read-side critical section.
+	rcu_dereference_check(p, c):
+		Use explicit check expression "c".
+	rcu_dereference_raw(p)
+		Don't check.  (Use sparingly, if at all.)
+
+The rcu_dereference_check() check expression can be any boolean
+expression, but would normally include one of the rcu_read_lock_held()
+family of functions and a lockdep expression.  However, any boolean
+expression can be used.  For a moderately ornate example, consider
+the following:
+
+	file = rcu_dereference_check(fdt->fd[fd],
+				     rcu_read_lock_held() ||
+				     lockdep_is_held(&files->file_lock) ||
+				     atomic_read(&files->count) == 1);
+
+This expression picks up the pointer "fdt->fd[fd]" in an RCU-safe manner,
+and, if CONFIG_PROVE_RCU is configured, verifies that this expression
+is used in:
+
+1.	An RCU read-side critical section, or
+2.	with files->file_lock held, or
+3.	on an unshared files_struct.
+
+In case (1), the pointer is picked up in an RCU-safe manner for vanilla
+RCU read-side critical sections, in case (2) the ->file_lock prevents
+any change from taking place, and finally, in case (3) the current task
+is the only task accessing the file_struct, again preventing any change
+from taking place.
+
+There are currently only "universal" versions of the rcu_assign_pointer()
+and RCU list-/tree-traversal primitives, which do not (yet) check for
+being in an RCU read-side critical section.  In the future, separate
+versions of these primitives might be created.
diff --git a/Documentation/RCU/rcu.txt b/Documentation/RCU/rcu.txt
index 2a23523ce47..31852705b58 100644
--- a/Documentation/RCU/rcu.txt
+++ b/Documentation/RCU/rcu.txt
@@ -75,6 +75,8 @@ o	I hear that RCU is patented?  What is with that?
 	search for the string "Patent" in RTFP.txt to find them.
 	Of these, one was allowed to lapse by the assignee, and the
 	others have been contributed to the Linux kernel under GPL.
+	There are now also LGPL implementations of user-level RCU
+	available (http://lttng.org/?q=node/18).
 
 o	I hear that RCU needs work in order to support realtime kernels?
 
@@ -91,48 +93,4 @@ o	Where can I find more information on RCU?
 
 o	What are all these files in this directory?
 
-
-	NMI-RCU.txt
-
-		Describes how to use RCU to implement dynamic
-		NMI handlers, which can be revectored on the fly,
-		without rebooting.
-
-	RTFP.txt
-
-		List of RCU-related publications and web sites.
-
-	UP.txt
-
-		Discussion of RCU usage in UP kernels.
-
-	arrayRCU.txt
-
-		Describes how to use RCU to protect arrays, with
-		resizeable arrays whose elements reference other
-		data structures being of the most interest.
-
-	checklist.txt
-
-		Lists things to check for when inspecting code that
-		uses RCU.
-
-	listRCU.txt
-
-		Describes how to use RCU to protect linked lists.
-		This is the simplest and most common use of RCU
-		in the Linux kernel.
-
-	rcu.txt
-
-		You are reading it!
-
-	rcuref.txt
-
-		Describes how to combine use of reference counts
-		with RCU.
-
-	whatisRCU.txt
-
-		Overview of how the RCU implementation works.  Along
-		the way, presents a conceptual view of RCU.
+	See 00-INDEX for the list.
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
new file mode 100644
index 00000000000..1423d2570d7
--- /dev/null
+++ b/Documentation/RCU/stallwarn.txt
@@ -0,0 +1,58 @@
+Using RCU's CPU Stall Detector
+
+The CONFIG_RCU_CPU_STALL_DETECTOR kernel config parameter enables
+RCU's CPU stall detector, which detects conditions that unduly delay
+RCU grace periods.  The stall detector's idea of what constitutes
+"unduly delayed" is controlled by a pair of C preprocessor macros:
+
+RCU_SECONDS_TILL_STALL_CHECK
+
+	This macro defines the period of time that RCU will wait from
+	the beginning of a grace period until it issues an RCU CPU
+	stall warning.	It is normally ten seconds.
+
+RCU_SECONDS_TILL_STALL_RECHECK
+
+	This macro defines the period of time that RCU will wait after
+	issuing a stall warning until it issues another stall warning.
+	It is normally set to thirty seconds.
+
+RCU_STALL_RAT_DELAY
+
+	The CPU stall detector tries to make the offending CPU rat on itself,
+	as this often gives better-quality stack traces.  However, if
+	the offending CPU does not detect its own stall in the number
+	of jiffies specified by RCU_STALL_RAT_DELAY, then other CPUs will
+	complain.  This is normally set to two jiffies.
+
+The following problems can result in an RCU CPU stall warning:
+
+o	A CPU looping in an RCU read-side critical section.
+	
+o	A CPU looping with interrupts disabled.
+
+o	A CPU looping with preemption disabled.
+
+o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
+	without invoking schedule().
+
+o	A bug in the RCU implementation.
+
+o	A hardware failure.  This is quite unlikely, but has occurred
+	at least once in a former life.  A CPU failed in a running system,
+	becoming unresponsive, but not causing an immediate crash.
+	This resulted in a series of RCU CPU stall warnings, eventually
+	leading the realization that the CPU had failed.
+
+The RCU, RCU-sched, and RCU-bh implementations have CPU stall warning.
+SRCU does not do so directly, but its calls to synchronize_sched() will
+result in RCU-sched detecting any CPU stalls that might be occurring.
+
+To diagnose the cause of the stall, inspect the stack traces.  The offending
+function will usually be near the top of the stack.  If you have a series
+of stall warnings from a single extended stall, comparing the stack traces
+can often help determine where the stall is occurring, which will usually
+be in the function nearest the top of the stack that stays the same from
+trace to trace.
+
+RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE.
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index 9dba3bb90e6..0e50bc2aa1e 100644
--- a/Documentation/RCU/torture.txt
+++ b/Documentation/RCU/torture.txt
@@ -30,6 +30,18 @@ MODULE PARAMETERS
 
 This module has the following parameters:
 
+fqs_duration	Duration (in microseconds) of artificially induced bursts
+		of force_quiescent_state() invocations.  In RCU
+		implementations having force_quiescent_state(), these
+		bursts help force races between forcing a given grace
+		period and that grace period ending on its own.
+
+fqs_holdoff	Holdoff time (in microseconds) between consecutive calls
+		to force_quiescent_state() within a burst.
+
+fqs_stutter	Wait time (in seconds) between consecutive bursts
+		of calls to force_quiescent_state().
+
 irqreaders	Says to invoke RCU readers from irq level.  This is currently
 		done via timers.  Defaults to "1" for variants of RCU that
 		permit this.  (Or, more accurately, variants of RCU that do
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index d542ca243b8..1dc00ee9716 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -323,14 +323,17 @@ used as follows:
 	Defer			Protect
 
 a.	synchronize_rcu()	rcu_read_lock() / rcu_read_unlock()
-	call_rcu()
+	call_rcu()		rcu_dereference()
 
 b.	call_rcu_bh()		rcu_read_lock_bh() / rcu_read_unlock_bh()
+				rcu_dereference_bh()
 
-c.	synchronize_sched()	preempt_disable() / preempt_enable()
+c.	synchronize_sched()	rcu_read_lock_sched() / rcu_read_unlock_sched()
+				preempt_disable() / preempt_enable()
 				local_irq_save() / local_irq_restore()
 				hardirq enter / hardirq exit
 				NMI enter / NMI exit
+				rcu_dereference_sched()
 
 These three mechanisms are used as follows:
 
@@ -780,9 +783,8 @@ Linux-kernel source code, but it helps to have a full list of the
 APIs, since there does not appear to be a way to categorize them
 in docbook.  Here is the list, by category.
 
-RCU pointer/list traversal:
+RCU list traversal:
 
-	rcu_dereference
 	list_for_each_entry_rcu
 	hlist_for_each_entry_rcu
 	hlist_nulls_for_each_entry_rcu
@@ -808,7 +810,7 @@ RCU:	Critical sections	Grace period		Barrier
 
 	rcu_read_lock		synchronize_net		rcu_barrier
 	rcu_read_unlock		synchronize_rcu
-				synchronize_rcu_expedited
+	rcu_dereference		synchronize_rcu_expedited
 				call_rcu
 
 
@@ -816,7 +818,7 @@ bh:	Critical sections	Grace period		Barrier
 
 	rcu_read_lock_bh	call_rcu_bh		rcu_barrier_bh
 	rcu_read_unlock_bh	synchronize_rcu_bh
-				synchronize_rcu_bh_expedited
+	rcu_dereference_bh	synchronize_rcu_bh_expedited
 
 
 sched:	Critical sections	Grace period		Barrier
@@ -825,12 +827,14 @@ sched:	Critical sections	Grace period		Barrier
 	rcu_read_unlock_sched	call_rcu_sched
 	[preempt_disable]	synchronize_sched_expedited
 	[and friends]
+	rcu_dereference_sched
 
 
 SRCU:	Critical sections	Grace period		Barrier
 
 	srcu_read_lock		synchronize_srcu	N/A
 	srcu_read_unlock	synchronize_srcu_expedited
+	srcu_dereference
 
 SRCU:	Initialization/cleanup
 	init_srcu_struct
diff --git a/Documentation/arm/memory.txt b/Documentation/arm/memory.txt
index 9d58c7c5edd..eb0fae18ffb 100644
--- a/Documentation/arm/memory.txt
+++ b/Documentation/arm/memory.txt
@@ -59,7 +59,11 @@ PAGE_OFFSET	high_memory-1	Kernel direct-mapped RAM region.
 				This maps the platforms RAM, and typically
 				maps all platform RAM in a 1:1 relationship.
 
-TASK_SIZE	PAGE_OFFSET-1	Kernel module space
+PKMAP_BASE	PAGE_OFFSET-1	Permanent kernel mappings
+				One way of mapping HIGHMEM pages into kernel
+				space.
+
+MODULES_VADDR	MODULES_END-1	Kernel module space
 				Kernel modules inserted via insmod are
 				placed here using dynamic mappings.
 
diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt
index e164403f60e..f65274081c8 100644
--- a/Documentation/block/queue-sysfs.txt
+++ b/Documentation/block/queue-sysfs.txt
@@ -25,11 +25,11 @@ size allowed by the hardware.
 
 nomerges (RW)
 -------------
-This enables the user to disable the lookup logic involved with IO merging
-requests in the block layer. Merging may still occur through a direct
-1-hit cache, since that comes for (almost) free. The IO scheduler will not
-waste cycles doing tree/hash lookups for merges if nomerges is 1. Defaults
-to 0, enabling all merges.
+This enables the user to disable the lookup logic involved with IO
+merging requests in the block layer. By default (0) all merges are
+enabled. When set to 1 only simple one-hit merges will be tried. When
+set to 2 no merge algorithms will be tried (including one-hit or more
+complex tree/hash lookups).
 
 nr_requests (RW)
 ----------------
diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt
index da42ab414c4..2b5f823abd0 100644
--- a/Documentation/cachetlb.txt
+++ b/Documentation/cachetlb.txt
@@ -88,12 +88,12 @@ changes occur:
 	This is used primarily during fault processing.
 
 5) void update_mmu_cache(struct vm_area_struct *vma,
-			 unsigned long address, pte_t pte)
+			 unsigned long address, pte_t *ptep)
 
 	At the end of every page fault, this routine is invoked to
 	tell the architecture specific code that a translation
-	described by "pte" now exists at virtual address "address"
-	for address space "vma->vm_mm", in the software page tables.
+	now exists at virtual address "address" for address space
+	"vma->vm_mm", in the software page tables.
 
 	A port may use this information in any way it so chooses.
 	For example, it could use this event to pre-load TLB
@@ -377,3 +377,27 @@ maps this page at its virtual address.
 	All the functionality of flush_icache_page can be implemented in
 	flush_dcache_page and update_mmu_cache. In 2.7 the hope is to
 	remove this interface completely.
+
+The final category of APIs is for I/O to deliberately aliased address
+ranges inside the kernel.  Such aliases are set up by use of the
+vmap/vmalloc API.  Since kernel I/O goes via physical pages, the I/O
+subsystem assumes that the user mapping and kernel offset mapping are
+the only aliases.  This isn't true for vmap aliases, so anything in
+the kernel trying to do I/O to vmap areas must manually manage
+coherency.  It must do this by flushing the vmap range before doing
+I/O and invalidating it after the I/O returns.
+
+  void flush_kernel_vmap_range(void *vaddr, int size)
+       flushes the kernel cache for a given virtual address range in
+       the vmap area.  This is to make sure that any data the kernel
+       modified in the vmap range is made visible to the physical
+       page.  The design is to make this area safe to perform I/O on.
+       Note that this API does *not* also flush the offset map alias
+       of the area.
+
+  void invalidate_kernel_vmap_range(void *vaddr, int size) invalidates
+       the cache for a given virtual address range in the vmap area
+       which prevents the processor from making the cache stale by
+       speculatively reading data while the I/O was occurring to the
+       physical pages.  This is only necessary for data reads into the
+       vmap area.
diff --git a/Documentation/cdrom/ide-cd b/Documentation/cdrom/ide-cd
index 2c558cd6c1e..f4dc9de2694 100644
--- a/Documentation/cdrom/ide-cd
+++ b/Documentation/cdrom/ide-cd
@@ -159,42 +159,7 @@ two arguments:  the CDROM device, and the slot number to which you wish
 to change.  If the slot number is -1, the drive is unloaded.
 
 
-4. Compilation options
-----------------------
-
-There are a few additional options which can be set when compiling the
-driver.  Most people should not need to mess with any of these; they
-are listed here simply for completeness.  A compilation option can be
-enabled by adding a line of the form `#define <option> 1' to the top
-of ide-cd.c.  All these options are disabled by default.
-
-VERBOSE_IDE_CD_ERRORS
-  If this is set, ATAPI error codes will be translated into textual
-  descriptions.  In addition, a dump is made of the command which
-  provoked the error.  This is off by default to save the memory used
-  by the (somewhat long) table of error descriptions.  
-
-STANDARD_ATAPI
-  If this is set, the code needed to deal with certain drives which do
-  not properly implement the ATAPI spec will be disabled.  If you know
-  your drive implements ATAPI properly, you can turn this on to get a
-  slightly smaller kernel.
-
-NO_DOOR_LOCKING
-  If this is set, the driver will never attempt to lock the door of
-  the drive.
-
-CDROM_NBLOCKS_BUFFER
-  This sets the size of the buffer to be used for a CDROMREADAUDIO
-  ioctl.  The default is 8.
-
-TEST
-  This currently enables an additional ioctl which enables a user-mode
-  program to execute an arbitrary packet command.  See the source for
-  details.  This should be left off unless you know what you're doing.
-
-
-5. Common problems
+4. Common problems
 ------------------
 
 This section discusses some common problems encountered when trying to
@@ -371,7 +336,7 @@ f. Data corruption.
     expense of low system performance.
 
 
-6. cdchange.c
+5. cdchange.c
 -------------
 
 /*
diff --git a/Documentation/cpu-freq/pcc-cpufreq.txt b/Documentation/cpu-freq/pcc-cpufreq.txt
new file mode 100644
index 00000000000..9e3c3b33514
--- /dev/null
+++ b/Documentation/cpu-freq/pcc-cpufreq.txt
@@ -0,0 +1,207 @@
+/*
+ *  pcc-cpufreq.txt - PCC interface documentation
+ *
+ *  Copyright (C) 2009 Red Hat, Matthew Garrett <mjg@redhat.com>
+ *  Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
+ *      Nagananda Chumbalkar <nagananda.chumbalkar@hp.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; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or NON
+ *  INFRINGEMENT. See the GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+
+			Processor Clocking Control Driver
+			---------------------------------
+
+Contents:
+---------
+1.	Introduction
+1.1	PCC interface
+1.1.1   Get Average Frequency
+1.1.2	Set Desired Frequency
+1.2	Platforms affected
+2.	Driver and /sys details
+2.1	scaling_available_frequencies
+2.2	cpuinfo_transition_latency
+2.3	cpuinfo_cur_freq
+2.4	related_cpus
+3.	Caveats
+
+1. Introduction:
+----------------
+Processor Clocking Control (PCC) is an interface between the platform
+firmware and OSPM. It is a mechanism for coordinating processor
+performance (ie: frequency) between the platform firmware and the OS.
+
+The PCC driver (pcc-cpufreq) allows OSPM to take advantage of the PCC
+interface.
+
+OS utilizes the PCC interface to inform platform firmware what frequency the
+OS wants for a logical processor. The platform firmware attempts to achieve
+the requested frequency. If the request for the target frequency could not be
+satisfied by platform firmware, then it usually means that power budget
+conditions are in place, and "power capping" is taking place.
+
+1.1 PCC interface:
+------------------
+The complete PCC specification is available here:
+http://www.acpica.org/download/Processor-Clocking-Control-v1p0.pdf
+
+PCC relies on a shared memory region that provides a channel for communication
+between the OS and platform firmware. PCC also implements a "doorbell" that
+is used by the OS to inform the platform firmware that a command has been
+sent.
+
+The ACPI PCCH() method is used to discover the location of the PCC shared
+memory region. The shared memory region header contains the "command" and
+"status" interface. PCCH() also contains details on how to access the platform
+doorbell.
+
+The following commands are supported by the PCC interface:
+* Get Average Frequency
+* Set Desired Frequency
+
+The ACPI PCCP() method is implemented for each logical processor and is
+used to discover the offsets for the input and output buffers in the shared
+memory region.
+
+When PCC mode is enabled, the platform will not expose processor performance
+or throttle states (_PSS, _TSS and related ACPI objects) to OSPM. Therefore,
+the native P-state driver (such as acpi-cpufreq for Intel, powernow-k8 for
+AMD) will not load.
+
+However, OSPM remains in control of policy. The governor (eg: "ondemand")
+computes the required performance for each processor based on server workload.
+The PCC driver fills in the command interface, and the input buffer and
+communicates the request to the platform firmware. The platform firmware is
+responsible for delivering the requested performance.
+
+Each PCC command is "global" in scope and can affect all the logical CPUs in
+the system. Therefore, PCC is capable of performing "group" updates. With PCC
+the OS is capable of getting/setting the frequency of all the logical CPUs in
+the system with a single call to the BIOS.
+
+1.1.1 Get Average Frequency:
+----------------------------
+This command is used by the OSPM to query the running frequency of the
+processor since the last time this command was completed. The output buffer
+indicates the average unhalted frequency of the logical processor expressed as
+a percentage of the nominal (ie: maximum) CPU frequency. The output buffer
+also signifies if the CPU frequency is limited by a power budget condition.
+
+1.1.2 Set Desired Frequency:
+----------------------------
+This command is used by the OSPM to communicate to the platform firmware the
+desired frequency for a logical processor. The output buffer is currently
+ignored by OSPM. The next invocation of "Get Average Frequency" will inform
+OSPM if the desired frequency was achieved or not.
+
+1.2 Platforms affected:
+-----------------------
+The PCC driver will load on any system where the platform firmware:
+* supports the PCC interface, and the associated PCCH() and PCCP() methods
+* assumes responsibility for managing the hardware clocking controls in order
+to deliver the requested processor performance
+
+Currently, certain HP ProLiant platforms implement the PCC interface. On those
+platforms PCC is the "default" choice.
+
+However, it is possible to disable this interface via a BIOS setting. In
+such an instance, as is also the case on platforms where the PCC interface
+is not implemented, the PCC driver will fail to load silently.
+
+2. Driver and /sys details:
+---------------------------
+When the driver loads, it merely prints the lowest and the highest CPU
+frequencies supported by the platform firmware.
+
+The PCC driver loads with a message such as:
+pcc-cpufreq: (v1.00.00) driver loaded with frequency limits: 1600 MHz, 2933
+MHz
+
+This means that the OPSM can request the CPU to run at any frequency in
+between the limits (1600 MHz, and 2933 MHz) specified in the message.
+
+Internally, there is no need for the driver to convert the "target" frequency
+to a corresponding P-state.
+
+The VERSION number for the driver will be of the format v.xy.ab.
+eg: 1.00.02
+   ----- --
+    |    |
+    |    -- this will increase with bug fixes/enhancements to the driver
+    |-- this is the version of the PCC specification the driver adheres to
+
+
+The following is a brief discussion on some of the fields exported via the
+/sys filesystem and how their values are affected by the PCC driver:
+
+2.1 scaling_available_frequencies:
+----------------------------------
+scaling_available_frequencies is not created in /sys. No intermediate
+frequencies need to be listed because the BIOS will try to achieve any
+frequency, within limits, requested by the governor. A frequency does not have
+to be strictly associated with a P-state.
+
+2.2 cpuinfo_transition_latency:
+-------------------------------
+The cpuinfo_transition_latency field is 0. The PCC specification does
+not include a field to expose this value currently.
+
+2.3 cpuinfo_cur_freq:
+---------------------
+A) Often cpuinfo_cur_freq will show a value different than what is declared
+in the scaling_available_frequencies or scaling_cur_freq, or scaling_max_freq.
+This is due to "turbo boost" available on recent Intel processors. If certain
+conditions are met the BIOS can achieve a slightly higher speed than requested
+by OSPM. An example:
+
+scaling_cur_freq	: 2933000
+cpuinfo_cur_freq	: 3196000
+
+B) There is a round-off error associated with the cpuinfo_cur_freq value.
+Since the driver obtains the current frequency as a "percentage" (%) of the
+nominal frequency from the BIOS, sometimes, the values displayed by
+scaling_cur_freq and cpuinfo_cur_freq may not match. An example:
+
+scaling_cur_freq	: 1600000
+cpuinfo_cur_freq	: 1583000
+
+In this example, the nominal frequency is 2933 MHz. The driver obtains the
+current frequency, cpuinfo_cur_freq, as 54% of the nominal frequency:
+
+	54% of 2933 MHz = 1583 MHz
+
+Nominal frequency is the maximum frequency of the processor, and it usually
+corresponds to the frequency of the P0 P-state.
+
+2.4 related_cpus:
+-----------------
+The related_cpus field is identical to affected_cpus.
+
+affected_cpus	: 4
+related_cpus	: 4
+
+Currently, the PCC driver does not evaluate _PSD. The platforms that support
+PCC do not implement SW_ALL. So OSPM doesn't need to perform any coordination
+to ensure that the same frequency is requested of all dependent CPUs.
+
+3. Caveats:
+-----------
+The "cpufreq_stats" module in its present form cannot be loaded and
+expected to work with the PCC driver. Since the "cpufreq_stats" module
+provides information wrt each P-state, it is not applicable to the PCC driver.
diff --git a/Documentation/device-mapper/snapshot.txt b/Documentation/device-mapper/snapshot.txt
index e3a77b21513..0d5bc46dc16 100644
--- a/Documentation/device-mapper/snapshot.txt
+++ b/Documentation/device-mapper/snapshot.txt
@@ -122,3 +122,47 @@ volumeGroup-base: 0 2097152 snapshot-merge 254:11 254:12 P 16
 brw-------  1 root root 254, 11 29 ago 18:15 /dev/mapper/volumeGroup-base-real
 brw-------  1 root root 254, 12 29 ago 18:16 /dev/mapper/volumeGroup-base-cow
 brw-------  1 root root 254, 10 29 ago 18:16 /dev/mapper/volumeGroup-base
+
+
+How to determine when a merging is complete
+===========================================
+The snapshot-merge and snapshot status lines end with:
+  <sectors_allocated>/<total_sectors> <metadata_sectors>
+
+Both <sectors_allocated> and <total_sectors> include both data and metadata.
+During merging, the number of sectors allocated gets smaller and
+smaller.  Merging has finished when the number of sectors holding data
+is zero, in other words <sectors_allocated> == <metadata_sectors>.
+
+Here is a practical example (using a hybrid of lvm and dmsetup commands):
+
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g
+  snap    volumeGroup swi-a- 1.00g base  18.97
+
+# dmsetup status volumeGroup-snap
+0 8388608 snapshot 397896/2097152 1560
+                                  ^^^^ metadata sectors
+
+# lvconvert --merge -b volumeGroup/snap
+  Merging of volume snap started.
+
+# lvs volumeGroup/snap
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup Owi-a- 4.00g          17.23
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 281688/2097152 1104
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 180480/2097152 712
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 16/2097152 16
+
+Merging has finished.
+
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g
diff --git a/Documentation/dontdiff b/Documentation/dontdiff
index 3ad6acead94..d9bcffd5943 100644
--- a/Documentation/dontdiff
+++ b/Documentation/dontdiff
@@ -69,7 +69,6 @@ av_permissions.h
 bbootsect
 bin2c
 binkernel.spec
-binoffset
 bootsect
 bounds.h
 bsetup
diff --git a/Documentation/dvb/get_dvb_firmware b/Documentation/dvb/get_dvb_firmware
index 14b7b5a3bcb..239cbdbf4d1 100644
--- a/Documentation/dvb/get_dvb_firmware
+++ b/Documentation/dvb/get_dvb_firmware
@@ -26,7 +26,7 @@ use IO::Handle;
 		"dec3000s", "vp7041", "dibusb", "nxt2002", "nxt2004",
 		"or51211", "or51132_qam", "or51132_vsb", "bluebird",
 		"opera1", "cx231xx", "cx18", "cx23885", "pvrusb2", "mpc718",
-		"af9015");
+		"af9015", "ngene");
 
 # Check args
 syntax() if (scalar(@ARGV) != 1);
@@ -39,7 +39,7 @@ for ($i=0; $i < scalar(@components); $i++) {
 	die $@ if $@;
 	print STDERR <<EOF;
 Firmware(s) $outfile extracted successfully.
-Now copy it(they) to either /usr/lib/hotplug/firmware or /lib/firmware
+Now copy it(them) to either /usr/lib/hotplug/firmware or /lib/firmware
 (depending on configuration of firmware hotplug).
 EOF
 	exit(0);
@@ -549,6 +549,24 @@ sub af9015 {
 	close INFILE;
 }
 
+sub ngene {
+    my $url = "http://www.digitaldevices.de/download/";
+    my $file1 = "ngene_15.fw";
+    my $hash1 = "d798d5a757121174f0dbc5f2833c0c85";
+    my $file2 = "ngene_17.fw";
+    my $hash2 = "26b687136e127b8ac24b81e0eeafc20b";
+
+    checkstandard();
+
+    wgetfile($file1, $url . $file1);
+    verify($file1, $hash1);
+
+    wgetfile($file2, $url . $file2);
+    verify($file2, $hash2);
+
+    "$file1, $file2";
+}
+
 # ---------------------------------------------------------------
 # Utilities
 
@@ -667,6 +685,7 @@ sub delzero{
 sub syntax() {
     print STDERR "syntax: get_dvb_firmware <component>\n";
     print STDERR "Supported components:\n";
+    @components = sort @components;
     for($i=0; $i < scalar(@components); $i++) {
 	print STDERR "\t" . $components[$i] . "\n";
     }
diff --git a/Documentation/fault-injection/provoke-crashes.txt b/Documentation/fault-injection/provoke-crashes.txt
new file mode 100644
index 00000000000..7a9d3d81525
--- /dev/null
+++ b/Documentation/fault-injection/provoke-crashes.txt
@@ -0,0 +1,38 @@
+The lkdtm module provides an interface to crash or injure the kernel at
+predefined crashpoints to evaluate the reliability of crash dumps obtained
+using different dumping solutions. The module uses KPROBEs to instrument
+crashing points, but can also crash the kernel directly without KRPOBE
+support.
+
+
+You can provide the way either through module arguments when inserting
+the module, or through a debugfs interface.
+
+Usage: insmod lkdtm.ko [recur_count={>0}] cpoint_name=<> cpoint_type=<>
+				[cpoint_count={>0}]
+
+  recur_count : Recursion level for the stack overflow test. Default is 10.
+
+  cpoint_name : Crash point where the kernel is to be crashed. It can be
+	 one of INT_HARDWARE_ENTRY, INT_HW_IRQ_EN, INT_TASKLET_ENTRY,
+	 FS_DEVRW, MEM_SWAPOUT, TIMERADD, SCSI_DISPATCH_CMD,
+	 IDE_CORE_CP, DIRECT
+
+  cpoint_type : Indicates the action to be taken on hitting the crash point.
+     It can be one of PANIC, BUG, EXCEPTION, LOOP, OVERFLOW,
+     CORRUPT_STACK, UNALIGNED_LOAD_STORE_WRITE, OVERWRITE_ALLOCATION,
+     WRITE_AFTER_FREE,
+
+  cpoint_count : Indicates the number of times the crash point is to be hit
+    to trigger an action. The default is 10.
+
+You can also induce failures by mounting debugfs and writing the type to
+<mountpoint>/provoke-crash/<crashpoint>. E.g.,
+
+  mount -t debugfs debugfs /mnt
+  echo EXCEPTION > /mnt/provoke-crash/INT_HARDWARE_ENTRY
+
+
+A special file is `DIRECT' which will induce the crash directly without
+KPROBE instrumentation. This mode is the only one available when the module
+is built on a kernel without KPROBEs support.
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 0a46833c1b7..a5cc0db63d7 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -6,21 +6,6 @@ be removed from this file.
 
 ---------------------------
 
-What:	USER_SCHED
-When:	2.6.34
-
-Why:	USER_SCHED was implemented as a proof of concept for group scheduling.
-	The effect of USER_SCHED can already be achieved from userspace with
-	the help of libcgroup. The removal of USER_SCHED will also simplify
-	the scheduler code with the removal of one major ifdef. There are also
-	issues USER_SCHED has with USER_NS. A decision was taken not to fix
-	those and instead remove USER_SCHED. Also new group scheduling
-	features will not be implemented for USER_SCHED.
-
-Who:	Dhaval Giani <dhaval@linux.vnet.ibm.com>
-
----------------------------
-
 What:	PRISM54
 When:	2.6.34
 
@@ -64,6 +49,17 @@ Who:	Robin Getz <rgetz@blackfin.uclinux.org> & Matt Mackall <mpm@selenic.com>
 
 ---------------------------
 
+What:	Deprecated snapshot ioctls
+When:	2.6.36
+
+Why:	The ioctls in kernel/power/user.c were marked as deprecated long time
+	ago. Now they notify users about that so that they need to replace
+	their userspace. After some more time, remove them completely.
+
+Who:	Jiri Slaby <jirislaby@gmail.com>
+
+---------------------------
+
 What:	The ieee80211_regdom module parameter
 When:	March 2010 / desktop catchup
 
@@ -88,27 +84,6 @@ Who:	Luis R. Rodriguez <lrodriguez@atheros.com>
 
 ---------------------------
 
-What:	CONFIG_WIRELESS_OLD_REGULATORY - old static regulatory information
-When:	March 2010 / desktop catchup
-
-Why:	The old regulatory infrastructure has been replaced with a new one
-	which does not require statically defined regulatory domains. We do
-	not want to keep static regulatory domains in the kernel due to the
-	the dynamic nature of regulatory law and localization. We kept around
-	the old static definitions for the regulatory domains of:
-
-		* US
-		* JP
-		* EU
-
-	and used by default the US when CONFIG_WIRELESS_OLD_REGULATORY was
-	set. We will remove this option once the standard Linux desktop catches
-	up with the new userspace APIs we have implemented.
-
-Who:	Luis R. Rodriguez <lrodriguez@atheros.com>
-
----------------------------
-
 What:	dev->power.power_state
 When:	July 2007
 Why:	Broken design for runtime control over driver power states, confusing
@@ -142,19 +117,25 @@ Who:	Mauro Carvalho Chehab <mchehab@infradead.org>
 ---------------------------
 
 What:	PCMCIA control ioctl (needed for pcmcia-cs [cardmgr, cardctl])
-When:	November 2005
+When:	2.6.35/2.6.36
 Files:	drivers/pcmcia/: pcmcia_ioctl.c
 Why:	With the 16-bit PCMCIA subsystem now behaving (almost) like a
 	normal hotpluggable bus, and with it using the default kernel
 	infrastructure (hotplug, driver core, sysfs) keeping the PCMCIA
 	control ioctl needed by cardmgr and cardctl from pcmcia-cs is
-	unnecessary, and makes further cleanups and integration of the
+	unnecessary and potentially harmful (it does not provide for
+	proper locking), and makes further cleanups and integration of the
 	PCMCIA subsystem into the Linux kernel device driver model more
 	difficult. The features provided by cardmgr and cardctl are either
 	handled by the kernel itself now or are available in the new
 	pcmciautils package available at
 	http://kernel.org/pub/linux/utils/kernel/pcmcia/
-Who:	Dominik Brodowski <linux@brodo.de>
+
+	For all architectures except ARM, the associated config symbol
+	has been removed from kernel 2.6.34; for ARM, it will be likely
+	be removed from kernel 2.6.35. The actual code will then likely
+	be removed from kernel 2.6.36.
+Who:	Dominik Brodowski <linux@dominikbrodowski.net>
 
 ---------------------------
 
@@ -468,12 +449,6 @@ Who:	Alok N Kataria <akataria@vmware.com>
 
 ----------------------------
 
-What:	adt7473 hardware monitoring driver
-When:	February 2010
-Why:	Obsoleted by the adt7475 driver.
-Who:	Jean Delvare <khali@linux-fr.org>
-
----------------------------
 What:	Support for lcd_switch and display_get in asus-laptop driver
 When:	March 2010
 Why:	These two features use non-standard interfaces. There are the
@@ -542,3 +517,68 @@ Why:	Duplicate functionality with the gspca_zc3xx driver, zc0301 only
 	sensors) wich are also supported by the gspca_zc3xx driver
 	(which supports 53 USB-ID's in total)
 Who:	Hans de Goede <hdegoede@redhat.com>
+
+----------------------------
+
+What:	corgikbd, spitzkbd, tosakbd driver
+When:	2.6.35
+Files:	drivers/input/keyboard/{corgi,spitz,tosa}kbd.c
+Why:	We now have a generic GPIO based matrix keyboard driver that
+	are fully capable of handling all the keys on these devices.
+	The original drivers manipulate the GPIO registers directly
+	and so are difficult to maintain.
+Who:	Eric Miao <eric.y.miao@gmail.com>
+
+----------------------------
+
+What:	corgi_ssp and corgi_ts driver
+When:	2.6.35
+Files:	arch/arm/mach-pxa/corgi_ssp.c, drivers/input/touchscreen/corgi_ts.c
+Why:	The corgi touchscreen is now deprecated in favour of the generic
+	ads7846.c driver. The noise reduction technique used in corgi_ts.c,
+	that's to wait till vsync before ADC sampling, is also integrated into
+	ads7846 driver now. Provided that the original driver is not generic
+	and is difficult to maintain, it will be removed later.
+Who:	Eric Miao <eric.y.miao@gmail.com>
+
+----------------------------
+
+What:	capifs
+When:	February 2011
+Files:	drivers/isdn/capi/capifs.*
+Why:	udev fully replaces this special file system that only contains CAPI
+	NCCI TTY device nodes. User space (pppdcapiplugin) works without
+	noticing the difference.
+Who:	Jan Kiszka <jan.kiszka@web.de>
+
+----------------------------
+
+What:	KVM memory aliases support
+When:	July 2010
+Why:	Memory aliasing support is used for speeding up guest vga access
+	through the vga windows.
+
+	Modern userspace no longer uses this feature, so it's just bitrotted
+	code and can be removed with no impact.
+Who:	Avi Kivity <avi@redhat.com>
+
+----------------------------
+
+What:	KVM kernel-allocated memory slots
+When:	July 2010
+Why:	Since 2.6.25, kvm supports user-allocated memory slots, which are
+	much more flexible than kernel-allocated slots.  All current userspace
+	supports the newer interface and this code can be removed with no
+	impact.
+Who:	Avi Kivity <avi@redhat.com>
+
+----------------------------
+
+What:	KVM paravirt mmu host support
+When:	January 2011
+Why:	The paravirt mmu host support is slower than non-paravirt mmu, both
+	on newer and older hardware.  It is already not exposed to the guest,
+	and kept only for live migration purposes.
+Who:	Avi Kivity <avi@redhat.com>
+
+----------------------------
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 875d49696b6..5139b8c9d5a 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -62,6 +62,8 @@ jfs.txt
 	- info and mount options for the JFS filesystem.
 locks.txt
 	- info on file locking implementations, flock() vs. fcntl(), etc.
+logfs.txt
+	- info on the LogFS flash filesystem.
 mandatory-locking.txt
 	- info on the Linux implementation of Sys V mandatory file locking.
 ncpfs.txt
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 18b9d0ca063..06bbbed7120 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -460,13 +460,6 @@ in sys_read() and friends.
 
 --------------------------- dquot_operations -------------------------------
 prototypes:
-	int (*initialize) (struct inode *, int);
-	int (*drop) (struct inode *);
-	int (*alloc_space) (struct inode *, qsize_t, int);
-	int (*alloc_inode) (const struct inode *, unsigned long);
-	int (*free_space) (struct inode *, qsize_t);
-	int (*free_inode) (const struct inode *, unsigned long);
-	int (*transfer) (struct inode *, struct iattr *);
 	int (*write_dquot) (struct dquot *);
 	int (*acquire_dquot) (struct dquot *);
 	int (*release_dquot) (struct dquot *);
@@ -479,13 +472,6 @@ a proper locking wrt the filesystem and call the generic quota operations.
 What filesystem should expect from the generic quota functions:
 
 		FS recursion	Held locks when called
-initialize:	yes		maybe dqonoff_sem
-drop:		yes		-
-alloc_space:	->mark_dirty()	-
-alloc_inode:	->mark_dirty()	-
-free_space:	->mark_dirty()	-
-free_inode:	->mark_dirty()	-
-transfer:	yes		-
 write_dquot:	yes		dqonoff_sem or dqptr_sem
 acquire_dquot:	yes		dqonoff_sem or dqptr_sem
 release_dquot:	yes		dqonoff_sem or dqptr_sem
@@ -495,10 +481,6 @@ write_info:	yes		dqonoff_sem
 FS recursion means calling ->quota_read() and ->quota_write() from superblock
 operations.
 
-->alloc_space(), ->alloc_inode(), ->free_space(), ->free_inode() are called
-only directly by the filesystem and do not call any fs functions only
-the ->mark_dirty() operation.
-
 More details about quota locking can be found in fs/dquot.c.
 
 --------------------------- vm_operations_struct -----------------------------
diff --git a/Documentation/filesystems/dentry-locking.txt b/Documentation/filesystems/dentry-locking.txt
index 4c0c575a401..79334ed5daa 100644
--- a/Documentation/filesystems/dentry-locking.txt
+++ b/Documentation/filesystems/dentry-locking.txt
@@ -62,7 +62,8 @@ changes are :
 2. Insertion of a dentry into the hash table is done using
    hlist_add_head_rcu() which take care of ordering the writes - the
    writes to the dentry must be visible before the dentry is
-   inserted. This works in conjunction with hlist_for_each_rcu() while
+   inserted. This works in conjunction with hlist_for_each_rcu(),
+   which has since been replaced by hlist_for_each_entry_rcu(), while
    walking the hash chain. The only requirement is that all
    initialization to the dentry must be done before
    hlist_add_head_rcu() since we don't have dcache_lock protection
diff --git a/Documentation/filesystems/logfs.txt b/Documentation/filesystems/logfs.txt
new file mode 100644
index 00000000000..e64c94ba401
--- /dev/null
+++ b/Documentation/filesystems/logfs.txt
@@ -0,0 +1,241 @@
+
+The LogFS Flash Filesystem
+==========================
+
+Specification
+=============
+
+Superblocks
+-----------
+
+Two superblocks exist at the beginning and end of the filesystem.
+Each superblock is 256 Bytes large, with another 3840 Bytes reserved
+for future purposes, making a total of 4096 Bytes.
+
+Superblock locations may differ for MTD and block devices.  On MTD the
+first non-bad block contains a superblock in the first 4096 Bytes and
+the last non-bad block contains a superblock in the last 4096 Bytes.
+On block devices, the first 4096 Bytes of the device contain the first
+superblock and the last aligned 4096 Byte-block contains the second
+superblock.
+
+For the most part, the superblocks can be considered read-only.  They
+are written only to correct errors detected within the superblocks,
+move the journal and change the filesystem parameters through tunefs.
+As a result, the superblock does not contain any fields that require
+constant updates, like the amount of free space, etc.
+
+Segments
+--------
+
+The space in the device is split up into equal-sized segments.
+Segments are the primary write unit of LogFS.  Within each segments,
+writes happen from front (low addresses) to back (high addresses.  If
+only a partial segment has been written, the segment number, the
+current position within and optionally a write buffer are stored in
+the journal.
+
+Segments are erased as a whole.  Therefore Garbage Collection may be
+required to completely free a segment before doing so.
+
+Journal
+--------
+
+The journal contains all global information about the filesystem that
+is subject to frequent change.  At mount time, it has to be scanned
+for the most recent commit entry, which contains a list of pointers to
+all currently valid entries.
+
+Object Store
+------------
+
+All space except for the superblocks and journal is part of the object
+store.  Each segment contains a segment header and a number of
+objects, each consisting of the object header and the payload.
+Objects are either inodes, directory entries (dentries), file data
+blocks or indirect blocks.
+
+Levels
+------
+
+Garbage collection (GC) may fail if all data is written
+indiscriminately.  One requirement of GC is that data is seperated
+roughly according to the distance between the tree root and the data.
+Effectively that means all file data is on level 0, indirect blocks
+are on levels 1, 2, 3 4 or 5 for 1x, 2x, 3x, 4x or 5x indirect blocks,
+respectively.  Inode file data is on level 6 for the inodes and 7-11
+for indirect blocks.
+
+Each segment contains objects of a single level only.  As a result,
+each level requires its own seperate segment to be open for writing.
+
+Inode File
+----------
+
+All inodes are stored in a special file, the inode file.  Single
+exception is the inode file's inode (master inode) which for obvious
+reasons is stored in the journal instead.  Instead of data blocks, the
+leaf nodes of the inode files are inodes.
+
+Aliases
+-------
+
+Writes in LogFS are done by means of a wandering tree.  A naïve
+implementation would require that for each write or a block, all
+parent blocks are written as well, since the block pointers have
+changed.  Such an implementation would not be very efficient.
+
+In LogFS, the block pointer changes are cached in the journal by means
+of alias entries.  Each alias consists of its logical address - inode
+number, block index, level and child number (index into block) - and
+the changed data.  Any 8-byte word can be changes in this manner.
+
+Currently aliases are used for block pointers, file size, file used
+bytes and the height of an inodes indirect tree.
+
+Segment Aliases
+---------------
+
+Related to regular aliases, these are used to handle bad blocks.
+Initially, bad blocks are handled by moving the affected segment
+content to a spare segment and noting this move in the journal with a
+segment alias, a simple (to, from) tupel.  GC will later empty this
+segment and the alias can be removed again.  This is used on MTD only.
+
+Vim
+---
+
+By cleverly predicting the life time of data, it is possible to
+seperate long-living data from short-living data and thereby reduce
+the GC overhead later.  Each type of distinc life expectency (vim) can
+have a seperate segment open for writing.  Each (level, vim) tupel can
+be open just once.  If an open segment with unknown vim is encountered
+at mount time, it is closed and ignored henceforth.
+
+Indirect Tree
+-------------
+
+Inodes in LogFS are similar to FFS-style filesystems with direct and
+indirect block pointers.  One difference is that LogFS uses a single
+indirect pointer that can be either a 1x, 2x, etc. indirect pointer.
+A height field in the inode defines the height of the indirect tree
+and thereby the indirection of the pointer.
+
+Another difference is the addressing of indirect blocks.  In LogFS,
+the first 16 pointers in the first indirect block are left empty,
+corresponding to the 16 direct pointers in the inode.  In ext2 (maybe
+others as well) the first pointer in the first indirect block
+corresponds to logical block 12, skipping the 12 direct pointers.
+So where ext2 is using arithmetic to better utilize space, LogFS keeps
+arithmetic simple and uses compression to save space.
+
+Compression
+-----------
+
+Both file data and metadata can be compressed.  Compression for file
+data can be enabled with chattr +c and disabled with chattr -c.  Doing
+so has no effect on existing data, but new data will be stored
+accordingly.  New inodes will inherit the compression flag of the
+parent directory.
+
+Metadata is always compressed.  However, the space accounting ignores
+this and charges for the uncompressed size.  Failing to do so could
+result in GC failures when, after moving some data, indirect blocks
+compress worse than previously.  Even on a 100% full medium, GC may
+not consume any extra space, so the compression gains are lost space
+to the user.
+
+However, they are not lost space to the filesystem internals.  By
+cheating the user for those bytes, the filesystem gained some slack
+space and GC will run less often and faster.
+
+Garbage Collection and Wear Leveling
+------------------------------------
+
+Garbage collection is invoked whenever the number of free segments
+falls below a threshold.  The best (known) candidate is picked based
+on the least amount of valid data contained in the segment.  All
+remaining valid data is copied elsewhere, thereby invalidating it.
+
+The GC code also checks for aliases and writes then back if their
+number gets too large.
+
+Wear leveling is done by occasionally picking a suboptimal segment for
+garbage collection.  If a stale segments erase count is significantly
+lower than the active segments' erase counts, it will be picked.  Wear
+leveling is rate limited, so it will never monopolize the device for
+more than one segment worth at a time.
+
+Values for "occasionally", "significantly lower" are compile time
+constants.
+
+Hashed directories
+------------------
+
+To satisfy efficient lookup(), directory entries are hashed and
+located based on the hash.  In order to both support large directories
+and not be overly inefficient for small directories, several hash
+tables of increasing size are used.  For each table, the hash value
+modulo the table size gives the table index.
+
+Tables sizes are chosen to limit the number of indirect blocks with a
+fully populated table to 0, 1, 2 or 3 respectively.  So the first
+table contains 16 entries, the second 512-16, etc.
+
+The last table is special in several ways.  First its size depends on
+the effective 32bit limit on telldir/seekdir cookies.  Since logfs
+uses the upper half of the address space for indirect blocks, the size
+is limited to 2^31.  Secondly the table contains hash buckets with 16
+entries each.
+
+Using single-entry buckets would result in birthday "attacks".  At
+just 2^16 used entries, hash collisions would be likely (P >= 0.5).
+My math skills are insufficient to do the combinatorics for the 17x
+collisions necessary to overflow a bucket, but testing showed that in
+10,000 runs the lowest directory fill before a bucket overflow was
+188,057,130 entries with an average of 315,149,915 entries.  So for
+directory sizes of up to a million, bucket overflows should be
+virtually impossible under normal circumstances.
+
+With carefully chosen filenames, it is obviously possible to cause an
+overflow with just 21 entries (4 higher tables + 16 entries + 1).  So
+there may be a security concern if a malicious user has write access
+to a directory.
+
+Open For Discussion
+===================
+
+Device Address Space
+--------------------
+
+A device address space is used for caching.  Both block devices and
+MTD provide functions to either read a single page or write a segment.
+Partial segments may be written for data integrity, but where possible
+complete segments are written for performance on simple block device
+flash media.
+
+Meta Inodes
+-----------
+
+Inodes are stored in the inode file, which is just a regular file for
+most purposes.  At umount time, however, the inode file needs to
+remain open until all dirty inodes are written.  So
+generic_shutdown_super() may not close this inode, but shouldn't
+complain about remaining inodes due to the inode file either.  Same
+goes for mapping inode of the device address space.
+
+Currently logfs uses a hack that essentially copies part of fs/inode.c
+code over.  A general solution would be preferred.
+
+Indirect block mapping
+----------------------
+
+With compression, the block device (or mapping inode) cannot be used
+to cache indirect blocks.  Some other place is required.  Currently
+logfs uses the top half of each inode's address space.  The low 8TB
+(on 32bit) are filled with file data, the high 8TB are used for
+indirect blocks.
+
+One problem is that 16TB files created on 64bit systems actually have
+data in the top 8TB.  But files >16TB would cause problems anyway, so
+only the limit has changed.
diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt
index 1bd0d0c0517..6a53a84afc7 100644
--- a/Documentation/filesystems/nfs/nfs41-server.txt
+++ b/Documentation/filesystems/nfs/nfs41-server.txt
@@ -17,8 +17,7 @@ kernels must turn 4.1 on or off *before* turning support for version 4
 on or off; rpc.nfsd does this correctly.)
 
 The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based
-on the latest NFSv4.1 Internet Draft:
-http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29
+on RFC 5661.
 
 From the many new features in NFSv4.1 the current implementation
 focuses on the mandatory-to-implement NFSv4.1 Sessions, providing
@@ -44,7 +43,7 @@ interoperability problems with future clients.  Known issues:
 	  trunking, but this is a mandatory feature, and its use is
 	  recommended to clients in a number of places.  (E.g. to ensure
 	  timely renewal in case an existing connection's retry timeouts
-	  have gotten too long; see section 8.3 of the draft.)
+	  have gotten too long; see section 8.3 of the RFC.)
 	  Therefore, lack of this feature may cause future clients to
 	  fail.
 	- Incomplete backchannel support: incomplete backchannel gss
diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt
index 839efd8a8a8..cf6d0d85ca8 100644
--- a/Documentation/filesystems/nilfs2.txt
+++ b/Documentation/filesystems/nilfs2.txt
@@ -74,6 +74,9 @@ norecovery		Disable recovery of the filesystem on mount.
 			This disables every write access on the device for
 			read-only mounts or snapshots.  This option will fail
 			for r/w mounts on an unclean volume.
+discard			Issue discard/TRIM commands to the underlying block
+			device when blocks are freed.  This is useful for SSD
+			devices and sparse/thinly-provisioned LUNs.
 
 NILFS2 usage
 ============
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 0d07513a67a..96a44dd95e0 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -164,6 +164,7 @@ read the file /proc/PID/status:
   VmExe:        68 kB
   VmLib:      1412 kB
   VmPTE:        20 kb
+  VmSwap:        0 kB
   Threads:        1
   SigQ:   0/28578
   SigPnd: 0000000000000000
@@ -188,6 +189,12 @@ memory usage. Its seven fields are explained in Table 1-3.  The stat file
 contains details information about the process itself.  Its fields are
 explained in Table 1-4.
 
+(for SMP CONFIG users)
+For making accounting scalable, RSS related information are handled in
+asynchronous manner and the vaule may not be very precise. To see a precise
+snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
+It's slow but very precise.
+
 Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
 ..............................................................................
  Field                       Content
@@ -213,6 +220,7 @@ Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
  VmExe                       size of text segment
  VmLib                       size of shared library code
  VmPTE                       size of page table entries
+ VmSwap                      size of swap usage (the number of referred swapents)
  Threads                     number of threads
  SigQ                        number of signals queued/max. number for queue
  SigPnd                      bitmap of pending signals for the thread
@@ -430,6 +438,7 @@ Table 1-5: Kernel info in /proc
  modules     List of loaded modules                            
  mounts      Mounted filesystems                               
  net         Networking info (see text)                        
+ pagetypeinfo Additional page allocator information (see text)  (2.5)
  partitions  Table of partitions known to the system           
  pci	     Deprecated info of PCI bus (new way -> /proc/bus/pci/,
              decoupled by lspci					(2.4)
@@ -584,7 +593,7 @@ Node 0, zone      DMA      0      4      5      4      4      3 ...
 Node 0, zone   Normal      1      0      0      1    101      8 ...
 Node 0, zone  HighMem      2      0      0      1      1      0 ...
 
-Memory fragmentation is a problem under some workloads, and buddyinfo is a 
+External fragmentation is a problem under some workloads, and buddyinfo is a
 useful tool for helping diagnose these problems.  Buddyinfo will give you a 
 clue as to how big an area you can safely allocate, or why a previous
 allocation failed.
@@ -594,6 +603,48 @@ available.  In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 
 available in ZONE_NORMAL, etc... 
 
+More information relevant to external fragmentation can be found in
+pagetypeinfo.
+
+> cat /proc/pagetypeinfo
+Page block order: 9
+Pages per block:  512
+
+Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
+Node    0, zone      DMA, type    Unmovable      0      0      0      1      1      1      1      1      1      1      0
+Node    0, zone      DMA, type  Reclaimable      0      0      0      0      0      0      0      0      0      0      0
+Node    0, zone      DMA, type      Movable      1      1      2      1      2      1      1      0      1      0      2
+Node    0, zone      DMA, type      Reserve      0      0      0      0      0      0      0      0      0      1      0
+Node    0, zone      DMA, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
+Node    0, zone    DMA32, type    Unmovable    103     54     77      1      1      1     11      8      7      1      9
+Node    0, zone    DMA32, type  Reclaimable      0      0      2      1      0      0      0      0      1      0      0
+Node    0, zone    DMA32, type      Movable    169    152    113     91     77     54     39     13      6      1    452
+Node    0, zone    DMA32, type      Reserve      1      2      2      2      2      0      1      1      1      1      0
+Node    0, zone    DMA32, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
+
+Number of blocks type     Unmovable  Reclaimable      Movable      Reserve      Isolate
+Node 0, zone      DMA            2            0            5            1            0
+Node 0, zone    DMA32           41            6          967            2            0
+
+Fragmentation avoidance in the kernel works by grouping pages of different
+migrate types into the same contiguous regions of memory called page blocks.
+A page block is typically the size of the default hugepage size e.g. 2MB on
+X86-64. By keeping pages grouped based on their ability to move, the kernel
+can reclaim pages within a page block to satisfy a high-order allocation.
+
+The pagetypinfo begins with information on the size of a page block. It
+then gives the same type of information as buddyinfo except broken down
+by migrate-type and finishes with details on how many page blocks of each
+type exist.
+
+If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
+from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
+make an estimate of the likely number of huge pages that can be allocated
+at a given point in time. All the "Movable" blocks should be allocatable
+unless memory has been mlock()'d. Some of the Reclaimable blocks should
+also be allocatable although a lot of filesystem metadata may have to be
+reclaimed to achieve this.
+
 ..............................................................................
 
 meminfo:
diff --git a/Documentation/filesystems/sharedsubtree.txt b/Documentation/filesystems/sharedsubtree.txt
index 23a181074f9..fc0e39af43c 100644
--- a/Documentation/filesystems/sharedsubtree.txt
+++ b/Documentation/filesystems/sharedsubtree.txt
@@ -837,6 +837,9 @@ replicas continue to be exactly same.
 	 individual lists does not affect propagation or the way propagation
 	 tree is modified by operations.
 
+	All vfsmounts in a peer group have the same ->mnt_master.  If it is
+	non-NULL, they form a contiguous (ordered) segment of slave list.
+
 	A example propagation tree looks as shown in the figure below.
 	[ NOTE: Though it looks like a forest, if we consider all the shared
 	mounts as a conceptual entity called 'pnode', it becomes a tree]
@@ -874,8 +877,19 @@ replicas continue to be exactly same.
 
 	NOTE: The propagation tree is orthogonal to the mount tree.
 
+8B Locking:
+
+	->mnt_share, ->mnt_slave, ->mnt_slave_list, ->mnt_master are protected
+	by namespace_sem (exclusive for modifications, shared for reading).
+
+	Normally we have ->mnt_flags modifications serialized by vfsmount_lock.
+	There are two exceptions: do_add_mount() and clone_mnt().
+	The former modifies a vfsmount that has not been visible in any shared
+	data structures yet.
+	The latter holds namespace_sem and the only references to vfsmount
+	are in lists that can't be traversed without namespace_sem.
 
-8B Algorithm:
+8C Algorithm:
 
 	The crux of the implementation resides in rbind/move operation.
 
diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt
index 1866c27eec6..c2c6e9b39bb 100644
--- a/Documentation/gpio.txt
+++ b/Documentation/gpio.txt
@@ -253,6 +253,70 @@ pin setup (e.g. controlling which pin the GPIO uses, pullup/pulldown).
 Also note that it's your responsibility to have stopped using a GPIO
 before you free it.
 
+Considering in most cases GPIOs are actually configured right after they
+are claimed, three additional calls are defined:
+
+	/* request a single GPIO, with initial configuration specified by
+	 * 'flags', identical to gpio_request() wrt other arguments and
+	 * return value
+	 */
+	int gpio_request_one(unsigned gpio, unsigned long flags, const char *label);
+
+	/* request multiple GPIOs in a single call
+	 */
+	int gpio_request_array(struct gpio *array, size_t num);
+
+	/* release multiple GPIOs in a single call
+	 */
+	void gpio_free_array(struct gpio *array, size_t num);
+
+where 'flags' is currently defined to specify the following properties:
+
+	* GPIOF_DIR_IN		- to configure direction as input
+	* GPIOF_DIR_OUT		- to configure direction as output
+
+	* GPIOF_INIT_LOW	- as output, set initial level to LOW
+	* GPIOF_INIT_HIGH	- as output, set initial level to HIGH
+
+since GPIOF_INIT_* are only valid when configured as output, so group valid
+combinations as:
+
+	* GPIOF_IN		- configure as input
+	* GPIOF_OUT_INIT_LOW	- configured as output, initial level LOW
+	* GPIOF_OUT_INIT_HIGH	- configured as output, initial level HIGH
+
+In the future, these flags can be extended to support more properties such
+as open-drain status.
+
+Further more, to ease the claim/release of multiple GPIOs, 'struct gpio' is
+introduced to encapsulate all three fields as:
+
+	struct gpio {
+		unsigned	gpio;
+		unsigned long	flags;
+		const char	*label;
+	};
+
+A typical example of usage:
+
+	static struct gpio leds_gpios[] = {
+		{ 32, GPIOF_OUT_INIT_HIGH, "Power LED" }, /* default to ON */
+		{ 33, GPIOF_OUT_INIT_LOW,  "Green LED" }, /* default to OFF */
+		{ 34, GPIOF_OUT_INIT_LOW,  "Red LED"   }, /* default to OFF */
+		{ 35, GPIOF_OUT_INIT_LOW,  "Blue LED"  }, /* default to OFF */
+		{ ... },
+	};
+
+	err = gpio_request_one(31, GPIOF_IN, "Reset Button");
+	if (err)
+		...
+
+	err = gpio_request_array(leds_gpios, ARRAY_SIZE(leds_gpios));
+	if (err)
+		...
+
+	gpio_free_array(leds_gpios, ARRAY_SIZE(leds_gpios));
+
 
 GPIOs mapped to IRQs
 --------------------
diff --git a/Documentation/hwmon/adt7411 b/Documentation/hwmon/adt7411
new file mode 100644
index 00000000000..1632960f974
--- /dev/null
+++ b/Documentation/hwmon/adt7411
@@ -0,0 +1,42 @@
+Kernel driver adt7411
+=====================
+
+Supported chips:
+  * Analog Devices ADT7411
+    Prefix: 'adt7411'
+    Addresses scanned: 0x48, 0x4a, 0x4b
+    Datasheet: Publicly available at the Analog Devices website
+
+Author: Wolfram Sang (based on adt7470 by Darrick J. Wong)
+
+Description
+-----------
+
+This driver implements support for the Analog Devices ADT7411 chip. There may
+be other chips that implement this interface.
+
+The ADT7411 can use an I2C/SMBus compatible 2-wire interface or an
+SPI-compatible 4-wire interface. It provides a 10-bit analog to digital
+converter which measures 1 temperature, vdd and 8 input voltages. It has an
+internal temperature sensor, but an external one can also be connected (one
+loses 2 inputs then). There are high- and low-limit registers for all inputs.
+
+Check the datasheet for details.
+
+sysfs-Interface
+---------------
+
+in0_input	- vdd voltage input
+in[1-8]_input	- analog 1-8 input
+temp1_input	- temperature input
+
+Besides standard interfaces, this driver adds (0 = off, 1 = on):
+
+  adc_ref_vdd	- Use vdd as reference instead of 2.25 V
+  fast_sampling	- Sample at 22.5 kHz instead of 1.4 kHz, but drop filters
+  no_average	- Turn off averaging over 16 samples
+
+Notes
+-----
+
+SPI, external temperature sensor and limit registers are not supported yet.
diff --git a/Documentation/hwmon/adt7473 b/Documentation/hwmon/adt7473
deleted file mode 100644
index 446612bd1fb..00000000000
--- a/Documentation/hwmon/adt7473
+++ /dev/null
@@ -1,74 +0,0 @@
-Kernel driver adt7473
-======================
-
-Supported chips:
-  * Analog Devices ADT7473
-    Prefix: 'adt7473'
-    Addresses scanned: I2C 0x2C, 0x2D, 0x2E
-    Datasheet: Publicly available at the Analog Devices website
-
-Author: Darrick J. Wong
-
-This driver is depreacted, please use the adt7475 driver instead.
-
-Description
------------
-
-This driver implements support for the Analog Devices ADT7473 chip family.
-
-The ADT7473 uses the 2-wire interface compatible with the SMBUS 2.0
-specification. Using an analog to digital converter it measures three (3)
-temperatures and two (2) voltages. It has four (4) 16-bit counters for
-measuring fan speed. There are three (3) PWM outputs that can be used
-to control fan speed.
-
-A sophisticated control system for the PWM outputs is designed into the
-ADT7473 that allows fan speed to be adjusted automatically based on any of the
-three temperature sensors. Each PWM output is individually adjustable and
-programmable. Once configured, the ADT7473 will adjust the PWM outputs in
-response to the measured temperatures without further host intervention.
-This feature can also be disabled for manual control of the PWM's.
-
-Each of the measured inputs (voltage, temperature, fan speed) has
-corresponding high/low limit values. The ADT7473 will signal an ALARM if
-any measured value exceeds either limit.
-
-The ADT7473 samples all inputs continuously. The driver will not read
-the registers more often than once every other second. Further,
-configuration data is only read once per minute.
-
-Special Features
-----------------
-
-The ADT7473 have a 10-bit ADC and can therefore measure temperatures
-with 0.25 degC resolution. Temperature readings can be configured either
-for twos complement format or "Offset 64" format, wherein 63 is subtracted
-from the raw value to get the temperature value.
-
-The Analog Devices datasheet is very detailed and describes a procedure for
-determining an optimal configuration for the automatic PWM control.
-
-Configuration Notes
--------------------
-
-Besides standard interfaces driver adds the following:
-
-* PWM Control
-
-* pwm#_auto_point1_pwm and temp#_auto_point1_temp and
-* pwm#_auto_point2_pwm and temp#_auto_point2_temp -
-
-point1: Set the pwm speed at a lower temperature bound.
-point2: Set the pwm speed at a higher temperature bound.
-
-The ADT7473 will scale the pwm between the lower and higher pwm speed when
-the temperature is between the two temperature boundaries.  PWM values range
-from 0 (off) to 255 (full speed).  Fan speed will be set to maximum when the
-temperature sensor associated with the PWM control exceeds temp#_max.
-
-Notes
------
-
-The NVIDIA binary driver presents an ADT7473 chip via an on-card i2c bus.
-Unfortunately, they fail to set the i2c adapter class, so this driver may
-fail to find the chip until the nvidia driver is patched.
diff --git a/Documentation/hwmon/asc7621 b/Documentation/hwmon/asc7621
new file mode 100644
index 00000000000..7287be7e1f2
--- /dev/null
+++ b/Documentation/hwmon/asc7621
@@ -0,0 +1,296 @@
+Kernel driver asc7621
+==================
+
+Supported chips:
+    Andigilog aSC7621 and aSC7621a
+    Prefix: 'asc7621'
+    Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+    Datasheet: http://www.fairview5.com/linux/asc7621/asc7621.pdf
+
+Author:
+		George Joseph
+
+Description provided by Dave Pivin @ Andigilog:
+
+Andigilog has both the PECI and pre-PECI versions of the Heceta-6, as
+Intel calls them. Heceta-6e has high frequency PWM and Heceta-6p has
+added PECI and a 4th thermal zone. The Andigilog aSC7611 is the
+Heceta-6e part and aSC7621 is the Heceta-6p part. They are both in
+volume production, shipping to Intel and their subs.
+
+We have enhanced both parts relative to the governing Intel
+specification. First enhancement is temperature reading resolution. We
+have used registers below 20h for vendor-specific functions in addition
+to those in the Intel-specified vendor range.
+
+Our conversion process produces a result that is reported as two bytes.
+The fan speed control uses this finer value to produce a "step-less" fan
+PWM output. These two bytes are "read-locked" to guarantee that once a
+high or low byte is read, the other byte is locked-in until after the
+next read of any register. So to get an atomic reading, read high or low
+byte, then the very next read should be the opposite byte. Our data
+sheet says 10-bits of resolution, although you may find the lower bits
+are active, they are not necessarily reliable or useful externally. We
+chose not to mask them.
+
+We employ significant filtering that is user tunable as described in the
+data sheet. Our temperature reports and fan PWM outputs are very smooth
+when compared to the competition, in addition to the higher resolution
+temperature reports. The smoother PWM output does not require user
+intervention.
+
+We offer GPIO features on the former VID pins. These are open-drain
+outputs or inputs and may be used as general purpose I/O or as alarm
+outputs that are based on temperature limits. These are in 19h and 1Ah.
+
+We offer flexible mapping of temperature readings to thermal zones. Any
+temperature may be mapped to any zone, which has a default assignment
+that follows Intel's specs.
+
+Since there is a fan to zone assignment that allows for the "hotter" of
+a set of zones to control the PWM of an individual fan, but there is no
+indication to the user, we have added an indicator that shows which zone
+is currently controlling the PWM for a given fan. This is in register
+00h.
+
+Both remote diode temperature readings may be given an offset value such
+that the reported reading as well as the temperature used to determine
+PWM may be offset for system calibration purposes.
+
+PECI Extended configuration allows for having more than two domains per
+PECI address and also provides an enabling function for each PECI
+address. One could use our flexible zone assignment to have a zone
+assigned to up to 4 PECI addresses. This is not possible in the default
+Intel configuration. This would be useful in multi-CPU systems with
+individual fans on each that would benefit from individual fan control.
+This is in register 0Eh.
+
+The tachometer measurement system is flexible and able to adapt to many
+fan types. We can also support pulse-stretched PWM so that 3-wire fans
+may be used. These characteristics are in registers 04h to 07h.
+
+Finally, we have added a tach disable function that turns off the tach
+measurement system for individual tachs in order to save power. That is
+in register 75h.
+
+--
+aSC7621 Product Description
+
+The aSC7621 has a two wire digital interface compatible with SMBus 2.0.
+Using a 10-bit ADC, the aSC7621 measures the temperature of two remote diode
+connected transistors as well as its own die. Support for Platform
+Environmental Control Interface (PECI) is included.
+
+Using temperature information from these four zones, an automatic fan speed
+control algorithm is employed to minimize acoustic impact while achieving
+recommended CPU temperature under varying operational loads.
+
+To set fan speed, the aSC7621 has three independent pulse width modulation
+(PWM) outputs that are controlled by one, or a combination of three,
+temperature zones. Both high- and low-frequency PWM ranges are supported.
+
+The aSC7621 also includes a digital filter that can be invoked to smooth
+temperature readings for better control of fan speed and minimum acoustic
+impact.
+
+The aSC7621 has tachometer inputs to measure fan speed on up to four fans.
+Limit and status registers for all measured values are included to alert
+the system host that any measurements are outside of programmed limits
+via status registers.
+
+System voltages of VCCP, 2.5V, 3.3V, 5.0V, and 12V motherboard power are
+monitored efficiently with internal scaling resistors.
+
+Features
+- Supports PECI interface and monitors internal and remote thermal diodes
+- 2-wire, SMBus 2.0 compliant, serial interface
+- 10-bit ADC
+- Monitors VCCP, 2.5V, 3.3V, 5.0V, and 12V motherboard/processor supplies
+- Programmable autonomous fan control based on temperature readings
+- Noise filtering of temperature reading for fan speed control
+- 0.25C digital temperature sensor resolution
+- 3 PWM fan speed control outputs for 2-, 3- or 4-wire fans and up to 4 fan
+	tachometer inputs
+- Enhanced measured temperature to Temperature Zone assignment.
+- Provides high and low PWM frequency ranges
+- 3 GPIO pins for custom use
+- 24-Lead QSOP package
+
+Configuration Notes
+===================
+
+Except where noted below, the sysfs entries created by this driver follow
+the standards defined in "sysfs-interface".
+
+temp1_source
+	0 	(default) peci_legacy = 0, Remote 1 Temperature
+			peci_legacy = 1, PECI Processor Temperature 0
+	1 	Remote 1 Temperature
+	2 	Remote 2 Temperature
+	3 	Internal Temperature
+	4 	PECI Processor Temperature 0
+	5 	PECI Processor Temperature 1
+	6 	PECI Processor Temperature 2
+	7  PECI Processor Temperature 3
+
+temp2_source
+	0 	(default) Internal Temperature
+	1 	Remote 1 Temperature
+	2 	Remote 2 Temperature
+	3 	Internal Temperature
+	4 	PECI Processor Temperature 0
+	5 	PECI Processor Temperature 1
+	6 	PECI Processor Temperature 2
+	7 	PECI Processor Temperature 3
+
+temp3_source
+	0 	(default) Remote 2 Temperature
+	1 	Remote 1 Temperature
+	2 	Remote 2 Temperature
+	3 	Internal Temperature
+	4 	PECI Processor Temperature 0
+	5 	PECI Processor Temperature 1
+	6 	PECI Processor Temperature 2
+	7 	PECI Processor Temperature 3
+
+temp4_source
+	0 	(default) peci_legacy = 0, PECI Processor Temperature 0
+			peci_legacy = 1, Remote 1 Temperature
+	1 	Remote 1 Temperature
+	2 	Remote 2 Temperature
+	3 	Internal Temperature
+	4 	PECI Processor Temperature 0
+	5 	PECI Processor Temperature 1
+	6 	PECI Processor Temperature 2
+	7 	PECI Processor Temperature 3
+
+temp[1-4]_smoothing_enable
+temp[1-4]_smoothing_time
+	Smooths spikes in temp readings caused by noise.
+	Valid values in milliseconds are:
+	35000
+	17600
+	11800
+	 7000
+	 4400
+	 3000
+	 1600
+	  800
+
+temp[1-4]_crit
+	When the corresponding zone temperature reaches this value,
+	ALL pwm outputs will got to 100%.
+
+temp[5-8]_input
+temp[5-8]_enable
+	The aSC7621 can also read temperatures provided by the processor
+	via the PECI bus.  Usually these are "core" temps and are relative
+	to the point where the automatic thermal control circuit starts
+	throttling.  This means that these are usually negative numbers.
+
+pwm[1-3]_enable
+	0		Fan off.
+	1		Fan on manual control.
+	2		Fan on automatic control and will run at the minimum pwm
+				if the temperature for the zone is below the minimum.
+	3		Fan on automatic control but will be off if the temperature
+				for the zone is below the minimum.
+	4-254	Ignored.
+	255		Fan on full.
+
+pwm[1-3]_auto_channels
+	Bitmap as described in sysctl-interface with the following
+	exceptions...
+	Only the following combination of zones (and their corresponding masks)
+	are valid:
+	1
+	2
+	3
+	2,3
+	1,2,3
+	4
+	1,2,3,4
+
+	Special values:
+	0			Disabled.
+	16		Fan on manual control.
+	31		Fan on full.
+
+
+pwm[1-3]_invert
+	When set, inverts the meaning of pwm[1-3].
+	i.e.  when pwm = 0, the fan will be on full and
+	when pwm = 255 the fan will be off.
+
+pwm[1-3]_freq
+	PWM frequency in Hz
+	Valid values in Hz are:
+
+	10
+	15
+	23
+	30  (default)
+	38
+	47
+	62
+	94
+	23000
+	24000
+	25000
+	26000
+	27000
+	28000
+	29000
+	30000
+
+	Setting any other value will be ignored.
+
+peci_enable
+	Enables or disables PECI
+
+peci_avg
+	Input filter average time.
+
+	0 	0 Sec. (no Smoothing) (default)
+	1 	0.25 Sec.
+	2 	0.5 Sec.
+	3 	1.0 Sec.
+	4 	2.0 Sec.
+	5 	4.0 Sec.
+	6 	8.0 Sec.
+	7 	0.0 Sec.
+
+peci_legacy
+
+	0	Standard Mode (default)
+		Remote Diode 1 reading is associated with
+		Temperature Zone 1, PECI is associated with
+		Zone 4
+
+	1	Legacy Mode
+		PECI is associated with Temperature Zone 1,
+		Remote Diode 1 is associated with Zone 4
+
+peci_diode
+	Diode filter
+
+	0	0.25 Sec.
+	1 	1.1 Sec.
+	2 	2.4 Sec.  (default)
+	3 	3.4 Sec.
+	4 	5.0 Sec.
+	5 	6.8 Sec.
+	6 	10.2 Sec.
+	7 	16.4 Sec.
+
+peci_4domain
+	Four domain enable
+
+	0 	1 or 2 Domains for enabled processors (default)
+	1 	3 or 4 Domains for enabled processors
+
+peci_domain
+	Domain
+
+	0 	Processor contains a single domain (0) 	 (default)
+	1 	Processor contains two domains (0,1)
diff --git a/Documentation/hwmon/it87 b/Documentation/hwmon/it87
index f9ba96c0ac4..8d08bf0d38e 100644
--- a/Documentation/hwmon/it87
+++ b/Documentation/hwmon/it87
@@ -5,31 +5,23 @@ Supported chips:
   * IT8705F
     Prefix: 'it87'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8705F_V.0.4.1.pdf
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8712F
     Prefix: 'it8712'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8712F_V0.9.1.pdf
-               http://www.ite.com.tw/product_info/file/pc/Errata%20V0.1%20for%20IT8712F%20V0.9.1.pdf
-               http://www.ite.com.tw/product_info/file/pc/IT8712F_V0.9.3.pdf
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8716F/IT8726F
     Prefix: 'it8716'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8716F_V0.3.ZIP
-               http://www.ite.com.tw/product_info/file/pc/IT8726F_V0.3.pdf
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8718F
     Prefix: 'it8718'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8718F_V0.2.zip
-               http://www.ite.com.tw/product_info/file/pc/IT8718F_V0%203_(for%20C%20version).zip
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8720F
     Prefix: 'it8720'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Not yet publicly available.
+    Datasheet: Not publicly available
   * SiS950   [clone of IT8705F]
     Prefix: 'it87'
     Addresses scanned: from Super I/O config space (8 I/O ports)
@@ -136,6 +128,10 @@ registers are read whenever any data is read (unless it is less than 1.5
 seconds since the last update). This means that you can easily miss
 once-only alarms.
 
+Out-of-limit readings can also result in beeping, if the chip is properly
+wired and configured. Beeping can be enabled or disabled per sensor type
+(temperatures, voltages and fans.)
+
 The IT87xx only updates its values each 1.5 seconds; reading it more often
 will do no harm, but will return 'old' values.
 
@@ -150,11 +146,38 @@ Fan speed control
 -----------------
 
 The fan speed control features are limited to manual PWM mode. Automatic
-"Smart Guardian" mode control handling is not implemented. However
-if you want to go for "manual mode" just write 1 to pwmN_enable.
+"Smart Guardian" mode control handling is only implemented for older chips
+(see below.) However if you want to go for "manual mode" just write 1 to
+pwmN_enable.
 
 If you are only able to control the fan speed with very small PWM values,
 try lowering the PWM base frequency (pwm1_freq). Depending on the fan,
 it may give you a somewhat greater control range. The same frequency is
 used to drive all fan outputs, which is why pwm2_freq and pwm3_freq are
 read-only.
+
+
+Automatic fan speed control (old interface)
+-------------------------------------------
+
+The driver supports the old interface to automatic fan speed control
+which is implemented by IT8705F chips up to revision F and IT8712F
+chips up to revision G.
+
+This interface implements 4 temperature vs. PWM output trip points.
+The PWM output of trip point 4 is always the maximum value (fan running
+at full speed) while the PWM output of the other 3 trip points can be
+freely chosen. The temperature of all 4 trip points can be freely chosen.
+Additionally, trip point 1 has an hysteresis temperature attached, to
+prevent fast switching between fan on and off.
+
+The chip automatically computes the PWM output value based on the input
+temperature, based on this simple rule: if the temperature value is
+between trip point N and trip point N+1 then the PWM output value is
+the one of trip point N. The automatic control mode is less flexible
+than the manual control mode, but it reacts faster, is more robust and
+doesn't use CPU cycles.
+
+Trip points must be set properly before switching to automatic fan speed
+control mode. The driver will perform basic integrity checks before
+actually switching to automatic control mode.
diff --git a/Documentation/hwmon/lm90 b/Documentation/hwmon/lm90
index 93d8e3d5515..6a03dd4bcc9 100644
--- a/Documentation/hwmon/lm90
+++ b/Documentation/hwmon/lm90
@@ -84,6 +84,10 @@ Supported chips:
     Addresses scanned: I2C 0x4c
     Datasheet: Publicly available at the Maxim website
                http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3500
+  * Winbond/Nuvoton W83L771AWG/ASG
+    Prefix: 'w83l771'
+    Addresses scanned: I2C 0x4c
+    Datasheet: Not publicly available, can be requested from Nuvoton
 
 
 Author: Jean Delvare <khali@linux-fr.org>
@@ -147,6 +151,12 @@ MAX6680 and MAX6681:
   * Selectable address
   * Remote sensor type selection
 
+W83L771AWG/ASG
+  * The AWG and ASG variants only differ in package format.
+  * Filter and alert configuration register at 0xBF
+  * Diode ideality factor configuration (remote sensor) at 0xE3
+  * Moving average (depending on conversion rate)
+
 All temperature values are given in degrees Celsius. Resolution
 is 1.0 degree for the local temperature, 0.125 degree for the remote
 temperature, except for the MAX6657, MAX6658 and MAX6659 which have a
@@ -163,6 +173,18 @@ The lm90 driver will not update its values more frequently than every
 other second; reading them more often will do no harm, but will return
 'old' values.
 
+SMBus Alert Support
+-------------------
+
+This driver has basic support for SMBus alert. When an alert is received,
+the status register is read and the faulty temperature channel is logged.
+
+The Analog Devices chips (ADM1032 and ADT7461) do not implement the SMBus
+alert protocol properly so additional care is needed: the ALERT output is
+disabled when an alert is received, and is re-enabled only when the alarm
+is gone. Otherwise the chip would block alerts from other chips in the bus
+as long as the alarm is active.
+
 PEC Support
 -----------
 
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index 81c0c59a60e..e1bb5b26169 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -15,7 +15,8 @@ Supported adapters:
   * Intel 82801I (ICH9)
   * Intel EP80579 (Tolapai)
   * Intel 82801JI (ICH10)
-  * Intel PCH
+  * Intel 3400/5 Series (PCH)
+  * Intel Cougar Point (PCH)
    Datasheets: Publicly available at the Intel website
 
 Authors: 
diff --git a/Documentation/i2c/busses/i2c-parport b/Documentation/i2c/busses/i2c-parport
index dceaba1ad93..2461c7b53b2 100644
--- a/Documentation/i2c/busses/i2c-parport
+++ b/Documentation/i2c/busses/i2c-parport
@@ -29,6 +29,9 @@ can be easily added when needed.
 Earlier kernels defaulted to type=0 (Philips).  But now, if the type
 parameter is missing, the driver will simply fail to initialize.
 
+SMBus alert support is available on adapters which have this line properly
+connected to the parallel port's interrupt pin.
+
 
 Building your own adapter
 -------------------------
diff --git a/Documentation/i2c/busses/i2c-parport-light b/Documentation/i2c/busses/i2c-parport-light
index 28743647852..bdc9cbb2e0f 100644
--- a/Documentation/i2c/busses/i2c-parport-light
+++ b/Documentation/i2c/busses/i2c-parport-light
@@ -9,3 +9,14 @@ parport handling is not an option. The drawback is a reduced portability
 and the impossibility to daisy-chain other parallel port devices.                 
   
 Please see i2c-parport for documentation.
+
+Module parameters:
+
+* type: type of adapter (see i2c-parport or modinfo)
+
+* base: base I/O address
+  Default is 0x378 which is fairly common for parallel ports, at least on PC.
+
+* irq: optional IRQ
+  This must be passed if you want SMBus alert support, assuming your adapter
+  actually supports this.
diff --git a/Documentation/i2c/smbus-protocol b/Documentation/i2c/smbus-protocol
index 9df47441f0e..7c19d1a2bea 100644
--- a/Documentation/i2c/smbus-protocol
+++ b/Documentation/i2c/smbus-protocol
@@ -185,6 +185,22 @@ the protocol. All ARP communications use slave address 0x61 and
 require PEC checksums.
 
 
+SMBus Alert
+===========
+
+SMBus Alert was introduced in Revision 1.0 of the specification.
+
+The SMBus alert protocol allows several SMBus slave devices to share a
+single interrupt pin on the SMBus master, while still allowing the master
+to know which slave triggered the interrupt.
+
+This is implemented the following way in the Linux kernel:
+* I2C bus drivers which support SMBus alert should call
+  i2c_setup_smbus_alert() to setup SMBus alert support.
+* I2C drivers for devices which can trigger SMBus alerts should implement
+  the optional alert() callback.
+
+
 I2C Block Transactions
 ======================
 
diff --git a/Documentation/i2c/writing-clients b/Documentation/i2c/writing-clients
index 0a74603eb67..3219ee0dbfe 100644
--- a/Documentation/i2c/writing-clients
+++ b/Documentation/i2c/writing-clients
@@ -318,8 +318,9 @@ Plain I2C communication
 These routines read and write some bytes from/to a client. The client
 contains the i2c address, so you do not have to include it. The second
 parameter contains the bytes to read/write, the third the number of bytes
-to read/write (must be less than the length of the buffer.) Returned is
-the actual number of bytes read/written.
+to read/write (must be less than the length of the buffer, also should be
+less than 64k since msg.len is u16.) Returned is the actual number of bytes
+read/written.
 
 	int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msg,
 			 int num);
diff --git a/Documentation/init.txt b/Documentation/init.txt
new file mode 100644
index 00000000000..535ad5e82b9
--- /dev/null
+++ b/Documentation/init.txt
@@ -0,0 +1,49 @@
+Explaining the dreaded "No init found." boot hang message
+=========================================================
+
+OK, so you've got this pretty unintuitive message (currently located
+in init/main.c) and are wondering what the H*** went wrong.
+Some high-level reasons for failure (listed roughly in order of execution)
+to load the init binary are:
+A) Unable to mount root FS
+B) init binary doesn't exist on rootfs
+C) broken console device
+D) binary exists but dependencies not available
+E) binary cannot be loaded
+
+Detailed explanations:
+0) Set "debug" kernel parameter (in bootloader config file or CONFIG_CMDLINE)
+   to get more detailed kernel messages.
+A) make sure you have the correct root FS type
+   (and root= kernel parameter points to the correct partition),
+   required drivers such as storage hardware (such as SCSI or USB!)
+   and filesystem (ext3, jffs2 etc.) are builtin (alternatively as modules,
+   to be pre-loaded by an initrd)
+C) Possibly a conflict in console= setup --> initial console unavailable.
+   E.g. some serial consoles are unreliable due to serial IRQ issues (e.g.
+   missing interrupt-based configuration).
+   Try using a different console= device or e.g. netconsole= .
+D) e.g. required library dependencies of the init binary such as
+   /lib/ld-linux.so.2 missing or broken. Use readelf -d <INIT>|grep NEEDED
+   to find out which libraries are required.
+E) make sure the binary's architecture matches your hardware.
+   E.g. i386 vs. x86_64 mismatch, or trying to load x86 on ARM hardware.
+   In case you tried loading a non-binary file here (shell script?),
+   you should make sure that the script specifies an interpreter in its shebang
+   header line (#!/...) that is fully working (including its library
+   dependencies). And before tackling scripts, better first test a simple
+   non-script binary such as /bin/sh and confirm its successful execution.
+   To find out more, add code to init/main.c to display kernel_execve()s
+   return values.
+
+Please extend this explanation whenever you find new failure causes
+(after all loading the init binary is a CRITICAL and hard transition step
+which needs to be made as painless as possible), then submit patch to LKML.
+Further TODOs:
+- Implement the various run_init_process() invocations via a struct array
+  which can then store the kernel_execve() result value and on failure
+  log it all by iterating over _all_ results (very important usability fix).
+- try to make the implementation itself more helpful in general,
+  e.g. by providing additional error messages at affected places.
+
+Andreas Mohr <andi at lisas period de>
diff --git a/Documentation/input/sentelic.txt b/Documentation/input/sentelic.txt
index f7160a2fb6a..b35affd5c64 100644
--- a/Documentation/input/sentelic.txt
+++ b/Documentation/input/sentelic.txt
@@ -1,5 +1,5 @@
-Copyright (C) 2002-2008 Sentelic Corporation.
-Last update: Oct-31-2008
+Copyright (C) 2002-2010 Sentelic Corporation.
+Last update: Jan-13-2010
 
 ==============================================================================
 * Finger Sensing Pad Intellimouse Mode(scrolling wheel, 4th and 5th buttons)
@@ -44,7 +44,7 @@ B) MSID 6: Horizontal and Vertical scrolling.
 Packet 1
    Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
 BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
-  1   |Y|X|y|x|1|M|R|L|  2  |X|X|X|X|X|X|X|X|  3 |Y|Y|Y|Y|Y|Y|Y|Y|  4 | | |B|F|l|r|u|d|
+  1   |Y|X|y|x|1|M|R|L|  2  |X|X|X|X|X|X|X|X|  3 |Y|Y|Y|Y|Y|Y|Y|Y|  4 | | |B|F|r|l|u|d|
       |---------------|     |---------------|    |---------------|    |---------------|
 
 Byte 1: Bit7 => Y overflow
@@ -59,15 +59,15 @@ Byte 2: X Movement(9-bit 2's complement integers)
 Byte 3: Y Movement(9-bit 2's complement integers)
 Byte 4: Bit0 => the Vertical scrolling movement downward.
 	Bit1 => the Vertical scrolling movement upward.
-	Bit2 => the Vertical scrolling movement rightward.
-	Bit3 => the Vertical scrolling movement leftward.
+	Bit2 => the Horizontal scrolling movement leftward.
+	Bit3 => the Horizontal scrolling movement rightward.
         Bit4 => 1 = 4th mouse button is pressed, Forward one page.
                 0 = 4th mouse button is not pressed.
         Bit5 => 1 = 5th mouse button is pressed, Backward one page.
                 0 = 5th mouse button is not pressed.
 
 C) MSID 7:
-# FSP uses 2 packets(8 Bytes) data to represent Absolute Position
+# FSP uses 2 packets (8 Bytes) to represent Absolute Position.
   so we have PACKET NUMBER to identify packets.
   If PACKET NUMBER is 0, the packet is Packet 1.
   If PACKET NUMBER is 1, the packet is Packet 2.
@@ -129,7 +129,7 @@ Byte 3: Message Type => 0x00 (Disabled)
 Byte 4: Bit7~Bit0 => Don't Care
 
 ==============================================================================
-* Absolute position for STL3888-A0.
+* Absolute position for STL3888-Ax.
 ==============================================================================
 Packet 1 (ABSOLUTE POSITION)
    Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
@@ -179,14 +179,14 @@ Byte 4: Bit1~Bit0 => Y coordinate (xpos[1:0])
         Bit5~Bit4 => y2_g
         Bit7~Bit6 => x2_g
 
-Notify Packet for STL3888-A0
+Notify Packet for STL3888-Ax
    Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
 BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
   1   |1|0|1|P|1|M|R|L|  2  |C|C|C|C|C|C|C|C|  3 |0|0|F|F|0|0|0|i|  4 |r|l|d|u|0|0|0|0|
       |---------------|     |---------------|    |---------------|    |---------------|
 
 Byte 1: Bit7~Bit6 => 00, Normal data packet
-                  => 01, Absolute coordination packet
+                  => 01, Absolute coordinates packet
                   => 10, Notify packet
         Bit5 => 1
         Bit4 => when in absolute coordinates mode (valid when EN_PKT_GO is 1):
@@ -205,15 +205,106 @@ Byte 4: Bit7 => scroll right button
         Bit6 => scroll left button
         Bit5 => scroll down button
         Bit4 => scroll up button
-            * Note that if gesture and additional button (Bit4~Bit7)
-	      happen at the same time, the button information will not
-	      be sent.
+            * Note that if gesture and additional buttoni (Bit4~Bit7)
+              happen at the same time, the button information will not
+              be sent.
+        Bit3~Bit0 => Reserved
+
+Sample sequence of Multi-finger, Multi-coordinate mode:
+
+	notify packet (valid bit == 1), abs pkt 1, abs pkt 2, abs pkt 1,
+	abs pkt 2, ..., notify packet (valid bit == 0)
+
+==============================================================================
+* Absolute position for STL3888-B0.
+==============================================================================
+Packet 1(ABSOLUTE POSITION)
+   Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
+BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
+  1   |0|1|V|F|1|0|R|L|  2  |X|X|X|X|X|X|X|X|  3 |Y|Y|Y|Y|Y|Y|Y|Y|  4 |r|l|u|d|X|X|Y|Y|
+      |---------------|     |---------------|    |---------------|    |---------------|
+
+Byte 1: Bit7~Bit6 => 00, Normal data packet
+                  => 01, Absolute coordinates packet
+                  => 10, Notify packet
+        Bit5 => Valid bit, 0 means that the coordinate is invalid or finger up.
+                When both fingers are up, the last two reports have zero valid
+                bit.
+        Bit4 => finger up/down information. 1: finger down, 0: finger up.
+        Bit3 => 1
+        Bit2 => finger index, 0 is the first finger, 1 is the second finger.
+        Bit1 => Right Button, 1 is pressed, 0 is not pressed.
+        Bit0 => Left Button, 1 is pressed, 0 is not pressed.
+Byte 2: X coordinate (xpos[9:2])
+Byte 3: Y coordinate (ypos[9:2])
+Byte 4: Bit1~Bit0 => Y coordinate (xpos[1:0])
+        Bit3~Bit2 => X coordinate (ypos[1:0])
+        Bit4 => scroll down button
+        Bit5 => scroll up button
+        Bit6 => scroll left button
+        Bit7 => scroll right button
+
+Packet 2 (ABSOLUTE POSITION)
+   Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
+BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
+  1   |0|1|V|F|1|1|R|L|  2  |X|X|X|X|X|X|X|X|  3 |Y|Y|Y|Y|Y|Y|Y|Y|  4 |r|l|u|d|X|X|Y|Y|
+      |---------------|     |---------------|    |---------------|    |---------------|
+
+Byte 1: Bit7~Bit6 => 00, Normal data packet
+                  => 01, Absolute coordination packet
+                  => 10, Notify packet
+        Bit5 => Valid bit, 0 means that the coordinate is invalid or finger up.
+                When both fingers are up, the last two reports have zero valid
+                bit.
+        Bit4 => finger up/down information. 1: finger down, 0: finger up.
+        Bit3 => 1
+        Bit2 => finger index, 0 is the first finger, 1 is the second finger.
+        Bit1 => Right Button, 1 is pressed, 0 is not pressed.
+        Bit0 => Left Button, 1 is pressed, 0 is not pressed.
+Byte 2: X coordinate (xpos[9:2])
+Byte 3: Y coordinate (ypos[9:2])
+Byte 4: Bit1~Bit0 => Y coordinate (xpos[1:0])
+        Bit3~Bit2 => X coordinate (ypos[1:0])
+        Bit4 => scroll down button
+        Bit5 => scroll up button
+        Bit6 => scroll left button
+        Bit7 => scroll right button
+
+Notify Packet for STL3888-B0
+   Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
+BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
+  1   |1|0|1|P|1|M|R|L|  2  |C|C|C|C|C|C|C|C|  3 |0|0|F|F|0|0|0|i|  4 |r|l|u|d|0|0|0|0|
+      |---------------|     |---------------|    |---------------|    |---------------|
+
+Byte 1: Bit7~Bit6 => 00, Normal data packet
+                  => 01, Absolute coordination packet
+                  => 10, Notify packet
+        Bit5 => 1
+        Bit4 => when in absolute coordinate mode (valid when EN_PKT_GO is 1):
+                0: left button is generated by the on-pad command
+                1: left button is generated by the external button
+        Bit3 => 1
+        Bit2 => Middle Button, 1 is pressed, 0 is not pressed.
+        Bit1 => Right Button, 1 is pressed, 0 is not pressed.
+        Bit0 => Left Button, 1 is pressed, 0 is not pressed.
+Byte 2: Message Type => 0xB7 (Multi Finger, Multi Coordinate mode)
+Byte 3: Bit7~Bit6 => Don't care
+        Bit5~Bit4 => Number of fingers
+        Bit3~Bit1 => Reserved
+        Bit0 => 1: enter gesture mode; 0: leaving gesture mode
+Byte 4: Bit7 => scroll right button
+        Bit6 => scroll left button
+        Bit5 => scroll up button
+        Bit4 => scroll down button
+            * Note that if gesture and additional button(Bit4~Bit7)
+              happen at the same time, the button information will not
+              be sent.
         Bit3~Bit0 => Reserved
 
 Sample sequence of Multi-finger, Multi-coordinate mode:
 
 	notify packet (valid bit == 1), abs pkt 1, abs pkt 2, abs pkt 1,
-	abs pkt 2, ..., notify packet(valid bit == 0)
+	abs pkt 2, ..., notify packet (valid bit == 0)
 
 ==============================================================================
 * FSP Enable/Disable packet
@@ -409,7 +500,8 @@ offset	width		default	r/w	name
 					0: read only, 1: read/write enable
 	(Note that following registers does not require clock gating being
 	enabled prior to write: 05 06 07 08 09 0c 0f 10 11 12 16 17 18 23 2e
-	40 41 42 43.)
+	40 41 42 43.  In addition to that, this bit must be 1 when gesture
+	mode is enabled)
 
 0x31				RW	on-pad command detection
 	bit7		0	RW	on-pad command left button down tag
@@ -463,6 +555,10 @@ offset	width		default	r/w	name
 	absolute coordinates; otherwise, host only receives packets with
 	relative coordinate.)
 
+	bit7		0	RW	EN_PS2_F2: PS/2 gesture mode 2nd
+					finger packet enable
+					0: disable, 1: enable
+
 0x43				RW	on-pad control
 	bit0		0	RW	on-pad control enable
 					0: disable, 1: enable
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 35cf64d4436..35c9b51d20e 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -139,7 +139,6 @@ Code  Seq#(hex)	Include File		Comments
 'K'	all	linux/kd.h
 'L'	00-1F	linux/loop.h		conflict!
 'L'	10-1F	drivers/scsi/mpt2sas/mpt2sas_ctl.h	conflict!
-'L'	20-2F	linux/usb/vstusb.h
 'L'	E0-FF	linux/ppdd.h		encrypted disk device driver
 					<http://linux01.gwdg.de/~alatham/ppdd.html>
 'M'	all	linux/soundcard.h	conflict!
diff --git a/Documentation/isdn/INTERFACE.CAPI b/Documentation/isdn/INTERFACE.CAPI
index 5fe8de5cc72..f172091fb7c 100644
--- a/Documentation/isdn/INTERFACE.CAPI
+++ b/Documentation/isdn/INTERFACE.CAPI
@@ -149,10 +149,11 @@ char *(*procinfo)(struct capi_ctr *ctrlr)
 	pointer to a callback function returning the entry for the device in
 	the CAPI controller info table, /proc/capi/controller
 
-read_proc_t *ctr_read_proc
-	pointer to the read_proc callback function for the device's proc file
-	system entry, /proc/capi/controllers/<n>; will be called with a
-	pointer to the device's capi_ctr structure as the last (data) argument
+const struct file_operations *proc_fops
+	pointers to callback functions for the device's proc file
+	system entry, /proc/capi/controllers/<n>; pointer to the device's
+	capi_ctr structure is available from struct proc_dir_entry::data
+	which is available from struct inode.
 
 Note: Callback functions except send_message() are never called in interrupt
 context.
diff --git a/Documentation/isdn/README.gigaset b/Documentation/isdn/README.gigaset
index 794941fc949..e472df84232 100644
--- a/Documentation/isdn/README.gigaset
+++ b/Documentation/isdn/README.gigaset
@@ -292,10 +292,10 @@ GigaSet 307x Device Driver
         to /etc/modprobe.d/gigaset, /etc/modprobe.conf.local or a similar file.
 
      Problem:
-        Your isdn script aborts with a message about isdnlog.
+        The isdnlog program emits error messages or just doesn't work.
      Solution:
-        Try deactivating (or commenting out) isdnlog. This driver does not
-        support it.
+        Isdnlog supports only the HiSax driver. Do not attempt to use it with
+	other drivers such as Gigaset.
 
      Problem:
         You have two or more DECT data adapters (M101/M105) and only the
@@ -321,8 +321,8 @@ GigaSet 307x Device Driver
      writing an appropriate value to /sys/module/gigaset/parameters/debug, e.g.
         echo 0 > /sys/module/gigaset/parameters/debug
      switches off debugging output completely,
-        echo 0x10a020 > /sys/module/gigaset/parameters/debug
-     enables the standard set of debugging output messages. These values are
+        echo 0x302020 > /sys/module/gigaset/parameters/debug
+     enables a reasonable set of debugging output messages. These values are
      bit patterns where every bit controls a certain type of debugging output.
      See the constants DEBUG_* in the source file gigaset.h for details.
 
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e7848a0d99e..3bc48b0bd3a 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -54,6 +54,7 @@ parameter is applicable:
 	IMA     Integrity measurement architecture is enabled.
 	IOSCHED	More than one I/O scheduler is enabled.
 	IP_PNP	IP DHCP, BOOTP, or RARP is enabled.
+	IPV6	IPv6 support is enabled.
 	ISAPNP	ISA PnP code is enabled.
 	ISDN	Appropriate ISDN support is enabled.
 	JOY	Appropriate joystick support is enabled.
@@ -356,6 +357,9 @@ and is between 256 and 4096 characters. It is defined in the file
 			Change the amount of debugging information output
 			when initialising the APIC and IO-APIC components.
 
+	autoconf=	[IPV6]
+			See Documentation/networking/ipv6.txt.
+
 	show_lapic=	[APIC,X86] Advanced Programmable Interrupt Controller
 			Limit apic dumping. The parameter defines the maximal
 			number of local apics being dumped. Also it is possible
@@ -638,6 +642,12 @@ and is between 256 and 4096 characters. It is defined in the file
 			See drivers/char/README.epca and
 			Documentation/serial/digiepca.txt.
 
+	disable=	[IPV6]
+			See Documentation/networking/ipv6.txt.
+
+	disable_ipv6=	[IPV6]
+			See Documentation/networking/ipv6.txt.
+
 	disable_mtrr_cleanup [X86]
 			The kernel tries to adjust MTRR layout from continuous
 			to discrete, to make X server driver able to add WB
@@ -1738,6 +1748,9 @@ and is between 256 and 4096 characters. It is defined in the file
 	nomfgpt		[X86-32] Disable Multi-Function General Purpose
 			Timer usage (for AMD Geode machines).
 
+	nopat		[X86] Disable PAT (page attribute table extension of
+			pagetables) support.
+
 	norandmaps	Don't use address space randomization.  Equivalent to
 			echo 0 > /proc/sys/kernel/randomize_va_space
 
@@ -1781,6 +1794,12 @@ and is between 256 and 4096 characters. It is defined in the file
 			purges which is reported from either PAL_VM_SUMMARY or
 			SAL PALO.
 
+	nr_cpus=	[SMP] Maximum number of processors that	an SMP kernel
+			could support.  nr_cpus=n : n >= 1 limits the kernel to
+			supporting 'n' processors. Later in runtime you can not
+			use hotplug cpu feature to put more cpu back to online.
+			just like you compile the kernel NR_CPUS=n
+
 	nr_uarts=	[SERIAL] maximum number of UARTs to be registered.
 
 	numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA.
@@ -1948,8 +1967,12 @@ and is between 256 and 4096 characters. It is defined in the file
 				IRQ routing is enabled.
 		noacpi		[X86] Do not use ACPI for IRQ routing
 				or for PCI scanning.
-		use_crs		[X86] Use _CRS for PCI resource
-				allocation.
+		use_crs		[X86] Use PCI host bridge window information
+				from ACPI.  On BIOSes from 2008 or later, this
+				is enabled by default.  If you need to use this,
+				please report a bug.
+		nocrs		[X86] Ignore PCI host bridge windows from ACPI.
+			        If you need to use this, please report a bug.
 		routeirq	Do IRQ routing for all PCI devices.
 				This is normally done in pci_enable_device(),
 				so this option is a temporary workaround
@@ -1998,6 +2021,14 @@ and is between 256 and 4096 characters. It is defined in the file
 		force	Enable ASPM even on devices that claim not to support it.
 			WARNING: Forcing ASPM on may cause system lockups.
 
+	pcie_pme=	[PCIE,PM] Native PCIe PME signaling options:
+		off	Do not use native PCIe PME signaling.
+		force	Use native PCIe PME signaling even if the BIOS refuses
+			to allow the kernel to control the relevant PCIe config
+			registers.
+		nomsi	Do not use MSI for native PCIe PME signaling (this makes
+			all PCIe root ports use INTx for everything).
+
 	pcmv=		[HW,PCMCIA] BadgePAD 4
 
 	pd.		[PARIDE]
@@ -2703,6 +2734,13 @@ and is between 256 and 4096 characters. It is defined in the file
 					medium is write-protected).
 			Example: quirks=0419:aaf5:rl,0421:0433:rc
 
+	userpte=
+			[X86] Flags controlling user PTE allocations.
+
+				nohigh = do not allocate PTE pages in
+					HIGHMEM regardless of setting
+					of CONFIG_HIGHPTE.
+
 	vdso=		[X86,SH]
 			vdso=2: enable compat VDSO (default with COMPAT_VDSO)
 			vdso=1: enable VDSO (default)
@@ -2796,6 +2834,12 @@ and is between 256 and 4096 characters. It is defined in the file
 			default x2apic cluster mode on platforms
 			supporting x2apic.
 
+	x86_mrst_timer= [X86-32,APBT]
+			Choose timer option for x86 Moorestown MID platform.
+			Two valid options are apbt timer only and lapic timer
+			plus one apbt timer for broadcast timer.
+			x86_mrst_timer=apbt_only | lapic_and_apbt
+
 	xd=		[HW,XT] Original XT pre-IDE (RLL encoded) disks.
 	xd_geo=		See header of drivers/block/xd.c.
 
diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt
index c79ab996dad..bdb13817e1e 100644
--- a/Documentation/kobject.txt
+++ b/Documentation/kobject.txt
@@ -266,7 +266,7 @@ kobj_type:
 
     struct kobj_type {
 	    void (*release)(struct kobject *);
-	    struct sysfs_ops	*sysfs_ops;
+	    const struct sysfs_ops *sysfs_ops;
 	    struct attribute	**default_attrs;
     };
 
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 053037a1fe6..2f9115c0ae6 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -1,6 +1,7 @@
 Title	: Kernel Probes (Kprobes)
 Authors	: Jim Keniston <jkenisto@us.ibm.com>
-	: Prasanna S Panchamukhi <prasanna@in.ibm.com>
+	: Prasanna S Panchamukhi <prasanna.panchamukhi@gmail.com>
+	: Masami Hiramatsu <mhiramat@redhat.com>
 
 CONTENTS
 
@@ -15,6 +16,7 @@ CONTENTS
 9. Jprobes Example
 10. Kretprobes Example
 Appendix A: The kprobes debugfs interface
+Appendix B: The kprobes sysctl interface
 
 1. Concepts: Kprobes, Jprobes, Return Probes
 
@@ -42,13 +44,13 @@ registration/unregistration of a group of *probes. These functions
 can speed up unregistration process when you have to unregister
 a lot of probes at once.
 
-The next three subsections explain how the different types of
-probes work.  They explain certain things that you'll need to
-know in order to make the best use of Kprobes -- e.g., the
-difference between a pre_handler and a post_handler, and how
-to use the maxactive and nmissed fields of a kretprobe.  But
-if you're in a hurry to start using Kprobes, you can skip ahead
-to section 2.
+The next four subsections explain how the different types of
+probes work and how jump optimization works.  They explain certain
+things that you'll need to know in order to make the best use of
+Kprobes -- e.g., the difference between a pre_handler and
+a post_handler, and how to use the maxactive and nmissed fields of
+a kretprobe.  But if you're in a hurry to start using Kprobes, you
+can skip ahead to section 2.
 
 1.1 How Does a Kprobe Work?
 
@@ -161,13 +163,125 @@ In case probed function is entered but there is no kretprobe_instance
 object available, then in addition to incrementing the nmissed count,
 the user entry_handler invocation is also skipped.
 
+1.4 How Does Jump Optimization Work?
+
+If you configured your kernel with CONFIG_OPTPROBES=y (currently
+this option is supported on x86/x86-64, non-preemptive kernel) and
+the "debug.kprobes_optimization" kernel parameter is set to 1 (see
+sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump
+instruction instead of a breakpoint instruction at each probepoint.
+
+1.4.1 Init a Kprobe
+
+When a probe is registered, before attempting this optimization,
+Kprobes inserts an ordinary, breakpoint-based kprobe at the specified
+address. So, even if it's not possible to optimize this particular
+probepoint, there'll be a probe there.
+
+1.4.2 Safety Check
+
+Before optimizing a probe, Kprobes performs the following safety checks:
+
+- Kprobes verifies that the region that will be replaced by the jump
+instruction (the "optimized region") lies entirely within one function.
+(A jump instruction is multiple bytes, and so may overlay multiple
+instructions.)
+
+- Kprobes analyzes the entire function and verifies that there is no
+jump into the optimized region.  Specifically:
+  - the function contains no indirect jump;
+  - the function contains no instruction that causes an exception (since
+  the fixup code triggered by the exception could jump back into the
+  optimized region -- Kprobes checks the exception tables to verify this);
+  and
+  - there is no near jump to the optimized region (other than to the first
+  byte).
+
+- For each instruction in the optimized region, Kprobes verifies that
+the instruction can be executed out of line.
+
+1.4.3 Preparing Detour Buffer
+
+Next, Kprobes prepares a "detour" buffer, which contains the following
+instruction sequence:
+- code to push the CPU's registers (emulating a breakpoint trap)
+- a call to the trampoline code which calls user's probe handlers.
+- code to restore registers
+- the instructions from the optimized region
+- a jump back to the original execution path.
+
+1.4.4 Pre-optimization
+
+After preparing the detour buffer, Kprobes verifies that none of the
+following situations exist:
+- The probe has either a break_handler (i.e., it's a jprobe) or a
+post_handler.
+- Other instructions in the optimized region are probed.
+- The probe is disabled.
+In any of the above cases, Kprobes won't start optimizing the probe.
+Since these are temporary situations, Kprobes tries to start
+optimizing it again if the situation is changed.
+
+If the kprobe can be optimized, Kprobes enqueues the kprobe to an
+optimizing list, and kicks the kprobe-optimizer workqueue to optimize
+it.  If the to-be-optimized probepoint is hit before being optimized,
+Kprobes returns control to the original instruction path by setting
+the CPU's instruction pointer to the copied code in the detour buffer
+-- thus at least avoiding the single-step.
+
+1.4.5 Optimization
+
+The Kprobe-optimizer doesn't insert the jump instruction immediately;
+rather, it calls synchronize_sched() for safety first, because it's
+possible for a CPU to be interrupted in the middle of executing the
+optimized region(*).  As you know, synchronize_sched() can ensure
+that all interruptions that were active when synchronize_sched()
+was called are done, but only if CONFIG_PREEMPT=n.  So, this version
+of kprobe optimization supports only kernels with CONFIG_PREEMPT=n.(**)
+
+After that, the Kprobe-optimizer calls stop_machine() to replace
+the optimized region with a jump instruction to the detour buffer,
+using text_poke_smp().
+
+1.4.6 Unoptimization
+
+When an optimized kprobe is unregistered, disabled, or blocked by
+another kprobe, it will be unoptimized.  If this happens before
+the optimization is complete, the kprobe is just dequeued from the
+optimized list.  If the optimization has been done, the jump is
+replaced with the original code (except for an int3 breakpoint in
+the first byte) by using text_poke_smp().
+
+(*)Please imagine that the 2nd instruction is interrupted and then
+the optimizer replaces the 2nd instruction with the jump *address*
+while the interrupt handler is running. When the interrupt
+returns to original address, there is no valid instruction,
+and it causes an unexpected result.
+
+(**)This optimization-safety checking may be replaced with the
+stop-machine method that ksplice uses for supporting a CONFIG_PREEMPT=y
+kernel.
+
+NOTE for geeks:
+The jump optimization changes the kprobe's pre_handler behavior.
+Without optimization, the pre_handler can change the kernel's execution
+path by changing regs->ip and returning 1.  However, when the probe
+is optimized, that modification is ignored.  Thus, if you want to
+tweak the kernel's execution path, you need to suppress optimization,
+using one of the following techniques:
+- Specify an empty function for the kprobe's post_handler or break_handler.
+ or
+- Config CONFIG_OPTPROBES=n.
+ or
+- Execute 'sysctl -w debug.kprobes_optimization=n'
+
 2. Architectures Supported
 
 Kprobes, jprobes, and return probes are implemented on the following
 architectures:
 
-- i386
-- x86_64 (AMD-64, EM64T)
+- i386 (Supports jump optimization)
+- x86_64 (AMD-64, EM64T) (Supports jump optimization)
 - ppc64
 - ia64 (Does not support probes on instruction slot1.)
 - sparc64 (Return probes not yet implemented.)
@@ -193,6 +307,10 @@ it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO),
 so you can use "objdump -d -l vmlinux" to see the source-to-object
 code mapping.
 
+If you want to reduce probing overhead, set "Kprobes jump optimization
+support" (CONFIG_OPTPROBES) to "y". You can find this option under the
+"Kprobes" line.
+
 4. API Reference
 
 The Kprobes API includes a "register" function and an "unregister"
@@ -389,7 +507,10 @@ the probe which has been registered.
 
 Kprobes allows multiple probes at the same address.  Currently,
 however, there cannot be multiple jprobes on the same function at
-the same time.
+the same time.  Also, a probepoint for which there is a jprobe or
+a post_handler cannot be optimized.  So if you install a jprobe,
+or a kprobe with a post_handler, at an optimized probepoint, the
+probepoint will be unoptimized automatically.
 
 In general, you can install a probe anywhere in the kernel.
 In particular, you can probe interrupt handlers.  Known exceptions
@@ -453,6 +574,38 @@ reason, Kprobes doesn't support return probes (or kprobes or jprobes)
 on the x86_64 version of __switch_to(); the registration functions
 return -EINVAL.
 
+On x86/x86-64, since the Jump Optimization of Kprobes modifies
+instructions widely, there are some limitations to optimization. To
+explain it, we introduce some terminology. Imagine a 3-instruction
+sequence consisting of a two 2-byte instructions and one 3-byte
+instruction.
+
+        IA
+         |
+[-2][-1][0][1][2][3][4][5][6][7]
+        [ins1][ins2][  ins3 ]
+	[<-     DCR       ->]
+	   [<- JTPR ->]
+
+ins1: 1st Instruction
+ins2: 2nd Instruction
+ins3: 3rd Instruction
+IA:  Insertion Address
+JTPR: Jump Target Prohibition Region
+DCR: Detoured Code Region
+
+The instructions in DCR are copied to the out-of-line buffer
+of the kprobe, because the bytes in DCR are replaced by
+a 5-byte jump instruction. So there are several limitations.
+
+a) The instructions in DCR must be relocatable.
+b) The instructions in DCR must not include a call instruction.
+c) JTPR must not be targeted by any jump or call instruction.
+d) DCR must not straddle the border betweeen functions.
+
+Anyway, these limitations are checked by the in-kernel instruction
+decoder, so you don't need to worry about that.
+
 6. Probe Overhead
 
 On a typical CPU in use in 2005, a kprobe hit takes 0.5 to 1.0
@@ -476,6 +629,19 @@ k = 0.49 usec; j = 0.76; r = 0.80; kr = 0.82; jr = 1.07
 ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU)
 k = 0.77 usec; j = 1.31; r = 1.26; kr = 1.45; jr = 1.99
 
+6.1 Optimized Probe Overhead
+
+Typically, an optimized kprobe hit takes 0.07 to 0.1 microseconds to
+process. Here are sample overhead figures (in usec) for x86 architectures.
+k = unoptimized kprobe, b = boosted (single-step skipped), o = optimized kprobe,
+r = unoptimized kretprobe, rb = boosted kretprobe, ro = optimized kretprobe.
+
+i386: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
+k = 0.80 usec; b = 0.33; o = 0.05; r = 1.10; rb = 0.61; ro = 0.33
+
+x86-64: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
+k = 0.99 usec; b = 0.43; o = 0.06; r = 1.24; rb = 0.68; ro = 0.30
+
 7. TODO
 
 a. SystemTap (http://sourceware.org/systemtap): Provides a simplified
@@ -523,7 +689,8 @@ is also specified. Following columns show probe status. If the probe is on
 a virtual address that is no longer valid (module init sections, module
 virtual addresses that correspond to modules that've been unloaded),
 such probes are marked with [GONE]. If the probe is temporarily disabled,
-such probes are marked with [DISABLED].
+such probes are marked with [DISABLED]. If the probe is optimized, it is
+marked with [OPTIMIZED].
 
 /sys/kernel/debug/kprobes/enabled: Turn kprobes ON/OFF forcibly.
 
@@ -533,3 +700,19 @@ registered probes will be disarmed, till such time a "1" is echoed to this
 file. Note that this knob just disarms and arms all kprobes and doesn't
 change each probe's disabling state. This means that disabled kprobes (marked
 [DISABLED]) will be not enabled if you turn ON all kprobes by this knob.
+
+
+Appendix B: The kprobes sysctl interface
+
+/proc/sys/debug/kprobes-optimization: Turn kprobes optimization ON/OFF.
+
+When CONFIG_OPTPROBES=y, this sysctl interface appears and it provides
+a knob to globally and forcibly turn jump optimization (see section
+1.4) ON or OFF. By default, jump optimization is allowed (ON).
+If you echo "0" to this file or set "debug.kprobes_optimization" to
+0 via sysctl, all optimized probes will be unoptimized, and any new
+probes registered after that will not be optimized.  Note that this
+knob *changes* the optimized state. This means that optimized probes
+(marked [OPTIMIZED]) will be unoptimized ([OPTIMIZED] tag will be
+removed). If the knob is turned on, they will be optimized again.
+
diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index 2811e452f75..c6416a39816 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -23,12 +23,12 @@ of a virtual machine.  The ioctls belong to three classes
    Only run vcpu ioctls from the same thread that was used to create the
    vcpu.
 
-2. File descritpors
+2. File descriptors
 
 The kvm API is centered around file descriptors.  An initial
 open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
 can be used to issue system ioctls.  A KVM_CREATE_VM ioctl on this
-handle will create a VM file descripror which can be used to issue VM
+handle will create a VM file descriptor which can be used to issue VM
 ioctls.  A KVM_CREATE_VCPU ioctl on a VM fd will create a virtual cpu
 and return a file descriptor pointing to it.  Finally, ioctls on a vcpu
 fd can be used to control the vcpu, including the important task of
@@ -643,7 +643,7 @@ Type: vm ioctl
 Parameters: struct kvm_clock_data (in)
 Returns: 0 on success, -1 on error
 
-Sets the current timestamp of kvmclock to the valued specific in its parameter.
+Sets the current timestamp of kvmclock to the value specified in its parameter.
 In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
 such as migration.
 
@@ -795,11 +795,11 @@ Unused.
 			__u64 data_offset; /* relative to kvm_run start */
 		} io;
 
-If exit_reason is KVM_EXIT_IO_IN or KVM_EXIT_IO_OUT, then the vcpu has
+If exit_reason is KVM_EXIT_IO, then the vcpu has
 executed a port I/O instruction which could not be satisfied by kvm.
 data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
 where kvm expects application code to place the data for the next
-KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a patcked array.
+KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a packed array.
 
 		struct {
 			struct kvm_debug_exit_arch arch;
@@ -815,7 +815,7 @@ Unused.
 			__u8  is_write;
 		} mmio;
 
-If exit_reason is KVM_EXIT_MMIO or KVM_EXIT_IO_OUT, then the vcpu has
+If exit_reason is KVM_EXIT_MMIO, then the vcpu has
 executed a memory-mapped I/O instruction which could not be satisfied
 by kvm.  The 'data' member contains the written data if 'is_write' is
 true, and should be filled by application code otherwise.
diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt
index 75afa1229fd..39c0a09d010 100644
--- a/Documentation/laptops/thinkpad-acpi.txt
+++ b/Documentation/laptops/thinkpad-acpi.txt
@@ -650,6 +650,10 @@ LCD, CRT or DVI (if available). The following commands are available:
 	echo expand_toggle > /proc/acpi/ibm/video
 	echo video_switch > /proc/acpi/ibm/video
 
+NOTE: Access to this feature is restricted to processes owning the
+CAP_SYS_ADMIN capability for safety reasons, as it can interact badly
+enough with some versions of X.org to crash it.
+
 Each video output device can be enabled or disabled individually.
 Reading /proc/acpi/ibm/video shows the status of each device.
 
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 42208511b5c..3119f5db75b 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -34,7 +34,6 @@
 #include <sys/uio.h>
 #include <termios.h>
 #include <getopt.h>
-#include <zlib.h>
 #include <assert.h>
 #include <sched.h>
 #include <limits.h>
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index 50189bf07d5..fe5c099b8fc 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -32,6 +32,8 @@ cs89x0.txt
 	- the Crystal LAN (CS8900/20-based) Ethernet ISA adapter driver
 cxacru.txt
 	- Conexant AccessRunner USB ADSL Modem
+cxacru-cf.py
+	- Conexant AccessRunner USB ADSL Modem configuration file parser
 de4x5.txt
 	- the Digital EtherWORKS DE4?? and DE5?? PCI Ethernet driver
 decnet.txt
diff --git a/Documentation/networking/cxacru-cf.py b/Documentation/networking/cxacru-cf.py
new file mode 100644
index 00000000000..b41d298398c
--- /dev/null
+++ b/Documentation/networking/cxacru-cf.py
@@ -0,0 +1,48 @@
+#!/usr/bin/env python
+# Copyright 2009 Simon Arlott
+#
+# 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.
+#
+# Usage: cxacru-cf.py < cxacru-cf.bin
+# Output: values string suitable for the sysfs adsl_config attribute
+#
+# Warning: cxacru-cf.bin with MD5 hash cdbac2689969d5ed5d4850f117702110
+# contains mis-aligned values which will stop the modem from being able
+# to make a connection. If the first and last two bytes are removed then
+# the values become valid, but the modulation will be forced to ANSI
+# T1.413 only which may not be appropriate.
+#
+# The original binary format is a packed list of le32 values.
+
+import sys
+import struct
+
+i = 0
+while True:
+	buf = sys.stdin.read(4)
+
+	if len(buf) == 0:
+		break
+	elif len(buf) != 4:
+		sys.stdout.write("\n")
+		sys.stderr.write("Error: read {0} not 4 bytes\n".format(len(buf)))
+		sys.exit(1)
+
+	if i > 0:
+		sys.stdout.write(" ")
+	sys.stdout.write("{0:x}={1}".format(i, struct.unpack("<I", buf)[0]))
+	i += 1
+
+sys.stdout.write("\n")
diff --git a/Documentation/networking/cxacru.txt b/Documentation/networking/cxacru.txt
index b074681a963..2cce04457b4 100644
--- a/Documentation/networking/cxacru.txt
+++ b/Documentation/networking/cxacru.txt
@@ -4,6 +4,12 @@ While it is capable of managing/maintaining the ADSL connection without the
 module loaded, the device will sometimes stop responding after unloading the
 driver and it is necessary to unplug/remove power to the device to fix this.
 
+Note: support for cxacru-cf.bin has been removed. It was not loaded correctly
+so it had no effect on the device configuration. Fixing it could have stopped
+existing devices working when an invalid configuration is supplied.
+
+There is a script cxacru-cf.py to convert an existing file to the sysfs form.
+
 Detected devices will appear as ATM devices named "cxacru". In /sys/class/atm/
 these are directories named cxacruN where N is the device number. A symlink
 named device points to the USB interface device's directory which contains
@@ -15,6 +21,15 @@ several sysfs attribute files for retrieving device statistics:
 * adsl_headend_environment
 	Information about the remote headend.
 
+* adsl_config
+	Configuration writing interface.
+	Write parameters in hexadecimal format <index>=<value>,
+	separated by whitespace, e.g.:
+		"1=0 a=5"
+	Up to 7 parameters at a time will be sent and the modem will restart
+	the ADSL connection when any value is set. These are logged for future
+	reference.
+
 * downstream_attenuation (dB)
 * downstream_bits_per_frame
 * downstream_rate (kbps)
@@ -61,6 +76,7 @@ several sysfs attribute files for retrieving device statistics:
 * mac_address
 
 * modulation
+	"" (when not connected)
 	"ANSI T1.413"
 	"ITU-T G.992.1 (G.DMT)"
 	"ITU-T G.992.2 (G.LITE)"
diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt
index b132e4a3cf0..a62fdf7a6bf 100644
--- a/Documentation/networking/dccp.txt
+++ b/Documentation/networking/dccp.txt
@@ -58,8 +58,10 @@ DCCP_SOCKOPT_GET_CUR_MPS is read-only and retrieves the current maximum packet
 size (application payload size) in bytes, see RFC 4340, section 14.
 
 DCCP_SOCKOPT_AVAILABLE_CCIDS is also read-only and returns the list of CCIDs
-supported by the endpoint (see include/linux/dccp.h for symbolic constants).
-The caller needs to provide a sufficiently large (> 2) array of type uint8_t.
+supported by the endpoint. The option value is an array of type uint8_t whose
+size is passed as option length. The minimum array size is 4 elements, the
+value returned in the optlen argument always reflects the true number of
+built-in CCIDs.
 
 DCCP_SOCKOPT_CCID is write-only and sets both the TX and RX CCIDs at the same
 time, combining the operation of the next two socket options. This option is
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index e87f3cdc8a6..8b72c88ba21 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -487,6 +487,30 @@ tcp_dma_copybreak - INTEGER
 	and CONFIG_NET_DMA is enabled.
 	Default: 4096
 
+tcp_thin_linear_timeouts - BOOLEAN
+	Enable dynamic triggering of linear timeouts for thin streams.
+	If set, a check is performed upon retransmission by timeout to
+	determine if the stream is thin (less than 4 packets in flight).
+	As long as the stream is found to be thin, up to 6 linear
+	timeouts may be performed before exponential backoff mode is
+	initiated. This improves retransmission latency for
+	non-aggressive thin streams, often found to be time-dependent.
+	For more information on thin streams, see
+	Documentation/networking/tcp-thin.txt
+	Default: 0
+
+tcp_thin_dupack - BOOLEAN
+	Enable dynamic triggering of retransmissions after one dupACK
+	for thin streams. If set, a check is performed upon reception
+	of a dupACK to determine if the stream is thin (less than 4
+	packets in flight). As long as the stream is found to be thin,
+	data is retransmitted on the first received dupACK. This
+	improves retransmission latency for non-aggressive thin
+	streams, often found to be time-dependent.
+	For more information on thin streams, see
+	Documentation/networking/tcp-thin.txt
+	Default: 0
+
 UDP variables:
 
 udp_mem - vector of 3 INTEGERs: min, pressure, max
@@ -692,6 +716,25 @@ proxy_arp - BOOLEAN
 	conf/{all,interface}/proxy_arp is set to TRUE,
 	it will be disabled otherwise
 
+proxy_arp_pvlan - BOOLEAN
+	Private VLAN proxy arp.
+	Basically allow proxy arp replies back to the same interface
+	(from which the ARP request/solicitation was received).
+
+	This is done to support (ethernet) switch features, like RFC
+	3069, where the individual ports are NOT allowed to
+	communicate with each other, but they are allowed to talk to
+	the upstream router.  As described in RFC 3069, it is possible
+	to allow these hosts to communicate through the upstream
+	router by proxy_arp'ing. Don't need to be used together with
+	proxy_arp.
+
+	This technology is known by different names:
+	  In RFC 3069 it is called VLAN Aggregation.
+	  Cisco and Allied Telesyn call it Private VLAN.
+	  Hewlett-Packard call it Source-Port filtering or port-isolation.
+	  Ericsson call it MAC-Forced Forwarding (RFC Draft).
+
 shared_media - BOOLEAN
 	Send(router) or accept(host) RFC1620 shared media redirects.
 	Overrides ip_secure_redirects.
@@ -833,9 +876,18 @@ arp_notify - BOOLEAN
 	    or hardware address changes.
 
 arp_accept - BOOLEAN
-	Define behavior when gratuitous arp replies are received:
-	0 - drop gratuitous arp frames
-	1 - accept gratuitous arp frames
+	Define behavior for gratuitous ARP frames who's IP is not
+	already present in the ARP table:
+	0 - don't create new entries in the ARP table
+	1 - create new entries in the ARP table
+
+	Both replies and requests type gratuitous arp will trigger the
+	ARP table to be updated, if this setting is on.
+
+	If the ARP table already contains the IP address of the
+	gratuitous arp frame, the arp table will be updated regardless
+	if this setting is on or off.
+
 
 app_solicit - INTEGER
 	The maximum number of probes to send to the user space ARP daemon
diff --git a/Documentation/networking/ixgbevf.txt b/Documentation/networking/ixgbevf.txt
new file mode 100755
index 00000000000..19015de6725
--- /dev/null
+++ b/Documentation/networking/ixgbevf.txt
@@ -0,0 +1,90 @@
+Linux* Base Driver for Intel(R) Network Connection
+==================================================
+
+November 24, 2009
+
+Contents
+========
+
+- In This Release
+- Identifying Your Adapter
+- Known Issues/Troubleshooting
+- Support
+
+In This Release
+===============
+
+This file describes the ixgbevf Linux* Base Driver for Intel Network
+Connection.
+
+The ixgbevf driver supports 82599-based virtual function devices that can only
+be activated on kernels with CONFIG_PCI_IOV enabled.
+
+The ixgbevf driver supports virtual functions generated by the ixgbe driver
+with a max_vfs value of 1 or greater.
+
+The guest OS loading the ixgbevf driver must support MSI-X interrupts.
+
+VLANs: There is a limit of a total of 32 shared VLANs to 1 or more VFs.
+
+Identifying Your Adapter
+========================
+
+For more information on how to identify your adapter, go to the Adapter &
+Driver ID Guide at:
+
+    http://support.intel.com/support/network/sb/CS-008441.htm
+
+Known Issues/Troubleshooting
+============================
+
+  Unloading Physical Function (PF) Driver Causes System Reboots When VM is
+  Running and VF is Loaded on the VM
+  ------------------------------------------------------------------------
+  Do not unload the PF driver (ixgbe) while VFs are assigned to guests.
+
+Support
+=======
+
+For general information, go to the Intel support website at:
+
+    http://support.intel.com
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+    http://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on the supported
+kernel with a supported adapter, email the specific information related
+to the issue to e1000-devel@lists.sf.net
+
+License
+=======
+
+Intel 10 Gigabit Linux driver.
+Copyright(c) 1999 - 2009 Intel Corporation.
+
+This program is free software; you can redistribute it and/or modify it
+under the terms and conditions of the GNU General Public License,
+version 2, as published by the Free Software Foundation.
+
+This program is distributed in the hope 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 St - Fifth Floor, Boston, MA 02110-1301 USA.
+
+The full GNU General Public License is included in this distribution in
+the file called "COPYING".
+
+Trademarks
+==========
+
+Intel, Itanium, and Pentium are trademarks or registered trademarks of
+Intel Corporation or its subsidiaries in the United States and other
+countries.
+
+* Other names and brands may be claimed as the property of others.
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index a22fd85e379..09ab0d29032 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -2,7 +2,7 @@
 + ABSTRACT
 --------------------------------------------------------------------------------
 
-This file documents the CONFIG_PACKET_MMAP option available with the PACKET
+This file documents the mmap() facility available with the PACKET
 socket interface on 2.4 and 2.6 kernels. This type of sockets is used for 
 capture network traffic with utilities like tcpdump or any other that needs
 raw access to network interface.
@@ -44,7 +44,7 @@ enabled. For transmission, check the MTU (Maximum Transmission Unit) used and
 supported by devices of your network.
 
 --------------------------------------------------------------------------------
-+ How to use CONFIG_PACKET_MMAP to improve capture process
++ How to use mmap() to improve capture process
 --------------------------------------------------------------------------------
 
 From the user standpoint, you should use the higher level libpcap library, which
@@ -64,7 +64,7 @@ the low level details or want to improve libpcap by including PACKET_MMAP
 support.
 
 --------------------------------------------------------------------------------
-+ How to use CONFIG_PACKET_MMAP directly to improve capture process
++ How to use mmap() directly to improve capture process
 --------------------------------------------------------------------------------
 
 From the system calls stand point, the use of PACKET_MMAP involves
@@ -105,7 +105,7 @@ also the mapping of the circular buffer in the user process and
 the use of this buffer.
 
 --------------------------------------------------------------------------------
-+ How to use CONFIG_PACKET_MMAP directly to improve transmission process
++ How to use mmap() directly to improve transmission process
 --------------------------------------------------------------------------------
 Transmission process is similar to capture as shown below.
 
diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt
index ee31369e9e5..9551622d0a7 100644
--- a/Documentation/networking/regulatory.txt
+++ b/Documentation/networking/regulatory.txt
@@ -188,3 +188,27 @@ Then in some part of your code after your wiphy has been registered:
 		       &mydriver_jp_regdom.reg_rules[i],
 		       sizeof(struct ieee80211_reg_rule));
 	regulatory_struct_hint(rd);
+
+Statically compiled regulatory database
+---------------------------------------
+
+In most situations the userland solution using CRDA as described
+above is the preferred solution.  However in some cases a set of
+rules built into the kernel itself may be desirable.  To account
+for this situation, a configuration option has been provided
+(i.e. CONFIG_CFG80211_INTERNAL_REGDB).  With this option enabled,
+the wireless database information contained in net/wireless/db.txt is
+used to generate a data structure encoded in net/wireless/regdb.c.
+That option also enables code in net/wireless/reg.c which queries
+the data in regdb.c as an alternative to using CRDA.
+
+The file net/wireless/db.txt should be kept up-to-date with the db.txt
+file available in the git repository here:
+
+    git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-regdb.git
+
+Again, most users in most situations should be using the CRDA package
+provided with their distribution, and in most other situations users
+should be building and using CRDA on their own rather than using
+this option.  If you are not absolutely sure that you should be using
+CONFIG_CFG80211_INTERNAL_REGDB then _DO_NOT_USE_IT_.
diff --git a/Documentation/networking/tcp-thin.txt b/Documentation/networking/tcp-thin.txt
new file mode 100644
index 00000000000..151e229980f
--- /dev/null
+++ b/Documentation/networking/tcp-thin.txt
@@ -0,0 +1,47 @@
+Thin-streams and TCP
+====================
+A wide range of Internet-based services that use reliable transport
+protocols display what we call thin-stream properties. This means
+that the application sends data with such a low rate that the
+retransmission mechanisms of the transport protocol are not fully
+effective. In time-dependent scenarios (like online games, control
+systems, stock trading etc.) where the user experience depends
+on the data delivery latency, packet loss can be devastating for
+the service quality. Extreme latencies are caused by TCP's
+dependency on the arrival of new data from the application to trigger
+retransmissions effectively through fast retransmit instead of
+waiting for long timeouts.
+
+After analysing a large number of time-dependent interactive
+applications, we have seen that they often produce thin streams
+and also stay with this traffic pattern throughout its entire
+lifespan. The combination of time-dependency and the fact that the
+streams provoke high latencies when using TCP is unfortunate.
+
+In order to reduce application-layer latency when packets are lost,
+a set of mechanisms has been made, which address these latency issues
+for thin streams. In short, if the kernel detects a thin stream,
+the retransmission mechanisms are modified in the following manner:
+
+1) If the stream is thin, fast retransmit on the first dupACK.
+2) If the stream is thin, do not apply exponential backoff.
+
+These enhancements are applied only if the stream is detected as
+thin. This is accomplished by defining a threshold for the number
+of packets in flight. If there are less than 4 packets in flight,
+fast retransmissions can not be triggered, and the stream is prone
+to experience high retransmission latencies.
+
+Since these mechanisms are targeted at time-dependent applications,
+they must be specifically activated by the application using the
+TCP_THIN_LINEAR_TIMEOUTS and TCP_THIN_DUPACK IOCTLS or the
+tcp_thin_linear_timeouts and tcp_thin_dupack sysctls. Both
+modifications are turned off by default.
+
+References
+==========
+More information on the modifications, as well as a wide range of
+experimental data can be found here:
+"Improving latency for interactive, thin-stream applications over
+reliable transport"
+http://simula.no/research/nd/publications/Simula.nd.477/simula_pdf_file
diff --git a/Documentation/pcmcia/locking.txt b/Documentation/pcmcia/locking.txt
new file mode 100644
index 00000000000..68f622bc406
--- /dev/null
+++ b/Documentation/pcmcia/locking.txt
@@ -0,0 +1,118 @@
+This file explains the locking and exclusion scheme used in the PCCARD
+and PCMCIA subsystems.
+
+
+A) Overview, Locking Hierarchy:
+===============================
+
+pcmcia_socket_list_rwsem	- protects only the list of sockets
+- skt_mutex			- serializes card insert / ejection
+  - ops_mutex			- serializes socket operation
+
+
+B) Exclusion
+============
+
+The following functions and callbacks to struct pcmcia_socket must
+be called with "skt_mutex" held:
+
+	socket_detect_change()
+	send_event()
+	socket_reset()
+	socket_shutdown()
+	socket_setup()
+	socket_remove()
+	socket_insert()
+	socket_early_resume()
+	socket_late_resume()
+	socket_resume()
+	socket_suspend()
+
+	struct pcmcia_callback	*callback
+
+The following functions and callbacks to struct pcmcia_socket must
+be called with "ops_mutex" held:
+
+	socket_reset()
+	socket_setup()
+
+	struct pccard_operations	*ops
+	struct pccard_resource_ops	*resource_ops;
+
+Note that send_event() and struct pcmcia_callback *callback must not be
+called with "ops_mutex" held.
+
+
+C) Protection
+=============
+
+1. Global Data:
+---------------
+struct list_head	pcmcia_socket_list;
+
+protected by pcmcia_socket_list_rwsem;
+
+
+2. Per-Socket Data:
+-------------------
+The resource_ops and their data are protected by ops_mutex.
+
+The "main" struct pcmcia_socket is protected as follows (read-only fields
+or single-use fields not mentioned):
+
+- by pcmcia_socket_list_rwsem:
+	struct list_head	socket_list;
+
+- by thread_lock:
+	unsigned int		thread_events;
+
+- by skt_mutex:
+	u_int			suspended_state;
+	void			(*tune_bridge);
+	struct pcmcia_callback	*callback;
+	int			resume_status;
+
+- by ops_mutex:
+	socket_state_t		socket;
+	u_int			state;
+	u_short			lock_count;
+	pccard_mem_map		cis_mem;
+	void __iomem 		*cis_virt;
+	struct { }		irq;
+	io_window_t		io[];
+	pccard_mem_map		win[];
+	struct list_head	cis_cache;
+	size_t			fake_cis_len;
+	u8			*fake_cis;
+	u_int			irq_mask;
+	void 			(*zoom_video);
+	int 			(*power_hook);
+	u8			resource...;
+	struct list_head	devices_list;
+	u8			device_count;
+	struct 			pcmcia_state;
+
+
+3. Per PCMCIA-device Data:
+--------------------------
+
+The "main" struct pcmcia_devie is protected as follows (read-only fields
+or single-use fields not mentioned):
+
+
+- by pcmcia_socket->ops_mutex:
+	struct list_head	socket_device_list;
+	struct config_t		*function_config;
+	u16			_irq:1;
+	u16			_io:1;
+	u16			_win:4;
+	u16			_locked:1;
+	u16			allow_func_id_match:1;
+	u16			suspended:1;
+	u16			_removed:1;
+
+- by the PCMCIA driver:
+	io_req_t		io;
+	irq_req_t		irq;
+	config_req_t		conf;
+	window_handle_t		win;
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 356fd86f4ea..ab00eeddeca 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -224,6 +224,12 @@ defined in include/linux/pm.h:
       RPM_SUSPENDED, which means that each device is initially regarded by the
       PM core as 'suspended', regardless of its real hardware status
 
+  unsigned int runtime_auto;
+    - if set, indicates that the user space has allowed the device driver to
+      power manage the device at run time via the /sys/devices/.../power/control
+      interface; it may only be modified with the help of the pm_runtime_allow()
+      and pm_runtime_forbid() helper functions
+
 All of the above fields are members of the 'power' member of 'struct device'.
 
 4. Run-time PM Device Helper Functions
@@ -329,6 +335,20 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       'power.runtime_error' is set or 'power.disable_depth' is greater than
       zero)
 
+  bool pm_runtime_suspended(struct device *dev);
+    - return true if the device's runtime PM status is 'suspended', or false
+      otherwise
+
+  void pm_runtime_allow(struct device *dev);
+    - set the power.runtime_auto flag for the device and decrease its usage
+      counter (used by the /sys/devices/.../power/control interface to
+      effectively allow the device to be power managed at run time)
+
+  void pm_runtime_forbid(struct device *dev);
+    - unset the power.runtime_auto flag for the device and increase its usage
+      counter (used by the /sys/devices/.../power/control interface to
+      effectively prevent the device from being power managed at run time)
+
 It is safe to execute the following helper functions from interrupt context:
 
 pm_request_idle()
@@ -382,6 +402,18 @@ may be desirable to suspend the device as soon as ->probe() or ->remove() has
 finished, so the PM core uses pm_runtime_idle_sync() to invoke the
 subsystem-level idle callback for the device at that time.
 
+The user space can effectively disallow the driver of the device to power manage
+it at run time by changing the value of its /sys/devices/.../power/control
+attribute to "on", which causes pm_runtime_forbid() to be called.  In principle,
+this mechanism may also be used by the driver to effectively turn off the
+run-time power management of the device until the user space turns it on.
+Namely, during the initialization the driver can make sure that the run-time PM
+status of the device is 'active' and call pm_runtime_forbid().  It should be
+noted, however, that if the user space has already intentionally changed the
+value of /sys/devices/.../power/control to "auto" to allow the driver to power
+manage the device at run time, the driver may confuse it by using
+pm_runtime_forbid() this way.
+
 6. Run-time PM and System Sleep
 
 Run-time PM and system sleep (i.e., system suspend and hibernation, also known
@@ -431,3 +463,64 @@ 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
+management callbacks provided by the PM core, defined in
+driver/base/power/generic_ops.c:
+
+  int pm_generic_runtime_idle(struct device *dev);
+    - invoke the ->runtime_idle() callback provided by the driver of this
+      device, if defined, and call pm_runtime_suspend() for this device if the
+      return value is 0 or the callback is not defined
+
+  int pm_generic_runtime_suspend(struct device *dev);
+    - invoke the ->runtime_suspend() callback provided by the driver of this
+      device and return its result, or return -EINVAL if not defined
+
+  int pm_generic_runtime_resume(struct device *dev);
+    - invoke the ->runtime_resume() callback provided by the driver of this
+      device and return its result, or return -EINVAL if not defined
+
+  int pm_generic_suspend(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->suspend()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+
+  int pm_generic_resume(struct device *dev);
+    - invoke the ->resume() callback provided by the driver of this device and,
+      if successful, change the device's runtime PM status to 'active'
+
+  int pm_generic_freeze(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->freeze()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+
+  int pm_generic_thaw(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->thaw()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+
+  int pm_generic_poweroff(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->poweroff()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+
+  int pm_generic_restore(struct device *dev);
+    - invoke the ->restore() callback provided by the driver of this device and,
+      if successful, change the device's runtime PM status to 'active'
+
+These functions can be assigned to the ->runtime_idle(), ->runtime_suspend(),
+->runtime_resume(), ->suspend(), ->resume(), ->freeze(), ->thaw(), ->poweroff(),
+or ->restore() callback pointers in the subsystem-level dev_pm_ops structures.
+
+If a subsystem wishes to use all of them at the same time, it can simply assign
+the GENERIC_SUBSYS_PM_OPS macro, defined in include/linux/pm.h, to its
+dev_pm_ops structure pointer.
+
+Device drivers that wish to use the same function as a system suspend, freeze,
+poweroff and run-time suspend callback, and similarly for system resume, thaw,
+restore, and run-time resume, can achieve this with the help of the
+UNIVERSAL_DEV_PM_OPS macro defined in include/linux/pm.h (possibly setting its
+last argument to NULL).
diff --git a/Documentation/powerpc/dts-bindings/fsl/can.txt b/Documentation/powerpc/dts-bindings/fsl/can.txt
new file mode 100644
index 00000000000..2fa4fcd38fd
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/can.txt
@@ -0,0 +1,53 @@
+CAN Device Tree Bindings
+------------------------
+
+(c) 2006-2009 Secret Lab Technologies Ltd
+Grant Likely <grant.likely@secretlab.ca>
+
+fsl,mpc5200-mscan nodes
+-----------------------
+In addition to the required compatible-, reg- and interrupt-properties, you can
+also specify which clock source shall be used for the controller:
+
+- fsl,mscan-clock-source : a string describing the clock source. Valid values
+			   are:	"ip" for ip bus clock
+				 "ref" for reference clock (XTAL)
+			   "ref" is default in case this property is not
+			   present.
+
+fsl,mpc5121-mscan nodes
+-----------------------
+In addition to the required compatible-, reg- and interrupt-properties, you can
+also specify which clock source and divider shall be used for the controller:
+
+- fsl,mscan-clock-source : a string describing the clock source. Valid values
+			   are:	"ip" for ip bus clock
+				"ref" for reference clock
+				"sys" for system clock
+			   If this property is not present, an optimal CAN
+			   clock source and frequency based on the system
+			   clock will be selected. If this is not possible,
+			   the reference clock will be used.
+
+- fsl,mscan-clock-divider: for the reference and system clock, an additional
+			   clock divider can be specified. By default, a
+			   value of 1 is used.
+
+Note that the MPC5121 Rev. 1 processor is not supported.
+
+Examples:
+	can@1300 {
+		compatible = "fsl,mpc5121-mscan";
+		interrupts = <12 0x8>;
+		interrupt-parent = <&ipic>;
+		reg = <0x1300 0x80>;
+	};
+
+	can@1380 {
+		compatible = "fsl,mpc5121-mscan";
+		interrupts = <13 0x8>;
+		interrupt-parent = <&ipic>;
+		reg = <0x1380 0x80>;
+		fsl,mscan-clock-source = "ref";
+		fsl,mscan-clock-divider = <3>;
+	};
diff --git a/Documentation/powerpc/dts-bindings/fsl/dma.txt b/Documentation/powerpc/dts-bindings/fsl/dma.txt
index 0732cdd05ba..2a4b4bce611 100644
--- a/Documentation/powerpc/dts-bindings/fsl/dma.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/dma.txt
@@ -44,21 +44,29 @@ Example:
 			compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
 			cell-index = <0>;
 			reg = <0 0x80>;
+			interrupt-parent = <&ipic>;
+			interrupts = <71 8>;
 		};
 		dma-channel@80 {
 			compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
 			cell-index = <1>;
 			reg = <0x80 0x80>;
+			interrupt-parent = <&ipic>;
+			interrupts = <71 8>;
 		};
 		dma-channel@100 {
 			compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
 			cell-index = <2>;
 			reg = <0x100 0x80>;
+			interrupt-parent = <&ipic>;
+			interrupts = <71 8>;
 		};
 		dma-channel@180 {
 			compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
 			cell-index = <3>;
 			reg = <0x180 0x80>;
+			interrupt-parent = <&ipic>;
+			interrupts = <71 8>;
 		};
 	};
 
diff --git a/Documentation/powerpc/dts-bindings/fsl/i2c.txt b/Documentation/powerpc/dts-bindings/fsl/i2c.txt
index b6d2e21474f..50da2031058 100644
--- a/Documentation/powerpc/dts-bindings/fsl/i2c.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/i2c.txt
@@ -2,15 +2,14 @@
 
 Required properties :
 
- - device_type : Should be "i2c"
  - reg : Offset and length of the register set for the device
+ - compatible : should be "fsl,CHIP-i2c" where CHIP is the name of a
+   compatible processor, e.g. mpc8313, mpc8543, mpc8544, mpc5121,
+   mpc5200 or mpc5200b. For the mpc5121, an additional node
+   "fsl,mpc5121-i2c-ctrl" is required as shown in the example below.
 
 Recommended properties :
 
- - compatible : compatibility list with 2 entries, the first should
-   be "fsl,CHIP-i2c" where CHIP is the name of a compatible processor,
-   e.g. mpc8313, mpc8543, mpc8544, mpc5200 or mpc5200b. The second one
-   should be "fsl-i2c".
  - interrupts : <a b> where a is the interrupt number and b is a
    field that represents an encoding of the sense and level
    information for the interrupt.  This should be encoded based on
@@ -24,25 +23,40 @@ Recommended properties :
 
 Examples :
 
+	/* MPC5121 based board */
+	i2c@1740 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "fsl,mpc5121-i2c", "fsl-i2c";
+		reg = <0x1740 0x20>;
+		interrupts = <11 0x8>;
+		interrupt-parent = <&ipic>;
+		clock-frequency = <100000>;
+	};
+
+	i2ccontrol@1760 {
+		compatible = "fsl,mpc5121-i2c-ctrl";
+		reg = <0x1760 0x8>;
+	};
+
+	/* MPC5200B based board */
 	i2c@3d00 {
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "fsl,mpc5200b-i2c","fsl,mpc5200-i2c","fsl-i2c";
-		cell-index = <0>;
 		reg = <0x3d00 0x40>;
 		interrupts = <2 15 0>;
 		interrupt-parent = <&mpc5200_pic>;
 		fsl,preserve-clocking;
 	};
 
+	/* MPC8544 base board */
 	i2c@3100 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		cell-index = <1>;
 		compatible = "fsl,mpc8544-i2c", "fsl-i2c";
 		reg = <0x3100 0x100>;
 		interrupts = <43 2>;
 		interrupt-parent = <&mpic>;
 		clock-frequency = <400000>;
 	};
-
diff --git a/Documentation/powerpc/dts-bindings/fsl/mpc5121-psc.txt b/Documentation/powerpc/dts-bindings/fsl/mpc5121-psc.txt
new file mode 100644
index 00000000000..8832e879891
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/mpc5121-psc.txt
@@ -0,0 +1,70 @@
+MPC5121 PSC Device Tree Bindings
+
+PSC in UART mode
+----------------
+
+For PSC in UART mode the needed PSC serial devices
+are specified by fsl,mpc5121-psc-uart nodes in the
+fsl,mpc5121-immr SoC node. Additionally the PSC FIFO
+Controller node fsl,mpc5121-psc-fifo is requered there:
+
+fsl,mpc5121-psc-uart nodes
+--------------------------
+
+Required properties :
+ - compatible : Should contain "fsl,mpc5121-psc-uart" and "fsl,mpc5121-psc"
+ - cell-index : Index of the PSC in hardware
+ - reg : Offset and length of the register set for the PSC device
+ - interrupts : <a b> where a is the interrupt number of the
+   PSC FIFO Controller and b is a field that represents an
+   encoding of the sense and level information for the interrupt.
+ - interrupt-parent : the phandle for the interrupt controller that
+   services interrupts for this device.
+
+Recommended properties :
+ - fsl,rx-fifo-size : the size of the RX fifo slice (a multiple of 4)
+ - fsl,tx-fifo-size : the size of the TX fifo slice (a multiple of 4)
+
+
+fsl,mpc5121-psc-fifo node
+-------------------------
+
+Required properties :
+ - compatible : Should be "fsl,mpc5121-psc-fifo"
+ - reg : Offset and length of the register set for the PSC
+         FIFO Controller
+ - interrupts : <a b> where a is the interrupt number of the
+   PSC FIFO Controller and b is a field that represents an
+   encoding of the sense and level information for the interrupt.
+ - interrupt-parent : the phandle for the interrupt controller that
+   services interrupts for this device.
+
+
+Example for a board using PSC0 and PSC1 devices in serial mode:
+
+serial@11000 {
+	compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+	cell-index = <0>;
+	reg = <0x11000 0x100>;
+	interrupts = <40 0x8>;
+	interrupt-parent = < &ipic >;
+	fsl,rx-fifo-size = <16>;
+	fsl,tx-fifo-size = <16>;
+};
+
+serial@11100 {
+	compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+	cell-index = <1>;
+	reg = <0x11100 0x100>;
+	interrupts = <40 0x8>;
+	interrupt-parent = < &ipic >;
+	fsl,rx-fifo-size = <16>;
+	fsl,tx-fifo-size = <16>;
+};
+
+pscfifo@11f00 {
+	compatible = "fsl,mpc5121-psc-fifo";
+	reg = <0x11f00 0x100>;
+	interrupts = <40 0x8>;
+	interrupt-parent = < &ipic >;
+};
diff --git a/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt b/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt
index 5c6602dbfdc..4ccb2cd5df9 100644
--- a/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt
@@ -195,11 +195,4 @@ External interrupts:
 
 fsl,mpc5200-mscan nodes
 -----------------------
-In addition to the required compatible-, reg- and interrupt-properites, you can
-also specify which clock source shall be used for the controller:
-
-- fsl,mscan-clock-source- a string describing the clock source. Valid values
-			  are:	"ip" for ip bus clock
-				"ref" for reference clock (XTAL)
-			  "ref" is default in case this property is not
-			  present.
+See file can.txt in this directory.
diff --git a/Documentation/powerpc/dts-bindings/fsl/spi.txt b/Documentation/powerpc/dts-bindings/fsl/spi.txt
index e7d9a344c4f..80510c018ee 100644
--- a/Documentation/powerpc/dts-bindings/fsl/spi.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/spi.txt
@@ -13,6 +13,11 @@ Required properties:
 - interrupt-parent : the phandle for the interrupt controller that
   services interrupts for this device.
 
+Optional properties:
+- gpios : specifies the gpio pins to be used for chipselects.
+  The gpios will be referred to as reg = <index> in the SPI child nodes.
+  If unspecified, a single SPI device without a chip select can be used.
+
 Example:
 	spi@4c0 {
 		cell-index = <0>;
@@ -21,4 +26,6 @@ Example:
 		interrupts = <82 0>;
 		interrupt-parent = <700>;
 		mode = "cpu";
+		gpios = <&gpio 18 1	// device reg=<0>
+			 &gpio 19 1>;	// device reg=<1>
 	};
diff --git a/Documentation/powerpc/ptrace.txt b/Documentation/powerpc/ptrace.txt
new file mode 100644
index 00000000000..f4a5499b7bc
--- /dev/null
+++ b/Documentation/powerpc/ptrace.txt
@@ -0,0 +1,134 @@
+GDB intends to support the following hardware debug features of BookE
+processors:
+
+4 hardware breakpoints (IAC)
+2 hardware watchpoints (read, write and read-write) (DAC)
+2 value conditions for the hardware watchpoints (DVC)
+
+For that, we need to extend ptrace so that GDB can query and set these
+resources. Since we're extending, we're trying to create an interface
+that's extendable and that covers both BookE and server processors, so
+that GDB doesn't need to special-case each of them. We added the
+following 3 new ptrace requests.
+
+1. PTRACE_PPC_GETHWDEBUGINFO
+
+Query for GDB to discover the hardware debug features. The main info to
+be returned here is the minimum alignment for the hardware watchpoints.
+BookE processors don't have restrictions here, but server processors have
+an 8-byte alignment restriction for hardware watchpoints. We'd like to avoid
+adding special cases to GDB based on what it sees in AUXV.
+
+Since we're at it, we added other useful info that the kernel can return to
+GDB: this query will return the number of hardware breakpoints, hardware
+watchpoints and whether it supports a range of addresses and a condition.
+The query will fill the following structure provided by the requesting process:
+
+struct ppc_debug_info {
+       unit32_t version;
+       unit32_t num_instruction_bps;
+       unit32_t num_data_bps;
+       unit32_t num_condition_regs;
+       unit32_t data_bp_alignment;
+       unit32_t sizeof_condition; /* size of the DVC register */
+       uint64_t features; /* bitmask of the individual flags */
+};
+
+features will have bits indicating whether there is support for:
+
+#define PPC_DEBUG_FEATURE_INSN_BP_RANGE		0x1
+#define PPC_DEBUG_FEATURE_INSN_BP_MASK		0x2
+#define PPC_DEBUG_FEATURE_DATA_BP_RANGE		0x4
+#define PPC_DEBUG_FEATURE_DATA_BP_MASK		0x8
+
+2. PTRACE_SETHWDEBUG
+
+Sets a hardware breakpoint or watchpoint, according to the provided structure:
+
+struct ppc_hw_breakpoint {
+        uint32_t version;
+#define PPC_BREAKPOINT_TRIGGER_EXECUTE  0x1
+#define PPC_BREAKPOINT_TRIGGER_READ     0x2
+#define PPC_BREAKPOINT_TRIGGER_WRITE    0x4
+        uint32_t trigger_type;       /* only some combinations allowed */
+#define PPC_BREAKPOINT_MODE_EXACT               0x0
+#define PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE     0x1
+#define PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE     0x2
+#define PPC_BREAKPOINT_MODE_MASK                0x3
+        uint32_t addr_mode;          /* address match mode */
+
+#define PPC_BREAKPOINT_CONDITION_MODE   0x3
+#define PPC_BREAKPOINT_CONDITION_NONE   0x0
+#define PPC_BREAKPOINT_CONDITION_AND    0x1
+#define PPC_BREAKPOINT_CONDITION_EXACT  0x1	/* different name for the same thing as above */
+#define PPC_BREAKPOINT_CONDITION_OR     0x2
+#define PPC_BREAKPOINT_CONDITION_AND_OR 0x3
+#define PPC_BREAKPOINT_CONDITION_BE_ALL 0x00ff0000	/* byte enable bits */
+#define PPC_BREAKPOINT_CONDITION_BE(n)  (1<<((n)+16))
+        uint32_t condition_mode;     /* break/watchpoint condition flags */
+
+        uint64_t addr;
+        uint64_t addr2;
+        uint64_t condition_value;
+};
+
+A request specifies one event, not necessarily just one register to be set.
+For instance, if the request is for a watchpoint with a condition, both the
+DAC and DVC registers will be set in the same request.
+
+With this GDB can ask for all kinds of hardware breakpoints and watchpoints
+that the BookE supports. COMEFROM breakpoints available in server processors
+are not contemplated, but that is out of the scope of this work.
+
+ptrace will return an integer (handle) uniquely identifying the breakpoint or
+watchpoint just created. This integer will be used in the PTRACE_DELHWDEBUG
+request to ask for its removal. Return -ENOSPC if the requested breakpoint
+can't be allocated on the registers.
+
+Some examples of using the structure to:
+
+- set a breakpoint in the first breakpoint register
+
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_EXECUTE;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_EXACT;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_NONE;
+  p.addr            = (uint64_t) address;
+  p.addr2           = 0;
+  p.condition_value = 0;
+
+- set a watchpoint which triggers on reads in the second watchpoint register
+
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_READ;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_EXACT;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_NONE;
+  p.addr            = (uint64_t) address;
+  p.addr2           = 0;
+  p.condition_value = 0;
+
+- set a watchpoint which triggers only with a specific value
+
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_READ;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_EXACT;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_AND | PPC_BREAKPOINT_CONDITION_BE_ALL;
+  p.addr            = (uint64_t) address;
+  p.addr2           = 0;
+  p.condition_value = (uint64_t) condition;
+
+- set a ranged hardware breakpoint
+
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_EXECUTE;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_NONE;
+  p.addr            = (uint64_t) begin_range;
+  p.addr2           = (uint64_t) end_range;
+  p.condition_value = 0;
+
+3. PTRACE_DELHWDEBUG
+
+Takes an integer which identifies an existing breakpoint or watchpoint
+(i.e., the value returned from PTRACE_SETHWDEBUG), and deletes the
+corresponding breakpoint or watchpoint..
diff --git a/Documentation/s390/CommonIO b/Documentation/s390/CommonIO
index 339207d11d9..d378cba6645 100644
--- a/Documentation/s390/CommonIO
+++ b/Documentation/s390/CommonIO
@@ -87,6 +87,12 @@ Command line parameters
   compatibility, by the device number in hexadecimal (0xabcd or abcd). Device
   numbers given as 0xabcd will be interpreted as 0.0.abcd.
 
+* /proc/cio_settle
+
+  A write request to this file is blocked until all queued cio actions are
+  handled. This will allow userspace to wait for pending work affecting
+  device availability after changing cio_ignore or the hardware configuration.
+
 * For some of the information present in the /proc filesystem in 2.4 (namely,
   /proc/subchannels and /proc/chpids), see driver-model.txt.
   Information formerly in /proc/irq_count is now in /proc/interrupts.
diff --git a/Documentation/s390/driver-model.txt b/Documentation/s390/driver-model.txt
index bde473df748..ed265cf54cd 100644
--- a/Documentation/s390/driver-model.txt
+++ b/Documentation/s390/driver-model.txt
@@ -223,8 +223,8 @@ touched by the driver - it should use the ccwgroup device's driver_data for its
 private data.
 
 To implement a ccwgroup driver, please refer to include/asm/ccwgroup.h. Keep in
-mind that most drivers will need to implement both a ccwgroup and a ccw driver
-(unless you have a meta ccw driver, like cu3088 for lcs and ctc).
+mind that most drivers will need to implement both a ccwgroup and a ccw
+driver.
 
 
 2. Channel paths
diff --git a/Documentation/scsi/ChangeLog.megaraid_sas b/Documentation/scsi/ChangeLog.megaraid_sas
index 17ffa060771..30023568805 100644
--- a/Documentation/scsi/ChangeLog.megaraid_sas
+++ b/Documentation/scsi/ChangeLog.megaraid_sas
@@ -1,3 +1,19 @@
+1 Release Date    : Thur.  Oct 29, 2009 09:12:45 PST 2009 -
+			(emaild-id:megaraidlinux@lsi.com)
+			Bo Yang
+
+2 Current Version : 00.00.04.17.1-rc1
+3 Older Version   : 00.00.04.12
+
+1.	Add the pad_0 in mfi frame structure to 0 to fix the
+	context value larger than 32bit value issue.
+
+2.	Add the logic drive list to the driver.  Driver will
+	keep the logic drive list internal after driver load.
+
+3.	driver fixed the device update issue after get the AEN
+	PD delete/ADD, LD add/delete from FW.
+
 1 Release Date    : Tues.  July 28, 2009 10:12:45 PST 2009 -
 			(emaild-id:megaraidlinux@lsi.com)
 			Bo Yang
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 8923597bd2b..bfcbbf88c44 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -482,6 +482,9 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 
     reference_rate	- reference sample rate, 44100 or 48000 (default)
     multiple		- multiple to ref. sample rate, 1 or 2 (default)
+    subsystem		- override the PCI SSID for probing; the value
+			  consists of SSVID << 16 | SSDID.  The default is
+			  zero, which means no override.
 
     This module supports multiple cards.
 
@@ -1123,6 +1126,21 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 
     This module supports multiple cards, autoprobe and ISA PnP.
 
+  Module snd-jazz16
+  -------------------
+
+    Module for Media Vision Jazz16 chipset. The chipset consists of 3 chips:
+    MVD1216 + MVA416 + MVA514.
+
+    port	- port # for SB DSP chip (0x210,0x220,0x230,0x240,0x250,0x260)
+    irq		- IRQ # for SB DSP chip (3,5,7,9,10,15)
+    dma8	- DMA # for SB DSP chip (1,3)
+    dma16	- DMA # for SB DSP chip (5,7)
+    mpu_port	- MPU-401 port # (0x300,0x310,0x320,0x330)
+    mpu_irq	- MPU-401 irq # (2,3,5,7)
+
+    This module supports multiple cards.
+
   Module snd-korg1212
   -------------------
 
@@ -1791,6 +1809,13 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 
     The power-management is supported.
 
+  Module snd-ua101
+  ----------------
+
+    Module for the Edirol UA-101/UA-1000 audio/MIDI interfaces.
+
+    This module supports multiple devices, autoprobe and hotplugging.
+
   Module snd-usb-audio
   --------------------
 
@@ -1923,7 +1948,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
   -------------------
 
     Module for sound cards based on the Asus AV100/AV200 chips,
-    i.e., Xonar D1, DX, D2, D2X, HDAV1.3 (Deluxe), Essence ST
+    i.e., Xonar D1, DX, D2, D2X, DS, HDAV1.3 (Deluxe), Essence ST
     (Deluxe) and Essence STX.
 
     This module supports autoprobe and multiple cards.
diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
index e72cee9e2a7..1d38b0dfba9 100644
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@@ -124,6 +124,8 @@ ALC882/883/885/888/889
   asus-a7m	ASUS A7M
   macpro	MacPro support
   mb5		Macbook 5,1
+  macmini3	Macmini 3,1
+  mba21		Macbook Air 2,1
   mbp3		Macbook Pro rev3
   imac24	iMac 24'' with jack detection
   imac91	iMac 9,1
@@ -279,13 +281,16 @@ Conexant 5051
   laptop	Basic Laptop config (default)
   hp		HP Spartan laptop
   hp-dv6736	HP dv6736
+  hp-f700	HP Compaq Presario F700
   lenovo-x200	Lenovo X200 laptop
+  toshiba	Toshiba Satellite M300
 
 Conexant 5066
 =============
   laptop	Basic Laptop config (default)
   dell-laptop	Dell laptops
   olpc-xo-1_5	OLPC XO 1.5
+  ideapad       Lenovo IdeaPad U150
 
 STAC9200
 ========
diff --git a/Documentation/sound/alsa/HD-Audio.txt b/Documentation/sound/alsa/HD-Audio.txt
index 6325bec06a7..f4dd3bf99d1 100644
--- a/Documentation/sound/alsa/HD-Audio.txt
+++ b/Documentation/sound/alsa/HD-Audio.txt
@@ -452,6 +452,33 @@ Similarly, the lines after `[verb]` are parsed as `init_verbs`
 sysfs entries, and the lines after `[hint]` are parsed as `hints`
 sysfs entries, respectively.
 
+Another example to override the codec vendor id from 0x12345678 to
+0xdeadbeef is like below:
+------------------------------------------------------------------------
+  [codec]
+  0x12345678 0xabcd1234 2
+
+  [vendor_id]
+  0xdeadbeef
+------------------------------------------------------------------------
+
+In the similar way, you can override the codec subsystem_id via
+`[subsystem_id]`, the revision id via `[revision_id]` line.
+Also, the codec chip name can be rewritten via `[chip_name]` line.
+------------------------------------------------------------------------
+  [codec]
+  0x12345678 0xabcd1234 2
+
+  [subsystem_id]
+  0xffff1111
+
+  [revision_id]
+  0x10
+
+  [chip_name]
+  My-own NEWS-0002
+------------------------------------------------------------------------
+
 The hd-audio driver reads the file via request_firmware().  Thus,
 a patch file has to be located on the appropriate firmware path,
 typically, /lib/firmware.  For example, when you pass the option
diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt
index 6a5a579126b..f1f81afee8a 100644
--- a/Documentation/trace/ftrace-design.txt
+++ b/Documentation/trace/ftrace-design.txt
@@ -238,11 +238,10 @@ HAVE_SYSCALL_TRACEPOINTS
 
 You need very few things to get the syscalls tracing in an arch.
 
+- Support HAVE_ARCH_TRACEHOOK (see arch/Kconfig).
 - Have a NR_syscalls variable in <asm/unistd.h> that provides the number
   of syscalls supported by the arch.
-- Implement arch_syscall_addr() that resolves a syscall address from a
-  syscall number.
-- Support the TIF_SYSCALL_TRACEPOINT thread flags
+- Support the TIF_SYSCALL_TRACEPOINT thread flags.
 - Put the trace_sys_enter() and trace_sys_exit() tracepoints calls from ptrace
   in the ptrace syscalls tracing path.
 - Tag this arch as HAVE_SYSCALL_TRACEPOINTS.
diff --git a/Documentation/usb/error-codes.txt b/Documentation/usb/error-codes.txt
index 9cf83e8c27b..d83703ea74b 100644
--- a/Documentation/usb/error-codes.txt
+++ b/Documentation/usb/error-codes.txt
@@ -41,8 +41,8 @@ USB-specific:
 
 -EFBIG		Host controller driver can't schedule that many ISO frames.
 
--EPIPE		Specified endpoint is stalled.  For non-control endpoints,
-		reset this status with usb_clear_halt().
+-EPIPE		The pipe type specified in the URB doesn't match the
+		endpoint's actual type.
 
 -EMSGSIZE	(a) endpoint maxpacket size is zero; it is not usable
 		    in the current interface altsetting.
@@ -60,6 +60,8 @@ USB-specific:
 
 -EHOSTUNREACH	URB was rejected because the device is suspended.
 
+-ENOEXEC	A control URB doesn't contain a Setup packet.
+
 
 **************************************************************************
 *                   Error codes returned by in urb->status               *
diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt
index 3bf6818c8cf..2790ad48cfc 100644
--- a/Documentation/usb/power-management.txt
+++ b/Documentation/usb/power-management.txt
@@ -2,7 +2,7 @@
 
 		 Alan Stern <stern@rowland.harvard.edu>
 
-			    November 10, 2009
+			    December 11, 2009
 
 
 
@@ -29,9 +29,9 @@ covered to some extent (see Documentation/power/*.txt for more
 information about system PM).
 
 Note: Dynamic PM support for USB is present only if the kernel was
-built with CONFIG_USB_SUSPEND enabled.  System PM support is present
-only if the kernel was built with CONFIG_SUSPEND or CONFIG_HIBERNATION
-enabled.
+built with CONFIG_USB_SUSPEND enabled (which depends on
+CONFIG_PM_RUNTIME).  System PM support is present only if the kernel
+was built with CONFIG_SUSPEND or CONFIG_HIBERNATION enabled.
 
 
 	What is Remote Wakeup?
@@ -229,6 +229,11 @@ necessary operations by hand or add them to a udev script.  You can
 also change the idle-delay time; 2 seconds is not the best choice for
 every device.
 
+If a driver knows that its device has proper suspend/resume support,
+it can enable autosuspend all by itself.  For example, the video
+driver for a laptop's webcam might do this, since these devices are
+rarely used and so should normally be autosuspended.
+
 Sometimes it turns out that even when a device does work okay with
 autosuspend there are still problems.  For example, there are
 experimental patches adding autosuspend support to the usbhid driver,
@@ -321,69 +326,81 @@ driver does so by calling these six functions:
 	void usb_autopm_get_interface_no_resume(struct usb_interface *intf);
 	void usb_autopm_put_interface_no_suspend(struct usb_interface *intf);
 
-The functions work by maintaining a counter in the usb_interface
-structure.  When intf->pm_usage_count is > 0 then the interface is
-deemed to be busy, and the kernel will not autosuspend the interface's
-device.  When intf->pm_usage_count is <= 0 then the interface is
-considered to be idle, and the kernel may autosuspend the device.
+The functions work by maintaining a usage counter in the
+usb_interface's embedded device structure.  When the counter is > 0
+then the interface is deemed to be busy, and the kernel will not
+autosuspend the interface's device.  When the usage counter is = 0
+then the interface is considered to be idle, and the kernel may
+autosuspend the device.
 
-(There is a similar pm_usage_count field in struct usb_device,
+(There is a similar usage counter field in struct usb_device,
 associated with the device itself rather than any of its interfaces.
-This field is used only by the USB core.)
-
-Drivers must not modify intf->pm_usage_count directly; its value
-should be changed only be using the functions listed above.  Drivers
-are responsible for insuring that the overall change to pm_usage_count
-during their lifetime balances out to 0 (it may be necessary for the
-disconnect method to call usb_autopm_put_interface() one or more times
-to fulfill this requirement).  The first two routines use the PM mutex
-in struct usb_device for mutual exclusion; drivers using the async
-routines are responsible for their own synchronization and mutual
-exclusion.
-
-	usb_autopm_get_interface() increments pm_usage_count and
-	attempts an autoresume if the new value is > 0 and the
-	device is suspended.
-
-	usb_autopm_put_interface() decrements pm_usage_count and
-	attempts an autosuspend if the new value is <= 0 and the
-	device isn't suspended.
+This counter is used only by the USB core.)
+
+Drivers need not be concerned about balancing changes to the usage
+counter; the USB core will undo any remaining "get"s when a driver
+is unbound from its interface.  As a corollary, drivers must not call
+any of the usb_autopm_* functions after their diconnect() routine has
+returned.
+
+Drivers using the async routines are responsible for their own
+synchronization and mutual exclusion.
+
+	usb_autopm_get_interface() increments the usage counter and
+	does an autoresume if the device is suspended.  If the
+	autoresume fails, the counter is decremented back.
+
+	usb_autopm_put_interface() decrements the usage counter and
+	attempts an autosuspend if the new value is = 0.
 
 	usb_autopm_get_interface_async() and
 	usb_autopm_put_interface_async() do almost the same things as
-	their non-async counterparts.  The differences are: they do
-	not acquire the PM mutex, and they use a workqueue to do their
+	their non-async counterparts.  The big difference is that they
+	use a workqueue to do the resume or suspend part of their
 	jobs.  As a result they can be called in an atomic context,
 	such as an URB's completion handler, but when they return the
-	device will not generally not yet be in the desired state.
+	device will generally not yet be in the desired state.
 
 	usb_autopm_get_interface_no_resume() and
 	usb_autopm_put_interface_no_suspend() merely increment or
-	decrement the pm_usage_count value; they do not attempt to
-	carry out an autoresume or an autosuspend.  Hence they can be
-	called in an atomic context.
+	decrement the usage counter; they do not attempt to carry out
+	an autoresume or an autosuspend.  Hence they can be called in
+	an atomic context.
 
-The conventional usage pattern is that a driver calls
+The simplest usage pattern is that a driver calls
 usb_autopm_get_interface() in its open routine and
-usb_autopm_put_interface() in its close or release routine.  But
-other patterns are possible.
+usb_autopm_put_interface() in its close or release routine.  But other
+patterns are possible.
 
 The autosuspend attempts mentioned above will often fail for one
 reason or another.  For example, the power/level attribute might be
 set to "on", or another interface in the same device might not be
 idle.  This is perfectly normal.  If the reason for failure was that
-the device hasn't been idle for long enough, a delayed workqueue
-routine is automatically set up to carry out the operation when the
-autosuspend idle-delay has expired.
+the device hasn't been idle for long enough, a timer is scheduled to
+carry out the operation automatically when the autosuspend idle-delay
+has expired.
 
 Autoresume attempts also can fail, although failure would mean that
 the device is no longer present or operating properly.  Unlike
-autosuspend, there's no delay for an autoresume.
+autosuspend, there's no idle-delay for an autoresume.
 
 
 	Other parts of the driver interface
 	-----------------------------------
 
+Drivers can enable autosuspend for their devices by calling
+
+	usb_enable_autosuspend(struct usb_device *udev);
+
+in their probe() routine, if they know that the device is capable of
+suspending and resuming correctly.  This is exactly equivalent to
+writing "auto" to the device's power/level attribute.  Likewise,
+drivers can disable autosuspend by calling
+
+	usb_disable_autosuspend(struct usb_device *udev);
+
+This is exactly the same as writing "on" to the power/level attribute.
+
 Sometimes a driver needs to make sure that remote wakeup is enabled
 during autosuspend.  For example, there's not much point
 autosuspending a keyboard if the user can't cause the keyboard to do a
@@ -395,26 +412,27 @@ though, setting this flag won't cause the kernel to autoresume it.
 Normally a driver would set this flag in its probe method, at which
 time the device is guaranteed not to be autosuspended.)
 
-The synchronous usb_autopm_* routines have to run in a sleepable
-process context; they must not be called from an interrupt handler or
-while holding a spinlock.  In fact, the entire autosuspend mechanism
-is not well geared toward interrupt-driven operation.  However there
-is one thing a driver can do in an interrupt handler:
+If a driver does its I/O asynchronously in interrupt context, it
+should call usb_autopm_get_interface_async() before starting output and
+usb_autopm_put_interface_async() when the output queue drains.  When
+it receives an input event, it should call
 
 	usb_mark_last_busy(struct usb_device *udev);
 
-This sets udev->last_busy to the current time.  udev->last_busy is the
-field used for idle-delay calculations; updating it will cause any
-pending autosuspend to be moved back.  The usb_autopm_* routines will
-also set the last_busy field to the current time.
-
-Calling urb_mark_last_busy() from within an URB completion handler is
-subject to races: The kernel may have just finished deciding the
-device has been idle for long enough but not yet gotten around to
-calling the driver's suspend method.  The driver would have to be
-responsible for synchronizing its suspend method with its URB
-completion handler and causing the autosuspend to fail with -EBUSY if
-an URB had completed too recently.
+in the event handler.  This sets udev->last_busy to the current time.
+udev->last_busy is the field used for idle-delay calculations;
+updating it will cause any pending autosuspend to be moved back.  Most
+of the usb_autopm_* routines will also set the last_busy field to the
+current time.
+
+Asynchronous operation is always subject to races.  For example, a
+driver may call one of the usb_autopm_*_interface_async() routines at
+a time when the core has just finished deciding the device has been
+idle for long enough but not yet gotten around to calling the driver's
+suspend method.  The suspend method must be responsible for
+synchronizing with the output request routine and the URB completion
+handler; it should cause autosuspends to fail with -EBUSY if the
+driver needs to use the device.
 
 External suspend calls should never be allowed to fail in this way,
 only autosuspend calls.  The driver can tell them apart by checking
@@ -422,75 +440,23 @@ the PM_EVENT_AUTO bit in the message.event argument to the suspend
 method; this bit will be set for internal PM events (autosuspend) and
 clear for external PM events.
 
-Many of the ingredients in the autosuspend framework are oriented
-towards interfaces: The usb_interface structure contains the
-pm_usage_cnt field, and the usb_autopm_* routines take an interface
-pointer as their argument.  But somewhat confusingly, a few of the
-pieces (i.e., usb_mark_last_busy()) use the usb_device structure
-instead.  Drivers need to keep this straight; they can call
-interface_to_usbdev() to find the device structure for a given
-interface.
-
 
-	Locking requirements
-	--------------------
+	Mutual exclusion
+	----------------
 
-All three suspend/resume methods are always called while holding the
-usb_device's PM mutex.  For external events -- but not necessarily for
-autosuspend or autoresume -- the device semaphore (udev->dev.sem) will
-also be held.  This implies that external suspend/resume events are
-mutually exclusive with calls to probe, disconnect, pre_reset, and
-post_reset; the USB core guarantees that this is true of internal
-suspend/resume events as well.
+For external events -- but not necessarily for autosuspend or
+autoresume -- the device semaphore (udev->dev.sem) will be held when a
+suspend or resume method is called.  This implies that external
+suspend/resume events are mutually exclusive with calls to probe,
+disconnect, pre_reset, and post_reset; the USB core guarantees that
+this is true of autosuspend/autoresume events as well.
 
 If a driver wants to block all suspend/resume calls during some
-critical section, it can simply acquire udev->pm_mutex. Note that
-calls to resume may be triggered indirectly. Block IO due to memory
-allocations can make the vm subsystem resume a device. Thus while
-holding this lock you must not allocate memory with GFP_KERNEL or
-GFP_NOFS.
-
-Alternatively, if the critical section might call some of the
-usb_autopm_* routines, the driver can avoid deadlock by doing:
-
-	down(&udev->dev.sem);
-	rc = usb_autopm_get_interface(intf);
-
-and at the end of the critical section:
-
-	if (!rc)
-		usb_autopm_put_interface(intf);
-	up(&udev->dev.sem);
-
-Holding the device semaphore will block all external PM calls, and the
-usb_autopm_get_interface() will prevent any internal PM calls, even if
-it fails.  (Exercise: Why?)
-
-The rules for locking order are:
-
-	Never acquire any device semaphore while holding any PM mutex.
-
-	Never acquire udev->pm_mutex while holding the PM mutex for
-	a device that isn't a descendant of udev.
-
-In other words, PM mutexes should only be acquired going up the device
-tree, and they should be acquired only after locking all the device
-semaphores you need to hold.  These rules don't matter to drivers very
-much; they usually affect just the USB core.
-
-Still, drivers do need to be careful.  For example, many drivers use a
-private mutex to synchronize their normal I/O activities with their
-disconnect method.  Now if the driver supports autosuspend then it
-must call usb_autopm_put_interface() from somewhere -- maybe from its
-close method.  It should make the call while holding the private mutex,
-since a driver shouldn't call any of the usb_autopm_* functions for an
-interface from which it has been unbound.
-
-But the usb_autpm_* routines always acquire the device's PM mutex, and
-consequently the locking order has to be: private mutex first, PM
-mutex second.  Since the suspend method is always called with the PM
-mutex held, it mustn't try to acquire the private mutex.  It has to
-synchronize with the driver's I/O activities in some other way.
+critical section, the best way is to lock the device and call
+usb_autopm_get_interface() (and do the reverse at the end of the
+critical section).  Holding the device semaphore will block all
+external PM calls, and the usb_autopm_get_interface() will prevent any
+internal PM calls, even if it fails.  (Exercise: Why?)
 
 
 	Interaction between dynamic PM and system PM
@@ -499,22 +465,11 @@ synchronize with the driver's I/O activities in some other way.
 Dynamic power management and system power management can interact in
 a couple of ways.
 
-Firstly, a device may already be manually suspended or autosuspended
-when a system suspend occurs.  Since system suspends are supposed to
-be as transparent as possible, the device should remain suspended
-following the system resume.  The 2.6.23 kernel obeys this principle
-for manually suspended devices but not for autosuspended devices; they
-do get resumed when the system wakes up.  (Presumably they will be
-autosuspended again after their idle-delay time expires.)  In later
-kernels this behavior will be fixed.
-
-(There is an exception.  If a device would undergo a reset-resume
-instead of a normal resume, and the device is enabled for remote
-wakeup, then the reset-resume takes place even if the device was
-already suspended when the system suspend began.  The justification is
-that a reset-resume is a kind of remote-wakeup event.  Or to put it
-another way, a device which needs a reset won't be able to generate
-normal remote-wakeup signals, so it ought to be resumed immediately.)
+Firstly, a device may already be autosuspended when a system suspend
+occurs.  Since system suspends are supposed to be as transparent as
+possible, the device should remain suspended following the system
+resume.  But this theory may not work out well in practice; over time
+the kernel's behavior in this regard has changed.
 
 Secondly, a dynamic power-management event may occur as a system
 suspend is underway.  The window for this is short, since system
diff --git a/Documentation/video4linux/CARDLIST.cx23885 b/Documentation/video4linux/CARDLIST.cx23885
index 7539e8fa1ff..16ca030e118 100644
--- a/Documentation/video4linux/CARDLIST.cx23885
+++ b/Documentation/video4linux/CARDLIST.cx23885
@@ -26,3 +26,4 @@
  25 -> Compro VideoMate E800                               [1858:e800]
  26 -> Hauppauge WinTV-HVR1290                             [0070:8551]
  27 -> Mygica X8558 PRO DMB-TH                             [14f1:8578]
+ 28 -> LEADTEK WinFast PxTV1200                            [107d:6f22]
diff --git a/Documentation/video4linux/CARDLIST.saa7134 b/Documentation/video4linux/CARDLIST.saa7134
index fce1e7eb047..b4a767060ed 100644
--- a/Documentation/video4linux/CARDLIST.saa7134
+++ b/Documentation/video4linux/CARDLIST.saa7134
@@ -174,3 +174,4 @@
 173 -> Zolid Hybrid TV Tuner PCI                [1131:2004]
 174 -> Asus Europa Hybrid OEM                   [1043:4847]
 175 -> Leadtek Winfast DTV1000S                 [107d:6655]
+176 -> Beholder BeholdTV 505 RDS                [0000:5051]
diff --git a/Documentation/video4linux/CARDLIST.tuner b/Documentation/video4linux/CARDLIST.tuner
index e0d298fe883..9b2e0dd6017 100644
--- a/Documentation/video4linux/CARDLIST.tuner
+++ b/Documentation/video4linux/CARDLIST.tuner
@@ -81,3 +81,4 @@ tuner=80 - Philips FQ1216LME MK3 PAL/SECAM w/active loopthrough
 tuner=81 - Partsnic (Daewoo) PTI-5NF05
 tuner=82 - Philips CU1216L
 tuner=83 - NXP TDA18271
+tuner=84 - Sony BTF-Pxn01Z
diff --git a/Documentation/video4linux/README.tlg2300 b/Documentation/video4linux/README.tlg2300
new file mode 100644
index 00000000000..416ccb93d8c
--- /dev/null
+++ b/Documentation/video4linux/README.tlg2300
@@ -0,0 +1,47 @@
+tlg2300 release notes
+====================
+
+This is a v4l2/dvb device driver for the tlg2300 chip.
+
+
+current status
+==============
+
+video
+	- support mmap and read().(no overlay)
+
+audio
+	- The driver will register a ALSA card for the audio input.
+
+vbi
+	- Works for almost TV norms.
+
+dvb-t
+	- works for DVB-T
+
+FM
+	- Works for radio.
+
+---------------------------------------------------------------------------
+TESTED APPLICATIONS:
+
+-VLC1.0.4 test the video and dvb. The GUI is friendly to use.
+
+-Mplayer test the video.
+
+-Mplayer test the FM. The mplayer should be compiled with --enable-radio and
+	 --enable-radio-capture.
+	The command runs as this(The alsa audio registers to card 1):
+	#mplayer radio://103.7/capture/ -radio adevice=hw=1,0:arate=48000 \
+		-rawaudio rate=48000:channels=2
+
+---------------------------------------------------------------------------
+KNOWN PROBLEMS:
+about preemphasis:
+	You can set the preemphasis for radio by the following command:
+	#v4l2-ctl -d /dev/radio0 --set-ctrl=pre_emphasis_settings=1
+
+	"pre_emphasis_settings=1" means that you select the 50us. If you want
+	to select the 75us, please use "pre_emphasis_settings=2"
+
+
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
index 1800a62cf13..181b9e6fd98 100644
--- a/Documentation/video4linux/gspca.txt
+++ b/Documentation/video4linux/gspca.txt
@@ -42,6 +42,7 @@ ov519		041e:4064	Creative Live! VISTA VF0420
 ov519		041e:4067	Creative Live! Cam Video IM (VF0350)
 ov519		041e:4068	Creative Live! VISTA VF0470
 spca561		0458:7004	Genius VideoCAM Express V2
+sn9c2028	0458:7005	Genius Smart 300, version 2
 sunplus		0458:7006	Genius Dsc 1.3 Smart
 zc3xx		0458:7007	Genius VideoCam V2
 zc3xx		0458:700c	Genius VideoCam V3
@@ -109,6 +110,7 @@ sunplus		04a5:3003	Benq DC 1300
 sunplus		04a5:3008	Benq DC 1500
 sunplus		04a5:300a	Benq DC 3410
 spca500		04a5:300c	Benq DC 1016
+benq		04a5:3035	Benq DC E300
 finepix		04cb:0104	Fujifilm FinePix 4800
 finepix		04cb:0109	Fujifilm FinePix A202
 finepix		04cb:010b	Fujifilm FinePix A203
@@ -142,6 +144,7 @@ sunplus		04fc:5360	Sunplus Generic
 spca500		04fc:7333	PalmPixDC85
 sunplus		04fc:ffff	Pure DigitalDakota
 spca501		0506:00df	3Com HomeConnect Lite
+sunplus		052b:1507	Megapixel 5 Pretec DC-1007
 sunplus		052b:1513	Megapix V4
 sunplus		052b:1803	MegaImage VI
 tv8532		0545:808b	Veo Stingray
@@ -151,6 +154,7 @@ sunplus		0546:3191	Polaroid Ion 80
 sunplus		0546:3273	Polaroid PDC2030
 ov519		054c:0154	Sonny toy4
 ov519		054c:0155	Sonny toy5
+cpia1		0553:0002	CPIA CPiA (version1) based cameras
 zc3xx		055f:c005	Mustek Wcam300A
 spca500		055f:c200	Mustek Gsmart 300
 sunplus		055f:c211	Kowa Bs888e Microcamera
@@ -188,8 +192,7 @@ spca500		06bd:0404	Agfa CL20
 spca500		06be:0800	Optimedia
 sunplus		06d6:0031	Trust 610 LCD PowerC@m Zoom
 spca506		06e1:a190	ADS Instant VCD
-ov534		06f8:3002	Hercules Blog Webcam
-ov534		06f8:3003	Hercules Dualpix HD Weblog
+ov534_9		06f8:3003	Hercules Dualpix HD Weblog
 sonixj		06f8:3004	Hercules Classic Silver
 sonixj		06f8:3008	Hercules Deluxe Optical Glass
 pac7302		06f8:3009	Hercules Classic Link
@@ -204,6 +207,7 @@ sunplus		0733:2221	Mercury Digital Pro 3.1p
 sunplus		0733:3261	Concord 3045 spca536a
 sunplus		0733:3281	Cyberpix S550V
 spca506		0734:043b	3DeMon USB Capture aka
+cpia1		0813:0001	QX3 camera
 ov519		0813:0002	Dual Mode USB Camera Plus
 spca500		084d:0003	D-Link DSC-350
 spca500		08ca:0103	Aiptek PocketDV
@@ -225,7 +229,8 @@ sunplus		08ca:2050	Medion MD 41437
 sunplus		08ca:2060	Aiptek PocketDV5300
 tv8532		0923:010f	ICM532 cams
 mars		093a:050f	Mars-Semi Pc-Camera
-mr97310a	093a:010f	Sakar Digital no. 77379
+mr97310a	093a:010e	All known CIF cams with this ID
+mr97310a	093a:010f	All known VGA cams with this ID
 pac207		093a:2460	Qtec Webcam 100
 pac207		093a:2461	HP Webcam
 pac207		093a:2463	Philips SPC 220 NC
@@ -302,6 +307,7 @@ sonixj		0c45:613b	Surfer SN-206
 sonixj		0c45:613c	Sonix Pccam168
 sonixj		0c45:6143	Sonix Pccam168
 sonixj		0c45:6148	Digitus DA-70811/ZSMC USB PC Camera ZS211/Microdia
+sonixj		0c45:614a	Frontech E-Ccam (JIL-2225)
 sn9c20x		0c45:6240	PC Camera (SN9C201 + MT9M001)
 sn9c20x		0c45:6242	PC Camera (SN9C201 + MT9M111)
 sn9c20x		0c45:6248	PC Camera (SN9C201 + OV9655)
@@ -324,6 +330,10 @@ sn9c20x		0c45:62b0	PC Camera (SN9C202 + MT9V011/MT9V111/MT9V112)
 sn9c20x		0c45:62b3	PC Camera (SN9C202 + OV9655)
 sn9c20x		0c45:62bb	PC Camera (SN9C202 + OV7660)
 sn9c20x		0c45:62bc	PC Camera (SN9C202 + HV7131R)
+sn9c2028	0c45:8001	Wild Planet Digital Spy Camera
+sn9c2028	0c45:8003	Sakar #11199, #6637x, #67480 keychain cams
+sn9c2028	0c45:8008	Mini-Shotz ms-350
+sn9c2028	0c45:800a	Vivitar Vivicam 3350B
 sunplus		0d64:0303	Sunplus FashionCam DXG
 ov519		0e96:c001	TRUST 380 USB2 SPACEC@M
 etoms		102c:6151	Qcam Sangha CIF
@@ -341,10 +351,11 @@ spca501		1776:501c	Arowana 300K CMOS Camera
 t613		17a1:0128	TASCORP JPEG Webcam, NGS Cyclops
 vc032x		17ef:4802	Lenovo Vc0323+MI1310_SOC
 pac207		2001:f115	D-Link DSB-C120
-sq905c		2770:9050	sq905c
-sq905c		2770:905c	DualCamera
-sq905		2770:9120	Argus Digital Camera DC1512
-sq905c		2770:913d	sq905c
+sq905c		2770:9050	Disney pix micro (CIF)
+sq905c		2770:9052	Disney pix micro 2 (VGA)
+sq905c		2770:905c	All 11 known cameras with this ID
+sq905		2770:9120	All 24 known cameras with this ID
+sq905c		2770:913d	All 4 known cameras with this ID
 spca500		2899:012c	Toptro Industrial
 ov519		8020:ef04	ov519
 spca508		8086:0110	Intel Easy PC Camera
diff --git a/Documentation/video4linux/v4l2-framework.txt b/Documentation/video4linux/v4l2-framework.txt
index 74d677c8b03..5155700c206 100644
--- a/Documentation/video4linux/v4l2-framework.txt
+++ b/Documentation/video4linux/v4l2-framework.txt
@@ -599,99 +599,13 @@ video_device::minor fields.
 video buffer helper functions
 -----------------------------
 
-The v4l2 core API provides a standard method for dealing with video
-buffers. Those methods allow a driver to implement read(), mmap() and
-overlay() on a consistent way.
-
-There are currently methods for using video buffers on devices that
-supports DMA with scatter/gather method (videobuf-dma-sg), DMA with
-linear access (videobuf-dma-contig), and vmalloced buffers, mostly
-used on USB drivers (videobuf-vmalloc).
-
-Any driver using videobuf should provide operations (callbacks) for
-four handlers:
-
-ops->buf_setup   - calculates the size of the video buffers and avoid they
-		   to waste more than some maximum limit of RAM;
-ops->buf_prepare - fills the video buffer structs and calls
-		   videobuf_iolock() to alloc and prepare mmaped memory;
-ops->buf_queue   - advices the driver that another buffer were
-		   requested (by read() or by QBUF);
-ops->buf_release - frees any buffer that were allocated.
-
-In order to use it, the driver need to have a code (generally called at
-interrupt context) that will properly handle the buffer request lists,
-announcing that a new buffer were filled.
-
-The irq handling code should handle the videobuf task lists, in order
-to advice videobuf that a new frame were filled, in order to honor to a
-request. The code is generally like this one:
-	if (list_empty(&dma_q->active))
-		return;
-
-	buf = list_entry(dma_q->active.next, struct vbuffer, vb.queue);
-
-	if (!waitqueue_active(&buf->vb.done))
-		return;
-
-	/* Some logic to handle the buf may be needed here */
-
-	list_del(&buf->vb.queue);
-	do_gettimeofday(&buf->vb.ts);
-	wake_up(&buf->vb.done);
-
-Those are the videobuffer functions used on drivers, implemented on
-videobuf-core:
-
-- Videobuf init functions
-  videobuf_queue_sg_init()
-      Initializes the videobuf infrastructure. This function should be
-      called before any other videobuf function on drivers that uses DMA
-      Scatter/Gather buffers.
-
-  videobuf_queue_dma_contig_init
-      Initializes the videobuf infrastructure. This function should be
-      called before any other videobuf function on drivers that need DMA
-      contiguous buffers.
-
-  videobuf_queue_vmalloc_init()
-      Initializes the videobuf infrastructure. This function should be
-      called before any other videobuf function on USB (and other drivers)
-      that need a vmalloced type of videobuf.
-
-- videobuf_iolock()
-  Prepares the videobuf memory for the proper method (read, mmap, overlay).
-
-- videobuf_queue_is_busy()
-  Checks if a videobuf is streaming.
-
-- videobuf_queue_cancel()
-  Stops video handling.
-
-- videobuf_mmap_free()
-  frees mmap buffers.
-
-- videobuf_stop()
-  Stops video handling, ends mmap and frees mmap and other buffers.
-
-- V4L2 api functions. Those functions correspond to VIDIOC_foo ioctls:
-   videobuf_reqbufs(), videobuf_querybuf(), videobuf_qbuf(),
-   videobuf_dqbuf(), videobuf_streamon(), videobuf_streamoff().
-
-- V4L1 api function (corresponds to VIDIOCMBUF ioctl):
-   videobuf_cgmbuf()
-      This function is used to provide backward compatibility with V4L1
-      API.
-
-- Some help functions for read()/poll() operations:
-   videobuf_read_stream()
-      For continuous stream read()
-   videobuf_read_one()
-      For snapshot read()
-   videobuf_poll_stream()
-      polling help function
-
-The better way to understand it is to take a look at vivi driver. One
-of the main reasons for vivi is to be a videobuf usage example. the
-vivi_thread_tick() does the task that the IRQ callback would do on PCI
-drivers (or the irq callback on USB).
+The v4l2 core API provides a set of standard methods (called "videobuf")
+for dealing with video buffers. Those methods allow a driver to implement
+read(), mmap() and overlay() in a consistent way.  There are currently
+methods for using video buffers on devices that supports DMA with
+scatter/gather method (videobuf-dma-sg), DMA with linear access
+(videobuf-dma-contig), and vmalloced buffers, mostly used on USB drivers
+(videobuf-vmalloc).
+
+Please see Documentation/video4linux/videobuf for more information on how
+to use the videobuf layer.
diff --git a/Documentation/video4linux/videobuf b/Documentation/video4linux/videobuf
new file mode 100644
index 00000000000..17a1f9abf26
--- /dev/null
+++ b/Documentation/video4linux/videobuf
@@ -0,0 +1,360 @@
+An introduction to the videobuf layer
+Jonathan Corbet <corbet@lwn.net>
+Current as of 2.6.33
+
+The videobuf layer functions as a sort of glue layer between a V4L2 driver
+and user space.  It handles the allocation and management of buffers for
+the storage of video frames.  There is a set of functions which can be used
+to implement many of the standard POSIX I/O system calls, including read(),
+poll(), and, happily, mmap().  Another set of functions can be used to
+implement the bulk of the V4L2 ioctl() calls related to streaming I/O,
+including buffer allocation, queueing and dequeueing, and streaming
+control.  Using videobuf imposes a few design decisions on the driver
+author, but the payback comes in the form of reduced code in the driver and
+a consistent implementation of the V4L2 user-space API.
+
+Buffer types
+
+Not all video devices use the same kind of buffers.  In fact, there are (at
+least) three common variations:
+
+ - Buffers which are scattered in both the physical and (kernel) virtual
+   address spaces.  (Almost) all user-space buffers are like this, but it
+   makes great sense to allocate kernel-space buffers this way as well when
+   it is possible.  Unfortunately, it is not always possible; working with
+   this kind of buffer normally requires hardware which can do
+   scatter/gather DMA operations.
+
+ - Buffers which are physically scattered, but which are virtually
+   contiguous; buffers allocated with vmalloc(), in other words.  These
+   buffers are just as hard to use for DMA operations, but they can be
+   useful in situations where DMA is not available but virtually-contiguous
+   buffers are convenient.
+
+ - Buffers which are physically contiguous.  Allocation of this kind of
+   buffer can be unreliable on fragmented systems, but simpler DMA
+   controllers cannot deal with anything else.
+
+Videobuf can work with all three types of buffers, but the driver author
+must pick one at the outset and design the driver around that decision.
+
+[It's worth noting that there's a fourth kind of buffer: "overlay" buffers
+which are located within the system's video memory.  The overlay
+functionality is considered to be deprecated for most use, but it still
+shows up occasionally in system-on-chip drivers where the performance
+benefits merit the use of this technique.  Overlay buffers can be handled
+as a form of scattered buffer, but there are very few implementations in
+the kernel and a description of this technique is currently beyond the
+scope of this document.]
+
+Data structures, callbacks, and initialization
+
+Depending on which type of buffers are being used, the driver should
+include one of the following files:
+
+    <media/videobuf-dma-sg.h>		/* Physically scattered */
+    <media/videobuf-vmalloc.h>		/* vmalloc() buffers	*/
+    <media/videobuf-dma-contig.h>	/* Physically contiguous */
+
+The driver's data structure describing a V4L2 device should include a
+struct videobuf_queue instance for the management of the buffer queue,
+along with a list_head for the queue of available buffers.  There will also
+need to be an interrupt-safe spinlock which is used to protect (at least)
+the queue.
+
+The next step is to write four simple callbacks to help videobuf deal with
+the management of buffers:
+
+    struct videobuf_queue_ops {
+	int (*buf_setup)(struct videobuf_queue *q,
+			 unsigned int *count, unsigned int *size);
+	int (*buf_prepare)(struct videobuf_queue *q,
+			   struct videobuf_buffer *vb,
+			   enum v4l2_field field);
+	void (*buf_queue)(struct videobuf_queue *q,
+			  struct videobuf_buffer *vb);
+	void (*buf_release)(struct videobuf_queue *q,
+			    struct videobuf_buffer *vb);
+    };
+
+buf_setup() is called early in the I/O process, when streaming is being
+initiated; its purpose is to tell videobuf about the I/O stream.  The count
+parameter will be a suggested number of buffers to use; the driver should
+check it for rationality and adjust it if need be.  As a practical rule, a
+minimum of two buffers are needed for proper streaming, and there is
+usually a maximum (which cannot exceed 32) which makes sense for each
+device.  The size parameter should be set to the expected (maximum) size
+for each frame of data.
+
+Each buffer (in the form of a struct videobuf_buffer pointer) will be
+passed to buf_prepare(), which should set the buffer's size, width, height,
+and field fields properly.  If the buffer's state field is
+VIDEOBUF_NEEDS_INIT, the driver should pass it to:
+
+    int videobuf_iolock(struct videobuf_queue* q, struct videobuf_buffer *vb,
+			struct v4l2_framebuffer *fbuf);
+
+Among other things, this call will usually allocate memory for the buffer.
+Finally, the buf_prepare() function should set the buffer's state to
+VIDEOBUF_PREPARED.
+
+When a buffer is queued for I/O, it is passed to buf_queue(), which should
+put it onto the driver's list of available buffers and set its state to
+VIDEOBUF_QUEUED.  Note that this function is called with the queue spinlock
+held; if it tries to acquire it as well things will come to a screeching
+halt.  Yes, this is the voice of experience.  Note also that videobuf may
+wait on the first buffer in the queue; placing other buffers in front of it
+could again gum up the works.  So use list_add_tail() to enqueue buffers.
+
+Finally, buf_release() is called when a buffer is no longer intended to be
+used.  The driver should ensure that there is no I/O active on the buffer,
+then pass it to the appropriate free routine(s):
+
+    /* Scatter/gather drivers */
+    int videobuf_dma_unmap(struct videobuf_queue *q,
+			   struct videobuf_dmabuf *dma);
+    int videobuf_dma_free(struct videobuf_dmabuf *dma);
+
+    /* vmalloc drivers */
+    void videobuf_vmalloc_free (struct videobuf_buffer *buf);
+
+    /* Contiguous drivers */
+    void videobuf_dma_contig_free(struct videobuf_queue *q,
+				  struct videobuf_buffer *buf);
+
+One way to ensure that a buffer is no longer under I/O is to pass it to:
+
+    int videobuf_waiton(struct videobuf_buffer *vb, int non_blocking, int intr);
+
+Here, vb is the buffer, non_blocking indicates whether non-blocking I/O
+should be used (it should be zero in the buf_release() case), and intr
+controls whether an interruptible wait is used.
+
+File operations
+
+At this point, much of the work is done; much of the rest is slipping
+videobuf calls into the implementation of the other driver callbacks.  The
+first step is in the open() function, which must initialize the
+videobuf queue.  The function to use depends on the type of buffer used:
+
+    void videobuf_queue_sg_init(struct videobuf_queue *q,
+				struct videobuf_queue_ops *ops,
+				struct device *dev,
+				spinlock_t *irqlock,
+				enum v4l2_buf_type type,
+				enum v4l2_field field,
+				unsigned int msize,
+				void *priv);
+
+    void videobuf_queue_vmalloc_init(struct videobuf_queue *q,
+				struct videobuf_queue_ops *ops,
+				struct device *dev,
+				spinlock_t *irqlock,
+				enum v4l2_buf_type type,
+				enum v4l2_field field,
+				unsigned int msize,
+				void *priv);
+
+    void videobuf_queue_dma_contig_init(struct videobuf_queue *q,
+				       struct videobuf_queue_ops *ops,
+				       struct device *dev,
+				       spinlock_t *irqlock,
+				       enum v4l2_buf_type type,
+				       enum v4l2_field field,
+				       unsigned int msize,
+				       void *priv);
+
+In each case, the parameters are the same: q is the queue structure for the
+device, ops is the set of callbacks as described above, dev is the device
+structure for this video device, irqlock is an interrupt-safe spinlock to
+protect access to the data structures, type is the buffer type used by the
+device (cameras will use V4L2_BUF_TYPE_VIDEO_CAPTURE, for example), field
+describes which field is being captured (often V4L2_FIELD_NONE for
+progressive devices), msize is the size of any containing structure used
+around struct videobuf_buffer, and priv is a private data pointer which
+shows up in the priv_data field of struct videobuf_queue.  Note that these
+are void functions which, evidently, are immune to failure.
+
+V4L2 capture drivers can be written to support either of two APIs: the
+read() system call and the rather more complicated streaming mechanism.  As
+a general rule, it is necessary to support both to ensure that all
+applications have a chance of working with the device.  Videobuf makes it
+easy to do that with the same code.  To implement read(), the driver need
+only make a call to one of:
+
+    ssize_t videobuf_read_one(struct videobuf_queue *q,
+			      char __user *data, size_t count,
+			      loff_t *ppos, int nonblocking);
+
+    ssize_t videobuf_read_stream(struct videobuf_queue *q,
+				 char __user *data, size_t count,
+				 loff_t *ppos, int vbihack, int nonblocking);
+
+Either one of these functions will read frame data into data, returning the
+amount actually read; the difference is that videobuf_read_one() will only
+read a single frame, while videobuf_read_stream() will read multiple frames
+if they are needed to satisfy the count requested by the application.  A
+typical driver read() implementation will start the capture engine, call
+one of the above functions, then stop the engine before returning (though a
+smarter implementation might leave the engine running for a little while in
+anticipation of another read() call happening in the near future).
+
+The poll() function can usually be implemented with a direct call to:
+
+    unsigned int videobuf_poll_stream(struct file *file,
+				      struct videobuf_queue *q,
+				      poll_table *wait);
+
+Note that the actual wait queue eventually used will be the one associated
+with the first available buffer.
+
+When streaming I/O is done to kernel-space buffers, the driver must support
+the mmap() system call to enable user space to access the data.  In many
+V4L2 drivers, the often-complex mmap() implementation simplifies to a
+single call to:
+
+    int videobuf_mmap_mapper(struct videobuf_queue *q,
+			     struct vm_area_struct *vma);
+
+Everything else is handled by the videobuf code.
+
+The release() function requires two separate videobuf calls:
+
+    void videobuf_stop(struct videobuf_queue *q);
+    int videobuf_mmap_free(struct videobuf_queue *q);
+
+The call to videobuf_stop() terminates any I/O in progress - though it is
+still up to the driver to stop the capture engine.  The call to
+videobuf_mmap_free() will ensure that all buffers have been unmapped; if
+so, they will all be passed to the buf_release() callback.  If buffers
+remain mapped, videobuf_mmap_free() returns an error code instead.  The
+purpose is clearly to cause the closing of the file descriptor to fail if
+buffers are still mapped, but every driver in the 2.6.32 kernel cheerfully
+ignores its return value.
+
+ioctl() operations
+
+The V4L2 API includes a very long list of driver callbacks to respond to
+the many ioctl() commands made available to user space.  A number of these
+- those associated with streaming I/O - turn almost directly into videobuf
+calls.  The relevant helper functions are:
+
+    int videobuf_reqbufs(struct videobuf_queue *q,
+			 struct v4l2_requestbuffers *req);
+    int videobuf_querybuf(struct videobuf_queue *q, struct v4l2_buffer *b);
+    int videobuf_qbuf(struct videobuf_queue *q, struct v4l2_buffer *b);
+    int videobuf_dqbuf(struct videobuf_queue *q, struct v4l2_buffer *b,
+		       int nonblocking);
+    int videobuf_streamon(struct videobuf_queue *q);
+    int videobuf_streamoff(struct videobuf_queue *q);
+    int videobuf_cgmbuf(struct videobuf_queue *q, struct video_mbuf *mbuf,
+			int count);
+
+So, for example, a VIDIOC_REQBUFS call turns into a call to the driver's
+vidioc_reqbufs() callback which, in turn, usually only needs to locate the
+proper struct videobuf_queue pointer and pass it to videobuf_reqbufs().
+These support functions can replace a great deal of buffer management
+boilerplate in a lot of V4L2 drivers.
+
+The vidioc_streamon() and vidioc_streamoff() functions will be a bit more
+complex, of course, since they will also need to deal with starting and
+stopping the capture engine.  videobuf_cgmbuf(), called from the driver's
+vidiocgmbuf() function, only exists if the V4L1 compatibility module has
+been selected with CONFIG_VIDEO_V4L1_COMPAT, so its use must be surrounded
+with #ifdef directives.
+
+Buffer allocation
+
+Thus far, we have talked about buffers, but have not looked at how they are
+allocated.  The scatter/gather case is the most complex on this front.  For
+allocation, the driver can leave buffer allocation entirely up to the
+videobuf layer; in this case, buffers will be allocated as anonymous
+user-space pages and will be very scattered indeed.  If the application is
+using user-space buffers, no allocation is needed; the videobuf layer will
+take care of calling get_user_pages() and filling in the scatterlist array.
+
+If the driver needs to do its own memory allocation, it should be done in
+the vidioc_reqbufs() function, *after* calling videobuf_reqbufs().  The
+first step is a call to:
+
+    struct videobuf_dmabuf *videobuf_to_dma(struct videobuf_buffer *buf);
+
+The returned videobuf_dmabuf structure (defined in
+<media/videobuf-dma-sg.h>) includes a couple of relevant fields:
+
+    struct scatterlist  *sglist;
+    int                 sglen;
+
+The driver must allocate an appropriately-sized scatterlist array and
+populate it with pointers to the pieces of the allocated buffer; sglen
+should be set to the length of the array.
+
+Drivers using the vmalloc() method need not (and cannot) concern themselves
+with buffer allocation at all; videobuf will handle those details.  The
+same is normally true of contiguous-DMA drivers as well; videobuf will
+allocate the buffers (with dma_alloc_coherent()) when it sees fit.  That
+means that these drivers may be trying to do high-order allocations at any
+time, an operation which is not always guaranteed to work.  Some drivers
+play tricks by allocating DMA space at system boot time; videobuf does not
+currently play well with those drivers.
+
+As of 2.6.31, contiguous-DMA drivers can work with a user-supplied buffer,
+as long as that buffer is physically contiguous.  Normal user-space
+allocations will not meet that criterion, but buffers obtained from other
+kernel drivers, or those contained within huge pages, will work with these
+drivers.
+
+Filling the buffers
+
+The final part of a videobuf implementation has no direct callback - it's
+the portion of the code which actually puts frame data into the buffers,
+usually in response to interrupts from the device.  For all types of
+drivers, this process works approximately as follows:
+
+ - Obtain the next available buffer and make sure that somebody is actually
+   waiting for it.
+
+ - Get a pointer to the memory and put video data there.
+
+ - Mark the buffer as done and wake up the process waiting for it.
+
+Step (1) above is done by looking at the driver-managed list_head structure
+- the one which is filled in the buf_queue() callback.  Because starting
+the engine and enqueueing buffers are done in separate steps, it's possible
+for the engine to be running without any buffers available - in the
+vmalloc() case especially.  So the driver should be prepared for the list
+to be empty.  It is equally possible that nobody is yet interested in the
+buffer; the driver should not remove it from the list or fill it until a
+process is waiting on it.  That test can be done by examining the buffer's
+done field (a wait_queue_head_t structure) with waitqueue_active().
+
+A buffer's state should be set to VIDEOBUF_ACTIVE before being mapped for
+DMA; that ensures that the videobuf layer will not try to do anything with
+it while the device is transferring data.
+
+For scatter/gather drivers, the needed memory pointers will be found in the
+scatterlist structure described above.  Drivers using the vmalloc() method
+can get a memory pointer with:
+
+    void *videobuf_to_vmalloc(struct videobuf_buffer *buf);
+
+For contiguous DMA drivers, the function to use is:
+
+    dma_addr_t videobuf_to_dma_contig(struct videobuf_buffer *buf);
+
+The contiguous DMA API goes out of its way to hide the kernel-space address
+of the DMA buffer from drivers.
+
+The final step is to set the size field of the relevant videobuf_buffer
+structure to the actual size of the captured image, set state to
+VIDEOBUF_DONE, then call wake_up() on the done queue.  At this point, the
+buffer is owned by the videobuf layer and the driver should not touch it
+again.
+
+Developers who are interested in more information can go into the relevant
+header files; there are a few low-level functions declared there which have
+not been talked about here.  Also worthwhile is the vivi driver
+(drivers/media/video/vivi.c), which is maintained as an example of how V4L2
+drivers should be written.  Vivi only uses the vmalloc() API, but it's good
+enough to get started with.  Note also that all of these calls are exported
+GPL-only, so they will not be available to non-GPL kernel modules.
diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt
index b37300edf27..07375e73981 100644
--- a/Documentation/vm/slub.txt
+++ b/Documentation/vm/slub.txt
@@ -41,6 +41,7 @@ Possible debug options are
 	P		Poisoning (object and padding)
 	U		User tracking (free and alloc)
 	T		Trace (please only use on single slabs)
+	A		Toggle failslab filter mark for the cache
 	O		Switch debugging off for caches that would have
 			caused higher minimum slab orders
 	-		Switch all debugging off (useful if the kernel is
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 29a6ff8bc7d..7fbbaf85f5b 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -166,19 +166,13 @@ NUMA
 
   numa=noacpi   Don't parse the SRAT table for NUMA setup
 
-  numa=fake=CMDLINE
-		If a number, fakes CMDLINE nodes and ignores NUMA setup of the
-		actual machine.  Otherwise, system memory is configured
-		depending on the sizes and coefficients listed.  For example:
-			numa=fake=2*512,1024,4*256,*128
-		gives two 512M nodes, a 1024M node, four 256M nodes, and the
-		rest split into 128M chunks.  If the last character of CMDLINE
-		is a *, the remaining memory is divided up equally among its
-		coefficient:
-			numa=fake=2*512,2*
-		gives two 512M nodes and the rest split into two nodes.
-		Otherwise, the remaining system RAM is allocated to an
-		additional node.
+  numa=fake=<size>[MG]
+		If given as a memory unit, fills all system RAM with nodes of
+		size interleaved over physical nodes.
+
+  numa=fake=<N>
+		If given as an integer, fills all system RAM with N fake nodes
+		interleaved over physical nodes.
 
 ACPI