Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound:
  ALSA: hda - Revert the check of NO_PRESENCE pincfg default bit
  ALSA: hda - Fix a regression for DMA-position check with CA0110
  ALSA: hda - Fix silent output regression with ALC861
  ALSA: control: remove compilation warning on 32-bit
  ALSA: ua101: fix crash when unplugging
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 1f89424..65bbd26 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -272,6 +272,8 @@
 	- how to get printk format specifiers right
 prio_tree.txt
 	- info on radix-priority-search-tree use for indexing vmas.
+ramoops.txt
+	- documentation of the ramoops oops/panic logging module.
 rbtree.txt
 	- info on what red-black trees are and what they are for.
 robust-futex-ABI.txt
diff --git a/Documentation/ABI/removed/o2cb b/Documentation/ABI/removed/o2cb
index 7f5daa4..20c91ad 100644
--- a/Documentation/ABI/removed/o2cb
+++ b/Documentation/ABI/removed/o2cb
@@ -1,6 +1,6 @@
 What:		/sys/o2cb symlink
 Date:		May 2011
-KernelVersion:	2.6.40
+KernelVersion:	3.0
 Contact:	ocfs2-devel@oss.oracle.com
 Description:	This is a symlink: /sys/o2cb to /sys/fs/o2cb. The symlink is
 		removed when new versions of ocfs2-tools which know to look
diff --git a/Documentation/ABI/removed/raw1394 b/Documentation/ABI/removed/raw1394
index 490aa1e..ec333e6 100644
--- a/Documentation/ABI/removed/raw1394
+++ b/Documentation/ABI/removed/raw1394
@@ -5,7 +5,7 @@
 	/dev/raw1394 was a character device file that allowed low-level
 	access to FireWire buses.  Its major drawbacks were its inability
 	to implement sensible device security policies, and its low level
-	of abstraction that required userspace clients do duplicate much
+	of abstraction that required userspace clients to duplicate much
 	of the kernel's ieee1394 core functionality.
 	Replaced by /dev/fw*, i.e. the <linux/firewire-cdev.h> ABI of
 	firewire-core.
diff --git a/Documentation/ABI/testing/debugfs-ideapad b/Documentation/ABI/testing/debugfs-ideapad
new file mode 100644
index 0000000..7079c0b
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-ideapad
@@ -0,0 +1,19 @@
+What:		/sys/kernel/debug/ideapad/cfg
+Date:		Sep 2011
+KernelVersion:	3.2
+Contact:	Ike Panhc <ike.pan@canonical.com>
+Description:
+
+cfg shows the return value of _CFG method in VPC2004 device. It tells machine
+capability and what graphic component within the machine.
+
+
+What:		/sys/kernel/debug/ideapad/status
+Date:		Sep 2011
+KernelVersion:	3.2
+Contact:	Ike Panhc <ike.pan@canonical.com>
+Description:
+
+status shows infos we can read and tells its meaning and value.
+
+
diff --git a/Documentation/ABI/testing/evm b/Documentation/ABI/testing/evm
new file mode 100644
index 0000000..8374d45
--- /dev/null
+++ b/Documentation/ABI/testing/evm
@@ -0,0 +1,23 @@
+What:		security/evm
+Date:		March 2011
+Contact:	Mimi Zohar <zohar@us.ibm.com>
+Description:
+		EVM protects a file's security extended attributes(xattrs)
+		against integrity attacks. The initial method maintains an
+		HMAC-sha1 value across the extended attributes, storing the
+		value as the extended attribute 'security.evm'.
+
+		EVM depends on the Kernel Key Retention System to provide it
+		with a trusted/encrypted key for the HMAC-sha1 operation.
+		The key is loaded onto the root's keyring using keyctl.  Until
+		EVM receives notification that the key has been successfully
+		loaded onto the keyring (echo 1 > <securityfs>/evm), EVM
+		can not create or validate the 'security.evm' xattr, but
+		returns INTEGRITY_UNKNOWN.  Loading the key and signaling EVM
+		should be done as early as possible.  Normally this is done
+		in the initramfs, which has already been measured as part
+		of the trusted boot.  For more information on creating and
+		loading existing trusted/encrypted keys, refer to:
+		Documentation/keys-trusted-encrypted.txt.  (A sample dracut
+		patch, which loads the trusted/encrypted key and enables
+		EVM, is available from http://linux-ima.sourceforge.net/#EVM.)
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index c1eb41c..2b5d561 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -206,3 +206,16 @@
 		when a discarded area is read the discard_zeroes_data
 		parameter will be set to one. Otherwise it will be 0 and
 		the result of reading a discarded area is undefined.
+What:		/sys/block/<disk>/alias
+Date:		Aug 2011
+Contact:	Nao Nishijima <nao.nishijima.xt@hitachi.com>
+Description:
+		A raw device name of a disk does not always point a same disk
+		each boot-up time. Therefore, users have to use persistent
+		device names, which udev creates when the kernel finds a disk,
+		instead of raw device name. However, kernel doesn't show those
+		persistent names on its messages (e.g. dmesg).
+		This file can store an alias of the disk and it would be
+		appeared in kernel messages if it is set. A disk can have an
+		alias which length is up to 255bytes. Users can use alphabets,
+		numbers, "-" and "_" in alias name. This file is writeonce.
diff --git a/Documentation/ABI/testing/sysfs-bus-bcma b/Documentation/ABI/testing/sysfs-bus-bcma
index 06b62ba..721b4ae 100644
--- a/Documentation/ABI/testing/sysfs-bus-bcma
+++ b/Documentation/ABI/testing/sysfs-bus-bcma
@@ -1,6 +1,6 @@
 What:		/sys/bus/bcma/devices/.../manuf
 Date:		May 2011
-KernelVersion:	2.6.40
+KernelVersion:	3.0
 Contact:	Rafał Miłecki <zajec5@gmail.com>
 Description:
 		Each BCMA core has it's manufacturer id. See
@@ -8,7 +8,7 @@
 
 What:		/sys/bus/bcma/devices/.../id
 Date:		May 2011
-KernelVersion:	2.6.40
+KernelVersion:	3.0
 Contact:	Rafał Miłecki <zajec5@gmail.com>
 Description:
 		There are a few types of BCMA cores, they can be identified by
@@ -16,7 +16,7 @@
 
 What:		/sys/bus/bcma/devices/.../rev
 Date:		May 2011
-KernelVersion:	2.6.40
+KernelVersion:	3.0
 Contact:	Rafał Miłecki <zajec5@gmail.com>
 Description:
 		BCMA cores of the same type can still slightly differ depending
@@ -24,7 +24,7 @@
 
 What:		/sys/bus/bcma/devices/.../class
 Date:		May 2011
-KernelVersion:	2.6.40
+KernelVersion:	3.0
 Contact:	Rafał Miłecki <zajec5@gmail.com>
 Description:
 		Each BCMA core is identified by few fields, including class it
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss
index f5bb0a3..53d99ed 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss
+++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss
@@ -71,3 +71,10 @@
 		a dump device, as kdump requires resetting the device in order
 		to work reliably.
 
+Where:		/sys/bus/pci/devices/<dev>/ccissX/transport_mode
+Date:		July 2011
+Kernel Version:	3.0
+Contact:	iss_storagedev@hp.com
+Description:	Value of "simple" indicates that the controller has been placed
+		in "simple mode". Value of "performant" indicates that the
+		controller has been placed in "performant mode".
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-drivers-ehci_hcd b/Documentation/ABI/testing/sysfs-bus-pci-drivers-ehci_hcd
new file mode 100644
index 0000000..60c60fa
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-pci-drivers-ehci_hcd
@@ -0,0 +1,46 @@
+What:		/sys/bus/pci/drivers/ehci_hcd/.../companion
+		/sys/bus/usb/devices/usbN/../companion
+Date:		January 2007
+KernelVersion:	2.6.21
+Contact:	Alan Stern <stern@rowland.harvard.edu>
+Description:
+		PCI-based EHCI USB controllers (i.e., high-speed USB-2.0
+		controllers) are often implemented along with a set of
+		"companion" full/low-speed USB-1.1 controllers.  When a
+		high-speed device is plugged in, the connection is routed
+		to the EHCI controller; when a full- or low-speed device
+		is plugged in, the connection is routed to the companion
+		controller.
+
+		Sometimes you want to force a high-speed device to connect
+		at full speed, which can be accomplished by forcing the
+		connection to be routed to the companion controller.
+		That's what this file does.  Writing a port number to the
+		file causes connections on that port to be routed to the
+		companion controller, and writing the negative of a port
+		number returns the port to normal operation.
+
+		For example: To force the high-speed device attached to
+		port 4 on bus 2 to run at full speed:
+
+			echo 4 >/sys/bus/usb/devices/usb2/../companion
+
+		To return the port to high-speed operation:
+
+			echo -4 >/sys/bus/usb/devices/usb2/../companion
+
+		Reading the file gives the list of ports currently forced
+		to the companion controller.
+
+		Note: Some EHCI controllers do not have companions; they
+		may contain an internal "transaction translator" or they
+		may be attached directly to a "rate-matching hub".  This
+		mechanism will not work with such controllers.  Also, it
+		cannot be used to force a port on a high-speed hub to
+		connect at full speed.
+
+		Note: When this file was first added, it appeared in a
+		different sysfs directory.  The location given above is
+		correct for 2.6.35 (and probably several earlier kernel
+		versions as well).
+
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb
index 294aa86..e647378 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb
+++ b/Documentation/ABI/testing/sysfs-bus-usb
@@ -142,3 +142,18 @@
 		such devices.
 Users:
 		usb_modeswitch
+
+What:		/sys/bus/usb/devices/.../power/usb2_hardware_lpm
+Date:		September 2011
+Contact:	Andiry Xu <andiry.xu@amd.com>
+Description:
+		If CONFIG_USB_SUSPEND is set and a USB 2.0 lpm-capable device
+		is plugged in to a xHCI host which support link PM, it will
+		perform a LPM test; if the test is passed and host supports
+		USB2 hardware LPM (xHCI 1.0 feature), USB2 hardware LPM will
+		be enabled for the device and the USB device directory will
+		contain a file named power/usb2_hardware_lpm.  The file holds
+		a string value (enable or disable) indicating whether or not
+		USB2 hardware LPM is enabled for the device. Developer can
+		write y/Y/1 or n/N/0 to the file to enable/disable the
+		feature.
diff --git a/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870 b/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870
index aa11dbd..4a9c545 100644
--- a/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870
+++ b/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870
@@ -4,8 +4,8 @@
 What:		/sys/class/backlight/<backlight>/l3_office_max
 What:		/sys/class/backlight/<backlight>/l4_indoor_max
 What:		/sys/class/backlight/<backlight>/l5_dark_max
-Date:		Mai 2011
-KernelVersion:	2.6.40
+Date:		May 2011
+KernelVersion:	3.0
 Contact:	device-drivers-devel@blackfin.uclinux.org
 Description:
 		Control the maximum brightness for <ambient light zone>
@@ -18,8 +18,8 @@
 What:		/sys/class/backlight/<backlight>/l3_office_dim
 What:		/sys/class/backlight/<backlight>/l4_indoor_dim
 What:		/sys/class/backlight/<backlight>/l5_dark_dim
-Date:		Mai 2011
-KernelVersion:	2.6.40
+Date:		May 2011
+KernelVersion:	3.0
 Contact:	device-drivers-devel@blackfin.uclinux.org
 Description:
 		Control the dim brightness for <ambient light zone>
@@ -29,8 +29,8 @@
 		this <ambient light zone>.
 
 What:		/sys/class/backlight/<backlight>/ambient_light_level
-Date:		Mai 2011
-KernelVersion:	2.6.40
+Date:		May 2011
+KernelVersion:	3.0
 Contact:	device-drivers-devel@blackfin.uclinux.org
 Description:
 		Get conversion value of the light sensor.
@@ -39,8 +39,8 @@
 		8000 (max ambient brightness)
 
 What:		/sys/class/backlight/<backlight>/ambient_light_zone
-Date:		Mai 2011
-KernelVersion:	2.6.40
+Date:		May 2011
+KernelVersion:	3.0
 Contact:	device-drivers-devel@blackfin.uclinux.org
 Description:
 		Get/Set current ambient light zone. Reading returns
diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq
new file mode 100644
index 0000000..23d78b5
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-devfreq
@@ -0,0 +1,52 @@
+What:		/sys/class/devfreq/.../
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		Provide a place in sysfs for the devfreq objects.
+		This allows accessing various devfreq specific variables.
+		The name of devfreq object denoted as ... is same as the
+		name of device using devfreq.
+
+What:		/sys/class/devfreq/.../governor
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../governor shows the name of the
+		governor used by the corresponding devfreq object.
+
+What:		/sys/class/devfreq/.../cur_freq
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../cur_freq shows the current
+		frequency of the corresponding devfreq object.
+
+What:		/sys/class/devfreq/.../central_polling
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../central_polling shows whether
+		the devfreq ojbect is using devfreq-provided central
+		polling mechanism or not.
+
+What:		/sys/class/devfreq/.../polling_interval
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../polling_interval shows and sets
+		the requested polling interval of the corresponding devfreq
+		object. The values are represented in ms. If the value is
+		less than 1 jiffy, it is considered to be 0, which means
+		no polling. This value is meaningless if the governor is
+		not polling; thus. If the governor is not using
+		devfreq-provided central polling
+		(/sys/class/devfreq/.../central_polling is 0), this value
+		may be useless.
+
+What:		/sys/class/devfreq/.../userspace/set_freq
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../userspace/set_freq shows and
+		sets the requested frequency for the devfreq object if
+		userspace governor is in effect.
diff --git a/Documentation/ABI/testing/sysfs-class-net-mesh b/Documentation/ABI/testing/sysfs-class-net-mesh
index 748fe17..b020014 100644
--- a/Documentation/ABI/testing/sysfs-class-net-mesh
+++ b/Documentation/ABI/testing/sysfs-class-net-mesh
@@ -22,6 +22,14 @@
                 mesh will be fragmented or silently discarded if the
                 packet size exceeds the outgoing interface MTU.
 
+What:		/sys/class/net/<mesh_iface>/mesh/ap_isolation
+Date:		May 2011
+Contact:	Antonio Quartulli <ordex@autistici.org>
+Description:
+		Indicates whether the data traffic going from a
+		wireless client to another wireless client will be
+		silently dropped.
+
 What:           /sys/class/net/<mesh_iface>/mesh/gw_bandwidth
 Date:           October 2010
 Contact:        Marek Lindner <lindner_marek@yahoo.de>
diff --git a/Documentation/ABI/testing/sysfs-class-scsi_host b/Documentation/ABI/testing/sysfs-class-scsi_host
new file mode 100644
index 0000000..29a4f89
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-scsi_host
@@ -0,0 +1,13 @@
+What:		/sys/class/scsi_host/hostX/isci_id
+Date:		June 2011
+Contact:	Dave Jiang <dave.jiang@intel.com>
+Description:
+		This file contains the enumerated host ID for the Intel
+		SCU controller. The Intel(R) C600 Series Chipset SATA/SAS
+		Storage Control Unit embeds up to two 4-port controllers in
+		a single PCI device.  The controllers are enumerated in order
+		which usually means the lowest number scsi_host corresponds
+		with the first controller, but this association is not
+		guaranteed.  The 'isci_id' attribute unambiguously identifies
+		the controller index: '0' for the first controller,
+		'1' for the second.
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff b/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff
new file mode 100644
index 0000000..9aec8ef
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff
@@ -0,0 +1,7 @@
+What:		/sys/module/hid_logitech/drivers/hid:logitech/<dev>/range.
+Date:		July 2011
+KernelVersion:	3.2
+Contact:	Michal Malý <madcatxster@gmail.com>
+Description:	Display minimum, maximum and current range of the steering
+		wheel. Writing a value within min and max boundaries sets the
+		range of the wheel.
diff --git a/Documentation/ABI/testing/sysfs-driver-wacom b/Documentation/ABI/testing/sysfs-driver-wacom
new file mode 100644
index 0000000..82d4df1
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-wacom
@@ -0,0 +1,72 @@
+What:		/sys/class/hidraw/hidraw*/device/speed
+Date:		April 2010
+Kernel Version:	2.6.35
+Contact:	linux-bluetooth@vger.kernel.org
+Description:
+		The /sys/class/hidraw/hidraw*/device/speed file controls
+		reporting speed of Wacom bluetooth tablet. Reading from
+		this file returns 1 if tablet reports in high speed mode
+		or 0 otherwise. Writing to this file one of these values
+		switches reporting speed.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<cfg>.<intf>/wacom_led/led
+Date:		August 2011
+Contact:	linux-input@vger.kernel.org
+Description:
+		Attribute group for control of the status LEDs and the OLEDs.
+		This attribute group is only available for Intuos 4 M, L,
+		and XL (with LEDs and OLEDs) and Cintiq 21UX2 (LEDs only).
+		Therefore its presence implicitly signifies the presence of
+		said LEDs and OLEDs on the tablet device.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<cfg>.<intf>/wacom_led/status0_luminance
+Date:		August 2011
+Contact:	linux-input@vger.kernel.org
+Description:
+		Writing to this file sets the status LED luminance (1..127)
+		when the stylus does not touch the tablet surface, and no
+		button is pressed on the stylus. This luminance level is
+		normally lower than the level when a button is pressed.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<cfg>.<intf>/wacom_led/status1_luminance
+Date:		August 2011
+Contact:	linux-input@vger.kernel.org
+Description:
+		Writing to this file sets the status LED luminance (1..127)
+		when the stylus touches the tablet surface, or any button is
+		pressed on the stylus.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<cfg>.<intf>/wacom_led/status_led0_select
+Date:		August 2011
+Contact:	linux-input@vger.kernel.org
+Description:
+		Writing to this file sets which one of the four (for Intuos 4)
+		or of the right four (for Cintiq 21UX2) status LEDs is active (0..3).
+		The other three LEDs on the same side are always inactive.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<cfg>.<intf>/wacom_led/status_led1_select
+Date:		September 2011
+Contact:	linux-input@vger.kernel.org
+Description:
+		Writing to this file sets which one of the left four (for Cintiq 21UX2)
+		status LEDs is active (0..3). The other three LEDs on the left are always
+		inactive.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<cfg>.<intf>/wacom_led/buttons_luminance
+Date:		August 2011
+Contact:	linux-input@vger.kernel.org
+Description:
+		Writing to this file sets the overall luminance level (0..15)
+		of all eight button OLED displays.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<cfg>.<intf>/wacom_led/button<n>_rawimg
+Date:		August 2011
+Contact:	linux-input@vger.kernel.org
+Description:
+		When writing a 1024 byte raw image in Wacom Intuos 4
+		interleaving format to the file, the image shows up on Button N
+		of the device. The image is a 64x32 pixel 4-bit gray image. The
+		1024 byte binary is split up into 16x 64 byte chunks. Each 64
+		byte chunk encodes the image data for two consecutive lines on
+		the display. The low nibble of each byte contains the first
+		line, and the high nibble contains the second line.
diff --git a/Documentation/ABI/testing/sysfs-platform-ideapad-laptop b/Documentation/ABI/testing/sysfs-platform-ideapad-laptop
index ff53183..814b013 100644
--- a/Documentation/ABI/testing/sysfs-platform-ideapad-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-ideapad-laptop
@@ -5,19 +5,4 @@
 Description:
 		Control the power of camera module. 1 means on, 0 means off.
 
-What:		/sys/devices/platform/ideapad/cfg
-Date:		Jun 2011
-KernelVersion:	3.1
-Contact:	"Ike Panhc <ike.pan@canonical.com>"
-Description:
-		Ideapad capability bits.
-		Bit 8-10: 1 - Intel graphic only
-		          2 - ATI graphic only
-		          3 - Nvidia graphic only
-		          4 - Intel and ATI graphic
-		          5 - Intel and Nvidia graphic
-		Bit 16: Bluetooth exist (1 for exist)
-		Bit 17: 3G exist (1 for exist)
-		Bit 18: Wifi exist (1 for exist)
-		Bit 19: Camera exist (1 for exist)
 
diff --git a/Documentation/ABI/testing/sysfs-wacom b/Documentation/ABI/testing/sysfs-wacom
deleted file mode 100644
index 1517976..0000000
--- a/Documentation/ABI/testing/sysfs-wacom
+++ /dev/null
@@ -1,10 +0,0 @@
-What:		/sys/class/hidraw/hidraw*/device/speed
-Date:		April 2010
-Kernel Version:	2.6.35
-Contact:	linux-bluetooth@vger.kernel.org
-Description:
-		The /sys/class/hidraw/hidraw*/device/speed file controls
-		reporting speed of wacom bluetooth tablet. Reading from
-		this file returns 1 if tablet reports in high speed mode
-		or 0 otherwise. Writing to this file one of these values
-		switches reporting speed.
diff --git a/Documentation/CodingStyle b/Documentation/CodingStyle
index c940239..2b90d32 100644
--- a/Documentation/CodingStyle
+++ b/Documentation/CodingStyle
@@ -166,8 +166,8 @@
 else
 	do_that();
 
-This does not apply if one branch of a conditional statement is a single
-statement. Use braces in both branches.
+This does not apply if only one branch of a conditional statement is a single
+statement; in the latter case use braces in both branches:
 
 if (condition) {
 	do_this();
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index fe23269..66bd97a 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -50,6 +50,13 @@
 implementation may choose to ignore flags that affect the location of
 the returned memory, like GFP_DMA).
 
+void *
+dma_zalloc_coherent(struct device *dev, size_t size,
+			     dma_addr_t *dma_handle, gfp_t flag)
+
+Wraps dma_alloc_coherent() and also zeroes the returned memory if the
+allocation attempt succeeded.
+
 void
 dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
 			   dma_addr_t dma_handle)
diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl
index 445289c..2014155 100644
--- a/Documentation/DocBook/80211.tmpl
+++ b/Documentation/DocBook/80211.tmpl
@@ -433,8 +433,18 @@
           Insert notes about VLAN interfaces with hw crypto here or
           in the hw crypto chapter.
         </para>
+      <section id="ps-client">
+        <title>support for powersaving clients</title>
+!Pinclude/net/mac80211.h AP support for powersaving clients
+      </section>
 !Finclude/net/mac80211.h ieee80211_get_buffered_bc
 !Finclude/net/mac80211.h ieee80211_beacon_get
+!Finclude/net/mac80211.h ieee80211_sta_eosp_irqsafe
+!Finclude/net/mac80211.h ieee80211_frame_release_type
+!Finclude/net/mac80211.h ieee80211_sta_ps_transition
+!Finclude/net/mac80211.h ieee80211_sta_ps_transition_ni
+!Finclude/net/mac80211.h ieee80211_sta_set_buffered
+!Finclude/net/mac80211.h ieee80211_sta_block_awake
       </chapter>
 
       <chapter id="multi-iface">
@@ -460,7 +470,6 @@
 !Finclude/net/mac80211.h sta_notify_cmd
 !Finclude/net/mac80211.h ieee80211_find_sta
 !Finclude/net/mac80211.h ieee80211_find_sta_by_ifaddr
-!Finclude/net/mac80211.h ieee80211_sta_block_awake
       </chapter>
 
       <chapter id="hardware-scan-offload">
diff --git a/Documentation/DocBook/media/dvb/dvbproperty.xml b/Documentation/DocBook/media/dvb/dvbproperty.xml
index 207e1a5..3bc8a61 100644
--- a/Documentation/DocBook/media/dvb/dvbproperty.xml
+++ b/Documentation/DocBook/media/dvb/dvbproperty.xml
@@ -352,6 +352,7 @@
 	SYS_CMMB,
 	SYS_DAB,
 	SYS_DVBT2,
+	SYS_TURBO,
 } fe_delivery_system_t;
 </programlisting>
 		</section>
@@ -809,6 +810,8 @@
 			<listitem><para><link linkend="DTV-INVERSION"><constant>DTV_INVERSION</constant></link></para></listitem>
 			<listitem><para><link linkend="DTV-SYMBOL-RATE"><constant>DTV_SYMBOL_RATE</constant></link></para></listitem>
 			<listitem><para><link linkend="DTV-INNER-FEC"><constant>DTV_INNER_FEC</constant></link></para></listitem>
+			<listitem><para><link linkend="DTV-VOLTAGE"><constant>DTV_VOLTAGE</constant></link></para></listitem>
+			<listitem><para><link linkend="DTV-TONE"><constant>DTV_TONE</constant></link></para></listitem>
 		</itemizedlist>
 		<para>Future implementations might add those two missing parameters:</para>
 		<itemizedlist mark='opencircle'>
@@ -818,25 +821,18 @@
 	</section>
 	<section id="dvbs2-params">
 		<title>DVB-S2 delivery system</title>
-		<para>The following parameters are valid for DVB-S2:</para>
+		<para>In addition to all parameters valid for DVB-S, DVB-S2 supports the following parameters:</para>
 		<itemizedlist mark='opencircle'>
-			<listitem><para><link linkend="DTV-API-VERSION"><constant>DTV_API_VERSION</constant></link></para></listitem>
-			<listitem><para><link linkend="DTV-DELIVERY-SYSTEM"><constant>DTV_DELIVERY_SYSTEM</constant></link></para></listitem>
-			<listitem><para><link linkend="DTV-TUNE"><constant>DTV_TUNE</constant></link></para></listitem>
-			<listitem><para><link linkend="DTV-CLEAR"><constant>DTV_CLEAR</constant></link></para></listitem>
-			<listitem><para><link linkend="DTV-FREQUENCY"><constant>DTV_FREQUENCY</constant></link></para></listitem>
-			<listitem><para><link linkend="DTV-INVERSION"><constant>DTV_INVERSION</constant></link></para></listitem>
-			<listitem><para><link linkend="DTV-SYMBOL-RATE"><constant>DTV_SYMBOL_RATE</constant></link></para></listitem>
-			<listitem><para><link linkend="DTV-INNER-FEC"><constant>DTV_INNER_FEC</constant></link></para></listitem>
-			<listitem><para><link linkend="DTV-VOLTAGE"><constant>DTV_VOLTAGE</constant></link></para></listitem>
-			<listitem><para><link linkend="DTV-TONE"><constant>DTV_TONE</constant></link></para></listitem>
+			<listitem><para><link linkend="DTV-MODULATION"><constant>DTV_MODULATION</constant></link></para></listitem>
 			<listitem><para><link linkend="DTV-PILOT"><constant>DTV_PILOT</constant></link></para></listitem>
 			<listitem><para><link linkend="DTV-ROLLOFF"><constant>DTV_ROLLOFF</constant></link></para></listitem>
 		</itemizedlist>
-		<para>Future implementations might add those two missing parameters:</para>
+	</section>
+	<section id="turbo-params">
+		<title>Turbo code delivery system</title>
+		<para>In addition to all parameters valid for DVB-S, turbo code supports the following parameters:</para>
 		<itemizedlist mark='opencircle'>
-			<listitem><para><link linkend="DTV-DISEQC-MASTER"><constant>DTV_DISEQC_MASTER</constant></link></para></listitem>
-			<listitem><para><link linkend="DTV-DISEQC-SLAVE-REPLY"><constant>DTV_DISEQC_SLAVE_REPLY</constant></link></para></listitem>
+			<listitem><para><link linkend="DTV-MODULATION"><constant>DTV_MODULATION</constant></link></para></listitem>
 		</itemizedlist>
 	</section>
 	<section id="isdbs-params">
diff --git a/Documentation/DocBook/media/dvb/intro.xml b/Documentation/DocBook/media/dvb/intro.xml
index c75dc7c..170064a 100644
--- a/Documentation/DocBook/media/dvb/intro.xml
+++ b/Documentation/DocBook/media/dvb/intro.xml
@@ -205,7 +205,7 @@
 additional include file <emphasis
 role="tt">linux/dvb/version.h</emphasis> exists, which defines the
 constant <emphasis role="tt">DVB_API_VERSION</emphasis>. This document
-describes <emphasis role="tt">DVB_API_VERSION&#x00A0;3</emphasis>.
+describes <emphasis role="tt">DVB_API_VERSION 5.4</emphasis>.
 </para>
 
 </section>
diff --git a/Documentation/DocBook/media/v4l/compat.xml b/Documentation/DocBook/media/v4l/compat.xml
index ce1004a..b68698f 100644
--- a/Documentation/DocBook/media/v4l/compat.xml
+++ b/Documentation/DocBook/media/v4l/compat.xml
@@ -2370,6 +2370,14 @@
         </listitem>
       </orderedlist>
     </section>
+    <section>
+      <title>V4L2 in Linux 3.2</title>
+      <orderedlist>
+        <listitem>
+	  <para>V4L2_CTRL_FLAG_VOLATILE was added to signal volatile controls to userspace.</para>
+        </listitem>
+      </orderedlist>
+    </section>
 
     <section id="other">
       <title>Relation of V4L2 to other Linux multimedia APIs</title>
@@ -2478,6 +2486,9 @@
         <listitem>
 	  <para>Flash API. <xref linkend="flash-controls" /></para>
         </listitem>
+        <listitem>
+	  <para>&VIDIOC-CREATE-BUFS; and &VIDIOC-PREPARE-BUF; ioctls.</para>
+        </listitem>
       </itemizedlist>
     </section>
 
diff --git a/Documentation/DocBook/media/v4l/controls.xml b/Documentation/DocBook/media/v4l/controls.xml
index 8516401..3bc5ee8 100644
--- a/Documentation/DocBook/media/v4l/controls.xml
+++ b/Documentation/DocBook/media/v4l/controls.xml
@@ -232,8 +232,9 @@
 	    <entry>Enables a power line frequency filter to avoid
 flicker. Possible values for <constant>enum v4l2_power_line_frequency</constant> are:
 <constant>V4L2_CID_POWER_LINE_FREQUENCY_DISABLED</constant> (0),
-<constant>V4L2_CID_POWER_LINE_FREQUENCY_50HZ</constant> (1) and
-<constant>V4L2_CID_POWER_LINE_FREQUENCY_60HZ</constant> (2).</entry>
+<constant>V4L2_CID_POWER_LINE_FREQUENCY_50HZ</constant> (1),
+<constant>V4L2_CID_POWER_LINE_FREQUENCY_60HZ</constant> (2) and
+<constant>V4L2_CID_POWER_LINE_FREQUENCY_AUTO</constant> (3).</entry>
 	  </row>
 	  <row>
 	    <entry><constant>V4L2_CID_HUE_AUTO</constant></entry>
@@ -1455,7 +1456,7 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-h264-vui-sar-idc">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_VUI_SAR_IDC</constant>&nbsp;</entry>
 		<entry>enum&nbsp;v4l2_mpeg_video_h264_vui_sar_idc</entry>
 	      </row>
@@ -1561,7 +1562,7 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-h264-level">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_LEVEL</constant>&nbsp;</entry>
 		<entry>enum&nbsp;v4l2_mpeg_video_h264_level</entry>
 	      </row>
@@ -1641,7 +1642,7 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-mpeg4-level">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_MPEG4_LEVEL</constant>&nbsp;</entry>
 		<entry>enum&nbsp;v4l2_mpeg_video_mpeg4_level</entry>
 	      </row>
@@ -1689,9 +1690,9 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-h264-profile">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_PROFILE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_h264_profile</entry>
+		<entry>enum&nbsp;v4l2_mpeg_video_h264_profile</entry>
 	      </row>
 	      <row><entry spanname="descr">The profile information for H264.
 Applicable to the H264 encoder.
@@ -1774,9 +1775,9 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-mpeg4-profile">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_MPEG4_PROFILE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_mpeg4_profile</entry>
+		<entry>enum&nbsp;v4l2_mpeg_video_mpeg4_profile</entry>
 	      </row>
 	      <row><entry spanname="descr">The profile information for MPEG4.
 Applicable to the MPEG4 encoder.
@@ -1820,9 +1821,9 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-multi-slice-mode">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MODE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_multi_slice_mode</entry>
+		<entry>enum&nbsp;v4l2_mpeg_video_multi_slice_mode</entry>
 	      </row>
 	      <row><entry spanname="descr">Determines how the encoder should handle division of frame into slices.
 Applicable to the encoder.
@@ -1868,9 +1869,9 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-h264-loop-filter-mode">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_MODE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_h264_loop_filter_mode</entry>
+		<entry>enum&nbsp;v4l2_mpeg_video_h264_loop_filter_mode</entry>
 	      </row>
 	      <row><entry spanname="descr">Loop filter mode for H264 encoder.
 Possible values are:</entry>
@@ -1913,9 +1914,9 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-h264-entropy-mode">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_ENTROPY_MODE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_h264_symbol_mode</entry>
+		<entry>enum&nbsp;v4l2_mpeg_video_h264_entropy_mode</entry>
 	      </row>
 	      <row><entry spanname="descr">Entropy coding mode for H264 - CABAC/CAVALC.
 Applicable to the H264 encoder.
@@ -2140,9 +2141,9 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-header-mode">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_HEADER_MODE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_header_mode</entry>
+		<entry>enum&nbsp;v4l2_mpeg_video_header_mode</entry>
 	      </row>
 	      <row><entry spanname="descr">Determines whether the header is returned as the first buffer or is
 it returned together with the first frame. Applicable to encoders.
@@ -2320,9 +2321,9 @@
 Applicable to the H264 encoder.</entry>
 	      </row>
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-mfc51-video-frame-skip-mode">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_MFC51_VIDEO_FRAME_SKIP_MODE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_mfc51_frame_skip_mode</entry>
+		<entry>enum&nbsp;v4l2_mpeg_mfc51_video_frame_skip_mode</entry>
 	      </row>
 	      <row><entry spanname="descr">
 Indicates in what conditions the encoder should skip frames. If encoding a frame would cause the encoded stream to be larger then
@@ -2361,9 +2362,9 @@
 </entry>
 	      </row>
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-mfc51-video-force-frame-type">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_MFC51_VIDEO_FORCE_FRAME_TYPE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_mfc51_force_frame_type</entry>
+		<entry>enum&nbsp;v4l2_mpeg_mfc51_video_force_frame_type</entry>
 	      </row>
 	      <row><entry spanname="descr">Force a frame type for the next queued buffer. Applicable to encoders.
 Possible values are:</entry>
diff --git a/Documentation/DocBook/media/v4l/dev-subdev.xml b/Documentation/DocBook/media/v4l/dev-subdev.xml
index 05c8fef..0916a73 100644
--- a/Documentation/DocBook/media/v4l/dev-subdev.xml
+++ b/Documentation/DocBook/media/v4l/dev-subdev.xml
@@ -266,7 +266,7 @@
 
       <para>When satisfied with the try results, applications can set the active
       formats by setting the <structfield>which</structfield> argument to
-      <constant>V4L2_SUBDEV_FORMAT_TRY</constant>. Active formats are changed
+      <constant>V4L2_SUBDEV_FORMAT_ACTIVE</constant>. Active formats are changed
       exactly as try formats by drivers. To avoid modifying the hardware state
       during format negotiation, applications should negotiate try formats first
       and then modify the active settings using the try formats returned during
diff --git a/Documentation/DocBook/media/v4l/io.xml b/Documentation/DocBook/media/v4l/io.xml
index c57d1ec..3f47df1 100644
--- a/Documentation/DocBook/media/v4l/io.xml
+++ b/Documentation/DocBook/media/v4l/io.xml
@@ -927,6 +927,33 @@
 Applications set or clear this flag before calling the
 <constant>VIDIOC_QBUF</constant> ioctl.</entry>
 	  </row>
+	  <row>
+	    <entry><constant>V4L2_BUF_FLAG_PREPARED</constant></entry>
+	    <entry>0x0400</entry>
+	    <entry>The buffer has been prepared for I/O and can be queued by the
+application. Drivers set or clear this flag when the
+<link linkend="vidioc-querybuf">VIDIOC_QUERYBUF</link>, <link
+	  linkend="vidioc-qbuf">VIDIOC_PREPARE_BUF</link>, <link
+	  linkend="vidioc-qbuf">VIDIOC_QBUF</link> or <link
+	  linkend="vidioc-qbuf">VIDIOC_DQBUF</link> ioctl is called.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>V4L2_BUF_FLAG_NO_CACHE_INVALIDATE</constant></entry>
+	    <entry>0x0400</entry>
+	    <entry>Caches do not have to be invalidated for this buffer.
+Typically applications shall use this flag if the data captured in the buffer
+is not going to be touched by the CPU, instead the buffer will, probably, be
+passed on to a DMA-capable hardware unit for further processing or output.
+</entry>
+	  </row>
+	  <row>
+	    <entry><constant>V4L2_BUF_FLAG_NO_CACHE_CLEAN</constant></entry>
+	    <entry>0x0800</entry>
+	    <entry>Caches do not have to be cleaned for this buffer.
+Typically applications shall use this flag for output buffers if the data
+in this buffer has not been created by the CPU but by some DMA-capable unit,
+in which case caches have not been used.</entry>
+	  </row>
 	</tbody>
       </tgroup>
     </table>
diff --git a/Documentation/DocBook/media/v4l/v4l2.xml b/Documentation/DocBook/media/v4l/v4l2.xml
index 0d05e87..2ab365c 100644
--- a/Documentation/DocBook/media/v4l/v4l2.xml
+++ b/Documentation/DocBook/media/v4l/v4l2.xml
@@ -128,6 +128,13 @@
 applications. -->
 
       <revision>
+	<revnumber>3.2</revnumber>
+	<date>2011-08-26</date>
+	<authorinitials>hv</authorinitials>
+	<revremark>Added V4L2_CTRL_FLAG_VOLATILE.</revremark>
+      </revision>
+
+      <revision>
 	<revnumber>3.1</revnumber>
 	<date>2011-06-27</date>
 	<authorinitials>mcc, po, hv</authorinitials>
@@ -410,7 +417,7 @@
 </partinfo>
 
 <title>Video for Linux Two API Specification</title>
- <subtitle>Revision 3.1</subtitle>
+ <subtitle>Revision 3.2</subtitle>
 
   <chapter id="common">
     &sub-common;
@@ -462,6 +469,7 @@
     &sub-close;
     &sub-ioctl;
     <!-- All ioctls go here. -->
+    &sub-create-bufs;
     &sub-cropcap;
     &sub-dbg-g-chip-ident;
     &sub-dbg-g-register;
@@ -504,6 +512,7 @@
     &sub-queryctrl;
     &sub-query-dv-preset;
     &sub-querystd;
+    &sub-prepare-buf;
     &sub-reqbufs;
     &sub-s-hw-freq-seek;
     &sub-streamon;
diff --git a/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml b/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml
new file mode 100644
index 0000000..73ae8a6
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml
@@ -0,0 +1,139 @@
+<refentry id="vidioc-create-bufs">
+  <refmeta>
+    <refentrytitle>ioctl VIDIOC_CREATE_BUFS</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>VIDIOC_CREATE_BUFS</refname>
+    <refpurpose>Create buffers for Memory Mapped or User Pointer I/O</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>struct v4l2_create_buffers *<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>&fd;</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>VIDIOC_CREATE_BUFS</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>This ioctl is used to create buffers for <link linkend="mmap">memory
+mapped</link> or <link linkend="userp">user pointer</link>
+I/O. It can be used as an alternative or in addition to the
+<constant>VIDIOC_REQBUFS</constant> ioctl, when a tighter control over buffers
+is required. This ioctl can be called multiple times to create buffers of
+different sizes.</para>
+
+    <para>To allocate device buffers applications initialize relevant fields of
+the <structname>v4l2_create_buffers</structname> structure. They set the
+<structfield>type</structfield> field in the
+<structname>v4l2_format</structname> structure, embedded in this
+structure, to the respective stream or buffer type.
+<structfield>count</structfield> must be set to the number of required buffers.
+<structfield>memory</structfield> specifies the required I/O method. The
+<structfield>format</structfield> field shall typically be filled in using
+either the <constant>VIDIOC_TRY_FMT</constant> or
+<constant>VIDIOC_G_FMT</constant> ioctl(). Additionally, applications can adjust
+<structfield>sizeimage</structfield> fields to fit their specific needs. The
+<structfield>reserved</structfield> array must be zeroed.</para>
+
+    <para>When the ioctl is called with a pointer to this structure the driver
+will attempt to allocate up to the requested number of buffers and store the
+actual number allocated and the starting index in the
+<structfield>count</structfield> and the <structfield>index</structfield> fields
+respectively. On return <structfield>count</structfield> can be smaller than
+the number requested. The driver may also increase buffer sizes if required,
+however, it will not update <structfield>sizeimage</structfield> field values.
+The user has to use <constant>VIDIOC_QUERYBUF</constant> to retrieve that
+information.</para>
+
+    <table pgwide="1" frame="none" id="v4l2-create-buffers">
+      <title>struct <structname>v4l2_create_buffers</structname></title>
+      <tgroup cols="3">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>index</structfield></entry>
+	    <entry>The starting buffer index, returned by the driver.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>count</structfield></entry>
+	    <entry>The number of buffers requested or granted.</entry>
+	  </row>
+	  <row>
+	    <entry>&v4l2-memory;</entry>
+	    <entry><structfield>memory</structfield></entry>
+	    <entry>Applications set this field to
+<constant>V4L2_MEMORY_MMAP</constant> or
+<constant>V4L2_MEMORY_USERPTR</constant>.</entry>
+	  </row>
+	  <row>
+	    <entry>&v4l2-format;</entry>
+	    <entry><structfield>format</structfield></entry>
+	    <entry>Filled in by the application, preserved by the driver.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved</structfield>[8]</entry>
+	    <entry>A place holder for future extensions.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+
+    <variablelist>
+      <varlistentry>
+	<term><errorcode>ENOMEM</errorcode></term>
+	<listitem>
+	  <para>No memory to allocate buffers for <link linkend="mmap">memory
+mapped</link> I/O.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><errorcode>EINVAL</errorcode></term>
+	<listitem>
+	  <para>The buffer type (<structfield>type</structfield> field) or the
+requested I/O method (<structfield>memory</structfield>) is not
+supported.</para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/vidioc-dqevent.xml b/Documentation/DocBook/media/v4l/vidioc-dqevent.xml
index 7769642..e8714aa 100644
--- a/Documentation/DocBook/media/v4l/vidioc-dqevent.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-dqevent.xml
@@ -88,6 +88,12 @@
 	  </row>
 	  <row>
 	    <entry></entry>
+	    <entry>&v4l2-event-frame-sync;</entry>
+            <entry><structfield>frame</structfield></entry>
+	    <entry>Event data for event V4L2_EVENT_FRAME_SYNC.</entry>
+	  </row>
+	  <row>
+	    <entry></entry>
 	    <entry>__u8</entry>
             <entry><structfield>data</structfield>[64]</entry>
 	    <entry>Event data. Defined by the event type. The union
@@ -135,6 +141,129 @@
       </tgroup>
     </table>
 
+    <table frame="none" pgwide="1" id="v4l2-event-vsync">
+      <title>struct <structname>v4l2_event_vsync</structname></title>
+      <tgroup cols="3">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>field</structfield></entry>
+	    <entry>The upcoming field. See &v4l2-field;.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table frame="none" pgwide="1" id="v4l2-event-ctrl">
+      <title>struct <structname>v4l2_event_ctrl</structname></title>
+      <tgroup cols="4">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>changes</structfield></entry>
+	    <entry></entry>
+	    <entry>A bitmask that tells what has changed. See <xref linkend="changes-flags" />.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>type</structfield></entry>
+	    <entry></entry>
+	    <entry>The type of the control. See &v4l2-ctrl-type;.</entry>
+	  </row>
+	  <row>
+	    <entry>union (anonymous)</entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry></entry>
+	  </row>
+	  <row>
+	    <entry></entry>
+	    <entry>__s32</entry>
+	    <entry><structfield>value</structfield></entry>
+	    <entry>The 32-bit value of the control for 32-bit control types.
+		This is 0 for string controls since the value of a string
+		cannot be passed using &VIDIOC-DQEVENT;.</entry>
+	  </row>
+	  <row>
+	    <entry></entry>
+	    <entry>__s64</entry>
+	    <entry><structfield>value64</structfield></entry>
+	    <entry>The 64-bit value of the control for 64-bit control types.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>flags</structfield></entry>
+	    <entry></entry>
+	    <entry>The control flags. See <xref linkend="control-flags" />.</entry>
+	  </row>
+	  <row>
+	    <entry>__s32</entry>
+	    <entry><structfield>minimum</structfield></entry>
+	    <entry></entry>
+	    <entry>The minimum value of the control. See &v4l2-queryctrl;.</entry>
+	  </row>
+	  <row>
+	    <entry>__s32</entry>
+	    <entry><structfield>maximum</structfield></entry>
+	    <entry></entry>
+	    <entry>The maximum value of the control. See &v4l2-queryctrl;.</entry>
+	  </row>
+	  <row>
+	    <entry>__s32</entry>
+	    <entry><structfield>step</structfield></entry>
+	    <entry></entry>
+	    <entry>The step value of the control. See &v4l2-queryctrl;.</entry>
+	  </row>
+	  <row>
+	    <entry>__s32</entry>
+	    <entry><structfield>default_value</structfield></entry>
+	    <entry></entry>
+	    <entry>The default value value of the control. See &v4l2-queryctrl;.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table frame="none" pgwide="1" id="v4l2-event-frame-sync">
+      <title>struct <structname>v4l2_event_frame_sync</structname></title>
+      <tgroup cols="3">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>frame_sequence</structfield></entry>
+	    <entry>
+	      The sequence number of the frame being received.
+	    </entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="changes-flags">
+      <title>Changes</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>V4L2_EVENT_CTRL_CH_VALUE</constant></entry>
+	    <entry>0x0001</entry>
+	    <entry>This control event was triggered because the value of the control
+		changed. Special case: if a button control is pressed, then this
+		event is sent as well, even though there is not explicit value
+		associated with a button control.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>V4L2_EVENT_CTRL_CH_FLAGS</constant></entry>
+	    <entry>0x0002</entry>
+	    <entry>This control event was triggered because the control flags
+		changed.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
   </refsect1>
   <refsect1>
     &return-value;
diff --git a/Documentation/DocBook/media/v4l/vidioc-prepare-buf.xml b/Documentation/DocBook/media/v4l/vidioc-prepare-buf.xml
new file mode 100644
index 0000000..7bde698
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/vidioc-prepare-buf.xml
@@ -0,0 +1,88 @@
+<refentry id="vidioc-prepare-buf">
+  <refmeta>
+    <refentrytitle>ioctl VIDIOC_PREPARE_BUF</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>VIDIOC_PREPARE_BUF</refname>
+    <refpurpose>Prepare a buffer for I/O</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>struct v4l2_buffer *<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>&fd;</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>VIDIOC_PREPARE_BUF</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>Applications can optionally call the
+<constant>VIDIOC_PREPARE_BUF</constant> ioctl to pass ownership of the buffer
+to the driver before actually enqueuing it, using the
+<constant>VIDIOC_QBUF</constant> ioctl, and to prepare it for future I/O.
+Such preparations may include cache invalidation or cleaning. Performing them
+in advance saves time during the actual I/O. In case such cache operations are
+not required, the application can use one of
+<constant>V4L2_BUF_FLAG_NO_CACHE_INVALIDATE</constant> and
+<constant>V4L2_BUF_FLAG_NO_CACHE_CLEAN</constant> flags to skip the respective
+step.</para>
+
+    <para>The <structname>v4l2_buffer</structname> structure is
+specified in <xref linkend="buffer" />.</para>
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+
+    <variablelist>
+      <varlistentry>
+	<term><errorcode>EBUSY</errorcode></term>
+	<listitem>
+	  <para>File I/O is in progress.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><errorcode>EINVAL</errorcode></term>
+	<listitem>
+	  <para>The buffer <structfield>type</structfield> is not
+supported, or the <structfield>index</structfield> is out of bounds,
+or no buffers have been allocated yet, or the
+<structfield>userptr</structfield> or
+<structfield>length</structfield> are invalid.</para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/vidioc-queryctrl.xml b/Documentation/DocBook/media/v4l/vidioc-queryctrl.xml
index 677ea64..0ac0057 100644
--- a/Documentation/DocBook/media/v4l/vidioc-queryctrl.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-queryctrl.xml
@@ -406,6 +406,15 @@
 writing a value will cause the device to carry out a given action
 (&eg; motor control) but no meaningful value can be returned.</entry>
 	  </row>
+	  <row>
+	    <entry><constant>V4L2_CTRL_FLAG_VOLATILE</constant></entry>
+	    <entry>0x0080</entry>
+	    <entry>This control is volatile, which means that the value of the control
+changes continuously. A typical example would be the current gain value if the device
+is in auto-gain mode. In such a case the hardware calculates the gain value based on
+the lighting conditions which can change over time. Note that setting a new value for
+a volatile control will have no effect. The new value will just be ignored.</entry>
+	  </row>
 	</tbody>
       </tgroup>
     </table>
diff --git a/Documentation/DocBook/media/v4l/vidioc-subscribe-event.xml b/Documentation/DocBook/media/v4l/vidioc-subscribe-event.xml
index 69c0d8a..5c70b61 100644
--- a/Documentation/DocBook/media/v4l/vidioc-subscribe-event.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-subscribe-event.xml
@@ -139,6 +139,22 @@
 	    </entry>
 	  </row>
 	  <row>
+	    <entry><constant>V4L2_EVENT_FRAME_SYNC</constant></entry>
+	    <entry>4</entry>
+	    <entry>
+	      <para>Triggered immediately when the reception of a
+	      frame has begun. This event has a
+	      &v4l2-event-frame-sync; associated with it.</para>
+
+	      <para>If the hardware needs to be stopped in the case of a
+	      buffer underrun it might not be able to generate this event.
+	      In such cases the <structfield>frame_sequence</structfield>
+	      field in &v4l2-event-frame-sync; will not be incremented. This
+	      causes two consecutive frame sequence numbers to have n times
+	      frame interval in between them.</para>
+	    </entry>
+	  </row>
+	  <row>
 	    <entry><constant>V4L2_EVENT_PRIVATE_START</constant></entry>
 	    <entry>0x08000000</entry>
 	    <entry>Base event number for driver-private events.</entry>
@@ -183,113 +199,6 @@
       </tgroup>
     </table>
 
-    <table frame="none" pgwide="1" id="v4l2-event-vsync">
-      <title>struct <structname>v4l2_event_vsync</structname></title>
-      <tgroup cols="3">
-	&cs-str;
-	<tbody valign="top">
-	  <row>
-	    <entry>__u8</entry>
-	    <entry><structfield>field</structfield></entry>
-	    <entry>The upcoming field. See &v4l2-field;.</entry>
-	  </row>
-	</tbody>
-      </tgroup>
-    </table>
-
-    <table frame="none" pgwide="1" id="v4l2-event-ctrl">
-      <title>struct <structname>v4l2_event_ctrl</structname></title>
-      <tgroup cols="4">
-	&cs-str;
-	<tbody valign="top">
-	  <row>
-	    <entry>__u32</entry>
-	    <entry><structfield>changes</structfield></entry>
-	    <entry></entry>
-	    <entry>A bitmask that tells what has changed. See <xref linkend="changes-flags" />.</entry>
-	  </row>
-	  <row>
-	    <entry>__u32</entry>
-	    <entry><structfield>type</structfield></entry>
-	    <entry></entry>
-	    <entry>The type of the control. See &v4l2-ctrl-type;.</entry>
-	  </row>
-	  <row>
-	    <entry>union (anonymous)</entry>
-	    <entry></entry>
-	    <entry></entry>
-	    <entry></entry>
-	  </row>
-	  <row>
-	    <entry></entry>
-	    <entry>__s32</entry>
-	    <entry><structfield>value</structfield></entry>
-	    <entry>The 32-bit value of the control for 32-bit control types.
-		This is 0 for string controls since the value of a string
-		cannot be passed using &VIDIOC-DQEVENT;.</entry>
-	  </row>
-	  <row>
-	    <entry></entry>
-	    <entry>__s64</entry>
-	    <entry><structfield>value64</structfield></entry>
-	    <entry>The 64-bit value of the control for 64-bit control types.</entry>
-	  </row>
-	  <row>
-	    <entry>__u32</entry>
-	    <entry><structfield>flags</structfield></entry>
-	    <entry></entry>
-	    <entry>The control flags. See <xref linkend="control-flags" />.</entry>
-	  </row>
-	  <row>
-	    <entry>__s32</entry>
-	    <entry><structfield>minimum</structfield></entry>
-	    <entry></entry>
-	    <entry>The minimum value of the control. See &v4l2-queryctrl;.</entry>
-	  </row>
-	  <row>
-	    <entry>__s32</entry>
-	    <entry><structfield>maximum</structfield></entry>
-	    <entry></entry>
-	    <entry>The maximum value of the control. See &v4l2-queryctrl;.</entry>
-	  </row>
-	  <row>
-	    <entry>__s32</entry>
-	    <entry><structfield>step</structfield></entry>
-	    <entry></entry>
-	    <entry>The step value of the control. See &v4l2-queryctrl;.</entry>
-	  </row>
-	  <row>
-	    <entry>__s32</entry>
-	    <entry><structfield>default_value</structfield></entry>
-	    <entry></entry>
-	    <entry>The default value value of the control. See &v4l2-queryctrl;.</entry>
-	  </row>
-	</tbody>
-      </tgroup>
-    </table>
-
-    <table pgwide="1" frame="none" id="changes-flags">
-      <title>Changes</title>
-      <tgroup cols="3">
-	&cs-def;
-	<tbody valign="top">
-	  <row>
-	    <entry><constant>V4L2_EVENT_CTRL_CH_VALUE</constant></entry>
-	    <entry>0x0001</entry>
-	    <entry>This control event was triggered because the value of the control
-		changed. Special case: if a button control is pressed, then this
-		event is sent as well, even though there is not explicit value
-		associated with a button control.</entry>
-	  </row>
-	  <row>
-	    <entry><constant>V4L2_EVENT_CTRL_CH_FLAGS</constant></entry>
-	    <entry>0x0002</entry>
-	    <entry>This control event was triggered because the control flags
-		changed.</entry>
-	  </row>
-	</tbody>
-      </tgroup>
-    </table>
   </refsect1>
   <refsect1>
     &return-value;
diff --git a/Documentation/DocBook/uio-howto.tmpl b/Documentation/DocBook/uio-howto.tmpl
index 7c4b514d..54883de 100644
--- a/Documentation/DocBook/uio-howto.tmpl
+++ b/Documentation/DocBook/uio-howto.tmpl
@@ -529,7 +529,7 @@
 </para></listitem>
 
 <listitem><para>
-<varname>unsigned long addr</varname>: Required if the mapping is used.
+<varname>phys_addr_t addr</varname>: Required if the mapping is used.
 Fill in the address of your memory block. This address is the one that
 appears in sysfs.
 </para></listitem>
diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt
index 3f5e0b0..53e6fca 100644
--- a/Documentation/PCI/MSI-HOWTO.txt
+++ b/Documentation/PCI/MSI-HOWTO.txt
@@ -45,7 +45,7 @@
 bridges).  In order to ensure that all the data has arrived in memory,
 the interrupt handler must read a register on the device which raised
 the interrupt.  PCI transaction ordering rules require that all the data
-arrives in memory before the value can be returned from the register.
+arrive in memory before the value may be returned from the register.
 Using MSIs avoids this problem as the interrupt-generating write cannot
 pass the data writes, so by the time the interrupt is raised, the driver
 knows that all the data has arrived in memory.
@@ -86,13 +86,13 @@
 
 int pci_enable_msi(struct pci_dev *dev)
 
-A successful call will allocate ONE interrupt to the device, regardless
-of how many MSIs the device supports.  The device will be switched from
+A successful call allocates ONE interrupt to the device, regardless
+of how many MSIs the device supports.  The device is switched from
 pin-based interrupt mode to MSI mode.  The dev->irq number is changed
-to a new number which represents the message signaled interrupt.
-This function should be called before the driver calls request_irq()
-since enabling MSIs disables the pin-based IRQ and the driver will not
-receive interrupts on the old interrupt.
+to a new number which represents the message signaled interrupt;
+consequently, this function should be called before the driver calls
+request_irq(), because an MSI is delivered via a vector that is
+different from the vector of a pin-based interrupt.
 
 4.2.2 pci_enable_msi_block
 
@@ -111,20 +111,20 @@
 
 If this function returns a negative number, it indicates an error and
 the driver should not attempt to request any more MSI interrupts for
-this device.  If this function returns a positive number, it will be
-less than 'count' and indicate the number of interrupts that could have
-been allocated.  In neither case will the irq value have been
-updated, nor will the device have been switched into MSI mode.
+this device.  If this function returns a positive number, it is
+less than 'count' and indicates the number of interrupts that could have
+been allocated.  In neither case is the irq value updated or the device
+switched into MSI mode.
 
 The device driver must decide what action to take if
-pci_enable_msi_block() returns a value less than the number asked for.
-Some devices can make use of fewer interrupts than the maximum they
-request; in this case the driver should call pci_enable_msi_block()
+pci_enable_msi_block() returns a value less than the number requested.
+For instance, the driver could still make use of fewer interrupts;
+in this case the driver should call pci_enable_msi_block()
 again.  Note that it is not guaranteed to succeed, even when the
 'count' has been reduced to the value returned from a previous call to
 pci_enable_msi_block().  This is because there are multiple constraints
 on the number of vectors that can be allocated; pci_enable_msi_block()
-will return as soon as it finds any constraint that doesn't allow the
+returns as soon as it finds any constraint that doesn't allow the
 call to succeed.
 
 4.2.3 pci_disable_msi
@@ -137,10 +137,10 @@
 interrupt(s).  The interrupt may subsequently be assigned to another
 device, so drivers should not cache the value of dev->irq.
 
-A device driver must always call free_irq() on the interrupt(s)
-for which it has called request_irq() before calling this function.
-Failure to do so will result in a BUG_ON(), the device will be left with
-MSI enabled and will leak its vector.
+Before calling this function, a device driver must always call free_irq()
+on any interrupt for which it previously called request_irq().
+Failure to do so results in a BUG_ON(), leaving the device with
+MSI enabled and thus leaking its vector.
 
 4.3 Using MSI-X
 
@@ -155,10 +155,10 @@
 };
 
 This allows for the device to use these interrupts in a sparse fashion;
-for example it could use interrupts 3 and 1027 and allocate only a
+for example, it could use interrupts 3 and 1027 and yet allocate only a
 two-element array.  The driver is expected to fill in the 'entry' value
-in each element of the array to indicate which entries it wants the kernel
-to assign interrupts for.  It is invalid to fill in two entries with the
+in each element of the array to indicate for which entries the kernel
+should assign interrupts; it is invalid to fill in two entries with the
 same number.
 
 4.3.1 pci_enable_msix
@@ -168,10 +168,11 @@
 Calling this function asks the PCI subsystem to allocate 'nvec' MSIs.
 The 'entries' argument is a pointer to an array of msix_entry structs
 which should be at least 'nvec' entries in size.  On success, the
-function will return 0 and the device will have been switched into
-MSI-X interrupt mode.  The 'vector' elements in each entry will have
-been filled in with the interrupt number.  The driver should then call
-request_irq() for each 'vector' that it decides to use.
+device is switched into MSI-X mode and the function returns 0.
+The 'vector' member in each entry is populated with the interrupt number;
+the driver should then call request_irq() for each 'vector' that it
+decides to use.  The device driver is responsible for keeping track of the
+interrupts assigned to the MSI-X vectors so it can free them again later.
 
 If this function returns a negative number, it indicates an error and
 the driver should not attempt to allocate any more MSI-X interrupts for
@@ -181,16 +182,14 @@
 
 This function, in contrast with pci_enable_msi(), does not adjust
 dev->irq.  The device will not generate interrupts for this interrupt
-number once MSI-X is enabled.  The device driver is responsible for
-keeping track of the interrupts assigned to the MSI-X vectors so it can
-free them again later.
+number once MSI-X is enabled.
 
 Device drivers should normally call this function once per device
 during the initialization phase.
 
-It is ideal if drivers can cope with a variable number of MSI-X interrupts,
+It is ideal if drivers can cope with a variable number of MSI-X interrupts;
 there are many reasons why the platform may not be able to provide the
-exact number a driver asks for.
+exact number that a driver asks for.
 
 A request loop to achieve that might look like:
 
@@ -212,15 +211,15 @@
 
 void pci_disable_msix(struct pci_dev *dev)
 
-This API should be used to undo the effect of pci_enable_msix().  It frees
+This function should be used to undo the effect of pci_enable_msix().  It frees
 the previously allocated message signaled interrupts.  The interrupts may
 subsequently be assigned to another device, so drivers should not cache
 the value of the 'vector' elements over a call to pci_disable_msix().
 
-A device driver must always call free_irq() on the interrupt(s)
-for which it has called request_irq() before calling this function.
-Failure to do so will result in a BUG_ON(), the device will be left with
-MSI enabled and will leak its vector.
+Before calling this function, a device driver must always call free_irq()
+on any interrupt for which it previously called request_irq().
+Failure to do so results in a BUG_ON(), leaving the device with
+MSI-X enabled and thus leaking its vector.
 
 4.3.3 The MSI-X Table
 
@@ -232,10 +231,10 @@
 4.4 Handling devices implementing both MSI and MSI-X capabilities
 
 If a device implements both MSI and MSI-X capabilities, it can
-run in either MSI mode or MSI-X mode but not both simultaneously.
+run in either MSI mode or MSI-X mode, but not both simultaneously.
 This is a requirement of the PCI spec, and it is enforced by the
 PCI layer.  Calling pci_enable_msi() when MSI-X is already enabled or
-pci_enable_msix() when MSI is already enabled will result in an error.
+pci_enable_msix() when MSI is already enabled results in an error.
 If a device driver wishes to switch between MSI and MSI-X at runtime,
 it must first quiesce the device, then switch it back to pin-interrupt
 mode, before calling pci_enable_msi() or pci_enable_msix() and resuming
@@ -251,7 +250,7 @@
 above, MSI-X supports any number of interrupts between 1 and 2048.
 In constrast, MSI is restricted to a maximum of 32 interrupts (and
 must be a power of two).  In addition, the MSI interrupt vectors must
-be allocated consecutively, so the system may not be able to allocate
+be allocated consecutively, so the system might not be able to allocate
 as many vectors for MSI as it could for MSI-X.  On some platforms, MSI
 interrupts must all be targeted at the same set of CPUs whereas MSI-X
 interrupts can all be targeted at different CPUs.
@@ -281,7 +280,7 @@
 
 Using 'lspci -v' (as root) may show some devices with "MSI", "Message
 Signalled Interrupts" or "MSI-X" capabilities.  Each of these capabilities
-has an 'Enable' flag which will be followed with either "+" (enabled)
+has an 'Enable' flag which is followed with either "+" (enabled)
 or "-" (disabled).
 
 
@@ -298,7 +297,7 @@
 
 Some host chipsets simply don't support MSIs properly.  If we're
 lucky, the manufacturer knows this and has indicated it in the ACPI
-FADT table.  In this case, Linux will automatically disable MSIs.
+FADT table.  In this case, Linux automatically disables MSIs.
 Some boards don't include this information in the table and so we have
 to detect them ourselves.  The complete list of these is found near the
 quirk_disable_all_msi() function in drivers/pci/quirks.c.
@@ -317,7 +316,7 @@
 PCI configuration space (especially the Hypertransport chipsets such
 as the nVidia nForce and Serverworks HT2000).  As with host chipsets,
 Linux mostly knows about them and automatically enables MSIs if it can.
-If you have a bridge which Linux doesn't yet know about, you can enable
+If you have a bridge unknown to Linux, you can enable
 MSIs in configuration space using whatever method you know works, then
 enable MSIs on that bridge by doing:
 
@@ -327,7 +326,7 @@
 0000:00:0e.0).
 
 To disable MSIs, echo 0 instead of 1.  Changing this value should be
-done with caution as it can break interrupt handling for all devices
+done with caution as it could break interrupt handling for all devices
 below this bridge.
 
 Again, please notify linux-pci@vger.kernel.org of any bridges that need
@@ -336,7 +335,7 @@
 5.3. Disabling MSIs on a single device
 
 Some devices are known to have faulty MSI implementations.  Usually this
-is handled in the individual device driver but occasionally it's necessary
+is handled in the individual device driver, but occasionally it's necessary
 to handle this with a quirk.  Some drivers have an option to disable use
 of MSI.  While this is a convenient workaround for the driver author,
 it is not good practise, and should not be emulated.
@@ -350,7 +349,7 @@
 have enabled CONFIG_PCI_MSI.
 
 Then, 'lspci -t' gives the list of bridges above a device.  Reading
-/sys/bus/pci/devices/*/msi_bus will tell you whether MSI are enabled (1)
+/sys/bus/pci/devices/*/msi_bus will tell you whether MSIs are enabled (1)
 or disabled (0).  If 0 is found in any of the msi_bus files belonging
 to bridges between the PCI root and the device, MSIs are disabled.
 
diff --git a/Documentation/PCI/pci.txt b/Documentation/PCI/pci.txt
index 6148d40..aa09e54 100644
--- a/Documentation/PCI/pci.txt
+++ b/Documentation/PCI/pci.txt
@@ -314,7 +314,7 @@
 as the PCI "bus address" might have been remapped to a "host physical"
 address by the arch/chip-set specific kernel support.
 
-See Documentation/IO-mapping.txt for how to access device registers
+See Documentation/io-mapping.txt for how to access device registers
 or device memory.
 
 The device driver needs to call pci_request_region() to verify
diff --git a/Documentation/RCU/NMI-RCU.txt b/Documentation/RCU/NMI-RCU.txt
index bf82851..687777f 100644
--- a/Documentation/RCU/NMI-RCU.txt
+++ b/Documentation/RCU/NMI-RCU.txt
@@ -95,7 +95,7 @@
 to free up the handler's data as soon as synchronize_sched() returns.
 
 Important note: for this to work, the architecture in question must
-invoke irq_enter() and irq_exit() on NMI entry and exit, respectively.
+invoke nmi_enter() and nmi_exit() on NMI entry and exit, respectively.
 
 
 Answer to Quick Quiz
diff --git a/Documentation/RCU/lockdep-splat.txt b/Documentation/RCU/lockdep-splat.txt
new file mode 100644
index 0000000..bf90611
--- /dev/null
+++ b/Documentation/RCU/lockdep-splat.txt
@@ -0,0 +1,110 @@
+Lockdep-RCU was added to the Linux kernel in early 2010
+(http://lwn.net/Articles/371986/).  This facility checks for some common
+misuses of the RCU API, most notably using one of the rcu_dereference()
+family to access an RCU-protected pointer without the proper protection.
+When such misuse is detected, an lockdep-RCU splat is emitted.
+
+The usual cause of a lockdep-RCU slat is someone accessing an
+RCU-protected data structure without either (1) being in the right kind of
+RCU read-side critical section or (2) holding the right update-side lock.
+This problem can therefore be serious: it might result in random memory
+overwriting or worse.  There can of course be false positives, this
+being the real world and all that.
+
+So let's look at an example RCU lockdep splat from 3.0-rc5, one that
+has long since been fixed:
+
+===============================
+[ INFO: suspicious RCU usage. ]
+-------------------------------
+block/cfq-iosched.c:2776 suspicious rcu_dereference_protected() usage!
+
+other info that might help us debug this:
+
+
+rcu_scheduler_active = 1, debug_locks = 0
+3 locks held by scsi_scan_6/1552:
+ #0:  (&shost->scan_mutex){+.+.+.}, at: [<ffffffff8145efca>]
+scsi_scan_host_selected+0x5a/0x150
+ #1:  (&eq->sysfs_lock){+.+...}, at: [<ffffffff812a5032>]
+elevator_exit+0x22/0x60
+ #2:  (&(&q->__queue_lock)->rlock){-.-...}, at: [<ffffffff812b6233>]
+cfq_exit_queue+0x43/0x190
+
+stack backtrace:
+Pid: 1552, comm: scsi_scan_6 Not tainted 3.0.0-rc5 #17
+Call Trace:
+ [<ffffffff810abb9b>] lockdep_rcu_dereference+0xbb/0xc0
+ [<ffffffff812b6139>] __cfq_exit_single_io_context+0xe9/0x120
+ [<ffffffff812b626c>] cfq_exit_queue+0x7c/0x190
+ [<ffffffff812a5046>] elevator_exit+0x36/0x60
+ [<ffffffff812a802a>] blk_cleanup_queue+0x4a/0x60
+ [<ffffffff8145cc09>] scsi_free_queue+0x9/0x10
+ [<ffffffff81460944>] __scsi_remove_device+0x84/0xd0
+ [<ffffffff8145dca3>] scsi_probe_and_add_lun+0x353/0xb10
+ [<ffffffff817da069>] ? error_exit+0x29/0xb0
+ [<ffffffff817d98ed>] ? _raw_spin_unlock_irqrestore+0x3d/0x80
+ [<ffffffff8145e722>] __scsi_scan_target+0x112/0x680
+ [<ffffffff812c690d>] ? trace_hardirqs_off_thunk+0x3a/0x3c
+ [<ffffffff817da069>] ? error_exit+0x29/0xb0
+ [<ffffffff812bcc60>] ? kobject_del+0x40/0x40
+ [<ffffffff8145ed16>] scsi_scan_channel+0x86/0xb0
+ [<ffffffff8145f0b0>] scsi_scan_host_selected+0x140/0x150
+ [<ffffffff8145f149>] do_scsi_scan_host+0x89/0x90
+ [<ffffffff8145f170>] do_scan_async+0x20/0x160
+ [<ffffffff8145f150>] ? do_scsi_scan_host+0x90/0x90
+ [<ffffffff810975b6>] kthread+0xa6/0xb0
+ [<ffffffff817db154>] kernel_thread_helper+0x4/0x10
+ [<ffffffff81066430>] ? finish_task_switch+0x80/0x110
+ [<ffffffff817d9c04>] ? retint_restore_args+0xe/0xe
+ [<ffffffff81097510>] ? __init_kthread_worker+0x70/0x70
+ [<ffffffff817db150>] ? gs_change+0xb/0xb
+
+Line 2776 of block/cfq-iosched.c in v3.0-rc5 is as follows:
+
+	if (rcu_dereference(ioc->ioc_data) == cic) {
+
+This form says that it must be in a plain vanilla RCU read-side critical
+section, but the "other info" list above shows that this is not the
+case.  Instead, we hold three locks, one of which might be RCU related.
+And maybe that lock really does protect this reference.  If so, the fix
+is to inform RCU, perhaps by changing __cfq_exit_single_io_context() to
+take the struct request_queue "q" from cfq_exit_queue() as an argument,
+which would permit us to invoke rcu_dereference_protected as follows:
+
+	if (rcu_dereference_protected(ioc->ioc_data,
+				      lockdep_is_held(&q->queue_lock)) == cic) {
+
+With this change, there would be no lockdep-RCU splat emitted if this
+code was invoked either from within an RCU read-side critical section
+or with the ->queue_lock held.  In particular, this would have suppressed
+the above lockdep-RCU splat because ->queue_lock is held (see #2 in the
+list above).
+
+On the other hand, perhaps we really do need an RCU read-side critical
+section.  In this case, the critical section must span the use of the
+return value from rcu_dereference(), or at least until there is some
+reference count incremented or some such.  One way to handle this is to
+add rcu_read_lock() and rcu_read_unlock() as follows:
+
+	rcu_read_lock();
+	if (rcu_dereference(ioc->ioc_data) == cic) {
+		spin_lock(&ioc->lock);
+		rcu_assign_pointer(ioc->ioc_data, NULL);
+		spin_unlock(&ioc->lock);
+	}
+	rcu_read_unlock();
+
+With this change, the rcu_dereference() is always within an RCU
+read-side critical section, which again would have suppressed the
+above lockdep-RCU splat.
+
+But in this particular case, we don't actually deference the pointer
+returned from rcu_dereference().  Instead, that pointer is just compared
+to the cic pointer, which means that the rcu_dereference() can be replaced
+by rcu_access_pointer() as follows:
+
+	if (rcu_access_pointer(ioc->ioc_data) == cic) {
+
+Because it is legal to invoke rcu_access_pointer() without protection,
+this change would also suppress the above lockdep-RCU splat.
diff --git a/Documentation/RCU/lockdep.txt b/Documentation/RCU/lockdep.txt
index d7a49b2..a102d4b 100644
--- a/Documentation/RCU/lockdep.txt
+++ b/Documentation/RCU/lockdep.txt
@@ -32,9 +32,27 @@
 	srcu_dereference(p, sp):
 		Check for SRCU read-side critical section.
 	rcu_dereference_check(p, c):
-		Use explicit check expression "c".  This is useful in
-		code that is invoked by both readers and updaters.
-	rcu_dereference_raw(p)
+		Use explicit check expression "c" along with
+		rcu_read_lock_held().  This is useful in code that is
+		invoked by both RCU readers and updaters.
+	rcu_dereference_bh_check(p, c):
+		Use explicit check expression "c" along with
+		rcu_read_lock_bh_held().  This is useful in code that
+		is invoked by both RCU-bh readers and updaters.
+	rcu_dereference_sched_check(p, c):
+		Use explicit check expression "c" along with
+		rcu_read_lock_sched_held().  This is useful in code that
+		is invoked by both RCU-sched readers and updaters.
+	srcu_dereference_check(p, c):
+		Use explicit check expression "c" along with
+		srcu_read_lock_held()().  This is useful in code that
+		is invoked by both SRCU readers and updaters.
+	rcu_dereference_index_check(p, c):
+		Use explicit check expression "c", but the caller
+		must supply one of the rcu_read_lock_held() functions.
+		This is useful in code that uses RCU-protected arrays
+		that is invoked by both RCU readers and updaters.
+	rcu_dereference_raw(p):
 		Don't check.  (Use sparingly, if at all.)
 	rcu_dereference_protected(p, c):
 		Use explicit check expression "c", and omit all barriers
@@ -48,13 +66,11 @@
 		value of the pointer itself, for example, against NULL.
 
 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:
+expression, but would normally include 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);
 
@@ -62,7 +78,7 @@
 and, if CONFIG_PROVE_RCU is configured, verifies that this expression
 is used in:
 
-1.	An RCU read-side critical section, or
+1.	An RCU read-side critical section (implicit), or
 2.	with files->file_lock held, or
 3.	on an unshared files_struct.
 
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index 5d90167..783d6c1 100644
--- a/Documentation/RCU/torture.txt
+++ b/Documentation/RCU/torture.txt
@@ -42,7 +42,7 @@
 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
+irqreader	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
 		-not- permit this know to ignore this variable.)
@@ -79,19 +79,68 @@
 		Specifying "stutter=0" causes the test to run continuously
 		without pausing, which is the old default behavior.
 
+test_boost	Whether or not to test the ability of RCU to do priority
+		boosting.  Defaults to "test_boost=1", which performs
+		RCU priority-inversion testing only if the selected
+		RCU implementation supports priority boosting.  Specifying
+		"test_boost=0" never performs RCU priority-inversion
+		testing.  Specifying "test_boost=2" performs RCU
+		priority-inversion testing even if the selected RCU
+		implementation does not support RCU priority boosting,
+		which can be used to test rcutorture's ability to
+		carry out RCU priority-inversion testing.
+
+test_boost_interval
+		The number of seconds in an RCU priority-inversion test
+		cycle.	Defaults to "test_boost_interval=7".  It is
+		usually wise for this value to be relatively prime to
+		the value selected for "stutter".
+
+test_boost_duration
+		The number of seconds to do RCU priority-inversion testing
+		within any given "test_boost_interval".  Defaults to
+		"test_boost_duration=4".
+
 test_no_idle_hz	Whether or not to test the ability of RCU to operate in
 		a kernel that disables the scheduling-clock interrupt to
 		idle CPUs.  Boolean parameter, "1" to test, "0" otherwise.
 		Defaults to omitting this test.
 
-torture_type	The type of RCU to test: "rcu" for the rcu_read_lock() API,
-		"rcu_sync" for rcu_read_lock() with synchronous reclamation,
-		"rcu_bh" for the rcu_read_lock_bh() API, "rcu_bh_sync" for
-		rcu_read_lock_bh() with synchronous reclamation, "srcu" for
-		the "srcu_read_lock()" API, "sched" for the use of
-		preempt_disable() together with synchronize_sched(),
-		and "sched_expedited" for the use of preempt_disable()
-		with synchronize_sched_expedited().
+torture_type	The type of RCU to test, with string values as follows:
+
+		"rcu":  rcu_read_lock(), rcu_read_unlock() and call_rcu().
+
+		"rcu_sync":  rcu_read_lock(), rcu_read_unlock(), and
+			synchronize_rcu().
+
+		"rcu_expedited": rcu_read_lock(), rcu_read_unlock(), and
+			synchronize_rcu_expedited().
+
+		"rcu_bh": rcu_read_lock_bh(), rcu_read_unlock_bh(), and
+			call_rcu_bh().
+
+		"rcu_bh_sync": rcu_read_lock_bh(), rcu_read_unlock_bh(),
+			and synchronize_rcu_bh().
+
+		"rcu_bh_expedited": rcu_read_lock_bh(), rcu_read_unlock_bh(),
+			and synchronize_rcu_bh_expedited().
+
+		"srcu": srcu_read_lock(), srcu_read_unlock() and
+			synchronize_srcu().
+
+		"srcu_expedited": srcu_read_lock(), srcu_read_unlock() and
+			synchronize_srcu_expedited().
+
+		"sched": preempt_disable(), preempt_enable(), and
+			call_rcu_sched().
+
+		"sched_sync": preempt_disable(), preempt_enable(), and
+			synchronize_sched().
+
+		"sched_expedited": preempt_disable(), preempt_enable(), and
+			synchronize_sched_expedited().
+
+		Defaults to "rcu".
 
 verbose		Enable debug printk()s.  Default is disabled.
 
@@ -100,12 +149,12 @@
 
 The statistics output is as follows:
 
-	rcu-torture: --- Start of test: nreaders=16 stat_interval=0 verbose=0
-	rcu-torture: rtc: 0000000000000000 ver: 1916 tfle: 0 rta: 1916 rtaf: 0 rtf: 1915
-	rcu-torture: Reader Pipe:  1466408 9747 0 0 0 0 0 0 0 0 0
-	rcu-torture: Reader Batch:  1464477 11678 0 0 0 0 0 0 0 0
-	rcu-torture: Free-Block Circulation:  1915 1915 1915 1915 1915 1915 1915 1915 1915 1915 0
-	rcu-torture: --- End of test
+	rcu-torture:--- Start of test: nreaders=16 nfakewriters=4 stat_interval=30 verbose=0 test_no_idle_hz=1 shuffle_interval=3 stutter=5 irqreader=1 fqs_duration=0 fqs_holdoff=0 fqs_stutter=3 test_boost=1/0 test_boost_interval=7 test_boost_duration=4
+	rcu-torture: rtc:           (null) ver: 155441 tfle: 0 rta: 155441 rtaf: 8884 rtf: 155440 rtmbe: 0 rtbke: 0 rtbre: 0 rtbf: 0 rtb: 0 nt: 3055767
+	rcu-torture: Reader Pipe:  727860534 34213 0 0 0 0 0 0 0 0 0
+	rcu-torture: Reader Batch:  727877838 17003 0 0 0 0 0 0 0 0 0
+	rcu-torture: Free-Block Circulation:  155440 155440 155440 155440 155440 155440 155440 155440 155440 155440 0
+	rcu-torture:--- End of test: SUCCESS: nreaders=16 nfakewriters=4 stat_interval=30 verbose=0 test_no_idle_hz=1 shuffle_interval=3 stutter=5 irqreader=1 fqs_duration=0 fqs_holdoff=0 fqs_stutter=3 test_boost=1/0 test_boost_interval=7 test_boost_duration=4
 
 The command "dmesg | grep torture:" will extract this information on
 most systems.  On more esoteric configurations, it may be necessary to
@@ -113,26 +162,55 @@
 the RCU torture test.  The printk()s use KERN_ALERT, so they should
 be evident.  ;-)
 
+The first and last lines show the rcutorture module parameters, and the
+last line shows either "SUCCESS" or "FAILURE", based on rcutorture's
+automatic determination as to whether RCU operated correctly.
+
 The entries are as follows:
 
 o	"rtc": The hexadecimal address of the structure currently visible
 	to readers.
 
-o	"ver": The number of times since boot that the rcutw writer task
+o	"ver": The number of times since boot that the RCU writer task
 	has changed the structure visible to readers.
 
 o	"tfle": If non-zero, indicates that the "torture freelist"
-	containing structure to be placed into the "rtc" area is empty.
+	containing structures to be placed into the "rtc" area is empty.
 	This condition is important, since it can fool you into thinking
 	that RCU is working when it is not.  :-/
 
 o	"rta": Number of structures allocated from the torture freelist.
 
 o	"rtaf": Number of allocations from the torture freelist that have
-	failed due to the list being empty.
+	failed due to the list being empty.  It is not unusual for this
+	to be non-zero, but it is bad for it to be a large fraction of
+	the value indicated by "rta".
 
 o	"rtf": Number of frees into the torture freelist.
 
+o	"rtmbe": A non-zero value indicates that rcutorture believes that
+	rcu_assign_pointer() and rcu_dereference() are not working
+	correctly.  This value should be zero.
+
+o	"rtbke": rcutorture was unable to create the real-time kthreads
+	used to force RCU priority inversion.  This value should be zero.
+
+o	"rtbre": Although rcutorture successfully created the kthreads
+	used to force RCU priority inversion, it was unable to set them
+	to the real-time priority level of 1.  This value should be zero.
+
+o	"rtbf": The number of times that RCU priority boosting failed
+	to resolve RCU priority inversion.
+
+o	"rtb": The number of times that rcutorture attempted to force
+	an RCU priority inversion condition.  If you are testing RCU
+	priority boosting via the "test_boost" module parameter, this
+	value should be non-zero.
+
+o	"nt": The number of times rcutorture ran RCU read-side code from
+	within a timer handler.  This value should be non-zero only
+	if you specified the "irqreader" module parameter.
+
 o	"Reader Pipe": Histogram of "ages" of structures seen by readers.
 	If any entries past the first two are non-zero, RCU is broken.
 	And rcutorture prints the error flag string "!!!" to make sure
@@ -162,26 +240,15 @@
 	somehow gets incremented farther than it should.
 
 Different implementations of RCU can provide implementation-specific
-additional information.  For example, SRCU provides the following:
+additional information.  For example, SRCU provides the following
+additional line:
 
-	srcu-torture: rtc: f8cf46a8 ver: 355 tfle: 0 rta: 356 rtaf: 0 rtf: 346 rtmbe: 0
-	srcu-torture: Reader Pipe:  559738 939 0 0 0 0 0 0 0 0 0
-	srcu-torture: Reader Batch:  560434 243 0 0 0 0 0 0 0 0
-	srcu-torture: Free-Block Circulation:  355 354 353 352 351 350 349 348 347 346 0
 	srcu-torture: per-CPU(idx=1): 0(0,1) 1(0,1) 2(0,0) 3(0,1)
 
-The first four lines are similar to those for RCU.  The last line shows
-the per-CPU counter state.  The numbers in parentheses are the values
-of the "old" and "current" counters for the corresponding CPU.  The
-"idx" value maps the "old" and "current" values to the underlying array,
-and is useful for debugging.
-
-Similarly, sched_expedited RCU provides the following:
-
-	sched_expedited-torture: rtc: d0000000016c1880 ver: 1090796 tfle: 0 rta: 1090796 rtaf: 0 rtf: 1090787 rtmbe: 0 nt: 27713319
-	sched_expedited-torture: Reader Pipe:  12660320201 95875 0 0 0 0 0 0 0 0 0
-	sched_expedited-torture: Reader Batch:  12660424885 0 0 0 0 0 0 0 0 0 0
-	sched_expedited-torture: Free-Block Circulation:  1090795 1090795 1090794 1090793 1090792 1090791 1090790 1090789 1090788 1090787 0
+This line shows the per-CPU counter state.  The numbers in parentheses are
+the values of the "old" and "current" counters for the corresponding CPU.
+The "idx" value maps the "old" and "current" values to the underlying
+array, and is useful for debugging.
 
 
 USAGE
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 8173cec..aaf65f6 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -33,23 +33,23 @@
 The output of "cat rcu/rcudata" looks as follows:
 
 rcu_sched:
-  0 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=545/1/0 df=50 of=0 ri=0 ql=163 qs=NRW. kt=0/W/0 ktl=ebc3 b=10 ci=153737 co=0 ca=0
-  1 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=967/1/0 df=58 of=0 ri=0 ql=634 qs=NRW. kt=0/W/1 ktl=58c b=10 ci=191037 co=0 ca=0
-  2 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=1081/1/0 df=175 of=0 ri=0 ql=74 qs=N.W. kt=0/W/2 ktl=da94 b=10 ci=75991 co=0 ca=0
-  3 c=20942 g=20943 pq=1 pqc=20942 qp=1 dt=1846/0/0 df=404 of=0 ri=0 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=72261 co=0 ca=0
-  4 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=369/1/0 df=83 of=0 ri=0 ql=48 qs=N.W. kt=0/W/4 ktl=e0e7 b=10 ci=128365 co=0 ca=0
-  5 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=381/1/0 df=64 of=0 ri=0 ql=169 qs=NRW. kt=0/W/5 ktl=fb2f b=10 ci=164360 co=0 ca=0
-  6 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=1037/1/0 df=183 of=0 ri=0 ql=62 qs=N.W. kt=0/W/6 ktl=d2ad b=10 ci=65663 co=0 ca=0
-  7 c=20897 g=20897 pq=1 pqc=20896 qp=0 dt=1572/0/0 df=382 of=0 ri=0 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=75006 co=0 ca=0
+  0 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=545/1/0 df=50 of=0 ri=0 ql=163 qs=NRW. kt=0/W/0 ktl=ebc3 b=10 ci=153737 co=0 ca=0
+  1 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=967/1/0 df=58 of=0 ri=0 ql=634 qs=NRW. kt=0/W/1 ktl=58c b=10 ci=191037 co=0 ca=0
+  2 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=1081/1/0 df=175 of=0 ri=0 ql=74 qs=N.W. kt=0/W/2 ktl=da94 b=10 ci=75991 co=0 ca=0
+  3 c=20942 g=20943 pq=1 pgp=20942 qp=1 dt=1846/0/0 df=404 of=0 ri=0 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=72261 co=0 ca=0
+  4 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=369/1/0 df=83 of=0 ri=0 ql=48 qs=N.W. kt=0/W/4 ktl=e0e7 b=10 ci=128365 co=0 ca=0
+  5 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=381/1/0 df=64 of=0 ri=0 ql=169 qs=NRW. kt=0/W/5 ktl=fb2f b=10 ci=164360 co=0 ca=0
+  6 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=1037/1/0 df=183 of=0 ri=0 ql=62 qs=N.W. kt=0/W/6 ktl=d2ad b=10 ci=65663 co=0 ca=0
+  7 c=20897 g=20897 pq=1 pgp=20896 qp=0 dt=1572/0/0 df=382 of=0 ri=0 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=75006 co=0 ca=0
 rcu_bh:
-  0 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=545/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/0 ktl=ebc3 b=10 ci=0 co=0 ca=0
-  1 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=967/1/0 df=3 of=0 ri=1 ql=0 qs=.... kt=0/W/1 ktl=58c b=10 ci=151 co=0 ca=0
-  2 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=1081/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/2 ktl=da94 b=10 ci=0 co=0 ca=0
-  3 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=1846/0/0 df=8 of=0 ri=1 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=0 co=0 ca=0
-  4 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=369/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/4 ktl=e0e7 b=10 ci=0 co=0 ca=0
-  5 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=381/1/0 df=4 of=0 ri=1 ql=0 qs=.... kt=0/W/5 ktl=fb2f b=10 ci=0 co=0 ca=0
-  6 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=1037/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/6 ktl=d2ad b=10 ci=0 co=0 ca=0
-  7 c=1474 g=1474 pq=1 pqc=1473 qp=0 dt=1572/0/0 df=8 of=0 ri=1 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=0 co=0 ca=0
+  0 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=545/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/0 ktl=ebc3 b=10 ci=0 co=0 ca=0
+  1 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=967/1/0 df=3 of=0 ri=1 ql=0 qs=.... kt=0/W/1 ktl=58c b=10 ci=151 co=0 ca=0
+  2 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=1081/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/2 ktl=da94 b=10 ci=0 co=0 ca=0
+  3 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=1846/0/0 df=8 of=0 ri=1 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=0 co=0 ca=0
+  4 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=369/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/4 ktl=e0e7 b=10 ci=0 co=0 ca=0
+  5 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=381/1/0 df=4 of=0 ri=1 ql=0 qs=.... kt=0/W/5 ktl=fb2f b=10 ci=0 co=0 ca=0
+  6 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=1037/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/6 ktl=d2ad b=10 ci=0 co=0 ca=0
+  7 c=1474 g=1474 pq=1 pgp=1473 qp=0 dt=1572/0/0 df=8 of=0 ri=1 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=0 co=0 ca=0
 
 The first section lists the rcu_data structures for rcu_sched, the second
 for rcu_bh.  Note that CONFIG_TREE_PREEMPT_RCU kernels will have an
@@ -84,7 +84,7 @@
 	CPU has not yet reported that fact, (2) some other CPU has not
 	yet reported for this grace period, or (3) both.
 
-o	"pqc" indicates which grace period the last-observed quiescent
+o	"pgp" indicates which grace period the last-observed quiescent
 	state for this CPU corresponds to.  This is important for handling
 	the race between CPU 0 reporting an extended dynticks-idle
 	quiescent state for CPU 1 and CPU 1 suddenly waking up and
@@ -184,10 +184,14 @@
 	The number after the final slash is the CPU that the kthread
 	is actually running on.
 
+	This field is displayed only for CONFIG_RCU_BOOST kernels.
+
 o	"ktl" is the low-order 16 bits (in hexadecimal) of the count of
 	the number of times that this CPU's per-CPU kthread has gone
 	through its loop servicing invoke_rcu_cpu_kthread() requests.
 
+	This field is displayed only for CONFIG_RCU_BOOST kernels.
+
 o	"b" is the batch limit for this CPU.  If more than this number
 	of RCU callbacks is ready to invoke, then the remainder will
 	be deferred.
diff --git a/Documentation/SubmittingDrivers b/Documentation/SubmittingDrivers
index 319baa8..36d16bb 100644
--- a/Documentation/SubmittingDrivers
+++ b/Documentation/SubmittingDrivers
@@ -130,7 +130,7 @@
 	ftp.??.kernel.org:/pub/linux/kernel/...
 	?? == your country code, such as "us", "uk", "fr", etc.
 
-	http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git
+	http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git
 
 Linux kernel mailing list:
 	linux-kernel@vger.kernel.org
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 569f353..4468ce2 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -303,7 +303,7 @@
 
 The sign-off is a simple line at the end of the explanation for the
 patch, which certifies that you wrote it or otherwise have the right to
-pass it on as a open-source patch.  The rules are pretty simple: if you
+pass it on as an open-source patch.  The rules are pretty simple: if you
 can certify the below:
 
         Developer's Certificate of Origin 1.1
diff --git a/Documentation/blackfin/bfin-gpio-notes.txt b/Documentation/blackfin/bfin-gpio-notes.txt
index f731c1e..d36b01f 100644
--- a/Documentation/blackfin/bfin-gpio-notes.txt
+++ b/Documentation/blackfin/bfin-gpio-notes.txt
@@ -1,5 +1,5 @@
 /*
- * File:         Documentation/blackfin/bfin-gpio-note.txt
+ * File:         Documentation/blackfin/bfin-gpio-notes.txt
  * Based on:
  * Author:
  *
diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index c6d84cf..e418dc0 100644
--- a/Documentation/block/biodoc.txt
+++ b/Documentation/block/biodoc.txt
@@ -186,7 +186,7 @@
 do not have a corresponding kernel virtual address space mapping) and
 low-memory pages.
 
-Note: Please refer to Documentation/PCI/PCI-DMA-mapping.txt for a discussion
+Note: Please refer to Documentation/DMA-API-HOWTO.txt for a discussion
 on PCI high mem DMA aspects and mapping of scatter gather lists, and support
 for 64 bit PCI.
 
diff --git a/Documentation/block/cfq-iosched.txt b/Documentation/block/cfq-iosched.txt
index e578fee..6d670f5 100644
--- a/Documentation/block/cfq-iosched.txt
+++ b/Documentation/block/cfq-iosched.txt
@@ -43,3 +43,74 @@
 to IOPS mode and starts providing fairness in terms of number of requests
 dispatched. Note that this mode switching takes effect only for group
 scheduling. For non-cgroup users nothing should change.
+
+CFQ IO scheduler Idling Theory
+===============================
+Idling on a queue is primarily about waiting for the next request to come
+on same queue after completion of a request. In this process CFQ will not
+dispatch requests from other cfq queues even if requests are pending there.
+
+The rationale behind idling is that it can cut down on number of seeks
+on rotational media. For example, if a process is doing dependent
+sequential reads (next read will come on only after completion of previous
+one), then not dispatching request from other queue should help as we
+did not move the disk head and kept on dispatching sequential IO from
+one queue.
+
+CFQ has following service trees and various queues are put on these trees.
+
+	sync-idle	sync-noidle	async
+
+All cfq queues doing synchronous sequential IO go on to sync-idle tree.
+On this tree we idle on each queue individually.
+
+All synchronous non-sequential queues go on sync-noidle tree. Also any
+request which are marked with REQ_NOIDLE go on this service tree. On this
+tree we do not idle on individual queues instead idle on the whole group
+of queues or the tree. So if there are 4 queues waiting for IO to dispatch
+we will idle only once last queue has dispatched the IO and there is
+no more IO on this service tree.
+
+All async writes go on async service tree. There is no idling on async
+queues.
+
+CFQ has some optimizations for SSDs and if it detects a non-rotational
+media which can support higher queue depth (multiple requests at in
+flight at a time), then it cuts down on idling of individual queues and
+all the queues move to sync-noidle tree and only tree idle remains. This
+tree idling provides isolation with buffered write queues on async tree.
+
+FAQ
+===
+Q1. Why to idle at all on queues marked with REQ_NOIDLE.
+
+A1. We only do tree idle (all queues on sync-noidle tree) on queues marked
+    with REQ_NOIDLE. This helps in providing isolation with all the sync-idle
+    queues. Otherwise in presence of many sequential readers, other
+    synchronous IO might not get fair share of disk.
+
+    For example, if there are 10 sequential readers doing IO and they get
+    100ms each. If a REQ_NOIDLE request comes in, it will be scheduled
+    roughly after 1 second. If after completion of REQ_NOIDLE request we
+    do not idle, and after a couple of milli seconds a another REQ_NOIDLE
+    request comes in, again it will be scheduled after 1second. Repeat it
+    and notice how a workload can lose its disk share and suffer due to
+    multiple sequential readers.
+
+    fsync can generate dependent IO where bunch of data is written in the
+    context of fsync, and later some journaling data is written. Journaling
+    data comes in only after fsync has finished its IO (atleast for ext4
+    that seemed to be the case). Now if one decides not to idle on fsync
+    thread due to REQ_NOIDLE, then next journaling write will not get
+    scheduled for another second. A process doing small fsync, will suffer
+    badly in presence of multiple sequential readers.
+
+    Hence doing tree idling on threads using REQ_NOIDLE flag on requests
+    provides isolation from multiple sequential readers and at the same
+    time we do not idle on individual threads.
+
+Q2. When to specify REQ_NOIDLE
+A2. I would think whenever one is doing synchronous write and not expecting
+    more writes to be dispatched from same context soon, should be able
+    to specify REQ_NOIDLE on writes and that probably should work well for
+    most of the cases.
diff --git a/Documentation/block/switching-sched.txt b/Documentation/block/switching-sched.txt
index 71cfbdc..3b2612e 100644
--- a/Documentation/block/switching-sched.txt
+++ b/Documentation/block/switching-sched.txt
@@ -1,6 +1,6 @@
 To choose IO schedulers at boot time, use the argument 'elevator=deadline'.
-'noop', 'as' and 'cfq' (the default) are also available. IO schedulers are
-assigned globally at boot time only presently.
+'noop' and 'cfq' (the default) are also available. IO schedulers are assigned
+globally at boot time only presently.
 
 Each io queue has a set of io scheduler tunables associated with it. These
 tunables control how the io scheduler works. You can find these entries
diff --git a/Documentation/blockdev/cciss.txt b/Documentation/blockdev/cciss.txt
index c00c6a5..71464e0 100644
--- a/Documentation/blockdev/cciss.txt
+++ b/Documentation/blockdev/cciss.txt
@@ -78,6 +78,16 @@
 /dev/cciss/c1d1p2		Controller 1, disk 1, partition 2
 /dev/cciss/c1d1p3		Controller 1, disk 1, partition 3
 
+CCISS simple mode support
+-------------------------
+
+The "cciss_simple_mode=1" boot parameter may be used to prevent the driver
+from putting the controller into "performant" mode. The difference is that
+with simple mode, each command completion requires an interrupt, while with
+"performant mode" (the default, and ordinarily better performing) it is
+possible to have multiple command completions indicated by a single
+interrupt.
+
 SCSI tape drive and medium changer support
 ------------------------------------------
 
diff --git a/Documentation/bus-virt-phys-mapping.txt b/Documentation/bus-virt-phys-mapping.txt
index 1b5aa10..2bc55ff 100644
--- a/Documentation/bus-virt-phys-mapping.txt
+++ b/Documentation/bus-virt-phys-mapping.txt
@@ -1,6 +1,6 @@
 [ NOTE: The virt_to_bus() and bus_to_virt() functions have been
 	superseded by the functionality provided by the PCI DMA interface
-	(see Documentation/PCI/PCI-DMA-mapping.txt).  They continue
+	(see Documentation/DMA-API-HOWTO.txt).  They continue
 	to be documented below for historical purposes, but new code
 	must not use them. --davidm 00/12/12 ]
 
diff --git a/Documentation/cdrom/packet-writing.txt b/Documentation/cdrom/packet-writing.txt
index 13c251d..2834170 100644
--- a/Documentation/cdrom/packet-writing.txt
+++ b/Documentation/cdrom/packet-writing.txt
@@ -109,7 +109,7 @@
 
 For a description of the sysfs interface look into the file:
 
-  Documentation/ABI/testing/sysfs-block-pktcdvd
+  Documentation/ABI/testing/sysfs-class-pktcdvd
 
 
 Using the pktcdvd debugfs interface
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index cd67e90..9c452ef 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -454,8 +454,8 @@
 move it into a new cgroup (possibly the root cgroup) by writing to the
 new cgroup's tasks file.
 
-Note: If the ns cgroup is active, moving a process to another cgroup can
-fail.
+Note: Due to some restrictions enforced by some cgroup subsystems, moving
+a process to another cgroup can fail.
 
 2.3 Mounting hierarchies by name
 --------------------------------
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 6f3c598..cc0ebc5 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -380,7 +380,7 @@
 
 5.2 stat file
 
-5.2.1 memory.stat file includes following statistics
+memory.stat file includes following statistics
 
 # per-memory cgroup local status
 cache		- # of bytes of page cache memory.
@@ -418,7 +418,6 @@
 
 # The following additional stats are dependent on CONFIG_DEBUG_VM.
 
-inactive_ratio		- VM internal parameter. (see mm/page_alloc.c)
 recent_rotated_anon	- VM internal parameter. (see mm/vmscan.c)
 recent_rotated_file	- VM internal parameter. (see mm/vmscan.c)
 recent_scanned_anon	- VM internal parameter. (see mm/vmscan.c)
@@ -438,89 +437,6 @@
 	 file_mapped is accounted only when the memory cgroup is owner of page
 	 cache.)
 
-5.2.2 memory.vmscan_stat
-
-memory.vmscan_stat includes statistics information for memory scanning and
-freeing, reclaiming. The statistics shows memory scanning information since
-memory cgroup creation and can be reset to 0 by writing 0 as
-
- #echo 0 > ../memory.vmscan_stat
-
-This file contains following statistics.
-
-[param]_[file_or_anon]_pages_by_[reason]_[under_heararchy]
-[param]_elapsed_ns_by_[reason]_[under_hierarchy]
-
-For example,
-
-  scanned_file_pages_by_limit indicates the number of scanned
-  file pages at vmscan.
-
-Now, 3 parameters are supported
-
-  scanned - the number of pages scanned by vmscan
-  rotated - the number of pages activated at vmscan
-  freed   - the number of pages freed by vmscan
-
-If "rotated" is high against scanned/freed, the memcg seems busy.
-
-Now, 2 reason are supported
-
-  limit - the memory cgroup's limit
-  system - global memory pressure + softlimit
-           (global memory pressure not under softlimit is not handled now)
-
-When under_hierarchy is added in the tail, the number indicates the
-total memcg scan of its children and itself.
-
-elapsed_ns is a elapsed time in nanosecond. This may include sleep time
-and not indicates CPU usage. So, please take this as just showing
-latency.
-
-Here is an example.
-
-# cat /cgroup/memory/A/memory.vmscan_stat
-scanned_pages_by_limit 9471864
-scanned_anon_pages_by_limit 6640629
-scanned_file_pages_by_limit 2831235
-rotated_pages_by_limit 4243974
-rotated_anon_pages_by_limit 3971968
-rotated_file_pages_by_limit 272006
-freed_pages_by_limit 2318492
-freed_anon_pages_by_limit 962052
-freed_file_pages_by_limit 1356440
-elapsed_ns_by_limit 351386416101
-scanned_pages_by_system 0
-scanned_anon_pages_by_system 0
-scanned_file_pages_by_system 0
-rotated_pages_by_system 0
-rotated_anon_pages_by_system 0
-rotated_file_pages_by_system 0
-freed_pages_by_system 0
-freed_anon_pages_by_system 0
-freed_file_pages_by_system 0
-elapsed_ns_by_system 0
-scanned_pages_by_limit_under_hierarchy 9471864
-scanned_anon_pages_by_limit_under_hierarchy 6640629
-scanned_file_pages_by_limit_under_hierarchy 2831235
-rotated_pages_by_limit_under_hierarchy 4243974
-rotated_anon_pages_by_limit_under_hierarchy 3971968
-rotated_file_pages_by_limit_under_hierarchy 272006
-freed_pages_by_limit_under_hierarchy 2318492
-freed_anon_pages_by_limit_under_hierarchy 962052
-freed_file_pages_by_limit_under_hierarchy 1356440
-elapsed_ns_by_limit_under_hierarchy 351386416101
-scanned_pages_by_system_under_hierarchy 0
-scanned_anon_pages_by_system_under_hierarchy 0
-scanned_file_pages_by_system_under_hierarchy 0
-rotated_pages_by_system_under_hierarchy 0
-rotated_anon_pages_by_system_under_hierarchy 0
-rotated_file_pages_by_system_under_hierarchy 0
-freed_pages_by_system_under_hierarchy 0
-freed_anon_pages_by_system_under_hierarchy 0
-freed_file_pages_by_system_under_hierarchy 0
-elapsed_ns_by_system_under_hierarchy 0
-
 5.3 swappiness
 
 Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt
index e74d0a2..d221781 100644
--- a/Documentation/cpu-freq/governors.txt
+++ b/Documentation/cpu-freq/governors.txt
@@ -132,7 +132,7 @@
 transition_latency * 100
 Or by kernel restrictions:
 If CONFIG_NO_HZ is set, the limit is 10ms fixed.
-If CONFIG_NO_HZ is not set or no_hz=off boot parameter is used, the
+If CONFIG_NO_HZ is not set or nohz=off boot parameter is used, the
 limits depend on the CONFIG_HZ option:
 HZ=1000: min=20000us  (20ms)
 HZ=250:  min=80000us  (80ms)
diff --git a/Documentation/development-process/4.Coding b/Documentation/development-process/4.Coding
index 83f5f5b..e3cb6a5 100644
--- a/Documentation/development-process/4.Coding
+++ b/Documentation/development-process/4.Coding
@@ -278,7 +278,7 @@
 fail; these failures can be restricted to a specific range of code.
 Running with fault injection enabled allows the programmer to see how the
 code responds when things go badly.  See
-Documentation/fault-injection/fault-injection.text for more information on
+Documentation/fault-injection/fault-injection.txt for more information on
 how to use this facility.
 
 Other kinds of errors can be found with the "sparse" static analysis tool.
diff --git a/Documentation/device-mapper/dm-log.txt b/Documentation/device-mapper/dm-log.txt
index 994dd75..c155ac5 100644
--- a/Documentation/device-mapper/dm-log.txt
+++ b/Documentation/device-mapper/dm-log.txt
@@ -48,7 +48,7 @@
 communication.
 
 There are currently two userspace log implementations that leverage this
-framework - "clustered_disk" and "clustered_core".  These implementations
+framework - "clustered-disk" and "clustered-core".  These implementations
 provide a cluster-coherent log for shared-storage.  Device-mapper mirroring
 can be used in a shared-storage environment when the cluster log implementations
 are employed.
diff --git a/Documentation/device-mapper/persistent-data.txt b/Documentation/device-mapper/persistent-data.txt
new file mode 100644
index 0000000..0e5df9b
--- /dev/null
+++ b/Documentation/device-mapper/persistent-data.txt
@@ -0,0 +1,84 @@
+Introduction
+============
+
+The more-sophisticated device-mapper targets require complex metadata
+that is managed in kernel.  In late 2010 we were seeing that various
+different targets were rolling their own data strutures, for example:
+
+- Mikulas Patocka's multisnap implementation
+- Heinz Mauelshagen's thin provisioning target
+- Another btree-based caching target posted to dm-devel
+- Another multi-snapshot target based on a design of Daniel Phillips
+
+Maintaining these data structures takes a lot of work, so if possible
+we'd like to reduce the number.
+
+The persistent-data library is an attempt to provide a re-usable
+framework for people who want to store metadata in device-mapper
+targets.  It's currently used by the thin-provisioning target and an
+upcoming hierarchical storage target.
+
+Overview
+========
+
+The main documentation is in the header files which can all be found
+under drivers/md/persistent-data.
+
+The block manager
+-----------------
+
+dm-block-manager.[hc]
+
+This provides access to the data on disk in fixed sized-blocks.  There
+is a read/write locking interface to prevent concurrent accesses, and
+keep data that is being used in the cache.
+
+Clients of persistent-data are unlikely to use this directly.
+
+The transaction manager
+-----------------------
+
+dm-transaction-manager.[hc]
+
+This restricts access to blocks and enforces copy-on-write semantics.
+The only way you can get hold of a writable block through the
+transaction manager is by shadowing an existing block (ie. doing
+copy-on-write) or allocating a fresh one.  Shadowing is elided within
+the same transaction so performance is reasonable.  The commit method
+ensures that all data is flushed before it writes the superblock.
+On power failure your metadata will be as it was when last committed.
+
+The Space Maps
+--------------
+
+dm-space-map.h
+dm-space-map-metadata.[hc]
+dm-space-map-disk.[hc]
+
+On-disk data structures that keep track of reference counts of blocks.
+Also acts as the allocator of new blocks.  Currently two
+implementations: a simpler one for managing blocks on a different
+device (eg. thinly-provisioned data blocks); and one for managing
+the metadata space.  The latter is complicated by the need to store
+its own data within the space it's managing.
+
+The data structures
+-------------------
+
+dm-btree.[hc]
+dm-btree-remove.c
+dm-btree-spine.c
+dm-btree-internal.h
+
+Currently there is only one data structure, a hierarchical btree.
+There are plans to add more.  For example, something with an
+array-like interface would see a lot of use.
+
+The btree is 'hierarchical' in that you can define it to be composed
+of nested btrees, and take multiple keys.  For example, the
+thin-provisioning target uses a btree with two levels of nesting.
+The first maps a device id to a mapping tree, and that in turn maps a
+virtual block to a physical block.
+
+Values stored in the btrees can have arbitrary size.  Keys are always
+64bits, although nesting allows you to use multiple keys.
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
new file mode 100644
index 0000000..801d9d1
--- /dev/null
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -0,0 +1,285 @@
+Introduction
+============
+
+This document descibes a collection of device-mapper targets that
+between them implement thin-provisioning and snapshots.
+
+The main highlight of this implementation, compared to the previous
+implementation of snapshots, is that it allows many virtual devices to
+be stored on the same data volume.  This simplifies administration and
+allows the sharing of data between volumes, thus reducing disk usage.
+
+Another significant feature is support for an arbitrary depth of
+recursive snapshots (snapshots of snapshots of snapshots ...).  The
+previous implementation of snapshots did this by chaining together
+lookup tables, and so performance was O(depth).  This new
+implementation uses a single data structure to avoid this degradation
+with depth.  Fragmentation may still be an issue, however, in some
+scenarios.
+
+Metadata is stored on a separate device from data, giving the
+administrator some freedom, for example to:
+
+- Improve metadata resilience by storing metadata on a mirrored volume
+  but data on a non-mirrored one.
+
+- Improve performance by storing the metadata on SSD.
+
+Status
+======
+
+These targets are very much still in the EXPERIMENTAL state.  Please
+do not yet rely on them in production.  But do experiment and offer us
+feedback.  Different use cases will have different performance
+characteristics, for example due to fragmentation of the data volume.
+
+If you find this software is not performing as expected please mail
+dm-devel@redhat.com with details and we'll try our best to improve
+things for you.
+
+Userspace tools for checking and repairing the metadata are under
+development.
+
+Cookbook
+========
+
+This section describes some quick recipes for using thin provisioning.
+They use the dmsetup program to control the device-mapper driver
+directly.  End users will be advised to use a higher-level volume
+manager such as LVM2 once support has been added.
+
+Pool device
+-----------
+
+The pool device ties together the metadata volume and the data volume.
+It maps I/O linearly to the data volume and updates the metadata via
+two mechanisms:
+
+- Function calls from the thin targets
+
+- Device-mapper 'messages' from userspace which control the creation of new
+  virtual devices amongst other things.
+
+Setting up a fresh pool device
+------------------------------
+
+Setting up a pool device requires a valid metadata device, and a
+data device.  If you do not have an existing metadata device you can
+make one by zeroing the first 4k to indicate empty metadata.
+
+    dd if=/dev/zero of=$metadata_dev bs=4096 count=1
+
+The amount of metadata you need will vary according to how many blocks
+are shared between thin devices (i.e. through snapshots).  If you have
+less sharing than average you'll need a larger-than-average metadata device.
+
+As a guide, we suggest you calculate the number of bytes to use in the
+metadata device as 48 * $data_dev_size / $data_block_size but round it up
+to 2MB if the answer is smaller.  The largest size supported is 16GB.
+
+If you're creating large numbers of snapshots which are recording large
+amounts of change, you may need find you need to increase this.
+
+Reloading a pool table
+----------------------
+
+You may reload a pool's table, indeed this is how the pool is resized
+if it runs out of space.  (N.B. While specifying a different metadata
+device when reloading is not forbidden at the moment, things will go
+wrong if it does not route I/O to exactly the same on-disk location as
+previously.)
+
+Using an existing pool device
+-----------------------------
+
+    dmsetup create pool \
+	--table "0 20971520 thin-pool $metadata_dev $data_dev \
+		 $data_block_size $low_water_mark"
+
+$data_block_size gives the smallest unit of disk space that can be
+allocated at a time expressed in units of 512-byte sectors.  People
+primarily interested in thin provisioning may want to use a value such
+as 1024 (512KB).  People doing lots of snapshotting may want a smaller value
+such as 128 (64KB).  If you are not zeroing newly-allocated data,
+a larger $data_block_size in the region of 256000 (128MB) is suggested.
+$data_block_size must be the same for the lifetime of the
+metadata device.
+
+$low_water_mark is expressed in blocks of size $data_block_size.  If
+free space on the data device drops below this level then a dm event
+will be triggered which a userspace daemon should catch allowing it to
+extend the pool device.  Only one such event will be sent.
+Resuming a device with a new table itself triggers an event so the
+userspace daemon can use this to detect a situation where a new table
+already exceeds the threshold.
+
+Thin provisioning
+-----------------
+
+i) Creating a new thinly-provisioned volume.
+
+  To create a new thinly- provisioned volume you must send a message to an
+  active pool device, /dev/mapper/pool in this example.
+
+    dmsetup message /dev/mapper/pool 0 "create_thin 0"
+
+  Here '0' is an identifier for the volume, a 24-bit number.  It's up
+  to the caller to allocate and manage these identifiers.  If the
+  identifier is already in use, the message will fail with -EEXIST.
+
+ii) Using a thinly-provisioned volume.
+
+  Thinly-provisioned volumes are activated using the 'thin' target:
+
+    dmsetup create thin --table "0 2097152 thin /dev/mapper/pool 0"
+
+  The last parameter is the identifier for the thinp device.
+
+Internal snapshots
+------------------
+
+i) Creating an internal snapshot.
+
+  Snapshots are created with another message to the pool.
+
+  N.B.  If the origin device that you wish to snapshot is active, you
+  must suspend it before creating the snapshot to avoid corruption.
+  This is NOT enforced at the moment, so please be careful!
+
+    dmsetup suspend /dev/mapper/thin
+    dmsetup message /dev/mapper/pool 0 "create_snap 1 0"
+    dmsetup resume /dev/mapper/thin
+
+  Here '1' is the identifier for the volume, a 24-bit number.  '0' is the
+  identifier for the origin device.
+
+ii) Using an internal snapshot.
+
+  Once created, the user doesn't have to worry about any connection
+  between the origin and the snapshot.  Indeed the snapshot is no
+  different from any other thinly-provisioned device and can be
+  snapshotted itself via the same method.  It's perfectly legal to
+  have only one of them active, and there's no ordering requirement on
+  activating or removing them both.  (This differs from conventional
+  device-mapper snapshots.)
+
+  Activate it exactly the same way as any other thinly-provisioned volume:
+
+    dmsetup create snap --table "0 2097152 thin /dev/mapper/pool 1"
+
+Deactivation
+------------
+
+All devices using a pool must be deactivated before the pool itself
+can be.
+
+    dmsetup remove thin
+    dmsetup remove snap
+    dmsetup remove pool
+
+Reference
+=========
+
+'thin-pool' target
+------------------
+
+i) Constructor
+
+    thin-pool <metadata dev> <data dev> <data block size (sectors)> \
+	      <low water mark (blocks)> [<number of feature args> [<arg>]*]
+
+    Optional feature arguments:
+    - 'skip_block_zeroing': skips the zeroing of newly-provisioned blocks.
+
+    Data block size must be between 64KB (128 sectors) and 1GB
+    (2097152 sectors) inclusive.
+
+
+ii) Status
+
+    <transaction id> <used metadata blocks>/<total metadata blocks>
+    <used data blocks>/<total data blocks> <held metadata root>
+
+
+    transaction id:
+	A 64-bit number used by userspace to help synchronise with metadata
+	from volume managers.
+
+    used data blocks / total data blocks
+	If the number of free blocks drops below the pool's low water mark a
+	dm event will be sent to userspace.  This event is edge-triggered and
+	it will occur only once after each resume so volume manager writers
+	should register for the event and then check the target's status.
+
+    held metadata root:
+	The location, in sectors, of the metadata root that has been
+	'held' for userspace read access.  '-' indicates there is no
+	held root.  This feature is not yet implemented so '-' is
+	always returned.
+
+iii) Messages
+
+    create_thin <dev id>
+
+	Create a new thinly-provisioned device.
+	<dev id> is an arbitrary unique 24-bit identifier chosen by
+	the caller.
+
+    create_snap <dev id> <origin id>
+
+	Create a new snapshot of another thinly-provisioned device.
+	<dev id> is an arbitrary unique 24-bit identifier chosen by
+	the caller.
+	<origin id> is the identifier of the thinly-provisioned device
+	of which the new device will be a snapshot.
+
+    delete <dev id>
+
+	Deletes a thin device.  Irreversible.
+
+    trim <dev id> <new size in sectors>
+
+	Delete mappings from the end of a thin device.  Irreversible.
+	You might want to use this if you're reducing the size of
+	your thinly-provisioned device.  In many cases, due to the
+	sharing of blocks between devices, it is not possible to
+	determine in advance how much space 'trim' will release.  (In
+	future a userspace tool might be able to perform this
+	calculation.)
+
+    set_transaction_id <current id> <new id>
+
+	Userland volume managers, such as LVM, need a way to
+	synchronise their external metadata with the internal metadata of the
+	pool target.  The thin-pool target offers to store an
+	arbitrary 64-bit transaction id and return it on the target's
+	status line.  To avoid races you must provide what you think
+	the current transaction id is when you change it with this
+	compare-and-swap message.
+
+'thin' target
+-------------
+
+i) Constructor
+
+    thin <pool dev> <dev id>
+
+    pool dev:
+	the thin-pool device, e.g. /dev/mapper/my_pool or 253:0
+
+    dev id:
+	the internal device identifier of the device to be
+	activated.
+
+The pool doesn't store any size against the thin devices.  If you
+load a thin target that is smaller than you've been using previously,
+then you'll have no access to blocks mapped beyond the end.  If you
+load a target that is bigger than before, then extra blocks will be
+provisioned as and when needed.
+
+If you wish to reduce the size of your thin device and potentially
+regain some space then send the 'trim' message to the pool.
+
+ii) Status
+
+     <nr mapped sectors> <highest mapped sector>
diff --git a/Documentation/devicetree/bindings/arm/calxeda.txt b/Documentation/devicetree/bindings/arm/calxeda.txt
new file mode 100644
index 0000000..4755caa
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/calxeda.txt
@@ -0,0 +1,8 @@
+Calxeda Highbank Platforms Device Tree Bindings
+-----------------------------------------------
+
+Boards with Calxeda Cortex-A9 based Highbank SOC shall have the following
+properties.
+
+Required root node properties:
+    - compatible = "calxeda,highbank";
diff --git a/Documentation/devicetree/bindings/arm/fsl.txt b/Documentation/devicetree/bindings/arm/fsl.txt
new file mode 100644
index 0000000..c9848ad
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/fsl.txt
@@ -0,0 +1,26 @@
+Freescale i.MX Platforms Device Tree Bindings
+-----------------------------------------------
+
+i.MX51 Babbage Board
+Required root node properties:
+    - compatible = "fsl,imx51-babbage", "fsl,imx51";
+
+i.MX53 Automotive Reference Design Board
+Required root node properties:
+    - compatible = "fsl,imx53-ard", "fsl,imx53";
+
+i.MX53 Evaluation Kit
+Required root node properties:
+    - compatible = "fsl,imx53-evk", "fsl,imx53";
+
+i.MX53 Quick Start Board
+Required root node properties:
+    - compatible = "fsl,imx53-qsb", "fsl,imx53";
+
+i.MX53 Smart Mobile Reference Design Board
+Required root node properties:
+    - compatible = "fsl,imx53-smd", "fsl,imx53";
+
+i.MX6 Quad SABRE Automotive Board
+Required root node properties:
+    - compatible = "fsl,imx6q-sabreauto", "fsl,imx6q";
diff --git a/Documentation/devicetree/bindings/arm/gic.txt b/Documentation/devicetree/bindings/arm/gic.txt
new file mode 100644
index 0000000..52916b4
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/gic.txt
@@ -0,0 +1,55 @@
+* ARM Generic Interrupt Controller
+
+ARM SMP cores are often associated with a GIC, providing per processor
+interrupts (PPI), shared processor interrupts (SPI) and software
+generated interrupts (SGI).
+
+Primary GIC is attached directly to the CPU and typically has PPIs and SGIs.
+Secondary GICs are cascaded into the upward interrupt controller and do not
+have PPIs or SGIs.
+
+Main node required properties:
+
+- compatible : should be one of:
+	"arm,cortex-a9-gic"
+	"arm,arm11mp-gic"
+- interrupt-controller : Identifies the node as an interrupt controller
+- #interrupt-cells : Specifies the number of cells needed to encode an
+  interrupt source.  The type shall be a <u32> and the value shall be 3.
+
+  The 1st cell is the interrupt type; 0 for SPI interrupts, 1 for PPI
+  interrupts.
+
+  The 2nd cell contains the interrupt number for the interrupt type.
+  SPI interrupts are in the range [0-987].  PPI interrupts are in the
+  range [0-15].
+
+  The 3rd cell is the flags, encoded as follows:
+	bits[3:0] trigger type and level flags.
+		1 = low-to-high edge triggered
+		2 = high-to-low edge triggered
+		4 = active high level-sensitive
+		8 = active low level-sensitive
+	bits[15:8] PPI interrupt cpu mask.  Each bit corresponds to each of
+	the 8 possible cpus attached to the GIC.  A bit set to '1' indicated
+	the interrupt is wired to that CPU.  Only valid for PPI interrupts.
+
+- reg : Specifies base physical address(s) and size of the GIC registers. The
+  first region is the GIC distributor register base and size. The 2nd region is
+  the GIC cpu interface register base and size.
+
+Optional
+- interrupts	: Interrupt source of the parent interrupt controller. Only
+  present on secondary GICs.
+
+Example:
+
+	intc: interrupt-controller@fff11000 {
+		compatible = "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <1>;
+		interrupt-controller;
+		reg = <0xfff11000 0x1000>,
+		      <0xfff10100 0x100>;
+	};
+
diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2cc.txt
new file mode 100644
index 0000000..7ca5216
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/l2cc.txt
@@ -0,0 +1,44 @@
+* ARM L2 Cache Controller
+
+ARM cores often have a separate level 2 cache controller. There are various
+implementations of the L2 cache controller with compatible programming models.
+The ARM L2 cache representation in the device tree should be done as follows:
+
+Required properties:
+
+- compatible : should be one of:
+	"arm,pl310-cache"
+	"arm,l220-cache"
+	"arm,l210-cache"
+- cache-unified : Specifies the cache is a unified cache.
+- cache-level : Should be set to 2 for a level 2 cache.
+- reg : Physical base address and size of cache controller's memory mapped
+  registers.
+
+Optional properties:
+
+- arm,data-latency : Cycles of latency for Data RAM accesses. Specifies 3 cells of
+  read, write and setup latencies. Minimum valid values are 1. Controllers
+  without setup latency control should use a value of 0.
+- arm,tag-latency : Cycles of latency for Tag RAM accesses. Specifies 3 cells of
+  read, write and setup latencies. Controllers without setup latency control
+  should use 0. Controllers without separate read and write Tag RAM latency
+  values should only use the first cell.
+- arm,dirty-latency : Cycles of latency for Dirty RAMs. This is a single cell.
+- arm,filter-ranges : <start length> Starting address and length of window to
+  filter. Addresses in the filter window are directed to the M1 port. Other
+  addresses will go to the M0 port.
+- interrupts : 1 combined interrupt.
+
+Example:
+
+L2: cache-controller {
+        compatible = "arm,pl310-cache";
+        reg = <0xfff12000 0x1000>;
+        arm,data-latency = <1 1 1>;
+        arm,tag-latency = <2 2 2>;
+        arm,filter-latency = <0x80000000 0x8000000>;
+        cache-unified;
+        cache-level = <2>;
+	interrupts = <45>;
+};
diff --git a/Documentation/devicetree/bindings/arm/omap/dsp.txt b/Documentation/devicetree/bindings/arm/omap/dsp.txt
new file mode 100644
index 0000000..d3830a3
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/omap/dsp.txt
@@ -0,0 +1,14 @@
+* TI - DSP (Digital Signal Processor)
+
+TI DSP included in OMAP SoC
+
+Required properties:
+- compatible : Should be "ti,omap3-c64" for OMAP3 & 4
+- ti,hwmods: "dsp"
+
+Examples:
+
+dsp {
+    compatible = "ti,omap3-c64";
+    ti,hwmods = "dsp";
+};
diff --git a/Documentation/devicetree/bindings/arm/omap/iva.txt b/Documentation/devicetree/bindings/arm/omap/iva.txt
new file mode 100644
index 0000000..6d62951
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/omap/iva.txt
@@ -0,0 +1,19 @@
+* TI - IVA (Imaging and Video Accelerator) subsystem
+
+The IVA contain various audio, video or imaging HW accelerator
+depending of the version.
+
+Required properties:
+- compatible : Should be:
+  - "ti,ivahd" for OMAP4
+  - "ti,iva2.2" for OMAP3
+  - "ti,iva2.1" for OMAP2430
+  - "ti,iva1" for OMAP2420
+- ti,hwmods: "iva"
+
+Examples:
+
+iva {
+    compatible = "ti,ivahd", "ti,iva";
+    ti,hwmods = "iva";
+};
diff --git a/Documentation/devicetree/bindings/arm/omap/l3-noc.txt b/Documentation/devicetree/bindings/arm/omap/l3-noc.txt
new file mode 100644
index 0000000..6888a5e
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/omap/l3-noc.txt
@@ -0,0 +1,19 @@
+* TI - L3 Network On Chip (NoC)
+
+This version is an implementation of the generic NoC IP
+provided by Arteris.
+
+Required properties:
+- compatible : Should be "ti,omap3-l3-smx" for OMAP3 family
+               Should be "ti,omap4-l3-noc" for OMAP4 family
+- ti,hwmods: "l3_main_1", ... One hwmod for each noc domain.
+
+Examples:
+
+ocp {
+	compatible = "ti,omap4-l3-noc", "simple-bus";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	ranges;
+	ti,hwmods = "l3_main_1", "l3_main_2", "l3_main_3";
+};
diff --git a/Documentation/devicetree/bindings/arm/omap/mpu.txt b/Documentation/devicetree/bindings/arm/omap/mpu.txt
new file mode 100644
index 0000000..1a5a42c
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/omap/mpu.txt
@@ -0,0 +1,27 @@
+* TI - MPU (Main Processor Unit) subsystem
+
+The MPU subsystem contain one or several ARM cores
+depending of the version.
+The MPU contain CPUs, GIC, L2 cache and a local PRCM.
+
+Required properties:
+- compatible : Should be "ti,omap3-mpu" for OMAP3
+               Should be "ti,omap4-mpu" for OMAP4
+- ti,hwmods: "mpu"
+
+Examples:
+
+- For an OMAP4 SMP system:
+
+mpu {
+    compatible = "ti,omap4-mpu";
+    ti,hwmods = "mpu";
+};
+
+
+- For an OMAP3 monocore system:
+
+mpu {
+    compatible = "ti,omap3-mpu";
+    ti,hwmods = "mpu";
+};
diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt
new file mode 100644
index 0000000..dbdab40
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/omap/omap.txt
@@ -0,0 +1,43 @@
+* Texas Instruments OMAP
+
+OMAP is currently using a static file per SoC family to describe the
+IPs present in the SoC.
+On top of that an omap_device is created to extend the platform_device
+capabilities and to allow binding with one or several hwmods.
+The hwmods will contain all the information to build the device:
+adresse range, irq lines, dma lines, interconnect, PRCM register,
+clock domain, input clocks.
+For the moment just point to the existing hwmod, the next step will be
+to move data from hwmod to device-tree representation.
+
+
+Required properties:
+- compatible: Every devices present in OMAP SoC should be in the
+  form: "ti,XXX"
+- ti,hwmods: list of hwmod names (ascii strings), that comes from the OMAP
+  HW documentation, attached to a device. Must contain at least
+  one hwmod.
+
+Optional properties:
+- ti,no_idle_on_suspend: When present, it prevents the PM to idle the module
+  during suspend.
+
+
+Example:
+
+spinlock@1 {
+    compatible = "ti,omap4-spinlock";
+    ti,hwmods = "spinlock";
+};
+
+
+Boards:
+
+- OMAP3 BeagleBoard : Low cost community board
+  compatible = "ti,omap3-beagle", "ti,omap3"
+
+- OMAP4 SDP : Software Developement Board
+  compatible = "ti,omap4-sdp", "ti,omap4430"
+
+- OMAP4 PandaBoard : Low cost community board
+  compatible = "ti,omap4-panda", "ti,omap4430"
diff --git a/Documentation/devicetree/bindings/arm/picoxcell.txt b/Documentation/devicetree/bindings/arm/picoxcell.txt
new file mode 100644
index 0000000..e75c0ef
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/picoxcell.txt
@@ -0,0 +1,24 @@
+Picochip picoXcell device tree bindings.
+========================================
+
+Required root node properties:
+    - compatible:
+	- "picochip,pc7302-pc3x3" : PC7302 development board with PC3X3 device.
+	- "picochip,pc7302-pc3x2" : PC7302 development board with PC3X2 device.
+	- "picochip,pc3x3" : picoXcell PC3X3 device based board.
+	- "picochip,pc3x2" : picoXcell PC3X2 device based board.
+
+Timers required properties:
+    - compatible = "picochip,pc3x2-timer"
+    - interrupts : The single IRQ line for the timer.
+    - clock-freq : The frequency in HZ of the timer.
+    - reg : The register bank for the timer.
+
+Note: two timers are required - one for the scheduler clock and one for the
+event tick/NOHZ.
+
+VIC required properties:
+    - compatible = "arm,pl192-vic".
+    - interrupt-controller.
+    - reg : The register bank for the device.
+    - #interrupt-cells : Must be 1.
diff --git a/Documentation/devicetree/bindings/arm/primecell.txt b/Documentation/devicetree/bindings/arm/primecell.txt
index 1d5d7a8..951ca46 100644
--- a/Documentation/devicetree/bindings/arm/primecell.txt
+++ b/Documentation/devicetree/bindings/arm/primecell.txt
@@ -6,7 +6,9 @@
 
 Required properties:
 
-- compatible : should be a specific value for peripheral and "arm,primecell"
+- compatible : should be a specific name for the peripheral and
+               "arm,primecell".  The specific name will match the ARM
+               engineering name for the logic block in the form: "arm,pl???"
 
 Optional properties:
 
diff --git a/Documentation/devicetree/bindings/ata/calxeda-sata.txt b/Documentation/devicetree/bindings/ata/calxeda-sata.txt
new file mode 100644
index 0000000..79caa56
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/calxeda-sata.txt
@@ -0,0 +1,17 @@
+* Calxeda SATA Controller
+
+SATA nodes are defined to describe on-chip Serial ATA controllers.
+Each SATA controller should have its own node.
+
+Required properties:
+- compatible        : compatible list, contains "calxeda,hb-ahci"
+- interrupts        : <interrupt mapping for SATA IRQ>
+- reg               : <registers mapping>
+
+Example:
+        sata@ffe08000 {
+		compatible = "calxeda,hb-ahci";
+                reg = <0xffe08000 0x1000>;
+                interrupts = <115>;
+        };
+
diff --git a/Documentation/devicetree/bindings/crypto/picochip-spacc.txt b/Documentation/devicetree/bindings/crypto/picochip-spacc.txt
new file mode 100644
index 0000000..d8609ec
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/picochip-spacc.txt
@@ -0,0 +1,23 @@
+Picochip picoXcell SPAcc (Security Protocol Accelerator) bindings
+
+Picochip picoXcell devices contain crypto offload engines that may be used for
+IPSEC and femtocell layer 2 ciphering.
+
+Required properties:
+  - compatible : "picochip,spacc-ipsec" for the IPSEC offload engine
+    "picochip,spacc-l2" for the femtocell layer 2 ciphering engine.
+  - reg : Offset and length of the register set for this device
+  - interrupt-parent : The interrupt controller that controls the SPAcc
+    interrupt.
+  - interrupts : The interrupt line from the SPAcc.
+  - ref-clock : The input clock that drives the SPAcc.
+
+Example SPAcc node:
+
+spacc@10000 {
+	compatible = "picochip,spacc-ipsec";
+	reg = <0x100000 0x10000>;
+	interrupt-parent = <&vic0>;
+	interrupts = <24>;
+	ref-clock = <&ipsec_clk>, "ref";
+};
diff --git a/Documentation/devicetree/bindings/gpio/led.txt b/Documentation/devicetree/bindings/gpio/led.txt
index 064db92..141087c 100644
--- a/Documentation/devicetree/bindings/gpio/led.txt
+++ b/Documentation/devicetree/bindings/gpio/led.txt
@@ -8,7 +8,7 @@
 
 LED sub-node properties:
 - gpios :  Should specify the LED's GPIO, see "Specifying GPIO information
-  for devices" in Documentation/powerpc/booting-without-of.txt.  Active
+  for devices" in Documentation/devicetree/booting-without-of.txt.  Active
   low LEDs should be indicated using flags in the GPIO specifier.
 - label :  (optional) The label for this LED.  If omitted, the label is
   taken from the node name (excluding the unit address).
diff --git a/Documentation/devicetree/bindings/gpio/pl061-gpio.txt b/Documentation/devicetree/bindings/gpio/pl061-gpio.txt
new file mode 100644
index 0000000..a2c416b
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/pl061-gpio.txt
@@ -0,0 +1,10 @@
+ARM PL061 GPIO controller
+
+Required properties:
+- compatible : "arm,pl061", "arm,primecell"
+- #gpio-cells : Should be two. The first cell is the pin number and the
+  second cell is used to specify optional parameters:
+  - bit 0 specifies polarity (0 for normal, 1 for inverted)
+- gpio-controller : Marks the device node as a GPIO controller.
+- interrupts : Interrupt mapping for GPIO IRQ.
+
diff --git a/Documentation/devicetree/bindings/i2c/fsl-imx-i2c.txt b/Documentation/devicetree/bindings/i2c/fsl-imx-i2c.txt
new file mode 100644
index 0000000..f3cf43b
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/fsl-imx-i2c.txt
@@ -0,0 +1,25 @@
+* Freescale Inter IC (I2C) and High Speed Inter IC (HS-I2C) for i.MX
+
+Required properties:
+- compatible : Should be "fsl,<chip>-i2c"
+- reg : Should contain I2C/HS-I2C registers location and length
+- interrupts : Should contain I2C/HS-I2C interrupt
+
+Optional properties:
+- clock-frequency : Constains desired I2C/HS-I2C bus clock frequency in Hz.
+  The absence of the propoerty indicates the default frequency 100 kHz.
+
+Examples:
+
+i2c@83fc4000 { /* I2C2 on i.MX51 */
+	compatible = "fsl,imx51-i2c", "fsl,imx1-i2c";
+	reg = <0x83fc4000 0x4000>;
+	interrupts = <63>;
+};
+
+i2c@70038000 { /* HS-I2C on i.MX51 */
+	compatible = "fsl,imx51-i2c", "fsl,imx1-i2c";
+	reg = <0x70038000 0x4000>;
+	interrupts = <64>;
+	clock-frequency = <400000>;
+};
diff --git a/Documentation/devicetree/bindings/i2c/samsung-i2c.txt b/Documentation/devicetree/bindings/i2c/samsung-i2c.txt
new file mode 100644
index 0000000..38832c7
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/samsung-i2c.txt
@@ -0,0 +1,39 @@
+* Samsung's I2C controller
+
+The Samsung's I2C controller is used to interface with I2C devices.
+
+Required properties:
+  - compatible: value should be either of the following.
+      (a) "samsung, s3c2410-i2c", for i2c compatible with s3c2410 i2c.
+      (b) "samsung, s3c2440-i2c", for i2c compatible with s3c2440 i2c.
+  - reg: physical base address of the controller and length of memory mapped
+    region.
+  - interrupts: interrupt number to the cpu.
+  - samsung,i2c-sda-delay: Delay (in ns) applied to data line (SDA) edges.
+  - gpios: The order of the gpios should be the following: <SDA, SCL>.
+    The gpio specifier depends on the gpio controller.
+
+Optional properties:
+  - samsung,i2c-slave-addr: Slave address in multi-master enviroment. If not
+    specified, default value is 0.
+  - samsung,i2c-max-bus-freq: Desired frequency in Hz of the bus. If not
+    specified, the default value in Hz is 100000.
+
+Example:
+
+	i2c@13870000 {
+		compatible = "samsung,s3c2440-i2c";
+		reg = <0x13870000 0x100>;
+		interrupts = <345>;
+		samsung,i2c-sda-delay = <100>;
+		samsung,i2c-max-bus-freq = <100000>;
+		gpios = <&gpd1 2 0 /* SDA */
+			 &gpd1 3 0 /* SCL */>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		wm8994@1a {
+			compatible = "wlf,wm8994";
+			reg = <0x1a>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/mmc/nvidia-sdhci.txt b/Documentation/devicetree/bindings/mmc/nvidia-sdhci.txt
new file mode 100644
index 0000000..7e51154
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/nvidia-sdhci.txt
@@ -0,0 +1,27 @@
+* NVIDIA Tegra Secure Digital Host Controller
+
+This controller on Tegra family SoCs provides an interface for MMC, SD,
+and SDIO types of memory cards.
+
+Required properties:
+- compatible : Should be "nvidia,<chip>-sdhci"
+- reg : Should contain SD/MMC registers location and length
+- interrupts : Should contain SD/MMC interrupt
+
+Optional properties:
+- cd-gpios : Specify GPIOs for card detection
+- wp-gpios : Specify GPIOs for write protection
+- power-gpios : Specify GPIOs for power control
+- support-8bit : Boolean, indicates if 8-bit mode should be used.
+
+Example:
+
+sdhci@c8000200 {
+	compatible = "nvidia,tegra20-sdhci";
+	reg = <0xc8000200 0x200>;
+	interrupts = <47>;
+	cd-gpios = <&gpio 69 0>; /* gpio PI5 */
+	wp-gpios = <&gpio 57 0>; /* gpio PH1 */
+	power-gpios = <&gpio 155 0>; /* gpio PT3 */
+	support-8bit;
+};
diff --git a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt b/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
index 1a729f0..1ad80d5 100644
--- a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
+++ b/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
@@ -1,61 +1,24 @@
-CAN Device Tree Bindings
-------------------------
-2011 Freescale Semiconductor, Inc.
+Flexcan CAN contoller on Freescale's ARM and PowerPC system-on-a-chip (SOC).
 
-fsl,flexcan-v1.0 nodes
------------------------
-In addition to the required compatible-, reg- and interrupt-properties, you can
-also specify which clock source shall be used for the controller.
+Required properties:
 
-CPI Clock- Can Protocol Interface Clock
-	This CLK_SRC bit of CTRL(control register) selects the clock source to
-	the CAN Protocol Interface(CPI) to be either the peripheral clock
-	(driven by the PLL) or the crystal oscillator clock. The selected clock
-	is the one fed to the prescaler to generate the Serial Clock (Sclock).
-	The PRESDIV field of CTRL(control register) controls a prescaler that
-	generates the Serial Clock (Sclock), whose period defines the
-	time quantum used to compose the CAN waveform.
+- compatible : Should be "fsl,<processor>-flexcan"
 
-Can Engine Clock Source
-	There are two sources for CAN clock
-	- Platform Clock  It represents the bus clock
-	- Oscillator Clock
+  An implementation should also claim any of the following compatibles
+  that it is fully backwards compatible with:
 
-	Peripheral Clock (PLL)
-	--------------
-		     |
-		    ---------		      -------------
-		    |       |CPI Clock	      | Prescaler |       Sclock
-		    |       |---------------->| (1.. 256) |------------>
-		    ---------		      -------------
-                     |  |
-	--------------  ---------------------CLK_SRC
-	Oscillator Clock
+  - fsl,p1010-flexcan
 
-- fsl,flexcan-clock-source : CAN Engine Clock Source.This property selects
-			     the peripheral clock. PLL clock is fed to the
-			     prescaler to generate the Serial Clock (Sclock).
-			     Valid values are "oscillator" and "platform"
-			     "oscillator": CAN engine clock source is oscillator clock.
-			     "platform" The CAN engine clock source is the bus clock
-		             (platform clock).
+- reg : Offset and length of the register set for this device
+- interrupts : Interrupt tuple for this device
+- clock-frequency : The oscillator frequency driving the flexcan device
 
-- fsl,flexcan-clock-divider : for the reference and system clock, an additional
-			      clock divider can be specified.
-- clock-frequency: frequency required to calculate the bitrate for FlexCAN.
+Example:
 
-Note:
-	- v1.0 of flexcan-v1.0 represent the IP block version for P1010 SOC.
-	- P1010 does not have oscillator as the Clock Source.So the default
-	  Clock Source is platform clock.
-Examples:
-
-	can0@1c000 {
-		compatible = "fsl,flexcan-v1.0";
+	can@1c000 {
+		compatible = "fsl,p1010-flexcan";
 		reg = <0x1c000 0x1000>;
 		interrupts = <48 0x2>;
 		interrupt-parent = <&mpic>;
-		fsl,flexcan-clock-source = "platform";
-		fsl,flexcan-clock-divider = <2>;
-		clock-frequency = <fixed by u-boot>;
+		clock-frequency = <200000000>; // filled in by bootloader
 	};
diff --git a/Documentation/devicetree/bindings/net/smsc911x.txt b/Documentation/devicetree/bindings/net/smsc911x.txt
new file mode 100644
index 0000000..adb5b57
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/smsc911x.txt
@@ -0,0 +1,38 @@
+* Smart Mixed-Signal Connectivity (SMSC) LAN911x/912x Controller
+
+Required properties:
+- compatible : Should be "smsc,lan<model>", "smsc,lan9115"
+- reg : Address and length of the io space for SMSC LAN
+- interrupts : Should contain SMSC LAN interrupt line
+- interrupt-parent : Should be the phandle for the interrupt controller
+  that services interrupts for this device
+- phy-mode : String, operation mode of the PHY interface.
+  Supported values are: "mii", "gmii", "sgmii", "tbi", "rmii",
+  "rgmii", "rgmii-id", "rgmii-rxid", "rgmii-txid", "rtbi", "smii".
+
+Optional properties:
+- reg-shift : Specify the quantity to shift the register offsets by
+- reg-io-width : Specify the size (in bytes) of the IO accesses that
+  should be performed on the device.  Valid value for SMSC LAN is
+  2 or 4.  If it's omitted or invalid, the size would be 2.
+- smsc,irq-active-high : Indicates the IRQ polarity is active-high
+- smsc,irq-push-pull : Indicates the IRQ type is push-pull
+- smsc,force-internal-phy : Forces SMSC LAN controller to use
+  internal PHY
+- smsc,force-external-phy : Forces SMSC LAN controller to use
+  external PHY
+- smsc,save-mac-address : Indicates that mac address needs to be saved
+  before resetting the controller
+- local-mac-address : 6 bytes, mac address
+
+Examples:
+
+lan9220@f4000000 {
+	compatible = "smsc,lan9220", "smsc,lan9115";
+	reg = <0xf4000000 0x2000000>;
+	phy-mode = "mii";
+	interrupt-parent = <&gpio1>;
+	interrupts = <31>;
+	reg-io-width = <4>;
+	smsc,irq-push-pull;
+};
diff --git a/Documentation/devicetree/bindings/pinmux/pinmux_nvidia.txt b/Documentation/devicetree/bindings/pinmux/pinmux_nvidia.txt
new file mode 100644
index 0000000..36f82db
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinmux/pinmux_nvidia.txt
@@ -0,0 +1,5 @@
+NVIDIA Tegra 2 pinmux controller
+
+Required properties:
+- compatible : "nvidia,tegra20-pinmux"
+
diff --git a/Documentation/devicetree/bindings/serial/rs485.txt b/Documentation/devicetree/bindings/serial/rs485.txt
new file mode 100644
index 0000000..1e753c6
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/rs485.txt
@@ -0,0 +1,31 @@
+* RS485 serial communications
+
+The RTS signal is capable of automatically controlling line direction for
+the built-in half-duplex mode.
+The properties described hereafter shall be given to a half-duplex capable
+UART node.
+
+Required properties:
+- rs485-rts-delay: prop-encoded-array <a b> where:
+  * a is the delay beteween rts signal and beginning of data sent in milliseconds.
+      it corresponds to the delay before sending data.
+  * b is the delay between end of data sent and rts signal in milliseconds
+      it corresponds to the delay after sending data and actual release of the line.
+
+Optional properties:
+- linux,rs485-enabled-at-boot-time: empty property telling to enable the rs485
+  feature at boot time. It can be disabled later with proper ioctl.
+- rs485-rx-during-tx: empty property that enables the receiving of data even
+  whilst sending data.
+
+RS485 example for Atmel USART:
+	usart0: serial@fff8c000 {
+		compatible = "atmel,at91sam9260-usart";
+		reg = <0xfff8c000 0x4000>;
+		interrupts = <7>;
+		atmel,use-dma-rx;
+		atmel,use-dma-tx;
+		linux,rs485-enabled-at-boot-time;
+		rs485-rts-delay = <0 200>;		// in milliseconds
+	};
+
diff --git a/Documentation/devicetree/bindings/spi/spi_pl022.txt b/Documentation/devicetree/bindings/spi/spi_pl022.txt
new file mode 100644
index 0000000..306ec3f
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi_pl022.txt
@@ -0,0 +1,12 @@
+ARM PL022 SPI controller
+
+Required properties:
+- compatible : "arm,pl022", "arm,primecell"
+- reg : Offset and length of the register set for the device
+- interrupts : Should contain SPI controller interrupt
+
+Optional properties:
+- cs-gpios : should specify GPIOs 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.
+
diff --git a/Documentation/devicetree/bindings/tty/serial/atmel-usart.txt b/Documentation/devicetree/bindings/tty/serial/atmel-usart.txt
new file mode 100644
index 0000000..a49d9a1
--- /dev/null
+++ b/Documentation/devicetree/bindings/tty/serial/atmel-usart.txt
@@ -0,0 +1,27 @@
+* Atmel Universal Synchronous Asynchronous Receiver/Transmitter (USART)
+
+Required properties:
+- compatible: Should be "atmel,<chip>-usart"
+  The compatible <chip> indicated will be the first SoC to support an
+  additional mode or an USART new feature.
+- reg: Should contain registers location and length
+- interrupts: Should contain interrupt
+
+Optional properties:
+- atmel,use-dma-rx: use of PDC or DMA for receiving data
+- atmel,use-dma-tx: use of PDC or DMA for transmitting data
+
+<chip> compatible description:
+- at91rm9200:  legacy USART support
+- at91sam9260: generic USART implementation for SAM9 SoCs
+
+Example:
+
+	usart0: serial@fff8c000 {
+		compatible = "atmel,at91sam9260-usart";
+		reg = <0xfff8c000 0x4000>;
+		interrupts = <7>;
+		atmel,use-dma-rx;
+		atmel,use-dma-tx;
+	};
+
diff --git a/Documentation/devicetree/bindings/tty/serial/msm_serial.txt b/Documentation/devicetree/bindings/tty/serial/msm_serial.txt
new file mode 100644
index 0000000..aef383e
--- /dev/null
+++ b/Documentation/devicetree/bindings/tty/serial/msm_serial.txt
@@ -0,0 +1,27 @@
+* Qualcomm MSM UART
+
+Required properties:
+- compatible :
+	- "qcom,msm-uart", and one of "qcom,msm-hsuart" or
+	  "qcom,msm-lsuart".
+- reg : offset and length of the register set for the device
+	for the hsuart operating in compatible mode, there should be a
+	second pair describing the gsbi registers.
+- interrupts : should contain the uart interrupt.
+
+There are two different UART blocks used in MSM devices,
+"qcom,msm-hsuart" and "qcom,msm-lsuart".  The msm-serial driver is
+able to handle both of these, and matches against the "qcom,msm-uart"
+as the compatibility.
+
+The registers for the "qcom,msm-hsuart" device need to specify both
+register blocks, even for the common driver.
+
+Example:
+
+	uart@19c400000 {
+		compatible = "qcom,msm-hsuart", "qcom,msm-uart";
+		reg = <0x19c40000 0x1000>,
+		      <0x19c00000 0x1000>;
+		interrupts = <195>;
+	};
diff --git a/Documentation/devicetree/bindings/tty/serial/snps-dw-apb-uart.txt b/Documentation/devicetree/bindings/tty/serial/snps-dw-apb-uart.txt
new file mode 100644
index 0000000..f13f1c5
--- /dev/null
+++ b/Documentation/devicetree/bindings/tty/serial/snps-dw-apb-uart.txt
@@ -0,0 +1,25 @@
+* Synopsys DesignWare ABP UART
+
+Required properties:
+- compatible : "snps,dw-apb-uart"
+- reg : offset and length of the register set for the device.
+- interrupts : should contain uart interrupt.
+- clock-frequency : the input clock frequency for the UART.
+
+Optional properties:
+- reg-shift : quantity to shift the register offsets by.  If this property is
+  not present then the register offsets are not shifted.
+- reg-io-width : the size (in bytes) of the IO accesses that should be
+  performed on the device.  If this property is not present then single byte
+  accesses are used.
+
+Example:
+
+	uart@80230000 {
+		compatible = "snps,dw-apb-uart";
+		reg = <0x80230000 0x100>;
+		clock-frequency = <3686400>;
+		interrupts = <10>;
+		reg-shift = <2>;
+		reg-io-width = <4>;
+	};
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
new file mode 100644
index 0000000..e855278
--- /dev/null
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -0,0 +1,40 @@
+Device tree binding vendor prefix registry.  Keep list in alphabetical order.
+
+This isn't an exhaustive list, but you should add new prefixes to it before
+using them to avoid name-space collisions.
+
+adi	Analog Devices, Inc.
+amcc	Applied Micro Circuits Corporation (APM, formally AMCC)
+apm	Applied Micro Circuits Corporation (APM)
+arm	ARM Ltd.
+atmel	Atmel Corporation
+chrp	Common Hardware Reference Platform
+dallas	Maxim Integrated Products (formerly Dallas Semiconductor)
+denx	Denx Software Engineering
+epson	Seiko Epson Corp.
+est	ESTeem Wireless Modems
+fsl	Freescale Semiconductor
+GEFanuc	GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+gef	GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+hp	Hewlett Packard
+ibm	International Business Machines (IBM)
+idt	Integrated Device Technologies, Inc.
+intercontrol	Inter Control Group
+linux	Linux-specific binding
+marvell	Marvell Technology Group Ltd.
+maxim	Maxim Integrated Products
+mosaixtech	Mosaix Technologies, Inc.
+national	National Semiconductor
+nintendo	Nintendo
+nvidia	NVIDIA
+nxp	NXP Semiconductors
+powervr	Imagination Technologies
+qcom	Qualcomm, Inc.
+ramtron	Ramtron International
+samsung	Samsung Semiconductor
+schindler	Schindler
+simtek
+sirf	SiRF Technology, Inc.
+stericsson	ST-Ericsson
+ti	Texas Instruments
+xlnx	Xilinx
diff --git a/Documentation/devicetree/bindings/virtio/mmio.txt b/Documentation/devicetree/bindings/virtio/mmio.txt
new file mode 100644
index 0000000..5069c1b
--- /dev/null
+++ b/Documentation/devicetree/bindings/virtio/mmio.txt
@@ -0,0 +1,17 @@
+* virtio memory mapped device
+
+See http://ozlabs.org/~rusty/virtio-spec/ for more details.
+
+Required properties:
+
+- compatible:	"virtio,mmio" compatibility string
+- reg:		control registers base address and size including configuration space
+- interrupts:	interrupt generated by the device
+
+Example:
+
+	virtio_block@3000 {
+		compatible = "virtio,mmio";
+		reg = <0x3000 0x100>;
+		interrupts = <41>;
+	}
diff --git a/Documentation/driver-model/binding.txt b/Documentation/driver-model/binding.txt
index f7ec9d6..abfc8e2 100644
--- a/Documentation/driver-model/binding.txt
+++ b/Documentation/driver-model/binding.txt
@@ -48,10 +48,6 @@
 and actually register it with the class, which happens with the
 class's register_dev callback.
 
-NOTE: The device class structures and core routines to manipulate them
-are not in the mainline kernel, so the discussion is still a bit
-speculative. 
-
 
 Driver
 ~~~~~~
diff --git a/Documentation/driver-model/device.txt b/Documentation/driver-model/device.txt
index bdefe72..1e70220 100644
--- a/Documentation/driver-model/device.txt
+++ b/Documentation/driver-model/device.txt
@@ -45,33 +45,52 @@
 			 const char *buf, size_t count);
 };
 
-Attributes of devices can be exported via drivers using a simple
-procfs-like interface. 
+Attributes of devices can be exported by a device driver through sysfs.
 
 Please see Documentation/filesystems/sysfs.txt for more information
 on how sysfs works.
 
+As explained in Documentation/kobject.txt, device attributes must be be
+created before the KOBJ_ADD uevent is generated. The only way to realize
+that is by defining an attribute group.
+
 Attributes are declared using a macro called DEVICE_ATTR:
 
 #define DEVICE_ATTR(name,mode,show,store)
 
 Example:
 
-DEVICE_ATTR(power,0644,show_power,store_power);
+static DEVICE_ATTR(type, 0444, show_type, NULL);
+static DEVICE_ATTR(power, 0644, show_power, store_power);
 
-This declares a structure of type struct device_attribute named
-'dev_attr_power'. This can then be added and removed to the device's
-directory using:
+This declares two structures of type struct device_attribute with respective
+names 'dev_attr_type' and 'dev_attr_power'. These two attributes can be
+organized as follows into a group:
 
-int device_create_file(struct device *device, struct device_attribute * entry);
-void device_remove_file(struct device * dev, struct device_attribute * attr);
+static struct attribute *dev_attrs[] = {
+	&dev_attr_type.attr,
+	&dev_attr_power.attr,
+	NULL,
+};
 
-Example:
+static struct attribute_group dev_attr_group = {
+	.attrs = dev_attrs,
+};
 
-device_create_file(dev,&dev_attr_power);
-device_remove_file(dev,&dev_attr_power);
+static const struct attribute_group *dev_attr_groups[] = {
+	&dev_attr_group,
+	NULL,
+};
 
-The file name will be 'power' with a mode of 0644 (-rw-r--r--).
+This array of groups can then be associated with a device by setting the
+group pointer in struct device before device_register() is invoked:
+
+      dev->groups = dev_attr_groups;
+      device_register(dev);
+
+The device_register() function will use the 'groups' pointer to create the
+device attributes and the device_unregister() function will use this pointer
+to remove the device attributes.
 
 Word of warning:  While the kernel allows device_create_file() and
 device_remove_file() to be called on a device at any time, userspace has
@@ -84,24 +103,4 @@
 This is important for device driver that need to publish additional
 attributes for a device at driver probe time.  If the device driver simply
 calls device_create_file() on the device structure passed to it, then
-userspace will never be notified of the new attributes.  Instead, it should
-probably use class_create() and class->dev_attrs to set up a list of
-desired attributes in the modules_init function, and then in the .probe()
-hook, and then use device_create() to create a new device as a child
-of the probed device.  The new device will generate a new uevent and
-properly advertise the new attributes to userspace.
-
-For example, if a driver wanted to add the following attributes:
-struct device_attribute mydriver_attribs[] = {
-	__ATTR(port_count, 0444, port_count_show),
-	__ATTR(serial_number, 0444, serial_number_show),
-	NULL
-};
-
-Then in the module init function is would do:
-	mydriver_class = class_create(THIS_MODULE, "my_attrs");
-	mydriver_class.dev_attr = mydriver_attribs;
-
-And assuming 'dev' is the struct device passed into the probe hook, the driver
-probe function would do something like:
-	device_create(&mydriver_class, dev, chrdev, &private_data, "my_name");
+userspace will never be notified of the new attributes.
diff --git a/Documentation/dvb/get_dvb_firmware b/Documentation/dvb/get_dvb_firmware
index c466f58..e67be7a 100755
--- a/Documentation/dvb/get_dvb_firmware
+++ b/Documentation/dvb/get_dvb_firmware
@@ -27,7 +27,8 @@
 		"or51211", "or51132_qam", "or51132_vsb", "bluebird",
 		"opera1", "cx231xx", "cx18", "cx23885", "pvrusb2", "mpc718",
 		"af9015", "ngene", "az6027", "lme2510_lg", "lme2510c_s7395",
-		"lme2510c_s7395_old", "drxk", "drxk_terratec_h5");
+		"lme2510c_s7395_old", "drxk", "drxk_terratec_h5", "tda10071",
+		"it9135" );
 
 # Check args
 syntax() if (scalar(@ARGV) != 1);
@@ -575,19 +576,10 @@
 }
 
 sub az6027{
-    my $file = "AZ6027_Linux_Driver.tar.gz";
-    my $url = "http://linux.terratec.de/files/$file";
     my $firmware = "dvb-usb-az6027-03.fw";
+    my $url = "http://linux.terratec.de/files/TERRATEC_S7/$firmware";
 
-    wgetfile($file, $url);
-
-    #untar
-    if( system("tar xzvf $file $firmware")){
-        die "failed to untar firmware";
-    }
-    if( system("rm $file")){
-        die ("unable to remove unnecessary files");
-    }
+    wgetfile($firmware, $url);
 
     $firmware;
 }
@@ -665,6 +657,41 @@
     "$fwfile"
 }
 
+sub it9135 {
+    my $url = "http://kworld.server261.com/kworld/CD/ITE_TiVme/V1.00/";
+    my $zipfile = "Driver_V10.323.1.0412.100412.zip";
+    my $hash = "79b597dc648698ed6820845c0c9d0d37";
+    my $tmpdir = tempdir(DIR => "/tmp", CLEANUP => 0);
+    my $drvfile = "Driver_V10.323.1.0412.100412/Data/x86/IT9135BDA.sys";
+    my $fwfile = "dvb-usb-it9137-01.fw";
+
+    checkstandard();
+
+    wgetfile($zipfile, $url . $zipfile);
+    verify($zipfile, $hash);
+    unzip($zipfile, $tmpdir);
+    extract("$tmpdir/$drvfile", 69632, 5731, "$fwfile");
+
+    "$fwfile"
+}
+
+sub tda10071 {
+    my $sourcefile = "PCTV_460e_reference.zip";
+    my $url = "ftp://ftp.pctvsystems.com/TV/driver/PCTV%2070e%2080e%20100e%20320e%20330e%20800e/";
+    my $hash = "4403de903bf2593464c8d74bbc200a57";
+    my $fwfile = "dvb-fe-tda10071.fw";
+    my $tmpdir = tempdir(DIR => "/tmp", CLEANUP => 1);
+
+    checkstandard();
+
+    wgetfile($sourcefile, $url . $sourcefile);
+    verify($sourcefile, $hash);
+    unzip($sourcefile, $tmpdir);
+    extract("$tmpdir/PCTV\ 70e\ 80e\ 100e\ 320e\ 330e\ 800e/32\ bit/emOEM.sys", 0x67d38, 40504, $fwfile);
+
+    "$fwfile";
+}
+
 # ---------------------------------------------------------------
 # Utilities
 
diff --git a/Documentation/dvb/it9137.txt b/Documentation/dvb/it9137.txt
new file mode 100644
index 0000000..9e6726e
--- /dev/null
+++ b/Documentation/dvb/it9137.txt
@@ -0,0 +1,9 @@
+To extract firmware for Kworld UB499-2T (id 1b80:e409) you need to copy the
+following file(s) to this directory.
+
+IT9135BDA.sys Dated Mon 22 Mar 2010 02:20:08 GMT
+
+extract using dd
+dd if=IT9135BDA.sys ibs=1 skip=69632 count=5731 of=dvb-usb-it9137-01.fw
+
+copy to default firmware location.
diff --git a/Documentation/email-clients.txt b/Documentation/email-clients.txt
index a0b58e2..860c29a 100644
--- a/Documentation/email-clients.txt
+++ b/Documentation/email-clients.txt
@@ -199,18 +199,16 @@
 
 To beat some sense out of the internal editor, do this:
 
-- Under account settings, composition and addressing, uncheck "Compose
-  messages in HTML format".
-
 - Edit your Thunderbird config settings so that it won't use format=flowed.
   Go to "edit->preferences->advanced->config editor" to bring up the
   thunderbird's registry editor, and set "mailnews.send_plaintext_flowed" to
   "false".
 
-- Enable "preformat" mode: Shft-click on the Write icon to bring up the HTML
-  composer, select "Preformat" from the drop-down box just under the subject
-  line, then close the message without saving.  (This setting also applies to
-  the text composer, but the only control for it is in the HTML composer.)
+- Disable HTML Format: Set "mail.identity.id1.compose_html" to "false".
+
+- Enable "preformat" mode: Set "editor.quotesPreformatted" to "true".
+
+- Enable UTF8: Set "prefs.converted-to-utf8" to "true".
 
 - Install the "toggle wordwrap" extension.  Download the file from:
     https://addons.mozilla.org/thunderbird/addon/2351/
diff --git a/Documentation/fault-injection/fault-injection.txt b/Documentation/fault-injection/fault-injection.txt
index 82a5d25..ba4be8b 100644
--- a/Documentation/fault-injection/fault-injection.txt
+++ b/Documentation/fault-injection/fault-injection.txt
@@ -21,6 +21,11 @@
   /sys/block/<device>/make-it-fail or
   /sys/block/<device>/<partition>/make-it-fail. (generic_make_request())
 
+o fail_mmc_request
+
+  injects MMC data errors on devices permitted by setting
+  debugfs entries under /sys/kernel/debug/mmc0/fail_mmc_request
+
 Configure fault-injection capabilities behavior
 -----------------------------------------------
 
@@ -115,7 +120,8 @@
 
 	failslab=
 	fail_page_alloc=
-	fail_make_request=<interval>,<probability>,<space>,<times>
+	fail_make_request=
+	mmc_core.fail_request=<interval>,<probability>,<space>,<times>
 
 How to add new fault injection capability
 -----------------------------------------
diff --git a/Documentation/fb/udlfb.txt b/Documentation/fb/udlfb.txt
index 7fdde2a..57d2f29 100644
--- a/Documentation/fb/udlfb.txt
+++ b/Documentation/fb/udlfb.txt
@@ -87,23 +87,38 @@
 options, however.
 
 From the command line, pass options to modprobe
-modprobe udlfb defio=1 console=1
+modprobe udlfb fb_defio=0 console=1 shadow=1
 
-Or for permanent option, create file like /etc/modprobe.d/options with text
-options udlfb defio=1 console=1
+Or modify options on the fly at /sys/module/udlfb/parameters directory via
+sudo nano fb_defio
+change the parameter in place, and save the file.
 
-Accepted options:
+Unplug/replug USB device to apply with new settings
+
+Or for permanent option, create file like /etc/modprobe.d/udlfb.conf with text
+options udlfb fb_defio=0 console=1 shadow=1
+
+Accepted boolean options:
 
 fb_defio	Make use of the fb_defio (CONFIG_FB_DEFERRED_IO) kernel
 		module to track changed areas of the framebuffer by page faults.
-        	Standard fbdev applications that use mmap but that do not
-		report damage, may be able to work with this enabled.
-		Disabled by default because of overhead and other issues.
+		Standard fbdev applications that use mmap but that do not
+		report damage, should be able to work with this enabled.
+		Disable when running with X server that supports reporting
+		changed regions via ioctl, as this method is simpler,
+		more stable, and higher performance.
+		default: fb_defio=1
 
-console		Allow fbcon to attach to udlfb provided framebuffers. This
-		is disabled by default because fbcon will aggressively consume
-		the first framebuffer it finds, which isn't usually what the
-		user wants in the case of USB displays.
+console	Allow fbcon to attach to udlfb provided framebuffers.
+		Can be disabled if fbcon and other clients
+		(e.g. X with --shared-vt) are in conflict.
+		default: console=1
+
+shadow		Allocate a 2nd framebuffer to shadow what's currently across
+		the USB bus in device memory. If any pixels are unchanged,
+		do not transmit. Spends host memory to save USB transfers.
+		Enabled by default. Only disable on very low memory systems.
+		default: shadow=1
 
 Sysfs Attributes
 ================
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index c4a6e14..3d84912 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -133,41 +133,6 @@
 
 ---------------------------
 
-What:	sys_sysctl
-When:	September 2010
-Option: CONFIG_SYSCTL_SYSCALL
-Why:	The same information is available in a more convenient from
-	/proc/sys, and none of the sysctl variables appear to be
-	important performance wise.
-
-	Binary sysctls are a long standing source of subtle kernel
-	bugs and security issues.
-
-	When I looked several months ago all I could find after
-	searching several distributions were 5 user space programs and
-	glibc (which falls back to /proc/sys) using this syscall.
-
-	The man page for sysctl(2) documents it as unusable for user
-	space programs.
-
-	sysctl(2) is not generally ABI compatible to a 32bit user
-	space application on a 64bit and a 32bit kernel.
-
-	For the last several months the policy has been no new binary
-	sysctls and no one has put forward an argument to use them.
-
-	Binary sysctls issues seem to keep happening appearing so
-	properly deprecating them (with a warning to user space) and a
-	2 year grace warning period will mean eventually we can kill
-	them and end the pain.
-
-	In the mean time individual binary sysctls can be dealt with
-	in a piecewise fashion.
-
-Who:	Eric Biederman <ebiederm@xmission.com>
-
----------------------------
-
 What:	/proc/<pid>/oom_adj
 When:	August 2012
 Why:	/proc/<pid>/oom_adj allows userspace to influence the oom killer's
@@ -495,29 +460,6 @@
 
 ----------------------------
 
-What:	Support for UVCIOC_CTRL_ADD in the uvcvideo driver
-When:	3.2
-Why:	The information passed to the driver by this ioctl is now queried
-	dynamically from the device.
-Who:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
-
-----------------------------
-
-What:	Support for UVCIOC_CTRL_MAP_OLD in the uvcvideo driver
-When:	3.2
-Why:	Used only by applications compiled against older driver versions.
-	Superseded by UVCIOC_CTRL_MAP which supports V4L2 menu controls.
-Who:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
-
-----------------------------
-
-What:	Support for UVCIOC_CTRL_GET and UVCIOC_CTRL_SET in the uvcvideo driver
-When:	3.2
-Why:	Superseded by the UVCIOC_CTRL_QUERY ioctl.
-Who:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
-
-----------------------------
-
 What:	Support for driver specific ioctls in the pwc driver (everything
 	defined in media/pwc-ioctl.h)
 When:	3.3
@@ -592,3 +534,20 @@
 	interface that was used by acer-wmi driver. It will replaced by
 	information log when acer-wmi initial.
 Who:    Lee, Chun-Yi <jlee@novell.com>
+
+----------------------------
+
+What:	The XFS nodelaylog mount option
+When:	3.3
+Why:	The delaylog mode that has been the default since 2.6.39 has proven
+	stable, and the old code is in the way of additional improvements in
+	the log code.
+Who:	Christoph Hellwig <hch@lst.de>
+
+----------------------------
+
+What:	iwlagn alias support
+When:	3.5
+Why:	The iwlagn module has been renamed iwlwifi.  The alias will be around
+	for backward compatibility for several cycles and then dropped.
+Who:	Don Fry <donald.h.fry@intel.com>
diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt
index 13de64c..2c03214 100644
--- a/Documentation/filesystems/9p.txt
+++ b/Documentation/filesystems/9p.txt
@@ -92,7 +92,7 @@
 
   wfdno=n	the file descriptor for writing with trans=fd
 
-  maxdata=n	the number of bytes to use for 9p packet payload (msize)
+  msize=n	the number of bytes to use for 9p packet payload
 
   port=n	port to connect to on the remote server
 
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 6533807..d819ba1 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -29,6 +29,7 @@
 d_compare:	yes		no		no		maybe
 d_delete:	no		yes		no		no
 d_release:	no		no		yes		no
+d_prune:        no              yes             no              no
 d_iput:		no		no		yes		no
 d_dname:	no		no		no		no
 d_automount:	no		no		yes		no
diff --git a/Documentation/filesystems/befs.txt b/Documentation/filesystems/befs.txt
index 6e49c36..da45e6c 100644
--- a/Documentation/filesystems/befs.txt
+++ b/Documentation/filesystems/befs.txt
@@ -27,7 +27,7 @@
 Does anyone know of a more current email address for Makoto? He doesn't
 respond to the address given above...
 
-Current maintainer: Sergey S. Kostyliov <rathamahata@php4.ru>
+This filesystem doesn't have a maintainer.
 
 WHAT IS THIS DRIVER?
 ==================
diff --git a/Documentation/filesystems/caching/object.txt b/Documentation/filesystems/caching/object.txt
index e8b0a35..5831334 100644
--- a/Documentation/filesystems/caching/object.txt
+++ b/Documentation/filesystems/caching/object.txt
@@ -127,9 +127,9 @@
 PROVISION OF CPU TIME
 ---------------------
 
-The work to be done by the various states is given CPU time by the threads of
-the slow work facility (see Documentation/slow-work.txt).  This is used in
-preference to the workqueue facility because:
+The work to be done by the various states was given CPU time by the threads of
+the slow work facility.  This was used in preference to the workqueue facility
+because:
 
  (1) Threads may be completely occupied for very long periods of time by a
      particular work item.  These state actions may be doing sequences of
diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt
index 22f3a0e..b100adc 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -73,14 +73,6 @@
 			also be used to enable or disable barriers, for
 			consistency with other ext3 mount options.
 
-orlov		(*)	This enables the new Orlov block allocator. It is
-			enabled by default.
-
-oldalloc		This disables the Orlov block allocator and enables
-			the old block allocator.  Orlov should have better
-			performance - we'd like to get some feedback if it's
-			the contrary for you.
-
 user_xattr		Enables Extended User Attributes.  Additionally, you
 			need to have extended attribute support enabled in the
 			kernel configuration (CONFIG_EXT3_FS_XATTR).  See the
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 232a575..4917cf2 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -160,7 +160,9 @@
                      	lead to any number of problems.
 
 data=journal		All data are committed into the journal prior to being
-			written into the main file system.
+			written into the main file system.  Enabling
+			this mode will disable delayed allocation and
+			O_DIRECT support.
 
 data=ordered	(*)	All data are forced directly out to the main file
 			system prior to its metadata being committed to the
@@ -201,30 +203,19 @@
 			table readahead algorithm will pre-read into
 			the buffer cache.  The default value is 32 blocks.
 
-orlov		(*)	This enables the new Orlov block allocator. It is
-			enabled by default.
-
-oldalloc		This disables the Orlov block allocator and enables
-			the old block allocator.  Orlov should have better
-			performance - we'd like to get some feedback if it's
-			the contrary for you.
-
-user_xattr		Enables Extended User Attributes.  Additionally, you
-			need to have extended attribute support enabled in the
-			kernel configuration (CONFIG_EXT4_FS_XATTR).  See the
-			attr(5) manual page and http://acl.bestbits.at/ to
-			learn more about extended attributes.
-
-nouser_xattr		Disables Extended User Attributes.
-
-acl			Enables POSIX Access Control Lists support.
-			Additionally, you need to have ACL support enabled in
-			the kernel configuration (CONFIG_EXT4_FS_POSIX_ACL).
-			See the acl(5) manual page and http://acl.bestbits.at/
-			for more information.
+nouser_xattr		Disables Extended User Attributes. If you have extended
+			attribute support enabled in the kernel configuration
+			(CONFIG_EXT4_FS_XATTR), extended attribute support
+			is enabled by default on mount. See the attr(5) manual
+			page and http://acl.bestbits.at/ for more information
+			about extended attributes.
 
 noacl			This option disables POSIX Access Control List
-			support.
+			support. If ACL support is enabled in the kernel
+			configuration (CONFIG_EXT4_FS_POSIX_ACL), ACL is
+			enabled by default on mount. See the acl(5) manual
+			page and http://acl.bestbits.at/ for more information
+			about acl.
 
 bsddf		(*)	Make 'df' act like BSD.
 minixdf			Make 'df' act like Minix.
@@ -419,8 +410,8 @@
 In the event of a crash, the journal can be replayed, bringing both data and
 metadata into a consistent state.  This mode is the slowest except when data
 needs to be read from and written to disk at the same time where it
-outperforms all others modes.  Currently ext4 does not have delayed
-allocation support if this data journalling mode is selected.
+outperforms all others modes.  Enabling this mode will disable delayed
+allocation and O_DIRECT support.
 
 /proc entries
 =============
diff --git a/Documentation/filesystems/hfs.txt b/Documentation/filesystems/hfs.txt
index bd0fa770..d096df6 100644
--- a/Documentation/filesystems/hfs.txt
+++ b/Documentation/filesystems/hfs.txt
@@ -1,3 +1,4 @@
+Note: This filesystem doesn't have a maintainer.
 
 Macintosh HFS Filesystem for Linux
 ==================================
@@ -76,8 +77,6 @@
 Credits
 =======
 
-The HFS drivers was written by Paul H. Hargrovea (hargrove@sccm.Stanford.EDU)
-and is now maintained by Roman Zippel (roman@ardistech.com) at Ardis
-Technologies.
-Roman rewrote large parts of the code and brought in btree routines derived
-from Brad Boyer's hfsplus driver (also maintained by Roman now).
+The HFS drivers was written by Paul H. Hargrovea (hargrove@sccm.Stanford.EDU).
+Roman Zippel (roman@ardistech.com) rewrote large parts of the code and brought
+in btree routines derived from Brad Boyer's hfsplus driver.
diff --git a/Documentation/filesystems/inotify.txt b/Documentation/filesystems/inotify.txt
index 59a919f..cfd0271 100644
--- a/Documentation/filesystems/inotify.txt
+++ b/Documentation/filesystems/inotify.txt
@@ -194,7 +194,8 @@
 Each watch is associated with an inotify_watch structure.  Watches are chained
 off of each associated inotify_handle and each associated inode.
 
-See fs/inotify.c and fs/inotify_user.c for the locking and lifetime rules.
+See fs/notify/inotify/inotify_fsnotify.c and fs/notify/inotify/inotify_user.c
+for the locking and lifetime rules.
 
 
 (vi) Rationale
diff --git a/Documentation/filesystems/locks.txt b/Documentation/filesystems/locks.txt
index fab857a..2cf8108 100644
--- a/Documentation/filesystems/locks.txt
+++ b/Documentation/filesystems/locks.txt
@@ -53,11 +53,12 @@
 1.3 Mandatory Locking As A Mount Option
 ---------------------------------------
 
-Mandatory locking, as described in 'Documentation/filesystems/mandatory.txt'
-was prior to this release a general configuration option that was valid for
-all mounted filesystems.  This had a number of inherent dangers, not the
-least of which was the ability to freeze an NFS server by asking it to read
-a file for which a mandatory lock existed.
+Mandatory locking, as described in
+'Documentation/filesystems/mandatory-locking.txt' was prior to this release a
+general configuration option that was valid for all mounted filesystems.  This
+had a number of inherent dangers, not the least of which was the ability to
+freeze an NFS server by asking it to read a file for which a mandatory lock
+existed.
 
 From this release of the kernel, mandatory locking can be turned on and off
 on a per-filesystem basis, using the mount options 'mand' and 'nomand'.
diff --git a/Documentation/filesystems/nfs/idmapper.txt b/Documentation/filesystems/nfs/idmapper.txt
index 9c8fd61..120fd3c 100644
--- a/Documentation/filesystems/nfs/idmapper.txt
+++ b/Documentation/filesystems/nfs/idmapper.txt
@@ -47,7 +47,7 @@
 this case, /some/other/program will handle all uid lookups and
 /usr/sbin/nfs.idmap will handle gid, user, and group lookups.
 
-See <file:Documentation/security/keys-request-keys.txt> for more information
+See <file:Documentation/security/keys-request-key.txt> for more information
 about the request-key function.
 
 
diff --git a/Documentation/filesystems/pohmelfs/design_notes.txt b/Documentation/filesystems/pohmelfs/design_notes.txt
index dcf8335..8aef9133 100644
--- a/Documentation/filesystems/pohmelfs/design_notes.txt
+++ b/Documentation/filesystems/pohmelfs/design_notes.txt
@@ -58,8 +58,9 @@
 POHMELFS clients operate with a working set of servers and are capable of balancing read-only
 operations (like lookups or directory listings) between them according to IO priorities.
 Administrators can add or remove servers from the set at run-time via special commands (described
-in Documentation/pohmelfs/info.txt file). Writes are replicated to all servers, which are connected
-with write permission turned on. IO priority and permissions can be changed in run-time.
+in Documentation/filesystems/pohmelfs/info.txt file). Writes are replicated to all servers, which
+are connected with write permission turned on. IO priority and permissions can be changed in
+run-time.
 
 POHMELFS is capable of full data channel encryption and/or strong crypto hashing.
 One can select any kernel supported cipher, encryption mode, hash type and operation mode
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index db3b1ab..0ec91f0 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -1263,7 +1263,7 @@
 This chapter  is  heavily  based  on the documentation included in the pre 2.2
 kernels, and became part of it in version 2.2.1 of the Linux kernel.
 
-Please see: Documentation/sysctls/ directory for descriptions of these
+Please see: Documentation/sysctl/ directory for descriptions of these
 entries.
 
 ------------------------------------------------------------------------------
diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt
index 597f728..07235ca 100644
--- a/Documentation/filesystems/sysfs.txt
+++ b/Documentation/filesystems/sysfs.txt
@@ -4,7 +4,7 @@
 Patrick Mochel	<mochel@osdl.org>
 Mike Murphy <mamurph@cs.clemson.edu>
 
-Revised:    15 July 2010
+Revised:    16 August 2011
 Original:   10 January 2003
 
 
@@ -370,3 +370,11 @@
 void driver_remove_file(struct device_driver *, const struct driver_attribute *);
 
 
+Documentation
+~~~~~~~~~~~~~
+
+The sysfs directory structure and the attributes in each directory define an
+ABI between the kernel and user space. As for any ABI, it is important that
+this ABI is stable and properly documented. All new sysfs attributes must be
+documented in Documentation/ABI. See also Documentation/ABI/README for more
+information.
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 52d8fb8..43cbd08 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -1053,9 +1053,6 @@
 	and the dentry is returned. The caller must use dput()
 	to free the dentry when it finishes using it.
 
-For further information on dentry locking, please refer to the document
-Documentation/filesystems/dentry-locking.txt.
-
 Mount Options
 =============
 
diff --git a/Documentation/frv/booting.txt b/Documentation/frv/booting.txt
index 37c4d84..9bdf4b4 100644
--- a/Documentation/frv/booting.txt
+++ b/Documentation/frv/booting.txt
@@ -180,9 +180,3 @@
 
       This tells the kernel what program to run initially. By default this is
       /sbin/init, but /sbin/sash or /bin/sh are common alternatives.
-
-  (*) vdc=...
-
-      This option configures the MB93493 companion chip visual display
-      driver. Please see Documentation/frv/mb93493/vdc.txt for more
-      information.
diff --git a/Documentation/hwmon/ad7314 b/Documentation/hwmon/ad7314
new file mode 100644
index 0000000..1912549
--- /dev/null
+++ b/Documentation/hwmon/ad7314
@@ -0,0 +1,25 @@
+Kernel driver ad7314
+====================
+
+Supported chips:
+   * Analog Devices AD7314
+     Prefix: 'ad7314'
+     Datasheet: Publicly available at Analog Devices website.
+   * Analog Devices ADT7301
+     Prefix: 'adt7301'
+     Datasheet: Publicly available at Analog Devices website.
+   * Analog Devices ADT7302
+     Prefix: 'adt7302'
+     Datasheet: Publicly available at Analog Devices website.
+
+Description
+-----------
+
+Driver supports the above parts.  The ad7314 has a 10 bit
+sensor with 1lsb = 0.25 degrees centigrade. The adt7301 and
+adt7302 have 14 bit sensors with 1lsb = 0.03125 degrees centigrade.
+
+Notes
+-----
+
+Currently power down mode is not supported.
diff --git a/Documentation/hwmon/adm1275 b/Documentation/hwmon/adm1275
index 097b3cc..ab70d96 100644
--- a/Documentation/hwmon/adm1275
+++ b/Documentation/hwmon/adm1275
@@ -6,6 +6,10 @@
     Prefix: 'adm1275'
     Addresses scanned: -
     Datasheet: www.analog.com/static/imported-files/data_sheets/ADM1275.pdf
+  * Analog Devices ADM1276
+    Prefix: 'adm1276'
+    Addresses scanned: -
+    Datasheet: www.analog.com/static/imported-files/data_sheets/ADM1276.pdf
 
 Author: Guenter Roeck <guenter.roeck@ericsson.com>
 
@@ -13,13 +17,13 @@
 Description
 -----------
 
-This driver supports hardware montoring for Analog Devices ADM1275 Hot-Swap
-Controller and Digital Power Monitor.
+This driver supports hardware montoring for Analog Devices ADM1275 and ADM1276
+Hot-Swap Controller and Digital Power Monitor.
 
-The ADM1275 is a hot-swap controller that allows a circuit board to be removed
-from or inserted into a live backplane. It also features current and voltage
-readback via an integrated 12-bit analog-to-digital converter (ADC), accessed
-using a PMBus. interface.
+ADM1275 and ADM1276 are hot-swap controllers that allow a circuit board to be
+removed from or inserted into a live backplane. They also feature current and
+voltage readback via an integrated 12-bit analog-to-digital converter (ADC),
+accessed using a PMBus interface.
 
 The driver is a client driver to the core PMBus driver. Please see
 Documentation/hwmon/pmbus for details on PMBus client drivers.
@@ -48,17 +52,25 @@
 
 in1_label		"vin1" or "vout1" depending on chip variant and
 			configuration.
-in1_input		Measured voltage. From READ_VOUT register.
-in1_min			Minumum Voltage. From VOUT_UV_WARN_LIMIT register.
-in1_max			Maximum voltage. From VOUT_OV_WARN_LIMIT register.
-in1_min_alarm		Voltage low alarm. From VOLTAGE_UV_WARNING status.
-in1_max_alarm		Voltage high alarm. From VOLTAGE_OV_WARNING status.
+in1_input		Measured voltage.
+in1_min			Minumum Voltage.
+in1_max			Maximum voltage.
+in1_min_alarm		Voltage low alarm.
+in1_max_alarm		Voltage high alarm.
 in1_highest		Historical maximum voltage.
 in1_reset_history	Write any value to reset history.
 
 curr1_label		"iout1"
-curr1_input		Measured current. From READ_IOUT register.
-curr1_max		Maximum current. From IOUT_OC_WARN_LIMIT register.
-curr1_max_alarm		Current high alarm. From IOUT_OC_WARN_LIMIT register.
+curr1_input		Measured current.
+curr1_max		Maximum current.
+curr1_max_alarm		Current high alarm.
+curr1_lcrit		Critical minimum current. Depending on the chip
+			configuration, either curr1_lcrit or curr1_crit is
+			supported, but not both.
+curr1_lcrit_alarm	Critical current low alarm.
+curr1_crit		Critical maximum current. Depending on the chip
+			configuration, either curr1_lcrit or curr1_crit is
+			supported, but not both.
+curr1_crit_alarm	Critical current high alarm.
 curr1_highest		Historical maximum current.
 curr1_reset_history	Write any value to reset history.
diff --git a/Documentation/hwmon/coretemp b/Documentation/hwmon/coretemp
index fa8776a..84d46c0 100644
--- a/Documentation/hwmon/coretemp
+++ b/Documentation/hwmon/coretemp
@@ -35,13 +35,6 @@
 All Sysfs entries are named with their core_id (represented here by 'X').
 tempX_input	 - Core temperature (in millidegrees Celsius).
 tempX_max	 - All cooling devices should be turned on (on Core2).
-		   Initialized with IA32_THERM_INTERRUPT. When the CPU
-		   temperature reaches this temperature, an interrupt is
-		   generated and tempX_max_alarm is set.
-tempX_max_hyst   - If the CPU temperature falls below than temperature,
-		   an interrupt is generated and tempX_max_alarm is reset.
-tempX_max_alarm  - Set if the temperature reaches or exceeds tempX_max.
-		   Reset if the temperature drops to or below tempX_max_hyst.
 tempX_crit	 - Maximum junction temperature (in millidegrees Celsius).
 tempX_crit_alarm - Set when Out-of-spec bit is set, never clears.
 		   Correct CPU operation is no longer guaranteed.
@@ -49,9 +42,10 @@
 		   number. For Package temp, this will be "Physical id Y",
 		   where Y is the package number.
 
-The TjMax temperature is set to 85 degrees C if undocumented model specific
-register (UMSR) 0xee has bit 30 set. If not the TjMax is 100 degrees C as
-(sometimes) documented in processor datasheet.
+On CPU models which support it, TjMax is read from a model-specific register.
+On other models, it is set to an arbitrary value based on weak heuristics.
+If these heuristics don't work for you, you can pass the correct TjMax value
+as a module parameter (tjmax).
 
 Appendix A. Known TjMax lists (TBD):
 Some information comes from ark.intel.com
diff --git a/Documentation/hwmon/exynos4_tmu b/Documentation/hwmon/exynos4_tmu
new file mode 100644
index 0000000..c3c6b41
--- /dev/null
+++ b/Documentation/hwmon/exynos4_tmu
@@ -0,0 +1,81 @@
+Kernel driver exynos4_tmu
+=================
+
+Supported chips:
+* ARM SAMSUNG EXYNOS4 series of SoC
+  Prefix: 'exynos4-tmu'
+  Datasheet: Not publicly available
+
+Authors: Donggeun Kim <dg77.kim@samsung.com>
+
+Description
+-----------
+
+This driver allows to read temperature inside SAMSUNG EXYNOS4 series of SoC.
+
+The chip only exposes the measured 8-bit temperature code value
+through a register.
+Temperature can be taken from the temperature code.
+There are three equations converting from temperature to temperature code.
+
+The three equations are:
+  1. Two point trimming
+	Tc = (T - 25) * (TI2 - TI1) / (85 - 25) + TI1
+
+  2. One point trimming
+	Tc = T + TI1 - 25
+
+  3. No trimming
+	Tc = T + 50
+
+  Tc: Temperature code, T: Temperature,
+  TI1: Trimming info for 25 degree Celsius (stored at TRIMINFO register)
+       Temperature code measured at 25 degree Celsius which is unchanged
+  TI2: Trimming info for 85 degree Celsius (stored at TRIMINFO register)
+       Temperature code measured at 85 degree Celsius which is unchanged
+
+TMU(Thermal Management Unit) in EXYNOS4 generates interrupt
+when temperature exceeds pre-defined levels.
+The maximum number of configurable threshold is four.
+The threshold levels are defined as follows:
+  Level_0: current temperature > trigger_level_0 + threshold
+  Level_1: current temperature > trigger_level_1 + threshold
+  Level_2: current temperature > trigger_level_2 + threshold
+  Level_3: current temperature > trigger_level_3 + threshold
+
+  The threshold and each trigger_level are set
+  through the corresponding registers.
+
+When an interrupt occurs, this driver notify user space of
+one of four threshold levels for the interrupt
+through kobject_uevent_env and sysfs_notify functions.
+Although an interrupt condition for level_0 can be set,
+it is not notified to user space through sysfs_notify function.
+
+Sysfs Interface
+---------------
+name		name of the temperature sensor
+		RO
+
+temp1_input	temperature
+		RO
+
+temp1_max	temperature for level_1 interrupt
+		RO
+
+temp1_crit	temperature for level_2 interrupt
+		RO
+
+temp1_emergency	temperature for level_3 interrupt
+		RO
+
+temp1_max_alarm	alarm for level_1 interrupt
+		RO
+
+temp1_crit_alarm
+		alarm for level_2 interrupt
+		RO
+
+temp1_emergency_alarm
+		alarm for level_3 interrupt
+		RO
diff --git a/Documentation/hwmon/lm75 b/Documentation/hwmon/lm75
index a179040..c91a1d1 100644
--- a/Documentation/hwmon/lm75
+++ b/Documentation/hwmon/lm75
@@ -12,26 +12,46 @@
     Addresses scanned: I2C 0x48 - 0x4f
     Datasheet: Publicly available at the National Semiconductor website
                http://www.national.com/
-  * Dallas Semiconductor DS75
-    Prefix: 'lm75'
-    Addresses scanned: I2C 0x48 - 0x4f
-    Datasheet: Publicly available at the Dallas Semiconductor website
-               http://www.maxim-ic.com/
-  * Dallas Semiconductor DS1775
-    Prefix: 'lm75'
-    Addresses scanned: I2C 0x48 - 0x4f
+  * Dallas Semiconductor DS75, DS1775
+    Prefixes: 'ds75', 'ds1775'
+    Addresses scanned: none
     Datasheet: Publicly available at the Dallas Semiconductor website
                http://www.maxim-ic.com/
   * Maxim MAX6625, MAX6626
-    Prefix: 'lm75'
-    Addresses scanned: I2C 0x48 - 0x4b
+    Prefixes: 'max6625', 'max6626'
+    Addresses scanned: none
     Datasheet: Publicly available at the Maxim website
                http://www.maxim-ic.com/
   * Microchip (TelCom) TCN75
     Prefix: 'lm75'
-    Addresses scanned: I2C 0x48 - 0x4f
+    Addresses scanned: none
     Datasheet: Publicly available at the Microchip website
                http://www.microchip.com/
+  * Microchip MCP9800, MCP9801, MCP9802, MCP9803
+    Prefix: 'mcp980x'
+    Addresses scanned: none
+    Datasheet: Publicly available at the Microchip website
+               http://www.microchip.com/
+  * Analog Devices ADT75
+    Prefix: 'adt75'
+    Addresses scanned: none
+    Datasheet: Publicly available at the Analog Devices website
+               http://www.analog.com/adt75
+  * ST Microelectronics STDS75
+    Prefix: 'stds75'
+    Addresses scanned: none
+    Datasheet: Publicly available at the ST website
+               http://www.st.com/internet/analog/product/121769.jsp
+  * Texas Instruments TMP100, TMP101, TMP105, TMP75, TMP175, TMP275
+    Prefixes: 'tmp100', 'tmp101', 'tmp105', 'tmp175', 'tmp75', 'tmp275'
+    Addresses scanned: none
+    Datasheet: Publicly available at the Texas Instruments website
+               http://www.ti.com/product/tmp100
+               http://www.ti.com/product/tmp101
+               http://www.ti.com/product/tmp105
+               http://www.ti.com/product/tmp75
+               http://www.ti.com/product/tmp175
+               http://www.ti.com/product/tmp275
 
 Author: Frodo Looijaard <frodol@dds.nl>
 
@@ -50,21 +70,16 @@
 The LM75 only updates its values each 1.5 seconds; reading it more often
 will do no harm, but will return 'old' values.
 
-The LM75 is usually used in combination with LM78-like chips, to measure
-the temperature of the processor(s).
-
-The DS75, DS1775, MAX6625, and MAX6626 are supported as well.
-They are not distinguished from an LM75. While most of these chips
-have three additional bits of accuracy (12 vs. 9 for the LM75),
-the additional bits are not supported. Not only that, but these chips will
-not be detected if not in 9-bit precision mode (use the force parameter if
-needed).
-
-The TCN75 is supported as well, and is not distinguished from an LM75.
+The original LM75 was typically used in combination with LM78-like chips
+on PC motherboards, to measure the temperature of the processor(s). Clones
+are now used in various embedded designs.
 
 The LM75 is essentially an industry standard; there may be other
 LM75 clones not listed here, with or without various enhancements,
-that are supported.
+that are supported. The clones are not detected by the driver, unless
+they reproduce the exact register tricks of the original LM75, and must
+therefore be instantiated explicitly. The specific enhancements (such as
+higher resolution) are not currently supported by the driver.
 
 The LM77 is not supported, contrary to what we pretended for a long time.
 Both chips are simply not compatible, value encoding differs.
diff --git a/Documentation/hwmon/ltc2978 b/Documentation/hwmon/ltc2978
new file mode 100644
index 0000000..c365f9b
--- /dev/null
+++ b/Documentation/hwmon/ltc2978
@@ -0,0 +1,103 @@
+Kernel driver ltc2978
+=====================
+
+Supported chips:
+  * Linear Technology LTC2978
+    Prefix: 'ltc2978'
+    Addresses scanned: -
+    Datasheet: http://cds.linear.com/docs/Datasheet/2978fa.pdf
+  * Linear Technology LTC3880
+    Prefix: 'ltc3880'
+    Addresses scanned: -
+    Datasheet: http://cds.linear.com/docs/Datasheet/3880f.pdf
+
+Author: Guenter Roeck <guenter.roeck@ericsson.com>
+
+
+Description
+-----------
+
+The LTC2978 is an octal power supply monitor, supervisor, sequencer and
+margin controller. The LTC3880 is a dual, PolyPhase DC/DC synchronous
+step-down switching regulator controller.
+
+
+Usage Notes
+-----------
+
+This driver does not probe for PMBus devices. You will have to instantiate
+devices explicitly.
+
+Example: the following commands will load the driver for an LTC2978 at address
+0x60 on I2C bus #1:
+
+# modprobe ltc2978
+# echo ltc2978 0x60 > /sys/bus/i2c/devices/i2c-1/new_device
+
+
+Sysfs attributes
+----------------
+
+in1_label		"vin"
+in1_input		Measured input voltage.
+in1_min			Minimum input voltage.
+in1_max			Maximum input voltage.
+in1_lcrit		Critical minimum input voltage.
+in1_crit		Critical maximum input voltage.
+in1_min_alarm		Input voltage low alarm.
+in1_max_alarm		Input voltage high alarm.
+in1_lcrit_alarm		Input voltage critical low alarm.
+in1_crit_alarm		Input voltage critical high alarm.
+in1_lowest		Lowest input voltage. LTC2978 only.
+in1_highest		Highest input voltage.
+in1_reset_history	Reset history. Writing into this attribute will reset
+			history for all attributes.
+
+in[2-9]_label		"vout[1-8]". Channels 3 to 9 on LTC2978 only.
+in[2-9]_input		Measured output voltage.
+in[2-9]_min		Minimum output voltage.
+in[2-9]_max		Maximum output voltage.
+in[2-9]_lcrit		Critical minimum output voltage.
+in[2-9]_crit		Critical maximum output voltage.
+in[2-9]_min_alarm	Output voltage low alarm.
+in[2-9]_max_alarm	Output voltage high alarm.
+in[2-9]_lcrit_alarm	Output voltage critical low alarm.
+in[2-9]_crit_alarm	Output voltage critical high alarm.
+in[2-9]_lowest		Lowest output voltage. LTC2978 only.
+in[2-9]_highest		Lowest output voltage.
+in[2-9]_reset_history	Reset history. Writing into this attribute will reset
+			history for all attributes.
+
+temp[1-3]_input		Measured temperature.
+			On LTC2978, only one temperature measurement is
+			supported and reflects the internal temperature.
+			On LTC3880, temp1 and temp2 report external
+			temperatures, and temp3 reports the internal
+			temperature.
+temp[1-3]_min		Mimimum temperature.
+temp[1-3]_max		Maximum temperature.
+temp[1-3]_lcrit		Critical low temperature.
+temp[1-3]_crit		Critical high temperature.
+temp[1-3]_min_alarm	Chip temperature low alarm.
+temp[1-3]_max_alarm	Chip temperature high alarm.
+temp[1-3]_lcrit_alarm	Chip temperature critical low alarm.
+temp[1-3]_crit_alarm	Chip temperature critical high alarm.
+temp[1-3]_lowest	Lowest measured temperature. LTC2978 only.
+temp[1-3]_highest	Highest measured temperature.
+temp[1-3]_reset_history	Reset history. Writing into this attribute will reset
+			history for all attributes.
+
+power[1-2]_label	"pout[1-2]". LTC3880 only.
+power[1-2]_input	Measured power.
+
+curr1_label		"iin". LTC3880 only.
+curr1_input		Measured input current.
+curr1_max		Maximum input current.
+curr1_max_alarm		Input current high alarm.
+
+curr[2-3]_label		"iout[1-2]". LTC3880 only.
+curr[2-3]_input		Measured input current.
+curr[2-3]_max		Maximum input current.
+curr[2-3]_crit		Critical input current.
+curr[2-3]_max_alarm	Input current high alarm.
+curr[2-3]_crit_alarm	Input current critical high alarm.
diff --git a/Documentation/hwmon/max16065 b/Documentation/hwmon/max16065
index 44b4f61..c11f64a 100644
--- a/Documentation/hwmon/max16065
+++ b/Documentation/hwmon/max16065
@@ -62,6 +62,13 @@
 the devices explicitly. Please see Documentation/i2c/instantiating-devices for
 details.
 
+WARNING: Do not access chip registers using the i2cdump command, and do not use
+any of the i2ctools commands on a command register (0xa5 to 0xac). The chips
+supported by this driver interpret any access to a command register (including
+read commands) as request to execute the command in question. This may result in
+power loss, board resets, and/or Flash corruption. Worst case, your board may
+turn into a brick.
+
 
 Sysfs entries
 -------------
diff --git a/Documentation/hwmon/pmbus b/Documentation/hwmon/pmbus
index c36c1c1..15ac911 100644
--- a/Documentation/hwmon/pmbus
+++ b/Documentation/hwmon/pmbus
@@ -8,11 +8,6 @@
     Addresses scanned: -
     Datasheet:
  http://archive.ericsson.net/service/internet/picov/get?DocNo=28701-EN/LZT146395
-  * Linear Technology LTC2978
-    Octal PMBus Power Supply Monitor and Controller
-    Prefix: 'ltc2978'
-    Addresses scanned: -
-    Datasheet: http://cds.linear.com/docs/Datasheet/2978fa.pdf
   * ON Semiconductor ADP4000, NCP4200, NCP4208
     Prefixes: 'adp4000', 'ncp4200', 'ncp4208'
     Addresses scanned: -
@@ -20,6 +15,14 @@
 	http://www.onsemi.com/pub_link/Collateral/ADP4000-D.PDF
 	http://www.onsemi.com/pub_link/Collateral/NCP4200-D.PDF
 	http://www.onsemi.com/pub_link/Collateral/JUNE%202009-%20REV.%200.PDF
+  * Lineage Power
+    Prefixes: 'pdt003', 'pdt006', 'pdt012', 'udt020'
+    Addresses scanned: -
+    Datasheets:
+	http://www.lineagepower.com/oem/pdf/PDT003A0X.pdf
+	http://www.lineagepower.com/oem/pdf/PDT006A0X.pdf
+	http://www.lineagepower.com/oem/pdf/PDT012A0X.pdf
+	http://www.lineagepower.com/oem/pdf/UDT020A0X.pdf
   * Generic PMBus devices
     Prefix: 'pmbus'
     Addresses scanned: -
diff --git a/Documentation/hwmon/pmbus-core b/Documentation/hwmon/pmbus-core
new file mode 100644
index 0000000..31e4720
--- /dev/null
+++ b/Documentation/hwmon/pmbus-core
@@ -0,0 +1,283 @@
+PMBus core driver and internal API
+==================================
+
+Introduction
+============
+
+[from pmbus.org] The Power Management Bus (PMBus) is an open standard
+power-management protocol with a fully defined command language that facilitates
+communication with power converters and other devices in a power system. The
+protocol is implemented over the industry-standard SMBus serial interface and
+enables programming, control, and real-time monitoring of compliant power
+conversion products. This flexible and highly versatile standard allows for
+communication between devices based on both analog and digital technologies, and
+provides true interoperability which will reduce design complexity and shorten
+time to market for power system designers. Pioneered by leading power supply and
+semiconductor companies, this open power system standard is maintained and
+promoted by the PMBus Implementers Forum (PMBus-IF), comprising 30+ adopters
+with the objective to provide support to, and facilitate adoption among, users.
+
+Unfortunately, while PMBus commands are standardized, there are no mandatory
+commands, and manufacturers can add as many non-standard commands as they like.
+Also, different PMBUs devices act differently if non-supported commands are
+executed. Some devices return an error, some devices return 0xff or 0xffff and
+set a status error flag, and some devices may simply hang up.
+
+Despite all those difficulties, a generic PMBus device driver is still useful
+and supported since kernel version 2.6.39. However, it was necessary to support
+device specific extensions in addition to the core PMBus driver, since it is
+simply unknown what new device specific functionality PMBus device developers
+come up with next.
+
+To make device specific extensions as scalable as possible, and to avoid having
+to modify the core PMBus driver repeatedly for new devices, the PMBus driver was
+split into core, generic, and device specific code. The core code (in
+pmbus_core.c) provides generic functionality. The generic code (in pmbus.c)
+provides support for generic PMBus devices. Device specific code is responsible
+for device specific initialization and, if needed, maps device specific
+functionality into generic functionality. This is to some degree comparable
+to PCI code, where generic code is augmented as needed with quirks for all kinds
+of devices.
+
+PMBus device capabilities auto-detection
+========================================
+
+For generic PMBus devices, code in pmbus.c attempts to auto-detect all supported
+PMBus commands. Auto-detection is somewhat limited, since there are simply too
+many variables to consider. For example, it is almost impossible to autodetect
+which PMBus commands are paged and which commands are replicated across all
+pages (see the PMBus specification for details on multi-page PMBus devices).
+
+For this reason, it often makes sense to provide a device specific driver if not
+all commands can be auto-detected. The data structures in this driver can be
+used to inform the core driver about functionality supported by individual
+chips.
+
+Some commands are always auto-detected. This applies to all limit commands
+(lcrit, min, max, and crit attributes) as well as associated alarm attributes.
+Limits and alarm attributes are auto-detected because there are simply too many
+possible combinations to provide a manual configuration interface.
+
+PMBus internal API
+==================
+
+The API between core and device specific PMBus code is defined in
+drivers/hwmon/pmbus/pmbus.h. In addition to the internal API, pmbus.h defines
+standard PMBus commands and virtual PMBus commands.
+
+Standard PMBus commands
+-----------------------
+
+Standard PMBus commands (commands values 0x00 to 0xff) are defined in the PMBUs
+specification.
+
+Virtual PMBus commands
+----------------------
+
+Virtual PMBus commands are provided to enable support for non-standard
+functionality which has been implemented by several chip vendors and is thus
+desirable to support.
+
+Virtual PMBus commands start with command value 0x100 and can thus easily be
+distinguished from standard PMBus commands (which can not have values larger
+than 0xff). Support for virtual PMBus commands is device specific and thus has
+to be implemented in device specific code.
+
+Virtual commands are named PMBUS_VIRT_xxx and start with PMBUS_VIRT_BASE. All
+virtual commands are word sized.
+
+There are currently two types of virtual commands.
+
+- READ commands are read-only; writes are either ignored or return an error.
+- RESET commands are read/write. Reading reset registers returns zero
+  (used for detection), writing any value causes the associated history to be
+  reset.
+
+Virtual commands have to be handled in device specific driver code. Chip driver
+code returns non-negative values if a virtual command is supported, or a
+negative error code if not. The chip driver may return -ENODATA or any other
+Linux error code in this case, though an error code other than -ENODATA is
+handled more efficiently and thus preferred. Either case, the calling PMBus
+core code will abort if the chip driver returns an error code when reading
+or writing virtual registers (in other words, the PMBus core code will never
+send a virtual command to a chip).
+
+PMBus driver information
+------------------------
+
+PMBus driver information, defined in struct pmbus_driver_info, is the main means
+for device specific drivers to pass information to the core PMBus driver.
+Specifically, it provides the following information.
+
+- For devices supporting its data in Direct Data Format, it provides coefficients
+  for converting register values into normalized data. This data is usually
+  provided by chip manufacturers in device datasheets.
+- Supported chip functionality can be provided to the core driver. This may be
+  necessary for chips which react badly if non-supported commands are executed,
+  and/or to speed up device detection and initialization.
+- Several function entry points are provided to support overriding and/or
+  augmenting generic command execution. This functionality can be used to map
+  non-standard PMBus commands to standard commands, or to augment standard
+  command return values with device specific information.
+
+  API functions
+  -------------
+
+  Functions provided by chip driver
+  ---------------------------------
+
+  All functions return the command return value (read) or zero (write) if
+  successful. A return value of -ENODATA indicates that there is no manufacturer
+  specific command, but that a standard PMBus command may exist. Any other
+  negative return value indicates that the commands does not exist for this
+  chip, and that no attempt should be made to read or write the standard
+  command.
+
+  As mentioned above, an exception to this rule applies to virtual commands,
+  which  _must_ be handled in driver specific code. See "Virtual PMBus Commands"
+  above for more details.
+
+  Command execution in the core PMBus driver code is as follows.
+
+	if (chip_access_function) {
+		status = chip_access_function();
+		if (status != -ENODATA)
+			return status;
+	}
+	if (command >= PMBUS_VIRT_BASE)	/* For word commands/registers only */
+		return -EINVAL;
+	return generic_access();
+
+  Chip drivers may provide pointers to the following functions in struct
+  pmbus_driver_info. All functions are optional.
+
+  int (*read_byte_data)(struct i2c_client *client, int page, int reg);
+
+  Read byte from page <page>, register <reg>.
+  <page> may be -1, which means "current page".
+
+  int (*read_word_data)(struct i2c_client *client, int page, int reg);
+
+  Read word from page <page>, register <reg>.
+
+  int (*write_word_data)(struct i2c_client *client, int page, int reg,
+		         u16 word);
+
+  Write word to page <page>, register <reg>.
+
+  int (*write_byte)(struct i2c_client *client, int page, u8 value);
+
+  Write byte to page <page>, register <reg>.
+  <page> may be -1, which means "current page".
+
+  int (*identify)(struct i2c_client *client, struct pmbus_driver_info *info);
+
+  Determine supported PMBus functionality. This function is only necessary
+  if a chip driver supports multiple chips, and the chip functionality is not
+  pre-determined. It is currently only used by the generic pmbus driver
+  (pmbus.c).
+
+  Functions exported by core driver
+  ---------------------------------
+
+  Chip drivers are expected to use the following functions to read or write
+  PMBus registers. Chip drivers may also use direct I2C commands. If direct I2C
+  commands are used, the chip driver code must not directly modify the current
+  page, since the selected page is cached in the core driver and the core driver
+  will assume that it is selected. Using pmbus_set_page() to select a new page
+  is mandatory.
+
+  int pmbus_set_page(struct i2c_client *client, u8 page);
+
+  Set PMBus page register to <page> for subsequent commands.
+
+  int pmbus_read_word_data(struct i2c_client *client, u8 page, u8 reg);
+
+  Read word data from <page>, <reg>. Similar to i2c_smbus_read_word_data(), but
+  selects page first.
+
+  int pmbus_write_word_data(struct i2c_client *client, u8 page, u8 reg,
+			    u16 word);
+
+  Write word data to <page>, <reg>. Similar to i2c_smbus_write_word_data(), but
+  selects page first.
+
+  int pmbus_read_byte_data(struct i2c_client *client, int page, u8 reg);
+
+  Read byte data from <page>, <reg>. Similar to i2c_smbus_read_byte_data(), but
+  selects page first. <page> may be -1, which means "current page".
+
+  int pmbus_write_byte(struct i2c_client *client, int page, u8 value);
+
+  Write byte data to <page>, <reg>. Similar to i2c_smbus_write_byte(), but
+  selects page first. <page> may be -1, which means "current page".
+
+  void pmbus_clear_faults(struct i2c_client *client);
+
+  Execute PMBus "Clear Fault" command on all chip pages.
+  This function calls the device specific write_byte function if defined.
+  Therefore, it must _not_ be called from that function.
+
+  bool pmbus_check_byte_register(struct i2c_client *client, int page, int reg);
+
+  Check if byte register exists. Return true if the register exists, false
+  otherwise.
+  This function calls the device specific write_byte function if defined to
+  obtain the chip status. Therefore, it must _not_ be called from that function.
+
+  bool pmbus_check_word_register(struct i2c_client *client, int page, int reg);
+
+  Check if word register exists. Return true if the register exists, false
+  otherwise.
+  This function calls the device specific write_byte function if defined to
+  obtain the chip status. Therefore, it must _not_ be called from that function.
+
+  int pmbus_do_probe(struct i2c_client *client, const struct i2c_device_id *id,
+                     struct pmbus_driver_info *info);
+
+  Execute probe function. Similar to standard probe function for other drivers,
+  with the pointer to struct pmbus_driver_info as additional argument. Calls
+  identify function if supported. Must only be called from device probe
+  function.
+
+  void pmbus_do_remove(struct i2c_client *client);
+
+  Execute driver remove function. Similar to standard driver remove function.
+
+  const struct pmbus_driver_info
+	*pmbus_get_driver_info(struct i2c_client *client);
+
+  Return pointer to struct pmbus_driver_info as passed to pmbus_do_probe().
+
+
+PMBus driver platform data
+==========================
+
+PMBus platform data is defined in include/linux/i2c/pmbus.h. Platform data
+currently only provides a flag field with a single bit used.
+
+#define PMBUS_SKIP_STATUS_CHECK (1 << 0)
+
+struct pmbus_platform_data {
+        u32 flags;              /* Device specific flags */
+};
+
+
+Flags
+-----
+
+PMBUS_SKIP_STATUS_CHECK
+
+During register detection, skip checking the status register for
+communication or command errors.
+
+Some PMBus chips respond with valid data when trying to read an unsupported
+register. For such chips, checking the status register is mandatory when
+trying to determine if a chip register exists or not.
+Other PMBus chips don't support the STATUS_CML register, or report
+communication errors for no explicable reason. For such chips, checking the
+status register must be disabled.
+
+Some i2c controllers do not support single-byte commands (write commands with
+no data, i2c_smbus_write_byte()). With such controllers, clearing the status
+register is impossible, and the PMBUS_SKIP_STATUS_CHECK flag must be set.
diff --git a/Documentation/hwmon/w83627ehf b/Documentation/hwmon/w83627ehf
index 76ffef9..3f44dbd 100644
--- a/Documentation/hwmon/w83627ehf
+++ b/Documentation/hwmon/w83627ehf
@@ -14,6 +14,10 @@
     Prefix: 'w83627dhg'
     Addresses scanned: ISA address retrieved from Super I/O registers
     Datasheet: not available
+  * Winbond W83627UHG
+    Prefix: 'w83627uhg'
+    Addresses scanned: ISA address retrieved from Super I/O registers
+    Datasheet: available from www.nuvoton.com
   * Winbond W83667HG
     Prefix: 'w83667hg'
     Addresses scanned: ISA address retrieved from Super I/O registers
@@ -42,14 +46,13 @@
 -----------
 
 This driver implements support for the Winbond W83627EHF, W83627EHG,
-W83627DHG, W83627DHG-P, W83667HG, W83667HG-B, W83667HG-I (NCT6775F),
-and NCT6776F super I/O chips. We will refer to them collectively as
-Winbond chips.
+W83627DHG, W83627DHG-P, W83627UHG, W83667HG, W83667HG-B, W83667HG-I
+(NCT6775F), and NCT6776F super I/O chips. We will refer to them collectively
+as Winbond chips.
 
-The chips implement three temperature sensors (up to four for 667HG-B, and nine
-for NCT6775F and NCT6776F), five fan rotation speed sensors, ten analog voltage
-sensors (only nine for the 627DHG), one VID (6 pins for the 627EHF/EHG, 8 pins
-for the 627DHG and 667HG), alarms with beep warnings (control unimplemented),
+The chips implement 2 to 4 temperature sensors (9 for NCT6775F and NCT6776F),
+2 to 5 fan rotation speed sensors, 8 to 10 analog voltage sensors, one VID
+(except for 627UHG), alarms with beep warnings (control unimplemented),
 and some automatic fan regulation strategies (plus manual fan control mode).
 
 The temperature sensor sources on W82677HG-B, NCT6775F, and NCT6776F are
@@ -86,17 +89,16 @@
 
 temp1 -> pwm1
 temp2 -> pwm2
-temp3 -> pwm3
+temp3 -> pwm3 (not on 627UHG)
 prog  -> pwm4 (not on 667HG and 667HG-B; the programmable setting is not
 	       supported by the driver)
 
 /sys files
 ----------
 
-name - this is a standard hwmon device entry. For the W83627EHF and W83627EHG,
-       it is set to "w83627ehf", for the W83627DHG it is set to "w83627dhg",
-       for the W83667HG and W83667HG-B it is set to "w83667hg", for NCT6775F it
-       is set to "nct6775", and for NCT6776F it is set to "nct6776".
+name - this is a standard hwmon device entry, it contains the name of
+       the device (see the prefix in the list of supported devices at
+       the top of this file)
 
 pwm[1-4] - this file stores PWM duty cycle or DC value (fan speed) in range:
 	   0 (stop) to 255 (full)
diff --git a/Documentation/hwmon/zl6100 b/Documentation/hwmon/zl6100
new file mode 100644
index 0000000..7617798
--- /dev/null
+++ b/Documentation/hwmon/zl6100
@@ -0,0 +1,125 @@
+Kernel driver zl6100
+====================
+
+Supported chips:
+  * Intersil / Zilker Labs ZL2004
+    Prefix: 'zl2004'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6847.pdf
+  * Intersil / Zilker Labs ZL2006
+    Prefix: 'zl2006'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6850.pdf
+  * Intersil / Zilker Labs ZL2008
+    Prefix: 'zl2008'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6859.pdf
+  * Intersil / Zilker Labs ZL2105
+    Prefix: 'zl2105'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6851.pdf
+  * Intersil / Zilker Labs ZL2106
+    Prefix: 'zl2106'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6852.pdf
+  * Intersil / Zilker Labs ZL6100
+    Prefix: 'zl6100'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6876.pdf
+  * Intersil / Zilker Labs ZL6105
+    Prefix: 'zl6105'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6906.pdf
+
+Author: Guenter Roeck <guenter.roeck@ericsson.com>
+
+
+Description
+-----------
+
+This driver supports hardware montoring for Intersil / Zilker Labs ZL6100 and
+compatible digital DC-DC controllers.
+
+The driver is a client driver to the core PMBus driver. Please see
+Documentation/hwmon/pmbus and Documentation.hwmon/pmbus-core for details
+on PMBus client drivers.
+
+
+Usage Notes
+-----------
+
+This driver does not auto-detect devices. You will have to instantiate the
+devices explicitly. Please see Documentation/i2c/instantiating-devices for
+details.
+
+WARNING: Do not access chip registers using the i2cdump command, and do not use
+any of the i2ctools commands on a command register used to save and restore
+configuration data (0x11, 0x12, 0x15, 0x16, and 0xf4). The chips supported by
+this driver interpret any access to those command registers (including read
+commands) as request to execute the command in question. Unless write accesses
+to those registers are protected, this may result in power loss, board resets,
+and/or Flash corruption. Worst case, your board may turn into a brick.
+
+
+Platform data support
+---------------------
+
+The driver supports standard PMBus driver platform data.
+
+
+Module parameters
+-----------------
+
+delay
+-----
+
+Some Intersil/Zilker Labs DC-DC controllers require a minimum interval between
+I2C bus accesses. According to Intersil, the minimum interval is 2 ms, though
+1 ms appears to be sufficient and has not caused any problems in testing.
+The problem is known to affect ZL6100, ZL2105, and ZL2008. It is known not to
+affect ZL2004 and ZL6105. The driver automatically sets the interval to 1 ms
+except for ZL2004 and ZL6105. To enable manual override, the driver provides a
+writeable module parameter, 'delay', which can be used to set the interval to
+a value between 0 and 65,535 microseconds.
+
+
+Sysfs entries
+-------------
+
+The following attributes are supported. Limits are read-write; all other
+attributes are read-only.
+
+in1_label		"vin"
+in1_input		Measured input voltage.
+in1_min			Minimum input voltage.
+in1_max			Maximum input voltage.
+in1_lcrit		Critical minumum input voltage.
+in1_crit		Critical maximum input voltage.
+in1_min_alarm		Input voltage low alarm.
+in1_max_alarm		Input voltage high alarm.
+in1_lcrit_alarm		Input voltage critical low alarm.
+in1_crit_alarm		Input voltage critical high alarm.
+
+in2_label		"vout1"
+in2_input		Measured output voltage.
+in2_lcrit		Critical minumum output Voltage.
+in2_crit		Critical maximum output voltage.
+in2_lcrit_alarm		Critical output voltage critical low alarm.
+in2_crit_alarm		Critical output voltage critical high alarm.
+
+curr1_label		"iout1"
+curr1_input		Measured output current.
+curr1_lcrit		Critical minimum output current.
+curr1_crit		Critical maximum output current.
+curr1_lcrit_alarm	Output current critical low alarm.
+curr1_crit_alarm	Output current critical high alarm.
+
+temp[12]_input		Measured temperature.
+temp[12]_min		Minimum temperature.
+temp[12]_max		Maximum temperature.
+temp[12]_lcrit		Critical low temperature.
+temp[12]_crit		Critical high temperature.
+temp[12]_min_alarm	Chip temperature low alarm.
+temp[12]_max_alarm	Chip temperature high alarm.
+temp[12]_lcrit_alarm	Chip temperature critical low alarm.
+temp[12]_crit_alarm	Chip temperature critical high alarm.
diff --git a/Documentation/hwspinlock.txt b/Documentation/hwspinlock.txt
index 7dcd1a4..a903ee5 100644
--- a/Documentation/hwspinlock.txt
+++ b/Documentation/hwspinlock.txt
@@ -39,23 +39,20 @@
      in case an unused hwspinlock isn't available. Users of this
      API will usually want to communicate the lock's id to the remote core
      before it can be used to achieve synchronization.
-     Can be called from an atomic context (this function will not sleep) but
-     not from within interrupt context.
+     Should be called from a process context (might sleep).
 
   struct hwspinlock *hwspin_lock_request_specific(unsigned int id);
    - assign a specific hwspinlock id and return its address, or NULL
      if that hwspinlock is already in use. Usually board code will
      be calling this function in order to reserve specific hwspinlock
      ids for predefined purposes.
-     Can be called from an atomic context (this function will not sleep) but
-     not from within interrupt context.
+     Should be called from a process context (might sleep).
 
   int hwspin_lock_free(struct hwspinlock *hwlock);
    - free a previously-assigned hwspinlock; returns 0 on success, or an
      appropriate error code on failure (e.g. -EINVAL if the hwspinlock
      is already free).
-     Can be called from an atomic context (this function will not sleep) but
-     not from within interrupt context.
+     Should be called from a process context (might sleep).
 
   int hwspin_lock_timeout(struct hwspinlock *hwlock, unsigned int timeout);
    - lock a previously-assigned hwspinlock with a timeout limit (specified in
@@ -230,45 +227,62 @@
 
 4. API for implementors
 
-  int hwspin_lock_register(struct hwspinlock *hwlock);
+  int hwspin_lock_register(struct hwspinlock_device *bank, struct device *dev,
+		const struct hwspinlock_ops *ops, int base_id, int num_locks);
    - to be called from the underlying platform-specific implementation, in
-     order to register a new hwspinlock instance. Can be called from an atomic
-     context (this function will not sleep) but not from within interrupt
-     context. Returns 0 on success, or appropriate error code on failure.
+     order to register a new hwspinlock device (which is usually a bank of
+     numerous locks). Should be called from a process context (this function
+     might sleep).
+     Returns 0 on success, or appropriate error code on failure.
 
-  struct hwspinlock *hwspin_lock_unregister(unsigned int id);
+  int hwspin_lock_unregister(struct hwspinlock_device *bank);
    - to be called from the underlying vendor-specific implementation, in order
-     to unregister an existing (and unused) hwspinlock instance.
-     Can be called from an atomic context (will not sleep) but not from
-     within interrupt context.
+     to unregister an hwspinlock device (which is usually a bank of numerous
+     locks).
+     Should be called from a process context (this function might sleep).
      Returns the address of hwspinlock on success, or NULL on error (e.g.
      if the hwspinlock is sill in use).
 
-5. struct hwspinlock
+5. Important structs
 
-This struct represents an hwspinlock instance. It is registered by the
-underlying hwspinlock implementation using the hwspin_lock_register() API.
+struct hwspinlock_device is a device which usually contains a bank
+of hardware locks. It is registered by the underlying hwspinlock
+implementation using the hwspin_lock_register() API.
 
 /**
- * struct hwspinlock - vendor-specific hwspinlock implementation
- *
- * @dev: underlying device, will be used with runtime PM api
- * @ops: vendor-specific hwspinlock handlers
- * @id: a global, unique, system-wide, index of the lock.
- * @lock: initialized and used by hwspinlock core
- * @owner: underlying implementation module, used to maintain module ref count
+ * struct hwspinlock_device - a device which usually spans numerous hwspinlocks
+ * @dev: underlying device, will be used to invoke runtime PM api
+ * @ops: platform-specific hwspinlock handlers
+ * @base_id: id index of the first lock in this device
+ * @num_locks: number of locks in this device
+ * @lock: dynamically allocated array of 'struct hwspinlock'
  */
-struct hwspinlock {
+struct hwspinlock_device {
 	struct device *dev;
 	const struct hwspinlock_ops *ops;
-	int id;
-	spinlock_t lock;
-	struct module *owner;
+	int base_id;
+	int num_locks;
+	struct hwspinlock lock[0];
 };
 
-The underlying implementation is responsible to assign the dev, ops, id and
-owner members. The lock member, OTOH, is initialized and used by the hwspinlock
-core.
+struct hwspinlock_device contains an array of hwspinlock structs, each
+of which represents a single hardware lock:
+
+/**
+ * struct hwspinlock - this struct represents a single hwspinlock instance
+ * @bank: the hwspinlock_device structure which owns this lock
+ * @lock: initialized and used by hwspinlock core
+ * @priv: private data, owned by the underlying platform-specific hwspinlock drv
+ */
+struct hwspinlock {
+	struct hwspinlock_device *bank;
+	spinlock_t lock;
+	void *priv;
+};
+
+When registering a bank of locks, the hwspinlock driver only needs to
+set the priv members of the locks. The rest of the members are set and
+initialized by the hwspinlock core itself.
 
 6. Implementation callbacks
 
diff --git a/Documentation/i2c/smbus-protocol b/Documentation/i2c/smbus-protocol
index 7c19d1a..49f5b68 100644
--- a/Documentation/i2c/smbus-protocol
+++ b/Documentation/i2c/smbus-protocol
@@ -88,6 +88,10 @@
 
 S Addr Wr [A] Comm [A] S Addr Rd [A] [DataLow] A [DataHigh] NA P
 
+Note the convenience function i2c_smbus_read_word_swapped is
+available for reads where the two data bytes are the other way
+around (not SMBus compliant, but very popular.)
+
 
 SMBus Write Byte:  i2c_smbus_write_byte_data()
 ==============================================
@@ -108,6 +112,10 @@
 
 S Addr Wr [A] Comm [A] DataLow [A] DataHigh [A] P
 
+Note the convenience function i2c_smbus_write_word_swapped is
+available for writes where the two data bytes are the other way
+around (not SMBus compliant, but very popular.)
+
 
 SMBus Process Call:  i2c_smbus_process_call()
 =============================================
diff --git a/Documentation/input/elantech.txt b/Documentation/input/elantech.txt
index db798af..5602eb7 100644
--- a/Documentation/input/elantech.txt
+++ b/Documentation/input/elantech.txt
@@ -16,15 +16,28 @@
 
  1. Introduction
  2. Extra knobs
- 3. Hardware version 1
-    3.1 Registers
-    3.2 Native relative mode 4 byte packet format
-    3.3 Native absolute mode 4 byte packet format
- 4. Hardware version 2
+ 3. Differentiating hardware versions
+ 4. Hardware version 1
     4.1 Registers
-    4.2 Native absolute mode 6 byte packet format
-        4.2.1 One finger touch
-        4.2.2 Two finger touch
+    4.2 Native relative mode 4 byte packet format
+    4.3 Native absolute mode 4 byte packet format
+ 5. Hardware version 2
+    5.1 Registers
+    5.2 Native absolute mode 6 byte packet format
+        5.2.1 Parity checking and packet re-synchronization
+        5.2.2 One/Three finger touch
+        5.2.3 Two finger touch
+ 6. Hardware version 3
+    6.1 Registers
+    6.2 Native absolute mode 6 byte packet format
+        6.2.1 One/Three finger touch
+        6.2.2 Two finger touch
+ 7. Hardware version 4
+    7.1 Registers
+    7.2 Native absolute mode 6 byte packet format
+        7.2.1 Status packet
+        7.2.2 Head packet
+        7.2.3 Motion packet
 
 
 
@@ -375,7 +388,7 @@
 
 In case an error is detected, all the packets are shifted by one (and packet[0] is discarded).
 
-5.2.1 One/Three finger touch
+5.2.2 One/Three finger touch
       ~~~~~~~~~~~~~~~~
 
 byte 0:
@@ -384,19 +397,19 @@
 	 n1  n0  w3  w2   .   .   R   L
 
          L, R = 1 when Left, Right mouse button pressed
-         n1..n0 = numbers of fingers on touchpad
+         n1..n0 = number of fingers on touchpad
 
 byte 1:
 
    bit   7   6   5   4   3   2   1   0
-	 p7  p6  p5  p4  .  x10 x9  x8
+	 p7  p6  p5  p4 x11 x10 x9  x8
 
 byte 2:
 
    bit   7   6   5   4   3   2   1   0
 	 x7  x6  x5  x4  x3  x2  x1  x0
 
-         x10..x0 = absolute x value (horizontal)
+         x11..x0 = absolute x value (horizontal)
 
 byte 3:
 
@@ -420,7 +433,7 @@
 byte 4:
 
    bit   7   6   5   4   3   2   1   0
-        p3  p1  p2  p0   .   .  y9  y8
+        p3  p1  p2  p0  y11 y10 y9  y8
 
 	 p7..p0 = pressure (not EF113)
 
@@ -429,10 +442,10 @@
    bit   7   6   5   4   3   2   1   0
         y7  y6  y5  y4  y3  y2  y1  y0
 
-         y9..y0 = absolute y value (vertical)
+         y11..y0 = absolute y value (vertical)
 
 
-4.2.2 Two finger touch
+5.2.3 Two finger touch
       ~~~~~~~~~~~~~~~~
 
 Note that the two pairs of coordinates are not exactly the coordinates of the
@@ -446,7 +459,7 @@
         n1  n0  ay8 ax8  .   .   R   L
 
          L, R = 1 when Left, Right mouse button pressed
-         n1..n0 = numbers of fingers on touchpad
+         n1..n0 = number of fingers on touchpad
 
 byte 1:
 
@@ -480,3 +493,253 @@
         by7 by8 by5 by4 by3 by2 by1 by0
 
          by8..by0 = upper-right finger absolute y value
+
+/////////////////////////////////////////////////////////////////////////////
+
+6. Hardware version 3
+   ==================
+
+6.1 Registers
+    ~~~~~~~~~
+* reg_10
+
+   bit   7   6   5   4   3   2   1   0
+         0   0   0   0   0   0   0   A
+
+         A: 1 = enable absolute tracking
+
+6.2 Native absolute mode 6 byte packet format
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+1 and 3 finger touch shares the same 6-byte packet format, except that
+3 finger touch only reports the position of the center of all three fingers.
+
+Firmware would send 12 bytes of data for 2 finger touch.
+
+Note on debounce:
+In case the box has unstable power supply or other electricity issues, or
+when number of finger changes, F/W would send "debounce packet" to inform
+driver that the hardware is in debounce status.
+The debouce packet has the following signature:
+    byte 0: 0xc4
+    byte 1: 0xff
+    byte 2: 0xff
+    byte 3: 0x02
+    byte 4: 0xff
+    byte 5: 0xff
+When we encounter this kind of packet, we just ignore it.
+
+6.2.1 One/Three finger touch
+      ~~~~~~~~~~~~~~~~~~~~~~
+
+byte 0:
+
+   bit   7   6   5   4   3   2   1   0
+        n1  n0  w3  w2   0   1   R   L
+
+        L, R = 1 when Left, Right mouse button pressed
+        n1..n0 = number of fingers on touchpad
+
+byte 1:
+
+   bit   7   6   5   4   3   2   1   0
+        p7  p6  p5  p4 x11 x10  x9  x8
+
+byte 2:
+
+   bit   7   6   5   4   3   2   1   0
+        x7  x6  x5  x4  x3  x2  x1  x0
+
+        x11..x0 = absolute x value (horizontal)
+
+byte 3:
+
+   bit   7   6   5   4   3   2   1   0
+         0   0  w1  w0   0   0   1   0
+
+         w3..w0 = width of the finger touch
+
+byte 4:
+
+   bit   7   6   5   4   3   2   1   0
+        p3  p1  p2  p0  y11 y10 y9  y8
+
+        p7..p0 = pressure
+
+byte 5:
+
+   bit   7   6   5   4   3   2   1   0
+        y7  y6  y5  y4  y3  y2  y1  y0
+
+        y11..y0 = absolute y value (vertical)
+
+6.2.2 Two finger touch
+      ~~~~~~~~~~~~~~~~
+
+The packet format is exactly the same for two finger touch, except the hardware
+sends two 6 byte packets. The first packet contains data for the first finger,
+the second packet has data for the second finger. So for two finger touch a
+total of 12 bytes are sent.
+
+/////////////////////////////////////////////////////////////////////////////
+
+7. Hardware version 4
+   ==================
+
+7.1 Registers
+    ~~~~~~~~~
+* reg_07
+
+   bit   7   6   5   4   3   2   1   0
+         0   0   0   0   0   0   0   A
+
+         A: 1 = enable absolute tracking
+
+7.2 Native absolute mode 6 byte packet format
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+v4 hardware is a true multitouch touchpad, capable of tracking up to 5 fingers.
+Unfortunately, due to PS/2's limited bandwidth, its packet format is rather
+complex.
+
+Whenever the numbers or identities of the fingers changes, the hardware sends a
+status packet to indicate how many and which fingers is on touchpad, followed by
+head packets or motion packets. A head packet contains data of finger id, finger
+position (absolute x, y values), width, and pressure. A motion packet contains
+two fingers' position delta.
+
+For example, when status packet tells there are 2 fingers on touchpad, then we
+can expect two following head packets. If the finger status doesn't change,
+the following packets would be motion packets, only sending delta of finger
+position, until we receive a status packet.
+
+One exception is one finger touch. when a status packet tells us there is only
+one finger, the hardware would just send head packets afterwards.
+
+7.2.1 Status packet
+      ~~~~~~~~~~~~~
+
+byte 0:
+
+   bit   7   6   5   4   3   2   1   0
+         .   .   .   .   0   1   R   L
+
+         L, R = 1 when Left, Right mouse button pressed
+
+byte 1:
+
+   bit   7   6   5   4   3   2   1   0
+         .   .   . ft4 ft3 ft2 ft1 ft0
+
+         ft4 ft3 ft2 ft1 ft0 ftn = 1 when finger n is on touchpad
+
+byte 2: not used
+
+byte 3:
+
+   bit   7   6   5   4   3   2   1   0
+         .   .   .   1   0   0   0   0
+
+         constant bits
+
+byte 4:
+
+   bit   7   6   5   4   3   2   1   0
+         p   .   .   .   .   .   .   .
+
+         p = 1 for palm
+
+byte 5: not used
+
+7.2.2 Head packet
+      ~~~~~~~~~~~
+
+byte 0:
+
+   bit   7   6   5   4   3   2   1   0
+        w3  w2  w1  w0   0   1   R   L
+
+        L, R = 1 when Left, Right mouse button pressed
+        w3..w0 = finger width (spans how many trace lines)
+
+byte 1:
+
+   bit   7   6   5   4   3   2   1   0
+        p7  p6  p5  p4 x11 x10  x9  x8
+
+byte 2:
+
+   bit   7   6   5   4   3   2   1   0
+        x7  x6  x5  x4  x3  x2  x1  x0
+
+        x11..x0 = absolute x value (horizontal)
+
+byte 3:
+
+   bit   7   6   5   4   3   2   1   0
+       id2 id1 id0   1   0   0   0   1
+
+       id2..id0 = finger id
+
+byte 4:
+
+   bit   7   6   5   4   3   2   1   0
+        p3  p1  p2  p0  y11 y10 y9  y8
+
+        p7..p0 = pressure
+
+byte 5:
+
+   bit   7   6   5   4   3   2   1   0
+        y7  y6  y5  y4  y3  y2  y1  y0
+
+        y11..y0 = absolute y value (vertical)
+
+7.2.3 Motion packet
+      ~~~~~~~~~~~~~
+
+byte 0:
+
+   bit   7   6   5   4   3   2   1   0
+       id2 id1 id0   w   0   1   R   L
+
+       L, R = 1 when Left, Right mouse button pressed
+       id2..id0 = finger id
+       w = 1 when delta overflows (> 127 or < -128), in this case
+       firmware sends us (delta x / 5) and (delta y  / 5)
+
+byte 1:
+
+   bit   7   6   5   4   3   2   1   0
+        x7  x6  x5  x4  x3  x2  x1  x0
+
+        x7..x0 = delta x (two's complement)
+
+byte 2:
+
+   bit   7   6   5   4   3   2   1   0
+        y7  y6  y5  y4  y3  y2  y1  y0
+
+        y7..y0 = delta y (two's complement)
+
+byte 3:
+
+   bit   7   6   5   4   3   2   1   0
+       id2 id1 id0   1   0   0   1   0
+
+       id2..id0 = finger id
+
+byte 4:
+
+   bit   7   6   5   4   3   2   1   0
+        x7  x6  x5  x4  x3  x2  x1  x0
+
+        x7..x0 = delta x (two's complement)
+
+byte 5:
+
+   bit   7   6   5   4   3   2   1   0
+        y7  y6  y5  y4  y3  y2  y1  y0
+
+        y7..y0 = delta y (two's complement)
+
+        byte 0 ~ 2 for one finger
+        byte 3 ~ 5 for another
diff --git a/Documentation/input/input.txt b/Documentation/input/input.txt
index b93c084..b3d6787 100644
--- a/Documentation/input/input.txt
+++ b/Documentation/input/input.txt
@@ -111,7 +111,7 @@
 
  The monitor and speaker controls should be easy to add to the hid/input
 interface, but for the UPSs and LCDs it doesn't make much sense. For this,
-the hiddev interface was designed. See Documentation/usb/hiddev.txt
+the hiddev interface was designed. See Documentation/hid/hiddev.txt
 for more information about it.
 
   The usage of the usbhid module is very simple, it takes no parameters,
diff --git a/Documentation/input/multi-touch-protocol.txt b/Documentation/input/multi-touch-protocol.txt
index 71536e7..543101c 100644
--- a/Documentation/input/multi-touch-protocol.txt
+++ b/Documentation/input/multi-touch-protocol.txt
@@ -65,6 +65,20 @@
 end.  Upon receiving an MT event, one simply updates the appropriate
 attribute of the current slot.
 
+Some devices identify and/or track more contacts than they can report to the
+driver.  A driver for such a device should associate one type B slot with each
+contact that is reported by the hardware.  Whenever the identity of the
+contact associated with a slot changes, the driver should invalidate that
+slot by changing its ABS_MT_TRACKING_ID.  If the hardware signals that it is
+tracking more contacts than it is currently reporting, the driver should use
+a BTN_TOOL_*TAP event to inform userspace of the total number of contacts
+being tracked by the hardware at that moment.  The driver should do this by
+explicitly sending the corresponding BTN_TOOL_*TAP event and setting
+use_count to false when calling input_mt_report_pointer_emulation().
+The driver should only advertise as many slots as the hardware can report.
+Userspace can detect that a driver can report more total contacts than slots
+by noting that the largest supported BTN_TOOL_*TAP event is larger than the
+total number of type B slots reported in the absinfo for the ABS_MT_SLOT axis.
 
 Protocol Example A
 ------------------
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 845a191..54078ed 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -319,4 +319,6 @@
 					<mailto:thomas@winischhofer.net>
 0xF4	00-1F	video/mbxfb.h		mbxfb
 					<mailto:raph@8d.com>
+0xF6	all	LTTng			Linux Trace Toolkit Next Generation
+					<mailto:mathieu.desnoyers@efficios.com>
 0xFD	all	linux/dm-ioctl.h
diff --git a/Documentation/kernel-docs.txt b/Documentation/kernel-docs.txt
index 9a86746..eda1eb1 100644
--- a/Documentation/kernel-docs.txt
+++ b/Documentation/kernel-docs.txt
@@ -300,7 +300,7 @@
        
      * Title: "The Kernel Hacking HOWTO"
        Author: Various Talented People, and Rusty.
-       Location: in kernel tree, Documentation/DocBook/kernel-hacking/
+       Location: in kernel tree, Documentation/DocBook/kernel-hacking.tmpl
        (must be built as "make {htmldocs | psdocs | pdfdocs})
        Keywords: HOWTO, kernel contexts, deadlock, locking, modules,
        symbols, return conventions.
@@ -351,7 +351,7 @@
        
      * Title: "Linux Kernel Locking HOWTO"
        Author: Various Talented People, and Rusty.
-       Location: in kernel tree, Documentation/DocBook/kernel-locking/
+       Location: in kernel tree, Documentation/DocBook/kernel-locking.tmpl
        (must be built as "make {htmldocs | psdocs | pdfdocs})
        Keywords: locks, locking, spinlock, semaphore, atomic, race
        condition, bottom halves, tasklets, softirqs.
@@ -620,17 +620,6 @@
        (including this document itself) have been moved there, and might
        be more up to date than the web version.
 
-     * Name: "Linux Source Driver"
-       URL: http://lsd.linux.cz
-       Keywords: Browsing source code.
-       Description: "Linux Source Driver (LSD) is an application, which
-       can make browsing source codes of Linux kernel easier than you can
-       imagine. You can select between multiple versions of kernel (e.g.
-       0.01, 1.0.0, 2.0.33, 2.0.34pre13, 2.0.0, 2.1.101 etc.). With LSD
-       you can search Linux kernel (fulltext, macros, types, functions
-       and variables) and LSD can generate patches for you on the fly
-       (files, directories or kernel)".
-
      * Name: "Linux Kernel Source Reference"
        Author: Thomas Graichen.
        URL: http://marc.info/?l=linux-kernel&m=96446640102205&w=4
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e279b72..a0c5c5f 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -40,6 +40,7 @@
 	ALSA	ALSA sound support is enabled.
 	APIC	APIC support is enabled.
 	APM	Advanced Power Management support is enabled.
+	ARM	ARM architecture is enabled.
 	AVR32	AVR32 architecture is enabled.
 	AX25	Appropriate AX.25 support is enabled.
 	BLACKFIN Blackfin architecture is enabled.
@@ -48,7 +49,9 @@
 	EDD	BIOS Enhanced Disk Drive Services (EDD) is enabled
 	EFI	EFI Partitioning (GPT) is enabled
 	EIDE	EIDE/ATAPI support is enabled.
+	EVM	Extended Verification Module
 	FB	The frame buffer device is enabled.
+	FTRACE	Function tracing enabled.
 	GCOV	GCOV profiling is enabled.
 	HW	Appropriate hardware is enabled.
 	IA-64	IA-64 architecture is enabled.
@@ -69,6 +72,7 @@
 			Documentation/m68k/kernel-options.txt.
 	MCA	MCA bus support is enabled.
 	MDA	MDA console support is enabled.
+	MIPS	MIPS architecture is enabled.
 	MOUSE	Appropriate mouse support is enabled.
 	MSI	Message Signaled Interrupts (PCI).
 	MTD	MTD (Memory Technology Device) support is enabled.
@@ -100,7 +104,6 @@
 	SPARC	Sparc architecture is enabled.
 	SWSUSP	Software suspend (hibernation) is enabled.
 	SUSPEND	System suspend states are enabled.
-	FTRACE	Function tracing enabled.
 	TPM	TPM drivers are enabled.
 	TS	Appropriate touchscreen support is enabled.
 	UMS	USB Mass Storage support is enabled.
@@ -115,7 +118,7 @@
 	X86-64	X86-64 architecture is enabled.
 			More X86-64 boot options can be found in
 			Documentation/x86/x86_64/boot-options.txt .
-	X86	Either 32bit or 64bit x86 (same as X86-32+X86-64)
+	X86	Either 32-bit or 64-bit x86 (same as X86-32+X86-64)
 	XEN	Xen support is enabled
 
 In addition, the following text indicates that the option:
@@ -161,7 +164,7 @@
 			rsdt -- prefer RSDT over (default) XSDT
 			copy_dsdt -- copy DSDT to memory
 
-			See also Documentation/power/pm.txt, pci=noacpi
+			See also Documentation/power/runtime_pm.txt, pci=noacpi
 
 	acpi_rsdp=	[ACPI,EFI,KEXEC]
 			Pass the RSDP address to the kernel, mostly used
@@ -304,6 +307,19 @@
 			behaviour to be specified.  Bit 0 enables warnings,
 			bit 1 enables fixups, and bit 2 sends a segfault.
 
+	align_va_addr=	[X86-64]
+			Align virtual addresses by clearing slice [14:12] when
+			allocating a VMA at process creation time. This option
+			gives you up to 3% performance improvement on AMD F15h
+			machines (where it is enabled by default) for a
+			CPU-intensive style benchmark, and it can vary highly in
+			a microbenchmark depending on workload and compiler.
+
+			1: only for 32-bit processes
+			2: only for 64-bit processes
+			on: enable for both 32- and 64-bit processes
+			off: disable for both 32- and 64-bit processes
+
 	amd_iommu=	[HW,X86-84]
 			Pass parameters to the AMD IOMMU driver in the system.
 			Possible values are:
@@ -317,7 +333,7 @@
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT
 			Format: <a>,<b>
-			See also Documentation/kernel/input/joystick.txt
+			See also Documentation/input/joystick.txt
 
 	analog.map=	[HW,JOY] Analog joystick and gamepad support
 			Specifies type or capabilities of an analog joystick
@@ -376,7 +392,7 @@
 	atkbd.softrepeat= [HW]
 			Use software keyboard repeat
 
-	autotest	[IA64]
+	autotest	[IA-64]
 
 	baycom_epp=	[HW,AX25]
 			Format: <io>,<mode>
@@ -406,7 +422,7 @@
 	bttv.radio=	Most important insmod options are available as
 			kernel args too.
 	bttv.pll=	See Documentation/video4linux/bttv/Insmod-options
-	bttv.tuner=	and Documentation/video4linux/bttv/CARDLIST
+	bttv.tuner=
 
 	bulk_remove=off	[PPC]  This parameter disables the use of the pSeries
 			firmware feature for flushing multiple hpte entries
@@ -681,8 +697,8 @@
 		uart[8250],mmio32,<addr>[,options]
 			Start an early, polled-mode console on the 8250/16550
 			UART at the specified I/O port or MMIO address.
-			MMIO inter-register address stride is either 8bit (mmio)
-                        or 32bit (mmio32).
+			MMIO inter-register address stride is either 8-bit
+			(mmio) or 32-bit (mmio32).
 			The options are the same as for ttyS, above.
 
 	earlyprintk=	[X86,SH,BLACKFIN]
@@ -722,13 +738,13 @@
 
 	elevator=	[IOSCHED]
 			Format: {"cfq" | "deadline" | "noop"}
-			See Documentation/block/as-iosched.txt and
+			See Documentation/block/cfq-iosched.txt and
 			Documentation/block/deadline-iosched.txt for details.
 
-	elfcorehdr=	[IA64,PPC,SH,X86]
+	elfcorehdr=[size[KMG]@]offset[KMG] [IA64,PPC,SH,X86,S390]
 			Specifies physical address of start of kernel core
-			image elf header. Generally kexec loader will
-			pass this option to capture kernel.
+			image elf header and optionally the size. Generally
+			kexec loader will pass this option to capture kernel.
 			See Documentation/kdump/kdump.txt for details.
 
 	enable_mtrr_cleanup [X86]
@@ -758,12 +774,17 @@
 			This option is obsoleted by the "netdev=" option, which
 			has equivalent usage. See its documentation for details.
 
+	evm=		[EVM]
+			Format: { "fix" }
+			Permit 'security.evm' to be updated regardless of
+			current integrity status.
+
 	failslab=
 	fail_page_alloc=
 	fail_make_request=[KNL]
 			General fault injection mechanism.
 			Format: <interval>,<probability>,<space>,<times>
-			See also /Documentation/fault-injection/.
+			See also Documentation/fault-injection/.
 
 	floppy=		[HW]
 			See Documentation/blockdev/floppy.txt.
@@ -791,7 +812,7 @@
 			tracer at boot up. function-list is a comma separated
 			list of functions. This list can be changed at run
 			time by the set_ftrace_filter file in the debugfs
-			tracing directory. 
+			tracing directory.
 
 	ftrace_notrace=[function-list]
 			[FTRACE] Do not trace the functions specified in
@@ -829,7 +850,7 @@
 
 	hashdist=	[KNL,NUMA] Large hashes allocated during boot
 			are distributed across NUMA nodes.  Defaults on
-			for 64bit NUMA, off otherwise.
+			for 64-bit NUMA, off otherwise.
 			Format: 0 | 1 (for off | on)
 
 	hcl=		[IA-64] SGI's Hardware Graph compatibility layer
@@ -952,6 +973,9 @@
 	ignore_loglevel	[KNL]
 			Ignore loglevel setting - this will print /all/
 			kernel messages to the console. Useful for debugging.
+			We also add it as printk module parameter, so users
+			could change it dynamically, usually by
+			/sys/module/printk/parameters/ignore_loglevel.
 
 	ihash_entries=	[KNL]
 			Set number of hash buckets for inode cache.
@@ -998,10 +1022,10 @@
 			DMA.
 		forcedac [x86_64]
 			With this option iommu will not optimize to look
-			for io virtual address below 32 bit forcing dual
+			for io virtual address below 32-bit forcing dual
 			address cycle on pci bus for cards supporting greater
-			than 32 bit addressing. The default is to look
-			for translation below 32 bit and if not available
+			than 32-bit addressing. The default is to look
+			for translation below 32-bit and if not available
 			then look in the higher range.
 		strict [Default Off]
 			With this option on every unmap_single operation will
@@ -1012,12 +1036,13 @@
 			has the capability. With this option, super page will
 			not be supported.
 	intremap=	[X86-64, Intel-IOMMU]
-			Format: { on (default) | off | nosid }
 			on	enable Interrupt Remapping (default)
 			off	disable Interrupt Remapping
 			nosid	disable Source ID checking
+			no_x2apic_optout
+				BIOS x2APIC opt-out request will be ignored
 
-	inttest=	[IA64]
+	inttest=	[IA-64]
 
 	iomem=		Disable strict checking of access to MMIO memory
 		strict	regions from userspace.
@@ -1034,7 +1059,7 @@
 		nomerge
 		forcesac
 		soft
-		pt	[x86, IA64]
+		pt	[x86, IA-64]
 
 	io7=		[HW] IO7 for Marvel based alpha systems
 			See comment before marvel_specify_io7 in
@@ -1165,7 +1190,7 @@
 
 	kvm-amd.npt=	[KVM,AMD] Disable nested paging (virtualized MMU)
 			for all guests.
-			Default is 1 (enabled) if in 64bit or 32bit-PAE mode
+			Default is 1 (enabled) if in 64-bit or 32-bit PAE mode.
 
 	kvm-intel.ept=	[KVM,Intel] Disable extended page tables
 			(virtualized MMU) support on capable Intel chips.
@@ -1179,6 +1204,10 @@
 			[KVM,Intel] Disable FlexPriority feature (TPR shadow).
 			Default is 1 (enabled)
 
+	kvm-intel.nested=
+			[KVM,Intel] Enable VMX nesting (nVMX).
+			Default is 0 (disabled)
+
 	kvm-intel.unrestricted_guest=
 			[KVM,Intel] Disable unrestricted guest feature
 			(virtualized real and unpaged mode) on capable
@@ -1202,10 +1231,10 @@
 			libata.dma=0	  Disable all PATA and SATA DMA
 			libata.dma=1	  PATA and SATA Disk DMA only
 			libata.dma=2	  ATAPI (CDROM) DMA only
-			libata.dma=4	  Compact Flash DMA only 
+			libata.dma=4	  Compact Flash DMA only
 			Combinations also work, so libata.dma=3 enables DMA
 			for disks and CDROMs, but not CFs.
-	
+
 	libata.ignore_hpa=	[LIBATA] Ignore HPA limit
 			libata.ignore_hpa=0	  keep BIOS limits (default)
 			libata.ignore_hpa=1	  ignore limits, using full disk
@@ -1331,7 +1360,7 @@
 	ltpc=		[NET]
 			Format: <io>,<irq>,<dma>
 
-	machvec=	[IA64] Force the use of a particular machine-vector
+	machvec=	[IA-64] Force the use of a particular machine-vector
 			(machvec) in a generic kernel.
 			Example: machvec=hpzx1_swiotlb
 
@@ -1348,9 +1377,12 @@
 			it is equivalent to "nosmp", which also disables
 			the IO APIC.
 
-	max_loop=	[LOOP] Maximum number of loopback devices that can
-			be mounted
-			Format: <1-256>
+	max_loop=	[LOOP] The number of loop block devices that get
+	(loop.max_loop)	unconditionally pre-created at init time. The default
+			number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead
+			of statically allocating a predefined number, loop
+			devices can be requested on-demand with the
+			/dev/loop-control interface.
 
 	mcatest=	[IA-64]
 
@@ -1637,6 +1669,11 @@
 			debugging driver suspend/resume hooks).  This may
 			not work reliably with all consoles, but is known
 			to work with serial and VGA consoles.
+			To facilitate more flexible debugging, we also add
+			console_suspend, a printk module parameter to control
+			it. Users could use console_suspend (usually
+			/sys/module/printk/parameters/console_suspend) to
+			turn on/off it dynamically.
 
 	noaliencache	[MM, NUMA, SLAB] Disables the allocation of alien
 			caches in the slab allocator.  Saves per-node memory,
@@ -1734,7 +1771,7 @@
 
 	nointroute	[IA-64]
 
-	nojitter	[IA64] Disables jitter checking for ITC timers.
+	nojitter	[IA-64] Disables jitter checking for ITC timers.
 
 	no-kvmclock	[X86,KVM] Disable paravirtualized KVM clock driver
 
@@ -1772,6 +1809,11 @@
 
 	noresidual	[PPC] Don't use residual data on PReP machines.
 
+	nordrand	[X86] Disable the direct use of the RDRAND
+			instruction even if it is supported by the
+			processor.  RDRAND is still available to user
+			space applications.
+
 	noresume	[SWSUSP] Disables resume and restores original swap
 			space.
 
@@ -1800,7 +1842,7 @@
 
 	nox2apic	[X86-64,APIC] Do not enable x2APIC mode.
 
-	nptcg=		[IA64] Override max number of concurrent global TLB
+	nptcg=		[IA-64] Override max number of concurrent global TLB
 			purges which is reported from either PAL_VM_SUMMARY or
 			SAL PALO.
 
@@ -2077,13 +2119,16 @@
 			Format: { parport<nr> | timid | 0 }
 			See also Documentation/parport.txt.
 
-	pmtmr=		[X86] Manual setup of pmtmr I/O Port. 
+	pmtmr=		[X86] Manual setup of pmtmr I/O Port.
 			Override pmtimer IOPort with a hex value.
 			e.g. pmtmr=0x508
 
-	pnp.debug	[PNP]
-			Enable PNP debug messages.  This depends on the
-			CONFIG_PNP_DEBUG_MESSAGES option.
+	pnp.debug=1	[PNP]
+			Enable PNP debug messages (depends on the
+			CONFIG_PNP_DEBUG_MESSAGES option).  Change at run-time
+			via /sys/module/pnp/parameters/debug.  We always show
+			current resource usage; turning this on also shows
+			possible settings and some assignment information.
 
 	pnpacpi=	[ACPI]
 			{ off }
@@ -2232,6 +2277,13 @@
 			in <PAGE_SIZE> units (needed only for swap files).
 			See  Documentation/power/swsusp-and-swap-files.txt
 
+	resumedelay=	[HIBERNATION] Delay (in seconds) to pause before attempting to
+			read the resume files
+
+	resumewait	[HIBERNATION] Wait (indefinitely) for resume device to show up.
+			Useful for devices that are detected asynchronously
+			(e.g. USB and MMC devices).
+
 	hibernate=	[HIBERNATION]
 		noresume	Don't check if there's a hibernation image
 				present during boot.
@@ -2367,7 +2419,7 @@
 			Format: <integer>
 
 	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
-			See Documentation/sonypi.txt
+			See Documentation/laptops/sonypi.txt
 
 	specialix=	[HW,SERIAL] Specialix multi-serial port adapter
 			See Documentation/serial/specialix.txt.
@@ -2635,6 +2687,16 @@
 					medium is write-protected).
 			Example: quirks=0419:aaf5:rl,0421:0433:rc
 
+	user_debug=	[KNL,ARM]
+			Format: <int>
+			See arch/arm/Kconfig.debug help text.
+				 1 - undefined instruction events
+				 2 - system calls
+				 4 - invalid data aborts
+				 8 - SIGSEGV faults
+				16 - SIGBUS faults
+			Example: user_debug=31
+
 	userpte=
 			[X86] Flags controlling user PTE allocations.
 
@@ -2680,6 +2742,28 @@
 	vmpoff=		[KNL,S390] Perform z/VM CP command after power off.
 			Format: <command>
 
+	vsyscall=	[X86-64]
+			Controls the behavior of vsyscalls (i.e. calls to
+			fixed addresses of 0xffffffffff600x00 from legacy
+			code).  Most statically-linked binaries and older
+			versions of glibc use these calls.  Because these
+			functions are at fixed addresses, they make nice
+			targets for exploits that can control RIP.
+
+			emulate     Vsyscalls turn into traps and are emulated
+			            reasonably safely.
+
+			native      [default] Vsyscalls are native syscall
+			            instructions.
+			            This is a little bit faster than trapping
+			            and makes a few dynamic recompilers work
+			            better than they would in emulation mode.
+			            It also makes exploits much easier to write.
+
+			none        Vsyscalls don't work at all.  This makes
+			            them quite hard to use for exploits but
+			            might break your system.
+
 	vt.cur_default=	[VT] Default cursor shape.
 			Format: 0xCCBBAA, where AA, BB, and CC are the same as
 			the parameters of the <Esc>[?A;B;Cc escape sequence;
diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt
index 6181548..9d66682 100644
--- a/Documentation/laptops/thinkpad-acpi.txt
+++ b/Documentation/laptops/thinkpad-acpi.txt
@@ -411,9 +411,9 @@
 
 0x1004	0x03	FN+F4		Sleep button (ACPI sleep button
 				semantics, i.e. sleep-to-RAM).
-				It is always generate some kind
+				It always generates some kind
 				of event, either the hot key
-				event or a ACPI sleep button
+				event or an ACPI sleep button
 				event. The firmware may
 				refuse to generate further FN+F4
 				key presses until a S3 or S4 ACPI
@@ -736,7 +736,7 @@
 sysfs notes:
 
 The ThinkLight sysfs interface is documented by the LED class
-documentation, in Documentation/leds-class.txt.  The ThinkLight LED name
+documentation, in Documentation/leds/leds-class.txt.  The ThinkLight LED name
 is "tpacpi::thinklight".
 
 Due to limitations in the sysfs LED class, if the status of the ThinkLight
@@ -833,7 +833,7 @@
 sysfs notes:
 
 The ThinkPad LED sysfs interface is described in detail by the LED class
-documentation, in Documentation/leds-class.txt.
+documentation, in Documentation/leds/leds-class.txt.
 
 The LEDs are named (in LED ID order, from 0 to 12):
 "tpacpi::power", "tpacpi:orange:batt", "tpacpi:green:batt",
diff --git a/Documentation/leds/leds-class.txt b/Documentation/leds/leds-class.txt
index 4996586..79699c2 100644
--- a/Documentation/leds/leds-class.txt
+++ b/Documentation/leds/leds-class.txt
@@ -61,8 +61,8 @@
 Some LEDs can be programmed to blink without any CPU interaction. To
 support this feature, a LED driver can optionally implement the
 blink_set() function (see <linux/leds.h>). To set an LED to blinking,
-however, it is better to use use the API function led_blink_set(),
-as it will check and implement software fallback if necessary.
+however, it is better to use the API function led_blink_set(), as it
+will check and implement software fallback if necessary.
 
 To turn off blinking again, use the API function led_brightness_set()
 as that will not just set the LED brightness but also stop any software
diff --git a/Documentation/media-framework.txt b/Documentation/media-framework.txt
index 669b5fb..3a0f879 100644
--- a/Documentation/media-framework.txt
+++ b/Documentation/media-framework.txt
@@ -9,8 +9,8 @@
 ------------
 
 The media controller API is documented in DocBook format in
-Documentation/DocBook/v4l/media-controller.xml. This document will focus on
-the kernel-side implementation of the media framework.
+Documentation/DocBook/media/v4l/media-controller.xml. This document will focus
+on the kernel-side implementation of the media framework.
 
 
 Abstract media device model
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index f0d3a80..2759f7c 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -438,7 +438,7 @@
 	[*] For information on bus mastering DMA and coherency please read:
 
 	    Documentation/PCI/pci.txt
-	    Documentation/PCI/PCI-DMA-mapping.txt
+	    Documentation/DMA-API-HOWTO.txt
 	    Documentation/DMA-API.txt
 
 
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index 4edd78d..bbce121 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -1,13 +1,21 @@
 00-INDEX
 	- this file
+3c359.txt
+	- information on the 3Com TokenLink Velocity XL (3c5359) driver.
 3c505.txt
 	- information on the 3Com EtherLink Plus (3c505) driver.
+3c509.txt
+	- information on the 3Com Etherlink III Series Ethernet cards.
 6pack.txt
 	- info on the 6pack protocol, an alternative to KISS for AX.25
 DLINK.txt
 	- info on the D-Link DE-600/DE-620 parallel port pocket adapters
 PLIP.txt
 	- PLIP: The Parallel Line Internet Protocol device driver
+README.ipw2100
+	- README for the Intel PRO/Wireless 2100 driver.
+README.ipw2200
+	- README for the Intel PRO/Wireless 2915ABG and 2200BG driver.
 README.sb1000
 	- info on General Instrument/NextLevel SURFboard1000 cable modem.
 alias.txt
@@ -20,8 +28,12 @@
 	- info on where to get ATM programs and support for Linux.
 ax25.txt
 	- info on using AX.25 and NET/ROM code for Linux
+batman-adv.txt
+	- B.A.T.M.A.N routing protocol on top of layer 2 Ethernet Frames.
 baycom.txt
 	- info on the driver for Baycom style amateur radio modems
+bonding.txt
+	- Linux Ethernet Bonding Driver HOWTO: link aggregation in Linux.
 bridge.txt
 	- where to get user space programs for ethernet bridging with Linux.
 can.txt
@@ -34,32 +46,60 @@
 	- Conexant AccessRunner USB ADSL Modem
 cxacru-cf.py
 	- Conexant AccessRunner USB ADSL Modem configuration file parser
+cxgb.txt
+	- Release Notes for the Chelsio N210 Linux device driver.
+dccp.txt
+	- the Datagram Congestion Control Protocol (DCCP) (RFC 4340..42).
 de4x5.txt
 	- the Digital EtherWORKS DE4?? and DE5?? PCI Ethernet driver
 decnet.txt
 	- info on using the DECnet networking layer in Linux.
 depca.txt
 	- the Digital DEPCA/EtherWORKS DE1?? and DE2?? LANCE Ethernet driver
+dl2k.txt
+	- README for D-Link DL2000-based Gigabit Ethernet Adapters (dl2k.ko).
+dm9000.txt
+	- README for the Simtec DM9000 Network driver.
 dmfe.txt
 	- info on the Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver.
+dns_resolver.txt
+	- The DNS resolver module allows kernel servies to make DNS queries.
+driver.txt
+	- Softnet driver issues.
 e100.txt
 	- info on Intel's EtherExpress PRO/100 line of 10/100 boards
 e1000.txt
 	- info on Intel's E1000 line of gigabit ethernet boards
+e1000e.txt
+	- README for the Intel Gigabit Ethernet Driver (e1000e).
 eql.txt
 	- serial IP load balancing
 ewrk3.txt
 	- the Digital EtherWORKS 3 DE203/4/5 Ethernet driver
+fib_trie.txt
+	- Level Compressed Trie (LC-trie) notes: a structure for routing.
 filter.txt
 	- Linux Socket Filtering
 fore200e.txt
 	- FORE Systems PCA-200E/SBA-200E ATM NIC driver info.
 framerelay.txt
 	- info on using Frame Relay/Data Link Connection Identifier (DLCI).
+gen_stats.txt
+	- Generic networking statistics for netlink users.
+generic_hdlc.txt
+	- The generic High Level Data Link Control (HDLC) layer.
 generic_netlink.txt
 	- info on Generic Netlink
+gianfar.txt
+	- Gianfar Ethernet Driver.
 ieee802154.txt
 	- Linux IEEE 802.15.4 implementation, API and drivers
+ifenslave.c
+	- Configure network interfaces for parallel routing (bonding).
+igb.txt
+	- README for the Intel Gigabit Ethernet Driver (igb).
+igbvf.txt
+	- README for the Intel Gigabit Ethernet Driver (igbvf).
 ip-sysctl.txt
 	- /proc/sys/net/ipv4/* variables
 ip_dynaddr.txt
@@ -68,41 +108,117 @@
 	- AppleTalk-IP Decapsulation and AppleTalk-IP Encapsulation
 iphase.txt
 	- Interphase PCI ATM (i)Chip IA Linux driver info.
+ipv6.txt
+	- Options to the ipv6 kernel module.
+ipvs-sysctl.txt
+	- Per-inode explanation of the /proc/sys/net/ipv4/vs interface.
 irda.txt
 	- where to get IrDA (infrared) utilities and info for Linux.
+ixgb.txt
+	- README for the Intel 10 Gigabit Ethernet Driver (ixgb).
+ixgbe.txt
+	- README for the Intel 10 Gigabit Ethernet Driver (ixgbe).
+ixgbevf.txt
+	- README for the Intel Virtual Function (VF) Driver (ixgbevf).
+l2tp.txt
+	- User guide to the L2TP tunnel protocol.
 lapb-module.txt
 	- programming information of the LAPB module.
 ltpc.txt
 	- the Apple or Farallon LocalTalk PC card driver
+mac80211-injection.txt
+	- HOWTO use packet injection with mac80211
 multicast.txt
 	- Behaviour of cards under Multicast
+multiqueue.txt
+	- HOWTO for multiqueue network device support.
+netconsole.txt
+	- The network console module netconsole.ko: configuration and notes.
+netdev-features.txt
+	- Network interface features API description.
 netdevices.txt
 	- info on network device driver functions exported to the kernel.
+netif-msg.txt
+	- Design of the network interface message level setting (NETIF_MSG_*).
+nfc.txt
+	- The Linux Near Field Communication (NFS) subsystem.
 olympic.txt
 	- IBM PCI Pit/Pit-Phy/Olympic Token Ring driver info.
+operstates.txt
+	- Overview of network interface operational states.
+packet_mmap.txt
+	- User guide to memory mapped packet socket rings (PACKET_[RT]X_RING).
+phonet.txt
+	- The Phonet packet protocol used in Nokia cellular modems.
+phy.txt
+	- The PHY abstraction layer.
+pktgen.txt
+	- User guide to the kernel packet generator (pktgen.ko).
 policy-routing.txt
 	- IP policy-based routing
+ppp_generic.txt
+	- Information about the generic PPP driver.
+proc_net_tcp.txt
+	- Per inode overview of the /proc/net/tcp and /proc/net/tcp6 interfaces.
+radiotap-headers.txt
+	- Background on radiotap headers.
 ray_cs.txt
 	- Raylink Wireless LAN card driver info.
+rds.txt
+	- Background on the reliable, ordered datagram delivery method RDS.
+regulatory.txt
+	- Overview of the Linux wireless regulatory infrastructure.
+rxrpc.txt
+	- Guide to the RxRPC protocol.
+s2io.txt
+	- Release notes for Neterion Xframe I/II 10GbE driver.
+scaling.txt
+	- Explanation of network scaling techniques: RSS, RPS, RFS, aRFS, XPS.
+sctp.txt
+	- Notes on the Linux kernel implementation of the SCTP protocol.
+secid.txt
+	- Explanation of the secid member in flow structures.
 skfp.txt
 	- SysKonnect FDDI (SK-5xxx, Compaq Netelligent) driver info.
 smc9.txt
 	- the driver for SMC's 9000 series of Ethernet cards
 smctr.txt
 	- SMC TokenCard TokenRing Linux driver info.
+spider-net.txt
+	- README for the Spidernet Driver (as found in PS3 / Cell BE).
+stmmac.txt
+	- README for the STMicro Synopsys Ethernet driver.
+tc-actions-env-rules.txt
+	- rules for traffic control (tc) actions.
+timestamping.txt
+	- overview of network packet timestamping variants.
 tcp.txt
 	- short blurb on how TCP output takes place.
+tcp-thin.txt
+	- kernel tuning options for low rate 'thin' TCP streams.
 tlan.txt
 	- ThunderLAN (Compaq Netelligent 10/100, Olicom OC-2xxx) driver info.
 tms380tr.txt
 	- SysKonnect Token Ring ISA/PCI adapter driver info.
+tproxy.txt
+	- Transparent proxy support user guide.
 tuntap.txt
 	- TUN/TAP device driver, allowing user space Rx/Tx of packets.
+udplite.txt
+	- UDP-Lite protocol (RFC 3828) introduction.
 vortex.txt
 	- info on using 3Com Vortex (3c590, 3c592, 3c595, 3c597) Ethernet cards.
+vxge.txt
+	- README for the Neterion X3100 PCIe Server Adapter.
 x25.txt
 	- general info on X.25 development.
 x25-iface.txt
 	- description of the X.25 Packet Layer to LAPB device interface.
+xfrm_proc.txt
+	- description of the statistics package for XFRM.
+xfrm_sync.txt
+	- sync patches for XFRM enable migration of an SA between hosts.
+xfrm_sysctl.txt
+	- description of the XFRM configuration options.
 z8530drv.txt
 	- info about Linux driver for Z8530 based HDLC cards for AX.25
diff --git a/Documentation/networking/LICENSE.qlcnic b/Documentation/networking/LICENSE.qlcnic
index 29ad4b1..e7fb2c6 100644
--- a/Documentation/networking/LICENSE.qlcnic
+++ b/Documentation/networking/LICENSE.qlcnic
@@ -1,61 +1,22 @@
-Copyright (c) 2009-2010 QLogic Corporation
+Copyright (c) 2009-2011 QLogic Corporation
 QLogic Linux qlcnic NIC Driver
 
-This program includes a device driver for Linux 2.6 that may be
-distributed with QLogic hardware specific firmware binary file.
 You may modify and redistribute the device driver code under the
 GNU General Public License (a copy of which is attached hereto as
 Exhibit A) published by the Free Software Foundation (version 2).
 
-You may redistribute the hardware specific firmware binary file
-under the following terms:
-
-       1. Redistribution of source code (only if applicable),
-          must retain the above copyright notice, this list of
-          conditions and the following disclaimer.
-
-       2. Redistribution in binary form must reproduce the above
-          copyright notice, this list of conditions and the
-          following disclaimer in the documentation and/or other
-          materials provided with the distribution.
-
-       3. The name of QLogic Corporation may not be used to
-          endorse or promote products derived from this software
-          without specific prior written permission
-
-REGARDLESS OF WHAT LICENSING MECHANISM IS USED OR APPLICABLE,
-THIS PROGRAM IS PROVIDED BY QLOGIC CORPORATION "AS IS'' AND ANY
-EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
-PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR
-BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
-EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
-TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
-DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
-ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
-OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.
-
-USER ACKNOWLEDGES AND AGREES THAT USE OF THIS PROGRAM WILL NOT
-CREATE OR GIVE GROUNDS FOR A LICENSE BY IMPLICATION, ESTOPPEL, OR
-OTHERWISE IN ANY INTELLECTUAL PROPERTY RIGHTS (PATENT, COPYRIGHT,
-TRADE SECRET, MASK WORK, OR OTHER PROPRIETARY RIGHT) EMBODIED IN
-ANY OTHER QLOGIC HARDWARE OR SOFTWARE EITHER SOLELY OR IN
-COMBINATION WITH THIS PROGRAM.
-
 
 EXHIBIT A
 
-                   GNU GENERAL PUBLIC LICENSE
-                      Version 2, June 1991
+		    GNU GENERAL PUBLIC LICENSE
+		       Version 2, June 1991
 
  Copyright (C) 1989, 1991 Free Software Foundation, Inc.
  51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
  Everyone is permitted to copy and distribute verbatim copies
  of this license document, but changing it is not allowed.
 
-                           Preamble
+			    Preamble
 
   The licenses for most software are designed to take away your
 freedom to share and change it.  By contrast, the GNU General Public
@@ -105,7 +66,7 @@
   The precise terms and conditions for copying, distribution and
 modification follow.
 
-                   GNU GENERAL PUBLIC LICENSE
+		    GNU GENERAL PUBLIC LICENSE
    TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
 
   0. This License applies to any program or other work which contains
@@ -304,7 +265,7 @@
 of preserving the free status of all derivatives of our free software and
 of promoting the sharing and reuse of software generally.
 
-                           NO WARRANTY
+			    NO WARRANTY
 
   11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
 FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
diff --git a/Documentation/networking/batman-adv.txt b/Documentation/networking/batman-adv.txt
index 88d4afb..c86d03f 100644
--- a/Documentation/networking/batman-adv.txt
+++ b/Documentation/networking/batman-adv.txt
@@ -1,4 +1,4 @@
-[state: 17-04-2011]
+[state: 21-08-2011]
 
 BATMAN-ADV
 ----------
@@ -68,9 +68,9 @@
 folder:
 
 #  ls  /sys/class/net/bat0/mesh/
-#  aggregated_ogms  gw_bandwidth  hop_penalty
-#  bonding          gw_mode       orig_interval
-#  fragmentation    gw_sel_class  vis_mode
+# aggregated_ogms   fragmentation gw_sel_class   vis_mode
+# ap_isolation      gw_bandwidth  hop_penalty
+# bonding           gw_mode       orig_interval
 
 
 There is a special folder for debugging information:
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index 5dd960d..91df678 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -238,6 +238,18 @@
 
 	This option was added in bonding version 3.4.0.
 
+all_slaves_active
+
+	Specifies that duplicate frames (received on inactive ports) should be
+	dropped (0) or delivered (1).
+
+	Normally, bonding will drop duplicate frames (received on inactive
+	ports), which is desirable for most users. But there are some times
+	it is nice to allow duplicate frames to be delivered.
+
+	The default value is 0 (drop duplicate frames received on inactive
+	ports).
+
 arp_interval
 
 	Specifies the ARP link monitoring frequency in milliseconds.
@@ -433,6 +445,23 @@
 	determined.  See the High Availability section for additional
 	information.  The default value is 0.
 
+min_links
+
+	Specifies the minimum number of links that must be active before
+	asserting carrier. It is similar to the Cisco EtherChannel min-links
+	feature. This allows setting the minimum number of member ports that
+	must be up (link-up state) before marking the bond device as up
+	(carrier on). This is useful for situations where higher level services
+	such as clustering want to ensure a minimum number of low bandwidth
+	links are active before switchover. This option only affect 802.3ad
+	mode.
+
+	The default value is 0. This will cause carrier to be asserted (for
+	802.3ad mode) whenever there is an active aggregator, regardless of the
+	number of available links in that aggregator. Note that, because an
+	aggregator cannot be active without at least one available link,
+	setting this option to 0 or to 1 has the exact same effect.
+
 mode
 
 	Specifies one of the bonding policies. The default is
diff --git a/Documentation/networking/dmfe.txt b/Documentation/networking/dmfe.txt
index 8006c22..25320bf 100644
--- a/Documentation/networking/dmfe.txt
+++ b/Documentation/networking/dmfe.txt
@@ -1,3 +1,5 @@
+Note: This driver doesn't have a maintainer.
+
 Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver for Linux.
 
 This program is free software; you can redistribute it and/or
@@ -55,7 +57,6 @@
 Authors:
 
 Sten Wang <sten_wang@davicom.com.tw >   : Original Author
-Tobias Ringstrom <tori@unhappy.mine.nu> : Current Maintainer
 
 Contributors:
 
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index db2a406..cb7f314 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -992,7 +992,7 @@
 		TRUE: disable IPv4-mapped address feature
 		FALSE: enable IPv4-mapped address feature
 
-	Default: FALSE (as specified in RFC2553bis)
+	Default: FALSE (as specified in RFC3493)
 
 IPv6 Fragmentation:
 
@@ -1042,9 +1042,14 @@
 	The functional behaviour for certain settings is different
 	depending on whether local forwarding is enabled or not.
 
-accept_ra - BOOLEAN
+accept_ra - INTEGER
 	Accept Router Advertisements; autoconfigure using them.
 
+	It also determines whether or not to transmit Router
+	Solicitations. If and only if the functional setting is to
+	accept Router Advertisements, Router Solicitations will be
+	transmitted.
+
 	Possible values are:
 		0 Do not accept Router Advertisements.
 		1 Accept Router Advertisements if forwarding is disabled.
@@ -1106,7 +1111,7 @@
 	The amount of Duplicate Address Detection probes to send.
 	Default: 1
 
-forwarding - BOOLEAN
+forwarding - INTEGER
 	Configure interface-specific Host/Router behaviour.
 
 	Note: It is recommended to have the same setting on all
@@ -1115,14 +1120,14 @@
 	Possible values are:
 		0 Forwarding disabled
 		1 Forwarding enabled
-		2 Forwarding enabled (Hybrid Mode)
 
 	FALSE (0):
 
 	By default, Host behaviour is assumed.  This means:
 
 	1. IsRouter flag is not set in Neighbour Advertisements.
-	2. Router Solicitations are being sent when necessary.
+	2. If accept_ra is TRUE (default), transmit Router
+	   Solicitations.
 	3. If accept_ra is TRUE (default), accept Router
 	   Advertisements (and do autoconfiguration).
 	4. If accept_redirects is TRUE (default), accept Redirects.
@@ -1133,16 +1138,10 @@
 	This means exactly the reverse from the above:
 
 	1. IsRouter flag is set in Neighbour Advertisements.
-	2. Router Solicitations are not sent.
+	2. Router Solicitations are not sent unless accept_ra is 2.
 	3. Router Advertisements are ignored unless accept_ra is 2.
 	4. Redirects are ignored.
 
-	TRUE (2):
-
-	Hybrid mode. Same behaviour as TRUE, except for:
-
-	2. Router Solicitations are being sent when necessary.
-
 	Default: 0 (disabled) if global forwarding is disabled (default),
 		 otherwise 1 (enabled).
 
diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt
index 4ccdbca..f2a2488 100644
--- a/Documentation/networking/ipvs-sysctl.txt
+++ b/Documentation/networking/ipvs-sysctl.txt
@@ -15,6 +15,23 @@
         enabled and the variable is automatically set to 2, otherwise
         the strategy is disabled and the variable is  set  to 1.
 
+conntrack - BOOLEAN
+	0 - disabled (default)
+	not 0 - enabled
+
+	If set, maintain connection tracking entries for
+	connections handled by IPVS.
+
+	This should be enabled if connections handled by IPVS are to be
+	also handled by stateful firewall rules. That is, iptables rules
+	that make use of connection tracking.  It is a performance
+	optimisation to disable this setting otherwise.
+
+	Connections handled by the IPVS FTP application module
+	will have connection tracking entries regardless of this setting.
+
+	Only available when IPVS is compiled with CONFIG_IP_VS_NFCT enabled.
+
 cache_bypass - BOOLEAN
         0 - disabled (default)
         not 0 - enabled
@@ -39,7 +56,7 @@
 	11         - IPVS packet handling (ip_vs_in/ip_vs_out)
 	12 or more - packet traversal
 
-	Only available when IPVS is compiled with the CONFIG_IPVS_DEBUG
+	Only available when IPVS is compiled with CONFIG_IP_VS_DEBUG enabled.
 
 	Higher debugging levels include the messages for lower debugging
 	levels, so setting debug level 2, includes level 0, 1 and 2
@@ -123,13 +140,11 @@
 secure_tcp - INTEGER
         0  - disabled (default)
 
-        The secure_tcp defense is to use a more complicated state
-        transition table and some possible short timeouts of each
-        state. In the VS/NAT, it delays the entering the ESTABLISHED
-        until the real server starts to send data and ACK packet
-        (after 3-way handshake).
+	The secure_tcp defense is to use a more complicated TCP state
+	transition table. For VS/NAT, it also delays entering the
+	TCP ESTABLISHED state until the three way handshake is completed.
 
-        The value definition is the same as that of drop_entry or
+        The value definition is the same as that of drop_entry and
         drop_packet.
 
 sync_threshold - INTEGER
@@ -141,3 +156,36 @@
         synchronized, every time the number of its incoming packets
         modulus 50 equals the threshold. The range of the threshold is
         from 0 to 49.
+
+snat_reroute - BOOLEAN
+	0 - disabled
+	not 0 - enabled (default)
+
+	If enabled, recalculate the route of SNATed packets from
+	realservers so that they are routed as if they originate from the
+	director. Otherwise they are routed as if they are forwarded by the
+	director.
+
+	If policy routing is in effect then it is possible that the route
+	of a packet originating from a director is routed differently to a
+	packet being forwarded by the director.
+
+	If policy routing is not in effect then the recalculated route will
+	always be the same as the original route so it is an optimisation
+	to disable snat_reroute and avoid the recalculation.
+
+sync_version - INTEGER
+	default 1
+
+	The version of the synchronisation protocol used when sending
+	synchronisation messages.
+
+	0 selects the original synchronisation protocol (version 0). This
+	should be used when sending synchronisation messages to a legacy
+	system that only understands the original synchronisation protocol.
+
+	1 selects the current synchronisation protocol (version 1). This
+	should be used where possible.
+
+	Kernels with this sync_version entry are able to receive messages
+	of both version 1 and version 2 of the synchronisation protocol.
diff --git a/Documentation/networking/mac80211-injection.txt b/Documentation/networking/mac80211-injection.txt
index b30e81a..3a93007 100644
--- a/Documentation/networking/mac80211-injection.txt
+++ b/Documentation/networking/mac80211-injection.txt
@@ -23,6 +23,10 @@
    IEEE80211_RADIOTAP_F_FRAG: frame will be fragmented if longer than the
 			      current fragmentation threshold.
 
+ * IEEE80211_RADIOTAP_TX_FLAGS
+
+   IEEE80211_RADIOTAP_F_TX_NOACK: frame should be sent without waiting for
+				  an ACK even if it is a unicast frame
 
 The injection code can also skip all other currently defined radiotap fields
 facilitating replay of captured radiotap headers directly.
diff --git a/Documentation/networking/netdevices.txt b/Documentation/networking/netdevices.txt
index 87b3d15..8935834 100644
--- a/Documentation/networking/netdevices.txt
+++ b/Documentation/networking/netdevices.txt
@@ -73,7 +73,7 @@
 	has to lock by itself when needed. It is recommended to use a try lock
 	for this and return NETDEV_TX_LOCKED when the spin lock fails.
 	The locking there should also properly protect against 
-	set_multicast_list. Note that the use of NETIF_F_LLTX is deprecated.
+	set_rx_mode. Note that the use of NETIF_F_LLTX is deprecated.
 	Don't use it for new drivers.
 
 	Context: Process with BHs disabled or BH (timer),
@@ -92,7 +92,7 @@
 	Context: BHs disabled
 	Notes: netif_queue_stopped() is guaranteed true
 
-dev->set_multicast_list:
+dev->set_rx_mode:
 	Synchronization: netif_tx_lock spinlock.
 	Context: BHs disabled
 
diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt
new file mode 100644
index 0000000..a177de2
--- /dev/null
+++ b/Documentation/networking/scaling.txt
@@ -0,0 +1,378 @@
+Scaling in the Linux Networking Stack
+
+
+Introduction
+============
+
+This document describes a set of complementary techniques in the Linux
+networking stack to increase parallelism and improve performance for
+multi-processor systems.
+
+The following technologies are described:
+
+  RSS: Receive Side Scaling
+  RPS: Receive Packet Steering
+  RFS: Receive Flow Steering
+  Accelerated Receive Flow Steering
+  XPS: Transmit Packet Steering
+
+
+RSS: Receive Side Scaling
+=========================
+
+Contemporary NICs support multiple receive and transmit descriptor queues
+(multi-queue). On reception, a NIC can send different packets to different
+queues to distribute processing among CPUs. The NIC distributes packets by
+applying a filter to each packet that assigns it to one of a small number
+of logical flows. Packets for each flow are steered to a separate receive
+queue, which in turn can be processed by separate CPUs. This mechanism is
+generally known as “Receive-side Scaling” (RSS). The goal of RSS and
+the other scaling techniques is to increase performance uniformly.
+Multi-queue distribution can also be used for traffic prioritization, but
+that is not the focus of these techniques.
+
+The filter used in RSS is typically a hash function over the network
+and/or transport layer headers-- for example, a 4-tuple hash over
+IP addresses and TCP ports of a packet. The most common hardware
+implementation of RSS uses a 128-entry indirection table where each entry
+stores a queue number. The receive queue for a packet is determined
+by masking out the low order seven bits of the computed hash for the
+packet (usually a Toeplitz hash), taking this number as a key into the
+indirection table and reading the corresponding value.
+
+Some advanced NICs allow steering packets to queues based on
+programmable filters. For example, webserver bound TCP port 80 packets
+can be directed to their own receive queue. Such “n-tuple” filters can
+be configured from ethtool (--config-ntuple).
+
+==== RSS Configuration
+
+The driver for a multi-queue capable NIC typically provides a kernel
+module parameter for specifying the number of hardware queues to
+configure. In the bnx2x driver, for instance, this parameter is called
+num_queues. A typical RSS configuration would be to have one receive queue
+for each CPU if the device supports enough queues, or otherwise at least
+one for each memory domain, where a memory domain is a set of CPUs that
+share a particular memory level (L1, L2, NUMA node, etc.).
+
+The indirection table of an RSS device, which resolves a queue by masked
+hash, is usually programmed by the driver at initialization. The
+default mapping is to distribute the queues evenly in the table, but the
+indirection table can be retrieved and modified at runtime using ethtool
+commands (--show-rxfh-indir and --set-rxfh-indir). Modifying the
+indirection table could be done to give different queues different
+relative weights.
+
+== RSS IRQ Configuration
+
+Each receive queue has a separate IRQ associated with it. The NIC triggers
+this to notify a CPU when new packets arrive on the given queue. The
+signaling path for PCIe devices uses message signaled interrupts (MSI-X),
+that can route each interrupt to a particular CPU. The active mapping
+of queues to IRQs can be determined from /proc/interrupts. By default,
+an IRQ may be handled on any CPU. Because a non-negligible part of packet
+processing takes place in receive interrupt handling, it is advantageous
+to spread receive interrupts between CPUs. To manually adjust the IRQ
+affinity of each interrupt see Documentation/IRQ-affinity.txt. Some systems
+will be running irqbalance, a daemon that dynamically optimizes IRQ
+assignments and as a result may override any manual settings.
+
+== Suggested Configuration
+
+RSS should be enabled when latency is a concern or whenever receive
+interrupt processing forms a bottleneck. Spreading load between CPUs
+decreases queue length. For low latency networking, the optimal setting
+is to allocate as many queues as there are CPUs in the system (or the
+NIC maximum, if lower). The most efficient high-rate configuration
+is likely the one with the smallest number of receive queues where no
+receive queue overflows due to a saturated CPU, because in default
+mode with interrupt coalescing enabled, the aggregate number of
+interrupts (and thus work) grows with each additional queue.
+
+Per-cpu load can be observed using the mpstat utility, but note that on
+processors with hyperthreading (HT), each hyperthread is represented as
+a separate CPU. For interrupt handling, HT has shown no benefit in
+initial tests, so limit the number of queues to the number of CPU cores
+in the system.
+
+
+RPS: Receive Packet Steering
+============================
+
+Receive Packet Steering (RPS) is logically a software implementation of
+RSS. Being in software, it is necessarily called later in the datapath.
+Whereas RSS selects the queue and hence CPU that will run the hardware
+interrupt handler, RPS selects the CPU to perform protocol processing
+above the interrupt handler. This is accomplished by placing the packet
+on the desired CPU’s backlog queue and waking up the CPU for processing.
+RPS has some advantages over RSS: 1) it can be used with any NIC,
+2) software filters can easily be added to hash over new protocols,
+3) it does not increase hardware device interrupt rate (although it does
+introduce inter-processor interrupts (IPIs)).
+
+RPS is called during bottom half of the receive interrupt handler, when
+a driver sends a packet up the network stack with netif_rx() or
+netif_receive_skb(). These call the get_rps_cpu() function, which
+selects the queue that should process a packet.
+
+The first step in determining the target CPU for RPS is to calculate a
+flow hash over the packet’s addresses or ports (2-tuple or 4-tuple hash
+depending on the protocol). This serves as a consistent hash of the
+associated flow of the packet. The hash is either provided by hardware
+or will be computed in the stack. Capable hardware can pass the hash in
+the receive descriptor for the packet; this would usually be the same
+hash used for RSS (e.g. computed Toeplitz hash). The hash is saved in
+skb->rx_hash and can be used elsewhere in the stack as a hash of the
+packet’s flow.
+
+Each receive hardware queue has an associated list of CPUs to which
+RPS may enqueue packets for processing. For each received packet,
+an index into the list is computed from the flow hash modulo the size
+of the list. The indexed CPU is the target for processing the packet,
+and the packet is queued to the tail of that CPU’s backlog queue. At
+the end of the bottom half routine, IPIs are sent to any CPUs for which
+packets have been queued to their backlog queue. The IPI wakes backlog
+processing on the remote CPU, and any queued packets are then processed
+up the networking stack.
+
+==== RPS Configuration
+
+RPS requires a kernel compiled with the CONFIG_RPS kconfig symbol (on
+by default for SMP). Even when compiled in, RPS remains disabled until
+explicitly configured. The list of CPUs to which RPS may forward traffic
+can be configured for each receive queue using a sysfs file entry:
+
+ /sys/class/net/<dev>/queues/rx-<n>/rps_cpus
+
+This file implements a bitmap of CPUs. RPS is disabled when it is zero
+(the default), in which case packets are processed on the interrupting
+CPU. Documentation/IRQ-affinity.txt explains how CPUs are assigned to
+the bitmap.
+
+== Suggested Configuration
+
+For a single queue device, a typical RPS configuration would be to set
+the rps_cpus to the CPUs in the same memory domain of the interrupting
+CPU. If NUMA locality is not an issue, this could also be all CPUs in
+the system. At high interrupt rate, it might be wise to exclude the
+interrupting CPU from the map since that already performs much work.
+
+For a multi-queue system, if RSS is configured so that a hardware
+receive queue is mapped to each CPU, then RPS is probably redundant
+and unnecessary. If there are fewer hardware queues than CPUs, then
+RPS might be beneficial if the rps_cpus for each queue are the ones that
+share the same memory domain as the interrupting CPU for that queue.
+
+
+RFS: Receive Flow Steering
+==========================
+
+While RPS steers packets solely based on hash, and thus generally
+provides good load distribution, it does not take into account
+application locality. This is accomplished by Receive Flow Steering
+(RFS). The goal of RFS is to increase datacache hitrate by steering
+kernel processing of packets to the CPU where the application thread
+consuming the packet is running. RFS relies on the same RPS mechanisms
+to enqueue packets onto the backlog of another CPU and to wake up that
+CPU.
+
+In RFS, packets are not forwarded directly by the value of their hash,
+but the hash is used as index into a flow lookup table. This table maps
+flows to the CPUs where those flows are being processed. The flow hash
+(see RPS section above) is used to calculate the index into this table.
+The CPU recorded in each entry is the one which last processed the flow.
+If an entry does not hold a valid CPU, then packets mapped to that entry
+are steered using plain RPS. Multiple table entries may point to the
+same CPU. Indeed, with many flows and few CPUs, it is very likely that
+a single application thread handles flows with many different flow hashes.
+
+rps_sock_flow_table is a global flow table that contains the *desired* CPU
+for flows: the CPU that is currently processing the flow in userspace.
+Each table value is a CPU index that is updated during calls to recvmsg
+and sendmsg (specifically, inet_recvmsg(), inet_sendmsg(), inet_sendpage()
+and tcp_splice_read()).
+
+When the scheduler moves a thread to a new CPU while it has outstanding
+receive packets on the old CPU, packets may arrive out of order. To
+avoid this, RFS uses a second flow table to track outstanding packets
+for each flow: rps_dev_flow_table is a table specific to each hardware
+receive queue of each device. Each table value stores a CPU index and a
+counter. The CPU index represents the *current* CPU onto which packets
+for this flow are enqueued for further kernel processing. Ideally, kernel
+and userspace processing occur on the same CPU, and hence the CPU index
+in both tables is identical. This is likely false if the scheduler has
+recently migrated a userspace thread while the kernel still has packets
+enqueued for kernel processing on the old CPU.
+
+The counter in rps_dev_flow_table values records the length of the current
+CPU's backlog when a packet in this flow was last enqueued. Each backlog
+queue has a head counter that is incremented on dequeue. A tail counter
+is computed as head counter + queue length. In other words, the counter
+in rps_dev_flow_table[i] records the last element in flow i that has
+been enqueued onto the currently designated CPU for flow i (of course,
+entry i is actually selected by hash and multiple flows may hash to the
+same entry i).
+
+And now the trick for avoiding out of order packets: when selecting the
+CPU for packet processing (from get_rps_cpu()) the rps_sock_flow table
+and the rps_dev_flow table of the queue that the packet was received on
+are compared. If the desired CPU for the flow (found in the
+rps_sock_flow table) matches the current CPU (found in the rps_dev_flow
+table), the packet is enqueued onto that CPU’s backlog. If they differ,
+the current CPU is updated to match the desired CPU if one of the
+following is true:
+
+- The current CPU's queue head counter >= the recorded tail counter
+  value in rps_dev_flow[i]
+- The current CPU is unset (equal to NR_CPUS)
+- The current CPU is offline
+
+After this check, the packet is sent to the (possibly updated) current
+CPU. These rules aim to ensure that a flow only moves to a new CPU when
+there are no packets outstanding on the old CPU, as the outstanding
+packets could arrive later than those about to be processed on the new
+CPU.
+
+==== RFS Configuration
+
+RFS is only available if the kconfig symbol CONFIG_RFS is enabled (on
+by default for SMP). The functionality remains disabled until explicitly
+configured. The number of entries in the global flow table is set through:
+
+ /proc/sys/net/core/rps_sock_flow_entries
+
+The number of entries in the per-queue flow table are set through:
+
+ /sys/class/net/<dev>/queues/rx-<n>/rps_flow_cnt
+
+== Suggested Configuration
+
+Both of these need to be set before RFS is enabled for a receive queue.
+Values for both are rounded up to the nearest power of two. The
+suggested flow count depends on the expected number of active connections
+at any given time, which may be significantly less than the number of open
+connections. We have found that a value of 32768 for rps_sock_flow_entries
+works fairly well on a moderately loaded server.
+
+For a single queue device, the rps_flow_cnt value for the single queue
+would normally be configured to the same value as rps_sock_flow_entries.
+For a multi-queue device, the rps_flow_cnt for each queue might be
+configured as rps_sock_flow_entries / N, where N is the number of
+queues. So for instance, if rps_flow_entries is set to 32768 and there
+are 16 configured receive queues, rps_flow_cnt for each queue might be
+configured as 2048.
+
+
+Accelerated RFS
+===============
+
+Accelerated RFS is to RFS what RSS is to RPS: a hardware-accelerated load
+balancing mechanism that uses soft state to steer flows based on where
+the application thread consuming the packets of each flow is running.
+Accelerated RFS should perform better than RFS since packets are sent
+directly to a CPU local to the thread consuming the data. The target CPU
+will either be the same CPU where the application runs, or at least a CPU
+which is local to the application thread’s CPU in the cache hierarchy.
+
+To enable accelerated RFS, the networking stack calls the
+ndo_rx_flow_steer driver function to communicate the desired hardware
+queue for packets matching a particular flow. The network stack
+automatically calls this function every time a flow entry in
+rps_dev_flow_table is updated. The driver in turn uses a device specific
+method to program the NIC to steer the packets.
+
+The hardware queue for a flow is derived from the CPU recorded in
+rps_dev_flow_table. The stack consults a CPU to hardware queue map which
+is maintained by the NIC driver. This is an auto-generated reverse map of
+the IRQ affinity table shown by /proc/interrupts. Drivers can use
+functions in the cpu_rmap (“CPU affinity reverse map”) kernel library
+to populate the map. For each CPU, the corresponding queue in the map is
+set to be one whose processing CPU is closest in cache locality.
+
+==== Accelerated RFS Configuration
+
+Accelerated RFS is only available if the kernel is compiled with
+CONFIG_RFS_ACCEL and support is provided by the NIC device and driver.
+It also requires that ntuple filtering is enabled via ethtool. The map
+of CPU to queues is automatically deduced from the IRQ affinities
+configured for each receive queue by the driver, so no additional
+configuration should be necessary.
+
+== Suggested Configuration
+
+This technique should be enabled whenever one wants to use RFS and the
+NIC supports hardware acceleration.
+
+XPS: Transmit Packet Steering
+=============================
+
+Transmit Packet Steering is a mechanism for intelligently selecting
+which transmit queue to use when transmitting a packet on a multi-queue
+device. To accomplish this, a mapping from CPU to hardware queue(s) is
+recorded. The goal of this mapping is usually to assign queues
+exclusively to a subset of CPUs, where the transmit completions for
+these queues are processed on a CPU within this set. This choice
+provides two benefits. First, contention on the device queue lock is
+significantly reduced since fewer CPUs contend for the same queue
+(contention can be eliminated completely if each CPU has its own
+transmit queue). Secondly, cache miss rate on transmit completion is
+reduced, in particular for data cache lines that hold the sk_buff
+structures.
+
+XPS is configured per transmit queue by setting a bitmap of CPUs that
+may use that queue to transmit. The reverse mapping, from CPUs to
+transmit queues, is computed and maintained for each network device.
+When transmitting the first packet in a flow, the function
+get_xps_queue() is called to select a queue. This function uses the ID
+of the running CPU as a key into the CPU-to-queue lookup table. If the
+ID matches a single queue, that is used for transmission. If multiple
+queues match, one is selected by using the flow hash to compute an index
+into the set.
+
+The queue chosen for transmitting a particular flow is saved in the
+corresponding socket structure for the flow (e.g. a TCP connection).
+This transmit queue is used for subsequent packets sent on the flow to
+prevent out of order (ooo) packets. The choice also amortizes the cost
+of calling get_xps_queues() over all packets in the flow. To avoid
+ooo packets, the queue for a flow can subsequently only be changed if
+skb->ooo_okay is set for a packet in the flow. This flag indicates that
+there are no outstanding packets in the flow, so the transmit queue can
+change without the risk of generating out of order packets. The
+transport layer is responsible for setting ooo_okay appropriately. TCP,
+for instance, sets the flag when all data for a connection has been
+acknowledged.
+
+==== XPS Configuration
+
+XPS is only available if the kconfig symbol CONFIG_XPS is enabled (on by
+default for SMP). The functionality remains disabled until explicitly
+configured. To enable XPS, the bitmap of CPUs that may use a transmit
+queue is configured using the sysfs file entry:
+
+/sys/class/net/<dev>/queues/tx-<n>/xps_cpus
+
+== Suggested Configuration
+
+For a network device with a single transmission queue, XPS configuration
+has no effect, since there is no choice in this case. In a multi-queue
+system, XPS is preferably configured so that each CPU maps onto one queue.
+If there are as many queues as there are CPUs in the system, then each
+queue can also map onto one CPU, resulting in exclusive pairings that
+experience no contention. If there are fewer queues than CPUs, then the
+best CPUs to share a given queue are probably those that share the cache
+with the CPU that processes transmit completions for that queue
+(transmit interrupts).
+
+
+Further Information
+===================
+RPS and RFS were introduced in kernel 2.6.35. XPS was incorporated into
+2.6.38. Original patches were submitted by Tom Herbert
+(therbert@google.com)
+
+Accelerated RFS was introduced in 2.6.35. Original patches were
+submitted by Ben Hutchings (bhutchings@solarflare.com)
+
+Authors:
+Tom Herbert (therbert@google.com)
+Willem de Bruijn (willemb@google.com)
diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt
index 57a2410..8d67980 100644
--- a/Documentation/networking/stmmac.txt
+++ b/Documentation/networking/stmmac.txt
@@ -76,7 +76,16 @@
 
 4.5) DMA descriptors
 Driver handles both normal and enhanced descriptors. The latter has been only
-tested on DWC Ether MAC 10/100/1000 Universal version 3.41a.
+tested on DWC Ether MAC 10/100/1000 Universal version 3.41a and later.
+
+STMMAC supports DMA descriptor to operate both in dual buffer (RING)
+and linked-list(CHAINED) mode. In RING each descriptor points to two
+data buffer pointers whereas in CHAINED mode they point to only one data
+buffer pointer. RING mode is the default.
+
+In CHAINED mode each descriptor will have pointer to next descriptor in
+the list, hence creating the explicit chaining in the descriptor itself,
+whereas such explicit chaining is not possible in RING mode.
 
 4.6) Ethtool support
 Ethtool is supported. Driver statistics and internal errors can be taken using:
@@ -235,7 +244,38 @@
  o enh_desc.c: functions for handling enhanced descriptors
  o norm_desc.c: functions for handling normal descriptors
 
-5) TODO:
+5) Debug Information
+
+The driver exports many information i.e. internal statistics,
+debug information, MAC and DMA registers etc.
+
+These can be read in several ways depending on the
+type of the information actually needed.
+
+For example a user can be use the ethtool support
+to get statistics: e.g. using: ethtool -S ethX
+(that shows the Management counters (MMC) if supported)
+or sees the MAC/DMA registers: e.g. using: ethtool -d ethX
+
+Compiling the Kernel with CONFIG_DEBUG_FS and enabling the
+STMMAC_DEBUG_FS option the driver will export the following
+debugfs entries:
+
+/sys/kernel/debug/stmmaceth/descriptors_status
+  To show the DMA TX/RX descriptor rings
+
+Developer can also use the "debug" module parameter to get
+further debug information.
+
+In the end, there are other macros (that cannot be enabled
+via menuconfig) to turn-on the RX/TX DMA debugging,
+specific MAC core debug printk etc. Others to enable the
+debug in the TX and RX processes.
+All these are only useful during the developing stage
+and should never enabled inside the code for general usage.
+In fact, these can generate an huge amount of debug messages.
+
+6) TODO:
  o XGMAC is not supported.
  o Review the timer optimisation code to use an embedded device that will be
   available in new chip generations.
diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt
new file mode 100644
index 0000000..b04cb7d
--- /dev/null
+++ b/Documentation/pinctrl.txt
@@ -0,0 +1,950 @@
+PINCTRL (PIN CONTROL) subsystem
+This document outlines the pin control subsystem in Linux
+
+This subsystem deals with:
+
+- Enumerating and naming controllable pins
+
+- Multiplexing of pins, pads, fingers (etc) see below for details
+
+The intention is to also deal with:
+
+- Software-controlled biasing and driving mode specific pins, such as
+  pull-up/down, open drain etc, load capacitance configuration when controlled
+  by software, etc.
+
+
+Top-level interface
+===================
+
+Definition of PIN CONTROLLER:
+
+- A pin controller is a piece of hardware, usually a set of registers, that
+  can control PINs. It may be able to multiplex, bias, set load capacitance,
+  set drive strength etc for individual pins or groups of pins.
+
+Definition of PIN:
+
+- PINS are equal to pads, fingers, balls or whatever packaging input or
+  output line you want to control and these are denoted by unsigned integers
+  in the range 0..maxpin. This numberspace is local to each PIN CONTROLLER, so
+  there may be several such number spaces in a system. This pin space may
+  be sparse - i.e. there may be gaps in the space with numbers where no
+  pin exists.
+
+When a PIN CONTROLLER is instatiated, it will register a descriptor to the
+pin control framework, and this descriptor contains an array of pin descriptors
+describing the pins handled by this specific pin controller.
+
+Here is an example of a PGA (Pin Grid Array) chip seen from underneath:
+
+        A   B   C   D   E   F   G   H
+
+   8    o   o   o   o   o   o   o   o
+
+   7    o   o   o   o   o   o   o   o
+
+   6    o   o   o   o   o   o   o   o
+
+   5    o   o   o   o   o   o   o   o
+
+   4    o   o   o   o   o   o   o   o
+
+   3    o   o   o   o   o   o   o   o
+
+   2    o   o   o   o   o   o   o   o
+
+   1    o   o   o   o   o   o   o   o
+
+To register a pin controller and name all the pins on this package we can do
+this in our driver:
+
+#include <linux/pinctrl/pinctrl.h>
+
+const struct pinctrl_pin_desc __refdata foo_pins[] = {
+      PINCTRL_PIN(0, "A1"),
+      PINCTRL_PIN(1, "A2"),
+      PINCTRL_PIN(2, "A3"),
+      ...
+      PINCTRL_PIN(61, "H6"),
+      PINCTRL_PIN(62, "H7"),
+      PINCTRL_PIN(63, "H8"),
+};
+
+static struct pinctrl_desc foo_desc = {
+	.name = "foo",
+	.pins = foo_pins,
+	.npins = ARRAY_SIZE(foo_pins),
+	.maxpin = 63,
+	.owner = THIS_MODULE,
+};
+
+int __init foo_probe(void)
+{
+	struct pinctrl_dev *pctl;
+
+	pctl = pinctrl_register(&foo_desc, <PARENT>, NULL);
+	if (IS_ERR(pctl))
+		pr_err("could not register foo pin driver\n");
+}
+
+Pins usually have fancier names than this. You can find these in the dataheet
+for your chip. Notice that the core pinctrl.h file provides a fancy macro
+called PINCTRL_PIN() to create the struct entries. As you can see I enumerated
+the pins from 0 in the upper left corner to 63 in the lower right corner,
+this enumeration was arbitrarily chosen, in practice you need to think
+through your numbering system so that it matches the layout of registers
+and such things in your driver, or the code may become complicated. You must
+also consider matching of offsets to the GPIO ranges that may be handled by
+the pin controller.
+
+For a padring with 467 pads, as opposed to actual pins, I used an enumeration
+like this, walking around the edge of the chip, which seems to be industry
+standard too (all these pads had names, too):
+
+
+     0 ..... 104
+   466        105
+     .        .
+     .        .
+   358        224
+    357 .... 225
+
+
+Pin groups
+==========
+
+Many controllers need to deal with groups of pins, so the pin controller
+subsystem has a mechanism for enumerating groups of pins and retrieving the
+actual enumerated pins that are part of a certain group.
+
+For example, say that we have a group of pins dealing with an SPI interface
+on { 0, 8, 16, 24 }, and a group of pins dealing with an I2C interface on pins
+on { 24, 25 }.
+
+These two groups are presented to the pin control subsystem by implementing
+some generic pinctrl_ops like this:
+
+#include <linux/pinctrl/pinctrl.h>
+
+struct foo_group {
+	const char *name;
+	const unsigned int *pins;
+	const unsigned num_pins;
+};
+
+static unsigned int spi0_pins[] = { 0, 8, 16, 24 };
+static unsigned int i2c0_pins[] = { 24, 25 };
+
+static const struct foo_group foo_groups[] = {
+	{
+		.name = "spi0_grp",
+		.pins = spi0_pins,
+		.num_pins = ARRAY_SIZE(spi0_pins),
+	},
+	{
+		.name = "i2c0_grp",
+		.pins = i2c0_pins,
+		.num_pins = ARRAY_SIZE(i2c0_pins),
+	},
+};
+
+
+static int foo_list_groups(struct pinctrl_dev *pctldev, unsigned selector)
+{
+	if (selector >= ARRAY_SIZE(foo_groups))
+		return -EINVAL;
+	return 0;
+}
+
+static const char *foo_get_group_name(struct pinctrl_dev *pctldev,
+				       unsigned selector)
+{
+	return foo_groups[selector].name;
+}
+
+static int foo_get_group_pins(struct pinctrl_dev *pctldev, unsigned selector,
+			       unsigned ** const pins,
+			       unsigned * const num_pins)
+{
+	*pins = (unsigned *) foo_groups[selector].pins;
+	*num_pins = foo_groups[selector].num_pins;
+	return 0;
+}
+
+static struct pinctrl_ops foo_pctrl_ops = {
+	.list_groups = foo_list_groups,
+	.get_group_name = foo_get_group_name,
+	.get_group_pins = foo_get_group_pins,
+};
+
+
+static struct pinctrl_desc foo_desc = {
+       ...
+       .pctlops = &foo_pctrl_ops,
+};
+
+The pin control subsystem will call the .list_groups() function repeatedly
+beginning on 0 until it returns non-zero to determine legal selectors, then
+it will call the other functions to retrieve the name and pins of the group.
+Maintaining the data structure of the groups is up to the driver, this is
+just a simple example - in practice you may need more entries in your group
+structure, for example specific register ranges associated with each group
+and so on.
+
+
+Interaction with the GPIO subsystem
+===================================
+
+The GPIO drivers may want to perform operations of various types on the same
+physical pins that are also registered as pin controller pins.
+
+Since the pin controller subsystem have its pinspace local to the pin
+controller we need a mapping so that the pin control subsystem can figure out
+which pin controller handles control of a certain GPIO pin. Since a single
+pin controller may be muxing several GPIO ranges (typically SoCs that have
+one set of pins but internally several GPIO silicon blocks, each modeled as
+a struct gpio_chip) any number of GPIO ranges can be added to a pin controller
+instance like this:
+
+struct gpio_chip chip_a;
+struct gpio_chip chip_b;
+
+static struct pinctrl_gpio_range gpio_range_a = {
+	.name = "chip a",
+	.id = 0,
+	.base = 32,
+	.npins = 16,
+	.gc = &chip_a;
+};
+
+static struct pinctrl_gpio_range gpio_range_a = {
+	.name = "chip b",
+	.id = 0,
+	.base = 48,
+	.npins = 8,
+	.gc = &chip_b;
+};
+
+
+{
+	struct pinctrl_dev *pctl;
+	...
+	pinctrl_add_gpio_range(pctl, &gpio_range_a);
+	pinctrl_add_gpio_range(pctl, &gpio_range_b);
+}
+
+So this complex system has one pin controller handling two different
+GPIO chips. Chip a has 16 pins and chip b has 8 pins. They are mapped in
+the global GPIO pin space at:
+
+chip a: [32 .. 47]
+chip b: [48 .. 55]
+
+When GPIO-specific functions in the pin control subsystem are called, these
+ranges will be used to look up the apropriate pin controller by inspecting
+and matching the pin to the pin ranges across all controllers. When a
+pin controller handling the matching range is found, GPIO-specific functions
+will be called on that specific pin controller.
+
+For all functionalities dealing with pin biasing, pin muxing etc, the pin
+controller subsystem will subtract the range's .base offset from the passed
+in gpio pin number, and pass that on to the pin control driver, so the driver
+will get an offset into its handled number range. Further it is also passed
+the range ID value, so that the pin controller knows which range it should
+deal with.
+
+For example: if a user issues pinctrl_gpio_set_foo(50), the pin control
+subsystem will find that the second range on this pin controller matches,
+subtract the base 48 and call the
+pinctrl_driver_gpio_set_foo(pinctrl, range, 2) where the latter function has
+this signature:
+
+int pinctrl_driver_gpio_set_foo(struct pinctrl_dev *pctldev,
+    struct pinctrl_gpio_range *rangeid,
+    unsigned offset);
+
+Now the driver knows that we want to do some GPIO-specific operation on the
+second GPIO range handled by "chip b", at offset 2 in that specific range.
+
+(If the GPIO subsystem is ever refactored to use a local per-GPIO controller
+pin space, this mapping will need to be augmented accordingly.)
+
+
+PINMUX interfaces
+=================
+
+These calls use the pinmux_* naming prefix.  No other calls should use that
+prefix.
+
+
+What is pinmuxing?
+==================
+
+PINMUX, also known as padmux, ballmux, alternate functions or mission modes
+is a way for chip vendors producing some kind of electrical packages to use
+a certain physical pin (ball, pad, finger, etc) for multiple mutually exclusive
+functions, depending on the application. By "application" in this context
+we usually mean a way of soldering or wiring the package into an electronic
+system, even though the framework makes it possible to also change the function
+at runtime.
+
+Here is an example of a PGA (Pin Grid Array) chip seen from underneath:
+
+        A   B   C   D   E   F   G   H
+      +---+
+   8  | o | o   o   o   o   o   o   o
+      |   |
+   7  | o | o   o   o   o   o   o   o
+      |   |
+   6  | o | o   o   o   o   o   o   o
+      +---+---+
+   5  | o | o | o   o   o   o   o   o
+      +---+---+               +---+
+   4    o   o   o   o   o   o | o | o
+                              |   |
+   3    o   o   o   o   o   o | o | o
+                              |   |
+   2    o   o   o   o   o   o | o | o
+      +-------+-------+-------+---+---+
+   1  | o   o | o   o | o   o | o | o |
+      +-------+-------+-------+---+---+
+
+This is not tetris. The game to think of is chess. Not all PGA/BGA packages
+are chessboard-like, big ones have "holes" in some arrangement according to
+different design patterns, but we're using this as a simple example. Of the
+pins you see some will be taken by things like a few VCC and GND to feed power
+to the chip, and quite a few will be taken by large ports like an external
+memory interface. The remaining pins will often be subject to pin multiplexing.
+
+The example 8x8 PGA package above will have pin numbers 0 thru 63 assigned to
+its physical pins. It will name the pins { A1, A2, A3 ... H6, H7, H8 } using
+pinctrl_register_pins() and a suitable data set as shown earlier.
+
+In this 8x8 BGA package the pins { A8, A7, A6, A5 } can be used as an SPI port
+(these are four pins: CLK, RXD, TXD, FRM). In that case, pin B5 can be used as
+some general-purpose GPIO pin. However, in another setting, pins { A5, B5 } can
+be used as an I2C port (these are just two pins: SCL, SDA). Needless to say,
+we cannot use the SPI port and I2C port at the same time. However in the inside
+of the package the silicon performing the SPI logic can alternatively be routed
+out on pins { G4, G3, G2, G1 }.
+
+On the botton row at { A1, B1, C1, D1, E1, F1, G1, H1 } we have something
+special - it's an external MMC bus that can be 2, 4 or 8 bits wide, and it will
+consume 2, 4 or 8 pins respectively, so either { A1, B1 } are taken or
+{ A1, B1, C1, D1 } or all of them. If we use all 8 bits, we cannot use the SPI
+port on pins { G4, G3, G2, G1 } of course.
+
+This way the silicon blocks present inside the chip can be multiplexed "muxed"
+out on different pin ranges. Often contemporary SoC (systems on chip) will
+contain several I2C, SPI, SDIO/MMC, etc silicon blocks that can be routed to
+different pins by pinmux settings.
+
+Since general-purpose I/O pins (GPIO) are typically always in shortage, it is
+common to be able to use almost any pin as a GPIO pin if it is not currently
+in use by some other I/O port.
+
+
+Pinmux conventions
+==================
+
+The purpose of the pinmux functionality in the pin controller subsystem is to
+abstract and provide pinmux settings to the devices you choose to instantiate
+in your machine configuration. It is inspired by the clk, GPIO and regulator
+subsystems, so devices will request their mux setting, but it's also possible
+to request a single pin for e.g. GPIO.
+
+Definitions:
+
+- FUNCTIONS can be switched in and out by a driver residing with the pin
+  control subsystem in the drivers/pinctrl/* directory of the kernel. The
+  pin control driver knows the possible functions. In the example above you can
+  identify three pinmux functions, one for spi, one for i2c and one for mmc.
+
+- FUNCTIONS are assumed to be enumerable from zero in a one-dimensional array.
+  In this case the array could be something like: { spi0, i2c0, mmc0 }
+  for the three available functions.
+
+- FUNCTIONS have PIN GROUPS as defined on the generic level - so a certain
+  function is *always* associated with a certain set of pin groups, could
+  be just a single one, but could also be many. In the example above the
+  function i2c is associated with the pins { A5, B5 }, enumerated as
+  { 24, 25 } in the controller pin space.
+
+  The Function spi is associated with pin groups { A8, A7, A6, A5 }
+  and { G4, G3, G2, G1 }, which are enumerated as { 0, 8, 16, 24 } and
+  { 38, 46, 54, 62 } respectively.
+
+  Group names must be unique per pin controller, no two groups on the same
+  controller may have the same name.
+
+- The combination of a FUNCTION and a PIN GROUP determine a certain function
+  for a certain set of pins. The knowledge of the functions and pin groups
+  and their machine-specific particulars are kept inside the pinmux driver,
+  from the outside only the enumerators are known, and the driver core can:
+
+  - Request the name of a function with a certain selector (>= 0)
+  - A list of groups associated with a certain function
+  - Request that a certain group in that list to be activated for a certain
+    function
+
+  As already described above, pin groups are in turn self-descriptive, so
+  the core will retrieve the actual pin range in a certain group from the
+  driver.
+
+- FUNCTIONS and GROUPS on a certain PIN CONTROLLER are MAPPED to a certain
+  device by the board file, device tree or similar machine setup configuration
+  mechanism, similar to how regulators are connected to devices, usually by
+  name. Defining a pin controller, function and group thus uniquely identify
+  the set of pins to be used by a certain device. (If only one possible group
+  of pins is available for the function, no group name need to be supplied -
+  the core will simply select the first and only group available.)
+
+  In the example case we can define that this particular machine shall
+  use device spi0 with pinmux function fspi0 group gspi0 and i2c0 on function
+  fi2c0 group gi2c0, on the primary pin controller, we get mappings
+  like these:
+
+  {
+    {"map-spi0", spi0, pinctrl0, fspi0, gspi0},
+    {"map-i2c0", i2c0, pinctrl0, fi2c0, gi2c0}
+  }
+
+  Every map must be assigned a symbolic name, pin controller and function.
+  The group is not compulsory - if it is omitted the first group presented by
+  the driver as applicable for the function will be selected, which is
+  useful for simple cases.
+
+  The device name is present in map entries tied to specific devices. Maps
+  without device names are referred to as SYSTEM pinmuxes, such as can be taken
+  by the machine implementation on boot and not tied to any specific device.
+
+  It is possible to map several groups to the same combination of device,
+  pin controller and function. This is for cases where a certain function on
+  a certain pin controller may use different sets of pins in different
+  configurations.
+
+- PINS for a certain FUNCTION using a certain PIN GROUP on a certain
+  PIN CONTROLLER are provided on a first-come first-serve basis, so if some
+  other device mux setting or GPIO pin request has already taken your physical
+  pin, you will be denied the use of it. To get (activate) a new setting, the
+  old one has to be put (deactivated) first.
+
+Sometimes the documentation and hardware registers will be oriented around
+pads (or "fingers") rather than pins - these are the soldering surfaces on the
+silicon inside the package, and may or may not match the actual number of
+pins/balls underneath the capsule. Pick some enumeration that makes sense to
+you. Define enumerators only for the pins you can control if that makes sense.
+
+Assumptions:
+
+We assume that the number possible function maps to pin groups is limited by
+the hardware. I.e. we assume that there is no system where any function can be
+mapped to any pin, like in a phone exchange. So the available pins groups for
+a certain function will be limited to a few choices (say up to eight or so),
+not hundreds or any amount of choices. This is the characteristic we have found
+by inspecting available pinmux hardware, and a necessary assumption since we
+expect pinmux drivers to present *all* possible function vs pin group mappings
+to the subsystem.
+
+
+Pinmux drivers
+==============
+
+The pinmux core takes care of preventing conflicts on pins and calling
+the pin controller driver to execute different settings.
+
+It is the responsibility of the pinmux driver to impose further restrictions
+(say for example infer electronic limitations due to load etc) to determine
+whether or not the requested function can actually be allowed, and in case it
+is possible to perform the requested mux setting, poke the hardware so that
+this happens.
+
+Pinmux drivers are required to supply a few callback functions, some are
+optional. Usually the enable() and disable() functions are implemented,
+writing values into some certain registers to activate a certain mux setting
+for a certain pin.
+
+A simple driver for the above example will work by setting bits 0, 1, 2, 3 or 4
+into some register named MUX to select a certain function with a certain
+group of pins would work something like this:
+
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
+
+struct foo_group {
+	const char *name;
+	const unsigned int *pins;
+	const unsigned num_pins;
+};
+
+static const unsigned spi0_0_pins[] = { 0, 8, 16, 24 };
+static const unsigned spi0_1_pins[] = { 38, 46, 54, 62 };
+static const unsigned i2c0_pins[] = { 24, 25 };
+static const unsigned mmc0_1_pins[] = { 56, 57 };
+static const unsigned mmc0_2_pins[] = { 58, 59 };
+static const unsigned mmc0_3_pins[] = { 60, 61, 62, 63 };
+
+static const struct foo_group foo_groups[] = {
+	{
+		.name = "spi0_0_grp",
+		.pins = spi0_0_pins,
+		.num_pins = ARRAY_SIZE(spi0_0_pins),
+	},
+	{
+		.name = "spi0_1_grp",
+		.pins = spi0_1_pins,
+		.num_pins = ARRAY_SIZE(spi0_1_pins),
+	},
+	{
+		.name = "i2c0_grp",
+		.pins = i2c0_pins,
+		.num_pins = ARRAY_SIZE(i2c0_pins),
+	},
+	{
+		.name = "mmc0_1_grp",
+		.pins = mmc0_1_pins,
+		.num_pins = ARRAY_SIZE(mmc0_1_pins),
+	},
+	{
+		.name = "mmc0_2_grp",
+		.pins = mmc0_2_pins,
+		.num_pins = ARRAY_SIZE(mmc0_2_pins),
+	},
+	{
+		.name = "mmc0_3_grp",
+		.pins = mmc0_3_pins,
+		.num_pins = ARRAY_SIZE(mmc0_3_pins),
+	},
+};
+
+
+static int foo_list_groups(struct pinctrl_dev *pctldev, unsigned selector)
+{
+	if (selector >= ARRAY_SIZE(foo_groups))
+		return -EINVAL;
+	return 0;
+}
+
+static const char *foo_get_group_name(struct pinctrl_dev *pctldev,
+				       unsigned selector)
+{
+	return foo_groups[selector].name;
+}
+
+static int foo_get_group_pins(struct pinctrl_dev *pctldev, unsigned selector,
+			       unsigned ** const pins,
+			       unsigned * const num_pins)
+{
+	*pins = (unsigned *) foo_groups[selector].pins;
+	*num_pins = foo_groups[selector].num_pins;
+	return 0;
+}
+
+static struct pinctrl_ops foo_pctrl_ops = {
+	.list_groups = foo_list_groups,
+	.get_group_name = foo_get_group_name,
+	.get_group_pins = foo_get_group_pins,
+};
+
+struct foo_pmx_func {
+	const char *name;
+	const char * const *groups;
+	const unsigned num_groups;
+};
+
+static const char * const spi0_groups[] = { "spi0_1_grp" };
+static const char * const i2c0_groups[] = { "i2c0_grp" };
+static const char * const mmc0_groups[] = { "mmc0_1_grp", "mmc0_2_grp",
+					"mmc0_3_grp" };
+
+static const struct foo_pmx_func foo_functions[] = {
+	{
+		.name = "spi0",
+		.groups = spi0_groups,
+		.num_groups = ARRAY_SIZE(spi0_groups),
+	},
+	{
+		.name = "i2c0",
+		.groups = i2c0_groups,
+		.num_groups = ARRAY_SIZE(i2c0_groups),
+	},
+	{
+		.name = "mmc0",
+		.groups = mmc0_groups,
+		.num_groups = ARRAY_SIZE(mmc0_groups),
+	},
+};
+
+int foo_list_funcs(struct pinctrl_dev *pctldev, unsigned selector)
+{
+	if (selector >= ARRAY_SIZE(foo_functions))
+		return -EINVAL;
+	return 0;
+}
+
+const char *foo_get_fname(struct pinctrl_dev *pctldev, unsigned selector)
+{
+	return myfuncs[selector].name;
+}
+
+static int foo_get_groups(struct pinctrl_dev *pctldev, unsigned selector,
+			  const char * const **groups,
+			  unsigned * const num_groups)
+{
+	*groups = foo_functions[selector].groups;
+	*num_groups = foo_functions[selector].num_groups;
+	return 0;
+}
+
+int foo_enable(struct pinctrl_dev *pctldev, unsigned selector,
+		unsigned group)
+{
+	u8 regbit = (1 << group);
+
+	writeb((readb(MUX)|regbit), MUX)
+	return 0;
+}
+
+int foo_disable(struct pinctrl_dev *pctldev, unsigned selector,
+		unsigned group)
+{
+	u8 regbit = (1 << group);
+
+	writeb((readb(MUX) & ~(regbit)), MUX)
+	return 0;
+}
+
+struct pinmux_ops foo_pmxops = {
+	.list_functions = foo_list_funcs,
+	.get_function_name = foo_get_fname,
+	.get_function_groups = foo_get_groups,
+	.enable = foo_enable,
+	.disable = foo_disable,
+};
+
+/* Pinmux operations are handled by some pin controller */
+static struct pinctrl_desc foo_desc = {
+	...
+	.pctlops = &foo_pctrl_ops,
+	.pmxops = &foo_pmxops,
+};
+
+In the example activating muxing 0 and 1 at the same time setting bits
+0 and 1, uses one pin in common so they would collide.
+
+The beauty of the pinmux subsystem is that since it keeps track of all
+pins and who is using them, it will already have denied an impossible
+request like that, so the driver does not need to worry about such
+things - when it gets a selector passed in, the pinmux subsystem makes
+sure no other device or GPIO assignment is already using the selected
+pins. Thus bits 0 and 1 in the control register will never be set at the
+same time.
+
+All the above functions are mandatory to implement for a pinmux driver.
+
+
+Pinmux interaction with the GPIO subsystem
+==========================================
+
+The function list could become long, especially if you can convert every
+individual pin into a GPIO pin independent of any other pins, and then try
+the approach to define every pin as a function.
+
+In this case, the function array would become 64 entries for each GPIO
+setting and then the device functions.
+
+For this reason there is an additional function a pinmux driver can implement
+to enable only GPIO on an individual pin: .gpio_request_enable(). The same
+.free() function as for other functions is assumed to be usable also for
+GPIO pins.
+
+This function will pass in the affected GPIO range identified by the pin
+controller core, so you know which GPIO pins are being affected by the request
+operation.
+
+Alternatively it is fully allowed to use named functions for each GPIO
+pin, the pinmux_request_gpio() will attempt to obtain the function "gpioN"
+where "N" is the global GPIO pin number if no special GPIO-handler is
+registered.
+
+
+Pinmux board/machine configuration
+==================================
+
+Boards and machines define how a certain complete running system is put
+together, including how GPIOs and devices are muxed, how regulators are
+constrained and how the clock tree looks. Of course pinmux settings are also
+part of this.
+
+A pinmux config for a machine looks pretty much like a simple regulator
+configuration, so for the example array above we want to enable i2c and
+spi on the second function mapping:
+
+#include <linux/pinctrl/machine.h>
+
+static struct pinmux_map pmx_mapping[] = {
+	{
+		.ctrl_dev_name = "pinctrl.0",
+		.function = "spi0",
+		.dev_name = "foo-spi.0",
+	},
+	{
+		.ctrl_dev_name = "pinctrl.0",
+		.function = "i2c0",
+		.dev_name = "foo-i2c.0",
+	},
+	{
+		.ctrl_dev_name = "pinctrl.0",
+		.function = "mmc0",
+		.dev_name = "foo-mmc.0",
+	},
+};
+
+The dev_name here matches to the unique device name that can be used to look
+up the device struct (just like with clockdev or regulators). The function name
+must match a function provided by the pinmux driver handling this pin range.
+
+As you can see we may have several pin controllers on the system and thus
+we need to specify which one of them that contain the functions we wish
+to map. The map can also use struct device * directly, so there is no
+inherent need to use strings to specify .dev_name or .ctrl_dev_name, these
+are for the situation where you do not have a handle to the struct device *,
+for example if they are not yet instantiated or cumbersome to obtain.
+
+You register this pinmux mapping to the pinmux subsystem by simply:
+
+       ret = pinmux_register_mappings(&pmx_mapping, ARRAY_SIZE(pmx_mapping));
+
+Since the above construct is pretty common there is a helper macro to make
+it even more compact which assumes you want to use pinctrl.0 and position
+0 for mapping, for example:
+
+static struct pinmux_map pmx_mapping[] = {
+       PINMUX_MAP_PRIMARY("I2CMAP", "i2c0", "foo-i2c.0"),
+};
+
+
+Complex mappings
+================
+
+As it is possible to map a function to different groups of pins an optional
+.group can be specified like this:
+
+...
+{
+	.name = "spi0-pos-A",
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "spi0",
+	.group = "spi0_0_grp",
+	.dev_name = "foo-spi.0",
+},
+{
+	.name = "spi0-pos-B",
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "spi0",
+	.group = "spi0_1_grp",
+	.dev_name = "foo-spi.0",
+},
+...
+
+This example mapping is used to switch between two positions for spi0 at
+runtime, as described further below under the heading "Runtime pinmuxing".
+
+Further it is possible to match several groups of pins to the same function
+for a single device, say for example in the mmc0 example above, where you can
+additively expand the mmc0 bus from 2 to 4 to 8 pins. If we want to use all
+three groups for a total of 2+2+4 = 8 pins (for an 8-bit MMC bus as is the
+case), we define a mapping like this:
+
+...
+{
+	.name "2bit"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "mmc0",
+	.group = "mmc0_0_grp",
+	.dev_name = "foo-mmc.0",
+},
+{
+	.name "4bit"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "mmc0",
+	.group = "mmc0_0_grp",
+	.dev_name = "foo-mmc.0",
+},
+{
+	.name "4bit"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "mmc0",
+	.group = "mmc0_1_grp",
+	.dev_name = "foo-mmc.0",
+},
+{
+	.name "8bit"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "mmc0",
+	.group = "mmc0_0_grp",
+	.dev_name = "foo-mmc.0",
+},
+{
+	.name "8bit"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "mmc0",
+	.group = "mmc0_1_grp",
+	.dev_name = "foo-mmc.0",
+},
+{
+	.name "8bit"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "mmc0",
+	.group = "mmc0_2_grp",
+	.dev_name = "foo-mmc.0",
+},
+...
+
+The result of grabbing this mapping from the device with something like
+this (see next paragraph):
+
+	pmx = pinmux_get(&device, "8bit");
+
+Will be that you activate all the three bottom records in the mapping at
+once. Since they share the same name, pin controller device, funcion and
+device, and since we allow multiple groups to match to a single device, they
+all get selected, and they all get enabled and disable simultaneously by the
+pinmux core.
+
+
+Pinmux requests from drivers
+============================
+
+Generally it is discouraged to let individual drivers get and enable pinmuxes.
+So if possible, handle the pinmuxes in platform code or some other place where
+you have access to all the affected struct device * pointers. In some cases
+where a driver needs to switch between different mux mappings at runtime
+this is not possible.
+
+A driver may request a certain mux to be activated, usually just the default
+mux like this:
+
+#include <linux/pinctrl/pinmux.h>
+
+struct foo_state {
+       struct pinmux *pmx;
+       ...
+};
+
+foo_probe()
+{
+	/* Allocate a state holder named "state" etc */
+	struct pinmux pmx;
+
+	pmx = pinmux_get(&device, NULL);
+	if IS_ERR(pmx)
+		return PTR_ERR(pmx);
+	pinmux_enable(pmx);
+
+	state->pmx = pmx;
+}
+
+foo_remove()
+{
+	pinmux_disable(state->pmx);
+	pinmux_put(state->pmx);
+}
+
+If you want to grab a specific mux mapping and not just the first one found for
+this device you can specify a specific mapping name, for example in the above
+example the second i2c0 setting: pinmux_get(&device, "spi0-pos-B");
+
+This get/enable/disable/put sequence can just as well be handled by bus drivers
+if you don't want each and every driver to handle it and you know the
+arrangement on your bus.
+
+The semantics of the get/enable respective disable/put is as follows:
+
+- pinmux_get() is called in process context to reserve the pins affected with
+  a certain mapping and set up the pinmux core and the driver. It will allocate
+  a struct from the kernel memory to hold the pinmux state.
+
+- pinmux_enable()/pinmux_disable() is quick and can be called from fastpath
+  (irq context) when you quickly want to set up/tear down the hardware muxing
+  when running a device driver. Usually it will just poke some values into a
+  register.
+
+- pinmux_disable() is called in process context to tear down the pin requests
+  and release the state holder struct for the mux setting.
+
+Usually the pinmux core handled the get/put pair and call out to the device
+drivers bookkeeping operations, like checking available functions and the
+associated pins, whereas the enable/disable pass on to the pin controller
+driver which takes care of activating and/or deactivating the mux setting by
+quickly poking some registers.
+
+The pins are allocated for your device when you issue the pinmux_get() call,
+after this you should be able to see this in the debugfs listing of all pins.
+
+
+System pinmux hogging
+=====================
+
+A system pinmux map entry, i.e. a pinmux setting that does not have a device
+associated with it, can be hogged by the core when the pin controller is
+registered. This means that the core will attempt to call pinmux_get() and
+pinmux_enable() on it immediately after the pin control device has been
+registered.
+
+This is enabled by simply setting the .hog_on_boot field in the map to true,
+like this:
+
+{
+	.name "POWERMAP"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "power_func",
+	.hog_on_boot = true,
+},
+
+Since it may be common to request the core to hog a few always-applicable
+mux settings on the primary pin controller, there is a convenience macro for
+this:
+
+PINMUX_MAP_PRIMARY_SYS_HOG("POWERMAP", "power_func")
+
+This gives the exact same result as the above construction.
+
+
+Runtime pinmuxing
+=================
+
+It is possible to mux a certain function in and out at runtime, say to move
+an SPI port from one set of pins to another set of pins. Say for example for
+spi0 in the example above, we expose two different groups of pins for the same
+function, but with different named in the mapping as described under
+"Advanced mapping" above. So we have two mappings named "spi0-pos-A" and
+"spi0-pos-B".
+
+This snippet first muxes the function in the pins defined by group A, enables
+it, disables and releases it, and muxes it in on the pins defined by group B:
+
+foo_switch()
+{
+	struct pinmux pmx;
+
+	/* Enable on position A */
+	pmx = pinmux_get(&device, "spi0-pos-A");
+	if IS_ERR(pmx)
+		return PTR_ERR(pmx);
+	pinmux_enable(pmx);
+
+	/* This releases the pins again */
+	pinmux_disable(pmx);
+	pinmux_put(pmx);
+
+	/* Enable on position B */
+	pmx = pinmux_get(&device, "spi0-pos-B");
+	if IS_ERR(pmx)
+		return PTR_ERR(pmx);
+	pinmux_enable(pmx);
+	...
+}
+
+The above has to be done from process context.
diff --git a/Documentation/power/00-INDEX b/Documentation/power/00-INDEX
index 45e9d4a..a4d682f 100644
--- a/Documentation/power/00-INDEX
+++ b/Documentation/power/00-INDEX
@@ -26,6 +26,8 @@
 	- How to get suspend to ram working (and debug it when it isn't)
 states.txt
 	- System power management states
+suspend-and-cpuhotplug.txt
+	- Explains the interaction between Suspend-to-RAM (S3) and CPU hotplug
 swsusp-and-swap-files.txt
 	- Using swap files with software suspend (to disk)
 swsusp-dmcrypt.txt
diff --git a/Documentation/power/basic-pm-debugging.txt b/Documentation/power/basic-pm-debugging.txt
index ddd78172..40a4c65 100644
--- a/Documentation/power/basic-pm-debugging.txt
+++ b/Documentation/power/basic-pm-debugging.txt
@@ -173,7 +173,7 @@
 information about the reasons of the suspend (resume) failure.  Alternatively,
 it may be possible to use a FireWire port for debugging with firescope
 (ftp://ftp.firstfloor.org/pub/ak/firescope/).  On x86 it is also possible to
-use the PM_TRACE mechanism documented in Documentation/s2ram.txt .
+use the PM_TRACE mechanism documented in Documentation/power/s2ram.txt .
 
 2. Testing suspend to RAM (STR)
 
@@ -201,3 +201,27 @@
 analogous to the one described in section 1.  If you find some failing drivers,
 you will have to unload them every time before an STR transition (ie. before
 you run s2ram), and please report the problems with them.
+
+There is a debugfs entry which shows the suspend to RAM statistics. Here is an
+example of its output.
+	# mount -t debugfs none /sys/kernel/debug
+	# cat /sys/kernel/debug/suspend_stats
+	success: 20
+	fail: 5
+	failed_freeze: 0
+	failed_prepare: 0
+	failed_suspend: 5
+	failed_suspend_noirq: 0
+	failed_resume: 0
+	failed_resume_noirq: 0
+	failures:
+	  last_failed_dev:	alarm
+				adc
+	  last_failed_errno:	-16
+				-16
+	  last_failed_step:	suspend
+				suspend
+Field success means the success number of suspend to RAM, and field fail means
+the failure number. Others are the failure number of different steps of suspend
+to RAM. suspend_stats just lists the last 2 failed devices, error number and
+failed step of suspend.
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index 3384d59..646a89e 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -152,7 +152,9 @@
 for the most part drivers should not change its value.  The initial value of
 should_wakeup is supposed to be false for the majority of devices; the major
 exceptions are power buttons, keyboards, and Ethernet adapters whose WoL
-(wake-on-LAN) feature has been set up with ethtool.
+(wake-on-LAN) feature has been set up with ethtool.  It should also default
+to true for devices that don't generate wakeup requests on their own but merely
+forward wakeup requests from one bus to another (like PCI bridges).
 
 Whether or not a device is capable of issuing wakeup events is a hardware
 matter, and the kernel is responsible for keeping track of it.  By contrast,
@@ -279,10 +281,6 @@
 	time.)  Unlike the other suspend-related phases, during the prepare
 	phase the device tree is traversed top-down.
 
-	In addition to that, if device drivers need to allocate additional
-	memory to be able to hadle device suspend correctly, that should be
-	done in the prepare phase.
-
 	After the prepare callback method returns, no new children may be
 	registered below the device.  The method may also prepare the device or
 	driver in some way for the upcoming system power transition (for
diff --git a/Documentation/power/freezing-of-tasks.txt b/Documentation/power/freezing-of-tasks.txt
index 38b5724..316c2ba 100644
--- a/Documentation/power/freezing-of-tasks.txt
+++ b/Documentation/power/freezing-of-tasks.txt
@@ -22,12 +22,12 @@
 either wakes them up, if they are kernel threads, or sends fake signals to them,
 if they are user space processes.  A task that has TIF_FREEZE set, should react
 to it by calling the function called refrigerator() (defined in
-kernel/power/process.c), which sets the task's PF_FROZEN flag, changes its state
+kernel/freezer.c), which sets the task's PF_FROZEN flag, changes its state
 to TASK_UNINTERRUPTIBLE and makes it loop until PF_FROZEN is cleared for it.
 Then, we say that the task is 'frozen' and therefore the set of functions
 handling this mechanism is referred to as 'the freezer' (these functions are
-defined in kernel/power/process.c and include/linux/freezer.h).  User space
-processes are generally frozen before kernel threads.
+defined in kernel/power/process.c, kernel/freezer.c & include/linux/freezer.h).
+User space processes are generally frozen before kernel threads.
 
 It is not recommended to call refrigerator() directly.  Instead, it is
 recommended to use the try_to_freeze() function (defined in
@@ -95,7 +95,7 @@
 additional memory and we prevent them from doing that by freezing them earlier.
 [Of course, this also means that device drivers should not allocate substantial
 amounts of memory from their .suspend() callbacks before hibernation, but this
-is e separate issue.]
+is a separate issue.]
 
 3. The third reason is to prevent user space processes and some kernel threads
 from interfering with the suspending and resuming of devices.  A user space
diff --git a/Documentation/power/pm_qos_interface.txt b/Documentation/power/pm_qos_interface.txt
index bfed898..17e130a 100644
--- a/Documentation/power/pm_qos_interface.txt
+++ b/Documentation/power/pm_qos_interface.txt
@@ -4,14 +4,19 @@
 performance expectations by drivers, subsystems and user space applications on
 one of the parameters.
 
-Currently we have {cpu_dma_latency, network_latency, network_throughput} as the
-initial set of pm_qos parameters.
+Two different PM QoS frameworks are available:
+1. PM QoS classes for cpu_dma_latency, network_latency, network_throughput.
+2. the per-device PM QoS framework provides the API to manage the per-device latency
+constraints.
 
 Each parameters have defined units:
  * latency: usec
  * timeout: usec
  * throughput: kbs (kilo bit / sec)
 
+
+1. PM QoS framework
+
 The infrastructure exposes multiple misc device nodes one per implemented
 parameter.  The set of parameters implement is defined by pm_qos_power_init()
 and pm_qos_params.h.  This is done because having the available parameters
@@ -23,14 +28,18 @@
 changes to the request list or elements of the list.  Typically the
 aggregated target value is simply the max or min of the request values held
 in the parameter list elements.
+Note: the aggregated target value is implemented as an atomic variable so that
+reading the aggregated value does not require any locking mechanism.
+
 
 From kernel mode the use of this interface is simple:
 
-handle = pm_qos_add_request(param_class, target_value):
-Will insert an element into the list for that identified PM_QOS class with the
+void pm_qos_add_request(handle, param_class, target_value):
+Will insert an element into the list for that identified PM QoS class with the
 target value.  Upon change to this list the new target is recomputed and any
 registered notifiers are called only if the target value is now different.
-Clients of pm_qos need to save the returned handle.
+Clients of pm_qos need to save the returned handle for future use in other
+pm_qos API functions.
 
 void pm_qos_update_request(handle, new_target_value):
 Will update the list element pointed to by the handle with the new target value
@@ -42,6 +51,20 @@
 call the notification tree if the target was changed as a result of removing
 the request.
 
+int pm_qos_request(param_class):
+Returns the aggregated value for a given PM QoS class.
+
+int pm_qos_request_active(handle):
+Returns if the request is still active, i.e. it has not been removed from a
+PM QoS class constraints list.
+
+int pm_qos_add_notifier(param_class, notifier):
+Adds a notification callback function to the PM QoS class. The callback is
+called when the aggregated value for the PM QoS class is changed.
+
+int pm_qos_remove_notifier(int param_class, notifier):
+Removes the notification callback function for the PM QoS class.
+
 
 From user mode:
 Only processes can register a pm_qos request.  To provide for automatic
@@ -63,4 +86,63 @@
 node.
 
 
+2. PM QoS per-device latency framework
+
+For each device a list of performance requests is maintained along with
+an aggregated target value.  The aggregated target value is updated with
+changes to the request list or elements of the list.  Typically the
+aggregated target value is simply the max or min of the request values held
+in the parameter list elements.
+Note: the aggregated target value is implemented as an atomic variable so that
+reading the aggregated value does not require any locking mechanism.
+
+
+From kernel mode the use of this interface is the following:
+
+int dev_pm_qos_add_request(device, handle, value):
+Will insert an element into the list for that identified device with the
+target value.  Upon change to this list the new target is recomputed and any
+registered notifiers are called only if the target value is now different.
+Clients of dev_pm_qos need to save the handle for future use in other
+dev_pm_qos API functions.
+
+int dev_pm_qos_update_request(handle, new_value):
+Will update the list element pointed to by the handle with the new target value
+and recompute the new aggregated target, calling the notification trees if the
+target is changed.
+
+int dev_pm_qos_remove_request(handle):
+Will remove the element.  After removal it will update the aggregate target and
+call the notification trees if the target was changed as a result of removing
+the request.
+
+s32 dev_pm_qos_read_value(device):
+Returns the aggregated value for a given device's constraints list.
+
+
+Notification mechanisms:
+The per-device PM QoS framework has 2 different and distinct notification trees:
+a per-device notification tree and a global notification tree.
+
+int dev_pm_qos_add_notifier(device, notifier):
+Adds a notification callback function for the device.
+The callback is called when the aggregated value of the device constraints list
+is changed.
+
+int dev_pm_qos_remove_notifier(device, notifier):
+Removes the notification callback function for the device.
+
+int dev_pm_qos_add_global_notifier(notifier):
+Adds a notification callback function in the global notification tree of the
+framework.
+The callback is called when the aggregated value for any device is changed.
+
+int dev_pm_qos_remove_global_notifier(notifier):
+Removes the notification callback function from the global notification tree
+of the framework.
+
+
+From user mode:
+No API for user space access to the per-device latency constraints is provided
+yet - still under discussion.
 
diff --git a/Documentation/power/regulator/machine.txt b/Documentation/power/regulator/machine.txt
index b42419b..ce63af0 100644
--- a/Documentation/power/regulator/machine.txt
+++ b/Documentation/power/regulator/machine.txt
@@ -16,7 +16,7 @@
 each regulator.
 
 struct regulator_consumer_supply {
-	struct device *dev;	/* consumer */
+	const char *dev_name;	/* consumer dev_name() */
 	const char *supply;	/* consumer supply - e.g. "vcc" */
 };
 
@@ -24,13 +24,13 @@
 
 static struct regulator_consumer_supply regulator1_consumers[] = {
 {
-	.dev	= &platform_consumerB_device.dev,
-	.supply	= "Vcc",
+	.dev_name	= "dev_name(consumer B)",
+	.supply		= "Vcc",
 },};
 
 static struct regulator_consumer_supply regulator2_consumers[] = {
 {
-	.dev	= &platform_consumerA_device.dev,
+	.dev	= "dev_name(consumer A"),
 	.supply	= "Vcc",
 },};
 
@@ -43,6 +43,7 @@
 
 static struct regulator_init_data regulator1_data = {
 	.constraints = {
+		.name = "Regulator-1",
 		.min_uV = 3300000,
 		.max_uV = 3300000,
 		.valid_modes_mask = REGULATOR_MODE_NORMAL,
@@ -51,13 +52,19 @@
 	.consumer_supplies = regulator1_consumers,
 };
 
+The name field should be set to something that is usefully descriptive
+for the board for configuration of supplies for other regulators and
+for use in logging and other diagnostic output.  Normally the name
+used for the supply rail in the schematic is a good choice.  If no
+name is provided then the subsystem will choose one.
+
 Regulator-1 supplies power to Regulator-2. This relationship must be registered
 with the core so that Regulator-1 is also enabled when Consumer A enables its
 supply (Regulator-2). The supply regulator is set by the supply_regulator
-field below:-
+field below and co:-
 
 static struct regulator_init_data regulator2_data = {
-	.supply_regulator = "regulator_name",
+	.supply_regulator = "Regulator-1",
 	.constraints = {
 		.min_uV = 1800000,
 		.max_uV = 2000000,
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 4ce5450..5336149 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -43,13 +43,18 @@
 	...
 };
 
-The ->runtime_suspend(), ->runtime_resume() and ->runtime_idle() callbacks are
-executed by the PM core for either the device type, or the class (if the device
-type's struct dev_pm_ops object does not exist), or the bus type (if the
-device type's and class' struct dev_pm_ops objects do not exist) of the given
-device (this allows device types to override callbacks provided by bus types or
-classes if necessary).  The bus type, device type and class callbacks are
-referred to as subsystem-level callbacks in what follows.
+The ->runtime_suspend(), ->runtime_resume() and ->runtime_idle() callbacks
+are executed by the PM core for either the power domain, or the device type
+(if the device power domain's struct dev_pm_ops does not exist), or the class
+(if the device power domain's and type's struct dev_pm_ops object does not
+exist), or the bus type (if the device power domain's, type's and class'
+struct dev_pm_ops objects do not exist) of the given device, so the priority
+order of callbacks from high to low is that power domain callbacks, device
+type callbacks, class callbacks and bus type callbacks, and the high priority
+one will take precedence over low priority one. The bus type, device type and
+class callbacks are referred to as subsystem-level callbacks in what follows,
+and generally speaking, the power domain callbacks are used for representing
+power domains within a SoC.
 
 By default, the callbacks are always invoked in process context with interrupts
 enabled.  However, subsystems can use the pm_runtime_irq_safe() helper function
@@ -431,8 +436,7 @@
 
   void pm_runtime_irq_safe(struct device *dev);
     - set the power.irq_safe flag for the device, causing the runtime-PM
-      suspend and resume callbacks (but not the idle callback) to be invoked
-      with interrupts disabled
+      callbacks to be invoked with interrupts off
 
   void pm_runtime_mark_last_busy(struct device *dev);
     - set the power.last_busy field to the current time
@@ -478,12 +482,14 @@
 If pm_runtime_irq_safe() has been called for a device then the following helper
 functions may also be used in interrupt context:
 
+pm_runtime_idle()
 pm_runtime_suspend()
 pm_runtime_autosuspend()
 pm_runtime_resume()
 pm_runtime_get_sync()
 pm_runtime_put_sync()
 pm_runtime_put_sync_suspend()
+pm_runtime_put_sync_autosuspend()
 
 5. Runtime PM Initialization, Device Probing and Removal
 
@@ -783,6 +789,16 @@
 Similarly, if the power.use_autosuspend field isn't set then the autosuspend
 helper functions will behave just like the non-autosuspend counterparts.
 
+Under some circumstances a driver or subsystem may want to prevent a device
+from autosuspending immediately, even though the usage counter is zero and the
+autosuspend delay time has expired.  If the ->runtime_suspend() callback
+returns -EAGAIN or -EBUSY, and if the next autosuspend delay expiration time is
+in the future (as it normally would be if the callback invoked
+pm_runtime_mark_last_busy()), the PM core will automatically reschedule the
+autosuspend.  The ->runtime_suspend() callback can't do this rescheduling
+itself because no suspend requests of any kind are accepted while the device is
+suspending (i.e., while the callback is running).
+
 The implementation is well suited for asynchronous use in interrupt contexts.
 However such use inevitably involves races, because the PM core can't
 synchronize ->runtime_suspend() callbacks with the arrival of I/O requests.
diff --git a/Documentation/power/suspend-and-cpuhotplug.txt b/Documentation/power/suspend-and-cpuhotplug.txt
new file mode 100644
index 0000000..f28f9a6
--- /dev/null
+++ b/Documentation/power/suspend-and-cpuhotplug.txt
@@ -0,0 +1,275 @@
+Interaction of Suspend code (S3) with the CPU hotplug infrastructure
+
+     (C) 2011 Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
+
+
+I. How does the regular CPU hotplug code differ from how the Suspend-to-RAM
+   infrastructure uses it internally? And where do they share common code?
+
+Well, a picture is worth a thousand words... So ASCII art follows :-)
+
+[This depicts the current design in the kernel, and focusses only on the
+interactions involving the freezer and CPU hotplug and also tries to explain
+the locking involved. It outlines the notifications involved as well.
+But please note that here, only the call paths are illustrated, with the aim
+of describing where they take different paths and where they share code.
+What happens when regular CPU hotplug and Suspend-to-RAM race with each other
+is not depicted here.]
+
+On a high level, the suspend-resume cycle goes like this:
+
+|Freeze| -> |Disable nonboot| -> |Do suspend| -> |Enable nonboot| -> |Thaw |
+|tasks |    |     cpus      |    |          |    |     cpus     |    |tasks|
+
+
+More details follow:
+
+                                Suspend call path
+                                -----------------
+
+                                  Write 'mem' to
+                                /sys/power/state
+                                    syfs file
+                                        |
+                                        v
+                               Acquire pm_mutex lock
+                                        |
+                                        v
+                             Send PM_SUSPEND_PREPARE
+                                   notifications
+                                        |
+                                        v
+                                   Freeze tasks
+                                        |
+                                        |
+                                        v
+                              disable_nonboot_cpus()
+                                   /* start */
+                                        |
+                                        v
+                            Acquire cpu_add_remove_lock
+                                        |
+                                        v
+                             Iterate over CURRENTLY
+                                   online CPUs
+                                        |
+                                        |
+                                        |                ----------
+                                        v                          | L
+             ======>               _cpu_down()                     |
+            |              [This takes cpuhotplug.lock             |
+  Common    |               before taking down the CPU             |
+   code     |               and releases it when done]             | O
+            |            While it is at it, notifications          |
+            |            are sent when notable events occur,       |
+             ======>     by running all registered callbacks.      |
+                                        |                          | O
+                                        |                          |
+                                        |                          |
+                                        v                          |
+                            Note down these cpus in                | P
+                                frozen_cpus mask         ----------
+                                        |
+                                        v
+                           Disable regular cpu hotplug
+                        by setting cpu_hotplug_disabled=1
+                                        |
+                                        v
+                            Release cpu_add_remove_lock
+                                        |
+                                        v
+                       /* disable_nonboot_cpus() complete */
+                                        |
+                                        v
+                                   Do suspend
+
+
+
+Resuming back is likewise, with the counterparts being (in the order of
+execution during resume):
+* enable_nonboot_cpus() which involves:
+   |  Acquire cpu_add_remove_lock
+   |  Reset cpu_hotplug_disabled to 0, thereby enabling regular cpu hotplug
+   |  Call _cpu_up() [for all those cpus in the frozen_cpus mask, in a loop]
+   |  Release cpu_add_remove_lock
+   v
+
+* thaw tasks
+* send PM_POST_SUSPEND notifications
+* Release pm_mutex lock.
+
+
+It is to be noted here that the pm_mutex lock is acquired at the very
+beginning, when we are just starting out to suspend, and then released only
+after the entire cycle is complete (i.e., suspend + resume).
+
+
+
+                          Regular CPU hotplug call path
+                          -----------------------------
+
+                                Write 0 (or 1) to
+                       /sys/devices/system/cpu/cpu*/online
+                                    sysfs file
+                                        |
+                                        |
+                                        v
+                                    cpu_down()
+                                        |
+                                        v
+                           Acquire cpu_add_remove_lock
+                                        |
+                                        v
+                          If cpu_hotplug_disabled is 1
+                                return gracefully
+                                        |
+                                        |
+                                        v
+             ======>                _cpu_down()
+            |              [This takes cpuhotplug.lock
+  Common    |               before taking down the CPU
+   code     |               and releases it when done]
+            |            While it is at it, notifications
+            |           are sent when notable events occur,
+             ======>    by running all registered callbacks.
+                                        |
+                                        |
+                                        v
+                          Release cpu_add_remove_lock
+                               [That's it!, for
+                              regular CPU hotplug]
+
+
+
+So, as can be seen from the two diagrams (the parts marked as "Common code"),
+regular CPU hotplug and the suspend code path converge at the _cpu_down() and
+_cpu_up() functions. They differ in the arguments passed to these functions,
+in that during regular CPU hotplug, 0 is passed for the 'tasks_frozen'
+argument. But during suspend, since the tasks are already frozen by the time
+the non-boot CPUs are offlined or onlined, the _cpu_*() functions are called
+with the 'tasks_frozen' argument set to 1.
+[See below for some known issues regarding this.]
+
+
+Important files and functions/entry points:
+------------------------------------------
+
+kernel/power/process.c : freeze_processes(), thaw_processes()
+kernel/power/suspend.c : suspend_prepare(), suspend_enter(), suspend_finish()
+kernel/cpu.c: cpu_[up|down](), _cpu_[up|down](), [disable|enable]_nonboot_cpus()
+
+
+
+II. What are the issues involved in CPU hotplug?
+    -------------------------------------------
+
+There are some interesting situations involving CPU hotplug and microcode
+update on the CPUs, as discussed below:
+
+[Please bear in mind that the kernel requests the microcode images from
+userspace, using the request_firmware() function defined in
+drivers/base/firmware_class.c]
+
+
+a. When all the CPUs are identical:
+
+   This is the most common situation and it is quite straightforward: we want
+   to apply the same microcode revision to each of the CPUs.
+   To give an example of x86, the collect_cpu_info() function defined in
+   arch/x86/kernel/microcode_core.c helps in discovering the type of the CPU
+   and thereby in applying the correct microcode revision to it.
+   But note that the kernel does not maintain a common microcode image for the
+   all CPUs, in order to handle case 'b' described below.
+
+
+b. When some of the CPUs are different than the rest:
+
+   In this case since we probably need to apply different microcode revisions
+   to different CPUs, the kernel maintains a copy of the correct microcode
+   image for each CPU (after appropriate CPU type/model discovery using
+   functions such as collect_cpu_info()).
+
+
+c. When a CPU is physically hot-unplugged and a new (and possibly different
+   type of) CPU is hot-plugged into the system:
+
+   In the current design of the kernel, whenever a CPU is taken offline during
+   a regular CPU hotplug operation, upon receiving the CPU_DEAD notification
+   (which is sent by the CPU hotplug code), the microcode update driver's
+   callback for that event reacts by freeing the kernel's copy of the
+   microcode image for that CPU.
+
+   Hence, when a new CPU is brought online, since the kernel finds that it
+   doesn't have the microcode image, it does the CPU type/model discovery
+   afresh and then requests the userspace for the appropriate microcode image
+   for that CPU, which is subsequently applied.
+
+   For example, in x86, the mc_cpu_callback() function (which is the microcode
+   update driver's callback registered for CPU hotplug events) calls
+   microcode_update_cpu() which would call microcode_init_cpu() in this case,
+   instead of microcode_resume_cpu() when it finds that the kernel doesn't
+   have a valid microcode image. This ensures that the CPU type/model
+   discovery is performed and the right microcode is applied to the CPU after
+   getting it from userspace.
+
+
+d. Handling microcode update during suspend/hibernate:
+
+   Strictly speaking, during a CPU hotplug operation which does not involve
+   physically removing or inserting CPUs, the CPUs are not actually powered
+   off during a CPU offline. They are just put to the lowest C-states possible.
+   Hence, in such a case, it is not really necessary to re-apply microcode
+   when the CPUs are brought back online, since they wouldn't have lost the
+   image during the CPU offline operation.
+
+   This is the usual scenario encountered during a resume after a suspend.
+   However, in the case of hibernation, since all the CPUs are completely
+   powered off, during restore it becomes necessary to apply the microcode
+   images to all the CPUs.
+
+   [Note that we don't expect someone to physically pull out nodes and insert
+   nodes with a different type of CPUs in-between a suspend-resume or a
+   hibernate/restore cycle.]
+
+   In the current design of the kernel however, during a CPU offline operation
+   as part of the suspend/hibernate cycle (the CPU_DEAD_FROZEN notification),
+   the existing copy of microcode image in the kernel is not freed up.
+   And during the CPU online operations (during resume/restore), since the
+   kernel finds that it already has copies of the microcode images for all the
+   CPUs, it just applies them to the CPUs, avoiding any re-discovery of CPU
+   type/model and the need for validating whether the microcode revisions are
+   right for the CPUs or not (due to the above assumption that physical CPU
+   hotplug will not be done in-between suspend/resume or hibernate/restore
+   cycles).
+
+
+III. Are there any known problems when regular CPU hotplug and suspend race
+     with each other?
+
+Yes, they are listed below:
+
+1. When invoking regular CPU hotplug, the 'tasks_frozen' argument passed to
+   the _cpu_down() and _cpu_up() functions is *always* 0.
+   This might not reflect the true current state of the system, since the
+   tasks could have been frozen by an out-of-band event such as a suspend
+   operation in progress. Hence, it will lead to wrong notifications being
+   sent during the cpu online/offline events (eg, CPU_ONLINE notification
+   instead of CPU_ONLINE_FROZEN) which in turn will lead to execution of
+   inappropriate code by the callbacks registered for such CPU hotplug events.
+
+2. If a regular CPU hotplug stress test happens to race with the freezer due
+   to a suspend operation in progress at the same time, then we could hit the
+   situation described below:
+
+    * A regular cpu online operation continues its journey from userspace
+      into the kernel, since the freezing has not yet begun.
+    * Then freezer gets to work and freezes userspace.
+    * If cpu online has not yet completed the microcode update stuff by now,
+      it will now start waiting on the frozen userspace in the
+      TASK_UNINTERRUPTIBLE state, in order to get the microcode image.
+    * Now the freezer continues and tries to freeze the remaining tasks. But
+      due to this wait mentioned above, the freezer won't be able to freeze
+      the cpu online hotplug task and hence freezing of tasks fails.
+
+   As a result of this task freezing failure, the suspend operation gets
+   aborted.
diff --git a/Documentation/power/userland-swsusp.txt b/Documentation/power/userland-swsusp.txt
index 1101bee..0e87082 100644
--- a/Documentation/power/userland-swsusp.txt
+++ b/Documentation/power/userland-swsusp.txt
@@ -77,7 +77,8 @@
 	resume_swap_area, as defined in kernel/power/suspend_ioctls.h,
 	containing the resume device specification and the offset); for swap
 	partitions the offset is always 0, but it is different from zero for
-	swap files (see Documentation/swsusp-and-swap-files.txt for details).
+	swap files (see Documentation/power/swsusp-and-swap-files.txt for
+	details).
 
 SNAPSHOT_PLATFORM_SUPPORT - enable/disable the hibernation platform support,
 	depending on the argument value (enable, if the argument is nonzero)
diff --git a/Documentation/ramoops.txt b/Documentation/ramoops.txt
new file mode 100644
index 0000000..8fb1ba7
--- /dev/null
+++ b/Documentation/ramoops.txt
@@ -0,0 +1,76 @@
+Ramoops oops/panic logger
+=========================
+
+Sergiu Iordache <sergiu@chromium.org>
+
+Updated: 8 August 2011
+
+0. Introduction
+
+Ramoops is an oops/panic logger that writes its logs to RAM before the system
+crashes. It works by logging oopses and panics in a circular buffer. Ramoops
+needs a system with persistent RAM so that the content of that area can
+survive after a restart.
+
+1. Ramoops concepts
+
+Ramoops uses a predefined memory area to store the dump. The start and size of
+the memory area are set using two variables:
+  * "mem_address" for the start
+  * "mem_size" for the size. The memory size will be rounded down to a
+  power of two.
+
+The memory area is divided into "record_size" chunks (also rounded down to
+power of two) and each oops/panic writes a "record_size" chunk of
+information.
+
+Dumping both oopses and panics can be done by setting 1 in the "dump_oops"
+variable while setting 0 in that variable dumps only the panics.
+
+The module uses a counter to record multiple dumps but the counter gets reset
+on restart (i.e. new dumps after the restart will overwrite old ones).
+
+2. Setting the parameters
+
+Setting the ramoops parameters can be done in 2 different manners:
+ 1. Use the module parameters (which have the names of the variables described
+ as before).
+ 2. Use a platform device and set the platform data. The parameters can then
+ be set through that platform data. An example of doing that is:
+
+#include <linux/ramoops.h>
+[...]
+
+static struct ramoops_platform_data ramoops_data = {
+        .mem_size               = <...>,
+        .mem_address            = <...>,
+        .record_size            = <...>,
+        .dump_oops              = <...>,
+};
+
+static struct platform_device ramoops_dev = {
+        .name = "ramoops",
+        .dev = {
+                .platform_data = &ramoops_data,
+        },
+};
+
+[... inside a function ...]
+int ret;
+
+ret = platform_device_register(&ramoops_dev);
+if (ret) {
+	printk(KERN_ERR "unable to register platform device\n");
+	return ret;
+}
+
+3. Dump format
+
+The data dump begins with a header, currently defined as "====" followed by a
+timestamp and a new line. The dump then continues with the actual data.
+
+4. Reading the data
+
+The dump data can be read from memory (through /dev/mem or other means).
+Getting the module parameters, which are needed in order to parse the data, can
+be done through /sys/module/ramoops/parameters/* .
diff --git a/Documentation/rapidio/rapidio.txt b/Documentation/rapidio/rapidio.txt
index be70ee1..c75694b 100644
--- a/Documentation/rapidio/rapidio.txt
+++ b/Documentation/rapidio/rapidio.txt
@@ -144,7 +144,7 @@
 
 After the host has completed enumeration of the entire network it releases
 devices by clearing device ID locks (calls rio_clear_locks()). For each endpoint
-in the system, it sets the Master Enable bit in the Port General Control CSR
+in the system, it sets the Discovered bit in the Port General Control CSR
 to indicate that enumeration is completed and agents are allowed to execute
 passive discovery of the network.
 
diff --git a/Documentation/rapidio/tsi721.txt b/Documentation/rapidio/tsi721.txt
new file mode 100644
index 0000000..335f3c6
--- /dev/null
+++ b/Documentation/rapidio/tsi721.txt
@@ -0,0 +1,49 @@
+RapidIO subsystem mport driver for IDT Tsi721 PCI Express-to-SRIO bridge.
+=========================================================================
+
+I. Overview
+
+This driver implements all currently defined RapidIO mport callback functions.
+It supports maintenance read and write operations, inbound and outbound RapidIO
+doorbells, inbound maintenance port-writes and RapidIO messaging.
+
+To generate SRIO maintenance transactions this driver uses one of Tsi721 DMA
+channels. This mechanism provides access to larger range of hop counts and
+destination IDs without need for changes in outbound window translation.
+
+RapidIO messaging support uses dedicated messaging channels for each mailbox.
+For inbound messages this driver uses destination ID matching to forward messages
+into the corresponding message queue. Messaging callbacks are implemented to be
+fully compatible with RIONET driver (Ethernet over RapidIO messaging services).
+
+II. Known problems
+
+  None.
+
+III. To do
+
+ Add DMA data transfers (non-messaging).
+ Add inbound region (SRIO-to-PCIe) mapping.
+
+IV. Version History
+
+  1.0.0 - Initial driver release.
+
+V.  License
+-----------------------------------------------
+
+  Copyright(c) 2011 Integrated Device Technology, Inc. All rights reserved.
+
+  This program is free software; you can redistribute it and/or modify it
+  under the terms of the GNU General Public License as published by the Free
+  Software Foundation; either version 2 of the License, or (at your option)
+  any later version.
+
+  This program is distributed in the hope that it will be useful, but WITHOUT
+  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+  more details.
+
+  You should have received a copy of the GNU General Public License along with
+  this program; if not, write to the Free Software Foundation, Inc.,
+  59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
diff --git a/Documentation/rfkill.txt b/Documentation/rfkill.txt
index 83668e5..03c9d92 100644
--- a/Documentation/rfkill.txt
+++ b/Documentation/rfkill.txt
@@ -117,5 +117,4 @@
 "type" sysfs files explained above.
 
 
-For further details consult Documentation/ABI/stable/dev-rfkill and
-Documentation/ABI/stable/sysfs-class-rfkill.
+For further details consult Documentation/ABI/stable/sysfs-class-rfkill.
diff --git a/Documentation/scheduler/sched-bwc.txt b/Documentation/scheduler/sched-bwc.txt
new file mode 100644
index 0000000..f6b1873
--- /dev/null
+++ b/Documentation/scheduler/sched-bwc.txt
@@ -0,0 +1,122 @@
+CFS Bandwidth Control
+=====================
+
+[ This document only discusses CPU bandwidth control for SCHED_NORMAL.
+  The SCHED_RT case is covered in Documentation/scheduler/sched-rt-group.txt ]
+
+CFS bandwidth control is a CONFIG_FAIR_GROUP_SCHED extension which allows the
+specification of the maximum CPU bandwidth available to a group or hierarchy.
+
+The bandwidth allowed for a group is specified using a quota and period. Within
+each given "period" (microseconds), a group is allowed to consume only up to
+"quota" microseconds of CPU time.  When the CPU bandwidth consumption of a
+group exceeds this limit (for that period), the tasks belonging to its
+hierarchy will be throttled and are not allowed to run again until the next
+period.
+
+A group's unused runtime is globally tracked, being refreshed with quota units
+above at each period boundary.  As threads consume this bandwidth it is
+transferred to cpu-local "silos" on a demand basis.  The amount transferred
+within each of these updates is tunable and described as the "slice".
+
+Management
+----------
+Quota and period are managed within the cpu subsystem via cgroupfs.
+
+cpu.cfs_quota_us: the total available run-time within a period (in microseconds)
+cpu.cfs_period_us: the length of a period (in microseconds)
+cpu.stat: exports throttling statistics [explained further below]
+
+The default values are:
+	cpu.cfs_period_us=100ms
+	cpu.cfs_quota=-1
+
+A value of -1 for cpu.cfs_quota_us indicates that the group does not have any
+bandwidth restriction in place, such a group is described as an unconstrained
+bandwidth group.  This represents the traditional work-conserving behavior for
+CFS.
+
+Writing any (valid) positive value(s) will enact the specified bandwidth limit.
+The minimum quota allowed for the quota or period is 1ms.  There is also an
+upper bound on the period length of 1s.  Additional restrictions exist when
+bandwidth limits are used in a hierarchical fashion, these are explained in
+more detail below.
+
+Writing any negative value to cpu.cfs_quota_us will remove the bandwidth limit
+and return the group to an unconstrained state once more.
+
+Any updates to a group's bandwidth specification will result in it becoming
+unthrottled if it is in a constrained state.
+
+System wide settings
+--------------------
+For efficiency run-time is transferred between the global pool and CPU local
+"silos" in a batch fashion.  This greatly reduces global accounting pressure
+on large systems.  The amount transferred each time such an update is required
+is described as the "slice".
+
+This is tunable via procfs:
+	/proc/sys/kernel/sched_cfs_bandwidth_slice_us (default=5ms)
+
+Larger slice values will reduce transfer overheads, while smaller values allow
+for more fine-grained consumption.
+
+Statistics
+----------
+A group's bandwidth statistics are exported via 3 fields in cpu.stat.
+
+cpu.stat:
+- nr_periods: Number of enforcement intervals that have elapsed.
+- nr_throttled: Number of times the group has been throttled/limited.
+- throttled_time: The total time duration (in nanoseconds) for which entities
+  of the group have been throttled.
+
+This interface is read-only.
+
+Hierarchical considerations
+---------------------------
+The interface enforces that an individual entity's bandwidth is always
+attainable, that is: max(c_i) <= C. However, over-subscription in the
+aggregate case is explicitly allowed to enable work-conserving semantics
+within a hierarchy.
+  e.g. \Sum (c_i) may exceed C
+[ Where C is the parent's bandwidth, and c_i its children ]
+
+
+There are two ways in which a group may become throttled:
+	a. it fully consumes its own quota within a period
+	b. a parent's quota is fully consumed within its period
+
+In case b) above, even though the child may have runtime remaining it will not
+be allowed to until the parent's runtime is refreshed.
+
+Examples
+--------
+1. Limit a group to 1 CPU worth of runtime.
+
+	If period is 250ms and quota is also 250ms, the group will get
+	1 CPU worth of runtime every 250ms.
+
+	# echo 250000 > cpu.cfs_quota_us /* quota = 250ms */
+	# echo 250000 > cpu.cfs_period_us /* period = 250ms */
+
+2. Limit a group to 2 CPUs worth of runtime on a multi-CPU machine.
+
+	With 500ms period and 1000ms quota, the group can get 2 CPUs worth of
+	runtime every 500ms.
+
+	# echo 1000000 > cpu.cfs_quota_us /* quota = 1000ms */
+	# echo 500000 > cpu.cfs_period_us /* period = 500ms */
+
+	The larger period here allows for increased burst capacity.
+
+3. Limit a group to 20% of 1 CPU.
+
+	With 50ms period, 10ms quota will be equivalent to 20% of 1 CPU.
+
+	# echo 10000 > cpu.cfs_quota_us /* quota = 10ms */
+	# echo 50000 > cpu.cfs_period_us /* period = 50ms */
+
+	By using a small period here we are ensuring a consistent latency
+	response at the expense of burst capacity.
+
diff --git a/Documentation/scsi/00-INDEX b/Documentation/scsi/00-INDEX
index c2e18e1..b48ded5 100644
--- a/Documentation/scsi/00-INDEX
+++ b/Documentation/scsi/00-INDEX
@@ -28,6 +28,8 @@
 	- Licence of the Flashpoint driver
 LICENSE.qla2xxx
 	- License for QLogic Linux Fibre Channel HBA Driver firmware.
+LICENSE.qla4xxx
+	- License for QLogic Linux iSCSI HBA Driver.
 Mylex.txt
 	- info on driver for Mylex adapters
 NinjaSCSI.txt
diff --git a/Documentation/scsi/ChangeLog.megaraid_sas b/Documentation/scsi/ChangeLog.megaraid_sas
index 1b6e27d..64adb98 100644
--- a/Documentation/scsi/ChangeLog.megaraid_sas
+++ b/Documentation/scsi/ChangeLog.megaraid_sas
@@ -1,3 +1,18 @@
+Release Date    : Wed. Oct 5, 2011 17:00:00 PST 2010 -
+			(emaild-id:megaraidlinux@lsi.com)
+			Adam Radford
+Current Version : 00.00.06.12-rc1
+Old Version     : 00.00.05.40-rc1
+    1. Continue booting immediately if FW in FAULT at driver load time.
+    2. Increase default cmds per lun to 256.
+    3. Fix mismatch in megasas_reset_fusion() mutex lock-unlock.
+    4. Remove some un-necessary code.
+    5. Clear state change interrupts for Fusion/Invader.
+    6. Clear FUSION_IN_RESET before enabling interrupts.
+    7. Add support for MegaRAID 9360/9380 12GB/s controllers.
+    8. Add multiple MSI-X vector/multiple reply queue support.
+    9. Add driver workaround for PERC5/1068 kdump kernel panic.
+-------------------------------------------------------------------------------
 Release Date    : Tue. Jul 26, 2011 17:00:00 PST 2010 -
 			(emaild-id:megaraidlinux@lsi.com)
 			Adam Radford
diff --git a/Documentation/scsi/LICENSE.qla4xxx b/Documentation/scsi/LICENSE.qla4xxx
new file mode 100644
index 0000000..494980e
--- /dev/null
+++ b/Documentation/scsi/LICENSE.qla4xxx
@@ -0,0 +1,310 @@
+Copyright (c) 2003-2011 QLogic Corporation
+QLogic Linux iSCSI HBA Driver
+
+This program includes a device driver for Linux 3.x.
+You may modify and redistribute the device driver code under the
+GNU General Public License (a copy of which is attached hereto as
+Exhibit A) published by the Free Software Foundation (version 2).
+
+REGARDLESS OF WHAT LICENSING MECHANISM IS USED OR APPLICABLE,
+THIS PROGRAM IS PROVIDED BY QLOGIC CORPORATION "AS IS'' AND ANY
+EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR
+BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
+TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+
+USER ACKNOWLEDGES AND AGREES THAT USE OF THIS PROGRAM WILL NOT
+CREATE OR GIVE GROUNDS FOR A LICENSE BY IMPLICATION, ESTOPPEL, OR
+OTHERWISE IN ANY INTELLECTUAL PROPERTY RIGHTS (PATENT, COPYRIGHT,
+TRADE SECRET, MASK WORK, OR OTHER PROPRIETARY RIGHT) EMBODIED IN
+ANY OTHER QLOGIC HARDWARE OR SOFTWARE EITHER SOLELY OR IN
+COMBINATION WITH THIS PROGRAM.
+
+
+EXHIBIT A
+
+		    GNU GENERAL PUBLIC LICENSE
+		       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+ 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+			    Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+		    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+			    NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
diff --git a/Documentation/scsi/aic7xxx_old.txt b/Documentation/scsi/aic7xxx_old.txt
index 7bd210a..ecfc474 100644
--- a/Documentation/scsi/aic7xxx_old.txt
+++ b/Documentation/scsi/aic7xxx_old.txt
@@ -444,7 +444,7 @@
   Kernel Compile options
   ------------------------------
     The various kernel compile time options for this driver are now fairly
-    well documented in the file Documentation/Configure.help.  In order to
+    well documented in the file drivers/scsi/Kconfig.  In order to
     see this documentation, you need to use one of the advanced configuration
     programs (menuconfig and xconfig).  If you are using the "make menuconfig"
     method of configuring your kernel, then you would simply highlight the
diff --git a/Documentation/scsi/bnx2fc.txt b/Documentation/scsi/bnx2fc.txt
new file mode 100644
index 0000000..8082355
--- /dev/null
+++ b/Documentation/scsi/bnx2fc.txt
@@ -0,0 +1,75 @@
+Operating FCoE using bnx2fc
+===========================
+Broadcom FCoE offload through bnx2fc is full stateful hardware offload that
+cooperates with all interfaces provided by the Linux ecosystem for FC/FCoE and
+SCSI controllers.  As such, FCoE functionality, once enabled is largely
+transparent. Devices discovered on the SAN will be registered and unregistered
+automatically with the upper storage layers.
+
+Despite the fact that the Broadcom's FCoE offload is fully offloaded, it does
+depend on the state of the network interfaces to operate. As such, the network
+interface (e.g. eth0) associated with the FCoE offload initiator must be 'up'.
+It is recommended that the network interfaces be configured to be brought up
+automatically at boot time.
+
+Furthermore, the Broadcom FCoE offload solution creates VLAN interfaces to
+support the VLANs that have been discovered for FCoE operation (e.g.
+eth0.1001-fcoe).  Do not delete or disable these interfaces or FCoE operation
+will be disrupted.
+
+Driver Usage Model:
+===================
+
+1. Ensure that fcoe-utils package is installed.
+
+2. Configure the interfaces on which bnx2fc driver has to operate on.
+Here are the steps to configure:
+	a. cd /etc/fcoe
+	b. copy cfg-ethx to cfg-eth5 if FCoE has to be enabled on eth5.
+	c. Repeat this for all the interfaces where FCoE has to be enabled.
+	d. Edit all the cfg-eth files to set "no" for DCB_REQUIRED** field, and
+	   "yes" for AUTO_VLAN.
+	e. Other configuration parameters should be left as default
+
+3. Ensure that "bnx2fc" is in SUPPORTED_DRIVERS list in /etc/fcoe/config.
+
+4. Start fcoe service. (service fcoe start). If Broadcom devices are present in
+the system, bnx2fc driver would automatically claim the interfaces, starts vlan
+discovery and log into the targets.
+
+5. "Symbolic Name" in 'fcoeadm -i' output would display if bnx2fc has claimed
+the interface.
+Eg:
+[root@bh2 ~]# fcoeadm -i
+    Description:      NetXtreme II BCM57712 10 Gigabit Ethernet
+    Revision:         01
+    Manufacturer:     Broadcom Corporation
+    Serial Number:    0010186FD558
+    Driver:           bnx2x 1.70.00-0
+    Number of Ports:  2
+
+        Symbolic Name:     bnx2fc v1.0.5 over eth5.4
+        OS Device Name:    host11
+        Node Name:         0x10000010186FD559
+        Port Name:         0x20000010186FD559
+        FabricName:        0x2001000DECB3B681
+        Speed:             10 Gbit
+        Supported Speed:   10 Gbit
+        MaxFrameSize:      2048
+        FC-ID (Port ID):   0x0F0377
+        State:             Online
+
+6. Verify the vlan discovery is performed by running ifconfig and notice
+<INTERFACE>.<VLAN>-fcoe interfaces are automatically created.
+
+Refer to fcoeadm manpage for more information on fcoeadm operations to
+create/destroy interfaces or to display lun/target information.
+
+NOTE:
+====
+** Broadcom FCoE capable devices implement a DCBX/LLDP client on-chip. Only one
+LLDP client is allowed per interface. For proper operation all host software
+based DCBX/LLDP clients (e.g. lldpad) must be disabled. To disable lldpad on a
+given interface, run the following command:
+
+lldptool set-lldp -i <interface_name> adminStatus=disabled
diff --git a/Documentation/scsi/scsi_mid_low_api.txt b/Documentation/scsi/scsi_mid_low_api.txt
index 5f17d29..a340b18 100644
--- a/Documentation/scsi/scsi_mid_low_api.txt
+++ b/Documentation/scsi/scsi_mid_low_api.txt
@@ -55,11 +55,6 @@
 about the USB mass storage driver see the 
 /usr/src/linux/drivers/usb/storage directory.
 
-The Linux kernel source Documentation/DocBook/scsidrivers.tmpl file
-refers to this file. With the appropriate DocBook tool-set, this permits
-users to generate html, ps and pdf renderings of information within this
-file (e.g. the interface functions).
-
 Driver structure
 ================
 Traditionally an LLD for the SCSI subsystem has been at least two files in
diff --git a/Documentation/security/keys-trusted-encrypted.txt b/Documentation/security/keys-trusted-encrypted.txt
index 5f50cca..c9e4855 100644
--- a/Documentation/security/keys-trusted-encrypted.txt
+++ b/Documentation/security/keys-trusted-encrypted.txt
@@ -156,4 +156,5 @@
 Other uses for trusted and encrypted keys, such as for disk and file encryption
 are anticipated.  In particular the new format 'ecryptfs' has been defined in
 in order to use encrypted keys to mount an eCryptfs filesystem.  More details
-about the usage can be found in the file 'Documentation/keys-ecryptfs.txt'.
+about the usage can be found in the file
+'Documentation/security/keys-ecryptfs.txt'.
diff --git a/Documentation/serial/computone.txt b/Documentation/serial/computone.txt
index 60a6f65..39ddcdb 100644
--- a/Documentation/serial/computone.txt
+++ b/Documentation/serial/computone.txt
@@ -20,8 +20,6 @@
 Date: 11/01/2001
 Historical Author: Andrew Manison <amanison@america.net>
 Primary Author: Doug McNash
-Support: support@computone.com
-Fixes and Updates: Mike Warfield <mhw@wittsend.com>
 
 This file assumes that you are using the Computone drivers which are
 integrated into the kernel sources.  For updating the drivers or installing
diff --git a/Documentation/serial/serial-rs485.txt b/Documentation/serial/serial-rs485.txt
index a493238..079cb3d 100644
--- a/Documentation/serial/serial-rs485.txt
+++ b/Documentation/serial/serial-rs485.txt
@@ -28,6 +28,10 @@
    RS485 communications. This data structure is used to set and configure RS485
    parameters in the platform data and in ioctls.
 
+   The device tree can also provide RS485 boot time parameters (see [2]
+   for bindings). The driver is in charge of filling this data structure from
+   the values given by the device tree.
+
    Any driver for devices capable of working both as RS232 and RS485 should
    provide at least the following ioctls:
 
@@ -104,6 +108,9 @@
 	rs485conf.flags |= SER_RS485_RTS_AFTER_SEND;
 	rs485conf.delay_rts_after_send = ...;
 
+	/* Set this flag if you want to receive data even whilst sending data */
+	rs485conf.flags |= SER_RS485_RX_DURING_TX;
+
 	if (ioctl (fd, TIOCSRS485, &rs485conf) < 0) {
 		/* Error handling. See errno. */
 	}
@@ -118,3 +125,4 @@
 5. REFERENCES
 
  [1]	include/linux/serial.h
+ [2]	Documentation/devicetree/bindings/serial/rs485.txt
diff --git a/Documentation/sound/oss/PAS16 b/Documentation/sound/oss/PAS16
index 951b3dc..3dca4b7 100644
--- a/Documentation/sound/oss/PAS16
+++ b/Documentation/sound/oss/PAS16
@@ -60,8 +60,7 @@
 
 The new stuff for 2.3.99 and later
 ============================================================================
-The following configuration options from Documentation/Configure.help
-are relevant to configuring the PAS16:
+The following configuration options are relevant to configuring the PAS16:
 
 Sound card support
 CONFIG_SOUND
diff --git a/Documentation/spi/pxa2xx b/Documentation/spi/pxa2xx
index 00511e0..3352f97 100644
--- a/Documentation/spi/pxa2xx
+++ b/Documentation/spi/pxa2xx
@@ -2,7 +2,7 @@
 ===================================================
 This a mini howto on the pxa2xx_spi driver.  The driver turns a PXA2xx
 synchronous serial port into a SPI master controller
-(see Documentation/spi/spi_summary). The driver has the following features
+(see Documentation/spi/spi-summary). The driver has the following features
 
 - Support for any PXA2xx SSP
 - SSP PIO and SSP DMA data transfers.
@@ -85,7 +85,7 @@
 -----------------------
 Typically each SPI slave (chip) is defined in the arch/.../mach-*/board-*.c
 using the "spi_board_info" structure found in "linux/spi/spi.h". See
-"Documentation/spi/spi_summary" for additional information.
+"Documentation/spi/spi-summary" for additional information.
 
 Each slave device attached to the PXA must provide slave specific configuration
 information via the structure "pxa2xx_spi_chip" found in
diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt
index e213f45..21fd05c 100644
--- a/Documentation/stable_kernel_rules.txt
+++ b/Documentation/stable_kernel_rules.txt
@@ -24,10 +24,10 @@
 Procedure for submitting patches to the -stable tree:
 
  - Send the patch, after verifying that it follows the above rules, to
-   stable@kernel.org.  You must note the upstream commit ID in the changelog
-   of your submission.
+   stable@vger.kernel.org.  You must note the upstream commit ID in the
+   changelog of your submission.
  - To have the patch automatically included in the stable tree, add the tag
-     Cc: stable@kernel.org
+     Cc: stable@vger.kernel.org
    in the sign-off area. Once the patch is merged it will be applied to
    the stable tree without anything else needing to be done by the author
    or subsystem maintainer.
@@ -35,10 +35,10 @@
    cherry-picked than this can be specified in the following format in
    the sign-off area:
 
-     Cc: <stable@kernel.org> # .32.x: a1f84a3: sched: Check for idle
-     Cc: <stable@kernel.org> # .32.x: 1b9508f: sched: Rate-limit newidle
-     Cc: <stable@kernel.org> # .32.x: fd21073: sched: Fix affinity logic
-     Cc: <stable@kernel.org> # .32.x
+     Cc: <stable@vger.kernel.org> # .32.x: a1f84a3: sched: Check for idle
+     Cc: <stable@vger.kernel.org> # .32.x: 1b9508f: sched: Rate-limit newidle
+     Cc: <stable@vger.kernel.org> # .32.x: fd21073: sched: Fix affinity logic
+     Cc: <stable@vger.kernel.org> # .32.x
     Signed-off-by: Ingo Molnar <mingo@elte.hu>
 
    The tag sequence has the meaning of:
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 704e474..1f24636 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -24,6 +24,7 @@
 - bootloader_type	     [ X86 only ]
 - bootloader_version	     [ X86 only ]
 - callhome		     [ S390 only ]
+- cap_last_cap
 - core_pattern
 - core_pipe_limit
 - core_uses_pid
@@ -155,6 +156,13 @@
 
 ==============================================================
 
+cap_last_cap
+
+Highest valid capability of the running kernel.  Exports
+CAP_LAST_CAP from the kernel.
+
+==============================================================
+
 core_pattern:
 
 core_pattern is used to specify a core dumpfile pattern name.
diff --git a/Documentation/timers/highres.txt b/Documentation/timers/highres.txt
index 2133223..e878997 100644
--- a/Documentation/timers/highres.txt
+++ b/Documentation/timers/highres.txt
@@ -30,7 +30,7 @@
 ---------------------------
 
 The hrtimer base infrastructure was merged into the 2.6.16 kernel. Details of
-the base implementation are covered in Documentation/hrtimers/hrtimer.txt. See
+the base implementation are covered in Documentation/timers/hrtimers.txt. See
 also figure #2 (OLS slides p. 15)
 
 The main differences to the timer wheel, which holds the armed timer_list type
diff --git a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
index 12cecc8..4a37c47 100644
--- a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
+++ b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
@@ -379,10 +379,10 @@
 
 			# To closer match vmstat scanning statistics, only count isolate_both
 			# and isolate_inactive as scanning. isolate_active is rotation
-			# isolate_inactive == 0
-			# isolate_active   == 1
-			# isolate_both     == 2
-			if ($isolate_mode != 1) {
+			# isolate_inactive == 1
+			# isolate_active   == 2
+			# isolate_both     == 3
+			if ($isolate_mode != 2) {
 				$perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned;
 			}
 			$perprocesspid{$process_pid}->{HIGH_NR_CONTIG_DIRTY} += $nr_contig_dirty;
diff --git a/Documentation/usb/dma.txt b/Documentation/usb/dma.txt
index 84ef865..444651e 100644
--- a/Documentation/usb/dma.txt
+++ b/Documentation/usb/dma.txt
@@ -7,7 +7,7 @@
 
 The big picture is that USB drivers can continue to ignore most DMA issues,
 though they still must provide DMA-ready buffers (see
-Documentation/PCI/PCI-DMA-mapping.txt).  That's how they've worked through
+Documentation/DMA-API-HOWTO.txt).  That's how they've worked through
 the 2.4 (and earlier) kernels.
 
 OR:  they can now be DMA-aware.
@@ -57,7 +57,7 @@
   force a consistent memory access ordering by using memory barriers.  It's
   not using a streaming DMA mapping, so it's good for small transfers on
   systems where the I/O would otherwise thrash an IOMMU mapping.  (See
-  Documentation/PCI/PCI-DMA-mapping.txt for definitions of "coherent" and
+  Documentation/DMA-API-HOWTO.txt for definitions of "coherent" and
   "streaming" DMA mappings.)
 
   Asking for 1/Nth of a page (as well as asking for N pages) is reasonably
@@ -88,7 +88,7 @@
 Existing buffers aren't usable for DMA without first being mapped into the
 DMA address space of the device.  However, most buffers passed to your
 driver can safely be used with such DMA mapping.  (See the first section
-of Documentation/PCI/PCI-DMA-mapping.txt, titled "What memory is DMA-able?")
+of Documentation/DMA-API-HOWTO.txt, titled "What memory is DMA-able?")
 
 - When you're using scatterlists, you can map everything at once.  On some
   systems, this kicks in an IOMMU and turns the scatterlists into single
diff --git a/Documentation/usb/dwc3.txt b/Documentation/usb/dwc3.txt
new file mode 100644
index 0000000..7b590ed
--- /dev/null
+++ b/Documentation/usb/dwc3.txt
@@ -0,0 +1,45 @@
+
+ TODO
+~~~~~~
+Please pick something while reading :)
+
+- Convert interrupt handler to per-ep-thread-irq
+
+  As it turns out some DWC3-commands ~1ms to complete. Currently we spin
+  until the command completes which is bad.
+
+  Implementation idea:
+  - dwc core implements a demultiplexing irq chip for interrupts per
+    endpoint. The interrupt numbers are allocated during probe and belong
+    to the device. If MSI provides per-endpoint interrupt this dummy
+    interrupt chip can be replaced with "real" interrupts.
+  - interrupts are requested / allocated on usb_ep_enable() and removed on
+    usb_ep_disable(). Worst case are 32 interrupts, the lower limit is two
+    for ep0/1.
+  - dwc3_send_gadget_ep_cmd() will sleep in wait_for_completion_timeout()
+    until the command completes.
+  - the interrupt handler is split into the following pieces:
+    - primary handler of the device
+      goes through every event and calls generic_handle_irq() for event
+      it. On return from generic_handle_irq() in acknowledges the event
+      counter so interrupt goes away (eventually).
+
+    - threaded handler of the device
+      none
+
+    - primary handler of the EP-interrupt
+      reads the event and tries to process it. Everything that requries
+      sleeping is handed over to the Thread. The event is saved in an
+      per-endpoint data-structure.
+      We probably have to pay attention not to process events once we
+      handed something to thread so we don't process event X prio Y
+      where X > Y.
+
+    - threaded handler of the EP-interrupt
+      handles the remaining EP work which might sleep such as waiting
+      for command completion.
+
+  Latency:
+   There should be no increase in latency since the interrupt-thread has a
+   high priority and will be run before an average task in user land
+   (except the user changed priorities).
diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt
index c9ffa9c..12511c9 100644
--- a/Documentation/usb/power-management.txt
+++ b/Documentation/usb/power-management.txt
@@ -439,10 +439,10 @@
 device.
 
 External suspend calls should never be allowed to fail in this way,
-only autosuspend calls.  The driver can tell them apart by checking
-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.
+only autosuspend calls.  The driver can tell them apart by applying
+the PMSG_IS_AUTO() macro to the message argument to the suspend
+method; it will return True for internal PM events (autosuspend) and
+False for external PM events.
 
 
 	Mutual exclusion
@@ -487,3 +487,29 @@
 resume as soon as the system suspend is complete.  Or the remote
 wakeup may fail and get lost.  Which outcome occurs depends on timing
 and on the hardware and firmware design.
+
+
+	xHCI hardware link PM
+	---------------------
+
+xHCI host controller provides hardware link power management to usb2.0
+(xHCI 1.0 feature) and usb3.0 devices which support link PM. By
+enabling hardware LPM, the host can automatically put the device into
+lower power state(L1 for usb2.0 devices, or U1/U2 for usb3.0 devices),
+which state device can enter and resume very quickly.
+
+The user interface for controlling USB2 hardware LPM is located in the
+power/ subdirectory of each USB device's sysfs directory, that is, in
+/sys/bus/usb/devices/.../power/ where "..." is the device's ID. The
+relevant attribute files is usb2_hardware_lpm.
+
+	power/usb2_hardware_lpm
+
+		When a USB2 device which support LPM is plugged to a
+		xHCI host root hub which support software LPM, the
+		host will run a software LPM test for it; if the device
+		enters L1 state and resume successfully and the host
+		supports USB2 hardware LPM, this file will show up and
+		driver will enable hardware LPM	for the device. You
+		can write y/Y/1 or n/N/0 to the file to	enable/disable
+		USB2 hardware LPM manually. This is for	test purpose mainly.
diff --git a/drivers/staging/tm6000/CARDLIST b/Documentation/video4linux/CARDLIST.tm6000
similarity index 100%
rename from drivers/staging/tm6000/CARDLIST
rename to Documentation/video4linux/CARDLIST.tm6000
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
index 5bfa9a7..b15e29f 100644
--- a/Documentation/video4linux/gspca.txt
+++ b/Documentation/video4linux/gspca.txt
@@ -8,6 +8,7 @@
 ----
 spca501		0000:0000	MystFromOri Unknown Camera
 spca508		0130:0130	Clone Digital Webcam 11043
+zc3xx		03f0:1b07	HP Premium Starter Cam
 m5602		0402:5602	ALi Video Camera Controller
 spca501		040a:0002	Kodak DVC-325
 spca500		040a:0300	Kodak EZ200
@@ -190,6 +191,7 @@
 ov519		05a9:0530	OmniVision
 ov519		05a9:2800	OmniVision SuperCAM
 ov519		05a9:4519	Webcam Classic
+ov534_9		05a9:8065	OmniVision test kit ov538+ov9712
 ov519		05a9:8519	OmniVision
 ov519		05a9:a511	D-Link USB Digital Video Camera
 ov519		05a9:a518	D-Link DSB-C310 Webcam
@@ -199,6 +201,8 @@
 gl860		05e3:f191	Genesys Logic PC Camera
 spca561		060b:a001	Maxell Compact Pc PM3
 zc3xx		0698:2003	CTX M730V built in
+topro		06a2:0003	TP6800 PC Camera, CmoX CX0342 webcam
+topro		06a2:6810	Creative Qmax
 nw80x		06a5:0000	Typhoon Webcam 100 USB
 nw80x		06a5:d001	Divio based webcams
 nw80x		06a5:d800	Divio Chicony TwinkleCam, Trust SpaceCam
diff --git a/Documentation/video4linux/omap3isp.txt b/Documentation/video4linux/omap3isp.txt
index 69be2c7..5dd1439 100644
--- a/Documentation/video4linux/omap3isp.txt
+++ b/Documentation/video4linux/omap3isp.txt
@@ -70,10 +70,11 @@
 The OMAP 3 ISP driver does support the V4L2 event interface on CCDC and
 statistics (AEWB, AF and histogram) subdevs.
 
-The CCDC subdev produces V4L2_EVENT_OMAP3ISP_HS_VS type event on HS_VS
-interrupt which is used to signal frame start. The event is triggered exactly
-when the reception of the first line of the frame starts in the CCDC module.
-The event can be subscribed on the CCDC subdev.
+The CCDC subdev produces V4L2_EVENT_FRAME_SYNC type event on HS_VS
+interrupt which is used to signal frame start. Earlier version of this
+driver used V4L2_EVENT_OMAP3ISP_HS_VS for this purpose. The event is
+triggered exactly when the reception of the first line of the frame starts
+in the CCDC module. The event can be subscribed on the CCDC subdev.
 
 (When using parallel interface one must pay account to correct configuration
 of the VS signal polarity. This is automatically correct when using the serial
diff --git a/Documentation/video4linux/v4l2-controls.txt b/Documentation/video4linux/v4l2-controls.txt
index 9346fc8..26aa057 100644
--- a/Documentation/video4linux/v4l2-controls.txt
+++ b/Documentation/video4linux/v4l2-controls.txt
@@ -285,11 +285,11 @@
 Note that you use the 'new value' union as well in g_volatile_ctrl. In general
 controls that need to implement g_volatile_ctrl are read-only controls.
 
-To mark a control as volatile you have to set the is_volatile flag:
+To mark a control as volatile you have to set V4L2_CTRL_FLAG_VOLATILE:
 
 	ctrl = v4l2_ctrl_new_std(&sd->ctrl_handler, ...);
 	if (ctrl)
-		ctrl->is_volatile = 1;
+		ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE;
 
 For try/s_ctrl the new values (i.e. as passed by the user) are filled in and
 you can modify them in try_ctrl or set them in s_ctrl. The 'cur' union
@@ -367,8 +367,7 @@
 The last argument is the priv pointer which can be set to driver-specific
 private data.
 
-The v4l2_ctrl_config struct also has fields to set the is_private and is_volatile
-flags.
+The v4l2_ctrl_config struct also has a field to set the is_private flag.
 
 If the name field is not set, then the framework will assume this is a standard
 control and will fill in the name, type and flags fields accordingly.
@@ -496,18 +495,20 @@
 
 A common type of control cluster is one that handles 'auto-foo/foo'-type
 controls. Typical examples are autogain/gain, autoexposure/exposure,
-autowhitebalance/red balance/blue balance. In all cases you have one controls
+autowhitebalance/red balance/blue balance. In all cases you have one control
 that determines whether another control is handled automatically by the hardware,
 or whether it is under manual control from the user.
 
 If the cluster is in automatic mode, then the manual controls should be
-marked inactive. When the volatile controls are read the g_volatile_ctrl
-operation should return the value that the hardware's automatic mode set up
-automatically.
+marked inactive and volatile. When the volatile controls are read the
+g_volatile_ctrl operation should return the value that the hardware's automatic
+mode set up automatically.
 
 If the cluster is put in manual mode, then the manual controls should become
-active again and the is_volatile flag should be ignored (so g_volatile_ctrl is
-no longer called while in manual mode).
+active again and the volatile flag is cleared (so g_volatile_ctrl is no longer
+called while in manual mode). In addition just before switching to manual mode
+the current values as determined by the auto mode are copied as the new manual
+values.
 
 Finally the V4L2_CTRL_FLAG_UPDATE should be set for the auto control since
 changing that control affects the control flags of the manual controls.
@@ -520,7 +521,11 @@
 
 The first two arguments are identical to v4l2_ctrl_cluster. The third argument
 tells the framework which value switches the cluster into manual mode. The
-last argument will optionally set the is_volatile flag for the non-auto controls.
+last argument will optionally set V4L2_CTRL_FLAG_VOLATILE for the non-auto controls.
+If it is false, then the manual controls are never volatile. You would typically
+use that if the hardware does not give you the option to read back to values as
+determined by the auto mode (e.g. if autogain is on, the hardware doesn't allow
+you to obtain the current gain value).
 
 The first control of the cluster is assumed to be the 'auto' control.
 
@@ -681,16 +686,6 @@
 count if nothing was done yet. If it is less than count then only the controls
 up to error_idx-1 were successfully applied.
 
-3) When attempting to read a button control the framework will return -EACCES
-instead of -EINVAL as stated in the spec. It seems to make more sense since
-button controls are write-only controls.
-
-4) Attempting to write to a read-only control will return -EACCES instead of
--EINVAL as the spec says.
-
-5) The spec does not mention what should happen when you try to set/get a
-control class controls. The framework will return -EACCES.
-
 
 Proposals for Extensions
 ========================
@@ -703,9 +698,3 @@
 2) It is possible to mark in the controls array which controls have been
 successfully written and which failed by for example adding a bit to the
 control ID. Not sure if it is worth the effort, though.
-
-3) Trying to set volatile inactive controls should result in -EACCESS.
-
-4) Add a new flag to mark volatile controls. Any application that wants
-to store the state of the controls can then skip volatile inactive controls.
-Currently it is not possible to detect such controls.
diff --git a/Documentation/virtual/00-INDEX b/Documentation/virtual/00-INDEX
index fe0251c..8e60199 100644
--- a/Documentation/virtual/00-INDEX
+++ b/Documentation/virtual/00-INDEX
@@ -8,3 +8,6 @@
 	- Extremely simple hypervisor for experimental/educational use.
 uml/
 	- User Mode Linux, builds/runs Linux kernel as a userspace program.
+virtio.txt
+	- Text version of draft virtio spec.
+          See http://ozlabs.org/~rusty/virtio-spec
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index b0e4b9c..7945b0b 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -175,10 +175,30 @@
 Returns: vcpu fd on success, -1 on error
 
 This API adds a vcpu to a virtual machine.  The vcpu id is a small integer
-in the range [0, max_vcpus).  You can use KVM_CAP_NR_VCPUS of the
-KVM_CHECK_EXTENSION ioctl() to determine the value for max_vcpus at run-time.
+in the range [0, max_vcpus).
+
+The recommended max_vcpus value can be retrieved using the KVM_CAP_NR_VCPUS of
+the KVM_CHECK_EXTENSION ioctl() at run-time.
+The maximum possible value for max_vcpus can be retrieved using the
+KVM_CAP_MAX_VCPUS of the KVM_CHECK_EXTENSION ioctl() at run-time.
+
 If the KVM_CAP_NR_VCPUS does not exist, you should assume that max_vcpus is 4
 cpus max.
+If the KVM_CAP_MAX_VCPUS does not exist, you should assume that max_vcpus is
+same as the value returned from KVM_CAP_NR_VCPUS.
+
+On powerpc using book3s_hv mode, the vcpus are mapped onto virtual
+threads in one or more virtual CPU cores.  (This is because the
+hardware requires all the hardware threads in a CPU core to be in the
+same partition.)  The KVM_CAP_PPC_SMT capability indicates the number
+of vcpus per virtual core (vcore).  The vcore id is obtained by
+dividing the vcpu id by the number of vcpus per vcore.  The vcpus in a
+given vcore will always be in the same physical core as each other
+(though that might be a different physical core from time to time).
+Userspace can control the threading (SMT) mode of the guest by its
+allocation of vcpu ids.  For example, if userspace wants
+single-threaded guest vcpus, it should make all vcpu ids be a multiple
+of the number of vcpus per vcore.
 
 On powerpc using book3s_hv mode, the vcpus are mapped onto virtual
 threads in one or more virtual CPU cores.  (This is because the
@@ -1633,3 +1653,50 @@
 		char padding[256];
 	};
 };
+
+6. Capabilities that can be enabled
+
+There are certain capabilities that change the behavior of the virtual CPU when
+enabled. To enable them, please see section 4.37. Below you can find a list of
+capabilities and what their effect on the vCPU is when enabling them.
+
+The following information is provided along with the description:
+
+  Architectures: which instruction set architectures provide this ioctl.
+      x86 includes both i386 and x86_64.
+
+  Parameters: what parameters are accepted by the capability.
+
+  Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
+      are not detailed, but errors with specific meanings are.
+
+6.1 KVM_CAP_PPC_OSI
+
+Architectures: ppc
+Parameters: none
+Returns: 0 on success; -1 on error
+
+This capability enables interception of OSI hypercalls that otherwise would
+be treated as normal system calls to be injected into the guest. OSI hypercalls
+were invented by Mac-on-Linux to have a standardized communication mechanism
+between the guest and the host.
+
+When this capability is enabled, KVM_EXIT_OSI can occur.
+
+6.2 KVM_CAP_PPC_PAPR
+
+Architectures: ppc
+Parameters: none
+Returns: 0 on success; -1 on error
+
+This capability enables interception of PAPR hypercalls. PAPR hypercalls are
+done using the hypercall instruction "sc 1".
+
+It also sets the guest privilege level to "supervisor" mode. Usually the guest
+runs in "hypervisor" privilege mode with a few missing features.
+
+In addition to the above, it changes the semantics of SDR1. In this mode, the
+HTAB address part of SDR1 contains an HVA instead of a GPA, as PAPR keeps the
+HTAB invisible to the guest.
+
+When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur.
diff --git a/Documentation/virtual/lguest/lguest.c b/Documentation/virtual/lguest/lguest.c
index 043bd7d..c095d79 100644
--- a/Documentation/virtual/lguest/lguest.c
+++ b/Documentation/virtual/lguest/lguest.c
@@ -436,7 +436,7 @@
 
 	/*
 	 * Go back to the start of the file and read the header.  It should be
-	 * a Linux boot header (see Documentation/x86/i386/boot.txt)
+	 * a Linux boot header (see Documentation/x86/boot.txt)
 	 */
 	lseek(fd, 0, SEEK_SET);
 	read(fd, &boot, sizeof(boot));
@@ -1996,6 +1996,9 @@
 	/* We use a simple helper to copy the arguments separated by spaces. */
 	concat((char *)(boot + 1), argv+optind+2);
 
+	/* Set kernel alignment to 16M (CONFIG_PHYSICAL_ALIGN) */
+	boot->hdr.kernel_alignment = 0x1000000;
+
 	/* Boot protocol version: 2.07 supports the fields for lguest. */
 	boot->hdr.version = 0x207;
 
diff --git a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
index 5d0fc8b..77dfecf 100644
--- a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
+++ b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
@@ -134,13 +134,13 @@
 
   ______________________________________________________________________
 
-  11..  IInnttrroodduuccttiioonn
+  1.  Introduction
 
   Welcome to User Mode Linux.  It's going to be fun.
 
 
 
-  11..11..  HHooww iiss UUsseerr MMooddee LLiinnuuxx DDiiffffeerreenntt??
+  1.1.  How is User Mode Linux Different?
 
   Normally, the Linux Kernel talks straight to your hardware (video
   card, keyboard, hard drives, etc), and any programs which run ask the
@@ -181,7 +181,7 @@
 
 
 
-  11..22..  WWhhyy WWoouulldd II WWaanntt UUsseerr MMooddee LLiinnuuxx??
+  1.2.  Why Would I Want User Mode Linux?
 
 
   1. If User Mode Linux crashes, your host kernel is still fine.
@@ -206,12 +206,12 @@
 
 
 
-  22..  CCoommppiilliinngg tthhee kkeerrnneell aanndd mmoodduulleess
+  2.  Compiling the kernel and modules
 
 
 
 
-  22..11..  CCoommppiilliinngg tthhee kkeerrnneell
+  2.1.  Compiling the kernel
 
 
   Compiling the user mode kernel is just like compiling any other
@@ -322,7 +322,7 @@
   bug fixes and enhancements that have gone into subsequent releases.
 
 
-  22..22..  CCoommppiilliinngg aanndd iinnssttaalllliinngg kkeerrnneell mmoodduulleess
+  2.2.  Compiling and installing kernel modules
 
   UML modules are built in the same way as the native kernel (with the
   exception of the 'ARCH=um' that you always need for UML):
@@ -386,19 +386,19 @@
 
 
 
-  22..33..  CCoommppiilliinngg aanndd iinnssttaalllliinngg uummll__uuttiilliittiieess
+  2.3.  Compiling and installing uml_utilities
 
   Many features of the UML kernel require a user-space helper program,
   so a uml_utilities package is distributed separately from the kernel
   patch which provides these helpers. Included within this is:
 
-  +o  port-helper - Used by consoles which connect to xterms or ports
+  o  port-helper - Used by consoles which connect to xterms or ports
 
-  +o  tunctl - Configuration tool to create and delete tap devices
+  o  tunctl - Configuration tool to create and delete tap devices
 
-  +o  uml_net - Setuid binary for automatic tap device configuration
+  o  uml_net - Setuid binary for automatic tap device configuration
 
-  +o  uml_switch - User-space virtual switch required for daemon
+  o  uml_switch - User-space virtual switch required for daemon
      transport
 
      The uml_utilities tree is compiled with:
@@ -423,11 +423,11 @@
 
 
 
-  33..  RRuunnnniinngg UUMMLL aanndd llooggggiinngg iinn
+  3.  Running UML and logging in
 
 
 
-  33..11..  RRuunnnniinngg UUMMLL
+  3.1.  Running UML
 
   It runs on 2.2.15 or later, and all 2.4 kernels.
 
@@ -454,7 +454,7 @@
 
 
 
-  33..22..  LLooggggiinngg iinn
+  3.2.  Logging in
 
 
 
@@ -468,7 +468,7 @@
 
   There are a couple of other ways to log in:
 
-  +o  On a virtual console
+  o  On a virtual console
 
 
 
@@ -480,7 +480,7 @@
 
 
 
-  +o  Over the serial line
+  o  Over the serial line
 
 
      In the boot output, find a line that looks like:
@@ -503,7 +503,7 @@
 
 
 
-  +o  Over the net
+  o  Over the net
 
 
      If the network is running, then you can telnet to the virtual
@@ -514,13 +514,13 @@
   down and the process will exit.
 
 
-  33..33..  EExxaammpplleess
+  3.3.  Examples
 
   Here are some examples of UML in action:
 
-  +o  A login session <http://user-mode-linux.sourceforge.net/login.html>
+  o  A login session <http://user-mode-linux.sourceforge.net/login.html>
 
-  +o  A virtual network <http://user-mode-linux.sourceforge.net/net.html>
+  o  A virtual network <http://user-mode-linux.sourceforge.net/net.html>
 
 
 
@@ -528,12 +528,12 @@
 
 
 
-  44..  UUMMLL oonn 22GG//22GG hhoossttss
+  4.  UML on 2G/2G hosts
 
 
 
 
-  44..11..  IInnttrroodduuccttiioonn
+  4.1.  Introduction
 
 
   Most Linux machines are configured so that the kernel occupies the
@@ -546,7 +546,7 @@
 
 
 
-  44..22..  TThhee pprroobblleemm
+  4.2.  The problem
 
 
   The prebuilt UML binaries on this site will not run on 2G/2G hosts
@@ -558,7 +558,7 @@
 
 
 
-  44..33..  TThhee ssoolluuttiioonn
+  4.3.  The solution
 
 
   The fix for this is to rebuild UML from source after enabling
@@ -576,7 +576,7 @@
 
 
 
-  55..  SSeettttiinngg uupp sseerriiaall lliinneess aanndd ccoonnssoolleess
+  5.  Setting up serial lines and consoles
 
 
   It is possible to attach UML serial lines and consoles to many types
@@ -586,12 +586,12 @@
   You can attach them to host ptys, ttys, file descriptors, and ports.
   This allows you to do things like
 
-  +o  have a UML console appear on an unused host console,
+  o  have a UML console appear on an unused host console,
 
-  +o  hook two virtual machines together by having one attach to a pty
+  o  hook two virtual machines together by having one attach to a pty
      and having the other attach to the corresponding tty
 
-  +o  make a virtual machine accessible from the net by attaching a
+  o  make a virtual machine accessible from the net by attaching a
      console to a port on the host.
 
 
@@ -599,7 +599,7 @@
 
 
 
-  55..11..  SSppeecciiffyyiinngg tthhee ddeevviiccee
+  5.1.  Specifying the device
 
   Devices are specified with "con" or "ssl" (console or serial line,
   respectively), optionally with a device number if you are talking
@@ -626,13 +626,13 @@
 
 
 
-  55..22..  SSppeecciiffyyiinngg tthhee cchhaannnneell
+  5.2.  Specifying the channel
 
   There are a number of different types of channels to attach a UML
   device to, each with a different way of specifying exactly what to
   attach to.
 
-  +o  pseudo-terminals - device=pty pts terminals - device=pts
+  o  pseudo-terminals - device=pty pts terminals - device=pts
 
 
      This will cause UML to allocate a free host pseudo-terminal for the
@@ -640,20 +640,20 @@
      log.  You access it by attaching a terminal program to the
      corresponding tty:
 
-  +o  screen /dev/pts/n
+  o  screen /dev/pts/n
 
-  +o  screen /dev/ttyxx
+  o  screen /dev/ttyxx
 
-  +o  minicom -o -p /dev/ttyxx - minicom seems not able to handle pts
+  o  minicom -o -p /dev/ttyxx - minicom seems not able to handle pts
      devices
 
-  +o  kermit - start it up, 'open' the device, then 'connect'
+  o  kermit - start it up, 'open' the device, then 'connect'
 
 
 
 
 
-  +o  terminals - device=tty:tty device file
+  o  terminals - device=tty:tty device file
 
 
      This will make UML attach the device to the specified tty (i.e
@@ -672,7 +672,7 @@
 
 
 
-  +o  xterms - device=xterm
+  o  xterms - device=xterm
 
 
      UML will run an xterm and the device will be attached to it.
@@ -681,7 +681,7 @@
 
 
 
-  +o  Port - device=port:port number
+  o  Port - device=port:port number
 
 
      This will attach the UML devices to the specified host port.
@@ -725,7 +725,7 @@
 
 
 
-  +o  already-existing file descriptors - device=file descriptor
+  o  already-existing file descriptors - device=file descriptor
 
 
      If you set up a file descriptor on the UML command line, you can
@@ -743,7 +743,7 @@
 
 
 
-  +o  Nothing - device=null
+  o  Nothing - device=null
 
 
      This allows the device to be opened, in contrast to 'none', but
@@ -754,7 +754,7 @@
 
 
 
-  +o  None - device=none
+  o  None - device=none
 
 
      This causes the device to disappear.
@@ -770,7 +770,7 @@
 
 
 
-  will cause serial line 3 to accept input on the host's /dev/tty3 and
+  will cause serial line 3 to accept input on the host's /dev/tty2 and
   display output on an xterm.  That's a silly example - the most common
   use of this syntax is to reattach the main console to stdin and stdout
   as shown above.
@@ -785,7 +785,7 @@
 
 
 
-  55..33..  EExxaammpplleess
+  5.3.  Examples
 
   There are a number of interesting things you can do with this
   capability.
@@ -838,7 +838,7 @@
   prompt of the other virtual machine.
 
 
-  66..  SSeettttiinngg uupp tthhee nneettwwoorrkk
+  6.  Setting up the network
 
 
 
@@ -858,19 +858,19 @@
   There are currently five transport types available for a UML virtual
   machine to exchange packets with other hosts:
 
-  +o  ethertap
+  o  ethertap
 
-  +o  TUN/TAP
+  o  TUN/TAP
 
-  +o  Multicast
+  o  Multicast
 
-  +o  a switch daemon
+  o  a switch daemon
 
-  +o  slip
+  o  slip
 
-  +o  slirp
+  o  slirp
 
-  +o  pcap
+  o  pcap
 
      The TUN/TAP, ethertap, slip, and slirp transports allow a UML
      instance to exchange packets with the host.  They may be directed
@@ -893,28 +893,28 @@
   With so many host transports, which one should you use?  Here's when
   you should use each one:
 
-  +o  ethertap - if you want access to the host networking and it is
+  o  ethertap - if you want access to the host networking and it is
      running 2.2
 
-  +o  TUN/TAP - if you want access to the host networking and it is
+  o  TUN/TAP - if you want access to the host networking and it is
      running 2.4.  Also, the TUN/TAP transport is able to use a
      preconfigured device, allowing it to avoid using the setuid uml_net
      helper, which is a security advantage.
 
-  +o  Multicast - if you want a purely virtual network and you don't want
+  o  Multicast - if you want a purely virtual network and you don't want
      to set up anything but the UML
 
-  +o  a switch daemon - if you want a purely virtual network and you
+  o  a switch daemon - if you want a purely virtual network and you
      don't mind running the daemon in order to get somewhat better
      performance
 
-  +o  slip - there is no particular reason to run the slip backend unless
+  o  slip - there is no particular reason to run the slip backend unless
      ethertap and TUN/TAP are just not available for some reason
 
-  +o  slirp - if you don't have root access on the host to setup
+  o  slirp - if you don't have root access on the host to setup
      networking, or if you don't want to allocate an IP to your UML
 
-  +o  pcap - not much use for actual network connectivity, but great for
+  o  pcap - not much use for actual network connectivity, but great for
      monitoring traffic on the host
 
      Ethertap is available on 2.4 and works fine.  TUN/TAP is preferred
@@ -926,7 +926,7 @@
      exploit the helper's root privileges.
 
 
-  66..11..  GGeenneerraall sseettuupp
+  6.1.  General setup
 
   First, you must have the virtual network enabled in your UML.  If are
   running a prebuilt kernel from this site, everything is already
@@ -995,7 +995,7 @@
 
 
 
-  66..22..  UUsseerrssppaaccee ddaaeemmoonnss
+  6.2.  Userspace daemons
 
   You will likely need the setuid helper, or the switch daemon, or both.
   They are both installed with the RPM and deb, so if you've installed
@@ -1011,7 +1011,7 @@
 
 
 
-  66..33..  SSppeecciiffyyiinngg eetthheerrnneett aaddddrreesssseess
+  6.3.  Specifying ethernet addresses
 
   Below, you will see that the TUN/TAP, ethertap, and daemon interfaces
   allow you to specify hardware addresses for the virtual ethernet
@@ -1023,11 +1023,11 @@
   sufficient to guarantee a unique hardware address for the device.  A
   couple of exceptions are:
 
-  +o  Another set of virtual ethernet devices are on the same network and
+  o  Another set of virtual ethernet devices are on the same network and
      they are assigned hardware addresses using a different scheme which
      may conflict with the UML IP address-based scheme
 
-  +o  You aren't going to use the device for IP networking, so you don't
+  o  You aren't going to use the device for IP networking, so you don't
      assign the device an IP address
 
      If you let the driver provide the hardware address, you should make
@@ -1049,7 +1049,7 @@
 
 
 
-  66..44..  UUMMLL iinntteerrffaaccee sseettuupp
+  6.4.  UML interface setup
 
   Once the network devices have been described on the command line, you
   should boot UML and log in.
@@ -1131,7 +1131,7 @@
 
 
 
-  66..55..  MMuullttiiccaasstt
+  6.5.  Multicast
 
   The simplest way to set up a virtual network between multiple UMLs is
   to use the mcast transport.  This was written by Harald Welte and is
@@ -1194,7 +1194,7 @@
 
 
 
-  66..66..  TTUUNN//TTAAPP wwiitthh tthhee uummll__nneett hheellppeerr
+  6.6.  TUN/TAP with the uml_net helper
 
   TUN/TAP is the preferred mechanism on 2.4 to exchange packets with the
   host.  The TUN/TAP backend has been in UML since 2.4.9-3um.
@@ -1247,10 +1247,10 @@
   There are a couple potential problems with running the TUN/TAP
   transport on a 2.4 host kernel
 
-  +o  TUN/TAP seems not to work on 2.4.3 and earlier.  Upgrade the host
+  o  TUN/TAP seems not to work on 2.4.3 and earlier.  Upgrade the host
      kernel or use the ethertap transport.
 
-  +o  With an upgraded kernel, TUN/TAP may fail with
+  o  With an upgraded kernel, TUN/TAP may fail with
 
 
        File descriptor in bad state
@@ -1269,7 +1269,7 @@
 
 
 
-  66..77..  TTUUNN//TTAAPP wwiitthh aa pprreeccoonnffiigguurreedd ttaapp ddeevviiccee
+  6.7.  TUN/TAP with a preconfigured tap device
 
   If you prefer not to have UML use uml_net (which is somewhat
   insecure), with UML 2.4.17-11, you can set up a TUN/TAP device
@@ -1277,7 +1277,7 @@
   there is no need for root assistance.  Setting up the device is done
   as follows:
 
-  +o  Create the device with tunctl (available from the UML utilities
+  o  Create the device with tunctl (available from the UML utilities
      tarball)
 
 
@@ -1291,7 +1291,7 @@
   where uid is the user id or username that UML will be run as.  This
   will tell you what device was created.
 
-  +o  Configure the device IP (change IP addresses and device name to
+  o  Configure the device IP (change IP addresses and device name to
      suit)
 
 
@@ -1303,7 +1303,7 @@
 
 
 
-  +o  Set up routing and arping if desired - this is my recipe, there are
+  o  Set up routing and arping if desired - this is my recipe, there are
      other ways of doing the same thing
 
 
@@ -1338,7 +1338,7 @@
   utility which reads the information from a config file and sets up
   devices at boot time.
 
-  +o  Rather than using up two IPs and ARPing for one of them, you can
+  o  Rather than using up two IPs and ARPing for one of them, you can
      also provide direct access to your LAN by the UML by using a
      bridge.
 
@@ -1417,7 +1417,7 @@
   Note that 'br0' should be setup using ifconfig with the existing IP
   address of eth0, as eth0 no longer has its own IP.
 
-  +o
+  o
 
 
      Also, the /dev/net/tun device must be writable by the user running
@@ -1438,11 +1438,11 @@
   devices and chgrp /dev/net/tun to that group with mode 664 or 660.
 
 
-  +o  Once the device is set up, run UML with 'eth0=tuntap,device name'
+  o  Once the device is set up, run UML with 'eth0=tuntap,device name'
      (i.e. 'eth0=tuntap,tap0') on the command line (or do it with the
      mconsole config command).
 
-  +o  Bring the eth device up in UML and you're in business.
+  o  Bring the eth device up in UML and you're in business.
 
      If you don't want that tap device any more, you can make it non-
      persistent with
@@ -1465,7 +1465,7 @@
 
 
 
-  66..88..  EEtthheerrttaapp
+  6.8.  Ethertap
 
   Ethertap is the general mechanism on 2.2 for userspace processes to
   exchange packets with the kernel.
@@ -1561,9 +1561,9 @@
 
 
 
-  66..99..  TThhee sswwiittcchh ddaaeemmoonn
+  6.9.  The switch daemon
 
-  NNoottee: This is the daemon formerly known as uml_router, but which was
+  Note: This is the daemon formerly known as uml_router, but which was
   renamed so the network weenies of the world would stop growling at me.
 
 
@@ -1649,7 +1649,7 @@
 
 
 
-  66..1100..  SSlliipp
+  6.10.  Slip
 
   Slip is another, less general, mechanism for a process to communicate
   with the host networking.  In contrast to the ethertap interface,
@@ -1681,7 +1681,7 @@
 
 
 
-  66..1111..  SSlliirrpp
+  6.11.  Slirp
 
   slirp uses an external program, usually /usr/bin/slirp, to provide IP
   only networking connectivity through the host. This is similar to IP
@@ -1737,7 +1737,7 @@
 
 
 
-  66..1122..  ppccaapp
+  6.12.  pcap
 
   The pcap transport is attached to a UML ethernet device on the command
   line or with uml_mconsole with the following syntax:
@@ -1777,7 +1777,7 @@
 
 
 
-  66..1133..  SSeettttiinngg uupp tthhee hhoosstt yyoouurrsseellff
+  6.13.  Setting up the host yourself
 
   If you don't specify an address for the host side of the ethertap or
   slip device, UML won't do any setup on the host.  So this is what is
@@ -1785,7 +1785,7 @@
   192.168.0.251 and a UML-side IP of 192.168.0.250 - adjust to suit your
   own network):
 
-  +o  The device needs to be configured with its IP address.  Tap devices
+  o  The device needs to be configured with its IP address.  Tap devices
      are also configured with an mtu of 1484.  Slip devices are
      configured with a point-to-point address pointing at the UML ip
      address.
@@ -1805,7 +1805,7 @@
 
 
 
-  +o  If a tap device is being set up, a route is set to the UML IP.
+  o  If a tap device is being set up, a route is set to the UML IP.
 
 
        UML# route add -host 192.168.0.250 gw 192.168.0.251
@@ -1814,7 +1814,7 @@
 
 
 
-  +o  To allow other hosts on your network to see the virtual machine,
+  o  To allow other hosts on your network to see the virtual machine,
      proxy arp is set up for it.
 
 
@@ -1824,7 +1824,7 @@
 
 
 
-  +o  Finally, the host is set up to route packets.
+  o  Finally, the host is set up to route packets.
 
 
        host#  echo 1 > /proc/sys/net/ipv4/ip_forward
@@ -1838,12 +1838,12 @@
 
 
 
-  77..  SShhaarriinngg FFiilleessyysstteemmss bbeettwweeeenn VViirrttuuaall MMaacchhiinneess
+  7.  Sharing Filesystems between Virtual Machines
 
 
 
 
-  77..11..  AA wwaarrnniinngg
+  7.1.  A warning
 
   Don't attempt to share filesystems simply by booting two UMLs from the
   same file.  That's the same thing as booting two physical machines
@@ -1851,7 +1851,7 @@
 
 
 
-  77..22..  UUssiinngg llaayyeerreedd bblloocckk ddeevviicceess
+  7.2.  Using layered block devices
 
   The way to share a filesystem between two virtual machines is to use
   the copy-on-write (COW) layering capability of the ubd block driver.
@@ -1896,7 +1896,7 @@
 
 
 
-  77..33..  NNoottee!!
+  7.3.  Note!
 
   When checking the size of the COW file in order to see the gobs of
   space that you're saving, make sure you use 'ls -ls' to see the actual
@@ -1926,7 +1926,7 @@
 
 
 
-  77..44..  AAnnootthheerr wwaarrnniinngg
+  7.4.  Another warning
 
   Once a filesystem is being used as a readonly backing file for a COW
   file, do not boot directly from it or modify it in any way.  Doing so
@@ -1952,7 +1952,7 @@
 
 
 
-  77..55..  uummll__mmoooo :: MMeerrggiinngg aa CCOOWW ffiillee wwiitthh iittss bbaacckkiinngg ffiillee
+  7.5.  uml_moo : Merging a COW file with its backing file
 
   Depending on how you use UML and COW devices, it may be advisable to
   merge the changes in the COW file into the backing file every once in
@@ -2001,7 +2001,7 @@
 
 
 
-  88..  CCrreeaattiinngg ffiilleessyysstteemmss
+  8.  Creating filesystems
 
 
   You may want to create and mount new UML filesystems, either because
@@ -2015,7 +2015,7 @@
   should be easy to translate to the filesystem of your choice.
 
 
-  88..11..  CCrreeaattee tthhee ffiilleessyysstteemm ffiillee
+  8.1.  Create the filesystem file
 
   dd is your friend.  All you need to do is tell dd to create an empty
   file of the appropriate size.  I usually make it sparse to save time
@@ -2032,7 +2032,7 @@
 
 
 
-  88..22..  AAssssiiggnn tthhee ffiillee ttoo aa UUMMLL ddeevviiccee
+  8.2.  Assign the file to a UML device
 
   Add an argument like the following to the UML command line:
 
@@ -2045,7 +2045,7 @@
 
 
 
-  88..33..  CCrreeaattiinngg aanndd mmoouunnttiinngg tthhee ffiilleessyysstteemm
+  8.3.  Creating and mounting the filesystem
 
   Make sure that the filesystem is available, either by being built into
   the kernel, or available as a module, then boot up UML and log in.  If
@@ -2096,7 +2096,7 @@
 
 
 
-  99..  HHoosstt ffiillee aacccceessss
+  9.  Host file access
 
 
   If you want to access files on the host machine from inside UML, you
@@ -2112,7 +2112,7 @@
   files contained in it just as you would on the host.
 
 
-  99..11..  UUssiinngg hhoossttffss
+  9.1.  Using hostfs
 
   To begin with, make sure that hostfs is available inside the virtual
   machine with
@@ -2151,7 +2151,7 @@
 
 
 
-  99..22..  hhoossttffss aass tthhee rroooott ffiilleessyysstteemm
+  9.2.  hostfs as the root filesystem
 
   It's possible to boot from a directory hierarchy on the host using
   hostfs rather than using the standard filesystem in a file.
@@ -2194,20 +2194,20 @@
   UML should then boot as it does normally.
 
 
-  99..33..  BBuuiillddiinngg hhoossttffss
+  9.3.  Building hostfs
 
   If you need to build hostfs because it's not in your kernel, you have
   two choices:
 
 
 
-  +o  Compiling hostfs into the kernel:
+  o  Compiling hostfs into the kernel:
 
 
      Reconfigure the kernel and set the 'Host filesystem' option under
 
 
-  +o  Compiling hostfs as a module:
+  o  Compiling hostfs as a module:
 
 
      Reconfigure the kernel and set the 'Host filesystem' option under
@@ -2228,7 +2228,7 @@
 
 
 
-  1100..  TThhee MMaannaaggeemmeenntt CCoonnssoollee
+  10.  The Management Console
 
 
 
@@ -2240,15 +2240,15 @@
 
   There are a number of things you can do with the mconsole interface:
 
-  +o  get the kernel version
+  o  get the kernel version
 
-  +o  add and remove devices
+  o  add and remove devices
 
-  +o  halt or reboot the machine
+  o  halt or reboot the machine
 
-  +o  Send SysRq commands
+  o  Send SysRq commands
 
-  +o  Pause and resume the UML
+  o  Pause and resume the UML
 
 
   You need the mconsole client (uml_mconsole) which is present in CVS
@@ -2300,28 +2300,28 @@
 
   You'll get a prompt, at which you can run one of these commands:
 
-  +o  version
+  o  version
 
-  +o  halt
+  o  halt
 
-  +o  reboot
+  o  reboot
 
-  +o  config
+  o  config
 
-  +o  remove
+  o  remove
 
-  +o  sysrq
+  o  sysrq
 
-  +o  help
+  o  help
 
-  +o  cad
+  o  cad
 
-  +o  stop
+  o  stop
 
-  +o  go
+  o  go
 
 
-  1100..11..  vveerrssiioonn
+  10.1.  version
 
   This takes no arguments.  It prints the UML version.
 
@@ -2342,7 +2342,7 @@
 
 
 
-  1100..22..  hhaalltt aanndd rreebboooott
+  10.2.  halt and reboot
 
   These take no arguments.  They shut the machine down immediately, with
   no syncing of disks and no clean shutdown of userspace.  So, they are
@@ -2357,7 +2357,7 @@
 
 
 
-  1100..33..  ccoonnffiigg
+  10.3.  config
 
   "config" adds a new device to the virtual machine.  Currently the ubd
   and network drivers support this.  It takes one argument, which is the
@@ -2378,7 +2378,7 @@
 
 
 
-  1100..44..  rreemmoovvee
+  10.4.  remove
 
   "remove" deletes a device from the system.  Its argument is just the
   name of the device to be removed. The device must be idle in whatever
@@ -2397,7 +2397,7 @@
 
 
 
-  1100..55..  ssyyssrrqq
+  10.5.  sysrq
 
   This takes one argument, which is a single letter.  It calls the
   generic kernel's SysRq driver, which does whatever is called for by
@@ -2407,14 +2407,14 @@
 
 
 
-  1100..66..  hheellpp
+  10.6.  help
 
   "help" returns a string listing the valid commands and what each one
   does.
 
 
 
-  1100..77..  ccaadd
+  10.7.  cad
 
   This invokes the Ctl-Alt-Del action on init.  What exactly this ends
   up doing is up to /etc/inittab.  Normally, it reboots the machine.
@@ -2432,7 +2432,7 @@
 
 
 
-  1100..88..  ssttoopp
+  10.8.  stop
 
   This puts the UML in a loop reading mconsole requests until a 'go'
   mconsole command is received. This is very useful for making backups
@@ -2448,7 +2448,7 @@
 
 
 
-  1100..99..  ggoo
+  10.9.  go
 
   This resumes a UML after being paused by a 'stop' command. Note that
   when the UML has resumed, TCP connections may have timed out and if
@@ -2462,10 +2462,10 @@
 
 
 
-  1111..  KKeerrnneell ddeebbuuggggiinngg
+  11.  Kernel debugging
 
 
-  NNoottee:: The interface that makes debugging, as described here, possible
+  Note: The interface that makes debugging, as described here, possible
   is present in 2.4.0-test6 kernels and later.
 
 
@@ -2485,7 +2485,7 @@
 
 
 
-  1111..11..  SSttaarrttiinngg tthhee kkeerrnneell uunnddeerr ggddbb
+  11.1.  Starting the kernel under gdb
 
   You can have the kernel running under the control of gdb from the
   beginning by putting 'debug' on the command line.  You will get an
@@ -2498,7 +2498,7 @@
   There is a transcript of a debugging session  here <debug-
   session.html> , with breakpoints being set in the scheduler and in an
   interrupt handler.
-  1111..22..  EExxaammiinniinngg sslleeeeppiinngg pprroocceesssseess
+  11.2.  Examining sleeping processes
 
   Not every bug is evident in the currently running process.  Sometimes,
   processes hang in the kernel when they shouldn't because they've
@@ -2516,7 +2516,7 @@
 
   Now what you do is this:
 
-  +o  detach from the current thread
+  o  detach from the current thread
 
 
        (UML gdb)  det
@@ -2525,7 +2525,7 @@
 
 
 
-  +o  attach to the thread you are interested in
+  o  attach to the thread you are interested in
 
 
        (UML gdb)  att <host pid>
@@ -2534,7 +2534,7 @@
 
 
 
-  +o  look at its stack and anything else of interest
+  o  look at its stack and anything else of interest
 
 
        (UML gdb)  bt
@@ -2545,7 +2545,7 @@
   Note that you can't do anything at this point that requires that a
   process execute, e.g. calling a function
 
-  +o  when you're done looking at that process, reattach to the current
+  o  when you're done looking at that process, reattach to the current
      thread and continue it
 
 
@@ -2569,12 +2569,12 @@
 
 
 
-  1111..33..  RRuunnnniinngg dddddd oonn UUMMLL
+  11.3.  Running ddd on UML
 
   ddd works on UML, but requires a special kludge.  The process goes
   like this:
 
-  +o  Start ddd
+  o  Start ddd
 
 
        host% ddd linux
@@ -2583,14 +2583,14 @@
 
 
 
-  +o  With ps, get the pid of the gdb that ddd started.  You can ask the
+  o  With ps, get the pid of the gdb that ddd started.  You can ask the
      gdb to tell you, but for some reason that confuses things and
      causes a hang.
 
-  +o  run UML with 'debug=parent gdb-pid=<pid>' added to the command line
+  o  run UML with 'debug=parent gdb-pid=<pid>' added to the command line
      - it will just sit there after you hit return
 
-  +o  type 'att 1' to the ddd gdb and you will see something like
+  o  type 'att 1' to the ddd gdb and you will see something like
 
 
        0xa013dc51 in __kill ()
@@ -2602,12 +2602,12 @@
 
 
 
-  +o  At this point, type 'c', UML will boot up, and you can use ddd just
+  o  At this point, type 'c', UML will boot up, and you can use ddd just
      as you do on any other process.
 
 
 
-  1111..44..  DDeebbuuggggiinngg mmoodduulleess
+  11.4.  Debugging modules
 
   gdb has support for debugging code which is dynamically loaded into
   the process.  This support is what is needed to debug kernel modules
@@ -2823,7 +2823,7 @@
 
 
 
-  1111..55..  AAttttaacchhiinngg ggddbb ttoo tthhee kkeerrnneell
+  11.5.  Attaching gdb to the kernel
 
   If you don't have the kernel running under gdb, you can attach gdb to
   it later by sending the tracing thread a SIGUSR1.  The first line of
@@ -2857,7 +2857,7 @@
 
 
 
-  1111..66..  UUssiinngg aalltteerrnnaattee ddeebbuuggggeerrss
+  11.6.  Using alternate debuggers
 
   UML has support for attaching to an already running debugger rather
   than starting gdb itself.  This is present in CVS as of 17 Apr 2001.
@@ -2886,7 +2886,7 @@
   An example of an alternate debugger is strace.  You can strace the
   actual kernel as follows:
 
-  +o  Run the following in a shell
+  o  Run the following in a shell
 
 
        host%
@@ -2894,10 +2894,10 @@
 
 
 
-  +o  Run UML with 'debug' and 'gdb-pid=<pid>' with the pid printed out
+  o  Run UML with 'debug' and 'gdb-pid=<pid>' with the pid printed out
      by the previous command
 
-  +o  Hit return in the shell, and UML will start running, and strace
+  o  Hit return in the shell, and UML will start running, and strace
      output will start accumulating in the output file.
 
      Note that this is different from running
@@ -2917,9 +2917,9 @@
 
 
 
-  1122..  KKeerrnneell ddeebbuuggggiinngg eexxaammpplleess
+  12.  Kernel debugging examples
 
-  1122..11..  TThhee ccaassee ooff tthhee hhuunngg ffsscckk
+  12.1.  The case of the hung fsck
 
   When booting up the kernel, fsck failed, and dropped me into a shell
   to fix things up.  I ran fsck -y, which hung:
@@ -3154,9 +3154,9 @@
 
   The interesting things here are :
 
-  +o  There are two segfaults on this stack (frames 9 and 14)
+  o  There are two segfaults on this stack (frames 9 and 14)
 
-  +o  The first faulting address (frame 11) is 0x50000800
+  o  The first faulting address (frame 11) is 0x50000800
 
   (gdb) p (void *)1342179328
   $16 = (void *) 0x50000800
@@ -3399,7 +3399,7 @@
   on will be somewhat clearer.
 
 
-  1122..22..  EEppiissooddee 22:: TThhee ccaassee ooff tthhee hhuunngg ffsscckk
+  12.2.  Episode 2: The case of the hung fsck
 
   After setting a trap in the SEGV handler for accesses to the signal
   thread's stack, I reran the kernel.
@@ -3788,12 +3788,12 @@
 
 
 
-  1133..  WWhhaatt ttoo ddoo wwhheenn UUMMLL ddooeessnn''tt wwoorrkk
+  13.  What to do when UML doesn't work
 
 
 
 
-  1133..11..  SSttrraannggee ccoommppiillaattiioonn eerrrroorrss wwhheenn yyoouu bbuuiilldd ffrroomm ssoouurrccee
+  13.1.  Strange compilation errors when you build from source
 
   As of test11, it is necessary to have "ARCH=um" in the environment or
   on the make command line for all steps in building UML, including
@@ -3824,8 +3824,8 @@
 
 
 
-  1133..33..  AA vvaarriieettyy ooff ppaanniiccss aanndd hhaannggss wwiitthh //ttmmpp oonn aa rreeiisseerrffss  ffiilleessyyss--
-  tteemm
+  13.3.  A variety of panics and hangs with /tmp on a reiserfs  filesys-
+  tem
 
   I saw this on reiserfs 3.5.21 and it seems to be fixed in 3.5.27.
   Panics preceded by
@@ -3842,8 +3842,8 @@
 
 
 
-  1133..44..  TThhee ccoommppiillee ffaaiillss wwiitthh eerrrroorrss aabboouutt ccoonnfflliiccttiinngg ttyyppeess ffoorr
-  ''ooppeenn'',, ''dduupp'',, aanndd ''wwaaiittppiidd''
+  13.4.  The compile fails with errors about conflicting types for
+  'open', 'dup', and 'waitpid'
 
   This happens when you build in /usr/src/linux.  The UML build makes
   the include/asm link point to include/asm-um.  /usr/include/asm points
@@ -3854,14 +3854,14 @@
 
 
 
-  1133..55..  UUMMLL ddooeessnn''tt wwoorrkk wwhheenn //ttmmpp iiss aann NNFFSS ffiilleessyysstteemm
+  13.5.  UML doesn't work when /tmp is an NFS filesystem
 
   This seems to be a similar situation with the ReiserFS problem above.
   Some versions of NFS seems not to handle mmap correctly, which UML
   depends on.  The workaround is have /tmp be a non-NFS directory.
 
 
-  1133..66..  UUMMLL hhaannggss oonn bboooott wwhheenn ccoommppiilleedd wwiitthh ggpprrooff ssuuppppoorrtt
+  13.6.  UML hangs on boot when compiled with gprof support
 
   If you build UML with gprof support and, early in the boot, it does
   this
@@ -3878,7 +3878,7 @@
 
 
 
-  1133..77..  ssyyssllooggdd ddiieess wwiitthh aa SSIIGGTTEERRMM oonn ssttaarrttuupp
+  13.7.  syslogd dies with a SIGTERM on startup
 
   The exact boot error depends on the distribution that you're booting,
   but Debian produces this:
@@ -3897,17 +3897,17 @@
 
 
 
-  1133..88..  TTUUNN//TTAAPP nneettwwoorrkkiinngg ddooeessnn''tt wwoorrkk oonn aa 22..44 hhoosstt
+  13.8.  TUN/TAP networking doesn't work on a 2.4 host
 
   There are a couple of problems which were
   <http://www.geocrawler.com/lists/3/SourceForge/597/0/> name="pointed
   out">  by Tim Robinson <timro at trkr dot net>
 
-  +o  It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier.
+  o  It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier.
      The fix is to upgrade to something more recent and then read the
      next item.
 
-  +o  If you see
+  o  If you see
 
 
        File descriptor in bad state
@@ -3921,8 +3921,8 @@
 
 
 
-  1133..99..  YYoouu ccaann nneettwwoorrkk ttoo tthhee hhoosstt bbuutt nnoott ttoo ootthheerr mmaacchhiinneess oonn tthhee
-  nneett
+  13.9.  You can network to the host but not to other machines on the
+  net
 
   If you can connect to the host, and the host can connect to UML, but
   you cannot connect to any other machines, then you may need to enable
@@ -3972,7 +3972,7 @@
 
 
 
-  1133..1100..  II hhaavvee nnoo rroooott aanndd II wwaanntt ttoo ssccrreeaamm
+  13.10.  I have no root and I want to scream
 
   Thanks to Birgit Wahlich for telling me about this strange one.  It
   turns out that there's a limit of six environment variables on the
@@ -3987,7 +3987,7 @@
 
 
 
-  1133..1111..  UUMMLL bbuuiilldd ccoonnfflliicctt bbeettwweeeenn ppttrraaccee..hh aanndd uuccoonntteexxtt..hh
+  13.11.  UML build conflict between ptrace.h and ucontext.h
 
   On some older systems, /usr/include/asm/ptrace.h and
   /usr/include/sys/ucontext.h define the same names.  So, when they're
@@ -4007,7 +4007,7 @@
 
 
 
-  1133..1122..  TThhee UUMMLL BBooggooMMiippss iiss eexxaaccttllyy hhaallff tthhee hhoosstt''ss BBooggooMMiippss
+  13.12.  The UML BogoMips is exactly half the host's BogoMips
 
   On i386 kernels, there are two ways of running the loop that is used
   to calculate the BogoMips rating, using the TSC if it's there or using
@@ -4019,7 +4019,7 @@
 
 
 
-  1133..1133..  WWhheenn yyoouu rruunn UUMMLL,, iitt iimmmmeeddiiaatteellyy sseeggffaauullttss
+  13.13.  When you run UML, it immediately segfaults
 
   If the host is configured with the 2G/2G address space split, that's
   why.  See ``UML on 2G/2G hosts''  for the details on getting UML to
@@ -4027,7 +4027,7 @@
 
 
 
-  1133..1144..  xxtteerrmmss aappppeeaarr,, tthheenn iimmmmeeddiiaatteellyy ddiissaappppeeaarr
+  13.14.  xterms appear, then immediately disappear
 
   If you're running an up to date kernel with an old release of
   uml_utilities, the port-helper program will not work properly, so
@@ -4039,7 +4039,7 @@
 
 
 
-  1133..1155..  AAnnyy ootthheerr ppaanniicc,, hhaanngg,, oorr ssttrraannggee bbeehhaavviioorr
+  13.15.  Any other panic, hang, or strange behavior
 
   If you're seeing truly strange behavior, such as hangs or panics that
   happen in random places, or you try running the debugger to see what's
@@ -4059,7 +4059,7 @@
 
   If you want to be super-helpful, read ``Diagnosing Problems'' and
   follow the instructions contained therein.
-  1144..  DDiiaaggnnoossiinngg PPrroobblleemmss
+  14.  Diagnosing Problems
 
 
   If you get UML to crash, hang, or otherwise misbehave, you should
@@ -4078,7 +4078,7 @@
   ``Kernel debugging''  UML first.
 
 
-  1144..11..  CCaassee 11 :: NNoorrmmaall kkeerrnneell ppaanniiccss
+  14.1.  Case 1 : Normal kernel panics
 
   The most common case is for a normal thread to panic.  To debug this,
   you will need to run it under the debugger (add 'debug' to the command
@@ -4128,7 +4128,7 @@
   to get that information from the faulting ip.
 
 
-  1144..22..  CCaassee 22 :: TTrraacciinngg tthhrreeaadd ppaanniiccss
+  14.2.  Case 2 : Tracing thread panics
 
   The less common and more painful case is when the tracing thread
   panics.  In this case, the kernel debugger will be useless because it
@@ -4161,7 +4161,7 @@
   backtrace in and wait for our crack debugging team to fix the problem.
 
 
-  1144..33..  CCaassee 33 :: TTrraacciinngg tthhrreeaadd ppaanniiccss ccaauusseedd bbyy ootthheerr tthhrreeaaddss
+  14.3.  Case 3 : Tracing thread panics caused by other threads
 
   However, there are cases where the misbehavior of another thread
   caused the problem.  The most common panic of this type is:
@@ -4227,7 +4227,7 @@
 
 
 
-  1144..44..  CCaassee 44 :: HHaannggss
+  14.4.  Case 4 : Hangs
 
   Hangs seem to be fairly rare, but they sometimes happen.  When a hang
   happens, we need a backtrace from the offending process.  Run the
@@ -4257,7 +4257,7 @@
 
 
 
-  1155..  TThhaannkkss
+  15.  Thanks
 
 
   A number of people have helped this project in various ways, and this
@@ -4274,20 +4274,20 @@
   bookkeeping lapses and I forget about contributions.
 
 
-  1155..11..  CCooddee aanndd DDooccuummeennttaattiioonn
+  15.1.  Code and Documentation
 
   Rusty Russell <rusty at linuxcare.com.au>  -
 
-  +o  wrote the  HOWTO <http://user-mode-
+  o  wrote the  HOWTO <http://user-mode-
      linux.sourceforge.net/UserModeLinux-HOWTO.html>
 
-  +o  prodded me into making this project official and putting it on
+  o  prodded me into making this project official and putting it on
      SourceForge
 
-  +o  came up with the way cool UML logo <http://user-mode-
+  o  came up with the way cool UML logo <http://user-mode-
      linux.sourceforge.net/uml-small.png>
 
-  +o  redid the config process
+  o  redid the config process
 
 
   Peter Moulder <reiter at netspace.net.au>  - Fixed my config and build
@@ -4296,18 +4296,18 @@
 
   Bill Stearns <wstearns at pobox.com>  -
 
-  +o  HOWTO updates
+  o  HOWTO updates
 
-  +o  lots of bug reports
+  o  lots of bug reports
 
-  +o  lots of testing
+  o  lots of testing
 
-  +o  dedicated a box (uml.ists.dartmouth.edu) to support UML development
+  o  dedicated a box (uml.ists.dartmouth.edu) to support UML development
 
-  +o  wrote the mkrootfs script, which allows bootable filesystems of
+  o  wrote the mkrootfs script, which allows bootable filesystems of
      RPM-based distributions to be cranked out
 
-  +o  cranked out a large number of filesystems with said script
+  o  cranked out a large number of filesystems with said script
 
 
   Jim Leu <jleu at mindspring.com>  - Wrote the virtual ethernet driver
@@ -4375,176 +4375,176 @@
 
   David Coulson <http://davidcoulson.net>  -
 
-  +o  Set up the usermodelinux.org <http://usermodelinux.org>  site,
+  o  Set up the usermodelinux.org <http://usermodelinux.org>  site,
      which is a great way of keeping the UML user community on top of
      UML goings-on.
 
-  +o  Site documentation and updates
+  o  Site documentation and updates
 
-  +o  Nifty little UML management daemon  UMLd
+  o  Nifty little UML management daemon  UMLd
      <http://uml.openconsultancy.com/umld/>
 
-  +o  Lots of testing and bug reports
+  o  Lots of testing and bug reports
 
 
 
 
-  1155..22..  FFlluusshhiinngg oouutt bbuuggss
+  15.2.  Flushing out bugs
 
 
 
-  +o  Yuri Pudgorodsky
+  o  Yuri Pudgorodsky
 
-  +o  Gerald Britton
+  o  Gerald Britton
 
-  +o  Ian Wehrman
+  o  Ian Wehrman
 
-  +o  Gord Lamb
+  o  Gord Lamb
 
-  +o  Eugene Koontz
+  o  Eugene Koontz
 
-  +o  John H. Hartman
+  o  John H. Hartman
 
-  +o  Anders Karlsson
+  o  Anders Karlsson
 
-  +o  Daniel Phillips
+  o  Daniel Phillips
 
-  +o  John Fremlin
+  o  John Fremlin
 
-  +o  Rainer Burgstaller
+  o  Rainer Burgstaller
 
-  +o  James Stevenson
+  o  James Stevenson
 
-  +o  Matt Clay
+  o  Matt Clay
 
-  +o  Cliff Jefferies
+  o  Cliff Jefferies
 
-  +o  Geoff Hoff
+  o  Geoff Hoff
 
-  +o  Lennert Buytenhek
+  o  Lennert Buytenhek
 
-  +o  Al Viro
+  o  Al Viro
 
-  +o  Frank Klingenhoefer
+  o  Frank Klingenhoefer
 
-  +o  Livio Baldini Soares
+  o  Livio Baldini Soares
 
-  +o  Jon Burgess
+  o  Jon Burgess
 
-  +o  Petru Paler
+  o  Petru Paler
 
-  +o  Paul
+  o  Paul
 
-  +o  Chris Reahard
+  o  Chris Reahard
 
-  +o  Sverker Nilsson
+  o  Sverker Nilsson
 
-  +o  Gong Su
+  o  Gong Su
 
-  +o  johan verrept
+  o  johan verrept
 
-  +o  Bjorn Eriksson
+  o  Bjorn Eriksson
 
-  +o  Lorenzo Allegrucci
+  o  Lorenzo Allegrucci
 
-  +o  Muli Ben-Yehuda
+  o  Muli Ben-Yehuda
 
-  +o  David Mansfield
+  o  David Mansfield
 
-  +o  Howard Goff
+  o  Howard Goff
 
-  +o  Mike Anderson
+  o  Mike Anderson
 
-  +o  John Byrne
+  o  John Byrne
 
-  +o  Sapan J. Batia
+  o  Sapan J. Batia
 
-  +o  Iris Huang
+  o  Iris Huang
 
-  +o  Jan Hudec
+  o  Jan Hudec
 
-  +o  Voluspa
+  o  Voluspa
 
 
 
 
-  1155..33..  BBuugglleettss aanndd cclleeaann--uuppss
+  15.3.  Buglets and clean-ups
 
 
 
-  +o  Dave Zarzycki
+  o  Dave Zarzycki
 
-  +o  Adam Lazur
+  o  Adam Lazur
 
-  +o  Boria Feigin
+  o  Boria Feigin
 
-  +o  Brian J. Murrell
+  o  Brian J. Murrell
 
-  +o  JS
+  o  JS
 
-  +o  Roman Zippel
+  o  Roman Zippel
 
-  +o  Wil Cooley
+  o  Wil Cooley
 
-  +o  Ayelet Shemesh
+  o  Ayelet Shemesh
 
-  +o  Will Dyson
+  o  Will Dyson
 
-  +o  Sverker Nilsson
+  o  Sverker Nilsson
 
-  +o  dvorak
+  o  dvorak
 
-  +o  v.naga srinivas
+  o  v.naga srinivas
 
-  +o  Shlomi Fish
+  o  Shlomi Fish
 
-  +o  Roger Binns
+  o  Roger Binns
 
-  +o  johan verrept
+  o  johan verrept
 
-  +o  MrChuoi
+  o  MrChuoi
 
-  +o  Peter Cleve
+  o  Peter Cleve
 
-  +o  Vincent Guffens
+  o  Vincent Guffens
 
-  +o  Nathan Scott
+  o  Nathan Scott
 
-  +o  Patrick Caulfield
+  o  Patrick Caulfield
 
-  +o  jbearce
+  o  jbearce
 
-  +o  Catalin Marinas
+  o  Catalin Marinas
 
-  +o  Shane Spencer
+  o  Shane Spencer
 
-  +o  Zou Min
+  o  Zou Min
 
 
-  +o  Ryan Boder
+  o  Ryan Boder
 
-  +o  Lorenzo Colitti
+  o  Lorenzo Colitti
 
-  +o  Gwendal Grignou
+  o  Gwendal Grignou
 
-  +o  Andre' Breiler
+  o  Andre' Breiler
 
-  +o  Tsutomu Yasuda
+  o  Tsutomu Yasuda
 
 
 
-  1155..44..  CCaassee SSttuuddiieess
+  15.4.  Case Studies
 
 
-  +o  Jon Wright
+  o  Jon Wright
 
-  +o  William McEwan
+  o  William McEwan
 
-  +o  Michael Richardson
+  o  Michael Richardson
 
 
 
-  1155..55..  OOtthheerr ccoonnttrriibbuuttiioonnss
+  15.5.  Other contributions
 
 
   Bill Carr <Bill.Carr at compaq.com>  made the Red Hat mkrootfs script
diff --git a/Documentation/virtual/virtio-spec.txt b/Documentation/virtual/virtio-spec.txt
new file mode 100644
index 0000000..a350ae1
--- /dev/null
+++ b/Documentation/virtual/virtio-spec.txt
@@ -0,0 +1,2200 @@
+[Generated file: see http://ozlabs.org/~rusty/virtio-spec/]
+Virtio PCI Card Specification
+v0.9.1 DRAFT
+-
+
+Rusty Russell <rusty@rustcorp.com.au>IBM Corporation (Editor)
+
+2011 August 1.
+
+Purpose and Description
+
+This document describes the specifications of the “virtio” family
+of PCI[LaTeX Command: nomenclature] devices. These are devices
+are found in virtual environments[LaTeX Command: nomenclature],
+yet by design they are not all that different from physical PCI
+devices, and this document treats them as such. This allows the
+guest to use standard PCI drivers and discovery mechanisms.
+
+The purpose of virtio and this specification is that virtual
+environments and guests should have a straightforward, efficient,
+standard and extensible mechanism for virtual devices, rather
+than boutique per-environment or per-OS mechanisms.
+
+  Straightforward: Virtio PCI devices use normal PCI mechanisms
+  of interrupts and DMA which should be familiar to any device
+  driver author. There is no exotic page-flipping or COW
+  mechanism: it's just a PCI device.[footnote:
+This lack of page-sharing implies that the implementation of the
+device (e.g. the hypervisor or host) needs full access to the
+guest memory. Communication with untrusted parties (i.e.
+inter-guest communication) requires copying.
+]
+
+  Efficient: Virtio PCI devices consist of rings of descriptors
+  for input and output, which are neatly separated to avoid cache
+  effects from both guest and device writing to the same cache
+  lines.
+
+  Standard: Virtio PCI makes no assumptions about the environment
+  in which it operates, beyond supporting PCI. In fact the virtio
+  devices specified in the appendices do not require PCI at all:
+  they have been implemented on non-PCI buses.[footnote:
+The Linux implementation further separates the PCI virtio code
+from the specific virtio drivers: these drivers are shared with
+the non-PCI implementations (currently lguest and S/390).
+]
+
+  Extensible: Virtio PCI devices contain feature bits which are
+  acknowledged by the guest operating system during device setup.
+  This allows forwards and backwards compatibility: the device
+  offers all the features it knows about, and the driver
+  acknowledges those it understands and wishes to use.
+
+  Virtqueues
+
+The mechanism for bulk data transport on virtio PCI devices is
+pretentiously called a virtqueue. Each device can have zero or
+more virtqueues: for example, the network device has one for
+transmit and one for receive.
+
+Each virtqueue occupies two or more physically-contiguous pages
+(defined, for the purposes of this specification, as 4096 bytes),
+and consists of three parts:
+
+
++-------------------+-----------------------------------+-----------+
+| Descriptor Table  |   Available Ring     (padding)    | Used Ring |
++-------------------+-----------------------------------+-----------+
+
+
+When the driver wants to send buffers to the device, it puts them
+in one or more slots in the descriptor table, and writes the
+descriptor indices into the available ring. It then notifies the
+device. When the device has finished with the buffers, it writes
+the descriptors into the used ring, and sends an interrupt.
+
+Specification
+
+  PCI Discovery
+
+Any PCI device with Vendor ID 0x1AF4, and Device ID 0x1000
+through 0x103F inclusive is a virtio device[footnote:
+The actual value within this range is ignored
+]. The device must also have a Revision ID of 0 to match this
+specification.
+
+The Subsystem Device ID indicates which virtio device is
+supported by the device. The Subsystem Vendor ID should reflect
+the PCI Vendor ID of the environment (it's currently only used
+for informational purposes by the guest).
+
+
++----------------------+--------------------+---------------+
+| Subsystem Device ID  |   Virtio Device    | Specification |
++----------------------+--------------------+---------------+
++----------------------+--------------------+---------------+
+|          1           |   network card     |  Appendix C   |
++----------------------+--------------------+---------------+
+|          2           |   block device     |  Appendix D   |
++----------------------+--------------------+---------------+
+|          3           |      console       |  Appendix E   |
++----------------------+--------------------+---------------+
+|          4           |  entropy source    |  Appendix F   |
++----------------------+--------------------+---------------+
+|          5           | memory ballooning  |  Appendix G   |
++----------------------+--------------------+---------------+
+|          6           |     ioMemory       |       -       |
++----------------------+--------------------+---------------+
+|          9           |   9P transport     |       -       |
++----------------------+--------------------+---------------+
+
+
+  Device Configuration
+
+To configure the device, we use the first I/O region of the PCI
+device. This contains a virtio header followed by a
+device-specific region.
+
+There may be different widths of accesses to the I/O region; the “
+natural” access method for each field in the virtio header must
+be used (i.e. 32-bit accesses for 32-bit fields, etc), but the
+device-specific region can be accessed using any width accesses,
+and should obtain the same results.
+
+Note that this is possible because while the virtio header is PCI
+(i.e. little) endian, the device-specific region is encoded in
+the native endian of the guest (where such distinction is
+applicable).
+
+  Device Initialization Sequence
+
+We start with an overview of device initialization, then expand
+on the details of the device and how each step is preformed.
+
+  Reset the device. This is not required on initial start up.
+
+  The ACKNOWLEDGE status bit is set: we have noticed the device.
+
+  The DRIVER status bit is set: we know how to drive the device.
+
+  Device-specific setup, including reading the Device Feature
+  Bits, discovery of virtqueues for the device, optional MSI-X
+  setup, and reading and possibly writing the virtio
+  configuration space.
+
+  The subset of Device Feature Bits understood by the driver is
+  written to the device.
+
+  The DRIVER_OK status bit is set.
+
+  The device can now be used (ie. buffers added to the
+  virtqueues)[footnote:
+Historically, drivers have used the device before steps 5 and 6.
+This is only allowed if the driver does not use any features
+which would alter this early use of the device.
+]
+
+If any of these steps go irrecoverably wrong, the guest should
+set the FAILED status bit to indicate that it has given up on the
+device (it can reset the device later to restart if desired).
+
+We now cover the fields required for general setup in detail.
+
+  Virtio Header
+
+The virtio header looks as follows:
+
+
++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+
+| Bits       || 32                  | 32                  | 32       | 16     | 16      | 16      | 8       | 8      |
++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+
+| Read/Write || R                   | R+W                 | R+W      | R      | R+W     | R+W     | R+W     | R      |
++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+
+| Purpose    || Device              | Guest               | Queue    | Queue  | Queue   | Queue   | Device  | ISR    |
+|            || Features bits 0:31  | Features bits 0:31  | Address  | Size   | Select  | Notify  | Status  | Status |
++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+
+
+
+If MSI-X is enabled for the device, two additional fields
+immediately follow this header:
+
+
++------------++----------------+--------+
+| Bits       || 16             | 16     |
+              +----------------+--------+
++------------++----------------+--------+
+| Read/Write || R+W            | R+W    |
++------------++----------------+--------+
+| Purpose    || Configuration  | Queue  |
+| (MSI-X)    || Vector         | Vector |
++------------++----------------+--------+
+
+
+Finally, if feature bits (VIRTIO_F_FEATURES_HI) this is
+immediately followed by two additional fields:
+
+
++------------++----------------------+----------------------
+| Bits       || 32                   | 32
++------------++----------------------+----------------------
+| Read/Write || R                    | R+W
++------------++----------------------+----------------------
+| Purpose    || Device               | Guest
+|            || Features bits 32:63  | Features bits 32:63
++------------++----------------------+----------------------
+
+
+Immediately following these general headers, there may be
+device-specific headers:
+
+
++------------++--------------------+
+| Bits       || Device Specific    |
+              +--------------------+
++------------++--------------------+
+| Read/Write || Device Specific    |
++------------++--------------------+
+| Purpose    || Device Specific... |
+|            ||                    |
++------------++--------------------+
+
+
+  Device Status
+
+The Device Status field is updated by the guest to indicate its
+progress. This provides a simple low-level diagnostic: it's most
+useful to imagine them hooked up to traffic lights on the console
+indicating the status of each device.
+
+The device can be reset by writing a 0 to this field, otherwise
+at least one bit should be set:
+
+  ACKNOWLEDGE (1) Indicates that the guest OS has found the
+  device and recognized it as a valid virtio device.
+
+  DRIVER (2) Indicates that the guest OS knows how to drive the
+  device. Under Linux, drivers can be loadable modules so there
+  may be a significant (or infinite) delay before setting this
+  bit.
+
+  DRIVER_OK (3) Indicates that the driver is set up and ready to
+  drive the device.
+
+  FAILED (8) Indicates that something went wrong in the guest,
+  and it has given up on the device. This could be an internal
+  error, or the driver didn't like the device for some reason, or
+  even a fatal error during device operation. The device must be
+  reset before attempting to re-initialize.
+
+  Feature Bits
+
+The least significant 31 bits of the first configuration field
+indicates the features that the device supports (the high bit is
+reserved, and will be used to indicate the presence of future
+feature bits elsewhere). If more than 31 feature bits are
+supported, the device indicates so by setting feature bit 31 (see
+[cha:Reserved-Feature-Bits]). The bits are allocated as follows:
+
+  0 to 23 Feature bits for the specific device type
+
+  24 to 40 Feature bits reserved for extensions to the queue and
+  feature negotiation mechanisms
+
+  41 to 63 Feature bits reserved for future extensions
+
+For example, feature bit 0 for a network device (i.e. Subsystem
+Device ID 1) indicates that the device supports checksumming of
+packets.
+
+The feature bits are negotiated: the device lists all the
+features it understands in the Device Features field, and the
+guest writes the subset that it understands into the Guest
+Features field. The only way to renegotiate is to reset the
+device.
+
+In particular, new fields in the device configuration header are
+indicated by offering a feature bit, so the guest can check
+before accessing that part of the configuration space.
+
+This allows for forwards and backwards compatibility: if the
+device is enhanced with a new feature bit, older guests will not
+write that feature bit back to the Guest Features field and it
+can go into backwards compatibility mode. Similarly, if a guest
+is enhanced with a feature that the device doesn't support, it
+will not see that feature bit in the Device Features field and
+can go into backwards compatibility mode (or, for poor
+implementations, set the FAILED Device Status bit).
+
+Access to feature bits 32 to 63 is enabled by Guest by setting
+feature bit 31. If this bit is unset, Device must assume that all
+feature bits > 31 are unset.
+
+  Configuration/Queue Vectors
+
+When MSI-X capability is present and enabled in the device
+(through standard PCI configuration space) 4 bytes at byte offset
+20 are used to map configuration change and queue interrupts to
+MSI-X vectors. In this case, the ISR Status field is unused, and
+device specific configuration starts at byte offset 24 in virtio
+header structure. When MSI-X capability is not enabled, device
+specific configuration starts at byte offset 20 in virtio header.
+
+Writing a valid MSI-X Table entry number, 0 to 0x7FF, to one of
+Configuration/Queue Vector registers, maps interrupts triggered
+by the configuration change/selected queue events respectively to
+the corresponding MSI-X vector. To disable interrupts for a
+specific event type, unmap it by writing a special NO_VECTOR
+value:
+
+/* Vector value used to disable MSI for queue */
+
+#define VIRTIO_MSI_NO_VECTOR            0xffff
+
+Reading these registers returns vector mapped to a given event,
+or NO_VECTOR if unmapped. All queue and configuration change
+events are unmapped by default.
+
+Note that mapping an event to vector might require allocating
+internal device resources, and might fail. Devices report such
+failures by returning the NO_VECTOR value when the relevant
+Vector field is read. After mapping an event to vector, the
+driver must verify success by reading the Vector field value: on
+success, the previously written value is returned, and on
+failure, NO_VECTOR is returned. If a mapping failure is detected,
+the driver can retry mapping with fewervectors, or disable MSI-X.
+
+  Virtqueue Configuration
+
+As a device can have zero or more virtqueues for bulk data
+transport (for example, the network driver has two), the driver
+needs to configure them as part of the device-specific
+configuration.
+
+This is done as follows, for each virtqueue a device has:
+
+  Write the virtqueue index (first queue is 0) to the Queue
+  Select field.
+
+  Read the virtqueue size from the Queue Size field, which is
+  always a power of 2. This controls how big the virtqueue is
+  (see below). If this field is 0, the virtqueue does not exist.
+
+  Allocate and zero virtqueue in contiguous physical memory, on a
+  4096 byte alignment. Write the physical address, divided by
+  4096 to the Queue Address field.[footnote:
+The 4096 is based on the x86 page size, but it's also large
+enough to ensure that the separate parts of the virtqueue are on
+separate cache lines.
+]
+
+  Optionally, if MSI-X capability is present and enabled on the
+  device, select a vector to use to request interrupts triggered
+  by virtqueue events. Write the MSI-X Table entry number
+  corresponding to this vector in Queue Vector field. Read the
+  Queue Vector field: on success, previously written value is
+  returned; on failure, NO_VECTOR value is returned.
+
+The Queue Size field controls the total number of bytes required
+for the virtqueue according to the following formula:
+
+#define ALIGN(x) (((x) + 4095) & ~4095)
+
+static inline unsigned vring_size(unsigned int qsz)
+
+{
+
+     return ALIGN(sizeof(struct vring_desc)*qsz + sizeof(u16)*(2
++ qsz))
+
+          + ALIGN(sizeof(struct vring_used_elem)*qsz);
+
+}
+
+This currently wastes some space with padding, but also allows
+future extensions. The virtqueue layout structure looks like this
+(qsz is the Queue Size field, which is a variable, so this code
+won't compile):
+
+struct vring {
+
+    /* The actual descriptors (16 bytes each) */
+
+    struct vring_desc desc[qsz];
+
+
+
+    /* A ring of available descriptor heads with free-running
+index. */
+
+    struct vring_avail avail;
+
+
+
+    // Padding to the next 4096 boundary.
+
+    char pad[];
+
+
+
+    // A ring of used descriptor heads with free-running index.
+
+    struct vring_used used;
+
+};
+
+  A Note on Virtqueue Endianness
+
+Note that the endian of these fields and everything else in the
+virtqueue is the native endian of the guest, not little-endian as
+PCI normally is. This makes for simpler guest code, and it is
+assumed that the host already has to be deeply aware of the guest
+endian so such an “endian-aware” device is not a significant
+issue.
+
+  Descriptor Table
+
+The descriptor table refers to the buffers the guest is using for
+the device. The addresses are physical addresses, and the buffers
+can be chained via the next field. Each descriptor describes a
+buffer which is read-only or write-only, but a chain of
+descriptors can contain both read-only and write-only buffers.
+
+No descriptor chain may be more than 2^32 bytes long in total.struct vring_desc {
+
+    /* Address (guest-physical). */
+
+    u64 addr;
+
+    /* Length. */
+
+    u32 len;
+
+/* This marks a buffer as continuing via the next field. */
+
+#define VRING_DESC_F_NEXT   1
+
+/* This marks a buffer as write-only (otherwise read-only). */
+
+#define VRING_DESC_F_WRITE     2
+
+/* This means the buffer contains a list of buffer descriptors.
+*/
+
+#define VRING_DESC_F_INDIRECT   4
+
+    /* The flags as indicated above. */
+
+    u16 flags;
+
+    /* Next field if flags & NEXT */
+
+    u16 next;
+
+};
+
+The number of descriptors in the table is specified by the Queue
+Size field for this virtqueue.
+
+  <sub:Indirect-Descriptors>Indirect Descriptors
+
+Some devices benefit by concurrently dispatching a large number
+of large requests. The VIRTIO_RING_F_INDIRECT_DESC feature can be
+used to allow this (see [cha:Reserved-Feature-Bits]). To increase
+ring capacity it is possible to store a table of indirect
+descriptors anywhere in memory, and insert a descriptor in main
+virtqueue (with flags&INDIRECT on) that refers to memory buffer
+containing this indirect descriptor table; fields addr and len
+refer to the indirect table address and length in bytes,
+respectively. The indirect table layout structure looks like this
+(len is the length of the descriptor that refers to this table,
+which is a variable, so this code won't compile):
+
+struct indirect_descriptor_table {
+
+    /* The actual descriptors (16 bytes each) */
+
+    struct vring_desc desc[len / 16];
+
+};
+
+The first indirect descriptor is located at start of the indirect
+descriptor table (index 0), additional indirect descriptors are
+chained by next field. An indirect descriptor without next field
+(with flags&NEXT off) signals the end of the indirect descriptor
+table, and transfers control back to the main virtqueue. An
+indirect descriptor can not refer to another indirect descriptor
+table (flags&INDIRECT must be off). A single indirect descriptor
+table can include both read-only and write-only descriptors;
+write-only flag (flags&WRITE) in the descriptor that refers to it
+is ignored.
+
+  Available Ring
+
+The available ring refers to what descriptors we are offering the
+device: it refers to the head of a descriptor chain. The “flags”
+field is currently 0 or 1: 1 indicating that we do not need an
+interrupt when the device consumes a descriptor from the
+available ring. Alternatively, the guest can ask the device to
+delay interrupts until an entry with an index specified by the “
+used_event” field is written in the used ring (equivalently,
+until the idx field in the used ring will reach the value
+used_event + 1). The method employed by the device is controlled
+by the VIRTIO_RING_F_EVENT_IDX feature bit (see [cha:Reserved-Feature-Bits]
+). This interrupt suppression is merely an optimization; it may
+not suppress interrupts entirely.
+
+The “idx” field indicates where we would put the next descriptor
+entry (modulo the ring size). This starts at 0, and increases.
+
+struct vring_avail {
+
+#define VRING_AVAIL_F_NO_INTERRUPT      1
+
+   u16 flags;
+
+   u16 idx;
+
+   u16 ring[qsz]; /* qsz is the Queue Size field read from device
+*/
+
+   u16 used_event;
+
+};
+
+  Used Ring
+
+The used ring is where the device returns buffers once it is done
+with them. The flags field can be used by the device to hint that
+no notification is necessary when the guest adds to the available
+ring. Alternatively, the “avail_event” field can be used by the
+device to hint that no notification is necessary until an entry
+with an index specified by the “avail_event” is written in the
+available ring (equivalently, until the idx field in the
+available ring will reach the value avail_event + 1). The method
+employed by the device is controlled by the guest through the
+VIRTIO_RING_F_EVENT_IDX feature bit (see [cha:Reserved-Feature-Bits]
+). [footnote:
+These fields are kept here because this is the only part of the
+virtqueue written by the device
+].
+
+Each entry in the ring is a pair: the head entry of the
+descriptor chain describing the buffer (this matches an entry
+placed in the available ring by the guest earlier), and the total
+of bytes written into the buffer. The latter is extremely useful
+for guests using untrusted buffers: if you do not know exactly
+how much has been written by the device, you usually have to zero
+the buffer to ensure no data leakage occurs.
+
+/* u32 is used here for ids for padding reasons. */
+
+struct vring_used_elem {
+
+    /* Index of start of used descriptor chain. */
+
+    u32 id;
+
+    /* Total length of the descriptor chain which was used
+(written to) */
+
+    u32 len;
+
+};
+
+
+
+struct vring_used {
+
+#define VRING_USED_F_NO_NOTIFY  1
+
+    u16 flags;
+
+    u16 idx;
+
+    struct vring_used_elem ring[qsz];
+
+    u16 avail_event;
+
+};
+
+  Helpers for Managing Virtqueues
+
+The Linux Kernel Source code contains the definitions above and
+helper routines in a more usable form, in
+include/linux/virtio_ring.h. This was explicitly licensed by IBM
+and Red Hat under the (3-clause) BSD license so that it can be
+freely used by all other projects, and is reproduced (with slight
+variation to remove Linux assumptions) in Appendix A.
+
+  Device Operation
+
+There are two parts to device operation: supplying new buffers to
+the device, and processing used buffers from the device. As an
+example, the virtio network device has two virtqueues: the
+transmit virtqueue and the receive virtqueue. The driver adds
+outgoing (read-only) packets to the transmit virtqueue, and then
+frees them after they are used. Similarly, incoming (write-only)
+buffers are added to the receive virtqueue, and processed after
+they are used.
+
+  Supplying Buffers to The Device
+
+Actual transfer of buffers from the guest OS to the device
+operates as follows:
+
+  Place the buffer(s) into free descriptor(s).
+
+  If there are no free descriptors, the guest may choose to
+    notify the device even if notifications are suppressed (to
+    reduce latency).[footnote:
+The Linux drivers do this only for read-only buffers: for
+write-only buffers, it is assumed that the driver is merely
+trying to keep the receive buffer ring full, and no notification
+of this expected condition is necessary.
+]
+
+  Place the id of the buffer in the next ring entry of the
+  available ring.
+
+  The steps (1) and (2) may be performed repeatedly if batching
+  is possible.
+
+  A memory barrier should be executed to ensure the device sees
+  the updated descriptor table and available ring before the next
+  step.
+
+  The available “idx” field should be increased by the number of
+  entries added to the available ring.
+
+  A memory barrier should be executed to ensure that we update
+  the idx field before checking for notification suppression.
+
+  If notifications are not suppressed, the device should be
+  notified of the new buffers.
+
+Note that the above code does not take precautions against the
+available ring buffer wrapping around: this is not possible since
+the ring buffer is the same size as the descriptor table, so step
+(1) will prevent such a condition.
+
+In addition, the maximum queue size is 32768 (it must be a power
+of 2 which fits in 16 bits), so the 16-bit “idx” value can always
+distinguish between a full and empty buffer.
+
+Here is a description of each stage in more detail.
+
+  Placing Buffers Into The Descriptor Table
+
+A buffer consists of zero or more read-only physically-contiguous
+elements followed by zero or more physically-contiguous
+write-only elements (it must have at least one element). This
+algorithm maps it into the descriptor table:
+
+  for each buffer element, b:
+
+  Get the next free descriptor table entry, d
+
+  Set d.addr to the physical address of the start of b
+
+  Set d.len to the length of b.
+
+  If b is write-only, set d.flags to VRING_DESC_F_WRITE,
+    otherwise 0.
+
+  If there is a buffer element after this:
+
+    Set d.next to the index of the next free descriptor element.
+
+    Set the VRING_DESC_F_NEXT bit in d.flags.
+
+In practice, the d.next fields are usually used to chain free
+descriptors, and a separate count kept to check there are enough
+free descriptors before beginning the mappings.
+
+  Updating The Available Ring
+
+The head of the buffer we mapped is the first d in the algorithm
+above. A naive implementation would do the following:
+
+avail->ring[avail->idx % qsz] = head;
+
+However, in general we can add many descriptors before we update
+the “idx” field (at which point they become visible to the
+device), so we keep a counter of how many we've added:
+
+avail->ring[(avail->idx + added++) % qsz] = head;
+
+  Updating The Index Field
+
+Once the idx field of the virtqueue is updated, the device will
+be able to access the descriptor entries we've created and the
+memory they refer to. This is why a memory barrier is generally
+used before the idx update, to ensure it sees the most up-to-date
+copy.
+
+The idx field always increments, and we let it wrap naturally at
+65536:
+
+avail->idx += added;
+
+  <sub:Notifying-The-Device>Notifying The Device
+
+Device notification occurs by writing the 16-bit virtqueue index
+of this virtqueue to the Queue Notify field of the virtio header
+in the first I/O region of the PCI device. This can be expensive,
+however, so the device can suppress such notifications if it
+doesn't need them. We have to be careful to expose the new idx
+value before checking the suppression flag: it's OK to notify
+gratuitously, but not to omit a required notification. So again,
+we use a memory barrier here before reading the flags or the
+avail_event field.
+
+If the VIRTIO_F_RING_EVENT_IDX feature is not negotiated, and if
+the VRING_USED_F_NOTIFY flag is not set, we go ahead and write to
+the PCI configuration space.
+
+If the VIRTIO_F_RING_EVENT_IDX feature is negotiated, we read the
+avail_event field in the available ring structure. If the
+available index crossed_the avail_event field value since the
+last notification, we go ahead and write to the PCI configuration
+space. The avail_event field wraps naturally at 65536 as well:
+
+(u16)(new_idx - avail_event - 1) < (u16)(new_idx - old_idx)
+
+  <sub:Receiving-Used-Buffers>Receiving Used Buffers From The
+  Device
+
+Once the device has used a buffer (read from or written to it, or
+parts of both, depending on the nature of the virtqueue and the
+device), it sends an interrupt, following an algorithm very
+similar to the algorithm used for the driver to send the device a
+buffer:
+
+  Write the head descriptor number to the next field in the used
+  ring.
+
+  Update the used ring idx.
+
+  Determine whether an interrupt is necessary:
+
+  If the VIRTIO_F_RING_EVENT_IDX feature is not negotiated: check
+    if f the VRING_AVAIL_F_NO_INTERRUPT flag is not set in avail-
+    >flags
+
+  If the VIRTIO_F_RING_EVENT_IDX feature is negotiated: check
+    whether the used index crossed the used_event field value
+    since the last update. The used_event field wraps naturally
+    at 65536 as well:(u16)(new_idx - used_event - 1) < (u16)(new_idx - old_idx)
+
+  If an interrupt is necessary:
+
+  If MSI-X capability is disabled:
+
+    Set the lower bit of the ISR Status field for the device.
+
+    Send the appropriate PCI interrupt for the device.
+
+  If MSI-X capability is enabled:
+
+    Request the appropriate MSI-X interrupt message for the
+      device, Queue Vector field sets the MSI-X Table entry
+      number.
+
+    If Queue Vector field value is NO_VECTOR, no interrupt
+      message is requested for this event.
+
+The guest interrupt handler should:
+
+  If MSI-X capability is disabled: read the ISR Status field,
+  which will reset it to zero. If the lower bit is zero, the
+  interrupt was not for this device. Otherwise, the guest driver
+  should look through the used rings of each virtqueue for the
+  device, to see if any progress has been made by the device
+  which requires servicing.
+
+  If MSI-X capability is enabled: look through the used rings of
+  each virtqueue mapped to the specific MSI-X vector for the
+  device, to see if any progress has been made by the device
+  which requires servicing.
+
+For each ring, guest should then disable interrupts by writing
+VRING_AVAIL_F_NO_INTERRUPT flag in avail structure, if required.
+It can then process used ring entries finally enabling interrupts
+by clearing the VRING_AVAIL_F_NO_INTERRUPT flag or updating the
+EVENT_IDX field in the available structure, Guest should then
+execute a memory barrier, and then recheck the ring empty
+condition. This is necessary to handle the case where, after the
+last check and before enabling interrupts, an interrupt has been
+suppressed by the device:
+
+vring_disable_interrupts(vq);
+
+for (;;) {
+
+    if (vq->last_seen_used != vring->used.idx) {
+
+		vring_enable_interrupts(vq);
+
+		mb();
+
+		if (vq->last_seen_used != vring->used.idx)
+
+			break;
+
+    }
+
+    struct vring_used_elem *e =
+vring.used->ring[vq->last_seen_used%vsz];
+
+    process_buffer(e);
+
+    vq->last_seen_used++;
+
+}
+
+  Dealing With Configuration Changes
+
+Some virtio PCI devices can change the device configuration
+state, as reflected in the virtio header in the PCI configuration
+space. In this case:
+
+  If MSI-X capability is disabled: an interrupt is delivered and
+  the second highest bit is set in the ISR Status field to
+  indicate that the driver should re-examine the configuration
+  space.Note that a single interrupt can indicate both that one
+  or more virtqueue has been used and that the configuration
+  space has changed: even if the config bit is set, virtqueues
+  must be scanned.
+
+  If MSI-X capability is enabled: an interrupt message is
+  requested. The Configuration Vector field sets the MSI-X Table
+  entry number to use. If Configuration Vector field value is
+  NO_VECTOR, no interrupt message is requested for this event.
+
+Creating New Device Types
+
+Various considerations are necessary when creating a new device
+type:
+
+  How Many Virtqueues?
+
+It is possible that a very simple device will operate entirely
+through its configuration space, but most will need at least one
+virtqueue in which it will place requests. A device with both
+input and output (eg. console and network devices described here)
+need two queues: one which the driver fills with buffers to
+receive input, and one which the driver places buffers to
+transmit output.
+
+  What Configuration Space Layout?
+
+Configuration space is generally used for rarely-changing or
+initialization-time parameters. But it is a limited resource, so
+it might be better to use a virtqueue to update configuration
+information (the network device does this for filtering,
+otherwise the table in the config space could potentially be very
+large).
+
+Note that this space is generally the guest's native endian,
+rather than PCI's little-endian.
+
+  What Device Number?
+
+Currently device numbers are assigned quite freely: a simple
+request mail to the author of this document or the Linux
+virtualization mailing list[footnote:
+
+https://lists.linux-foundation.org/mailman/listinfo/virtualization
+] will be sufficient to secure a unique one.
+
+Meanwhile for experimental drivers, use 65535 and work backwards.
+
+  How many MSI-X vectors?
+
+Using the optional MSI-X capability devices can speed up
+interrupt processing by removing the need to read ISR Status
+register by guest driver (which might be an expensive operation),
+reducing interrupt sharing between devices and queues within the
+device, and handling interrupts from multiple CPUs. However, some
+systems impose a limit (which might be as low as 256) on the
+total number of MSI-X vectors that can be allocated to all
+devices. Devices and/or device drivers should take this into
+account, limiting the number of vectors used unless the device is
+expected to cause a high volume of interrupts. Devices can
+control the number of vectors used by limiting the MSI-X Table
+Size or not presenting MSI-X capability in PCI configuration
+space. Drivers can control this by mapping events to as small
+number of vectors as possible, or disabling MSI-X capability
+altogether.
+
+  Message Framing
+
+The descriptors used for a buffer should not effect the semantics
+of the message, except for the total length of the buffer. For
+example, a network buffer consists of a 10 byte header followed
+by the network packet. Whether this is presented in the ring
+descriptor chain as (say) a 10 byte buffer and a 1514 byte
+buffer, or a single 1524 byte buffer, or even three buffers,
+should have no effect.
+
+In particular, no implementation should use the descriptor
+boundaries to determine the size of any header in a request.[footnote:
+The current qemu device implementations mistakenly insist that
+the first descriptor cover the header in these cases exactly, so
+a cautious driver should arrange it so.
+]
+
+  Device Improvements
+
+Any change to configuration space, or new virtqueues, or
+behavioural changes, should be indicated by negotiation of a new
+feature bit. This establishes clarity[footnote:
+Even if it does mean documenting design or implementation
+mistakes!
+] and avoids future expansion problems.
+
+Clusters of functionality which are always implemented together
+can use a single bit, but if one feature makes sense without the
+others they should not be gratuitously grouped together to
+conserve feature bits. We can always extend the spec when the
+first person needs more than 24 feature bits for their device.
+
+[LaTeX Command: printnomenclature]
+
+Appendix A: virtio_ring.h
+
+#ifndef VIRTIO_RING_H
+
+#define VIRTIO_RING_H
+
+/* An interface for efficient virtio implementation.
+
+ *
+
+ * This header is BSD licensed so anyone can use the definitions
+
+ * to implement compatible drivers/servers.
+
+ *
+
+ * Copyright 2007, 2009, IBM Corporation
+
+ * Copyright 2011, Red Hat, Inc
+
+ * All rights reserved.
+
+ *
+
+ * Redistribution and use in source and binary forms, with or
+without
+
+ * modification, are permitted provided that the following
+conditions
+
+ * are met:
+
+ * 1. Redistributions of source code must retain the above
+copyright
+
+ *    notice, this list of conditions and the following
+disclaimer.
+
+ * 2. Redistributions in binary form must reproduce the above
+copyright
+
+ *    notice, this list of conditions and the following
+disclaimer in the
+
+ *    documentation and/or other materials provided with the
+distribution.
+
+ * 3. Neither the name of IBM nor the names of its contributors
+
+ *    may be used to endorse or promote products derived from
+this software
+
+ *    without specific prior written permission.
+
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+CONTRIBUTORS ``AS IS'' AND
+
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+TO, THE
+
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+PARTICULAR PURPOSE
+
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE
+LIABLE
+
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL
+
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS
+
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION)
+
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT
+
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+IN ANY WAY
+
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF
+
+ * SUCH DAMAGE.
+
+ */
+
+
+
+/* This marks a buffer as continuing via the next field. */
+
+#define VRING_DESC_F_NEXT       1
+
+/* This marks a buffer as write-only (otherwise read-only). */
+
+#define VRING_DESC_F_WRITE      2
+
+
+
+/* The Host uses this in used->flags to advise the Guest: don't
+kick me
+
+ * when you add a buffer.  It's unreliable, so it's simply an
+
+ * optimization.  Guest will still kick if it's out of buffers.
+*/
+
+#define VRING_USED_F_NO_NOTIFY  1
+
+/* The Guest uses this in avail->flags to advise the Host: don't
+
+ * interrupt me when you consume a buffer.  It's unreliable, so
+it's
+
+ * simply an optimization.  */
+
+#define VRING_AVAIL_F_NO_INTERRUPT      1
+
+
+
+/* Virtio ring descriptors: 16 bytes.
+
+ * These can chain together via "next". */
+
+struct vring_desc {
+
+        /* Address (guest-physical). */
+
+        uint64_t addr;
+
+        /* Length. */
+
+        uint32_t len;
+
+        /* The flags as indicated above. */
+
+        uint16_t flags;
+
+        /* We chain unused descriptors via this, too */
+
+        uint16_t next;
+
+};
+
+
+
+struct vring_avail {
+
+        uint16_t flags;
+
+        uint16_t idx;
+
+        uint16_t ring[];
+
+        uint16_t used_event;
+
+};
+
+
+
+/* u32 is used here for ids for padding reasons. */
+
+struct vring_used_elem {
+
+        /* Index of start of used descriptor chain. */
+
+        uint32_t id;
+
+        /* Total length of the descriptor chain which was written
+to. */
+
+        uint32_t len;
+
+};
+
+
+
+struct vring_used {
+
+        uint16_t flags;
+
+        uint16_t idx;
+
+        struct vring_used_elem ring[];
+
+        uint16_t avail_event;
+
+};
+
+
+
+struct vring {
+
+        unsigned int num;
+
+
+
+        struct vring_desc *desc;
+
+        struct vring_avail *avail;
+
+        struct vring_used *used;
+
+};
+
+
+
+/* The standard layout for the ring is a continuous chunk of
+memory which
+
+ * looks like this.  We assume num is a power of 2.
+
+ *
+
+ * struct vring {
+
+ *      // The actual descriptors (16 bytes each)
+
+ *      struct vring_desc desc[num];
+
+ *
+
+ *      // A ring of available descriptor heads with free-running
+index.
+
+ *      __u16 avail_flags;
+
+ *      __u16 avail_idx;
+
+ *      __u16 available[num];
+
+ *
+
+ *      // Padding to the next align boundary.
+
+ *      char pad[];
+
+ *
+
+ *      // A ring of used descriptor heads with free-running
+index.
+
+ *      __u16 used_flags;
+
+ *      __u16 EVENT_IDX;
+
+ *      struct vring_used_elem used[num];
+
+ * };
+
+ * Note: for virtio PCI, align is 4096.
+
+ */
+
+static inline void vring_init(struct vring *vr, unsigned int num,
+void *p,
+
+                              unsigned long align)
+
+{
+
+        vr->num = num;
+
+        vr->desc = p;
+
+        vr->avail = p + num*sizeof(struct vring_desc);
+
+        vr->used = (void *)(((unsigned long)&vr->avail->ring[num]
+
+                              + align-1)
+
+                            & ~(align - 1));
+
+}
+
+
+
+static inline unsigned vring_size(unsigned int num, unsigned long
+align)
+
+{
+
+        return ((sizeof(struct vring_desc)*num +
+sizeof(uint16_t)*(2+num)
+
+                 + align - 1) & ~(align - 1))
+
+                + sizeof(uint16_t)*3 + sizeof(struct
+vring_used_elem)*num;
+
+}
+
+
+
+static inline int vring_need_event(uint16_t event_idx, uint16_t
+new_idx, uint16_t old_idx)
+
+{
+
+         return (uint16_t)(new_idx - event_idx - 1) <
+(uint16_t)(new_idx - old_idx);
+
+}
+
+#endif /* VIRTIO_RING_H */
+
+<cha:Reserved-Feature-Bits>Appendix B: Reserved Feature Bits
+
+Currently there are five device-independent feature bits defined:
+
+  VIRTIO_F_NOTIFY_ON_EMPTY (24) Negotiating this feature
+  indicates that the driver wants an interrupt if the device runs
+  out of available descriptors on a virtqueue, even though
+  interrupts are suppressed using the VRING_AVAIL_F_NO_INTERRUPT
+  flag or the used_event field. An example of this is the
+  networking driver: it doesn't need to know every time a packet
+  is transmitted, but it does need to free the transmitted
+  packets a finite time after they are transmitted. It can avoid
+  using a timer if the device interrupts it when all the packets
+  are transmitted.
+
+  VIRTIO_F_RING_INDIRECT_DESC (28) Negotiating this feature
+  indicates that the driver can use descriptors with the
+  VRING_DESC_F_INDIRECT flag set, as described in [sub:Indirect-Descriptors]
+  .
+
+  VIRTIO_F_RING_EVENT_IDX(29) This feature enables the used_event
+  and the avail_event fields. If set, it indicates that the
+  device should ignore the flags field in the available ring
+  structure. Instead, the used_event field in this structure is
+  used by guest to suppress device interrupts. Further, the
+  driver should ignore the flags field in the used ring
+  structure. Instead, the avail_event field in this structure is
+  used by the device to suppress notifications. If unset, the
+  driver should ignore the used_event field; the device should
+  ignore the avail_event field; the flags field is used
+
+  VIRTIO_F_BAD_FEATURE(30) This feature should never be
+  negotiated by the guest; doing so is an indication that the
+  guest is faulty[footnote:
+An experimental virtio PCI driver contained in Linux version
+2.6.25 had this problem, and this feature bit can be used to
+detect it.
+]
+
+  VIRTIO_F_FEATURES_HIGH(31) This feature indicates that the
+  device supports feature bits 32:63. If unset, feature bits
+  32:63 are unset.
+
+Appendix C: Network Device
+
+The virtio network device is a virtual ethernet card, and is the
+most complex of the devices supported so far by virtio. It has
+enhanced rapidly and demonstrates clearly how support for new
+features should be added to an existing device. Empty buffers are
+placed in one virtqueue for receiving packets, and outgoing
+packets are enqueued into another for transmission in that order.
+A third command queue is used to control advanced filtering
+features.
+
+  Configuration
+
+  Subsystem Device ID 1
+
+  Virtqueues 0:receiveq. 1:transmitq. 2:controlq[footnote:
+Only if VIRTIO_NET_F_CTRL_VQ set
+]
+
+  Feature bits
+
+  VIRTIO_NET_F_CSUM (0) Device handles packets with partial
+    checksum
+
+  VIRTIO_NET_F_GUEST_CSUM (1) Guest handles packets with partial
+    checksum
+
+  VIRTIO_NET_F_MAC (5) Device has given MAC address.
+
+  VIRTIO_NET_F_GSO (6) (Deprecated) device handles packets with
+    any GSO type.[footnote:
+It was supposed to indicate segmentation offload support, but
+upon further investigation it became clear that multiple bits
+were required.
+]
+
+  VIRTIO_NET_F_GUEST_TSO4 (7) Guest can receive TSOv4.
+
+  VIRTIO_NET_F_GUEST_TSO6 (8) Guest can receive TSOv6.
+
+  VIRTIO_NET_F_GUEST_ECN (9) Guest can receive TSO with ECN.
+
+  VIRTIO_NET_F_GUEST_UFO (10) Guest can receive UFO.
+
+  VIRTIO_NET_F_HOST_TSO4 (11) Device can receive TSOv4.
+
+  VIRTIO_NET_F_HOST_TSO6 (12) Device can receive TSOv6.
+
+  VIRTIO_NET_F_HOST_ECN (13) Device can receive TSO with ECN.
+
+  VIRTIO_NET_F_HOST_UFO (14) Device can receive UFO.
+
+  VIRTIO_NET_F_MRG_RXBUF (15) Guest can merge receive buffers.
+
+  VIRTIO_NET_F_STATUS (16) Configuration status field is
+    available.
+
+  VIRTIO_NET_F_CTRL_VQ (17) Control channel is available.
+
+  VIRTIO_NET_F_CTRL_RX (18) Control channel RX mode support.
+
+  VIRTIO_NET_F_CTRL_VLAN (19) Control channel VLAN filtering.
+
+  Device configuration layout Two configuration fields are
+  currently defined. The mac address field always exists (though
+  is only valid if VIRTIO_NET_F_MAC is set), and the status field
+  only exists if VIRTIO_NET_F_STATUS is set. Only one bit is
+  currently defined for the status field: VIRTIO_NET_S_LINK_UP. #define VIRTIO_NET_S_LINK_UP	1
+
+
+
+struct virtio_net_config {
+
+    u8 mac[6];
+
+    u16 status;
+
+};
+
+  Device Initialization
+
+  The initialization routine should identify the receive and
+  transmission virtqueues.
+
+  If the VIRTIO_NET_F_MAC feature bit is set, the configuration
+  space “mac” entry indicates the “physical” address of the the
+  network card, otherwise a private MAC address should be
+  assigned. All guests are expected to negotiate this feature if
+  it is set.
+
+  If the VIRTIO_NET_F_CTRL_VQ feature bit is negotiated, identify
+  the control virtqueue.
+
+  If the VIRTIO_NET_F_STATUS feature bit is negotiated, the link
+  status can be read from the bottom bit of the “status” config
+  field. Otherwise, the link should be assumed active.
+
+  The receive virtqueue should be filled with receive buffers.
+  This is described in detail below in “Setting Up Receive
+  Buffers”.
+
+  A driver can indicate that it will generate checksumless
+  packets by negotating the VIRTIO_NET_F_CSUM feature. This “
+  checksum offload” is a common feature on modern network cards.
+
+  If that feature is negotiated, a driver can use TCP or UDP
+  segmentation offload by negotiating the VIRTIO_NET_F_HOST_TSO4
+  (IPv4 TCP), VIRTIO_NET_F_HOST_TSO6 (IPv6 TCP) and
+  VIRTIO_NET_F_HOST_UFO (UDP fragmentation) features. It should
+  not send TCP packets requiring segmentation offload which have
+  the Explicit Congestion Notification bit set, unless the
+  VIRTIO_NET_F_HOST_ECN feature is negotiated.[footnote:
+This is a common restriction in real, older network cards.
+]
+
+  The converse features are also available: a driver can save the
+  virtual device some work by negotiating these features.[footnote:
+For example, a network packet transported between two guests on
+the same system may not require checksumming at all, nor
+segmentation, if both guests are amenable.
+] The VIRTIO_NET_F_GUEST_CSUM feature indicates that partially
+  checksummed packets can be received, and if it can do that then
+  the VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
+  VIRTIO_NET_F_GUEST_UFO and VIRTIO_NET_F_GUEST_ECN are the input
+  equivalents of the features described above. See “Receiving
+  Packets” below.
+
+  Device Operation
+
+Packets are transmitted by placing them in the transmitq, and
+buffers for incoming packets are placed in the receiveq. In each
+case, the packet itself is preceeded by a header:
+
+struct virtio_net_hdr {
+
+#define VIRTIO_NET_HDR_F_NEEDS_CSUM    1
+
+	u8 flags;
+
+#define VIRTIO_NET_HDR_GSO_NONE        0
+
+#define VIRTIO_NET_HDR_GSO_TCPV4       1
+
+#define VIRTIO_NET_HDR_GSO_UDP		 3
+
+#define VIRTIO_NET_HDR_GSO_TCPV6       4
+
+#define VIRTIO_NET_HDR_GSO_ECN      0x80
+
+	u8 gso_type;
+
+	u16 hdr_len;
+
+	u16 gso_size;
+
+	u16 csum_start;
+
+	u16 csum_offset;
+
+/* Only if VIRTIO_NET_F_MRG_RXBUF: */
+
+	u16 num_buffers
+
+};
+
+The controlq is used to control device features such as
+filtering.
+
+  Packet Transmission
+
+Transmitting a single packet is simple, but varies depending on
+the different features the driver negotiated.
+
+  If the driver negotiated VIRTIO_NET_F_CSUM, and the packet has
+  not been fully checksummed, then the virtio_net_hdr's fields
+  are set as follows. Otherwise, the packet must be fully
+  checksummed, and flags is zero.
+
+  flags has the VIRTIO_NET_HDR_F_NEEDS_CSUM set,
+
+  <ite:csum_start-is-set>csum_start is set to the offset within
+    the packet to begin checksumming, and
+
+  csum_offset indicates how many bytes after the csum_start the
+    new (16 bit ones' complement) checksum should be placed.[footnote:
+For example, consider a partially checksummed TCP (IPv4) packet.
+It will have a 14 byte ethernet header and 20 byte IP header
+followed by the TCP header (with the TCP checksum field 16 bytes
+into that header). csum_start will be 14+20 = 34 (the TCP
+checksum includes the header), and csum_offset will be 16. The
+value in the TCP checksum field will be the sum of the TCP pseudo
+header, so that replacing it by the ones' complement checksum of
+the TCP header and body will give the correct result.
+]
+
+  <enu:If-the-driver>If the driver negotiated
+  VIRTIO_NET_F_HOST_TSO4, TSO6 or UFO, and the packet requires
+  TCP segmentation or UDP fragmentation, then the “gso_type”
+  field is set to VIRTIO_NET_HDR_GSO_TCPV4, TCPV6 or UDP.
+  (Otherwise, it is set to VIRTIO_NET_HDR_GSO_NONE). In this
+  case, packets larger than 1514 bytes can be transmitted: the
+  metadata indicates how to replicate the packet header to cut it
+  into smaller packets. The other gso fields are set:
+
+  hdr_len is a hint to the device as to how much of the header
+    needs to be kept to copy into each packet, usually set to the
+    length of the headers, including the transport header.[footnote:
+Due to various bugs in implementations, this field is not useful
+as a guarantee of the transport header size.
+]
+
+  gso_size is the size of the packet beyond that header (ie.
+    MSS).
+
+  If the driver negotiated the VIRTIO_NET_F_HOST_ECN feature, the
+    VIRTIO_NET_HDR_GSO_ECN bit may be set in “gso_type” as well,
+    indicating that the TCP packet has the ECN bit set.[footnote:
+This case is not handled by some older hardware, so is called out
+specifically in the protocol.
+]
+
+  If the driver negotiated the VIRTIO_NET_F_MRG_RXBUF feature,
+  the num_buffers field is set to zero.
+
+  The header and packet are added as one output buffer to the
+  transmitq, and the device is notified of the new entry (see [sub:Notifying-The-Device]
+  ).[footnote:
+Note that the header will be two bytes longer for the
+VIRTIO_NET_F_MRG_RXBUF case.
+]
+
+  Packet Transmission Interrupt
+
+Often a driver will suppress transmission interrupts using the
+VRING_AVAIL_F_NO_INTERRUPT flag (see [sub:Receiving-Used-Buffers]
+) and check for used packets in the transmit path of following
+packets. However, it will still receive interrupts if the
+VIRTIO_F_NOTIFY_ON_EMPTY feature is negotiated, indicating that
+the transmission queue is completely emptied.
+
+The normal behavior in this interrupt handler is to retrieve and
+new descriptors from the used ring and free the corresponding
+headers and packets.
+
+  Setting Up Receive Buffers
+
+It is generally a good idea to keep the receive virtqueue as
+fully populated as possible: if it runs out, network performance
+will suffer.
+
+If the VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6 or
+VIRTIO_NET_F_GUEST_UFO features are used, the Guest will need to
+accept packets of up to 65550 bytes long (the maximum size of a
+TCP or UDP packet, plus the 14 byte ethernet header), otherwise
+1514 bytes. So unless VIRTIO_NET_F_MRG_RXBUF is negotiated, every
+buffer in the receive queue needs to be at least this length [footnote:
+Obviously each one can be split across multiple descriptor
+elements.
+].
+
+If VIRTIO_NET_F_MRG_RXBUF is negotiated, each buffer must be at
+least the size of the struct virtio_net_hdr.
+
+  Packet Receive Interrupt
+
+When a packet is copied into a buffer in the receiveq, the
+optimal path is to disable further interrupts for the receiveq
+(see [sub:Receiving-Used-Buffers]) and process packets until no
+more are found, then re-enable them.
+
+Processing packet involves:
+
+  If the driver negotiated the VIRTIO_NET_F_MRG_RXBUF feature,
+  then the “num_buffers” field indicates how many descriptors
+  this packet is spread over (including this one). This allows
+  receipt of large packets without having to allocate large
+  buffers. In this case, there will be at least “num_buffers” in
+  the used ring, and they should be chained together to form a
+  single packet. The other buffers will not begin with a struct
+  virtio_net_hdr.
+
+  If the VIRTIO_NET_F_MRG_RXBUF feature was not negotiated, or
+  the “num_buffers” field is one, then the entire packet will be
+  contained within this buffer, immediately following the struct
+  virtio_net_hdr.
+
+  If the VIRTIO_NET_F_GUEST_CSUM feature was negotiated, the
+  VIRTIO_NET_HDR_F_NEEDS_CSUM bit in the “flags” field may be
+  set: if so, the checksum on the packet is incomplete and the “
+  csum_start” and “csum_offset” fields indicate how to calculate
+  it (see [ite:csum_start-is-set]).
+
+  If the VIRTIO_NET_F_GUEST_TSO4, TSO6 or UFO options were
+  negotiated, then the “gso_type” may be something other than
+  VIRTIO_NET_HDR_GSO_NONE, and the “gso_size” field indicates the
+  desired MSS (see [enu:If-the-driver]).Control Virtqueue
+
+The driver uses the control virtqueue (if VIRTIO_NET_F_VTRL_VQ is
+negotiated) to send commands to manipulate various features of
+the device which would not easily map into the configuration
+space.
+
+All commands are of the following form:
+
+struct virtio_net_ctrl {
+
+	u8 class;
+
+	u8 command;
+
+	u8 command-specific-data[];
+
+	u8 ack;
+
+};
+
+
+
+/* ack values */
+
+#define VIRTIO_NET_OK     0
+
+#define VIRTIO_NET_ERR    1
+
+The class, command and command-specific-data are set by the
+driver, and the device sets the ack byte. There is little it can
+do except issue a diagnostic if the ack byte is not
+VIRTIO_NET_OK.
+
+  Packet Receive Filtering
+
+If the VIRTIO_NET_F_CTRL_RX feature is negotiated, the driver can
+send control commands for promiscuous mode, multicast receiving,
+and filtering of MAC addresses.
+
+Note that in general, these commands are best-effort: unwanted
+packets may still arrive.
+
+  Setting Promiscuous Mode
+
+#define VIRTIO_NET_CTRL_RX    0
+
+ #define VIRTIO_NET_CTRL_RX_PROMISC      0
+
+ #define VIRTIO_NET_CTRL_RX_ALLMULTI     1
+
+The class VIRTIO_NET_CTRL_RX has two commands:
+VIRTIO_NET_CTRL_RX_PROMISC turns promiscuous mode on and off, and
+VIRTIO_NET_CTRL_RX_ALLMULTI turns all-multicast receive on and
+off. The command-specific-data is one byte containing 0 (off) or
+1 (on).
+
+  Setting MAC Address Filtering
+
+struct virtio_net_ctrl_mac {
+
+	u32 entries;
+
+	u8 macs[entries][ETH_ALEN];
+
+};
+
+
+
+#define VIRTIO_NET_CTRL_MAC    1
+
+ #define VIRTIO_NET_CTRL_MAC_TABLE_SET        0
+
+The device can filter incoming packets by any number of
+destination MAC addresses.[footnote:
+Since there are no guarentees, it can use a hash filter
+orsilently switch to allmulti or promiscuous mode if it is given
+too many addresses.
+] This table is set using the class VIRTIO_NET_CTRL_MAC and the
+command VIRTIO_NET_CTRL_MAC_TABLE_SET. The command-specific-data
+is two variable length tables of 6-byte MAC addresses. The first
+table contains unicast addresses, and the second contains
+multicast addresses.
+
+  VLAN Filtering
+
+If the driver negotiates the VIRTION_NET_F_CTRL_VLAN feature, it
+can control a VLAN filter table in the device.
+
+#define VIRTIO_NET_CTRL_VLAN       2
+
+ #define VIRTIO_NET_CTRL_VLAN_ADD             0
+
+ #define VIRTIO_NET_CTRL_VLAN_DEL             1
+
+Both the VIRTIO_NET_CTRL_VLAN_ADD and VIRTIO_NET_CTRL_VLAN_DEL
+command take a 16-bit VLAN id as the command-specific-data.
+
+Appendix D: Block Device
+
+The virtio block device is a simple virtual block device (ie.
+disk). Read and write requests (and other exotic requests) are
+placed in the queue, and serviced (probably out of order) by the
+device except where noted.
+
+  Configuration
+
+  Subsystem Device ID 2
+
+  Virtqueues 0:requestq.
+
+  Feature bits
+
+  VIRTIO_BLK_F_BARRIER (0) Host supports request barriers.
+
+  VIRTIO_BLK_F_SIZE_MAX (1) Maximum size of any single segment is
+    in “size_max”.
+
+  VIRTIO_BLK_F_SEG_MAX (2) Maximum number of segments in a
+    request is in “seg_max”.
+
+  VIRTIO_BLK_F_GEOMETRY (4) Disk-style geometry specified in “
+    geometry”.
+
+  VIRTIO_BLK_F_RO (5) Device is read-only.
+
+  VIRTIO_BLK_F_BLK_SIZE (6) Block size of disk is in “blk_size”.
+
+  VIRTIO_BLK_F_SCSI (7) Device supports scsi packet commands.
+
+  VIRTIO_BLK_F_FLUSH (9) Cache flush command support.
+
+
+
+  Device configuration layout The capacity of the device
+  (expressed in 512-byte sectors) is always present. The
+  availability of the others all depend on various feature bits
+  as indicated above. struct virtio_blk_config {
+
+	u64 capacity;
+
+	u32 size_max;
+
+	u32 seg_max;
+
+	struct virtio_blk_geometry {
+
+		u16 cylinders;
+
+		u8 heads;
+
+		u8 sectors;
+
+	} geometry;
+
+	u32 blk_size;
+
+
+
+};
+
+  Device Initialization
+
+  The device size should be read from the “capacity”
+  configuration field. No requests should be submitted which goes
+  beyond this limit.
+
+  If the VIRTIO_BLK_F_BLK_SIZE feature is negotiated, the
+  blk_size field can be read to determine the optimal sector size
+  for the driver to use. This does not effect the units used in
+  the protocol (always 512 bytes), but awareness of the correct
+  value can effect performance.
+
+  If the VIRTIO_BLK_F_RO feature is set by the device, any write
+  requests will fail.
+
+
+
+  Device Operation
+
+The driver queues requests to the virtqueue, and they are used by
+the device (not necessarily in order). Each request is of form:
+
+struct virtio_blk_req {
+
+
+
+	u32 type;
+
+	u32 ioprio;
+
+	u64 sector;
+
+	char data[][512];
+
+	u8 status;
+
+};
+
+If the device has VIRTIO_BLK_F_SCSI feature, it can also support
+scsi packet command requests, each of these requests is of form:struct virtio_scsi_pc_req {
+
+	u32 type;
+
+	u32 ioprio;
+
+	u64 sector;
+
+    char cmd[];
+
+	char data[][512];
+
+#define SCSI_SENSE_BUFFERSIZE   96
+
+    u8 sense[SCSI_SENSE_BUFFERSIZE];
+
+    u32 errors;
+
+    u32 data_len;
+
+    u32 sense_len;
+
+    u32 residual;
+
+	u8 status;
+
+};
+
+The type of the request is either a read (VIRTIO_BLK_T_IN), a
+write (VIRTIO_BLK_T_OUT), a scsi packet command
+(VIRTIO_BLK_T_SCSI_CMD or VIRTIO_BLK_T_SCSI_CMD_OUT[footnote:
+the SCSI_CMD and SCSI_CMD_OUT types are equivalent, the device
+does not distinguish between them
+]) or a flush (VIRTIO_BLK_T_FLUSH or VIRTIO_BLK_T_FLUSH_OUT[footnote:
+the FLUSH and FLUSH_OUT types are equivalent, the device does not
+distinguish between them
+]). If the device has VIRTIO_BLK_F_BARRIER feature the high bit
+(VIRTIO_BLK_T_BARRIER) indicates that this request acts as a
+barrier and that all preceeding requests must be complete before
+this one, and all following requests must not be started until
+this is complete. Note that a barrier does not flush caches in
+the underlying backend device in host, and thus does not serve as
+data consistency guarantee. Driver must use FLUSH request to
+flush the host cache.
+
+#define VIRTIO_BLK_T_IN           0
+
+#define VIRTIO_BLK_T_OUT          1
+
+#define VIRTIO_BLK_T_SCSI_CMD     2
+
+#define VIRTIO_BLK_T_SCSI_CMD_OUT 3
+
+#define VIRTIO_BLK_T_FLUSH        4
+
+#define VIRTIO_BLK_T_FLUSH_OUT    5
+
+#define VIRTIO_BLK_T_BARRIER	 0x80000000
+
+The ioprio field is a hint about the relative priorities of
+requests to the device: higher numbers indicate more important
+requests.
+
+The sector number indicates the offset (multiplied by 512) where
+the read or write is to occur. This field is unused and set to 0
+for scsi packet commands and for flush commands.
+
+The cmd field is only present for scsi packet command requests,
+and indicates the command to perform. This field must reside in a
+single, separate read-only buffer; command length can be derived
+from the length of this buffer.
+
+Note that these first three (four for scsi packet commands)
+fields are always read-only: the data field is either read-only
+or write-only, depending on the request. The size of the read or
+write can be derived from the total size of the request buffers.
+
+The sense field is only present for scsi packet com