303 files changed, 15379 insertions, 3756 deletions
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 06b982affe76..dd10b51b4e65 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -250,6 +250,8 @@ numastat.txt
        - info on how to read Numa policy hit/miss statistics in sysfs.
 oops-tracing.txt
        - how to decode those nasty internal kernel error dump messages.
+padata.txt
+        - An introduction to the "padata" parallel execution API
 parisc/
        - directory with info on using Linux on PA-RISC architecture.
 parport.txt
diff --git a/Documentation/ABI/obsolete/sysfs-bus-usb b/Documentation/ABI/obsolete/sysfs-bus-usb
new file mode 100644
index 000000000000..bd096d33fbc7
--- /dev/null
+++ b/Documentation/ABI/obsolete/sysfs-bus-usb
@@ -0,0 +1,31 @@
+What:           /sys/bus/usb/devices/.../power/level
+Date:           March 2007
+KernelVersion:  2.6.21
+Contact:        Alan Stern <stern@rowland.harvard.edu>
+Description:
+                Each USB device directory will contain a file named
+                power/level.  This file holds a power-level setting for
+                the device, either "on" or "auto".
+                "on" means that the device is not allowed to autosuspend,
+                although normal suspends for system sleep will still
+                be honored.  "auto" means the device will autosuspend
+                and autoresume in the usual manner, according to the
+                capabilities of its driver.
+                During normal use, devices should be left in the "auto"
+                level.  The "on" level is meant for administrative uses.
+                If you want to suspend a device immediately but leave it
+                free to wake up in response to I/O requests, you should
+                write "0" to power/autosuspend.
+                Device not capable of proper suspend and resume should be
+                left in the "on" level.  Although the USB spec requires
+                devices to support suspend/resume, many of them do not.
+                In fact so many don't that by default, the USB core
+                initializes all non-hub devices in the "on" level.  Some
+                drivers may change this setting when they are bound.
+                This file is deprecated and will be removed after 2010.
+                Use the power/control file instead; it does exactly the
+                same thing.
diff --git a/Documentation/ABI/obsolete/sysfs-class-rfkill b/Documentation/ABI/obsolete/sysfs-class-rfkill
new file mode 100644
index 000000000000..4201d5b05515
--- /dev/null
+++ b/Documentation/ABI/obsolete/sysfs-class-rfkill
@@ -0,0 +1,29 @@
+rfkill - radio frequency (RF) connector kill switch support
+For details to this subsystem look at Documentation/rfkill.txt.
+What:           /sys/class/rfkill/rfkill[0-9]+/state
+Date:           09-Jul-2007
+KernelVersion   v2.6.22
+Contact:        linux-wireless@vger.kernel.org
+Description:    Current state of the transmitter.
+                This file is deprecated and sheduled to be removed in 2014,
+                because its not possible to express the 'soft and hard block'
+                state of the rfkill driver.
+Values:         A numeric value.
+                0: RFKILL_STATE_SOFT_BLOCKED
+                        transmitter is turned off by software
+                1: RFKILL_STATE_UNBLOCKED
+                        transmitter is (potentially) active
+                2: RFKILL_STATE_HARD_BLOCKED
+                        transmitter is forced off by something outside of
+                        the driver's control.
+What:           /sys/class/rfkill/rfkill[0-9]+/claim
+Date:           09-Jul-2007
+KernelVersion   v2.6.22
+Contact:        linux-wireless@vger.kernel.org
+Description:    This file is deprecated because there no longer is a way to
+                claim just control over a single rfkill instance.
+                This file is scheduled to be removed in 2012.
+Values:         0: Kernel handles events
diff --git a/Documentation/ABI/stable/sysfs-class-rfkill b/Documentation/ABI/stable/sysfs-class-rfkill
new file mode 100644
index 000000000000..097f522c33bb
--- /dev/null
+++ b/Documentation/ABI/stable/sysfs-class-rfkill
@@ -0,0 +1,67 @@
+rfkill - radio frequency (RF) connector kill switch support
+For details to this subsystem look at Documentation/rfkill.txt.
+For the deprecated /sys/class/rfkill/*/state and
+/sys/class/rfkill/*/claim knobs of this interface look in
+Documentation/ABI/obsolete/sysfs-class-rfkill.
+What:           /sys/class/rfkill
+Date:           09-Jul-2007
+KernelVersion:  v2.6.22
+Contact:        linux-wireless@vger.kernel.org,
+Description:    The rfkill class subsystem folder.
+                Each registered rfkill driver is represented by an rfkillX
+                subfolder (X being an integer > 0).
+What:           /sys/class/rfkill/rfkill[0-9]+/name
+Date:           09-Jul-2007
+KernelVersion   v2.6.22
+Contact:        linux-wireless@vger.kernel.org
+Description:    Name assigned by driver to this key (interface or driver name).
+Values:         arbitrary string.
+What:           /sys/class/rfkill/rfkill[0-9]+/type
+Date:           09-Jul-2007
+KernelVersion   v2.6.22
+Contact:        linux-wireless@vger.kernel.org
+Description:    Driver type string ("wlan", "bluetooth", etc).
+Values:         See include/linux/rfkill.h.
+What:           /sys/class/rfkill/rfkill[0-9]+/persistent
+Date:           09-Jul-2007
+KernelVersion   v2.6.22
+Contact:        linux-wireless@vger.kernel.org
+Description:    Whether the soft blocked state is initialised from non-volatile
+                storage at startup.
+Values:         A numeric value.
+                0: false
+                1: true
+What:           /sys/class/rfkill/rfkill[0-9]+/hard
+Date:           12-March-2010
+KernelVersion   v2.6.34
+Contact:        linux-wireless@vger.kernel.org
+Description:    Current hardblock state. This file is read only.
+Values:         A numeric value.
+                0: inactive
+                        The transmitter is (potentially) active.
+                1: active
+                        The transmitter is forced off by something outside of
+                        the driver's control.
+What:           /sys/class/rfkill/rfkill[0-9]+/soft
+Date:           12-March-2010
+KernelVersion   v2.6.34
+Contact:        linux-wireless@vger.kernel.org
+Description:    Current softblock state. This file is read and write.
+Values:         A numeric value.
+                0: inactive
+                        The transmitter is (potentially) active.
+                1: active
+                        The transmitter is turned off by software.
diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node
new file mode 100644
index 000000000000..49b82cad7003
--- /dev/null
+++ b/Documentation/ABI/stable/sysfs-devices-node
@@ -0,0 +1,7 @@
+What:           /sys/devices/system/node/nodeX
+Date:           October 2002
+Contact:        Linux Memory Management list <linux-mm@kvack.org>
+Description:
+                When CONFIG_NUMA is enabled, this is a directory containing
+                information on node X such as what CPUs are local to the
+                node.
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index d2f90334bb93..4873c759d535 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -128,3 +128,17 @@ Description:
                preferred request size for workloads where sustained
                throughput is desired.  If no optimal I/O size is
                reported this file contains 0.
+What:           /sys/block/<disk>/queue/nomerges
+Date:           January 2010
+Contact:
+Description:
+                Standard I/O elevator operations include attempts to
+                merge contiguous I/Os. For known random I/O loads these
+                attempts will always fail and result in extra cycles
+                being spent in the kernel. This allows one to turn off
+                this behavior on one of two ways: When set to 1, complex
+                merge checks are disabled, but the simple one-shot merges
+                with the previous I/O request are enabled. When set to 2,
+                all merge tries are disabled. The default value is 0 -
+                which enables all types of merge tries.
diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci
index 25be3250f7d6..428676cfa61e 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci
+++ b/Documentation/ABI/testing/sysfs-bus-pci
@@ -133,6 +133,46 @@ Description:
                The symbolic link points to the PCI device sysfs entry of the
                Physical Function this device associates with.
+What:           /sys/bus/pci/slots/...
+Date:           April 2005 (possibly older)
+KernelVersion:  2.6.12 (possibly older)
+Contact:        linux-pci@vger.kernel.org
+Description:
+                When the appropriate driver is loaded, it will create a
+                directory per claimed physical PCI slot in
+                /sys/bus/pci/slots/.  The names of these directories are
+                specific to the driver, which in turn, are specific to the
+                platform, but in general, should match the label on the
+                machine's physical chassis.
+                The drivers that can create slot directories include the
+                PCI hotplug drivers, and as of 2.6.27, the pci_slot driver.
+                The slot directories contain, at a minimum, a file named
+                'address' which contains the PCI bus:device:function tuple.
+                Other files may appear as well, but are specific to the
+                driver.
+What:           /sys/bus/pci/slots/.../function[0-7]
+Date:           March 2010
+KernelVersion:  2.6.35
+Contact:        linux-pci@vger.kernel.org
+Description:
+                If PCI slot directories (as described above) are created,
+                and the physical slot is actually populated with a device,
+                symbolic links in the slot directory pointing to the
+                device's PCI functions are created as well.
+What:           /sys/bus/pci/devices/.../slot
+Date:           March 2010
+KernelVersion:  2.6.35
+Contact:        linux-pci@vger.kernel.org
+Description:
+                If PCI slot directories (as described above) are created,
+                a symbolic link pointing to the slot directory will be
+                created as well.
 What:           /sys/bus/pci/slots/.../module
 Date:           June 2009
 Contact:        linux-pci@vger.kernel.org
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb
index a07c0f366f91..294aa864a60a 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb
+++ b/Documentation/ABI/testing/sysfs-bus-usb
@@ -14,34 +14,6 @@ Description:
                The autosuspend delay for newly-created devices is set to
                the value of the usbcore.autosuspend module parameter.
-What:           /sys/bus/usb/devices/.../power/level
-Date:           March 2007
-KernelVersion:  2.6.21
-Contact:        Alan Stern <stern@rowland.harvard.edu>
-Description:
-                Each USB device directory will contain a file named
-                power/level.  This file holds a power-level setting for
-                the device, either "on" or "auto".
-                "on" means that the device is not allowed to autosuspend,
-                although normal suspends for system sleep will still
-                be honored.  "auto" means the device will autosuspend
-                and autoresume in the usual manner, according to the
-                capabilities of its driver.
-                During normal use, devices should be left in the "auto"
-                level.  The "on" level is meant for administrative uses.
-                If you want to suspend a device immediately but leave it
-                free to wake up in response to I/O requests, you should
-                write "0" to power/autosuspend.
-                Device not capable of proper suspend and resume should be
-                left in the "on" level.  Although the USB spec requires
-                devices to support suspend/resume, many of them do not.
-                In fact so many don't that by default, the USB core
-                initializes all non-hub devices in the "on" level.  Some
-                drivers may change this setting when they are bound.
 What:           /sys/bus/usb/devices/.../power/persist
 Date:           May 2007
 KernelVersion:  2.6.23
@@ -159,3 +131,14 @@ Description:
                device.  This is useful to ensure auto probing won't
                match the driver to the device.  For example:
                # echo "046d c315" > /sys/bus/usb/drivers/foo/remove_id
+What:           /sys/bus/usb/device/.../avoid_reset_quirk
+Date:           December 2009
+Contact:        Oliver Neukum <oliver@neukum.org>
+Description:
+                Writing 1 to this file tells the kernel that this
+                device will morph into another mode when it is reset.
+                Drivers will not use reset for error handling for
+                such devices.
+Users:
+                usb_modeswitch
diff --git a/Documentation/ABI/testing/sysfs-class-power b/Documentation/ABI/testing/sysfs-class-power
new file mode 100644
index 000000000000..78c7baca3587
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-power
@@ -0,0 +1,20 @@
+What:           /sys/class/power/ds2760-battery.*/charge_now
+Date:           May 2010
+KernelVersion:  2.6.35
+Contact:        Daniel Mack <daniel@caiaq.de>
+Description:
+                This file is writeable and can be used to set the current
+                coloumb counter value inside the battery monitor chip. This
+                is needed for unavoidable corrections of aging batteries.
+                A userspace daemon can monitor the battery charging logic
+                and once the counter drops out of considerable bounds, take
+                appropriate action.
+What:           /sys/class/power/ds2760-battery.*/charge_full
+Date:           May 2010
+KernelVersion:  2.6.35
+Contact:        Daniel Mack <daniel@caiaq.de>
+Description:
+                This file is writeable and can be used to set the assumed
+                battery 'full level'. As batteries age, this value has to be
+                amended over time.
diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory
index bf1627b02a03..aba7d989208c 100644
--- a/Documentation/ABI/testing/sysfs-devices-memory
+++ b/Documentation/ABI/testing/sysfs-devices-memory
@@ -43,7 +43,7 @@ Date:		September 2008
 Contact:        Badari Pulavarty <pbadari@us.ibm.com>
 Description:
                The file /sys/devices/system/memory/memoryX/state
-                is read-write.  When read, it's contents show the
+                is read-write.  When read, its contents show the
                online/offline state of the memory section.  When written,
                root can toggle the the online/offline state of a removable
                memory section (see removable file description above)
diff --git a/Documentation/ABI/testing/sysfs-devices-node b/Documentation/ABI/testing/sysfs-devices-node
new file mode 100644
index 000000000000..453a210c3ceb
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-node
@@ -0,0 +1,7 @@
+What:           /sys/devices/system/node/nodeX/compact
+Date:           February 2010
+Contact:        Mel Gorman <mel@csn.ul.ie>
+Description:
+                When this file is written to, all memory within that node
+                will be compacted. When it completes, memory will be freed
+                into blocks which have as many contiguous pages as possible
diff --git a/Documentation/ABI/testing/sysfs-devices-platform-_UDC_-gadget b/Documentation/ABI/testing/sysfs-devices-platform-_UDC_-gadget
new file mode 100644
index 000000000000..34034027b13c
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-platform-_UDC_-gadget
@@ -0,0 +1,9 @@
+What:           /sys/devices/platform/_UDC_/gadget/suspended
+Date:           April 2010
+Contact:        Fabien Chouteau <fabien.chouteau@barco.com>
+Description:
+                Show the suspend state of an USB composite gadget.
+                1 -> suspended
+                0 -> resumed
+                (_UDC_ is the name of the USB Device Controller driver)
diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power
new file mode 100644
index 000000000000..6123c523bfd7
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-power
@@ -0,0 +1,79 @@
+What:           /sys/devices/.../power/
+Date:           January 2009
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../power directory contains attributes
+                allowing the user space to check and modify some power
+                management related properties of given device.
+What:           /sys/devices/.../power/wakeup
+Date:           January 2009
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../power/wakeup attribute allows the user
+                space to check if the device is enabled to wake up the system
+                from sleep states, such as the memory sleep state (suspend to
+                RAM) and hibernation (suspend to disk), and to enable or disable
+                it to do that as desired.
+                Some devices support "wakeup" events, which are hardware signals
+                used to activate the system from a sleep state.  Such devices
+                have one of the following two values for the sysfs power/wakeup
+                file:
+                + "enabled\n" to issue the events;
+                + "disabled\n" not to do so;
+                In that cases the user space can change the setting represented
+                by the contents of this file by writing either "enabled", or
+                "disabled" to it.
+                For the devices that are not capable of generating system wakeup
+                events this file contains "\n".  In that cases the user space
+                cannot modify the contents of this file and the device cannot be
+                enabled to wake up the system.
+What:           /sys/devices/.../power/control
+Date:           January 2009
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../power/control attribute allows the user
+                space to control the run-time power management of the device.
+                All devices have one of the following two values for the
+                power/control file:
+                + "auto\n" to allow the device to be power managed at run time;
+                + "on\n" to prevent the device from being power managed;
+                The default for all devices is "auto", which means that they may
+                be subject to automatic power management, depending on their
+                drivers.  Changing this attribute to "on" prevents the driver
+                from power managing the device at run time.  Doing that while
+                the device is suspended causes it to be woken up.
+What:           /sys/devices/.../power/async
+Date:           January 2009
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../async attribute allows the user space to
+                enable or diasble the device's suspend and resume callbacks to
+                be executed asynchronously (ie. in separate threads, in parallel
+                with the main suspend/resume thread) during system-wide power
+                transitions (eg. suspend to RAM, hibernation).
+                All devices have one of the following two values for the
+                power/async file:
+                + "enabled\n" to permit the asynchronous suspend/resume;
+                + "disabled\n" to forbid it;
+                The value of this attribute may be changed by writing either
+                "enabled", or "disabled" to it.
+                It generally is unsafe to permit the asynchronous suspend/resume
+                of a device unless it is certain that all of the PM dependencies
+                of the device are known to the PM core.  However, for some
+                devices this attribute is set to "enabled" by bus type code or
+                device drivers and in that cases it should be safe to leave the
+                default value.
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-picolcd b/Documentation/ABI/testing/sysfs-driver-hid-picolcd
new file mode 100644
index 000000000000..08579e7e1e89
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-hid-picolcd
@@ -0,0 +1,43 @@
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/operation_mode
+Date:           March 2010
+Contact:        Bruno Prémont <bonbons@linux-vserver.org>
+Description:    Make it possible to switch the PicoLCD device between LCD
+                (firmware) and bootloader (flasher) operation modes.
+                Reading: returns list of available modes, the active mode being
+                enclosed in brackets ('[' and ']')
+                Writing: causes operation mode switch. Permitted values are
+                the non-active mode names listed when read.
+                Note: when switching mode the current PicoLCD HID device gets
+                disconnected and reconnects after above delay (see attribute
+                operation_mode_delay for its value).
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/operation_mode_delay
+Date:           April 2010
+Contact:        Bruno Prémont <bonbons@linux-vserver.org>
+Description:    Delay PicoLCD waits before restarting in new mode when
+                operation_mode has changed.
+                Reading/Writing: It is expressed in ms and permitted range is
+                0..30000ms.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/fb_update_rate
+Date:           March 2010
+Contact:        Bruno Prémont <bonbons@linux-vserver.org>
+Description:    Make it possible to adjust defio refresh rate.
+                Reading: returns list of available refresh rates (expressed in Hz),
+                the active refresh rate being enclosed in brackets ('[' and ']')
+                Writing: accepts new refresh rate expressed in integer Hz
+                within permitted rates.
+                Note: As device can barely do 2 complete refreshes a second
+                it only makes sense to adjust this value if only one or two
+                tiles get changed and it's not appropriate to expect the application
+                to flush it's tiny changes explicitely at higher than default rate.
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-prodikeys b/Documentation/ABI/testing/sysfs-driver-hid-prodikeys
new file mode 100644
index 000000000000..05d988c29a83
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-hid-prodikeys
@@ -0,0 +1,29 @@
+What:           /sys/bus/hid/drivers/prodikeys/.../channel
+Date:           April 2010
+KernelVersion:  2.6.34
+Contact:        Don Prince <dhprince.devel@yahoo.co.uk>
+Description:
+                Allows control (via software) the midi channel to which
+                that the pc-midi keyboard will output.midi data.
+                Range: 0..15
+                Type:  Read/write
+What:           /sys/bus/hid/drivers/prodikeys/.../sustain
+Date:           April 2010
+KernelVersion:  2.6.34
+Contact:        Don Prince <dhprince.devel@yahoo.co.uk>
+Description:
+                Allows control (via software) the sustain duration of a
+                note held by the pc-midi driver.
+                0 means sustain mode is disabled.
+                Range: 0..5000 (milliseconds)
+                Type:  Read/write
+What:           /sys/bus/hid/drivers/prodikeys/.../octave
+Date:           April 2010
+KernelVersion:  2.6.34
+Contact:        Don Prince <dhprince.devel@yahoo.co.uk>
+Description:
+                Controls the octave shift modifier in the pc-midi driver.
+                The octave can be shifted via software up/down 2 octaves.
+                0 means the no ocatve shift.
+                Range: -2..2 (minus 2 to plus 2)
+                Type: Read/Write
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone b/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone
new file mode 100644
index 000000000000..88340a23ce91
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone
@@ -0,0 +1,111 @@
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/actual_dpi
+Date:           March 2010
+Contact:        Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:    It is possible to switch the dpi setting of the mouse with the
+                press of a button.
+                When read, this file returns the raw number of the actual dpi
+                setting reported by the mouse. This number has to be further
+                processed to receive the real dpi value.
+                VALUE DPI
+                1     800
+                2     1200
+                3     1600
+                4     2000
+                5     2400
+                6     3200
+                This file is readonly.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/actual_profile
+Date:           March 2010
+Contact:        Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:    When read, this file returns the number of the actual profile.
+                This file is readonly.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/firmware_version
+Date:           March 2010
+Contact:        Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:    When read, this file returns the raw integer version number of the
+                firmware reported by the mouse. Using the integer value eases
+                further usage in other programs. To receive the real version
+                number the decimal point has to be shifted 2 positions to the
+                left. E.g. a returned value of 138 means 1.38
+                This file is readonly.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/kone_driver_version
+Date:           March 2010
+Contact:        Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:    When read, this file returns the driver version.
+                The format of the string is "v<major>.<minor>.<patchlevel>".
+                This attribute is used by the userland tools to find the sysfs-
+                paths of installed kone-mice and determine the capabilites of
+                the driver. Versions of this driver for old kernels replace
+                usbhid instead of generic-usb. The way to scan for this file
+                has been chosen to provide a consistent way for all supported
+                kernel versions.
+                This file is readonly.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/profile[1-5]
+Date:           March 2010
+Contact:        Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:    The mouse can store 5 profiles which can be switched by the
+                press of a button. A profile holds informations like button
+                mappings, sensitivity, the colors of the 5 leds and light
+                effects.
+                When read, these files return the respective profile. The
+                returned data is 975 bytes in size.
+                When written, this file lets one write the respective profile
+                data back to the mouse. The data has to be 975 bytes long.
+                The mouse will reject invalid data, whereas the profile number
+                stored in the profile doesn't need to fit the number of the
+                store.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/settings
+Date:           March 2010
+Contact:        Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:    When read, this file returns the settings stored in the mouse.
+                The size of the data is 36 bytes and holds information like the
+                startup_profile, tcu state and calibration_data.
+                When written, this file lets write settings back to the mouse.
+                The data has to be 36 bytes long. The mouse will reject invalid
+                data.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/startup_profile
+Date:           March 2010
+Contact:        Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:    The integer value of this attribute ranges from 1 to 5.
+                When read, this attribute returns the number of the profile
+                that's active when the mouse is powered on.
+                When written, this file sets the number of the startup profile
+                and the mouse activates this profile immediately.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/tcu
+Date:           March 2010
+Contact:        Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:    The mouse has a "Tracking Control Unit" which lets the user
+                calibrate the laser power to fit the mousepad surface.
+                When read, this file returns the current state of the TCU,
+                where 0 means off and 1 means on.
+                Writing 0 in this file will switch the TCU off.
+                Writing 1 in this file will start the calibration which takes
+                around 6 seconds to complete and activates the TCU.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/weight
+Date:           March 2010
+Contact:        Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:    The mouse can be equipped with one of four supplied weights
+                ranging from 5 to 20 grams which are recognized by the mouse
+                and its value can be read out. When read, this file returns the
+                raw value returned by the mouse which eases further processing
+                in other software.
+                The values map to the weights as follows:
+                VALUE WEIGHT
+                0     none
+                1     5g
+                2     10g
+                3     15g
+                4     20g
+                This file is readonly.
diff --git a/Documentation/ABI/testing/sysfs-platform-asus-laptop b/Documentation/ABI/testing/sysfs-platform-asus-laptop
index a1cb660c50cf..1d775390e856 100644
--- a/Documentation/ABI/testing/sysfs-platform-asus-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-asus-laptop
@@ -1,4 +1,4 @@
-What:           /sys/devices/platform/asus-laptop/display
+What:           /sys/devices/platform/asus_laptop/display
 Date:           January 2007
 KernelVersion:  2.6.20
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
@@ -13,7 +13,7 @@ Description:
                Ex: - 0 (0000b) means no display
                    - 3 (0011b) CRT+LCD.
-What:           /sys/devices/platform/asus-laptop/gps
+What:           /sys/devices/platform/asus_laptop/gps
 Date:           January 2007
 KernelVersion:  2.6.20
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
@@ -21,7 +21,7 @@ Description:
                Control the gps device. 1 means on, 0 means off.
 Users:          Lapsus
-What:           /sys/devices/platform/asus-laptop/ledd
+What:           /sys/devices/platform/asus_laptop/ledd
 Date:           January 2007
 KernelVersion:  2.6.20
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
@@ -29,11 +29,11 @@ Description:
                Some models like the W1N have a LED display that can be
                used to display several informations.
                To control the LED display, use the following :
-                    echo 0x0T000DDD > /sys/devices/platform/asus-laptop/
+                    echo 0x0T000DDD > /sys/devices/platform/asus_laptop/
                where T control the 3 letters display, and DDD the 3 digits display.
                The DDD table can be found in Documentation/laptops/asus-laptop.txt
-What:           /sys/devices/platform/asus-laptop/bluetooth
+What:           /sys/devices/platform/asus_laptop/bluetooth
 Date:           January 2007
 KernelVersion:  2.6.20
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
@@ -42,7 +42,7 @@ Description:
                This may control the led, the device or both.
 Users:          Lapsus
-What:           /sys/devices/platform/asus-laptop/wlan
+What:           /sys/devices/platform/asus_laptop/wlan
 Date:           January 2007
 KernelVersion:  2.6.20
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
diff --git a/Documentation/ABI/testing/sysfs-platform-eeepc-laptop b/Documentation/ABI/testing/sysfs-platform-eeepc-laptop
index 7445dfb321b5..5b026c69587a 100644
--- a/Documentation/ABI/testing/sysfs-platform-eeepc-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-eeepc-laptop
@@ -1,4 +1,4 @@
-What:           /sys/devices/platform/eeepc-laptop/disp
+What:           /sys/devices/platform/eeepc/disp
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
@@ -9,21 +9,21 @@ Description:
                - 3 = LCD+CRT
                If you run X11, you should use xrandr instead.
-What:           /sys/devices/platform/eeepc-laptop/camera
+What:           /sys/devices/platform/eeepc/camera
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
 Description:
                Control the camera. 1 means on, 0 means off.
-What:           /sys/devices/platform/eeepc-laptop/cardr
+What:           /sys/devices/platform/eeepc/cardr
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
 Description:
                Control the card reader. 1 means on, 0 means off.
-What:           /sys/devices/platform/eeepc-laptop/cpufv
+What:           /sys/devices/platform/eeepc/cpufv
 Date:           Jun 2009
 KernelVersion:  2.6.31
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
@@ -42,7 +42,7 @@ Description:
                    `------------ Availables modes
                For example, 0x301 means: mode 1 selected, 3 available modes.
-What:           /sys/devices/platform/eeepc-laptop/available_cpufv
+What:           /sys/devices/platform/eeepc/available_cpufv
 Date:           Jun 2009
 KernelVersion:  2.6.31
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index dcff4d0623ad..d6a801f45b48 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -101,3 +101,16 @@ Description:
                CAUTION: Using it will cause your machine's real-time (CMOS)
                clock to be set to a random invalid time after a resume.
+What:           /sys/power/pm_async
+Date:           January 2009
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/power/pm_async file controls the switch allowing the
+                user space to enable or disable asynchronous suspend and resume
+                of devices.  If enabled, this feature will cause some device
+                drivers' suspend and resume callbacks to be executed in parallel
+                with each other and with the main suspend thread.  It is enabled
+                if this file contains "1", which is the default.  It may be
+                disabled by writing "0" to this file, in which case all devices
+                will be suspended and resumed synchronously.
diff --git a/Documentation/ABI/testing/sysfs-wacom b/Documentation/ABI/testing/sysfs-wacom
new file mode 100644
index 000000000000..1517976e25c4
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-wacom
@@ -0,0 +1,10 @@
+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/Changes b/Documentation/Changes
index f08b313cd235..eca9f6e6fbe6 100644
--- a/Documentation/Changes
+++ b/Documentation/Changes
@@ -49,7 +49,7 @@ o  oprofile               0.9                     # oprofiled --version
 o  udev                   081                     # udevinfo -V
 o  grub                   0.93                    # grub --version
 o  mcelog                 0.6
-o  iptables               1.4.1                   # iptables -V
+o  iptables               1.4.2                   # iptables -V
 Kernel compilation
diff --git a/Documentation/PCI/PCI-DMA-mapping.txt b/Documentation/DMA-API-HOWTO.txt
index ecad88d9fe59..98ce51796f71 100644
--- a/Documentation/PCI/PCI-DMA-mapping.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -1,12 +1,12 @@
-                        Dynamic DMA mapping
+                     Dynamic DMA mapping Guide
-                        ===================
+                     =========================
                 David S. Miller <davem@redhat.com>
                 Richard Henderson <rth@cygnus.com>
                  Jakub Jelinek <jakub@redhat.com>
-This document describes the DMA mapping system in terms of the pci_
+This is a guide to device driver writers on how to use the DMA API
-API.  For a similar API that works for generic devices, see
+with example pseudo-code.  For a concise description of the API, see
 DMA-API.txt.
 Most of the 64bit platforms have special hardware that translates bus
@@ -26,12 +26,15 @@ mapped only for the time they are actually used and unmapped after the DMA
 transfer.
 The following API will work of course even on platforms where no such
-hardware exists, see e.g. arch/x86/include/asm/pci.h for how it is implemented on
+hardware exists.
-top of the virt_to_bus interface.
+Note that the DMA API works with any bus independent of the underlying
+microprocessor architecture. You should use the DMA API rather than
+the bus specific DMA API (e.g. pci_dma_*).
 First of all, you should make sure
-#include <linux/pci.h>
+#include <linux/dma-mapping.h>
 is in your driver. This file will obtain for you the definition of the
 dma_addr_t (which can hold any valid DMA address for the platform)
@@ -78,44 +81,43 @@ for you to DMA from/to.
                        DMA addressing limitations
 Does your device have any DMA addressing limitations?  For example, is
-your device only capable of driving the low order 24-bits of address
+your device only capable of driving the low order 24-bits of address?
-on the PCI bus for SAC DMA transfers?  If so, you need to inform the
+If so, you need to inform the kernel of this fact.
-PCI layer of this fact.
 By default, the kernel assumes that your device can address the full
-32-bits in a SAC cycle.  For a 64-bit DAC capable device, this needs
+32-bits.  For a 64-bit capable device, this needs to be increased.
-to be increased.  And for a device with limitations, as discussed in
+And for a device with limitations, as discussed in the previous
-the previous paragraph, it needs to be decreased.
+paragraph, it needs to be decreased.
-pci_alloc_consistent() by default will return 32-bit DMA addresses.
+Special note about PCI: PCI-X specification requires PCI-X devices to
-PCI-X specification requires PCI-X devices to support 64-bit
+support 64-bit addressing (DAC) for all transactions.  And at least
-addressing (DAC) for all transactions. And at least one platform (SGI
+one platform (SGI SN2) requires 64-bit consistent allocations to
-SN2) requires 64-bit consistent allocations to operate correctly when
+operate correctly when the IO bus is in PCI-X mode.
-the IO bus is in PCI-X mode. Therefore, like with pci_set_dma_mask(),
-it's good practice to call pci_set_consistent_dma_mask() to set the
+For correct operation, you must interrogate the kernel in your device
-appropriate mask even if your device only supports 32-bit DMA
+probe routine to see if the DMA controller on the machine can properly
-(default) and especially if it's a PCI-X device.
+support the DMA addressing limitation your device has.  It is good
+style to do this even if your device holds the default setting,
-For correct operation, you must interrogate the PCI layer in your
-device probe routine to see if the PCI controller on the machine can
-properly support the DMA addressing limitation your device has.  It is
-good style to do this even if your device holds the default setting,
 because this shows that you did think about these issues wrt. your
 device.
-The query is performed via a call to pci_set_dma_mask():
+The query is performed via a call to dma_set_mask():
-        int pci_set_dma_mask(struct pci_dev *pdev, u64 device_mask);
+        int dma_set_mask(struct device *dev, u64 mask);
 The query for consistent allocations is performed via a call to
-pci_set_consistent_dma_mask():
+dma_set_coherent_mask():
-        int pci_set_consistent_dma_mask(struct pci_dev *pdev, u64 device_mask);
+        int dma_set_coherent_mask(struct device *dev, u64 mask);
-Here, pdev is a pointer to the PCI device struct of your device, and
+Here, dev is a pointer to the device struct of your device, and mask
-device_mask is a bit mask describing which bits of a PCI address your
+is a bit mask describing which bits of an address your device
-device supports.  It returns zero if your card can perform DMA
+supports.  It returns zero if your card can perform DMA properly on
-properly on the machine given the address mask you provided.
+the machine given the address mask you provided.  In general, the
+device struct of your device is embedded in the bus specific device
+struct of your device.  For example, a pointer to the device struct of
+your PCI device is pdev->dev (pdev is a pointer to the PCI device
+struct of your device).
 If it returns non-zero, your device cannot perform DMA properly on
 this platform, and attempting to do so will result in undefined
@@ -133,31 +135,30 @@ of your driver reports that performance is bad or that the device is not
 even detected, you can ask them for the kernel messages to find out
 exactly why.
-The standard 32-bit addressing PCI device would do something like
+The standard 32-bit addressing device would do something like this:
-this:
-        if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
+        if (dma_set_mask(dev, DMA_BIT_MASK(32))) {
                printk(KERN_WARNING
                       "mydev: No suitable DMA available.\n");
                goto ignore_this_device;
        }
-Another common scenario is a 64-bit capable device.  The approach
+Another common scenario is a 64-bit capable device.  The approach here
-here is to try for 64-bit DAC addressing, but back down to a
+is to try for 64-bit addressing, but back down to a 32-bit mask that
-32-bit mask should that fail.  The PCI platform code may fail the
+should not fail.  The kernel may fail the 64-bit mask not because the
-64-bit mask not because the platform is not capable of 64-bit
+platform is not capable of 64-bit addressing.  Rather, it may fail in
-addressing.  Rather, it may fail in this case simply because
+this case simply because 32-bit addressing is done more efficiently
-32-bit SAC addressing is done more efficiently than DAC addressing.
+than 64-bit addressing.  For example, Sparc64 PCI SAC addressing is
-Sparc64 is one platform which behaves in this way.
+more efficient than DAC addressing.
 Here is how you would handle a 64-bit capable device which can drive
 all 64-bits when accessing streaming DMA:
        int using_dac;
-        if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+        if (!dma_set_mask(dev, DMA_BIT_MASK(64))) {
                using_dac = 1;
-        } else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
+        } else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) {
                using_dac = 0;
        } else {
                printk(KERN_WARNING
@@ -170,36 +171,36 @@ the case would look like this:
        int using_dac, consistent_using_dac;
-        if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+        if (!dma_set_mask(dev, DMA_BIT_MASK(64))) {
                using_dac = 1;
                consistent_using_dac = 1;
-                pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+                dma_set_coherent_mask(dev, DMA_BIT_MASK(64));
-        } else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
+        } else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) {
                using_dac = 0;
                consistent_using_dac = 0;
-                pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+                dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
        } else {
                printk(KERN_WARNING
                       "mydev: No suitable DMA available.\n");
                goto ignore_this_device;
        }
-pci_set_consistent_dma_mask() will always be able to set the same or a
+dma_set_coherent_mask() will always be able to set the same or a
-smaller mask as pci_set_dma_mask(). However for the rare case that a
+smaller mask as dma_set_mask(). However for the rare case that a
 device driver only uses consistent allocations, one would have to
-check the return value from pci_set_consistent_dma_mask().
+check the return value from dma_set_coherent_mask().
 Finally, if your device can only drive the low 24-bits of
-address during PCI bus mastering you might do something like:
+address you might do something like:
-        if (pci_set_dma_mask(pdev, DMA_BIT_MASK(24))) {
+        if (dma_set_mask(dev, DMA_BIT_MASK(24))) {
                printk(KERN_WARNING
                       "mydev: 24-bit DMA addressing not available.\n");
                goto ignore_this_device;
        }
-When pci_set_dma_mask() is successful, and returns zero, the PCI layer
+When dma_set_mask() is successful, and returns zero, the kernel saves
-saves away this mask you have provided.  The PCI layer will use this
+away this mask you have provided.  The kernel will use this
 information later when you make DMA mappings.
 There is a case which we are aware of at this time, which is worth
@@ -208,7 +209,7 @@ functions (for example a sound card provides playback and record
 functions) and the various different functions have _different_
 DMA addressing limitations, you may wish to probe each mask and
 only provide the functionality which the machine can handle.  It
-is important that the last call to pci_set_dma_mask() be for the
+is important that the last call to dma_set_mask() be for the
 most specific mask.
 Here is pseudo-code showing how this might be done:
@@ -217,17 +218,17 @@ Here is pseudo-code showing how this might be done:
        #define RECORD_ADDRESS_BITS     DMA_BIT_MASK(24)
        struct my_sound_card *card;
-        struct pci_dev *pdev;
+        struct device *dev;
        ...
-        if (!pci_set_dma_mask(pdev, PLAYBACK_ADDRESS_BITS)) {
+        if (!dma_set_mask(dev, PLAYBACK_ADDRESS_BITS)) {
                card->playback_enabled = 1;
        } else {
                card->playback_enabled = 0;
                printk(KERN_WARNING "%s: Playback disabled due to DMA limitations.\n",
                       card->name);
        }
-        if (!pci_set_dma_mask(pdev, RECORD_ADDRESS_BITS)) {
+        if (!dma_set_mask(dev, RECORD_ADDRESS_BITS)) {
                card->record_enabled = 1;
        } else {
                card->record_enabled = 0;
@@ -252,8 +253,8 @@ There are two types of DMA mappings:
  Think of "consistent" as "synchronous" or "coherent".
  The current default is to return consistent memory in the low 32
-  bits of the PCI bus space.  However, for future compatibility you
+  bits of the bus space.  However, for future compatibility you should
-  should set the consistent mask even if this default is fine for your
+  set the consistent mask even if this default is fine for your
  driver.
  Good examples of what to use consistent mappings for are:
@@ -285,9 +286,9 @@ There are two types of DMA mappings:
             found in PCI bridges (such as by reading a register's value
             after writing it).
- Streaming DMA mappings which are usually mapped for one DMA transfer,
+- Streaming DMA mappings which are usually mapped for one DMA
-  unmapped right after it (unless you use pci_dma_sync_* below) and for which
+  transfer, unmapped right after it (unless you use dma_sync_* below)
-  hardware can optimize for sequential accesses.
+  and for which hardware can optimize for sequential accesses.
  This of "streaming" as "asynchronous" or "outside the coherency
  domain".
@@ -302,8 +303,8 @@ There are two types of DMA mappings:
  optimizations the hardware allows.  To this end, when using
  such mappings you must be explicit about what you want to happen.
-Neither type of DMA mapping has alignment restrictions that come
+Neither type of DMA mapping has alignment restrictions that come from
-from PCI, although some devices may have such restrictions.
+the underlying bus, although some devices may have such restrictions.
 Also, systems with caches that aren't DMA-coherent will work better
 when the underlying buffers don't share cache lines with other data.
@@ -315,33 +316,27 @@ you should do:
        dma_addr_t dma_handle;
-        cpu_addr = pci_alloc_consistent(pdev, size, &dma_handle);
+        cpu_addr = dma_alloc_coherent(dev, size, &dma_handle, gfp);
-where pdev is a struct pci_dev *. This may be called in interrupt context.
-You should use dma_alloc_coherent (see DMA-API.txt) for buses
-where devices don't have struct pci_dev (like ISA, EISA).
-This argument is needed because the DMA translations may be bus
+where device is a struct device *. This may be called in interrupt
-specific (and often is private to the bus which the device is attached
+context with the GFP_ATOMIC flag.
-to).
 Size is the length of the region you want to allocate, in bytes.
 This routine will allocate RAM for that region, so it acts similarly to
 __get_free_pages (but takes size instead of a page order).  If your
 driver needs regions sized smaller than a page, you may prefer using
-the pci_pool interface, described below.
+the dma_pool interface, described below.
-The consistent DMA mapping interfaces, for non-NULL pdev, will by
+The consistent DMA mapping interfaces, for non-NULL dev, will by
-default return a DMA address which is SAC (Single Address Cycle)
+default return a DMA address which is 32-bit addressable.  Even if the
-addressable.  Even if the device indicates (via PCI dma mask) that it
+device indicates (via DMA mask) that it may address the upper 32-bits,
-may address the upper 32-bits and thus perform DAC cycles, consistent
+consistent allocation will only return > 32-bit addresses for DMA if
-allocation will only return > 32-bit PCI addresses for DMA if the
+the consistent DMA mask has been explicitly changed via
-consistent dma mask has been explicitly changed via
+dma_set_coherent_mask().  This is true of the dma_pool interface as
-pci_set_consistent_dma_mask().  This is true of the pci_pool interface
+well.
-as well.
+dma_alloc_coherent returns two values: the virtual address which you
-pci_alloc_consistent returns two values: the virtual address which you
 can use to access it from the CPU and dma_handle which you pass to the
 card.
@@ -354,54 +349,54 @@ buffer you receive will not cross a 64K boundary.
 To unmap and free such a DMA region, you call:
-        pci_free_consistent(pdev, size, cpu_addr, dma_handle);
+        dma_free_coherent(dev, size, cpu_addr, dma_handle);
-where pdev, size are the same as in the above call and cpu_addr and
+where dev, size are the same as in the above call and cpu_addr and
-dma_handle are the values pci_alloc_consistent returned to you.
+dma_handle are the values dma_alloc_coherent returned to you.
 This function may not be called in interrupt context.
 If your driver needs lots of smaller memory regions, you can write
-custom code to subdivide pages returned by pci_alloc_consistent,
+custom code to subdivide pages returned by dma_alloc_coherent,
-or you can use the pci_pool API to do that.  A pci_pool is like
+or you can use the dma_pool API to do that.  A dma_pool is like
-a kmem_cache, but it uses pci_alloc_consistent not __get_free_pages.
+a kmem_cache, but it uses dma_alloc_coherent not __get_free_pages.
 Also, it understands common hardware constraints for alignment,
 like queue heads needing to be aligned on N byte boundaries.
-Create a pci_pool like this:
+Create a dma_pool like this:
-        struct pci_pool *pool;
+        struct dma_pool *pool;
-        pool = pci_pool_create(name, pdev, size, align, alloc);
+        pool = dma_pool_create(name, dev, size, align, alloc);
-The "name" is for diagnostics (like a kmem_cache name); pdev and size
+The "name" is for diagnostics (like a kmem_cache name); dev and size
 are as above.  The device's hardware alignment requirement for this
 type of data is "align" (which is expressed in bytes, and must be a
 power of two).  If your device has no boundary crossing restrictions,
 pass 0 for alloc; passing 4096 says memory allocated from this pool
 must not cross 4KByte boundaries (but at that time it may be better to
-go for pci_alloc_consistent directly instead).
+go for dma_alloc_coherent directly instead).
-Allocate memory from a pci pool like this:
+Allocate memory from a dma pool like this:
-        cpu_addr = pci_pool_alloc(pool, flags, &dma_handle);
+        cpu_addr = dma_pool_alloc(pool, flags, &dma_handle);
 flags are SLAB_KERNEL if blocking is permitted (not in_interrupt nor
-holding SMP locks), SLAB_ATOMIC otherwise.  Like pci_alloc_consistent,
+holding SMP locks), SLAB_ATOMIC otherwise.  Like dma_alloc_coherent,
 this returns two values, cpu_addr and dma_handle.
-Free memory that was allocated from a pci_pool like this:
+Free memory that was allocated from a dma_pool like this:
-        pci_pool_free(pool, cpu_addr, dma_handle);
+        dma_pool_free(pool, cpu_addr, dma_handle);
-where pool is what you passed to pci_pool_alloc, and cpu_addr and
+where pool is what you passed to dma_pool_alloc, and cpu_addr and
-dma_handle are the values pci_pool_alloc returned. This function
+dma_handle are the values dma_pool_alloc returned. This function
 may be called in interrupt context.
-Destroy a pci_pool by calling:
+Destroy a dma_pool by calling:
-        pci_pool_destroy(pool);
+        dma_pool_destroy(pool);
-Make sure you've called pci_pool_free for all memory allocated
+Make sure you've called dma_pool_free for all memory allocated
 from a pool before you destroy the pool. This function may not
 be called in interrupt context.
@@ -411,15 +406,15 @@ The interfaces described in subsequent portions of this document
 take a DMA direction argument, which is an integer and takes on
 one of the following values:
- PCI_DMA_BIDIRECTIONAL
+ DMA_BIDIRECTIONAL
- PCI_DMA_TODEVICE
+ DMA_TO_DEVICE
- PCI_DMA_FROMDEVICE
+ DMA_FROM_DEVICE
- PCI_DMA_NONE
+ DMA_NONE
 One should provide the exact DMA direction if you know it.
-PCI_DMA_TODEVICE means "from main memory to the PCI device"
+DMA_TO_DEVICE means "from main memory to the device"
-PCI_DMA_FROMDEVICE means "from the PCI device to main memory"
+DMA_FROM_DEVICE means "from the device to main memory"
 It is the direction in which the data moves during the DMA
 transfer.
@@ -427,12 +422,12 @@ You are _strongly_ encouraged to specify this as precisely
 as you possibly can.
 If you absolutely cannot know the direction of the DMA transfer,
-specify PCI_DMA_BIDIRECTIONAL.  It means that the DMA can go in
+specify DMA_BIDIRECTIONAL.  It means that the DMA can go in
 either direction.  The platform guarantees that you may legally
 specify this, and that it will work, but this may be at the
 cost of performance for example.
-The value PCI_DMA_NONE is to be used for debugging.  One can
+The value DMA_NONE is to be used for debugging.  One can
 hold this in a data structure before you come to know the
 precise direction, and this will help catch cases where your
 direction tracking logic has failed to set things up properly.
@@ -442,21 +437,21 @@ potential platform-specific optimizations of such) is for debugging.
 Some platforms actually have a write permission boolean which DMA
 mappings can be marked with, much like page protections in the user
 program address space.  Such platforms can and do report errors in the
-kernel logs when the PCI controller hardware detects violation of the
+kernel logs when the DMA controller hardware detects violation of the
 permission setting.
 Only streaming mappings specify a direction, consistent mappings
 implicitly have a direction attribute setting of
-PCI_DMA_BIDIRECTIONAL.
+DMA_BIDIRECTIONAL.
 The SCSI subsystem tells you the direction to use in the
 'sc_data_direction' member of the SCSI command your driver is
 working on.
 For Networking drivers, it's a rather simple affair.  For transmit
-packets, map/unmap them with the PCI_DMA_TODEVICE direction
+packets, map/unmap them with the DMA_TO_DEVICE direction
 specifier.  For receive packets, just the opposite, map/unmap them
-with the PCI_DMA_FROMDEVICE direction specifier.
+with the DMA_FROM_DEVICE direction specifier.
                  Using Streaming DMA mappings
@@ -467,43 +462,43 @@ scatterlist.
 To map a single region, you do:
-        struct pci_dev *pdev = mydev->pdev;
+        struct device *dev = &my_dev->dev;
        dma_addr_t dma_handle;
        void *addr = buffer->ptr;
        size_t size = buffer->len;
-        dma_handle = pci_map_single(pdev, addr, size, direction);
+        dma_handle = dma_map_single(dev, addr, size, direction);
 and to unmap it:
-        pci_unmap_single(pdev, dma_handle, size, direction);
+        dma_unmap_single(dev, dma_handle, size, direction);
-You should call pci_unmap_single when the DMA activity is finished, e.g.
+You should call dma_unmap_single when the DMA activity is finished, e.g.
 from the interrupt which told you that the DMA transfer is done.
 Using cpu pointers like this for single mappings has a disadvantage,
 you cannot reference HIGHMEM memory in this way.  Thus, there is a
-map/unmap interface pair akin to pci_{map,unmap}_single.  These
+map/unmap interface pair akin to dma_{map,unmap}_single.  These
 interfaces deal with page/offset pairs instead of cpu pointers.
 Specifically:
-        struct pci_dev *pdev = mydev->pdev;
+        struct device *dev = &my_dev->dev;
        dma_addr_t dma_handle;
        struct page *page = buffer->page;
        unsigned long offset = buffer->offset;
        size_t size = buffer->len;
-        dma_handle = pci_map_page(pdev, page, offset, size, direction);
+        dma_handle = dma_map_page(dev, page, offset, size, direction);
        ...
-        pci_unmap_page(pdev, dma_handle, size, direction);
+        dma_unmap_page(dev, dma_handle, size, direction);
 Here, "offset" means byte offset within the given page.
 With scatterlists, you map a region gathered from several regions by:
-        int i, count = pci_map_sg(pdev, sglist, nents, direction);
+        int i, count = dma_map_sg(dev, sglist, nents, direction);
        struct scatterlist *sg;
        for_each_sg(sglist, sg, count, i) {
@@ -527,16 +522,16 @@ accessed sg->address and sg->length as shown above.
 To unmap a scatterlist, just call:
-        pci_unmap_sg(pdev, sglist, nents, direction);
+        dma_unmap_sg(dev, sglist, nents, direction);
 Again, make sure DMA activity has already finished.
-PLEASE NOTE:  The 'nents' argument to the pci_unmap_sg call must be
+PLEASE NOTE:  The 'nents' argument to the dma_unmap_sg call must be
-              the _same_ one you passed into the pci_map_sg call,
+              the _same_ one you passed into the dma_map_sg call,
              it should _NOT_ be the 'count' value _returned_ from the
-              pci_map_sg call.
+              dma_map_sg call.
-Every pci_map_{single,sg} call should have its pci_unmap_{single,sg}
+Every dma_map_{single,sg} call should have its dma_unmap_{single,sg}
 counterpart, because the bus address space is a shared resource (although
 in some ports the mapping is per each BUS so less devices contend for the
 same bus address space) and you could render the machine unusable by eating
@@ -547,14 +542,14 @@ the data in between the DMA transfers, the buffer needs to be synced
 properly in order for the cpu and device to see the most uptodate and
 correct copy of the DMA buffer.
-So, firstly, just map it with pci_map_{single,sg}, and after each DMA
+So, firstly, just map it with dma_map_{single,sg}, and after each DMA
 transfer call either:
-        pci_dma_sync_single_for_cpu(pdev, dma_handle, size, direction);
+        dma_sync_single_for_cpu(dev, dma_handle, size, direction);
 or:
-        pci_dma_sync_sg_for_cpu(pdev, sglist, nents, direction);
+        dma_sync_sg_for_cpu(dev, sglist, nents, direction);
 as appropriate.
@@ -562,27 +557,27 @@ Then, if you wish to let the device get at the DMA area again,
 finish accessing the data with the cpu, and then before actually
 giving the buffer to the hardware call either:
-        pci_dma_sync_single_for_device(pdev, dma_handle, size, direction);
+        dma_sync_single_for_device(dev, dma_handle, size, direction);
 or:
-        pci_dma_sync_sg_for_device(dev, sglist, nents, direction);
+        dma_sync_sg_for_device(dev, sglist, nents, direction);
 as appropriate.
 After the last DMA transfer call one of the DMA unmap routines
-pci_unmap_{single,sg}. If you don't touch the data from the first pci_map_*
+dma_unmap_{single,sg}. If you don't touch the data from the first dma_map_*
-call till pci_unmap_*, then you don't have to call the pci_dma_sync_*
+call till dma_unmap_*, then you don't have to call the dma_sync_*
 routines at all.
 Here is pseudo code which shows a situation in which you would need
-to use the pci_dma_sync_*() interfaces.
+to use the dma_sync_*() interfaces.
        my_card_setup_receive_buffer(struct my_card *cp, char *buffer, int len)
        {
                dma_addr_t mapping;
-                mapping = pci_map_single(cp->pdev, buffer, len, PCI_DMA_FROMDEVICE);
+                mapping = dma_map_single(cp->dev, buffer, len, DMA_FROM_DEVICE);
                cp->rx_buf = buffer;
                cp->rx_len = len;
@@ -606,25 +601,25 @@ to use the pci_dma_sync_*() interfaces.
                         * the DMA transfer with the CPU first
                         * so that we see updated contents.
                         */
-                        pci_dma_sync_single_for_cpu(cp->pdev, cp->rx_dma,
+                        dma_sync_single_for_cpu(&cp->dev, cp->rx_dma,
-                                                    cp->rx_len,
+                                                cp->rx_len,
-                                                    PCI_DMA_FROMDEVICE);
+                                                DMA_FROM_DEVICE);
                        /* Now it is safe to examine the buffer. */
                        hp = (struct my_card_header *) cp->rx_buf;
                        if (header_is_ok(hp)) {
-                                pci_unmap_single(cp->pdev, cp->rx_dma, cp->rx_len,
+                                dma_unmap_single(&cp->dev, cp->rx_dma, cp->rx_len,
-                                                 PCI_DMA_FROMDEVICE);
+                                                 DMA_FROM_DEVICE);
                                pass_to_upper_layers(cp->rx_buf);
                                make_and_setup_new_rx_buf(cp);
                        } else {
                                /* Just sync the buffer and give it back
                                 * to the card.
                                 */
-                                pci_dma_sync_single_for_device(cp->pdev,
+                                dma_sync_single_for_device(&cp->dev,
-                                                               cp->rx_dma,
+                                                           cp->rx_dma,
-                                                               cp->rx_len,
+                                                           cp->rx_len,
-                                                               PCI_DMA_FROMDEVICE);
+                                                           DMA_FROM_DEVICE);
                                give_rx_buf_to_card(cp);
                        }
                }
@@ -634,19 +629,49 @@ Drivers converted fully to this interface should not use virt_to_bus any
 longer, nor should they use bus_to_virt. Some drivers have to be changed a
 little bit, because there is no longer an equivalent to bus_to_virt in the
 dynamic DMA mapping scheme - you have to always store the DMA addresses
-returned by the pci_alloc_consistent, pci_pool_alloc, and pci_map_single
+returned by the dma_alloc_coherent, dma_pool_alloc, and dma_map_single
-calls (pci_map_sg stores them in the scatterlist itself if the platform
+calls (dma_map_sg stores them in the scatterlist itself if the platform
 supports dynamic DMA mapping in hardware) in your driver structures and/or
 in the card registers.
-All PCI drivers should be using these interfaces with no exceptions.
+All drivers should be using these interfaces with no exceptions.  It
-It is planned to completely remove virt_to_bus() and bus_to_virt() as
+is planned to completely remove virt_to_bus() and bus_to_virt() as
 they are entirely deprecated.  Some ports already do not provide these
 as it is impossible to correctly support them.
+                        Handling Errors
+DMA address space is limited on some architectures and an allocation
+failure can be determined by:
+- checking if dma_alloc_coherent returns NULL or dma_map_sg returns 0
+- checking the returned dma_addr_t of dma_map_single and dma_map_page
+  by using dma_mapping_error():
+        dma_addr_t dma_handle;
+        dma_handle = dma_map_single(dev, addr, size, direction);
+        if (dma_mapping_error(dev, dma_handle)) {
+                /*
+                 * reduce current DMA mapping usage,
+                 * delay and try again later or
+                 * reset driver.
+                 */
+        }
+Networking drivers must call dev_kfree_skb to free the socket buffer
+and return NETDEV_TX_OK if the DMA mapping fails on the transmit hook
+(ndo_start_xmit). This means that the socket buffer is just dropped in
+the failure case.
+SCSI drivers must return SCSI_MLQUEUE_HOST_BUSY if the DMA mapping
+fails in the queuecommand hook. This means that the SCSI subsystem
+passes the command to the driver again later.
                Optimizing Unmap State Space Consumption
-On many platforms, pci_unmap_{single,page}() is simply a nop.
+On many platforms, dma_unmap_{single,page}() is simply a nop.
 Therefore, keeping track of the mapping address and length is a waste
 of space.  Instead of filling your drivers up with ifdefs and the like
 to "work around" this (which would defeat the whole purpose of a
@@ -655,7 +680,7 @@ portable API) the following facilities are provided.
 Actually, instead of describing the macros one by one, we'll
 transform some example code.
-1) Use DECLARE_PCI_UNMAP_{ADDR,LEN} in state saving structures.
+1) Use DEFINE_DMA_UNMAP_{ADDR,LEN} in state saving structures.
   Example, before:
        struct ring_state {
@@ -668,14 +693,11 @@ transform some example code.
        struct ring_state {
                struct sk_buff *skb;
-                DECLARE_PCI_UNMAP_ADDR(mapping)
+                DEFINE_DMA_UNMAP_ADDR(mapping);
-                DECLARE_PCI_UNMAP_LEN(len)
+                DEFINE_DMA_UNMAP_LEN(len);
        };
-   NOTE: DO NOT put a semicolon at the end of the DECLARE_*()
+2) Use dma_unmap_{addr,len}_set to set these values.
-         macro.
-2) Use pci_unmap_{addr,len}_set to set these values.
   Example, before:
        ringp->mapping = FOO;
@@ -683,21 +705,21 @@ transform some example code.
   after:
-        pci_unmap_addr_set(ringp, mapping, FOO);
+        dma_unmap_addr_set(ringp, mapping, FOO);
-        pci_unmap_len_set(ringp, len, BAR);
+        dma_unmap_len_set(ringp, len, BAR);
-3) Use pci_unmap_{addr,len} to access these values.
+3) Use dma_unmap_{addr,len} to access these values.
   Example, before:
-        pci_unmap_single(pdev, ringp->mapping, ringp->len,
+        dma_unmap_single(dev, ringp->mapping, ringp->len,
-                         PCI_DMA_FROMDEVICE);
+                         DMA_FROM_DEVICE);
   after:
-        pci_unmap_single(pdev,
+        dma_unmap_single(dev,
-                         pci_unmap_addr(ringp, mapping),
+                         dma_unmap_addr(ringp, mapping),
-                         pci_unmap_len(ringp, len),
+                         dma_unmap_len(ringp, len),
-                         PCI_DMA_FROMDEVICE);
+                         DMA_FROM_DEVICE);
 It really should be self-explanatory.  We treat the ADDR and LEN
 separately, because it is possible for an implementation to only
@@ -711,46 +733,29 @@ to "Closing".
 1) Struct scatterlist requirements.
-   Struct scatterlist must contain, at a minimum, the following
+   Don't invent the architecture specific struct scatterlist; just use
-   members:
+   <asm-generic/scatterlist.h>. You need to enable
+   CONFIG_NEED_SG_DMA_LENGTH if the architecture supports IOMMUs
-        struct page *page;
+   (including software IOMMU).
-        unsigned int offset;
-        unsigned int length;
-   The base address is specified by a "page+offset" pair.
-   Previous versions of struct scatterlist contained a "void *address"
-   field that was sometimes used instead of page+offset.  As of Linux
-   2.5., page+offset is always used, and the "address" field has been
-   deleted.
-2) More to come...
-                        Handling Errors
-DMA address space is limited on some architectures and an allocation
-failure can be determined by:
- checking if pci_alloc_consistent returns NULL or pci_map_sg returns 0
+2) ARCH_KMALLOC_MINALIGN
- checking the returned dma_addr_t of pci_map_single and pci_map_page
+   Architectures must ensure that kmalloc'ed buffer is
-  by using pci_dma_mapping_error():
+   DMA-safe. Drivers and subsystems depend on it. If an architecture
+   isn't fully DMA-coherent (i.e. hardware doesn't ensure that data in
+   the CPU cache is identical to data in main memory),
+   ARCH_KMALLOC_MINALIGN must be set so that the memory allocator
+   makes sure that kmalloc'ed buffer doesn't share a cache line with
+   the others. See arch/arm/include/asm/cache.h as an example.
-        dma_addr_t dma_handle;
+   Note that ARCH_KMALLOC_MINALIGN is about DMA memory alignment
+   constraints. You don't need to worry about the architecture data
-        dma_handle = pci_map_single(pdev, addr, size, direction);
+   alignment constraints (e.g. the alignment constraints about 64-bit
-        if (pci_dma_mapping_error(pdev, dma_handle)) {
+   objects).
-                /*
-                 * reduce current DMA mapping usage,
-                 * delay and try again later or
-                 * reset driver.
-                 */
-        }
                           Closing
-This document, and the API itself, would not be in it's current
+This document, and the API itself, would not be in its current
 form without the feedback and suggestions from numerous individuals.
 We would like to specifically mention, in no particular order, the
 following people:
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 5aceb88b3f8b..05e2ae236865 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -4,20 +4,18 @@
        James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
 This document describes the DMA API.  For a more gentle introduction
-phrased in terms of the pci_ equivalents (and actual examples) see
+of the API (and actual examples) see
-Documentation/PCI/PCI-DMA-mapping.txt.
+Documentation/DMA-API-HOWTO.txt.
-This API is split into two pieces.  Part I describes the API and the
+This API is split into two pieces.  Part I describes the API.  Part II
-corresponding pci_ API.  Part II describes the extensions to the API
+describes the extensions to the API for supporting non-consistent
-for supporting non-consistent memory machines.  Unless you know that
+memory machines.  Unless you know that your driver absolutely has to
-your driver absolutely has to support non-consistent platforms (this
+support non-consistent platforms (this is usually only legacy
-is usually only legacy platforms) you should only use the API
+platforms) you should only use the API described in part I.
-described in part I.
-Part I - pci_ and dma_ Equivalent API 
+Part I - dma_ API
 -------------------------------------
-To get the pci_ API, you must #include <linux/pci.h>
 To get the dma_ API, you must #include <linux/dma-mapping.h>
@@ -27,9 +25,6 @@ Part Ia - Using large dma-coherent buffers
 void *
 dma_alloc_coherent(struct device *dev, size_t size,
                             dma_addr_t *dma_handle, gfp_t flag)
-void *
-pci_alloc_consistent(struct pci_dev *dev, size_t size,
-                             dma_addr_t *dma_handle)
 Consistent memory is memory for which a write by either the device or
 the processor can immediately be read by the processor or device
@@ -53,15 +48,11 @@ The simplest way to do that is to use the dma_pool calls (see below).
 The flag parameter (dma_alloc_coherent only) allows the caller to
 specify the GFP_ flags (see kmalloc) for the allocation (the
 implementation may choose to ignore flags that affect the location of
-the returned memory, like GFP_DMA).  For pci_alloc_consistent, you
+the returned memory, like GFP_DMA).
-must assume GFP_ATOMIC behaviour.
 void
 dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
                           dma_addr_t dma_handle)
-void
-pci_free_consistent(struct pci_dev *dev, size_t size, void *cpu_addr,
-                           dma_addr_t dma_handle)
 Free the region of consistent memory you previously allocated.  dev,
 size and dma_handle must all be the same as those passed into the
@@ -89,10 +80,6 @@ for alignment, like queue heads needing to be aligned on N-byte boundaries.
        dma_pool_create(const char *name, struct device *dev,
                        size_t size, size_t align, size_t alloc);
-        struct pci_pool *
-        pci_pool_create(const char *name, struct pci_device *dev,
-                        size_t size, size_t align, size_t alloc);
 The pool create() routines initialize a pool of dma-coherent buffers
 for use with a given device.  It must be called in a context which
 can sleep.
@@ -108,9 +95,6 @@ from this pool must not cross 4KByte boundaries.
        void *dma_pool_alloc(struct dma_pool *pool, gfp_t gfp_flags,
                        dma_addr_t *dma_handle);
-        void *pci_pool_alloc(struct pci_pool *pool, gfp_t gfp_flags,
-                        dma_addr_t *dma_handle);
 This allocates memory from the pool; the returned memory will meet the size
 and alignment requirements specified at creation time.  Pass GFP_ATOMIC to
 prevent blocking, or if it's permitted (not in_interrupt, not holding SMP locks),
@@ -122,9 +106,6 @@ pool's device.
        void dma_pool_free(struct dma_pool *pool, void *vaddr,
                        dma_addr_t addr);
-        void pci_pool_free(struct pci_pool *pool, void *vaddr,
-                        dma_addr_t addr);
 This puts memory back into the pool.  The pool is what was passed to
 the pool allocation routine; the cpu (vaddr) and dma addresses are what
 were returned when that routine allocated the memory being freed.
@@ -132,8 +113,6 @@ were returned when that routine allocated the memory being freed.
        void dma_pool_destroy(struct dma_pool *pool);
-        void pci_pool_destroy(struct pci_pool *pool);
 The pool destroy() routines free the resources of the pool.  They must be
 called in a context which can sleep.  Make sure you've freed all allocated
 memory back to the pool before you destroy it.
@@ -144,8 +123,6 @@ Part Ic - DMA addressing limitations
 int
 dma_supported(struct device *dev, u64 mask)
-int
-pci_dma_supported(struct pci_dev *hwdev, u64 mask)
 Checks to see if the device can support DMA to the memory described by
 mask.
@@ -159,8 +136,14 @@ driver writers.
 int
 dma_set_mask(struct device *dev, u64 mask)
+Checks to see if the mask is possible and updates the device
+parameters if it is.
+Returns: 0 if successful and a negative error if not.
 int
-pci_set_dma_mask(struct pci_device *dev, u64 mask)
+dma_set_coherent_mask(struct device *dev, u64 mask)
 Checks to see if the mask is possible and updates the device
 parameters if it is.
@@ -187,9 +170,6 @@ Part Id - Streaming DMA mappings
 dma_addr_t
 dma_map_single(struct device *dev, void *cpu_addr, size_t size,
                      enum dma_data_direction direction)
-dma_addr_t
-pci_map_single(struct pci_dev *hwdev, void *cpu_addr, size_t size,
-                      int direction)
 Maps a piece of processor virtual memory so it can be accessed by the
 device and returns the physical handle of the memory.
@@ -198,14 +178,10 @@ The direction for both api's may be converted freely by casting.
 However the dma_ API uses a strongly typed enumerator for its
 direction:
-DMA_NONE                = PCI_DMA_NONE          no direction (used for
+DMA_NONE                no direction (used for debugging)
-                                                debugging)
+DMA_TO_DEVICE           data is going from the memory to the device
-DMA_TO_DEVICE           = PCI_DMA_TODEVICE      data is going from the
+DMA_FROM_DEVICE         data is coming from the device to the memory
-                                                memory to the device
+DMA_BIDIRECTIONAL       direction isn't known
-DMA_FROM_DEVICE         = PCI_DMA_FROMDEVICE    data is coming from
-                                                the device to the
-                                                memory
-DMA_BIDIRECTIONAL       = PCI_DMA_BIDIRECTIONAL direction isn't known
 Notes:  Not all memory regions in a machine can be mapped by this
 API.  Further, regions that appear to be physically contiguous in
@@ -268,9 +244,6 @@ cache lines are updated with data that the device may have changed).
 void
 dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
                 enum dma_data_direction direction)
-void
-pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr,
-                 size_t size, int direction)
 Unmaps the region previously mapped.  All the parameters passed in
 must be identical to those passed in (and returned) by the mapping
@@ -280,15 +253,9 @@ dma_addr_t
 dma_map_page(struct device *dev, struct page *page,
                    unsigned long offset, size_t size,
                    enum dma_data_direction direction)
-dma_addr_t
-pci_map_page(struct pci_dev *hwdev, struct page *page,
-                    unsigned long offset, size_t size, int direction)
 void
 dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
               enum dma_data_direction direction)
-void
-pci_unmap_page(struct pci_dev *hwdev, dma_addr_t dma_address,
-               size_t size, int direction)
 API for mapping and unmapping for pages.  All the notes and warnings
 for the other mapping APIs apply here.  Also, although the <offset>
@@ -299,9 +266,6 @@ cache width is.
 int
 dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-int
-pci_dma_mapping_error(struct pci_dev *hwdev, dma_addr_t dma_addr)
 In some circumstances dma_map_single and dma_map_page will fail to create
 a mapping. A driver can check for these errors by testing the returned
 dma address with dma_mapping_error(). A non-zero return value means the mapping
@@ -311,9 +275,6 @@ reduce current DMA mapping usage or delay and try again later).
        int
        dma_map_sg(struct device *dev, struct scatterlist *sg,
                int nents, enum dma_data_direction direction)
-        int
-        pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg,
-                int nents, int direction)
 Returns: the number of physical segments mapped (this may be shorter
 than <nents> passed in if some elements of the scatter/gather list are
@@ -353,9 +314,6 @@ accessed sg->address and sg->length as shown above.
        void
        dma_unmap_sg(struct device *dev, struct scatterlist *sg,
                int nhwentries, enum dma_data_direction direction)
-        void
-        pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg,
-                int nents, int direction)
 Unmap the previously mapped scatter/gather list.  All the parameters
 must be the same as those and passed in to the scatter/gather mapping
@@ -365,21 +323,23 @@ Note: <nents> must be the number you passed in, *not* the number of
 physical entries returned.
 void
-dma_sync_single(struct device *dev, dma_addr_t dma_handle, size_t size,
+dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
-                enum dma_data_direction direction)
+                        enum dma_data_direction direction)
 void
-pci_dma_sync_single(struct pci_dev *hwdev, dma_addr_t dma_handle,
+dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size,
-                           size_t size, int direction)
+                           enum dma_data_direction direction)
 void
-dma_sync_sg(struct device *dev, struct scatterlist *sg, int nelems,
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
-                          enum dma_data_direction direction)
+                    enum dma_data_direction direction)
 void
-pci_dma_sync_sg(struct pci_dev *hwdev, struct scatterlist *sg,
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
-                       int nelems, int direction)
+                       enum dma_data_direction direction)
-Synchronise a single contiguous or scatter/gather mapping.  All the
+Synchronise a single contiguous or scatter/gather mapping for the cpu
-parameters must be the same as those passed into the single mapping
+and device. With the sync_sg API, all the parameters must be the same
-API.
+as those passed into the single mapping API. With the sync_single API,
+you can use dma_handle and size parameters that aren't identical to
+those passed into the single mapping API to do a partial sync.
 Notes:  You must do this:
@@ -461,9 +421,9 @@ void whizco_dma_map_sg_attrs(struct device *dev, dma_addr_t dma_addr,
 Part II - Advanced dma_ usage
 -----------------------------
-Warning: These pieces of the DMA API have no PCI equivalent.  They
+Warning: These pieces of the DMA API should not be used in the
-should also not be used in the majority of cases, since they cater for
+majority of cases, since they cater for unlikely corner cases that
-unlikely corner cases that don't belong in usual drivers.
+don't belong in usual drivers.
 If you don't understand how cache line coherency works between a
 processor and an I/O device, you should not be using this part of the
@@ -514,16 +474,6 @@ into the width returned by this call.  It will also always be a power
 of two for easy alignment.
 void
-dma_sync_single_range(struct device *dev, dma_addr_t dma_handle,
-                      unsigned long offset, size_t size,
-                      enum dma_data_direction direction)
-Does a partial sync, starting at offset and continuing for size.  You
-must be careful to observe the cache alignment and width when doing
-anything like this.  You must also be extra careful about accessing
-memory you intend to sync partially.
-void
 dma_cache_sync(struct device *dev, void *vaddr, size_t size,
               enum dma_data_direction direction)
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index 325cfd1d6d99..c7e5dc7e8cb3 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -14,7 +14,7 @@ DOCBOOKS := z8530book.xml mcabook.xml device-drivers.xml \
            genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
            mac80211.xml debugobjects.xml sh.xml regulator.xml \
            alsa-driver-api.xml writing-an-alsa-driver.xml \
-            tracepoint.xml media.xml
+            tracepoint.xml media.xml drm.xml
 ###
 # The build process is as follows (targets):
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index f9a6e2c75f12..1b2dd4fc3db2 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -45,7 +45,7 @@
     </sect1>
     <sect1><title>Atomic and pointer manipulation</title>
-!Iarch/x86/include/asm/atomic_32.h
+!Iarch/x86/include/asm/atomic.h
 !Iarch/x86/include/asm/unaligned.h
     </sect1>
diff --git a/Documentation/DocBook/deviceiobook.tmpl b/Documentation/DocBook/deviceiobook.tmpl
index 3ed88126ab8f..c1ed6a49e598 100644
--- a/Documentation/DocBook/deviceiobook.tmpl
+++ b/Documentation/DocBook/deviceiobook.tmpl
@@ -316,7 +316,7 @@ CPU B:  spin_unlock_irqrestore(&amp;dev_lock, flags)
  <chapter id="pubfunctions">
     <title>Public Functions Provided</title>
-!Iarch/x86/include/asm/io_32.h
+!Iarch/x86/include/asm/io.h
 !Elib/iomap.c
  </chapter>
diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
new file mode 100644
index 000000000000..7583dc7cf64d
--- /dev/null
+++ b/Documentation/DocBook/drm.tmpl
@@ -0,0 +1,839 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
+        "http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
+<book id="drmDevelopersGuide">
+  <bookinfo>
+    <title>Linux DRM Developer's Guide</title>
+    <copyright>
+      <year>2008-2009</year>
+      <holder>
+        Intel Corporation (Jesse Barnes &lt;jesse.barnes@intel.com&gt;)
+      </holder>
+    </copyright>
+    <legalnotice>
+      <para>
+        The contents of this file may be used under the terms of the GNU
+        General Public License version 2 (the "GPL") as distributed in
+        the kernel source COPYING file.
+      </para>
+    </legalnotice>
+  </bookinfo>
+<toc></toc>
+  <!-- Introduction -->
+  <chapter id="drmIntroduction">
+    <title>Introduction</title>
+    <para>
+      The Linux DRM layer contains code intended to support the needs
+      of complex graphics devices, usually containing programmable
+      pipelines well suited to 3D graphics acceleration.  Graphics
+      drivers in the kernel can make use of DRM functions to make
+      tasks like memory management, interrupt handling and DMA easier,
+      and provide a uniform interface to applications.
+    </para>
+    <para>
+      A note on versions: this guide covers features found in the DRM
+      tree, including the TTM memory manager, output configuration and
+      mode setting, and the new vblank internals, in addition to all
+      the regular features found in current kernels.
+    </para>
+    <para>
+      [Insert diagram of typical DRM stack here]
+    </para>
+  </chapter>
+  <!-- Internals -->
+  <chapter id="drmInternals">
+    <title>DRM Internals</title>
+    <para>
+      This chapter documents DRM internals relevant to driver authors
+      and developers working to add support for the latest features to
+      existing drivers.
+    </para>
+    <para>
+      First, we'll go over some typical driver initialization
+      requirements, like setting up command buffers, creating an
+      initial output configuration, and initializing core services.
+      Subsequent sections will cover core internals in more detail,
+      providing implementation notes and examples.
+    </para>
+    <para>
+      The DRM layer provides several services to graphics drivers,
+      many of them driven by the application interfaces it provides
+      through libdrm, the library that wraps most of the DRM ioctls.
+      These include vblank event handling, memory
+      management, output management, framebuffer management, command
+      submission &amp; fencing, suspend/resume support, and DMA
+      services.
+    </para>
+    <para>
+      The core of every DRM driver is struct drm_device.  Drivers
+      will typically statically initialize a drm_device structure,
+      then pass it to drm_init() at load time.
+    </para>
+  <!-- Internals: driver init -->
+  <sect1>
+    <title>Driver initialization</title>
+    <para>
+      Before calling the DRM initialization routines, the driver must
+      first create and fill out a struct drm_device structure.
+    </para>
+    <programlisting>
+      static struct drm_driver driver = {
+        /* don't use mtrr's here, the Xserver or user space app should
+         * deal with them for intel hardware.
+         */
+        .driver_features =
+            DRIVER_USE_AGP | DRIVER_REQUIRE_AGP |
+            DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_MODESET,
+        .load = i915_driver_load,
+        .unload = i915_driver_unload,
+        .firstopen = i915_driver_firstopen,
+        .lastclose = i915_driver_lastclose,
+        .preclose = i915_driver_preclose,
+        .save = i915_save,
+        .restore = i915_restore,
+        .device_is_agp = i915_driver_device_is_agp,
+        .get_vblank_counter = i915_get_vblank_counter,
+        .enable_vblank = i915_enable_vblank,
+        .disable_vblank = i915_disable_vblank,
+        .irq_preinstall = i915_driver_irq_preinstall,
+        .irq_postinstall = i915_driver_irq_postinstall,
+        .irq_uninstall = i915_driver_irq_uninstall,
+        .irq_handler = i915_driver_irq_handler,
+        .reclaim_buffers = drm_core_reclaim_buffers,
+        .get_map_ofs = drm_core_get_map_ofs,
+        .get_reg_ofs = drm_core_get_reg_ofs,
+        .fb_probe = intelfb_probe,
+        .fb_remove = intelfb_remove,
+        .fb_resize = intelfb_resize,
+        .master_create = i915_master_create,
+        .master_destroy = i915_master_destroy,
+#if defined(CONFIG_DEBUG_FS)
+        .debugfs_init = i915_debugfs_init,
+        .debugfs_cleanup = i915_debugfs_cleanup,
+#endif
+        .gem_init_object = i915_gem_init_object,
+        .gem_free_object = i915_gem_free_object,
+        .gem_vm_ops = &amp;i915_gem_vm_ops,
+        .ioctls = i915_ioctls,
+        .fops = {
+                .owner = THIS_MODULE,
+                .open = drm_open,
+                .release = drm_release,
+                .ioctl = drm_ioctl,
+                .mmap = drm_mmap,
+                .poll = drm_poll,
+                .fasync = drm_fasync,
+#ifdef CONFIG_COMPAT
+                .compat_ioctl = i915_compat_ioctl,
+#endif
+                },
+        .pci_driver = {
+                .name = DRIVER_NAME,
+                .id_table = pciidlist,
+                .probe = probe,
+                .remove = __devexit_p(drm_cleanup_pci),
+                },
+        .name = DRIVER_NAME,
+        .desc = DRIVER_DESC,
+        .date = DRIVER_DATE,
+        .major = DRIVER_MAJOR,
+        .minor = DRIVER_MINOR,
+        .patchlevel = DRIVER_PATCHLEVEL,
+      };
+    </programlisting>
+    <para>
+      In the example above, taken from the i915 DRM driver, the driver
+      sets several flags indicating what core features it supports.
+      We'll go over the individual callbacks in later sections.  Since
+      flags indicate which features your driver supports to the DRM
+      core, you need to set most of them prior to calling drm_init().  Some,
+      like DRIVER_MODESET can be set later based on user supplied parameters,
+      but that's the exception rather than the rule.
+    </para>
+    <variablelist>
+      <title>Driver flags</title>
+      <varlistentry>
+        <term>DRIVER_USE_AGP</term>
+        <listitem><para>
+            Driver uses AGP interface
+        </para></listitem>
+      </varlistentry>
+      <varlistentry>
+        <term>DRIVER_REQUIRE_AGP</term>
+        <listitem><para>
+            Driver needs AGP interface to function.
+        </para></listitem>
+      </varlistentry>
+      <varlistentry>
+        <term>DRIVER_USE_MTRR</term>
+        <listitem>
+          <para>
+            Driver uses MTRR interface for mapping memory.  Deprecated.
+          </para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+        <term>DRIVER_PCI_DMA</term>
+        <listitem><para>
+            Driver is capable of PCI DMA.  Deprecated.
+        </para></listitem>
+      </varlistentry>
+      <varlistentry>
+        <term>DRIVER_SG</term>
+        <listitem><para>
+            Driver can perform scatter/gather DMA.  Deprecated.
+        </para></listitem>
+      </varlistentry>
+      <varlistentry>
+        <term>DRIVER_HAVE_DMA</term>
+        <listitem><para>Driver supports DMA.  Deprecated.</para></listitem>
+      </varlistentry>
+      <varlistentry>
+        <term>DRIVER_HAVE_IRQ</term><term>DRIVER_IRQ_SHARED</term>
+        <listitem>
+          <para>
+            DRIVER_HAVE_IRQ indicates whether the driver has a IRQ
+            handler, DRIVER_IRQ_SHARED indicates whether the device &amp;
+            handler support shared IRQs (note that this is required of
+            PCI drivers).
+          </para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+        <term>DRIVER_DMA_QUEUE</term>
+        <listitem>
+          <para>
+            If the driver queues DMA requests and completes them
+            asynchronously, this flag should be set.  Deprecated.
+          </para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+        <term>DRIVER_FB_DMA</term>
+        <listitem>
+          <para>
+            Driver supports DMA to/from the framebuffer.  Deprecated.
+          </para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+        <term>DRIVER_MODESET</term>
+        <listitem>
+          <para>
+            Driver supports mode setting interfaces.
+          </para>
+        </listitem>
+      </varlistentry>
+    </variablelist>
+    <para>
+      In this specific case, the driver requires AGP and supports
+      IRQs.  DMA, as we'll see, is handled by device specific ioctls
+      in this case.  It also supports the kernel mode setting APIs, though
+      unlike in the actual i915 driver source, this example unconditionally
+      exports KMS capability.
+    </para>
+  </sect1>
+  <!-- Internals: driver load -->
+  <sect1>
+    <title>Driver load</title>
+    <para>
+      In the previous section, we saw what a typical drm_driver
+      structure might look like.  One of the more important fields in
+      the structure is the hook for the load function.
+    </para>
+    <programlisting>
+      static struct drm_driver driver = {
+        ...
+        .load = i915_driver_load,
+        ...
+      };
+    </programlisting>
+    <para>
+      The load function has many responsibilities: allocating a driver
+      private structure, specifying supported performance counters,
+      configuring the device (e.g. mapping registers &amp; command
+      buffers), initializing the memory manager, and setting up the
+      initial output configuration.
+    </para>
+    <para>
+      Note that the tasks performed at driver load time must not
+      conflict with DRM client requirements.  For instance, if user
+      level mode setting drivers are in use, it would be problematic
+      to perform output discovery &amp; configuration at load time.
+      Likewise, if pre-memory management aware user level drivers are
+      in use, memory management and command buffer setup may need to
+      be omitted.  These requirements are driver specific, and care
+      needs to be taken to keep both old and new applications and
+      libraries working.  The i915 driver supports the "modeset"
+      module parameter to control whether advanced features are
+      enabled at load time or in legacy fashion.  If compatibility is
+      a concern (e.g. with drivers converted over to the new interfaces
+      from the old ones), care must be taken to prevent incompatible
+      device initialization and control with the currently active
+      userspace drivers.
+    </para>
+    <sect2>
+      <title>Driver private &amp; performance counters</title>
+      <para>
+        The driver private hangs off the main drm_device structure and
+        can be used for tracking various device specific bits of
+        information, like register offsets, command buffer status,
+        register state for suspend/resume, etc.  At load time, a
+        driver can simply allocate one and set drm_device.dev_priv
+        appropriately; at unload the driver can free it and set
+        drm_device.dev_priv to NULL.
+      </para>
+      <para>
+        The DRM supports several counters which can be used for rough
+        performance characterization.  Note that the DRM stat counter
+        system is not often used by applications, and supporting
+        additional counters is completely optional.
+      </para>
+      <para>
+        These interfaces are deprecated and should not be used.  If performance
+        monitoring is desired, the developer should investigate and
+        potentially enhance the kernel perf and tracing infrastructure to export
+        GPU related performance information to performance monitoring
+        tools and applications.
+      </para>
+    </sect2>
+    <sect2>
+      <title>Configuring the device</title>
+      <para>
+        Obviously, device configuration will be device specific.
+        However, there are several common operations: finding a
+        device's PCI resources, mapping them, and potentially setting
+        up an IRQ handler.
+      </para>
+      <para>
+        Finding &amp; mapping resources is fairly straightforward.  The
+        DRM wrapper functions, drm_get_resource_start() and
+        drm_get_resource_len() can be used to find BARs on the given
+        drm_device struct.  Once those values have been retrieved, the
+        driver load function can call drm_addmap() to create a new
+        mapping for the BAR in question.  Note you'll probably want a
+        drm_local_map_t in your driver private structure to track any
+        mappings you create.
+<!-- !Fdrivers/gpu/drm/drm_bufs.c drm_get_resource_* -->
+<!-- !Finclude/drm/drmP.h drm_local_map_t -->
+      </para>
+      <para>
+        if compatibility with other operating systems isn't a concern
+        (DRM drivers can run under various BSD variants and OpenSolaris),
+        native Linux calls can be used for the above, e.g. pci_resource_*
+        and iomap*/iounmap.  See the Linux device driver book for more
+        info.
+      </para>
+      <para>
+        Once you have a register map, you can use the DRM_READn() and
+        DRM_WRITEn() macros to access the registers on your device, or
+        use driver specific versions to offset into your MMIO space
+        relative to a driver specific base pointer (see I915_READ for
+        example).
+      </para>
+      <para>
+        If your device supports interrupt generation, you may want to
+        setup an interrupt handler at driver load time as well.  This
+        is done using the drm_irq_install() function.  If your device
+        supports vertical blank interrupts, it should call
+        drm_vblank_init() to initialize the core vblank handling code before
+        enabling interrupts on your device.  This ensures the vblank related
+        structures are allocated and allows the core to handle vblank events.
+      </para>
+<!--!Fdrivers/char/drm/drm_irq.c drm_irq_install-->
+      <para>
+        Once your interrupt handler is registered (it'll use your
+        drm_driver.irq_handler as the actual interrupt handling
+        function), you can safely enable interrupts on your device,
+        assuming any other state your interrupt handler uses is also
+        initialized.
+      </para>
+      <para>
+        Another task that may be necessary during configuration is
+        mapping the video BIOS.  On many devices, the VBIOS describes
+        device configuration, LCD panel timings (if any), and contains
+        flags indicating device state.  Mapping the BIOS can be done
+        using the pci_map_rom() call, a convenience function that
+        takes care of mapping the actual ROM, whether it has been
+        shadowed into memory (typically at address 0xc0000) or exists
+        on the PCI device in the ROM BAR.  Note that once you've
+        mapped the ROM and extracted any necessary information, be
+        sure to unmap it; on many devices the ROM address decoder is
+        shared with other BARs, so leaving it mapped can cause
+        undesired behavior like hangs or memory corruption.
+<!--!Fdrivers/pci/rom.c pci_map_rom-->
+      </para>
+    </sect2>
+    <sect2>
+      <title>Memory manager initialization</title>
+      <para>
+        In order to allocate command buffers, cursor memory, scanout
+        buffers, etc., as well as support the latest features provided
+        by packages like Mesa and the X.Org X server, your driver
+        should support a memory manager.
+      </para>
+      <para>
+        If your driver supports memory management (it should!), you'll
+        need to set that up at load time as well.  How you intialize
+        it depends on which memory manager you're using, TTM or GEM.
+      </para>
+      <sect3>
+        <title>TTM initialization</title>
+        <para>
+          TTM (for Translation Table Manager) manages video memory and
+          aperture space for graphics devices. TTM supports both UMA devices
+          and devices with dedicated video RAM (VRAM), i.e. most discrete
+          graphics devices.  If your device has dedicated RAM, supporting
+          TTM is desireable.  TTM also integrates tightly with your
+          driver specific buffer execution function.  See the radeon
+          driver for examples.
+        </para>
+        <para>
+          The core TTM structure is the ttm_bo_driver struct.  It contains
+          several fields with function pointers for initializing the TTM,
+          allocating and freeing memory, waiting for command completion
+          and fence synchronization, and memory migration.  See the
+          radeon_ttm.c file for an example of usage.
+        </para>
+        <para>
+          The ttm_global_reference structure is made up of several fields:
+        </para>
+        <programlisting>
+          struct ttm_global_reference {
+                enum ttm_global_types global_type;
+                size_t size;
+                void *object;
+                int (*init) (struct ttm_global_reference *);
+                void (*release) (struct ttm_global_reference *);
+          };
+        </programlisting>
+        <para>
+          There should be one global reference structure for your memory
+          manager as a whole, and there will be others for each object
+          created by the memory manager at runtime.  Your global TTM should
+          have a type of TTM_GLOBAL_TTM_MEM.  The size field for the global
+          object should be sizeof(struct ttm_mem_global), and the init and
+          release hooks should point at your driver specific init and
+          release routines, which will probably eventually call
+          ttm_mem_global_init and ttm_mem_global_release respectively.
+        </para>
+        <para>
+          Once your global TTM accounting structure is set up and initialized
+          (done by calling ttm_global_item_ref on the global object you
+          just created), you'll need to create a buffer object TTM to
+          provide a pool for buffer object allocation by clients and the
+          kernel itself.  The type of this object should be TTM_GLOBAL_TTM_BO,
+          and its size should be sizeof(struct ttm_bo_global).  Again,
+          driver specific init and release functions can be provided,
+          likely eventually calling ttm_bo_global_init and
+          ttm_bo_global_release, respectively.  Also like the previous
+          object, ttm_global_item_ref is used to create an initial reference
+          count for the TTM, which will call your initalization function.
+        </para>
+      </sect3>
+      <sect3>
+        <title>GEM initialization</title>
+        <para>
+          GEM is an alternative to TTM, designed specifically for UMA
+          devices.  It has simpler initialization and execution requirements
+          than TTM, but has no VRAM management capability.  Core GEM
+          initialization is comprised of a basic drm_mm_init call to create
+          a GTT DRM MM object, which provides an address space pool for
+          object allocation.  In a KMS configuration, the driver will
+          need to allocate and initialize a command ring buffer following
+          basic GEM initialization.  Most UMA devices have a so-called
+          "stolen" memory region, which provides space for the initial
+          framebuffer and large, contiguous memory regions required by the
+          device.  This space is not typically managed by GEM, and must
+          be initialized separately into its own DRM MM object.
+        </para>
+        <para>
+          Initialization will be driver specific, and will depend on
+          the architecture of the device.  In the case of Intel
+          integrated graphics chips like 965GM, GEM initialization can
+          be done by calling the internal GEM init function,
+          i915_gem_do_init().  Since the 965GM is a UMA device
+          (i.e. it doesn't have dedicated VRAM), GEM will manage
+          making regular RAM available for GPU operations.  Memory set
+          aside by the BIOS (called "stolen" memory by the i915
+          driver) will be managed by the DRM memrange allocator; the
+          rest of the aperture will be managed by GEM.
+          <programlisting>
+            /* Basic memrange allocator for stolen space (aka vram) */
+            drm_memrange_init(&amp;dev_priv->vram, 0, prealloc_size);
+            /* Let GEM Manage from end of prealloc space to end of aperture */
+            i915_gem_do_init(dev, prealloc_size, agp_size);
+          </programlisting>
+<!--!Edrivers/char/drm/drm_memrange.c-->
+        </para>
+        <para>
+          Once the memory manager has been set up, we can allocate the
+          command buffer.  In the i915 case, this is also done with a
+          GEM function, i915_gem_init_ringbuffer().
+        </para>
+      </sect3>
+    </sect2>
+    <sect2>
+      <title>Output configuration</title>
+      <para>
+        The final initialization task is output configuration.  This involves
+        finding and initializing the CRTCs, encoders and connectors
+        for your device, creating an initial configuration and
+        registering a framebuffer console driver.
+      </para>
+      <sect3>
+        <title>Output discovery and initialization</title>
+        <para>
+          Several core functions exist to create CRTCs, encoders and
+          connectors, namely drm_crtc_init(), drm_connector_init() and
+          drm_encoder_init(), along with several "helper" functions to
+          perform common tasks.
+        </para>
+        <para>
+          Connectors should be registered with sysfs once they've been
+          detected and initialized, using the
+          drm_sysfs_connector_add() function.  Likewise, when they're
+          removed from the system, they should be destroyed with
+          drm_sysfs_connector_remove().
+        </para>
+        <programlisting>
+<![CDATA[
+void intel_crt_init(struct drm_device *dev)
+{
+        struct drm_connector *connector;
+        struct intel_output *intel_output;
+        intel_output = kzalloc(sizeof(struct intel_output), GFP_KERNEL);
+        if (!intel_output)
+                return;
+        connector = &intel_output->base;
+        drm_connector_init(dev, &intel_output->base,
+                           &intel_crt_connector_funcs, DRM_MODE_CONNECTOR_VGA);
+        drm_encoder_init(dev, &intel_output->enc, &intel_crt_enc_funcs,
+                         DRM_MODE_ENCODER_DAC);
+        drm_mode_connector_attach_encoder(&intel_output->base,
+                                          &intel_output->enc);
+        /* Set up the DDC bus. */
+        intel_output->ddc_bus = intel_i2c_create(dev, GPIOA, "CRTDDC_A");
+        if (!intel_output->ddc_bus) {
+                dev_printk(KERN_ERR, &dev->pdev->dev, "DDC bus registration "
+                           "failed.\n");
+                return;
+        }
+        intel_output->type = INTEL_OUTPUT_ANALOG;
+        connector->interlace_allowed = 0;
+        connector->doublescan_allowed = 0;
+        drm_encoder_helper_add(&intel_output->enc, &intel_crt_helper_funcs);
+        drm_connector_helper_add(connector, &intel_crt_connector_helper_funcs);
+        drm_sysfs_connector_add(connector);
+}
+]]>
+        </programlisting>
+        <para>
+          In the example above (again, taken from the i915 driver), a
+          CRT connector and encoder combination is created.  A device
+          specific i2c bus is also created, for fetching EDID data and
+          performing monitor detection.  Once the process is complete,
+          the new connector is regsitered with sysfs, to make its
+          properties available to applications.
+        </para>
+        <sect4>
+          <title>Helper functions and core functions</title>
+          <para>
+            Since many PC-class graphics devices have similar display output
+            designs, the DRM provides a set of helper functions to make
+            output management easier.  The core helper routines handle
+            encoder re-routing and disabling of unused functions following
+            mode set.  Using the helpers is optional, but recommended for
+            devices with PC-style architectures (i.e. a set of display planes
+            for feeding pixels to encoders which are in turn routed to
+            connectors).  Devices with more complex requirements needing
+            finer grained management can opt to use the core callbacks
+            directly.
+          </para>
+          <para>
+            [Insert typical diagram here.]  [Insert OMAP style config here.]
+          </para>
+        </sect4>
+        <para>
+          For each encoder, CRTC and connector, several functions must
+          be provided, depending on the object type.  Encoder objects
+          need should provide a DPMS (basically on/off) function, mode fixup
+          (for converting requested modes into native hardware timings),
+          and prepare, set and commit functions for use by the core DRM
+          helper functions.  Connector helpers need to provide mode fetch and
+          validity functions as well as an encoder matching function for
+          returing an ideal encoder for a given connector.  The core
+          connector functions include a DPMS callback, (deprecated)
+          save/restore routines, detection, mode probing, property handling,
+          and cleanup functions.
+        </para>
+<!--!Edrivers/char/drm/drm_crtc.h-->
+<!--!Edrivers/char/drm/drm_crtc.c-->
+<!--!Edrivers/char/drm/drm_crtc_helper.c-->
+      </sect3>
+    </sect2>
+  </sect1>
+  <!-- Internals: vblank handling -->
+  <sect1>
+    <title>VBlank event handling</title>
+    <para>
+      The DRM core exposes two vertical blank related ioctls:
+      DRM_IOCTL_WAIT_VBLANK and DRM_IOCTL_MODESET_CTL.
+<!--!Edrivers/char/drm/drm_irq.c-->
+    </para>
+    <para>
+      DRM_IOCTL_WAIT_VBLANK takes a struct drm_wait_vblank structure
+      as its argument, and is used to block or request a signal when a
+      specified vblank event occurs.
+    </para>
+    <para>
+      DRM_IOCTL_MODESET_CTL should be called by application level
+      drivers before and after mode setting, since on many devices the
+      vertical blank counter will be reset at that time.  Internally,
+      the DRM snapshots the last vblank count when the ioctl is called
+      with the _DRM_PRE_MODESET command so that the counter won't go
+      backwards (which is dealt with when _DRM_POST_MODESET is used).
+    </para>
+    <para>
+      To support the functions above, the DRM core provides several
+      helper functions for tracking vertical blank counters, and
+      requires drivers to provide several callbacks:
+      get_vblank_counter(), enable_vblank() and disable_vblank().  The
+      core uses get_vblank_counter() to keep the counter accurate
+      across interrupt disable periods.  It should return the current
+      vertical blank event count, which is often tracked in a device
+      register.  The enable and disable vblank callbacks should enable
+      and disable vertical blank interrupts, respectively.  In the
+      absence of DRM clients waiting on vblank events, the core DRM
+      code will use the disable_vblank() function to disable
+      interrupts, which saves power.  They'll be re-enabled again when
+      a client calls the vblank wait ioctl above.
+    </para>
+    <para>
+      Devices that don't provide a count register can simply use an
+      internal atomic counter incremented on every vertical blank
+      interrupt, and can make their enable and disable vblank
+      functions into no-ops.
+    </para>
+  </sect1>
+  <sect1>
+    <title>Memory management</title>
+    <para>
+      The memory manager lies at the heart of many DRM operations, and
+      is also required to support advanced client features like OpenGL
+      pbuffers.  The DRM currently contains two memory managers, TTM
+      and GEM.
+    </para>
+    <sect2>
+      <title>The Translation Table Manager (TTM)</title>
+      <para>
+        TTM was developed by Tungsten Graphics, primarily by Thomas
+        Hellström, and is intended to be a flexible, high performance
+        graphics memory manager.
+      </para>
+      <para>
+        Drivers wishing to support TTM must fill out a drm_bo_driver
+        structure.
+      </para>
+      <para>
+        TTM design background and information belongs here.
+      </para>
+    </sect2>
+    <sect2>
+      <title>The Graphics Execution Manager (GEM)</title>
+      <para>
+        GEM is an Intel project, authored by Eric Anholt and Keith
+        Packard.  It provides simpler interfaces than TTM, and is well
+        suited for UMA devices.
+      </para>
+      <para>
+        GEM-enabled drivers must provide gem_init_object() and
+        gem_free_object() callbacks to support the core memory
+        allocation routines.  They should also provide several driver
+        specific ioctls to support command execution, pinning, buffer
+        read &amp; write, mapping, and domain ownership transfers.
+      </para>
+      <para>
+        On a fundamental level, GEM involves several operations: memory
+        allocation and freeing, command execution, and aperture management
+        at command execution time.  Buffer object allocation is relatively
+        straightforward and largely provided by Linux's shmem layer, which
+        provides memory to back each object.  When mapped into the GTT
+        or used in a command buffer, the backing pages for an object are
+        flushed to memory and marked write combined so as to be coherent
+        with the GPU.  Likewise, when the GPU finishes rendering to an object,
+        if the CPU accesses it, it must be made coherent with the CPU's view
+        of memory, usually involving GPU cache flushing of various kinds.
+        This core CPU&lt;-&gt;GPU coherency management is provided by the GEM
+        set domain function, which evaluates an object's current domain and
+        performs any necessary flushing or synchronization to put the object
+        into the desired coherency domain (note that the object may be busy,
+        i.e. an active render target; in that case the set domain function
+        will block the client and wait for rendering to complete before
+        performing any necessary flushing operations).
+      </para>
+      <para>
+        Perhaps the most important GEM function is providing a command
+        execution interface to clients.  Client programs construct command
+        buffers containing references to previously allocated memory objects
+        and submit them to GEM.  At that point, GEM will take care to bind
+        all the objects into the GTT, execute the buffer, and provide
+        necessary synchronization between clients accessing the same buffers.
+        This often involves evicting some objects from the GTT and re-binding
+        others (a fairly expensive operation), and providing relocation
+        support which hides fixed GTT offsets from clients.  Clients must
+        take care not to submit command buffers that reference more objects
+        than can fit in the GTT or GEM will reject them and no rendering
+        will occur.  Similarly, if several objects in the buffer require
+        fence registers to be allocated for correct rendering (e.g. 2D blits
+        on pre-965 chips), care must be taken not to require more fence
+        registers than are available to the client.  Such resource management
+        should be abstracted from the client in libdrm.
+      </para>
+    </sect2>
+  </sect1>
+  <!-- Output management -->
+  <sect1>
+    <title>Output management</title>
+    <para>
+      At the core of the DRM output management code is a set of
+      structures representing CRTCs, encoders and connectors.
+    </para>
+    <para>
+      A CRTC is an abstraction representing a part of the chip that
+      contains a pointer to a scanout buffer.  Therefore, the number
+      of CRTCs available determines how many independent scanout
+      buffers can be active at any given time.  The CRTC structure
+      contains several fields to support this: a pointer to some video
+      memory, a display mode, and an (x, y) offset into the video
+      memory to support panning or configurations where one piece of
+      video memory spans multiple CRTCs.
+    </para>
+    <para>
+      An encoder takes pixel data from a CRTC and converts it to a
+      format suitable for any attached connectors.  On some devices,
+      it may be possible to have a CRTC send data to more than one
+      encoder.  In that case, both encoders would receive data from
+      the same scanout buffer, resulting in a "cloned" display
+      configuration across the connectors attached to each encoder.
+    </para>
+    <para>
+      A connector is the final destination for pixel data on a device,
+      and usually connects directly to an external display device like
+      a monitor or laptop panel.  A connector can only be attached to
+      one encoder at a time.  The connector is also the structure
+      where information about the attached display is kept, so it
+      contains fields for display data, EDID data, DPMS &amp;
+      connection status, and information about modes supported on the
+      attached displays.
+    </para>
+<!--!Edrivers/char/drm/drm_crtc.c-->
+  </sect1>
+  <sect1>
+    <title>Framebuffer management</title>
+    <para>
+      In order to set a mode on a given CRTC, encoder and connector
+      configuration, clients need to provide a framebuffer object which
+      will provide a source of pixels for the CRTC to deliver to the encoder(s)
+      and ultimately the connector(s) in the configuration.  A framebuffer
+      is fundamentally a driver specific memory object, made into an opaque
+      handle by the DRM addfb function.  Once an fb has been created this
+      way it can be passed to the KMS mode setting routines for use in
+      a configuration.
+    </para>
+  </sect1>
+  <sect1>
+    <title>Command submission &amp; fencing</title>
+    <para>
+      This should cover a few device specific command submission
+      implementations.
+    </para>
+  </sect1>
+  <sect1>
+    <title>Suspend/resume</title>
+    <para>
+      The DRM core provides some suspend/resume code, but drivers
+      wanting full suspend/resume support should provide save() and
+      restore() functions.  These will be called at suspend,
+      hibernate, or resume time, and should perform any state save or
+      restore required by your device across suspend or hibernate
+      states.
+    </para>
+  </sect1>
+  <sect1>
+    <title>DMA services</title>
+    <para>
+      This should cover how DMA mapping etc. is supported by the core.
+      These functions are deprecated and should not be used.
+    </para>
+  </sect1>
+  </chapter>
+  <!-- External interfaces -->
+  <chapter id="drmExternals">
+    <title>Userland interfaces</title>
+    <para>
+      The DRM core exports several interfaces to applications,
+      generally intended to be used through corresponding libdrm
+      wrapper functions.  In addition, drivers export device specific
+      interfaces for use by userspace drivers &amp; device aware
+      applications through ioctls and sysfs files.
+    </para>
+    <para>
+      External interfaces include: memory mapping, context management,
+      DMA operations, AGP management, vblank control, fence
+      management, memory management, and output management.
+    </para>
+    <para>
+      Cover generic ioctls and sysfs layout here.  Only need high
+      level info, since man pages will cover the rest.
+    </para>
+  </chapter>
+  <!-- API reference -->
+  <appendix id="drmDriverApi">
+    <title>DRM Driver API</title>
+    <para>
+      Include auto-generated API reference here (need to reference it
+      from paragraphs above too).
+    </para>
+  </appendix>
+</book>
diff --git a/Documentation/DocBook/kgdb.tmpl b/Documentation/DocBook/kgdb.tmpl
index 5cff41a5fa7c..55f12ac37acd 100644
--- a/Documentation/DocBook/kgdb.tmpl
+++ b/Documentation/DocBook/kgdb.tmpl
@@ -4,7 +4,7 @@
 <book id="kgdbOnLinux">
 <bookinfo>
-  <title>Using kgdb and the kgdb Internals</title>
+  <title>Using kgdb, kdb and the kernel debugger internals</title>
  <authorgroup>
   <author>
@@ -17,33 +17,8 @@
    </affiliation>
   </author>
  </authorgroup>
-  <authorgroup>
-   <author>
-    <firstname>Tom</firstname>
-    <surname>Rini</surname>
-    <affiliation>
-     <address>
-      <email>trini@kernel.crashing.org</email>
-     </address>
-    </affiliation>
-   </author>
-  </authorgroup>
-  <authorgroup>
-   <author>
-    <firstname>Amit S.</firstname>
-    <surname>Kale</surname>
-    <affiliation>
-     <address>
-      <email>amitkale@linsyssoft.com</email>
-     </address>
-    </affiliation>
-   </author>
-  </authorgroup>
  <copyright>
-   <year>2008</year>
+   <year>2008,2010</year>
   <holder>Wind River Systems, Inc.</holder>
  </copyright>
  <copyright>
@@ -69,41 +44,76 @@
  <chapter id="Introduction">
    <title>Introduction</title>
    <para>
-    kgdb is a source level debugger for linux kernel. It is used along
+    The kernel has two different debugger front ends (kdb and kgdb)
-    with gdb to debug a linux kernel.  The expectation is that gdb can
+    which interface to the debug core.  It is possible to use either
-    be used to "break in" to the kernel to inspect memory, variables
+    of the debugger front ends and dynamically transition between them
-    and look through call stack information similar to what an
+    if you configure the kernel properly at compile and runtime.
-    application developer would use gdb for.  It is possible to place
+    </para>
-    breakpoints in kernel code and perform some limited execution
+    <para>
-    stepping.
+    Kdb is simplistic shell-style interface which you can use on a
+    system console with a keyboard or serial console.  You can use it
+    to inspect memory, registers, process lists, dmesg, and even set
+    breakpoints to stop in a certain location.  Kdb is not a source
+    level debugger, although you can set breakpoints and execute some
+    basic kernel run control.  Kdb is mainly aimed at doing some
+    analysis to aid in development or diagnosing kernel problems.  You
+    can access some symbols by name in kernel built-ins or in kernel
+    modules if the code was built
+    with <symbol>CONFIG_KALLSYMS</symbol>.
+    </para>
+    <para>
+    Kgdb is intended to be used as a source level debugger for the
+    Linux kernel. It is used along with gdb to debug a Linux kernel.
+    The expectation is that gdb can be used to "break in" to the
+    kernel to inspect memory, variables and look through call stack
+    information similar to the way an application developer would use
+    gdb to debug an application.  It is possible to place breakpoints
+    in kernel code and perform some limited execution stepping.
    </para>
    <para>
-    Two machines are required for using kgdb. One of these machines is a
+    Two machines are required for using kgdb. One of these machines is
-    development machine and the other is a test machine.  The kernel
+    a development machine and the other is the target machine.  The
-    to be debugged runs on the test machine. The development machine
+    kernel to be debugged runs on the target machine. The development
-    runs an instance of gdb against the vmlinux file which contains
+    machine runs an instance of gdb against the vmlinux file which
-    the symbols (not boot image such as bzImage, zImage, uImage...).
+    contains the symbols (not boot image such as bzImage, zImage,
-    In gdb the developer specifies the connection parameters and
+    uImage...).  In gdb the developer specifies the connection
-    connects to kgdb.  The type of connection a developer makes with
+    parameters and connects to kgdb.  The type of connection a
-    gdb depends on the availability of kgdb I/O modules compiled as
+    developer makes with gdb depends on the availability of kgdb I/O
-    builtin's or kernel modules in the test machine's kernel.
+    modules compiled as built-ins or loadable kernel modules in the test
+    machine's kernel.
    </para>
  </chapter>
  <chapter id="CompilingAKernel">
-    <title>Compiling a kernel</title>
+  <title>Compiling a kernel</title>
+  <para>
+  <itemizedlist>
+  <listitem><para>In order to enable compilation of kdb, you must first enable kgdb.</para></listitem>
+  <listitem><para>The kgdb test compile options are described in the kgdb test suite chapter.</para></listitem>
+  </itemizedlist>
+  </para>
+  <sect1 id="CompileKGDB">
+    <title>Kernel config options for kgdb</title>
    <para>
    To enable <symbol>CONFIG_KGDB</symbol> you should first turn on
    "Prompt for development and/or incomplete code/drivers"
    (CONFIG_EXPERIMENTAL) in  "General setup", then under the
-    "Kernel debugging" select "KGDB: kernel debugging with remote gdb".
+    "Kernel debugging" select "KGDB: kernel debugger".
+    </para>
+    <para>
+    While it is not a hard requirement that you have symbols in your
+    vmlinux file, gdb tends not to be very useful without the symbolic
+    data, so you will want to turn
+    on <symbol>CONFIG_DEBUG_INFO</symbol> which is called "Compile the
+    kernel with debug info" in the config menu.
    </para>
    <para>
    It is advised, but not required that you turn on the
-    CONFIG_FRAME_POINTER kernel option.  This option inserts code to
+    <symbol>CONFIG_FRAME_POINTER</symbol> kernel option which is called "Compile the
-    into the compiled executable which saves the frame information in
+    kernel with frame pointers" in the config menu.  This option
-    registers or on the stack at different points which will allow a
+    inserts code to into the compiled executable which saves the frame
-    debugger such as gdb to more accurately construct stack back traces
+    information in registers or on the stack at different points which
-    while debugging the kernel.
+    allows a debugger such as gdb to more accurately construct
+    stack back traces while debugging the kernel.
    </para>
    <para>
    If the architecture that you are using supports the kernel option
@@ -116,38 +126,160 @@
    this option.
    </para>
    <para>
-    Next you should choose one of more I/O drivers to interconnect debugging
+    Next you should choose one of more I/O drivers to interconnect
-    host and debugged target.  Early boot debugging requires a KGDB
+    debugging host and debugged target.  Early boot debugging requires
-    I/O driver that supports early debugging and the driver must be
+    a KGDB I/O driver that supports early debugging and the driver
-    built into the kernel directly. Kgdb I/O driver configuration
+    must be built into the kernel directly. Kgdb I/O driver
-    takes place via kernel or module parameters, see following
+    configuration takes place via kernel or module parameters which
-    chapter.
+    you can learn more about in the in the section that describes the
+    parameter "kgdboc".
    </para>
-    <para>
+    <para>Here is an example set of .config symbols to enable or
-    The kgdb test compile options are described in the kgdb test suite chapter.
+    disable for kgdb:
+    <itemizedlist>
+    <listitem><para># CONFIG_DEBUG_RODATA is not set</para></listitem>
+    <listitem><para>CONFIG_FRAME_POINTER=y</para></listitem>
+    <listitem><para>CONFIG_KGDB=y</para></listitem>
+    <listitem><para>CONFIG_KGDB_SERIAL_CONSOLE=y</para></listitem>
+    </itemizedlist>
    </para>
+  </sect1>
+  <sect1 id="CompileKDB">
+    <title>Kernel config options for kdb</title>
+    <para>Kdb is quite a bit more complex than the simple gdbstub
+    sitting on top of the kernel's debug core.  Kdb must implement a
+    shell, and also adds some helper functions in other parts of the
+    kernel, responsible for printing out interesting data such as what
+    you would see if you ran "lsmod", or "ps".  In order to build kdb
+    into the kernel you follow the same steps as you would for kgdb.
+    </para>
+    <para>The main config option for kdb
+    is <symbol>CONFIG_KGDB_KDB</symbol> which is called "KGDB_KDB:
+    include kdb frontend for kgdb" in the config menu.  In theory you
+    would have already also selected an I/O driver such as the
+    CONFIG_KGDB_SERIAL_CONSOLE interface if you plan on using kdb on a
+    serial port, when you were configuring kgdb.
+    </para>
+    <para>If you want to use a PS/2-style keyboard with kdb, you would
+    select CONFIG_KDB_KEYBOARD which is called "KGDB_KDB: keyboard as
+    input device" in the config menu.  The CONFIG_KDB_KEYBOARD option
+    is not used for anything in the gdb interface to kgdb.  The
+    CONFIG_KDB_KEYBOARD option only works with kdb.
+    </para>
+    <para>Here is an example set of .config symbols to enable/disable kdb:
+    <itemizedlist>
+    <listitem><para># CONFIG_DEBUG_RODATA is not set</para></listitem>
+    <listitem><para>CONFIG_FRAME_POINTER=y</para></listitem>
+    <listitem><para>CONFIG_KGDB=y</para></listitem>
+    <listitem><para>CONFIG_KGDB_SERIAL_CONSOLE=y</para></listitem>
+    <listitem><para>CONFIG_KGDB_KDB=y</para></listitem>
+    <listitem><para>CONFIG_KDB_KEYBOARD=y</para></listitem>
+    </itemizedlist>
+    </para>
+  </sect1>
  </chapter>
-  <chapter id="EnableKGDB">
+  <chapter id="kgdbKernelArgs">
-   <title>Enable kgdb for debugging</title>
+  <title>Kernel Debugger Boot Arguments</title>
-   <para>
+  <para>This section describes the various runtime kernel
-   In order to use kgdb you must activate it by passing configuration
+  parameters that affect the configuration of the kernel debugger.
-   information to one of the kgdb I/O drivers.  If you do not pass any
+  The following chapter covers using kdb and kgdb as well as
-   configuration information kgdb will not do anything at all.  Kgdb
+  provides some examples of the configuration parameters.</para>
-   will only actively hook up to the kernel trap hooks if a kgdb I/O
+   <sect1 id="kgdboc">
-   driver is loaded and configured.  If you unconfigure a kgdb I/O
+   <title>Kernel parameter: kgdboc</title>
-   driver, kgdb will unregister all the kernel hook points.
+   <para>The kgdboc driver was originally an abbreviation meant to
+   stand for "kgdb over console".  Today it is the primary mechanism
+   to configure how to communicate from gdb to kgdb as well as the
+   devices you want to use to interact with the kdb shell.
+   </para>
+   <para>For kgdb/gdb, kgdboc is designed to work with a single serial
+   port. It is intended to cover the circumstance where you want to
+   use a serial console as your primary console as well as using it to
+   perform kernel debugging.  It is also possible to use kgdb on a
+   serial port which is not designated as a system console.  Kgdboc
+   may be configured as a kernel built-in or a kernel loadable module.
+   You can only make use of <constant>kgdbwait</constant> and early
+   debugging if you build kgdboc into the kernel as a built-in.
   </para>
+   <sect2 id="kgdbocArgs">
+   <title>kgdboc arguments</title>
+   <para>Usage: <constant>kgdboc=[kbd][[,]serial_device][,baud]</constant></para>
+   <sect3 id="kgdbocArgs1">
+   <title>Using loadable module or built-in</title>
   <para>
-   All drivers can be reconfigured at run time, if
+   <orderedlist>
-   <symbol>CONFIG_SYSFS</symbol> and <symbol>CONFIG_MODULES</symbol>
+   <listitem><para>As a kernel built-in:</para>
-   are enabled, by echo'ing a new config string to
+   <para>Use the kernel boot argument: <constant>kgdboc=&lt;tty-device&gt;,[baud]</constant></para></listitem>
-   <constant>/sys/module/&lt;driver&gt;/parameter/&lt;option&gt;</constant>.
+   <listitem>
-   The driver can be unconfigured by passing an empty string.  You cannot
+   <para>As a kernel loadable module:</para>
-   change the configuration while the debugger is attached.  Make sure
+   <para>Use the command: <constant>modprobe kgdboc kgdboc=&lt;tty-device&gt;,[baud]</constant></para>
-   to detach the debugger with the <constant>detach</constant> command
+   <para>Here are two examples of how you might formate the kgdboc
-   prior to trying unconfigure a kgdb I/O driver.
+   string. The first is for an x86 target using the first serial port.
+   The second example is for the ARM Versatile AB using the second
+   serial port.
+   <orderedlist>
+   <listitem><para><constant>kgdboc=ttyS0,115200</constant></para></listitem>
+   <listitem><para><constant>kgdboc=ttyAMA1,115200</constant></para></listitem>
+   </orderedlist>
   </para>
+   </listitem>
+   </orderedlist></para>
+   </sect3>
+   <sect3 id="kgdbocArgs2">
+   <title>Configure kgdboc at runtime with sysfs</title>
+   <para>At run time you can enable or disable kgdboc by echoing a
+   parameters into the sysfs.  Here are two examples:</para>
+   <orderedlist>
+   <listitem><para>Enable kgdboc on ttyS0</para>
+   <para><constant>echo ttyS0 &gt; /sys/module/kgdboc/parameters/kgdboc</constant></para></listitem>
+   <listitem><para>Disable kgdboc</para>
+   <para><constant>echo "" &gt; /sys/module/kgdboc/parameters/kgdboc</constant></para></listitem>
+   </orderedlist>
+   <para>NOTE: You do not need to specify the baud if you are
+   configuring the console on tty which is already configured or
+   open.</para>
+   </sect3>
+   <sect3 id="kgdbocArgs3">
+   <title>More examples</title>
+   <para>You can configure kgdboc to use the keyboard, and or a serial device
+   depending on if you are using kdb and or kgdb, in one of the
+   following scenarios.
+   <orderedlist>
+   <listitem><para>kdb and kgdb over only a serial port</para>
+   <para><constant>kgdboc=&lt;serial_device&gt;[,baud]</constant></para>
+   <para>Example: <constant>kgdboc=ttyS0,115200</constant></para>
+   </listitem>
+   <listitem><para>kdb and kgdb with keyboard and a serial port</para>
+   <para><constant>kgdboc=kbd,&lt;serial_device&gt;[,baud]</constant></para>
+   <para>Example: <constant>kgdboc=kbd,ttyS0,115200</constant></para>
+   </listitem>
+   <listitem><para>kdb with a keyboard</para>
+   <para><constant>kgdboc=kbd</constant></para>
+   </listitem>
+   </orderedlist>
+   </para>
+   </sect3>
+   <para>NOTE: Kgdboc does not support interrupting the target via the
+   gdb remote protocol.  You must manually send a sysrq-g unless you
+   have a proxy that splits console output to a terminal program.
+   A console proxy has a separate TCP port for the debugger and a separate
+   TCP port for the "human" console.  The proxy can take care of sending
+   the sysrq-g for you.
+   </para>
+   <para>When using kgdboc with no debugger proxy, you can end up
+    connecting the debugger at one of two entry points.  If an
+    exception occurs after you have loaded kgdboc, a message should
+    print on the console stating it is waiting for the debugger.  In
+    this case you disconnect your terminal program and then connect the
+    debugger in its place.  If you want to interrupt the target system
+    and forcibly enter a debug session you have to issue a Sysrq
+    sequence and then type the letter <constant>g</constant>.  Then
+    you disconnect the terminal session and connect gdb.  Your options
+    if you don't like this are to hack gdb to send the sysrq-g for you
+    as well as on the initial connect, or to use a debugger proxy that
+    allows an unmodified gdb to do the debugging.
+   </para>
+   </sect2>
+   </sect1>
   <sect1 id="kgdbwait">
   <title>Kernel parameter: kgdbwait</title>
   <para>
@@ -162,103 +294,204 @@
   </para>
   <para>
   The kernel will stop and wait as early as the I/O driver and
-   architecture will allow when you use this option.  If you build the
+   architecture allows when you use this option.  If you build the
-   kgdb I/O driver as a kernel module kgdbwait will not do anything.
+   kgdb I/O driver as a loadable kernel module kgdbwait will not do
+   anything.
   </para>
   </sect1>
-  <sect1 id="kgdboc">
+   <sect1 id="kgdbcon">
-  <title>Kernel parameter: kgdboc</title>
+   <title>Kernel parameter: kgdbcon</title>
-  <para>
+   <para> The kgdbcon feature allows you to see printk() messages
-  The kgdboc driver was originally an abbreviation meant to stand for
+   inside gdb while gdb is connected to the kernel.  Kdb does not make
-  "kgdb over console".  Kgdboc is designed to work with a single
+    use of the kgdbcon feature.
-  serial port. It was meant to cover the circumstance
+   </para>
-  where you wanted to use a serial console as your primary console as
+   <para>Kgdb supports using the gdb serial protocol to send console
-  well as using it to perform kernel debugging.  Of course you can
+   messages to the debugger when the debugger is connected and running.
-  also use kgdboc without assigning a console to the same port.
+   There are two ways to activate this feature.
+   <orderedlist>
+   <listitem><para>Activate with the kernel command line option:</para>
+   <para><constant>kgdbcon</constant></para>
+   </listitem>
+   <listitem><para>Use sysfs before configuring an I/O driver</para>
+   <para>
+   <constant>echo 1 &gt; /sys/module/kgdb/parameters/kgdb_use_con</constant>
+   </para>
+   <para>
+   NOTE: If you do this after you configure the kgdb I/O driver, the
+   setting will not take effect until the next point the I/O is
+   reconfigured.
+   </para>
+   </listitem>
+   </orderedlist>
+   <para>IMPORTANT NOTE: You cannot use kgdboc + kgdbcon on a tty that is an
+   active system console.  An example incorrect usage is <constant>console=ttyS0,115200 kgdboc=ttyS0 kgdbcon</constant>
+   </para>
+   <para>It is possible to use this option with kgdboc on a tty that is not a system console.
+   </para>
  </para>
-  <sect2 id="UsingKgdboc">
+  </sect1>
-  <title>Using kgdboc</title>
+  </chapter>
-  <para>
+  <chapter id="usingKDB">
-  You can configure kgdboc via sysfs or a module or kernel boot line
+  <title>Using kdb</title>
-  parameter depending on if you build with CONFIG_KGDBOC as a module
-  or built-in.
-  <orderedlist>
-  <listitem><para>From the module load or build-in</para>
-  <para><constant>kgdboc=&lt;tty-device&gt;,[baud]</constant></para>
  <para>
-  The example here would be if your console port was typically ttyS0, you would use something like <constant>kgdboc=ttyS0,115200</constant> or on the ARM Versatile AB you would likely use <constant>kgdboc=ttyAMA0,115200</constant>
+  </para>
+  <sect1 id="quickKDBserial">
+  <title>Quick start for kdb on a serial port</title>
+  <para>This is a quick example of how to use kdb.</para>
+  <para><orderedlist>
+  <listitem><para>Boot kernel with arguments:
+  <itemizedlist>
+  <listitem><para><constant>console=ttyS0,115200 kgdboc=ttyS0,115200</constant></para></listitem>
+  </itemizedlist></para>
+  <para>OR</para>
+  <para>Configure kgdboc after the kernel booted; assuming you are using a serial port console:
+  <itemizedlist>
+  <listitem><para><constant>echo ttyS0 &gt; /sys/module/kgdboc/parameters/kgdboc</constant></para></listitem>
+  </itemizedlist>
  </para>
  </listitem>
-  <listitem><para>From sysfs</para>
+  <listitem><para>Enter the kernel debugger manually or by waiting for an oops or fault.  There are several ways you can enter the kernel debugger manually; all involve using the sysrq-g, which means you must have enabled CONFIG_MAGIC_SYSRQ=y in your kernel config.</para>
-  <para><constant>echo ttyS0 &gt; /sys/module/kgdboc/parameters/kgdboc</constant></para>
+  <itemizedlist>
+  <listitem><para>When logged in as root or with a super user session you can run:</para>
+   <para><constant>echo g &gt; /proc/sysrq-trigger</constant></para></listitem>
+  <listitem><para>Example using minicom 2.2</para>
+  <para>Press: <constant>Control-a</constant></para>
+  <para>Press: <constant>f</constant></para>
+  <para>Press: <constant>g</constant></para>
  </listitem>
-  </orderedlist>
+  <listitem><para>When you have telneted to a terminal server that supports sending a remote break</para>
-  </para>
+  <para>Press: <constant>Control-]</constant></para>
-  <para>
+  <para>Type in:<constant>send break</constant></para>
-  NOTE: Kgdboc does not support interrupting the target via the
+  <para>Press: <constant>Enter</constant></para>
-  gdb remote protocol.  You must manually send a sysrq-g unless you
+  <para>Press: <constant>g</constant></para>
-  have a proxy that splits console output to a terminal problem and
+  </listitem>
-  has a separate port for the debugger to connect to that sends the
+  </itemizedlist>
-  sysrq-g for you.
+  </listitem>
+  <listitem><para>From the kdb prompt you can run the "help" command to see a complete list of the commands that are available.</para>
+  <para>Some useful commands in kdb include:
+  <itemizedlist>
+  <listitem><para>lsmod  -- Shows where kernel modules are loaded</para></listitem>
+  <listitem><para>ps -- Displays only the active processes</para></listitem>
+  <listitem><para>ps A -- Shows all the processes</para></listitem>
+  <listitem><para>summary -- Shows kernel version info and memory usage</para></listitem>
+  <listitem><para>bt -- Get a backtrace of the current process using dump_stack()</para></listitem>
+  <listitem><para>dmesg -- View the kernel syslog buffer</para></listitem>
+  <listitem><para>go -- Continue the system</para></listitem>
+  </itemizedlist>
  </para>
-  <para>When using kgdboc with no debugger proxy, you can end up
+  </listitem>
-  connecting the debugger for one of two entry points.  If an
+  <listitem>
-  exception occurs after you have loaded kgdboc a message should print
+  <para>When you are done using kdb you need to consider rebooting the
-  on the console stating it is waiting for the debugger.  In case you
+  system or using the "go" command to resuming normal kernel
-  disconnect your terminal program and then connect the debugger in
+  execution.  If you have paused the kernel for a lengthy period of
-  its place.  If you want to interrupt the target system and forcibly
+  time, applications that rely on timely networking or anything to do
-  enter a debug session you have to issue a Sysrq sequence and then
+  with real wall clock time could be adversely affected, so you
-  type the letter <constant>g</constant>.  Then you disconnect the
+  should take this into consideration when using the kernel
-  terminal session and connect gdb.  Your options if you don't like
+  debugger.</para>
-  this are to hack gdb to send the sysrq-g for you as well as on the
+  </listitem>
-  initial connect, or to use a debugger proxy that allows an
+  </orderedlist></para>
-  unmodified gdb to do the debugging.
+  </sect1>
+  <sect1 id="quickKDBkeyboard">
+  <title>Quick start for kdb using a keyboard connected console</title>
+  <para>This is a quick example of how to use kdb with a keyboard.</para>
+  <para><orderedlist>
+  <listitem><para>Boot kernel with arguments:
+  <itemizedlist>
+  <listitem><para><constant>kgdboc=kbd</constant></para></listitem>
+  </itemizedlist></para>
+  <para>OR</para>
+  <para>Configure kgdboc after the kernel booted:
+  <itemizedlist>
+  <listitem><para><constant>echo kbd &gt; /sys/module/kgdboc/parameters/kgdboc</constant></para></listitem>
+  </itemizedlist>
  </para>
-  </sect2>
+  </listitem>
+  <listitem><para>Enter the kernel debugger manually or by waiting for an oops or fault.  There are several ways you can enter the kernel debugger manually; all involve using the sysrq-g, which means you must have enabled CONFIG_MAGIC_SYSRQ=y in your kernel config.</para>
+  <itemizedlist>
+  <listitem><para>When logged in as root or with a super user session you can run:</para>
+   <para><constant>echo g &gt; /proc/sysrq-trigger</constant></para></listitem>
+  <listitem><para>Example using a laptop keyboard</para>
+  <para>Press and hold down: <constant>Alt</constant></para>
+  <para>Press and hold down: <constant>Fn</constant></para>
+  <para>Press and release the key with the label: <constant>SysRq</constant></para>
+  <para>Release: <constant>Fn</constant></para>
+  <para>Press and release: <constant>g</constant></para>
+  <para>Release: <constant>Alt</constant></para>
+  </listitem>
+  <listitem><para>Example using a PS/2 101-key keyboard</para>
+  <para>Press and hold down: <constant>Alt</constant></para>
+  <para>Press and release the key with the label: <constant>SysRq</constant></para>
+  <para>Press and release: <constant>g</constant></para>
+  <para>Release: <constant>Alt</constant></para>
+  </listitem>
+  </itemizedlist>
+  </listitem>
+  <listitem>
+  <para>Now type in a kdb command such as "help", "dmesg", "bt" or "go" to continue kernel execution.</para>
+  </listitem>
+  </orderedlist></para>
  </sect1>
-  <sect1 id="kgdbcon">
+  </chapter>
-  <title>Kernel parameter: kgdbcon</title>
+  <chapter id="EnableKGDB">
-  <para>
+   <title>Using kgdb / gdb</title>
-  Kgdb supports using the gdb serial protocol to send console messages
+   <para>In order to use kgdb you must activate it by passing
-  to the debugger when the debugger is connected and running.  There
+   configuration information to one of the kgdb I/O drivers.  If you
-  are two ways to activate this feature.
+   do not pass any configuration information kgdb will not do anything
+   at all.  Kgdb will only actively hook up to the kernel trap hooks
+   if a kgdb I/O driver is loaded and configured.  If you unconfigure
+   a kgdb I/O driver, kgdb will unregister all the kernel hook points.
+   </para>
+   <para> All kgdb I/O drivers can be reconfigured at run time, if
+   <symbol>CONFIG_SYSFS</symbol> and <symbol>CONFIG_MODULES</symbol>
+   are enabled, by echo'ing a new config string to
+   <constant>/sys/module/&lt;driver&gt;/parameter/&lt;option&gt;</constant>.
+   The driver can be unconfigured by passing an empty string.  You cannot
+   change the configuration while the debugger is attached.  Make sure
+   to detach the debugger with the <constant>detach</constant> command
+   prior to trying to unconfigure a kgdb I/O driver.
+   </para>
+  <sect1 id="ConnectingGDB">
+  <title>Connecting with gdb to a serial port</title>
  <orderedlist>
-  <listitem><para>Activate with the kernel command line option:</para>
+  <listitem><para>Configure kgdboc</para>
-  <para><constant>kgdbcon</constant></para>
+   <para>Boot kernel with arguments:
+   <itemizedlist>
+    <listitem><para><constant>kgdboc=ttyS0,115200</constant></para></listitem>
+   </itemizedlist></para>
+   <para>OR</para>
+   <para>Configure kgdboc after the kernel booted:
+   <itemizedlist>
+    <listitem><para><constant>echo ttyS0 &gt; /sys/module/kgdboc/parameters/kgdboc</constant></para></listitem>
+   </itemizedlist></para>
  </listitem>
-  <listitem><para>Use sysfs before configuring an io driver</para>
+  <listitem>
-  <para>
+  <para>Stop kernel execution (break into the debugger)</para>
-  <constant>echo 1 &gt; /sys/module/kgdb/parameters/kgdb_use_con</constant>
+  <para>In order to connect to gdb via kgdboc, the kernel must
-  </para>
+  first be stopped.  There are several ways to stop the kernel which
-  <para>
+  include using kgdbwait as a boot argument, via a sysrq-g, or running
-  NOTE: If you do this after you configure the kgdb I/O driver, the
+  the kernel until it takes an exception where it waits for the
-  setting will not take effect until the next point the I/O is
+  debugger to attach.
-  reconfigured.
+  <itemizedlist>
-  </para>
+  <listitem><para>When logged in as root or with a super user session you can run:</para>
+   <para><constant>echo g &gt; /proc/sysrq-trigger</constant></para></listitem>
+  <listitem><para>Example using minicom 2.2</para>
+  <para>Press: <constant>Control-a</constant></para>
+  <para>Press: <constant>f</constant></para>
+  <para>Press: <constant>g</constant></para>
  </listitem>
-  </orderedlist>
+  <listitem><para>When you have telneted to a terminal server that supports sending a remote break</para>
-  </para>
+  <para>Press: <constant>Control-]</constant></para>
-  <para>
+  <para>Type in:<constant>send break</constant></para>
-  IMPORTANT NOTE: Using this option with kgdb over the console
+  <para>Press: <constant>Enter</constant></para>
-  (kgdboc) is not supported.
+  <para>Press: <constant>g</constant></para>
+  </listitem>
+  </itemizedlist>
  </para>
-  </sect1>
+  </listitem>
-  </chapter>
+  <listitem>
-  <chapter id="ConnectingGDB">
+    <para>Connect from from gdb</para>
-  <title>Connecting gdb</title>
-    <para>
-    If you are using kgdboc, you need to have used kgdbwait as a boot
-    argument, issued a sysrq-g, or the system you are going to debug
-    has already taken an exception and is waiting for the debugger to
-    attach before you can connect gdb.
-    </para>
-    <para>
-    If you are not using different kgdb I/O driver other than kgdboc,
-    you should be able to connect and the target will automatically
-    respond.
-    </para>
    <para>
-    Example (using a serial port):
+    Example (using a directly connected port):
    </para>
    <programlisting>
    % gdb ./vmlinux
@@ -266,7 +499,7 @@
    (gdb) target remote /dev/ttyS0
    </programlisting>
    <para>
-    Example (kgdb to a terminal server on tcp port 2012):
+    Example (kgdb to a terminal server on TCP port 2012):
    </para>
    <programlisting>
    % gdb ./vmlinux
@@ -283,6 +516,83 @@
    communications.  You do this prior to issuing the <constant>target
    remote</constant> command by typing in: <constant>set debug remote 1</constant>
    </para>
+  </listitem>
+  </orderedlist>
+  <para>Remember if you continue in gdb, and need to "break in" again,
+  you need to issue an other sysrq-g.  It is easy to create a simple
+  entry point by putting a breakpoint at <constant>sys_sync</constant>
+  and then you can run "sync" from a shell or script to break into the
+  debugger.</para>
+  </sect1>
+  </chapter>
+  <chapter id="switchKdbKgdb">
+  <title>kgdb and kdb interoperability</title>
+  <para>It is possible to transition between kdb and kgdb dynamically.
+  The debug core will remember which you used the last time and
+  automatically start in the same mode.</para>
+  <sect1>
+  <title>Switching between kdb and kgdb</title>
+  <sect2>
+  <title>Switching from kgdb to kdb</title>
+  <para>
+  There are two ways to switch from kgdb to kdb: you can use gdb to
+  issue a maintenance packet, or you can blindly type the command $3#33.
+  Whenever kernel debugger stops in kgdb mode it will print the
+  message <constant>KGDB or $3#33 for KDB</constant>.  It is important
+  to note that you have to type the sequence correctly in one pass.
+  You cannot type a backspace or delete because kgdb will interpret
+  that as part of the debug stream.
+  <orderedlist>
+  <listitem><para>Change from kgdb to kdb by blindly typing:</para>
+  <para><constant>$3#33</constant></para></listitem>
+  <listitem><para>Change from kgdb to kdb with gdb</para>
+  <para><constant>maintenance packet 3</constant></para>
+  <para>NOTE: Now you must kill gdb. Typically you press control-z and
+  issue the command: kill -9 %</para></listitem>
+  </orderedlist>
+  </para>
+  </sect2>
+  <sect2>
+  <title>Change from kdb to kgdb</title>
+  <para>There are two ways you can change from kdb to kgdb.  You can
+  manually enter kgdb mode by issuing the kgdb command from the kdb
+  shell prompt, or you can connect gdb while the kdb shell prompt is
+  active.  The kdb shell looks for the typical first commands that gdb
+  would issue with the gdb remote protocol and if it sees one of those
+  commands it automatically changes into kgdb mode.</para>
+  <orderedlist>
+  <listitem><para>From kdb issue the command:</para>
+  <para><constant>kgdb</constant></para>
+  <para>Now disconnect your terminal program and connect gdb in its place</para></listitem>
+  <listitem><para>At the kdb prompt, disconnect the terminal program and connect gdb in its place.</para></listitem>
+  </orderedlist>
+  </sect2>
+  </sect1>
+  <sect1>
+  <title>Running kdb commands from gdb</title>
+  <para>It is possible to run a limited set of kdb commands from gdb,
+  using the gdb monitor command.  You don't want to execute any of the
+  run control or breakpoint operations, because it can disrupt the
+  state of the kernel debugger.  You should be using gdb for
+  breakpoints and run control operations if you have gdb connected.
+  The more useful commands to run are things like lsmod, dmesg, ps or
+  possibly some of the memory information commands.  To see all the kdb
+  commands you can run <constant>monitor help</constant>.</para>
+  <para>Example:
+  <informalexample><programlisting>
+(gdb) monitor ps
+1 idle process (state I) and
+27 sleeping system daemon (state M) processes suppressed,
+use 'ps A' to see all.
+Task Addr       Pid   Parent [*] cpu State Thread     Command
+0xc78291d0        1        0  0    0   S  0xc7829404  init
+0xc7954150      942        1  0    0   S  0xc7954384  dropbear
+0xc78789c0      944        1  0    0   S  0xc7878bf4  sh
+(gdb)
+  </programlisting></informalexample>
+  </para>
+  </sect1>
  </chapter>
  <chapter id="KGDBTestSuite">
    <title>kgdb Test Suite</title>
@@ -309,34 +619,36 @@
    </para>
  </chapter>
  <chapter id="CommonBackEndReq">
-  <title>KGDB Internals</title>
+  <title>Kernel Debugger Internals</title>
  <sect1 id="kgdbArchitecture">
    <title>Architecture Specifics</title>
      <para>
-      Kgdb is organized into three basic components:
+      The kernel debugger is organized into a number of components:
      <orderedlist>
-      <listitem><para>kgdb core</para>
+      <listitem><para>The debug core</para>
      <para>
-      The kgdb core is found in kernel/kgdb.c.  It contains:
+      The debug core is found in kernel/debugger/debug_core.c.  It contains:
      <itemizedlist>
-      <listitem><para>All the logic to implement the gdb serial protocol</para></listitem>
+      <listitem><para>A generic OS exception handler which includes
-      <listitem><para>A generic OS exception handler which includes sync'ing the processors into a stopped state on an multi cpu system.</para></listitem>
+      sync'ing the processors into a stopped state on an multi-CPU
+      system.</para></listitem>
      <listitem><para>The API to talk to the kgdb I/O drivers</para></listitem>
-      <listitem><para>The API to make calls to the arch specific kgdb implementation</para></listitem>
+      <listitem><para>The API to make calls to the arch-specific kgdb implementation</para></listitem>
      <listitem><para>The logic to perform safe memory reads and writes to memory while using the debugger</para></listitem>
      <listitem><para>A full implementation for software breakpoints unless overridden by the arch</para></listitem>
+      <listitem><para>The API to invoke either the kdb or kgdb frontend to the debug core.</para></listitem>
      </itemizedlist>
      </para>
      </listitem>
-      <listitem><para>kgdb arch specific implementation</para>
+      <listitem><para>kgdb arch-specific implementation</para>
      <para>
      This implementation is generally found in arch/*/kernel/kgdb.c.
      As an example, arch/x86/kernel/kgdb.c contains the specifics to
      implement HW breakpoint as well as the initialization to
      dynamically register and unregister for the trap handlers on
-      this architecture.  The arch specific portion implements:
+      this architecture.  The arch-specific portion implements:
      <itemizedlist>
-      <listitem><para>contains an arch specific trap catcher which
+      <listitem><para>contains an arch-specific trap catcher which
      invokes kgdb_handle_exception() to start kgdb about doing its
      work</para></listitem>
      <listitem><para>translation to and from gdb specific packet format to pt_regs</para></listitem>
@@ -347,11 +659,35 @@
      </itemizedlist>
      </para>
      </listitem>
+      <listitem><para>gdbstub frontend (aka kgdb)</para>
+      <para>The gdbstub is located in kernel/debug/gdbstub.c. It contains:</para>
+      <itemizedlist>
+        <listitem><para>All the logic to implement the gdb serial protocol</para></listitem>
+      </itemizedlist>
+      </listitem>
+      <listitem><para>kdb frontend</para>
+      <para>The kdb debugger shell is broken down into a number of
+      components.  The kdb core is located in kernel/debug/kdb.  There
+      are a number of helper functions in some of the other kernel
+      components to make it possible for kdb to examine and report
+      information about the kernel without taking locks that could
+      cause a kernel deadlock.  The kdb core contains implements the following functionality.</para>
+      <itemizedlist>
+        <listitem><para>A simple shell</para></listitem>
+        <listitem><para>The kdb core command set</para></listitem>
+        <listitem><para>A registration API to register additional kdb shell commands.</para>
+        <para>A good example of a self-contained kdb module is the "ftdump" command for dumping the ftrace buffer.  See: kernel/trace/trace_kdb.c</para></listitem>
+        <listitem><para>The implementation for kdb_printf() which
+        emits messages directly to I/O drivers, bypassing the kernel
+        log.</para></listitem>
+        <listitem><para>SW / HW breakpoint management for the kdb shell</para></listitem>
+      </itemizedlist>
+      </listitem>
      <listitem><para>kgdb I/O driver</para>
      <para>
-      Each kgdb I/O driver has to provide an implemenation for the following:
+      Each kgdb I/O driver has to provide an implementation for the following:
      <itemizedlist>
-      <listitem><para>configuration via builtin or module</para></listitem>
+      <listitem><para>configuration via built-in or module</para></listitem>
      <listitem><para>dynamic configuration and kgdb hook registration calls</para></listitem>
      <listitem><para>read and write character interface</para></listitem>
      <listitem><para>A cleanup handler for unconfiguring from the kgdb core</para></listitem>
@@ -416,15 +752,15 @@
  underlying low level to the hardware driver having "polling hooks"
  which the to which the tty driver is attached.  In the initial
  implementation of kgdboc it the serial_core was changed to expose a
-  low level uart hook for doing polled mode reading and writing of a
+  low level UART hook for doing polled mode reading and writing of a
  single character while in an atomic context.  When kgdb makes an I/O
  request to the debugger, kgdboc invokes a call back in the serial
-  core which in turn uses the call back in the uart driver.  It is
+  core which in turn uses the call back in the UART driver.  It is
-  certainly possible to extend kgdboc to work with non-uart based
+  certainly possible to extend kgdboc to work with non-UART based
  consoles in the future.
  </para>
  <para>
-  When using kgdboc with a uart, the uart driver must implement two callbacks in the <constant>struct uart_ops</constant>. Example from drivers/8250.c:<programlisting>
+  When using kgdboc with a UART, the UART driver must implement two callbacks in the <constant>struct uart_ops</constant>. Example from drivers/8250.c:<programlisting>
 #ifdef CONFIG_CONSOLE_POLL
        .poll_get_char = serial8250_get_poll_char,
        .poll_put_char = serial8250_put_poll_char,
@@ -434,7 +770,7 @@
  <constant>#ifdef CONFIG_CONSOLE_POLL</constant>, as shown above.
  Keep in mind that polling hooks have to be implemented in such a way
  that they can be called from an atomic context and have to restore
-  the state of the uart chip on return such that the system can return
+  the state of the UART chip on return such that the system can return
  to normal when the debugger detaches.  You need to be very careful
  with any kind of lock you consider, because failing here is most
  going to mean pressing the reset button.
@@ -453,6 +789,10 @@
                <itemizedlist>
                <listitem><para>Jason Wessel<email>jason.wessel@windriver.com</email></para></listitem>
                </itemizedlist>
+                In Jan 2010 this document was updated to include kdb.
+                <itemizedlist>
+                <listitem><para>Jason Wessel<email>jason.wessel@windriver.com</email></para></listitem>
+                </itemizedlist>
        </para>
  </chapter>
 </book>
diff --git a/Documentation/DocBook/libata.tmpl b/Documentation/DocBook/libata.tmpl
index ba9975771503..8c5411cfeaf0 100644
--- a/Documentation/DocBook/libata.tmpl
+++ b/Documentation/DocBook/libata.tmpl
@@ -81,16 +81,14 @@ void (*port_disable) (struct ata_port *);
        </programlisting>
        <para>
-        Called from ata_bus_probe() and ata_bus_reset() error paths,
+        Called from ata_bus_probe() error path, as well as when
-        as well as when unregistering from the SCSI module (rmmod, hot
+        unregistering from the SCSI module (rmmod, hot unplug).
-        unplug).
        This function should do whatever needs to be done to take the
        port out of use.  In most cases, ata_port_disable() can be used
        as this hook.
        </para>
        <para>
        Called from ata_bus_probe() on a failed probe.
-        Called from ata_bus_reset() on a failed bus reset.
        Called from ata_scsi_release().
        </para>
@@ -107,10 +105,6 @@ void (*dev_config) (struct ata_port *, struct ata_device *);
        issue of SET FEATURES - XFER MODE, and prior to operation.
        </para>
        <para>
-        Called by ata_device_add() after ata_dev_identify() determines
-        a device is present.
-        </para>
-        <para>
        This entry may be specified as NULL in ata_port_operations.
        </para>
@@ -154,8 +148,8 @@ unsigned int (*mode_filter) (struct ata_port *, struct ata_device *, unsigned in
        <sect2><title>Taskfile read/write</title>
        <programlisting>
-void (*tf_load) (struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_tf_load) (struct ata_port *ap, struct ata_taskfile *tf);
-void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
        </programlisting>
        <para>
@@ -164,36 +158,35 @@ void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
        hardware registers / DMA buffers, to obtain the current set of
        taskfile register values.
        Most drivers for taskfile-based hardware (PIO or MMIO) use
-        ata_tf_load() and ata_tf_read() for these hooks.
+        ata_sff_tf_load() and ata_sff_tf_read() for these hooks.
        </para>
        </sect2>
        <sect2><title>PIO data read/write</title>
        <programlisting>
-void (*data_xfer) (struct ata_device *, unsigned char *, unsigned int, int);
+void (*sff_data_xfer) (struct ata_device *, unsigned char *, unsigned int, int);
        </programlisting>
        <para>
 All bmdma-style drivers must implement this hook.  This is the low-level
 operation that actually copies the data bytes during a PIO data
 transfer.
-Typically the driver
+Typically the driver will choose one of ata_sff_data_xfer_noirq(),
-will choose one of ata_pio_data_xfer_noirq(), ata_pio_data_xfer(), or
+ata_sff_data_xfer(), or ata_sff_data_xfer32().
-ata_mmio_data_xfer().
        </para>
        </sect2>
        <sect2><title>ATA command execute</title>
        <programlisting>
-void (*exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
        </programlisting>
        <para>
        causes an ATA command, previously loaded with
        ->tf_load(), to be initiated in hardware.
-        Most drivers for taskfile-based hardware use ata_exec_command()
+        Most drivers for taskfile-based hardware use ata_sff_exec_command()
        for this hook.
        </para>
@@ -218,8 +211,8 @@ command.
        <sect2><title>Read specific ATA shadow registers</title>
        <programlisting>
-u8   (*check_status)(struct ata_port *ap);
+u8   (*sff_check_status)(struct ata_port *ap);
-u8   (*check_altstatus)(struct ata_port *ap);
+u8   (*sff_check_altstatus)(struct ata_port *ap);
        </programlisting>
        <para>
@@ -227,20 +220,26 @@ u8   (*check_altstatus)(struct ata_port *ap);
        hardware.  On some hardware, reading the Status register has
        the side effect of clearing the interrupt condition.
        Most drivers for taskfile-based hardware use
-        ata_check_status() for this hook.
+        ata_sff_check_status() for this hook.
        </para>
+        </sect2>
+        <sect2><title>Write specific ATA shadow register</title>
+        <programlisting>
+void (*sff_set_devctl)(struct ata_port *ap, u8 ctl);
+        </programlisting>
        <para>
-        Note that because this is called from ata_device_add(), at
+        Write the device control ATA shadow register to the hardware.
-        least a dummy function that clears device interrupts must be
+        Most drivers don't need to define this.
-        provided for all drivers, even if the controller doesn't
-        actually have a taskfile status register.
        </para>
        </sect2>
        <sect2><title>Select ATA device on bus</title>
        <programlisting>
-void (*dev_select)(struct ata_port *ap, unsigned int device);
+void (*sff_dev_select)(struct ata_port *ap, unsigned int device);
        </programlisting>
        <para>
@@ -251,9 +250,7 @@ void (*dev_select)(struct ata_port *ap, unsigned int device);
        </para>
        <para>
        Most drivers for taskfile-based hardware use
-        ata_std_dev_select() for this hook.  Controllers which do not
+        ata_sff_dev_select() for this hook.
-        support second drives on a port (such as SATA contollers) will
-        use ata_noop_dev_select().
        </para>
        </sect2>
@@ -441,13 +438,13 @@ void (*irq_clear) (struct ata_port *);
        to struct ata_host_set.
        </para>
        <para>
-        Most legacy IDE drivers use ata_interrupt() for the
+        Most legacy IDE drivers use ata_sff_interrupt() for the
        irq_handler hook, which scans all ports in the host_set,
        determines which queued command was active (if any), and calls
-        ata_host_intr(ap,qc).
+        ata_sff_host_intr(ap,qc).
        </para>
        <para>
-        Most legacy IDE drivers use ata_bmdma_irq_clear() for the
+        Most legacy IDE drivers use ata_sff_irq_clear() for the
        irq_clear() hook, which simply clears the interrupt and error
        flags in the DMA status register.
        </para>
@@ -490,16 +487,12 @@ void (*host_stop) (struct ata_host_set *host_set);
        allocates space for a legacy IDE PRD table and returns.
        </para>
        <para>
-        ->port_stop() is called after ->host_stop().  It's sole function
+        ->port_stop() is called after ->host_stop().  Its sole function
        is to release DMA/memory resources, now that they are no longer
        actively being used.  Many drivers also free driver-private
        data from port at this time.
        </para>
        <para>
-        Many drivers use ata_port_stop() as this hook, which frees the
-        PRD table.
-        </para>
-        <para>
        ->host_stop() is called after all ->port_stop() calls
 have completed.  The hook must finalize hardware shutdown, release DMA
 and other resources, etc.
diff --git a/Documentation/DocBook/mac80211.tmpl b/Documentation/DocBook/mac80211.tmpl
index f3f37f141dbd..affb15a344a1 100644
--- a/Documentation/DocBook/mac80211.tmpl
+++ b/Documentation/DocBook/mac80211.tmpl
@@ -144,7 +144,7 @@ usage should require reading the full document.
        this though and the recommendation to allow only a single
        interface in STA mode at first!
      </para>
-!Finclude/net/mac80211.h ieee80211_if_init_conf
+!Finclude/net/mac80211.h ieee80211_vif
    </chapter>
    <chapter id="rx-tx">
@@ -234,7 +234,6 @@ usage should require reading the full document.
      <title>Multiple queues and QoS support</title>
      <para>TBD</para>
 !Finclude/net/mac80211.h ieee80211_tx_queue_params
-!Finclude/net/mac80211.h ieee80211_tx_queue_stats
    </chapter>
    <chapter id="AP">
diff --git a/Documentation/DocBook/media-entities.tmpl b/Documentation/DocBook/media-entities.tmpl
index c725cb852c54..5d4d40f429a5 100644
--- a/Documentation/DocBook/media-entities.tmpl
+++ b/Documentation/DocBook/media-entities.tmpl
@@ -17,6 +17,7 @@
 <!ENTITY VIDIOC-DBG-G-REGISTER "<link linkend='vidioc-dbg-g-register'><constant>VIDIOC_DBG_G_REGISTER</constant></link>">
 <!ENTITY VIDIOC-DBG-S-REGISTER "<link linkend='vidioc-dbg-g-register'><constant>VIDIOC_DBG_S_REGISTER</constant></link>">
 <!ENTITY VIDIOC-DQBUF "<link linkend='vidioc-qbuf'><constant>VIDIOC_DQBUF</constant></link>">
+<!ENTITY VIDIOC-DQEVENT "<link linkend='vidioc-dqevent'><constant>VIDIOC_DQEVENT</constant></link>">
 <!ENTITY VIDIOC-ENCODER-CMD "<link linkend='vidioc-encoder-cmd'><constant>VIDIOC_ENCODER_CMD</constant></link>">
 <!ENTITY VIDIOC-ENUMAUDIO "<link linkend='vidioc-enumaudio'><constant>VIDIOC_ENUMAUDIO</constant></link>">
 <!ENTITY VIDIOC-ENUMAUDOUT "<link linkend='vidioc-enumaudioout'><constant>VIDIOC_ENUMAUDOUT</constant></link>">
@@ -60,6 +61,7 @@
 <!ENTITY VIDIOC-REQBUFS "<link linkend='vidioc-reqbufs'><constant>VIDIOC_REQBUFS</constant></link>">
 <!ENTITY VIDIOC-STREAMOFF "<link linkend='vidioc-streamon'><constant>VIDIOC_STREAMOFF</constant></link>">
 <!ENTITY VIDIOC-STREAMON "<link linkend='vidioc-streamon'><constant>VIDIOC_STREAMON</constant></link>">
+<!ENTITY VIDIOC-SUBSCRIBE-EVENT "<link linkend='vidioc-subscribe-event'><constant>VIDIOC_SUBSCRIBE_EVENT</constant></link>">
 <!ENTITY VIDIOC-S-AUDIO "<link linkend='vidioc-g-audio'><constant>VIDIOC_S_AUDIO</constant></link>">
 <!ENTITY VIDIOC-S-AUDOUT "<link linkend='vidioc-g-audioout'><constant>VIDIOC_S_AUDOUT</constant></link>">
 <!ENTITY VIDIOC-S-CROP "<link linkend='vidioc-g-crop'><constant>VIDIOC_S_CROP</constant></link>">
@@ -83,6 +85,7 @@
 <!ENTITY VIDIOC-TRY-ENCODER-CMD "<link linkend='vidioc-encoder-cmd'><constant>VIDIOC_TRY_ENCODER_CMD</constant></link>">
 <!ENTITY VIDIOC-TRY-EXT-CTRLS "<link linkend='vidioc-g-ext-ctrls'><constant>VIDIOC_TRY_EXT_CTRLS</constant></link>">
 <!ENTITY VIDIOC-TRY-FMT "<link linkend='vidioc-g-fmt'><constant>VIDIOC_TRY_FMT</constant></link>">
+<!ENTITY VIDIOC-UNSUBSCRIBE-EVENT "<link linkend='vidioc-subscribe-event'><constant>VIDIOC_UNSUBSCRIBE_EVENT</constant></link>">
 <!-- Types -->
 <!ENTITY v4l2-std-id "<link linkend='v4l2-std-id'>v4l2_std_id</link>">
@@ -141,6 +144,9 @@
 <!ENTITY v4l2-enc-idx "struct&nbsp;<link linkend='v4l2-enc-idx'>v4l2_enc_idx</link>">
 <!ENTITY v4l2-enc-idx-entry "struct&nbsp;<link linkend='v4l2-enc-idx-entry'>v4l2_enc_idx_entry</link>">
 <!ENTITY v4l2-encoder-cmd "struct&nbsp;<link linkend='v4l2-encoder-cmd'>v4l2_encoder_cmd</link>">
+<!ENTITY v4l2-event "struct&nbsp;<link linkend='v4l2-event'>v4l2_event</link>">
+<!ENTITY v4l2-event-subscription "struct&nbsp;<link linkend='v4l2-event-subscription'>v4l2_event_subscription</link>">
+<!ENTITY v4l2-event-vsync "struct&nbsp;<link linkend='v4l2-event-vsync'>v4l2_event_vsync</link>">
 <!ENTITY v4l2-ext-control "struct&nbsp;<link linkend='v4l2-ext-control'>v4l2_ext_control</link>">
 <!ENTITY v4l2-ext-controls "struct&nbsp;<link linkend='v4l2-ext-controls'>v4l2_ext_controls</link>">
 <!ENTITY v4l2-fmtdesc "struct&nbsp;<link linkend='v4l2-fmtdesc'>v4l2_fmtdesc</link>">
@@ -200,6 +206,7 @@
 <!ENTITY sub-controls SYSTEM "v4l/controls.xml">
 <!ENTITY sub-dev-capture SYSTEM "v4l/dev-capture.xml">
 <!ENTITY sub-dev-codec SYSTEM "v4l/dev-codec.xml">
+<!ENTITY sub-dev-event SYSTEM "v4l/dev-event.xml">
 <!ENTITY sub-dev-effect SYSTEM "v4l/dev-effect.xml">
 <!ENTITY sub-dev-osd SYSTEM "v4l/dev-osd.xml">
 <!ENTITY sub-dev-output SYSTEM "v4l/dev-output.xml">
@@ -292,6 +299,8 @@
 <!ENTITY sub-v4l2grab-c SYSTEM "v4l/v4l2grab.c.xml">
 <!ENTITY sub-videodev2-h SYSTEM "v4l/videodev2.h.xml">
 <!ENTITY sub-v4l2 SYSTEM "v4l/v4l2.xml">
+<!ENTITY sub-dqevent SYSTEM "v4l/vidioc-dqevent.xml">
+<!ENTITY sub-subscribe-event SYSTEM "v4l/vidioc-subscribe-event.xml">
 <!ENTITY sub-intro SYSTEM "dvb/intro.xml">
 <!ENTITY sub-frontend SYSTEM "dvb/frontend.xml">
 <!ENTITY sub-dvbproperty SYSTEM "dvb/dvbproperty.xml">
@@ -381,3 +390,5 @@
 <!ENTITY reqbufs SYSTEM "v4l/vidioc-reqbufs.xml">
 <!ENTITY s-hw-freq-seek SYSTEM "v4l/vidioc-s-hw-freq-seek.xml">
 <!ENTITY streamon SYSTEM "v4l/vidioc-streamon.xml">
+<!ENTITY dqevent SYSTEM "v4l/vidioc-dqevent.xml">
+<!ENTITY subscribe_event SYSTEM "v4l/vidioc-subscribe-event.xml">
diff --git a/Documentation/DocBook/mtdnand.tmpl b/Documentation/DocBook/mtdnand.tmpl
index 5e7d84b48505..020ac80d4682 100644
--- a/Documentation/DocBook/mtdnand.tmpl
+++ b/Documentation/DocBook/mtdnand.tmpl
@@ -269,7 +269,7 @@ static void board_hwcontrol(struct mtd_info *mtd, int cmd)
                        information about the device.
                </para>
                <programlisting>
-int __init board_init (void)
+static int __init board_init (void)
 {
        struct nand_chip *this;
        int err = 0;
@@ -488,7 +488,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
                                The ECC bytes must be placed immidiately after the data
                                bytes in order to make the syndrome generator work. This
                                is contrary to the usual layout used by software ECC. The
-                                seperation of data and out of band area is not longer
+                                separation of data and out of band area is not longer
                                possible. The nand driver code handles this layout and
                                the remaining free bytes in the oob area are managed by 
                                the autoplacement code. Provide a matching oob-layout
@@ -560,7 +560,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
                                bad blocks. They have factory marked good blocks. The marker pattern
                                is erased when the block is erased to be reused. So in case of
                                powerloss before writing the pattern back to the chip this block 
-                                would be lost and added to the bad blocks. Therefor we scan the 
+                                would be lost and added to the bad blocks. Therefore we scan the 
                                chip(s) when we detect them the first time for good blocks and 
                                store this information in a bad block table before erasing any 
                                of the blocks.
@@ -1094,7 +1094,7 @@ in this page</entry>
                manufacturers specifications. This applies similar to the spare area. 
        </para>
        <para>
-                Therefor NAND aware filesystems must either write in page size chunks
+                Therefore NAND aware filesystems must either write in page size chunks
                or hold a writebuffer to collect smaller writes until they sum up to 
                pagesize. Available NAND aware filesystems: JFFS2, YAFFS.               
        </para>
diff --git a/Documentation/DocBook/sh.tmpl b/Documentation/DocBook/sh.tmpl
index 0c3dc4c69dd1..d858d92cf6d9 100644
--- a/Documentation/DocBook/sh.tmpl
+++ b/Documentation/DocBook/sh.tmpl
@@ -19,13 +19,17 @@
  </authorgroup>
  <copyright>
-   <year>2008</year>
+   <year>2008-2010</year>
   <holder>Paul Mundt</holder>
  </copyright>
  <copyright>
-   <year>2008</year>
+   <year>2008-2010</year>
   <holder>Renesas Technology Corp.</holder>
  </copyright>
+  <copyright>
+   <year>2010</year>
+   <holder>Renesas Electronics Corp.</holder>
+  </copyright>
  <legalnotice>
   <para>
@@ -77,7 +81,7 @@
  </chapter>
  <chapter id="clk">
    <title>Clock Framework Extensions</title>
-!Iarch/sh/include/asm/clock.h
+!Iinclude/linux/sh_clk.h
  </chapter>
  <chapter id="mach">
    <title>Machine Specific Interfaces</title>
diff --git a/Documentation/DocBook/tracepoint.tmpl b/Documentation/DocBook/tracepoint.tmpl
index 8bca1d5cec09..e8473eae2a20 100644
--- a/Documentation/DocBook/tracepoint.tmpl
+++ b/Documentation/DocBook/tracepoint.tmpl
@@ -16,6 +16,15 @@
     </address>
    </affiliation>
   </author>
+   <author>
+    <firstname>William</firstname>
+    <surname>Cohen</surname>
+    <affiliation>
+     <address>
+      <email>wcohen@redhat.com</email>
+     </address>
+    </affiliation>
+   </author>
  </authorgroup>
  <legalnotice>
@@ -91,4 +100,8 @@
 !Iinclude/trace/events/signal.h
  </chapter>
+  <chapter id="block">
+   <title>Block IO</title>
+!Iinclude/trace/events/block.h
+  </chapter>
 </book>
diff --git a/Documentation/DocBook/v4l/common.xml b/Documentation/DocBook/v4l/common.xml
index c65f0ac9b6ee..cea23e1c4fc6 100644
--- a/Documentation/DocBook/v4l/common.xml
+++ b/Documentation/DocBook/v4l/common.xml
@@ -1170,7 +1170,7 @@ frames per second. If less than this number of frames is to be
 captured or output, applications can request frame skipping or
 duplicating on the driver side. This is especially useful when using
 the &func-read; or &func-write;, which are not augmented by timestamps
-or sequence counters, and to avoid unneccessary data copying.</para>
+or sequence counters, and to avoid unnecessary data copying.</para>
    <para>Finally these ioctls can be used to determine the number of
 buffers used internally by a driver in read/write mode. For
diff --git a/Documentation/DocBook/v4l/compat.xml b/Documentation/DocBook/v4l/compat.xml
index b9dbdf9e6d29..b42b935913cd 100644
--- a/Documentation/DocBook/v4l/compat.xml
+++ b/Documentation/DocBook/v4l/compat.xml
@@ -2332,15 +2332,26 @@ more information.</para>
        </listitem>
      </orderedlist>
    </section>
-   </section>
+    <section>
+      <title>V4L2 in Linux 2.6.34</title>
+      <orderedlist>
+        <listitem>
+          <para>Added
+<constant>V4L2_CID_IRIS_ABSOLUTE</constant> and
+<constant>V4L2_CID_IRIS_RELATIVE</constant> controls to the
+            <link linkend="camera-controls">Camera controls class</link>.
+          </para>
+        </listitem>
+      </orderedlist>
+    </section>
-   <section id="other">
+    <section id="other">
-     <title>Relation of V4L2 to other Linux multimedia APIs</title>
+      <title>Relation of V4L2 to other Linux multimedia APIs</title>
-    <section id="xvideo">
+      <section id="xvideo">
-      <title>X Video Extension</title>
+        <title>X Video Extension</title>
-      <para>The X Video Extension (abbreviated XVideo or just Xv) is
+        <para>The X Video Extension (abbreviated XVideo or just Xv) is
 an extension of the X Window system, implemented for example by the
 XFree86 project. Its scope is similar to V4L2, an API to video capture
 and output devices for X clients. Xv allows applications to display
@@ -2351,7 +2362,7 @@ capture or output still images in XPixmaps<footnote>
 extension available across many operating systems and
 architectures.</para>
-      <para>Because the driver is embedded into the X server Xv has a
+        <para>Because the driver is embedded into the X server Xv has a
 number of advantages over the V4L2 <link linkend="overlay">video
 overlay interface</link>. The driver can easily determine the overlay
 target, &ie; visible graphics memory or off-screen buffers for a
@@ -2360,16 +2371,16 @@ overlay, scaling or color-keying, or the clipping functions of the
 video capture hardware, always in sync with drawing operations or
 windows moving or changing their stacking order.</para>
-      <para>To combine the advantages of Xv and V4L a special Xv
+        <para>To combine the advantages of Xv and V4L a special Xv
 driver exists in XFree86 and XOrg, just programming any overlay capable
 Video4Linux device it finds. To enable it
 <filename>/etc/X11/XF86Config</filename> must contain these lines:</para>
-      <para><screen>
+        <para><screen>
 Section "Module"
    Load "v4l"
 EndSection</screen></para>
-      <para>As of XFree86 4.2 this driver still supports only V4L
+        <para>As of XFree86 4.2 this driver still supports only V4L
 ioctls, however it should work just fine with all V4L2 devices through
 the V4L2 backward-compatibility layer. Since V4L2 permits multiple
 opens it is possible (if supported by the V4L2 driver) to capture
@@ -2377,83 +2388,84 @@ video while an X client requested video overlay. Restrictions of
 simultaneous capturing and overlay are discussed in <xref
          linkend="overlay" /> apply.</para>
-      <para>Only marginally related to V4L2, XFree86 extended Xv to
+        <para>Only marginally related to V4L2, XFree86 extended Xv to
 support hardware YUV to RGB conversion and scaling for faster video
 playback, and added an interface to MPEG-2 decoding hardware. This API
 is useful to display images captured with V4L2 devices.</para>
-    </section>
+      </section>
-    <section>
+      <section>
-      <title>Digital Video</title>
+        <title>Digital Video</title>
-      <para>V4L2 does not support digital terrestrial, cable or
+        <para>V4L2 does not support digital terrestrial, cable or
 satellite broadcast. A separate project aiming at digital receivers
 exists. You can find its homepage at <ulink
 url="http://linuxtv.org">http://linuxtv.org</ulink>. The Linux DVB API
 has no connection to the V4L2 API except that drivers for hybrid
 hardware may support both.</para>
-    </section>
+      </section>
-    <section>
+      <section>
-      <title>Audio Interfaces</title>
+        <title>Audio Interfaces</title>
-      <para>[to do - OSS/ALSA]</para>
+        <para>[to do - OSS/ALSA]</para>
+      </section>
    </section>
-  </section>
-  <section id="experimental">
+    <section id="experimental">
-    <title>Experimental API Elements</title>
+      <title>Experimental API Elements</title>
-    <para>The following V4L2 API elements are currently experimental
+      <para>The following V4L2 API elements are currently experimental
 and may change in the future.</para>
-    <itemizedlist>
+      <itemizedlist>
-      <listitem>
+        <listitem>
-        <para>Video Output Overlay (OSD) Interface, <xref
+          <para>Video Output Overlay (OSD) Interface, <xref
            linkend="osd" />.</para>
-      </listitem>
+        </listitem>
        <listitem>
-        <para><constant>V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY</constant>,
+          <para><constant>V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY</constant>,
        &v4l2-buf-type;, <xref linkend="v4l2-buf-type" />.</para>
-      </listitem>
+        </listitem>
-      <listitem>
+        <listitem>
-        <para><constant>V4L2_CAP_VIDEO_OUTPUT_OVERLAY</constant>,
+          <para><constant>V4L2_CAP_VIDEO_OUTPUT_OVERLAY</constant>,
 &VIDIOC-QUERYCAP; ioctl, <xref linkend="device-capabilities" />.</para>
-      </listitem>
+        </listitem>
-      <listitem>
+        <listitem>
-        <para>&VIDIOC-ENUM-FRAMESIZES; and
+          <para>&VIDIOC-ENUM-FRAMESIZES; and
 &VIDIOC-ENUM-FRAMEINTERVALS; ioctls.</para>
-      </listitem>
+        </listitem>
-      <listitem>
+        <listitem>
-        <para>&VIDIOC-G-ENC-INDEX; ioctl.</para>
+          <para>&VIDIOC-G-ENC-INDEX; ioctl.</para>
-      </listitem>
+        </listitem>
-      <listitem>
+        <listitem>
-        <para>&VIDIOC-ENCODER-CMD; and &VIDIOC-TRY-ENCODER-CMD;
+          <para>&VIDIOC-ENCODER-CMD; and &VIDIOC-TRY-ENCODER-CMD;
 ioctls.</para>
-      </listitem>
+        </listitem>
-      <listitem>
+        <listitem>
-        <para>&VIDIOC-DBG-G-REGISTER; and &VIDIOC-DBG-S-REGISTER;
+          <para>&VIDIOC-DBG-G-REGISTER; and &VIDIOC-DBG-S-REGISTER;
 ioctls.</para>
-      </listitem>
+        </listitem>
-      <listitem>
+        <listitem>
-        <para>&VIDIOC-DBG-G-CHIP-IDENT; ioctl.</para>
+          <para>&VIDIOC-DBG-G-CHIP-IDENT; ioctl.</para>
-      </listitem>
+        </listitem>
-    </itemizedlist>
+      </itemizedlist>
-  </section>
+    </section>
-  <section id="obsolete">
+    <section id="obsolete">
-    <title>Obsolete API Elements</title>
+      <title>Obsolete API Elements</title>
-    <para>The following V4L2 API elements were superseded by new
+      <para>The following V4L2 API elements were superseded by new
 interfaces and should not be implemented in new drivers.</para>
-    <itemizedlist>
+      <itemizedlist>
-      <listitem>
+        <listitem>
-        <para><constant>VIDIOC_G_MPEGCOMP</constant> and
+          <para><constant>VIDIOC_G_MPEGCOMP</constant> and
 <constant>VIDIOC_S_MPEGCOMP</constant> ioctls. Use Extended Controls,
 <xref linkend="extended-controls" />.</para>
-      </listitem>
+        </listitem>
-    </itemizedlist>
+      </itemizedlist>
+    </section>
  </section>
  <!--
diff --git a/Documentation/DocBook/v4l/controls.xml b/Documentation/DocBook/v4l/controls.xml
index f46450610412..8408caaee276 100644
--- a/Documentation/DocBook/v4l/controls.xml
+++ b/Documentation/DocBook/v4l/controls.xml
@@ -267,6 +267,12 @@ minimum value disables backlight compensation.</entry>
            <entry>Chroma automatic gain control.</entry>
          </row>
          <row>
+            <entry><constant>V4L2_CID_CHROMA_GAIN</constant></entry>
+            <entry>integer</entry>
+            <entry>Adjusts the Chroma gain control (for use when chroma AGC
+            is disabled).</entry>
+          </row>
+          <row>
            <entry><constant>V4L2_CID_COLOR_KILLER</constant></entry>
            <entry>boolean</entry>
            <entry>Enable the color killer (&ie; force a black &amp; white image in case of a weak video signal).</entry>
@@ -277,8 +283,15 @@ minimum value disables backlight compensation.</entry>
            <entry>Selects a color effect. Possible values for
 <constant>enum v4l2_colorfx</constant> are:
 <constant>V4L2_COLORFX_NONE</constant> (0),
-<constant>V4L2_COLORFX_BW</constant> (1) and
+<constant>V4L2_COLORFX_BW</constant> (1),
-<constant>V4L2_COLORFX_SEPIA</constant> (2).</entry>
+<constant>V4L2_COLORFX_SEPIA</constant> (2),
+<constant>V4L2_COLORFX_NEGATIVE</constant> (3),
+<constant>V4L2_COLORFX_EMBOSS</constant> (4),
+<constant>V4L2_COLORFX_SKETCH</constant> (5),
+<constant>V4L2_COLORFX_SKY_BLUE</constant> (6),
+<constant>V4L2_COLORFX_GRASS_GREEN</constant> (7),
+<constant>V4L2_COLORFX_SKIN_WHITEN</constant> (8) and
+<constant>V4L2_COLORFX_VIVID</constant> (9).</entry>
          </row>
          <row>
            <entry><constant>V4L2_CID_ROTATE</constant></entry>
@@ -1825,6 +1838,25 @@ wide-angle direction. The zoom speed unit is driver-specific.</entry>
          <row><entry></entry></row>
          <row>
+            <entry spanname="id"><constant>V4L2_CID_IRIS_ABSOLUTE</constant>&nbsp;</entry>
+            <entry>integer</entry>
+          </row><row><entry spanname="descr">This control sets the
+camera's aperture to the specified value. The unit is undefined.
+Larger values open the iris wider, smaller values close it.</entry>
+          </row>
+          <row><entry></entry></row>
+          <row>
+            <entry spanname="id"><constant>V4L2_CID_IRIS_RELATIVE</constant>&nbsp;</entry>
+            <entry>integer</entry>
+          </row><row><entry spanname="descr">This control modifies the
+camera's aperture by the specified amount. The unit is undefined.
+Positive values open the iris one step further, negative values close
+it one step further. This is a write-only control.</entry>
+          </row>
+          <row><entry></entry></row>
+          <row>
            <entry spanname="id"><constant>V4L2_CID_PRIVACY</constant>&nbsp;</entry>
            <entry>boolean</entry>
          </row><row><entry spanname="descr">Prevent video from being acquired
diff --git a/Documentation/DocBook/v4l/dev-event.xml b/Documentation/DocBook/v4l/dev-event.xml
new file mode 100644
index 000000000000..be5a98fb4fab
--- /dev/null
+++ b/Documentation/DocBook/v4l/dev-event.xml
@@ -0,0 +1,31 @@
+  <title>Event Interface</title>
+  <para>The V4L2 event interface provides means for user to get
+  immediately notified on certain conditions taking place on a device.
+  This might include start of frame or loss of signal events, for
+  example.
+  </para>
+  <para>To receive events, the events the user is interested in first must
+  be subscribed using the &VIDIOC-SUBSCRIBE-EVENT; ioctl. Once an event is
+  subscribed, the events of subscribed types are dequeueable using the
+  &VIDIOC-DQEVENT; ioctl. Events may be unsubscribed using
+  VIDIOC_UNSUBSCRIBE_EVENT ioctl. The special event type V4L2_EVENT_ALL may
+  be used to unsubscribe all the events the driver supports.</para>
+  <para>The event subscriptions and event queues are specific to file
+  handles. Subscribing an event on one file handle does not affect
+  other file handles.
+  </para>
+  <para>The information on dequeueable events is obtained by using select or
+  poll system calls on video devices. The V4L2 events use POLLPRI events on
+  poll system call and exceptions on select system call.  </para>
+  <!--
+Local Variables:
+mode: sgml
+sgml-parent-document: "v4l2.sgml"
+indent-tabs-mode: nil
+End:
+  -->
diff --git a/Documentation/DocBook/v4l/io.xml b/Documentation/DocBook/v4l/io.xml
index f92f24323b2a..d424886beda0 100644
--- a/Documentation/DocBook/v4l/io.xml
+++ b/Documentation/DocBook/v4l/io.xml
@@ -589,7 +589,8 @@ number of a video input as in &v4l2-input; field
            <entry></entry>
            <entry>A place holder for future extensions and custom
 (driver defined) buffer types
-<constant>V4L2_BUF_TYPE_PRIVATE</constant> and higher.</entry>
+<constant>V4L2_BUF_TYPE_PRIVATE</constant> and higher. Applications
+should set this to 0.</entry>
          </row>
        </tbody>
      </tgroup>
@@ -701,6 +702,16 @@ They can be both cleared however, then the buffer is in "dequeued"
 state, in the application domain to say so.</entry>
          </row>
          <row>
+            <entry><constant>V4L2_BUF_FLAG_ERROR</constant></entry>
+            <entry>0x0040</entry>
+            <entry>When this flag is set, the buffer has been dequeued
+            successfully, although the data might have been corrupted.
+            This is recoverable, streaming may continue as normal and
+            the buffer may be reused normally.
+            Drivers set this flag when the <constant>VIDIOC_DQBUF</constant>
+            ioctl is called.</entry>
+          </row>
+          <row>
            <entry><constant>V4L2_BUF_FLAG_KEYFRAME</constant></entry>
            <entry>0x0008</entry>
          <entry>Drivers set or clear this flag when calling the
@@ -917,8 +928,8 @@ order</emphasis>.</para>
    <para>When the driver provides or accepts images field by field
 rather than interleaved, it is also important applications understand
-how the fields combine to frames. We distinguish between top and
+how the fields combine to frames. We distinguish between top (aka odd) and
-bottom fields, the <emphasis>spatial order</emphasis>: The first line
+bottom (aka even) fields, the <emphasis>spatial order</emphasis>: The first line
 of the top field is the first line of an interlaced frame, the first
 line of the bottom field is the second line of that frame.</para>
@@ -971,12 +982,12 @@ between <constant>V4L2_FIELD_TOP</constant> and
          <row>
            <entry><constant>V4L2_FIELD_TOP</constant></entry>
            <entry>2</entry>
-            <entry>Images consist of the top field only.</entry>
+            <entry>Images consist of the top (aka odd) field only.</entry>
          </row>
          <row>
            <entry><constant>V4L2_FIELD_BOTTOM</constant></entry>
            <entry>3</entry>
-            <entry>Images consist of the bottom field only.
+            <entry>Images consist of the bottom (aka even) field only.
 Applications may wish to prevent a device from capturing interlaced
 images because they will have "comb" or "feathering" artefacts around
 moving objects.</entry>
diff --git a/Documentation/DocBook/v4l/pixfmt.xml b/Documentation/DocBook/v4l/pixfmt.xml
index 885968d6a2fc..c4ad0a8e42dc 100644
--- a/Documentation/DocBook/v4l/pixfmt.xml
+++ b/Documentation/DocBook/v4l/pixfmt.xml
@@ -792,6 +792,18 @@ http://www.thedirks.org/winnov/</ulink></para></entry>
            <entry>'YYUV'</entry>
            <entry>unknown</entry>
          </row>
+          <row id="V4L2-PIX-FMT-Y4">
+            <entry><constant>V4L2_PIX_FMT_Y4</constant></entry>
+            <entry>'Y04 '</entry>
+            <entry>Old 4-bit greyscale format. Only the least significant 4 bits of each byte are used,
+the other bits are set to 0.</entry>
+          </row>
+          <row id="V4L2-PIX-FMT-Y6">
+            <entry><constant>V4L2_PIX_FMT_Y6</constant></entry>
+            <entry>'Y06 '</entry>
+            <entry>Old 6-bit greyscale format. Only the least significant 6 bits of each byte are used,
+the other bits are set to 0.</entry>
+          </row>
        </tbody>
      </tgroup>
    </table>
diff --git a/Documentation/DocBook/v4l/v4l2.xml b/Documentation/DocBook/v4l/v4l2.xml
index 060105af49e5..9737243377a3 100644
--- a/Documentation/DocBook/v4l/v4l2.xml
+++ b/Documentation/DocBook/v4l/v4l2.xml
@@ -401,6 +401,7 @@ and discussions on the V4L mailing list.</revremark>
    <section id="ttx"> &sub-dev-teletext; </section>
    <section id="radio"> &sub-dev-radio; </section>
    <section id="rds"> &sub-dev-rds; </section>
+    <section id="event"> &sub-dev-event; </section>
  </chapter>
  <chapter id="driver">
@@ -426,6 +427,7 @@ and discussions on the V4L mailing list.</revremark>
    &sub-cropcap;
    &sub-dbg-g-chip-ident;
    &sub-dbg-g-register;
+    &sub-dqevent;
    &sub-encoder-cmd;
    &sub-enumaudio;
    &sub-enumaudioout;
@@ -467,6 +469,7 @@ and discussions on the V4L mailing list.</revremark>
    &sub-reqbufs;
    &sub-s-hw-freq-seek;
    &sub-streamon;
+    &sub-subscribe-event;
    <!-- End of ioctls. -->
    &sub-mmap;
    &sub-munmap;
diff --git a/Documentation/DocBook/v4l/videodev2.h.xml b/Documentation/DocBook/v4l/videodev2.h.xml
index 068325940658..865b06d9e679 100644
--- a/Documentation/DocBook/v4l/videodev2.h.xml
+++ b/Documentation/DocBook/v4l/videodev2.h.xml
@@ -1018,6 +1018,13 @@ enum <link linkend="v4l2-colorfx">v4l2_colorfx</link> {
        V4L2_COLORFX_NONE       = 0,
        V4L2_COLORFX_BW         = 1,
        V4L2_COLORFX_SEPIA      = 2,
+        V4L2_COLORFX_NEGATIVE   = 3,
+        V4L2_COLORFX_EMBOSS     = 4,
+        V4L2_COLORFX_SKETCH     = 5,
+        V4L2_COLORFX_SKY_BLUE   = 6,
+        V4L2_COLORFX_GRASS_GREEN = 7,
+        V4L2_COLORFX_SKIN_WHITEN = 8,
+        V4L2_COLORFX_VIVID      = 9.
 };
 #define V4L2_CID_AUTOBRIGHTNESS                 (V4L2_CID_BASE+32)
 #define V4L2_CID_BAND_STOP_FILTER               (V4L2_CID_BASE+33)
@@ -1271,6 +1278,9 @@ enum  <link linkend="v4l2-exposure-auto-type">v4l2_exposure_auto_type</link> {
 #define V4L2_CID_PRIVACY                        (V4L2_CID_CAMERA_CLASS_BASE+16)
+#define V4L2_CID_IRIS_ABSOLUTE                  (V4L2_CID_CAMERA_CLASS_BASE+17)
+#define V4L2_CID_IRIS_RELATIVE                  (V4L2_CID_CAMERA_CLASS_BASE+18)
 /* FM Modulator class control IDs */
 #define V4L2_CID_FM_TX_CLASS_BASE               (V4L2_CTRL_CLASS_FM_TX | 0x900)
 #define V4L2_CID_FM_TX_CLASS                    (V4L2_CTRL_CLASS_FM_TX | 1)
diff --git a/Documentation/DocBook/v4l/vidioc-dqevent.xml b/Documentation/DocBook/v4l/vidioc-dqevent.xml
new file mode 100644
index 000000000000..4e0a7cc30812
--- /dev/null
+++ b/Documentation/DocBook/v4l/vidioc-dqevent.xml
@@ -0,0 +1,131 @@
+<refentry id="vidioc-dqevent">
+  <refmeta>
+    <refentrytitle>ioctl VIDIOC_DQEVENT</refentrytitle>
+    &manvol;
+  </refmeta>
+  <refnamediv>
+    <refname>VIDIOC_DQEVENT</refname>
+    <refpurpose>Dequeue event</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_event
+*<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_DQEVENT</para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+        <term><parameter>argp</parameter></term>
+        <listitem>
+          <para></para>
+        </listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+  <refsect1>
+    <title>Description</title>
+    <para>Dequeue an event from a video device. No input is required
+    for this ioctl. All the fields of the &v4l2-event; structure are
+    filled by the driver. The file handle will also receive exceptions
+    which the application may get by e.g. using the select system
+    call.</para>
+    <table frame="none" pgwide="1" id="v4l2-event">
+      <title>struct <structname>v4l2_event</structname></title>
+      <tgroup cols="4">
+        &cs-str;
+        <tbody valign="top">
+          <row>
+            <entry>__u32</entry>
+            <entry><structfield>type</structfield></entry>
+            <entry></entry>
+            <entry>Type of the event.</entry>
+          </row>
+          <row>
+            <entry>union</entry>
+            <entry><structfield>u</structfield></entry>
+            <entry></entry>
+            <entry></entry>
+          </row>
+          <row>
+            <entry></entry>
+            <entry>&v4l2-event-vsync;</entry>
+            <entry><structfield>vsync</structfield></entry>
+            <entry>Event data for event V4L2_EVENT_VSYNC.
+            </entry>
+          </row>
+          <row>
+            <entry></entry>
+            <entry>__u8</entry>
+            <entry><structfield>data</structfield>[64]</entry>
+            <entry>Event data. Defined by the event type. The union
+            should be used to define easily accessible type for
+            events.</entry>
+          </row>
+          <row>
+            <entry>__u32</entry>
+            <entry><structfield>pending</structfield></entry>
+            <entry></entry>
+            <entry>Number of pending events excluding this one.</entry>
+          </row>
+          <row>
+            <entry>__u32</entry>
+            <entry><structfield>sequence</structfield></entry>
+            <entry></entry>
+            <entry>Event sequence number. The sequence number is
+            incremented for every subscribed event that takes place.
+            If sequence numbers are not contiguous it means that
+            events have been lost.
+            </entry>
+          </row>
+          <row>
+            <entry>struct timespec</entry>
+            <entry><structfield>timestamp</structfield></entry>
+            <entry></entry>
+            <entry>Event timestamp.</entry>
+          </row>
+          <row>
+            <entry>__u32</entry>
+            <entry><structfield>reserved</structfield>[9]</entry>
+            <entry></entry>
+            <entry>Reserved for future extensions. Drivers must set
+            the array to zero.</entry>
+          </row>
+        </tbody>
+      </tgroup>
+    </table>
+  </refsect1>
+</refentry>
+<!--
+Local Variables:
+mode: sgml
+sgml-parent-document: "v4l2.sgml"
+indent-tabs-mode: nil
+End:
+-->
diff --git a/Documentation/DocBook/v4l/vidioc-enuminput.xml b/Documentation/DocBook/v4l/vidioc-enuminput.xml
index 71b868e2fb8f..476fe1d2bba0 100644
--- a/Documentation/DocBook/v4l/vidioc-enuminput.xml
+++ b/Documentation/DocBook/v4l/vidioc-enuminput.xml
@@ -283,7 +283,7 @@ input/output interface to linux-media@vger.kernel.org on 19 Oct 2009.
            <entry>This input supports setting DV presets by using VIDIOC_S_DV_PRESET.</entry>
          </row>
          <row>
-            <entry><constant>V4L2_OUT_CAP_CUSTOM_TIMINGS</constant></entry>
+            <entry><constant>V4L2_IN_CAP_CUSTOM_TIMINGS</constant></entry>
            <entry>0x00000002</entry>
            <entry>This input supports setting custom video timings by using VIDIOC_S_DV_TIMINGS.</entry>
          </row>
diff --git a/Documentation/DocBook/v4l/vidioc-g-parm.xml b/Documentation/DocBook/v4l/vidioc-g-parm.xml
index 78332d365ce9..392aa9e5571e 100644
--- a/Documentation/DocBook/v4l/vidioc-g-parm.xml
+++ b/Documentation/DocBook/v4l/vidioc-g-parm.xml
@@ -55,7 +55,7 @@ captured or output, applications can request frame skipping or
 duplicating on the driver side. This is especially useful when using
 the <function>read()</function> or <function>write()</function>, which
 are not augmented by timestamps or sequence counters, and to avoid
-unneccessary data copying.</para>
+unnecessary data copying.</para>
    <para>Further these ioctls can be used to determine the number of
 buffers used internally by a driver in read/write mode. For
diff --git a/Documentation/DocBook/v4l/vidioc-qbuf.xml b/Documentation/DocBook/v4l/vidioc-qbuf.xml
index 187081778154..ab691ebf3b93 100644
--- a/Documentation/DocBook/v4l/vidioc-qbuf.xml
+++ b/Documentation/DocBook/v4l/vidioc-qbuf.xml
@@ -54,12 +54,10 @@ to enqueue an empty (capturing) or filled (output) buffer in the
 driver's incoming queue. The semantics depend on the selected I/O
 method.</para>
-    <para>To enqueue a <link linkend="mmap">memory mapped</link>
+    <para>To enqueue a buffer applications set the <structfield>type</structfield>
-buffer applications set the <structfield>type</structfield> field of a
+field of a &v4l2-buffer; to the same buffer type as was previously used
-&v4l2-buffer; to the same buffer type as previously &v4l2-format;
+with &v4l2-format; <structfield>type</structfield> and &v4l2-requestbuffers;
-<structfield>type</structfield> and &v4l2-requestbuffers;
+<structfield>type</structfield>. Applications must also set the
-<structfield>type</structfield>, the <structfield>memory</structfield>
-field to <constant>V4L2_MEMORY_MMAP</constant> and the
 <structfield>index</structfield> field. Valid index numbers range from
 zero to the number of buffers allocated with &VIDIOC-REQBUFS;
 (&v4l2-requestbuffers; <structfield>count</structfield>) minus one. The
@@ -70,8 +68,19 @@ intended for output (<structfield>type</structfield> is
 <constant>V4L2_BUF_TYPE_VBI_OUTPUT</constant>) applications must also
 initialize the <structfield>bytesused</structfield>,
 <structfield>field</structfield> and
-<structfield>timestamp</structfield> fields. See <xref
+<structfield>timestamp</structfield> fields, see <xref
-        linkend="buffer" /> for details. When
+linkend="buffer" /> for details.
+Applications must also set <structfield>flags</structfield> to 0. If a driver
+supports capturing from specific video inputs and you want to specify a video
+input, then <structfield>flags</structfield> should be set to
+<constant>V4L2_BUF_FLAG_INPUT</constant> and the field
+<structfield>input</structfield> must be initialized to the desired input.
+The <structfield>reserved</structfield> field must be set to 0.
+</para>
+    <para>To enqueue a <link linkend="mmap">memory mapped</link>
+buffer applications set the <structfield>memory</structfield>
+field to <constant>V4L2_MEMORY_MMAP</constant>. When
 <constant>VIDIOC_QBUF</constant> is called with a pointer to this
 structure the driver sets the
 <constant>V4L2_BUF_FLAG_MAPPED</constant> and
@@ -81,14 +90,10 @@ structure the driver sets the
 &EINVAL;.</para>
    <para>To enqueue a <link linkend="userp">user pointer</link>
-buffer applications set the <structfield>type</structfield> field of a
+buffer applications set the <structfield>memory</structfield>
-&v4l2-buffer; to the same buffer type as previously &v4l2-format;
+field to <constant>V4L2_MEMORY_USERPTR</constant>, the
-<structfield>type</structfield> and &v4l2-requestbuffers;
-<structfield>type</structfield>, the <structfield>memory</structfield>
-field to <constant>V4L2_MEMORY_USERPTR</constant> and the
 <structfield>m.userptr</structfield> field to the address of the
-buffer and <structfield>length</structfield> to its size. When the
+buffer and <structfield>length</structfield> to its size.
-buffer is intended for output additional fields must be set as above.
 When <constant>VIDIOC_QBUF</constant> is called with a pointer to this
 structure the driver sets the <constant>V4L2_BUF_FLAG_QUEUED</constant>
 flag and clears the <constant>V4L2_BUF_FLAG_MAPPED</constant> and
@@ -96,16 +101,21 @@ flag and clears the <constant>V4L2_BUF_FLAG_MAPPED</constant> and
 <structfield>flags</structfield> field, or it returns an error code.
 This ioctl locks the memory pages of the buffer in physical memory,
 they cannot be swapped out to disk. Buffers remain locked until
-dequeued, until the &VIDIOC-STREAMOFF; or &VIDIOC-REQBUFS; ioctl are
+dequeued, until the &VIDIOC-STREAMOFF; or &VIDIOC-REQBUFS; ioctl is
 called, or until the device is closed.</para>
    <para>Applications call the <constant>VIDIOC_DQBUF</constant>
 ioctl to dequeue a filled (capturing) or displayed (output) buffer
 from the driver's outgoing queue. They just set the
-<structfield>type</structfield> and <structfield>memory</structfield>
+<structfield>type</structfield>, <structfield>memory</structfield>
+and <structfield>reserved</structfield>
 fields of a &v4l2-buffer; as above, when <constant>VIDIOC_DQBUF</constant>
 is called with a pointer to this structure the driver fills the
-remaining fields or returns an error code.</para>
+remaining fields or returns an error code. The driver may also set
+<constant>V4L2_BUF_FLAG_ERROR</constant> in the <structfield>flags</structfield>
+field. It indicates a non-critical (recoverable) streaming error. In such case
+the application may continue as normal, but should be aware that data in the
+dequeued buffer might be corrupted.</para>
    <para>By default <constant>VIDIOC_DQBUF</constant> blocks when no
 buffer is in the outgoing queue. When the
@@ -152,7 +162,13 @@ enqueue a user pointer buffer.</para>
          <para><constant>VIDIOC_DQBUF</constant> failed due to an
 internal error. Can also indicate temporary problems like signal
 loss. Note the driver might dequeue an (empty) buffer despite
-returning an error, or even stop capturing.</para>
+returning an error, or even stop capturing. Reusing such buffer may be unsafe
+though and its details (e.g. <structfield>index</structfield>) may not be
+returned either. It is recommended that drivers indicate recoverable errors
+by setting the <constant>V4L2_BUF_FLAG_ERROR</constant> and returning 0 instead.
+In that case the application should be able to safely reuse the buffer and
+continue streaming.
+        </para>
        </listitem>
      </varlistentry>
    </variablelist>
diff --git a/Documentation/DocBook/v4l/vidioc-querybuf.xml b/Documentation/DocBook/v4l/vidioc-querybuf.xml
index d834993e6191..e649805a4908 100644
--- a/Documentation/DocBook/v4l/vidioc-querybuf.xml
+++ b/Documentation/DocBook/v4l/vidioc-querybuf.xml
@@ -54,12 +54,13 @@ buffer at any time after buffers have been allocated with the
 &VIDIOC-REQBUFS; ioctl.</para>
    <para>Applications set the <structfield>type</structfield> field
-    of a &v4l2-buffer; to the same buffer type as previously
+    of a &v4l2-buffer; to the same buffer type as was previously used with
 &v4l2-format; <structfield>type</structfield> and &v4l2-requestbuffers;
 <structfield>type</structfield>, and the <structfield>index</structfield>
    field. Valid index numbers range from zero
 to the number of buffers allocated with &VIDIOC-REQBUFS;
    (&v4l2-requestbuffers; <structfield>count</structfield>) minus one.
+The <structfield>reserved</structfield> field should to set to 0.
 After calling <constant>VIDIOC_QUERYBUF</constant> with a pointer to
    this structure drivers return an error code or fill the rest of
 the structure.</para>
@@ -68,8 +69,8 @@ the structure.</para>
 <constant>V4L2_BUF_FLAG_MAPPED</constant>,
 <constant>V4L2_BUF_FLAG_QUEUED</constant> and
 <constant>V4L2_BUF_FLAG_DONE</constant> flags will be valid. The
-<structfield>memory</structfield> field will be set to
+<structfield>memory</structfield> field will be set to the current
-<constant>V4L2_MEMORY_MMAP</constant>, the <structfield>m.offset</structfield>
+I/O method, the <structfield>m.offset</structfield>
 contains the offset of the buffer from the start of the device memory,
 the <structfield>length</structfield> field its size. The driver may
 or may not set the remaining fields and flags, they are meaningless in
diff --git a/Documentation/DocBook/v4l/vidioc-queryctrl.xml b/Documentation/DocBook/v4l/vidioc-queryctrl.xml
index 4876ff1a1a04..8e0e055ac934 100644
--- a/Documentation/DocBook/v4l/vidioc-queryctrl.xml
+++ b/Documentation/DocBook/v4l/vidioc-queryctrl.xml
@@ -325,7 +325,7 @@ should be part of the control documentation.</entry>
            <entry>n/a</entry>
            <entry>This is not a control. When
 <constant>VIDIOC_QUERYCTRL</constant> is called with a control ID
-equal to a control class code (see <xref linkend="ctrl-class" />), the
+equal to a control class code (see <xref linkend="ctrl-class" />) + 1, the
 ioctl returns the name of the control class and this control type.
 Older drivers which do not support this feature return an
 &EINVAL;.</entry>
diff --git a/Documentation/DocBook/v4l/vidioc-reqbufs.xml b/Documentation/DocBook/v4l/vidioc-reqbufs.xml
index bab38084454f..69800ae23348 100644
--- a/Documentation/DocBook/v4l/vidioc-reqbufs.xml
+++ b/Documentation/DocBook/v4l/vidioc-reqbufs.xml
@@ -54,23 +54,23 @@ I/O. Memory mapped buffers are located in device memory and must be
 allocated with this ioctl before they can be mapped into the
 application's address space. User buffers are allocated by
 applications themselves, and this ioctl is merely used to switch the
-driver into user pointer I/O mode.</para>
+driver into user pointer I/O mode and to setup some internal structures.</para>
-    <para>To allocate device buffers applications initialize three
+    <para>To allocate device buffers applications initialize all
-fields of a <structname>v4l2_requestbuffers</structname> structure.
+fields of the <structname>v4l2_requestbuffers</structname> structure.
 They set the <structfield>type</structfield> field to the respective
 stream or buffer type, the <structfield>count</structfield> field to
-the desired number of buffers, and <structfield>memory</structfield>
+the desired number of buffers, <structfield>memory</structfield>
-must be set to <constant>V4L2_MEMORY_MMAP</constant>. When the ioctl
+must be set to the requested I/O method and the <structfield>reserved</structfield> array
-is called with a pointer to this structure the driver attempts to
+must be zeroed. When the ioctl
-allocate the requested number of buffers and stores the actual number
+is called with a pointer to this structure the driver will attempt to allocate
+the requested number of buffers and it stores the actual number
 allocated in the <structfield>count</structfield> field. It can be
 smaller than the number requested, even zero, when the driver runs out
-of free memory. A larger number is possible when the driver requires
+of free memory. A larger number is also possible when the driver requires
-more buffers to function correctly.<footnote>
+more buffers to function correctly. For example video output requires at least two buffers,
-        <para>For example video output requires at least two buffers,
 one displayed and one filled by the application.</para>
-        </footnote> When memory mapping I/O is not supported the ioctl
+    <para>When the I/O method is not supported the ioctl
 returns an &EINVAL;.</para>
    <para>Applications can call <constant>VIDIOC_REQBUFS</constant>
@@ -81,14 +81,6 @@ in progress, an implicit &VIDIOC-STREAMOFF;. <!-- mhs: I see no
 reason why munmap()ping one or even all buffers must imply
 streamoff.--></para>
-    <para>To negotiate user pointer I/O, applications initialize only
-the <structfield>type</structfield> field and set
-<structfield>memory</structfield> to
-<constant>V4L2_MEMORY_USERPTR</constant>. When the ioctl is called
-with a pointer to this structure the driver prepares for user pointer
-I/O, when this I/O method is not supported the ioctl returns an
-&EINVAL;.</para>
    <table pgwide="1" frame="none" id="v4l2-requestbuffers">
      <title>struct <structname>v4l2_requestbuffers</structname></title>
      <tgroup cols="3">
@@ -97,9 +89,7 @@ I/O, when this I/O method is not supported the ioctl returns an
          <row>
            <entry>__u32</entry>
            <entry><structfield>count</structfield></entry>
-            <entry>The number of buffers requested or granted. This
+            <entry>The number of buffers requested or granted.</entry>
-field is only used when <structfield>memory</structfield> is set to
-<constant>V4L2_MEMORY_MMAP</constant>.</entry>
          </row>
          <row>
            <entry>&v4l2-buf-type;</entry>
@@ -120,7 +110,7 @@ as the &v4l2-format; <structfield>type</structfield> field. See <xref
            <entry><structfield>reserved</structfield>[2]</entry>
            <entry>A place holder for future extensions and custom
 (driver defined) buffer types <constant>V4L2_BUF_TYPE_PRIVATE</constant> and
-higher.</entry>
+higher. This array should be zeroed by applications.</entry>
          </row>
        </tbody>
      </tgroup>
diff --git a/Documentation/DocBook/v4l/vidioc-subscribe-event.xml b/Documentation/DocBook/v4l/vidioc-subscribe-event.xml
new file mode 100644
index 000000000000..8b501791aa68
--- /dev/null
+++ b/Documentation/DocBook/v4l/vidioc-subscribe-event.xml
@@ -0,0 +1,133 @@
+<refentry id="vidioc-subscribe-event">
+  <refmeta>
+    <refentrytitle>ioctl VIDIOC_SUBSCRIBE_EVENT, VIDIOC_UNSUBSCRIBE_EVENT</refentrytitle>
+    &manvol;
+  </refmeta>
+  <refnamediv>
+    <refname>VIDIOC_SUBSCRIBE_EVENT, VIDIOC_UNSUBSCRIBE_EVENT</refname>
+    <refpurpose>Subscribe or unsubscribe event</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_event_subscription
+*<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_SUBSCRIBE_EVENT, VIDIOC_UNSUBSCRIBE_EVENT</para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+        <term><parameter>argp</parameter></term>
+        <listitem>
+          <para></para>
+        </listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+  <refsect1>
+    <title>Description</title>
+    <para>Subscribe or unsubscribe V4L2 event. Subscribed events are
+    dequeued by using the &VIDIOC-DQEVENT; ioctl.</para>
+    <table frame="none" pgwide="1" id="v4l2-event-subscription">
+      <title>struct <structname>v4l2_event_subscription</structname></title>
+      <tgroup cols="3">
+        &cs-str;
+        <tbody valign="top">
+          <row>
+            <entry>__u32</entry>
+            <entry><structfield>type</structfield></entry>
+            <entry>Type of the event.</entry>
+          </row>
+          <row>
+            <entry>__u32</entry>
+            <entry><structfield>reserved</structfield>[7]</entry>
+            <entry>Reserved for future extensions. Drivers and applications
+            must set the array to zero.</entry>
+          </row>
+        </tbody>
+      </tgroup>
+    </table>
+    <table frame="none" pgwide="1" id="event-type">
+      <title>Event Types</title>
+      <tgroup cols="3">
+        &cs-def;
+        <tbody valign="top">
+          <row>
+            <entry><constant>V4L2_EVENT_ALL</constant></entry>
+            <entry>0</entry>
+            <entry>All events. V4L2_EVENT_ALL is valid only for
+            VIDIOC_UNSUBSCRIBE_EVENT for unsubscribing all events at once.
+            </entry>
+          </row>
+          <row>
+            <entry><constant>V4L2_EVENT_VSYNC</constant></entry>
+            <entry>1</entry>
+            <entry>This event is triggered on the vertical sync.
+            This event has &v4l2-event-vsync; associated with it.
+            </entry>
+          </row>
+          <row>
+            <entry><constant>V4L2_EVENT_EOS</constant></entry>
+            <entry>2</entry>
+            <entry>This event is triggered when the end of a stream is reached.
+            This is typically used with MPEG decoders to report to the application
+            when the last of the MPEG stream has been decoded.
+            </entry>
+          </row>
+          <row>
+            <entry><constant>V4L2_EVENT_PRIVATE_START</constant></entry>
+            <entry>0x08000000</entry>
+            <entry>Base event number for driver-private events.</entry>
+          </row>
+        </tbody>
+      </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>
+  </refsect1>
+</refentry>
+<!--
+Local Variables:
+mode: sgml
+sgml-parent-document: "v4l2.sgml"
+indent-tabs-mode: nil
+End:
+-->
diff --git a/Documentation/DocBook/writing-an-alsa-driver.tmpl b/Documentation/DocBook/writing-an-alsa-driver.tmpl
index 0d0f7b4d4b1a..0ba149de2608 100644
--- a/Documentation/DocBook/writing-an-alsa-driver.tmpl
+++ b/Documentation/DocBook/writing-an-alsa-driver.tmpl
@@ -5518,34 +5518,41 @@ struct _snd_pcm_runtime {
 ]]>
        </programlisting>
      </informalexample>
+      For the raw data, <structfield>size</structfield> field must be
+      set properly.  This specifies the maximum size of the proc file access.
    </para>
    <para>
-      The callback is much more complicated than the text-file
+      The read/write callbacks of raw mode are more direct than the text mode.
-      version. You need to use a low-level I/O functions such as
+      You need to use a low-level I/O functions such as
      <function>copy_from/to_user()</function> to transfer the
      data.
      <informalexample>
        <programlisting>
 <![CDATA[
-  static long my_file_io_read(struct snd_info_entry *entry,
+  static ssize_t my_file_io_read(struct snd_info_entry *entry,
                              void *file_private_data,
                              struct file *file,
                              char *buf,
-                              unsigned long count,
+                              size_t count,
-                              unsigned long pos)
+                              loff_t pos)
  {
-          long size = count;
+          if (copy_to_user(buf, local_data + pos, count))
-          if (pos + size > local_max_size)
-                  size = local_max_size - pos;
-          if (copy_to_user(buf, local_data + pos, size))
                  return -EFAULT;
-          return size;
+          return count;
  }
 ]]>
        </programlisting>
      </informalexample>
+      If the size of the info entry has been set up properly,
+      <structfield>count</structfield> and <structfield>pos</structfield> are
+      guaranteed to fit within 0 and the given size.
+      You don't have to check the range in the callbacks unless any
+      other condition is required.
    </para>
  </chapter>
diff --git a/Documentation/DocBook/writing_usb_driver.tmpl b/Documentation/DocBook/writing_usb_driver.tmpl
index eeff19ca831b..bd97a13fa5ae 100644
--- a/Documentation/DocBook/writing_usb_driver.tmpl
+++ b/Documentation/DocBook/writing_usb_driver.tmpl
@@ -342,7 +342,7 @@ static inline void skel_delete (struct usb_skel *dev)
 {
    kfree (dev->bulk_in_buffer);
    if (dev->bulk_out_buffer != NULL)
-        usb_buffer_free (dev->udev, dev->bulk_out_size,
+        usb_free_coherent (dev->udev, dev->bulk_out_size,
            dev->bulk_out_buffer,
            dev->write_urb->transfer_dma);
    usb_free_urb (dev->write_urb);
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index 8495fc970391..40ada93b820a 100644
--- a/Documentation/HOWTO
+++ b/Documentation/HOWTO
@@ -221,8 +221,8 @@ branches.  These different branches are:
  - main 2.6.x kernel tree
  - 2.6.x.y -stable kernel tree
  - 2.6.x -git kernel patches
-  - 2.6.x -mm kernel patches
  - subsystem specific kernel trees and patches
+  - the 2.6.x -next kernel tree for integration tests
 2.6.x kernel tree
 -----------------
@@ -232,9 +232,9 @@ process is as follows:
  - As soon as a new kernel is released a two weeks window is open,
    during this period of time maintainers can submit big diffs to
    Linus, usually the patches that have already been included in the
-    -mm kernel for a few weeks.  The preferred way to submit big changes
+    -next kernel for a few weeks.  The preferred way to submit big changes
    is using git (the kernel's source management tool, more information
-    can be found at http://git.or.cz/) but plain patches are also just
+    can be found at http://git-scm.com/) but plain patches are also just
    fine.
  - After two weeks a -rc1 kernel is released it is now possible to push
    only patches that do not include new features that could affect the
@@ -293,84 +293,43 @@ daily and represent the current state of Linus' tree.  They are more
 experimental than -rc kernels since they are generated automatically
 without even a cursory glance to see if they are sane.
-2.6.x -mm kernel patches
------------------------
-These are experimental kernel patches released by Andrew Morton.  Andrew
-takes all of the different subsystem kernel trees and patches and mushes
-them together, along with a lot of patches that have been plucked from
-the linux-kernel mailing list.  This tree serves as a proving ground for
-new features and patches.  Once a patch has proved its worth in -mm for
-a while Andrew or the subsystem maintainer pushes it on to Linus for
-inclusion in mainline.
-It is heavily encouraged that all new patches get tested in the -mm tree
-before they are sent to Linus for inclusion in the main kernel tree.  Code
-which does not make an appearance in -mm before the opening of the merge
-window will prove hard to merge into the mainline.
-These kernels are not appropriate for use on systems that are supposed
-to be stable and they are more risky to run than any of the other
-branches.
-If you wish to help out with the kernel development process, please test
-and use these kernel releases and provide feedback to the linux-kernel
-mailing list if you have any problems, and if everything works properly.
-In addition to all the other experimental patches, these kernels usually
-also contain any changes in the mainline -git kernels available at the
-time of release.
-The -mm kernels are not released on a fixed schedule, but usually a few
-mm kernels are released in between each -rc kernel (1 to 3 is common).
 Subsystem Specific kernel trees and patches
 -------------------------------------------
-A number of the different kernel subsystem developers expose their
+The maintainers of the various kernel subsystems --- and also many
-development trees so that others can see what is happening in the
+kernel subsystem developers --- expose their current state of
-different areas of the kernel.  These trees are pulled into the -mm
+development in source repositories.  That way, others can see what is
-kernel releases as described above.
+happening in the different areas of the kernel.  In areas where
+development is rapid, a developer may be asked to base his submissions
-Here is a list of some of the different kernel trees available:
+onto such a subsystem kernel tree so that conflicts between the
-  git trees:
+submission and other already ongoing work are avoided.
-    - Kbuild development tree, Sam Ravnborg <sam@ravnborg.org>
-        git.kernel.org:/pub/scm/linux/kernel/git/sam/kbuild.git
+Most of these repositories are git trees, but there are also other SCMs
+in use, or patch queues being published as quilt series.  Addresses of
-    - ACPI development tree, Len Brown <len.brown@intel.com>
+these subsystem repositories are listed in the MAINTAINERS file.  Many
-        git.kernel.org:/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6.git
+of them can be browsed at http://git.kernel.org/.
-    - Block development tree, Jens Axboe <jens.axboe@oracle.com>
+Before a proposed patch is committed to such a subsystem tree, it is
-        git.kernel.org:/pub/scm/linux/kernel/git/axboe/linux-2.6-block.git
+subject to review which primarily happens on mailing lists (see the
+respective section below).  For several kernel subsystems, this review
-    - DRM development tree, Dave Airlie <airlied@linux.ie>
+process is tracked with the tool patchwork.  Patchwork offers a web
-        git.kernel.org:/pub/scm/linux/kernel/git/airlied/drm-2.6.git
+interface which shows patch postings, any comments on a patch or
+revisions to it, and maintainers can mark patches as under review,
-    - ia64 development tree, Tony Luck <tony.luck@intel.com>
+accepted, or rejected.  Most of these patchwork sites are listed at
-        git.kernel.org:/pub/scm/linux/kernel/git/aegl/linux-2.6.git
+http://patchwork.kernel.org/ or http://patchwork.ozlabs.org/.
-    - infiniband, Roland Dreier <rolandd@cisco.com>
+2.6.x -next kernel tree for integration tests
-        git.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband.git
+---------------------------------------------
+Before updates from subsystem trees are merged into the mainline 2.6.x
-    - libata, Jeff Garzik <jgarzik@pobox.com>
+tree, they need to be integration-tested.  For this purpose, a special
-        git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/libata-dev.git
+testing repository exists into which virtually all subsystem trees are
+pulled on an almost daily basis:
-    - network drivers, Jeff Garzik <jgarzik@pobox.com>
+        http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git
-        git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6.git
+        http://linux.f-seidel.de/linux-next/pmwiki/
-    - pcmcia, Dominik Brodowski <linux@dominikbrodowski.net>
+This way, the -next kernel gives a summary outlook onto what will be
-        git.kernel.org:/pub/scm/linux/kernel/git/brodo/pcmcia-2.6.git
+expected to go into the mainline kernel at the next merge period.
+Adventurous testers are very welcome to runtime-test the -next kernel.
-    - SCSI, James Bottomley <James.Bottomley@hansenpartnership.com>
-        git.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6.git
-    - x86, Ingo Molnar <mingo@elte.hu>
-        git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git
-  quilt trees:
-    - USB, Driver Core, and I2C, Greg Kroah-Hartman <gregkh@suse.de>
-        kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
-  Other kernel trees can be found listed at http://git.kernel.org/ and in
-  the MAINTAINERS file.
 Bug Reporting
 -------------
diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt
index bc38283379f0..69dd29ed824e 100644
--- a/Documentation/IPMI.txt
+++ b/Documentation/IPMI.txt
@@ -365,6 +365,7 @@ You can change this at module load time (for a module) with:
       regshifts=<shift1>,<shift2>,...
       slave_addrs=<addr1>,<addr2>,...
       force_kipmid=<enable1>,<enable2>,...
+       kipmid_max_busy_us=<ustime1>,<ustime2>,...
       unload_when_empty=[0|1]
 Each of these except si_trydefaults is a list, the first item for the
@@ -433,6 +434,7 @@ kernel command line as:
       ipmi_si.regshifts=<shift1>,<shift2>,...
       ipmi_si.slave_addrs=<addr1>,<addr2>,...
       ipmi_si.force_kipmid=<enable1>,<enable2>,...
+       ipmi_si.kipmid_max_busy_us=<ustime1>,<ustime2>,...
 It works the same as the module parameters of the same names.
@@ -450,6 +452,16 @@ force this thread on or off.  If you force it off and don't have
 interrupts, the driver will run VERY slowly.  Don't blame me,
 these interfaces suck.
+Unfortunately, this thread can use a lot of CPU depending on the
+interface's performance.  This can waste a lot of CPU and cause
+various issues with detecting idle CPU and using extra power.  To
+avoid this, the kipmid_max_busy_us sets the maximum amount of time, in
+microseconds, that kipmid will spin before sleeping for a tick.  This
+value sets a balance between performance and CPU waste and needs to be
+tuned to your needs.  Maybe, someday, auto-tuning will be added, but
+that's not a simple thing and even the auto-tuning would need to be
+tuned to the user's desired performance.
 The driver supports a hot add and remove of interfaces.  This way,
 interfaces can be added or removed after the kernel is up and running.
 This is done using /sys/modules/ipmi_si/parameters/hotmod, which is a
diff --git a/Documentation/Makefile b/Documentation/Makefile
index 94b945733534..6fc7ea1d1f9d 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -1,3 +1,3 @@
 obj-m := DocBook/ accounting/ auxdisplay/ connector/ \
-        filesystems/configfs/ ia64/ networking/ \
+        filesystems/ filesystems/configfs/ ia64/ laptops/ networking/ \
-        pcmcia/ spi/ video4linux/ vm/ watchdog/src/
+        pcmcia/ spi/ timers/ video4linux/ vm/ watchdog/src/
diff --git a/Documentation/PCI/pci-error-recovery.txt b/Documentation/PCI/pci-error-recovery.txt
index e83f2ea76415..898ded24510d 100644
--- a/Documentation/PCI/pci-error-recovery.txt
+++ b/Documentation/PCI/pci-error-recovery.txt
@@ -216,7 +216,7 @@ The driver should return one of the following result codes:
                - PCI_ERS_RESULT_NEED_RESET
                  Driver returns this if it thinks the device is not
-                  recoverable in it's current state and it needs a slot
+                  recoverable in its current state and it needs a slot
                  reset to proceed.
                - PCI_ERS_RESULT_DISCONNECT
@@ -241,7 +241,7 @@ in working condition.
 The driver is not supposed to restart normal driver I/O operations
 at this point.  It should limit itself to "probing" the device to
-check it's recoverability status. If all is right, then the platform
+check its recoverability status. If all is right, then the platform
 will call resume() once all drivers have ack'd link_reset().
        Result codes:
diff --git a/Documentation/PCI/pcieaer-howto.txt b/Documentation/PCI/pcieaer-howto.txt
index be21001ab144..26d3d945c3c2 100644
--- a/Documentation/PCI/pcieaer-howto.txt
+++ b/Documentation/PCI/pcieaer-howto.txt
@@ -13,7 +13,7 @@ Reporting (AER) driver and provides information on how to use it, as
 well as how to enable the drivers of endpoint devices to conform with
 PCI Express AER driver.
-1.2 Copyright � Intel Corporation 2006.
+1.2 Copyright (C) Intel Corporation 2006.
 1.3 What is the PCI Express AER Driver?
@@ -71,15 +71,11 @@ console. If it's a correctable error, it is outputed as a warning.
 Otherwise, it is printed as an error. So users could choose different
 log level to filter out correctable error messages.
-Below shows an example.
+Below shows an example:
-+------ PCI-Express Device Error -----+
+0000:50:00.0: PCIe Bus Error: severity=Uncorrected (Fatal), type=Transaction Layer, id=0500(Requester ID)
-Error Severity          : Uncorrected (Fatal)
+0000:50:00.0:   device [8086:0329] error status/mask=00100000/00000000
-PCIE Bus Error type     : Transaction Layer
+0000:50:00.0:    [20] Unsupported Request    (First)
-Unsupported Request     : First
+0000:50:00.0:   TLP Header: 04000001 00200a03 05010000 00050100
-Requester ID            : 0500
-VendorID=8086h, DeviceID=0329h, Bus=05h, Device=00h, Function=00h
-TLB Header:
-04000001 00200a03 05010000 00050100
 In the example, 'Requester ID' means the ID of the device who sends
 the error message to root port. Pls. refer to pci express specs for
@@ -112,7 +108,7 @@ but the PCI Express link itself is fully functional. Fatal errors, on
 the other hand, cause the link to be unreliable.
 When AER is enabled, a PCI Express device will automatically send an
-error message to the PCIE root port above it when the device captures
+error message to the PCIe root port above it when the device captures
 an error. The Root Port, upon receiving an error reporting message,
 internally processes and logs the error message in its PCI Express
 capability structure. Error information being logged includes storing
@@ -198,8 +194,9 @@ to reset link, AER port service driver is required to provide the
 function to reset link. Firstly, kernel looks for if the upstream
 component has an aer driver. If it has, kernel uses the reset_link
 callback of the aer driver. If the upstream component has no aer driver
-and the port is downstream port, we will use the aer driver of the
+and the port is downstream port, we will perform a hot reset as the
-root port who reports the AER error. As for upstream ports,
+default by setting the Secondary Bus Reset bit of the Bridge Control
+register associated with the downstream port. As for upstream ports,
 they should provide their own aer service drivers with reset_link
 function. If error_detected returns PCI_ERS_RESULT_CAN_RECOVER and
 reset_link returns PCI_ERS_RESULT_RECOVERED, the error handling goes
@@ -253,11 +250,11 @@ cleanup uncorrectable status register. Pls. refer to section 3.3.
 4. Software error injection
-Debugging PCIE AER error recovery code is quite difficult because it
+Debugging PCIe AER error recovery code is quite difficult because it
 is hard to trigger real hardware errors. Software based error
-injection can be used to fake various kinds of PCIE errors.
+injection can be used to fake various kinds of PCIe errors.
-First you should enable PCIE AER software error injection in kernel
+First you should enable PCIe AER software error injection in kernel
 configuration, that is, following item should be in your .config.
 CONFIG_PCIEAER_INJECT=y or CONFIG_PCIEAER_INJECT=m
diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX
index 9bb62f7b89c3..71b6f500ddb9 100644
--- a/Documentation/RCU/00-INDEX
+++ b/Documentation/RCU/00-INDEX
@@ -6,16 +6,22 @@ checklist.txt
        - Review Checklist for RCU Patches
 listRCU.txt
        - Using RCU to Protect Read-Mostly Linked Lists
+lockdep.txt
+        - RCU and lockdep checking
 NMI-RCU.txt
        - Using RCU to Protect Dynamic NMI Handlers
+rcubarrier.txt
+        - RCU and Unloadable Modules
+rculist_nulls.txt
+        - RCU list primitives for use with SLAB_DESTROY_BY_RCU
 rcuref.txt
        - Reference-count design for elements of lists/arrays protected by RCU
 rcu.txt
        - RCU Concepts
-rcubarrier.txt
-        - Unloading modules that use RCU callbacks
 RTFP.txt
        - List of RCU papers (bibliography) going back to 1980.
+stallwarn.txt
+        - RCU CPU stall warnings (CONFIG_RCU_CPU_STALL_DETECTOR)
 torture.txt
        - RCU Torture Test Operation (CONFIG_RCU_TORTURE_TEST)
 trace.txt
diff --git a/Documentation/RCU/NMI-RCU.txt b/Documentation/RCU/NMI-RCU.txt
index a6d32e65d222..a8536cb88091 100644
--- a/Documentation/RCU/NMI-RCU.txt
+++ b/Documentation/RCU/NMI-RCU.txt
@@ -34,7 +34,7 @@ NMI handler.
                cpu = smp_processor_id();
                ++nmi_count(cpu);
-                if (!rcu_dereference(nmi_callback)(regs, cpu))
+                if (!rcu_dereference_sched(nmi_callback)(regs, cpu))
                        default_do_nmi(regs);
                nmi_exit();
@@ -47,12 +47,13 @@ function pointer.  If this handler returns zero, do_nmi() invokes the
 default_do_nmi() function to handle a machine-specific NMI.  Finally,
 preemption is restored.
-Strictly speaking, rcu_dereference() is not needed, since this code runs
+In theory, rcu_dereference_sched() is not needed, since this code runs
-only on i386, which does not need rcu_dereference() anyway.  However,
+only on i386, which in theory does not need rcu_dereference_sched()
-it is a good documentation aid, particularly for anyone attempting to
+anyway.  However, in practice it is a good documentation aid, particularly
-do something similar on Alpha.
+for anyone attempting to do something similar on Alpha or on systems
+with aggressive optimizing compilers.
-Quick Quiz:  Why might the rcu_dereference() be necessary on Alpha,
+Quick Quiz:  Why might the rcu_dereference_sched() be necessary on Alpha,
             given that the code referenced by the pointer is read-only?
@@ -99,17 +100,21 @@ invoke irq_enter() and irq_exit() on NMI entry and exit, respectively.
 Answer to Quick Quiz
-        Why might the rcu_dereference() be necessary on Alpha, given
+        Why might the rcu_dereference_sched() be necessary on Alpha, given
        that the code referenced by the pointer is read-only?
        Answer: The caller to set_nmi_callback() might well have
-                initialized some data that is to be used by the
+                initialized some data that is to be used by the new NMI
-                new NMI handler.  In this case, the rcu_dereference()
+                handler.  In this case, the rcu_dereference_sched() would
-                would be needed, because otherwise a CPU that received
+                be needed, because otherwise a CPU that received an NMI
-                an NMI just after the new handler was set might see
+                just after the new handler was set might see the pointer
-                the pointer to the new NMI handler, but the old
+                to the new NMI handler, but the old pre-initialized
-                pre-initialized version of the handler's data.
+                version of the handler's data.
-                More important, the rcu_dereference() makes it clear
+                This same sad story can happen on other CPUs when using
-                to someone reading the code that the pointer is being
+                a compiler with aggressive pointer-value speculation
-                protected by RCU.
+                optimizations.
+                More important, the rcu_dereference_sched() makes it
+                clear to someone reading the code that the pointer is
+                being protected by RCU-sched.
diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt
index d2b85237c76e..5aea459e3dd6 100644
--- a/Documentation/RCU/RTFP.txt
+++ b/Documentation/RCU/RTFP.txt
@@ -25,10 +25,10 @@ to be referencing the data structure.  However, this mechanism was not
 optimized for modern computer systems, which is not surprising given
 that these overheads were not so expensive in the mid-80s.  Nonetheless,
 passive serialization appears to be the first deferred-destruction
-mechanism to be used in production.  Furthermore, the relevant patent has
+mechanism to be used in production.  Furthermore, the relevant patent
-lapsed, so this approach may be used in non-GPL software, if desired.
+has lapsed, so this approach may be used in non-GPL software, if desired.
-(In contrast, use of RCU is permitted only in software licensed under
+(In contrast, implementation of RCU is permitted only in software licensed
-GPL.  Sorry!!!)
+under either GPL or LGPL.  Sorry!!!)
 In 1990, Pugh [Pugh90] noted that explicitly tracking which threads
 were reading a given data structure permitted deferred free to operate
@@ -150,6 +150,18 @@ preemptible RCU [PaulEMcKenney2007PreemptibleRCU], and the three-part
 LWN "What is RCU?" series [PaulEMcKenney2007WhatIsRCUFundamentally,
 PaulEMcKenney2008WhatIsRCUUsage, and PaulEMcKenney2008WhatIsRCUAPI].
+2008 saw a journal paper on real-time RCU [DinakarGuniguntala2008IBMSysJ],
+a history of how Linux changed RCU more than RCU changed Linux
+[PaulEMcKenney2008RCUOSR], and a design overview of hierarchical RCU
+[PaulEMcKenney2008HierarchicalRCU].
+2009 introduced user-level RCU algorithms [PaulEMcKenney2009MaliciousURCU],
+which Mathieu Desnoyers is now maintaining [MathieuDesnoyers2009URCU]
+[MathieuDesnoyersPhD].  TINY_RCU [PaulEMcKenney2009BloatWatchRCU] made
+its appearance, as did expedited RCU [PaulEMcKenney2009expeditedRCU].
+The problem of resizeable RCU-protected hash tables may now be on a path
+to a solution [JoshTriplett2009RPHash].
 Bibtex Entries
 @article{Kung80
@@ -730,6 +742,11 @@ Revised:
 "
 }
+#
+#       "What is RCU?" LWN series.
+#
+########################################################################
 @article{DinakarGuniguntala2008IBMSysJ
 ,author="D. Guniguntala and P. E. McKenney and J. Triplett and J. Walpole"
 ,title="The read-copy-update mechanism for supporting real-time applications on shared-memory multiprocessor systems with {Linux}"
@@ -820,3 +837,39 @@ Revised:
        Uniprocessor assumptions allow simplified RCU implementation.
 "
 }
+@unpublished{PaulEMcKenney2009expeditedRCU
+,Author="Paul E. McKenney"
+,Title="[{PATCH} -tip 0/3] expedited 'big hammer' {RCU} grace periods"
+,month="June"
+,day="25"
+,year="2009"
+,note="Available:
+\url{http://lkml.org/lkml/2009/6/25/306}
+[Viewed August 16, 2009]"
+,annotation="
+        First posting of expedited RCU to be accepted into -tip.
+"
+}
+@unpublished{JoshTriplett2009RPHash
+,Author="Josh Triplett"
+,Title="Scalable concurrent hash tables via relativistic programming"
+,month="September"
+,year="2009"
+,note="Linux Plumbers Conference presentation"
+,annotation="
+        RP fun with hash tables.
+"
+}
+@phdthesis{MathieuDesnoyersPhD
+, title  = "Low-Impact Operating System Tracing"
+, author = "Mathieu Desnoyers"
+, school = "Ecole Polytechnique de Montr\'{e}al"
+, month  = "December"
+, year   = 2009
+,note="Available:
+\url{http://www.lttng.org/pub/thesis/desnoyers-dissertation-2009-12.pdf}
+[Viewed December 9, 2009]"
+}
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 51525a30e8b4..790d1a812376 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -8,13 +8,12 @@ would cause.  This list is based on experiences reviewing such patches
 over a rather long period of time, but improvements are always welcome!
 0.      Is RCU being applied to a read-mostly situation?  If the data
-        structure is updated more than about 10% of the time, then
+        structure is updated more than about 10% of the time, then you
-        you should strongly consider some other approach, unless
+        should strongly consider some other approach, unless detailed
-        detailed performance measurements show that RCU is nonetheless
+        performance measurements show that RCU is nonetheless the right
-        the right tool for the job.  Yes, you might think of RCU
+        tool for the job.  Yes, RCU does reduce read-side overhead by
-        as simply cutting overhead off of the readers and imposing it
+        increasing write-side overhead, which is exactly why normal uses
-        on the writers.  That is exactly why normal uses of RCU will
+        of RCU will do much more reading than updating.
-        do much more reading than updating.
        Another exception is where performance is not an issue, and RCU
        provides a simpler implementation.  An example of this situation
@@ -35,13 +34,13 @@ over a rather long period of time, but improvements are always welcome!
        If you choose #b, be prepared to describe how you have handled
        memory barriers on weakly ordered machines (pretty much all of
-        them -- even x86 allows reads to be reordered), and be prepared
+        them -- even x86 allows later loads to be reordered to precede
-        to explain why this added complexity is worthwhile.  If you
+        earlier stores), and be prepared to explain why this added
-        choose #c, be prepared to explain how this single task does not
+        complexity is worthwhile.  If you choose #c, be prepared to
-        become a major bottleneck on big multiprocessor machines (for
+        explain how this single task does not become a major bottleneck on
-        example, if the task is updating information relating to itself
+        big multiprocessor machines (for example, if the task is updating
-        that other tasks can read, there by definition can be no
+        information relating to itself that other tasks can read, there
-        bottleneck).
+        by definition can be no bottleneck).
 2.      Do the RCU read-side critical sections make proper use of
        rcu_read_lock() and friends?  These primitives are needed
@@ -51,8 +50,10 @@ over a rather long period of time, but improvements are always welcome!
        actuarial risk of your kernel.
        As a rough rule of thumb, any dereference of an RCU-protected
-        pointer must be covered by rcu_read_lock() or rcu_read_lock_bh()
+        pointer must be covered by rcu_read_lock(), rcu_read_lock_bh(),
-        or by the appropriate update-side lock.
+        rcu_read_lock_sched(), or by the appropriate update-side lock.
+        Disabling of preemption can serve as rcu_read_lock_sched(), but
+        is less readable.
 3.      Does the update code tolerate concurrent accesses?
@@ -62,25 +63,27 @@ over a rather long period of time, but improvements are always welcome!
        of ways to handle this concurrency, depending on the situation:
        a.      Use the RCU variants of the list and hlist update
-                primitives to add, remove, and replace elements on an
+                primitives to add, remove, and replace elements on
-                RCU-protected list.  Alternatively, use the RCU-protected
+                an RCU-protected list.  Alternatively, use the other
-                trees that have been added to the Linux kernel.
+                RCU-protected data structures that have been added to
+                the Linux kernel.
                This is almost always the best approach.
        b.      Proceed as in (a) above, but also maintain per-element
                locks (that are acquired by both readers and writers)
                that guard per-element state.  Of course, fields that
-                the readers refrain from accessing can be guarded by the
+                the readers refrain from accessing can be guarded by
-                update-side lock.
+                some other lock acquired only by updaters, if desired.
                This works quite well, also.
        c.      Make updates appear atomic to readers.  For example,
-                pointer updates to properly aligned fields will appear
+                pointer updates to properly aligned fields will
-                atomic, as will individual atomic primitives.  Operations
+                appear atomic, as will individual atomic primitives.
-                performed under a lock and sequences of multiple atomic
+                Sequences of perations performed under a lock will -not-
-                primitives will -not- appear to be atomic.
+                appear to be atomic to RCU readers, nor will sequences
+                of multiple atomic primitives.
                This can work, but is starting to get a bit tricky.
@@ -98,9 +101,9 @@ over a rather long period of time, but improvements are always welcome!
                a new structure containing updated values.
 4.      Weakly ordered CPUs pose special challenges.  Almost all CPUs
-        are weakly ordered -- even i386 CPUs allow reads to be reordered.
+        are weakly ordered -- even x86 CPUs allow later loads to be
-        RCU code must take all of the following measures to prevent
+        reordered to precede earlier stores.  RCU code must take all of
-        memory-corruption problems:
+        the following measures to prevent memory-corruption problems:
        a.      Readers must maintain proper ordering of their memory
                accesses.  The rcu_dereference() primitive ensures that
@@ -113,14 +116,25 @@ over a rather long period of time, but improvements are always welcome!
                The rcu_dereference() primitive is also an excellent
                documentation aid, letting the person reading the code
                know exactly which pointers are protected by RCU.
+                Please note that compilers can also reorder code, and
-                The rcu_dereference() primitive is used by the various
+                they are becoming increasingly aggressive about doing
-                "_rcu()" list-traversal primitives, such as the
+                just that.  The rcu_dereference() primitive therefore
-                list_for_each_entry_rcu().  Note that it is perfectly
+                also prevents destructive compiler optimizations.
-                legal (if redundant) for update-side code to use
-                rcu_dereference() and the "_rcu()" list-traversal
+                The rcu_dereference() primitive is used by the
-                primitives.  This is particularly useful in code
+                various "_rcu()" list-traversal primitives, such
-                that is common to readers and updaters.
+                as the list_for_each_entry_rcu().  Note that it is
+                perfectly legal (if redundant) for update-side code to
+                use rcu_dereference() and the "_rcu()" list-traversal
+                primitives.  This is particularly useful in code that
+                is common to readers and updaters.  However, lockdep
+                will complain if you access rcu_dereference() outside
+                of an RCU read-side critical section.  See lockdep.txt
+                to learn what to do about this.
+                Of course, neither rcu_dereference() nor the "_rcu()"
+                list-traversal primitives can substitute for a good
+                concurrency design coordinating among multiple updaters.
        b.      If the list macros are being used, the list_add_tail_rcu()
                and list_add_rcu() primitives must be used in order
@@ -135,11 +149,14 @@ over a rather long period of time, but improvements are always welcome!
                readers.  Similarly, if the hlist macros are being used,
                the hlist_del_rcu() primitive is required.
-                The list_replace_rcu() primitive may be used to
+                The list_replace_rcu() and hlist_replace_rcu() primitives
-                replace an old structure with a new one in an
+                may be used to replace an old structure with a new one
-                RCU-protected list.
+                in their respective types of RCU-protected lists.
+        d.      Rules similar to (4b) and (4c) apply to the "hlist_nulls"
+                type of RCU-protected linked lists.
-        d.      Updates must ensure that initialization of a given
+        e.      Updates must ensure that initialization of a given
                structure happens before pointers to that structure are
                publicized.  Use the rcu_assign_pointer() primitive
                when publicizing a pointer to a structure that can
@@ -151,16 +168,31 @@ over a rather long period of time, but improvements are always welcome!
        it cannot block.
 6.      Since synchronize_rcu() can block, it cannot be called from
-        any sort of irq context.  Ditto for synchronize_sched() and
+        any sort of irq context.  The same rule applies for
-        synchronize_srcu().
+        synchronize_rcu_bh(), synchronize_sched(), synchronize_srcu(),
+        synchronize_rcu_expedited(), synchronize_rcu_bh_expedited(),
-7.      If the updater uses call_rcu(), then the corresponding readers
+        synchronize_sched_expedite(), and synchronize_srcu_expedited().
-        must use rcu_read_lock() and rcu_read_unlock().  If the updater
-        uses call_rcu_bh(), then the corresponding readers must use
+        The expedited forms of these primitives have the same semantics
-        rcu_read_lock_bh() and rcu_read_unlock_bh().  If the updater
+        as the non-expedited forms, but expediting is both expensive
-        uses call_rcu_sched(), then the corresponding readers must
+        and unfriendly to real-time workloads.  Use of the expedited
-        disable preemption.  Mixing things up will result in confusion
+        primitives should be restricted to rare configuration-change
-        and broken kernels.
+        operations that would not normally be undertaken while a real-time
+        workload is running.
+7.      If the updater uses call_rcu() or synchronize_rcu(), then the
+        corresponding readers must use rcu_read_lock() and
+        rcu_read_unlock().  If the updater uses call_rcu_bh() or
+        synchronize_rcu_bh(), then the corresponding readers must
+        use rcu_read_lock_bh() and rcu_read_unlock_bh().  If the
+        updater uses call_rcu_sched() or synchronize_sched(), then
+        the corresponding readers must disable preemption, possibly
+        by calling rcu_read_lock_sched() and rcu_read_unlock_sched().
+        If the updater uses synchronize_srcu(), the the corresponding
+        readers must use srcu_read_lock() and srcu_read_unlock(),
+        and with the same srcu_struct.  The rules for the expedited
+        primitives are the same as for their non-expedited counterparts.
+        Mixing things up will result in confusion and broken kernels.
        One exception to this rule: rcu_read_lock() and rcu_read_unlock()
        may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
@@ -212,6 +244,8 @@ over a rather long period of time, but improvements are always welcome!
        e.      Periodically invoke synchronize_rcu(), permitting a limited
                number of updates per grace period.
+        The same cautions apply to call_rcu_bh() and call_rcu_sched().
 9.      All RCU list-traversal primitives, which include
        rcu_dereference(), list_for_each_entry_rcu(),
        list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
@@ -219,17 +253,21 @@ over a rather long period of time, but improvements are always welcome!
        must be protected by appropriate update-side locks.  RCU
        read-side critical sections are delimited by rcu_read_lock()
        and rcu_read_unlock(), or by similar primitives such as
-        rcu_read_lock_bh() and rcu_read_unlock_bh().
+        rcu_read_lock_bh() and rcu_read_unlock_bh(), in which case
+        the matching rcu_dereference() primitive must be used in order
+        to keep lockdep happy, in this case, rcu_dereference_bh().
        The reason that it is permissible to use RCU list-traversal
        primitives when the update-side lock is held is that doing so
        can be quite helpful in reducing code bloat when common code is
-        shared between readers and updaters.
+        shared between readers and updaters.  Additional primitives
+        are provided for this case, as discussed in lockdep.txt.
 10.     Conversely, if you are in an RCU read-side critical section,
        and you don't hold the appropriate update-side lock, you -must-
        use the "_rcu()" variants of the list macros.  Failing to do so
-        will break Alpha and confuse people reading your code.
+        will break Alpha, cause aggressive compilers to generate bad code,
+        and confuse people trying to read your code.
 11.     Note that synchronize_rcu() -only- guarantees to wait until
        all currently executing rcu_read_lock()-protected RCU read-side
@@ -239,15 +277,21 @@ over a rather long period of time, but improvements are always welcome!
        rcu_read_lock()-protected read-side critical sections, do -not-
        use synchronize_rcu().
-        If you want to wait for some of these other things, you might
+        Similarly, disabling preemption is not an acceptable substitute
-        instead need to use synchronize_irq() or synchronize_sched().
+        for rcu_read_lock().  Code that attempts to use preemption
+        disabling where it should be using rcu_read_lock() will break
+        in real-time kernel builds.
+        If you want to wait for interrupt handlers, NMI handlers, and
+        code under the influence of preempt_disable(), you instead
+        need to use synchronize_irq() or synchronize_sched().
 12.     Any lock acquired by an RCU callback must be acquired elsewhere
        with softirq disabled, e.g., via spin_lock_irqsave(),
        spin_lock_bh(), etc.  Failing to disable irq on a given
-        acquisition of that lock will result in deadlock as soon as the
+        acquisition of that lock will result in deadlock as soon as
-        RCU callback happens to interrupt that acquisition's critical
+        the RCU softirq handler happens to run your RCU callback while
-        section.
+        interrupting that acquisition's critical section.
 13.     RCU callbacks can be and are executed in parallel.  In many cases,
        the callback code simply wrappers around kfree(), so that this
@@ -265,29 +309,30 @@ over a rather long period of time, but improvements are always welcome!
        not the case, a self-spawning RCU callback would prevent the
        victim CPU from ever going offline.)
-14.     SRCU (srcu_read_lock(), srcu_read_unlock(), and synchronize_srcu())
+14.     SRCU (srcu_read_lock(), srcu_read_unlock(), srcu_dereference(),
-        may only be invoked from process context.  Unlike other forms of
+        synchronize_srcu(), and synchronize_srcu_expedited()) may only
-        RCU, it -is- permissible to block in an SRCU read-side critical
+        be invoked from process context.  Unlike other forms of RCU, it
-        section (demarked by srcu_read_lock() and srcu_read_unlock()),
+        -is- permissible to block in an SRCU read-side critical section
-        hence the "SRCU": "sleepable RCU".  Please note that if you
+        (demarked by srcu_read_lock() and srcu_read_unlock()), hence the
-        don't need to sleep in read-side critical sections, you should
+        "SRCU": "sleepable RCU".  Please note that if you don't need
-        be using RCU rather than SRCU, because RCU is almost always
+        to sleep in read-side critical sections, you should be using
-        faster and easier to use than is SRCU.
+        RCU rather than SRCU, because RCU is almost always faster and
+        easier to use than is SRCU.
        Also unlike other forms of RCU, explicit initialization
        and cleanup is required via init_srcu_struct() and
        cleanup_srcu_struct().  These are passed a "struct srcu_struct"
        that defines the scope of a given SRCU domain.  Once initialized,
        the srcu_struct is passed to srcu_read_lock(), srcu_read_unlock()
-        and synchronize_srcu().  A given synchronize_srcu() waits only
+        synchronize_srcu(), and synchronize_srcu_expedited().  A given
-        for SRCU read-side critical sections governed by srcu_read_lock()
+        synchronize_srcu() waits only for SRCU read-side critical
-        and srcu_read_unlock() calls that have been passd the same
+        sections governed by srcu_read_lock() and srcu_read_unlock()
-        srcu_struct.  This property is what makes sleeping read-side
+        calls that have been passed the same srcu_struct.  This property
-        critical sections tolerable -- a given subsystem delays only
+        is what makes sleeping read-side critical sections tolerable --
-        its own updates, not those of other subsystems using SRCU.
+        a given subsystem delays only its own updates, not those of other
-        Therefore, SRCU is less prone to OOM the system than RCU would
+        subsystems using SRCU.  Therefore, SRCU is less prone to OOM the
-        be if RCU's read-side critical sections were permitted to
+        system than RCU would be if RCU's read-side critical sections
-        sleep.
+        were permitted to sleep.
        The ability to sleep in read-side critical sections does not
        come for free.  First, corresponding srcu_read_lock() and
@@ -300,8 +345,8 @@ over a rather long period of time, but improvements are always welcome!
        requiring SRCU's read-side deadlock immunity or low read-side
        realtime latency.
-        Note that, rcu_assign_pointer() and rcu_dereference() relate to
+        Note that, rcu_assign_pointer() relates to SRCU just as they do
-        SRCU just as they do to other forms of RCU.
+        to other forms of RCU.
 15.     The whole point of call_rcu(), synchronize_rcu(), and friends
        is to wait until all pre-existing readers have finished before
@@ -311,12 +356,12 @@ over a rather long period of time, but improvements are always welcome!
        destructive operation, and -only- -then- invoke call_rcu(),
        synchronize_rcu(), or friends.
-        Because these primitives only wait for pre-existing readers,
+        Because these primitives only wait for pre-existing readers, it
-        it is the caller's responsibility to guarantee safety to
+        is the caller's responsibility to guarantee that any subsequent
-        any subsequent readers.
+        readers will execute safely.
-16.     The various RCU read-side primitives do -not- contain memory
+16.     The various RCU read-side primitives do -not- necessarily contain
-        barriers.  The CPU (and in some cases, the compiler) is free
+        memory barriers.  You should therefore plan for the CPU
-        to reorder code into and out of RCU read-side critical sections.
+        and the compiler to freely reorder code into and out of RCU
-        It is the responsibility of the RCU update-side primitives to
+        read-side critical sections.  It is the responsibility of the
-        deal with this.
+        RCU update-side primitives to deal with this.
diff --git a/Documentation/RCU/lockdep.txt b/Documentation/RCU/lockdep.txt
new file mode 100644
index 000000000000..d7a49b2f6994
--- /dev/null
+++ b/Documentation/RCU/lockdep.txt
@@ -0,0 +1,91 @@
+RCU and lockdep checking
+All flavors of RCU have lockdep checking available, so that lockdep is
+aware of when each task enters and leaves any flavor of RCU read-side
+critical section.  Each flavor of RCU is tracked separately (but note
+that this is not the case in 2.6.32 and earlier).  This allows lockdep's
+tracking to include RCU state, which can sometimes help when debugging
+deadlocks and the like.
+In addition, RCU provides the following primitives that check lockdep's
+state:
+        rcu_read_lock_held() for normal RCU.
+        rcu_read_lock_bh_held() for RCU-bh.
+        rcu_read_lock_sched_held() for RCU-sched.
+        srcu_read_lock_held() for SRCU.
+These functions are conservative, and will therefore return 1 if they
+aren't certain (for example, if CONFIG_DEBUG_LOCK_ALLOC is not set).
+This prevents things like WARN_ON(!rcu_read_lock_held()) from giving false
+positives when lockdep is disabled.
+In addition, a separate kernel config parameter CONFIG_PROVE_RCU enables
+checking of rcu_dereference() primitives:
+        rcu_dereference(p):
+                Check for RCU read-side critical section.
+        rcu_dereference_bh(p):
+                Check for RCU-bh read-side critical section.
+        rcu_dereference_sched(p):
+                Check for RCU-sched read-side critical section.
+        srcu_dereference(p, sp):
+                Check for SRCU read-side critical section.
+        rcu_dereference_check(p, c):
+                Use explicit check expression "c".  This is useful in
+                code that is invoked by both 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
+                and compiler constraints.  This is useful when the data
+                structure cannot change, for example, in code that is
+                invoked only by updaters.
+        rcu_access_pointer(p):
+                Return the value of the pointer and omit all barriers,
+                but retain the compiler constraints that prevent duplicating
+                or coalescsing.  This is useful when when testing the
+                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:
+        file = rcu_dereference_check(fdt->fd[fd],
+                                     rcu_read_lock_held() ||
+                                     lockdep_is_held(&files->file_lock) ||
+                                     atomic_read(&files->count) == 1);
+This expression picks up the pointer "fdt->fd[fd]" in an RCU-safe manner,
+and, if CONFIG_PROVE_RCU is configured, verifies that this expression
+is used in:
+1.      An RCU read-side critical section, or
+2.      with files->file_lock held, or
+3.      on an unshared files_struct.
+In case (1), the pointer is picked up in an RCU-safe manner for vanilla
+RCU read-side critical sections, in case (2) the ->file_lock prevents
+any change from taking place, and finally, in case (3) the current task
+is the only task accessing the file_struct, again preventing any change
+from taking place.  If the above statement was invoked only from updater
+code, it could instead be written as follows:
+        file = rcu_dereference_protected(fdt->fd[fd],
+                                         lockdep_is_held(&files->file_lock) ||
+                                         atomic_read(&files->count) == 1);
+This would verify cases #2 and #3 above, and furthermore lockdep would
+complain if this was used in an RCU read-side critical section unless one
+of these two cases held.  Because rcu_dereference_protected() omits all
+barriers and compiler constraints, it generates better code than do the
+other flavors of rcu_dereference().  On the other hand, it is illegal
+to use rcu_dereference_protected() if either the RCU-protected pointer
+or the RCU-protected data that it points to can change concurrently.
+There are currently only "universal" versions of the rcu_assign_pointer()
+and RCU list-/tree-traversal primitives, which do not (yet) check for
+being in an RCU read-side critical section.  In the future, separate
+versions of these primitives might be created.
diff --git a/Documentation/RCU/rcu.txt b/Documentation/RCU/rcu.txt
index 2a23523ce471..31852705b586 100644
--- a/Documentation/RCU/rcu.txt
+++ b/Documentation/RCU/rcu.txt
@@ -75,6 +75,8 @@ o	I hear that RCU is patented?  What is with that?
        search for the string "Patent" in RTFP.txt to find them.
        Of these, one was allowed to lapse by the assignee, and the
        others have been contributed to the Linux kernel under GPL.
+        There are now also LGPL implementations of user-level RCU
+        available (http://lttng.org/?q=node/18).
 o       I hear that RCU needs work in order to support realtime kernels?
@@ -91,48 +93,4 @@ o	Where can I find more information on RCU?
 o       What are all these files in this directory?
+        See 00-INDEX for the list.
-        NMI-RCU.txt
-                Describes how to use RCU to implement dynamic
-                NMI handlers, which can be revectored on the fly,
-                without rebooting.
-        RTFP.txt
-                List of RCU-related publications and web sites.
-        UP.txt
-                Discussion of RCU usage in UP kernels.
-        arrayRCU.txt
-                Describes how to use RCU to protect arrays, with
-                resizeable arrays whose elements reference other
-                data structures being of the most interest.
-        checklist.txt
-                Lists things to check for when inspecting code that
-                uses RCU.
-        listRCU.txt
-                Describes how to use RCU to protect linked lists.
-                This is the simplest and most common use of RCU
-                in the Linux kernel.
-        rcu.txt
-                You are reading it!
-        rcuref.txt
-                Describes how to combine use of reference counts
-                with RCU.
-        whatisRCU.txt
-                Overview of how the RCU implementation works.  Along
-                the way, presents a conceptual view of RCU.
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
new file mode 100644
index 000000000000..44c6dcc93d6d
--- /dev/null
+++ b/Documentation/RCU/stallwarn.txt
@@ -0,0 +1,106 @@
+Using RCU's CPU Stall Detector
+The CONFIG_RCU_CPU_STALL_DETECTOR kernel config parameter enables
+RCU's CPU stall detector, which detects conditions that unduly delay
+RCU grace periods.  The stall detector's idea of what constitutes
+"unduly delayed" is controlled by a set of C preprocessor macros:
+RCU_SECONDS_TILL_STALL_CHECK
+        This macro defines the period of time that RCU will wait from
+        the beginning of a grace period until it issues an RCU CPU
+        stall warning.  This time period is normally ten seconds.
+RCU_SECONDS_TILL_STALL_RECHECK
+        This macro defines the period of time that RCU will wait after
+        issuing a stall warning until it issues another stall warning
+        for the same stall.  This time period is normally set to thirty
+        seconds.
+RCU_STALL_RAT_DELAY
+        The CPU stall detector tries to make the offending CPU print its
+        own warnings, as this often gives better-quality stack traces.
+        However, if the offending CPU does not detect its own stall in
+        the number of jiffies specified by RCU_STALL_RAT_DELAY, then
+        some other CPU will complain.  This delay is normally set to
+        two jiffies.
+When a CPU detects that it is stalling, it will print a message similar
+to the following:
+INFO: rcu_sched_state detected stall on CPU 5 (t=2500 jiffies)
+This message indicates that CPU 5 detected that it was causing a stall,
+and that the stall was affecting RCU-sched.  This message will normally be
+followed by a stack dump of the offending CPU.  On TREE_RCU kernel builds,
+RCU and RCU-sched are implemented by the same underlying mechanism,
+while on TREE_PREEMPT_RCU kernel builds, RCU is instead implemented
+by rcu_preempt_state.
+On the other hand, if the offending CPU fails to print out a stall-warning
+message quickly enough, some other CPU will print a message similar to
+the following:
+INFO: rcu_bh_state detected stalls on CPUs/tasks: { 3 5 } (detected by 2, 2502 jiffies)
+This message indicates that CPU 2 detected that CPUs 3 and 5 were both
+causing stalls, and that the stall was affecting RCU-bh.  This message
+will normally be followed by stack dumps for each CPU.  Please note that
+TREE_PREEMPT_RCU builds can be stalled by tasks as well as by CPUs,
+and that the tasks will be indicated by PID, for example, "P3421".
+It is even possible for a rcu_preempt_state stall to be caused by both
+CPUs -and- tasks, in which case the offending CPUs and tasks will all
+be called out in the list.
+Finally, if the grace period ends just as the stall warning starts
+printing, there will be a spurious stall-warning message:
+INFO: rcu_bh_state detected stalls on CPUs/tasks: { } (detected by 4, 2502 jiffies)
+This is rare, but does happen from time to time in real life.
+So your kernel printed an RCU CPU stall warning.  The next question is
+"What caused it?"  The following problems can result in RCU CPU stall
+warnings:
+o       A CPU looping in an RCU read-side critical section.
+        
+o       A CPU looping with interrupts disabled.  This condition can
+        result in RCU-sched and RCU-bh stalls.
+o       A CPU looping with preemption disabled.  This condition can
+        result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
+        stalls.
+o       A CPU looping with bottom halves disabled.  This condition can
+        result in RCU-sched and RCU-bh stalls.
+o       For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
+        without invoking schedule().
+o       A bug in the RCU implementation.
+o       A hardware failure.  This is quite unlikely, but has occurred
+        at least once in real life.  A CPU failed in a running system,
+        becoming unresponsive, but not causing an immediate crash.
+        This resulted in a series of RCU CPU stall warnings, eventually
+        leading the realization that the CPU had failed.
+The RCU, RCU-sched, and RCU-bh implementations have CPU stall
+warning.  SRCU does not have its own CPU stall warnings, but its
+calls to synchronize_sched() will result in RCU-sched detecting
+RCU-sched-related CPU stalls.  Please note that RCU only detects
+CPU stalls when there is a grace period in progress.  No grace period,
+no CPU stall warnings.
+To diagnose the cause of the stall, inspect the stack traces.
+The offending function will usually be near the top of the stack.
+If you have a series of stall warnings from a single extended stall,
+comparing the stack traces can often help determine where the stall
+is occurring, which will usually be in the function nearest the top of
+that portion of the stack which remains the same from trace to trace.
+If you can reliably trigger the stall, ftrace can be quite helpful.
+RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE.
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index 9dba3bb90e60..5d9016795fd8 100644
--- a/Documentation/RCU/torture.txt
+++ b/Documentation/RCU/torture.txt
@@ -30,6 +30,18 @@ MODULE PARAMETERS
 This module has the following parameters:
+fqs_duration    Duration (in microseconds) of artificially induced bursts
+                of force_quiescent_state() invocations.  In RCU
+                implementations having force_quiescent_state(), these
+                bursts help force races between forcing a given grace
+                period and that grace period ending on its own.
+fqs_holdoff     Holdoff time (in microseconds) between consecutive calls
+                to force_quiescent_state() within a burst.
+fqs_stutter     Wait time (in seconds) between consecutive bursts
+                of calls to force_quiescent_state().
 irqreaders      Says to invoke RCU readers from irq level.  This is currently
                done via timers.  Defaults to "1" for variants of RCU that
                permit this.  (Or, more accurately, variants of RCU that do
@@ -170,16 +182,6 @@ Similarly, sched_expedited RCU provides the following:
        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
-        state: -1 / 0:0 3:0 4:0
-As before, the first four lines are similar to those for RCU.
-The last line shows the task-migration state.  The first number is
-1 if synchronize_sched_expedited() is idle, -2 if in the process of
-posting wakeups to the migration kthreads, and N when waiting on CPU N.
-Each of the colon-separated fields following the "/" is a CPU:state pair.
-Valid states are "0" for idle, "1" for waiting for quiescent state,
-"2" for passed through quiescent state, and "3" when a race with a
-CPU-hotplug event forces use of the synchronize_sched() primitive.
 USAGE
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 8608fd85e921..efd8cc95c06b 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -256,23 +256,23 @@ o	Each element of the form "1/1 0:127 ^0" represents one struct
 The output of "cat rcu/rcu_pending" looks as follows:
 rcu_sched:
-  0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
+  0 np=255892 qsp=53936 rpq=85 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
-  1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
+  1 np=261224 qsp=54638 rpq=33 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
-  2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
+  2 np=237496 qsp=49664 rpq=23 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
-  3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
+  3 np=236249 qsp=48766 rpq=98 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
-  4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
+  4 np=221310 qsp=46850 rpq=7 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
-  5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
+  5 np=237332 qsp=48449 rpq=9 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
-  6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
+  6 np=219995 qsp=46718 rpq=12 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
-  7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
+  7 np=249893 qsp=49390 rpq=42 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
 rcu_bh:
-  0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
+  0 np=146741 qsp=1419 rpq=6 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
-  1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
+  1 np=155792 qsp=12597 rpq=3 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
-  2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
+  2 np=136629 qsp=18680 rpq=1 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
-  3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
+  3 np=137723 qsp=2843 rpq=0 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
-  4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
+  4 np=123110 qsp=12433 rpq=0 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
-  5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
+  5 np=137456 qsp=4210 rpq=1 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
-  6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
+  6 np=120834 qsp=9902 rpq=2 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
-  7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
+  7 np=144888 qsp=26336 rpq=0 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
 As always, this is once again split into "rcu_sched" and "rcu_bh"
 portions, with CONFIG_TREE_PREEMPT_RCU kernels having an additional
@@ -284,6 +284,9 @@ o	"np" is the number of times that __rcu_pending() has been invoked
 o       "qsp" is the number of times that the RCU was waiting for a
        quiescent state from this CPU.
+o       "rpq" is the number of times that the CPU had passed through
+        a quiescent state, but not yet reported it to RCU.
 o       "cbr" is the number of times that this CPU had RCU callbacks
        that had passed through a grace period, and were thus ready
        to be invoked.
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index d542ca243b80..cfaac34c4557 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -323,14 +323,17 @@ used as follows:
        Defer                   Protect
 a.      synchronize_rcu()       rcu_read_lock() / rcu_read_unlock()
-        call_rcu()
+        call_rcu()              rcu_dereference()
 b.      call_rcu_bh()           rcu_read_lock_bh() / rcu_read_unlock_bh()
+                                rcu_dereference_bh()
-c.      synchronize_sched()     preempt_disable() / preempt_enable()
+c.      synchronize_sched()     rcu_read_lock_sched() / rcu_read_unlock_sched()
+                                preempt_disable() / preempt_enable()
                                local_irq_save() / local_irq_restore()
                                hardirq enter / hardirq exit
                                NMI enter / NMI exit
+                                rcu_dereference_sched()
 These three mechanisms are used as follows:
@@ -780,9 +783,8 @@ Linux-kernel source code, but it helps to have a full list of the
 APIs, since there does not appear to be a way to categorize them
 in docbook.  Here is the list, by category.
-RCU pointer/list traversal:
+RCU list traversal:
-        rcu_dereference
        list_for_each_entry_rcu
        hlist_for_each_entry_rcu
        hlist_nulls_for_each_entry_rcu
@@ -808,7 +810,7 @@ RCU:	Critical sections	Grace period		Barrier
        rcu_read_lock           synchronize_net         rcu_barrier
        rcu_read_unlock         synchronize_rcu
-                                synchronize_rcu_expedited
+        rcu_dereference         synchronize_rcu_expedited
                                call_rcu
@@ -816,7 +818,7 @@ bh:	Critical sections	Grace period		Barrier
        rcu_read_lock_bh        call_rcu_bh             rcu_barrier_bh
        rcu_read_unlock_bh      synchronize_rcu_bh
-                                synchronize_rcu_bh_expedited
+        rcu_dereference_bh      synchronize_rcu_bh_expedited
 sched:  Critical sections       Grace period            Barrier
@@ -825,17 +827,25 @@ sched:	Critical sections	Grace period		Barrier
        rcu_read_unlock_sched   call_rcu_sched
        [preempt_disable]       synchronize_sched_expedited
        [and friends]
+        rcu_dereference_sched
 SRCU:   Critical sections       Grace period            Barrier
        srcu_read_lock          synchronize_srcu        N/A
        srcu_read_unlock        synchronize_srcu_expedited
+        srcu_dereference
 SRCU:   Initialization/cleanup
        init_srcu_struct
        cleanup_srcu_struct
+All:  lockdep-checked RCU-protected pointer access
+        rcu_dereference_check
+        rcu_dereference_protected
+        rcu_access_pointer
 See the comment headers in the source code (or the docbook generated
 from them) for more information.
diff --git a/Documentation/Smack.txt b/Documentation/Smack.txt
index 34614b4c708e..e9dab41c0fe0 100644
--- a/Documentation/Smack.txt
+++ b/Documentation/Smack.txt
@@ -73,7 +73,7 @@ NOTE: Smack labels are limited to 23 characters. The attr command
 If you don't do anything special all users will get the floor ("_")
 label when they log in. If you do want to log in via the hacked ssh
 at other labels use the attr command to set the smack value on the
-home directory and it's contents.
+home directory and its contents.
 You can add access rules in /etc/smack/accesses. They take the form:
diff --git a/Documentation/SubmitChecklist b/Documentation/SubmitChecklist
index 1053a56be3b1..da0382daa395 100644
--- a/Documentation/SubmitChecklist
+++ b/Documentation/SubmitChecklist
@@ -9,10 +9,16 @@ Documentation/SubmittingPatches and elsewhere regarding submitting Linux
 kernel patches.
-1: Builds cleanly with applicable or modified CONFIG options =y, =m, and
+1: If you use a facility then #include the file that defines/declares
+   that facility.  Don't depend on other header files pulling in ones
+   that you use.
+2: Builds cleanly with applicable or modified CONFIG options =y, =m, and
   =n.  No gcc warnings/errors, no linker warnings/errors.
-2: Passes allnoconfig, allmodconfig
+2b: Passes allnoconfig, allmodconfig
+2c: Builds successfully when using O=builddir
 3: Builds on multiple CPU architectures by using local cross-compile tools
   or some other build farm.
@@ -91,3 +97,13 @@ kernel patches.
 25: If any ioctl's are added by the patch, then also update
    Documentation/ioctl/ioctl-number.txt.
+26: If your modified source code depends on or uses any of the kernel
+    APIs or features that are related to the following kconfig symbols,
+    then test multiple builds with the related kconfig symbols disabled
+    and/or =m (if that option is available) [not all of these at the
+    same time, just various/random combinations of them]:
+    CONFIG_SMP, CONFIG_SYSFS, CONFIG_PROC_FS, CONFIG_INPUT, CONFIG_PCI,
+    CONFIG_BLOCK, CONFIG_PM, CONFIG_HOTPLUG, CONFIG_MAGIC_SYSRQ,
+    CONFIG_NET, CONFIG_INET=n (but latter with CONFIG_NET=y)
diff --git a/Documentation/SubmittingDrivers b/Documentation/SubmittingDrivers
index 99e72a81fa2f..4947fd8fb182 100644
--- a/Documentation/SubmittingDrivers
+++ b/Documentation/SubmittingDrivers
@@ -130,6 +130,8 @@ Linux kernel master tree:
        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
 Linux kernel mailing list:
        linux-kernel@vger.kernel.org
        [mail majordomo@vger.kernel.org to subscribe]
@@ -160,3 +162,6 @@ How to NOT write kernel driver by Arjan van de Ven:
 Kernel Janitor:
        http://janitor.kernelnewbies.org/
+GIT, Fast Version Control System:
+        http://git-scm.com/
diff --git a/Documentation/arm/00-INDEX b/Documentation/arm/00-INDEX
index 82e418d648d0..7f5fc3ba9c91 100644
--- a/Documentation/arm/00-INDEX
+++ b/Documentation/arm/00-INDEX
@@ -20,6 +20,8 @@ Samsung-S3C24XX
        - S3C24XX ARM Linux Overview
 Sharp-LH
        - Linux on Sharp LH79524 and LH7A40X System On a Chip (SOC)
+SPEAr
+        - ST SPEAr platform Linux Overview
 VFP/
        - Release notes for Linux Kernel Vector Floating Point support code
 empeg/
diff --git a/Documentation/arm/SA1100/ADSBitsy b/Documentation/arm/SA1100/ADSBitsy
index 7197a9e958ee..f9f62e8c0719 100644
--- a/Documentation/arm/SA1100/ADSBitsy
+++ b/Documentation/arm/SA1100/ADSBitsy
@@ -32,7 +32,7 @@ Notes:
 - The flash on board is divided into 3 partitions.
  You should be careful to use flash on board.
-  It's partition is different from GraphicsClient Plus and GraphicsMaster
+  Its partition is different from GraphicsClient Plus and GraphicsMaster
 - 16bpp mode requires a different cable than what ships with the board.
  Contact ADS or look through the manual to wire your own. Currently,
diff --git a/Documentation/arm/SPEAr/overview.txt b/Documentation/arm/SPEAr/overview.txt
new file mode 100644
index 000000000000..253a35c6f782
--- /dev/null
+++ b/Documentation/arm/SPEAr/overview.txt
@@ -0,0 +1,60 @@
+                        SPEAr ARM Linux Overview
+                        ==========================
+Introduction
+------------
+  SPEAr (Structured Processor Enhanced Architecture).
+  weblink : http://www.st.com/spear
+  The ST Microelectronics SPEAr range of ARM9/CortexA9 System-on-Chip CPUs are
+  supported by the 'spear' platform of ARM Linux. Currently SPEAr300,
+  SPEAr310, SPEAr320 and SPEAr600 SOCs are supported. Support for the SPEAr13XX
+  series is in progress.
+  Hierarchy in SPEAr is as follows:
+  SPEAr (Platform)
+        - SPEAr3XX (3XX SOC series, based on ARM9)
+                - SPEAr300 (SOC)
+                        - SPEAr300_EVB (Evaluation Board)
+                - SPEAr310 (SOC)
+                        - SPEAr310_EVB (Evaluation Board)
+                - SPEAr320 (SOC)
+                        - SPEAr320_EVB (Evaluation Board)
+        - SPEAr6XX (6XX SOC series, based on ARM9)
+                - SPEAr600 (SOC)
+                        - SPEAr600_EVB (Evaluation Board)
+        - SPEAr13XX (13XX SOC series, based on ARM CORTEXA9)
+                - SPEAr1300 (SOC)
+  Configuration
+  -------------
+  A generic configuration is provided for each machine, and can be used as the
+  default by
+        make spear600_defconfig
+        make spear300_defconfig
+        make spear310_defconfig
+        make spear320_defconfig
+  Layout
+  ------
+  The common files for multiple machine families (SPEAr3XX, SPEAr6XX and
+  SPEAr13XX) are located in the platform code contained in arch/arm/plat-spear
+  with headers in plat/.
+  Each machine series have a directory with name arch/arm/mach-spear followed by
+  series name. Like mach-spear3xx, mach-spear6xx and mach-spear13xx.
+  Common file for machines of spear3xx family is mach-spear3xx/spear3xx.c and for
+  spear6xx is mach-spear6xx/spear6xx.c. mach-spear* also contain soc/machine
+  specific files, like spear300.c, spear310.c, spear320.c and spear600.c.
+  mach-spear* also contains board specific files for each machine type.
+  Document Author
+  ---------------
+  Viresh Kumar, (c) 2010 ST Microelectronics
diff --git a/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt b/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt
index 76b3a11e90be..fa968aa99d67 100644
--- a/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt
+++ b/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt
@@ -14,8 +14,8 @@ Introduction
 how the clocks are arranged. The first implementation used as single
 PLL to feed the ARM, memory and peripherals via a series of dividers
 and muxes and this is the implementation that is documented here. A
- newer version where there is a seperate PLL and clock divider for the
+ newer version where there is a separate PLL and clock divider for the
- ARM core is available as a seperate driver.
+ ARM core is available as a separate driver.
 Layout
diff --git a/Documentation/arm/Samsung/Overview.txt b/Documentation/arm/Samsung/Overview.txt
new file mode 100644
index 000000000000..7cced1fea9c3
--- /dev/null
+++ b/Documentation/arm/Samsung/Overview.txt
@@ -0,0 +1,86 @@
+                Samsung ARM Linux Overview
+                ==========================
+Introduction
+------------
+  The Samsung range of ARM SoCs spans many similar devices, from the initial
+  ARM9 through to the newest ARM cores. This document shows an overview of
+  the current kernel support, how to use it and where to find the code
+  that supports this.
+  The currently supported SoCs are:
+  - S3C24XX: See Documentation/arm/Samsung-S3C24XX/Overview.txt for full list
+  - S3C64XX: S3C6400 and S3C6410
+  - S5PC6440
+  S5PC100 and S5PC110 support is currently being merged
+S3C24XX Systems
+---------------
+  There is still documentation in Documnetation/arm/Samsung-S3C24XX/ which
+  deals with the architecture and drivers specific to these devices.
+  See Documentation/arm/Samsung-S3C24XX/Overview.txt for more information
+  on the implementation details and specific support.
+Configuration
+-------------
+  A number of configurations are supplied, as there is no current way of
+  unifying all the SoCs into one kernel.
+  s5p6440_defconfig - S5P6440 specific default configuration
+  s5pc100_defconfig - S5PC100 specific default configuration
+Layout
+------
+  The directory layout is currently being restructured, and consists of
+  several platform directories and then the machine specific directories
+  of the CPUs being built for.
+  plat-samsung provides the base for all the implementations, and is the
+  last in the line of include directories that are processed for the build
+  specific information. It contains the base clock, GPIO and device definitions
+  to get the system running.
+  plat-s3c is the s3c24xx/s3c64xx platform directory, although it is currently
+  involved in other builds this will be phased out once the relevant code is
+  moved elsewhere.
+  plat-s3c24xx is for s3c24xx specific builds, see the S3C24XX docs.
+  plat-s3c64xx is for the s3c64xx specific bits, see the S3C24XX docs.
+  plat-s5p is for s5p specific builds, more to be added.
+  [ to finish ]
+Port Contributors
+-----------------
+  Ben Dooks (BJD)
+  Vincent Sanders
+  Herbert Potzl
+  Arnaud Patard (RTP)
+  Roc Wu
+  Klaus Fetscher
+  Dimitry Andric
+  Shannon Holland
+  Guillaume Gourat (NexVision)
+  Christer Weinigel (wingel) (Acer N30)
+  Lucas Correia Villa Real (S3C2400 port)
+Document Author
+---------------
+Copyright 2009-2010 Ben Dooks <ben-linux@fluff.org>
diff --git a/Documentation/arm/Samsung/clksrc-change-registers.awk b/Documentation/arm/Samsung/clksrc-change-registers.awk
new file mode 100755
index 000000000000..0c50220851fb
--- /dev/null
+++ b/Documentation/arm/Samsung/clksrc-change-registers.awk
@@ -0,0 +1,167 @@
+#!/usr/bin/awk -f
+#
+# Copyright 2010 Ben Dooks <ben-linux@fluff.org>
+#
+# Released under GPLv2
+# example usage
+# ./clksrc-change-registers.awk arch/arm/plat-s5pc1xx/include/plat/regs-clock.h < src > dst
+function extract_value(s)
+{
+    eqat = index(s, "=")
+    comat = index(s, ",")
+    return substr(s, eqat+2, (comat-eqat)-2)
+}
+function remove_brackets(b)
+{
+    return substr(b, 2, length(b)-2)
+}
+function splitdefine(l, p)
+{
+    r = split(l, tp)
+    p[0] = tp[2]
+    p[1] = remove_brackets(tp[3])
+}
+function find_length(f)
+{
+    if (0)
+        printf "find_length " f "\n" > "/dev/stderr"
+    if (f ~ /0x1/)
+        return 1
+    else if (f ~ /0x3/)
+        return 2
+    else if (f ~ /0x7/)
+        return 3
+    else if (f ~ /0xf/)
+        return 4
+    printf "unknown legnth " f "\n" > "/dev/stderr"
+    exit
+}
+function find_shift(s)
+{
+    id = index(s, "<")
+    if (id <= 0) {
+        printf "cannot find shift " s "\n" > "/dev/stderr"
+        exit
+    }
+    return substr(s, id+2)
+}
+BEGIN {
+    if (ARGC < 2) {
+        print "too few arguments" > "/dev/stderr"
+        exit
+    }
+# read the header file and find the mask values that we will need
+# to replace and create an associative array of values
+    while (getline line < ARGV[1] > 0) {
+        if (line ~ /\#define.*_MASK/ &&
+            !(line ~ /S5PC100_EPLL_MASK/) &&
+            !(line ~ /USB_SIG_MASK/)) {
+            splitdefine(line, fields)
+            name = fields[0]
+            if (0)
+                printf "MASK " line "\n" > "/dev/stderr"
+            dmask[name,0] = find_length(fields[1])
+            dmask[name,1] = find_shift(fields[1])
+            if (0)
+                printf "=> '" name "' LENGTH=" dmask[name,0] " SHIFT=" dmask[name,1] "\n" > "/dev/stderr"
+        } else {
+        }
+    }
+    delete ARGV[1]
+}
+/clksrc_clk.*=.*{/ {
+    shift=""
+    mask=""
+    divshift=""
+    reg_div=""
+    reg_src=""
+    indent=1
+    print $0
+    for(; indent >= 1;) {
+        if ((getline line) <= 0) {
+            printf "unexpected end of file" > "/dev/stderr"
+            exit 1;
+        }
+        if (line ~ /\.shift/) {
+            shift = extract_value(line)
+        } else if (line ~ /\.mask/) {
+            mask = extract_value(line)
+        } else if (line ~ /\.reg_divider/) {
+            reg_div = extract_value(line)
+        } else if (line ~ /\.reg_source/) {
+            reg_src = extract_value(line)
+        } else if (line ~ /\.divider_shift/) {
+            divshift = extract_value(line)
+        } else if (line ~ /{/) {
+                indent++
+                print line
+            } else if (line ~ /}/) {
+            indent--
+            if (indent == 0) {
+                if (0) {
+                    printf "shift '" shift   "' ='" dmask[shift,0] "'\n" > "/dev/stderr"
+                    printf "mask  '" mask    "'\n" > "/dev/stderr"
+                    printf "dshft '" divshift "'\n" > "/dev/stderr"
+                    printf "rdiv  '" reg_div "'\n" > "/dev/stderr"
+                    printf "rsrc  '" reg_src "'\n" > "/dev/stderr"
+                }
+                generated = mask
+                sub(reg_src, reg_div, generated)
+                if (0) {
+                    printf "/* rsrc " reg_src " */\n"
+                    printf "/* rdiv " reg_div " */\n"
+                    printf "/* shift " shift " */\n"
+                    printf "/* mask " mask " */\n"
+                    printf "/* generated " generated " */\n"
+                }
+                if (reg_div != "") {
+                    printf "\t.reg_div = { "
+                    printf ".reg = " reg_div ", "
+                    printf ".shift = " dmask[generated,1] ", "
+                    printf ".size = " dmask[generated,0] ", "
+                    printf "},\n"
+                }
+                printf "\t.reg_src = { "
+                printf ".reg = " reg_src ", "
+                printf ".shift = " dmask[mask,1] ", "
+                printf ".size = " dmask[mask,0] ", "
+                printf "},\n"
+            }
+            print line
+        } else {
+            print line
+        }
+        if (0)
+            printf indent ":" line "\n" > "/dev/stderr"
+    }
+}
+// && ! /clksrc_clk.*=.*{/ { print $0 }
diff --git a/Documentation/arm/Sharp-LH/ADC-LH7-Touchscreen b/Documentation/arm/Sharp-LH/ADC-LH7-Touchscreen
index 1e6a23fdf2fc..dc460f055647 100644
--- a/Documentation/arm/Sharp-LH/ADC-LH7-Touchscreen
+++ b/Documentation/arm/Sharp-LH/ADC-LH7-Touchscreen
@@ -7,7 +7,7 @@ The driver only implements a four-wire touch panel protocol.
 The touchscreen driver is maintenance free except for the pen-down or
 touch threshold.  Some resistive displays and board combinations may
-require tuning of this threshold.  The driver exposes some of it's
+require tuning of this threshold.  The driver exposes some of its
 internal state in the sys filesystem.  If the kernel is configured
 with it, CONFIG_SYSFS, and sysfs is mounted at /sys, there will be a
 directory
diff --git a/Documentation/arm/memory.txt b/Documentation/arm/memory.txt
index 9d58c7c5eddd..eb0fae18ffb1 100644
--- a/Documentation/arm/memory.txt
+++ b/Documentation/arm/memory.txt
@@ -59,7 +59,11 @@ PAGE_OFFSET	high_memory-1	Kernel direct-mapped RAM region.
                                This maps the platforms RAM, and typically
                                maps all platform RAM in a 1:1 relationship.
-TASK_SIZE       PAGE_OFFSET-1   Kernel module space
+PKMAP_BASE      PAGE_OFFSET-1   Permanent kernel mappings
+                                One way of mapping HIGHMEM pages into kernel
+                                space.
+MODULES_VADDR   MODULES_END-1   Kernel module space
                                Kernel modules inserted via insmod are
                                placed here using dynamic mappings.
diff --git a/Documentation/atomic_ops.txt b/Documentation/atomic_ops.txt
index 396bec3b74ed..ac4d47187122 100644
--- a/Documentation/atomic_ops.txt
+++ b/Documentation/atomic_ops.txt
@@ -320,7 +320,7 @@ counter decrement would not become globally visible until the
 obj->active update does.
 As a historical note, 32-bit Sparc used to only allow usage of
-24-bits of it's atomic_t type.  This was because it used 8 bits
+24-bits of its atomic_t type.  This was because it used 8 bits
 as a spinlock for SMP safety.  Sparc32 lacked a "compare and swap"
 type instruction.  However, 32-bit Sparc has since been moved over
 to a "hash table of spinlocks" scheme, that allows the full 32-bit
diff --git a/Documentation/blackfin/bfin-gpio-notes.txt b/Documentation/blackfin/bfin-gpio-notes.txt
index 9898c7ded7d3..f731c1e56475 100644
--- a/Documentation/blackfin/bfin-gpio-notes.txt
+++ b/Documentation/blackfin/bfin-gpio-notes.txt
@@ -43,7 +43,7 @@
        void bfin_gpio_irq_free(unsigned gpio);
    The request functions will record the function state for a certain pin,
-    the free functions will clear it's function state.
+    the free functions will clear its function state.
    Once a pin is requested, it can't be requested again before it is freed by
    previous caller, otherwise kernel will dump stacks, and the request
    function fail.
diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index 6fab97ea7e6b..508b5b2b0289 100644
--- a/Documentation/block/biodoc.txt
+++ b/Documentation/block/biodoc.txt
@@ -1162,8 +1162,8 @@ where a driver received a request ala this before:
 As mentioned, there is no virtual mapping of a bio. For DMA, this is
 not a problem as the driver probably never will need a virtual mapping.
-Instead it needs a bus mapping (pci_map_page for a single segment or
+Instead it needs a bus mapping (dma_map_page for a single segment or
-use blk_rq_map_sg for scatter gather) to be able to ship it to the driver. For
+use dma_map_sg for scatter gather) to be able to ship it to the driver. For
 PIO drivers (or drivers that need to revert to PIO transfer once in a
 while (IDE for example)), where the CPU is doing the actual data
 transfer a virtual mapping is needed. If the driver supports highmem I/O,
diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt
index e164403f60e1..f65274081c8d 100644
--- a/Documentation/block/queue-sysfs.txt
+++ b/Documentation/block/queue-sysfs.txt
@@ -25,11 +25,11 @@ size allowed by the hardware.
 nomerges (RW)
 -------------
-This enables the user to disable the lookup logic involved with IO merging
+This enables the user to disable the lookup logic involved with IO
-requests in the block layer. Merging may still occur through a direct
+merging requests in the block layer. By default (0) all merges are
-1-hit cache, since that comes for (almost) free. The IO scheduler will not
+enabled. When set to 1 only simple one-hit merges will be tried. When
-waste cycles doing tree/hash lookups for merges if nomerges is 1. Defaults
+set to 2 no merge algorithms will be tried (including one-hit or more
-to 0, enabling all merges.
+complex tree/hash lookups).
 nr_requests (RW)
 ----------------
diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt
index da42ab414c48..9164ae3b83bc 100644
--- a/Documentation/cachetlb.txt
+++ b/Documentation/cachetlb.txt
@@ -5,7 +5,7 @@
 This document describes the cache/tlb flushing interfaces called
 by the Linux VM subsystem.  It enumerates over each interface,
-describes it's intended purpose, and what side effect is expected
+describes its intended purpose, and what side effect is expected
 after the interface is invoked.
 The side effects described below are stated for a uniprocessor
@@ -88,12 +88,12 @@ changes occur:
        This is used primarily during fault processing.
 5) void update_mmu_cache(struct vm_area_struct *vma,
-                         unsigned long address, pte_t pte)
+                         unsigned long address, pte_t *ptep)
        At the end of every page fault, this routine is invoked to
        tell the architecture specific code that a translation
-        described by "pte" now exists at virtual address "address"
+        now exists at virtual address "address" for address space
-        for address space "vma->vm_mm", in the software page tables.
+        "vma->vm_mm", in the software page tables.
        A port may use this information in any way it so chooses.
        For example, it could use this event to pre-load TLB
@@ -231,7 +231,7 @@ require a whole different set of interfaces to handle properly.
 The biggest problem is that of virtual aliasing in the data cache
 of a processor.
-Is your port susceptible to virtual aliasing in it's D-cache?
+Is your port susceptible to virtual aliasing in its D-cache?
 Well, if your D-cache is virtually indexed, is larger in size than
 PAGE_SIZE, and does not prevent multiple cache lines for the same
 physical address from existing at once, you have this problem.
@@ -249,7 +249,7 @@ one way to solve this (in particular SPARC_FLAG_MMAPSHARED).
 Next, you have to solve the D-cache aliasing issue for all
 other cases.  Please keep in mind that fact that, for a given page
 mapped into some user address space, there is always at least one more
-mapping, that of the kernel in it's linear mapping starting at
+mapping, that of the kernel in its linear mapping starting at
 PAGE_OFFSET.  So immediately, once the first user maps a given
 physical page into its address space, by implication the D-cache
 aliasing problem has the potential to exist since the kernel already
@@ -377,3 +377,27 @@ maps this page at its virtual address.
        All the functionality of flush_icache_page can be implemented in
        flush_dcache_page and update_mmu_cache. In 2.7 the hope is to
        remove this interface completely.
+The final category of APIs is for I/O to deliberately aliased address
+ranges inside the kernel.  Such aliases are set up by use of the
+vmap/vmalloc API.  Since kernel I/O goes via physical pages, the I/O
+subsystem assumes that the user mapping and kernel offset mapping are
+the only aliases.  This isn't true for vmap aliases, so anything in
+the kernel trying to do I/O to vmap areas must manually manage
+coherency.  It must do this by flushing the vmap range before doing
+I/O and invalidating it after the I/O returns.
+  void flush_kernel_vmap_range(void *vaddr, int size)
+       flushes the kernel cache for a given virtual address range in
+       the vmap area.  This is to make sure that any data the kernel
+       modified in the vmap range is made visible to the physical
+       page.  The design is to make this area safe to perform I/O on.
+       Note that this API does *not* also flush the offset map alias
+       of the area.
+  void invalidate_kernel_vmap_range(void *vaddr, int size) invalidates
+       the cache for a given virtual address range in the vmap area
+       which prevents the processor from making the cache stale by
+       speculatively reading data while the I/O was occurring to the
+       physical pages.  This is only necessary for data reads into the
+       vmap area.
diff --git a/Documentation/cdrom/ide-cd b/Documentation/cdrom/ide-cd
index 2c558cd6c1ef..f4dc9de2694e 100644
--- a/Documentation/cdrom/ide-cd
+++ b/Documentation/cdrom/ide-cd
@@ -159,42 +159,7 @@ two arguments:  the CDROM device, and the slot number to which you wish
 to change.  If the slot number is -1, the drive is unloaded.
-4. Compilation options
+4. Common problems
----------------------
-There are a few additional options which can be set when compiling the
-driver.  Most people should not need to mess with any of these; they
-are listed here simply for completeness.  A compilation option can be
-enabled by adding a line of the form `#define <option> 1' to the top
-of ide-cd.c.  All these options are disabled by default.
-VERBOSE_IDE_CD_ERRORS
-  If this is set, ATAPI error codes will be translated into textual
-  descriptions.  In addition, a dump is made of the command which
-  provoked the error.  This is off by default to save the memory used
-  by the (somewhat long) table of error descriptions.  
-STANDARD_ATAPI
-  If this is set, the code needed to deal with certain drives which do
-  not properly implement the ATAPI spec will be disabled.  If you know
-  your drive implements ATAPI properly, you can turn this on to get a
-  slightly smaller kernel.
-NO_DOOR_LOCKING
-  If this is set, the driver will never attempt to lock the door of
-  the drive.
-CDROM_NBLOCKS_BUFFER
-  This sets the size of the buffer to be used for a CDROMREADAUDIO
-  ioctl.  The default is 8.
-TEST
-  This currently enables an additional ioctl which enables a user-mode
-  program to execute an arbitrary packet command.  See the source for
-  details.  This should be left off unless you know what you're doing.
-5. Common problems
 ------------------
 This section discusses some common problems encountered when trying to
@@ -371,7 +336,7 @@ f. Data corruption.
    expense of low system performance.
-6. cdchange.c
+5. cdchange.c
 -------------
 /*
diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt
index 630879cd9a42..48e0b21b0059 100644
--- a/Documentation/cgroups/blkio-controller.txt
+++ b/Documentation/cgroups/blkio-controller.txt
@@ -17,6 +17,9 @@ HOWTO
 You can do a very simple testing of running two dd threads in two different
 cgroups. Here is what you can do.
+- Enable Block IO controller
+        CONFIG_BLK_CGROUP=y
 - Enable group scheduling in CFQ
        CONFIG_CFQ_GROUP_IOSCHED=y
@@ -54,32 +57,52 @@ cgroups. Here is what you can do.
 Various user visible config options
 ===================================
-CONFIG_CFQ_GROUP_IOSCHED
-        - Enables group scheduling in CFQ. Currently only 1 level of group
-          creation is allowed.
-CONFIG_DEBUG_CFQ_IOSCHED
-        - Enables some debugging messages in blktrace. Also creates extra
-          cgroup file blkio.dequeue.
-Config options selected automatically
-=====================================
-These config options are not user visible and are selected/deselected
-automatically based on IO scheduler configuration.
 CONFIG_BLK_CGROUP
-        - Block IO controller. Selected by CONFIG_CFQ_GROUP_IOSCHED.
+        - Block IO controller.
 CONFIG_DEBUG_BLK_CGROUP
-        - Debug help. Selected by CONFIG_DEBUG_CFQ_IOSCHED.
+        - Debug help. Right now some additional stats file show up in cgroup
+          if this option is enabled.
+CONFIG_CFQ_GROUP_IOSCHED
+        - Enables group scheduling in CFQ. Currently only 1 level of group
+          creation is allowed.
 Details of cgroup files
 =======================
 - blkio.weight
-        - Specifies per cgroup weight.
+        - Specifies per cgroup weight. This is default weight of the group
+          on all the devices until and unless overridden by per device rule.
+          (See blkio.weight_device).
          Currently allowed range of weights is from 100 to 1000.
+- blkio.weight_device
+        - One can specify per cgroup per device rules using this interface.
+          These rules override the default value of group weight as specified
+          by blkio.weight.
+          Following is the format.
+          #echo dev_maj:dev_minor weight > /path/to/cgroup/blkio.weight_device
+          Configure weight=300 on /dev/sdb (8:16) in this cgroup
+          # echo 8:16 300 > blkio.weight_device
+          # cat blkio.weight_device
+          dev     weight
+          8:16    300
+          Configure weight=500 on /dev/sda (8:0) in this cgroup
+          # echo 8:0 500 > blkio.weight_device
+          # cat blkio.weight_device
+          dev     weight
+          8:0     500
+          8:16    300
+          Remove specific weight for /dev/sda in this cgroup
+          # echo 8:0 0 > blkio.weight_device
+          # cat blkio.weight_device
+          dev     weight
+          8:16    300
 - blkio.time
        - disk time allocated to cgroup per device in milliseconds. First
          two fields specify the major and minor number of the device and
@@ -92,13 +115,105 @@ Details of cgroup files
          third field specifies the number of sectors transferred by the
          group to/from the device.
+- blkio.io_service_bytes
+        - Number of bytes transferred to/from the disk by the group. These
+          are further divided by the type of operation - read or write, sync
+          or async. First two fields specify the major and minor number of the
+          device, third field specifies the operation type and the fourth field
+          specifies the number of bytes.
+- blkio.io_serviced
+        - Number of IOs completed to/from the disk by the group. These
+          are further divided by the type of operation - read or write, sync
+          or async. First two fields specify the major and minor number of the
+          device, third field specifies the operation type and the fourth field
+          specifies the number of IOs.
+- blkio.io_service_time
+        - Total amount of time between request dispatch and request completion
+          for the IOs done by this cgroup. This is in nanoseconds to make it
+          meaningful for flash devices too. For devices with queue depth of 1,
+          this time represents the actual service time. When queue_depth > 1,
+          that is no longer true as requests may be served out of order. This
+          may cause the service time for a given IO to include the service time
+          of multiple IOs when served out of order which may result in total
+          io_service_time > actual time elapsed. This time is further divided by
+          the type of operation - read or write, sync or async. First two fields
+          specify the major and minor number of the device, third field
+          specifies the operation type and the fourth field specifies the
+          io_service_time in ns.
+- blkio.io_wait_time
+        - Total amount of time the IOs for this cgroup spent waiting in the
+          scheduler queues for service. This can be greater than the total time
+          elapsed since it is cumulative io_wait_time for all IOs. It is not a
+          measure of total time the cgroup spent waiting but rather a measure of
+          the wait_time for its individual IOs. For devices with queue_depth > 1
+          this metric does not include the time spent waiting for service once
+          the IO is dispatched to the device but till it actually gets serviced
+          (there might be a time lag here due to re-ordering of requests by the
+          device). This is in nanoseconds to make it meaningful for flash
+          devices too. This time is further divided by the type of operation -
+          read or write, sync or async. First two fields specify the major and
+          minor number of the device, third field specifies the operation type
+          and the fourth field specifies the io_wait_time in ns.
+- blkio.io_merged
+        - Total number of bios/requests merged into requests belonging to this
+          cgroup. This is further divided by the type of operation - read or
+          write, sync or async.
+- blkio.io_queued
+        - Total number of requests queued up at any given instant for this
+          cgroup. This is further divided by the type of operation - read or
+          write, sync or async.
+- blkio.avg_queue_size
+        - Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y.
+          The average queue size for this cgroup over the entire time of this
+          cgroup's existence. Queue size samples are taken each time one of the
+          queues of this cgroup gets a timeslice.
+- blkio.group_wait_time
+        - Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y.
+          This is the amount of time the cgroup had to wait since it became busy
+          (i.e., went from 0 to 1 request queued) to get a timeslice for one of
+          its queues. This is different from the io_wait_time which is the
+          cumulative total of the amount of time spent by each IO in that cgroup
+          waiting in the scheduler queue. This is in nanoseconds. If this is
+          read when the cgroup is in a waiting (for timeslice) state, the stat
+          will only report the group_wait_time accumulated till the last time it
+          got a timeslice and will not include the current delta.
+- blkio.empty_time
+        - Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y.
+          This is the amount of time a cgroup spends without any pending
+          requests when not being served, i.e., it does not include any time
+          spent idling for one of the queues of the cgroup. This is in
+          nanoseconds. If this is read when the cgroup is in an empty state,
+          the stat will only report the empty_time accumulated till the last
+          time it had a pending request and will not include the current delta.
+- blkio.idle_time
+        - Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y.
+          This is the amount of time spent by the IO scheduler idling for a
+          given cgroup in anticipation of a better request than the exising ones
+          from other queues/cgroups. This is in nanoseconds. If this is read
+          when the cgroup is in an idling state, the stat will only report the
+          idle_time accumulated till the last idle period and will not include
+          the current delta.
 - blkio.dequeue
-        - Debugging aid only enabled if CONFIG_DEBUG_CFQ_IOSCHED=y. This
+        - Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y. This
          gives the statistics about how many a times a group was dequeued
          from service tree of the device. First two fields specify the major
          and minor number of the device and third field specifies the number
          of times a group was dequeued from a particular device.
+- blkio.reset_stats
+        - Writing an int to this file will result in resetting all the stats
+          for that cgroup.
 CFQ sysfs tunable
 =================
 /sys/block/<disk>/queue/iosched/group_isolation
diff --git a/Documentation/cgroups/cgroup_event_listener.c b/Documentation/cgroups/cgroup_event_listener.c
new file mode 100644
index 000000000000..8c2bfc4a6358
--- /dev/null
+++ b/Documentation/cgroups/cgroup_event_listener.c
@@ -0,0 +1,110 @@
+/*
+ * cgroup_event_listener.c - Simple listener of cgroup events
+ *
+ * Copyright (C) Kirill A. Shutemov <kirill@shutemov.name>
+ */
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <libgen.h>
+#include <limits.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/eventfd.h>
+#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>\n"
+int main(int argc, char **argv)
+{
+        int efd = -1;
+        int cfd = -1;
+        int event_control = -1;
+        char event_control_path[PATH_MAX];
+        char line[LINE_MAX];
+        int ret;
+        if (argc != 3) {
+                fputs(USAGE_STR, stderr);
+                return 1;
+        }
+        cfd = open(argv[1], O_RDONLY);
+        if (cfd == -1) {
+                fprintf(stderr, "Cannot open %s: %s\n", argv[1],
+                                strerror(errno));
+                goto out;
+        }
+        ret = snprintf(event_control_path, PATH_MAX, "%s/cgroup.event_control",
+                        dirname(argv[1]));
+        if (ret >= PATH_MAX) {
+                fputs("Path to cgroup.event_control is too long\n", stderr);
+                goto out;
+        }
+        event_control = open(event_control_path, O_WRONLY);
+        if (event_control == -1) {
+                fprintf(stderr, "Cannot open %s: %s\n", event_control_path,
+                                strerror(errno));
+                goto out;
+        }
+        efd = eventfd(0, 0);
+        if (efd == -1) {
+                perror("eventfd() failed");
+                goto out;
+        }
+        ret = snprintf(line, LINE_MAX, "%d %d %s", efd, cfd, argv[2]);
+        if (ret >= LINE_MAX) {
+                fputs("Arguments string is too long\n", stderr);
+                goto out;
+        }
+        ret = write(event_control, line, strlen(line) + 1);
+        if (ret == -1) {
+                perror("Cannot write to cgroup.event_control");
+                goto out;
+        }
+        while (1) {
+                uint64_t result;
+                ret = read(efd, &result, sizeof(result));
+                if (ret == -1) {
+                        if (errno == EINTR)
+                                continue;
+                        perror("Cannot read from eventfd");
+                        break;
+                }
+                assert(ret == sizeof(result));
+                ret = access(event_control_path, W_OK);
+                if ((ret == -1) && (errno == ENOENT)) {
+                                puts("The cgroup seems to have removed.");
+                                ret = 0;
+                                break;
+                }
+                if (ret == -1) {
+                        perror("cgroup.event_control "
+                                        "is not accessable any more");
+                        break;
+                }
+                printf("%s %s: crossed\n", argv[1], argv[2]);
+        }
+out:
+        if (efd >= 0)
+                close(efd);
+        if (event_control >= 0)
+                close(event_control);
+        if (cfd >= 0)
+                close(cfd);
+        return (ret != 0);
+}
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 0b33bfe7dde9..b34823ff1646 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -22,6 +22,8 @@ CONTENTS:
 2. Usage Examples and Syntax
  2.1 Basic Usage
  2.2 Attaching processes
+  2.3 Mounting hierarchies by name
+  2.4 Notification API
 3. Kernel API
  3.1 Overview
  3.2 Synchronization
@@ -233,8 +235,7 @@ containing the following files describing that cgroup:
 - cgroup.procs: list of tgids in the cgroup.  This list is not
   guaranteed to be sorted or free of duplicate tgids, and userspace
   should sort/uniquify the list if this property is required.
-   Writing a tgid into this file moves all threads with that tgid into
+   This is a read-only file, for now.
-   this cgroup.
 - notify_on_release flag: run the release agent on exit?
 - release_agent: the path to use for release notifications (this file
   exists in the top cgroup only)
@@ -338,7 +339,7 @@ To mount a cgroup hierarchy with all available subsystems, type:
 The "xxx" is not interpreted by the cgroup code, but will appear in
 /proc/mounts so may be any useful identifying string that you like.
-To mount a cgroup hierarchy with just the cpuset and numtasks
+To mount a cgroup hierarchy with just the cpuset and memory
 subsystems, type:
 # mount -t cgroup -o cpuset,memory hier1 /dev/cgroup
@@ -434,6 +435,25 @@ you give a subsystem a name.
 The name of the subsystem appears as part of the hierarchy description
 in /proc/mounts and /proc/<pid>/cgroups.
+2.4 Notification API
+--------------------
+There is mechanism which allows to get notifications about changing
+status of a cgroup.
+To register new notification handler you need:
+ - create a file descriptor for event notification using eventfd(2);
+ - open a control file to be monitored (e.g. memory.usage_in_bytes);
+ - write "<event_fd> <control_fd> <args>" to cgroup.event_control.
+   Interpretation of args is defined by control file implementation;
+eventfd will be woken up by control file implementation or when the
+cgroup is removed.
+To unregister notification handler just close eventfd.
+NOTE: Support of notifications should be implemented for the control
+file. See documentation for the subsystem.
 3. Kernel API
 =============
@@ -488,6 +508,11 @@ Each subsystem should:
 - add an entry in linux/cgroup_subsys.h
 - define a cgroup_subsys object called <name>_subsys
+If a subsystem can be compiled as a module, it should also have in its
+module initcall a call to cgroup_load_subsys(), and in its exitcall a
+call to cgroup_unload_subsys(). It should also set its_subsys.module =
+THIS_MODULE in its .c file.
 Each subsystem may export the following methods. The only mandatory
 methods are create/destroy. Any others that are null are presumed to
 be successful no-ops.
@@ -536,10 +561,21 @@ returns an error, this will abort the attach operation.  If a NULL
 task is passed, then a successful result indicates that *any*
 unspecified task can be moved into the cgroup. Note that this isn't
 called on a fork. If this method returns 0 (success) then this should
-remain valid while the caller holds cgroup_mutex. If threadgroup is
+remain valid while the caller holds cgroup_mutex and it is ensured that either
+attach() or cancel_attach() will be called in future. If threadgroup is
 true, then a successful result indicates that all threads in the given
 thread's threadgroup can be moved together.
+void cancel_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+               struct task_struct *task, bool threadgroup)
+(cgroup_mutex held by caller)
+Called when a task attach operation has failed after can_attach() has succeeded.
+A subsystem whose can_attach() has some side-effects should provide this
+function, so that the subsystem can implement a rollback. If not, not necessary.
+This will be called only about subsystems whose can_attach() operation have
+succeeded.
 void attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
            struct cgroup *old_cgrp, struct task_struct *task,
            bool threadgroup)
diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt
index 1d7e9784439a..51682ab2dd1a 100644
--- a/Documentation/cgroups/cpusets.txt
+++ b/Documentation/cgroups/cpusets.txt
@@ -42,7 +42,7 @@ Nodes to a set of tasks.   In this document "Memory Node" refers to
 an on-line node that contains memory.
 Cpusets constrain the CPU and Memory placement of tasks to only
-the resources within a tasks current cpuset.  They form a nested
+the resources within a task's current cpuset.  They form a nested
 hierarchy visible in a virtual file system.  These are the essential
 hooks, beyond what is already present, required to manage dynamic
 job placement on large systems.
@@ -53,11 +53,11 @@ Documentation/cgroups/cgroups.txt.
 Requests by a task, using the sched_setaffinity(2) system call to
 include CPUs in its CPU affinity mask, and using the mbind(2) and
 set_mempolicy(2) system calls to include Memory Nodes in its memory
-policy, are both filtered through that tasks cpuset, filtering out any
+policy, are both filtered through that task's cpuset, filtering out any
 CPUs or Memory Nodes not in that cpuset.  The scheduler will not
 schedule a task on a CPU that is not allowed in its cpus_allowed
 vector, and the kernel page allocator will not allocate a page on a
-node that is not allowed in the requesting tasks mems_allowed vector.
+node that is not allowed in the requesting task's mems_allowed vector.
 User level code may create and destroy cpusets by name in the cgroup
 virtual file system, manage the attributes and permissions of these
@@ -121,9 +121,9 @@ Cpusets extends these two mechanisms as follows:
 - Each task in the system is attached to a cpuset, via a pointer
   in the task structure to a reference counted cgroup structure.
 - Calls to sched_setaffinity are filtered to just those CPUs
-   allowed in that tasks cpuset.
+   allowed in that task's cpuset.
 - Calls to mbind and set_mempolicy are filtered to just
-   those Memory Nodes allowed in that tasks cpuset.
+   those Memory Nodes allowed in that task's cpuset.
 - The root cpuset contains all the systems CPUs and Memory
   Nodes.
 - For any cpuset, one can define child cpusets containing a subset
@@ -141,11 +141,11 @@ into the rest of the kernel, none in performance critical paths:
 - in init/main.c, to initialize the root cpuset at system boot.
 - in fork and exit, to attach and detach a task from its cpuset.
 - in sched_setaffinity, to mask the requested CPUs by what's
-   allowed in that tasks cpuset.
+   allowed in that task's cpuset.
 - in sched.c migrate_live_tasks(), to keep migrating tasks within
   the CPUs allowed by their cpuset, if possible.
 - in the mbind and set_mempolicy system calls, to mask the requested
-   Memory Nodes by what's allowed in that tasks cpuset.
+   Memory Nodes by what's allowed in that task's cpuset.
 - in page_alloc.c, to restrict memory to allowed nodes.
 - in vmscan.c, to restrict page recovery to the current cpuset.
@@ -155,7 +155,7 @@ new system calls are added for cpusets - all support for querying and
 modifying cpusets is via this cpuset file system.
 The /proc/<pid>/status file for each task has four added lines,
-displaying the tasks cpus_allowed (on which CPUs it may be scheduled)
+displaying the task's cpus_allowed (on which CPUs it may be scheduled)
 and mems_allowed (on which Memory Nodes it may obtain memory),
 in the two formats seen in the following example:
@@ -168,20 +168,20 @@ Each cpuset is represented by a directory in the cgroup file system
 containing (on top of the standard cgroup files) the following
 files describing that cpuset:
- - cpus: list of CPUs in that cpuset
+ - cpuset.cpus: list of CPUs in that cpuset
- - mems: list of Memory Nodes in that cpuset
+ - cpuset.mems: list of Memory Nodes in that cpuset
- - memory_migrate flag: if set, move pages to cpusets nodes
+ - cpuset.memory_migrate flag: if set, move pages to cpusets nodes
- - cpu_exclusive flag: is cpu placement exclusive?
+ - cpuset.cpu_exclusive flag: is cpu placement exclusive?
- - mem_exclusive flag: is memory placement exclusive?
+ - cpuset.mem_exclusive flag: is memory placement exclusive?
- - mem_hardwall flag:  is memory allocation hardwalled
+ - cpuset.mem_hardwall flag:  is memory allocation hardwalled
- - memory_pressure: measure of how much paging pressure in cpuset
+ - cpuset.memory_pressure: measure of how much paging pressure in cpuset
- - memory_spread_page flag: if set, spread page cache evenly on allowed nodes
+ - cpuset.memory_spread_page flag: if set, spread page cache evenly on allowed nodes
- - memory_spread_slab flag: if set, spread slab cache evenly on allowed nodes
+ - cpuset.memory_spread_slab flag: if set, spread slab cache evenly on allowed nodes
- - sched_load_balance flag: if set, load balance within CPUs on that cpuset
+ - cpuset.sched_load_balance flag: if set, load balance within CPUs on that cpuset
- - sched_relax_domain_level: the searching range when migrating tasks
+ - cpuset.sched_relax_domain_level: the searching range when migrating tasks
 In addition, the root cpuset only has the following file:
- - memory_pressure_enabled flag: compute memory_pressure?
+ - cpuset.memory_pressure_enabled flag: compute memory_pressure?
 New cpusets are created using the mkdir system call or shell
 command.  The properties of a cpuset, such as its flags, allowed
@@ -229,7 +229,7 @@ If a cpuset is cpu or mem exclusive, no other cpuset, other than
 a direct ancestor or descendant, may share any of the same CPUs or
 Memory Nodes.
-A cpuset that is mem_exclusive *or* mem_hardwall is "hardwalled",
+A cpuset that is cpuset.mem_exclusive *or* cpuset.mem_hardwall is "hardwalled",
 i.e. it restricts kernel allocations for page, buffer and other data
 commonly shared by the kernel across multiple users.  All cpusets,
 whether hardwalled or not, restrict allocations of memory for user
@@ -304,15 +304,15 @@ times 1000.
 ---------------------------
 There are two boolean flag files per cpuset that control where the
 kernel allocates pages for the file system buffers and related in
-kernel data structures.  They are called 'memory_spread_page' and
+kernel data structures.  They are called 'cpuset.memory_spread_page' and
-'memory_spread_slab'.
+'cpuset.memory_spread_slab'.
-If the per-cpuset boolean flag file 'memory_spread_page' is set, then
+If the per-cpuset boolean flag file 'cpuset.memory_spread_page' is set, then
 the kernel will spread the file system buffers (page cache) evenly
 over all the nodes that the faulting task is allowed to use, instead
 of preferring to put those pages on the node where the task is running.
-If the per-cpuset boolean flag file 'memory_spread_slab' is set,
+If the per-cpuset boolean flag file 'cpuset.memory_spread_slab' is set,
 then the kernel will spread some file system related slab caches,
 such as for inodes and dentries evenly over all the nodes that the
 faulting task is allowed to use, instead of preferring to put those
@@ -323,41 +323,41 @@ stack segment pages of a task.
 By default, both kinds of memory spreading are off, and memory
 pages are allocated on the node local to where the task is running,
-except perhaps as modified by the tasks NUMA mempolicy or cpuset
+except perhaps as modified by the task's NUMA mempolicy or cpuset
 configuration, so long as sufficient free memory pages are available.
 When new cpusets are created, they inherit the memory spread settings
 of their parent.
 Setting memory spreading causes allocations for the affected page
-or slab caches to ignore the tasks NUMA mempolicy and be spread
+or slab caches to ignore the task's NUMA mempolicy and be spread
 instead.    Tasks using mbind() or set_mempolicy() calls to set NUMA
 mempolicies will not notice any change in these calls as a result of
-their containing tasks memory spread settings.  If memory spreading
+their containing task's memory spread settings.  If memory spreading
 is turned off, then the currently specified NUMA mempolicy once again
 applies to memory page allocations.
-Both 'memory_spread_page' and 'memory_spread_slab' are boolean flag
+Both 'cpuset.memory_spread_page' and 'cpuset.memory_spread_slab' are boolean flag
 files.  By default they contain "0", meaning that the feature is off
 for that cpuset.  If a "1" is written to that file, then that turns
 the named feature on.
 The implementation is simple.
-Setting the flag 'memory_spread_page' turns on a per-process flag
+Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag
 PF_SPREAD_PAGE for each task that is in that cpuset or subsequently
 joins that cpuset.  The page allocation calls for the page cache
 is modified to perform an inline check for this PF_SPREAD_PAGE task
 flag, and if set, a call to a new routine cpuset_mem_spread_node()
 returns the node to prefer for the allocation.
-Similarly, setting 'memory_spread_slab' turns on the flag
+Similarly, setting 'cpuset.memory_spread_slab' turns on the flag
 PF_SPREAD_SLAB, and appropriately marked slab caches will allocate
 pages from the node returned by cpuset_mem_spread_node().
 The cpuset_mem_spread_node() routine is also simple.  It uses the
 value of a per-task rotor cpuset_mem_spread_rotor to select the next
-node in the current tasks mems_allowed to prefer for the allocation.
+node in the current task's mems_allowed to prefer for the allocation.
 This memory placement policy is also known (in other contexts) as
 round-robin or interleave.
@@ -404,24 +404,24 @@ the following two situations:
    system overhead on those CPUs, including avoiding task load
    balancing if that is not needed.
-When the per-cpuset flag "sched_load_balance" is enabled (the default
+When the per-cpuset flag "cpuset.sched_load_balance" is enabled (the default
-setting), it requests that all the CPUs in that cpusets allowed 'cpus'
+setting), it requests that all the CPUs in that cpusets allowed 'cpuset.cpus'
 be contained in a single sched domain, ensuring that load balancing
 can move a task (not otherwised pinned, as by sched_setaffinity)
 from any CPU in that cpuset to any other.
-When the per-cpuset flag "sched_load_balance" is disabled, then the
+When the per-cpuset flag "cpuset.sched_load_balance" is disabled, then the
 scheduler will avoid load balancing across the CPUs in that cpuset,
 --except-- in so far as is necessary because some overlapping cpuset
 has "sched_load_balance" enabled.
-So, for example, if the top cpuset has the flag "sched_load_balance"
+So, for example, if the top cpuset has the flag "cpuset.sched_load_balance"
 enabled, then the scheduler will have one sched domain covering all
-CPUs, and the setting of the "sched_load_balance" flag in any other
+CPUs, and the setting of the "cpuset.sched_load_balance" flag in any other
 cpusets won't matter, as we're already fully load balancing.
 Therefore in the above two situations, the top cpuset flag
-"sched_load_balance" should be disabled, and only some of the smaller,
+"cpuset.sched_load_balance" should be disabled, and only some of the smaller,
 child cpusets have this flag enabled.
 When doing this, you don't usually want to leave any unpinned tasks in
@@ -433,7 +433,7 @@ scheduler might not consider the possibility of load balancing that
 task to that underused CPU.
 Of course, tasks pinned to a particular CPU can be left in a cpuset
-that disables "sched_load_balance" as those tasks aren't going anywhere
+that disables "cpuset.sched_load_balance" as those tasks aren't going anywhere
 else anyway.
 There is an impedance mismatch here, between cpusets and sched domains.
@@ -443,19 +443,19 @@ overlap and each CPU is in at most one sched domain.
 It is necessary for sched domains to be flat because load balancing
 across partially overlapping sets of CPUs would risk unstable dynamics
 that would be beyond our understanding.  So if each of two partially
-overlapping cpusets enables the flag 'sched_load_balance', then we
+overlapping cpusets enables the flag 'cpuset.sched_load_balance', then we
 form a single sched domain that is a superset of both.  We won't move
 a task to a CPU outside it cpuset, but the scheduler load balancing
 code might waste some compute cycles considering that possibility.
 This mismatch is why there is not a simple one-to-one relation
-between which cpusets have the flag "sched_load_balance" enabled,
+between which cpusets have the flag "cpuset.sched_load_balance" enabled,
 and the sched domain configuration.  If a cpuset enables the flag, it
 will get balancing across all its CPUs, but if it disables the flag,
 it will only be assured of no load balancing if no other overlapping
 cpuset enables the flag.
-If two cpusets have partially overlapping 'cpus' allowed, and only
+If two cpusets have partially overlapping 'cpuset.cpus' allowed, and only
 one of them has this flag enabled, then the other may find its
 tasks only partially load balanced, just on the overlapping CPUs.
 This is just the general case of the top_cpuset example given a few
@@ -468,23 +468,23 @@ load balancing to the other CPUs.
 1.7.1 sched_load_balance implementation details.
 ------------------------------------------------
-The per-cpuset flag 'sched_load_balance' defaults to enabled (contrary
+The per-cpuset flag 'cpuset.sched_load_balance' defaults to enabled (contrary
 to most cpuset flags.)  When enabled for a cpuset, the kernel will
 ensure that it can load balance across all the CPUs in that cpuset
 (makes sure that all the CPUs in the cpus_allowed of that cpuset are
 in the same sched domain.)
-If two overlapping cpusets both have 'sched_load_balance' enabled,
+If two overlapping cpusets both have 'cpuset.sched_load_balance' enabled,
 then they will be (must be) both in the same sched domain.
-If, as is the default, the top cpuset has 'sched_load_balance' enabled,
+If, as is the default, the top cpuset has 'cpuset.sched_load_balance' enabled,
 then by the above that means there is a single sched domain covering
 the whole system, regardless of any other cpuset settings.
 The kernel commits to user space that it will avoid load balancing
 where it can.  It will pick as fine a granularity partition of sched
 domains as it can while still providing load balancing for any set
-of CPUs allowed to a cpuset having 'sched_load_balance' enabled.
+of CPUs allowed to a cpuset having 'cpuset.sched_load_balance' enabled.
 The internal kernel cpuset to scheduler interface passes from the
 cpuset code to the scheduler code a partition of the load balanced
@@ -495,9 +495,9 @@ all the CPUs that must be load balanced.
 The cpuset code builds a new such partition and passes it to the
 scheduler sched domain setup code, to have the sched domains rebuilt
 as necessary, whenever:
- - the 'sched_load_balance' flag of a cpuset with non-empty CPUs changes,
+ - the 'cpuset.sched_load_balance' flag of a cpuset with non-empty CPUs changes,
 - or CPUs come or go from a cpuset with this flag enabled,
- - or 'sched_relax_domain_level' value of a cpuset with non-empty CPUs
+ - or 'cpuset.sched_relax_domain_level' value of a cpuset with non-empty CPUs
   and with this flag enabled changes,
 - or a cpuset with non-empty CPUs and with this flag enabled is removed,
 - or a cpu is offlined/onlined.
@@ -542,7 +542,7 @@ As the result, task B on CPU X need to wait task A or wait load balance
 on the next tick.  For some applications in special situation, waiting
 1 tick may be too long.
-The 'sched_relax_domain_level' file allows you to request changing
+The 'cpuset.sched_relax_domain_level' file allows you to request changing
 this searching range as you like.  This file takes int value which
 indicates size of searching range in levels ideally as follows,
 otherwise initial value -1 that indicates the cpuset has no request.
@@ -559,8 +559,8 @@ The system default is architecture dependent.  The system default
 can be changed using the relax_domain_level= boot parameter.
 This file is per-cpuset and affect the sched domain where the cpuset
-belongs to.  Therefore if the flag 'sched_load_balance' of a cpuset
+belongs to.  Therefore if the flag 'cpuset.sched_load_balance' of a cpuset
-is disabled, then 'sched_relax_domain_level' have no effect since
+is disabled, then 'cpuset.sched_relax_domain_level' have no effect since
 there is no sched domain belonging the cpuset.
 If multiple cpusets are overlapping and hence they form a single sched
@@ -594,7 +594,7 @@ is attached, is subtle.
 If a cpuset has its Memory Nodes modified, then for each task attached
 to that cpuset, the next time that the kernel attempts to allocate
 a page of memory for that task, the kernel will notice the change
-in the tasks cpuset, and update its per-task memory placement to
+in the task's cpuset, and update its per-task memory placement to
 remain within the new cpusets memory placement.  If the task was using
 mempolicy MPOL_BIND, and the nodes to which it was bound overlap with
 its new cpuset, then the task will continue to use whatever subset
@@ -603,13 +603,13 @@ was using MPOL_BIND and now none of its MPOL_BIND nodes are allowed
 in the new cpuset, then the task will be essentially treated as if it
 was MPOL_BIND bound to the new cpuset (even though its NUMA placement,
 as queried by get_mempolicy(), doesn't change).  If a task is moved
-from one cpuset to another, then the kernel will adjust the tasks
+from one cpuset to another, then the kernel will adjust the task's
 memory placement, as above, the next time that the kernel attempts
 to allocate a page of memory for that task.
-If a cpuset has its 'cpus' modified, then each task in that cpuset
+If a cpuset has its 'cpuset.cpus' modified, then each task in that cpuset
 will have its allowed CPU placement changed immediately.  Similarly,
-if a tasks pid is written to another cpusets 'tasks' file, then its
+if a task's pid is written to another cpusets 'cpuset.tasks' file, then its
 allowed CPU placement is changed immediately.  If such a task had been
 bound to some subset of its cpuset using the sched_setaffinity() call,
 the task will be allowed to run on any CPU allowed in its new cpuset,
@@ -622,21 +622,21 @@ and the processor placement is updated immediately.
 Normally, once a page is allocated (given a physical page
 of main memory) then that page stays on whatever node it
 was allocated, so long as it remains allocated, even if the
-cpusets memory placement policy 'mems' subsequently changes.
+cpusets memory placement policy 'cpuset.mems' subsequently changes.
-If the cpuset flag file 'memory_migrate' is set true, then when
+If the cpuset flag file 'cpuset.memory_migrate' is set true, then when
 tasks are attached to that cpuset, any pages that task had
 allocated to it on nodes in its previous cpuset are migrated
-to the tasks new cpuset. The relative placement of the page within
+to the task's new cpuset. The relative placement of the page within
 the cpuset is preserved during these migration operations if possible.
 For example if the page was on the second valid node of the prior cpuset
 then the page will be placed on the second valid node of the new cpuset.
-Also if 'memory_migrate' is set true, then if that cpusets
+Also if 'cpuset.memory_migrate' is set true, then if that cpuset's
-'mems' file is modified, pages allocated to tasks in that
+'cpuset.mems' file is modified, pages allocated to tasks in that
-cpuset, that were on nodes in the previous setting of 'mems',
+cpuset, that were on nodes in the previous setting of 'cpuset.mems',
 will be moved to nodes in the new setting of 'mems.'
-Pages that were not in the tasks prior cpuset, or in the cpusets
+Pages that were not in the task's prior cpuset, or in the cpuset's
-prior 'mems' setting, will not be moved.
+prior 'cpuset.mems' setting, will not be moved.
 There is an exception to the above.  If hotplug functionality is used
 to remove all the CPUs that are currently assigned to a cpuset,
@@ -655,7 +655,7 @@ There is a second exception to the above.  GFP_ATOMIC requests are
 kernel internal allocations that must be satisfied, immediately.
 The kernel may drop some request, in rare cases even panic, if a
 GFP_ATOMIC alloc fails.  If the request cannot be satisfied within
-the current tasks cpuset, then we relax the cpuset, and look for
+the current task's cpuset, then we relax the cpuset, and look for
 memory anywhere we can find it.  It's better to violate the cpuset
 than stress the kernel.
@@ -678,8 +678,8 @@ and then start a subshell 'sh' in that cpuset:
  cd /dev/cpuset
  mkdir Charlie
  cd Charlie
-  /bin/echo 2-3 > cpus
+  /bin/echo 2-3 > cpuset.cpus
-  /bin/echo 1 > mems
+  /bin/echo 1 > cpuset.mems
  /bin/echo $$ > tasks
  sh
  # The subshell 'sh' is now running in cpuset Charlie
@@ -725,10 +725,13 @@ Now you want to do something with this cpuset.
 In this directory you can find several files:
 # ls
-cpu_exclusive  memory_migrate      mems                      tasks
+cpuset.cpu_exclusive       cpuset.memory_spread_slab
-cpus           memory_pressure     notify_on_release
+cpuset.cpus                cpuset.mems
-mem_exclusive  memory_spread_page  sched_load_balance
+cpuset.mem_exclusive       cpuset.sched_load_balance
-mem_hardwall   memory_spread_slab  sched_relax_domain_level
+cpuset.mem_hardwall        cpuset.sched_relax_domain_level
+cpuset.memory_migrate      notify_on_release
+cpuset.memory_pressure     tasks
+cpuset.memory_spread_page
 Reading them will give you information about the state of this cpuset:
 the CPUs and Memory Nodes it can use, the processes that are using
@@ -736,13 +739,13 @@ it, its properties.  By writing to these files you can manipulate
 the cpuset.
 Set some flags:
-# /bin/echo 1 > cpu_exclusive
+# /bin/echo 1 > cpuset.cpu_exclusive
 Add some cpus:
-# /bin/echo 0-7 > cpus
+# /bin/echo 0-7 > cpuset.cpus
 Add some mems:
-# /bin/echo 0-7 > mems
+# /bin/echo 0-7 > cpuset.mems
 Now attach your shell to this cpuset:
 # /bin/echo $$ > tasks
@@ -774,28 +777,28 @@ echo "/sbin/cpuset_release_agent" > /dev/cpuset/release_agent
 This is the syntax to use when writing in the cpus or mems files
 in cpuset directories:
-# /bin/echo 1-4 > cpus          -> set cpus list to cpus 1,2,3,4
+# /bin/echo 1-4 > cpuset.cpus           -> set cpus list to cpus 1,2,3,4
-# /bin/echo 1,2,3,4 > cpus      -> set cpus list to cpus 1,2,3,4
+# /bin/echo 1,2,3,4 > cpuset.cpus       -> set cpus list to cpus 1,2,3,4
 To add a CPU to a cpuset, write the new list of CPUs including the
 CPU to be added. To add 6 to the above cpuset:
-# /bin/echo 1-4,6 > cpus        -> set cpus list to cpus 1,2,3,4,6
+# /bin/echo 1-4,6 > cpuset.cpus -> set cpus list to cpus 1,2,3,4,6
 Similarly to remove a CPU from a cpuset, write the new list of CPUs
 without the CPU to be removed.
 To remove all the CPUs:
-# /bin/echo "" > cpus           -> clear cpus list
+# /bin/echo "" > cpuset.cpus            -> clear cpus list
 2.3 Setting flags
 -----------------
 The syntax is very simple:
-# /bin/echo 1 > cpu_exclusive   -> set flag 'cpu_exclusive'
+# /bin/echo 1 > cpuset.cpu_exclusive    -> set flag 'cpuset.cpu_exclusive'
-# /bin/echo 0 > cpu_exclusive   -> unset flag 'cpu_exclusive'
+# /bin/echo 0 > cpuset.cpu_exclusive    -> unset flag 'cpuset.cpu_exclusive'
 2.4 Attaching processes
 -----------------------
diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt
index 72db89ed0609..b7eececfb195 100644
--- a/Documentation/cgroups/memcg_test.txt
+++ b/Documentation/cgroups/memcg_test.txt
@@ -1,6 +1,6 @@
 Memory Resource Controller(Memcg)  Implementation Memo.
-Last Updated: 2009/1/20
+Last Updated: 2010/2
-Base Kernel Version: based on 2.6.29-rc2.
+Base Kernel Version: based on 2.6.33-rc7-mm(candidate for 34).
 Because VM is getting complex (one of reasons is memcg...), memcg's behavior
 is complex. This is a document for memcg's internal behavior.
@@ -244,7 +244,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
          we have to check if OLDPAGE/NEWPAGE is a valid page after commit().
 8. LRU
-        Each memcg has its own private LRU. Now, it's handling is under global
+        Each memcg has its own private LRU. Now, its handling is under global
        VM's control (means that it's handled under global zone->lru_lock).
        Almost all routines around memcg's LRU is called by global LRU's
        list management functions under zone->lru_lock().
@@ -337,7 +337,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
        race and lock dependency with other cgroup subsystems.
        example)
-        # mount -t cgroup none /cgroup -t cpuset,memory,cpu,devices
+        # mount -t cgroup none /cgroup -o cpuset,memory,cpu,devices
        and do task move, mkdir, rmdir etc...under this.
@@ -348,7 +348,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
        For example, test like following is good.
        (Shell-A)
-        # mount -t cgroup none /cgroup -t memory
+        # mount -t cgroup none /cgroup -o memory
        # mkdir /cgroup/test
        # echo 40M > /cgroup/test/memory.limit_in_bytes
        # echo 0 > /cgroup/test/tasks
@@ -378,3 +378,42 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
        #echo 50M > memory.limit_in_bytes
        #echo 50M > memory.memsw.limit_in_bytes
        run 51M of malloc
+ 9.9 Move charges at task migration
+        Charges associated with a task can be moved along with task migration.
+        (Shell-A)
+        #mkdir /cgroup/A
+        #echo $$ >/cgroup/A/tasks
+        run some programs which uses some amount of memory in /cgroup/A.
+        (Shell-B)
+        #mkdir /cgroup/B
+        #echo 1 >/cgroup/B/memory.move_charge_at_immigrate
+        #echo "pid of the program running in group A" >/cgroup/B/tasks
+        You can see charges have been moved by reading *.usage_in_bytes or
+        memory.stat of both A and B.
+        See 8.2 of Documentation/cgroups/memory.txt to see what value should be
+        written to move_charge_at_immigrate.
+ 9.10 Memory thresholds
+        Memory controler implements memory thresholds using cgroups notification
+        API. You can use Documentation/cgroups/cgroup_event_listener.c to test
+        it.
+        (Shell-A) Create cgroup and run event listener
+        # mkdir /cgroup/A
+        # ./cgroup_event_listener /cgroup/A/memory.usage_in_bytes 5M
+        (Shell-B) Add task to cgroup and try to allocate and free memory
+        # echo $$ >/cgroup/A/tasks
+        # a="$(dd if=/dev/zero bs=1M count=10)"
+        # a=
+        You will see message from cgroup_event_listener every time you cross
+        the thresholds.
+        Use /cgroup/A/memory.memsw.usage_in_bytes to test memsw thresholds.
+        It's good idea to test root cgroup as well.
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index b871f2552b45..7781857dc940 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -1,18 +1,15 @@
 Memory Resource Controller
 NOTE: The Memory Resource Controller has been generically been referred
-to as the memory controller in this document. Do not confuse memory controller
+      to as the memory controller in this document. Do not confuse memory
-used here with the memory controller that is used in hardware.
+      controller used here with the memory controller that is used in hardware.
-Salient features
+(For editors)
+In this document:
-a. Enable control of Anonymous, Page Cache (mapped and unmapped) and
+      When we mention a cgroup (cgroupfs's directory) with memory controller,
-   Swap Cache memory pages.
+      we call it "memory cgroup". When you see git-log and source code, you'll
-b. The infrastructure allows easy addition of other types of memory to control
+      see patch's title and function names tend to use "memcg".
-c. Provides *zero overhead* for non memory controller users
+      In this document, we avoid using it.
-d. Provides a double LRU: global memory pressure causes reclaim from the
-   global LRU; a cgroup on hitting a limit, reclaims from the per
-   cgroup LRU
 Benefits and Purpose of the memory controller
@@ -33,6 +30,45 @@ d. A CD/DVD burner could control the amount of memory used by the
 e. There are several other use cases, find one or use the controller just
   for fun (to learn and hack on the VM subsystem).
+Current Status: linux-2.6.34-mmotm(development version of 2010/April)
+Features:
+ - accounting anonymous pages, file caches, swap caches usage and limiting them.
+ - private LRU and reclaim routine. (system's global LRU and private LRU
+   work independently from each other)
+ - optionally, memory+swap usage can be accounted and limited.
+ - hierarchical accounting
+ - soft limit
+ - moving(recharging) account at moving a task is selectable.
+ - usage threshold notifier
+ - oom-killer disable knob and oom-notifier
+ - Root cgroup has no limit controls.
+ Kernel memory and Hugepages are not under control yet. We just manage
+ pages on LRU. To add more controls, we have to take care of performance.
+Brief summary of control files.
+ tasks                           # attach a task(thread) and show list of threads
+ cgroup.procs                    # show list of processes
+ cgroup.event_control            # an interface for event_fd()
+ memory.usage_in_bytes           # show current memory(RSS+Cache) usage.
+ memory.memsw.usage_in_bytes     # show current memory+Swap usage
+ memory.limit_in_bytes           # set/show limit of memory usage
+ memory.memsw.limit_in_bytes     # set/show limit of memory+Swap usage
+ memory.failcnt                  # show the number of memory usage hits limits
+ memory.memsw.failcnt            # show the number of memory+Swap hits limits
+ memory.max_usage_in_bytes       # show max memory usage recorded
+ memory.memsw.usage_in_bytes     # show max memory+Swap usage recorded
+ memory.soft_limit_in_bytes      # set/show soft limit of memory usage
+ memory.stat                     # show various statistics
+ memory.use_hierarchy            # set/show hierarchical account enabled
+ memory.force_empty              # trigger forced move charge to parent
+ memory.swappiness               # set/show swappiness parameter of vmscan
+                                 (See sysctl's vm.swappiness)
+ memory.move_charge_at_immigrate # set/show controls of moving charges
+ memory.oom_control              # set/show oom controls.
 1. History
 The memory controller has a long history. A request for comments for the memory
@@ -106,14 +142,14 @@ the necessary data structures and check if the cgroup that is being charged
 is over its limit. If it is then reclaim is invoked on the cgroup.
 More details can be found in the reclaim section of this document.
 If everything goes well, a page meta-data-structure called page_cgroup is
-allocated and associated with the page.  This routine also adds the page to
+updated. page_cgroup has its own LRU on cgroup.
-the per cgroup LRU.
+(*) page_cgroup structure is allocated at boot/memory-hotplug time.
 2.2.1 Accounting details
 All mapped anon pages (RSS) and cache pages (Page Cache) are accounted.
-(some pages which never be reclaimable and will not be on global LRU
+Some pages which are never reclaimable and will not be on the global LRU
- are not accounted. we just accounts pages under usual vm management.)
+are not accounted. We just account pages under usual VM management.
 RSS pages are accounted at page_fault unless they've already been accounted
 for earlier. A file page will be accounted for as Page Cache when it's
@@ -121,12 +157,19 @@ inserted into inode (radix-tree). While it's mapped into the page tables of
 processes, duplicate accounting is carefully avoided.
 A RSS page is unaccounted when it's fully unmapped. A PageCache page is
-unaccounted when it's removed from radix-tree.
+unaccounted when it's removed from radix-tree. Even if RSS pages are fully
+unmapped (by kswapd), they may exist as SwapCache in the system until they
+are really freed. Such SwapCaches also also accounted.
+A swapped-in page is not accounted until it's mapped.
+Note: The kernel does swapin-readahead and read multiple swaps at once.
+This means swapped-in pages may contain pages for other tasks than a task
+causing page fault. So, we avoid accounting at swap-in I/O.
 At page migration, accounting information is kept.
-Note: we just account pages-on-lru because our purpose is to control amount
+Note: we just account pages-on-LRU because our purpose is to control amount
-of used pages. not-on-lru pages are tend to be out-of-control from vm view.
+of used pages; not-on-LRU pages tend to be out-of-control from VM view.
 2.3 Shared Page Accounting
@@ -143,6 +186,7 @@ caller of swapoff rather than the users of shmem.
 2.4 Swap Extension (CONFIG_CGROUP_MEM_RES_CTLR_SWAP)
 Swap Extension allows you to record charge for swap. A swapped-in page is
 charged back to original page allocator if possible.
@@ -150,13 +194,20 @@ When swap is accounted, following files are added.
 - memory.memsw.usage_in_bytes.
 - memory.memsw.limit_in_bytes.
-usage of mem+swap is limited by memsw.limit_in_bytes.
+memsw means memory+swap. Usage of memory+swap is limited by
+memsw.limit_in_bytes.
-* why 'mem+swap' rather than swap.
+Example: Assume a system with 4G of swap. A task which allocates 6G of memory
+(by mistake) under 2G memory limitation will use all swap.
+In this case, setting memsw.limit_in_bytes=3G will prevent bad use of swap.
+By using memsw limit, you can avoid system OOM which can be caused by swap
+shortage.
+* why 'memory+swap' rather than swap.
 The global LRU(kswapd) can swap out arbitrary pages. Swap-out means
 to move account from memory to swap...there is no change in usage of
-mem+swap. In other words, when we want to limit the usage of swap without
+memory+swap. In other words, when we want to limit the usage of swap without
-affecting global LRU, mem+swap limit is better than just limiting swap from
+affecting global LRU, memory+swap limit is better than just limiting swap from
 OS point of view.
 * What happens when a cgroup hits memory.memsw.limit_in_bytes
@@ -168,12 +219,12 @@ it by cgroup.
 2.5 Reclaim
-Each cgroup maintains a per cgroup LRU that consists of an active
+Each cgroup maintains a per cgroup LRU which has the same structure as
-and inactive list. When a cgroup goes over its limit, we first try
+global VM. When a cgroup goes over its limit, we first try
 to reclaim memory from the cgroup so as to make space for the new
 pages that the cgroup has touched. If the reclaim is unsuccessful,
 an OOM routine is invoked to select and kill the bulkiest task in the
-cgroup.
+cgroup. (See 10. OOM Control below.)
 The reclaim algorithm has not been modified for cgroups, except that
 pages that are selected for reclaiming come from the per cgroup LRU
@@ -182,13 +233,24 @@ list.
 NOTE: Reclaim does not work for the root cgroup, since we cannot set any
 limits on the root cgroup.
-2. Locking
+Note2: When panic_on_oom is set to "2", the whole system will panic.
+When oom event notifier is registered, event will be delivered.
+(See oom_control section)
+2.6 Locking
-The memory controller uses the following hierarchy
+   lock_page_cgroup()/unlock_page_cgroup() should not be called under
+   mapping->tree_lock.
-1. zone->lru_lock is used for selecting pages to be isolated
+   Other lock order is following:
-2. mem->per_zone->lru_lock protects the per cgroup LRU (per zone)
+   PG_locked.
-3. lock_page_cgroup() is used to protect page->page_cgroup
+   mm->page_table_lock
+       zone->lru_lock
+          lock_page_cgroup.
+  In many cases, just lock_page_cgroup() is called.
+  per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
+  zone->lru_lock, it has no lock of its own.
 3. User Interface
@@ -197,6 +259,7 @@ The memory controller uses the following hierarchy
 a. Enable CONFIG_CGROUPS
 b. Enable CONFIG_RESOURCE_COUNTERS
 c. Enable CONFIG_CGROUP_MEM_RES_CTLR
+d. Enable CONFIG_CGROUP_MEM_RES_CTLR_SWAP (to use swap extension)
 1. Prepare the cgroups
 # mkdir -p /cgroups
@@ -204,31 +267,28 @@ c. Enable CONFIG_CGROUP_MEM_RES_CTLR
 2. Make the new group and move bash into it
 # mkdir /cgroups/0
-# echo $$ >  /cgroups/0/tasks
+# echo $$ > /cgroups/0/tasks
-Since now we're in the 0 cgroup,
+Since now we're in the 0 cgroup, we can alter the memory limit:
-We can alter the memory limit:
 # echo 4M > /cgroups/0/memory.limit_in_bytes
 NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo,
-mega or gigabytes.
+mega or gigabytes. (Here, Kilo, Mega, Giga are Kibibytes, Mebibytes, Gibibytes.)
 NOTE: We can write "-1" to reset the *.limit_in_bytes(unlimited).
 NOTE: We cannot set limits on the root cgroup any more.
 # cat /cgroups/0/memory.limit_in_bytes
 4194304
-NOTE: The interface has now changed to display the usage in bytes
-instead of pages
 We can check the usage:
 # cat /cgroups/0/memory.usage_in_bytes
 1216512
 A successful write to this file does not guarantee a successful set of
-this limit to the value written into the file.  This can be due to a
+this limit to the value written into the file. This can be due to a
 number of factors, such as rounding up to page boundaries or the total
-availability of memory on the system.  The user is required to re-read
+availability of memory on the system. The user is required to re-read
 this file after a write to guarantee the value committed by the kernel.
 # echo 1 > memory.limit_in_bytes
@@ -243,15 +303,23 @@ caches, RSS and Active pages/Inactive pages are shown.
 4. Testing
-Balbir posted lmbench, AIM9, LTP and vmmstress results [10] and [11].
+For testing features and implementation, see memcg_test.txt.
-Apart from that v6 has been tested with several applications and regular
-daily use. The controller has also been tested on the PPC64, x86_64 and
+Performance test is also important. To see pure memory controller's overhead,
-UML platforms.
+testing on tmpfs will give you good numbers of small overheads.
+Example: do kernel make on tmpfs.
+Page-fault scalability is also important. At measuring parallel
+page fault test, multi-process test may be better than multi-thread
+test because it has noise of shared objects/status.
+But the above two are testing extreme situations.
+Trying usual test under memory controller is always helpful.
 4.1 Troubleshooting
 Sometimes a user might find that the application under a cgroup is
-terminated. There are several causes for this:
+terminated by OOM killer. There are several causes for this:
 1. The cgroup limit is too low (just too low to do anything useful)
 2. The user is using anonymous memory and swap is turned off or too low
@@ -259,21 +327,29 @@ terminated. There are several causes for this:
 A sync followed by echo 1 > /proc/sys/vm/drop_caches will help get rid of
 some of the pages cached in the cgroup (page cache pages).
+To know what happens, disable OOM_Kill by 10. OOM Control(see below) and
+seeing what happens will be helpful.
 4.2 Task migration
-When a task migrates from one cgroup to another, it's charge is not
+When a task migrates from one cgroup to another, its charge is not
-carried forward. The pages allocated from the original cgroup still
+carried forward by default. The pages allocated from the original cgroup still
 remain charged to it, the charge is dropped when the page is freed or
 reclaimed.
+You can move charges of a task along with task migration.
+See 8. "Move charges at task migration"
 4.3 Removing a cgroup
 A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a
 cgroup might have some charge associated with it, even though all
-tasks have migrated away from it.
+tasks have migrated away from it. (because we charge against pages, not
-Such charges are freed(at default) or moved to its parent. When moved,
+against tasks.)
-both of RSS and CACHES are moved to parent.
-If both of them are busy, rmdir() returns -EBUSY. See 5.1 Also.
+Such charges are freed or moved to their parent. At moving, both of RSS
+and CACHES are moved to parent.
+rmdir() may return -EBUSY if freeing/moving fails. See 5.1 also.
 Charges recorded in swap information is not updated at removal of cgroup.
 Recorded information is discarded and a cgroup which uses swap (swapcache)
@@ -289,10 +365,10 @@ will be charged as a new owner of it.
  # echo 0 > memory.force_empty
-  Almost all pages tracked by this memcg will be unmapped and freed. Some of
+  Almost all pages tracked by this memory cgroup will be unmapped and freed.
-  pages cannot be freed because it's locked or in-use. Such pages are moved
+  Some pages cannot be freed because they are locked or in-use. Such pages are
-  to parent and this cgroup will be empty. But this may return -EBUSY in
+  moved to parent and this cgroup will be empty. This may return -EBUSY if
-  some too busy case.
+  VM is too busy to free/move all pages immediately.
  Typical use case of this interface is that calling this before rmdir().
  Because rmdir() moves all pages to parent, some out-of-use page caches can be
@@ -302,19 +378,41 @@ will be charged as a new owner of it.
 memory.stat file includes following statistics
+# per-memory cgroup local status
 cache           - # of bytes of page cache memory.
 rss             - # of bytes of anonymous and swap cache memory.
+mapped_file     - # of bytes of mapped file (includes tmpfs/shmem)
 pgpgin          - # of pages paged in (equivalent to # of charging events).
 pgpgout         - # of pages paged out (equivalent to # of uncharging events).
-active_anon     - # of bytes of anonymous and  swap cache memory on active
+swap            - # of bytes of swap usage
-                  lru list.
 inactive_anon   - # of bytes of anonymous memory and swap cache memory on
-                  inactive lru list.
+                LRU list.
-active_file     - # of bytes of file-backed memory on active lru list.
+active_anon     - # of bytes of anonymous and swap cache memory on active
-inactive_file   - # of bytes of file-backed memory on inactive lru list.
+                inactive LRU list.
+inactive_file   - # of bytes of file-backed memory on inactive LRU list.
+active_file     - # of bytes of file-backed memory on active LRU list.
 unevictable     - # of bytes of memory that cannot be reclaimed (mlocked etc).
-The following additional stats are dependent on CONFIG_DEBUG_VM.
+# status considering hierarchy (see memory.use_hierarchy settings)
+hierarchical_memory_limit - # of bytes of memory limit with regard to hierarchy
+                        under which the memory cgroup is
+hierarchical_memsw_limit - # of bytes of memory+swap limit with regard to
+                        hierarchy under which memory cgroup is.
+total_cache             - sum of all children's "cache"
+total_rss               - sum of all children's "rss"
+total_mapped_file       - sum of all children's "cache"
+total_pgpgin            - sum of all children's "pgpgin"
+total_pgpgout           - sum of all children's "pgpgout"
+total_swap              - sum of all children's "swap"
+total_inactive_anon     - sum of all children's "inactive_anon"
+total_active_anon       - sum of all children's "active_anon"
+total_inactive_file     - sum of all children's "inactive_file"
+total_active_file       - sum of all children's "active_file"
+total_unevictable       - sum of all children's "unevictable"
+# 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)
@@ -323,24 +421,37 @@ recent_scanned_anon	- VM internal parameter. (see mm/vmscan.c)
 recent_scanned_file     - VM internal parameter. (see mm/vmscan.c)
 Memo:
-        recent_rotated means recent frequency of lru rotation.
+        recent_rotated means recent frequency of LRU rotation.
-        recent_scanned means recent # of scans to lru.
+        recent_scanned means recent # of scans to LRU.
        showing for better debug please see the code for meanings.
 Note:
        Only anonymous and swap cache memory is listed as part of 'rss' stat.
        This should not be confused with the true 'resident set size' or the
-        amount of physical memory used by the cgroup. Per-cgroup rss
+        amount of physical memory used by the cgroup.
-        accounting is not done yet.
+        'rss + file_mapped" will give you resident set size of cgroup.
+        (Note: file and shmem may be shared among other cgroups. In that case,
+         file_mapped is accounted only when the memory cgroup is owner of page
+         cache.)
 5.3 swappiness
-  Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
-  Following cgroups' swapiness can't be changed.
+Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
-  - root cgroup (uses /proc/sys/vm/swappiness).
-  - a cgroup which uses hierarchy and it has child cgroup.
+Following cgroups' swappiness can't be changed.
-  - a cgroup which uses hierarchy and not the root of hierarchy.
+- root cgroup (uses /proc/sys/vm/swappiness).
+- a cgroup which uses hierarchy and it has other cgroup(s) below it.
+- a cgroup which uses hierarchy and not the root of hierarchy.
+5.4 failcnt
+A memory cgroup provides memory.failcnt and memory.memsw.failcnt files.
+This failcnt(== failure count) shows the number of times that a usage counter
+hit its limit. When a memory cgroup hits a limit, failcnt increases and
+memory under it will be reclaimed.
+You can reset failcnt by writing 0 to failcnt file.
+# echo 0 > .../memory.failcnt
 6. Hierarchy support
@@ -359,13 +470,13 @@ hierarchy
 In the diagram above, with hierarchical accounting enabled, all memory
 usage of e, is accounted to its ancestors up until the root (i.e, c and root),
-that has memory.use_hierarchy enabled.  If one of the ancestors goes over its
+that has memory.use_hierarchy enabled. If one of the ancestors goes over its
 limit, the reclaim algorithm reclaims from the tasks in the ancestor and the
 children of the ancestor.
 6.1 Enabling hierarchical accounting and reclaim
-The memory controller by default disables the hierarchy feature. Support
+A memory cgroup by default disables the hierarchy feature. Support
 can be enabled by writing 1 to memory.use_hierarchy file of the root cgroup
 # echo 1 > memory.use_hierarchy
@@ -375,9 +486,10 @@ The feature can be disabled by
 # echo 0 > memory.use_hierarchy
 NOTE1: Enabling/disabling will fail if the cgroup already has other
-cgroups created below it.
+       cgroups created below it.
-NOTE2: This feature can be enabled/disabled per subtree.
+NOTE2: When panic_on_oom is set to "2", the whole system will panic in
+       case of an OOM event in any cgroup.
 7. Soft limits
@@ -387,7 +499,7 @@ is to allow control groups to use as much of the memory as needed, provided
 a. There is no memory contention
 b. They do not exceed their hard limit
-When the system detects memory contention or low memory control groups
+When the system detects memory contention or low memory, control groups
 are pushed back to their soft limits. If the soft limit of each control
 group is very high, they are pushed back as much as possible to make
 sure that one control group does not starve the others of memory.
@@ -401,7 +513,7 @@ it gets invoked from balance_pgdat (kswapd).
 7.1 Interface
 Soft limits can be setup by using the following commands (in this example we
-assume a soft limit of 256 megabytes)
+assume a soft limit of 256 MiB)
 # echo 256M > memory.soft_limit_in_bytes
@@ -414,7 +526,121 @@ NOTE1: Soft limits take effect over a long period of time, since they involve
 NOTE2: It is recommended to set the soft limit always below the hard limit,
       otherwise the hard limit will take precedence.
-8. TODO
+8. Move charges at task migration
+Users can move charges associated with a task along with task migration, that
+is, uncharge task's pages from the old cgroup and charge them to the new cgroup.
+This feature is not supported in !CONFIG_MMU environments because of lack of
+page tables.
+8.1 Interface
+This feature is disabled by default. It can be enabled(and disabled again) by
+writing to memory.move_charge_at_immigrate of the destination cgroup.
+If you want to enable it:
+# echo (some positive value) > memory.move_charge_at_immigrate
+Note: Each bits of move_charge_at_immigrate has its own meaning about what type
+      of charges should be moved. See 8.2 for details.
+Note: Charges are moved only when you move mm->owner, IOW, a leader of a thread
+      group.
+Note: If we cannot find enough space for the task in the destination cgroup, we
+      try to make space by reclaiming memory. Task migration may fail if we
+      cannot make enough space.
+Note: It can take several seconds if you move charges much.
+And if you want disable it again:
+# echo 0 > memory.move_charge_at_immigrate
+8.2 Type of charges which can be move
+Each bits of move_charge_at_immigrate has its own meaning about what type of
+charges should be moved. But in any cases, it must be noted that an account of
+a page or a swap can be moved only when it is charged to the task's current(old)
+memory cgroup.
+  bit | what type of charges would be moved ?
+ -----+------------------------------------------------------------------------
+   0  | A charge of an anonymous page(or swap of it) used by the target task.
+      | Those pages and swaps must be used only by the target task. You must
+      | enable Swap Extension(see 2.4) to enable move of swap charges.
+ -----+------------------------------------------------------------------------
+   1  | A charge of file pages(normal file, tmpfs file(e.g. ipc shared memory)
+      | and swaps of tmpfs file) mmapped by the target task. Unlike the case of
+      | anonymous pages, file pages(and swaps) in the range mmapped by the task
+      | will be moved even if the task hasn't done page fault, i.e. they might
+      | not be the task's "RSS", but other task's "RSS" that maps the same file.
+      | And mapcount of the page is ignored(the page can be moved even if
+      | page_mapcount(page) > 1). You must enable Swap Extension(see 2.4) to
+      | enable move of swap charges.
+8.3 TODO
+- Implement madvise(2) to let users decide the vma to be moved or not to be
+  moved.
+- All of moving charge operations are done under cgroup_mutex. It's not good
+  behavior to hold the mutex too long, so we may need some trick.
+9. Memory thresholds
+Memory cgroup implements memory thresholds using cgroups notification
+API (see cgroups.txt). It allows to register multiple memory and memsw
+thresholds and gets notifications when it crosses.
+To register a threshold application need:
+- create an eventfd using eventfd(2);
+- open memory.usage_in_bytes or memory.memsw.usage_in_bytes;
+- write string like "<event_fd> <fd of memory.usage_in_bytes> <threshold>" to
+  cgroup.event_control.
+Application will be notified through eventfd when memory usage crosses
+threshold in any direction.
+It's applicable for root and non-root cgroup.
+10. OOM Control
+memory.oom_control file is for OOM notification and other controls.
+Memory cgroup implements OOM notifier using cgroup notification
+API (See cgroups.txt). It allows to register multiple OOM notification
+delivery and gets notification when OOM happens.
+To register a notifier, application need:
+ - create an eventfd using eventfd(2)
+ - open memory.oom_control file
+ - write string like "<event_fd> <fd of memory.oom_control>" to
+   cgroup.event_control
+Application will be notified through eventfd when OOM happens.
+OOM notification doesn't work for root cgroup.
+You can disable OOM-killer by writing "1" to memory.oom_control file, as:
+        #echo 1 > memory.oom_control
+This operation is only allowed to the top cgroup of sub-hierarchy.
+If OOM-killer is disabled, tasks under cgroup will hang/sleep
+in memory cgroup's OOM-waitqueue when they request accountable memory.
+For running them, you have to relax the memory cgroup's OOM status by
+        * enlarge limit or reduce usage.
+To reduce usage,
+        * kill some tasks.
+        * move some tasks to other group with account migration.
+        * remove some files (on tmpfs?)
+Then, stopped tasks will work again.
+At reading, current status of OOM is shown.
+        oom_kill_disable 0 or 1 (if 1, oom-killer is disabled)
+        under_oom        0 or 1 (if 1, the memory cgroup is under OOM, tasks may
+                                 be stopped.)
+11. TODO
 1. Add support for accounting huge pages (as a separate controller)
 2. Make per-cgroup scanner reclaim not-shared pages first
diff --git a/Documentation/circular-buffers.txt b/Documentation/circular-buffers.txt
new file mode 100644
index 000000000000..8117e5bf6065
--- /dev/null
+++ b/Documentation/circular-buffers.txt
@@ -0,0 +1,234 @@
+                               ================
+                               CIRCULAR BUFFERS
+                               ================
+By: David Howells <dhowells@redhat.com>
+    Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+Linux provides a number of features that can be used to implement circular
+buffering.  There are two sets of such features:
+ (1) Convenience functions for determining information about power-of-2 sized
+     buffers.
+ (2) Memory barriers for when the producer and the consumer of objects in the
+     buffer don't want to share a lock.
+To use these facilities, as discussed below, there needs to be just one
+producer and just one consumer.  It is possible to handle multiple producers by
+serialising them, and to handle multiple consumers by serialising them.
+Contents:
+ (*) What is a circular buffer?
+ (*) Measuring power-of-2 buffers.
+ (*) Using memory barriers with circular buffers.
+     - The producer.
+     - The consumer.
+==========================
+WHAT IS A CIRCULAR BUFFER?
+==========================
+First of all, what is a circular buffer?  A circular buffer is a buffer of
+fixed, finite size into which there are two indices:
+ (1) A 'head' index - the point at which the producer inserts items into the
+     buffer.
+ (2) A 'tail' index - the point at which the consumer finds the next item in
+     the buffer.
+Typically when the tail pointer is equal to the head pointer, the buffer is
+empty; and the buffer is full when the head pointer is one less than the tail
+pointer.
+The head index is incremented when items are added, and the tail index when
+items are removed.  The tail index should never jump the head index, and both
+indices should be wrapped to 0 when they reach the end of the buffer, thus
+allowing an infinite amount of data to flow through the buffer.
+Typically, items will all be of the same unit size, but this isn't strictly
+required to use the techniques below.  The indices can be increased by more
+than 1 if multiple items or variable-sized items are to be included in the
+buffer, provided that neither index overtakes the other.  The implementer must
+be careful, however, as a region more than one unit in size may wrap the end of
+the buffer and be broken into two segments.
+============================
+MEASURING POWER-OF-2 BUFFERS
+============================
+Calculation of the occupancy or the remaining capacity of an arbitrarily sized
+circular buffer would normally be a slow operation, requiring the use of a
+modulus (divide) instruction.  However, if the buffer is of a power-of-2 size,
+then a much quicker bitwise-AND instruction can be used instead.
+Linux provides a set of macros for handling power-of-2 circular buffers.  These
+can be made use of by:
+        #include <linux/circ_buf.h>
+The macros are:
+ (*) Measure the remaining capacity of a buffer:
+        CIRC_SPACE(head_index, tail_index, buffer_size);
+     This returns the amount of space left in the buffer[1] into which items
+     can be inserted.
+ (*) Measure the maximum consecutive immediate space in a buffer:
+        CIRC_SPACE_TO_END(head_index, tail_index, buffer_size);
+     This returns the amount of consecutive space left in the buffer[1] into
+     which items can be immediately inserted without having to wrap back to the
+     beginning of the buffer.
+ (*) Measure the occupancy of a buffer:
+        CIRC_CNT(head_index, tail_index, buffer_size);
+     This returns the number of items currently occupying a buffer[2].
+ (*) Measure the non-wrapping occupancy of a buffer:
+        CIRC_CNT_TO_END(head_index, tail_index, buffer_size);
+     This returns the number of consecutive items[2] that can be extracted from
+     the buffer without having to wrap back to the beginning of the buffer.
+Each of these macros will nominally return a value between 0 and buffer_size-1,
+however:
+ [1] CIRC_SPACE*() are intended to be used in the producer.  To the producer
+     they will return a lower bound as the producer controls the head index,
+     but the consumer may still be depleting the buffer on another CPU and
+     moving the tail index.
+     To the consumer it will show an upper bound as the producer may be busy
+     depleting the space.
+ [2] CIRC_CNT*() are intended to be used in the consumer.  To the consumer they
+     will return a lower bound as the consumer controls the tail index, but the
+     producer may still be filling the buffer on another CPU and moving the
+     head index.
+     To the producer it will show an upper bound as the consumer may be busy
+     emptying the buffer.
+ [3] To a third party, the order in which the writes to the indices by the
+     producer and consumer become visible cannot be guaranteed as they are
+     independent and may be made on different CPUs - so the result in such a
+     situation will merely be a guess, and may even be negative.
+===========================================
+USING MEMORY BARRIERS WITH CIRCULAR BUFFERS
+===========================================
+By using memory barriers in conjunction with circular buffers, you can avoid
+the need to:
+ (1) use a single lock to govern access to both ends of the buffer, thus
+     allowing the buffer to be filled and emptied at the same time; and
+ (2) use atomic counter operations.
+There are two sides to this: the producer that fills the buffer, and the
+consumer that empties it.  Only one thing should be filling a buffer at any one
+time, and only one thing should be emptying a buffer at any one time, but the
+two sides can operate simultaneously.
+THE PRODUCER
+------------
+The producer will look something like this:
+        spin_lock(&producer_lock);
+        unsigned long head = buffer->head;
+        unsigned long tail = ACCESS_ONCE(buffer->tail);
+        if (CIRC_SPACE(head, tail, buffer->size) >= 1) {
+                /* insert one item into the buffer */
+                struct item *item = buffer[head];
+                produce_item(item);
+                smp_wmb(); /* commit the item before incrementing the head */
+                buffer->head = (head + 1) & (buffer->size - 1);
+                /* wake_up() will make sure that the head is committed before
+                 * waking anyone up */
+                wake_up(consumer);
+        }
+        spin_unlock(&producer_lock);
+This will instruct the CPU that the contents of the new item must be written
+before the head index makes it available to the consumer and then instructs the
+CPU that the revised head index must be written before the consumer is woken.
+Note that wake_up() doesn't have to be the exact mechanism used, but whatever
+is used must guarantee a (write) memory barrier between the update of the head
+index and the change of state of the consumer, if a change of state occurs.
+THE CONSUMER
+------------
+The consumer will look something like this:
+        spin_lock(&consumer_lock);
+        unsigned long head = ACCESS_ONCE(buffer->head);
+        unsigned long tail = buffer->tail;
+        if (CIRC_CNT(head, tail, buffer->size) >= 1) {
+                /* read index before reading contents at that index */
+                smp_read_barrier_depends();
+                /* extract one item from the buffer */
+                struct item *item = buffer[tail];
+                consume_item(item);
+                smp_mb(); /* finish reading descriptor before incrementing tail */
+                buffer->tail = (tail + 1) & (buffer->size - 1);
+        }
+        spin_unlock(&consumer_lock);
+This will instruct the CPU to make sure the index is up to date before reading
+the new item, and then it shall make sure the CPU has finished reading the item
+before it writes the new tail pointer, which will erase the item.
+Note the use of ACCESS_ONCE() in both algorithms to read the opposition index.
+This prevents the compiler from discarding and reloading its cached value -
+which some compilers will do across smp_read_barrier_depends().  This isn't
+strictly needed if you can be sure that the opposition index will _only_ be
+used the once.
+===============
+FURTHER READING
+===============
+See also Documentation/memory-barriers.txt for a description of Linux's memory
+barrier facilities.
diff --git a/Documentation/connector/cn_test.c b/Documentation/connector/cn_test.c
index b07add3467f1..7764594778d4 100644
--- a/Documentation/connector/cn_test.c
+++ b/Documentation/connector/cn_test.c
@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/skbuff.h>
+#include <linux/slab.h>
 #include <linux/timer.h>
 #include <linux/connector.h>
diff --git a/Documentation/connector/connector.txt b/Documentation/connector/connector.txt
index 78c9466a9aa8..e5c5f5e6ab70 100644
--- a/Documentation/connector/connector.txt
+++ b/Documentation/connector/connector.txt
@@ -88,7 +88,7 @@ int cn_netlink_send(struct cn_msg *msg, u32 __groups, int gfp_mask);
 int gfp_mask                   - GFP mask.
 Note: When registering new callback user, connector core assigns
- netlink group to the user which is equal to it's id.idx.
+ netlink group to the user which is equal to its id.idx.
 /*****************************************/
 Protocol description.
diff --git a/Documentation/console/console.txt b/Documentation/console/console.txt
index 877a1b26cc3d..926cf1b5e63e 100644
--- a/Documentation/console/console.txt
+++ b/Documentation/console/console.txt
@@ -74,7 +74,7 @@ driver takes over the consoles vacated by the driver. Binding, on the other
 hand, will bind the driver to the consoles that are currently occupied by a
 system driver.
-NOTE1: Binding and binding must be selected in Kconfig. It's under:
+NOTE1: Binding and unbinding must be selected in Kconfig. It's under:
 Device Drivers -> Character devices -> Support for binding and unbinding
 console drivers
diff --git a/Documentation/cpu-freq/pcc-cpufreq.txt b/Documentation/cpu-freq/pcc-cpufreq.txt
new file mode 100644
index 000000000000..9e3c3b33514c
--- /dev/null
+++ b/Documentation/cpu-freq/pcc-cpufreq.txt
@@ -0,0 +1,207 @@
+/*
+ *  pcc-cpufreq.txt - PCC interface documentation
+ *
+ *  Copyright (C) 2009 Red Hat, Matthew Garrett <mjg@redhat.com>
+ *  Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
+ *      Nagananda Chumbalkar <nagananda.chumbalkar@hp.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or NON
+ *  INFRINGEMENT. See the GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+                        Processor Clocking Control Driver
+                        ---------------------------------
+Contents:
+---------
+1.      Introduction
+1.1     PCC interface
+1.1.1   Get Average Frequency
+1.1.2   Set Desired Frequency
+1.2     Platforms affected
+2.      Driver and /sys details
+2.1     scaling_available_frequencies
+2.2     cpuinfo_transition_latency
+2.3     cpuinfo_cur_freq
+2.4     related_cpus
+3.      Caveats
+1. Introduction:
+----------------
+Processor Clocking Control (PCC) is an interface between the platform
+firmware and OSPM. It is a mechanism for coordinating processor
+performance (ie: frequency) between the platform firmware and the OS.
+The PCC driver (pcc-cpufreq) allows OSPM to take advantage of the PCC
+interface.
+OS utilizes the PCC interface to inform platform firmware what frequency the
+OS wants for a logical processor. The platform firmware attempts to achieve
+the requested frequency. If the request for the target frequency could not be
+satisfied by platform firmware, then it usually means that power budget
+conditions are in place, and "power capping" is taking place.
+1.1 PCC interface:
+------------------
+The complete PCC specification is available here:
+http://www.acpica.org/download/Processor-Clocking-Control-v1p0.pdf
+PCC relies on a shared memory region that provides a channel for communication
+between the OS and platform firmware. PCC also implements a "doorbell" that
+is used by the OS to inform the platform firmware that a command has been
+sent.
+The ACPI PCCH() method is used to discover the location of the PCC shared
+memory region. The shared memory region header contains the "command" and
+"status" interface. PCCH() also contains details on how to access the platform
+doorbell.
+The following commands are supported by the PCC interface:
+* Get Average Frequency
+* Set Desired Frequency
+The ACPI PCCP() method is implemented for each logical processor and is
+used to discover the offsets for the input and output buffers in the shared
+memory region.
+When PCC mode is enabled, the platform will not expose processor performance
+or throttle states (_PSS, _TSS and related ACPI objects) to OSPM. Therefore,
+the native P-state driver (such as acpi-cpufreq for Intel, powernow-k8 for
+AMD) will not load.
+However, OSPM remains in control of policy. The governor (eg: "ondemand")
+computes the required performance for each processor based on server workload.
+The PCC driver fills in the command interface, and the input buffer and
+communicates the request to the platform firmware. The platform firmware is
+responsible for delivering the requested performance.
+Each PCC command is "global" in scope and can affect all the logical CPUs in
+the system. Therefore, PCC is capable of performing "group" updates. With PCC
+the OS is capable of getting/setting the frequency of all the logical CPUs in
+the system with a single call to the BIOS.
+1.1.1 Get Average Frequency:
+----------------------------
+This command is used by the OSPM to query the running frequency of the
+processor since the last time this command was completed. The output buffer
+indicates the average unhalted frequency of the logical processor expressed as
+a percentage of the nominal (ie: maximum) CPU frequency. The output buffer
+also signifies if the CPU frequency is limited by a power budget condition.
+1.1.2 Set Desired Frequency:
+----------------------------
+This command is used by the OSPM to communicate to the platform firmware the
+desired frequency for a logical processor. The output buffer is currently
+ignored by OSPM. The next invocation of "Get Average Frequency" will inform
+OSPM if the desired frequency was achieved or not.
+1.2 Platforms affected:
+-----------------------
+The PCC driver will load on any system where the platform firmware:
+* supports the PCC interface, and the associated PCCH() and PCCP() methods
+* assumes responsibility for managing the hardware clocking controls in order
+to deliver the requested processor performance
+Currently, certain HP ProLiant platforms implement the PCC interface. On those
+platforms PCC is the "default" choice.
+However, it is possible to disable this interface via a BIOS setting. In
+such an instance, as is also the case on platforms where the PCC interface
+is not implemented, the PCC driver will fail to load silently.
+2. Driver and /sys details:
+---------------------------
+When the driver loads, it merely prints the lowest and the highest CPU
+frequencies supported by the platform firmware.
+The PCC driver loads with a message such as:
+pcc-cpufreq: (v1.00.00) driver loaded with frequency limits: 1600 MHz, 2933
+MHz
+This means that the OPSM can request the CPU to run at any frequency in
+between the limits (1600 MHz, and 2933 MHz) specified in the message.
+Internally, there is no need for the driver to convert the "target" frequency
+to a corresponding P-state.
+The VERSION number for the driver will be of the format v.xy.ab.
+eg: 1.00.02
+   ----- --
+    |    |
+    |    -- this will increase with bug fixes/enhancements to the driver
+    |-- this is the version of the PCC specification the driver adheres to
+The following is a brief discussion on some of the fields exported via the
+/sys filesystem and how their values are affected by the PCC driver:
+2.1 scaling_available_frequencies:
+----------------------------------
+scaling_available_frequencies is not created in /sys. No intermediate
+frequencies need to be listed because the BIOS will try to achieve any
+frequency, within limits, requested by the governor. A frequency does not have
+to be strictly associated with a P-state.
+2.2 cpuinfo_transition_latency:
+-------------------------------
+The cpuinfo_transition_latency field is 0. The PCC specification does
+not include a field to expose this value currently.
+2.3 cpuinfo_cur_freq:
+---------------------
+A) Often cpuinfo_cur_freq will show a value different than what is declared
+in the scaling_available_frequencies or scaling_cur_freq, or scaling_max_freq.
+This is due to "turbo boost" available on recent Intel processors. If certain
+conditions are met the BIOS can achieve a slightly higher speed than requested
+by OSPM. An example:
+scaling_cur_freq        : 2933000
+cpuinfo_cur_freq        : 3196000
+B) There is a round-off error associated with the cpuinfo_cur_freq value.
+Since the driver obtains the current frequency as a "percentage" (%) of the
+nominal frequency from the BIOS, sometimes, the values displayed by
+scaling_cur_freq and cpuinfo_cur_freq may not match. An example:
+scaling_cur_freq        : 1600000
+cpuinfo_cur_freq        : 1583000
+In this example, the nominal frequency is 2933 MHz. The driver obtains the
+current frequency, cpuinfo_cur_freq, as 54% of the nominal frequency:
+        54% of 2933 MHz = 1583 MHz
+Nominal frequency is the maximum frequency of the processor, and it usually
+corresponds to the frequency of the P0 P-state.
+2.4 related_cpus:
+-----------------
+The related_cpus field is identical to affected_cpus.
+affected_cpus   : 4
+related_cpus    : 4
+Currently, the PCC driver does not evaluate _PSD. The platforms that support
+PCC do not implement SW_ALL. So OSPM doesn't need to perform any coordination
+to ensure that the same frequency is requested of all dependent CPUs.
+3. Caveats:
+-----------
+The "cpufreq_stats" module in its present form cannot be loaded and
+expected to work with the PCC driver. Since the "cpufreq_stats" module
+provides information wrt each P-state, it is not applicable to the PCC driver.
diff --git a/Documentation/credentials.txt b/Documentation/credentials.txt
index df03169782ea..a2db35287003 100644
--- a/Documentation/credentials.txt
+++ b/Documentation/credentials.txt
@@ -408,9 +408,6 @@ This should be used inside the RCU read lock, as in the following example:
                ...
        }
-A function need not get RCU read lock to use __task_cred() if it is holding a
-spinlock at the time as this implicitly holds the RCU read lock.
 Should it be necessary to hold another task's credentials for a long period of
 time, and possibly to sleep whilst doing so, then the caller should get a
 reference on them using:
@@ -426,17 +423,16 @@ credentials, hiding the RCU magic from the caller:
        uid_t task_uid(task)            Task's real UID
        uid_t task_euid(task)           Task's effective UID
-If the caller is holding a spinlock or the RCU read lock at the time anyway,
+If the caller is holding the RCU read lock at the time anyway, then:
-then:
        __task_cred(task)->uid
        __task_cred(task)->euid
 should be used instead.  Similarly, if multiple aspects of a task's credentials
-need to be accessed, RCU read lock or a spinlock should be used, __task_cred()
+need to be accessed, RCU read lock should be used, __task_cred() called, the
-called, the result stored in a temporary pointer and then the credential
+result stored in a temporary pointer and then the credential aspects called
-aspects called from that before dropping the lock.  This prevents the
+from that before dropping the lock.  This prevents the potentially expensive
-potentially expensive RCU magic from being invoked multiple times.
+RCU magic from being invoked multiple times.
 Should some other single aspect of another task's credentials need to be
 accessed, then this can be used:
diff --git a/Documentation/development-process/2.Process b/Documentation/development-process/2.Process
index d750321acd5a..97726eba6102 100644
--- a/Documentation/development-process/2.Process
+++ b/Documentation/development-process/2.Process
@@ -151,7 +151,7 @@ The stages that a patch goes through are, generally:
   well.
 - Wider review.  When the patch is getting close to ready for mainline
-   inclusion, it will be accepted by a relevant subsystem maintainer -
+   inclusion, it should be accepted by a relevant subsystem maintainer -
   though this acceptance is not a guarantee that the patch will make it
   all the way to the mainline.  The patch will show up in the maintainer's
   subsystem tree and into the staging trees (described below).  When the
@@ -159,6 +159,15 @@ The stages that a patch goes through are, generally:
   the discovery of any problems resulting from the integration of this
   patch with work being done by others.
+-  Please note that most maintainers also have day jobs, so merging
+   your patch may not be their highest priority.  If your patch is
+   getting feedback about changes that are needed, you should either
+   make those changes or justify why they should not be made.  If your
+   patch has no review complaints but is not being merged by its
+   appropriate subsystem or driver maintainer, you should be persistent
+   in updating the patch to the current kernel so that it applies cleanly
+   and keep sending it for review and merging.
 - Merging into the mainline.  Eventually, a successful patch will be
   merged into the mainline repository managed by Linus Torvalds.  More
   comments and/or problems may surface at this time; it is important that
@@ -258,12 +267,8 @@ an appropriate subsystem tree or be sent directly to Linus.  In a typical
 development cycle, approximately 10% of the patches going into the mainline
 get there via -mm.
-The current -mm patch can always be found from the front page of
+The current -mm patch is available in the "mmotm" (-mm of the moment)
+directory at:
-        http://kernel.org/
-Those who want to see the current state of -mm can get the "-mm of the
-moment" tree, found at:
        http://userweb.kernel.org/~akpm/mmotm/
@@ -298,6 +303,12 @@ volatility of linux-next tends to make it a difficult development target.
 See http://lwn.net/Articles/289013/ for more information on this topic, and
 stay tuned; much is still in flux where linux-next is involved.
+Besides the mmotm and linux-next trees, the kernel source tree now contains
+the drivers/staging/ directory and many sub-directories for drivers or
+filesystems that are on their way to being added to the kernel tree
+proper, but they remain in drivers/staging/ while they still need more
+work.
 2.5: TOOLS
@@ -319,9 +330,9 @@ developers; even if they do not use it for their own work, they'll need git
 to keep up with what other developers (and the mainline) are doing.
 Git is now packaged by almost all Linux distributions.  There is a home
-page at 
+page at:
-        http://git.or.cz/
+        http://git-scm.com/
 That page has pointers to documentation and tutorials.  One should be
 aware, in particular, of the Kernel Hacker's Guide to git, which has
diff --git a/Documentation/development-process/7.AdvancedTopics b/Documentation/development-process/7.AdvancedTopics
index a2cf74093aa1..837179447e17 100644
--- a/Documentation/development-process/7.AdvancedTopics
+++ b/Documentation/development-process/7.AdvancedTopics
@@ -25,7 +25,7 @@ long document in its own right.  Instead, the focus here will be on how git
 fits into the kernel development process in particular.  Developers who
 wish to come up to speed with git will find more information at:
-        http://git.or.cz/
+        http://git-scm.com/
        http://www.kernel.org/pub/software/scm/git/docs/user-manual.html
diff --git a/Documentation/device-mapper/snapshot.txt b/Documentation/device-mapper/snapshot.txt
index e3a77b215135..0d5bc46dc167 100644
--- a/Documentation/device-mapper/snapshot.txt
+++ b/Documentation/device-mapper/snapshot.txt
@@ -122,3 +122,47 @@ volumeGroup-base: 0 2097152 snapshot-merge 254:11 254:12 P 16
 brw-------  1 root root 254, 11 29 ago 18:15 /dev/mapper/volumeGroup-base-real
 brw-------  1 root root 254, 12 29 ago 18:16 /dev/mapper/volumeGroup-base-cow
 brw-------  1 root root 254, 10 29 ago 18:16 /dev/mapper/volumeGroup-base
+How to determine when a merging is complete
+===========================================
+The snapshot-merge and snapshot status lines end with:
+  <sectors_allocated>/<total_sectors> <metadata_sectors>
+Both <sectors_allocated> and <total_sectors> include both data and metadata.
+During merging, the number of sectors allocated gets smaller and
+smaller.  Merging has finished when the number of sectors holding data
+is zero, in other words <sectors_allocated> == <metadata_sectors>.
+Here is a practical example (using a hybrid of lvm and dmsetup commands):
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g
+  snap    volumeGroup swi-a- 1.00g base  18.97
+# dmsetup status volumeGroup-snap
+0 8388608 snapshot 397896/2097152 1560
+                                  ^^^^ metadata sectors
+# lvconvert --merge -b volumeGroup/snap
+  Merging of volume snap started.
+# lvs volumeGroup/snap
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup Owi-a- 4.00g          17.23
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 281688/2097152 1104
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 180480/2097152 712
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 16/2097152 16
+Merging has finished.
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g
diff --git a/Documentation/devices.txt b/Documentation/devices.txt
index 53d64d382343..1d83d124056c 100644
--- a/Documentation/devices.txt
+++ b/Documentation/devices.txt
@@ -443,6 +443,8 @@ Your cooperation is appreciated.
                231 = /dev/snapshot     System memory snapshot device
                232 = /dev/kvm          Kernel-based virtual machine (hardware virtualization extensions)
                233 = /dev/kmview       View-OS A process with a view
+                234 = /dev/btrfs-control        Btrfs control device
+                235 = /dev/autofs       Autofs control device
                240-254                 Reserved for local use
                255                     Reserved for MISC_DYNAMIC_MINOR
diff --git a/Documentation/dontdiff b/Documentation/dontdiff
index 3ad6acead949..d9bcffd59433 100644
--- a/Documentation/dontdiff
+++ b/Documentation/dontdiff
@@ -69,7 +69,6 @@ av_permissions.h
 bbootsect
 bin2c
 binkernel.spec
-binoffset
 bootsect
 bounds.h
 bsetup
diff --git a/Documentation/driver-model/platform.txt b/Documentation/driver-model/platform.txt
index 2e2c2ea90ceb..41f41632ee55 100644
--- a/Documentation/driver-model/platform.txt
+++ b/Documentation/driver-model/platform.txt
@@ -192,7 +192,7 @@ command line. This will execute all matching early_param() callbacks.
 User specified early platform devices will be registered at this point.
 For the early serial console case the user can specify port on the
 kernel command line as "earlyprintk=serial.0" where "earlyprintk" is
-the class string, "serial" is the name of the platfrom driver and
+the class string, "serial" is the name of the platform driver and
 0 is the platform device id. If the id is -1 then the dot and the
 id can be omitted.
diff --git a/Documentation/dvb/ci.txt b/Documentation/dvb/ci.txt
index 2ecd834585e6..4a0c2b56e690 100644
--- a/Documentation/dvb/ci.txt
+++ b/Documentation/dvb/ci.txt
@@ -41,7 +41,7 @@ This application requires the following to function properly as of now.
 * Cards that fall in this category
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-At present the cards that fall in this category are the Twinhan and it's
+At present the cards that fall in this category are the Twinhan and its
 clones, these cards are available as VVMER, Tomato, Hercules, Orange and
 so on.
diff --git a/Documentation/dvb/contributors.txt b/Documentation/dvb/contributors.txt
index 4865addebe1c..47c30098dab6 100644
--- a/Documentation/dvb/contributors.txt
+++ b/Documentation/dvb/contributors.txt
@@ -1,7 +1,7 @@
 Thanks go to the following people for patches and contributions:
 Michael Hunold <m.hunold@gmx.de>
-  for the initial saa7146 driver and it's recent overhaul
+  for the initial saa7146 driver and its recent overhaul
 Christian Theiss
  for his work on the initial Linux DVB driver
diff --git a/Documentation/dvb/get_dvb_firmware b/Documentation/dvb/get_dvb_firmware
index 14b7b5a3bcb9..239cbdbf4d12 100644
--- a/Documentation/dvb/get_dvb_firmware
+++ b/Documentation/dvb/get_dvb_firmware
@@ -26,7 +26,7 @@ use IO::Handle;
                "dec3000s", "vp7041", "dibusb", "nxt2002", "nxt2004",
                "or51211", "or51132_qam", "or51132_vsb", "bluebird",
                "opera1", "cx231xx", "cx18", "cx23885", "pvrusb2", "mpc718",
-                "af9015");
+                "af9015", "ngene");
 # Check args
 syntax() if (scalar(@ARGV) != 1);
@@ -39,7 +39,7 @@ for ($i=0; $i < scalar(@components); $i++) {
        die $@ if $@;
        print STDERR <<EOF;
 Firmware(s) $outfile extracted successfully.
-Now copy it(they) to either /usr/lib/hotplug/firmware or /lib/firmware
+Now copy it(them) to either /usr/lib/hotplug/firmware or /lib/firmware
 (depending on configuration of firmware hotplug).
 EOF
        exit(0);
@@ -549,6 +549,24 @@ sub af9015 {
        close INFILE;
 }
+sub ngene {
+    my $url = "http://www.digitaldevices.de/download/";
+    my $file1 = "ngene_15.fw";
+    my $hash1 = "d798d5a757121174f0dbc5f2833c0c85";
+    my $file2 = "ngene_17.fw";
+    my $hash2 = "26b687136e127b8ac24b81e0eeafc20b";
+    checkstandard();
+    wgetfile($file1, $url . $file1);
+    verify($file1, $hash1);
+    wgetfile($file2, $url . $file2);
+    verify($file2, $hash2);
+    "$file1, $file2";
+}
 # ---------------------------------------------------------------
 # Utilities
@@ -667,6 +685,7 @@ sub delzero{
 sub syntax() {
    print STDERR "syntax: get_dvb_firmware <component>\n";
    print STDERR "Supported components:\n";
+    @components = sort @components;
    for($i=0; $i < scalar(@components); $i++) {
        print STDERR "\t" . $components[$i] . "\n";
    }
diff --git a/Documentation/eisa.txt b/Documentation/eisa.txt
index 60e361ba08c0..f297fc1202ae 100644
--- a/Documentation/eisa.txt
+++ b/Documentation/eisa.txt
@@ -171,7 +171,7 @@ device.
 virtual_root.force_probe :
 Force the probing code to probe EISA slots even when it cannot find an
-EISA compliant mainboard (nothing appears on slot 0). Defaultd to 0
+EISA compliant mainboard (nothing appears on slot 0). Defaults to 0
 (don't force), and set to 1 (force probing) when either
 CONFIG_ALPHA_JENSEN or CONFIG_EISA_VLB_PRIMING are set.
diff --git a/Documentation/email-clients.txt b/Documentation/email-clients.txt
index a618efab7b15..945ff3fda433 100644
--- a/Documentation/email-clients.txt
+++ b/Documentation/email-clients.txt
@@ -216,26 +216,14 @@ Works.  Use "Insert file..." or external editor.
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Gmail (Web GUI)
-If you just have to use Gmail to send patches, it CAN be made to work.  It
+Does not work for sending patches.
-requires a bit of external help, though.
+Gmail web client converts tabs to spaces automatically.
-The first problem is that Gmail converts tabs to spaces.  This will
-totally break your patches.  To prevent this, you have to use a different
+At the same time it wraps lines every 78 chars with CRLF style line breaks
-editor.  There is a firefox extension called "ViewSourceWith"
+although tab2space problem can be solved with external editor.
-(https://addons.mozilla.org/en-US/firefox/addon/394) which allows you to
-edit any text box in the editor of your choice.  Configure it to launch
+Another problem is that Gmail will base64-encode any message that has a
-your favorite editor.  When you want to send a patch, use this technique.
+non-ASCII character. That includes things like European names.
-Once you have crafted your messsage + patch, save and exit the editor,
-which should reload the Gmail edit box.  GMAIL WILL PRESERVE THE TABS.
-Hoorah.  Apparently you can cut-n-paste literal tabs, but Gmail will
-convert those to spaces upon sending!
-The second problem is that Gmail converts tabs to spaces on replies.  If
-you reply to a patch, don't expect to be able to apply it as a patch.
-The last problem is that Gmail will base64-encode any message that has a
-non-ASCII character.  That includes things like European names.  Be aware.
-Gmail is not convenient for lkml patches, but CAN be made to work.
                                ###
diff --git a/Documentation/fault-injection/provoke-crashes.txt b/Documentation/fault-injection/provoke-crashes.txt
new file mode 100644
index 000000000000..7a9d3d81525b
--- /dev/null
+++ b/Documentation/fault-injection/provoke-crashes.txt
@@ -0,0 +1,38 @@
+The lkdtm module provides an interface to crash or injure the kernel at
+predefined crashpoints to evaluate the reliability of crash dumps obtained
+using different dumping solutions. The module uses KPROBEs to instrument
+crashing points, but can also crash the kernel directly without KRPOBE
+support.
+You can provide the way either through module arguments when inserting
+the module, or through a debugfs interface.
+Usage: insmod lkdtm.ko [recur_count={>0}] cpoint_name=<> cpoint_type=<>
+                                [cpoint_count={>0}]
+  recur_count : Recursion level for the stack overflow test. Default is 10.
+  cpoint_name : Crash point where the kernel is to be crashed. It can be
+         one of INT_HARDWARE_ENTRY, INT_HW_IRQ_EN, INT_TASKLET_ENTRY,
+         FS_DEVRW, MEM_SWAPOUT, TIMERADD, SCSI_DISPATCH_CMD,
+         IDE_CORE_CP, DIRECT
+  cpoint_type : Indicates the action to be taken on hitting the crash point.
+     It can be one of PANIC, BUG, EXCEPTION, LOOP, OVERFLOW,
+     CORRUPT_STACK, UNALIGNED_LOAD_STORE_WRITE, OVERWRITE_ALLOCATION,
+     WRITE_AFTER_FREE,
+  cpoint_count : Indicates the number of times the crash point is to be hit
+    to trigger an action. The default is 10.
+You can also induce failures by mounting debugfs and writing the type to
+<mountpoint>/provoke-crash/<crashpoint>. E.g.,
+  mount -t debugfs debugfs /mnt
+  echo EXCEPTION > /mnt/provoke-crash/INT_HARDWARE_ENTRY
+A special file is `DIRECT' which will induce the crash directly without
+KPROBE instrumentation. This mode is the only one available when the module
+is built on a kernel without KPROBEs support.
diff --git a/Documentation/fb/imacfb.txt b/Documentation/fb/efifb.txt
index 316ec9bb7deb..a59916c29b33 100644
--- a/Documentation/fb/imacfb.txt
+++ b/Documentation/fb/efifb.txt
@@ -1,9 +1,9 @@
-What is imacfb?
+What is efifb?
 ===============
 This is a generic EFI platform driver for Intel based Apple computers.
-Imacfb is only for EFI booted Intel Macs.
+efifb is only for EFI booted Intel Macs.
 Supported Hardware
 ==================
@@ -16,16 +16,16 @@ MacMini
 How to use it?
 ==============
-Imacfb does not have any kind of autodetection of your machine.
+efifb does not have any kind of autodetection of your machine.
 You have to add the following kernel parameters in your elilo.conf:
        Macbook :
-                video=imacfb:macbook
+                video=efifb:macbook
        MacMini :
-                video=imacfb:mini
+                video=efifb:mini
        Macbook Pro 15", iMac 17" :
-                video=imacfb:i17
+                video=efifb:i17
        Macbook Pro 17", iMac 20" :
-                video=imacfb:i20
+                video=efifb:i20
 --
 Edgar Hucek <gimli@dark-green.com>
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 88a216d18092..672be0109d02 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -6,21 +6,6 @@ be removed from this file.
 ---------------------------
-What:   USER_SCHED
-When:   2.6.34
-Why:    USER_SCHED was implemented as a proof of concept for group scheduling.
-        The effect of USER_SCHED can already be achieved from userspace with
-        the help of libcgroup. The removal of USER_SCHED will also simplify
-        the scheduler code with the removal of one major ifdef. There are also
-        issues USER_SCHED has with USER_NS. A decision was taken not to fix
-        those and instead remove USER_SCHED. Also new group scheduling
-        features will not be implemented for USER_SCHED.
-Who:    Dhaval Giani <dhaval@linux.vnet.ibm.com>
---------------------------
 What:   PRISM54
 When:   2.6.34
@@ -64,6 +49,17 @@ Who:	Robin Getz <rgetz@blackfin.uclinux.org> & Matt Mackall <mpm@selenic.com>
 ---------------------------
+What:   Deprecated snapshot ioctls
+When:   2.6.36
+Why:    The ioctls in kernel/power/user.c were marked as deprecated long time
+        ago. Now they notify users about that so that they need to replace
+        their userspace. After some more time, remove them completely.
+Who:    Jiri Slaby <jirislaby@gmail.com>
+---------------------------
 What:   The ieee80211_regdom module parameter
 When:   March 2010 / desktop catchup
@@ -88,27 +84,6 @@ Who:	Luis R. Rodriguez <lrodriguez@atheros.com>
 ---------------------------
-What:   CONFIG_WIRELESS_OLD_REGULATORY - old static regulatory information
-When:   March 2010 / desktop catchup
-Why:    The old regulatory infrastructure has been replaced with a new one
-        which does not require statically defined regulatory domains. We do
-        not want to keep static regulatory domains in the kernel due to the
-        the dynamic nature of regulatory law and localization. We kept around
-        the old static definitions for the regulatory domains of:
-                * US
-                * JP
-                * EU
-        and used by default the US when CONFIG_WIRELESS_OLD_REGULATORY was
-        set. We will remove this option once the standard Linux desktop catches
-        up with the new userspace APIs we have implemented.
-Who:    Luis R. Rodriguez <lrodriguez@atheros.com>
---------------------------
 What:   dev->power.power_state
 When:   July 2007
 Why:    Broken design for runtime control over driver power states, confusing
@@ -142,19 +117,25 @@ Who:	Mauro Carvalho Chehab <mchehab@infradead.org>
 ---------------------------
 What:   PCMCIA control ioctl (needed for pcmcia-cs [cardmgr, cardctl])
-When:   November 2005
+When:   2.6.35/2.6.36
 Files:  drivers/pcmcia/: pcmcia_ioctl.c
 Why:    With the 16-bit PCMCIA subsystem now behaving (almost) like a
        normal hotpluggable bus, and with it using the default kernel
        infrastructure (hotplug, driver core, sysfs) keeping the PCMCIA
        control ioctl needed by cardmgr and cardctl from pcmcia-cs is
-        unnecessary, and makes further cleanups and integration of the
+        unnecessary and potentially harmful (it does not provide for
+        proper locking), and makes further cleanups and integration of the
        PCMCIA subsystem into the Linux kernel device driver model more
        difficult. The features provided by cardmgr and cardctl are either
        handled by the kernel itself now or are available in the new
        pcmciautils package available at
        http://kernel.org/pub/linux/utils/kernel/pcmcia/
-Who:    Dominik Brodowski <linux@brodo.de>
+        For all architectures except ARM, the associated config symbol
+        has been removed from kernel 2.6.34; for ARM, it will be likely
+        be removed from kernel 2.6.35. The actual code will then likely
+        be removed from kernel 2.6.36.
+Who:    Dominik Brodowski <linux@dominikbrodowski.net>
 ---------------------------
@@ -260,16 +241,6 @@ Who:	Thomas Gleixner <tglx@linutronix.de>
 ---------------------------
-What (Why):
-        - xt_recent: the old ipt_recent proc dir
-          (superseded by /proc/net/xt_recent)
-When:   January 2009 or Linux 2.7.0, whichever comes first
-Why:    Superseded by newer revisions or modules
-Who:    Jan Engelhardt <jengelh@computergmbh.de>
---------------------------
 What:   GPIO autorequest on gpio_direction_{input,output}() in gpiolib
 When:   February 2010
 Why:    All callers should use explicit gpio_request()/gpio_free().
@@ -468,12 +439,6 @@ Who:	Alok N Kataria <akataria@vmware.com>
 ----------------------------
-What:   adt7473 hardware monitoring driver
-When:   February 2010
-Why:    Obsoleted by the adt7475 driver.
-Who:    Jean Delvare <khali@linux-fr.org>
---------------------------
 What:   Support for lcd_switch and display_get in asus-laptop driver
 When:   March 2010
 Why:    These two features use non-standard interfaces. There are the
@@ -545,6 +510,142 @@ Who:	Hans de Goede <hdegoede@redhat.com>
 ----------------------------
+What:   sysfs-class-rfkill state file
+When:   Feb 2014
+Files:  net/rfkill/core.c
+Why:    Documented as obsolete since Feb 2010. This file is limited to 3
+        states while the rfkill drivers can have 4 states.
+Who:    anybody or Florian Mickler <florian@mickler.org>
+----------------------------
+What:   sysfs-class-rfkill claim file
+When:   Feb 2012
+Files:  net/rfkill/core.c
+Why:    It is not possible to claim an rfkill driver since 2007. This is
+        Documented as obsolete since Feb 2010.
+Who:    anybody or Florian Mickler <florian@mickler.org>
+----------------------------
+What:   capifs
+When:   February 2011
+Files:  drivers/isdn/capi/capifs.*
+Why:    udev fully replaces this special file system that only contains CAPI
+        NCCI TTY device nodes. User space (pppdcapiplugin) works without
+        noticing the difference.
+Who:    Jan Kiszka <jan.kiszka@web.de>
+----------------------------
+What:   KVM memory aliases support
+When:   July 2010
+Why:    Memory aliasing support is used for speeding up guest vga access
+        through the vga windows.
+        Modern userspace no longer uses this feature, so it's just bitrotted
+        code and can be removed with no impact.
+Who:    Avi Kivity <avi@redhat.com>
+----------------------------
+What:   xtime, wall_to_monotonic
+When:   2.6.36+
+Files:  kernel/time/timekeeping.c include/linux/time.h
+Why:    Cleaning up timekeeping internal values. Please use
+        existing timekeeping accessor functions to access
+        the equivalent functionality.
+Who:    John Stultz <johnstul@us.ibm.com>
+----------------------------
+What:   KVM kernel-allocated memory slots
+When:   July 2010
+Why:    Since 2.6.25, kvm supports user-allocated memory slots, which are
+        much more flexible than kernel-allocated slots.  All current userspace
+        supports the newer interface and this code can be removed with no
+        impact.
+Who:    Avi Kivity <avi@redhat.com>
+----------------------------
+What:   KVM paravirt mmu host support
+When:   January 2011
+Why:    The paravirt mmu host support is slower than non-paravirt mmu, both
+        on newer and older hardware.  It is already not exposed to the guest,
+        and kept only for live migration purposes.
+Who:    Avi Kivity <avi@redhat.com>
+----------------------------
+What:   "acpi=ht" boot option
+When:   2.6.35
+Why:    Useful in 2003, implementation is a hack.
+        Generally invoked by accident today.
+        Seen as doing more harm than good.
+Who:    Len Brown <len.brown@intel.com>
+----------------------------
+What:   iwlwifi 50XX module parameters
+When:   2.6.40
+Why:    The "..50" modules parameters were used to configure 5000 series and
+        up devices; different set of module parameters also available for 4965
+        with same functionalities. Consolidate both set into single place
+        in drivers/net/wireless/iwlwifi/iwl-agn.c
+Who:    Wey-Yi Guy <wey-yi.w.guy@intel.com>
+----------------------------
+What:   iwl4965 alias support
+When:   2.6.40
+Why:    Internal alias support has been present in module-init-tools for some
+        time, the MODULE_ALIAS("iwl4965") boilerplate aliases can be removed
+        with no impact.
+Who:    Wey-Yi Guy <wey-yi.w.guy@intel.com>
+---------------------------
+What:   xt_NOTRACK
+Files:  net/netfilter/xt_NOTRACK.c
+When:   April 2011
+Why:    Superseded by xt_CT
+Who:    Netfilter developer team <netfilter-devel@vger.kernel.org>
+---------------------------
+What:   video4linux /dev/vtx teletext API support
+When:   2.6.35
+Files:  drivers/media/video/saa5246a.c drivers/media/video/saa5249.c
+        include/linux/videotext.h
+Why:    The vtx device nodes have been superseded by vbi device nodes
+        for many years. No applications exist that use the vtx support.
+        Of the two i2c drivers that actually support this API the saa5249
+        has been impossible to use for a year now and no known hardware
+        that supports this device exists. The saa5246a is theoretically
+        supported by the old mxb boards, but it never actually worked.
+        In summary: there is no hardware that can use this API and there
+        are no applications actually implementing this API.
+        The vtx support still reserves minors 192-223 and we would really
+        like to reuse those for upcoming new functionality. In the unlikely
+        event that new hardware appears that wants to use the functionality
+        provided by the vtx API, then that functionality should be build
+        around the sliced VBI API instead.
+Who:    Hans Verkuil <hverkuil@xs4all.nl>
+----------------------------
+What:   IRQF_DISABLED
+When:   2.6.36
+Why:    The flag is a NOOP as we run interrupt handlers with interrupts disabled
+Who:    Thomas Gleixner <tglx@linutronix.de>
+----------------------------
 What:   old ieee1394 subsystem (CONFIG_IEEE1394)
 When:   2.6.37
 Files:  drivers/ieee1394/ except init_ohci1394_dma.c
@@ -552,3 +653,6 @@ Why:	superseded by drivers/firewire/ (CONFIG_FIREWIRE) which offers more
        features, better performance, and better security, all with smaller
        and more modern code base
 Who:    Stefan Richter <stefanr@s5r6.in-berlin.de>
+----------------------------
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 875d49696b6e..4303614b5add 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -16,6 +16,8 @@ befs.txt
        - information about the BeOS filesystem for Linux.
 bfs.txt
        - info for the SCO UnixWare Boot Filesystem (BFS).
+ceph.txt
+        - info for the Ceph Distributed File System
 cifs.txt
        - description of the CIFS filesystem.
 coda.txt
@@ -32,6 +34,8 @@ dlmfs.txt
        - info on the userspace interface to the OCFS2 DLM.
 dnotify.txt
        - info about directory notification in Linux.
+dnotify_test.c
+        - example program for dnotify
 ecryptfs.txt
        - docs on eCryptfs: stacked cryptographic filesystem for Linux.
 exofs.txt
@@ -62,6 +66,8 @@ jfs.txt
        - info and mount options for the JFS filesystem.
 locks.txt
        - info on file locking implementations, flock() vs. fcntl(), etc.
+logfs.txt
+        - info on the LogFS flash filesystem.
 mandatory-locking.txt
        - info on the Linux implementation of Sys V mandatory file locking.
 ncpfs.txt
diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt
index 57e0b80a5274..c0236e753bc8 100644
--- a/Documentation/filesystems/9p.txt
+++ b/Documentation/filesystems/9p.txt
@@ -37,6 +37,15 @@ For Plan 9 From User Space applications (http://swtch.com/plan9)
        mount -t 9p `namespace`/acme /mnt/9 -o trans=unix,uname=$USER
+For server running on QEMU host with virtio transport:
+        mount -t 9p -o trans=virtio <mount_tag> /mnt/9
+where mount_tag is the tag associated by the server to each of the exported
+mount points. Each 9P export is seen by the client as a virtio device with an
+associated "mount_tag" property. Available mount tags can be
+seen by reading /sys/bus/virtio/drivers/9pnet_virtio/virtio<n>/mount_tag files.
 OPTIONS
 =======
@@ -47,7 +56,7 @@ OPTIONS
                        fd      - used passed file descriptors for connection
                                (see rfdno and wfdno)
                        virtio  - connect to the next virtio channel available
-                                (from lguest or KVM with trans_virtio module)
+                                (from QEMU with trans_virtio module)
                        rdma    - connect to a specified RDMA channel
  uname=name    user name to attempt mount as on the remote server.  The
@@ -85,7 +94,12 @@ OPTIONS
  port=n        port to connect to on the remote server
-  noextend      force legacy mode (no 9p2000.u semantics)
+  noextend      force legacy mode (no 9p2000.u or 9p2000.L semantics)
+  version=name  Select 9P protocol version. Valid options are:
+                        9p2000          - Legacy mode (same as noextend)
+                        9p2000.u        - Use 9P2000.u protocol
+                        9p2000.L        - Use 9P2000.L protocol
  dfltuid       attempt to mount as a particular uid
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 18b9d0ca0630..61c98f03baa1 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -178,7 +178,7 @@ prototypes:
 locking rules:
        All except set_page_dirty may block
-                        BKL     PageLocked(page)        i_sem
+                        BKL     PageLocked(page)        i_mutex
 writepage:              no      yes, unlocks (see below)
 readpage:               no      yes, unlocks
 sync_page:              no      maybe
@@ -429,8 +429,9 @@ check_flags:		no
 implementations.  If your fs is not using generic_file_llseek, you
 need to acquire and release the appropriate locks in your ->llseek().
 For many filesystems, it is probably safe to acquire the inode
-semaphore.  Note some filesystems (i.e. remote ones) provide no
+mutex or just to use i_size_read() instead.
-protection for i_size so you will need to use the BKL.
+Note: this does not protect the file->f_pos against concurrent modifications
+since this is something the userspace has to take care about.
 Note: ext2_release() was *the* source of contention on fs-intensive
 loads and dropping BKL on ->release() helps to get rid of that (we still
@@ -460,13 +461,6 @@ in sys_read() and friends.
 --------------------------- dquot_operations -------------------------------
 prototypes:
-        int (*initialize) (struct inode *, int);
-        int (*drop) (struct inode *);
-        int (*alloc_space) (struct inode *, qsize_t, int);
-        int (*alloc_inode) (const struct inode *, unsigned long);
-        int (*free_space) (struct inode *, qsize_t);
-        int (*free_inode) (const struct inode *, unsigned long);
-        int (*transfer) (struct inode *, struct iattr *);
        int (*write_dquot) (struct dquot *);
        int (*acquire_dquot) (struct dquot *);
        int (*release_dquot) (struct dquot *);
@@ -479,13 +473,6 @@ a proper locking wrt the filesystem and call the generic quota operations.
 What filesystem should expect from the generic quota functions:
                FS recursion    Held locks when called
-initialize:     yes             maybe dqonoff_sem
-drop:           yes             -
-alloc_space:    ->mark_dirty()  -
-alloc_inode:    ->mark_dirty()  -
-free_space:     ->mark_dirty()  -
-free_inode:     ->mark_dirty()  -
-transfer:       yes             -
 write_dquot:    yes             dqonoff_sem or dqptr_sem
 acquire_dquot:  yes             dqonoff_sem or dqptr_sem
 release_dquot:  yes             dqonoff_sem or dqptr_sem
@@ -495,10 +482,6 @@ write_info:	yes		dqonoff_sem
 FS recursion means calling ->quota_read() and ->quota_write() from superblock
 operations.
->alloc_space(), ->alloc_inode(), ->free_space(), ->free_inode() are called
-only directly by the filesystem and do not call any fs functions only
-the ->mark_dirty() operation.
 More details about quota locking can be found in fs/dquot.c.
 --------------------------- vm_operations_struct -----------------------------
diff --git a/Documentation/filesystems/Makefile b/Documentation/filesystems/Makefile
new file mode 100644
index 000000000000..a5dd114da14f
--- /dev/null
+++ b/Documentation/filesystems/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+# List of programs to build
+hostprogs-y := dnotify_test
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/filesystems/autofs4-mount-control.txt b/Documentation/filesystems/autofs4-mount-control.txt
index 8f78ded4b648..51986bf08a4d 100644
--- a/Documentation/filesystems/autofs4-mount-control.txt
+++ b/Documentation/filesystems/autofs4-mount-control.txt
@@ -146,7 +146,7 @@ found to be inadequate, in this case. The Generic Netlink system was
 used for this as raw Netlink would lead to a significant increase in
 complexity. There's no question that the Generic Netlink system is an
 elegant solution for common case ioctl functions but it's not a complete
-replacement probably because it's primary purpose in life is to be a
+replacement probably because its primary purpose in life is to be a
 message bus implementation rather than specifically an ioctl replacement.
 While it would be possible to work around this there is one concern
 that lead to the decision to not use it. This is that the autofs
diff --git a/Documentation/filesystems/ceph.txt b/Documentation/filesystems/ceph.txt
new file mode 100644
index 000000000000..763d8ebbbebd
--- /dev/null
+++ b/Documentation/filesystems/ceph.txt
@@ -0,0 +1,140 @@
+Ceph Distributed File System
+============================
+Ceph is a distributed network file system designed to provide good
+performance, reliability, and scalability.
+Basic features include:
+ * POSIX semantics
+ * Seamless scaling from 1 to many thousands of nodes
+ * High availability and reliability.  No single point of failure.
+ * N-way replication of data across storage nodes
+ * Fast recovery from node failures
+ * Automatic rebalancing of data on node addition/removal
+ * Easy deployment: most FS components are userspace daemons
+Also,
+ * Flexible snapshots (on any directory)
+ * Recursive accounting (nested files, directories, bytes)
+In contrast to cluster filesystems like GFS, OCFS2, and GPFS that rely
+on symmetric access by all clients to shared block devices, Ceph
+separates data and metadata management into independent server
+clusters, similar to Lustre.  Unlike Lustre, however, metadata and
+storage nodes run entirely as user space daemons.  Storage nodes
+utilize btrfs to store data objects, leveraging its advanced features
+(checksumming, metadata replication, etc.).  File data is striped
+across storage nodes in large chunks to distribute workload and
+facilitate high throughputs.  When storage nodes fail, data is
+re-replicated in a distributed fashion by the storage nodes themselves
+(with some minimal coordination from a cluster monitor), making the
+system extremely efficient and scalable.
+Metadata servers effectively form a large, consistent, distributed
+in-memory cache above the file namespace that is extremely scalable,
+dynamically redistributes metadata in response to workload changes,
+and can tolerate arbitrary (well, non-Byzantine) node failures.  The
+metadata server takes a somewhat unconventional approach to metadata
+storage to significantly improve performance for common workloads.  In
+particular, inodes with only a single link are embedded in
+directories, allowing entire directories of dentries and inodes to be
+loaded into its cache with a single I/O operation.  The contents of
+extremely large directories can be fragmented and managed by
+independent metadata servers, allowing scalable concurrent access.
+The system offers automatic data rebalancing/migration when scaling
+from a small cluster of just a few nodes to many hundreds, without
+requiring an administrator carve the data set into static volumes or
+go through the tedious process of migrating data between servers.
+When the file system approaches full, new nodes can be easily added
+and things will "just work."
+Ceph includes flexible snapshot mechanism that allows a user to create
+a snapshot on any subdirectory (and its nested contents) in the
+system.  Snapshot creation and deletion are as simple as 'mkdir
+.snap/foo' and 'rmdir .snap/foo'.
+Ceph also provides some recursive accounting on directories for nested
+files and bytes.  That is, a 'getfattr -d foo' on any directory in the
+system will reveal the total number of nested regular files and
+subdirectories, and a summation of all nested file sizes.  This makes
+the identification of large disk space consumers relatively quick, as
+no 'du' or similar recursive scan of the file system is required.
+Mount Syntax
+============
+The basic mount syntax is:
+ # mount -t ceph monip[:port][,monip2[:port]...]:/[subdir] mnt
+You only need to specify a single monitor, as the client will get the
+full list when it connects.  (However, if the monitor you specify
+happens to be down, the mount won't succeed.)  The port can be left
+off if the monitor is using the default.  So if the monitor is at
+1.2.3.4,
+ # mount -t ceph 1.2.3.4:/ /mnt/ceph
+is sufficient.  If /sbin/mount.ceph is installed, a hostname can be
+used instead of an IP address.
+Mount Options
+=============
+  ip=A.B.C.D[:N]
+        Specify the IP and/or port the client should bind to locally.
+        There is normally not much reason to do this.  If the IP is not
+        specified, the client's IP address is determined by looking at the
+        address its connection to the monitor originates from.
+  wsize=X
+        Specify the maximum write size in bytes.  By default there is no
+        maximum.  Ceph will normally size writes based on the file stripe
+        size.
+  rsize=X
+        Specify the maximum readahead.
+  mount_timeout=X
+        Specify the timeout value for mount (in seconds), in the case
+        of a non-responsive Ceph file system.  The default is 30
+        seconds.
+  rbytes
+        When stat() is called on a directory, set st_size to 'rbytes',
+        the summation of file sizes over all files nested beneath that
+        directory.  This is the default.
+  norbytes
+        When stat() is called on a directory, set st_size to the
+        number of entries in that directory.
+  nocrc
+        Disable CRC32C calculation for data writes.  If set, the storage node
+        must rely on TCP's error correction to detect data corruption
+        in the data payload.
+  noasyncreaddir
+        Disable client's use its local cache to satisfy readdir
+        requests.  (This does not change correctness; the client uses
+        cached metadata only when a lease or capability ensures it is
+        valid.)
+More Information
+================
+For more information on Ceph, see the home page at
+        http://ceph.newdream.net/
+The Linux kernel client source tree is available at
+        git://ceph.newdream.net/git/ceph-client.git
+        git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+and the source for the full system is at
+        git://ceph.newdream.net/git/ceph.git
diff --git a/Documentation/filesystems/dentry-locking.txt b/Documentation/filesystems/dentry-locking.txt
index 4c0c575a4012..79334ed5daa7 100644
--- a/Documentation/filesystems/dentry-locking.txt
+++ b/Documentation/filesystems/dentry-locking.txt
@@ -62,7 +62,8 @@ changes are :
 2. Insertion of a dentry into the hash table is done using
   hlist_add_head_rcu() which take care of ordering the writes - the
   writes to the dentry must be visible before the dentry is
-   inserted. This works in conjunction with hlist_for_each_rcu() while
+   inserted. This works in conjunction with hlist_for_each_rcu(),
+   which has since been replaced by hlist_for_each_entry_rcu(), while
   walking the hash chain. The only requirement is that all
   initialization to the dentry must be done before
   hlist_add_head_rcu() since we don't have dcache_lock protection
diff --git a/Documentation/filesystems/dlmfs.txt b/Documentation/filesystems/dlmfs.txt
index c50bbb2d52b4..1b528b2ad809 100644
--- a/Documentation/filesystems/dlmfs.txt
+++ b/Documentation/filesystems/dlmfs.txt
@@ -47,7 +47,7 @@ You'll want to start heartbeating on a volume which all the nodes in
 your lockspace can access. The easiest way to do this is via
 ocfs2_hb_ctl (distributed with ocfs2-tools). Right now it requires
 that an OCFS2 file system be in place so that it can automatically
-find it's heartbeat area, though it will eventually support heartbeat
+find its heartbeat area, though it will eventually support heartbeat
 against raw disks.
 Please see the ocfs2_hb_ctl and mkfs.ocfs2 manual pages distributed
diff --git a/Documentation/filesystems/dnotify.txt b/Documentation/filesystems/dnotify.txt
index 9f5d338ddbb8..6baf88f46859 100644
--- a/Documentation/filesystems/dnotify.txt
+++ b/Documentation/filesystems/dnotify.txt
@@ -62,38 +62,9 @@ disabled, fcntl(fd, F_NOTIFY, ...) will return -EINVAL.
 Example
 -------
+See Documentation/filesystems/dnotify_test.c for an example.
-        #define _GNU_SOURCE     /* needed to get the defines */
+NOTE
-        #include <fcntl.h>      /* in glibc 2.2 this has the needed
+----
-                                           values defined */
+Beginning with Linux 2.6.13, dnotify has been replaced by inotify.
-        #include <signal.h>
+See Documentation/filesystems/inotify.txt for more information on it.
-        #include <stdio.h>
-        #include <unistd.h>
-        static volatile int event_fd;
-        static void handler(int sig, siginfo_t *si, void *data)
-        {
-                event_fd = si->si_fd;
-        }
-        int main(void)
-        {
-                struct sigaction act;
-                int fd;
-                act.sa_sigaction = handler;
-                sigemptyset(&act.sa_mask);
-                act.sa_flags = SA_SIGINFO;
-                sigaction(SIGRTMIN + 1, &act, NULL);
-                fd = open(".", O_RDONLY);
-                fcntl(fd, F_SETSIG, SIGRTMIN + 1);
-                fcntl(fd, F_NOTIFY, DN_MODIFY|DN_CREATE|DN_MULTISHOT);
-                /* we will now be notified if any of the files
-                   in "." is modified or new files are created */
-                while (1) {
-                        pause();
-                        printf("Got event on fd=%d\n", event_fd);
-                }
-        }
diff --git a/Documentation/filesystems/dnotify_test.c b/Documentation/filesystems/dnotify_test.c
new file mode 100644
index 000000000000..8b37b4a1e18d
--- /dev/null
+++ b/Documentation/filesystems/dnotify_test.c
@@ -0,0 +1,34 @@
+#define _GNU_SOURCE     /* needed to get the defines */
+#include <fcntl.h>      /* in glibc 2.2 this has the needed
+                                   values defined */
+#include <signal.h>
+#include <stdio.h>
+#include <unistd.h>
+static volatile int event_fd;
+static void handler(int sig, siginfo_t *si, void *data)
+{
+        event_fd = si->si_fd;
+}
+int main(void)
+{
+        struct sigaction act;
+        int fd;
+        act.sa_sigaction = handler;
+        sigemptyset(&act.sa_mask);
+        act.sa_flags = SA_SIGINFO;
+        sigaction(SIGRTMIN + 1, &act, NULL);
+        fd = open(".", O_RDONLY);
+        fcntl(fd, F_SETSIG, SIGRTMIN + 1);
+        fcntl(fd, F_NOTIFY, DN_MODIFY|DN_CREATE|DN_MULTISHOT);
+        /* we will now be notified if any of the files
+           in "." is modified or new files are created */
+        while (1) {
+                pause();
+                printf("Got event on fd=%d\n", event_fd);
+        }
+}
diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt
index 867c5b50cb42..272f80d5f966 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -59,8 +59,19 @@ commit=nrsec	(*)	Ext3 can be told to sync all its data and metadata
                        Setting it to very large values will improve
                        performance.
-barrier=1               This enables/disables barriers.  barrier=0 disables
+barrier=<0(*)|1>        This enables/disables the use of write barriers in
-                        it, barrier=1 enables it.
+barrier                 the jbd code.  barrier=0 disables, barrier=1 enables.
+nobarrier       (*)     This also requires an IO stack which can support
+                        barriers, and if jbd gets an error on a barrier
+                        write, it will disable again with a warning.
+                        Write barriers enforce proper on-disk ordering
+                        of journal commits, making volatile disk write caches
+                        safe to use, at some performance penalty.  If
+                        your disks are battery-backed in one way or another,
+                        disabling barriers may safely improve performance.
+                        The mount options "barrier" and "nobarrier" can
+                        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.
diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt
index 606233cd4618..1b805a0efbb0 100644
--- a/Documentation/filesystems/fiemap.txt
+++ b/Documentation/filesystems/fiemap.txt
@@ -38,7 +38,7 @@ flags, it will return EBADR and the contents of fm_flags will contain
 the set of flags which caused the error. If the kernel is compatible
 with all flags passed, the contents of fm_flags will be unmodified.
 It is up to userspace to determine whether rejection of a particular
-flag is fatal to it's operation. This scheme is intended to allow the
+flag is fatal to its operation. This scheme is intended to allow the
 fiemap interface to grow in the future but without losing
 compatibility with old software.
@@ -56,7 +56,7 @@ If this flag is set, the kernel will sync the file before mapping extents.
 * FIEMAP_FLAG_XATTR
 If this flag is set, the extents returned will describe the inodes
-extended attribute lookup tree, instead of it's data tree.
+extended attribute lookup tree, instead of its data tree.
 Extent Mapping
@@ -89,7 +89,7 @@ struct fiemap_extent {
 };
 All offsets and lengths are in bytes and mirror those on disk.  It is valid
-for an extents logical offset to start before the request or it's logical
+for an extents logical offset to start before the request or its logical
 length to extend past the request.  Unless FIEMAP_EXTENT_NOT_ALIGNED is
 returned, fe_logical, fe_physical, and fe_length will be aligned to the
 block size of the file system.  With the exception of extents flagged as
@@ -125,7 +125,7 @@ been allocated for the file yet.
 * FIEMAP_EXTENT_DELALLOC
  - This will also set FIEMAP_EXTENT_UNKNOWN.
-Delayed allocation - while there is data for this extent, it's
+Delayed allocation - while there is data for this extent, its
 physical location has not been allocated yet.
 * FIEMAP_EXTENT_ENCODED
@@ -159,7 +159,7 @@ Data is located within a meta data block.
 Data is packed into a block with data from other files.
 * FIEMAP_EXTENT_UNWRITTEN
-Unwritten extent - the extent is allocated but it's data has not been
+Unwritten extent - the extent is allocated but its data has not been
 initialized.  This indicates the extent's data will be all zero if read
 through the filesystem but the contents are undefined if read directly from
 the device.
@@ -176,7 +176,7 @@ VFS -> File System Implementation
 File systems wishing to support fiemap must implement a ->fiemap callback on
 their inode_operations structure. The fs ->fiemap call is responsible for
-defining it's set of supported fiemap flags, and calling a helper function on
+defining its set of supported fiemap flags, and calling a helper function on
 each discovered extent:
 struct inode_operations {
diff --git a/Documentation/filesystems/fuse.txt b/Documentation/filesystems/fuse.txt
index 397a41adb4c3..13af4a49e7db 100644
--- a/Documentation/filesystems/fuse.txt
+++ b/Documentation/filesystems/fuse.txt
@@ -91,7 +91,7 @@ Mount options
 'default_permissions'
  By default FUSE doesn't check file access permissions, the
-  filesystem is free to implement it's access policy or leave it to
+  filesystem is free to implement its access policy or leave it to
  the underlying file access mechanism (e.g. in case of network
  filesystems).  This option enables permission checking, restricting
  access based on file mode.  It is usually useful together with the
@@ -171,7 +171,7 @@ or may honor them by sending a reply to the _original_ request, with
 the error set to EINTR.
 It is also possible that there's a race between processing the
-original request and it's INTERRUPT request.  There are two possibilities:
+original request and its INTERRUPT request.  There are two possibilities:
  1) The INTERRUPT request is processed before the original request is
     processed
diff --git a/Documentation/filesystems/gfs2.txt b/Documentation/filesystems/gfs2.txt
index 5e3ab8f3beff..0b59c0200912 100644
--- a/Documentation/filesystems/gfs2.txt
+++ b/Documentation/filesystems/gfs2.txt
@@ -1,7 +1,7 @@
 Global File System
 ------------------
-http://sources.redhat.com/cluster/
+http://sources.redhat.com/cluster/wiki/
 GFS is a cluster file system. It allows a cluster of computers to
 simultaneously use a block device that is shared between them (with FC,
@@ -36,11 +36,11 @@ GFS2 is not on-disk compatible with previous versions of GFS, but it
 is pretty close.
 The following man pages can be found at the URL above:
-  fsck.gfs2     to repair a filesystem
+  fsck.gfs2             to repair a filesystem
-  gfs2_grow     to expand a filesystem online
+  gfs2_grow             to expand a filesystem online
-  gfs2_jadd     to add journals to a filesystem online
+  gfs2_jadd             to add journals to a filesystem online
-  gfs2_tool     to manipulate, examine and tune a filesystem
+  gfs2_tool             to manipulate, examine and tune a filesystem
  gfs2_quota    to examine and change quota values in a filesystem
  gfs2_convert  to convert a gfs filesystem to gfs2 in-place
  mount.gfs2    to help mount(8) mount a filesystem
-  mkfs.gfs2     to make a filesystem
+  mkfs.gfs2             to make a filesystem
diff --git a/Documentation/filesystems/hpfs.txt b/Documentation/filesystems/hpfs.txt
index fa45c3baed98..74630bd504fb 100644
--- a/Documentation/filesystems/hpfs.txt
+++ b/Documentation/filesystems/hpfs.txt
@@ -103,7 +103,7 @@ to analyze or change OS2SYS.INI.
 Codepages
 HPFS can contain several uppercasing tables for several codepages and each
-file has a pointer to codepage it's name is in. However OS/2 was created in
+file has a pointer to codepage its name is in. However OS/2 was created in
 America where people don't care much about codepages and so multiple codepages
 support is quite buggy. I have Czech OS/2 working in codepage 852 on my disk.
 Once I booted English OS/2 working in cp 850 and I created a file on my 852
diff --git a/Documentation/filesystems/logfs.txt b/Documentation/filesystems/logfs.txt
new file mode 100644
index 000000000000..bca42c22a143
--- /dev/null
+++ b/Documentation/filesystems/logfs.txt
@@ -0,0 +1,241 @@
+The LogFS Flash Filesystem
+==========================
+Specification
+=============
+Superblocks
+-----------
+Two superblocks exist at the beginning and end of the filesystem.
+Each superblock is 256 Bytes large, with another 3840 Bytes reserved
+for future purposes, making a total of 4096 Bytes.
+Superblock locations may differ for MTD and block devices.  On MTD the
+first non-bad block contains a superblock in the first 4096 Bytes and
+the last non-bad block contains a superblock in the last 4096 Bytes.
+On block devices, the first 4096 Bytes of the device contain the first
+superblock and the last aligned 4096 Byte-block contains the second
+superblock.
+For the most part, the superblocks can be considered read-only.  They
+are written only to correct errors detected within the superblocks,
+move the journal and change the filesystem parameters through tunefs.
+As a result, the superblock does not contain any fields that require
+constant updates, like the amount of free space, etc.
+Segments
+--------
+The space in the device is split up into equal-sized segments.
+Segments are the primary write unit of LogFS.  Within each segments,
+writes happen from front (low addresses) to back (high addresses.  If
+only a partial segment has been written, the segment number, the
+current position within and optionally a write buffer are stored in
+the journal.
+Segments are erased as a whole.  Therefore Garbage Collection may be
+required to completely free a segment before doing so.
+Journal
+--------
+The journal contains all global information about the filesystem that
+is subject to frequent change.  At mount time, it has to be scanned
+for the most recent commit entry, which contains a list of pointers to
+all currently valid entries.
+Object Store
+------------
+All space except for the superblocks and journal is part of the object
+store.  Each segment contains a segment header and a number of
+objects, each consisting of the object header and the payload.
+Objects are either inodes, directory entries (dentries), file data
+blocks or indirect blocks.
+Levels
+------
+Garbage collection (GC) may fail if all data is written
+indiscriminately.  One requirement of GC is that data is separated
+roughly according to the distance between the tree root and the data.
+Effectively that means all file data is on level 0, indirect blocks
+are on levels 1, 2, 3 4 or 5 for 1x, 2x, 3x, 4x or 5x indirect blocks,
+respectively.  Inode file data is on level 6 for the inodes and 7-11
+for indirect blocks.
+Each segment contains objects of a single level only.  As a result,
+each level requires its own separate segment to be open for writing.
+Inode File
+----------
+All inodes are stored in a special file, the inode file.  Single
+exception is the inode file's inode (master inode) which for obvious
+reasons is stored in the journal instead.  Instead of data blocks, the
+leaf nodes of the inode files are inodes.
+Aliases
+-------
+Writes in LogFS are done by means of a wandering tree.  A naïve
+implementation would require that for each write or a block, all
+parent blocks are written as well, since the block pointers have
+changed.  Such an implementation would not be very efficient.
+In LogFS, the block pointer changes are cached in the journal by means
+of alias entries.  Each alias consists of its logical address - inode
+number, block index, level and child number (index into block) - and
+the changed data.  Any 8-byte word can be changes in this manner.
+Currently aliases are used for block pointers, file size, file used
+bytes and the height of an inodes indirect tree.
+Segment Aliases
+---------------
+Related to regular aliases, these are used to handle bad blocks.
+Initially, bad blocks are handled by moving the affected segment
+content to a spare segment and noting this move in the journal with a
+segment alias, a simple (to, from) tupel.  GC will later empty this
+segment and the alias can be removed again.  This is used on MTD only.
+Vim
+---
+By cleverly predicting the life time of data, it is possible to
+separate long-living data from short-living data and thereby reduce
+the GC overhead later.  Each type of distinc life expectency (vim) can
+have a separate segment open for writing.  Each (level, vim) tupel can
+be open just once.  If an open segment with unknown vim is encountered
+at mount time, it is closed and ignored henceforth.
+Indirect Tree
+-------------
+Inodes in LogFS are similar to FFS-style filesystems with direct and
+indirect block pointers.  One difference is that LogFS uses a single
+indirect pointer that can be either a 1x, 2x, etc. indirect pointer.
+A height field in the inode defines the height of the indirect tree
+and thereby the indirection of the pointer.
+Another difference is the addressing of indirect blocks.  In LogFS,
+the first 16 pointers in the first indirect block are left empty,
+corresponding to the 16 direct pointers in the inode.  In ext2 (maybe
+others as well) the first pointer in the first indirect block
+corresponds to logical block 12, skipping the 12 direct pointers.
+So where ext2 is using arithmetic to better utilize space, LogFS keeps
+arithmetic simple and uses compression to save space.
+Compression
+-----------
+Both file data and metadata can be compressed.  Compression for file
+data can be enabled with chattr +c and disabled with chattr -c.  Doing
+so has no effect on existing data, but new data will be stored
+accordingly.  New inodes will inherit the compression flag of the
+parent directory.
+Metadata is always compressed.  However, the space accounting ignores
+this and charges for the uncompressed size.  Failing to do so could
+result in GC failures when, after moving some data, indirect blocks
+compress worse than previously.  Even on a 100% full medium, GC may
+not consume any extra space, so the compression gains are lost space
+to the user.
+However, they are not lost space to the filesystem internals.  By
+cheating the user for those bytes, the filesystem gained some slack
+space and GC will run less often and faster.
+Garbage Collection and Wear Leveling
+------------------------------------
+Garbage collection is invoked whenever the number of free segments
+falls below a threshold.  The best (known) candidate is picked based
+on the least amount of valid data contained in the segment.  All
+remaining valid data is copied elsewhere, thereby invalidating it.
+The GC code also checks for aliases and writes then back if their
+number gets too large.
+Wear leveling is done by occasionally picking a suboptimal segment for
+garbage collection.  If a stale segments erase count is significantly
+lower than the active segments' erase counts, it will be picked.  Wear
+leveling is rate limited, so it will never monopolize the device for
+more than one segment worth at a time.
+Values for "occasionally", "significantly lower" are compile time
+constants.
+Hashed directories
+------------------
+To satisfy efficient lookup(), directory entries are hashed and
+located based on the hash.  In order to both support large directories
+and not be overly inefficient for small directories, several hash
+tables of increasing size are used.  For each table, the hash value
+modulo the table size gives the table index.
+Tables sizes are chosen to limit the number of indirect blocks with a
+fully populated table to 0, 1, 2 or 3 respectively.  So the first
+table contains 16 entries, the second 512-16, etc.
+The last table is special in several ways.  First its size depends on
+the effective 32bit limit on telldir/seekdir cookies.  Since logfs
+uses the upper half of the address space for indirect blocks, the size
+is limited to 2^31.  Secondly the table contains hash buckets with 16
+entries each.
+Using single-entry buckets would result in birthday "attacks".  At
+just 2^16 used entries, hash collisions would be likely (P >= 0.5).
+My math skills are insufficient to do the combinatorics for the 17x
+collisions necessary to overflow a bucket, but testing showed that in
+10,000 runs the lowest directory fill before a bucket overflow was
+188,057,130 entries with an average of 315,149,915 entries.  So for
+directory sizes of up to a million, bucket overflows should be
+virtually impossible under normal circumstances.
+With carefully chosen filenames, it is obviously possible to cause an
+overflow with just 21 entries (4 higher tables + 16 entries + 1).  So
+there may be a security concern if a malicious user has write access
+to a directory.
+Open For Discussion
+===================
+Device Address Space
+--------------------
+A device address space is used for caching.  Both block devices and
+MTD provide functions to either read a single page or write a segment.
+Partial segments may be written for data integrity, but where possible
+complete segments are written for performance on simple block device
+flash media.
+Meta Inodes
+-----------
+Inodes are stored in the inode file, which is just a regular file for
+most purposes.  At umount time, however, the inode file needs to
+remain open until all dirty inodes are written.  So
+generic_shutdown_super() may not close this inode, but shouldn't
+complain about remaining inodes due to the inode file either.  Same
+goes for mapping inode of the device address space.
+Currently logfs uses a hack that essentially copies part of fs/inode.c
+code over.  A general solution would be preferred.
+Indirect block mapping
+----------------------
+With compression, the block device (or mapping inode) cannot be used
+to cache indirect blocks.  Some other place is required.  Currently
+logfs uses the top half of each inode's address space.  The low 8TB
+(on 32bit) are filled with file data, the high 8TB are used for
+indirect blocks.
+One problem is that 16TB files created on 64bit systems actually have
+data in the top 8TB.  But files >16TB would cause problems anyway, so
+only the limit has changed.
diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt
index 1bd0d0c05171..04884914a1c8 100644
--- a/Documentation/filesystems/nfs/nfs41-server.txt
+++ b/Documentation/filesystems/nfs/nfs41-server.txt
@@ -17,8 +17,7 @@ kernels must turn 4.1 on or off *before* turning support for version 4
 on or off; rpc.nfsd does this correctly.)
 The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based
-on the latest NFSv4.1 Internet Draft:
+on RFC 5661.
-http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29
 From the many new features in NFSv4.1 the current implementation
 focuses on the mandatory-to-implement NFSv4.1 Sessions, providing
@@ -44,7 +43,7 @@ interoperability problems with future clients.  Known issues:
          trunking, but this is a mandatory feature, and its use is
          recommended to clients in a number of places.  (E.g. to ensure
          timely renewal in case an existing connection's retry timeouts
-          have gotten too long; see section 8.3 of the draft.)
+          have gotten too long; see section 8.3 of the RFC.)
          Therefore, lack of this feature may cause future clients to
          fail.
        - Incomplete backchannel support: incomplete backchannel gss
@@ -138,7 +137,7 @@ NS*| OPENATTR             | OPT        |              | Section 18.17  |
   | READ                 | REQ        |              | Section 18.22  |
   | READDIR              | REQ        |              | Section 18.23  |
   | READLINK             | OPT        |              | Section 18.24  |
-NS | RECLAIM_COMPLETE     | REQ        |              | Section 18.51  |
+   | RECLAIM_COMPLETE     | REQ        |              | Section 18.51  |
   | RELEASE_LOCKOWNER    | MNI        |              | N/A            |
   | REMOVE               | REQ        |              | Section 18.25  |
   | RENAME               | REQ        |              | Section 18.26  |
diff --git a/Documentation/filesystems/nfs/rpc-cache.txt b/Documentation/filesystems/nfs/rpc-cache.txt
index 8a382bea6808..ebcaaee21616 100644
--- a/Documentation/filesystems/nfs/rpc-cache.txt
+++ b/Documentation/filesystems/nfs/rpc-cache.txt
@@ -185,7 +185,7 @@ failed lookup meant a definite 'no'.
 request/response format
 -----------------------
-While each cache is free to use it's own format for requests
+While each cache is free to use its own format for requests
 and responses over channel, the following is recommended as
 appropriate and support routines are available to help:
 Each request or response record should be printable ASCII
diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt
index 839efd8a8a8c..d3e7673995eb 100644
--- a/Documentation/filesystems/nilfs2.txt
+++ b/Documentation/filesystems/nilfs2.txt
@@ -50,8 +50,8 @@ NILFS2 supports the following mount options:
 (*) == default
 nobarrier               Disables barriers.
-errors=continue(*)      Keep going on a filesystem error.
+errors=continue         Keep going on a filesystem error.
-errors=remount-ro       Remount the filesystem read-only on an error.
+errors=remount-ro(*)    Remount the filesystem read-only on an error.
 errors=panic            Panic and halt the machine if an error occurs.
 cp=n                    Specify the checkpoint-number of the snapshot to be
                        mounted.  Checkpoints and snapshots are listed by lscp
@@ -74,6 +74,9 @@ norecovery		Disable recovery of the filesystem on mount.
                        This disables every write access on the device for
                        read-only mounts or snapshots.  This option will fail
                        for r/w mounts on an unclean volume.
+discard                 Issue discard/TRIM commands to the underlying block
+                        device when blocks are freed.  This is useful for SSD
+                        devices and sparse/thinly-provisioned LUNs.
 NILFS2 usage
 ============
diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt
index c58b9f5ba002..1f7ae144f6d8 100644
--- a/Documentation/filesystems/ocfs2.txt
+++ b/Documentation/filesystems/ocfs2.txt
@@ -80,3 +80,10 @@ user_xattr	(*)	Enables Extended User Attributes.
 nouser_xattr            Disables Extended User Attributes.
 acl                     Enables POSIX Access Control Lists support.
 noacl           (*)     Disables POSIX Access Control Lists support.
+resv_level=2    (*)     Set how agressive allocation reservations will be.
+                        Valid values are between 0 (reservations off) to 8
+                        (maximum space for reservations).
+dir_resv_level= (*)     By default, directory reservations will scale with file
+                        reservations - users should rarely need to change this
+                        value. If allocation reservations are turned off, this
+                        option will have no effect.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 0d07513a67a6..9fb6cbe70bde 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -164,6 +164,7 @@ read the file /proc/PID/status:
  VmExe:        68 kB
  VmLib:      1412 kB
  VmPTE:        20 kb
+  VmSwap:        0 kB
  Threads:        1
  SigQ:   0/28578
  SigPnd: 0000000000000000
@@ -188,7 +189,13 @@ memory usage. Its seven fields are explained in Table 1-3.  The stat file
 contains details information about the process itself.  Its fields are
 explained in Table 1-4.
-Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
+(for SMP CONFIG users)
+For making accounting scalable, RSS related information are handled in
+asynchronous manner and the vaule may not be very precise. To see a precise
+snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
+It's slow but very precise.
+Table 1-2: Contents of the status files (as of 2.6.30-rc7)
 ..............................................................................
 Field                       Content
 Name                        filename of the executable
@@ -213,6 +220,7 @@ Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
 VmExe                       size of text segment
 VmLib                       size of shared library code
 VmPTE                       size of page table entries
+ VmSwap                      size of swap usage (the number of referred swapents)
 Threads                     number of threads
 SigQ                        number of signals queued/max. number for queue
 SigPnd                      bitmap of pending signals for the thread
@@ -297,7 +305,7 @@ Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
  cgtime        guest time of the task children in jiffies
 ..............................................................................
-The /proc/PID/map file containing the currently mapped memory regions and
+The /proc/PID/maps file containing the currently mapped memory regions and
 their access permissions.
 The format is:
@@ -308,7 +316,7 @@ address           perms offset  dev   inode      pathname
 08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
 0804a000-0806b000 rw-p 00000000 00:00 0          [heap]
 a7cb1000-a7cb2000 ---p 00000000 00:00 0
-a7cb2000-a7eb2000 rw-p 00000000 00:00 0          [threadstack:001ff4b4]
+a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 a7eb2000-a7eb3000 ---p 00000000 00:00 0
 a7eb3000-a7ed5000 rw-p 00000000 00:00 0
 a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
@@ -344,7 +352,6 @@ is not associated with a file:
 [stack]                  = the stack of the main process
 [vdso]                   = the "virtual dynamic shared object",
                            the kernel system call handler
- [threadstack:xxxxxxxx]   = the stack of the thread, xxxxxxxx is the stack size
 or if empty, the mapping is anonymous.
@@ -430,6 +437,7 @@ Table 1-5: Kernel info in /proc
 modules     List of loaded modules                            
 mounts      Mounted filesystems                               
 net         Networking info (see text)                        
+ pagetypeinfo Additional page allocator information (see text)  (2.5)
 partitions  Table of partitions known to the system           
 pci         Deprecated info of PCI bus (new way -> /proc/bus/pci/,
             decoupled by lspci                                 (2.4)
@@ -557,6 +565,10 @@ The default_smp_affinity mask applies to all non-active IRQs, which are the
 IRQs which have not yet been allocated/activated, and hence which lack a
 /proc/irq/[0-9]* directory.
+The node file on an SMP system shows the node to which the device using the IRQ
+reports itself as being attached. This hardware locality information does not
+include information about any possible driver locality preference.
 prof_cpu_mask specifies which CPUs are to be profiled by the system wide
 profiler. Default value is ffffffff (all cpus).
@@ -584,7 +596,7 @@ Node 0, zone      DMA      0      4      5      4      4      3 ...
 Node 0, zone   Normal      1      0      0      1    101      8 ...
 Node 0, zone  HighMem      2      0      0      1      1      0 ...
-Memory fragmentation is a problem under some workloads, and buddyinfo is a 
+External fragmentation is a problem under some workloads, and buddyinfo is a
 useful tool for helping diagnose these problems.  Buddyinfo will give you a 
 clue as to how big an area you can safely allocate, or why a previous
 allocation failed.
@@ -594,6 +606,48 @@ available.  In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 
 available in ZONE_NORMAL, etc... 
+More information relevant to external fragmentation can be found in
+pagetypeinfo.
+> cat /proc/pagetypeinfo
+Page block order: 9
+Pages per block:  512
+Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
+Node    0, zone      DMA, type    Unmovable      0      0      0      1      1      1      1      1      1      1      0
+Node    0, zone      DMA, type  Reclaimable      0      0      0      0      0      0      0      0      0      0      0
+Node    0, zone      DMA, type      Movable      1      1      2      1      2      1      1      0      1      0      2
+Node    0, zone      DMA, type      Reserve      0      0      0      0      0      0      0      0      0      1      0
+Node    0, zone      DMA, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
+Node    0, zone    DMA32, type    Unmovable    103     54     77      1      1      1     11      8      7      1      9
+Node    0, zone    DMA32, type  Reclaimable      0      0      2      1      0      0      0      0      1      0      0
+Node    0, zone    DMA32, type      Movable    169    152    113     91     77     54     39     13      6      1    452
+Node    0, zone    DMA32, type      Reserve      1      2      2      2      2      0      1      1      1      1      0
+Node    0, zone    DMA32, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
+Number of blocks type     Unmovable  Reclaimable      Movable      Reserve      Isolate
+Node 0, zone      DMA            2            0            5            1            0
+Node 0, zone    DMA32           41            6          967            2            0
+Fragmentation avoidance in the kernel works by grouping pages of different
+migrate types into the same contiguous regions of memory called page blocks.
+A page block is typically the size of the default hugepage size e.g. 2MB on
+X86-64. By keeping pages grouped based on their ability to move, the kernel
+can reclaim pages within a page block to satisfy a high-order allocation.
+The pagetypinfo begins with information on the size of a page block. It
+then gives the same type of information as buddyinfo except broken down
+by migrate-type and finishes with details on how many page blocks of each
+type exist.
+If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
+from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
+make an estimate of the likely number of huge pages that can be allocated
+at a given point in time. All the "Movable" blocks should be allocatable
+unless memory has been mlock()'d. Some of the Reclaimable blocks should
+also be allocatable although a lot of filesystem metadata may have to be
+reclaimed to achieve this.
 ..............................................................................
 meminfo:
@@ -914,7 +968,7 @@ your system and how much traffic was routed over those devices:
  ...] 1375103    17405    0    0    0     0       0          0 
  ...] 1703981     5535    0    0    0     3       0          0 
-In addition, each Channel Bond interface has it's own directory.  For
+In addition, each Channel Bond interface has its own directory.  For
 example, the bond0 device will have a directory called /proc/net/bond0/.
 It will contain information that is specific to that bond, such as the
 current slaves of the bond, the link status of the slaves, and how
@@ -1311,7 +1365,7 @@ been accounted as having caused 1MB of write.
 In other words: The number of bytes which this process caused to not happen,
 by truncating pagecache. A task can cause "negative" IO too. If this task
 truncates some dirty pagecache, some IO which another task has been accounted
-for (in it's write_bytes) will not be happening. We _could_ just subtract that
+for (in its write_bytes) will not be happening. We _could_ just subtract that
 from the truncating task's write_bytes, but there is information loss in doing
 that.
diff --git a/Documentation/filesystems/sharedsubtree.txt b/Documentation/filesystems/sharedsubtree.txt
index 23a181074f94..fc0e39af43c3 100644
--- a/Documentation/filesystems/sharedsubtree.txt
+++ b/Documentation/filesystems/sharedsubtree.txt
@@ -837,6 +837,9 @@ replicas continue to be exactly same.
         individual lists does not affect propagation or the way propagation
         tree is modified by operations.
+        All vfsmounts in a peer group have the same ->mnt_master.  If it is
+        non-NULL, they form a contiguous (ordered) segment of slave list.
        A example propagation tree looks as shown in the figure below.
        [ NOTE: Though it looks like a forest, if we consider all the shared
        mounts as a conceptual entity called 'pnode', it becomes a tree]
@@ -874,8 +877,19 @@ replicas continue to be exactly same.
        NOTE: The propagation tree is orthogonal to the mount tree.
+8B Locking:
+        ->mnt_share, ->mnt_slave, ->mnt_slave_list, ->mnt_master are protected
+        by namespace_sem (exclusive for modifications, shared for reading).
+        Normally we have ->mnt_flags modifications serialized by vfsmount_lock.
+        There are two exceptions: do_add_mount() and clone_mnt().
+        The former modifies a vfsmount that has not been visible in any shared
+        data structures yet.
+        The latter holds namespace_sem and the only references to vfsmount
+        are in lists that can't be traversed without namespace_sem.
-8B Algorithm:
+8C Algorithm:
        The crux of the implementation resides in rbind/move operation.
diff --git a/Documentation/filesystems/smbfs.txt b/Documentation/filesystems/smbfs.txt
index f673ef0de0f7..194fb0decd2c 100644
--- a/Documentation/filesystems/smbfs.txt
+++ b/Documentation/filesystems/smbfs.txt
@@ -3,6 +3,6 @@ protocol used by Windows for Workgroups, Windows 95 and Windows NT.
 Smbfs was inspired by Samba, the program written by Andrew Tridgell
 that turns any Unix host into a file server for DOS or Windows clients.
-Smbfs is a SMB client, but uses parts of samba for it's operation. For
+Smbfs is a SMB client, but uses parts of samba for its operation. For
 more info on samba, including documentation, please go to
 http://www.samba.org/ and then on to your nearest mirror.
diff --git a/Documentation/filesystems/squashfs.txt b/Documentation/filesystems/squashfs.txt
index b324c033035a..203f7202cc9e 100644
--- a/Documentation/filesystems/squashfs.txt
+++ b/Documentation/filesystems/squashfs.txt
@@ -38,7 +38,8 @@ Hard link support:		yes			no
 Real inode numbers:             yes                     no
 32-bit uids/gids:               yes                     no
 File creation time:             yes                     no
-Xattr and ACL support:          no                      no
+Xattr support:                  yes                     no
+ACL support:                    no                      no
 Squashfs compresses data, inodes and directories.  In addition, inode and
 directory data are highly compacted, and packed on byte boundaries.  Each
@@ -58,7 +59,7 @@ obtained from this site also.
 3. SQUASHFS FILESYSTEM DESIGN
 -----------------------------
-A squashfs filesystem consists of seven parts, packed together on a byte
+A squashfs filesystem consists of a maximum of eight parts, packed together on a byte
 alignment:
         ---------------
@@ -80,6 +81,9 @@ alignment:
        |---------------|
        |    uid/gid    |
        |  lookup table |
+        |---------------|
+        |     xattr     |
+        |     table     |
         ---------------
 Compressed data blocks are written to the filesystem as files are read from
@@ -192,6 +196,26 @@ This table is stored compressed into metadata blocks.  A second index table is
 used to locate these.  This second index table for speed of access (and because
 it is small) is read at mount time and cached in memory.
+3.7 Xattr table
+---------------
+The xattr table contains extended attributes for each inode.  The xattrs
+for each inode are stored in a list, each list entry containing a type,
+name and value field.  The type field encodes the xattr prefix
+("user.", "trusted." etc) and it also encodes how the name/value fields
+should be interpreted.  Currently the type indicates whether the value
+is stored inline (in which case the value field contains the xattr value),
+or if it is stored out of line (in which case the value field stores a
+reference to where the actual value is stored).  This allows large values
+to be stored out of line improving scanning and lookup performance and it
+also allows values to be de-duplicated, the value being stored once, and
+all other occurences holding an out of line reference to that value.
+The xattr lists are packed into compressed 8K metadata blocks.
+To reduce overhead in inodes, rather than storing the on-disk
+location of the xattr list inside each inode, a 32-bit xattr id
+is stored.  This xattr id is mapped into the location of the xattr
+list using a second xattr id lookup table.
 4. TODOS AND OUTSTANDING ISSUES
 -------------------------------
@@ -199,9 +223,7 @@ it is small) is read at mount time and cached in memory.
 4.1 Todo list
 -------------
-Implement Xattr and ACL support.  The Squashfs 4.0 filesystem layout has hooks
+Implement ACL support.
-for these but the code has not been written.  Once the code has been written
-the existing layout should not require modification.
 4.2 Squashfs internal cache
 ---------------------------
diff --git a/Documentation/filesystems/sysfs-tagging.txt b/Documentation/filesystems/sysfs-tagging.txt
new file mode 100644
index 000000000000..caaaf1266d8f
--- /dev/null
+++ b/Documentation/filesystems/sysfs-tagging.txt
@@ -0,0 +1,42 @@
+Sysfs tagging
+-------------
+(Taken almost verbatim from Eric Biederman's netns tagging patch
+commit msg)
+The problem.  Network devices show up in sysfs and with the network
+namespace active multiple devices with the same name can show up in
+the same directory, ouch!
+To avoid that problem and allow existing applications in network
+namespaces to see the same interface that is currently presented in
+sysfs, sysfs now has tagging directory support.
+By using the network namespace pointers as tags to separate out the
+the sysfs directory entries we ensure that we don't have conflicts
+in the directories and applications only see a limited set of
+the network devices.
+Each sysfs directory entry may be tagged with zero or one
+namespaces.  A sysfs_dirent is augmented with a void *s_ns.  If a
+directory entry is tagged, then sysfs_dirent->s_flags will have a
+flag between KOBJ_NS_TYPE_NONE and KOBJ_NS_TYPES, and s_ns will
+point to the namespace to which it belongs.
+Each sysfs superblock's sysfs_super_info contains an array void
+*ns[KOBJ_NS_TYPES].  When a a task in a tagging namespace
+kobj_nstype first mounts sysfs, a new superblock is created.  It
+will be differentiated from other sysfs mounts by having its
+s_fs_info->ns[kobj_nstype] set to the new namespace.  Note that
+through bind mounting and mounts propagation, a task can easily view
+the contents of other namespaces' sysfs mounts.  Therefore, when a
+namespace exits, it will call kobj_ns_exit() to invalidate any
+sysfs_dirent->s_ns pointers pointing to it.
+Users of this interface:
+- define a type in the kobj_ns_type enumeration.
+- call kobj_ns_type_register() with its kobj_ns_type_operations which has
+  - current_ns() which returns current's namespace
+  - netlink_ns() which returns a socket's namespace
+  - initial_ns() which returns the initial namesapce
+- call kobj_ns_exit() when an individual tag is no longer valid
diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt
index 3015da0c6b2a..98ef55124158 100644
--- a/Documentation/filesystems/tmpfs.txt
+++ b/Documentation/filesystems/tmpfs.txt
@@ -82,21 +82,31 @@ tmpfs has a mount option to set the NUMA memory allocation policy for
 all files in that instance (if CONFIG_NUMA is enabled) - which can be
 adjusted on the fly via 'mount -o remount ...'
-mpol=default             prefers to allocate memory from the local node
+mpol=default             use the process allocation policy
+                         (see set_mempolicy(2))
 mpol=prefer:Node         prefers to allocate memory from the given Node
 mpol=bind:NodeList       allocates memory only from nodes in NodeList
 mpol=interleave          prefers to allocate from each node in turn
 mpol=interleave:NodeList allocates from each node of NodeList in turn
+mpol=local               prefers to allocate memory from the local node
 NodeList format is a comma-separated list of decimal numbers and ranges,
 a range being two hyphen-separated decimal numbers, the smallest and
 largest node numbers in the range.  For example, mpol=bind:0-3,5,7,9-15
+A memory policy with a valid NodeList will be saved, as specified, for
+use at file creation time.  When a task allocates a file in the file
+system, the mount option memory policy will be applied with a NodeList,
+if any, modified by the calling task's cpuset constraints
+[See Documentation/cgroups/cpusets.txt] and any optional flags, listed
+below.  If the resulting NodeLists is the empty set, the effective memory
+policy for the file will revert to "default" policy.
 NUMA memory allocation policies have optional flags that can be used in
 conjunction with their modes.  These optional flags can be specified
 when tmpfs is mounted by appending them to the mode before the NodeList.
 See Documentation/vm/numa_memory_policy.txt for a list of all available
-memory allocation policy mode flags.
+memory allocation policy mode flags and their effect on memory policy.
        =static         is equivalent to        MPOL_F_STATIC_NODES
        =relative       is equivalent to        MPOL_F_RELATIVE_NODES
@@ -134,3 +144,5 @@ Author:
   Christoph Rohland <cr@sap.com>, 1.12.01
 Updated:
   Hugh Dickins, 4 June 2007
+Updated:
+   KOSAKI Motohiro, 16 Mar 2010
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 3de2f32edd90..b66858538df5 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -72,7 +72,7 @@ structure (this is the kernel-side implementation of file
 descriptors). The freshly allocated file structure is initialized with
 a pointer to the dentry and a set of file operation member functions.
 These are taken from the inode data. The open() file method is then
-called so the specific filesystem implementation can do it's work. You
+called so the specific filesystem implementation can do its work. You
 can see that this is another switch performed by the VFS. The file
 structure is placed into the file descriptor table for the process.
diff --git a/Documentation/filesystems/xfs-delayed-logging-design.txt b/Documentation/filesystems/xfs-delayed-logging-design.txt
new file mode 100644
index 000000000000..d8119e9d2d60
--- /dev/null
+++ b/Documentation/filesystems/xfs-delayed-logging-design.txt
@@ -0,0 +1,816 @@
+XFS Delayed Logging Design
+--------------------------
+Introduction to Re-logging in XFS
+---------------------------------
+XFS logging is a combination of logical and physical logging. Some objects,
+such as inodes and dquots, are logged in logical format where the details
+logged are made up of the changes to in-core structures rather than on-disk
+structures. Other objects - typically buffers - have their physical changes
+logged. The reason for these differences is to reduce the amount of log space
+required for objects that are frequently logged. Some parts of inodes are more
+frequently logged than others, and inodes are typically more frequently logged
+than any other object (except maybe the superblock buffer) so keeping the
+amount of metadata logged low is of prime importance.
+The reason that this is such a concern is that XFS allows multiple separate
+modifications to a single object to be carried in the log at any given time.
+This allows the log to avoid needing to flush each change to disk before
+recording a new change to the object. XFS does this via a method called
+"re-logging". Conceptually, this is quite simple - all it requires is that any
+new change to the object is recorded with a *new copy* of all the existing
+changes in the new transaction that is written to the log.
+That is, if we have a sequence of changes A through to F, and the object was
+written to disk after change D, we would see in the log the following series
+of transactions, their contents and the log sequence number (LSN) of the
+transaction:
+        Transaction             Contents        LSN
+           A                       A               X
+           B                      A+B             X+n
+           C                     A+B+C           X+n+m
+           D                    A+B+C+D         X+n+m+o
+            <object written to disk>
+           E                       E               Y (> X+n+m+o)
+           F                      E+F             Yٍ+p
+In other words, each time an object is relogged, the new transaction contains
+the aggregation of all the previous changes currently held only in the log.
+This relogging technique also allows objects to be moved forward in the log so
+that an object being relogged does not prevent the tail of the log from ever
+moving forward.  This can be seen in the table above by the changing
+(increasing) LSN of each subsquent transaction - the LSN is effectively a
+direct encoding of the location in the log of the transaction.
+This relogging is also used to implement long-running, multiple-commit
+transactions.  These transaction are known as rolling transactions, and require
+a special log reservation known as a permanent transaction reservation. A
+typical example of a rolling transaction is the removal of extents from an
+inode which can only be done at a rate of two extents per transaction because
+of reservation size limitations. Hence a rolling extent removal transaction
+keeps relogging the inode and btree buffers as they get modified in each
+removal operation. This keeps them moving forward in the log as the operation
+progresses, ensuring that current operation never gets blocked by itself if the
+log wraps around.
+Hence it can be seen that the relogging operation is fundamental to the correct
+working of the XFS journalling subsystem. From the above description, most
+people should be able to see why the XFS metadata operations writes so much to
+the log - repeated operations to the same objects write the same changes to
+the log over and over again. Worse is the fact that objects tend to get
+dirtier as they get relogged, so each subsequent transaction is writing more
+metadata into the log.
+Another feature of the XFS transaction subsystem is that most transactions are
+asynchronous. That is, they don't commit to disk until either a log buffer is
+filled (a log buffer can hold multiple transactions) or a synchronous operation
+forces the log buffers holding the transactions to disk. This means that XFS is
+doing aggregation of transactions in memory - batching them, if you like - to
+minimise the impact of the log IO on transaction throughput.
+The limitation on asynchronous transaction throughput is the number and size of
+log buffers made available by the log manager. By default there are 8 log
+buffers available and the size of each is 32kB - the size can be increased up
+to 256kB by use of a mount option.
+Effectively, this gives us the maximum bound of outstanding metadata changes
+that can be made to the filesystem at any point in time - if all the log
+buffers are full and under IO, then no more transactions can be committed until
+the current batch completes. It is now common for a single current CPU core to
+be to able to issue enough transactions to keep the log buffers full and under
+IO permanently. Hence the XFS journalling subsystem can be considered to be IO
+bound.
+Delayed Logging: Concepts
+-------------------------
+The key thing to note about the asynchronous logging combined with the
+relogging technique XFS uses is that we can be relogging changed objects
+multiple times before they are committed to disk in the log buffers. If we
+return to the previous relogging example, it is entirely possible that
+transactions A through D are committed to disk in the same log buffer.
+That is, a single log buffer may contain multiple copies of the same object,
+but only one of those copies needs to be there - the last one "D", as it
+contains all the changes from the previous changes. In other words, we have one
+necessary copy in the log buffer, and three stale copies that are simply
+wasting space. When we are doing repeated operations on the same set of
+objects, these "stale objects" can be over 90% of the space used in the log
+buffers. It is clear that reducing the number of stale objects written to the
+log would greatly reduce the amount of metadata we write to the log, and this
+is the fundamental goal of delayed logging.
+From a conceptual point of view, XFS is already doing relogging in memory (where
+memory == log buffer), only it is doing it extremely inefficiently. It is using
+logical to physical formatting to do the relogging because there is no
+infrastructure to keep track of logical changes in memory prior to physically
+formatting the changes in a transaction to the log buffer. Hence we cannot avoid
+accumulating stale objects in the log buffers.
+Delayed logging is the name we've given to keeping and tracking transactional
+changes to objects in memory outside the log buffer infrastructure. Because of
+the relogging concept fundamental to the XFS journalling subsystem, this is
+actually relatively easy to do - all the changes to logged items are already
+tracked in the current infrastructure. The big problem is how to accumulate
+them and get them to the log in a consistent, recoverable manner.
+Describing the problems and how they have been solved is the focus of this
+document.
+One of the key changes that delayed logging makes to the operation of the
+journalling subsystem is that it disassociates the amount of outstanding
+metadata changes from the size and number of log buffers available. In other
+words, instead of there only being a maximum of 2MB of transaction changes not
+written to the log at any point in time, there may be a much greater amount
+being accumulated in memory. Hence the potential for loss of metadata on a
+crash is much greater than for the existing logging mechanism.
+It should be noted that this does not change the guarantee that log recovery
+will result in a consistent filesystem. What it does mean is that as far as the
+recovered filesystem is concerned, there may be many thousands of transactions
+that simply did not occur as a result of the crash. This makes it even more
+important that applications that care about their data use fsync() where they
+need to ensure application level data integrity is maintained.
+It should be noted that delayed logging is not an innovative new concept that
+warrants rigorous proofs to determine whether it is correct or not. The method
+of accumulating changes in memory for some period before writing them to the
+log is used effectively in many filesystems including ext3 and ext4. Hence
+no time is spent in this document trying to convince the reader that the
+concept is sound. Instead it is simply considered a "solved problem" and as
+such implementing it in XFS is purely an exercise in software engineering.
+The fundamental requirements for delayed logging in XFS are simple:
+        1. Reduce the amount of metadata written to the log by at least
+           an order of magnitude.
+        2. Supply sufficient statistics to validate Requirement #1.
+        3. Supply sufficient new tracing infrastructure to be able to debug
+           problems with the new code.
+        4. No on-disk format change (metadata or log format).
+        5. Enable and disable with a mount option.
+        6. No performance regressions for synchronous transaction workloads.
+Delayed Logging: Design
+-----------------------
+Storing Changes
+The problem with accumulating changes at a logical level (i.e. just using the
+existing log item dirty region tracking) is that when it comes to writing the
+changes to the log buffers, we need to ensure that the object we are formatting
+is not changing while we do this. This requires locking the object to prevent
+concurrent modification. Hence flushing the logical changes to the log would
+require us to lock every object, format them, and then unlock them again.
+This introduces lots of scope for deadlocks with transactions that are already
+running. For example, a transaction has object A locked and modified, but needs
+the delayed logging tracking lock to commit the transaction. However, the
+flushing thread has the delayed logging tracking lock already held, and is
+trying to get the lock on object A to flush it to the log buffer. This appears
+to be an unsolvable deadlock condition, and it was solving this problem that
+was the barrier to implementing delayed logging for so long.
+The solution is relatively simple - it just took a long time to recognise it.
+Put simply, the current logging code formats the changes to each item into an
+vector array that points to the changed regions in the item. The log write code
+simply copies the memory these vectors point to into the log buffer during
+transaction commit while the item is locked in the transaction. Instead of
+using the log buffer as the destination of the formatting code, we can use an
+allocated memory buffer big enough to fit the formatted vector.
+If we then copy the vector into the memory buffer and rewrite the vector to
+point to the memory buffer rather than the object itself, we now have a copy of
+the changes in a format that is compatible with the log buffer writing code.
+that does not require us to lock the item to access. This formatting and
+rewriting can all be done while the object is locked during transaction commit,
+resulting in a vector that is transactionally consistent and can be accessed
+without needing to lock the owning item.
+Hence we avoid the need to lock items when we need to flush outstanding
+asynchronous transactions to the log. The differences between the existing
+formatting method and the delayed logging formatting can be seen in the
+diagram below.
+Current format log vector:
+Object    +---------------------------------------------+
+Vector 1      +----+
+Vector 2                    +----+
+Vector 3                                   +----------+
+After formatting:
+Log Buffer    +-V1-+-V2-+----V3----+
+Delayed logging vector:
+Object    +---------------------------------------------+
+Vector 1      +----+
+Vector 2                    +----+
+Vector 3                                   +----------+
+After formatting:
+Memory Buffer +-V1-+-V2-+----V3----+
+Vector 1      +----+
+Vector 2           +----+
+Vector 3                +----------+
+The memory buffer and associated vector need to be passed as a single object,
+but still need to be associated with the parent object so if the object is
+relogged we can replace the current memory buffer with a new memory buffer that
+contains the latest changes.
+The reason for keeping the vector around after we've formatted the memory
+buffer is to support splitting vectors across log buffer boundaries correctly.
+If we don't keep the vector around, we do not know where the region boundaries
+are in the item, so we'd need a new encapsulation method for regions in the log
+buffer writing (i.e. double encapsulation). This would be an on-disk format
+change and as such is not desirable.  It also means we'd have to write the log
+region headers in the formatting stage, which is problematic as there is per
+region state that needs to be placed into the headers during the log write.
+Hence we need to keep the vector, but by attaching the memory buffer to it and
+rewriting the vector addresses to point at the memory buffer we end up with a
+self-describing object that can be passed to the log buffer write code to be
+handled in exactly the same manner as the existing log vectors are handled.
+Hence we avoid needing a new on-disk format to handle items that have been
+relogged in memory.
+Tracking Changes
+Now that we can record transactional changes in memory in a form that allows
+them to be used without limitations, we need to be able to track and accumulate
+them so that they can be written to the log at some later point in time.  The
+log item is the natural place to store this vector and buffer, and also makes sense
+to be the object that is used to track committed objects as it will always
+exist once the object has been included in a transaction.
+The log item is already used to track the log items that have been written to
+the log but not yet written to disk. Such log items are considered "active"
+and as such are stored in the Active Item List (AIL) which is a LSN-ordered
+double linked list. Items are inserted into this list during log buffer IO
+completion, after which they are unpinned and can be written to disk. An object
+that is in the AIL can be relogged, which causes the object to be pinned again
+and then moved forward in the AIL when the log buffer IO completes for that
+transaction.
+Essentially, this shows that an item that is in the AIL can still be modified
+and relogged, so any tracking must be separate to the AIL infrastructure. As
+such, we cannot reuse the AIL list pointers for tracking committed items, nor
+can we store state in any field that is protected by the AIL lock. Hence the
+committed item tracking needs it's own locks, lists and state fields in the log
+item.
+Similar to the AIL, tracking of committed items is done through a new list
+called the Committed Item List (CIL).  The list tracks log items that have been
+committed and have formatted memory buffers attached to them. It tracks objects
+in transaction commit order, so when an object is relogged it is removed from
+it's place in the list and re-inserted at the tail. This is entirely arbitrary
+and done to make it easy for debugging - the last items in the list are the
+ones that are most recently modified. Ordering of the CIL is not necessary for
+transactional integrity (as discussed in the next section) so the ordering is
+done for convenience/sanity of the developers.
+Delayed Logging: Checkpoints
+When we have a log synchronisation event, commonly known as a "log force",
+all the items in the CIL must be written into the log via the log buffers.
+We need to write these items in the order that they exist in the CIL, and they
+need to be written as an atomic transaction. The need for all the objects to be
+written as an atomic transaction comes from the requirements of relogging and
+log replay - all the changes in all the objects in a given transaction must
+either be completely replayed during log recovery, or not replayed at all. If
+a transaction is not replayed because it is not complete in the log, then
+no later transactions should be replayed, either.
+To fulfill this requirement, we need to write the entire CIL in a single log
+transaction. Fortunately, the XFS log code has no fixed limit on the size of a
+transaction, nor does the log replay code. The only fundamental limit is that
+the transaction cannot be larger than just under half the size of the log.  The
+reason for this limit is that to find the head and tail of the log, there must
+be at least one complete transaction in the log at any given time. If a
+transaction is larger than half the log, then there is the possibility that a
+crash during the write of a such a transaction could partially overwrite the
+only complete previous transaction in the log. This will result in a recovery
+failure and an inconsistent filesystem and hence we must enforce the maximum
+size of a checkpoint to be slightly less than a half the log.
+Apart from this size requirement, a checkpoint transaction looks no different
+to any other transaction - it contains a transaction header, a series of
+formatted log items and a commit record at the tail. From a recovery
+perspective, the checkpoint transaction is also no different - just a lot
+bigger with a lot more items in it. The worst case effect of this is that we
+might need to tune the recovery transaction object hash size.
+Because the checkpoint is just another transaction and all the changes to log
+items are stored as log vectors, we can use the existing log buffer writing
+code to write the changes into the log. To do this efficiently, we need to
+minimise the time we hold the CIL locked while writing the checkpoint
+transaction. The current log write code enables us to do this easily with the
+way it separates the writing of the transaction contents (the log vectors) from
+the transaction commit record, but tracking this requires us to have a
+per-checkpoint context that travels through the log write process through to
+checkpoint completion.
+Hence a checkpoint has a context that tracks the state of the current
+checkpoint from initiation to checkpoint completion. A new context is initiated
+at the same time a checkpoint transaction is started. That is, when we remove
+all the current items from the CIL during a checkpoint operation, we move all
+those changes into the current checkpoint context. We then initialise a new
+context and attach that to the CIL for aggregation of new transactions.
+This allows us to unlock the CIL immediately after transfer of all the
+committed items and effectively allow new transactions to be issued while we
+are formatting the checkpoint into the log. It also allows concurrent
+checkpoints to be written into the log buffers in the case of log force heavy
+workloads, just like the existing transaction commit code does. This, however,
+requires that we strictly order the commit records in the log so that
+checkpoint sequence order is maintained during log replay.
+To ensure that we can be writing an item into a checkpoint transaction at
+the same time another transaction modifies the item and inserts the log item
+into the new CIL, then checkpoint transaction commit code cannot use log items
+to store the list of log vectors that need to be written into the transaction.
+Hence log vectors need to be able to be chained together to allow them to be
+detatched from the log items. That is, when the CIL is flushed the memory
+buffer and log vector attached to each log item needs to be attached to the
+checkpoint context so that the log item can be released. In diagrammatic form,
+the CIL would look like this before the flush:
+        CIL Head
+           |
+           V
+        Log Item <-> log vector 1       -> memory buffer
+           |                            -> vector array
+           V
+        Log Item <-> log vector 2       -> memory buffer
+           |                            -> vector array
+           V
+        ......
+           |
+           V
+        Log Item <-> log vector N-1     -> memory buffer
+           |                            -> vector array
+           V
+        Log Item <-> log vector N       -> memory buffer
+                                        -> vector array
+And after the flush the CIL head is empty, and the checkpoint context log
+vector list would look like:
+        Checkpoint Context
+           |
+           V
+        log vector 1    -> memory buffer
+           |            -> vector array
+           |            -> Log Item
+           V
+        log vector 2    -> memory buffer
+           |            -> vector array
+           |            -> Log Item
+           V
+        ......
+           |
+           V
+        log vector N-1  -> memory buffer
+           |            -> vector array
+           |            -> Log Item
+           V
+        log vector N    -> memory buffer
+                        -> vector array
+                        -> Log Item
+Once this transfer is done, the CIL can be unlocked and new transactions can
+start, while the checkpoint flush code works over the log vector chain to
+commit the checkpoint.
+Once the checkpoint is written into the log buffers, the checkpoint context is
+attached to the log buffer that the commit record was written to along with a
+completion callback. Log IO completion will call that callback, which can then
+run transaction committed processing for the log items (i.e. insert into AIL
+and unpin) in the log vector chain and then free the log vector chain and
+checkpoint context.
+Discussion Point: I am uncertain as to whether the log item is the most
+efficient way to track vectors, even though it seems like the natural way to do
+it. The fact that we walk the log items (in the CIL) just to chain the log
+vectors and break the link between the log item and the log vector means that
+we take a cache line hit for the log item list modification, then another for
+the log vector chaining. If we track by the log vectors, then we only need to
+break the link between the log item and the log vector, which means we should
+dirty only the log item cachelines. Normally I wouldn't be concerned about one
+vs two dirty cachelines except for the fact I've seen upwards of 80,000 log
+vectors in one checkpoint transaction. I'd guess this is a "measure and
+compare" situation that can be done after a working and reviewed implementation
+is in the dev tree....
+Delayed Logging: Checkpoint Sequencing
+One of the key aspects of the XFS transaction subsystem is that it tags
+committed transactions with the log sequence number of the transaction commit.
+This allows transactions to be issued asynchronously even though there may be
+future operations that cannot be completed until that transaction is fully
+committed to the log. In the rare case that a dependent operation occurs (e.g.
+re-using a freed metadata extent for a data extent), a special, optimised log
+force can be issued to force the dependent transaction to disk immediately.
+To do this, transactions need to record the LSN of the commit record of the
+transaction. This LSN comes directly from the log buffer the transaction is
+written into. While this works just fine for the existing transaction
+mechanism, it does not work for delayed logging because transactions are not
+written directly into the log buffers. Hence some other method of sequencing
+transactions is required.
+As discussed in the checkpoint section, delayed logging uses per-checkpoint
+contexts, and as such it is simple to assign a sequence number to each
+checkpoint. Because the switching of checkpoint contexts must be done
+atomically, it is simple to ensure that each new context has a monotonically
+increasing sequence number assigned to it without the need for an external
+atomic counter - we can just take the current context sequence number and add
+one to it for the new context.
+Then, instead of assigning a log buffer LSN to the transaction commit LSN
+during the commit, we can assign the current checkpoint sequence. This allows
+operations that track transactions that have not yet completed know what
+checkpoint sequence needs to be committed before they can continue. As a
+result, the code that forces the log to a specific LSN now needs to ensure that
+the log forces to a specific checkpoint.
+To ensure that we can do this, we need to track all the checkpoint contexts
+that are currently committing to the log. When we flush a checkpoint, the
+context gets added to a "committing" list which can be searched. When a
+checkpoint commit completes, it is removed from the committing list. Because
+the checkpoint context records the LSN of the commit record for the checkpoint,
+we can also wait on the log buffer that contains the commit record, thereby
+using the existing log force mechanisms to execute synchronous forces.
+It should be noted that the synchronous forces may need to be extended with
+mitigation algorithms similar to the current log buffer code to allow
+aggregation of multiple synchronous transactions if there are already
+synchronous transactions being flushed. Investigation of the performance of the
+current design is needed before making any decisions here.
+The main concern with log forces is to ensure that all the previous checkpoints
+are also committed to disk before the one we need to wait for. Therefore we
+need to check that all the prior contexts in the committing list are also
+complete before waiting on the one we need to complete. We do this
+synchronisation in the log force code so that we don't need to wait anywhere
+else for such serialisation - it only matters when we do a log force.
+The only remaining complexity is that a log force now also has to handle the
+case where the forcing sequence number is the same as the current context. That
+is, we need to flush the CIL and potentially wait for it to complete. This is a
+simple addition to the existing log forcing code to check the sequence numbers
+and push if required. Indeed, placing the current sequence checkpoint flush in
+the log force code enables the current mechanism for issuing synchronous
+transactions to remain untouched (i.e. commit an asynchronous transaction, then
+force the log at the LSN of that transaction) and so the higher level code
+behaves the same regardless of whether delayed logging is being used or not.
+Delayed Logging: Checkpoint Log Space Accounting
+The big issue for a checkpoint transaction is the log space reservation for the
+transaction. We don't know how big a checkpoint transaction is going to be
+ahead of time, nor how many log buffers it will take to write out, nor the
+number of split log vector regions are going to be used. We can track the
+amount of log space required as we add items to the commit item list, but we
+still need to reserve the space in the log for the checkpoint.
+A typical transaction reserves enough space in the log for the worst case space
+usage of the transaction. The reservation accounts for log record headers,
+transaction and region headers, headers for split regions, buffer tail padding,
+etc. as well as the actual space for all the changed metadata in the
+transaction. While some of this is fixed overhead, much of it is dependent on
+the size of the transaction and the number of regions being logged (the number
+of log vectors in the transaction).
+An example of the differences would be logging directory changes versus logging
+inode changes. If you modify lots of inode cores (e.g. chmod -R g+w *), then
+there are lots of transactions that only contain an inode core and an inode log
+format structure. That is, two vectors totaling roughly 150 bytes. If we modify
+10,000 inodes, we have about 1.5MB of metadata to write in 20,000 vectors. Each
+vector is 12 bytes, so the total to be logged is approximately 1.75MB. In
+comparison, if we are logging full directory buffers, they are typically 4KB
+each, so we in 1.5MB of directory buffers we'd have roughly 400 buffers and a
+buffer format structure for each buffer - roughly 800 vectors or 1.51MB total
+space.  From this, it should be obvious that a static log space reservation is
+not particularly flexible and is difficult to select the "optimal value" for
+all workloads.
+Further, if we are going to use a static reservation, which bit of the entire
+reservation does it cover? We account for space used by the transaction
+reservation by tracking the space currently used by the object in the CIL and
+then calculating the increase or decrease in space used as the object is
+relogged. This allows for a checkpoint reservation to only have to account for
+log buffer metadata used such as log header records.
+However, even using a static reservation for just the log metadata is
+problematic. Typically log record headers use at least 16KB of log space per
+1MB of log space consumed (512 bytes per 32k) and the reservation needs to be
+large enough to handle arbitrary sized checkpoint transactions. This
+reservation needs to be made before the checkpoint is started, and we need to
+be able to reserve the space without sleeping.  For a 8MB checkpoint, we need a
+reservation of around 150KB, which is a non-trivial amount of space.
+A static reservation needs to manipulate the log grant counters - we can take a
+permanent reservation on the space, but we still need to make sure we refresh
+the write reservation (the actual space available to the transaction) after
+every checkpoint transaction completion. Unfortunately, if this space is not
+available when required, then the regrant code will sleep waiting for it.
+The problem with this is that it can lead to deadlocks as we may need to commit
+checkpoints to be able to free up log space (refer back to the description of
+rolling transactions for an example of this).  Hence we *must* always have
+space available in the log if we are to use static reservations, and that is
+very difficult and complex to arrange. It is possible to do, but there is a
+simpler way.
+The simpler way of doing this is tracking the entire log space used by the
+items in the CIL and using this to dynamically calculate the amount of log
+space required by the log metadata. If this log metadata space changes as a
+result of a transaction commit inserting a new memory buffer into the CIL, then
+the difference in space required is removed from the transaction that causes
+the change. Transactions at this level will *always* have enough space
+available in their reservation for this as they have already reserved the
+maximal amount of log metadata space they require, and such a delta reservation
+will always be less than or equal to the maximal amount in the reservation.
+Hence we can grow the checkpoint transaction reservation dynamically as items
+are added to the CIL and avoid the need for reserving and regranting log space
+up front. This avoids deadlocks and removes a blocking point from the
+checkpoint flush code.
+As mentioned early, transactions can't grow to more than half the size of the
+log. Hence as part of the reservation growing, we need to also check the size
+of the reservation against the maximum allowed transaction size. If we reach
+the maximum threshold, we need to push the CIL to the log. This is effectively
+a "background flush" and is done on demand. This is identical to
+a CIL push triggered by a log force, only that there is no waiting for the
+checkpoint commit to complete. This background push is checked and executed by
+transaction commit code.
+If the transaction subsystem goes idle while we still have items in the CIL,
+they will be flushed by the periodic log force issued by the xfssyncd. This log
+force will push the CIL to disk, and if the transaction subsystem stays idle,
+allow the idle log to be covered (effectively marked clean) in exactly the same
+manner that is done for the existing logging method. A discussion point is
+whether this log force needs to be done more frequently than the current rate
+which is once every 30s.
+Delayed Logging: Log Item Pinning
+Currently log items are pinned during transaction commit while the items are
+still locked. This happens just after the items are formatted, though it could
+be done any time before the items are unlocked. The result of this mechanism is
+that items get pinned once for every transaction that is committed to the log
+buffers. Hence items that are relogged in the log buffers will have a pin count
+for every outstanding transaction they were dirtied in. When each of these
+transactions is completed, they will unpin the item once. As a result, the item
+only becomes unpinned when all the transactions complete and there are no
+pending transactions. Thus the pinning and unpinning of a log item is symmetric
+as there is a 1:1 relationship with transaction commit and log item completion.
+For delayed logging, however, we have an assymetric transaction commit to
+completion relationship. Every time an object is relogged in the CIL it goes
+through the commit process without a corresponding completion being registered.
+That is, we now have a many-to-one relationship between transaction commit and
+log item completion. The result of this is that pinning and unpinning of the
+log items becomes unbalanced if we retain the "pin on transaction commit, unpin
+on transaction completion" model.
+To keep pin/unpin symmetry, the algorithm needs to change to a "pin on
+insertion into the CIL, unpin on checkpoint completion". In other words, the
+pinning and unpinning becomes symmetric around a checkpoint context. We have to
+pin the object the first time it is inserted into the CIL - if it is already in
+the CIL during a transaction commit, then we do not pin it again. Because there
+can be multiple outstanding checkpoint contexts, we can still see elevated pin
+counts, but as each checkpoint completes the pin count will retain the correct
+value according to it's context.
+Just to make matters more slightly more complex, this checkpoint level context
+for the pin count means that the pinning of an item must take place under the
+CIL commit/flush lock. If we pin the object outside this lock, we cannot
+guarantee which context the pin count is associated with. This is because of
+the fact pinning the item is dependent on whether the item is present in the
+current CIL or not. If we don't pin the CIL first before we check and pin the
+object, we have a race with CIL being flushed between the check and the pin
+(or not pinning, as the case may be). Hence we must hold the CIL flush/commit
+lock to guarantee that we pin the items correctly.
+Delayed Logging: Concurrent Scalability
+A fundamental requirement for the CIL is that accesses through transaction
+commits must scale to many concurrent commits. The current transaction commit
+code does not break down even when there are transactions coming from 2048
+processors at once. The current transaction code does not go any faster than if
+there was only one CPU using it, but it does not slow down either.
+As a result, the delayed logging transaction commit code needs to be designed
+for concurrency from the ground up. It is obvious that there are serialisation
+points in the design - the three important ones are:
+        1. Locking out new transaction commits while flushing the CIL
+        2. Adding items to the CIL and updating item space accounting
+        3. Checkpoint commit ordering
+Looking at the transaction commit and CIL flushing interactions, it is clear
+that we have a many-to-one interaction here. That is, the only restriction on
+the number of concurrent transactions that can be trying to commit at once is
+the amount of space available in the log for their reservations. The practical
+limit here is in the order of several hundred concurrent transactions for a
+128MB log, which means that it is generally one per CPU in a machine.
+The amount of time a transaction commit needs to hold out a flush is a
+relatively long period of time - the pinning of log items needs to be done
+while we are holding out a CIL flush, so at the moment that means it is held
+across the formatting of the objects into memory buffers (i.e. while memcpy()s
+are in progress). Ultimately a two pass algorithm where the formatting is done
+separately to the pinning of objects could be used to reduce the hold time of
+the transaction commit side.
+Because of the number of potential transaction commit side holders, the lock
+really needs to be a sleeping lock - if the CIL flush takes the lock, we do not
+want every other CPU in the machine spinning on the CIL lock. Given that
+flushing the CIL could involve walking a list of tens of thousands of log
+items, it will get held for a significant time and so spin contention is a
+significant concern. Preventing lots of CPUs spinning doing nothing is the
+main reason for choosing a sleeping lock even though nothing in either the
+transaction commit or CIL flush side sleeps with the lock held.
+It should also be noted that CIL flushing is also a relatively rare operation
+compared to transaction commit for asynchronous transaction workloads - only
+time will tell if using a read-write semaphore for exclusion will limit
+transaction commit concurrency due to cache line bouncing of the lock on the
+read side.
+The second serialisation point is on the transaction commit side where items
+are inserted into the CIL. Because transactions can enter this code
+concurrently, the CIL needs to be protected separately from the above
+commit/flush exclusion. It also needs to be an exclusive lock but it is only
+held for a very short time and so a spin lock is appropriate here. It is
+possible that this lock will become a contention point, but given the short
+hold time once per transaction I think that contention is unlikely.
+The final serialisation point is the checkpoint commit record ordering code
+that is run as part of the checkpoint commit and log force sequencing. The code
+path that triggers a CIL flush (i.e. whatever triggers the log force) will enter
+an ordering loop after writing all the log vectors into the log buffers but
+before writing the commit record. This loop walks the list of committing
+checkpoints and needs to block waiting for checkpoints to complete their commit
+record write. As a result it needs a lock and a wait variable. Log force
+sequencing also requires the same lock, list walk, and blocking mechanism to
+ensure completion of checkpoints.
+These two sequencing operations can use the mechanism even though the
+events they are waiting for are different. The checkpoint commit record
+sequencing needs to wait until checkpoint contexts contain a commit LSN
+(obtained through completion of a commit record write) while log force
+sequencing needs to wait until previous checkpoint contexts are removed from
+the committing list (i.e. they've completed). A simple wait variable and
+broadcast wakeups (thundering herds) has been used to implement these two
+serialisation queues. They use the same lock as the CIL, too. If we see too
+much contention on the CIL lock, or too many context switches as a result of
+the broadcast wakeups these operations can be put under a new spinlock and
+given separate wait lists to reduce lock contention and the number of processes
+woken by the wrong event.
+Lifecycle Changes
+The existing log item life cycle is as follows:
+        1. Transaction allocate
+        2. Transaction reserve
+        3. Lock item
+        4. Join item to transaction
+                If not already attached,
+                        Allocate log item
+                        Attach log item to owner item
+                Attach log item to transaction
+        5. Modify item
+                Record modifications in log item
+        6. Transaction commit
+                Pin item in memory
+                Format item into log buffer
+                Write commit LSN into transaction
+                Unlock item
+                Attach transaction to log buffer
+        <log buffer IO dispatched>
+        <log buffer IO completes>
+        7. Transaction completion
+                Mark log item committed
+                Insert log item into AIL
+                        Write commit LSN into log item
+                Unpin log item
+        8. AIL traversal
+                Lock item
+                Mark log item clean
+                Flush item to disk
+        <item IO completion>
+        9. Log item removed from AIL
+                Moves log tail
+                Item unlocked
+Essentially, steps 1-6 operate independently from step 7, which is also
+independent of steps 8-9. An item can be locked in steps 1-6 or steps 8-9
+at the same time step 7 is occurring, but only steps 1-6 or 8-9 can occur
+at the same time. If the log item is in the AIL or between steps 6 and 7
+and steps 1-6 are re-entered, then the item is relogged. Only when steps 8-9
+are entered and completed is the object considered clean.
+With delayed logging, there are new steps inserted into the life cycle:
+        1. Transaction allocate
+        2. Transaction reserve
+        3. Lock item
+        4. Join item to transaction
+                If not already attached,
+                        Allocate log item
+                        Attach log item to owner item
+                Attach log item to transaction
+        5. Modify item
+                Record modifications in log item
+        6. Transaction commit
+                Pin item in memory if not pinned in CIL
+                Format item into log vector + buffer
+                Attach log vector and buffer to log item
+                Insert log item into CIL
+                Write CIL context sequence into transaction
+                Unlock item
+        <next log force>
+        7. CIL push
+                lock CIL flush
+                Chain log vectors and buffers together
+                Remove items from CIL
+                unlock CIL flush
+                write log vectors into log
+                sequence commit records
+                attach checkpoint context to log buffer
+        <log buffer IO dispatched>
+        <log buffer IO completes>
+        8. Checkpoint completion
+                Mark log item committed
+                Insert item into AIL
+                        Write commit LSN into log item
+                Unpin log item
+        9. AIL traversal
+                Lock item
+                Mark log item clean
+                Flush item to disk
+        <item IO completion>
+        10. Log item removed from AIL
+                Moves log tail
+                Item unlocked
+From this, it can be seen that the only life cycle differences between the two
+logging methods are in the middle of the life cycle - they still have the same
+beginning and end and execution constraints. The only differences are in the
+commiting of the log items to the log itself and the completion processing.
+Hence delayed logging should not introduce any constraints on log item
+behaviour, allocation or freeing that don't already exist.
+As a result of this zero-impact "insertion" of delayed logging infrastructure
+and the design of the internal structures to avoid on disk format changes, we
+can basically switch between delayed logging and the existing mechanism with a
+mount option. Fundamentally, there is no reason why the log manager would not
+be able to swap methods automatically and transparently depending on load
+characteristics, but this should not be necessary if delayed logging works as
+designed.
+Roadmap:
+2.6.35 Inclusion in mainline as an experimental mount option
+        => approximately 2-3 months to merge window
+        => needs to be in xfs-dev tree in 4-6 weeks
+        => code is nearing readiness for review
+2.6.37 Remove experimental tag from mount option
+        => should be roughly 6 months after initial merge
+        => enough time to:
+                => gain confidence and fix problems reported by early
+                   adopters (a.k.a. guinea pigs)
+                => address worst performance regressions and undesired
+                   behaviours
+                => start tuning/optimising code for parallelism
+                => start tuning/optimising algorithms consuming
+                   excessive CPU time
+2.6.39 Switch default mount option to use delayed logging
+        => should be roughly 12 months after initial merge
+        => enough time to shake out remaining problems before next round of
+           enterprise distro kernel rebases
diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt
index 1866c27eec69..c2c6e9b39bbe 100644
--- a/Documentation/gpio.txt
+++ b/Documentation/gpio.txt
@@ -253,6 +253,70 @@ pin setup (e.g. controlling which pin the GPIO uses, pullup/pulldown).
 Also note that it's your responsibility to have stopped using a GPIO
 before you free it.
+Considering in most cases GPIOs are actually configured right after they
+are claimed, three additional calls are defined:
+        /* request a single GPIO, with initial configuration specified by
+         * 'flags', identical to gpio_request() wrt other arguments and
+         * return value
+         */
+        int gpio_request_one(unsigned gpio, unsigned long flags, const char *label);
+        /* request multiple GPIOs in a single call
+         */
+        int gpio_request_array(struct gpio *array, size_t num);
+        /* release multiple GPIOs in a single call
+         */
+        void gpio_free_array(struct gpio *array, size_t num);
+where 'flags' is currently defined to specify the following properties:
+        * GPIOF_DIR_IN          - to configure direction as input
+        * GPIOF_DIR_OUT         - to configure direction as output
+        * GPIOF_INIT_LOW        - as output, set initial level to LOW
+        * GPIOF_INIT_HIGH       - as output, set initial level to HIGH
+since GPIOF_INIT_* are only valid when configured as output, so group valid
+combinations as:
+        * GPIOF_IN              - configure as input
+        * GPIOF_OUT_INIT_LOW    - configured as output, initial level LOW
+        * GPIOF_OUT_INIT_HIGH   - configured as output, initial level HIGH
+In the future, these flags can be extended to support more properties such
+as open-drain status.
+Further more, to ease the claim/release of multiple GPIOs, 'struct gpio' is
+introduced to encapsulate all three fields as:
+        struct gpio {
+                unsigned        gpio;
+                unsigned long   flags;
+                const char      *label;
+        };
+A typical example of usage:
+        static struct gpio leds_gpios[] = {
+                { 32, GPIOF_OUT_INIT_HIGH, "Power LED" }, /* default to ON */
+                { 33, GPIOF_OUT_INIT_LOW,  "Green LED" }, /* default to OFF */
+                { 34, GPIOF_OUT_INIT_LOW,  "Red LED"   }, /* default to OFF */
+                { 35, GPIOF_OUT_INIT_LOW,  "Blue LED"  }, /* default to OFF */
+                { ... },
+        };
+        err = gpio_request_one(31, GPIOF_IN, "Reset Button");
+        if (err)
+                ...
+        err = gpio_request_array(leds_gpios, ARRAY_SIZE(leds_gpios));
+        if (err)
+                ...
+        gpio_free_array(leds_gpios, ARRAY_SIZE(leds_gpios));
 GPIOs mapped to IRQs
 --------------------
diff --git a/Documentation/hwmon/abituguru b/Documentation/hwmon/abituguru
index 87ffa0f5ec70..5eb3b9d5f0d5 100644
--- a/Documentation/hwmon/abituguru
+++ b/Documentation/hwmon/abituguru
@@ -30,7 +30,7 @@ Supported chips:
           bank1_types=1,1,0,0,0,0,0,2,0,0,0,0,2,0,0,1
           You may also need to specify the fan_sensors option for these boards
           fan_sensors=5
-        2) There is a seperate abituguru3 driver for these motherboards,
+        2) There is a separate abituguru3 driver for these motherboards,
           the abituguru (without the 3 !) driver will not work on these
           motherboards (and visa versa)!
diff --git a/Documentation/hwmon/adt7411 b/Documentation/hwmon/adt7411
new file mode 100644
index 000000000000..1632960f9745
--- /dev/null
+++ b/Documentation/hwmon/adt7411
@@ -0,0 +1,42 @@
+Kernel driver adt7411
+=====================
+Supported chips:
+  * Analog Devices ADT7411
+    Prefix: 'adt7411'
+    Addresses scanned: 0x48, 0x4a, 0x4b
+    Datasheet: Publicly available at the Analog Devices website
+Author: Wolfram Sang (based on adt7470 by Darrick J. Wong)
+Description
+-----------
+This driver implements support for the Analog Devices ADT7411 chip. There may
+be other chips that implement this interface.
+The ADT7411 can use an I2C/SMBus compatible 2-wire interface or an
+SPI-compatible 4-wire interface. It provides a 10-bit analog to digital
+converter which measures 1 temperature, vdd and 8 input voltages. It has an
+internal temperature sensor, but an external one can also be connected (one
+loses 2 inputs then). There are high- and low-limit registers for all inputs.
+Check the datasheet for details.
+sysfs-Interface
+---------------
+in0_input       - vdd voltage input
+in[1-8]_input   - analog 1-8 input
+temp1_input     - temperature input
+Besides standard interfaces, this driver adds (0 = off, 1 = on):
+  adc_ref_vdd   - Use vdd as reference instead of 2.25 V
+  fast_sampling - Sample at 22.5 kHz instead of 1.4 kHz, but drop filters
+  no_average    - Turn off averaging over 16 samples
+Notes
+-----
+SPI, external temperature sensor and limit registers are not supported yet.
diff --git a/Documentation/hwmon/adt7473 b/Documentation/hwmon/adt7473
deleted file mode 100644
index 446612bd1fb9..000000000000
--- a/Documentation/hwmon/adt7473
+++ /dev/null
@@ -1,74 +0,0 @@
-Kernel driver adt7473
-======================
-Supported chips:
-  * Analog Devices ADT7473
-    Prefix: 'adt7473'
-    Addresses scanned: I2C 0x2C, 0x2D, 0x2E
-    Datasheet: Publicly available at the Analog Devices website
-Author: Darrick J. Wong
-This driver is depreacted, please use the adt7475 driver instead.
-Description
-----------
-This driver implements support for the Analog Devices ADT7473 chip family.
-The ADT7473 uses the 2-wire interface compatible with the SMBUS 2.0
-specification. Using an analog to digital converter it measures three (3)
-temperatures and two (2) voltages. It has four (4) 16-bit counters for
-measuring fan speed. There are three (3) PWM outputs that can be used
-to control fan speed.
-A sophisticated control system for the PWM outputs is designed into the
-ADT7473 that allows fan speed to be adjusted automatically based on any of the
-three temperature sensors. Each PWM output is individually adjustable and
-programmable. Once configured, the ADT7473 will adjust the PWM outputs in
-response to the measured temperatures without further host intervention.
-This feature can also be disabled for manual control of the PWM's.
-Each of the measured inputs (voltage, temperature, fan speed) has
-corresponding high/low limit values. The ADT7473 will signal an ALARM if
-any measured value exceeds either limit.
-The ADT7473 samples all inputs continuously. The driver will not read
-the registers more often than once every other second. Further,
-configuration data is only read once per minute.
-Special Features
----------------
-The ADT7473 have a 10-bit ADC and can therefore measure temperatures
-with 0.25 degC resolution. Temperature readings can be configured either
-for twos complement format or "Offset 64" format, wherein 63 is subtracted
-from the raw value to get the temperature value.
-The Analog Devices datasheet is very detailed and describes a procedure for
-determining an optimal configuration for the automatic PWM control.
-Configuration Notes
-------------------
-Besides standard interfaces driver adds the following:
-* PWM Control
-* pwm#_auto_point1_pwm and temp#_auto_point1_temp and
-* pwm#_auto_point2_pwm and temp#_auto_point2_temp -
-point1: Set the pwm speed at a lower temperature bound.
-point2: Set the pwm speed at a higher temperature bound.
-The ADT7473 will scale the pwm between the lower and higher pwm speed when
-the temperature is between the two temperature boundaries.  PWM values range
-from 0 (off) to 255 (full speed).  Fan speed will be set to maximum when the
-temperature sensor associated with the PWM control exceeds temp#_max.
-Notes
-----
-The NVIDIA binary driver presents an ADT7473 chip via an on-card i2c bus.
-Unfortunately, they fail to set the i2c adapter class, so this driver may
-fail to find the chip until the nvidia driver is patched.
diff --git a/Documentation/hwmon/asc7621 b/Documentation/hwmon/asc7621
new file mode 100644
index 000000000000..7287be7e1f21
--- /dev/null
+++ b/Documentation/hwmon/asc7621
@@ -0,0 +1,296 @@
+Kernel driver asc7621
+==================
+Supported chips:
+    Andigilog aSC7621 and aSC7621a
+    Prefix: 'asc7621'
+    Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+    Datasheet: http://www.fairview5.com/linux/asc7621/asc7621.pdf
+Author:
+                George Joseph
+Description provided by Dave Pivin @ Andigilog:
+Andigilog has both the PECI and pre-PECI versions of the Heceta-6, as
+Intel calls them. Heceta-6e has high frequency PWM and Heceta-6p has
+added PECI and a 4th thermal zone. The Andigilog aSC7611 is the
+Heceta-6e part and aSC7621 is the Heceta-6p part. They are both in
+volume production, shipping to Intel and their subs.
+We have enhanced both parts relative to the governing Intel
+specification. First enhancement is temperature reading resolution. We
+have used registers below 20h for vendor-specific functions in addition
+to those in the Intel-specified vendor range.
+Our conversion process produces a result that is reported as two bytes.
+The fan speed control uses this finer value to produce a "step-less" fan
+PWM output. These two bytes are "read-locked" to guarantee that once a
+high or low byte is read, the other byte is locked-in until after the
+next read of any register. So to get an atomic reading, read high or low
+byte, then the very next read should be the opposite byte. Our data
+sheet says 10-bits of resolution, although you may find the lower bits
+are active, they are not necessarily reliable or useful externally. We
+chose not to mask them.
+We employ significant filtering that is user tunable as described in the
+data sheet. Our temperature reports and fan PWM outputs are very smooth
+when compared to the competition, in addition to the higher resolution
+temperature reports. The smoother PWM output does not require user
+intervention.
+We offer GPIO features on the former VID pins. These are open-drain
+outputs or inputs and may be used as general purpose I/O or as alarm
+outputs that are based on temperature limits. These are in 19h and 1Ah.
+We offer flexible mapping of temperature readings to thermal zones. Any
+temperature may be mapped to any zone, which has a default assignment
+that follows Intel's specs.
+Since there is a fan to zone assignment that allows for the "hotter" of
+a set of zones to control the PWM of an individual fan, but there is no
+indication to the user, we have added an indicator that shows which zone
+is currently controlling the PWM for a given fan. This is in register
+00h.
+Both remote diode temperature readings may be given an offset value such
+that the reported reading as well as the temperature used to determine
+PWM may be offset for system calibration purposes.
+PECI Extended configuration allows for having more than two domains per
+PECI address and also provides an enabling function for each PECI
+address. One could use our flexible zone assignment to have a zone
+assigned to up to 4 PECI addresses. This is not possible in the default
+Intel configuration. This would be useful in multi-CPU systems with
+individual fans on each that would benefit from individual fan control.
+This is in register 0Eh.
+The tachometer measurement system is flexible and able to adapt to many
+fan types. We can also support pulse-stretched PWM so that 3-wire fans
+may be used. These characteristics are in registers 04h to 07h.
+Finally, we have added a tach disable function that turns off the tach
+measurement system for individual tachs in order to save power. That is
+in register 75h.
+--
+aSC7621 Product Description
+The aSC7621 has a two wire digital interface compatible with SMBus 2.0.
+Using a 10-bit ADC, the aSC7621 measures the temperature of two remote diode
+connected transistors as well as its own die. Support for Platform
+Environmental Control Interface (PECI) is included.
+Using temperature information from these four zones, an automatic fan speed
+control algorithm is employed to minimize acoustic impact while achieving
+recommended CPU temperature under varying operational loads.
+To set fan speed, the aSC7621 has three independent pulse width modulation
+(PWM) outputs that are controlled by one, or a combination of three,
+temperature zones. Both high- and low-frequency PWM ranges are supported.
+The aSC7621 also includes a digital filter that can be invoked to smooth
+temperature readings for better control of fan speed and minimum acoustic
+impact.
+The aSC7621 has tachometer inputs to measure fan speed on up to four fans.
+Limit and status registers for all measured values are included to alert
+the system host that any measurements are outside of programmed limits
+via status registers.
+System voltages of VCCP, 2.5V, 3.3V, 5.0V, and 12V motherboard power are
+monitored efficiently with internal scaling resistors.
+Features
+- Supports PECI interface and monitors internal and remote thermal diodes
+- 2-wire, SMBus 2.0 compliant, serial interface
+- 10-bit ADC
+- Monitors VCCP, 2.5V, 3.3V, 5.0V, and 12V motherboard/processor supplies
+- Programmable autonomous fan control based on temperature readings
+- Noise filtering of temperature reading for fan speed control
+- 0.25C digital temperature sensor resolution
+- 3 PWM fan speed control outputs for 2-, 3- or 4-wire fans and up to 4 fan
+        tachometer inputs
+- Enhanced measured temperature to Temperature Zone assignment.
+- Provides high and low PWM frequency ranges
+- 3 GPIO pins for custom use
+- 24-Lead QSOP package
+Configuration Notes
+===================
+Except where noted below, the sysfs entries created by this driver follow
+the standards defined in "sysfs-interface".
+temp1_source
+        0       (default) peci_legacy = 0, Remote 1 Temperature
+                        peci_legacy = 1, PECI Processor Temperature 0
+        1       Remote 1 Temperature
+        2       Remote 2 Temperature
+        3       Internal Temperature
+        4       PECI Processor Temperature 0
+        5       PECI Processor Temperature 1
+        6       PECI Processor Temperature 2
+        7  PECI Processor Temperature 3
+temp2_source
+        0       (default) Internal Temperature
+        1       Remote 1 Temperature
+        2       Remote 2 Temperature
+        3       Internal Temperature
+        4       PECI Processor Temperature 0
+        5       PECI Processor Temperature 1
+        6       PECI Processor Temperature 2
+        7       PECI Processor Temperature 3
+temp3_source
+        0       (default) Remote 2 Temperature
+        1       Remote 1 Temperature
+        2       Remote 2 Temperature
+        3       Internal Temperature
+        4       PECI Processor Temperature 0
+        5       PECI Processor Temperature 1
+        6       PECI Processor Temperature 2
+        7       PECI Processor Temperature 3
+temp4_source
+        0       (default) peci_legacy = 0, PECI Processor Temperature 0
+                        peci_legacy = 1, Remote 1 Temperature
+        1       Remote 1 Temperature
+        2       Remote 2 Temperature
+        3       Internal Temperature
+        4       PECI Processor Temperature 0
+        5       PECI Processor Temperature 1
+        6       PECI Processor Temperature 2
+        7       PECI Processor Temperature 3
+temp[1-4]_smoothing_enable
+temp[1-4]_smoothing_time
+        Smooths spikes in temp readings caused by noise.
+        Valid values in milliseconds are:
+        35000
+        17600
+        11800
+         7000
+         4400
+         3000
+         1600
+          800
+temp[1-4]_crit
+        When the corresponding zone temperature reaches this value,
+        ALL pwm outputs will got to 100%.
+temp[5-8]_input
+temp[5-8]_enable
+        The aSC7621 can also read temperatures provided by the processor
+        via the PECI bus.  Usually these are "core" temps and are relative
+        to the point where the automatic thermal control circuit starts
+        throttling.  This means that these are usually negative numbers.
+pwm[1-3]_enable
+        0               Fan off.
+        1               Fan on manual control.
+        2               Fan on automatic control and will run at the minimum pwm
+                                if the temperature for the zone is below the minimum.
+        3               Fan on automatic control but will be off if the temperature
+                                for the zone is below the minimum.
+        4-254   Ignored.
+        255             Fan on full.
+pwm[1-3]_auto_channels
+        Bitmap as described in sysctl-interface with the following
+        exceptions...
+        Only the following combination of zones (and their corresponding masks)
+        are valid:
+        1
+        2
+        3
+        2,3
+        1,2,3
+        4
+        1,2,3,4
+        Special values:
+        0                       Disabled.
+        16              Fan on manual control.
+        31              Fan on full.
+pwm[1-3]_invert
+        When set, inverts the meaning of pwm[1-3].
+        i.e.  when pwm = 0, the fan will be on full and
+        when pwm = 255 the fan will be off.
+pwm[1-3]_freq
+        PWM frequency in Hz
+        Valid values in Hz are:
+        10
+        15
+        23
+        30  (default)
+        38
+        47
+        62
+        94
+        23000
+        24000
+        25000
+        26000
+        27000
+        28000
+        29000
+        30000
+        Setting any other value will be ignored.
+peci_enable
+        Enables or disables PECI
+peci_avg
+        Input filter average time.
+        0       0 Sec. (no Smoothing) (default)
+        1       0.25 Sec.
+        2       0.5 Sec.
+        3       1.0 Sec.
+        4       2.0 Sec.
+        5       4.0 Sec.
+        6       8.0 Sec.
+        7       0.0 Sec.
+peci_legacy
+        0       Standard Mode (default)
+                Remote Diode 1 reading is associated with
+                Temperature Zone 1, PECI is associated with
+                Zone 4
+        1       Legacy Mode
+                PECI is associated with Temperature Zone 1,
+                Remote Diode 1 is associated with Zone 4
+peci_diode
+        Diode filter
+        0       0.25 Sec.
+        1       1.1 Sec.
+        2       2.4 Sec.  (default)
+        3       3.4 Sec.
+        4       5.0 Sec.
+        5       6.8 Sec.
+        6       10.2 Sec.
+        7       16.4 Sec.
+peci_4domain
+        Four domain enable
+        0       1 or 2 Domains for enabled processors (default)
+        1       3 or 4 Domains for enabled processors
+peci_domain
+        Domain
+        0       Processor contains a single domain (0)   (default)
+        1       Processor contains two domains (0,1)
diff --git a/Documentation/hwmon/it87 b/Documentation/hwmon/it87
index f9ba96c0ac4a..8d08bf0d38ed 100644
--- a/Documentation/hwmon/it87
+++ b/Documentation/hwmon/it87
@@ -5,31 +5,23 @@ Supported chips:
  * IT8705F
    Prefix: 'it87'
    Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
+    Datasheet: Once publicly available at the ITE website, but no longer
-               http://www.ite.com.tw/product_info/file/pc/IT8705F_V.0.4.1.pdf
  * IT8712F
    Prefix: 'it8712'
    Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
+    Datasheet: Once publicly available at the ITE website, but no longer
-               http://www.ite.com.tw/product_info/file/pc/IT8712F_V0.9.1.pdf
-               http://www.ite.com.tw/product_info/file/pc/Errata%20V0.1%20for%20IT8712F%20V0.9.1.pdf
-               http://www.ite.com.tw/product_info/file/pc/IT8712F_V0.9.3.pdf
  * IT8716F/IT8726F
    Prefix: 'it8716'
    Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
+    Datasheet: Once publicly available at the ITE website, but no longer
-               http://www.ite.com.tw/product_info/file/pc/IT8716F_V0.3.ZIP
-               http://www.ite.com.tw/product_info/file/pc/IT8726F_V0.3.pdf
  * IT8718F
    Prefix: 'it8718'
    Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
+    Datasheet: Once publicly available at the ITE website, but no longer
-               http://www.ite.com.tw/product_info/file/pc/IT8718F_V0.2.zip
-               http://www.ite.com.tw/product_info/file/pc/IT8718F_V0%203_(for%20C%20version).zip
  * IT8720F
    Prefix: 'it8720'
    Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Not yet publicly available.
+    Datasheet: Not publicly available
  * SiS950   [clone of IT8705F]
    Prefix: 'it87'
    Addresses scanned: from Super I/O config space (8 I/O ports)
@@ -136,6 +128,10 @@ registers are read whenever any data is read (unless it is less than 1.5
 seconds since the last update). This means that you can easily miss
 once-only alarms.
+Out-of-limit readings can also result in beeping, if the chip is properly
+wired and configured. Beeping can be enabled or disabled per sensor type
+(temperatures, voltages and fans.)
 The IT87xx only updates its values each 1.5 seconds; reading it more often
 will do no harm, but will return 'old' values.
@@ -150,11 +146,38 @@ Fan speed control
 -----------------
 The fan speed control features are limited to manual PWM mode. Automatic
-"Smart Guardian" mode control handling is not implemented. However
+"Smart Guardian" mode control handling is only implemented for older chips
-if you want to go for "manual mode" just write 1 to pwmN_enable.
+(see below.) However if you want to go for "manual mode" just write 1 to
+pwmN_enable.
 If you are only able to control the fan speed with very small PWM values,
 try lowering the PWM base frequency (pwm1_freq). Depending on the fan,
 it may give you a somewhat greater control range. The same frequency is
 used to drive all fan outputs, which is why pwm2_freq and pwm3_freq are
 read-only.
+Automatic fan speed control (old interface)
+-------------------------------------------
+The driver supports the old interface to automatic fan speed control
+which is implemented by IT8705F chips up to revision F and IT8712F
+chips up to revision G.
+This interface implements 4 temperature vs. PWM output trip points.
+The PWM output of trip point 4 is always the maximum value (fan running
+at full speed) while the PWM output of the other 3 trip points can be
+freely chosen. The temperature of all 4 trip points can be freely chosen.
+Additionally, trip point 1 has an hysteresis temperature attached, to
+prevent fast switching between fan on and off.
+The chip automatically computes the PWM output value based on the input
+temperature, based on this simple rule: if the temperature value is
+between trip point N and trip point N+1 then the PWM output value is
+the one of trip point N. The automatic control mode is less flexible
+than the manual control mode, but it reacts faster, is more robust and
+doesn't use CPU cycles.
+Trip points must be set properly before switching to automatic fan speed
+control mode. The driver will perform basic integrity checks before
+actually switching to automatic control mode.
diff --git a/Documentation/hwmon/lm85 b/Documentation/hwmon/lm85
index a13680871bc7..a76aefeeb68a 100644
--- a/Documentation/hwmon/lm85
+++ b/Documentation/hwmon/lm85
@@ -157,7 +157,7 @@ temperature configuration points:
 There are three PWM outputs. The LM85 datasheet suggests that the
 pwm3 output control both fan3 and fan4. Each PWM can be individually
-configured and assigned to a zone for it's control value. Each PWM can be
+configured and assigned to a zone for its control value. Each PWM can be
 configured individually according to the following options.
 * pwm#_auto_pwm_min - this specifies the PWM value for temp#_auto_temp_off
diff --git a/Documentation/hwmon/lm90 b/Documentation/hwmon/lm90
index 93d8e3d55150..6a03dd4bcc94 100644
--- a/Documentation/hwmon/lm90
+++ b/Documentation/hwmon/lm90
@@ -84,6 +84,10 @@ Supported chips:
    Addresses scanned: I2C 0x4c
    Datasheet: Publicly available at the Maxim website
               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3500
+  * Winbond/Nuvoton W83L771AWG/ASG
+    Prefix: 'w83l771'
+    Addresses scanned: I2C 0x4c
+    Datasheet: Not publicly available, can be requested from Nuvoton
 Author: Jean Delvare <khali@linux-fr.org>
@@ -147,6 +151,12 @@ MAX6680 and MAX6681:
  * Selectable address
  * Remote sensor type selection
+W83L771AWG/ASG
+  * The AWG and ASG variants only differ in package format.
+  * Filter and alert configuration register at 0xBF
+  * Diode ideality factor configuration (remote sensor) at 0xE3
+  * Moving average (depending on conversion rate)
 All temperature values are given in degrees Celsius. Resolution
 is 1.0 degree for the local temperature, 0.125 degree for the remote
 temperature, except for the MAX6657, MAX6658 and MAX6659 which have a
@@ -163,6 +173,18 @@ The lm90 driver will not update its values more frequently than every
 other second; reading them more often will do no harm, but will return
 'old' values.
+SMBus Alert Support
+-------------------
+This driver has basic support for SMBus alert. When an alert is received,
+the status register is read and the faulty temperature channel is logged.
+The Analog Devices chips (ADM1032 and ADT7461) do not implement the SMBus
+alert protocol properly so additional care is needed: the ALERT output is
+disabled when an alert is received, and is re-enabled only when the alarm
+is gone. Otherwise the chip would block alerts from other chips in the bus
+as long as the alarm is active.
 PEC Support
 -----------
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index 81c0c59a60ea..e307914a3eda 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -15,7 +15,8 @@ Supported adapters:
  * Intel 82801I (ICH9)
  * Intel EP80579 (Tolapai)
  * Intel 82801JI (ICH10)
-  * Intel PCH
+  * Intel 3400/5 Series (PCH)
+  * Intel Cougar Point (PCH)
   Datasheets: Publicly available at the Intel website
 Authors: 
@@ -26,7 +27,13 @@ Authors:
 Module Parameters
 -----------------
-None.
+* disable_features (bit vector)
+Disable selected features normally supported by the device. This makes it
+possible to work around possible driver or hardware bugs if the feature in
+question doesn't work as intended for whatever reason. Bit values:
+  1  disable SMBus PEC
+  2  disable the block buffer
+  8  disable the I2C block read functionality
 Description
diff --git a/Documentation/i2c/busses/i2c-parport b/Documentation/i2c/busses/i2c-parport
index dceaba1ad930..2461c7b53b2c 100644
--- a/Documentation/i2c/busses/i2c-parport
+++ b/Documentation/i2c/busses/i2c-parport
@@ -29,6 +29,9 @@ can be easily added when needed.
 Earlier kernels defaulted to type=0 (Philips).  But now, if the type
 parameter is missing, the driver will simply fail to initialize.
+SMBus alert support is available on adapters which have this line properly
+connected to the parallel port's interrupt pin.
 Building your own adapter
 -------------------------
diff --git a/Documentation/i2c/busses/i2c-parport-light b/Documentation/i2c/busses/i2c-parport-light
index 287436478520..bdc9cbb2e0f2 100644
--- a/Documentation/i2c/busses/i2c-parport-light
+++ b/Documentation/i2c/busses/i2c-parport-light
@@ -9,3 +9,14 @@ parport handling is not an option. The drawback is a reduced portability
 and the impossibility to daisy-chain other parallel port devices.                 
  
 Please see i2c-parport for documentation.
+Module parameters:
+* type: type of adapter (see i2c-parport or modinfo)
+* base: base I/O address
+  Default is 0x378 which is fairly common for parallel ports, at least on PC.
+* irq: optional IRQ
+  This must be passed if you want SMBus alert support, assuming your adapter
+  actually supports this.
diff --git a/Documentation/i2c/smbus-protocol b/Documentation/i2c/smbus-protocol
index 9df47441f0e7..7c19d1a2bea0 100644
--- a/Documentation/i2c/smbus-protocol
+++ b/Documentation/i2c/smbus-protocol
@@ -185,6 +185,22 @@ the protocol. All ARP communications use slave address 0x61 and
 require PEC checksums.
+SMBus Alert
+===========
+SMBus Alert was introduced in Revision 1.0 of the specification.
+The SMBus alert protocol allows several SMBus slave devices to share a
+single interrupt pin on the SMBus master, while still allowing the master
+to know which slave triggered the interrupt.
+This is implemented the following way in the Linux kernel:
+* I2C bus drivers which support SMBus alert should call
+  i2c_setup_smbus_alert() to setup SMBus alert support.
+* I2C drivers for devices which can trigger SMBus alerts should implement
+  the optional alert() callback.
 I2C Block Transactions
 ======================
diff --git a/Documentation/i2c/writing-clients b/Documentation/i2c/writing-clients
index 0a74603eb671..5ebf5af1d716 100644
--- a/Documentation/i2c/writing-clients
+++ b/Documentation/i2c/writing-clients
@@ -74,6 +74,11 @@ structure at all.  You should use this to keep device-specific data.
        /* retrieve the value */
        void *i2c_get_clientdata(const struct i2c_client *client);
+Note that starting with kernel 2.6.34, you don't have to set the `data' field
+to NULL in remove() or if probe() failed anymore. The i2c-core does this
+automatically on these occasions. Those are also the only times the core will
+touch this field.
 Accessing the client
 ====================
@@ -318,8 +323,9 @@ Plain I2C communication
 These routines read and write some bytes from/to a client. The client
 contains the i2c address, so you do not have to include it. The second
 parameter contains the bytes to read/write, the third the number of bytes
-to read/write (must be less than the length of the buffer.) Returned is
+to read/write (must be less than the length of the buffer, also should be
-the actual number of bytes read/written.
+less than 64k since msg.len is u16.) Returned is the actual number of bytes
+read/written.
        int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msg,
                         int num);
diff --git a/Documentation/init.txt b/Documentation/init.txt
new file mode 100644
index 000000000000..535ad5e82b98
--- /dev/null
+++ b/Documentation/init.txt
@@ -0,0 +1,49 @@
+Explaining the dreaded "No init found." boot hang message
+=========================================================
+OK, so you've got this pretty unintuitive message (currently located
+in init/main.c) and are wondering what the H*** went wrong.
+Some high-level reasons for failure (listed roughly in order of execution)
+to load the init binary are:
+A) Unable to mount root FS
+B) init binary doesn't exist on rootfs
+C) broken console device
+D) binary exists but dependencies not available
+E) binary cannot be loaded
+Detailed explanations:
+0) Set "debug" kernel parameter (in bootloader config file or CONFIG_CMDLINE)
+   to get more detailed kernel messages.
+A) make sure you have the correct root FS type
+   (and root= kernel parameter points to the correct partition),
+   required drivers such as storage hardware (such as SCSI or USB!)
+   and filesystem (ext3, jffs2 etc.) are builtin (alternatively as modules,
+   to be pre-loaded by an initrd)
+C) Possibly a conflict in console= setup --> initial console unavailable.
+   E.g. some serial consoles are unreliable due to serial IRQ issues (e.g.
+   missing interrupt-based configuration).
+   Try using a different console= device or e.g. netconsole= .
+D) e.g. required library dependencies of the init binary such as
+   /lib/ld-linux.so.2 missing or broken. Use readelf -d <INIT>|grep NEEDED
+   to find out which libraries are required.
+E) make sure the binary's architecture matches your hardware.
+   E.g. i386 vs. x86_64 mismatch, or trying to load x86 on ARM hardware.
+   In case you tried loading a non-binary file here (shell script?),
+   you should make sure that the script specifies an interpreter in its shebang
+   header line (#!/...) that is fully working (including its library
+   dependencies). And before tackling scripts, better first test a simple
+   non-script binary such as /bin/sh and confirm its successful execution.
+   To find out more, add code to init/main.c to display kernel_execve()s
+   return values.
+Please extend this explanation whenever you find new failure causes
+(after all loading the init binary is a CRITICAL and hard transition step
+which needs to be made as painless as possible), then submit patch to LKML.
+Further TODOs:
+- Implement the various run_init_process() invocations via a struct array
+  which can then store the kernel_execve() result value and on failure
+  log it all by iterating over _all_ results (very important usability fix).
+- try to make the implementation itself more helpful in general,
+  e.g. by providing additional error messages at affected places.
+Andreas Mohr <andi at lisas period de>
diff --git a/Documentation/input/elantech.txt b/Documentation/input/elantech.txt
index a10c3b6ba7c4..56941ae1f5db 100644
--- a/Documentation/input/elantech.txt
+++ b/Documentation/input/elantech.txt
@@ -333,14 +333,14 @@ byte 0:
 byte 1:
   bit   7   6   5   4   3   2   1   0
-        x15 x14 x13 x12 x11 x10 x9  x8
+         .   .   .   .   .  x10 x9  x8
 byte 2:
   bit   7   6   5   4   3   2   1   0
        x7  x6  x5  x4  x4  x2  x1  x0
-         x15..x0 = absolute x value (horizontal)
+         x10..x0 = absolute x value (horizontal)
 byte 3:
@@ -350,14 +350,14 @@ byte 3:
 byte 4:
   bit   7   6   5   4   3   2   1   0
-        y15 y14 y13 y12 y11 y10 y8  y8
+         .   .   .   .   .   .  y9  y8
 byte 5:
   bit   7   6   5   4   3   2   1   0
        y7  y6  y5  y4  y3  y2  y1  y0
-         y15..y0 = absolute y value (vertical)
+         y9..y0 = absolute y value (vertical)
 4.2.2 Two finger touch
diff --git a/Documentation/input/joystick.txt b/Documentation/input/joystick.txt
index 154d767b2acb..8007b7ca87bf 100644
--- a/Documentation/input/joystick.txt
+++ b/Documentation/input/joystick.txt
@@ -402,7 +402,7 @@ for the port of the SoundFusion is supported by the cs461x.c module.
 ~~~~~~~~~~~~~~~~~~~~~~~~
  The Live! has a special PCI gameport, which, although it doesn't provide
 any "Enhanced" stuff like 4DWave and friends, is quite a bit faster than
-it's ISA counterparts. It also requires special support, hence the
+its ISA counterparts. It also requires special support, hence the
 emu10k1-gp.c module for it instead of the normal ns558.c one.
 3.15 SoundBlaster 64 and 128 - ES1370 and ES1371, ESS Solo1 and S3 SonicVibes
diff --git a/Documentation/input/multi-touch-protocol.txt b/Documentation/input/multi-touch-protocol.txt
index 8490480ce432..c0fc1c75fd88 100644
--- a/Documentation/input/multi-touch-protocol.txt
+++ b/Documentation/input/multi-touch-protocol.txt
@@ -68,6 +68,22 @@ like:
   SYN_MT_REPORT
   SYN_REPORT
+Here is the sequence after lifting one of the fingers:
+   ABS_MT_POSITION_X
+   ABS_MT_POSITION_Y
+   SYN_MT_REPORT
+   SYN_REPORT
+And here is the sequence after lifting the remaining finger:
+   SYN_MT_REPORT
+   SYN_REPORT
+If the driver reports one of BTN_TOUCH or ABS_PRESSURE in addition to the
+ABS_MT events, the last SYN_MT_REPORT event may be omitted. Otherwise, the
+last SYN_REPORT will be dropped by the input core, resulting in no
+zero-finger event reaching userland.
 Event Semantics
 ---------------
@@ -217,11 +233,6 @@ where examples can be found.
 difference between the contact position and the approaching tool position
 could be used to derive tilt.
 [2] The list can of course be extended.
-[3] The multi-touch X driver is currently in the prototyping stage. At the
+[3] Multitouch X driver project: http://bitmath.org/code/multitouch/.
-time of writing (April 2009), the MT protocol is not yet merged, and the
-prototype implements finger matching, basic mouse support and two-finger
-scrolling. The project aims at improving the quality of current multi-touch
-functionality available in the Synaptics X driver, and in addition
-implement more advanced gestures.
 [4] See the section on event computation.
 [5] See the section on finger tracking.
diff --git a/Documentation/input/rotary-encoder.txt b/Documentation/input/rotary-encoder.txt
index 3a6aec40c0b0..8b4129de1d2d 100644
--- a/Documentation/input/rotary-encoder.txt
+++ b/Documentation/input/rotary-encoder.txt
@@ -75,7 +75,7 @@ and the number of steps or will clamp at the maximum and zero depending on
 the configuration.
 Because GPIO to IRQ mapping is platform specific, this information must
-be given in seperately to the driver. See the example below.
+be given in separately to the driver. See the example below.
 ---------<snip>---------
diff --git a/Documentation/input/sentelic.txt b/Documentation/input/sentelic.txt
index f7160a2fb6a2..b35affd5c649 100644
--- a/Documentation/input/sentelic.txt
+++ b/Documentation/input/sentelic.txt
@@ -1,5 +1,5 @@
-Copyright (C) 2002-2008 Sentelic Corporation.
+Copyright (C) 2002-2010 Sentelic Corporation.
-Last update: Oct-31-2008
+Last update: Jan-13-2010
 ==============================================================================
 * Finger Sensing Pad Intellimouse Mode(scrolling wheel, 4th and 5th buttons)
@@ -44,7 +44,7 @@ B) MSID 6: Horizontal and Vertical scrolling.
 Packet 1
   Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
 BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
-  1   |Y|X|y|x|1|M|R|L|  2  |X|X|X|X|X|X|X|X|  3 |Y|Y|Y|Y|Y|Y|Y|Y|  4 | | |B|F|l|r|u|d|
+  1   |Y|X|y|x|1|M|R|L|  2  |X|X|X|X|X|X|X|X|  3 |Y|Y|Y|Y|Y|Y|Y|Y|  4 | | |B|F|r|l|u|d|
      |---------------|     |---------------|    |---------------|    |---------------|
 Byte 1: Bit7 => Y overflow
@@ -59,15 +59,15 @@ Byte 2: X Movement(9-bit 2's complement integers)
 Byte 3: Y Movement(9-bit 2's complement integers)
 Byte 4: Bit0 => the Vertical scrolling movement downward.
        Bit1 => the Vertical scrolling movement upward.
-        Bit2 => the Vertical scrolling movement rightward.
+        Bit2 => the Horizontal scrolling movement leftward.
-        Bit3 => the Vertical scrolling movement leftward.
+        Bit3 => the Horizontal scrolling movement rightward.
        Bit4 => 1 = 4th mouse button is pressed, Forward one page.
                0 = 4th mouse button is not pressed.
        Bit5 => 1 = 5th mouse button is pressed, Backward one page.
                0 = 5th mouse button is not pressed.
 C) MSID 7:
-# FSP uses 2 packets(8 Bytes) data to represent Absolute Position
+# FSP uses 2 packets (8 Bytes) to represent Absolute Position.
  so we have PACKET NUMBER to identify packets.
  If PACKET NUMBER is 0, the packet is Packet 1.
  If PACKET NUMBER is 1, the packet is Packet 2.
@@ -129,7 +129,7 @@ Byte 3: Message Type => 0x00 (Disabled)
 Byte 4: Bit7~Bit0 => Don't Care
 ==============================================================================
-* Absolute position for STL3888-A0.
+* Absolute position for STL3888-Ax.
 ==============================================================================
 Packet 1 (ABSOLUTE POSITION)
   Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
@@ -179,14 +179,14 @@ Byte 4: Bit1~Bit0 => Y coordinate (xpos[1:0])
        Bit5~Bit4 => y2_g
        Bit7~Bit6 => x2_g
-Notify Packet for STL3888-A0
+Notify Packet for STL3888-Ax
   Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
 BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
  1   |1|0|1|P|1|M|R|L|  2  |C|C|C|C|C|C|C|C|  3 |0|0|F|F|0|0|0|i|  4 |r|l|d|u|0|0|0|0|
      |---------------|     |---------------|    |---------------|    |---------------|
 Byte 1: Bit7~Bit6 => 00, Normal data packet
-                  => 01, Absolute coordination packet
+                  => 01, Absolute coordinates packet
                  => 10, Notify packet
        Bit5 => 1
        Bit4 => when in absolute coordinates mode (valid when EN_PKT_GO is 1):
@@ -205,15 +205,106 @@ Byte 4: Bit7 => scroll right button
        Bit6 => scroll left button
        Bit5 => scroll down button
        Bit4 => scroll up button
-            * Note that if gesture and additional button (Bit4~Bit7)
+            * Note that if gesture and additional buttoni (Bit4~Bit7)
-              happen at the same time, the button information will not
+              happen at the same time, the button information will not
-              be sent.
+              be sent.
+        Bit3~Bit0 => Reserved
+Sample sequence of Multi-finger, Multi-coordinate mode:
+        notify packet (valid bit == 1), abs pkt 1, abs pkt 2, abs pkt 1,
+        abs pkt 2, ..., notify packet (valid bit == 0)
+==============================================================================
+* Absolute position for STL3888-B0.
+==============================================================================
+Packet 1(ABSOLUTE POSITION)
+   Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
+BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
+  1   |0|1|V|F|1|0|R|L|  2  |X|X|X|X|X|X|X|X|  3 |Y|Y|Y|Y|Y|Y|Y|Y|  4 |r|l|u|d|X|X|Y|Y|
+      |---------------|     |---------------|    |---------------|    |---------------|
+Byte 1: Bit7~Bit6 => 00, Normal data packet
+                  => 01, Absolute coordinates packet
+                  => 10, Notify packet
+        Bit5 => Valid bit, 0 means that the coordinate is invalid or finger up.
+                When both fingers are up, the last two reports have zero valid
+                bit.
+        Bit4 => finger up/down information. 1: finger down, 0: finger up.
+        Bit3 => 1
+        Bit2 => finger index, 0 is the first finger, 1 is the second finger.
+        Bit1 => Right Button, 1 is pressed, 0 is not pressed.
+        Bit0 => Left Button, 1 is pressed, 0 is not pressed.
+Byte 2: X coordinate (xpos[9:2])
+Byte 3: Y coordinate (ypos[9:2])
+Byte 4: Bit1~Bit0 => Y coordinate (xpos[1:0])
+        Bit3~Bit2 => X coordinate (ypos[1:0])
+        Bit4 => scroll down button
+        Bit5 => scroll up button
+        Bit6 => scroll left button
+        Bit7 => scroll right button
+Packet 2 (ABSOLUTE POSITION)
+   Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
+BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
+  1   |0|1|V|F|1|1|R|L|  2  |X|X|X|X|X|X|X|X|  3 |Y|Y|Y|Y|Y|Y|Y|Y|  4 |r|l|u|d|X|X|Y|Y|
+      |---------------|     |---------------|    |---------------|    |---------------|
+Byte 1: Bit7~Bit6 => 00, Normal data packet
+                  => 01, Absolute coordination packet
+                  => 10, Notify packet
+        Bit5 => Valid bit, 0 means that the coordinate is invalid or finger up.
+                When both fingers are up, the last two reports have zero valid
+                bit.
+        Bit4 => finger up/down information. 1: finger down, 0: finger up.
+        Bit3 => 1
+        Bit2 => finger index, 0 is the first finger, 1 is the second finger.
+        Bit1 => Right Button, 1 is pressed, 0 is not pressed.
+        Bit0 => Left Button, 1 is pressed, 0 is not pressed.
+Byte 2: X coordinate (xpos[9:2])
+Byte 3: Y coordinate (ypos[9:2])
+Byte 4: Bit1~Bit0 => Y coordinate (xpos[1:0])
+        Bit3~Bit2 => X coordinate (ypos[1:0])
+        Bit4 => scroll down button
+        Bit5 => scroll up button
+        Bit6 => scroll left button
+        Bit7 => scroll right button
+Notify Packet for STL3888-B0
+   Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
+BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
+  1   |1|0|1|P|1|M|R|L|  2  |C|C|C|C|C|C|C|C|  3 |0|0|F|F|0|0|0|i|  4 |r|l|u|d|0|0|0|0|
+      |---------------|     |---------------|    |---------------|    |---------------|
+Byte 1: Bit7~Bit6 => 00, Normal data packet
+                  => 01, Absolute coordination packet
+                  => 10, Notify packet
+        Bit5 => 1
+        Bit4 => when in absolute coordinate mode (valid when EN_PKT_GO is 1):
+                0: left button is generated by the on-pad command
+                1: left button is generated by the external button
+        Bit3 => 1
+        Bit2 => Middle Button, 1 is pressed, 0 is not pressed.
+        Bit1 => Right Button, 1 is pressed, 0 is not pressed.
+        Bit0 => Left Button, 1 is pressed, 0 is not pressed.
+Byte 2: Message Type => 0xB7 (Multi Finger, Multi Coordinate mode)
+Byte 3: Bit7~Bit6 => Don't care
+        Bit5~Bit4 => Number of fingers
+        Bit3~Bit1 => Reserved
+        Bit0 => 1: enter gesture mode; 0: leaving gesture mode
+Byte 4: Bit7 => scroll right button
+        Bit6 => scroll left button
+        Bit5 => scroll up button
+        Bit4 => scroll down button
+            * Note that if gesture and additional button(Bit4~Bit7)
+              happen at the same time, the button information will not
+              be sent.
        Bit3~Bit0 => Reserved
 Sample sequence of Multi-finger, Multi-coordinate mode:
        notify packet (valid bit == 1), abs pkt 1, abs pkt 2, abs pkt 1,
-        abs pkt 2, ..., notify packet(valid bit == 0)
+        abs pkt 2, ..., notify packet (valid bit == 0)
 ==============================================================================
 * FSP Enable/Disable packet
@@ -409,7 +500,8 @@ offset	width		default	r/w	name
                                        0: read only, 1: read/write enable
        (Note that following registers does not require clock gating being
        enabled prior to write: 05 06 07 08 09 0c 0f 10 11 12 16 17 18 23 2e
-        40 41 42 43.)
+        40 41 42 43.  In addition to that, this bit must be 1 when gesture
+        mode is enabled)
 0x31                            RW      on-pad command detection
        bit7            0       RW      on-pad command left button down tag
@@ -463,6 +555,10 @@ offset	width		default	r/w	name
        absolute coordinates; otherwise, host only receives packets with
        relative coordinate.)
+        bit7            0       RW      EN_PS2_F2: PS/2 gesture mode 2nd
+                                        finger packet enable
+                                        0: disable, 1: enable
 0x43                            RW      on-pad control
        bit0            0       RW      on-pad control enable
                                        0: disable, 1: enable
diff --git a/Documentation/intel_txt.txt b/Documentation/intel_txt.txt
index f40a1f030019..5dc59b04a71f 100644
--- a/Documentation/intel_txt.txt
+++ b/Documentation/intel_txt.txt
@@ -126,7 +126,7 @@ o  Tboot then applies an (optional) user-defined launch policy to
 o  Tboot adjusts the e820 table provided by the bootloader to reserve
   its own location in memory as well as to reserve certain other
   TXT-related regions.
-o  As part of it's launch, tboot DMA protects all of RAM (using the
+o  As part of its launch, tboot DMA protects all of RAM (using the
   VT-d PMRs).  Thus, the kernel must be booted with 'intel_iommu=on'
   in order to remove this blanket protection and use VT-d's
   page-level protection.
@@ -161,13 +161,15 @@ o  In order to put a system into any of the sleep states after a TXT
      has been restored, it will restore the TPM PCRs and then
      transfer control back to the kernel's S3 resume vector.
      In order to preserve system integrity across S3, the kernel
-      provides tboot with a set of memory ranges (kernel
+      provides tboot with a set of memory ranges (RAM and RESERVED_KERN
-      code/data/bss, S3 resume code, and AP trampoline) that tboot
+      in the e820 table, but not any memory that BIOS might alter over
-      will calculate a MAC (message authentication code) over and then
+      the S3 transition) that tboot will calculate a MAC (message
-      seal with the TPM.  On resume and once the measured environment
+      authentication code) over and then seal with the TPM. On resume
-      has been re-established, tboot will re-calculate the MAC and
+      and once the measured environment has been re-established, tboot
-      verify it against the sealed value.  Tboot's policy determines
+      will re-calculate the MAC and verify it against the sealed value.
-      what happens if the verification fails.
+      Tboot's policy determines what happens if the verification fails.
+      Note that the c/s 194 of tboot which has the new MAC code supports
+      this.
 That's pretty much it for TXT support.
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 35cf64d4436d..dd5806f4fcc4 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -139,7 +139,6 @@ Code  Seq#(hex)	Include File		Comments
 'K'     all     linux/kd.h
 'L'     00-1F   linux/loop.h            conflict!
 'L'     10-1F   drivers/scsi/mpt2sas/mpt2sas_ctl.h      conflict!
-'L'     20-2F   linux/usb/vstusb.h
 'L'     E0-FF   linux/ppdd.h            encrypted disk device driver
                                        <http://linux01.gwdg.de/~alatham/ppdd.html>
 'M'     all     linux/soundcard.h       conflict!
@@ -292,6 +291,7 @@ Code  Seq#(hex)	Include File		Comments
 0x92    00-0F   drivers/usb/mon/mon_bin.c
 0x93    60-7F   linux/auto_fs.h
 0x94    all     fs/btrfs/ioctl.h
+0x97    00-7F   fs/ceph/ioctl.h         Ceph file system
 0x99    00-0F                           537-Addinboard driver
                                        <mailto:buk@buks.ipn.de>
 0xA0    all     linux/sdp/sdp.h         Industrial Device Project
diff --git a/Documentation/isdn/INTERFACE.CAPI b/Documentation/isdn/INTERFACE.CAPI
index 5fe8de5cc727..f172091fb7cd 100644
--- a/Documentation/isdn/INTERFACE.CAPI
+++ b/Documentation/isdn/INTERFACE.CAPI
@@ -149,10 +149,11 @@ char *(*procinfo)(struct capi_ctr *ctrlr)
        pointer to a callback function returning the entry for the device in
        the CAPI controller info table, /proc/capi/controller
-read_proc_t *ctr_read_proc
+const struct file_operations *proc_fops
-        pointer to the read_proc callback function for the device's proc file
+        pointers to callback functions for the device's proc file
-        system entry, /proc/capi/controllers/<n>; will be called with a
+        system entry, /proc/capi/controllers/<n>; pointer to the device's
-        pointer to the device's capi_ctr structure as the last (data) argument
+        capi_ctr structure is available from struct proc_dir_entry::data
+        which is available from struct inode.
 Note: Callback functions except send_message() are never called in interrupt
 context.
diff --git a/Documentation/isdn/README.gigaset b/Documentation/isdn/README.gigaset
index 794941fc9493..e472df842323 100644
--- a/Documentation/isdn/README.gigaset
+++ b/Documentation/isdn/README.gigaset
@@ -292,10 +292,10 @@ GigaSet 307x Device Driver
        to /etc/modprobe.d/gigaset, /etc/modprobe.conf.local or a similar file.
     Problem:
-        Your isdn script aborts with a message about isdnlog.
+        The isdnlog program emits error messages or just doesn't work.
     Solution:
-        Try deactivating (or commenting out) isdnlog. This driver does not
+        Isdnlog supports only the HiSax driver. Do not attempt to use it with
-        support it.
+        other drivers such as Gigaset.
     Problem:
        You have two or more DECT data adapters (M101/M105) and only the
@@ -321,8 +321,8 @@ GigaSet 307x Device Driver
     writing an appropriate value to /sys/module/gigaset/parameters/debug, e.g.
        echo 0 > /sys/module/gigaset/parameters/debug
     switches off debugging output completely,
-        echo 0x10a020 > /sys/module/gigaset/parameters/debug
+        echo 0x302020 > /sys/module/gigaset/parameters/debug
-     enables the standard set of debugging output messages. These values are
+     enables a reasonable set of debugging output messages. These values are
     bit patterns where every bit controls a certain type of debugging output.
     See the constants DEBUG_* in the source file gigaset.h for details.
diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt
index c412c245848f..b472e4e0ba67 100644
--- a/Documentation/kbuild/kconfig-language.txt
+++ b/Documentation/kbuild/kconfig-language.txt
@@ -181,7 +181,7 @@ Expressions are listed in decreasing order of precedence.
 (7) Returns the result of max(/expr/, /expr/).
 An expression can have a value of 'n', 'm' or 'y' (or 0, 1, 2
-respectively for calculations). A menu entry becomes visible when it's
+respectively for calculations). A menu entry becomes visible when its
 expression evaluates to 'm' or 'y'.
 There are two types of symbols: constant and non-constant symbols.
diff --git a/Documentation/kbuild/kconfig.txt b/Documentation/kbuild/kconfig.txt
index 49efae703979..b2cb16ebcb16 100644
--- a/Documentation/kbuild/kconfig.txt
+++ b/Documentation/kbuild/kconfig.txt
@@ -96,7 +96,7 @@ Environment variables for 'silentoldconfig'
 KCONFIG_NOSILENTUPDATE
 --------------------------------------------------
 If this variable has a non-blank value, it prevents silent kernel
-config udpates (requires explicit updates).
+config updates (requires explicit updates).
 KCONFIG_AUTOCONFIG
 --------------------------------------------------
diff --git a/Documentation/kernel-docs.txt b/Documentation/kernel-docs.txt
index 28cdc2af2131..ec8d31ee12e0 100644
--- a/Documentation/kernel-docs.txt
+++ b/Documentation/kernel-docs.txt
@@ -116,7 +116,7 @@
       Author: Ingo Molnar, Gadi Oxman and Miguel de Icaza.
       URL: http://www.linuxjournal.com/article.php?sid=2391
       Keywords: RAID, MD driver.
-       Description: Linux Journal Kernel Korner article. Here is it's
+       Description: Linux Journal Kernel Korner article. Here is its
       abstract: "A description of the implementation of the RAID-1,
       RAID-4 and RAID-5 personalities of the MD device driver in the
       Linux kernel, providing users with high performance and reliable,
@@ -127,7 +127,7 @@
       URL: http://www.linuxjournal.com/article.php?sid=1219
       Keywords: device driver, module, loading/unloading modules,
       allocating resources.
-       Description: Linux Journal Kernel Korner article. Here is it's
+       Description: Linux Journal Kernel Korner article. Here is its
       abstract: "This is the first of a series of four articles
       co-authored by Alessandro Rubini and Georg Zezchwitz which present
       a practical approach to writing Linux device drivers as kernel
@@ -141,7 +141,7 @@
       Keywords: character driver, init_module, clean_up module,
       autodetection, mayor number, minor number, file operations,
       open(), close().
-       Description: Linux Journal Kernel Korner article. Here is it's
+       Description: Linux Journal Kernel Korner article. Here is its
       abstract: "This article, the second of four, introduces part of
       the actual code to create custom module implementing a character
       device driver. It describes the code for module initialization and
@@ -152,7 +152,7 @@
       URL: http://www.linuxjournal.com/article.php?sid=1221
       Keywords: read(), write(), select(), ioctl(), blocking/non
       blocking mode, interrupt handler.
-       Description: Linux Journal Kernel Korner article. Here is it's
+       Description: Linux Journal Kernel Korner article. Here is its
       abstract: "This article, the third of four on writing character
       device drivers, introduces concepts of reading, writing, and using
       ioctl-calls".
@@ -161,7 +161,7 @@
       Author: Alessandro Rubini and Georg v. Zezschwitz.
       URL: http://www.linuxjournal.com/article.php?sid=1222
       Keywords: interrupts, irqs, DMA, bottom halves, task queues.
-       Description: Linux Journal Kernel Korner article. Here is it's
+       Description: Linux Journal Kernel Korner article. Here is its
       abstract: "This is the fourth in a series of articles about
       writing character device drivers as loadable kernel modules. This
       month, we further investigate the field of interrupt handling.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e7848a0d99eb..b56ea860da21 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -54,9 +54,11 @@ parameter is applicable:
        IMA     Integrity measurement architecture is enabled.
        IOSCHED More than one I/O scheduler is enabled.
        IP_PNP  IP DHCP, BOOTP, or RARP is enabled.
+        IPV6    IPv6 support is enabled.
        ISAPNP  ISA PnP code is enabled.
        ISDN    Appropriate ISDN support is enabled.
        JOY     Appropriate joystick support is enabled.
+        KGDB    Kernel debugger support is enabled.
        KVM     Kernel Virtual Machine support is enabled.
        LIBATA  Libata driver is enabled
        LP      Printer support is enabled.
@@ -98,6 +100,7 @@ parameter is applicable:
        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.
        USB     USB support is enabled.
@@ -150,6 +153,7 @@ and is between 256 and 4096 characters. It is defined in the file
                        strict -- Be less tolerant of platforms that are not
                                strictly ACPI specification compliant.
                        rsdt -- prefer RSDT over (default) XSDT
+                        copy_dsdt -- copy DSDT to memory
                        See also Documentation/power/pm.txt, pci=noacpi
@@ -199,10 +203,6 @@ and is between 256 and 4096 characters. It is defined in the file
                        acpi_display_output=video
                        See above.
-        acpi_early_pdc_eval     [HW,ACPI] Evaluate processor _PDC methods
-                                early. Needed on some platforms to properly
-                                initialize the EC.
        acpi_irq_balance [HW,ACPI]
                        ACPI will balance active IRQs
                        default in APIC mode
@@ -290,9 +290,6 @@ and is between 256 and 4096 characters. It is defined in the file
        advansys=       [HW,SCSI]
                        See header of drivers/scsi/advansys.c.
-        advwdt=         [HW,WDT] Advantech WDT
-                        Format: <iostart>,<iostop>
        aedsp16=        [HW,OSS] Audio Excel DSP 16
                        Format: <io>,<irq>,<dma>,<mss_io>,<mpu_io>,<mpu_irq>
                        See also header of sound/oss/aedsp16.c.
@@ -323,15 +320,12 @@ and is between 256 and 4096 characters. It is defined in the file
        amd_iommu=      [HW,X86-84]
                        Pass parameters to the AMD IOMMU driver in the system.
                        Possible values are:
-                        isolate - enable device isolation (each device, as far
-                                  as possible, will get its own protection
-                                  domain) [default]
-                        share - put every device behind one IOMMU into the
-                                same protection domain
                        fullflush - enable flushing of IO/TLB entries when
                                    they are unmapped. Otherwise they are
                                    flushed before they will be reused, which
                                    is a lot of faster
+                        off       - do not initialize any AMD IOMMU found in
+                                    the system
        amijoy.map=     [HW,JOY] Amiga joystick support
                        Map of devices attached to JOY0DAT and JOY1DAT
@@ -356,6 +350,9 @@ and is between 256 and 4096 characters. It is defined in the file
                        Change the amount of debugging information output
                        when initialising the APIC and IO-APIC components.
+        autoconf=       [IPV6]
+                        See Documentation/networking/ipv6.txt.
        show_lapic=     [APIC,X86] Advanced Programmable Interrupt Controller
                        Limit apic dumping. The parameter defines the maximal
                        number of local apics being dumped. Also it is possible
@@ -638,6 +635,12 @@ and is between 256 and 4096 characters. It is defined in the file
                        See drivers/char/README.epca and
                        Documentation/serial/digiepca.txt.
+        disable=        [IPV6]
+                        See Documentation/networking/ipv6.txt.
+        disable_ipv6=   [IPV6]
+                        See Documentation/networking/ipv6.txt.
        disable_mtrr_cleanup [X86]
                        The kernel tries to adjust MTRR layout from continuous
                        to discrete, to make X server driver able to add WB
@@ -707,6 +710,12 @@ and is between 256 and 4096 characters. It is defined in the file
                        The VGA output is eventually overwritten by the real
                        console.
+        ekgdboc=        [X86,KGDB] Allow early kernel console debugging
+                        ekgdboc=kbd
+                        This is desgined to be used in conjunction with
+                        the boot argument: earlyprintk=vga
        eata=           [HW,SCSI]
        edd=            [EDD]
@@ -753,9 +762,6 @@ and is between 256 and 4096 characters. It is defined in the file
                        This option is obsoleted by the "netdev=" option, which
                        has equivalent usage. See its documentation for details.
-        eurwdt=         [HW,WDT] Eurotech CPU-1220/1410 onboard watchdog.
-                        Format: <io>[,<irq>]
        failslab=
        fail_page_alloc=
        fail_make_request=[KNL]
@@ -783,8 +789,12 @@ and is between 256 and 4096 characters. It is defined in the file
                        as early as possible in order to facilitate early
                        boot debugging.
-        ftrace_dump_on_oops
+        ftrace_dump_on_oops[=orig_cpu]
                        [FTRACE] will dump the trace buffers on oops.
+                        If no parameter is passed, ftrace will dump
+                        buffers of all CPUs, but if you pass orig_cpu, it will
+                        dump only the buffer of the CPU that triggered the
+                        oops.
        ftrace_filter=[function-list]
                        [FTRACE] Limit the functions traced by the function
@@ -1111,10 +1121,26 @@ and is between 256 and 4096 characters. It is defined in the file
                        use the HighMem zone if it exists, and the Normal
                        zone if it does not.
-        kgdboc=         [HW] kgdb over consoles.
+        kgdbdbgp=       [KGDB,HW] kgdb over EHCI usb debug port.
-                        Requires a tty driver that supports console polling.
+                        Format: <Controller#>[,poll interval]
-                        (only serial supported for now)
+                        The controller # is the number of the ehci usb debug
-                        Format: <serial_device>[,baud]
+                        port as it is probed via PCI.  The poll interval is
+                        optional and is the number seconds in between
+                        each poll cycle to the debug port in case you need
+                        the functionality for interrupting the kernel with
+                        gdb or control-c on the dbgp connection.  When
+                        not using this parameter you use sysrq-g to break into
+                        the kernel debugger.
+        kgdboc=         [KGDB,HW] kgdb over consoles.
+                        Requires a tty driver that supports console polling,
+                        or a supported polling keyboard driver (non-usb).
+                        Serial only format: <serial_device>[,baud]
+                        keyboard only format: kbd
+                        keyboard and serial format: kbd,<serial_device>[,baud]
+        kgdbwait        [KGDB] Stop kernel execution and enter the
+                        kernel debugger at the earliest opportunity.
        kmac=           [MIPS] korina ethernet MAC address.
                        Configure the RouterBoard 532 series on-chip
@@ -1193,7 +1219,7 @@ and is between 256 and 4096 characters. It is defined in the file
        libata.force=   [LIBATA] Force configurations.  The format is comma
                        separated list of "[ID:]VAL" where ID is
-                        PORT[:DEVICE].  PORT and DEVICE are decimal numbers
+                        PORT[.DEVICE].  PORT and DEVICE are decimal numbers
                        matching port, link or device.  Basically, it matches
                        the ATA ID string printed on console by libata.  If
                        the whole ID part is omitted, the last PORT and DEVICE
@@ -1738,6 +1764,9 @@ and is between 256 and 4096 characters. It is defined in the file
        nomfgpt         [X86-32] Disable Multi-Function General Purpose
                        Timer usage (for AMD Geode machines).
+        nopat           [X86] Disable PAT (page attribute table extension of
+                        pagetables) support.
        norandmaps      Don't use address space randomization.  Equivalent to
                        echo 0 > /proc/sys/kernel/randomize_va_space
@@ -1781,6 +1810,12 @@ and is between 256 and 4096 characters. It is defined in the file
                        purges which is reported from either PAL_VM_SUMMARY or
                        SAL PALO.
+        nr_cpus=        [SMP] Maximum number of processors that an SMP kernel
+                        could support.  nr_cpus=n : n >= 1 limits the kernel to
+                        supporting 'n' processors. Later in runtime you can not
+                        use hotplug cpu feature to put more cpu back to online.
+                        just like you compile the kernel NR_CPUS=n
        nr_uarts=       [SERIAL] maximum number of UARTs to be registered.
        numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA.
@@ -1948,8 +1983,12 @@ and is between 256 and 4096 characters. It is defined in the file
                                IRQ routing is enabled.
                noacpi          [X86] Do not use ACPI for IRQ routing
                                or for PCI scanning.
-                use_crs         [X86] Use _CRS for PCI resource
+                use_crs         [X86] Use PCI host bridge window information
-                                allocation.
+                                from ACPI.  On BIOSes from 2008 or later, this
+                                is enabled by default.  If you need to use this,
+                                please report a bug.
+                nocrs           [X86] Ignore PCI host bridge windows from ACPI.
+                                If you need to use this, please report a bug.
                routeirq        Do IRQ routing for all PCI devices.
                                This is normally done in pci_enable_device(),
                                so this option is a temporary workaround
@@ -1998,6 +2037,14 @@ and is between 256 and 4096 characters. It is defined in the file
                force   Enable ASPM even on devices that claim not to support it.
                        WARNING: Forcing ASPM on may cause system lockups.
+        pcie_pme=       [PCIE,PM] Native PCIe PME signaling options:
+                off     Do not use native PCIe PME signaling.
+                force   Use native PCIe PME signaling even if the BIOS refuses
+                        to allow the kernel to control the relevant PCIe config
+                        registers.
+                nomsi   Do not use MSI for native PCIe PME signaling (this makes
+                        all PCIe root ports use INTx for everything).
        pcmv=           [HW,PCMCIA] BadgePAD 4
        pd.             [PARIDE]
@@ -2214,9 +2261,6 @@ and is between 256 and 4096 characters. It is defined in the file
        sched_debug     [KNL] Enables verbose scheduler debug messages.
-        sc1200wdt=      [HW,WDT] SC1200 WDT (watchdog) driver
-                        Format: <io>[,<timeout>[,<isapnp>]]
        scsi_debug_*=   [SCSI]
                        See drivers/scsi/scsi_debug.c.
@@ -2588,6 +2632,15 @@ and is between 256 and 4096 characters. It is defined in the file
        tp720=          [HW,PS2]
+        tpm_suspend_pcr=[HW,TPM]
+                        Format: integer pcr id
+                        Specify that at suspend time, the tpm driver
+                        should extend the specified pcr with zeros,
+                        as a workaround for some chips which fail to
+                        flush the last written pcr on TPM_SaveState.
+                        This will guarantee that all the other pcrs
+                        are saved.
        trace_buf_size=nn[KMG]
                        [FTRACE] will set tracing buffer size.
@@ -2703,6 +2756,13 @@ and is between 256 and 4096 characters. It is defined in the file
                                        medium is write-protected).
                        Example: quirks=0419:aaf5:rl,0421:0433:rc
+        userpte=
+                        [X86] Flags controlling user PTE allocations.
+                                nohigh = do not allocate PTE pages in
+                                        HIGHMEM regardless of setting
+                                        of CONFIG_HIGHPTE.
        vdso=           [X86,SH]
                        vdso=2: enable compat VDSO (default with COMPAT_VDSO)
                        vdso=1: enable VDSO (default)
@@ -2789,13 +2849,21 @@ and is between 256 and 4096 characters. It is defined in the file
        wd7000=         [HW,SCSI]
                        See header of drivers/scsi/wd7000.c.
-        wdt=            [WDT] Watchdog
+        watchdog timers [HW,WDT] For information on watchdog timers,
-                        See Documentation/watchdog/wdt.txt.
+                        see Documentation/watchdog/watchdog-parameters.txt
+                        or other driver-specific files in the
+                        Documentation/watchdog/ directory.
        x2apic_phys     [X86-64,APIC] Use x2apic physical mode instead of
                        default x2apic cluster mode on platforms
                        supporting x2apic.
+        x86_mrst_timer= [X86-32,APBT]
+                        Choose timer option for x86 Moorestown MID platform.
+                        Two valid options are apbt timer only and lapic timer
+                        plus one apbt timer for broadcast timer.
+                        x86_mrst_timer=apbt_only | lapic_and_apbt
        xd=             [HW,XT] Original XT pre-IDE (RLL encoded) disks.
        xd_geo=         See header of drivers/block/xd.c.
diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt
index c79ab996dada..3ab2472509cb 100644
--- a/Documentation/kobject.txt
+++ b/Documentation/kobject.txt
@@ -59,37 +59,56 @@ nice to have in other objects.  The C language does not allow for the
 direct expression of inheritance, so other techniques - such as structure
 embedding - must be used.
-So, for example, the UIO code has a structure that defines the memory
+(As an aside, for those familiar with the kernel linked list implementation,
-region associated with a uio device:
+this is analogous as to how "list_head" structs are rarely useful on
+their own, but are invariably found embedded in the larger objects of
+interest.)
-struct uio_mem {
+So, for example, the UIO code in drivers/uio/uio.c has a structure that
+defines the memory region associated with a uio device:
+    struct uio_map {
        struct kobject kobj;
-        unsigned long addr;
+        struct uio_mem *mem;
-        unsigned long size;
+    };
-        int memtype;
-        void __iomem *internal_addr;
-};
-If you have a struct uio_mem structure, finding its embedded kobject is
+If you have a struct uio_map structure, finding its embedded kobject is
 just a matter of using the kobj member.  Code that works with kobjects will
 often have the opposite problem, however: given a struct kobject pointer,
 what is the pointer to the containing structure?  You must avoid tricks
 (such as assuming that the kobject is at the beginning of the structure)
 and, instead, use the container_of() macro, found in <linux/kernel.h>:
-        container_of(pointer, type, member)
+    container_of(pointer, type, member)
+where:
+  * "pointer" is the pointer to the embedded kobject,
+  * "type" is the type of the containing structure, and
+  * "member" is the name of the structure field to which "pointer" points.
+The return value from container_of() is a pointer to the corresponding
+container type. So, for example, a pointer "kp" to a struct kobject
+embedded *within* a struct uio_map could be converted to a pointer to the
+*containing* uio_map structure with:
+    struct uio_map *u_map = container_of(kp, struct uio_map, kobj);
+For convenience, programmers often define a simple macro for "back-casting"
+kobject pointers to the containing type.  Exactly this happens in the
+earlier drivers/uio/uio.c, as you can see here:
+    struct uio_map {
+        struct kobject kobj;
+        struct uio_mem *mem;
+    };
-where pointer is the pointer to the embedded kobject, type is the type of
+    #define to_map(map) container_of(map, struct uio_map, kobj)
-the containing structure, and member is the name of the structure field to
-which pointer points.  The return value from container_of() is a pointer to
-the given type. So, for example, a pointer "kp" to a struct kobject
-embedded within a struct uio_mem could be converted to a pointer to the
-containing uio_mem structure with:
-    struct uio_mem *u_mem = container_of(kp, struct uio_mem, kobj);
+where the macro argument "map" is a pointer to the struct kobject in
+question.  That macro is subsequently invoked with:
-Programmers often define a simple macro for "back-casting" kobject pointers
+    struct uio_map *map = to_map(kobj);
-to the containing type.
 Initialization of kobjects
@@ -266,7 +285,7 @@ kobj_type:
    struct kobj_type {
            void (*release)(struct kobject *);
-            struct sysfs_ops    *sysfs_ops;
+            const struct sysfs_ops *sysfs_ops;
            struct attribute    **default_attrs;
    };
@@ -387,4 +406,5 @@ called, and the objects in the former circle release each other.
 Example code to copy from
 For a more complete example of using ksets and kobjects properly, see the
-sample/kobject/kset-example.c code.
+example programs samples/kobject/{kobject-example.c,kset-example.c},
+which will be built as loadable modules if you select CONFIG_SAMPLE_KOBJECT.
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 053037a1fe6d..6653017680dd 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -1,6 +1,7 @@
 Title   : Kernel Probes (Kprobes)
 Authors : Jim Keniston <jkenisto@us.ibm.com>
-        : Prasanna S Panchamukhi <prasanna@in.ibm.com>
+        : Prasanna S Panchamukhi <prasanna.panchamukhi@gmail.com>
+        : Masami Hiramatsu <mhiramat@redhat.com>
 CONTENTS
@@ -15,6 +16,7 @@ CONTENTS
 9. Jprobes Example
 10. Kretprobes Example
 Appendix A: The kprobes debugfs interface
+Appendix B: The kprobes sysctl interface
 1. Concepts: Kprobes, Jprobes, Return Probes
@@ -42,13 +44,13 @@ registration/unregistration of a group of *probes. These functions
 can speed up unregistration process when you have to unregister
 a lot of probes at once.
-The next three subsections explain how the different types of
+The next four subsections explain how the different types of
-probes work.  They explain certain things that you'll need to
+probes work and how jump optimization works.  They explain certain
-know in order to make the best use of Kprobes -- e.g., the
+things that you'll need to know in order to make the best use of
-difference between a pre_handler and a post_handler, and how
+Kprobes -- e.g., the difference between a pre_handler and
-to use the maxactive and nmissed fields of a kretprobe.  But
+a post_handler, and how to use the maxactive and nmissed fields of
-if you're in a hurry to start using Kprobes, you can skip ahead
+a kretprobe.  But if you're in a hurry to start using Kprobes, you
-to section 2.
+can skip ahead to section 2.
 1.1 How Does a Kprobe Work?
@@ -161,13 +163,123 @@ In case probed function is entered but there is no kretprobe_instance
 object available, then in addition to incrementing the nmissed count,
 the user entry_handler invocation is also skipped.
+1.4 How Does Jump Optimization Work?
+If your kernel is built with CONFIG_OPTPROBES=y (currently this flag
+is automatically set 'y' on x86/x86-64, non-preemptive kernel) and
+the "debug.kprobes_optimization" kernel parameter is set to 1 (see
+sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump
+instruction instead of a breakpoint instruction at each probepoint.
+1.4.1 Init a Kprobe
+When a probe is registered, before attempting this optimization,
+Kprobes inserts an ordinary, breakpoint-based kprobe at the specified
+address. So, even if it's not possible to optimize this particular
+probepoint, there'll be a probe there.
+1.4.2 Safety Check
+Before optimizing a probe, Kprobes performs the following safety checks:
+- Kprobes verifies that the region that will be replaced by the jump
+instruction (the "optimized region") lies entirely within one function.
+(A jump instruction is multiple bytes, and so may overlay multiple
+instructions.)
+- Kprobes analyzes the entire function and verifies that there is no
+jump into the optimized region.  Specifically:
+  - the function contains no indirect jump;
+  - the function contains no instruction that causes an exception (since
+  the fixup code triggered by the exception could jump back into the
+  optimized region -- Kprobes checks the exception tables to verify this);
+  and
+  - there is no near jump to the optimized region (other than to the first
+  byte).
+- For each instruction in the optimized region, Kprobes verifies that
+the instruction can be executed out of line.
+1.4.3 Preparing Detour Buffer
+Next, Kprobes prepares a "detour" buffer, which contains the following
+instruction sequence:
+- code to push the CPU's registers (emulating a breakpoint trap)
+- a call to the trampoline code which calls user's probe handlers.
+- code to restore registers
+- the instructions from the optimized region
+- a jump back to the original execution path.
+1.4.4 Pre-optimization
+After preparing the detour buffer, Kprobes verifies that none of the
+following situations exist:
+- The probe has either a break_handler (i.e., it's a jprobe) or a
+post_handler.
+- Other instructions in the optimized region are probed.
+- The probe is disabled.
+In any of the above cases, Kprobes won't start optimizing the probe.
+Since these are temporary situations, Kprobes tries to start
+optimizing it again if the situation is changed.
+If the kprobe can be optimized, Kprobes enqueues the kprobe to an
+optimizing list, and kicks the kprobe-optimizer workqueue to optimize
+it.  If the to-be-optimized probepoint is hit before being optimized,
+Kprobes returns control to the original instruction path by setting
+the CPU's instruction pointer to the copied code in the detour buffer
+-- thus at least avoiding the single-step.
+1.4.5 Optimization
+The Kprobe-optimizer doesn't insert the jump instruction immediately;
+rather, it calls synchronize_sched() for safety first, because it's
+possible for a CPU to be interrupted in the middle of executing the
+optimized region(*).  As you know, synchronize_sched() can ensure
+that all interruptions that were active when synchronize_sched()
+was called are done, but only if CONFIG_PREEMPT=n.  So, this version
+of kprobe optimization supports only kernels with CONFIG_PREEMPT=n.(**)
+After that, the Kprobe-optimizer calls stop_machine() to replace
+the optimized region with a jump instruction to the detour buffer,
+using text_poke_smp().
+1.4.6 Unoptimization
+When an optimized kprobe is unregistered, disabled, or blocked by
+another kprobe, it will be unoptimized.  If this happens before
+the optimization is complete, the kprobe is just dequeued from the
+optimized list.  If the optimization has been done, the jump is
+replaced with the original code (except for an int3 breakpoint in
+the first byte) by using text_poke_smp().
+(*)Please imagine that the 2nd instruction is interrupted and then
+the optimizer replaces the 2nd instruction with the jump *address*
+while the interrupt handler is running. When the interrupt
+returns to original address, there is no valid instruction,
+and it causes an unexpected result.
+(**)This optimization-safety checking may be replaced with the
+stop-machine method that ksplice uses for supporting a CONFIG_PREEMPT=y
+kernel.
+NOTE for geeks:
+The jump optimization changes the kprobe's pre_handler behavior.
+Without optimization, the pre_handler can change the kernel's execution
+path by changing regs->ip and returning 1.  However, when the probe
+is optimized, that modification is ignored.  Thus, if you want to
+tweak the kernel's execution path, you need to suppress optimization,
+using one of the following techniques:
+- Specify an empty function for the kprobe's post_handler or break_handler.
+ or
+- Execute 'sysctl -w debug.kprobes_optimization=n'
 2. Architectures Supported
 Kprobes, jprobes, and return probes are implemented on the following
 architectures:
- i386
+- i386 (Supports jump optimization)
- x86_64 (AMD-64, EM64T)
+- x86_64 (AMD-64, EM64T) (Supports jump optimization)
 - ppc64
 - ia64 (Does not support probes on instruction slot1.)
 - sparc64 (Return probes not yet implemented.)
@@ -214,7 +326,7 @@ occurs during execution of kp->pre_handler or kp->post_handler,
 or during single-stepping of the probed instruction, Kprobes calls
 kp->fault_handler.  Any or all handlers can be NULL. If kp->flags
 is set KPROBE_FLAG_DISABLED, that kp will be registered but disabled,
-so, it's handlers aren't hit until calling enable_kprobe(kp).
+so, its handlers aren't hit until calling enable_kprobe(kp).
 NOTE:
 1. With the introduction of the "symbol_name" field to struct kprobe,
@@ -389,7 +501,10 @@ the probe which has been registered.
 Kprobes allows multiple probes at the same address.  Currently,
 however, there cannot be multiple jprobes on the same function at
-the same time.
+the same time.  Also, a probepoint for which there is a jprobe or
+a post_handler cannot be optimized.  So if you install a jprobe,
+or a kprobe with a post_handler, at an optimized probepoint, the
+probepoint will be unoptimized automatically.
 In general, you can install a probe anywhere in the kernel.
 In particular, you can probe interrupt handlers.  Known exceptions
@@ -453,6 +568,38 @@ reason, Kprobes doesn't support return probes (or kprobes or jprobes)
 on the x86_64 version of __switch_to(); the registration functions
 return -EINVAL.
+On x86/x86-64, since the Jump Optimization of Kprobes modifies
+instructions widely, there are some limitations to optimization. To
+explain it, we introduce some terminology. Imagine a 3-instruction
+sequence consisting of a two 2-byte instructions and one 3-byte
+instruction.
+        IA
+         |
+[-2][-1][0][1][2][3][4][5][6][7]
+        [ins1][ins2][  ins3 ]
+        [<-     DCR       ->]
+           [<- JTPR ->]
+ins1: 1st Instruction
+ins2: 2nd Instruction
+ins3: 3rd Instruction
+IA:  Insertion Address
+JTPR: Jump Target Prohibition Region
+DCR: Detoured Code Region
+The instructions in DCR are copied to the out-of-line buffer
+of the kprobe, because the bytes in DCR are replaced by
+a 5-byte jump instruction. So there are several limitations.
+a) The instructions in DCR must be relocatable.
+b) The instructions in DCR must not include a call instruction.
+c) JTPR must not be targeted by any jump or call instruction.
+d) DCR must not straddle the border betweeen functions.
+Anyway, these limitations are checked by the in-kernel instruction
+decoder, so you don't need to worry about that.
 6. Probe Overhead
 On a typical CPU in use in 2005, a kprobe hit takes 0.5 to 1.0
@@ -476,6 +623,19 @@ k = 0.49 usec; j = 0.76; r = 0.80; kr = 0.82; jr = 1.07
 ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU)
 k = 0.77 usec; j = 1.31; r = 1.26; kr = 1.45; jr = 1.99
+6.1 Optimized Probe Overhead
+Typically, an optimized kprobe hit takes 0.07 to 0.1 microseconds to
+process. Here are sample overhead figures (in usec) for x86 architectures.
+k = unoptimized kprobe, b = boosted (single-step skipped), o = optimized kprobe,
+r = unoptimized kretprobe, rb = boosted kretprobe, ro = optimized kretprobe.
+i386: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
+k = 0.80 usec; b = 0.33; o = 0.05; r = 1.10; rb = 0.61; ro = 0.33
+x86-64: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
+k = 0.99 usec; b = 0.43; o = 0.06; r = 1.24; rb = 0.68; ro = 0.30
 7. TODO
 a. SystemTap (http://sourceware.org/systemtap): Provides a simplified
@@ -523,7 +683,8 @@ is also specified. Following columns show probe status. If the probe is on
 a virtual address that is no longer valid (module init sections, module
 virtual addresses that correspond to modules that've been unloaded),
 such probes are marked with [GONE]. If the probe is temporarily disabled,
-such probes are marked with [DISABLED].
+such probes are marked with [DISABLED]. If the probe is optimized, it is
+marked with [OPTIMIZED].
 /sys/kernel/debug/kprobes/enabled: Turn kprobes ON/OFF forcibly.
@@ -533,3 +694,19 @@ registered probes will be disarmed, till such time a "1" is echoed to this
 file. Note that this knob just disarms and arms all kprobes and doesn't
 change each probe's disabling state. This means that disabled kprobes (marked
 [DISABLED]) will be not enabled if you turn ON all kprobes by this knob.
+Appendix B: The kprobes sysctl interface
+/proc/sys/debug/kprobes-optimization: Turn kprobes optimization ON/OFF.
+When CONFIG_OPTPROBES=y, this sysctl interface appears and it provides
+a knob to globally and forcibly turn jump optimization (see section
+1.4) ON or OFF. By default, jump optimization is allowed (ON).
+If you echo "0" to this file or set "debug.kprobes_optimization" to
+0 via sysctl, all optimized probes will be unoptimized, and any new
+probes registered after that will not be optimized.  Note that this
+knob *changes* the optimized state. This means that optimized probes
+(marked [OPTIMIZED]) will be unoptimized ([OPTIMIZED] tag will be
+removed). If the knob is turned on, they will be optimized again.
diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index 2811e452f756..a237518e51b9 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -23,12 +23,12 @@ of a virtual machine.  The ioctls belong to three classes
   Only run vcpu ioctls from the same thread that was used to create the
   vcpu.
-2. File descritpors
+2. File descriptors
 The kvm API is centered around file descriptors.  An initial
 open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
 can be used to issue system ioctls.  A KVM_CREATE_VM ioctl on this
-handle will create a VM file descripror which can be used to issue VM
+handle will create a VM file descriptor which can be used to issue VM
 ioctls.  A KVM_CREATE_VCPU ioctl on a VM fd will create a virtual cpu
 and return a file descriptor pointing to it.  Finally, ioctls on a vcpu
 fd can be used to control the vcpu, including the important task of
@@ -643,7 +643,7 @@ Type: vm ioctl
 Parameters: struct kvm_clock_data (in)
 Returns: 0 on success, -1 on error
-Sets the current timestamp of kvmclock to the valued specific in its parameter.
+Sets the current timestamp of kvmclock to the value specified in its parameter.
 In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
 such as migration.
@@ -656,6 +656,7 @@ struct kvm_clock_data {
 4.29 KVM_GET_VCPU_EVENTS
 Capability: KVM_CAP_VCPU_EVENTS
+Extended by: KVM_CAP_INTR_SHADOW
 Architectures: x86
 Type: vm ioctl
 Parameters: struct kvm_vcpu_event (out)
@@ -676,7 +677,7 @@ struct kvm_vcpu_events {
                __u8 injected;
                __u8 nr;
                __u8 soft;
-                __u8 pad;
+                __u8 shadow;
        } interrupt;
        struct {
                __u8 injected;
@@ -688,9 +689,13 @@ struct kvm_vcpu_events {
        __u32 flags;
 };
+KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
+interrupt.shadow contains a valid state. Otherwise, this field is undefined.
 4.30 KVM_SET_VCPU_EVENTS
 Capability: KVM_CAP_VCPU_EVENTS
+Extended by: KVM_CAP_INTR_SHADOW
 Architectures: x86
 Type: vm ioctl
 Parameters: struct kvm_vcpu_event (in)
@@ -709,6 +714,183 @@ current in-kernel state. The bits are:
 KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
 KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
+If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
+the flags field to signal that interrupt.shadow contains a valid state and
+shall be written into the VCPU.
+4.32 KVM_GET_DEBUGREGS
+Capability: KVM_CAP_DEBUGREGS
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_debugregs (out)
+Returns: 0 on success, -1 on error
+Reads debug registers from the vcpu.
+struct kvm_debugregs {
+        __u64 db[4];
+        __u64 dr6;
+        __u64 dr7;
+        __u64 flags;
+        __u64 reserved[9];
+};
+4.33 KVM_SET_DEBUGREGS
+Capability: KVM_CAP_DEBUGREGS
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_debugregs (in)
+Returns: 0 on success, -1 on error
+Writes debug registers into the vcpu.
+See KVM_GET_DEBUGREGS for the data structure. The flags field is unused
+yet and must be cleared on entry.
+4.34 KVM_SET_USER_MEMORY_REGION
+Capability: KVM_CAP_USER_MEM
+Architectures: all
+Type: vm ioctl
+Parameters: struct kvm_userspace_memory_region (in)
+Returns: 0 on success, -1 on error
+struct kvm_userspace_memory_region {
+        __u32 slot;
+        __u32 flags;
+        __u64 guest_phys_addr;
+        __u64 memory_size; /* bytes */
+        __u64 userspace_addr; /* start of the userspace allocated memory */
+};
+/* for kvm_memory_region::flags */
+#define KVM_MEM_LOG_DIRTY_PAGES  1UL
+This ioctl allows the user to create or modify a guest physical memory
+slot.  When changing an existing slot, it may be moved in the guest
+physical memory space, or its flags may be modified.  It may not be
+resized.  Slots may not overlap in guest physical address space.
+Memory for the region is taken starting at the address denoted by the
+field userspace_addr, which must point at user addressable memory for
+the entire memory slot size.  Any object may back this memory, including
+anonymous memory, ordinary files, and hugetlbfs.
+It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
+be identical.  This allows large pages in the guest to be backed by large
+pages in the host.
+The flags field supports just one flag, KVM_MEM_LOG_DIRTY_PAGES, which
+instructs kvm to keep track of writes to memory within the slot.  See
+the KVM_GET_DIRTY_LOG ioctl.
+When the KVM_CAP_SYNC_MMU capability, changes in the backing of the memory
+region are automatically reflected into the guest.  For example, an mmap()
+that affects the region will be made visible immediately.  Another example
+is madvise(MADV_DROP).
+It is recommended to use this API instead of the KVM_SET_MEMORY_REGION ioctl.
+The KVM_SET_MEMORY_REGION does not allow fine grained control over memory
+allocation and is deprecated.
+4.35 KVM_SET_TSS_ADDR
+Capability: KVM_CAP_SET_TSS_ADDR
+Architectures: x86
+Type: vm ioctl
+Parameters: unsigned long tss_address (in)
+Returns: 0 on success, -1 on error
+This ioctl defines the physical address of a three-page region in the guest
+physical address space.  The region must be within the first 4GB of the
+guest physical address space and must not conflict with any memory slot
+or any mmio address.  The guest may malfunction if it accesses this memory
+region.
+This ioctl is required on Intel-based hosts.  This is needed on Intel hardware
+because of a quirk in the virtualization implementation (see the internals
+documentation when it pops into existence).
+4.36 KVM_ENABLE_CAP
+Capability: KVM_CAP_ENABLE_CAP
+Architectures: ppc
+Type: vcpu ioctl
+Parameters: struct kvm_enable_cap (in)
+Returns: 0 on success; -1 on error
+Not all extensions are enabled by default. Using this ioctl the application
+can enable an extension, making it available to the guest.
+On systems that do not support this ioctl, it always fails. On systems that
+do support it, it only works for extensions that are supported for enablement.
+To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should
+be used.
+struct kvm_enable_cap {
+       /* in */
+       __u32 cap;
+The capability that is supposed to get enabled.
+       __u32 flags;
+A bitfield indicating future enhancements. Has to be 0 for now.
+       __u64 args[4];
+Arguments for enabling a feature. If a feature needs initial values to
+function properly, this is the place to put them.
+       __u8  pad[64];
+};
+4.37 KVM_GET_MP_STATE
+Capability: KVM_CAP_MP_STATE
+Architectures: x86, ia64
+Type: vcpu ioctl
+Parameters: struct kvm_mp_state (out)
+Returns: 0 on success; -1 on error
+struct kvm_mp_state {
+        __u32 mp_state;
+};
+Returns the vcpu's current "multiprocessing state" (though also valid on
+uniprocessor guests).
+Possible values are:
+ - KVM_MP_STATE_RUNNABLE:        the vcpu is currently running
+ - KVM_MP_STATE_UNINITIALIZED:   the vcpu is an application processor (AP)
+                                 which has not yet received an INIT signal
+ - KVM_MP_STATE_INIT_RECEIVED:   the vcpu has received an INIT signal, and is
+                                 now ready for a SIPI
+ - KVM_MP_STATE_HALTED:          the vcpu has executed a HLT instruction and
+                                 is waiting for an interrupt
+ - KVM_MP_STATE_SIPI_RECEIVED:   the vcpu has just received a SIPI (vector
+                                 accesible via KVM_GET_VCPU_EVENTS)
+This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
+irqchip, the multiprocessing state must be maintained by userspace.
+4.38 KVM_SET_MP_STATE
+Capability: KVM_CAP_MP_STATE
+Architectures: x86, ia64
+Type: vcpu ioctl
+Parameters: struct kvm_mp_state (in)
+Returns: 0 on success; -1 on error
+Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
+arguments.
+This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
+irqchip, the multiprocessing state must be maintained by userspace.
 5. The kvm_run structure
@@ -795,11 +977,11 @@ Unused.
                        __u64 data_offset; /* relative to kvm_run start */
                } io;
-If exit_reason is KVM_EXIT_IO_IN or KVM_EXIT_IO_OUT, then the vcpu has
+If exit_reason is KVM_EXIT_IO, then the vcpu has
 executed a port I/O instruction which could not be satisfied by kvm.
 data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
 where kvm expects application code to place the data for the next
-KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a patcked array.
+KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a packed array.
                struct {
                        struct kvm_debug_exit_arch arch;
@@ -815,11 +997,18 @@ Unused.
                        __u8  is_write;
                } mmio;
-If exit_reason is KVM_EXIT_MMIO or KVM_EXIT_IO_OUT, then the vcpu has
+If exit_reason is KVM_EXIT_MMIO, then the vcpu has
 executed a memory-mapped I/O instruction which could not be satisfied
 by kvm.  The 'data' member contains the written data if 'is_write' is
 true, and should be filled by application code otherwise.
+NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO and KVM_EXIT_OSI, the corresponding
+operations are complete (and guest state is consistent) only after userspace
+has re-entered the kernel with KVM_RUN.  The kernel side will first finish
+incomplete operations and then check for pending signals.  Userspace
+can re-enter the guest with an unmasked signal pending to complete
+pending operations.
                /* KVM_EXIT_HYPERCALL */
                struct {
                        __u64 nr;
@@ -829,7 +1018,9 @@ true, and should be filled by application code otherwise.
                        __u32 pad;
                } hypercall;
-Unused.
+Unused.  This was once used for 'hypercall to userspace'.  To implement
+such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO (all except s390).
+Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO.
                /* KVM_EXIT_TPR_ACCESS */
                struct {
@@ -870,6 +1061,19 @@ s390 specific.
 powerpc specific.
+                /* KVM_EXIT_OSI */
+                struct {
+                        __u64 gprs[32];
+                } osi;
+MOL uses a special hypercall interface it calls 'OSI'. To enable it, we catch
+hypercalls and exit with this exit struct that contains all the guest gprs.
+If exit_reason is KVM_EXIT_OSI, then the vcpu has triggered such a hypercall.
+Userspace can now handle the hypercall and when it's done modify the gprs as
+necessary. Upon guest entry all guest GPRs will then be replaced by the values
+in this struct.
                /* Fix the size of the union. */
                char padding[256];
        };
diff --git a/Documentation/kvm/cpuid.txt b/Documentation/kvm/cpuid.txt
new file mode 100644
index 000000000000..14a12ea92b7f
--- /dev/null
+++ b/Documentation/kvm/cpuid.txt
@@ -0,0 +1,42 @@
+KVM CPUID bits
+Glauber Costa <glommer@redhat.com>, Red Hat Inc, 2010
+=====================================================
+A guest running on a kvm host, can check some of its features using
+cpuid. This is not always guaranteed to work, since userspace can
+mask-out some, or even all KVM-related cpuid features before launching
+a guest.
+KVM cpuid functions are:
+function: KVM_CPUID_SIGNATURE (0x40000000)
+returns : eax = 0,
+          ebx = 0x4b4d564b,
+          ecx = 0x564b4d56,
+          edx = 0x4d.
+Note that this value in ebx, ecx and edx corresponds to the string "KVMKVMKVM".
+This function queries the presence of KVM cpuid leafs.
+function: define KVM_CPUID_FEATURES (0x40000001)
+returns : ebx, ecx, edx = 0
+          eax = and OR'ed group of (1 << flag), where each flags is:
+flag                               || value || meaning
+=============================================================================
+KVM_FEATURE_CLOCKSOURCE            ||     0 || kvmclock available at msrs
+                                   ||       || 0x11 and 0x12.
+------------------------------------------------------------------------------
+KVM_FEATURE_NOP_IO_DELAY           ||     1 || not necessary to perform delays
+                                   ||       || on PIO operations.
+------------------------------------------------------------------------------
+KVM_FEATURE_MMU_OP                 ||     2 || deprecated.
+------------------------------------------------------------------------------
+KVM_FEATURE_CLOCKSOURCE2           ||     3 || kvmclock available at msrs
+                                   ||       || 0x4b564d00 and 0x4b564d01
+------------------------------------------------------------------------------
+KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side
+                                   ||       || per-cpu warps are expected in
+                                   ||       || kvmclock.
+------------------------------------------------------------------------------
diff --git a/Documentation/kvm/mmu.txt b/Documentation/kvm/mmu.txt
new file mode 100644
index 000000000000..aaed6ab9d7ab
--- /dev/null
+++ b/Documentation/kvm/mmu.txt
@@ -0,0 +1,304 @@
+The x86 kvm shadow mmu
+======================
+The mmu (in arch/x86/kvm, files mmu.[ch] and paging_tmpl.h) is responsible
+for presenting a standard x86 mmu to the guest, while translating guest
+physical addresses to host physical addresses.
+The mmu code attempts to satisfy the following requirements:
+- correctness: the guest should not be able to determine that it is running
+               on an emulated mmu except for timing (we attempt to comply
+               with the specification, not emulate the characteristics of
+               a particular implementation such as tlb size)
+- security:    the guest must not be able to touch host memory not assigned
+               to it
+- performance: minimize the performance penalty imposed by the mmu
+- scaling:     need to scale to large memory and large vcpu guests
+- hardware:    support the full range of x86 virtualization hardware
+- integration: Linux memory management code must be in control of guest memory
+               so that swapping, page migration, page merging, transparent
+               hugepages, and similar features work without change
+- dirty tracking: report writes to guest memory to enable live migration
+               and framebuffer-based displays
+- footprint:   keep the amount of pinned kernel memory low (most memory
+               should be shrinkable)
+- reliablity:  avoid multipage or GFP_ATOMIC allocations
+Acronyms
+========
+pfn   host page frame number
+hpa   host physical address
+hva   host virtual address
+gfn   guest frame number
+gpa   guest physical address
+gva   guest virtual address
+ngpa  nested guest physical address
+ngva  nested guest virtual address
+pte   page table entry (used also to refer generically to paging structure
+      entries)
+gpte  guest pte (referring to gfns)
+spte  shadow pte (referring to pfns)
+tdp   two dimensional paging (vendor neutral term for NPT and EPT)
+Virtual and real hardware supported
+===================================
+The mmu supports first-generation mmu hardware, which allows an atomic switch
+of the current paging mode and cr3 during guest entry, as well as
+two-dimensional paging (AMD's NPT and Intel's EPT).  The emulated hardware
+it exposes is the traditional 2/3/4 level x86 mmu, with support for global
+pages, pae, pse, pse36, cr0.wp, and 1GB pages.  Work is in progress to support
+exposing NPT capable hardware on NPT capable hosts.
+Translation
+===========
+The primary job of the mmu is to program the processor's mmu to translate
+addresses for the guest.  Different translations are required at different
+times:
+- when guest paging is disabled, we translate guest physical addresses to
+  host physical addresses (gpa->hpa)
+- when guest paging is enabled, we translate guest virtual addresses, to
+  guest physical addresses, to host physical addresses (gva->gpa->hpa)
+- when the guest launches a guest of its own, we translate nested guest
+  virtual addresses, to nested guest physical addresses, to guest physical
+  addresses, to host physical addresses (ngva->ngpa->gpa->hpa)
+The primary challenge is to encode between 1 and 3 translations into hardware
+that support only 1 (traditional) and 2 (tdp) translations.  When the
+number of required translations matches the hardware, the mmu operates in
+direct mode; otherwise it operates in shadow mode (see below).
+Memory
+======
+Guest memory (gpa) is part of the user address space of the process that is
+using kvm.  Userspace defines the translation between guest addresses and user
+addresses (gpa->hva); note that two gpas may alias to the same gva, but not
+vice versa.
+These gvas may be backed using any method available to the host: anonymous
+memory, file backed memory, and device memory.  Memory might be paged by the
+host at any time.
+Events
+======
+The mmu is driven by events, some from the guest, some from the host.
+Guest generated events:
+- writes to control registers (especially cr3)
+- invlpg/invlpga instruction execution
+- access to missing or protected translations
+Host generated events:
+- changes in the gpa->hpa translation (either through gpa->hva changes or
+  through hva->hpa changes)
+- memory pressure (the shrinker)
+Shadow pages
+============
+The principal data structure is the shadow page, 'struct kvm_mmu_page'.  A
+shadow page contains 512 sptes, which can be either leaf or nonleaf sptes.  A
+shadow page may contain a mix of leaf and nonleaf sptes.
+A nonleaf spte allows the hardware mmu to reach the leaf pages and
+is not related to a translation directly.  It points to other shadow pages.
+A leaf spte corresponds to either one or two translations encoded into
+one paging structure entry.  These are always the lowest level of the
+translation stack, with optional higher level translations left to NPT/EPT.
+Leaf ptes point at guest pages.
+The following table shows translations encoded by leaf ptes, with higher-level
+translations in parentheses:
+ Non-nested guests:
+  nonpaging:     gpa->hpa
+  paging:        gva->gpa->hpa
+  paging, tdp:   (gva->)gpa->hpa
+ Nested guests:
+  non-tdp:       ngva->gpa->hpa  (*)
+  tdp:           (ngva->)ngpa->gpa->hpa
+(*) the guest hypervisor will encode the ngva->gpa translation into its page
+    tables if npt is not present
+Shadow pages contain the following information:
+  role.level:
+    The level in the shadow paging hierarchy that this shadow page belongs to.
+    1=4k sptes, 2=2M sptes, 3=1G sptes, etc.
+  role.direct:
+    If set, leaf sptes reachable from this page are for a linear range.
+    Examples include real mode translation, large guest pages backed by small
+    host pages, and gpa->hpa translations when NPT or EPT is active.
+    The linear range starts at (gfn << PAGE_SHIFT) and its size is determined
+    by role.level (2MB for first level, 1GB for second level, 0.5TB for third
+    level, 256TB for fourth level)
+    If clear, this page corresponds to a guest page table denoted by the gfn
+    field.
+  role.quadrant:
+    When role.cr4_pae=0, the guest uses 32-bit gptes while the host uses 64-bit
+    sptes.  That means a guest page table contains more ptes than the host,
+    so multiple shadow pages are needed to shadow one guest page.
+    For first-level shadow pages, role.quadrant can be 0 or 1 and denotes the
+    first or second 512-gpte block in the guest page table.  For second-level
+    page tables, each 32-bit gpte is converted to two 64-bit sptes
+    (since each first-level guest page is shadowed by two first-level
+    shadow pages) so role.quadrant takes values in the range 0..3.  Each
+    quadrant maps 1GB virtual address space.
+  role.access:
+    Inherited guest access permissions in the form uwx.  Note execute
+    permission is positive, not negative.
+  role.invalid:
+    The page is invalid and should not be used.  It is a root page that is
+    currently pinned (by a cpu hardware register pointing to it); once it is
+    unpinned it will be destroyed.
+  role.cr4_pae:
+    Contains the value of cr4.pae for which the page is valid (e.g. whether
+    32-bit or 64-bit gptes are in use).
+  role.cr4_nxe:
+    Contains the value of efer.nxe for which the page is valid.
+  role.cr0_wp:
+    Contains the value of cr0.wp for which the page is valid.
+  gfn:
+    Either the guest page table containing the translations shadowed by this
+    page, or the base page frame for linear translations.  See role.direct.
+  spt:
+    A pageful of 64-bit sptes containing the translations for this page.
+    Accessed by both kvm and hardware.
+    The page pointed to by spt will have its page->private pointing back
+    at the shadow page structure.
+    sptes in spt point either at guest pages, or at lower-level shadow pages.
+    Specifically, if sp1 and sp2 are shadow pages, then sp1->spt[n] may point
+    at __pa(sp2->spt).  sp2 will point back at sp1 through parent_pte.
+    The spt array forms a DAG structure with the shadow page as a node, and
+    guest pages as leaves.
+  gfns:
+    An array of 512 guest frame numbers, one for each present pte.  Used to
+    perform a reverse map from a pte to a gfn.
+  slot_bitmap:
+    A bitmap containing one bit per memory slot.  If the page contains a pte
+    mapping a page from memory slot n, then bit n of slot_bitmap will be set
+    (if a page is aliased among several slots, then it is not guaranteed that
+    all slots will be marked).
+    Used during dirty logging to avoid scanning a shadow page if none if its
+    pages need tracking.
+  root_count:
+    A counter keeping track of how many hardware registers (guest cr3 or
+    pdptrs) are now pointing at the page.  While this counter is nonzero, the
+    page cannot be destroyed.  See role.invalid.
+  multimapped:
+    Whether there exist multiple sptes pointing at this page.
+  parent_pte/parent_ptes:
+    If multimapped is zero, parent_pte points at the single spte that points at
+    this page's spt.  Otherwise, parent_ptes points at a data structure
+    with a list of parent_ptes.
+  unsync:
+    If true, then the translations in this page may not match the guest's
+    translation.  This is equivalent to the state of the tlb when a pte is
+    changed but before the tlb entry is flushed.  Accordingly, unsync ptes
+    are synchronized when the guest executes invlpg or flushes its tlb by
+    other means.  Valid for leaf pages.
+  unsync_children:
+    How many sptes in the page point at pages that are unsync (or have
+    unsynchronized children).
+  unsync_child_bitmap:
+    A bitmap indicating which sptes in spt point (directly or indirectly) at
+    pages that may be unsynchronized.  Used to quickly locate all unsychronized
+    pages reachable from a given page.
+Reverse map
+===========
+The mmu maintains a reverse mapping whereby all ptes mapping a page can be
+reached given its gfn.  This is used, for example, when swapping out a page.
+Synchronized and unsynchronized pages
+=====================================
+The guest uses two events to synchronize its tlb and page tables: tlb flushes
+and page invalidations (invlpg).
+A tlb flush means that we need to synchronize all sptes reachable from the
+guest's cr3.  This is expensive, so we keep all guest page tables write
+protected, and synchronize sptes to gptes when a gpte is written.
+A special case is when a guest page table is reachable from the current
+guest cr3.  In this case, the guest is obliged to issue an invlpg instruction
+before using the translation.  We take advantage of that by removing write
+protection from the guest page, and allowing the guest to modify it freely.
+We synchronize modified gptes when the guest invokes invlpg.  This reduces
+the amount of emulation we have to do when the guest modifies multiple gptes,
+or when the a guest page is no longer used as a page table and is used for
+random guest data.
+As a side effect we have to resynchronize all reachable unsynchronized shadow
+pages on a tlb flush.
+Reaction to events
+==================
+- guest page fault (or npt page fault, or ept violation)
+This is the most complicated event.  The cause of a page fault can be:
+  - a true guest fault (the guest translation won't allow the access) (*)
+  - access to a missing translation
+  - access to a protected translation
+    - when logging dirty pages, memory is write protected
+    - synchronized shadow pages are write protected (*)
+  - access to untranslatable memory (mmio)
+  (*) not applicable in direct mode
+Handling a page fault is performed as follows:
+ - if needed, walk the guest page tables to determine the guest translation
+   (gva->gpa or ngpa->gpa)
+   - if permissions are insufficient, reflect the fault back to the guest
+ - determine the host page
+   - if this is an mmio request, there is no host page; call the emulator
+     to emulate the instruction instead
+ - walk the shadow page table to find the spte for the translation,
+   instantiating missing intermediate page tables as necessary
+ - try to unsynchronize the page
+   - if successful, we can let the guest continue and modify the gpte
+ - emulate the instruction
+   - if failed, unshadow the page and let the guest continue
+ - update any translations that were modified by the instruction
+invlpg handling:
+  - walk the shadow page hierarchy and drop affected translations
+  - try to reinstantiate the indicated translation in the hope that the
+    guest will use it in the near future
+Guest control register updates:
+- mov to cr3
+  - look up new shadow roots
+  - synchronize newly reachable shadow pages
+- mov to cr0/cr4/efer
+  - set up mmu context for new paging mode
+  - look up new shadow roots
+  - synchronize newly reachable shadow pages
+Host translation updates:
+  - mmu notifier called with updated hva
+  - look up affected sptes through reverse map
+  - drop (or update) translations
+Further reading
+===============
+- NPT presentation from KVM Forum 2008
+  http://www.linux-kvm.org/wiki/images/c/c8/KvmForum2008%24kdf2008_21.pdf
diff --git a/Documentation/laptops/00-INDEX b/Documentation/laptops/00-INDEX
index ee5692b26dd4..fa688538e757 100644
--- a/Documentation/laptops/00-INDEX
+++ b/Documentation/laptops/00-INDEX
@@ -2,6 +2,12 @@
        - This file
 acer-wmi.txt
        - information on the Acer Laptop WMI Extras driver.
+asus-laptop.txt
+        - information on the Asus Laptop Extras driver.
+disk-shock-protection.txt
+        - information on hard disk shock protection.
+dslm.c
+        - Simple Disk Sleep Monitor program
 laptop-mode.txt
        - how to conserve battery power using laptop-mode.
 sony-laptop.txt
diff --git a/Documentation/laptops/Makefile b/Documentation/laptops/Makefile
new file mode 100644
index 000000000000..5cb144af3c09
--- /dev/null
+++ b/Documentation/laptops/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+# List of programs to build
+hostprogs-y := dslm
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/laptops/dslm.c b/Documentation/laptops/dslm.c
new file mode 100644
index 000000000000..72ff290c5fc6
--- /dev/null
+++ b/Documentation/laptops/dslm.c
@@ -0,0 +1,166 @@
+/*
+ * dslm.c
+ * Simple Disk Sleep Monitor
+ *  by Bartek Kania
+ * Licenced under the GPL
+ */
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <time.h>
+#include <string.h>
+#include <signal.h>
+#include <sys/ioctl.h>
+#include <linux/hdreg.h>
+#ifdef DEBUG
+#define D(x) x
+#else
+#define D(x)
+#endif
+int endit = 0;
+/* Check if the disk is in powersave-mode
+ * Most of the code is stolen from hdparm.
+ * 1 = active, 0 = standby/sleep, -1 = unknown */
+static int check_powermode(int fd)
+{
+    unsigned char args[4] = {WIN_CHECKPOWERMODE1,0,0,0};
+    int state;
+    if (ioctl(fd, HDIO_DRIVE_CMD, &args)
+        && (args[0] = WIN_CHECKPOWERMODE2) /* try again with 0x98 */
+        && ioctl(fd, HDIO_DRIVE_CMD, &args)) {
+        if (errno != EIO || args[0] != 0 || args[1] != 0) {
+            state = -1; /* "unknown"; */
+        } else
+            state = 0; /* "sleeping"; */
+    } else {
+        state = (args[2] == 255) ? 1 : 0;
+    }
+    D(printf(" drive state is:  %d\n", state));
+    return state;
+}
+static char *state_name(int i)
+{
+    if (i == -1) return "unknown";
+    if (i == 0) return "sleeping";
+    if (i == 1) return "active";
+    return "internal error";
+}
+static char *myctime(time_t time)
+{
+    char *ts = ctime(&time);
+    ts[strlen(ts) - 1] = 0;
+    return ts;
+}
+static void measure(int fd)
+{
+    time_t start_time;
+    int last_state;
+    time_t last_time;
+    int curr_state;
+    time_t curr_time = 0;
+    time_t time_diff;
+    time_t active_time = 0;
+    time_t sleep_time = 0;
+    time_t unknown_time = 0;
+    time_t total_time = 0;
+    int changes = 0;
+    float tmp;
+    printf("Starting measurements\n");
+    last_state = check_powermode(fd);
+    start_time = last_time = time(0);
+    printf("  System is in state %s\n\n", state_name(last_state));
+    while(!endit) {
+        sleep(1);
+        curr_state = check_powermode(fd);
+        if (curr_state != last_state || endit) {
+            changes++;
+            curr_time = time(0);
+            time_diff = curr_time - last_time;
+            if (last_state == 1) active_time += time_diff;
+            else if (last_state == 0) sleep_time += time_diff;
+            else unknown_time += time_diff;
+            last_state = curr_state;
+            last_time = curr_time;
+            printf("%s: State-change to %s\n", myctime(curr_time),
+                   state_name(curr_state));
+        }
+    }
+    changes--; /* Compensate for SIGINT */
+    total_time = time(0) - start_time;
+    printf("\nTotal running time:  %lus\n", curr_time - start_time);
+    printf(" State changed %d times\n", changes);
+    tmp = (float)sleep_time / (float)total_time * 100;
+    printf(" Time in sleep state:   %lus (%.2f%%)\n", sleep_time, tmp);
+    tmp = (float)active_time / (float)total_time * 100;
+    printf(" Time in active state:  %lus (%.2f%%)\n", active_time, tmp);
+    tmp = (float)unknown_time / (float)total_time * 100;
+    printf(" Time in unknown state: %lus (%.2f%%)\n", unknown_time, tmp);
+}
+static void ender(int s)
+{
+    endit = 1;
+}
+static void usage(void)
+{
+    puts("usage: dslm [-w <time>] <disk>");
+    exit(0);
+}
+int main(int argc, char **argv)
+{
+    int fd;
+    char *disk = 0;
+    int settle_time = 60;
+    /* Parse the simple command-line */
+    if (argc == 2)
+        disk = argv[1];
+    else if (argc == 4) {
+        settle_time = atoi(argv[2]);
+        disk = argv[3];
+    } else
+        usage();
+    if (!(fd = open(disk, O_RDONLY|O_NONBLOCK))) {
+        printf("Can't open %s, because: %s\n", disk, strerror(errno));
+        exit(-1);
+    }
+    if (settle_time) {
+        printf("Waiting %d seconds for the system to settle down to "
+               "'normal'\n", settle_time);
+        sleep(settle_time);
+    } else
+        puts("Not waiting for system to settle down");
+    signal(SIGINT, ender);
+    measure(fd);
+    close(fd);
+    return 0;
+}
diff --git a/Documentation/laptops/laptop-mode.txt b/Documentation/laptops/laptop-mode.txt
index eeedee11c8c2..0bf25eebce94 100644
--- a/Documentation/laptops/laptop-mode.txt
+++ b/Documentation/laptops/laptop-mode.txt
@@ -207,7 +207,7 @@ Tips & Tricks
 * Drew Scott Daniels observed: "I don't know why, but when I decrease the number
  of colours that my display uses it consumes less battery power. I've seen
  this on powerbooks too. I hope that this is a piece of information that
-  might be useful to the Laptop Mode patch or it's users."
+  might be useful to the Laptop Mode patch or its users."
 * In syslog.conf, you can prefix entries with a dash ``-'' to omit syncing the
  file after every logging. When you're using laptop-mode and your disk doesn't
@@ -779,172 +779,4 @@ Monitoring tool
 ---------------
 Bartek Kania submitted this, it can be used to measure how much time your disk
-spends spun up/down.
+spends spun up/down.  See Documentation/laptops/dslm.c
---------------------------dslm.c BEGIN-----------------------------------------
-/*
- * Simple Disk Sleep Monitor
- *  by Bartek Kania
- * Licenced under the GPL
- */
-#include <unistd.h>
-#include <stdlib.h>
-#include <stdio.h>
-#include <fcntl.h>
-#include <errno.h>
-#include <time.h>
-#include <string.h>
-#include <signal.h>
-#include <sys/ioctl.h>
-#include <linux/hdreg.h>
-#ifdef DEBUG
-#define D(x) x
-#else
-#define D(x)
-#endif
-int endit = 0;
-/* Check if the disk is in powersave-mode
- * Most of the code is stolen from hdparm.
- * 1 = active, 0 = standby/sleep, -1 = unknown */
-int check_powermode(int fd)
-{
-    unsigned char args[4] = {WIN_CHECKPOWERMODE1,0,0,0};
-    int state;
-    if (ioctl(fd, HDIO_DRIVE_CMD, &args)
-        && (args[0] = WIN_CHECKPOWERMODE2) /* try again with 0x98 */
-        && ioctl(fd, HDIO_DRIVE_CMD, &args)) {
-        if (errno != EIO || args[0] != 0 || args[1] != 0) {
-            state = -1; /* "unknown"; */
-        } else
-            state = 0; /* "sleeping"; */
-    } else {
-        state = (args[2] == 255) ? 1 : 0;
-    }
-    D(printf(" drive state is:  %d\n", state));
-    return state;
-}
-char *state_name(int i)
-{
-    if (i == -1) return "unknown";
-    if (i == 0) return "sleeping";
-    if (i == 1) return "active";
-    return "internal error";
-}
-char *myctime(time_t time)
-{
-    char *ts = ctime(&time);
-    ts[strlen(ts) - 1] = 0;
-    return ts;
-}
-void measure(int fd)
-{
-    time_t start_time;
-    int last_state;
-    time_t last_time;
-    int curr_state;
-    time_t curr_time = 0;
-    time_t time_diff;
-    time_t active_time = 0;
-    time_t sleep_time = 0;
-    time_t unknown_time = 0;
-    time_t total_time = 0;
-    int changes = 0;
-    float tmp;
-    printf("Starting measurements\n");
-    last_state = check_powermode(fd);
-    start_time = last_time = time(0);
-    printf("  System is in state %s\n\n", state_name(last_state));
-    while(!endit) {
-        sleep(1);
-        curr_state = check_powermode(fd);
-        if (curr_state != last_state || endit) {
-            changes++;
-            curr_time = time(0);
-            time_diff = curr_time - last_time;
-            if (last_state == 1) active_time += time_diff;
-            else if (last_state == 0) sleep_time += time_diff;
-            else unknown_time += time_diff;
-            last_state = curr_state;
-            last_time = curr_time;
-            printf("%s: State-change to %s\n", myctime(curr_time),
-                   state_name(curr_state));
-        }
-    }
-    changes--; /* Compensate for SIGINT */
-    total_time = time(0) - start_time;
-    printf("\nTotal running time:  %lus\n", curr_time - start_time);
-    printf(" State changed %d times\n", changes);
-    tmp = (float)sleep_time / (float)total_time * 100;
-    printf(" Time in sleep state:   %lus (%.2f%%)\n", sleep_time, tmp);
-    tmp = (float)active_time / (float)total_time * 100;
-    printf(" Time in active state:  %lus (%.2f%%)\n", active_time, tmp);
-    tmp = (float)unknown_time / (float)total_time * 100;
-    printf(" Time in unknown state: %lus (%.2f%%)\n", unknown_time, tmp);
-}
-void ender(int s)
-{
-    endit = 1;
-}
-void usage()
-{
-    puts("usage: dslm [-w <time>] <disk>");
-    exit(0);
-}
-int main(int argc, char **argv)
-{
-    int fd;
-    char *disk = 0;
-    int settle_time = 60;
-    /* Parse the simple command-line */
-    if (argc == 2)
-        disk = argv[1];
-    else if (argc == 4) {
-        settle_time = atoi(argv[2]);
-        disk = argv[3];
-    } else
-        usage();
-    if (!(fd = open(disk, O_RDONLY|O_NONBLOCK))) {
-        printf("Can't open %s, because: %s\n", disk, strerror(errno));
-        exit(-1);
-    }
-    if (settle_time) {
-        printf("Waiting %d seconds for the system to settle down to "
-               "'normal'\n", settle_time);
-        sleep(settle_time);
-    } else
-        puts("Not waiting for system to settle down");
-    signal(SIGINT, ender);
-    measure(fd);
-    close(fd);
-    return 0;
-}
---------------------------dslm.c END-------------------------------------------
diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt
index 75afa1229fd7..fc15538d8b46 100644
--- a/Documentation/laptops/thinkpad-acpi.txt
+++ b/Documentation/laptops/thinkpad-acpi.txt
@@ -292,13 +292,13 @@ sysfs notes:
                Warning: when in NVRAM mode, the volume up/down/mute
                keys are synthesized according to changes in the mixer,
-                so you have to use volume up or volume down to unmute,
+                which uses a single volume up or volume down hotkey
-                as per the ThinkPad volume mixer user interface.  When
+                press to unmute, as per the ThinkPad volume mixer user
-                in ACPI event mode, volume up/down/mute are reported as
+                interface.  When in ACPI event mode, volume up/down/mute
-                separate events, but this behaviour may be corrected in
+                events are reported by the firmware and can behave
-                future releases of this driver, in which case the
+                differently (and that behaviour changes with firmware
-                ThinkPad volume mixer user interface semantics will be
+                version -- not just with firmware models -- as well as
-                enforced.
+                OSI(Linux) state).
        hotkey_poll_freq:
                frequency in Hz for hot key polling. It must be between
@@ -309,7 +309,7 @@ sysfs notes:
                will cause hot key presses that require NVRAM polling
                to never be reported.
-                Setting hotkey_poll_freq too low will cause repeated
+                Setting hotkey_poll_freq too low may cause repeated
                pressings of the same hot key to be misreported as a
                single key press, or to not even be detected at all.
                The recommended polling frequency is 10Hz.
@@ -397,6 +397,7 @@ ACPI	Scan
 event   code    Key             Notes
 0x1001  0x00    FN+F1           -
 0x1002  0x01    FN+F2           IBM: battery (rare)
                                Lenovo: Screen lock
@@ -404,7 +405,8 @@ event	code	Key		Notes
                                this hot key, even with hot keys
                                disabled or with Fn+F3 masked
                                off
-                                IBM: screen lock
+                                IBM: screen lock, often turns
+                                off the ThinkLight as side-effect
                                Lenovo: battery
 0x1004  0x03    FN+F4           Sleep button (ACPI sleep button
@@ -433,7 +435,8 @@ event	code	Key		Notes
                                Do you feel lucky today?
 0x1008  0x07    FN+F8           IBM: toggle screen expand
-                                Lenovo: configure UltraNav
+                                Lenovo: configure UltraNav,
+                                or toggle screen expand
 0x1009  0x08    FN+F9           -
        ..      ..              ..
@@ -444,7 +447,7 @@ event	code	Key		Notes
                                either through the ACPI event,
                                or through a hotkey event.
                                The firmware may refuse to
-                                generate further FN+F4 key
+                                generate further FN+F12 key
                                press events until a S3 or S4
                                ACPI sleep cycle is performed,
                                or some time passes.
@@ -512,15 +515,19 @@ events for switches:
 SW_RFKILL_ALL   T60 and later hardware rfkill rocker switch
 SW_TABLET_MODE  Tablet ThinkPads HKEY events 0x5009 and 0x500A
-Non hot-key ACPI HKEY event map:
+Non hotkey ACPI HKEY event map:
+-------------------------------
+Events that are not propagated by the driver, except for legacy
+compatibility purposes when hotkey_report_mode is set to 1:
 0x5001          Lid closed
 0x5002          Lid opened
 0x5009          Tablet swivel: switched to tablet mode
 0x500A          Tablet swivel: switched to normal mode
 0x7000          Radio Switch may have changed state
-The above events are not propagated by the driver, except for legacy
+Events that are never propagated by the driver:
-compatibility purposes when hotkey_report_mode is set to 1.
 0x2304          System is waking up from suspend to undock
 0x2305          System is waking up from suspend to eject bay
@@ -528,14 +535,39 @@ compatibility purposes when hotkey_report_mode is set to 1.
 0x2405          System is waking up from hibernation to eject bay
 0x5010          Brightness level changed/control event
-The above events are never propagated by the driver.
+Events that are propagated by the driver to userspace:
+0x2313          ALARM: System is waking up from suspend because
+                the battery is nearly empty
+0x2413          ALARM: System is waking up from hibernation because
+                the battery is nearly empty
 0x3003          Bay ejection (see 0x2x05) complete, can sleep again
+0x3006          Bay hotplug request (hint to power up SATA link when
+                the optical drive tray is ejected)
 0x4003          Undocked (see 0x2x04), can sleep again
 0x500B          Tablet pen inserted into its storage bay
 0x500C          Tablet pen removed from its storage bay
+0x6011          ALARM: battery is too hot
-The above events are propagated by the driver.
+0x6012          ALARM: battery is extremely hot
+0x6021          ALARM: a sensor is too hot
+0x6022          ALARM: a sensor is extremely hot
+0x6030          System thermal table changed
+Battery nearly empty alarms are a last resort attempt to get the
+operating system to hibernate or shutdown cleanly (0x2313), or shutdown
+cleanly (0x2413) before power is lost.  They must be acted upon, as the
+wake up caused by the firmware will have negated most safety nets...
+When any of the "too hot" alarms happen, according to Lenovo the user
+should suspend or hibernate the laptop (and in the case of battery
+alarms, unplug the AC adapter) to let it cool down.  These alarms do
+signal that something is wrong, they should never happen on normal
+operating conditions.
+The "extremely hot" alarms are emergencies.  According to Lenovo, the
+operating system is to force either an immediate suspend or hibernate
+cycle, or a system shutdown.  Obviously, something is very wrong if this
+happens.
 Compatibility notes:
@@ -650,6 +682,10 @@ LCD, CRT or DVI (if available). The following commands are available:
        echo expand_toggle > /proc/acpi/ibm/video
        echo video_switch > /proc/acpi/ibm/video
+NOTE: Access to this feature is restricted to processes owning the
+CAP_SYS_ADMIN capability for safety reasons, as it can interact badly
+enough with some versions of X.org to crash it.
 Each video output device can be enabled or disabled individually.
 Reading /proc/acpi/ibm/video shows the status of each device.
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 42208511b5c0..e9ce3c554514 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -34,7 +34,6 @@
 #include <sys/uio.h>
 #include <termios.h>
 #include <getopt.h>
-#include <zlib.h>
 #include <assert.h>
 #include <sched.h>
 #include <limits.h>
@@ -264,7 +263,7 @@ static u8 *get_feature_bits(struct device *dev)
 * Launcher virtual with an offset.
 *
 * This can be tough to get your head around, but usually it just means that we
- * use these trivial conversion functions when the Guest gives us it's
+ * use these trivial conversion functions when the Guest gives us its
 * "physical" addresses:
 */
 static void *from_guest_phys(unsigned long addr)
diff --git a/Documentation/md.txt b/Documentation/md.txt
index 188f4768f1d5..e4e893ef3e01 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -136,7 +136,7 @@ raid_disks != 0.
 Then uninitialized devices can be added with ADD_NEW_DISK.  The
 structure passed to ADD_NEW_DISK must specify the state of the device
-and it's role in the array.
+and its role in the array.
 Once started with RUN_ARRAY, uninitialized spares can be added with
 HOT_ADD_DISK.
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 7f5809eddee6..631ad2f1b229 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -3,6 +3,7 @@
                         ============================
 By: David Howells <dhowells@redhat.com>
+    Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 Contents:
@@ -60,6 +61,10 @@ Contents:
     - And then there's the Alpha.
+ (*) Example uses.
+     - Circular buffers.
 (*) References.
@@ -2226,6 +2231,21 @@ The Alpha defines the Linux kernel's memory barrier model.
 See the subsection on "Cache Coherency" above.
+============
+EXAMPLE USES
+============
+CIRCULAR BUFFERS
+----------------
+Memory barriers can be used to implement circular buffering without the need
+of a lock to serialise the producer with the consumer.  See:
+        Documentation/circular-buffers.txt
+for details.
 ==========
 REFERENCES
 ==========
diff --git a/Documentation/netlabel/lsm_interface.txt b/Documentation/netlabel/lsm_interface.txt
index 98dd9f7430f2..638c74f7de7f 100644
--- a/Documentation/netlabel/lsm_interface.txt
+++ b/Documentation/netlabel/lsm_interface.txt
@@ -38,7 +38,7 @@ Depending on the exact configuration, translation between the network packet
 label and the internal LSM security identifier can be time consuming.  The
 NetLabel label mapping cache is a caching mechanism which can be used to
 sidestep much of this overhead once a mapping has been established.  Once the
-LSM has received a packet, used NetLabel to decode it's security attributes,
+LSM has received a packet, used NetLabel to decode its security attributes,
 and translated the security attributes into a LSM internal identifier the LSM
 can use the NetLabel caching functions to associate the LSM internal
 identifier with the network packet's label.  This means that in the future
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index 50189bf07d53..fe5c099b8fc8 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -32,6 +32,8 @@ cs89x0.txt
        - the Crystal LAN (CS8900/20-based) Ethernet ISA adapter driver
 cxacru.txt
        - Conexant AccessRunner USB ADSL Modem
+cxacru-cf.py
+        - Conexant AccessRunner USB ADSL Modem configuration file parser
 de4x5.txt
        - the Digital EtherWORKS DE4?? and DE5?? PCI Ethernet driver
 decnet.txt
diff --git a/Documentation/networking/Makefile b/Documentation/networking/Makefile
index 6d8af1ac56c4..5aba7a33aeeb 100644
--- a/Documentation/networking/Makefile
+++ b/Documentation/networking/Makefile
@@ -6,3 +6,5 @@ hostprogs-y := ifenslave
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
+obj-m := timestamping/
diff --git a/Documentation/networking/caif/Linux-CAIF.txt b/Documentation/networking/caif/Linux-CAIF.txt
new file mode 100644
index 000000000000..7fe7a9a33a4f
--- /dev/null
+++ b/Documentation/networking/caif/Linux-CAIF.txt
@@ -0,0 +1,212 @@
+Linux CAIF
+===========
+copyright (C) ST-Ericsson AB 2010
+Author: Sjur Brendeland/ sjur.brandeland@stericsson.com
+License terms: GNU General Public License (GPL) version 2
+Introduction
+------------
+CAIF is a MUX protocol used by ST-Ericsson cellular modems for
+communication between Modem and host. The host processes can open virtual AT
+channels, initiate GPRS Data connections, Video channels and Utility Channels.
+The Utility Channels are general purpose pipes between modem and host.
+ST-Ericsson modems support a number of transports between modem
+and host. Currently, UART and Loopback are available for Linux.
+Architecture:
+------------
+The implementation of CAIF is divided into:
+* CAIF Socket Layer, Kernel API, and  Net Device.
+* CAIF Core Protocol Implementation
+* CAIF Link Layer, implemented as NET devices.
+  RTNL
+   !
+   !     +------+   +------+   +------+
+   !    +------+!  +------+!  +------+!
+   !    ! Sock !!  !Kernel!!  ! Net  !!
+   !    ! API  !+  ! API  !+  ! Dev  !+   <- CAIF Client APIs
+   !    +------+   +------!   +------+
+   !       !          !          !
+   !       +----------!----------+
+   !               +------+               <- CAIF Protocol Implementation
+   +------->       ! CAIF !
+                   ! Core !
+                   +------+
+             +--------!--------+
+             !                 !
+          +------+          +-----+
+          !      !          ! TTY !       <- Link Layer (Net Devices)
+          +------+          +-----+
+Using the Kernel API
+----------------------
+The Kernel API is used for accessing CAIF channels from the
+kernel.
+The user of the API has to implement two callbacks for receive
+and control.
+The receive callback gives a CAIF packet as a SKB. The control
+callback will
+notify of channel initialization complete, and flow-on/flow-
+off.
+  struct caif_device caif_dev = {
+    .caif_config = {
+     .name = "MYDEV"
+     .type = CAIF_CHTY_AT
+    }
+   .receive_cb = my_receive,
+   .control_cb = my_control,
+  };
+  caif_add_device(&caif_dev);
+  caif_transmit(&caif_dev, skb);
+See the caif_kernel.h for details about the CAIF kernel API.
+I M P L E M E N T A T I O N
+===========================
+===========================
+CAIF Core Protocol Layer
+=========================================
+CAIF Core layer implements the CAIF protocol as defined by ST-Ericsson.
+It implements the CAIF protocol stack in a layered approach, where
+each layer described in the specification is implemented as a separate layer.
+The architecture is inspired by the design patterns "Protocol Layer" and
+"Protocol Packet".
+== CAIF structure ==
+The Core CAIF implementation contains:
+      - Simple implementation of CAIF.
+      - Layered architecture (a la Streams), each layer in the CAIF
+        specification is implemented in a separate c-file.
+      - Clients must implement PHY layer to access physical HW
+        with receive and transmit functions.
+      - Clients must call configuration function to add PHY layer.
+      - Clients must implement CAIF layer to consume/produce
+        CAIF payload with receive and transmit functions.
+      - Clients must call configuration function to add and connect the
+        Client layer.
+      - When receiving / transmitting CAIF Packets (cfpkt), ownership is passed
+        to the called function (except for framing layers' receive functions
+        or if a transmit function returns an error, in which case the caller
+        must free the packet).
+Layered Architecture
+--------------------
+The CAIF protocol can be divided into two parts: Support functions and Protocol
+Implementation. The support functions include:
+      - CFPKT CAIF Packet. Implementation of CAIF Protocol Packet. The
+        CAIF Packet has functions for creating, destroying and adding content
+        and for adding/extracting header and trailers to protocol packets.
+      - CFLST CAIF list implementation.
+      - CFGLUE CAIF Glue. Contains OS Specifics, such as memory
+        allocation, endianness, etc.
+The CAIF Protocol implementation contains:
+      - CFCNFG CAIF Configuration layer. Configures the CAIF Protocol
+        Stack and provides a Client interface for adding Link-Layer and
+        Driver interfaces on top of the CAIF Stack.
+      - CFCTRL CAIF Control layer. Encodes and Decodes control messages
+        such as enumeration and channel setup. Also matches request and
+        response messages.
+      - CFSERVL General CAIF Service Layer functionality; handles flow
+        control and remote shutdown requests.
+      - CFVEI CAIF VEI layer. Handles CAIF AT Channels on VEI (Virtual
+        External Interface). This layer encodes/decodes VEI frames.
+      - CFDGML CAIF Datagram layer. Handles CAIF Datagram layer (IP
+        traffic), encodes/decodes Datagram frames.
+      - CFMUX CAIF Mux layer. Handles multiplexing between multiple
+        physical bearers and multiple channels such as VEI, Datagram, etc.
+        The MUX keeps track of the existing CAIF Channels and
+        Physical Instances and selects the apropriate instance based
+        on Channel-Id and Physical-ID.
+      - CFFRML CAIF Framing layer. Handles Framing i.e. Frame length
+        and frame checksum.
+      - CFSERL CAIF Serial layer. Handles concatenation/split of frames
+        into CAIF Frames with correct length.
+                    +---------+
+                    | Config  |
+                    | CFCNFG  |
+                    +---------+
+                         !
+    +---------+     +---------+     +---------+
+    |   AT    |     | Control |     | Datagram|
+    | CFVEIL  |     | CFCTRL  |     | CFDGML  |
+    +---------+     +---------+     +---------+
+           \_____________!______________/
+                         !
+                    +---------+
+                    |   MUX   |
+                    |         |
+                    +---------+
+                    _____!_____
+                   /           \
+            +---------+     +---------+
+            | CFFRML  |     | CFFRML  |
+            | Framing |     | Framing |
+            +---------+     +---------+
+                 !              !
+            +---------+     +---------+
+            |         |     | Serial  |
+            |         |     | CFSERL  |
+            +---------+     +---------+
+In this layered approach the following "rules" apply.
+      - All layers embed the same structure "struct cflayer"
+      - A layer does not depend on any other layer's private data.
+      - Layers are stacked by setting the pointers
+                  layer->up , layer->dn
+      - In order to send data upwards, each layer should do
+                 layer->up->receive(layer->up, packet);
+      - In order to send data downwards, each layer should do
+                 layer->dn->transmit(layer->dn, packet);
+Linux Driver Implementation
+===========================
+Linux GPRS Net Device and CAIF socket are implemented on top of the
+CAIF Core protocol. The Net device and CAIF socket have an instance of
+'struct cflayer', just like the CAIF Core protocol stack.
+Net device and Socket implement the 'receive()' function defined by
+'struct cflayer', just like the rest of the CAIF stack. In this way, transmit and
+receive of packets is handled as by the rest of the layers: the 'dn->transmit()'
+function is called in order to transmit data.
+The layer on top of the CAIF Core implementation is
+sometimes referred to as the "Client layer".
+Configuration of Link Layer
+---------------------------
+The Link Layer is implemented as Linux net devices (struct net_device).
+Payload handling and registration is done using standard Linux mechanisms.
+The CAIF Protocol relies on a loss-less link layer without implementing
+retransmission. This implies that packet drops must not happen.
+Therefore a flow-control mechanism is implemented where the physical
+interface can initiate flow stop for all CAIF Channels.
diff --git a/Documentation/networking/caif/README b/Documentation/networking/caif/README
new file mode 100644
index 000000000000..757ccfaa1385
--- /dev/null
+++ b/Documentation/networking/caif/README
@@ -0,0 +1,109 @@
+Copyright (C) ST-Ericsson AB 2010
+Author: Sjur Brendeland/ sjur.brandeland@stericsson.com
+License terms: GNU General Public License (GPL) version 2
+---------------------------------------------------------
+=== Start ===
+If you have compiled CAIF for modules do:
+$modprobe crc_ccitt
+$modprobe caif
+$modprobe caif_socket
+$modprobe chnl_net
+=== Preparing the setup with a STE modem ===
+If you are working on integration of CAIF you should make sure
+that the kernel is built with module support.
+There are some things that need to be tweaked to get the host TTY correctly
+set up to talk to the modem.
+Since the CAIF stack is running in the kernel and we want to use the existing
+TTY, we are installing our physical serial driver as a line discipline above
+the TTY device.
+To achieve this we need to install the N_CAIF ldisc from user space.
+The benefit is that we can hook up to any TTY.
+The use of Start-of-frame-extension (STX) must also be set as
+module parameter "ser_use_stx".
+Normally Frame Checksum is always used on UART, but this is also provided as a
+module parameter "ser_use_fcs".
+$ modprobe caif_serial ser_ttyname=/dev/ttyS0 ser_use_stx=yes
+$ ifconfig caif_ttyS0 up
+PLEASE NOTE:    There is a limitation in Android shell.
+                It only accepts one argument to insmod/modprobe!
+=== Trouble shooting ===
+There are debugfs parameters provided for serial communication.
+/sys/kernel/debug/caif_serial/<tty-name>/
+* ser_state:   Prints the bit-mask status where
+  - 0x02 means SENDING, this is a transient state.
+  - 0x10 means FLOW_OFF_SENT, i.e. the previous frame has not been sent
+        and is blocking further send operation. Flow OFF has been propagated
+        to all CAIF Channels using this TTY.
+* tty_status: Prints the bit-mask tty status information
+  - 0x01 - tty->warned is on.
+  - 0x02 - tty->low_latency is on.
+  - 0x04 - tty->packed is on.
+  - 0x08 - tty->flow_stopped is on.
+  - 0x10 - tty->hw_stopped is on.
+  - 0x20 - tty->stopped is on.
+* last_tx_msg: Binary blob Prints the last transmitted frame.
+        This can be printed with
+        $od --format=x1 /sys/kernel/debug/caif_serial/<tty>/last_rx_msg.
+        The first two tx messages sent look like this. Note: The initial
+        byte 02 is start of frame extension (STX) used for re-syncing
+        upon errors.
+  - Enumeration:
+        0000000  02 05 00 00 03 01 d2 02
+                 |  |     |  |  |  |
+                 STX(1)   |  |  |  |
+                    Length(2)|  |  |
+                          Control Channel(1)
+                             Command:Enumeration(1)
+                                Link-ID(1)
+                                    Checksum(2)
+  - Channel Setup:
+        0000000  02 07 00 00 00 21 a1 00 48 df
+                 |  |     |  |  |  |  |  |
+                 STX(1)   |  |  |  |  |  |
+                    Length(2)|  |  |  |  |
+                          Control Channel(1)
+                             Command:Channel Setup(1)
+                                Channel Type(1)
+                                    Priority and Link-ID(1)
+                                      Endpoint(1)
+                                          Checksum(2)
+* last_rx_msg: Prints the last transmitted frame.
+        The RX messages for LinkSetup look almost identical but they have the
+        bit 0x20 set in the command bit, and Channel Setup has added one byte
+        before Checksum containing Channel ID.
+        NOTE: Several CAIF Messages might be concatenated. The maximum debug
+        buffer size is 128 bytes.
+== Error Scenarios:
+- last_tx_msg contains channel setup message and last_rx_msg is empty ->
+  The host seems to be able to send over the UART, at least the CAIF ldisc get
+  notified that sending is completed.
+- last_tx_msg contains enumeration message and last_rx_msg is empty ->
+  The host is not able to send the message from UART, the tty has not been
+  able to complete the transmit operation.
+- if /sys/kernel/debug/caif_serial/<tty>/tty_status is non-zero there
+  might be problems transmitting over UART.
+  E.g. host and modem wiring is not correct you will typically see
+  tty_status = 0x10 (hw_stopped) and ser_state = 0x10 (FLOW_OFF_SENT).
+  You will probably see the enumeration message in last_tx_message
+  and empty last_rx_message.
diff --git a/Documentation/networking/cxacru-cf.py b/Documentation/networking/cxacru-cf.py
new file mode 100644
index 000000000000..b41d298398c8
--- /dev/null
+++ b/Documentation/networking/cxacru-cf.py
@@ -0,0 +1,48 @@
+#!/usr/bin/env python
+# Copyright 2009 Simon Arlott
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms of the GNU General Public License as published by the Free
+# Software Foundation; either version 2 of the License, or (at your option)
+# any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+# more details.
+#
+# You should have received a copy of the GNU General Public License along with
+# this program; if not, write to the Free Software Foundation, Inc., 59
+# Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+#
+# Usage: cxacru-cf.py < cxacru-cf.bin
+# Output: values string suitable for the sysfs adsl_config attribute
+#
+# Warning: cxacru-cf.bin with MD5 hash cdbac2689969d5ed5d4850f117702110
+# contains mis-aligned values which will stop the modem from being able
+# to make a connection. If the first and last two bytes are removed then
+# the values become valid, but the modulation will be forced to ANSI
+# T1.413 only which may not be appropriate.
+#
+# The original binary format is a packed list of le32 values.
+import sys
+import struct
+i = 0
+while True:
+        buf = sys.stdin.read(4)
+        if len(buf) == 0:
+                break
+        elif len(buf) != 4:
+                sys.stdout.write("\n")
+                sys.stderr.write("Error: read {0} not 4 bytes\n".format(len(buf)))
+                sys.exit(1)
+        if i > 0:
+                sys.stdout.write(" ")
+        sys.stdout.write("{0:x}={1}".format(i, struct.unpack("<I", buf)[0]))
+        i += 1
+sys.stdout.write("\n")
diff --git a/Documentation/networking/cxacru.txt b/Documentation/networking/cxacru.txt
index b074681a963e..2cce04457b4d 100644
--- a/Documentation/networking/cxacru.txt
+++ b/Documentation/networking/cxacru.txt
@@ -4,6 +4,12 @@ While it is capable of managing/maintaining the ADSL connection without the
 module loaded, the device will sometimes stop responding after unloading the
 driver and it is necessary to unplug/remove power to the device to fix this.
+Note: support for cxacru-cf.bin has been removed. It was not loaded correctly
+so it had no effect on the device configuration. Fixing it could have stopped
+existing devices working when an invalid configuration is supplied.
+There is a script cxacru-cf.py to convert an existing file to the sysfs form.
 Detected devices will appear as ATM devices named "cxacru". In /sys/class/atm/
 these are directories named cxacruN where N is the device number. A symlink
 named device points to the USB interface device's directory which contains
@@ -15,6 +21,15 @@ several sysfs attribute files for retrieving device statistics:
 * adsl_headend_environment
        Information about the remote headend.
+* adsl_config
+        Configuration writing interface.
+        Write parameters in hexadecimal format <index>=<value>,
+        separated by whitespace, e.g.:
+                "1=0 a=5"
+        Up to 7 parameters at a time will be sent and the modem will restart
+        the ADSL connection when any value is set. These are logged for future
+        reference.
 * downstream_attenuation (dB)
 * downstream_bits_per_frame
 * downstream_rate (kbps)
@@ -61,6 +76,7 @@ several sysfs attribute files for retrieving device statistics:
 * mac_address
 * modulation
+        "" (when not connected)
        "ANSI T1.413"
        "ITU-T G.992.1 (G.DMT)"
        "ITU-T G.992.2 (G.LITE)"
diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt
index b132e4a3cf0f..a62fdf7a6bff 100644
--- a/Documentation/networking/dccp.txt
+++ b/Documentation/networking/dccp.txt
@@ -58,8 +58,10 @@ DCCP_SOCKOPT_GET_CUR_MPS is read-only and retrieves the current maximum packet
 size (application payload size) in bytes, see RFC 4340, section 14.
 DCCP_SOCKOPT_AVAILABLE_CCIDS is also read-only and returns the list of CCIDs
-supported by the endpoint (see include/linux/dccp.h for symbolic constants).
+supported by the endpoint. The option value is an array of type uint8_t whose
-The caller needs to provide a sufficiently large (> 2) array of type uint8_t.
+size is passed as option length. The minimum array size is 4 elements, the
+value returned in the optlen argument always reflects the true number of
+built-in CCIDs.
 DCCP_SOCKOPT_CCID is write-only and sets both the TX and RX CCIDs at the same
 time, combining the operation of the next two socket options. This option is
diff --git a/Documentation/networking/ifenslave.c b/Documentation/networking/ifenslave.c
index 1b96ccda3836..2bac9618c345 100644
--- a/Documentation/networking/ifenslave.c
+++ b/Documentation/networking/ifenslave.c
@@ -756,7 +756,7 @@ static int enslave(char *master_ifname, char *slave_ifname)
                 */
                if (abi_ver < 1) {
                        /* For old ABI, the master needs to be
-                         * down before setting it's hwaddr
+                         * down before setting its hwaddr
                         */
                        res = set_if_down(master_ifname, master_flags.ifr_flags);
                        if (res) {
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index e87f3cdc8a6a..d0536b5a4e01 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -487,6 +487,30 @@ tcp_dma_copybreak - INTEGER
        and CONFIG_NET_DMA is enabled.
        Default: 4096
+tcp_thin_linear_timeouts - BOOLEAN
+        Enable dynamic triggering of linear timeouts for thin streams.
+        If set, a check is performed upon retransmission by timeout to
+        determine if the stream is thin (less than 4 packets in flight).
+        As long as the stream is found to be thin, up to 6 linear
+        timeouts may be performed before exponential backoff mode is
+        initiated. This improves retransmission latency for
+        non-aggressive thin streams, often found to be time-dependent.
+        For more information on thin streams, see
+        Documentation/networking/tcp-thin.txt
+        Default: 0
+tcp_thin_dupack - BOOLEAN
+        Enable dynamic triggering of retransmissions after one dupACK
+        for thin streams. If set, a check is performed upon reception
+        of a dupACK to determine if the stream is thin (less than 4
+        packets in flight). As long as the stream is found to be thin,
+        data is retransmitted on the first received dupACK. This
+        improves retransmission latency for non-aggressive thin
+        streams, often found to be time-dependent.
+        For more information on thin streams, see
+        Documentation/networking/tcp-thin.txt
+        Default: 0
 UDP variables:
 udp_mem - vector of 3 INTEGERs: min, pressure, max
@@ -564,6 +588,37 @@ ip_local_port_range - 2 INTEGERS
        (i.e. by default) range 1024-4999 is enough to issue up to
        2000 connections per second to systems supporting timestamps.
+ip_local_reserved_ports - list of comma separated ranges
+        Specify the ports which are reserved for known third-party
+        applications. These ports will not be used by automatic port
+        assignments (e.g. when calling connect() or bind() with port
+        number 0). Explicit port allocation behavior is unchanged.
+        The format used for both input and output is a comma separated
+        list of ranges (e.g. "1,2-4,10-10" for ports 1, 2, 3, 4 and
+        10). Writing to the file will clear all previously reserved
+        ports and update the current list with the one given in the
+        input.
+        Note that ip_local_port_range and ip_local_reserved_ports
+        settings are independent and both are considered by the kernel
+        when determining which ports are available for automatic port
+        assignments.
+        You can reserve ports which are not in the current
+        ip_local_port_range, e.g.:
+        $ cat /proc/sys/net/ipv4/ip_local_port_range
+        32000   61000
+        $ cat /proc/sys/net/ipv4/ip_local_reserved_ports
+        8080,9148
+        although this is redundant. However such a setting is useful
+        if later the port range is changed to a value that will
+        include the reserved ports.
+        Default: Empty
 ip_nonlocal_bind - BOOLEAN
        If set, allows processes to bind() to non-local IP addresses,
        which can be quite useful - but may break some applications.
@@ -692,6 +747,25 @@ proxy_arp - BOOLEAN
        conf/{all,interface}/proxy_arp is set to TRUE,
        it will be disabled otherwise
+proxy_arp_pvlan - BOOLEAN
+        Private VLAN proxy arp.
+        Basically allow proxy arp replies back to the same interface
+        (from which the ARP request/solicitation was received).
+        This is done to support (ethernet) switch features, like RFC
+        3069, where the individual ports are NOT allowed to
+        communicate with each other, but they are allowed to talk to
+        the upstream router.  As described in RFC 3069, it is possible
+        to allow these hosts to communicate through the upstream
+        router by proxy_arp'ing. Don't need to be used together with
+        proxy_arp.
+        This technology is known by different names:
+          In RFC 3069 it is called VLAN Aggregation.
+          Cisco and Allied Telesyn call it Private VLAN.
+          Hewlett-Packard call it Source-Port filtering or port-isolation.
+          Ericsson call it MAC-Forced Forwarding (RFC Draft).
 shared_media - BOOLEAN
        Send(router) or accept(host) RFC1620 shared media redirects.
        Overrides ip_secure_redirects.
@@ -833,9 +907,18 @@ arp_notify - BOOLEAN
            or hardware address changes.
 arp_accept - BOOLEAN
-        Define behavior when gratuitous arp replies are received:
+        Define behavior for gratuitous ARP frames who's IP is not
-        0 - drop gratuitous arp frames
+        already present in the ARP table:
-        1 - accept gratuitous arp frames
+        0 - don't create new entries in the ARP table
+        1 - create new entries in the ARP table
+        Both replies and requests type gratuitous arp will trigger the
+        ARP table to be updated, if this setting is on.
+        If the ARP table already contains the IP address of the
+        gratuitous arp frame, the arp table will be updated regardless
+        if this setting is on or off.
 app_solicit - INTEGER
        The maximum number of probes to send to the user space ARP daemon
diff --git a/Documentation/networking/ixgbevf.txt b/Documentation/networking/ixgbevf.txt
new file mode 100755
index 000000000000..19015de6725f
--- /dev/null
+++ b/Documentation/networking/ixgbevf.txt
@@ -0,0 +1,90 @@
+Linux* Base Driver for Intel(R) Network Connection
+==================================================
+November 24, 2009
+Contents
+========
+- In This Release
+- Identifying Your Adapter
+- Known Issues/Troubleshooting
+- Support
+In This Release
+===============
+This file describes the ixgbevf Linux* Base Driver for Intel Network
+Connection.
+The ixgbevf driver supports 82599-based virtual function devices that can only
+be activated on kernels with CONFIG_PCI_IOV enabled.
+The ixgbevf driver supports virtual functions generated by the ixgbe driver
+with a max_vfs value of 1 or greater.
+The guest OS loading the ixgbevf driver must support MSI-X interrupts.
+VLANs: There is a limit of a total of 32 shared VLANs to 1 or more VFs.
+Identifying Your Adapter
+========================
+For more information on how to identify your adapter, go to the Adapter &
+Driver ID Guide at:
+    http://support.intel.com/support/network/sb/CS-008441.htm
+Known Issues/Troubleshooting
+============================
+  Unloading Physical Function (PF) Driver Causes System Reboots When VM is
+  Running and VF is Loaded on the VM
+  ------------------------------------------------------------------------
+  Do not unload the PF driver (ixgbe) while VFs are assigned to guests.
+Support
+=======
+For general information, go to the Intel support website at:
+    http://support.intel.com
+or the Intel Wired Networking project hosted by Sourceforge at:
+    http://sourceforge.net/projects/e1000
+If an issue is identified with the released source code on the supported
+kernel with a supported adapter, email the specific information related
+to the issue to e1000-devel@lists.sf.net
+License
+=======
+Intel 10 Gigabit Linux driver.
+Copyright(c) 1999 - 2009 Intel Corporation.
+This program is free software; you can redistribute it and/or modify it
+under the terms and conditions of the GNU General Public License,
+version 2, as published by the Free Software Foundation.
+This program is distributed in the hope it will be useful, but WITHOUT
+ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+more details.
+You should have received a copy of the GNU General Public License along with
+this program; if not, write to the Free Software Foundation, Inc.,
+51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+The full GNU General Public License is included in this distribution in
+the file called "COPYING".
+Trademarks
+==========
+Intel, Itanium, and Pentium are trademarks or registered trademarks of
+Intel Corporation or its subsidiaries in the United States and other
+countries.
+* Other names and brands may be claimed as the property of others.
diff --git a/Documentation/networking/l2tp.txt b/Documentation/networking/l2tp.txt
index 63214b280e00..e7bf3979facb 100644
--- a/Documentation/networking/l2tp.txt
+++ b/Documentation/networking/l2tp.txt
@@ -1,44 +1,95 @@
-This brief document describes how to use the kernel's PPPoL2TP driver
+This document describes how to use the kernel's L2TP drivers to
-to provide L2TP functionality. L2TP is a protocol that tunnels one or
+provide L2TP functionality. L2TP is a protocol that tunnels one or
-more PPP sessions over a UDP tunnel. It is commonly used for VPNs
+more sessions over an IP tunnel. It is commonly used for VPNs
 (L2TP/IPSec) and by ISPs to tunnel subscriber PPP sessions over an IP
-network infrastructure.
+network infrastructure. With L2TPv3, it is also useful as a Layer-2
+tunneling infrastructure.
+Features
+========
+L2TPv2 (PPP over L2TP (UDP tunnels)).
+L2TPv3 ethernet pseudowires.
+L2TPv3 PPP pseudowires.
+L2TPv3 IP encapsulation.
+Netlink sockets for L2TPv3 configuration management.
+History
+=======
+The original pppol2tp driver was introduced in 2.6.23 and provided
+L2TPv2 functionality (rfc2661). L2TPv2 is used to tunnel one or more PPP
+sessions over a UDP tunnel.
+L2TPv3 (rfc3931) changes the protocol to allow different frame types
+to be passed over an L2TP tunnel by moving the PPP-specific parts of
+the protocol out of the core L2TP packet headers. Each frame type is
+known as a pseudowire type. Ethernet, PPP, HDLC, Frame Relay and ATM
+pseudowires for L2TP are defined in separate RFC standards. Another
+change for L2TPv3 is that it can be carried directly over IP with no
+UDP header (UDP is optional). It is also possible to create static
+unmanaged L2TPv3 tunnels manually without a control protocol
+(userspace daemon) to manage them.
+To support L2TPv3, the original pppol2tp driver was split up to
+separate the L2TP and PPP functionality. Existing L2TPv2 userspace
+apps should be unaffected as the original pppol2tp sockets API is
+retained. L2TPv3, however, uses netlink to manage L2TPv3 tunnels and
+sessions.
 Design
 ======
-The PPPoL2TP driver, drivers/net/pppol2tp.c, provides a mechanism by
+The L2TP protocol separates control and data frames.  The L2TP kernel
-which PPP frames carried through an L2TP session are passed through
+drivers handle only L2TP data frames; control frames are always
-the kernel's PPP subsystem. The standard PPP daemon, pppd, handles all
+handled by userspace. L2TP control frames carry messages between L2TP
-PPP interaction with the peer. PPP network interfaces are created for
+clients/servers and are used to setup / teardown tunnels and
-each local PPP endpoint.
+sessions. An L2TP client or server is implemented in userspace.
-The L2TP protocol http://www.faqs.org/rfcs/rfc2661.html defines L2TP
+Each L2TP tunnel is implemented using a UDP or L2TPIP socket; L2TPIP
-control and data frames. L2TP control frames carry messages between
+provides L2TPv3 IP encapsulation (no UDP) and is implemented using a
-L2TP clients/servers and are used to setup / teardown tunnels and
+new l2tpip socket family. The tunnel socket is typically created by
-sessions. An L2TP client or server is implemented in userspace and
+userspace, though for unmanaged L2TPv3 tunnels, the socket can also be
-will use a regular UDP socket per tunnel. L2TP data frames carry PPP
+created by the kernel. Each L2TP session (pseudowire) gets a network
-frames, which may be PPP control or PPP data. The kernel's PPP
+interface instance. In the case of PPP, these interfaces are created
+indirectly by pppd using a pppol2tp socket. In the case of ethernet,
+the netdevice is created upon a netlink request to create an L2TPv3
+ethernet pseudowire.
+For PPP, the PPPoL2TP driver, net/l2tp/l2tp_ppp.c, provides a
+mechanism by which PPP frames carried through an L2TP session are
+passed through the kernel's PPP subsystem. The standard PPP daemon,
+pppd, handles all PPP interaction with the peer. PPP network
+interfaces are created for each local PPP endpoint. The kernel's PPP
 subsystem arranges for PPP control frames to be delivered to pppd,
 while data frames are forwarded as usual.
+For ethernet, the L2TPETH driver, net/l2tp/l2tp_eth.c, implements a
+netdevice driver, managing virtual ethernet devices, one per
+pseudowire. These interfaces can be managed using standard Linux tools
+such as "ip" and "ifconfig". If only IP frames are passed over the
+tunnel, the interface can be given an IP addresses of itself and its
+peer. If non-IP frames are to be passed over the tunnel, the interface
+can be added to a bridge using brctl. All L2TP datapath protocol
+functions are handled by the L2TP core driver.
 Each tunnel and session within a tunnel is assigned a unique tunnel_id
 and session_id. These ids are carried in the L2TP header of every
-control and data packet. The pppol2tp driver uses them to lookup
+control and data packet. (Actually, in L2TPv3, the tunnel_id isn't
-internal tunnel and/or session contexts. Zero tunnel / session ids are
+present in data frames - it is inferred from the IP connection on
-treated specially - zero ids are never assigned to tunnels or sessions
+which the packet was received.) The L2TP driver uses the ids to lookup
-in the network. In the driver, the tunnel context keeps a pointer to
+internal tunnel and/or session contexts to determine how to handle the
-the tunnel UDP socket. The session context keeps a pointer to the
+packet. Zero tunnel / session ids are treated specially - zero ids are
-PPPoL2TP socket, as well as other data that lets the driver interface
+never assigned to tunnels or sessions in the network. In the driver,
-to the kernel PPP subsystem.
+the tunnel context keeps a reference to the tunnel UDP or L2TPIP
+socket. The session context holds data that lets the driver interface
-Note that the pppol2tp kernel driver handles only L2TP data frames;
+to the kernel's network frame type subsystems, i.e. PPP, ethernet.
-L2TP control frames are simply passed up to userspace in the UDP
-tunnel socket. The kernel handles all datapath aspects of the
+Userspace Programming
-protocol, including data packet resequencing (if enabled).
+=====================
-There are a number of requirements on the userspace L2TP daemon in
+For L2TPv2, there are a number of requirements on the userspace L2TP
-order to use the pppol2tp driver.
+daemon in order to use the pppol2tp driver.
 1. Use a UDP socket per tunnel.
@@ -86,6 +137,35 @@ In addition to the standard PPP ioctls, a PPPIOCGL2TPSTATS is provided
 to retrieve tunnel and session statistics from the kernel using the
 PPPoX socket of the appropriate tunnel or session.
+For L2TPv3, userspace must use the netlink API defined in
+include/linux/l2tp.h to manage tunnel and session contexts. The
+general procedure to create a new L2TP tunnel with one session is:-
+1. Open a GENL socket using L2TP_GENL_NAME for configuring the kernel
+   using netlink.
+2. Create a UDP or L2TPIP socket for the tunnel.
+3. Create a new L2TP tunnel using a L2TP_CMD_TUNNEL_CREATE
+   request. Set attributes according to desired tunnel parameters,
+   referencing the UDP or L2TPIP socket created in the previous step.
+4. Create a new L2TP session in the tunnel using a
+   L2TP_CMD_SESSION_CREATE request.
+The tunnel and all of its sessions are closed when the tunnel socket
+is closed. The netlink API may also be used to delete sessions and
+tunnels. Configuration and status info may be set or read using netlink.
+The L2TP driver also supports static (unmanaged) L2TPv3 tunnels. These
+are where there is no L2TP control message exchange with the peer to
+setup the tunnel; the tunnel is configured manually at each end of the
+tunnel. There is no need for an L2TP userspace application in this
+case -- the tunnel socket is created by the kernel and configured
+using parameters sent in the L2TP_CMD_TUNNEL_CREATE netlink
+request. The "ip" utility of iproute2 has commands for managing static
+L2TPv3 tunnels; do "ip l2tp help" for more information.
 Debugging
 =========
@@ -102,6 +182,69 @@ PPPOL2TP_MSG_CONTROL  userspace - kernel interface
 PPPOL2TP_MSG_SEQ      sequence numbers handling
 PPPOL2TP_MSG_DATA     data packets
+If enabled, files under a l2tp debugfs directory can be used to dump
+kernel state about L2TP tunnels and sessions. To access it, the
+debugfs filesystem must first be mounted.
+# mount -t debugfs debugfs /debug
+Files under the l2tp directory can then be accessed.
+# cat /debug/l2tp/tunnels
+The debugfs files should not be used by applications to obtain L2TP
+state information because the file format is subject to change. It is
+implemented to provide extra debug information to help diagnose
+problems.) Users should use the netlink API.
+/proc/net/pppol2tp is also provided for backwards compaibility with
+the original pppol2tp driver. It lists information about L2TPv2
+tunnels and sessions only. Its use is discouraged.
+Unmanaged L2TPv3 Tunnels
+========================
+Some commercial L2TP products support unmanaged L2TPv3 ethernet
+tunnels, where there is no L2TP control protocol; tunnels are
+configured at each side manually. New commands are available in
+iproute2's ip utility to support this.
+To create an L2TPv3 ethernet pseudowire between local host 192.168.1.1
+and peer 192.168.1.2, using IP addresses 10.5.1.1 and 10.5.1.2 for the
+tunnel endpoints:-
+# modprobe l2tp_eth
+# modprobe l2tp_netlink
+# ip l2tp add tunnel tunnel_id 1 peer_tunnel_id 1 udp_sport 5000 \
+  udp_dport 5000 encap udp local 192.168.1.1 remote 192.168.1.2
+# ip l2tp add session tunnel_id 1 session_id 1 peer_session_id 1
+# ifconfig -a
+# ip addr add 10.5.1.2/32 peer 10.5.1.1/32 dev l2tpeth0
+# ifconfig l2tpeth0 up
+Choose IP addresses to be the address of a local IP interface and that
+of the remote system. The IP addresses of the l2tpeth0 interface can be
+anything suitable.
+Repeat the above at the peer, with ports, tunnel/session ids and IP
+addresses reversed.  The tunnel and session IDs can be any non-zero
+32-bit number, but the values must be reversed at the peer.
+Host 1                         Host2
+udp_sport=5000                 udp_sport=5001
+udp_dport=5001                 udp_dport=5000
+tunnel_id=42                   tunnel_id=45
+peer_tunnel_id=45              peer_tunnel_id=42
+session_id=128                 session_id=5196755
+peer_session_id=5196755        peer_session_id=128
+When done at both ends of the tunnel, it should be possible to send
+data over the network. e.g.
+# ping 10.5.1.1
 Sample Userspace Code
 =====================
@@ -158,12 +301,48 @@ Sample Userspace Code
        }
        return 0;
+Internal Implementation
+=======================
+The driver keeps a struct l2tp_tunnel context per L2TP tunnel and a
+struct l2tp_session context for each session. The l2tp_tunnel is
+always associated with a UDP or L2TP/IP socket and keeps a list of
+sessions in the tunnel. The l2tp_session context keeps kernel state
+about the session. It has private data which is used for data specific
+to the session type. With L2TPv2, the session always carried PPP
+traffic. With L2TPv3, the session can also carry ethernet frames
+(ethernet pseudowire) or other data types such as ATM, HDLC or Frame
+Relay.
+When a tunnel is first opened, the reference count on the socket is
+increased using sock_hold(). This ensures that the kernel socket
+cannot be removed while L2TP's data structures reference it.
+Some L2TP sessions also have a socket (PPP pseudowires) while others
+do not (ethernet pseudowires). We can't use the socket reference count
+as the reference count for session contexts. The L2TP implementation
+therefore has its own internal reference counts on the session
+contexts.
+To Do
+=====
+Add L2TP tunnel switching support. This would route tunneled traffic
+from one L2TP tunnel into another. Specified in
+http://tools.ietf.org/html/draft-ietf-l2tpext-tunnel-switching-08
+Add L2TPv3 VLAN pseudowire support.
+Add L2TPv3 IP pseudowire support.
+Add L2TPv3 ATM pseudowire support.
 Miscellaneous
-============
+=============
-The PPPoL2TP driver was developed as part of the OpenL2TP project by
+The L2TP drivers were developed as part of the OpenL2TP project by
 Katalix Systems Ltd. OpenL2TP is a full-featured L2TP client / server,
 designed from the ground up to have the L2TP datapath in the
 kernel. The project also implemented the pppol2tp plugin for pppd
 which allows pppd to use the kernel driver. Details can be found at
-http://openl2tp.sourceforge.net.
+http://www.openl2tp.org.
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index a22fd85e3796..98f71a5cef00 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -2,7 +2,7 @@
 + ABSTRACT
 --------------------------------------------------------------------------------
-This file documents the CONFIG_PACKET_MMAP option available with the PACKET
+This file documents the mmap() facility available with the PACKET
 socket interface on 2.4 and 2.6 kernels. This type of sockets is used for 
 capture network traffic with utilities like tcpdump or any other that needs
 raw access to network interface.
@@ -44,7 +44,7 @@ enabled. For transmission, check the MTU (Maximum Transmission Unit) used and
 supported by devices of your network.
 --------------------------------------------------------------------------------
-+ How to use CONFIG_PACKET_MMAP to improve capture process
+ How to use mmap() to improve capture process
 --------------------------------------------------------------------------------
 From the user standpoint, you should use the higher level libpcap library, which
@@ -64,7 +64,7 @@ the low level details or want to improve libpcap by including PACKET_MMAP
 support.
 --------------------------------------------------------------------------------
-+ How to use CONFIG_PACKET_MMAP directly to improve capture process
+ How to use mmap() directly to improve capture process
 --------------------------------------------------------------------------------
 From the system calls stand point, the use of PACKET_MMAP involves
@@ -100,12 +100,12 @@ by the kernel.
 The destruction of the socket and all associated resources
 is done by a simple call to close(fd).
-Next I will describe PACKET_MMAP settings and it's constraints,
+Next I will describe PACKET_MMAP settings and its constraints,
 also the mapping of the circular buffer in the user process and 
 the use of this buffer.
 --------------------------------------------------------------------------------
-+ How to use CONFIG_PACKET_MMAP directly to improve transmission process
+ How to use mmap() directly to improve transmission process
 --------------------------------------------------------------------------------
 Transmission process is similar to capture as shown below.
@@ -432,7 +432,7 @@ TP_STATUS_LOSING      : indicates there were packet drops from last time
                        the PACKET_STATISTICS option.
 TP_STATUS_CSUMNOTREADY: currently it's used for outgoing IP packets which 
-                        it's checksum will be done in hardware. So while 
+                        its checksum will be done in hardware. So while
                        reading the packet we should not try to check the 
                        checksum. 
diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt
index ee31369e9e5b..9551622d0a7b 100644
--- a/Documentation/networking/regulatory.txt
+++ b/Documentation/networking/regulatory.txt
@@ -188,3 +188,27 @@ Then in some part of your code after your wiphy has been registered:
                       &mydriver_jp_regdom.reg_rules[i],
                       sizeof(struct ieee80211_reg_rule));
        regulatory_struct_hint(rd);
+Statically compiled regulatory database
+---------------------------------------
+In most situations the userland solution using CRDA as described
+above is the preferred solution.  However in some cases a set of
+rules built into the kernel itself may be desirable.  To account
+for this situation, a configuration option has been provided
+(i.e. CONFIG_CFG80211_INTERNAL_REGDB).  With this option enabled,
+the wireless database information contained in net/wireless/db.txt is
+used to generate a data structure encoded in net/wireless/regdb.c.
+That option also enables code in net/wireless/reg.c which queries
+the data in regdb.c as an alternative to using CRDA.
+The file net/wireless/db.txt should be kept up-to-date with the db.txt
+file available in the git repository here:
+    git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-regdb.git
+Again, most users in most situations should be using the CRDA package
+provided with their distribution, and in most other situations users
+should be building and using CRDA on their own rather than using
+this option.  If you are not absolutely sure that you should be using
+CONFIG_CFG80211_INTERNAL_REGDB then _DO_NOT_USE_IT_.
diff --git a/Documentation/networking/skfp.txt b/Documentation/networking/skfp.txt
index abfddf81e34a..203ec66c9fb4 100644
--- a/Documentation/networking/skfp.txt
+++ b/Documentation/networking/skfp.txt
@@ -68,7 +68,7 @@ Compaq adapters (not tested):
 =======================
 From v2.01 on, the driver is integrated in the linux kernel sources.
-Therefor, the installation is the same as for any other adapter
+Therefore, the installation is the same as for any other adapter
 supported by the kernel.
 Refer to the manual of your distribution about the installation
 of network adapters.
diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt
new file mode 100644
index 000000000000..7ee770b5ef5f
--- /dev/null
+++ b/Documentation/networking/stmmac.txt
@@ -0,0 +1,143 @@
+       STMicroelectronics 10/100/1000 Synopsys Ethernet driver
+Copyright (C) 2007-2010  STMicroelectronics Ltd
+Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
+This is the driver for the MAC 10/100/1000 on-chip Ethernet controllers
+(Synopsys IP blocks); it has been fully tested on STLinux platforms.
+Currently this network device driver is for all STM embedded MAC/GMAC
+(7xxx SoCs).
+DWC Ether MAC 10/100/1000 Universal version 3.41a and DWC Ether MAC 10/100
+Universal version 4.0 have been used for developing the first code
+implementation.
+Please, for more information also visit: www.stlinux.com
+1) Kernel Configuration
+The kernel configuration option is STMMAC_ETH:
+ Device Drivers ---> Network device support ---> Ethernet (1000 Mbit) --->
+ STMicroelectronics 10/100/1000 Ethernet driver (STMMAC_ETH)
+2) Driver parameters list:
+        debug: message level (0: no output, 16: all);
+        phyaddr: to manually provide the physical address to the PHY device;
+        dma_rxsize: DMA rx ring size;
+        dma_txsize: DMA tx ring size;
+        buf_sz: DMA buffer size;
+        tc: control the HW FIFO threshold;
+        tx_coe: Enable/Disable Tx Checksum Offload engine;
+        watchdog: transmit timeout (in milliseconds);
+        flow_ctrl: Flow control ability [on/off];
+        pause: Flow Control Pause Time;
+        tmrate: timer period (only if timer optimisation is configured).
+3) Command line options
+Driver parameters can be also passed in command line by using:
+        stmmaceth=dma_rxsize:128,dma_txsize:512
+4) Driver information and notes
+4.1) Transmit process
+The xmit method is invoked when the kernel needs to transmit a packet; it sets
+the descriptors in the ring and informs the DMA engine that there is a packet
+ready to be transmitted.
+Once the controller has finished transmitting the packet, an interrupt is
+triggered; So the driver will be able to release the socket buffers.
+By default, the driver sets the NETIF_F_SG bit in the features field of the
+net_device structure enabling the scatter/gather feature.
+4.2) Receive process
+When one or more packets are received, an interrupt happens. The interrupts
+are not queued so the driver has to scan all the descriptors in the ring during
+the receive process.
+This is based on NAPI so the interrupt handler signals only if there is work to be
+done, and it exits.
+Then the poll method will be scheduled at some future point.
+The incoming packets are stored, by the DMA, in a list of pre-allocated socket
+buffers in order to avoid the memcpy (Zero-copy).
+4.3) Timer-Driver Interrupt
+Instead of having the device that asynchronously notifies the frame receptions, the
+driver configures a timer to generate an interrupt at regular intervals.
+Based on the granularity of the timer, the frames that are received by the device
+will experience different levels of latency. Some NICs have dedicated timer
+device to perform this task. STMMAC can use either the RTC device or the TMU
+channel 2  on STLinux platforms.
+The timers frequency can be passed to the driver as parameter; when change it,
+take care of both hardware capability and network stability/performance impact.
+Several performance tests on STM platforms showed this optimisation allows to spare
+the CPU while having the maximum throughput.
+4.4) WOL
+Wake up on Lan feature through Magic Frame is only supported for the GMAC
+core.
+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.
+4.6) Ethtool support
+Ethtool is supported. Driver statistics and internal errors can be taken using:
+ethtool -S ethX command. It is possible to dump registers etc.
+4.7) Jumbo and Segmentation Offloading
+Jumbo frames are supported and tested for the GMAC.
+The GSO has been also added but it's performed in software.
+LRO is not supported.
+4.8) Physical
+The driver is compatible with PAL to work with PHY and GPHY devices.
+4.9) Platform information
+Several information came from the platform; please refer to the
+driver's Header file in include/linux directory.
+struct plat_stmmacenet_data {
+        int bus_id;
+        int pbl;
+        int has_gmac;
+        void (*fix_mac_speed)(void *priv, unsigned int speed);
+        void (*bus_setup)(unsigned long ioaddr);
+#ifdef CONFIG_STM_DRIVERS
+        struct stm_pad_config *pad_config;
+#endif
+        void *bsp_priv;
+};
+Where:
+- pbl (Programmable Burst Length) is maximum number of
+  beats to be transferred in one DMA transaction.
+  GMAC also enables the 4xPBL by default.
+- fix_mac_speed and bus_setup are used to configure internal target
+  registers (on STM platforms);
+- has_gmac: GMAC core is on board (get it at run-time in the next step);
+- bus_id: bus identifier.
+struct plat_stmmacphy_data {
+        int bus_id;
+        int phy_addr;
+        unsigned int phy_mask;
+        int interface;
+        int (*phy_reset)(void *priv);
+        void *priv;
+};
+Where:
+- bus_id: bus identifier;
+- phy_addr: physical address used for the attached phy device;
+            set it to -1 to get it at run-time;
+- interface: physical MII interface mode;
+- phy_reset: hook to reset HW function.
+TODO:
+- Continue to make the driver more generic and suitable for other Synopsys
+  Ethernet controllers used on other architectures (i.e. ARM).
+- 10G controllers are not supported.
+- MAC uses Normal descriptors and GMAC uses enhanced ones.
+  This is a limit that should be reviewed. MAC could want to
+  use the enhanced structure.
+- Checksumming: Rx/Tx csum is done in HW in case of GMAC only.
+- Review the timer optimisation code to use an embedded device that seems to be
+  available in new chip generations.
diff --git a/Documentation/networking/tcp-thin.txt b/Documentation/networking/tcp-thin.txt
new file mode 100644
index 000000000000..151e229980f1
--- /dev/null
+++ b/Documentation/networking/tcp-thin.txt
@@ -0,0 +1,47 @@
+Thin-streams and TCP
+====================
+A wide range of Internet-based services that use reliable transport
+protocols display what we call thin-stream properties. This means
+that the application sends data with such a low rate that the
+retransmission mechanisms of the transport protocol are not fully
+effective. In time-dependent scenarios (like online games, control
+systems, stock trading etc.) where the user experience depends
+on the data delivery latency, packet loss can be devastating for
+the service quality. Extreme latencies are caused by TCP's
+dependency on the arrival of new data from the application to trigger
+retransmissions effectively through fast retransmit instead of
+waiting for long timeouts.
+After analysing a large number of time-dependent interactive
+applications, we have seen that they often produce thin streams
+and also stay with this traffic pattern throughout its entire
+lifespan. The combination of time-dependency and the fact that the
+streams provoke high latencies when using TCP is unfortunate.
+In order to reduce application-layer latency when packets are lost,
+a set of mechanisms has been made, which address these latency issues
+for thin streams. In short, if the kernel detects a thin stream,
+the retransmission mechanisms are modified in the following manner:
+1) If the stream is thin, fast retransmit on the first dupACK.
+2) If the stream is thin, do not apply exponential backoff.
+These enhancements are applied only if the stream is detected as
+thin. This is accomplished by defining a threshold for the number
+of packets in flight. If there are less than 4 packets in flight,
+fast retransmissions can not be triggered, and the stream is prone
+to experience high retransmission latencies.
+Since these mechanisms are targeted at time-dependent applications,
+they must be specifically activated by the application using the
+TCP_THIN_LINEAR_TIMEOUTS and TCP_THIN_DUPACK IOCTLS or the
+tcp_thin_linear_timeouts and tcp_thin_dupack sysctls. Both
+modifications are turned off by default.
+References
+==========
+More information on the modifications, as well as a wide range of
+experimental data can be found here:
+"Improving latency for interactive, thin-stream applications over
+reliable transport"
+http://simula.no/research/nd/publications/Simula.nd.477/simula_pdf_file
diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt
index 0e58b4539176..e8c8f4f06c67 100644
--- a/Documentation/networking/timestamping.txt
+++ b/Documentation/networking/timestamping.txt
@@ -41,11 +41,12 @@ SOF_TIMESTAMPING_SOFTWARE:     return system time stamp generated in
 SOF_TIMESTAMPING_TX/RX determine how time stamps are generated.
 SOF_TIMESTAMPING_RAW/SYS determine how they are reported in the
 following control message:
-    struct scm_timestamping {
-           struct timespec systime;
+struct scm_timestamping {
-           struct timespec hwtimetrans;
+        struct timespec systime;
-           struct timespec hwtimeraw;
+        struct timespec hwtimetrans;
-    };
+        struct timespec hwtimeraw;
+};
 recvmsg() can be used to get this control message for regular incoming
 packets. For send time stamps the outgoing packet is looped back to
@@ -87,12 +88,13 @@ by the network device and will be empty without that support.
 SIOCSHWTSTAMP:
 Hardware time stamping must also be initialized for each device driver
-that is expected to do hardware time stamping. The parameter is:
+that is expected to do hardware time stamping. The parameter is defined in
+/include/linux/net_tstamp.h as:
 struct hwtstamp_config {
-    int flags;           /* no flags defined right now, must be zero */
+        int flags;      /* no flags defined right now, must be zero */
-    int tx_type;         /* HWTSTAMP_TX_* */
+        int tx_type;    /* HWTSTAMP_TX_* */
-    int rx_filter;       /* HWTSTAMP_FILTER_* */
+        int rx_filter;  /* HWTSTAMP_FILTER_* */
 };
 Desired behavior is passed into the kernel and to a specific device by
@@ -139,42 +141,56 @@ enum {
        /* time stamp any incoming packet */
        HWTSTAMP_FILTER_ALL,
-        /* return value: time stamp all packets requested plus some others */
+        /* return value: time stamp all packets requested plus some others */
-        HWTSTAMP_FILTER_SOME,
+        HWTSTAMP_FILTER_SOME,
        /* PTP v1, UDP, any kind of event packet */
        HWTSTAMP_FILTER_PTP_V1_L4_EVENT,
-        ...
+        /* for the complete list of values, please check
+         * the include file /include/linux/net_tstamp.h
+         */
 };
 DEVICE IMPLEMENTATION
 A driver which supports hardware time stamping must support the
-SIOCSHWTSTAMP ioctl. Time stamps for received packets must be stored
+SIOCSHWTSTAMP ioctl and update the supplied struct hwtstamp_config with
-in the skb with skb_hwtstamp_set().
+the actual values as described in the section on SIOCSHWTSTAMP.
+Time stamps for received packets must be stored in the skb. To get a pointer
+to the shared time stamp structure of the skb call skb_hwtstamps(). Then
+set the time stamps in the structure:
+struct skb_shared_hwtstamps {
+        /* hardware time stamp transformed into duration
+         * since arbitrary point in time
+         */
+        ktime_t hwtstamp;
+        ktime_t syststamp; /* hwtstamp transformed to system time base */
+};
 Time stamps for outgoing packets are to be generated as follows:
- In hard_start_xmit(), check if skb_hwtstamp_check_tx_hardware()
+- In hard_start_xmit(), check if skb_tx(skb)->hardware is set no-zero.
-  returns non-zero. If yes, then the driver is expected
+  If yes, then the driver is expected to do hardware time stamping.
-  to do hardware time stamping.
 - If this is possible for the skb and requested, then declare
-  that the driver is doing the time stamping by calling
+  that the driver is doing the time stamping by setting the field
-  skb_hwtstamp_tx_in_progress(). A driver not supporting
+  skb_tx(skb)->in_progress non-zero. You might want to keep a pointer
-  hardware time stamping doesn't do that. A driver must never
+  to the associated skb for the next step and not free the skb. A driver
-  touch sk_buff::tstamp! It is used to store how time stamping
+  not supporting hardware time stamping doesn't do that. A driver must
-  for an outgoing packets is to be done.
+  never touch sk_buff::tstamp! It is used to store software generated
+  time stamps by the network subsystem.
 - As soon as the driver has sent the packet and/or obtained a
  hardware time stamp for it, it passes the time stamp back by
  calling skb_hwtstamp_tx() with the original skb, the raw
-  hardware time stamp and a handle to the device (necessary
+  hardware time stamp. skb_hwtstamp_tx() clones the original skb and
-  to convert the hardware time stamp to system time). If obtaining
+  adds the timestamps, therefore the original skb has to be freed now.
-  the hardware time stamp somehow fails, then the driver should
+  If obtaining the hardware time stamp somehow fails, then the driver
-  not fall back to software time stamping. The rationale is that
+  should not fall back to software time stamping. The rationale is that
-  this would occur at a later time in the processing pipeline
+  this would occur at a later time in the processing pipeline than other
-  than other software time stamping and therefore could lead
+  software time stamping and therefore could lead to unexpected deltas
-  to unexpected deltas between time stamps.
+  between time stamps.
- If the driver did not call skb_hwtstamp_tx_in_progress(), then
+- If the driver did not call set skb_tx(skb)->in_progress, then
  dev_hard_start_xmit() checks whether software time stamping
  is wanted as fallback and potentially generates the time stamp.
diff --git a/Documentation/networking/timestamping/Makefile b/Documentation/networking/timestamping/Makefile
index 2a1489fdc036..e79973443e9f 100644
--- a/Documentation/networking/timestamping/Makefile
+++ b/Documentation/networking/timestamping/Makefile
@@ -1,6 +1,13 @@
-CPPFLAGS = -I../../../include
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
-timestamping: timestamping.c
+# List of programs to build
+hostprogs-y := timestamping
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+HOSTCFLAGS_timestamping.o += -I$(objtree)/usr/include
 clean:
        rm -f timestamping
diff --git a/Documentation/networking/timestamping/timestamping.c b/Documentation/networking/timestamping/timestamping.c
index a7936fe8444a..8ba82bfe6a33 100644
--- a/Documentation/networking/timestamping/timestamping.c
+++ b/Documentation/networking/timestamping/timestamping.c
@@ -41,9 +41,9 @@
 #include <arpa/inet.h>
 #include <net/if.h>
-#include "asm/types.h"
+#include <asm/types.h>
-#include "linux/net_tstamp.h"
+#include <linux/net_tstamp.h>
-#include "linux/errqueue.h"
+#include <linux/errqueue.h>
 #ifndef SO_TIMESTAMPING
 # define SO_TIMESTAMPING         37
@@ -164,7 +164,7 @@ static void printpacket(struct msghdr *msg, int res,
        gettimeofday(&now, 0);
-        printf("%ld.%06ld: received %s data, %d bytes from %s, %d bytes control messages\n",
+        printf("%ld.%06ld: received %s data, %d bytes from %s, %zu bytes control messages\n",
               (long)now.tv_sec, (long)now.tv_usec,
               (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular",
               res,
@@ -173,7 +173,7 @@ static void printpacket(struct msghdr *msg, int res,
        for (cmsg = CMSG_FIRSTHDR(msg);
             cmsg;
             cmsg = CMSG_NXTHDR(msg, cmsg)) {
-                printf("   cmsg len %d: ", cmsg->cmsg_len);
+                printf("   cmsg len %zu: ", cmsg->cmsg_len);
                switch (cmsg->cmsg_level) {
                case SOL_SOCKET:
                        printf("SOL_SOCKET ");
@@ -370,7 +370,7 @@ int main(int argc, char **argv)
        }
        sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_UDP);
-        if (socket < 0)
+        if (sock < 0)
                bail("socket");
        memset(&device, 0, sizeof(device));
diff --git a/Documentation/networking/x25-iface.txt b/Documentation/networking/x25-iface.txt
index 975cc87ebdd1..78f662ee0622 100644
--- a/Documentation/networking/x25-iface.txt
+++ b/Documentation/networking/x25-iface.txt
@@ -20,23 +20,23 @@ the rest of the skbuff, if any more information does exist.
 Packet Layer to Device Driver
 -----------------------------
-First Byte = 0x00
+First Byte = 0x00 (X25_IFACE_DATA)
 This indicates that the rest of the skbuff contains data to be transmitted
 over the LAPB link. The LAPB link should already exist before any data is
 passed down.
-First Byte = 0x01
+First Byte = 0x01 (X25_IFACE_CONNECT)
 Establish the LAPB link. If the link is already established then the connect
 confirmation message should be returned as soon as possible.
-First Byte = 0x02
+First Byte = 0x02 (X25_IFACE_DISCONNECT)
 Terminate the LAPB link. If it is already disconnected then the disconnect
 confirmation message should be returned as soon as possible.
-First Byte = 0x03
+First Byte = 0x03 (X25_IFACE_PARAMS)
 LAPB parameters. To be defined.
@@ -44,22 +44,22 @@ LAPB parameters. To be defined.
 Device Driver to Packet Layer
 -----------------------------
-First Byte = 0x00
+First Byte = 0x00 (X25_IFACE_DATA)
 This indicates that the rest of the skbuff contains data that has been
 received over the LAPB link.
-First Byte = 0x01
+First Byte = 0x01 (X25_IFACE_CONNECT)
 LAPB link has been established. The same message is used for both a LAPB
 link connect_confirmation and a connect_indication.
-First Byte = 0x02
+First Byte = 0x02 (X25_IFACE_DISCONNECT)
 LAPB link has been terminated. This same message is used for both a LAPB
 link disconnect_confirmation and a disconnect_indication.
-First Byte = 0x03
+First Byte = 0x03 (X25_IFACE_PARAMS)
 LAPB parameters. To be defined.
diff --git a/Documentation/oops-tracing.txt b/Documentation/oops-tracing.txt
index c10c022b911c..6fe9001b9263 100644
--- a/Documentation/oops-tracing.txt
+++ b/Documentation/oops-tracing.txt
@@ -256,9 +256,13 @@ characters, each representing a particular tainted value.
  9: 'A' if the ACPI table has been overridden.
 10: 'W' if a warning has previously been issued by the kernel.
+     (Though some warnings may set more specific taint flags.)
 11: 'C' if a staging driver has been loaded.
+ 12: 'I' if the kernel is working around a severe bug in the platform
+     firmware (BIOS or similar).
 The primary reason for the 'Tainted: ' string is to tell kernel
 debuggers if this is a clean kernel or if anything unusual has
 occurred.  Tainting is permanent: even if an offending module is
diff --git a/Documentation/padata.txt b/Documentation/padata.txt
new file mode 100644
index 000000000000..269d7d0d8335
--- /dev/null
+++ b/Documentation/padata.txt
@@ -0,0 +1,107 @@
+The padata parallel execution mechanism
+Last updated for 2.6.34
+Padata is a mechanism by which the kernel can farm work out to be done in
+parallel on multiple CPUs while retaining the ordering of tasks.  It was
+developed for use with the IPsec code, which needs to be able to perform
+encryption and decryption on large numbers of packets without reordering
+those packets.  The crypto developers made a point of writing padata in a
+sufficiently general fashion that it could be put to other uses as well.
+The first step in using padata is to set up a padata_instance structure for
+overall control of how tasks are to be run:
+    #include <linux/padata.h>
+    struct padata_instance *padata_alloc(const struct cpumask *cpumask,
+                                         struct workqueue_struct *wq);
+The cpumask describes which processors will be used to execute work
+submitted to this instance.  The workqueue wq is where the work will
+actually be done; it should be a multithreaded queue, naturally.
+There are functions for enabling and disabling the instance:
+    void padata_start(struct padata_instance *pinst);
+    void padata_stop(struct padata_instance *pinst);
+These functions literally do nothing beyond setting or clearing the
+"padata_start() was called" flag; if that flag is not set, other functions
+will refuse to work.
+The list of CPUs to be used can be adjusted with these functions:
+    int padata_set_cpumask(struct padata_instance *pinst,
+                           cpumask_var_t cpumask);
+    int padata_add_cpu(struct padata_instance *pinst, int cpu);
+    int padata_remove_cpu(struct padata_instance *pinst, int cpu);
+Changing the CPU mask has the look of an expensive operation, though, so it
+probably should not be done with great frequency.
+Actually submitting work to the padata instance requires the creation of a
+padata_priv structure:
+    struct padata_priv {
+        /* Other stuff here... */
+        void                    (*parallel)(struct padata_priv *padata);
+        void                    (*serial)(struct padata_priv *padata);
+    };
+This structure will almost certainly be embedded within some larger
+structure specific to the work to be done.  Most its fields are private to
+padata, but the structure should be zeroed at initialization time, and the
+parallel() and serial() functions should be provided.  Those functions will
+be called in the process of getting the work done as we will see
+momentarily.
+The submission of work is done with:
+    int padata_do_parallel(struct padata_instance *pinst,
+                           struct padata_priv *padata, int cb_cpu);
+The pinst and padata structures must be set up as described above; cb_cpu
+specifies which CPU will be used for the final callback when the work is
+done; it must be in the current instance's CPU mask.  The return value from
+padata_do_parallel() is a little strange; zero is an error return
+indicating that the caller forgot the padata_start() formalities.  -EBUSY
+means that somebody, somewhere else is messing with the instance's CPU
+mask, while -EINVAL is a complaint about cb_cpu not being in that CPU mask.
+If all goes well, this function will return -EINPROGRESS, indicating that
+the work is in progress.
+Each task submitted to padata_do_parallel() will, in turn, be passed to
+exactly one call to the above-mentioned parallel() function, on one CPU, so
+true parallelism is achieved by submitting multiple tasks.  Despite the
+fact that the workqueue is used to make these calls, parallel() is run with
+software interrupts disabled and thus cannot sleep.  The parallel()
+function gets the padata_priv structure pointer as its lone parameter;
+information about the actual work to be done is probably obtained by using
+container_of() to find the enclosing structure.
+Note that parallel() has no return value; the padata subsystem assumes that
+parallel() will take responsibility for the task from this point.  The work
+need not be completed during this call, but, if parallel() leaves work
+outstanding, it should be prepared to be called again with a new job before
+the previous one completes.  When a task does complete, parallel() (or
+whatever function actually finishes the job) should inform padata of the
+fact with a call to:
+    void padata_do_serial(struct padata_priv *padata);
+At some point in the future, padata_do_serial() will trigger a call to the
+serial() function in the padata_priv structure.  That call will happen on
+the CPU requested in the initial call to padata_do_parallel(); it, too, is
+done through the workqueue, but with local software interrupts disabled.
+Note that this call may be deferred for a while since the padata code takes
+pains to ensure that tasks are completed in the order in which they were
+submitted.
+The one remaining function in the padata API should be called to clean up
+when a padata instance is no longer needed:
+    void padata_free(struct padata_instance *pinst);
+This function will busy-wait while any remaining tasks are completed, so it
+might be best not to call it while there is work outstanding.  Shutting
+down the workqueue, if necessary, should be done separately.
diff --git a/Documentation/pcmcia/driver-changes.txt b/Documentation/pcmcia/driver-changes.txt
index 446f43b309df..61bc4e943116 100644
--- a/Documentation/pcmcia/driver-changes.txt
+++ b/Documentation/pcmcia/driver-changes.txt
@@ -1,4 +1,17 @@
 This file details changes in 2.6 which affect PCMCIA card driver authors:
+* No dev_node_t (as of 2.6.35)
+   There is no more need to fill out a "dev_node_t" structure.
+* New IRQ request rules (as of 2.6.35)
+   Instead of the old pcmcia_request_irq() interface, drivers may now
+   choose between:
+   - calling request_irq/free_irq directly. Use the IRQ from *p_dev->irq.
+   - use pcmcia_request_irq(p_dev, handler_t); the PCMCIA core will
+     clean up automatically on calls to pcmcia_disable_device() or
+     device ejection.
+   - drivers still not capable of IRQF_SHARED (or not telling us so) may
+     use the deprecated pcmcia_request_exclusive_irq() for the time
+     being; they might receive a shared IRQ nonetheless.
 * no cs_error / CS_CHECK / CONFIG_PCMCIA_DEBUG (as of 2.6.33)
   Instead of the cs_error() callback or the CS_CHECK() macro, please use
diff --git a/Documentation/pcmcia/locking.txt b/Documentation/pcmcia/locking.txt
new file mode 100644
index 000000000000..68f622bc4064
--- /dev/null
+++ b/Documentation/pcmcia/locking.txt
@@ -0,0 +1,118 @@
+This file explains the locking and exclusion scheme used in the PCCARD
+and PCMCIA subsystems.
+A) Overview, Locking Hierarchy:
+===============================
+pcmcia_socket_list_rwsem        - protects only the list of sockets
+- skt_mutex                     - serializes card insert / ejection
+  - ops_mutex                   - serializes socket operation
+B) Exclusion
+============
+The following functions and callbacks to struct pcmcia_socket must
+be called with "skt_mutex" held:
+        socket_detect_change()
+        send_event()
+        socket_reset()
+        socket_shutdown()
+        socket_setup()
+        socket_remove()
+        socket_insert()
+        socket_early_resume()
+        socket_late_resume()
+        socket_resume()
+        socket_suspend()
+        struct pcmcia_callback  *callback
+The following functions and callbacks to struct pcmcia_socket must
+be called with "ops_mutex" held:
+        socket_reset()
+        socket_setup()
+        struct pccard_operations        *ops
+        struct pccard_resource_ops      *resource_ops;
+Note that send_event() and struct pcmcia_callback *callback must not be
+called with "ops_mutex" held.
+C) Protection
+=============
+1. Global Data:
+---------------
+struct list_head        pcmcia_socket_list;
+protected by pcmcia_socket_list_rwsem;
+2. Per-Socket Data:
+-------------------
+The resource_ops and their data are protected by ops_mutex.
+The "main" struct pcmcia_socket is protected as follows (read-only fields
+or single-use fields not mentioned):
+- by pcmcia_socket_list_rwsem:
+        struct list_head        socket_list;
+- by thread_lock:
+        unsigned int            thread_events;
+- by skt_mutex:
+        u_int                   suspended_state;
+        void                    (*tune_bridge);
+        struct pcmcia_callback  *callback;
+        int                     resume_status;
+- by ops_mutex:
+        socket_state_t          socket;
+        u_int                   state;
+        u_short                 lock_count;
+        pccard_mem_map          cis_mem;
+        void __iomem            *cis_virt;
+        struct { }              irq;
+        io_window_t             io[];
+        pccard_mem_map          win[];
+        struct list_head        cis_cache;
+        size_t                  fake_cis_len;
+        u8                      *fake_cis;
+        u_int                   irq_mask;
+        void                    (*zoom_video);
+        int                     (*power_hook);
+        u8                      resource...;
+        struct list_head        devices_list;
+        u8                      device_count;
+        struct                  pcmcia_state;
+3. Per PCMCIA-device Data:
+--------------------------
+The "main" struct pcmcia_devie is protected as follows (read-only fields
+or single-use fields not mentioned):
+- by pcmcia_socket->ops_mutex:
+        struct list_head        socket_device_list;
+        struct config_t         *function_config;
+        u16                     _irq:1;
+        u16                     _io:1;
+        u16                     _win:4;
+        u16                     _locked:1;
+        u16                     allow_func_id_match:1;
+        u16                     suspended:1;
+        u16                     _removed:1;
+- by the PCMCIA driver:
+        io_req_t                io;
+        irq_req_t               irq;
+        config_req_t            conf;
+        window_handle_t         win;
diff --git a/Documentation/pnp.txt b/Documentation/pnp.txt
index a327db67782a..763e4659bf18 100644
--- a/Documentation/pnp.txt
+++ b/Documentation/pnp.txt
@@ -57,7 +57,7 @@ PC standard floppy disk controller
 # cat resources
 DISABLED
- Notice the string "DISABLED".  THis means the device is not active.
+- Notice the string "DISABLED".  This means the device is not active.
 3.) check the device's possible configurations (optional)
 # cat options
@@ -139,7 +139,7 @@ Plug and Play but it is planned to be in the near future.
 Requirements for a Linux PnP protocol:
 1.) the protocol must use EISA IDs
-2.) the protocol must inform the PnP Layer of a devices current configuration
+2.) the protocol must inform the PnP Layer of a device's current configuration
 - the ability to set resources is optional but preferred.
 The following are PnP protocol related functions:
@@ -158,7 +158,7 @@ pnp_remove_device
 - automatically will free mem used by the device and related structures
 pnp_add_id
- adds a EISA ID to the list of supported IDs for the specified device
+- adds an EISA ID to the list of supported IDs for the specified device
 For more information consult the source of a protocol such as
 /drivers/pnp/pnpbios/core.c.
@@ -167,7 +167,7 @@ For more information consult the source of a protocol such as
 Linux Plug and Play Drivers
 ---------------------------
-        This section contains information for linux PnP driver developers.
+        This section contains information for Linux PnP driver developers.
 The New Way
 ...........
@@ -235,11 +235,10 @@ static int __init serial8250_pnp_init(void)
 The Old Way
 ...........
-a series of compatibility functions have been created to make it easy to convert 
+A series of compatibility functions have been created to make it easy to convert
 ISAPNP drivers.  They should serve as a temporary solution only.
-they are as follows:
+They are as follows:
 struct pnp_card *pnp_find_card(unsigned short vendor,
                                 unsigned short device,
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index c9abbd86bc18..57080cd74575 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -1,7 +1,13 @@
+Device Power Management
+Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+Copyright (c) 2010 Alan Stern <stern@rowland.harvard.edu>
 Most of the code in Linux is device drivers, so most of the Linux power
-management code is also driver-specific.  Most drivers will do very little;
+management (PM) code is also driver-specific.  Most drivers will do very
-others, especially for platforms with small batteries (like cell phones),
+little; others, especially for platforms with small batteries (like cell
-will do a lot.
+phones), will do a lot.
 This writeup gives an overview of how drivers interact with system-wide
 power management goals, emphasizing the models and interfaces that are
@@ -15,9 +21,10 @@ Drivers will use one or both of these models to put devices into low-power
 states:
    System Sleep model:
-        Drivers can enter low power states as part of entering system-wide
+        Drivers can enter low-power states as part of entering system-wide
-        low-power states like "suspend-to-ram", or (mostly for systems with
+        low-power states like "suspend" (also known as "suspend-to-RAM"), or
-        disks) "hibernate" (suspend-to-disk).
+        (mostly for systems with disks) "hibernation" (also known as
+        "suspend-to-disk").
        This is something that device, bus, and class drivers collaborate on
        by implementing various role-specific suspend and resume methods to
@@ -25,33 +32,41 @@ states:
        them without loss of data.
        Some drivers can manage hardware wakeup events, which make the system
-        leave that low-power state.  This feature may be disabled using the
+        leave the low-power state.  This feature may be enabled or disabled
-        relevant /sys/devices/.../power/wakeup file; enabling it may cost some
+        using the relevant /sys/devices/.../power/wakeup file (for Ethernet
-        power usage, but let the whole system enter low power states more often.
+        drivers the ioctl interface used by ethtool may also be used for this
+        purpose); enabling it may cost some power usage, but let the whole
+        system enter low-power states more often.
    Runtime Power Management model:
-        Drivers may also enter low power states while the system is running,
+        Devices may also be put into low-power states while the system is
-        independently of other power management activity.  Upstream drivers
+        running, independently of other power management activity in principle.
-        will normally not know (or care) if the device is in some low power
+        However, devices are not generally independent of each other (for
-        state when issuing requests; the driver will auto-resume anything
+        example, a parent device cannot be suspended unless all of its child
-        that's needed when it gets a request.
+        devices have been suspended).  Moreover, depending on the bus type the
+        device is on, it may be necessary to carry out some bus-specific
-        This doesn't have, or need much infrastructure; it's just something you
+        operations on the device for this purpose.  Devices put into low power
-        should do when writing your drivers.  For example, clk_disable() unused
+        states at run time may require special handling during system-wide power
-        clocks as part of minimizing power drain for currently-unused hardware.
+        transitions (suspend or hibernation).
-        Of course, sometimes clusters of drivers will collaborate with each
-        other, which could involve task-specific power management.
+        For these reasons not only the device driver itself, but also the
+        appropriate subsystem (bus type, device type or device class) driver and
-There's not a lot to be said about those low power states except that they
+        the PM core are involved in runtime power management.  As in the system
-are very system-specific, and often device-specific.  Also, that if enough
+        sleep power management case, they need to collaborate by implementing
-drivers put themselves into low power states (at "runtime"), the effect may be
+        various role-specific suspend and resume methods, so that the hardware
-the same as entering some system-wide low-power state (system sleep) ... and
+        is cleanly powered down and reactivated without data or service loss.
-that synergies exist, so that several drivers using runtime pm might put the
-system into a state where even deeper power saving options are available.
+There's not a lot to be said about those low-power states except that they are
+very system-specific, and often device-specific.  Also, that if enough devices
-Most suspended devices will have quiesced all I/O:  no more DMA or irqs, no
+have been put into low-power states (at runtime), the effect may be very similar
-more data read or written, and requests from upstream drivers are no longer
+to entering some system-wide low-power state (system sleep) ... and that
-accepted.  A given bus or platform may have different requirements though.
+synergies exist, so that several drivers using runtime PM might put the system
+into a state where even deeper power saving options are available.
+Most suspended devices will have quiesced all I/O: no more DMA or IRQs (except
+for wakeup events), no more data read or written, and requests from upstream
+drivers are no longer accepted.  A given bus or platform may have different
+requirements though.
 Examples of hardware wakeup events include an alarm from a real time clock,
 network wake-on-LAN packets, keyboard or mouse activity, and media insertion
@@ -60,129 +75,152 @@ or removal (for PCMCIA, MMC/SD, USB, and so on).
 Interfaces for Entering System Sleep States
 ===========================================
-Most of the programming interfaces a device driver needs to know about
+There are programming interfaces provided for subsystems (bus type, device type,
-relate to that first model:  entering a system-wide low power state,
+device class) and device drivers to allow them to participate in the power
-rather than just minimizing power consumption by one device.
+management of devices they are concerned with.  These interfaces cover both
+system sleep and runtime power management.
-Bus Driver Methods
------------------
+Device Power Management Operations
-The core methods to suspend and resume devices reside in struct bus_type.
+----------------------------------
-These are mostly of interest to people writing infrastructure for busses
+Device power management operations, at the subsystem level as well as at the
-like PCI or USB, or because they define the primitives that device drivers
+device driver level, are implemented by defining and populating objects of type
-may need to apply in domain-specific ways to their devices:
+struct dev_pm_ops:
-struct bus_type {
+struct dev_pm_ops {
-        ...
+        int (*prepare)(struct device *dev);
-        int  (*suspend)(struct device *dev, pm_message_t state);
+        void (*complete)(struct device *dev);
-        int  (*resume)(struct device *dev);
+        int (*suspend)(struct device *dev);
+        int (*resume)(struct device *dev);
+        int (*freeze)(struct device *dev);
+        int (*thaw)(struct device *dev);
+        int (*poweroff)(struct device *dev);
+        int (*restore)(struct device *dev);
+        int (*suspend_noirq)(struct device *dev);
+        int (*resume_noirq)(struct device *dev);
+        int (*freeze_noirq)(struct device *dev);
+        int (*thaw_noirq)(struct device *dev);
+        int (*poweroff_noirq)(struct device *dev);
+        int (*restore_noirq)(struct device *dev);
+        int (*runtime_suspend)(struct device *dev);
+        int (*runtime_resume)(struct device *dev);
+        int (*runtime_idle)(struct device *dev);
 };
-Bus drivers implement those methods as appropriate for the hardware and
+This structure is defined in include/linux/pm.h and the methods included in it
-the drivers using it; PCI works differently from USB, and so on.  Not many
+are also described in that file.  Their roles will be explained in what follows.
-people write bus drivers; most driver code is a "device driver" that
+For now, it should be sufficient to remember that the last three methods are
-builds on top of bus-specific framework code.
+specific to runtime power management while the remaining ones are used during
+system-wide power transitions.
-For more information on these driver calls, see the description later;
+There also is a deprecated "old" or "legacy" interface for power management
-they are called in phases for every device, respecting the parent-child
+operations available at least for some subsystems.  This approach does not use
-sequencing in the driver model tree.  Note that as this is being written,
+struct dev_pm_ops objects and it is suitable only for implementing system sleep
-only the suspend() and resume() are widely available; not many bus drivers
+power management methods.  Therefore it is not described in this document, so
-leverage all of those phases, or pass them down to lower driver levels.
+please refer directly to the source code for more information about it.
-/sys/devices/.../power/wakeup files
+Subsystem-Level Methods
-----------------------------------
+-----------------------
-All devices in the driver model have two flags to control handling of
+The core methods to suspend and resume devices reside in struct dev_pm_ops
-wakeup events, which are hardware signals that can force the device and/or
+pointed to by the pm member of struct bus_type, struct device_type and
-system out of a low power state.  These are initialized by bus or device
+struct class.  They are mostly of interest to the people writing infrastructure
-driver code using device_init_wakeup(dev,can_wakeup).
+for buses, like PCI or USB, or device type and device class drivers.
-The "can_wakeup" flag just records whether the device (and its driver) can
+Bus drivers implement these methods as appropriate for the hardware and the
-physically support wakeup events.  When that flag is clear, the sysfs
+drivers using it; PCI works differently from USB, and so on.  Not many people
-"wakeup" file is empty, and device_may_wakeup() returns false.
+write subsystem-level drivers; most driver code is a "device driver" that builds
+on top of bus-specific framework code.
-For devices that can issue wakeup events, a separate flag controls whether
+For more information on these driver calls, see the description later;
-that device should try to use its wakeup mechanism.  The initial value of
+they are called in phases for every device, respecting the parent-child
-device_may_wakeup() will be true, so that the device's "wakeup" file holds
+sequencing in the driver model tree.
-the value "enabled".  Userspace can change that to "disabled" so that
-device_may_wakeup() returns false; or change it back to "enabled" (so that
-it returns true again).
-EXAMPLE:  PCI Device Driver Methods
+/sys/devices/.../power/wakeup files
 -----------------------------------
-PCI framework software calls these methods when the PCI device driver bound
+All devices in the driver model have two flags to control handling of wakeup
-to a device device has provided them:
+events (hardware signals that can force the device and/or system out of a low
+power state).  These flags are initialized by bus or device driver code using
-struct pci_driver {
+device_set_wakeup_capable() and device_set_wakeup_enable(), defined in
-        ...
+include/linux/pm_wakeup.h.
-        int  (*suspend)(struct pci_device *pdev, pm_message_t state);
-        int  (*suspend_late)(struct pci_device *pdev, pm_message_t state);
-        int  (*resume_early)(struct pci_device *pdev);
+The "can_wakeup" flag just records whether the device (and its driver) can
-        int  (*resume)(struct pci_device *pdev);
+physically support wakeup events.  The device_set_wakeup_capable() routine
-};
+affects this flag.  The "should_wakeup" flag controls whether the device should
+try to use its wakeup mechanism.  device_set_wakeup_enable() affects this flag;
-Drivers will implement those methods, and call PCI-specific procedures
+for the most part drivers should not change its value.  The initial value of
-like pci_set_power_state(), pci_enable_wake(), pci_save_state(), and
+should_wakeup is supposed to be false for the majority of devices; the major
-pci_restore_state() to manage PCI-specific mechanisms.  (PCI config space
+exceptions are power buttons, keyboards, and Ethernet adapters whose WoL
-could be saved during driver probe, if it weren't for the fact that some
+(wake-on-LAN) feature has been set up with ethtool.
-systems rely on userspace tweaking using setpci.)  Devices are suspended
-before their bridges enter low power states, and likewise bridges resume
+Whether or not a device is capable of issuing wakeup events is a hardware
-before their devices.
+matter, and the kernel is responsible for keeping track of it.  By contrast,
+whether or not a wakeup-capable device should issue wakeup events is a policy
+decision, and it is managed by user space through a sysfs attribute: the
-Upper Layers of Driver Stacks
+power/wakeup file.  User space can write the strings "enabled" or "disabled" to
-----------------------------
+set or clear the should_wakeup flag, respectively.  Reads from the file will
-Device drivers generally have at least two interfaces, and the methods
+return the corresponding string if can_wakeup is true, but if can_wakeup is
-sketched above are the ones which apply to the lower level (nearer PCI, USB,
+false then reads will return an empty string, to indicate that the device
-or other bus hardware).  The network and block layers are examples of upper
+doesn't support wakeup events.  (But even though the file appears empty, writes
-level interfaces, as is a character device talking to userspace.
+will still affect the should_wakeup flag.)
-Power management requests normally need to flow through those upper levels,
+The device_may_wakeup() routine returns true only if both flags are set.
-which often use domain-oriented requests like "blank that screen".  In
+Drivers should check this routine when putting devices in a low-power state
-some cases those upper levels will have power management intelligence that
+during a system sleep transition, to see whether or not to enable the devices'
-relates to end-user activity, or other devices that work in cooperation.
+wakeup mechanisms.  However for runtime power management, wakeup events should
+be enabled whenever the device and driver both support them, regardless of the
-When those interfaces are structured using class interfaces, there is a
+should_wakeup flag.
-standard way to have the upper layer stop issuing requests to a given
-class device (and restart later):
+/sys/devices/.../power/control files
-struct class {
+------------------------------------
-        ...
+Each device in the driver model has a flag to control whether it is subject to
-        int  (*suspend)(struct device *dev, pm_message_t state);
+runtime power management.  This flag, called runtime_auto, is initialized by the
-        int  (*resume)(struct device *dev);
+bus type (or generally subsystem) code using pm_runtime_allow() or
-};
+pm_runtime_forbid(); the default is to allow runtime power management.
-Those calls are issued in specific phases of the process by which the
+The setting can be adjusted by user space by writing either "on" or "auto" to
-system enters a low power "suspend" state, or resumes from it.
+the device's power/control sysfs file.  Writing "auto" calls pm_runtime_allow(),
+setting the flag and allowing the device to be runtime power-managed by its
+driver.  Writing "on" calls pm_runtime_forbid(), clearing the flag, returning
-Calling Drivers to Enter System Sleep States
+the device to full power if it was in a low-power state, and preventing the
-============================================
+device from being runtime power-managed.  User space can check the current value
-When the system enters a low power state, each device's driver is asked
+of the runtime_auto flag by reading the file.
-to suspend the device by putting it into state compatible with the target
+The device's runtime_auto flag has no effect on the handling of system-wide
+power transitions.  In particular, the device can (and in the majority of cases
+should and will) be put into a low-power state during a system-wide transition
+to a sleep state even though its runtime_auto flag is clear.
+For more information about the runtime power management framework, refer to
+Documentation/power/runtime_pm.txt.
+Calling Drivers to Enter and Leave System Sleep States
+======================================================
+When the system goes into a sleep state, each device's driver is asked to
+suspend the device by putting it into a state compatible with the target
 system state.  That's usually some version of "off", but the details are
 system-specific.  Also, wakeup-enabled devices will usually stay partly
 functional in order to wake the system.
-When the system leaves that low power state, the device's driver is asked
+When the system leaves that low-power state, the device's driver is asked to
-to resume it.  The suspend and resume operations always go together, and
+resume it by returning it to full power.  The suspend and resume operations
-both are multi-phase operations.
+always go together, and both are multi-phase operations.
-For simple drivers, suspend might quiesce the device using the class code
+For simple drivers, suspend might quiesce the device using class code
-and then turn its hardware as "off" as possible with late_suspend.  The
+and then turn its hardware as "off" as possible during suspend_noirq.  The
 matching resume calls would then completely reinitialize the hardware
 before reactivating its class I/O queues.
-More power-aware drivers drivers will use more than one device low power
+More power-aware drivers might prepare the devices for triggering system wakeup
-state, either at runtime or during system sleep states, and might trigger
+events.
-system wakeup events.
 Call Sequence Guarantees
 ------------------------
-To ensure that bridges and similar links needed to talk to a device are
+To ensure that bridges and similar links needing to talk to a device are
 available when the device is suspended or resumed, the device tree is
 walked in a bottom-up order to suspend devices.  A top-down order is
 used to resume those devices.
@@ -194,67 +232,310 @@ its parent; and can't be removed or suspended after that parent.
 The policy is that the device tree should match hardware bus topology.
 (Or at least the control bus, for devices which use multiple busses.)
 In particular, this means that a device registration may fail if the parent of
-the device is suspending (ie. has been chosen by the PM core as the next
+the device is suspending (i.e. has been chosen by the PM core as the next
 device to suspend) or has already suspended, as well as after all of the other
 devices have been suspended.  Device drivers must be prepared to cope with such
 situations.
-Suspending Devices
+System Power Management Phases
------------------
+------------------------------
-Suspending a given device is done in several phases.  Suspending the
+Suspending or resuming the system is done in several phases.  Different phases
-system always includes every phase, executing calls for every device
+are used for standby or memory sleep states ("suspend-to-RAM") and the
-before the next phase begins.  Not all busses or classes support all
+hibernation state ("suspend-to-disk").  Each phase involves executing callbacks
-these callbacks; and not all drivers use all the callbacks.
+for every device before the next phase begins.  Not all busses or classes
+support all these callbacks and not all drivers use all the callbacks.  The
+various phases always run after tasks have been frozen and before they are
+unfrozen.  Furthermore, the *_noirq phases run at a time when IRQ handlers have
+been disabled (except for those marked with the IRQ_WAKEUP flag).
-The phases are seen by driver notifications issued in this order:
+Most phases use bus, type, and class callbacks (that is, methods defined in
+dev->bus->pm, dev->type->pm, and dev->class->pm).  The prepare and complete
+phases are exceptions; they use only bus callbacks.  When multiple callbacks
+are used in a phase, they are invoked in the order: <class, type, bus> during
+power-down transitions and in the opposite order during power-up transitions.
+For example, during the suspend phase the PM core invokes
-   1    class.suspend(dev, message) is called after tasks are frozen, for
+        dev->class->pm.suspend(dev);
-        devices associated with a class that has such a method.  This
+        dev->type->pm.suspend(dev);
-        method may sleep.
+        dev->bus->pm.suspend(dev);
-        Since I/O activity usually comes from such higher layers, this is
+before moving on to the next device, whereas during the resume phase the core
-        a good place to quiesce all drivers of a given type (and keep such
+invokes
-        code out of those drivers).
-   2    bus.suspend(dev, message) is called next.  This method may sleep,
+        dev->bus->pm.resume(dev);
-        and is often morphed into a device driver call with bus-specific
+        dev->type->pm.resume(dev);
-        parameters and/or rules.
+        dev->class->pm.resume(dev);
-        This call should handle parts of device suspend logic that require
+These callbacks may in turn invoke device- or driver-specific methods stored in
-        sleeping.  It probably does work to quiesce the device which hasn't
+dev->driver->pm, but they don't have to.
-        been abstracted into class.suspend().
-The pm_message_t parameter is currently used to refine those semantics
-(described later).
-At the end of those phases, drivers should normally have stopped all I/O
+Entering System Suspend
-transactions (DMA, IRQs), saved enough state that they can re-initialize
+-----------------------
-or restore previous state (as needed by the hardware), and placed the
+When the system goes into the standby or memory sleep state, the phases are:
-device into a low-power state.  On many platforms they will also use
-clk_disable() to gate off one or more clock sources; sometimes they will
+                prepare, suspend, suspend_noirq.
-also switch off power supplies, or reduce voltages.  Drivers which have
-runtime PM support may already have performed some or all of the steps
+    1.  The prepare phase is meant to prevent races by preventing new devices
-needed to prepare for the upcoming system sleep state.
+        from being registered; the PM core would never know that all the
+        children of a device had been suspended if new children could be
+        registered at will.  (By contrast, devices may be unregistered at any
+        time.)  Unlike the other suspend-related phases, during the prepare
+        phase the device tree is traversed top-down.
+        The prepare phase uses only a bus callback.  After the 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, but it should not put the device into a
+        low-power state.
+    2.  The suspend methods should quiesce the device to stop it from performing
+        I/O.  They also may save the device registers and put it into the
+        appropriate low-power state, depending on the bus type the device is on,
+        and they may enable wakeup events.
+    3.  The suspend_noirq phase occurs after IRQ handlers have been disabled,
+        which means that the driver's interrupt handler will not be called while
+        the callback method is running.  The methods should save the values of
+        the device's registers that weren't saved previously and finally put the
+        device into the appropriate low-power state.
+        The majority of subsystems and device drivers need not implement this
+        callback.  However, bus types allowing devices to share interrupt
+        vectors, like PCI, generally need it; otherwise a driver might encounter
+        an error during the suspend phase by fielding a shared interrupt
+        generated by some other device after its own device had been set to low
+        power.
+At the end of these phases, drivers should have stopped all I/O transactions
+(DMA, IRQs), saved enough state that they can re-initialize or restore previous
+state (as needed by the hardware), and placed the device into a low-power state.
+On many platforms they will gate off one or more clock sources; sometimes they
+will also switch off power supplies or reduce voltages.  (Drivers supporting
+runtime PM may already have performed some or all of these steps.)
+If device_may_wakeup(dev) returns true, the device should be prepared for
+generating hardware wakeup signals to trigger a system wakeup event when the
+system is in the sleep state.  For example, enable_irq_wake() might identify
+GPIO signals hooked up to a switch or other external hardware, and
+pci_enable_wake() does something similar for the PCI PME signal.
+If any of these callbacks returns an error, the system won't enter the desired
+low-power state.  Instead the PM core will unwind its actions by resuming all
+the devices that were suspended.
+Leaving System Suspend
+----------------------
+When resuming from standby or memory sleep, the phases are:
+                resume_noirq, resume, complete.
+    1.  The resume_noirq callback methods should perform any actions needed
+        before the driver's interrupt handlers are invoked.  This generally
+        means undoing the actions of the suspend_noirq phase.  If the bus type
+        permits devices to share interrupt vectors, like PCI, the method should
+        bring the device and its driver into a state in which the driver can
+        recognize if the device is the source of incoming interrupts, if any,
+        and handle them correctly.
+        For example, the PCI bus type's ->pm.resume_noirq() puts the device into
+        the full-power state (D0 in the PCI terminology) and restores the
+        standard configuration registers of the device.  Then it calls the
+        device driver's ->pm.resume_noirq() method to perform device-specific
+        actions.
+    2.  The resume methods should bring the the device back to its operating
+        state, so that it can perform normal I/O.  This generally involves
+        undoing the actions of the suspend phase.
+    3.  The complete phase uses only a bus callback.  The method should undo the
+        actions of the prepare phase.  Note, however, that new children may be
+        registered below the device as soon as the resume callbacks occur; it's
+        not necessary to wait until the complete phase.
+At the end of these phases, drivers should be as functional as they were before
+suspending: I/O can be performed using DMA and IRQs, and the relevant clocks are
+gated on.  Even if the device was in a low-power state before the system sleep
+because of runtime power management, afterwards it should be back in its
+full-power state.  There are multiple reasons why it's best to do this; they are
+discussed in more detail in Documentation/power/runtime_pm.txt.
-When any driver sees that its device_can_wakeup(dev), it should make sure
+However, the details here may again be platform-specific.  For example,
-to use the relevant hardware signals to trigger a system wakeup event.
+some systems support multiple "run" states, and the mode in effect at
-For example, enable_irq_wake() might identify GPIO signals hooked up to
+the end of resume might not be the one which preceded suspension.
-a switch or other external hardware, and pci_enable_wake() does something
+That means availability of certain clocks or power supplies changed,
-similar for PCI's PME# signal.
+which could easily affect how a driver works.
+Drivers need to be able to handle hardware which has been reset since the
+suspend methods were called, for example by complete reinitialization.
+This may be the hardest part, and the one most protected by NDA'd documents
+and chip errata.  It's simplest if the hardware state hasn't changed since
+the suspend was carried out, but that can't be guaranteed (in fact, it ususally
+is not the case).
+Drivers must also be prepared to notice that the device has been removed
+while the system was powered down, whenever that's physically possible.
+PCMCIA, MMC, USB, Firewire, SCSI, and even IDE are common examples of busses
+where common Linux platforms will see such removal.  Details of how drivers
+will notice and handle such removals are currently bus-specific, and often
+involve a separate thread.
+These callbacks may return an error value, but the PM core will ignore such
+errors since there's nothing it can do about them other than printing them in
+the system log.
+Entering Hibernation
+--------------------
+Hibernating the system is more complicated than putting it into the standby or
+memory sleep state, because it involves creating and saving a system image.
+Therefore there are more phases for hibernation, with a different set of
+callbacks.  These phases always run after tasks have been frozen and memory has
+been freed.
+The general procedure for hibernation is to quiesce all devices (freeze), create
+an image of the system memory while everything is stable, reactivate all
+devices (thaw), write the image to permanent storage, and finally shut down the
+system (poweroff).  The phases used to accomplish this are:
+        prepare, freeze, freeze_noirq, thaw_noirq, thaw, complete,
+        prepare, poweroff, poweroff_noirq
+    1.  The prepare phase is discussed in the "Entering System Suspend" section
+        above.
+    2.  The freeze methods should quiesce the device so that it doesn't generate
+        IRQs or DMA, and they may need to save the values of device registers.
+        However the device does not have to be put in a low-power state, and to
+        save time it's best not to do so.  Also, the device should not be
+        prepared to generate wakeup events.
+    3.  The freeze_noirq phase is analogous to the suspend_noirq phase discussed
+        above, except again that the device should not be put in a low-power
+        state and should not be allowed to generate wakeup events.
+At this point the system image is created.  All devices should be inactive and
+the contents of memory should remain undisturbed while this happens, so that the
+image forms an atomic snapshot of the system state.
+    4.  The thaw_noirq phase is analogous to the resume_noirq phase discussed
+        above.  The main difference is that its methods can assume the device is
+        in the same state as at the end of the freeze_noirq phase.
+    5.  The thaw phase is analogous to the resume phase discussed above.  Its
+        methods should bring the device back to an operating state, so that it
+        can be used for saving the image if necessary.
+    6.  The complete phase is discussed in the "Leaving System Suspend" section
+        above.
+At this point the system image is saved, and the devices then need to be
+prepared for the upcoming system shutdown.  This is much like suspending them
+before putting the system into the standby or memory sleep state, and the phases
+are similar.
+    7.  The prepare phase is discussed above.
+    8.  The poweroff phase is analogous to the suspend phase.
+    9.  The poweroff_noirq phase is analogous to the suspend_noirq phase.
+The poweroff and poweroff_noirq callbacks should do essentially the same things
+as the suspend and suspend_noirq callbacks.  The only notable difference is that
+they need not store the device register values, because the registers should
+already have been stored during the freeze or freeze_noirq phases.
+Leaving Hibernation
+-------------------
+Resuming from hibernation is, again, more complicated than resuming from a sleep
+state in which the contents of main memory are preserved, because it requires
+a system image to be loaded into memory and the pre-hibernation memory contents
+to be restored before control can be passed back to the image kernel.
+Although in principle, the image might be loaded into memory and the
+pre-hibernation memory contents restored by the boot loader, in practice this
+can't be done because boot loaders aren't smart enough and there is no
+established protocol for passing the necessary information.  So instead, the
+boot loader loads a fresh instance of the kernel, called the boot kernel, into
+memory and passes control to it in the usual way.  Then the boot kernel reads
+the system image, restores the pre-hibernation memory contents, and passes
+control to the image kernel.  Thus two different kernels are involved in
+resuming from hibernation.  In fact, the boot kernel may be completely different
+from the image kernel: a different configuration and even a different version.
+This has important consequences for device drivers and their subsystems.
+To be able to load the system image into memory, the boot kernel needs to
+include at least a subset of device drivers allowing it to access the storage
+medium containing the image, although it doesn't need to include all of the
+drivers present in the image kernel.  After the image has been loaded, the
+devices managed by the boot kernel need to be prepared for passing control back
+to the image kernel.  This is very similar to the initial steps involved in
+creating a system image, and it is accomplished in the same way, using prepare,
+freeze, and freeze_noirq phases.  However the devices affected by these phases
+are only those having drivers in the boot kernel; other devices will still be in
+whatever state the boot loader left them.
+Should the restoration of the pre-hibernation memory contents fail, the boot
+kernel would go through the "thawing" procedure described above, using the
+thaw_noirq, thaw, and complete phases, and then continue running normally.  This
+happens only rarely.  Most often the pre-hibernation memory contents are
+restored successfully and control is passed to the image kernel, which then
+becomes responsible for bringing the system back to the working state.
+To achieve this, the image kernel must restore the devices' pre-hibernation
+functionality.  The operation is much like waking up from the memory sleep
+state, although it involves different phases:
+        restore_noirq, restore, complete
+    1.  The restore_noirq phase is analogous to the resume_noirq phase.
+    2.  The restore phase is analogous to the resume phase.
+    3.  The complete phase is discussed above.
+The main difference from resume[_noirq] is that restore[_noirq] must assume the
+device has been accessed and reconfigured by the boot loader or the boot kernel.
+Consequently the state of the device may be different from the state remembered
+from the freeze and freeze_noirq phases.  The device may even need to be reset
+and completely re-initialized.  In many cases this difference doesn't matter, so
+the resume[_noirq] and restore[_norq] method pointers can be set to the same
+routines.  Nevertheless, different callback pointers are used in case there is a
+situation where it actually matters.
-If a driver (or bus, or class) fails it suspend method, the system won't
-enter the desired low power state; it will resume all the devices it's
-suspended so far.
-Note that drivers may need to perform different actions based on the target
+System Devices
-system lowpower/sleep state.  At this writing, there are only platform
+--------------
-specific APIs through which drivers could determine those target states.
+System devices (sysdevs) follow a slightly different API, which can be found in
+        include/linux/sysdev.h
+        drivers/base/sys.c
+System devices will be suspended with interrupts disabled, and after all other
+devices have been suspended.  On resume, they will be resumed before any other
+devices, and also with interrupts disabled.  These things occur in special
+"sysdev_driver" phases, which affect only system devices.
+Thus, after the suspend_noirq (or freeze_noirq or poweroff_noirq) phase, when
+the non-boot CPUs are all offline and IRQs are disabled on the remaining online
+CPU, then a sysdev_driver.suspend phase is carried out, and the system enters a
+sleep state (or a system image is created).  During resume (or after the image
+has been created or loaded) a sysdev_driver.resume phase is carried out, IRQs
+are enabled on the only online CPU, the non-boot CPUs are enabled, and the
+resume_noirq (or thaw_noirq or restore_noirq) phase begins.
+Code to actually enter and exit the system-wide low power state sometimes
+involves hardware details that are only known to the boot firmware, and
+may leave a CPU running software (from SRAM or flash memory) that monitors
+the system and manages its wakeup sequence.
 Device Low Power (suspend) States
 ---------------------------------
-Device low-power states aren't very standard.  One device might only handle
+Device low-power states aren't standard.  One device might only handle
 "on" and "off, while another might support a dozen different versions of
 "on" (how many engines are active?), plus a state that gets back to "on"
 faster than from a full "off".
@@ -265,7 +546,7 @@ PCI device may not perform DMA or issue IRQs, and any wakeup events it
 issues would be issued through the PME# bus signal.  Plus, there are
 several PCI-standard device states, some of which are optional.
-In contrast, integrated system-on-chip processors often use irqs as the
+In contrast, integrated system-on-chip processors often use IRQs as the
 wakeup event sources (so drivers would call enable_irq_wake) and might
 be able to treat DMA completion as a wakeup event (sometimes DMA can stay
 active too, it'd only be the CPU and some peripherals that sleep).
@@ -284,120 +565,17 @@ ways; the aforementioned LCD might be active in one product's "standby",
 but a different product using the same SOC might work differently.
-Meaning of pm_message_t.event
+Power Management Notifiers
-----------------------------
+--------------------------
-Parameters to suspend calls include the device affected and a message of
+There are some operations that cannot be carried out by the power management
-type pm_message_t, which has one field:  the event.  If driver does not
+callbacks discussed above, because the callbacks occur too late or too early.
-recognize the event code, suspend calls may abort the request and return
+To handle these cases, subsystems and device drivers may register power
-a negative errno.  However, most drivers will be fine if they implement
+management notifiers that are called before tasks are frozen and after they have
-PM_EVENT_SUSPEND semantics for all messages.
+been thawed.  Generally speaking, the PM notifiers are suitable for performing
+actions that either require user space to be available, or at least won't
+interfere with user space.
-The event codes are used to refine the goal of suspending the device, and
+For details refer to Documentation/power/notifiers.txt.
-mostly matter when creating or resuming system memory image snapshots, as
-used with suspend-to-disk:
-    PM_EVENT_SUSPEND -- quiesce the driver and put hardware into a low-power
-        state.  When used with system sleep states like "suspend-to-RAM" or
-        "standby", the upcoming resume() call will often be able to rely on
-        state kept in hardware, or issue system wakeup events.
-    PM_EVENT_HIBERNATE -- Put hardware into a low-power state and enable wakeup
-        events as appropriate.  It is only used with hibernation
-        (suspend-to-disk) and few devices are able to wake up the system from
-        this state; most are completely powered off.
-    PM_EVENT_FREEZE -- quiesce the driver, but don't necessarily change into
-        any low power mode.  A system snapshot is about to be taken, often
-        followed by a call to the driver's resume() method.  Neither wakeup
-        events nor DMA are allowed.
-    PM_EVENT_PRETHAW -- quiesce the driver, knowing that the upcoming resume()
-        will restore a suspend-to-disk snapshot from a different kernel image.
-        Drivers that are smart enough to look at their hardware state during
-        resume() processing need that state to be correct ... a PRETHAW could
-        be used to invalidate that state (by resetting the device), like a
-        shutdown() invocation would before a kexec() or system halt.  Other
-        drivers might handle this the same way as PM_EVENT_FREEZE.  Neither
-        wakeup events nor DMA are allowed.
-To enter "standby" (ACPI S1) or "Suspend to RAM" (STR, ACPI S3) states, or
-the similarly named APM states, only PM_EVENT_SUSPEND is used; the other event
-codes are used for hibernation ("Suspend to Disk", STD, ACPI S4).
-There's also PM_EVENT_ON, a value which never appears as a suspend event
-but is sometimes used to record the "not suspended" device state.
-Resuming Devices
----------------
-Resuming is done in multiple phases, much like suspending, with all
-devices processing each phase's calls before the next phase begins.
-The phases are seen by driver notifications issued in this order:
-   1    bus.resume(dev) reverses the effects of bus.suspend().  This may
-        be morphed into a device driver call with bus-specific parameters;
-        implementations may sleep.
-   2    class.resume(dev) is called for devices associated with a class
-        that has such a method.  Implementations may sleep.
-        This reverses the effects of class.suspend(), and would usually
-        reactivate the device's I/O queue.
-At the end of those phases, drivers should normally be as functional as
-they were before suspending:  I/O can be performed using DMA and IRQs, and
-the relevant clocks are gated on.  The device need not be "fully on"; it
-might be in a runtime lowpower/suspend state that acts as if it were.
-However, the details here may again be platform-specific.  For example,
-some systems support multiple "run" states, and the mode in effect at
-the end of resume() might not be the one which preceded suspension.
-That means availability of certain clocks or power supplies changed,
-which could easily affect how a driver works.
-Drivers need to be able to handle hardware which has been reset since the
-suspend methods were called, for example by complete reinitialization.
-This may be the hardest part, and the one most protected by NDA'd documents
-and chip errata.  It's simplest if the hardware state hasn't changed since
-the suspend() was called, but that can't always be guaranteed.
-Drivers must also be prepared to notice that the device has been removed
-while the system was powered off, whenever that's physically possible.
-PCMCIA, MMC, USB, Firewire, SCSI, and even IDE are common examples of busses
-where common Linux platforms will see such removal.  Details of how drivers
-will notice and handle such removals are currently bus-specific, and often
-involve a separate thread.
-Note that the bus-specific runtime PM wakeup mechanism can exist, and might
-be defined to share some of the same driver code as for system wakeup.  For
-example, a bus-specific device driver's resume() method might be used there,
-so it wouldn't only be called from bus.resume() during system-wide wakeup.
-See bus-specific information about how runtime wakeup events are handled.
-System Devices
--------------
-System devices follow a slightly different API, which can be found in
-        include/linux/sysdev.h
-        drivers/base/sys.c
-System devices will only be suspended with interrupts disabled, and after
-all other devices have been suspended.  On resume, they will be resumed
-before any other devices, and also with interrupts disabled.
-That is, IRQs are disabled, the suspend_late() phase begins, then the
-sysdev_driver.suspend() phase, and the system enters a sleep state.  Then
-the sysdev_driver.resume() phase begins, followed by the resume_early()
-phase, after which IRQs are enabled.
-Code to actually enter and exit the system-wide low power state sometimes
-involves hardware details that are only known to the boot firmware, and
-may leave a CPU running software (from SRAM or flash memory) that monitors
-the system and manages its wakeup sequence.
 Runtime Power Management
@@ -407,82 +585,23 @@ running. This feature is useful for devices that are not being used, and
 can offer significant power savings on a running system.  These devices
 often support a range of runtime power states, which might use names such
 as "off", "sleep", "idle", "active", and so on.  Those states will in some
-cases (like PCI) be partially constrained by a bus the device uses, and will
+cases (like PCI) be partially constrained by the bus the device uses, and will
 usually include hardware states that are also used in system sleep states.
-However, note that if a driver puts a device into a runtime low power state
+A system-wide power transition can be started while some devices are in low
-and the system then goes into a system-wide sleep state, it normally ought
+power states due to runtime power management.  The system sleep PM callbacks
-to resume into that runtime low power state rather than "full on".  Such
+should recognize such situations and react to them appropriately, but the
-distinctions would be part of the driver-internal state machine for that
+necessary actions are subsystem-specific.
-hardware; the whole point of runtime power management is to be sure that
-drivers are decoupled in that way from the state machine governing phases
+In some cases the decision may be made at the subsystem level while in other
-of the system-wide power/sleep state transitions.
+cases the device driver may be left to decide.  In some cases it may be
+desirable to leave a suspended device in that state during a system-wide power
+transition, but in other cases the device must be put back into the full-power
-Power Saving Techniques
+state temporarily, for example so that its system wakeup capability can be
-----------------------
+disabled.  This all depends on the hardware and the design of the subsystem and
-Normally runtime power management is handled by the drivers without specific
+device driver in question.
-userspace or kernel intervention, by device-aware use of techniques like:
+During system-wide resume from a sleep state it's best to put devices into the
-    Using information provided by other system layers
+full-power state, as explained in Documentation/power/runtime_pm.txt.  Refer to
-        - stay deeply "off" except between open() and close()
+that document for more information regarding this particular issue as well as
-        - if transceiver/PHY indicates "nobody connected", stay "off"
+for information on the device runtime power management framework in general.
-        - application protocols may include power commands or hints
-    Using fewer CPU cycles
-        - using DMA instead of PIO
-        - removing timers, or making them lower frequency
-        - shortening "hot" code paths
-        - eliminating cache misses
-        - (sometimes) offloading work to device firmware
-    Reducing other resource costs
-        - gating off unused clocks in software (or hardware)
-        - switching off unused power supplies
-        - eliminating (or delaying/merging) IRQs
-        - tuning DMA to use word and/or burst modes
-    Using device-specific low power states
-        - using lower voltages
-        - avoiding needless DMA transfers
-Read your hardware documentation carefully to see the opportunities that
-may be available.  If you can, measure the actual power usage and check
-it against the budget established for your project.
-Examples:  USB hosts, system timer, system CPU
----------------------------------------------
-USB host controllers make interesting, if complex, examples.  In many cases
-these have no work to do:  no USB devices are connected, or all of them are
-in the USB "suspend" state.  Linux host controller drivers can then disable
-periodic DMA transfers that would otherwise be a constant power drain on the
-memory subsystem, and enter a suspend state.  In power-aware controllers,
-entering that suspend state may disable the clock used with USB signaling,
-saving a certain amount of power.
-The controller will be woken from that state (with an IRQ) by changes to the
-signal state on the data lines of a given port, for example by an existing
-peripheral requesting "remote wakeup" or by plugging a new peripheral.  The
-same wakeup mechanism usually works from "standby" sleep states, and on some
-systems also from "suspend to RAM" (or even "suspend to disk") states.
-(Except that ACPI may be involved instead of normal IRQs, on some hardware.)
-System devices like timers and CPUs may have special roles in the platform
-power management scheme.  For example, system timers using a "dynamic tick"
-approach don't just save CPU cycles (by eliminating needless timer IRQs),
-but they may also open the door to using lower power CPU "idle" states that
-cost more than a jiffie to enter and exit.  On x86 systems these are states
-like "C3"; note that periodic DMA transfers from a USB host controller will
-also prevent entry to a C3 state, much like a periodic timer IRQ.
-That kind of runtime mechanism interaction is common.  "System On Chip" (SOC)
-processors often have low power idle modes that can't be entered unless
-certain medium-speed clocks (often 12 or 48 MHz) are gated off.  When the
-drivers gate those clocks effectively, then the system idle task may be able
-to use the lower power idle modes and thereby increase battery life.
-If the CPU can have a "cpufreq" driver, there also may be opportunities
-to shift to lower voltage settings and reduce the power cost of executing
-a given number of instructions.  (Without voltage adjustment, it's rare
-for cpufreq to save much power; the cost-per-instruction must go down.)
diff --git a/Documentation/power/pci.txt b/Documentation/power/pci.txt
index dd8fe43888d3..62328d76b55b 100644
--- a/Documentation/power/pci.txt
+++ b/Documentation/power/pci.txt
@@ -1,299 +1,1025 @@
 PCI Power Management
-~~~~~~~~~~~~~~~~~~~~
-An overview of the concepts and the related functions in the Linux kernel
+Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+An overview of concepts and the Linux kernel's interfaces related to PCI power
+management.  Based on previous work by Patrick Mochel <mochel@transmeta.com>
+(and others).
-Patrick Mochel <mochel@transmeta.com>
+This document only covers the aspects of power management specific to PCI
-(and others)
+devices.  For general description of the kernel's interfaces related to device
+power management refer to Documentation/power/devices.txt and
+Documentation/power/runtime_pm.txt.
 ---------------------------------------------------------------------------
-1. Overview
+1. Hardware and Platform Support for PCI Power Management
-2. How the PCI Subsystem Does Power Management
+2. PCI Subsystem and Device Power Management
-3. PCI Utility Functions
+3. PCI Device Drivers and Power Management
-4. PCI Device Drivers
+4. Resources
-5. Resources
-1. Overview
+1. Hardware and Platform Support for PCI Power Management
-~~~~~~~~~~~
+=========================================================
-The PCI Power Management Specification was introduced between the PCI 2.1 and
+1.1. Native and Platform-Based Power Management
-PCI 2.2 Specifications. It a standard interface for controlling various 
+-----------------------------------------------
-power management operations.
+In general, power management is a feature allowing one to save energy by putting
+devices into states in which they draw less power (low-power states) at the
-Implementation of the PCI PM Spec is optional, as are several sub-components of
+price of reduced functionality or performance.
-it. If a device supports the PCI PM Spec, the device will have an 8 byte
-capability field in its PCI configuration space. This field is used to describe
+Usually, a device is put into a low-power state when it is underutilized or
-and control the standard PCI power management features.
+completely inactive.  However, when it is necessary to use the device once
+again, it has to be put back into the "fully functional" state (full-power
-The PCI PM spec defines 4 operating states for devices (D0 - D3) and for buses
+state).  This may happen when there are some data for the device to handle or
-(B0 - B3). The higher the number, the less power the device consumes. However,
+as a result of an external event requiring the device to be active, which may
-the higher the number, the longer the latency is for the device to return to 
+be signaled by the device itself.
-an operational state (D0).
+PCI devices may be put into low-power states in two ways, by using the device
-There are actually two D3 states.  When someone talks about D3, they usually
+capabilities introduced by the PCI Bus Power Management Interface Specification,
-mean D3hot, which corresponds to an ACPI D2 state (power is reduced, the
+or with the help of platform firmware, such as an ACPI BIOS.  In the first
-device may lose some context).  But they may also mean D3cold, which is an
+approach, that is referred to as the native PCI power management (native PCI PM)
-ACPI D3 state (power is fully off, all state was discarded); or both.
+in what follows, the device power state is changed as a result of writing a
+specific value into one of its standard configuration registers.  The second
-Bus power management is not covered in this version of this document.
+approach requires the platform firmware to provide special methods that may be
+used by the kernel to change the device's power state.
-Note that all PCI devices support D0 and D3cold by default, regardless of
-whether or not they implement any of the PCI PM spec.
+Devices supporting the native PCI PM usually can generate wakeup signals called
+Power Management Events (PMEs) to let the kernel know about external events
-The possible state transitions that a device can undergo are:
+requiring the device to be active.  After receiving a PME the kernel is supposed
+to put the device that sent it into the full-power state.  However, the PCI Bus
-+---------------------------+
+Power Management Interface Specification doesn't define any standard method of
-| Current State | New State |
+delivering the PME from the device to the CPU and the operating system kernel.
-+---------------------------+
+It is assumed that the platform firmware will perform this task and therefore,
-| D0            | D1, D2, D3|
+even though a PCI device is set up to generate PMEs, it also may be necessary to
-+---------------------------+
+prepare the platform firmware for notifying the CPU of the PMEs coming from the
-| D1            | D2, D3    |
+device (e.g. by generating interrupts).
-+---------------------------+
-| D2            | D3        |
+In turn, if the methods provided by the platform firmware are used for changing
-+---------------------------+
+the power state of a device, usually the platform also provides a method for
-| D1, D2, D3    | D0        |
+preparing the device to generate wakeup signals.  In that case, however, it
-+---------------------------+
+often also is necessary to prepare the device for generating PMEs using the
+native PCI PM mechanism, because the method provided by the platform depends on
-Note that when the system is entering a global suspend state, all devices will
+that.
-be placed into D3 and when resuming, all devices will be placed into D0.
-However, when the system is running, other state transitions are possible.
+Thus in many situations both the native and the platform-based power management
+mechanisms have to be used simultaneously to obtain the desired result.
-2. How The PCI Subsystem Handles Power Management
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+1.2. Native PCI Power Management
+--------------------------------
-The PCI suspend/resume functionality is accessed indirectly via the Power
+The PCI Bus Power Management Interface Specification (PCI PM Spec) was
-Management subsystem. At boot, the PCI driver registers a power management
+introduced between the PCI 2.1 and PCI 2.2 Specifications.  It defined a
-callback with that layer. Upon entering a suspend state, the PM layer iterates
+standard interface for performing various operations related to power
-through all of its registered callbacks. This currently takes place only during
+management.
-APM state transitions.
+The implementation of the PCI PM Spec is optional for conventional PCI devices,
-Upon going to sleep, the PCI subsystem walks its device tree twice. Both times,
+but it is mandatory for PCI Express devices.  If a device supports the PCI PM
-it does a depth first walk of the device tree. The first walk saves each of the
+Spec, it has an 8 byte power management capability field in its PCI
-device's state and checks for devices that will prevent the system from entering
+configuration space.  This field is used to describe and control the standard
-a global power state. The next walk then places the devices in a low power
+features related to the native PCI power management.
+The PCI PM Spec defines 4 operating states for devices (D0-D3) and for buses
+(B0-B3).  The higher the number, the less power is drawn by the device or bus
+in that state.  However, the higher the number, the longer the latency for
+the device or bus to return to the full-power state (D0 or B0, respectively).
+There are two variants of the D3 state defined by the specification.  The first
+one is D3hot, referred to as the software accessible D3, because devices can be
+programmed to go into it.  The second one, D3cold, is the state that PCI devices
+are in when the supply voltage (Vcc) is removed from them.  It is not possible
+to program a PCI device to go into D3cold, although there may be a programmable
+interface for putting the bus the device is on into a state in which Vcc is
+removed from all devices on the bus.
+PCI bus power management, however, is not supported by the Linux kernel at the
+time of this writing and therefore it is not covered by this document.
+Note that every PCI device can be in the full-power state (D0) or in D3cold,
+regardless of whether or not it implements the PCI PM Spec.  In addition to
+that, if the PCI PM Spec is implemented by the device, it must support D3hot
+as well as D0.  The support for the D1 and D2 power states is optional.
+PCI devices supporting the PCI PM Spec can be programmed to go to any of the
+supported low-power states (except for D3cold).  While in D1-D3hot the
+standard configuration registers of the device must be accessible to software
+(i.e. the device is required to respond to PCI configuration accesses), although
+its I/O and memory spaces are then disabled.  This allows the device to be
+programmatically put into D0.  Thus the kernel can switch the device back and
+forth between D0 and the supported low-power states (except for D3cold) and the
+possible power state transitions the device can undergo are the following:
+----------------------------+
+| Current State | New State  |
+----------------------------+
+| D0            | D1, D2, D3 |
+----------------------------+
+| D1            | D2, D3     |
+----------------------------+
+| D2            | D3         |
+----------------------------+
+| D1, D2, D3    | D0         |
+----------------------------+
+The transition from D3cold to D0 occurs when the supply voltage is provided to
+the device (i.e. power is restored).  In that case the device returns to D0 with
+a full power-on reset sequence and the power-on defaults are restored to the
+device by hardware just as at initial power up.
+PCI devices supporting the PCI PM Spec can be programmed to generate PMEs
+while in a low-power state (D1-D3), but they are not required to be capable
+of generating PMEs from all supported low-power states.  In particular, the
+capability of generating PMEs from D3cold is optional and depends on the
+presence of additional voltage (3.3Vaux) allowing the device to remain
+sufficiently active to generate a wakeup signal.
+1.3. ACPI Device Power Management
+---------------------------------
+The platform firmware support for the power management of PCI devices is
+system-specific.  However, if the system in question is compliant with the
+Advanced Configuration and Power Interface (ACPI) Specification, like the
+majority of x86-based systems, it is supposed to implement device power
+management interfaces defined by the ACPI standard.
+For this purpose the ACPI BIOS provides special functions called "control
+methods" that may be executed by the kernel to perform specific tasks, such as
+putting a device into a low-power state.  These control methods are encoded
+using special byte-code language called the ACPI Machine Language (AML) and
+stored in the machine's BIOS.  The kernel loads them from the BIOS and executes
+them as needed using an AML interpreter that translates the AML byte code into
+computations and memory or I/O space accesses.  This way, in theory, a BIOS
+writer can provide the kernel with a means to perform actions depending
+on the system design in a system-specific fashion.
+ACPI control methods may be divided into global control methods, that are not
+associated with any particular devices, and device control methods, that have
+to be defined separately for each device supposed to be handled with the help of
+the platform.  This means, in particular, that ACPI device control methods can
+only be used to handle devices that the BIOS writer knew about in advance.  The
+ACPI methods used for device power management fall into that category.
+The ACPI specification assumes that devices can be in one of four power states
+labeled as D0, D1, D2, and D3 that roughly correspond to the native PCI PM
+D0-D3 states (although the difference between D3hot and D3cold is not taken
+into account by ACPI).  Moreover, for each power state of a device there is a
+set of power resources that have to be enabled for the device to be put into
+that state.  These power resources are controlled (i.e. enabled or disabled)
+with the help of their own control methods, _ON and _OFF, that have to be
+defined individually for each of them.
+To put a device into the ACPI power state Dx (where x is a number between 0 and
+3 inclusive) the kernel is supposed to (1) enable the power resources required
+by the device in this state using their _ON control methods and (2) execute the
+_PSx control method defined for the device.  In addition to that, if the device
+is going to be put into a low-power state (D1-D3) and is supposed to generate
+wakeup signals from that state, the _DSW (or _PSW, replaced with _DSW by ACPI
+3.0) control method defined for it has to be executed before _PSx.  Power
+resources that are not required by the device in the target power state and are
+not required any more by any other device should be disabled (by executing their
+_OFF control methods).  If the current power state of the device is D3, it can
+only be put into D0 this way.
+However, quite often the power states of devices are changed during a
+system-wide transition into a sleep state or back into the working state.  ACPI
+defines four system sleep states, S1, S2, S3, and S4, and denotes the system
+working state as S0.  In general, the target system sleep (or working) state
+determines the highest power (lowest number) state the device can be put
+into and the kernel is supposed to obtain this information by executing the
+device's _SxD control method (where x is a number between 0 and 4 inclusive).
+If the device is required to wake up the system from the target sleep state, the
+lowest power (highest number) state it can be put into is also determined by the
+target state of the system.  The kernel is then supposed to use the device's
+_SxW control method to obtain the number of that state.  It also is supposed to
+use the device's _PRW control method to learn which power resources need to be
+enabled for the device to be able to generate wakeup signals.
+1.4. Wakeup Signaling
+---------------------
+Wakeup signals generated by PCI devices, either as native PCI PMEs, or as
+a result of the execution of the _DSW (or _PSW) ACPI control method before
+putting the device into a low-power state, have to be caught and handled as
+appropriate.  If they are sent while the system is in the working state
+(ACPI S0), they should be translated into interrupts so that the kernel can
+put the devices generating them into the full-power state and take care of the
+events that triggered them.  In turn, if they are sent while the system is
+sleeping, they should cause the system's core logic to trigger wakeup.
+On ACPI-based systems wakeup signals sent by conventional PCI devices are
+converted into ACPI General-Purpose Events (GPEs) which are hardware signals
+from the system core logic generated in response to various events that need to
+be acted upon.  Every GPE is associated with one or more sources of potentially
+interesting events.  In particular, a GPE may be associated with a PCI device
+capable of signaling wakeup.  The information on the connections between GPEs
+and event sources is recorded in the system's ACPI BIOS from where it can be
+read by the kernel.
+If a PCI device known to the system's ACPI BIOS signals wakeup, the GPE
+associated with it (if there is one) is triggered.  The GPEs associated with PCI
+bridges may also be triggered in response to a wakeup signal from one of the
+devices below the bridge (this also is the case for root bridges) and, for
+example, native PCI PMEs from devices unknown to the system's ACPI BIOS may be
+handled this way.
+A GPE may be triggered when the system is sleeping (i.e. when it is in one of
+the ACPI S1-S4 states), in which case system wakeup is started by its core logic
+(the device that was the source of the signal causing the system wakeup to occur
+may be identified later).  The GPEs used in such situations are referred to as
+wakeup GPEs.
+Usually, however, GPEs are also triggered when the system is in the working
+state (ACPI S0) and in that case the system's core logic generates a System
+Control Interrupt (SCI) to notify the kernel of the event.  Then, the SCI
+handler identifies the GPE that caused the interrupt to be generated which,
+in turn, allows the kernel to identify the source of the event (that may be
+a PCI device signaling wakeup).  The GPEs used for notifying the kernel of
+events occurring while the system is in the working state are referred to as
+runtime GPEs.
+Unfortunately, there is no standard way of handling wakeup signals sent by
+conventional PCI devices on systems that are not ACPI-based, but there is one
+for PCI Express devices.  Namely, the PCI Express Base Specification introduced
+a native mechanism for converting native PCI PMEs into interrupts generated by
+root ports.  For conventional PCI devices native PMEs are out-of-band, so they
+are routed separately and they need not pass through bridges (in principle they
+may be routed directly to the system's core logic), but for PCI Express devices
+they are in-band messages that have to pass through the PCI Express hierarchy,
+including the root port on the path from the device to the Root Complex.  Thus
+it was possible to introduce a mechanism by which a root port generates an
+interrupt whenever it receives a PME message from one of the devices below it.
+The PCI Express Requester ID of the device that sent the PME message is then
+recorded in one of the root port's configuration registers from where it may be
+read by the interrupt handler allowing the device to be identified.  [PME
+messages sent by PCI Express endpoints integrated with the Root Complex don't
+pass through root ports, but instead they cause a Root Complex Event Collector
+(if there is one) to generate interrupts.]
+In principle the native PCI Express PME signaling may also be used on ACPI-based
+systems along with the GPEs, but to use it the kernel has to ask the system's
+ACPI BIOS to release control of root port configuration registers.  The ACPI
+BIOS, however, is not required to allow the kernel to control these registers
+and if it doesn't do that, the kernel must not modify their contents.  Of course
+the native PCI Express PME signaling cannot be used by the kernel in that case.
+2. PCI Subsystem and Device Power Management
+============================================
+2.1. Device Power Management Callbacks
+--------------------------------------
+The PCI Subsystem participates in the power management of PCI devices in a
+number of ways.  First of all, it provides an intermediate code layer between
+the device power management core (PM core) and PCI device drivers.
+Specifically, the pm field of the PCI subsystem's struct bus_type object,
+pci_bus_type, points to a struct dev_pm_ops object, pci_dev_pm_ops, containing
+pointers to several device power management callbacks:
+const struct dev_pm_ops pci_dev_pm_ops = {
+        .prepare = pci_pm_prepare,
+        .complete = pci_pm_complete,
+        .suspend = pci_pm_suspend,
+        .resume = pci_pm_resume,
+        .freeze = pci_pm_freeze,
+        .thaw = pci_pm_thaw,
+        .poweroff = pci_pm_poweroff,
+        .restore = pci_pm_restore,
+        .suspend_noirq = pci_pm_suspend_noirq,
+        .resume_noirq = pci_pm_resume_noirq,
+        .freeze_noirq = pci_pm_freeze_noirq,
+        .thaw_noirq = pci_pm_thaw_noirq,
+        .poweroff_noirq = pci_pm_poweroff_noirq,
+        .restore_noirq = pci_pm_restore_noirq,
+        .runtime_suspend = pci_pm_runtime_suspend,
+        .runtime_resume = pci_pm_runtime_resume,
+        .runtime_idle = pci_pm_runtime_idle,
+};
+These callbacks are executed by the PM core in various situations related to
+device power management and they, in turn, execute power management callbacks
+provided by PCI device drivers.  They also perform power management operations
+involving some standard configuration registers of PCI devices that device
+drivers need not know or care about.
+The structure representing a PCI device, struct pci_dev, contains several fields
+that these callbacks operate on:
+struct pci_dev {
+        ...
+        pci_power_t     current_state;  /* Current operating state. */
+        int             pm_cap;         /* PM capability offset in the
+                                           configuration space */
+        unsigned int    pme_support:5;  /* Bitmask of states from which PME#
+                                           can be generated */
+        unsigned int    pme_interrupt:1;/* Is native PCIe PME signaling used? */
+        unsigned int    d1_support:1;   /* Low power state D1 is supported */
+        unsigned int    d2_support:1;   /* Low power state D2 is supported */
+        unsigned int    no_d1d2:1;      /* D1 and D2 are forbidden */
+        unsigned int    wakeup_prepared:1;  /* Device prepared for wake up */
+        unsigned int    d3_delay;       /* D3->D0 transition time in ms */
+        ...
+};
+They also indirectly use some fields of the struct device that is embedded in
+struct pci_dev.
+2.2. Device Initialization
+--------------------------
+The PCI subsystem's first task related to device power management is to
+prepare the device for power management and initialize the fields of struct
+pci_dev used for this purpose.  This happens in two functions defined in
+drivers/pci/pci.c, pci_pm_init() and platform_pci_wakeup_init().
+The first of these functions checks if the device supports native PCI PM
+and if that's the case the offset of its power management capability structure
+in the configuration space is stored in the pm_cap field of the device's struct
+pci_dev object.  Next, the function checks which PCI low-power states are
+supported by the device and from which low-power states the device can generate
+native PCI PMEs.  The power management fields of the device's struct pci_dev and
+the struct device embedded in it are updated accordingly and the generation of
+PMEs by the device is disabled.
+The second function checks if the device can be prepared to signal wakeup with
+the help of the platform firmware, such as the ACPI BIOS.  If that is the case,
+the function updates the wakeup fields in struct device embedded in the
+device's struct pci_dev and uses the firmware-provided method to prevent the
+device from signaling wakeup.
+At this point the device is ready for power management.  For driverless devices,
+however, this functionality is limited to a few basic operations carried out
+during system-wide transitions to a sleep state and back to the working state.
+2.3. Runtime Device Power Management
+------------------------------------
+The PCI subsystem plays a vital role in the runtime power management of PCI
+devices.  For this purpose it uses the general runtime power management
+(runtime PM) framework described in Documentation/power/runtime_pm.txt.
+Namely, it provides subsystem-level callbacks:
+        pci_pm_runtime_suspend()
+        pci_pm_runtime_resume()
+        pci_pm_runtime_idle()
+that are executed by the core runtime PM routines.  It also implements the
+entire mechanics necessary for handling runtime wakeup signals from PCI devices
+in low-power states, which at the time of this writing works for both the native
+PCI Express PME signaling and the ACPI GPE-based wakeup signaling described in
+Section 1.
+First, a PCI device is put into a low-power state, or suspended, with the help
+of pm_schedule_suspend() or pm_runtime_suspend() which for PCI devices call
+pci_pm_runtime_suspend() to do the actual job.  For this to work, the device's
+driver has to provide a pm->runtime_suspend() callback (see below), which is
+run by pci_pm_runtime_suspend() as the first action.  If the driver's callback
+returns successfully, the device's standard configuration registers are saved,
+the device is prepared to generate wakeup signals and, finally, it is put into
+the target low-power state.
+The low-power state to put the device into is the lowest-power (highest number)
+state from which it can signal wakeup.  The exact method of signaling wakeup is
+system-dependent and is determined by the PCI subsystem on the basis of the
+reported capabilities of the device and the platform firmware.  To prepare the
+device for signaling wakeup and put it into the selected low-power state, the
+PCI subsystem can use the platform firmware as well as the device's native PCI
+PM capabilities, if supported.
+It is expected that the device driver's pm->runtime_suspend() callback will
+not attempt to prepare the device for signaling wakeup or to put it into a
+low-power state.  The driver ought to leave these tasks to the PCI subsystem
+that has all of the information necessary to perform them.
+A suspended device is brought back into the "active" state, or resumed,
+with the help of pm_request_resume() or pm_runtime_resume() which both call
+pci_pm_runtime_resume() for PCI devices.  Again, this only works if the device's
+driver provides a pm->runtime_resume() callback (see below).  However, before
+the driver's callback is executed, pci_pm_runtime_resume() brings the device
+back into the full-power state, prevents it from signaling wakeup while in that
+state and restores its standard configuration registers.  Thus the driver's
+callback need not worry about the PCI-specific aspects of the device resume.
+Note that generally pci_pm_runtime_resume() may be called in two different
+situations.  First, it may be called at the request of the device's driver, for
+example if there are some data for it to process.  Second, it may be called
+as a result of a wakeup signal from the device itself (this sometimes is
+referred to as "remote wakeup").  Of course, for this purpose the wakeup signal
+is handled in one of the ways described in Section 1 and finally converted into
+a notification for the PCI subsystem after the source device has been
+identified.
+The pci_pm_runtime_idle() function, called for PCI devices by pm_runtime_idle()
+and pm_request_idle(), executes the device driver's pm->runtime_idle()
+callback, if defined, and if that callback doesn't return error code (or is not
+present at all), suspends the device with the help of pm_runtime_suspend().
+Sometimes pci_pm_runtime_idle() is called automatically by the PM core (for
+example, it is called right after the device has just been resumed), in which
+cases it is expected to suspend the device if that makes sense.  Usually,
+however, the PCI subsystem doesn't really know if the device really can be
+suspended, so it lets the device's driver decide by running its
+pm->runtime_idle() callback.
+2.4. System-Wide Power Transitions
+----------------------------------
+There are a few different types of system-wide power transitions, described in
+Documentation/power/devices.txt.  Each of them requires devices to be handled
+in a specific way and the PM core executes subsystem-level power management
+callbacks for this purpose.  They are executed in phases such that each phase
+involves executing the same subsystem-level callback for every device belonging
+to the given subsystem before the next phase begins.  These phases always run
+after tasks have been frozen.
+2.4.1. System Suspend
+When the system is going into a sleep state in which the contents of memory will
+be preserved, such as one of the ACPI sleep states S1-S3, the phases are:
+        prepare, suspend, suspend_noirq.
+The following PCI bus type's callbacks, respectively, are used in these phases:
+        pci_pm_prepare()
+        pci_pm_suspend()
+        pci_pm_suspend_noirq()
+The pci_pm_prepare() routine first puts the device into the "fully functional"
+state with the help of pm_runtime_resume().  Then, it executes the device
+driver's pm->prepare() callback if defined (i.e. if the driver's struct
+dev_pm_ops object is present and the prepare pointer in that object is valid).
+The pci_pm_suspend() routine first checks if the device's driver implements
+legacy PCI suspend routines (see Section 3), in which case the driver's legacy
+suspend callback is executed, if present, and its result is returned.  Next, if
+the device's driver doesn't provide a struct dev_pm_ops object (containing
+pointers to the driver's callbacks), pci_pm_default_suspend() is called, which
+simply turns off the device's bus master capability and runs
+pcibios_disable_device() to disable it, unless the device is a bridge (PCI
+bridges are ignored by this routine).  Next, the device driver's pm->suspend()
+callback is executed, if defined, and its result is returned if it fails.
+Finally, pci_fixup_device() is called to apply hardware suspend quirks related
+to the device if necessary.
+Note that the suspend phase is carried out asynchronously for PCI devices, so
+the pci_pm_suspend() callback may be executed in parallel for any pair of PCI
+devices that don't depend on each other in a known way (i.e. none of the paths
+in the device tree from the root bridge to a leaf device contains both of them).
+The pci_pm_suspend_noirq() routine is executed after suspend_device_irqs() has
+been called, which means that the device driver's interrupt handler won't be
+invoked while this routine is running.  It first checks if the device's driver
+implements legacy PCI suspends routines (Section 3), in which case the legacy
+late suspend routine is called and its result is returned (the standard
+configuration registers of the device are saved if the driver's callback hasn't
+done that).  Second, if the device driver's struct dev_pm_ops object is not
+present, the device's standard configuration registers are saved and the routine
+returns success.  Otherwise the device driver's pm->suspend_noirq() callback is
+executed, if present, and its result is returned if it fails.  Next, if the
+device's standard configuration registers haven't been saved yet (one of the
+device driver's callbacks executed before might do that), pci_pm_suspend_noirq()
+saves them, prepares the device to signal wakeup (if necessary) and puts it into
+a low-power state.
+The low-power state to put the device into is the lowest-power (highest number)
+state from which it can signal wakeup while the system is in the target sleep
+state.  Just like in the runtime PM case described above, the mechanism of
+signaling wakeup is system-dependent and determined by the PCI subsystem, which
+is also responsible for preparing the device to signal wakeup from the system's
+target sleep state as appropriate.
+PCI device drivers (that don't implement legacy power management callbacks) are
+generally not expected to prepare devices for signaling wakeup or to put them
+into low-power states.  However, if one of the driver's suspend callbacks
+(pm->suspend() or pm->suspend_noirq()) saves the device's standard configuration
+registers, pci_pm_suspend_noirq() will assume that the device has been prepared
+to signal wakeup and put into a low-power state by the driver (the driver is
+then assumed to have used the helper functions provided by the PCI subsystem for
+this purpose).  PCI device drivers are not encouraged to do that, but in some
+rare cases doing that in the driver may be the optimum approach.
+2.4.2. System Resume
+When the system is undergoing a transition from a sleep state in which the
+contents of memory have been preserved, such as one of the ACPI sleep states
+S1-S3, into the working state (ACPI S0), the phases are:
+        resume_noirq, resume, complete.
+The following PCI bus type's callbacks, respectively, are executed in these
+phases:
+        pci_pm_resume_noirq()
+        pci_pm_resume()
+        pci_pm_complete()
+The pci_pm_resume_noirq() routine first puts the device into the full-power
+state, restores its standard configuration registers and applies early resume
+hardware quirks related to the device, if necessary.  This is done
+unconditionally, regardless of whether or not the device's driver implements
+legacy PCI power management callbacks (this way all PCI devices are in the
+full-power state and their standard configuration registers have been restored
+when their interrupt handlers are invoked for the first time during resume,
+which allows the kernel to avoid problems with the handling of shared interrupts
+by drivers whose devices are still suspended).  If legacy PCI power management
+callbacks (see Section 3) are implemented by the device's driver, the legacy
+early resume callback is executed and its result is returned.  Otherwise, the
+device driver's pm->resume_noirq() callback is executed, if defined, and its
+result is returned.
+The pci_pm_resume() routine first checks if the device's standard configuration
+registers have been restored and restores them if that's not the case (this
+only is necessary in the error path during a failing suspend).  Next, resume
+hardware quirks related to the device are applied, if necessary, and if the
+device's driver implements legacy PCI power management callbacks (see
+Section 3), the driver's legacy resume callback is executed and its result is
+returned.  Otherwise, the device's wakeup signaling mechanisms are blocked and
+its driver's pm->resume() callback is executed, if defined (the callback's
+result is then returned).
+The resume phase is carried out asynchronously for PCI devices, like the
+suspend phase described above, which means that if two PCI devices don't depend
+on each other in a known way, the pci_pm_resume() routine may be executed for
+the both of them in parallel.
+The pci_pm_complete() routine only executes the device driver's pm->complete()
+callback, if defined.
+2.4.3. System Hibernation
+System hibernation is more complicated than system suspend, because it requires
+a system image to be created and written into a persistent storage medium.  The
+image is created atomically and all devices are quiesced, or frozen, before that
+happens.
+The freezing of devices is carried out after enough memory has been freed (at
+the time of this writing the image creation requires at least 50% of system RAM
+to be free) in the following three phases:
+        prepare, freeze, freeze_noirq
+that correspond to the PCI bus type's callbacks:
+        pci_pm_prepare()
+        pci_pm_freeze()
+        pci_pm_freeze_noirq()
+This means that the prepare phase is exactly the same as for system suspend.
+The other two phases, however, are different.
+The pci_pm_freeze() routine is quite similar to pci_pm_suspend(), but it runs
+the device driver's pm->freeze() callback, if defined, instead of pm->suspend(),
+and it doesn't apply the suspend-related hardware quirks.  It is executed
+asynchronously for different PCI devices that don't depend on each other in a
+known way.
+The pci_pm_freeze_noirq() routine, in turn, is similar to
+pci_pm_suspend_noirq(), but it calls the device driver's pm->freeze_noirq()
+routine instead of pm->suspend_noirq().  It also doesn't attempt to prepare the
+device for signaling wakeup and put it into a low-power state.  Still, it saves
+the device's standard configuration registers if they haven't been saved by one
+of the driver's callbacks.
+Once the image has been created, it has to be saved.  However, at this point all
+devices are frozen and they cannot handle I/O, while their ability to handle
+I/O is obviously necessary for the image saving.  Thus they have to be brought
+back to the fully functional state and this is done in the following phases:
+        thaw_noirq, thaw, complete
+using the following PCI bus type's callbacks:
+        pci_pm_thaw_noirq()
+        pci_pm_thaw()
+        pci_pm_complete()
+respectively.
+The first of them, pci_pm_thaw_noirq(), is analogous to pci_pm_resume_noirq(),
+but it doesn't put the device into the full power state and doesn't attempt to
+restore its standard configuration registers.  It also executes the device
+driver's pm->thaw_noirq() callback, if defined, instead of pm->resume_noirq().
+The pci_pm_thaw() routine is similar to pci_pm_resume(), but it runs the device
+driver's pm->thaw() callback instead of pm->resume().  It is executed
+asynchronously for different PCI devices that don't depend on each other in a
+known way.
+The complete phase it the same as for system resume.
+After saving the image, devices need to be powered down before the system can
+enter the target sleep state (ACPI S4 for ACPI-based systems).  This is done in
+three phases:
+        prepare, poweroff, poweroff_noirq
+where the prepare phase is exactly the same as for system suspend.  The other
+two phases are analogous to the suspend and suspend_noirq phases, respectively.
+The PCI subsystem-level callbacks they correspond to
+        pci_pm_poweroff()
+        pci_pm_poweroff_noirq()
+work in analogy with pci_pm_suspend() and pci_pm_poweroff_noirq(), respectively,
+although they don't attempt to save the device's standard configuration
+registers.
+2.4.4. System Restore
+System restore requires a hibernation image to be loaded into memory and the
+pre-hibernation memory contents to be restored before the pre-hibernation system
+activity can be resumed.
+As described in Documentation/power/devices.txt, the hibernation image is loaded
+into memory by a fresh instance of the kernel, called the boot kernel, which in
+turn is loaded and run by a boot loader in the usual way.  After the boot kernel
+has loaded the image, it needs to replace its own code and data with the code
+and data of the "hibernated" kernel stored within the image, called the image
+kernel.  For this purpose all devices are frozen just like before creating
+the image during hibernation, in the
+        prepare, freeze, freeze_noirq
+phases described above.  However, the devices affected by these phases are only
+those having drivers in the boot kernel; other devices will still be in whatever
+state the boot loader left them.
+Should the restoration of the pre-hibernation memory contents fail, the boot
+kernel would go through the "thawing" procedure described above, using the
+thaw_noirq, thaw, and complete phases (that will only affect the devices having
+drivers in the boot kernel), and then continue running normally.
+If the pre-hibernation memory contents are restored successfully, which is the
+usual situation, control is passed to the image kernel, which then becomes
+responsible for bringing the system back to the working state.  To achieve this,
+it must restore the devices' pre-hibernation functionality, which is done much
+like waking up from the memory sleep state, although it involves different
+phases:
+        restore_noirq, restore, complete
+The first two of these are analogous to the resume_noirq and resume phases
+described above, respectively, and correspond to the following PCI subsystem
+callbacks:
+        pci_pm_restore_noirq()
+        pci_pm_restore()
+These callbacks work in analogy with pci_pm_resume_noirq() and pci_pm_resume(),
+respectively, but they execute the device driver's pm->restore_noirq() and
+pm->restore() callbacks, if available.
+The complete phase is carried out in exactly the same way as during system
+resume.
+3. PCI Device Drivers and Power Management
+==========================================
+3.1. Power Management Callbacks
+-------------------------------
+PCI device drivers participate in power management by providing callbacks to be
+executed by the PCI subsystem's power management routines described above and by
+controlling the runtime power management of their devices.
+At the time of this writing there are two ways to define power management
+callbacks for a PCI device driver, the recommended one, based on using a
+dev_pm_ops structure described in Documentation/power/devices.txt, and the
+"legacy" one, in which the .suspend(), .suspend_late(), .resume_early(), and
+.resume() callbacks from struct pci_driver are used.  The legacy approach,
+however, doesn't allow one to define runtime power management callbacks and is
+not really suitable for any new drivers.  Therefore it is not covered by this
+document (refer to the source code to learn more about it).
+It is recommended that all PCI device drivers define a struct dev_pm_ops object
+containing pointers to power management (PM) callbacks that will be executed by
+the PCI subsystem's PM routines in various circumstances.  A pointer to the
+driver's struct dev_pm_ops object has to be assigned to the driver.pm field in
+its struct pci_driver object.  Once that has happened, the "legacy" PM callbacks
+in struct pci_driver are ignored (even if they are not NULL).
+The PM callbacks in struct dev_pm_ops are not mandatory and if they are not
+defined (i.e. the respective fields of struct dev_pm_ops are unset) the PCI
+subsystem will handle the device in a simplified default manner.  If they are
+defined, though, they are expected to behave as described in the following
+subsections.
+3.1.1. prepare()
+The prepare() callback is executed during system suspend, during hibernation
+(when a hibernation image is about to be created), during power-off after
+saving a hibernation image and during system restore, when a hibernation image
+has just been loaded into memory.
+This callback is only necessary if the driver's device has children that in
+general may be registered at any time.  In that case the role of the prepare()
+callback is to prevent new children of the device from being registered until
+one of the resume_noirq(), thaw_noirq(), or restore_noirq() callbacks is run.
+In addition to that the prepare() callback may carry out some operations
+preparing the device to be suspended, although it should not allocate memory
+(if additional memory is required to suspend the device, it has to be
+preallocated earlier, for example in a suspend/hibernate notifier as described
+in Documentation/power/notifiers.txt).
+3.1.2. suspend()
+The suspend() callback is only executed during system suspend, after prepare()
+callbacks have been executed for all devices in the system.
+This callback is expected to quiesce the device and prepare it to be put into a
+low-power state by the PCI subsystem.  It is not required (in fact it even is
+not recommended) that a PCI driver's suspend() callback save the standard
+configuration registers of the device, prepare it for waking up the system, or
+put it into a low-power state.  All of these operations can very well be taken
+care of by the PCI subsystem, without the driver's participation.
+However, in some rare case it is convenient to carry out these operations in
+a PCI driver.  Then, pci_save_state(), pci_prepare_to_sleep(), and
+pci_set_power_state() should be used to save the device's standard configuration
+registers, to prepare it for system wakeup (if necessary), and to put it into a
+low-power state, respectively.  Moreover, if the driver calls pci_save_state(),
+the PCI subsystem will not execute either pci_prepare_to_sleep(), or
+pci_set_power_state() for its device, so the driver is then responsible for
+handling the device as appropriate.
+While the suspend() callback is being executed, the driver's interrupt handler
+can be invoked to handle an interrupt from the device, so all suspend-related
+operations relying on the driver's ability to handle interrupts should be
+carried out in this callback.
+3.1.3. suspend_noirq()
+The suspend_noirq() callback is only executed during system suspend, after
+suspend() callbacks have been executed for all devices in the system and
+after device interrupts have been disabled by the PM core.
+The difference between suspend_noirq() and suspend() is that the driver's
+interrupt handler will not be invoked while suspend_noirq() is running.  Thus
+suspend_noirq() can carry out operations that would cause race conditions to
+arise if they were performed in suspend().
+3.1.4. freeze()
+The freeze() callback is hibernation-specific and is executed in two situations,
+during hibernation, after prepare() callbacks have been executed for all devices
+in preparation for the creation of a system image, and during restore,
+after a system image has been loaded into memory from persistent storage and the
+prepare() callbacks have been executed for all devices.
+The role of this callback is analogous to the role of the suspend() callback
+described above.  In fact, they only need to be different in the rare cases when
+the driver takes the responsibility for putting the device into a low-power
 state.
-The first walk allows a graceful recovery in the event of a failure, since none
+In that cases the freeze() callback should not prepare the device system wakeup
-of the devices have actually been powered down.
+or put it into a low-power state.  Still, either it or freeze_noirq() should
+save the device's standard configuration registers using pci_save_state().
-In both walks, in particular the second, all children of a bridge are touched
-before the actual bridge itself. This allows the bridge to retain power while
-its children are being accessed.
-Upon resuming from sleep, just the opposite must be true: all bridges must be
-powered on and restored before their children are powered on. This is easily
-accomplished with a breadth-first walk of the PCI device tree.
-3. PCI Utility Functions
-~~~~~~~~~~~~~~~~~~~~~~~~
-These are helper functions designed to be called by individual device drivers.
-Assuming that a device behaves as advertised, these should be applicable in most
-cases. However, results may vary.
-Note that these functions are never implicitly called for the driver. The driver
-is always responsible for deciding when and if to call these.
-pci_save_state
--------------
-Usage:
-        pci_save_state(struct pci_dev *dev);
-Description:
-        Save first 64 bytes of PCI config space, along with any additional
-        PCI-Express or PCI-X information.
-pci_restore_state
-----------------
-Usage:
-        pci_restore_state(struct pci_dev *dev);
-Description:
-        Restore previously saved config space.
-pci_set_power_state
-------------------
-Usage:
-        pci_set_power_state(struct pci_dev *dev, pci_power_t state);
-Description:
-        Transition device to low power state using PCI PM Capabilities
-        registers.
-        Will fail under one of the following conditions:
-        - If state is less than current state, but not D0 (illegal transition)
-        - Device doesn't support PM Capabilities
-        - Device does not support requested state
-pci_enable_wake
---------------
-Usage:
-        pci_enable_wake(struct pci_dev *dev, pci_power_t state, int enable);
-Description:
-        Enable device to generate PME# during low power state using PCI PM 
-        Capabilities.
-        Checks whether if device supports generating PME# from requested state
-        and fail if it does not, unless enable == 0 (request is to disable wake
-        events, which is implicit if it doesn't even support it in the first
-        place).
-        Note that the PMC Register in the device's PM Capabilities has a bitmask
-        of the states it supports generating PME# from. D3hot is bit 3 and
-        D3cold is bit 4. So, while a value of 4 as the state may not seem
-        semantically correct, it is. 
-4. PCI Device Drivers
-~~~~~~~~~~~~~~~~~~~~~
-These functions are intended for use by individual drivers, and are defined in 
-struct pci_driver:
-        int  (*suspend) (struct pci_dev *dev, pm_message_t state);
-        int  (*resume) (struct pci_dev *dev);
-suspend
-------
-Usage:
-if (dev->driver && dev->driver->suspend)
-        dev->driver->suspend(dev,state);
-A driver uses this function to actually transition the device into a low power
-state. This should include disabling I/O, IRQs, and bus-mastering, as well as
-physically transitioning the device to a lower power state; it may also include
-calls to pci_enable_wake().
-Bus mastering may be disabled by doing:
-pci_disable_device(dev);
-For devices that support the PCI PM Spec, this may be used to set the device's
-power state to match the suspend() parameter:
-pci_set_power_state(dev,state);
-The driver is also responsible for disabling any other device-specific features
-(e.g blanking screen, turning off on-card memory, etc).
-The driver should be sure to track the current state of the device, as it may
-obviate the need for some operations.
-The driver should update the current_state field in its pci_dev structure in
-this function, except for PM-capable devices when pci_set_power_state is used.
-resume
------
-Usage:
-if (dev->driver && dev->driver->resume)
-        dev->driver->resume(dev)
-The resume callback may be called from any power state, and is always meant to
+3.1.5. freeze_noirq()
-transition the device to the D0 state. 
-The driver is responsible for reenabling any features of the device that had
+The freeze_noirq() callback is hibernation-specific.  It is executed during
-been disabled during previous suspend calls, such as IRQs and bus mastering,
+hibernation, after prepare() and freeze() callbacks have been executed for all
-as well as calling pci_restore_state().
+devices in preparation for the creation of a system image, and during restore,
+after a system image has been loaded into memory and after prepare() and
+freeze() callbacks have been executed for all devices.  It is always executed
+after device interrupts have been disabled by the PM core.
-If the device is currently in D3, it may need to be reinitialized in resume().
+The role of this callback is analogous to the role of the suspend_noirq()
+callback described above and it very rarely is necessary to define
+freeze_noirq().
-  * Some types of devices, like bus controllers, will preserve context in D3hot
+The difference between freeze_noirq() and freeze() is analogous to the
-    (using Vcc power).  Their drivers will often want to avoid re-initializing
+difference between suspend_noirq() and suspend().
-    them after re-entering D0 (perhaps to avoid resetting downstream devices).
-  * Other kinds of devices in D3hot will discard device context as part of a
+3.1.6. poweroff()
-    soft reset when re-entering the D0 state.
-    
-  * Devices resuming from D3cold always go through a power-on reset.  Some
-    device context can also be preserved using Vaux power.
-  * Some systems hide D3cold resume paths from drivers.  For example, on PCs
+The poweroff() callback is hibernation-specific.  It is executed when the system
-    the resume path for suspend-to-disk often runs BIOS powerup code, which
+is about to be powered off after saving a hibernation image to a persistent
-    will sometimes re-initialize the device.
+storage.  prepare() callbacks are executed for all devices before poweroff() is
+called.
-To handle resets during D3 to D0 transitions, it may be convenient to share
+The role of this callback is analogous to the role of the suspend() and freeze()
-device initialization code between probe() and resume().  Device parameters
+callbacks described above, although it does not need to save the contents of
-can also be saved before the driver suspends into D3, avoiding re-probe.
+the device's registers.  In particular, if the driver wants to put the device
+into a low-power state itself instead of allowing the PCI subsystem to do that,
+the poweroff() callback should use pci_prepare_to_sleep() and
+pci_set_power_state() to prepare the device for system wakeup and to put it
+into a low-power state, respectively, but it need not save the device's standard
+configuration registers.
-If the device supports the PCI PM Spec, it can use this to physically transition
+3.1.7. poweroff_noirq()
-the device to D0:
-pci_set_power_state(dev,0);
+The poweroff_noirq() callback is hibernation-specific.  It is executed after
+poweroff() callbacks have been executed for all devices in the system.
-Note that if the entire system is transitioning out of a global sleep state, all
+The role of this callback is analogous to the role of the suspend_noirq() and
-devices will be placed in the D0 state, so this is not necessary. However, in
+freeze_noirq() callbacks described above, but it does not need to save the
-the event that the device is placed in the D3 state during normal operation,
+contents of the device's registers.
-this call is necessary. It is impossible to determine which of the two events is
-taking place in the driver, so it is always a good idea to make that call.
-The driver should take note of the state that it is resuming from in order to
+The difference between poweroff_noirq() and poweroff() is analogous to the
-ensure correct (and speedy) operation.
+difference between suspend_noirq() and suspend().
-The driver should update the current_state field in its pci_dev structure in
+3.1.8. resume_noirq()
-this function, except for PM-capable devices when pci_set_power_state is used.
+The resume_noirq() callback is only executed during system resume, after the
+PM core has enabled the non-boot CPUs.  The driver's interrupt handler will not
+be invoked while resume_noirq() is running, so this callback can carry out
+operations that might race with the interrupt handler.
+Since the PCI subsystem unconditionally puts all devices into the full power
+state in the resume_noirq phase of system resume and restores their standard
+configuration registers, resume_noirq() is usually not necessary.  In general
+it should only be used for performing operations that would lead to race
+conditions if carried out by resume().
-A reference implementation
+3.1.9. resume()
-------------------------
-.suspend()
-{
-        /* driver specific operations */
-        /* Disable IRQ */
+The resume() callback is only executed during system resume, after
-        free_irq();
+resume_noirq() callbacks have been executed for all devices in the system and
-        /* If using MSI */
+device interrupts have been enabled by the PM core.
-        pci_disable_msi();
-        pci_save_state();
+This callback is responsible for restoring the pre-suspend configuration of the
-        pci_enable_wake();
+device and bringing it back to the fully functional state.  The device should be
-        /* Disable IO/bus master/irq router */
+able to process I/O in a usual way after resume() has returned.
-        pci_disable_device();
-        pci_set_power_state(pci_choose_state());
-}
-.resume()
+3.1.10. thaw_noirq()
-{
-        pci_set_power_state(PCI_D0);
-        pci_restore_state();
-        /* device's irq possibly is changed, driver should take care */
-        pci_enable_device();
-        pci_set_master();
-        /* if using MSI, device's vector possibly is changed */
+The thaw_noirq() callback is hibernation-specific.  It is executed after a
-        pci_enable_msi();
+system image has been created and the non-boot CPUs have been enabled by the PM
+core, in the thaw_noirq phase of hibernation.  It also may be executed if the
+loading of a hibernation image fails during system restore (it is then executed
+after enabling the non-boot CPUs).  The driver's interrupt handler will not be
+invoked while thaw_noirq() is running.
-        request_irq();
+The role of this callback is analogous to the role of resume_noirq().  The
-        /* driver specific operations; */
+difference between these two callbacks is that thaw_noirq() is executed after
-}
+freeze() and freeze_noirq(), so in general it does not need to modify the
+contents of the device's registers.
-This is a typical implementation. Drivers can slightly change the order
+3.1.11. thaw()
-of the operations in the implementation, ignore some operations or add
-more driver specific operations in it, but drivers should do something like
-this on the whole.
-5. Resources
+The thaw() callback is hibernation-specific.  It is executed after thaw_noirq()
-~~~~~~~~~~~~
+callbacks have been executed for all devices in the system and after device
+interrupts have been enabled by the PM core.
-PCI Local Bus Specification 
+This callback is responsible for restoring the pre-freeze configuration of
-PCI Bus Power Management Interface Specification
+the device, so that it will work in a usual way after thaw() has returned.
-  http://www.pcisig.com
+3.1.12. restore_noirq()
+The restore_noirq() callback is hibernation-specific.  It is executed in the
+restore_noirq phase of hibernation, when the boot kernel has passed control to
+the image kernel and the non-boot CPUs have been enabled by the image kernel's
+PM core.
+This callback is analogous to resume_noirq() with the exception that it cannot
+make any assumption on the previous state of the device, even if the BIOS (or
+generally the platform firmware) is known to preserve that state over a
+suspend-resume cycle.
+For the vast majority of PCI device drivers there is no difference between
+resume_noirq() and restore_noirq().
+3.1.13. restore()
+The restore() callback is hibernation-specific.  It is executed after
+restore_noirq() callbacks have been executed for all devices in the system and
+after the PM core has enabled device drivers' interrupt handlers to be invoked.
+This callback is analogous to resume(), just like restore_noirq() is analogous
+to resume_noirq().  Consequently, the difference between restore_noirq() and
+restore() is analogous to the difference between resume_noirq() and resume().
+For the vast majority of PCI device drivers there is no difference between
+resume() and restore().
+3.1.14. complete()
+The complete() callback is executed in the following situations:
+  - during system resume, after resume() callbacks have been executed for all
+    devices,
+  - during hibernation, before saving the system image, after thaw() callbacks
+    have been executed for all devices,
+  - during system restore, when the system is going back to its pre-hibernation
+    state, after restore() callbacks have been executed for all devices.
+It also may be executed if the loading of a hibernation image into memory fails
+(in that case it is run after thaw() callbacks have been executed for all
+devices that have drivers in the boot kernel).
+This callback is entirely optional, although it may be necessary if the
+prepare() callback performs operations that need to be reversed.
+3.1.15. runtime_suspend()
+The runtime_suspend() callback is specific to device runtime power management
+(runtime PM).  It is executed by the PM core's runtime PM framework when the
+device is about to be suspended (i.e. quiesced and put into a low-power state)
+at run time.
+This callback is responsible for freezing the device and preparing it to be
+put into a low-power state, but it must allow the PCI subsystem to perform all
+of the PCI-specific actions necessary for suspending the device.
+3.1.16. runtime_resume()
+The runtime_resume() callback is specific to device runtime PM.  It is executed
+by the PM core's runtime PM framework when the device is about to be resumed
+(i.e. put into the full-power state and programmed to process I/O normally) at
+run time.
+This callback is responsible for restoring the normal functionality of the
+device after it has been put into the full-power state by the PCI subsystem.
+The device is expected to be able to process I/O in the usual way after
+runtime_resume() has returned.
+3.1.17. runtime_idle()
+The runtime_idle() callback is specific to device runtime PM.  It is executed
+by the PM core's runtime PM framework whenever it may be desirable to suspend
+the device according to the PM core's information.  In particular, it is
+automatically executed right after runtime_resume() has returned in case the
+resume of the device has happened as a result of a spurious event.
+This callback is optional, but if it is not implemented or if it returns 0, the
+PCI subsystem will call pm_runtime_suspend() for the device, which in turn will
+cause the driver's runtime_suspend() callback to be executed.
+3.1.18. Pointing Multiple Callback Pointers to One Routine
+Although in principle each of the callbacks described in the previous
+subsections can be defined as a separate function, it often is convenient to
+point two or more members of struct dev_pm_ops to the same routine.  There are
+a few convenience macros that can be used for this purpose.
+The SIMPLE_DEV_PM_OPS macro declares a struct dev_pm_ops object with one
+suspend routine pointed to by the .suspend(), .freeze(), and .poweroff()
+members and one resume routine pointed to by the .resume(), .thaw(), and
+.restore() members.  The other function pointers in this struct dev_pm_ops are
+unset.
+The UNIVERSAL_DEV_PM_OPS macro is similar to SIMPLE_DEV_PM_OPS, but it
+additionally sets the .runtime_resume() pointer to the same value as
+.resume() (and .thaw(), and .restore()) and the .runtime_suspend() pointer to
+the same value as .suspend() (and .freeze() and .poweroff()).
+The SET_SYSTEM_SLEEP_PM_OPS can be used inside of a declaration of struct
+dev_pm_ops to indicate that one suspend routine is to be pointed to by the
+.suspend(), .freeze(), and .poweroff() members and one resume routine is to
+be pointed to by the .resume(), .thaw(), and .restore() members.
+3.2. Device Runtime Power Management
+------------------------------------
+In addition to providing device power management callbacks PCI device drivers
+are responsible for controlling the runtime power management (runtime PM) of
+their devices.
+The PCI device runtime PM is optional, but it is recommended that PCI device
+drivers implement it at least in the cases where there is a reliable way of
+verifying that the device is not used (like when the network cable is detached
+from an Ethernet adapter or there are no devices attached to a USB controller).
+To support the PCI runtime PM the driver first needs to implement the
+runtime_suspend() and runtime_resume() callbacks.  It also may need to implement
+the runtime_idle() callback to prevent the device from being suspended again
+every time right after the runtime_resume() callback has returned
+(alternatively, the runtime_suspend() callback will have to check if the
+device should really be suspended and return -EAGAIN if that is not the case).
+The runtime PM of PCI devices is disabled by default.  It is also blocked by
+pci_pm_init() that runs the pm_runtime_forbid() helper function.  If a PCI
+driver implements the runtime PM callbacks and intends to use the runtime PM
+framework provided by the PM core and the PCI subsystem, it should enable this
+feature by executing the pm_runtime_enable() helper function.  However, the
+driver should not call the pm_runtime_allow() helper function unblocking
+the runtime PM of the device.  Instead, it should allow user space or some
+platform-specific code to do that (user space can do it via sysfs), although
+once it has called pm_runtime_enable(), it must be prepared to handle the
+runtime PM of the device correctly as soon as pm_runtime_allow() is called
+(which may happen at any time).  [It also is possible that user space causes
+pm_runtime_allow() to be called via sysfs before the driver is loaded, so in
+fact the driver has to be prepared to handle the runtime PM of the device as
+soon as it calls pm_runtime_enable().]
+The runtime PM framework works by processing requests to suspend or resume
+devices, or to check if they are idle (in which cases it is reasonable to
+subsequently request that they be suspended).  These requests are represented
+by work items put into the power management workqueue, pm_wq.  Although there
+are a few situations in which power management requests are automatically
+queued by the PM core (for example, after processing a request to resume a
+device the PM core automatically queues a request to check if the device is
+idle), device drivers are generally responsible for queuing power management
+requests for their devices.  For this purpose they should use the runtime PM
+helper functions provided by the PM core, discussed in
+Documentation/power/runtime_pm.txt.
+Devices can also be suspended and resumed synchronously, without placing a
+request into pm_wq.  In the majority of cases this also is done by their
+drivers that use helper functions provided by the PM core for this purpose.
+For more information on the runtime PM of devices refer to
+Documentation/power/runtime_pm.txt.
+4. Resources
+============
+PCI Local Bus Specification, Rev. 3.0
+PCI Bus Power Management Interface Specification, Rev. 1.2
+Advanced Configuration and Power Interface (ACPI) Specification, Rev. 3.0b
+PCI Express Base Specification, Rev. 2.0
+Documentation/power/devices.txt
+Documentation/power/runtime_pm.txt
diff --git a/Documentation/power/pm_qos_interface.txt b/Documentation/power/pm_qos_interface.txt
index c40866e8b957..bfed898a03fc 100644
--- a/Documentation/power/pm_qos_interface.txt
+++ b/Documentation/power/pm_qos_interface.txt
@@ -18,44 +18,46 @@ and pm_qos_params.h.  This is done because having the available parameters
 being runtime configurable or changeable from a driver was seen as too easy to
 abuse.
-For each parameter a list of performance requirements is maintained along with
+For each parameter a list of performance requests is maintained along with
 an aggregated target value.  The aggregated target value is updated with
-changes to the requirement list or elements of the list.  Typically the
+changes to the request list or elements of the list.  Typically the
-aggregated target value is simply the max or min of the requirement values held
+aggregated target value is simply the max or min of the request values held
 in the parameter list elements.
 From kernel mode the use of this interface is simple:
-pm_qos_add_requirement(param_id, name, target_value):
-Will insert a named element in the list for that identified PM_QOS parameter
-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.
-pm_qos_update_requirement(param_id, name, new_target_value):
+handle = pm_qos_add_request(param_class, target_value):
-Will search the list identified by the param_id for the named list element and
+Will insert an element into the list for that identified PM_QOS class with the
-then update its target value, calling the notification tree if the aggregated
+target value.  Upon change to this list the new target is recomputed and any
-target is changed.  with that name is already registered.
+registered notifiers are called only if the target value is now different.
+Clients of pm_qos need to save the returned handle.
-pm_qos_remove_requirement(param_id, name):
+void pm_qos_update_request(handle, new_target_value):
-Will search the identified list for the named element and remove it, after
+Will update the list element pointed to by the handle with the new target value
-removal it will update the aggregate target and call the notification tree if
+and recompute the new aggregated target, calling the notification tree if the
-the target was changed as a result of removing the named requirement.
+target is changed.
+void pm_qos_remove_request(handle):
+Will remove the element.  After removal it will update the aggregate target and
+call the notification tree if the target was changed as a result of removing
+the request.
 From user mode:
-Only processes can register a pm_qos requirement.  To provide for automatic
+Only processes can register a pm_qos request.  To provide for automatic
-cleanup for process the interface requires the process to register its
+cleanup of a process, the interface requires the process to register its
-parameter requirements in the following way:
+parameter requests in the following way:
 To register the default pm_qos target for the specific parameter, the process
 must open one of /dev/[cpu_dma_latency, network_latency, network_throughput]
 As long as the device node is held open that process has a registered
-requirement on the parameter.  The name of the requirement is "process_<PID>"
+request on the parameter.
-derived from the current->pid from within the open system call.
-To change the requested target value the process needs to write a s32 value to
+To change the requested target value the process needs to write an s32 value to
-the open device node.  This translates to a pm_qos_update_requirement call.
+the open device node.  Alternatively the user mode program could write a hex
+string for the value using 10 char long format e.g. "0x12345678".  This
+translates to a pm_qos_update_request call.
 To remove the user mode request for a target value simply close the device
 node.
diff --git a/Documentation/power/regulator/consumer.txt b/Documentation/power/regulator/consumer.txt
index cdebb5145c25..55c4175d8099 100644
--- a/Documentation/power/regulator/consumer.txt
+++ b/Documentation/power/regulator/consumer.txt
@@ -8,11 +8,11 @@ Please see overview.txt for a description of the terms used in this text.
 1. Consumer Regulator Access (static & dynamic drivers)
 =======================================================
-A consumer driver can get access to it's supply regulator by calling :-
+A consumer driver can get access to its supply regulator by calling :-
 regulator = regulator_get(dev, "Vcc");
-The consumer passes in it's struct device pointer and power supply ID. The core
+The consumer passes in its struct device pointer and power supply ID. The core
 then finds the correct regulator by consulting a machine specific lookup table.
 If the lookup is successful then this call will return a pointer to the struct
 regulator that supplies this consumer.
@@ -34,7 +34,7 @@ usually be called in your device drivers probe() and remove() respectively.
 2. Regulator Output Enable & Disable (static & dynamic drivers)
 ====================================================================
-A consumer can enable it's power supply by calling:-
+A consumer can enable its power supply by calling:-
 int regulator_enable(regulator);
@@ -49,7 +49,7 @@ int regulator_is_enabled(regulator);
 This will return > zero when the regulator is enabled.
-A consumer can disable it's supply when no longer needed by calling :-
+A consumer can disable its supply when no longer needed by calling :-
 int regulator_disable(regulator);
@@ -140,7 +140,7 @@ by calling :-
 int regulator_set_optimum_mode(struct regulator *regulator, int load_uA);
 This will cause the core to recalculate the total load on the regulator (based
-on all it's consumers) and change operating mode (if necessary and permitted)
+on all its consumers) and change operating mode (if necessary and permitted)
 to best match the current operating load.
 The load_uA value can be determined from the consumers datasheet. e.g.most
diff --git a/Documentation/power/regulator/machine.txt b/Documentation/power/regulator/machine.txt
index 63728fed620b..bdec39b9bd75 100644
--- a/Documentation/power/regulator/machine.txt
+++ b/Documentation/power/regulator/machine.txt
@@ -52,7 +52,7 @@ static struct regulator_init_data regulator1_data = {
 };
 Regulator-1 supplies power to Regulator-2. This relationship must be registered
-with the core so that Regulator-1 is also enabled when Consumer A enables it's
+with the core so that Regulator-1 is also enabled when Consumer A enables its
 supply (Regulator-2). The supply regulator is set by the supply_regulator_dev
 field below:-
diff --git a/Documentation/power/regulator/overview.txt b/Documentation/power/regulator/overview.txt
index ffd185bb6054..9363e056188a 100644
--- a/Documentation/power/regulator/overview.txt
+++ b/Documentation/power/regulator/overview.txt
@@ -35,16 +35,16 @@ Some terms used in this document:-
  o Consumer     - Electronic device that is supplied power by a regulator.
                   Consumers can be classified into two types:-
-                   Static: consumer does not change it's supply voltage or
+                   Static: consumer does not change its supply voltage or
                   current limit. It only needs to enable or disable it's
-                   power supply. It's supply voltage is set by the hardware,
+                   power supply. Its supply voltage is set by the hardware,
                   bootloader, firmware or kernel board initialisation code.
                   Dynamic: consumer needs to change it's supply voltage or
                   current limit to meet operation demands.
-  o Power Domain - Electronic circuit that is supplied it's input power by the
+  o Power Domain - Electronic circuit that is supplied its input power by the
                   output power of a regulator, switch or by another power
                   domain.
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 356fd86f4ea8..55b859b3bc72 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -224,6 +224,12 @@ defined in include/linux/pm.h:
      RPM_SUSPENDED, which means that each device is initially regarded by the
      PM core as 'suspended', regardless of its real hardware status
+  unsigned int runtime_auto;
+    - if set, indicates that the user space has allowed the device driver to
+      power manage the device at run time via the /sys/devices/.../power/control
+      interface; it may only be modified with the help of the pm_runtime_allow()
+      and pm_runtime_forbid() helper functions
 All of the above fields are members of the 'power' member of 'struct device'.
 4. Run-time PM Device Helper Functions
@@ -250,7 +256,7 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
      to suspend the device again in future
  int pm_runtime_resume(struct device *dev);
-    - execute the subsystem-leve resume callback for the device; returns 0 on
+    - execute the subsystem-level resume callback for the device; returns 0 on
      success, 1 if the device's run-time PM status was already 'active' or
      error code on failure, where -EAGAIN means it may be safe to attempt to
      resume the device again in future, but 'power.runtime_error' should be
@@ -329,6 +335,20 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
      'power.runtime_error' is set or 'power.disable_depth' is greater than
      zero)
+  bool pm_runtime_suspended(struct device *dev);
+    - return true if the device's runtime PM status is 'suspended', or false
+      otherwise
+  void pm_runtime_allow(struct device *dev);
+    - set the power.runtime_auto flag for the device and decrease its usage
+      counter (used by the /sys/devices/.../power/control interface to
+      effectively allow the device to be power managed at run time)
+  void pm_runtime_forbid(struct device *dev);
+    - unset the power.runtime_auto flag for the device and increase its usage
+      counter (used by the /sys/devices/.../power/control interface to
+      effectively prevent the device from being power managed at run time)
 It is safe to execute the following helper functions from interrupt context:
 pm_request_idle()
@@ -382,6 +402,18 @@ may be desirable to suspend the device as soon as ->probe() or ->remove() has
 finished, so the PM core uses pm_runtime_idle_sync() to invoke the
 subsystem-level idle callback for the device at that time.
+The user space can effectively disallow the driver of the device to power manage
+it at run time by changing the value of its /sys/devices/.../power/control
+attribute to "on", which causes pm_runtime_forbid() to be called.  In principle,
+this mechanism may also be used by the driver to effectively turn off the
+run-time power management of the device until the user space turns it on.
+Namely, during the initialization the driver can make sure that the run-time PM
+status of the device is 'active' and call pm_runtime_forbid().  It should be
+noted, however, that if the user space has already intentionally changed the
+value of /sys/devices/.../power/control to "auto" to allow the driver to power
+manage the device at run time, the driver may confuse it by using
+pm_runtime_forbid() this way.
 6. Run-time PM and System Sleep
 Run-time PM and system sleep (i.e., system suspend and hibernation, also known
@@ -431,3 +463,64 @@ The PM core always increments the run-time usage counter before calling the
 ->prepare() callback and decrements it after calling the ->complete() callback.
 Hence disabling run-time PM temporarily like this will not cause any run-time
 suspend callbacks to be lost.
+7. Generic subsystem callbacks
+Subsystems may wish to conserve code space by using the set of generic power
+management callbacks provided by the PM core, defined in
+driver/base/power/generic_ops.c:
+  int pm_generic_runtime_idle(struct device *dev);
+    - invoke the ->runtime_idle() callback provided by the driver of this
+      device, if defined, and call pm_runtime_suspend() for this device if the
+      return value is 0 or the callback is not defined
+  int pm_generic_runtime_suspend(struct device *dev);
+    - invoke the ->runtime_suspend() callback provided by the driver of this
+      device and return its result, or return -EINVAL if not defined
+  int pm_generic_runtime_resume(struct device *dev);
+    - invoke the ->runtime_resume() callback provided by the driver of this
+      device and return its result, or return -EINVAL if not defined
+  int pm_generic_suspend(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->suspend()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+  int pm_generic_resume(struct device *dev);
+    - invoke the ->resume() callback provided by the driver of this device and,
+      if successful, change the device's runtime PM status to 'active'
+  int pm_generic_freeze(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->freeze()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+  int pm_generic_thaw(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->thaw()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+  int pm_generic_poweroff(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->poweroff()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+  int pm_generic_restore(struct device *dev);
+    - invoke the ->restore() callback provided by the driver of this device and,
+      if successful, change the device's runtime PM status to 'active'
+These functions can be assigned to the ->runtime_idle(), ->runtime_suspend(),
+->runtime_resume(), ->suspend(), ->resume(), ->freeze(), ->thaw(), ->poweroff(),
+or ->restore() callback pointers in the subsystem-level dev_pm_ops structures.
+If a subsystem wishes to use all of them at the same time, it can simply assign
+the GENERIC_SUBSYS_PM_OPS macro, defined in include/linux/pm.h, to its
+dev_pm_ops structure pointer.
+Device drivers that wish to use the same function as a system suspend, freeze,
+poweroff and run-time suspend callback, and similarly for system resume, thaw,
+restore, and run-time resume, can achieve this with the help of the
+UNIVERSAL_DEV_PM_OPS macro defined in include/linux/pm.h (possibly setting its
+last argument to NULL).
diff --git a/Documentation/power/userland-swsusp.txt b/Documentation/power/userland-swsusp.txt
index b967cd9137d6..81680f9f5909 100644
--- a/Documentation/power/userland-swsusp.txt
+++ b/Documentation/power/userland-swsusp.txt
@@ -24,6 +24,10 @@ assumed to be in the resume mode.  The device cannot be open for simultaneous
 reading and writing.  It is also impossible to have the device open more than
 once at a time.
+Even opening the device has side effects. Data structures are
+allocated, and PM_HIBERNATION_PREPARE / PM_RESTORE_PREPARE chains are
+called.
 The ioctl() commands recognized by the device are:
 SNAPSHOT_FREEZE - freeze user space processes (the current process is
diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt
index 79f533f38c61..46d22105aa07 100644
--- a/Documentation/powerpc/booting-without-of.txt
+++ b/Documentation/powerpc/booting-without-of.txt
@@ -1289,7 +1289,7 @@ link between a device node and its interrupt parent in
 the interrupt tree.  The value of interrupt-parent is the
 phandle of the parent node.
-If the interrupt-parent property is not defined for a node, it's
+If the interrupt-parent property is not defined for a node, its
 interrupt parent is assumed to be an ancestor in the node's
 _device tree_ hierarchy.
diff --git a/Documentation/powerpc/dts-bindings/4xx/reboot.txt b/Documentation/powerpc/dts-bindings/4xx/reboot.txt
new file mode 100644
index 000000000000..d7217260589c
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/4xx/reboot.txt
@@ -0,0 +1,18 @@
+Reboot property to control system reboot on PPC4xx systems:
+By setting "reset_type" to one of the following values, the default
+software reset mechanism may be overidden. Here the possible values of
+"reset_type":
+      1 - PPC4xx core reset
+      2 - PPC4xx chip reset
+      3 - PPC4xx system reset (default)
+Example:
+                cpu@0 {
+                        device_type = "cpu";
+                        model = "PowerPC,440SPe";
+                        ...
+                        reset-type = <2>;       /* Use chip-reset */
+                };
diff --git a/Documentation/powerpc/dts-bindings/fsl/8xxx_gpio.txt b/Documentation/powerpc/dts-bindings/fsl/8xxx_gpio.txt
index d015dcec4011..b0019eb5330e 100644
--- a/Documentation/powerpc/dts-bindings/fsl/8xxx_gpio.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/8xxx_gpio.txt
@@ -11,7 +11,7 @@ Required properties:
  83xx, "fsl,mpc8572-gpio" for 85xx and "fsl,mpc8610-gpio" for 86xx.
 - #gpio-cells : Should be two. The first cell is the pin number and the
  second cell is used to specify optional parameters (currently unused).
- - interrupts : Interrupt mapping for GPIO IRQ (currently unused).
+ - interrupts : Interrupt mapping for GPIO IRQ.
 - interrupt-parent : Phandle for the interrupt controller that
   services interrupts for this device.
 - gpio-controller : Marks the port as GPIO controller.
@@ -38,3 +38,23 @@ Example of gpio-controller nodes for a MPC8347 SoC:
 See booting-without-of.txt for details of how to specify GPIO
 information for devices.
+To use GPIO pins as interrupt sources for peripherals, specify the
+GPIO controller as the interrupt parent and define GPIO number +
+trigger mode using the interrupts property, which is defined like
+this:
+interrupts = <number trigger>, where:
+ - number: GPIO pin (0..31)
+ - trigger: trigger mode:
+        2 = trigger on falling edge
+        3 = trigger on both edges
+Example of device using this is:
+        funkyfpga@0 {
+                compatible = "funky-fpga";
+                ...
+                interrupts = <4 3>;
+                interrupt-parent = <&gpio1>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/can.txt b/Documentation/powerpc/dts-bindings/fsl/can.txt
new file mode 100644
index 000000000000..2fa4fcd38fd6
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/can.txt
@@ -0,0 +1,53 @@
+CAN Device Tree Bindings
+------------------------
+(c) 2006-2009 Secret Lab Technologies Ltd
+Grant Likely <grant.likely@secretlab.ca>
+fsl,mpc5200-mscan nodes
+-----------------------
+In addition to the required compatible-, reg- and interrupt-properties, you can
+also specify which clock source shall be used for the controller:
+- fsl,mscan-clock-source : a string describing the clock source. Valid values
+                           are: "ip" for ip bus clock
+                                 "ref" for reference clock (XTAL)
+                           "ref" is default in case this property is not
+                           present.
+fsl,mpc5121-mscan nodes
+-----------------------
+In addition to the required compatible-, reg- and interrupt-properties, you can
+also specify which clock source and divider shall be used for the controller:
+- fsl,mscan-clock-source : a string describing the clock source. Valid values
+                           are: "ip" for ip bus clock
+                                "ref" for reference clock
+                                "sys" for system clock
+                           If this property is not present, an optimal CAN
+                           clock source and frequency based on the system
+                           clock will be selected. If this is not possible,
+                           the reference clock will be used.
+- fsl,mscan-clock-divider: for the reference and system clock, an additional
+                           clock divider can be specified. By default, a
+                           value of 1 is used.
+Note that the MPC5121 Rev. 1 processor is not supported.
+Examples:
+        can@1300 {
+                compatible = "fsl,mpc5121-mscan";
+                interrupts = <12 0x8>;
+                interrupt-parent = <&ipic>;
+                reg = <0x1300 0x80>;
+        };
+        can@1380 {
+                compatible = "fsl,mpc5121-mscan";
+                interrupts = <13 0x8>;
+                interrupt-parent = <&ipic>;
+                reg = <0x1380 0x80>;
+                fsl,mscan-clock-source = "ref";
+                fsl,mscan-clock-divider = <3>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt
index 6e37be1eeb2d..4f8930263dd9 100644
--- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt
@@ -21,6 +21,15 @@ Required properties:
 - fsl,qe-num-snums: define how many serial number(SNUM) the QE can use for the
  threads.
+Optional properties:
+- fsl,firmware-phandle:
+    Usage: required only if there is no fsl,qe-firmware child node
+    Value type: <phandle>
+    Definition: Points to a firmware node (see "QE Firmware Node" below)
+        that contains the firmware that should be uploaded for this QE.
+        The compatible property for the firmware node should say,
+        "fsl,qe-firmware".
 Recommended properties
 - brg-frequency : the internal clock source frequency for baud-rate
  generators in Hz.
@@ -59,3 +68,48 @@ Example:
                reg = <0 c000>;
        };
     };
+* QE Firmware Node
+This node defines a firmware binary that is embedded in the device tree, for
+the purpose of passing the firmware from bootloader to the kernel, or from
+the hypervisor to the guest.
+The firmware node itself contains the firmware binary contents, a compatible
+property, and any firmware-specific properties.  The node should be placed
+inside a QE node that needs it.  Doing so eliminates the need for a
+fsl,firmware-phandle property.  Other QE nodes that need the same firmware
+should define an fsl,firmware-phandle property that points to the firmware node
+in the first QE node.
+The fsl,firmware property can be specified in the DTS (possibly using incbin)
+or can be inserted by the boot loader at boot time.
+Required properties:
+  - compatible
+      Usage: required
+      Value type: <string>
+      Definition: A standard property.  Specify a string that indicates what
+          kind of firmware it is.  For QE, this should be "fsl,qe-firmware".
+   - fsl,firmware
+      Usage: required
+      Value type: <prop-encoded-array>, encoded as an array of bytes
+      Definition: A standard property.  This property contains the firmware
+          binary "blob".
+Example:
+        qe1@e0080000 {
+                compatible = "fsl,qe";
+                qe_firmware:qe-firmware {
+                        compatible = "fsl,qe-firmware";
+                        fsl,firmware = [0x70 0xcd 0x00 0x00 0x01 0x46 0x45 ...];
+                };
+                ...
+        };
+        qe2@e0090000 {
+                compatible = "fsl,qe";
+                fsl,firmware-phandle = <&qe_firmware>;
+                ...
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/dma.txt b/Documentation/powerpc/dts-bindings/fsl/dma.txt
index 0732cdd05ba1..2a4b4bce6110 100644
--- a/Documentation/powerpc/dts-bindings/fsl/dma.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/dma.txt
@@ -44,21 +44,29 @@ Example:
                        compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
                        cell-index = <0>;
                        reg = <0 0x80>;
+                        interrupt-parent = <&ipic>;
+                        interrupts = <71 8>;
                };
                dma-channel@80 {
                        compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
                        cell-index = <1>;
                        reg = <0x80 0x80>;
+                        interrupt-parent = <&ipic>;
+                        interrupts = <71 8>;
                };
                dma-channel@100 {
                        compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
                        cell-index = <2>;
                        reg = <0x100 0x80>;
+                        interrupt-parent = <&ipic>;
+                        interrupts = <71 8>;
                };
                dma-channel@180 {
                        compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
                        cell-index = <3>;
                        reg = <0x180 0x80>;
+                        interrupt-parent = <&ipic>;
+                        interrupts = <71 8>;
                };
        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/i2c.txt b/Documentation/powerpc/dts-bindings/fsl/i2c.txt
index b6d2e21474f9..50da20310585 100644
--- a/Documentation/powerpc/dts-bindings/fsl/i2c.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/i2c.txt
@@ -2,15 +2,14 @@
 Required properties :
- - device_type : Should be "i2c"
 - reg : Offset and length of the register set for the device
+ - compatible : should be "fsl,CHIP-i2c" where CHIP is the name of a
+   compatible processor, e.g. mpc8313, mpc8543, mpc8544, mpc5121,
+   mpc5200 or mpc5200b. For the mpc5121, an additional node
+   "fsl,mpc5121-i2c-ctrl" is required as shown in the example below.
 Recommended properties :
- - compatible : compatibility list with 2 entries, the first should
-   be "fsl,CHIP-i2c" where CHIP is the name of a compatible processor,
-   e.g. mpc8313, mpc8543, mpc8544, mpc5200 or mpc5200b. The second one
-   should be "fsl-i2c".
 - interrupts : <a b> where a is the interrupt number and b is a
   field that represents an encoding of the sense and level
   information for the interrupt.  This should be encoded based on
@@ -24,25 +23,40 @@ Recommended properties :
 Examples :
+        /* MPC5121 based board */
+        i2c@1740 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                compatible = "fsl,mpc5121-i2c", "fsl-i2c";
+                reg = <0x1740 0x20>;
+                interrupts = <11 0x8>;
+                interrupt-parent = <&ipic>;
+                clock-frequency = <100000>;
+        };
+        i2ccontrol@1760 {
+                compatible = "fsl,mpc5121-i2c-ctrl";
+                reg = <0x1760 0x8>;
+        };
+        /* MPC5200B based board */
        i2c@3d00 {
                #address-cells = <1>;
                #size-cells = <0>;
                compatible = "fsl,mpc5200b-i2c","fsl,mpc5200-i2c","fsl-i2c";
-                cell-index = <0>;
                reg = <0x3d00 0x40>;
                interrupts = <2 15 0>;
                interrupt-parent = <&mpc5200_pic>;
                fsl,preserve-clocking;
        };
+        /* MPC8544 base board */
        i2c@3100 {
                #address-cells = <1>;
                #size-cells = <0>;
-                cell-index = <1>;
                compatible = "fsl,mpc8544-i2c", "fsl-i2c";
                reg = <0x3100 0x100>;
                interrupts = <43 2>;
                interrupt-parent = <&mpic>;
                clock-frequency = <400000>;
        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/mpc5121-psc.txt b/Documentation/powerpc/dts-bindings/fsl/mpc5121-psc.txt
new file mode 100644
index 000000000000..8832e8798912
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/mpc5121-psc.txt
@@ -0,0 +1,70 @@
+MPC5121 PSC Device Tree Bindings
+PSC in UART mode
+----------------
+For PSC in UART mode the needed PSC serial devices
+are specified by fsl,mpc5121-psc-uart nodes in the
+fsl,mpc5121-immr SoC node. Additionally the PSC FIFO
+Controller node fsl,mpc5121-psc-fifo is requered there:
+fsl,mpc5121-psc-uart nodes
+--------------------------
+Required properties :
+ - compatible : Should contain "fsl,mpc5121-psc-uart" and "fsl,mpc5121-psc"
+ - cell-index : Index of the PSC in hardware
+ - reg : Offset and length of the register set for the PSC device
+ - interrupts : <a b> where a is the interrupt number of the
+   PSC FIFO Controller and b is a field that represents an
+   encoding of the sense and level information for the interrupt.
+ - interrupt-parent : the phandle for the interrupt controller that
+   services interrupts for this device.
+Recommended properties :
+ - fsl,rx-fifo-size : the size of the RX fifo slice (a multiple of 4)
+ - fsl,tx-fifo-size : the size of the TX fifo slice (a multiple of 4)
+fsl,mpc5121-psc-fifo node
+-------------------------
+Required properties :
+ - compatible : Should be "fsl,mpc5121-psc-fifo"
+ - reg : Offset and length of the register set for the PSC
+         FIFO Controller
+ - interrupts : <a b> where a is the interrupt number of the
+   PSC FIFO Controller and b is a field that represents an
+   encoding of the sense and level information for the interrupt.
+ - interrupt-parent : the phandle for the interrupt controller that
+   services interrupts for this device.
+Example for a board using PSC0 and PSC1 devices in serial mode:
+serial@11000 {
+        compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+        cell-index = <0>;
+        reg = <0x11000 0x100>;
+        interrupts = <40 0x8>;
+        interrupt-parent = < &ipic >;
+        fsl,rx-fifo-size = <16>;
+        fsl,tx-fifo-size = <16>;
+};
+serial@11100 {
+        compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+        cell-index = <1>;
+        reg = <0x11100 0x100>;
+        interrupts = <40 0x8>;
+        interrupt-parent = < &ipic >;
+        fsl,rx-fifo-size = <16>;
+        fsl,tx-fifo-size = <16>;
+};
+pscfifo@11f00 {
+        compatible = "fsl,mpc5121-psc-fifo";
+        reg = <0x11f00 0x100>;
+        interrupts = <40 0x8>;
+        interrupt-parent = < &ipic >;
+};
diff --git a/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt b/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt
index 5c6602dbfdc2..4ccb2cd5df94 100644
--- a/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt
@@ -195,11 +195,4 @@ External interrupts:
 fsl,mpc5200-mscan nodes
 -----------------------
-In addition to the required compatible-, reg- and interrupt-properites, you can
+See file can.txt in this directory.
-also specify which clock source shall be used for the controller:
- fsl,mscan-clock-source- a string describing the clock source. Valid values
-                          are:  "ip" for ip bus clock
-                                "ref" for reference clock (XTAL)
-                          "ref" is default in case this property is not
-                          present.
diff --git a/Documentation/powerpc/dts-bindings/fsl/spi.txt b/Documentation/powerpc/dts-bindings/fsl/spi.txt
index e7d9a344c4f4..80510c018eea 100644
--- a/Documentation/powerpc/dts-bindings/fsl/spi.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/spi.txt
@@ -13,6 +13,11 @@ Required properties:
 - interrupt-parent : the phandle for the interrupt controller that
  services interrupts for this device.
+Optional properties:
+- gpios : specifies the gpio pins to be used for chipselects.
+  The gpios will be referred to as reg = <index> in the SPI child nodes.
+  If unspecified, a single SPI device without a chip select can be used.
 Example:
        spi@4c0 {
                cell-index = <0>;
@@ -21,4 +26,6 @@ Example:
                interrupts = <82 0>;
                interrupt-parent = <700>;
                mode = "cpu";
+                gpios = <&gpio 18 1     // device reg=<0>
+                         &gpio 19 1>;   // device reg=<1>
        };
diff --git a/Documentation/powerpc/dts-bindings/xilinx.txt b/Documentation/powerpc/dts-bindings/xilinx.txt
index ea68046bb9cb..299d0923537b 100644
--- a/Documentation/powerpc/dts-bindings/xilinx.txt
+++ b/Documentation/powerpc/dts-bindings/xilinx.txt
@@ -11,7 +11,7 @@
   control how the core is synthesized.  Historically, the EDK tool would
   extract the device parameters relevant to device drivers and copy them
   into an 'xparameters.h' in the form of #define symbols.  This tells the
-   device drivers how the IP cores are configured, but it requres the kernel
+   device drivers how the IP cores are configured, but it requires the kernel
   to be recompiled every time the FPGA bitstream is resynthesized.
   The new approach is to export the parameters into the device tree and
diff --git a/Documentation/powerpc/phyp-assisted-dump.txt b/Documentation/powerpc/phyp-assisted-dump.txt
index c4682b982a2e..ad340205d96a 100644
--- a/Documentation/powerpc/phyp-assisted-dump.txt
+++ b/Documentation/powerpc/phyp-assisted-dump.txt
@@ -19,7 +19,7 @@ dump offers several strong, practical advantages:
   immediately available to the system for normal use.
 -- After the dump is completed, no further reboots are
   required; the system will be fully usable, and running
-   in it's normal, production mode on it normal kernel.
+   in its normal, production mode on its normal kernel.
 The above can only be accomplished by coordination with,
 and assistance from the hypervisor. The procedure is
diff --git a/Documentation/powerpc/ptrace.txt b/Documentation/powerpc/ptrace.txt
new file mode 100644
index 000000000000..f4a5499b7bc6
--- /dev/null
+++ b/Documentation/powerpc/ptrace.txt
@@ -0,0 +1,134 @@
+GDB intends to support the following hardware debug features of BookE
+processors:
+4 hardware breakpoints (IAC)
+2 hardware watchpoints (read, write and read-write) (DAC)
+2 value conditions for the hardware watchpoints (DVC)
+For that, we need to extend ptrace so that GDB can query and set these
+resources. Since we're extending, we're trying to create an interface
+that's extendable and that covers both BookE and server processors, so
+that GDB doesn't need to special-case each of them. We added the
+following 3 new ptrace requests.
+1. PTRACE_PPC_GETHWDEBUGINFO
+Query for GDB to discover the hardware debug features. The main info to
+be returned here is the minimum alignment for the hardware watchpoints.
+BookE processors don't have restrictions here, but server processors have
+an 8-byte alignment restriction for hardware watchpoints. We'd like to avoid
+adding special cases to GDB based on what it sees in AUXV.
+Since we're at it, we added other useful info that the kernel can return to
+GDB: this query will return the number of hardware breakpoints, hardware
+watchpoints and whether it supports a range of addresses and a condition.
+The query will fill the following structure provided by the requesting process:
+struct ppc_debug_info {
+       unit32_t version;
+       unit32_t num_instruction_bps;
+       unit32_t num_data_bps;
+       unit32_t num_condition_regs;
+       unit32_t data_bp_alignment;
+       unit32_t sizeof_condition; /* size of the DVC register */
+       uint64_t features; /* bitmask of the individual flags */
+};
+features will have bits indicating whether there is support for:
+#define PPC_DEBUG_FEATURE_INSN_BP_RANGE         0x1
+#define PPC_DEBUG_FEATURE_INSN_BP_MASK          0x2
+#define PPC_DEBUG_FEATURE_DATA_BP_RANGE         0x4
+#define PPC_DEBUG_FEATURE_DATA_BP_MASK          0x8
+2. PTRACE_SETHWDEBUG
+Sets a hardware breakpoint or watchpoint, according to the provided structure:
+struct ppc_hw_breakpoint {
+        uint32_t version;
+#define PPC_BREAKPOINT_TRIGGER_EXECUTE  0x1
+#define PPC_BREAKPOINT_TRIGGER_READ     0x2
+#define PPC_BREAKPOINT_TRIGGER_WRITE    0x4
+        uint32_t trigger_type;       /* only some combinations allowed */
+#define PPC_BREAKPOINT_MODE_EXACT               0x0
+#define PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE     0x1
+#define PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE     0x2
+#define PPC_BREAKPOINT_MODE_MASK                0x3
+        uint32_t addr_mode;          /* address match mode */
+#define PPC_BREAKPOINT_CONDITION_MODE   0x3
+#define PPC_BREAKPOINT_CONDITION_NONE   0x0
+#define PPC_BREAKPOINT_CONDITION_AND    0x1
+#define PPC_BREAKPOINT_CONDITION_EXACT  0x1     /* different name for the same thing as above */
+#define PPC_BREAKPOINT_CONDITION_OR     0x2
+#define PPC_BREAKPOINT_CONDITION_AND_OR 0x3
+#define PPC_BREAKPOINT_CONDITION_BE_ALL 0x00ff0000      /* byte enable bits */
+#define PPC_BREAKPOINT_CONDITION_BE(n)  (1<<((n)+16))
+        uint32_t condition_mode;     /* break/watchpoint condition flags */
+        uint64_t addr;
+        uint64_t addr2;
+        uint64_t condition_value;
+};
+A request specifies one event, not necessarily just one register to be set.
+For instance, if the request is for a watchpoint with a condition, both the
+DAC and DVC registers will be set in the same request.
+With this GDB can ask for all kinds of hardware breakpoints and watchpoints
+that the BookE supports. COMEFROM breakpoints available in server processors
+are not contemplated, but that is out of the scope of this work.
+ptrace will return an integer (handle) uniquely identifying the breakpoint or
+watchpoint just created. This integer will be used in the PTRACE_DELHWDEBUG
+request to ask for its removal. Return -ENOSPC if the requested breakpoint
+can't be allocated on the registers.
+Some examples of using the structure to:
+- set a breakpoint in the first breakpoint register
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_EXECUTE;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_EXACT;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_NONE;
+  p.addr            = (uint64_t) address;
+  p.addr2           = 0;
+  p.condition_value = 0;
+- set a watchpoint which triggers on reads in the second watchpoint register
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_READ;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_EXACT;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_NONE;
+  p.addr            = (uint64_t) address;
+  p.addr2           = 0;
+  p.condition_value = 0;
+- set a watchpoint which triggers only with a specific value
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_READ;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_EXACT;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_AND | PPC_BREAKPOINT_CONDITION_BE_ALL;
+  p.addr            = (uint64_t) address;
+  p.addr2           = 0;
+  p.condition_value = (uint64_t) condition;
+- set a ranged hardware breakpoint
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_EXECUTE;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_NONE;
+  p.addr            = (uint64_t) begin_range;
+  p.addr2           = (uint64_t) end_range;
+  p.condition_value = 0;
+3. PTRACE_DELHWDEBUG
+Takes an integer which identifies an existing breakpoint or watchpoint
+(i.e., the value returned from PTRACE_SETHWDEBUG), and deletes the
+corresponding breakpoint or watchpoint..
diff --git a/Documentation/rbtree.txt b/Documentation/rbtree.txt
index aae8355d3166..221f38be98f4 100644
--- a/Documentation/rbtree.txt
+++ b/Documentation/rbtree.txt
@@ -190,3 +190,61 @@ Example:
  for (node = rb_first(&mytree); node; node = rb_next(node))
        printk("key=%s\n", rb_entry(node, struct mytype, node)->keystring);
+Support for Augmented rbtrees
+-----------------------------
+Augmented rbtree is an rbtree with "some" additional data stored in each node.
+This data can be used to augment some new functionality to rbtree.
+Augmented rbtree is an optional feature built on top of basic rbtree
+infrastructure. rbtree user who wants this feature will have an augment
+callback function in rb_root initialized.
+This callback function will be called from rbtree core routines whenever
+a node has a change in one or both of its children. It is the responsibility
+of the callback function to recalculate the additional data that is in the
+rb node using new children information. Note that if this new additional
+data affects the parent node's additional data, then callback function has
+to handle it and do the recursive updates.
+Interval tree is an example of augmented rb tree. Reference -
+"Introduction to Algorithms" by Cormen, Leiserson, Rivest and Stein.
+More details about interval trees:
+Classical rbtree has a single key and it cannot be directly used to store
+interval ranges like [lo:hi] and do a quick lookup for any overlap with a new
+lo:hi or to find whether there is an exact match for a new lo:hi.
+However, rbtree can be augmented to store such interval ranges in a structured
+way making it possible to do efficient lookup and exact match.
+This "extra information" stored in each node is the maximum hi
+(max_hi) value among all the nodes that are its descendents. This
+information can be maintained at each node just be looking at the node
+and its immediate children. And this will be used in O(log n) lookup
+for lowest match (lowest start address among all possible matches)
+with something like:
+find_lowest_match(lo, hi, node)
+{
+        lowest_match = NULL;
+        while (node) {
+                if (max_hi(node->left) > lo) {
+                        // Lowest overlap if any must be on left side
+                        node = node->left;
+                } else if (overlap(lo, hi, node)) {
+                        lowest_match = node;
+                        break;
+                } else if (lo > node->lo) {
+                        // Lowest overlap if any must be on right side
+                        node = node->right;
+                } else {
+                        break;
+                }
+        }
+        return lowest_match;
+}
+Finding exact match will be to first find lowest match and then to follow
+successor nodes looking for exact match, until the start of a node is beyond
+the hi value we are looking for.
diff --git a/Documentation/rfkill.txt b/Documentation/rfkill.txt
index b4860509c319..83668e5dd17f 100644
--- a/Documentation/rfkill.txt
+++ b/Documentation/rfkill.txt
@@ -99,37 +99,15 @@ system. Also, it is possible to switch all rfkill drivers (or all drivers of
 a specified type) into a state which also updates the default state for
 hotplugged devices.
-After an application opens /dev/rfkill, it can read the current state of
+After an application opens /dev/rfkill, it can read the current state of all
-all devices, and afterwards can poll the descriptor for hotplug or state
+devices. Changes can be either obtained by either polling the descriptor for
-change events.
+hotplug or state change events or by listening for uevents emitted by the
+rfkill core framework.
-Applications must ignore operations (the "op" field) they do not handle,
-this allows the API to be extended in the future.
+Additionally, each rfkill device is registered in sysfs and emits uevents.
-Additionally, each rfkill device is registered in sysfs and there has the
+rfkill devices issue uevents (with an action of "change"), with the following
-following attributes:
+environment variables set:
-        name: Name assigned by driver to this key (interface or driver name).
-        type: Driver type string ("wlan", "bluetooth", etc).
-        persistent: Whether the soft blocked state is initialised from
-                    non-volatile storage at startup.
-        state: Current state of the transmitter
-                0: RFKILL_STATE_SOFT_BLOCKED
-                        transmitter is turned off by software
-                1: RFKILL_STATE_UNBLOCKED
-                        transmitter is (potentially) active
-                2: RFKILL_STATE_HARD_BLOCKED
-                        transmitter is forced off by something outside of
-                        the driver's control.
-               This file is deprecated because it can only properly show
-               three of the four possible states, soft-and-hard-blocked is
-               missing.
-        claim: 0: Kernel handles events
-               This file is deprecated because there no longer is a way to
-               claim just control over a single rfkill instance.
-rfkill devices also issue uevents (with an action of "change"), with the
-following environment variables set:
 RFKILL_NAME
 RFKILL_STATE
@@ -137,3 +115,7 @@ RFKILL_TYPE
 The contents of these variables corresponds to the "name", "state" and
 "type" sysfs files explained above.
+For further details consult Documentation/ABI/stable/dev-rfkill and
+Documentation/ABI/stable/sysfs-class-rfkill.
diff --git a/Documentation/rt-mutex-design.txt b/Documentation/rt-mutex-design.txt
index 4b736d24da7a..8df0b782c4d7 100644
--- a/Documentation/rt-mutex-design.txt
+++ b/Documentation/rt-mutex-design.txt
@@ -657,7 +657,7 @@ here.
 The waiter structure has a "task" field that points to the task that is blocked
 on the mutex.  This field can be NULL the first time it goes through the loop
-or if the task is a pending owner and had it's mutex stolen.  If the "task"
+or if the task is a pending owner and had its mutex stolen.  If the "task"
 field is NULL then we need to set up the accounting for it.
 Task blocks on mutex
diff --git a/Documentation/s390/CommonIO b/Documentation/s390/CommonIO
index 339207d11d95..d378cba66456 100644
--- a/Documentation/s390/CommonIO
+++ b/Documentation/s390/CommonIO
@@ -87,6 +87,12 @@ Command line parameters
  compatibility, by the device number in hexadecimal (0xabcd or abcd). Device
  numbers given as 0xabcd will be interpreted as 0.0.abcd.
+* /proc/cio_settle
+  A write request to this file is blocked until all queued cio actions are
+  handled. This will allow userspace to wait for pending work affecting
+  device availability after changing cio_ignore or the hardware configuration.
 * For some of the information present in the /proc filesystem in 2.4 (namely,
  /proc/subchannels and /proc/chpids), see driver-model.txt.
  Information formerly in /proc/irq_count is now in /proc/interrupts.
diff --git a/Documentation/s390/driver-model.txt b/Documentation/s390/driver-model.txt
index bde473df748d..ed265cf54cde 100644
--- a/Documentation/s390/driver-model.txt
+++ b/Documentation/s390/driver-model.txt
@@ -223,8 +223,8 @@ touched by the driver - it should use the ccwgroup device's driver_data for its
 private data.
 To implement a ccwgroup driver, please refer to include/asm/ccwgroup.h. Keep in
-mind that most drivers will need to implement both a ccwgroup and a ccw driver
+mind that most drivers will need to implement both a ccwgroup and a ccw
-(unless you have a meta ccw driver, like cu3088 for lcs and ctc).
+driver.
 2. Channel paths
diff --git a/Documentation/s390/kvm.txt b/Documentation/s390/kvm.txt
index 6f5ceb0f09fc..85f3280d7ef6 100644
--- a/Documentation/s390/kvm.txt
+++ b/Documentation/s390/kvm.txt
@@ -102,7 +102,7 @@ args:		unsigned long
 see also:       include/linux/kvm.h
 This ioctl stores the state of the cpu at the guest real address given as
 argument, unless one of the following values defined in include/linux/kvm.h
-is given as arguement:
+is given as argument:
 KVM_S390_STORE_STATUS_NOADDR - the CPU stores its status to the save area in
 absolute lowcore as defined by the principles of operation
 KVM_S390_STORE_STATUS_PREFIXED - the CPU stores its status to the save area in
diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt
index 6f33593e59e2..8239ebbcddce 100644
--- a/Documentation/scheduler/sched-design-CFS.txt
+++ b/Documentation/scheduler/sched-design-CFS.txt
@@ -211,7 +211,7 @@ provide fair CPU time to each such task group.  For example, it may be
 desirable to first provide fair CPU time to each user on the system and then to
 each task belonging to a user.
-CONFIG_GROUP_SCHED strives to achieve exactly that.  It lets tasks to be
+CONFIG_CGROUP_SCHED strives to achieve exactly that.  It lets tasks to be
 grouped and divides CPU time fairly among such groups.
 CONFIG_RT_GROUP_SCHED permits to group real-time (i.e., SCHED_FIFO and
@@ -220,38 +220,11 @@ SCHED_RR) tasks.
 CONFIG_FAIR_GROUP_SCHED permits to group CFS (i.e., SCHED_NORMAL and
 SCHED_BATCH) tasks.
-At present, there are two (mutually exclusive) mechanisms to group tasks for
+   These options need CONFIG_CGROUPS to be defined, and let the administrator
-CPU bandwidth control purposes:
- - Based on user id (CONFIG_USER_SCHED)
-   With this option, tasks are grouped according to their user id.
- - Based on "cgroup" pseudo filesystem (CONFIG_CGROUP_SCHED)
-   This options needs CONFIG_CGROUPS to be defined, and lets the administrator
   create arbitrary groups of tasks, using the "cgroup" pseudo filesystem.  See
   Documentation/cgroups/cgroups.txt for more information about this filesystem.
-Only one of these options to group tasks can be chosen and not both.
+When CONFIG_FAIR_GROUP_SCHED is defined, a "cpu.shares" file is created for each
-When CONFIG_USER_SCHED is defined, a directory is created in sysfs for each new
-user and a "cpu_share" file is added in that directory.
-        # cd /sys/kernel/uids
-        # cat 512/cpu_share             # Display user 512's CPU share
-        1024
-        # echo 2048 > 512/cpu_share     # Modify user 512's CPU share
-        # cat 512/cpu_share             # Display user 512's CPU share
-        2048
-        #
-CPU bandwidth between two users is divided in the ratio of their CPU shares.
-For example: if you would like user "root" to get twice the bandwidth of user
-"guest," then set the cpu_share for both the users such that "root"'s cpu_share
-is twice "guest"'s cpu_share.
-When CONFIG_CGROUP_SCHED is defined, a "cpu.shares" file is created for each
 group created using the pseudo filesystem.  See example steps below to create
 task groups and modify their CPU share using the "cgroups" pseudo filesystem.
@@ -273,24 +246,3 @@ task groups and modify their CPU share using the "cgroups" pseudo filesystem.
        # #Launch gmplayer (or your favourite movie player)
        # echo <movie_player_pid> > multimedia/tasks
-8. Implementation note: user namespaces
-User namespaces are intended to be hierarchical.  But they are currently
-only partially implemented.  Each of those has ramifications for CFS.
-First, since user namespaces are hierarchical, the /sys/kernel/uids
-presentation is inadequate.  Eventually we will likely want to use sysfs
-tagging to provide private views of /sys/kernel/uids within each user
-namespace.
-Second, the hierarchical nature is intended to support completely
-unprivileged use of user namespaces.  So if using user groups, then
-we want the users in a user namespace to be children of the user
-who created it.
-That is currently unimplemented.  So instead, every user in a new
-user namespace will receive 1024 shares just like any user in the
-initial user namespace.  Note that at the moment creation of a new
-user namespace requires each of CAP_SYS_ADMIN, CAP_SETUID, and
-CAP_SETGID.
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 86eabe6c3419..605b0d40329d 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -126,23 +126,12 @@ priority!
 2.3 Basis for grouping tasks
 ----------------------------
-There are two compile-time settings for allocating CPU bandwidth. These are
+Enabling CONFIG_RT_GROUP_SCHED lets you explicitly allocate real
-configured using the "Basis for grouping tasks" multiple choice menu under
+CPU bandwidth to task groups.
-General setup > Group CPU Scheduler:
-a. CONFIG_USER_SCHED (aka "Basis for grouping tasks" =  "user id")
-This lets you use the virtual files under
-"/sys/kernel/uids/<uid>/cpu_rt_runtime_us" to control he CPU time reserved for
-each user .
-The other option is:
-.o CONFIG_CGROUP_SCHED (aka "Basis for grouping tasks" = "Control groups")
 This uses the /cgroup virtual file system and
 "/cgroup/<cgroup>/cpu.rt_runtime_us" to control the CPU time reserved for each
-control group instead.
+control group.
 For more information on working with control groups, you should read
 Documentation/cgroups/cgroups.txt as well.
@@ -161,8 +150,7 @@ For now, this can be simplified to just the following (but see Future plans):
 ===============
 There is work in progress to make the scheduling period for each group
-("/sys/kernel/uids/<uid>/cpu_rt_period_us" or
+("/cgroup/<cgroup>/cpu.rt_period_us") configurable as well.
-"/cgroup/<cgroup>/cpu.rt_period_us" respectively) configurable as well.
 The constraint on the period is that a subgroup must have a smaller or
 equal period to its parent. But realistically its not very useful _yet_
diff --git a/Documentation/scsi/ChangeLog.lpfc b/Documentation/scsi/ChangeLog.lpfc
index ff19a52fe004..e759e92e286d 100644
--- a/Documentation/scsi/ChangeLog.lpfc
+++ b/Documentation/scsi/ChangeLog.lpfc
@@ -707,7 +707,7 @@ Changes from 20040920 to 20041018
        * Integrate patches from Christoph Hellwig: two new helpers common
          to lpfc_sli_resume_iocb and lpfc_sli_issue_iocb - singificant
          cleanup of those two functions - the unused SLI_IOCB_USE_TXQ is
-          gone - lpfc_sli_issue_iocb_wait loses it's flags argument
+          gone - lpfc_sli_issue_iocb_wait loses its flags argument
          totally.
        * Fix in lpfc_sli.c: we can not store a 5 bit value in a 4-bit
          field.
@@ -989,8 +989,8 @@ Changes from 20040709 to 20040716
        * Remove redundant port_cmp != 2 check in if
          (!port_cmp) { .... if (port_cmp != 2).... }
        * Clock changes: removed struct clk_data and timerList.
-        * Clock changes: seperate nodev_tmo and els_retry_delay into 2
+        * Clock changes: separate nodev_tmo and els_retry_delay into 2
-          seperate timers and convert to 1 argument changed
+          separate timers and convert to 1 argument changed
          LPFC_NODE_FARP_PEND_t to struct lpfc_node_farp_pend convert
          ipfarp_tmo to 1 argument convert target struct tmofunc and
          rtplunfunc to 1 argument * cr_count, cr_delay and
@@ -1028,7 +1028,7 @@ Changes from 20040614 to 20040709
        * Remove the need for buf_tmo.
        * Changed ULP_BDE64 to struct ulp_bde64.
        * Changed ULP_BDE to struct ulp_bde.
-        * Cleanup lpfc_os_return_scsi_cmd() and it's call path.
+        * Cleanup lpfc_os_return_scsi_cmd() and its call path.
        * Removed lpfc_no_device_delay.
        * Consolidating lpfc_hba_put_event() into lpfc_put_event().
        * Removed following attributes and their functionality:
@@ -1514,7 +1514,7 @@ Changes from 20040402 to 20040409
        * Remove unused elxclock declaration in elx_sli.h.
        * Since everywhere IOCB_ENTRY is used, the return value is cast,
          move the cast into the macro.
-        * Split ioctls out into seperate files
+        * Split ioctls out into separate files
 Changes from 20040326 to 20040402
@@ -1534,7 +1534,7 @@ Changes from 20040326 to 20040402
        * Unused variable cleanup
        * Use Linux list macros for DMABUF_t
        * Break up ioctls into 3 sections, dfc, util, hbaapi
-          rearranged code so this could be easily seperated into a
+          rearranged code so this could be easily separated into a
          differnet module later All 3 are currently turned on by
          defines in lpfc_ioctl.c LPFC_DFC_IOCTL, LPFC_UTIL_IOCTL,
          LPFC_HBAAPI_IOCTL
@@ -1551,7 +1551,7 @@ Changes from 20040326 to 20040402
          started by lpfc_online().  lpfc_offline() only stopped
          els_timeout routine.  It now stops all timeout routines
          associated with that hba.
-        * Replace seperate next and prev pointers in struct
+        * Replace separate next and prev pointers in struct
          lpfc_bindlist with list_head type.  In elxHBA_t, replace
          fc_nlpbind_start and _end with fc_nlpbind_list and use
          list_head macros to access it.
diff --git a/Documentation/scsi/ChangeLog.megaraid_sas b/Documentation/scsi/ChangeLog.megaraid_sas
index 17ffa0607712..30023568805e 100644
--- a/Documentation/scsi/ChangeLog.megaraid_sas
+++ b/Documentation/scsi/ChangeLog.megaraid_sas
@@ -1,3 +1,19 @@
+1 Release Date    : Thur.  Oct 29, 2009 09:12:45 PST 2009 -
+                        (emaild-id:megaraidlinux@lsi.com)
+                        Bo Yang
+2 Current Version : 00.00.04.17.1-rc1
+3 Older Version   : 00.00.04.12
+1.      Add the pad_0 in mfi frame structure to 0 to fix the
+        context value larger than 32bit value issue.
+2.      Add the logic drive list to the driver.  Driver will
+        keep the logic drive list internal after driver load.
+3.      driver fixed the device update issue after get the AEN
+        PD delete/ADD, LD add/delete from FW.
 1 Release Date    : Tues.  July 28, 2009 10:12:45 PST 2009 -
                        (emaild-id:megaraidlinux@lsi.com)
                        Bo Yang
diff --git a/Documentation/scsi/FlashPoint.txt b/Documentation/scsi/FlashPoint.txt
index d5acaa300a46..1540a92f6d2b 100644
--- a/Documentation/scsi/FlashPoint.txt
+++ b/Documentation/scsi/FlashPoint.txt
@@ -71,7 +71,7 @@ peters@mylex.com
 Ever since its introduction last October, the BusLogic FlashPoint LT has
 been problematic for members of the Linux community, in that no Linux
-drivers have been available for this new Ultra SCSI product.  Despite it's
+drivers have been available for this new Ultra SCSI product.  Despite its
 officially being positioned as a desktop workstation product, and not being
 particularly well suited for a high performance multitasking operating
 system like Linux, the FlashPoint LT has been touted by computer system
diff --git a/Documentation/scsi/dtc3x80.txt b/Documentation/scsi/dtc3x80.txt
index e8ae6230ab3e..1d7af9f9a8ed 100644
--- a/Documentation/scsi/dtc3x80.txt
+++ b/Documentation/scsi/dtc3x80.txt
@@ -12,7 +12,7 @@ The 3180 does not.  Otherwise, they are identical.
 The DTC3x80 does not support DMA but it does have Pseudo-DMA which is
 supported by the driver.
-It's DTC406 scsi chip is supposedly compatible with the NCR 53C400.
+Its DTC406 scsi chip is supposedly compatible with the NCR 53C400.
 It is memory mapped, uses an IRQ, but no dma or io-port.  There is
 internal DMA, between SCSI bus and an on-chip 128-byte buffer.  Double
 buffering is done automagically by the chip.  Data is transferred
diff --git a/Documentation/scsi/ncr53c8xx.txt b/Documentation/scsi/ncr53c8xx.txt
index 08e2b4d04aab..cda5f8fa2c66 100644
--- a/Documentation/scsi/ncr53c8xx.txt
+++ b/Documentation/scsi/ncr53c8xx.txt
@@ -1479,7 +1479,7 @@ Wide16 SCSI.
 Enabling serial NVRAM support enables detection of the serial NVRAM included
 on Symbios and some Symbios compatible host adaptors, and Tekram boards. The 
 serial NVRAM is used by Symbios and Tekram to hold set up parameters for the 
-host adaptor and it's attached drives.
+host adaptor and its attached drives.
 The Symbios NVRAM also holds data on the boot order of host adaptors in a
 system with more than one host adaptor. This enables the order of scanning
diff --git a/Documentation/scsi/osst.txt b/Documentation/scsi/osst.txt
index f536907e241d..2b21890bc983 100644
--- a/Documentation/scsi/osst.txt
+++ b/Documentation/scsi/osst.txt
@@ -40,7 +40,7 @@ behavior looks very much the same as st to the userspace applications.
 History
 -------
-In the first place, osst shared it's identity very much with st. That meant
+In the first place, osst shared its identity very much with st. That meant
 that it used the same kernel structures and the same device node as st.
 So you could only have either of them being present in the kernel. This has
 been fixed by registering an own device, now.
diff --git a/Documentation/scsi/scsi_fc_transport.txt b/Documentation/scsi/scsi_fc_transport.txt
index aec6549ab097..e00192de4d1c 100644
--- a/Documentation/scsi/scsi_fc_transport.txt
+++ b/Documentation/scsi/scsi_fc_transport.txt
@@ -70,7 +70,7 @@ Overview:
    up to an administrative entity controlling the vport. For example,
    if vports are to be associated with virtual machines, a XEN mgmt
    utility would be responsible for creating wwpn/wwnn's for the vport,
-    using it's own naming authority and OUI. (Note: it already does this
+    using its own naming authority and OUI. (Note: it already does this
    for virtual MAC addresses).
@@ -81,7 +81,7 @@ Device Trees and Vport Objects:
  with rports and scsi target objects underneath it. Currently the FC
  transport creates the vport object and places it under the scsi_host
  object corresponding to the physical adapter.  The LLDD will allocate
-  a new scsi_host for the vport and link it's object under the vport.
+  a new scsi_host for the vport and link its object under the vport.
  The remainder of the tree under the vports scsi_host is the same
  as the non-NPIV case. The transport is written currently to easily
  allow the parent of the vport to be something other than the scsi_host.
diff --git a/Documentation/scsi/sym53c8xx_2.txt b/Documentation/scsi/sym53c8xx_2.txt
index eb9a7b905b64..6f63b7989679 100644
--- a/Documentation/scsi/sym53c8xx_2.txt
+++ b/Documentation/scsi/sym53c8xx_2.txt
@@ -687,7 +687,7 @@ maintain the driver code.
 Enabling serial NVRAM support enables detection of the serial NVRAM included
 on Symbios and some Symbios compatible host adaptors, and Tekram boards. The 
 serial NVRAM is used by Symbios and Tekram to hold set up parameters for the 
-host adaptor and it's attached drives.
+host adaptor and its attached drives.
 The Symbios NVRAM also holds data on the boot order of host adaptors in a
 system with more than one host adaptor.  This information is no longer used
diff --git a/Documentation/serial/tty.txt b/Documentation/serial/tty.txt
index 5e5349a4fcd2..7c900507279f 100644
--- a/Documentation/serial/tty.txt
+++ b/Documentation/serial/tty.txt
@@ -105,6 +105,10 @@ write_wakeup()	-	May be called at any point between open and close.
                        is permitted to call the driver write method from
                        this function. In such a situation defer it.
+dcd_change()    -       Report to the tty line the current DCD pin status
+                        changes and the relative timestamp. The timestamp
+                        can be NULL.
 Driver Access
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 8923597bd2bd..2075bbb8b3e2 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -227,6 +227,16 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
    The power-management is supported.
+  Module snd-asihpi
+  -----------------
+    Module for AudioScience ASI soundcards
+    enable_hpi_hwdep    - enable HPI hwdep for AudioScience soundcard
+    This module supports multiple cards.
+    The driver requires the firmware loader support on kernel.
  Module snd-atiixp
  -----------------
@@ -482,6 +492,9 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
    reference_rate      - reference sample rate, 44100 or 48000 (default)
    multiple            - multiple to ref. sample rate, 1 or 2 (default)
+    subsystem           - override the PCI SSID for probing; the value
+                          consists of SSVID << 16 | SSDID.  The default is
+                          zero, which means no override.
    This module supports multiple cards.
@@ -619,28 +632,23 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
    
    The power-management is supported.
-  Module snd-es968
-  ----------------
-    Module for sound cards based on ESS ES968 chip (PnP only).
-    This module supports multiple cards, PnP and autoprobe.
-    
-    The power-management is supported.
  Module snd-es1688
  -----------------
    Module for ESS AudioDrive ES-1688 and ES-688 sound cards.
-    port        - port # for ES-1688 chip (0x220,0x240,0x260)
+    isapnp      - ISA PnP detection - 0 = disable, 1 = enable (default)
-    fm_port     - port # for OPL3 (option; share the same port as default)
    mpu_port    - port # for MPU-401 port (0x300,0x310,0x320,0x330), -1 = disable (default)
-    irq         - IRQ # for ES-1688 chip (5,7,9,10)
    mpu_irq     - IRQ # for MPU-401 port (5,7,9,10)
+    fm_port     - port # for OPL3 (option; share the same port as default)
+    with isapnp=0, the following additional options are available:
+    port        - port # for ES-1688 chip (0x220,0x240,0x260)
+    irq         - IRQ # for ES-1688 chip (5,7,9,10)
    dma8        - DMA # for ES-1688 chip (0,1,3)
-    This module supports multiple cards and autoprobe (without MPU-401 port).
+    This module supports multiple cards and autoprobe (without MPU-401 port)
+    and PnP with the ES968 chip.
  Module snd-es18xx
  -----------------
@@ -1123,6 +1131,21 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
    This module supports multiple cards, autoprobe and ISA PnP.
+  Module snd-jazz16
+  -------------------
+    Module for Media Vision Jazz16 chipset. The chipset consists of 3 chips:
+    MVD1216 + MVA416 + MVA514.
+    port        - port # for SB DSP chip (0x210,0x220,0x230,0x240,0x250,0x260)
+    irq         - IRQ # for SB DSP chip (3,5,7,9,10,15)
+    dma8        - DMA # for SB DSP chip (1,3)
+    dma16       - DMA # for SB DSP chip (5,7)
+    mpu_port    - MPU-401 port # (0x300,0x310,0x320,0x330)
+    mpu_irq     - MPU-401 irq # (2,3,5,7)
+    This module supports multiple cards.
  Module snd-korg1212
  -------------------
@@ -1791,6 +1814,13 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
    The power-management is supported.
+  Module snd-ua101
+  ----------------
+    Module for the Edirol UA-101/UA-1000 audio/MIDI interfaces.
+    This module supports multiple devices, autoprobe and hotplugging.
  Module snd-usb-audio
  --------------------
@@ -1923,7 +1953,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
  -------------------
    Module for sound cards based on the Asus AV100/AV200 chips,
-    i.e., Xonar D1, DX, D2, D2X, HDAV1.3 (Deluxe), Essence ST
+    i.e., Xonar D1, DX, D2, D2X, DS, HDAV1.3 (Deluxe), Essence ST
    (Deluxe) and Essence STX.
    This module supports autoprobe and multiple cards.
diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
index e72cee9e2a71..1d38b0dfba95 100644
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@@ -124,6 +124,8 @@ ALC882/883/885/888/889
  asus-a7m      ASUS A7M
  macpro        MacPro support
  mb5           Macbook 5,1
+  macmini3      Macmini 3,1
+  mba21         Macbook Air 2,1
  mbp3          Macbook Pro rev3
  imac24        iMac 24'' with jack detection
  imac91        iMac 9,1
@@ -279,13 +281,16 @@ Conexant 5051
  laptop        Basic Laptop config (default)
  hp            HP Spartan laptop
  hp-dv6736     HP dv6736
+  hp-f700       HP Compaq Presario F700
  lenovo-x200   Lenovo X200 laptop
+  toshiba       Toshiba Satellite M300
 Conexant 5066
 =============
  laptop        Basic Laptop config (default)
  dell-laptop   Dell laptops
  olpc-xo-1_5   OLPC XO 1.5
+  ideapad       Lenovo IdeaPad U150
 STAC9200
 ========
diff --git a/Documentation/sound/alsa/HD-Audio.txt b/Documentation/sound/alsa/HD-Audio.txt
index 6325bec06a72..bdafdbd32561 100644
--- a/Documentation/sound/alsa/HD-Audio.txt
+++ b/Documentation/sound/alsa/HD-Audio.txt
@@ -119,10 +119,18 @@ the codec slots 0 and 1 no matter what the hardware reports.
 Interrupt Handling
 ~~~~~~~~~~~~~~~~~~
-In rare but some cases, the interrupt isn't properly handled as
+HD-audio driver uses MSI as default (if available) since 2.6.33
-default.  You would notice this by the DMA transfer error reported by
+kernel as MSI works better on some machines, and in general, it's
-ALSA PCM core, for example.  Using MSI might help in such a case.
+better for performance.  However, Nvidia controllers showed bad
-Pass `enable_msi=1` option for enabling MSI.
+regressions with MSI (especially in a combination with AMD chipset),
+thus we disabled MSI for them.
+There seem also still other devices that don't work with MSI.  If you
+see a regression wrt the sound quality (stuttering, etc) or a lock-up
+in the recent kernel, try to pass `enable_msi=0` option to disable
+MSI.  If it works, you can add the known bad device to the blacklist
+defined in hda_intel.c.  In such a case, please report and give the
+patch back to the upstream developer. 
 HD-AUDIO CODEC
@@ -196,7 +204,6 @@ generic parser regardless of the codec.  Usually the codec-specific
 parser is much better than the generic parser (as now).  Thus this
 option is more about the debugging purpose.
 Speaker and Headphone Output
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 One of the most frequent (and obvious) bugs with HD-audio is the
@@ -452,6 +459,33 @@ Similarly, the lines after `[verb]` are parsed as `init_verbs`
 sysfs entries, and the lines after `[hint]` are parsed as `hints`
 sysfs entries, respectively.
+Another example to override the codec vendor id from 0x12345678 to
+0xdeadbeef is like below:
+------------------------------------------------------------------------
+  [codec]
+  0x12345678 0xabcd1234 2
+  [vendor_id]
+  0xdeadbeef
+------------------------------------------------------------------------
+In the similar way, you can override the codec subsystem_id via
+`[subsystem_id]`, the revision id via `[revision_id]` line.
+Also, the codec chip name can be rewritten via `[chip_name]` line.
+------------------------------------------------------------------------
+  [codec]
+  0x12345678 0xabcd1234 2
+  [subsystem_id]
+  0xffff1111
+  [revision_id]
+  0x10
+  [chip_name]
+  My-own NEWS-0002
+------------------------------------------------------------------------
 The hd-audio driver reads the file via request_firmware().  Thus,
 a patch file has to be located on the appropriate firmware path,
 typically, /lib/firmware.  For example, when you pass the option
@@ -565,6 +599,9 @@ probing, the proc file is available, so you can get the raw codec
 information before modified by the driver.  Of course, the driver
 isn't usable with `probe_only=1`.  But you can continue the
 configuration via hwdep sysfs file if hda-reconfig option is enabled.
+Using `probe_only` mask 2 skips the reset of HDA codecs (use
+`probe_only=3` as module option). The hwdep interface can be used
+to determine the BIOS codec initialization.
 hda-verb
diff --git a/Documentation/sound/alsa/soc/dapm.txt b/Documentation/sound/alsa/soc/dapm.txt
index 9ac842be9b4f..05bf5a0eee41 100644
--- a/Documentation/sound/alsa/soc/dapm.txt
+++ b/Documentation/sound/alsa/soc/dapm.txt
@@ -188,8 +188,8 @@ The WM8731 output mixer has 3 inputs (sources)
 3. Mic Sidetone Input
 Each input in this example has a kcontrol associated with it (defined in example
-above) and is connected to the output mixer via it's kcontrol name. We can now
+above) and is connected to the output mixer via its kcontrol name. We can now
-connect the destination widget (wrt audio signal) with it's source widgets.
+connect the destination widget (wrt audio signal) with its source widgets.
        /* output mixer */
        {"Output Mixer", "Line Bypass Switch", "Line Input"},
diff --git a/Documentation/sound/alsa/soc/machine.txt b/Documentation/sound/alsa/soc/machine.txt
index bab7711ce963..2524c75557df 100644
--- a/Documentation/sound/alsa/soc/machine.txt
+++ b/Documentation/sound/alsa/soc/machine.txt
@@ -67,7 +67,7 @@ static struct snd_soc_dai_link corgi_dai = {
        .ops = &corgi_ops,
 };
-struct snd_soc_card then sets up the machine with it's DAIs. e.g.
+struct snd_soc_card then sets up the machine with its DAIs. e.g.
 /* corgi audio machine driver */
 static struct snd_soc_card snd_soc_corgi = {
diff --git a/Documentation/sound/alsa/soc/overview.txt b/Documentation/sound/alsa/soc/overview.txt
index 1e4c6d3655f2..138ac88c1461 100644
--- a/Documentation/sound/alsa/soc/overview.txt
+++ b/Documentation/sound/alsa/soc/overview.txt
@@ -33,7 +33,7 @@ features :-
    and machines.
  * Easy I2S/PCM audio interface setup between codec and SoC. Each SoC
-    interface and codec registers it's audio interface capabilities with the
+    interface and codec registers its audio interface capabilities with the
    core and are subsequently matched and configured when the application
    hardware parameters are known.
diff --git a/Documentation/sparse.txt b/Documentation/sparse.txt
index 34c76a55bc04..9b659c79a547 100644
--- a/Documentation/sparse.txt
+++ b/Documentation/sparse.txt
@@ -54,12 +54,12 @@ Getting sparse
 ~~~~~~~~~~~~~~
 You can get latest released versions from the Sparse homepage at
-http://www.kernel.org/pub/linux/kernel/people/josh/sparse/
+https://sparse.wiki.kernel.org/index.php/Main_Page
 Alternatively, you can get snapshots of the latest development version
 of sparse using git to clone..
-        git://git.kernel.org/pub/scm/linux/kernel/git/josh/sparse.git
+        git://git.kernel.org/pub/scm/devel/sparse/sparse.git
 DaveJ has hourly generated tarballs of the git tree available at..
diff --git a/Documentation/spi/ep93xx_spi b/Documentation/spi/ep93xx_spi
new file mode 100644
index 000000000000..6325f5b48635
--- /dev/null
+++ b/Documentation/spi/ep93xx_spi
@@ -0,0 +1,95 @@
+Cirrus EP93xx SPI controller driver HOWTO
+=========================================
+ep93xx_spi driver brings SPI master support for EP93xx SPI controller.  Chip
+selects are implemented with GPIO lines.
+NOTE: If possible, don't use SFRMOUT (SFRM1) signal as a chip select. It will
+not work correctly (it cannot be controlled by software). Use GPIO lines
+instead.
+Sample configuration
+====================
+Typically driver configuration is done in platform board files (the files under
+arch/arm/mach-ep93xx/*.c). In this example we configure MMC over SPI through
+this driver on TS-7260 board. You can adapt the code to suit your needs.
+This example uses EGPIO9 as SD/MMC card chip select (this is wired in DIO1
+header on the board).
+You need to select CONFIG_MMC_SPI to use mmc_spi driver.
+arch/arm/mach-ep93xx/ts72xx.c:
+...
+#include <linux/gpio.h>
+#include <linux/spi/spi.h>
+#include <mach/ep93xx_spi.h>
+/* this is our GPIO line used for chip select */
+#define MMC_CHIP_SELECT_GPIO EP93XX_GPIO_LINE_EGPIO9
+static int ts72xx_mmc_spi_setup(struct spi_device *spi)
+{
+        int err;
+        err = gpio_request(MMC_CHIP_SELECT_GPIO, spi->modalias);
+        if (err)
+                return err;
+        gpio_direction_output(MMC_CHIP_SELECT_GPIO, 1);
+        return 0;
+}
+static void ts72xx_mmc_spi_cleanup(struct spi_device *spi)
+{
+        gpio_set_value(MMC_CHIP_SELECT_GPIO, 1);
+        gpio_direction_input(MMC_CHIP_SELECT_GPIO);
+        gpio_free(MMC_CHIP_SELECT_GPIO);
+}
+static void ts72xx_mmc_spi_cs_control(struct spi_device *spi, int value)
+{
+        gpio_set_value(MMC_CHIP_SELECT_GPIO, value);
+}
+static struct ep93xx_spi_chip_ops ts72xx_mmc_spi_ops = {
+        .setup          = ts72xx_mmc_spi_setup,
+        .cleanup        = ts72xx_mmc_spi_cleanup,
+        .cs_control     = ts72xx_mmc_spi_cs_control,
+};
+static struct spi_board_info ts72xx_spi_devices[] __initdata = {
+        {
+                .modalias               = "mmc_spi",
+                .controller_data        = &ts72xx_mmc_spi_ops,
+                /*
+                 * We use 10 MHz even though the maximum is 7.4 MHz. The driver
+                 * will limit it automatically to max. frequency.
+                 */
+                .max_speed_hz           = 10 * 1000 * 1000,
+                .bus_num                = 0,
+                .chip_select            = 0,
+                .mode                   = SPI_MODE_0,
+        },
+};
+static struct ep93xx_spi_info ts72xx_spi_info = {
+        .num_chipselect = ARRAY_SIZE(ts72xx_spi_devices),
+};
+static void __init ts72xx_init_machine(void)
+{
+        ...
+        ep93xx_register_spi(&ts72xx_spi_info, ts72xx_spi_devices,
+                            ARRAY_SIZE(ts72xx_spi_devices));
+}
+Thanks to
+=========
+Martin Guy, H. Hartley Sweeten and others who helped me during development of
+the driver. Simplemachines.it donated me a Sim.One board which I used testing
+the driver on EP9307.
diff --git a/Documentation/spi/spidev_fdx.c b/Documentation/spi/spidev_fdx.c
index fc354f760384..36ec0774ca0b 100644
--- a/Documentation/spi/spidev_fdx.c
+++ b/Documentation/spi/spidev_fdx.c
@@ -58,10 +58,10 @@ static void do_msg(int fd, int len)
                len = sizeof buf;
        buf[0] = 0xaa;
-        xfer[0].tx_buf = (__u64) buf;
+        xfer[0].tx_buf = (unsigned long)buf;
        xfer[0].len = 1;
-        xfer[1].rx_buf = (__u64) buf;
+        xfer[1].rx_buf = (unsigned long) buf;
        xfer[1].len = len;
        status = ioctl(fd, SPI_IOC_MESSAGE(2), xfer);
diff --git a/Documentation/spi/spidev_test.c b/Documentation/spi/spidev_test.c
index 10abd3773e49..16feda901469 100644
--- a/Documentation/spi/spidev_test.c
+++ b/Documentation/spi/spidev_test.c
@@ -58,7 +58,7 @@ static void transfer(int fd)
        };
        ret = ioctl(fd, SPI_IOC_MESSAGE(1), &tr);
-        if (ret == 1)
+        if (ret < 1)
                pabort("can't send spi message");
        for (ret = 0; ret < ARRAY_SIZE(tx); ret++) {
diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt
index 5effa5bd993b..e213f45cf9d7 100644
--- a/Documentation/stable_kernel_rules.txt
+++ b/Documentation/stable_kernel_rules.txt
@@ -18,16 +18,15 @@ Rules on what kind of patches are accepted, and which ones are not, into the
 - It cannot contain any "trivial" fixes in it (spelling changes,
   whitespace cleanups, etc).
 - It must follow the Documentation/SubmittingPatches rules.
- - It or an equivalent fix must already exist in Linus' tree.  Quote the
+ - It or an equivalent fix must already exist in Linus' tree (upstream).
-   respective commit ID in Linus' tree in your patch submission to -stable.
 Procedure for submitting patches to the -stable tree:
 - Send the patch, after verifying that it follows the above rules, to
-   stable@kernel.org.
+   stable@kernel.org.  You must note the upstream commit ID in the changelog
- - To have the patch automatically included in the stable tree, add the
+   of your submission.
-   the tag
+ - To have the patch automatically included in the stable tree, add the tag
     Cc: stable@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
diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index df38ef046f8d..cbd05ffc606b 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -84,6 +84,16 @@ netdev_max_backlog
 Maximum number  of  packets,  queued  on  the  INPUT  side, when the interface
 receives packets faster than kernel can process them.
+netdev_tstamp_prequeue
+----------------------
+If set to 0, RX packet timestamps can be sampled after RPS processing, when
+the target CPU processes packets. It might give some delay on timestamps, but
+permit to distribute the load on several cpus.
+If set to 1 (default), timestamps are sampled as soon as possible, before
+queueing.
 optmem_max
 ----------
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index fc5790d36cd9..5fdbb612aeb8 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -19,6 +19,7 @@ files can be found in mm/swap.c.
 Currently, these files are in /proc/sys/vm:
 - block_dump
+- compact_memory
 - dirty_background_bytes
 - dirty_background_ratio
 - dirty_bytes
@@ -26,6 +27,7 @@ Currently, these files are in /proc/sys/vm:
 - dirty_ratio
 - dirty_writeback_centisecs
 - drop_caches
+- extfrag_threshold
 - hugepages_treat_as_movable
 - hugetlb_shm_group
 - laptop_mode
@@ -64,6 +66,15 @@ information on block I/O debugging is in Documentation/laptops/laptop-mode.txt.
 ==============================================================
+compact_memory
+Available only when CONFIG_COMPACTION is set. When 1 is written to the file,
+all zones are compacted such that free memory is available in contiguous
+blocks where possible. This can be important for example in the allocation of
+huge pages although processes will also directly compact memory as required.
+==============================================================
 dirty_background_bytes
 Contains the amount of dirty memory at which the pdflush background writeback
@@ -139,6 +150,20 @@ user should run `sync' first.
 ==============================================================
+extfrag_threshold
+This parameter affects whether the kernel will compact memory or direct
+reclaim to satisfy a high-order allocation. /proc/extfrag_index shows what
+the fragmentation index for each order is in each zone in the system. Values
+tending towards 0 imply allocations would fail due to lack of memory,
+values towards 1000 imply failures are due to fragmentation and -1 implies
+that the allocation will succeed as long as watermarks are met.
+The kernel will not compact memory in a zone if the
+fragmentation index is <= extfrag_threshold. The default value is 500.
+==============================================================
 hugepages_treat_as_movable
 This parameter is only useful when kernelcore= is specified at boot time to
@@ -573,11 +598,14 @@ Because other nodes' memory may be free. This means system total status
 may be not fatal yet.
 If this is set to 2, the kernel panics compulsorily even on the
-above-mentioned.
+above-mentioned. Even oom happens under memory cgroup, the whole
+system panics.
 The default value is 0.
 1 and 2 are for failover of clustering. Please select either
 according to your policy of failover.
+panic_on_oom=2+kdump gives you very strong tool to investigate
+why oom happens. You can get snapshot.
 =============================================================
diff --git a/Documentation/sysfs-rules.txt b/Documentation/sysfs-rules.txt
index 5d8bc2cd250c..c1a1fd636bf9 100644
--- a/Documentation/sysfs-rules.txt
+++ b/Documentation/sysfs-rules.txt
@@ -125,7 +125,7 @@ versions of the sysfs interface.
 - Block
  The converted block subsystem at /sys/class/block or
  /sys/subsystem/block will contain the links for disks and partitions
-  at the same level, never in a hierarchy. Assuming the block subsytem to
+  at the same level, never in a hierarchy. Assuming the block subsystem to
  contain only disks and not partition devices in the same flat list is
  a bug in the application.
diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
index d56a01775423..5c17196c8fe9 100644
--- a/Documentation/sysrq.txt
+++ b/Documentation/sysrq.txt
@@ -177,13 +177,13 @@ virtual console (ALT+Fn) and then back again should also help.
 *  I hit SysRq, but nothing seems to happen, what's wrong?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-There are some keyboards that send different scancodes for SysRq than the
+There are some keyboards that produce a different keycode for SysRq than the
-pre-defined 0x54. So if SysRq doesn't work out of the box for a certain
+pre-defined value of 99 (see KEY_SYSRQ in include/linux/input.h), or which
-keyboard, run 'showkey -s' to find out the proper scancode sequence. Then
+don't have a SysRq key at all. In these cases, run 'showkey -s' to find an
-use 'setkeycodes <sequence> 84' to define this sequence to the usual SysRq
+appropriate scancode sequence, and use 'setkeycodes <sequence> 99' to map
-code (84 is decimal for 0x54). It's probably best to put this command in a
+this sequence to the usual SysRq code (e.g., 'setkeycodes e05b 99'). It's
-boot script. Oh, and by the way, you exit 'showkey' by not typing anything
+probably best to put this command in a boot script. Oh, and by the way, you
-for ten seconds.
+exit 'showkey' by not typing anything for ten seconds.
 *  I want to add SysRQ key events to a module, how does it work?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/timers/00-INDEX b/Documentation/timers/00-INDEX
index 397dc35e1323..a9248da5cdbc 100644
--- a/Documentation/timers/00-INDEX
+++ b/Documentation/timers/00-INDEX
@@ -4,6 +4,8 @@ highres.txt
        - High resolution timers and dynamic ticks design notes
 hpet.txt
        - High Precision Event Timer Driver for Linux
+hpet_example.c
+        - sample hpet timer test program
 hrtimers.txt
        - subsystem for high-resolution kernel timers
 timer_stats.txt
diff --git a/Documentation/timers/Makefile b/Documentation/timers/Makefile
new file mode 100644
index 000000000000..c85625f4ab25
--- /dev/null
+++ b/Documentation/timers/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+# List of programs to build
+hostprogs-y := hpet_example
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/timers/hpet.txt b/Documentation/timers/hpet.txt
index 16d25e6b5a00..767392ffd31e 100644
--- a/Documentation/timers/hpet.txt
+++ b/Documentation/timers/hpet.txt
@@ -26,274 +26,5 @@ initialization.  An example of this initialization can be found in
 arch/x86/kernel/hpet.c.
 The driver provides a userspace API which resembles the API found in the
-RTC driver framework.  An example user space program is provided below.
+RTC driver framework.  An example user space program is provided in
+file:Documentation/timers/hpet_example.c
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <fcntl.h>
-#include <string.h>
-#include <memory.h>
-#include <malloc.h>
-#include <time.h>
-#include <ctype.h>
-#include <sys/types.h>
-#include <sys/wait.h>
-#include <signal.h>
-#include <fcntl.h>
-#include <errno.h>
-#include <sys/time.h>
-#include <linux/hpet.h>
-extern void hpet_open_close(int, const char **);
-extern void hpet_info(int, const char **);
-extern void hpet_poll(int, const char **);
-extern void hpet_fasync(int, const char **);
-extern void hpet_read(int, const char **);
-#include <sys/poll.h>
-#include <sys/ioctl.h>
-#include <signal.h>
-struct hpet_command {
-        char            *command;
-        void            (*func)(int argc, const char ** argv);
-} hpet_command[] = {
-        {
-                "open-close",
-                hpet_open_close
-        },
-        {
-                "info",
-                hpet_info
-        },
-        {
-                "poll",
-                hpet_poll
-        },
-        {
-                "fasync",
-                hpet_fasync
-        },
-};
-int
-main(int argc, const char ** argv)
-{
-        int     i;
-        argc--;
-        argv++;
-        if (!argc) {
-                fprintf(stderr, "-hpet: requires command\n");
-                return -1;
-        }
-        for (i = 0; i < (sizeof (hpet_command) / sizeof (hpet_command[0])); i++)
-                if (!strcmp(argv[0], hpet_command[i].command)) {
-                        argc--;
-                        argv++;
-                        fprintf(stderr, "-hpet: executing %s\n",
-                                hpet_command[i].command);
-                        hpet_command[i].func(argc, argv);
-                        return 0;
-                }
-        fprintf(stderr, "do_hpet: command %s not implemented\n", argv[0]);
-        return -1;
-}
-void
-hpet_open_close(int argc, const char **argv)
-{
-        int     fd;
-        if (argc != 1) {
-                fprintf(stderr, "hpet_open_close: device-name\n");
-                return;
-        }
-        fd = open(argv[0], O_RDONLY);
-        if (fd < 0)
-                fprintf(stderr, "hpet_open_close: open failed\n");
-        else
-                close(fd);
-        return;
-}
-void
-hpet_info(int argc, const char **argv)
-{
-}
-void
-hpet_poll(int argc, const char **argv)
-{
-        unsigned long           freq;
-        int                     iterations, i, fd;
-        struct pollfd           pfd;
-        struct hpet_info        info;
-        struct timeval          stv, etv;
-        struct timezone         tz;
-        long                    usec;
-        if (argc != 3) {
-                fprintf(stderr, "hpet_poll: device-name freq iterations\n");
-                return;
-        }
-        freq = atoi(argv[1]);
-        iterations = atoi(argv[2]);
-        fd = open(argv[0], O_RDONLY);
-        if (fd < 0) {
-                fprintf(stderr, "hpet_poll: open of %s failed\n", argv[0]);
-                return;
-        }
-        if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
-                fprintf(stderr, "hpet_poll: HPET_IRQFREQ failed\n");
-                goto out;
-        }
-        if (ioctl(fd, HPET_INFO, &info) < 0) {
-                fprintf(stderr, "hpet_poll: failed to get info\n");
-                goto out;
-        }
-        fprintf(stderr, "hpet_poll: info.hi_flags 0x%lx\n", info.hi_flags);
-        if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
-                fprintf(stderr, "hpet_poll: HPET_EPI failed\n");
-                goto out;
-        }
-        if (ioctl(fd, HPET_IE_ON, 0) < 0) {
-                fprintf(stderr, "hpet_poll, HPET_IE_ON failed\n");
-                goto out;
-        }
-        pfd.fd = fd;
-        pfd.events = POLLIN;
-        for (i = 0; i < iterations; i++) {
-                pfd.revents = 0;
-                gettimeofday(&stv, &tz);
-                if (poll(&pfd, 1, -1) < 0)
-                        fprintf(stderr, "hpet_poll: poll failed\n");
-                else {
-                        long    data;
-                        gettimeofday(&etv, &tz);
-                        usec = stv.tv_sec * 1000000 + stv.tv_usec;
-                        usec = (etv.tv_sec * 1000000 + etv.tv_usec) - usec;
-                        fprintf(stderr,
-                                "hpet_poll: expired time = 0x%lx\n", usec);
-                        fprintf(stderr, "hpet_poll: revents = 0x%x\n",
-                                pfd.revents);
-                        if (read(fd, &data, sizeof(data)) != sizeof(data)) {
-                                fprintf(stderr, "hpet_poll: read failed\n");
-                        }
-                        else
-                                fprintf(stderr, "hpet_poll: data 0x%lx\n",
-                                        data);
-                }
-        }
-out:
-        close(fd);
-        return;
-}
-static int hpet_sigio_count;
-static void
-hpet_sigio(int val)
-{
-        fprintf(stderr, "hpet_sigio: called\n");
-        hpet_sigio_count++;
-}
-void
-hpet_fasync(int argc, const char **argv)
-{
-        unsigned long           freq;
-        int                     iterations, i, fd, value;
-        sig_t                   oldsig;
-        struct hpet_info        info;
-        hpet_sigio_count = 0;
-        fd = -1;
-        if ((oldsig = signal(SIGIO, hpet_sigio)) == SIG_ERR) {
-                fprintf(stderr, "hpet_fasync: failed to set signal handler\n");
-                return;
-        }
-        if (argc != 3) {
-                fprintf(stderr, "hpet_fasync: device-name freq iterations\n");
-                goto out;
-        }
-        fd = open(argv[0], O_RDONLY);
-        if (fd < 0) {
-                fprintf(stderr, "hpet_fasync: failed to open %s\n", argv[0]);
-                return;
-        }
-        if ((fcntl(fd, F_SETOWN, getpid()) == 1) ||
-                ((value = fcntl(fd, F_GETFL)) == 1) ||
-                (fcntl(fd, F_SETFL, value | O_ASYNC) == 1)) {
-                fprintf(stderr, "hpet_fasync: fcntl failed\n");
-                goto out;
-        }
-        freq = atoi(argv[1]);
-        iterations = atoi(argv[2]);
-        if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
-                fprintf(stderr, "hpet_fasync: HPET_IRQFREQ failed\n");
-                goto out;
-        }
-        if (ioctl(fd, HPET_INFO, &info) < 0) {
-                fprintf(stderr, "hpet_fasync: failed to get info\n");
-                goto out;
-        }
-        fprintf(stderr, "hpet_fasync: info.hi_flags 0x%lx\n", info.hi_flags);
-        if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
-                fprintf(stderr, "hpet_fasync: HPET_EPI failed\n");
-                goto out;
-        }
-        if (ioctl(fd, HPET_IE_ON, 0) < 0) {
-                fprintf(stderr, "hpet_fasync, HPET_IE_ON failed\n");
-                goto out;
-        }
-        for (i = 0; i < iterations; i++) {
-                (void) pause();
-                fprintf(stderr, "hpet_fasync: count = %d\n", hpet_sigio_count);
-        }
-out:
-        signal(SIGIO, oldsig);
-        if (fd >= 0)
-                close(fd);
-        return;
-}
diff --git a/Documentation/timers/hpet_example.c b/Documentation/timers/hpet_example.c
new file mode 100644
index 000000000000..4bfafb7bc4c5
--- /dev/null
+++ b/Documentation/timers/hpet_example.c
@@ -0,0 +1,267 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <string.h>
+#include <memory.h>
+#include <malloc.h>
+#include <time.h>
+#include <ctype.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <signal.h>
+#include <errno.h>
+#include <sys/time.h>
+#include <linux/hpet.h>
+extern void hpet_open_close(int, const char **);
+extern void hpet_info(int, const char **);
+extern void hpet_poll(int, const char **);
+extern void hpet_fasync(int, const char **);
+extern void hpet_read(int, const char **);
+#include <sys/poll.h>
+#include <sys/ioctl.h>
+struct hpet_command {
+        char            *command;
+        void            (*func)(int argc, const char ** argv);
+} hpet_command[] = {
+        {
+                "open-close",
+                hpet_open_close
+        },
+        {
+                "info",
+                hpet_info
+        },
+        {
+                "poll",
+                hpet_poll
+        },
+        {
+                "fasync",
+                hpet_fasync
+        },
+};
+int
+main(int argc, const char ** argv)
+{
+        int     i;
+        argc--;
+        argv++;
+        if (!argc) {
+                fprintf(stderr, "-hpet: requires command\n");
+                return -1;
+        }
+        for (i = 0; i < (sizeof (hpet_command) / sizeof (hpet_command[0])); i++)
+                if (!strcmp(argv[0], hpet_command[i].command)) {
+                        argc--;
+                        argv++;
+                        fprintf(stderr, "-hpet: executing %s\n",
+                                hpet_command[i].command);
+                        hpet_command[i].func(argc, argv);
+                        return 0;
+                }
+        fprintf(stderr, "do_hpet: command %s not implemented\n", argv[0]);
+        return -1;
+}
+void
+hpet_open_close(int argc, const char **argv)
+{
+        int     fd;
+        if (argc != 1) {
+                fprintf(stderr, "hpet_open_close: device-name\n");
+                return;
+        }
+        fd = open(argv[0], O_RDONLY);
+        if (fd < 0)
+                fprintf(stderr, "hpet_open_close: open failed\n");
+        else
+                close(fd);
+        return;
+}
+void
+hpet_info(int argc, const char **argv)
+{
+}
+void
+hpet_poll(int argc, const char **argv)
+{
+        unsigned long           freq;
+        int                     iterations, i, fd;
+        struct pollfd           pfd;
+        struct hpet_info        info;
+        struct timeval          stv, etv;
+        struct timezone         tz;
+        long                    usec;
+        if (argc != 3) {
+                fprintf(stderr, "hpet_poll: device-name freq iterations\n");
+                return;
+        }
+        freq = atoi(argv[1]);
+        iterations = atoi(argv[2]);
+        fd = open(argv[0], O_RDONLY);
+        if (fd < 0) {
+                fprintf(stderr, "hpet_poll: open of %s failed\n", argv[0]);
+                return;
+        }
+        if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
+                fprintf(stderr, "hpet_poll: HPET_IRQFREQ failed\n");
+                goto out;
+        }
+        if (ioctl(fd, HPET_INFO, &info) < 0) {
+                fprintf(stderr, "hpet_poll: failed to get info\n");
+                goto out;
+        }
+        fprintf(stderr, "hpet_poll: info.hi_flags 0x%lx\n", info.hi_flags);
+        if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
+                fprintf(stderr, "hpet_poll: HPET_EPI failed\n");
+                goto out;
+        }
+        if (ioctl(fd, HPET_IE_ON, 0) < 0) {
+                fprintf(stderr, "hpet_poll, HPET_IE_ON failed\n");
+                goto out;
+        }
+        pfd.fd = fd;
+        pfd.events = POLLIN;
+        for (i = 0; i < iterations; i++) {
+                pfd.revents = 0;
+                gettimeofday(&stv, &tz);
+                if (poll(&pfd, 1, -1) < 0)
+                        fprintf(stderr, "hpet_poll: poll failed\n");
+                else {
+                        long    data;
+                        gettimeofday(&etv, &tz);
+                        usec = stv.tv_sec * 1000000 + stv.tv_usec;
+                        usec = (etv.tv_sec * 1000000 + etv.tv_usec) - usec;
+                        fprintf(stderr,
+                                "hpet_poll: expired time = 0x%lx\n", usec);
+                        fprintf(stderr, "hpet_poll: revents = 0x%x\n",
+                                pfd.revents);
+                        if (read(fd, &data, sizeof(data)) != sizeof(data)) {
+                                fprintf(stderr, "hpet_poll: read failed\n");
+                        }
+                        else
+                                fprintf(stderr, "hpet_poll: data 0x%lx\n",
+                                        data);
+                }
+        }
+out:
+        close(fd);
+        return;
+}
+static int hpet_sigio_count;
+static void
+hpet_sigio(int val)
+{
+        fprintf(stderr, "hpet_sigio: called\n");
+        hpet_sigio_count++;
+}
+void
+hpet_fasync(int argc, const char **argv)
+{
+        unsigned long           freq;
+        int                     iterations, i, fd, value;
+        sig_t                   oldsig;
+        struct hpet_info        info;
+        hpet_sigio_count = 0;
+        fd = -1;
+        if ((oldsig = signal(SIGIO, hpet_sigio)) == SIG_ERR) {
+                fprintf(stderr, "hpet_fasync: failed to set signal handler\n");
+                return;
+        }
+        if (argc != 3) {
+                fprintf(stderr, "hpet_fasync: device-name freq iterations\n");
+                goto out;
+        }
+        fd = open(argv[0], O_RDONLY);
+        if (fd < 0) {
+                fprintf(stderr, "hpet_fasync: failed to open %s\n", argv[0]);
+                return;
+        }
+        if ((fcntl(fd, F_SETOWN, getpid()) == 1) ||
+                ((value = fcntl(fd, F_GETFL)) == 1) ||
+                (fcntl(fd, F_SETFL, value | O_ASYNC) == 1)) {
+                fprintf(stderr, "hpet_fasync: fcntl failed\n");
+                goto out;
+        }
+        freq = atoi(argv[1]);
+        iterations = atoi(argv[2]);
+        if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
+                fprintf(stderr, "hpet_fasync: HPET_IRQFREQ failed\n");
+                goto out;
+        }
+        if (ioctl(fd, HPET_INFO, &info) < 0) {
+                fprintf(stderr, "hpet_fasync: failed to get info\n");
+                goto out;
+        }
+        fprintf(stderr, "hpet_fasync: info.hi_flags 0x%lx\n", info.hi_flags);
+        if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
+                fprintf(stderr, "hpet_fasync: HPET_EPI failed\n");
+                goto out;
+        }
+        if (ioctl(fd, HPET_IE_ON, 0) < 0) {
+                fprintf(stderr, "hpet_fasync, HPET_IE_ON failed\n");
+                goto out;
+        }
+        for (i = 0; i < iterations; i++) {
+                (void) pause();
+                fprintf(stderr, "hpet_fasync: count = %d\n", hpet_sigio_count);
+        }
+out:
+        signal(SIGIO, oldsig);
+        if (fd >= 0)
+                close(fd);
+        return;
+}
diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt
index 02ac6ed38b2d..09bd8e902989 100644
--- a/Documentation/trace/events.txt
+++ b/Documentation/trace/events.txt
@@ -90,7 +90,8 @@ In order to facilitate early boot debugging, use boot option:
        trace_event=[event-list]
-The format of this boot option is the same as described in section 2.1.
+event-list is a comma separated list of events. See section 2.1 for event
+format.
 3. Defining an event-enabled tracepoint
 =======================================
@@ -238,7 +239,7 @@ subsystem's filter file.
 For convenience, filters for every event in a subsystem can be set or
 cleared as a group by writing a filter expression into the filter file
-at the root of the subsytem.  Note however, that if a filter for any
+at the root of the subsystem.  Note however, that if a filter for any
 event within the subsystem lacks a field specified in the subsystem
 filter, or if the filter can't be applied for any other reason, the
 filter for that event will retain its previous setting.  This can
@@ -250,7 +251,7 @@ fields can be guaranteed to propagate successfully to all events.
 Here are a few subsystem filter examples that also illustrate the
 above points:
-Clear the filters on all events in the sched subsytem:
+Clear the filters on all events in the sched subsystem:
 # cd /sys/kernel/debug/tracing/events/sched
 # echo 0 > filter
@@ -260,7 +261,7 @@ none
 none
 Set a filter using only common fields for all events in the sched
-subsytem (all events end up with the same filter):
+subsystem (all events end up with the same filter):
 # cd /sys/kernel/debug/tracing/events/sched
 # echo common_pid == 0 > filter
@@ -270,7 +271,7 @@ common_pid == 0
 common_pid == 0
 Attempt to set a filter using a non-common field for all events in the
-sched subsytem (all events but those that have a prev_pid field retain
+sched subsystem (all events but those that have a prev_pid field retain
 their old filters):
 # cd /sys/kernel/debug/tracing/events/sched
diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt
index 6a5a579126b0..f1f81afee8a0 100644
--- a/Documentation/trace/ftrace-design.txt
+++ b/Documentation/trace/ftrace-design.txt
@@ -238,11 +238,10 @@ HAVE_SYSCALL_TRACEPOINTS
 You need very few things to get the syscalls tracing in an arch.
+- Support HAVE_ARCH_TRACEHOOK (see arch/Kconfig).
 - Have a NR_syscalls variable in <asm/unistd.h> that provides the number
  of syscalls supported by the arch.
- Implement arch_syscall_addr() that resolves a syscall address from a
+- Support the TIF_SYSCALL_TRACEPOINT thread flags.
-  syscall number.
- Support the TIF_SYSCALL_TRACEPOINT thread flags
 - Put the trace_sys_enter() and trace_sys_exit() tracepoints calls from ptrace
  in the ptrace syscalls tracing path.
 - Tag this arch as HAVE_SYSCALL_TRACEPOINTS.
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index bab3040da548..557c1edeccaf 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -155,6 +155,9 @@ of ftrace. Here is a list of some of the key files:
        to be traced. Echoing names of functions into this file
        will limit the trace to only those functions.
+        This interface also allows for commands to be used. See the
+        "Filter commands" section for more details.
  set_ftrace_notrace:
        This has an effect opposite to that of
@@ -1337,12 +1340,14 @@ ftrace_dump_on_oops must be set. To set ftrace_dump_on_oops, one
 can either use the sysctl function or set it via the proc system
 interface.
-  sysctl kernel.ftrace_dump_on_oops=1
+  sysctl kernel.ftrace_dump_on_oops=n
 or
-  echo 1 > /proc/sys/kernel/ftrace_dump_on_oops
+  echo n > /proc/sys/kernel/ftrace_dump_on_oops
+If n = 1, ftrace will dump buffers of all CPUs, if n = 2 ftrace will
+only dump the buffer of the CPU that triggered the oops.
 Here's an example of such a dump after a null pointer
 dereference in a kernel module:
@@ -1588,7 +1593,7 @@ module author does not need to worry about it.
 When tracing is enabled, kstop_machine is called to prevent
 races with the CPUS executing code being modified (which can
-cause the CPU to do undesireable things), and the nops are
+cause the CPU to do undesirable things), and the nops are
 patched back to calls. But this time, they do not call mcount
 (which is just a function stub). They now call into the ftrace
 infrastructure.
@@ -1822,6 +1827,47 @@ this special filter via:
 echo > set_graph_function
+Filter commands
+---------------
+A few commands are supported by the set_ftrace_filter interface.
+Trace commands have the following format:
+<function>:<command>:<parameter>
+The following commands are supported:
+- mod
+  This command enables function filtering per module. The
+  parameter defines the module. For example, if only the write*
+  functions in the ext3 module are desired, run:
+   echo 'write*:mod:ext3' > set_ftrace_filter
+  This command interacts with the filter in the same way as
+  filtering based on function names. Thus, adding more functions
+  in a different module is accomplished by appending (>>) to the
+  filter file. Remove specific module functions by prepending
+  '!':
+   echo '!writeback*:mod:ext3' >> set_ftrace_filter
+- traceon/traceoff
+  These commands turn tracing on and off when the specified
+  functions are hit. The parameter determines how many times the
+  tracing system is turned on and off. If unspecified, there is
+  no limit. For example, to disable tracing when a schedule bug
+  is hit the first 5 times, run:
+   echo '__schedule_bug:traceoff:5' > set_ftrace_filter
+  These commands are cumulative whether or not they are appended
+  to set_ftrace_filter. To remove a command, prepend it by '!'
+  and drop the parameter:
+   echo '!__schedule_bug:traceoff' > set_ftrace_filter
 trace_pipe
 ----------
diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index 47aabeebbdf6..ec94748ae65b 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -24,6 +24,7 @@ Synopsis of kprobe_events
 -------------------------
  p[:[GRP/]EVENT] SYMBOL[+offs]|MEMADDR [FETCHARGS]     : Set a probe
  r[:[GRP/]EVENT] SYMBOL[+0] [FETCHARGS]                : Set a return probe
+  -:[GRP/]EVENT                                         : Clear a probe
 GRP            : Group name. If omitted, use "kprobes" for it.
 EVENT          : Event name. If omitted, the event name is generated
@@ -37,15 +38,14 @@ Synopsis of kprobe_events
  @SYM[+|-offs] : Fetch memory at SYM +|- offs (SYM should be a data symbol)
  $stackN       : Fetch Nth entry of stack (N >= 0)
  $stack        : Fetch stack address.
-  $argN         : Fetch function argument. (N >= 0)(*)
+  $retval       : Fetch return value.(*)
-  $retval       : Fetch return value.(**)
+  +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
-  +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(***)
+  NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
-  NAME=FETCHARG: Set NAME as the argument name of FETCHARG.
+  FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
+                  (u8/u16/u32/u64/s8/s16/s32/s64) are supported.
-  (*) aN may not correct on asmlinkaged functions and at the middle of
+  (*) only for return probe.
-      function body.
+  (**) this is useful for fetching a field of data structures.
-  (**) only for return probe.
-  (***) this is useful for fetching a field of data structures.
 Per-Probe Event Filtering
@@ -82,13 +82,16 @@ Usage examples
 To add a probe as a new event, write a new definition to kprobe_events
 as below.
-  echo p:myprobe do_sys_open dfd=$arg0 filename=$arg1 flags=$arg2 mode=$arg3 > /sys/kernel/debug/tracing/kprobe_events
+  echo 'p:myprobe do_sys_open dfd=%ax filename=%dx flags=%cx mode=+4($stack)' > /sys/kernel/debug/tracing/kprobe_events
 This sets a kprobe on the top of do_sys_open() function with recording
-1st to 4th arguments as "myprobe" event. As this example shows, users can
+1st to 4th arguments as "myprobe" event. Note, which register/stack entry is
-choose more familiar names for each arguments.
+assigned to each function argument depends on arch-specific ABI. If you unsure
+the ABI, please try to use probe subcommand of perf-tools (you can find it
+under tools/perf/).
+As this example shows, users can choose more familiar names for each arguments.
-  echo r:myretprobe do_sys_open $retval >> /sys/kernel/debug/tracing/kprobe_events
+  echo 'r:myretprobe do_sys_open $retval' >> /sys/kernel/debug/tracing/kprobe_events
 This sets a kretprobe on the return point of do_sys_open() function with
 recording return value as "myretprobe" event.
@@ -97,23 +100,24 @@ recording return value as "myretprobe" event.
  cat /sys/kernel/debug/tracing/events/kprobes/myprobe/format
 name: myprobe
-ID: 75
+ID: 780
 format:
-        field:unsigned short common_type;       offset:0;       size:2;
+        field:unsigned short common_type;       offset:0;       size:2; signed:0;
-        field:unsigned char common_flags;       offset:2;       size:1;
+        field:unsigned char common_flags;       offset:2;       size:1; signed:0;
-        field:unsigned char common_preempt_count;       offset:3;       size:1;
+        field:unsigned char common_preempt_count;       offset:3; size:1;signed:0;
-        field:int common_pid;   offset:4;       size:4;
+        field:int common_pid;   offset:4;       size:4; signed:1;
-        field:int common_tgid;  offset:8;       size:4;
+        field:int common_lock_depth;    offset:8;       size:4; signed:1;
-        field: unsigned long ip;        offset:16;tsize:8;
+        field:unsigned long __probe_ip; offset:12;      size:4; signed:0;
-        field: int nargs;       offset:24;tsize:4;
+        field:int __probe_nargs;        offset:16;      size:4; signed:1;
-        field: unsigned long dfd;       offset:32;tsize:8;
+        field:unsigned long dfd;        offset:20;      size:4; signed:0;
-        field: unsigned long filename;  offset:40;tsize:8;
+        field:unsigned long filename;   offset:24;      size:4; signed:0;
-        field: unsigned long flags;     offset:48;tsize:8;
+        field:unsigned long flags;      offset:28;      size:4; signed:0;
-        field: unsigned long mode;      offset:56;tsize:8;
+        field:unsigned long mode;       offset:32;      size:4; signed:0;
-print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->ip, REC->dfd, REC->filename, REC->flags, REC->mode
+print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->__probe_ip,
+REC->dfd, REC->filename, REC->flags, REC->mode
 You can see that the event has 4 arguments as in the expressions you specified.
@@ -121,6 +125,12 @@ print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->ip, REC->dfd, R
 This clears all probe points.
+ Or,
+  echo -:myprobe >> kprobe_events
+ This clears probe points selectively.
 Right after definition, each event is disabled by default. For tracing these
 events, you need to enable it.
@@ -146,4 +156,3 @@ events, you need to enable it.
 returns from SYMBOL(e.g. "sys_open+0x1b/0x1d <- do_sys_open" means kernel
 returns from do_sys_open to sys_open+0x1b).
diff --git a/Documentation/usb/WUSB-Design-overview.txt b/Documentation/usb/WUSB-Design-overview.txt
index c480e9c32dbd..4c5e37939344 100644
--- a/Documentation/usb/WUSB-Design-overview.txt
+++ b/Documentation/usb/WUSB-Design-overview.txt
@@ -381,7 +381,7 @@ descriptor that gives us the status of the transfer, its identification
 we issue another URB to read into the destination buffer the chunk of
 data coming out of the remote endpoint. Done, wait for the next guy. The
 callbacks for the URBs issued from here are the ones that will declare
-the xfer complete at some point and call it's callback.
+the xfer complete at some point and call its callback.
 Seems simple, but the implementation is not trivial.
diff --git a/Documentation/usb/bulk-streams.txt b/Documentation/usb/bulk-streams.txt
new file mode 100644
index 000000000000..ffc02021863e
--- /dev/null
+++ b/Documentation/usb/bulk-streams.txt
@@ -0,0 +1,78 @@
+Background
+==========
+Bulk endpoint streams were added in the USB 3.0 specification.  Streams allow a
+device driver to overload a bulk endpoint so that multiple transfers can be
+queued at once.
+Streams are defined in sections 4.4.6.4 and 8.12.1.4 of the Universal Serial Bus
+3.0 specification at http://www.usb.org/developers/docs/  The USB Attached SCSI
+Protocol, which uses streams to queue multiple SCSI commands, can be found on
+the T10 website (http://t10.org/).
+Device-side implications
+========================
+Once a buffer has been queued to a stream ring, the device is notified (through
+an out-of-band mechanism on another endpoint) that data is ready for that stream
+ID.  The device then tells the host which "stream" it wants to start.  The host
+can also initiate a transfer on a stream without the device asking, but the
+device can refuse that transfer.  Devices can switch between streams at any
+time.
+Driver implications
+===================
+int usb_alloc_streams(struct usb_interface *interface,
+                struct usb_host_endpoint **eps, unsigned int num_eps,
+                unsigned int num_streams, gfp_t mem_flags);
+Device drivers will call this API to request that the host controller driver
+allocate memory so the driver can use up to num_streams stream IDs.  They must
+pass an array of usb_host_endpoints that need to be setup with similar stream
+IDs.  This is to ensure that a UASP driver will be able to use the same stream
+ID for the bulk IN and OUT endpoints used in a Bi-directional command sequence.
+The return value is an error condition (if one of the endpoints doesn't support
+streams, or the xHCI driver ran out of memory), or the number of streams the
+host controller allocated for this endpoint.  The xHCI host controller hardware
+declares how many stream IDs it can support, and each bulk endpoint on a
+SuperSpeed device will say how many stream IDs it can handle.  Therefore,
+drivers should be able to deal with being allocated less stream IDs than they
+requested.
+Do NOT call this function if you have URBs enqueued for any of the endpoints
+passed in as arguments.  Do not call this function to request less than two
+streams.
+Drivers will only be allowed to call this API once for the same endpoint
+without calling usb_free_streams().  This is a simplification for the xHCI host
+controller driver, and may change in the future.
+Picking new Stream IDs to use
+============================
+Stream ID 0 is reserved, and should not be used to communicate with devices.  If
+usb_alloc_streams() returns with a value of N, you may use streams 1 though N.
+To queue an URB for a specific stream, set the urb->stream_id value.  If the
+endpoint does not support streams, an error will be returned.
+Note that new API to choose the next stream ID will have to be added if the xHCI
+driver supports secondary stream IDs.
+Clean up
+========
+If a driver wishes to stop using streams to communicate with the device, it
+should call
+void usb_free_streams(struct usb_interface *interface,
+                struct usb_host_endpoint **eps, unsigned int num_eps,
+                gfp_t mem_flags);
+All stream IDs will be deallocated when the driver releases the interface, to
+ensure that drivers that don't support streams will be able to use the endpoint.
diff --git a/Documentation/usb/dma.txt b/Documentation/usb/dma.txt
index cfdcd16e3abf..84ef865237db 100644
--- a/Documentation/usb/dma.txt
+++ b/Documentation/usb/dma.txt
@@ -16,11 +16,11 @@ OR:  they can now be DMA-aware.
  manage dma mappings for existing dma-ready buffers (see below).
 - URBs have an additional "transfer_dma" field, as well as a transfer_flags
-  bit saying if it's valid.  (Control requests also have "setup_dma" and a
+  bit saying if it's valid.  (Control requests also have "setup_dma", but
-  corresponding transfer_flags bit.)
+  drivers must not use it.)
- "usbcore" will map those DMA addresses, if a DMA-aware driver didn't do
+- "usbcore" will map this DMA address, if a DMA-aware driver didn't do
-  it first and set URB_NO_TRANSFER_DMA_MAP or URB_NO_SETUP_DMA_MAP.  HCDs
+  it first and set URB_NO_TRANSFER_DMA_MAP.  HCDs
  don't manage dma mappings for URBs.
 - There's a new "generic DMA API", parts of which are usable by USB device
@@ -43,22 +43,16 @@ and effects like cache-trashing can impose subtle penalties.
  kind of addresses to store in urb->transfer_buffer and urb->transfer_dma.
  You'd also set URB_NO_TRANSFER_DMA_MAP in urb->transfer_flags:
-        void *usb_buffer_alloc (struct usb_device *dev, size_t size,
+        void *usb_alloc_coherent (struct usb_device *dev, size_t size,
                int mem_flags, dma_addr_t *dma);
-        void usb_buffer_free (struct usb_device *dev, size_t size,
+        void usb_free_coherent (struct usb_device *dev, size_t size,
                void *addr, dma_addr_t dma);
  Most drivers should *NOT* be using these primitives; they don't need
  to use this type of memory ("dma-coherent"), and memory returned from
  kmalloc() will work just fine.
-  For control transfers you can use the buffer primitives or not for each
-  of the transfer buffer and setup buffer independently.  Set the flag bits
-  URB_NO_TRANSFER_DMA_MAP and URB_NO_SETUP_DMA_MAP to indicate which
-  buffers you have prepared.  For non-control transfers URB_NO_SETUP_DMA_MAP
-  is ignored.
  The memory buffer returned is "dma-coherent"; sometimes you might need to
  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
@@ -130,8 +124,8 @@ of Documentation/PCI/PCI-DMA-mapping.txt, titled "What memory is DMA-able?")
        void usb_buffer_unmap (struct urb *urb);
  The calls manage urb->transfer_dma for you, and set URB_NO_TRANSFER_DMA_MAP
-  so that usbcore won't map or unmap the buffer.  The same goes for
+  so that usbcore won't map or unmap the buffer.  They cannot be used for
-  urb->setup_dma and URB_NO_SETUP_DMA_MAP for control requests.
+  setup_packet buffers in control requests.
 Note that several of those interfaces are currently commented out, since
 they don't have current users.  See the source code.  Other than the dmasync
diff --git a/Documentation/usb/error-codes.txt b/Documentation/usb/error-codes.txt
index 9cf83e8c27b8..d83703ea74b2 100644
--- a/Documentation/usb/error-codes.txt
+++ b/Documentation/usb/error-codes.txt
@@ -41,8 +41,8 @@ USB-specific:
 -EFBIG          Host controller driver can't schedule that many ISO frames.
-EPIPE          Specified endpoint is stalled.  For non-control endpoints,
+-EPIPE          The pipe type specified in the URB doesn't match the
-                reset this status with usb_clear_halt().
+                endpoint's actual type.
 -EMSGSIZE       (a) endpoint maxpacket size is zero; it is not usable
                    in the current interface altsetting.
@@ -60,6 +60,8 @@ USB-specific:
 -EHOSTUNREACH   URB was rejected because the device is suspended.
+-ENOEXEC        A control URB doesn't contain a Setup packet.
 **************************************************************************
 *                   Error codes returned by in urb->status               *
diff --git a/Documentation/usb/gadget_hid.txt b/Documentation/usb/gadget_hid.txt
new file mode 100644
index 000000000000..f4a51f567427
--- /dev/null
+++ b/Documentation/usb/gadget_hid.txt
@@ -0,0 +1,445 @@
+                     Linux USB HID gadget driver
+Introduction
+        The HID Gadget driver provides emulation of USB Human Interface
+        Devices (HID). The basic HID handling is done in the kernel,
+        and HID reports can be sent/received through I/O on the
+        /dev/hidgX character devices.
+        For more details about HID, see the developer page on
+        http://www.usb.org/developers/hidpage/
+Configuration
+        g_hid is a platform driver, so to use it you need to add
+        struct platform_device(s) to your platform code defining the
+        HID function descriptors you want to use - E.G. something
+        like:
+#include <linux/platform_device.h>
+#include <linux/usb/g_hid.h>
+/* hid descriptor for a keyboard */
+static struct hidg_func_descriptor my_hid_data = {
+        .subclass               = 0, /* No subclass */
+        .protocol               = 1, /* Keyboard */
+        .report_length          = 8,
+        .report_desc_length     = 63,
+        .report_desc            = {
+                0x05, 0x01,     /* USAGE_PAGE (Generic Desktop)           */
+                0x09, 0x06,     /* USAGE (Keyboard)                       */
+                0xa1, 0x01,     /* COLLECTION (Application)               */
+                0x05, 0x07,     /*   USAGE_PAGE (Keyboard)                */
+                0x19, 0xe0,     /*   USAGE_MINIMUM (Keyboard LeftControl) */
+                0x29, 0xe7,     /*   USAGE_MAXIMUM (Keyboard Right GUI)   */
+                0x15, 0x00,     /*   LOGICAL_MINIMUM (0)                  */
+                0x25, 0x01,     /*   LOGICAL_MAXIMUM (1)                  */
+                0x75, 0x01,     /*   REPORT_SIZE (1)                      */
+                0x95, 0x08,     /*   REPORT_COUNT (8)                     */
+                0x81, 0x02,     /*   INPUT (Data,Var,Abs)                 */
+                0x95, 0x01,     /*   REPORT_COUNT (1)                     */
+                0x75, 0x08,     /*   REPORT_SIZE (8)                      */
+                0x81, 0x03,     /*   INPUT (Cnst,Var,Abs)                 */
+                0x95, 0x05,     /*   REPORT_COUNT (5)                     */
+                0x75, 0x01,     /*   REPORT_SIZE (1)                      */
+                0x05, 0x08,     /*   USAGE_PAGE (LEDs)                    */
+                0x19, 0x01,     /*   USAGE_MINIMUM (Num Lock)             */
+                0x29, 0x05,     /*   USAGE_MAXIMUM (Kana)                 */
+                0x91, 0x02,     /*   OUTPUT (Data,Var,Abs)                */
+                0x95, 0x01,     /*   REPORT_COUNT (1)                     */
+                0x75, 0x03,     /*   REPORT_SIZE (3)                      */
+                0x91, 0x03,     /*   OUTPUT (Cnst,Var,Abs)                */
+                0x95, 0x06,     /*   REPORT_COUNT (6)                     */
+                0x75, 0x08,     /*   REPORT_SIZE (8)                      */
+                0x15, 0x00,     /*   LOGICAL_MINIMUM (0)                  */
+                0x25, 0x65,     /*   LOGICAL_MAXIMUM (101)                */
+                0x05, 0x07,     /*   USAGE_PAGE (Keyboard)                */
+                0x19, 0x00,     /*   USAGE_MINIMUM (Reserved)             */
+                0x29, 0x65,     /*   USAGE_MAXIMUM (Keyboard Application) */
+                0x81, 0x00,     /*   INPUT (Data,Ary,Abs)                 */
+                0xc0            /* END_COLLECTION                         */
+        }
+};
+static struct platform_device my_hid = {
+        .name                   = "hidg",
+        .id                     = 0,
+        .num_resources          = 0,
+        .resource               = 0,
+        .dev.platform_data      = &my_hid_data,
+};
+        You can add as many HID functions as you want, only limited by
+        the amount of interrupt endpoints your gadget driver supports.
+Send and receive HID reports
+        HID reports can be sent/received using read/write on the
+        /dev/hidgX character devices. See below for an example program
+        to do this.
+        hid_gadget_test is a small interactive program to test the HID
+        gadget driver. To use, point it at a hidg device and set the
+        device type (keyboard / mouse / joystick) - E.G.:
+                # hid_gadget_test /dev/hidg0 keyboard
+        You are now in the prompt of hid_gadget_test. You can type any
+        combination of options and values. Available options and
+        values are listed at program start. In keyboard mode you can
+        send up to six values.
+        For example type: g i s t r --left-shift
+        Hit return and the corresponding report will be sent by the
+        HID gadget.
+        Another interesting example is the caps lock test. Type
+        -–caps-lock and hit return. A report is then sent by the
+        gadget and you should receive the host answer, corresponding
+        to the caps lock LED status.
+                --caps-lock
+                recv report:2
+        With this command:
+                # hid_gadget_test /dev/hidg1 mouse
+        You can test the mouse emulation. Values are two signed numbers.
+Sample code
+/* hid_gadget_test */
+#include <pthread.h>
+#include <string.h>
+#include <stdio.h>
+#include <ctype.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#define BUF_LEN 512
+struct options {
+        const char    *opt;
+        unsigned char val;
+};
+static struct options kmod[] = {
+        {.opt = "--left-ctrl",          .val = 0x01},
+        {.opt = "--right-ctrl",         .val = 0x10},
+        {.opt = "--left-shift",         .val = 0x02},
+        {.opt = "--right-shift",        .val = 0x20},
+        {.opt = "--left-alt",           .val = 0x04},
+        {.opt = "--right-alt",          .val = 0x40},
+        {.opt = "--left-meta",          .val = 0x08},
+        {.opt = "--right-meta",         .val = 0x80},
+        {.opt = NULL}
+};
+static struct options kval[] = {
+        {.opt = "--return",     .val = 0x28},
+        {.opt = "--esc",        .val = 0x29},
+        {.opt = "--bckspc",     .val = 0x2a},
+        {.opt = "--tab",        .val = 0x2b},
+        {.opt = "--spacebar",   .val = 0x2c},
+        {.opt = "--caps-lock",  .val = 0x39},
+        {.opt = "--f1",         .val = 0x3a},
+        {.opt = "--f2",         .val = 0x3b},
+        {.opt = "--f3",         .val = 0x3c},
+        {.opt = "--f4",         .val = 0x3d},
+        {.opt = "--f5",         .val = 0x3e},
+        {.opt = "--f6",         .val = 0x3f},
+        {.opt = "--f7",         .val = 0x40},
+        {.opt = "--f8",         .val = 0x41},
+        {.opt = "--f9",         .val = 0x42},
+        {.opt = "--f10",        .val = 0x43},
+        {.opt = "--f11",        .val = 0x44},
+        {.opt = "--f12",        .val = 0x45},
+        {.opt = "--insert",     .val = 0x49},
+        {.opt = "--home",       .val = 0x4a},
+        {.opt = "--pageup",     .val = 0x4b},
+        {.opt = "--del",        .val = 0x4c},
+        {.opt = "--end",        .val = 0x4d},
+        {.opt = "--pagedown",   .val = 0x4e},
+        {.opt = "--right",      .val = 0x4f},
+        {.opt = "--left",       .val = 0x50},
+        {.opt = "--down",       .val = 0x51},
+        {.opt = "--kp-enter",   .val = 0x58},
+        {.opt = "--up",         .val = 0x52},
+        {.opt = "--num-lock",   .val = 0x53},
+        {.opt = NULL}
+};
+int keyboard_fill_report(char report[8], char buf[BUF_LEN], int *hold)
+{
+        char *tok = strtok(buf, " ");
+        int key = 0;
+        int i = 0;
+        for (; tok != NULL; tok = strtok(NULL, " ")) {
+                if (strcmp(tok, "--quit") == 0)
+                        return -1;
+                if (strcmp(tok, "--hold") == 0) {
+                        *hold = 1;
+                        continue;
+                }
+                if (key < 6) {
+                        for (i = 0; kval[i].opt != NULL; i++)
+                                if (strcmp(tok, kval[i].opt) == 0) {
+                                        report[2 + key++] = kval[i].val;
+                                        break;
+                                }
+                        if (kval[i].opt != NULL)
+                                continue;
+                }
+                if (key < 6)
+                        if (islower(tok[0])) {
+                                report[2 + key++] = (tok[0] - ('a' - 0x04));
+                                continue;
+                        }
+                for (i = 0; kmod[i].opt != NULL; i++)
+                        if (strcmp(tok, kmod[i].opt) == 0) {
+                                report[0] = report[0] | kmod[i].val;
+                                break;
+                        }
+                if (kmod[i].opt != NULL)
+                        continue;
+                if (key < 6)
+                        fprintf(stderr, "unknown option: %s\n", tok);
+        }
+        return 8;
+}
+static struct options mmod[] = {
+        {.opt = "--b1", .val = 0x01},
+        {.opt = "--b2", .val = 0x02},
+        {.opt = "--b3", .val = 0x04},
+        {.opt = NULL}
+};
+int mouse_fill_report(char report[8], char buf[BUF_LEN], int *hold)
+{
+        char *tok = strtok(buf, " ");
+        int mvt = 0;
+        int i = 0;
+        for (; tok != NULL; tok = strtok(NULL, " ")) {
+                if (strcmp(tok, "--quit") == 0)
+                        return -1;
+                if (strcmp(tok, "--hold") == 0) {
+                        *hold = 1;
+                        continue;
+                }
+                for (i = 0; mmod[i].opt != NULL; i++)
+                        if (strcmp(tok, mmod[i].opt) == 0) {
+                                report[0] = report[0] | mmod[i].val;
+                                break;
+                        }
+                if (mmod[i].opt != NULL)
+                        continue;
+                if (!(tok[0] == '-' && tok[1] == '-') && mvt < 2) {
+                        errno = 0;
+                        report[1 + mvt++] = (char)strtol(tok, NULL, 0);
+                        if (errno != 0) {
+                                fprintf(stderr, "Bad value:'%s'\n", tok);
+                                report[1 + mvt--] = 0;
+                        }
+                        continue;
+                }
+                fprintf(stderr, "unknown option: %s\n", tok);
+        }
+        return 3;
+}
+static struct options jmod[] = {
+        {.opt = "--b1",         .val = 0x10},
+        {.opt = "--b2",         .val = 0x20},
+        {.opt = "--b3",         .val = 0x40},
+        {.opt = "--b4",         .val = 0x80},
+        {.opt = "--hat1",       .val = 0x00},
+        {.opt = "--hat2",       .val = 0x01},
+        {.opt = "--hat3",       .val = 0x02},
+        {.opt = "--hat4",       .val = 0x03},
+        {.opt = "--hatneutral", .val = 0x04},
+        {.opt = NULL}
+};
+int joystick_fill_report(char report[8], char buf[BUF_LEN], int *hold)
+{
+        char *tok = strtok(buf, " ");
+        int mvt = 0;
+        int i = 0;
+        *hold = 1;
+        /* set default hat position: neutral */
+        report[3] = 0x04;
+        for (; tok != NULL; tok = strtok(NULL, " ")) {
+                if (strcmp(tok, "--quit") == 0)
+                        return -1;
+                for (i = 0; jmod[i].opt != NULL; i++)
+                        if (strcmp(tok, jmod[i].opt) == 0) {
+                                report[3] = (report[3] & 0xF0) | jmod[i].val;
+                                break;
+                        }
+                if (jmod[i].opt != NULL)
+                        continue;
+                if (!(tok[0] == '-' && tok[1] == '-') && mvt < 3) {
+                        errno = 0;
+                        report[mvt++] = (char)strtol(tok, NULL, 0);
+                        if (errno != 0) {
+                                fprintf(stderr, "Bad value:'%s'\n", tok);
+                                report[mvt--] = 0;
+                        }
+                        continue;
+                }
+                fprintf(stderr, "unknown option: %s\n", tok);
+        }
+        return 4;
+}
+void print_options(char c)
+{
+        int i = 0;
+        if (c == 'k') {
+                printf("        keyboard options:\n"
+                       "                --hold\n");
+                for (i = 0; kmod[i].opt != NULL; i++)
+                        printf("\t\t%s\n", kmod[i].opt);
+                printf("\n      keyboard values:\n"
+                       "                [a-z] or\n");
+                for (i = 0; kval[i].opt != NULL; i++)
+                        printf("\t\t%-8s%s", kval[i].opt, i % 2 ? "\n" : "");
+                printf("\n");
+        } else if (c == 'm') {
+                printf("        mouse options:\n"
+                       "                --hold\n");
+                for (i = 0; mmod[i].opt != NULL; i++)
+                        printf("\t\t%s\n", mmod[i].opt);
+                printf("\n      mouse values:\n"
+                       "                Two signed numbers\n"
+                       "--quit to close\n");
+        } else {
+                printf("        joystick options:\n");
+                for (i = 0; jmod[i].opt != NULL; i++)
+                        printf("\t\t%s\n", jmod[i].opt);
+                printf("\n      joystick values:\n"
+                       "                three signed numbers\n"
+                       "--quit to close\n");
+        }
+}
+int main(int argc, const char *argv[])
+{
+        const char *filename = NULL;
+        int fd = 0;
+        char buf[BUF_LEN];
+        int cmd_len;
+        char report[8];
+        int to_send = 8;
+        int hold = 0;
+        fd_set rfds;
+        int retval, i;
+        if (argc < 3) {
+                fprintf(stderr, "Usage: %s devname mouse|keyboard|joystick\n",
+                        argv[0]);
+                return 1;
+        }
+        if (argv[2][0] != 'k' && argv[2][0] != 'm' && argv[2][0] != 'j')
+          return 2;
+        filename = argv[1];
+        if ((fd = open(filename, O_RDWR, 0666)) == -1) {
+                perror(filename);
+                return 3;
+        }
+        print_options(argv[2][0]);
+        while (42) {
+                FD_ZERO(&rfds);
+                FD_SET(STDIN_FILENO, &rfds);
+                FD_SET(fd, &rfds);
+                retval = select(fd + 1, &rfds, NULL, NULL, NULL);
+                if (retval == -1 && errno == EINTR)
+                        continue;
+                if (retval < 0) {
+                        perror("select()");
+                        return 4;
+                }
+                if (FD_ISSET(fd, &rfds)) {
+                        cmd_len = read(fd, buf, BUF_LEN - 1);
+                        printf("recv report:");
+                        for (i = 0; i < cmd_len; i++)
+                                printf(" %02x", buf[i]);
+                        printf("\n");
+                }
+                if (FD_ISSET(STDIN_FILENO, &rfds)) {
+                        memset(report, 0x0, sizeof(report));
+                        cmd_len = read(STDIN_FILENO, buf, BUF_LEN - 1);
+                        if (cmd_len == 0)
+                                break;
+                        buf[cmd_len - 1] = '\0';
+                        hold = 0;
+                        memset(report, 0x0, sizeof(report));
+                        if (argv[2][0] == 'k')
+                                to_send = keyboard_fill_report(report, buf, &hold);
+                        else if (argv[2][0] == 'm')
+                                to_send = mouse_fill_report(report, buf, &hold);
+                        else
+                                to_send = joystick_fill_report(report, buf, &hold);
+                        if (to_send == -1)
+                                break;
+                        if (write(fd, report, to_send) != to_send) {
+                                perror(filename);
+                                return 5;
+                        }
+                        if (!hold) {
+                                memset(report, 0x0, sizeof(report));
+                                if (write(fd, report, to_send) != to_send) {
+                                        perror(filename);
+                                        return 6;
+                                }
+                        }
+                }
+        }
+        close(fd);
+        return 0;
+}
diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt
index 3bf6818c8cf5..b29d8e56cf28 100644
--- a/Documentation/usb/power-management.txt
+++ b/Documentation/usb/power-management.txt
@@ -2,7 +2,7 @@
                 Alan Stern <stern@rowland.harvard.edu>
-                            November 10, 2009
+                            December 11, 2009
@@ -29,9 +29,9 @@ covered to some extent (see Documentation/power/*.txt for more
 information about system PM).
 Note: Dynamic PM support for USB is present only if the kernel was
-built with CONFIG_USB_SUSPEND enabled.  System PM support is present
+built with CONFIG_USB_SUSPEND enabled (which depends on
-only if the kernel was built with CONFIG_SUSPEND or CONFIG_HIBERNATION
+CONFIG_PM_RUNTIME).  System PM support is present only if the kernel
-enabled.
+was built with CONFIG_SUSPEND or CONFIG_HIBERNATION enabled.
        What is Remote Wakeup?
@@ -107,7 +107,9 @@ allowed to issue dynamic suspends.
 The user interface for controlling dynamic PM 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 are: wakeup, level, and autosuspend.
+relevant attribute files are: wakeup, control, and autosuspend.
+(There may also be a file named "level"; this file was deprecated
+as of the 2.6.35 kernel and replaced by the "control" file.)
        power/wakeup
@@ -120,7 +122,7 @@ relevant attribute files are: wakeup, level, and autosuspend.
                while the device is suspended, the change won't take
                effect until the following suspend.)
-        power/level
+        power/control
                This file contains one of two words: "on" or "auto".
                You can write those words to the file to change the
@@ -148,14 +150,15 @@ relevant attribute files are: wakeup, level, and autosuspend.
                never to autosuspend.  You can write a number to the
                file to change the autosuspend idle-delay time.
-Writing "-1" to power/autosuspend and writing "on" to power/level do
+Writing "-1" to power/autosuspend and writing "on" to power/control do
 essentially the same thing -- they both prevent the device from being
 autosuspended.  Yes, this is a redundancy in the API.
 (In 2.6.21 writing "0" to power/autosuspend would prevent the device
 from being autosuspended; the behavior was changed in 2.6.22.  The
 power/autosuspend attribute did not exist prior to 2.6.21, and the
-power/level attribute did not exist prior to 2.6.22.)
+power/level attribute did not exist prior to 2.6.22.  power/control
+was added in 2.6.34.)
        Changing the default idle-delay time
@@ -212,7 +215,7 @@ among printers and scanners, but plenty of other types of device have
 the same deficiency.
 For this reason, by default the kernel disables autosuspend (the
-power/level attribute is initialized to "on") for all devices other
+power/control attribute is initialized to "on") for all devices other
 than hubs.  Hubs, at least, appear to be reasonably well-behaved in
 this regard.
@@ -229,6 +232,11 @@ necessary operations by hand or add them to a udev script.  You can
 also change the idle-delay time; 2 seconds is not the best choice for
 every device.
+If a driver knows that its device has proper suspend/resume support,
+it can enable autosuspend all by itself.  For example, the video
+driver for a laptop's webcam might do this, since these devices are
+rarely used and so should normally be autosuspended.
 Sometimes it turns out that even when a device does work okay with
 autosuspend there are still problems.  For example, there are
 experimental patches adding autosuspend support to the usbhid driver,
@@ -321,69 +329,81 @@ driver does so by calling these six functions:
        void usb_autopm_get_interface_no_resume(struct usb_interface *intf);
        void usb_autopm_put_interface_no_suspend(struct usb_interface *intf);
-The functions work by maintaining a counter in the usb_interface
+The functions work by maintaining a usage counter in the
-structure.  When intf->pm_usage_count is > 0 then the interface is
+usb_interface's embedded device structure.  When the counter is > 0
-deemed to be busy, and the kernel will not autosuspend the interface's
+then the interface is deemed to be busy, and the kernel will not
-device.  When intf->pm_usage_count is <= 0 then the interface is
+autosuspend the interface's device.  When the usage counter is = 0
-considered to be idle, and the kernel may autosuspend the device.
+then the interface is considered to be idle, and the kernel may
+autosuspend the device.
-(There is a similar pm_usage_count field in struct usb_device,
+(There is a similar usage counter field in struct usb_device,
 associated with the device itself rather than any of its interfaces.
-This field is used only by the USB core.)
+This counter is used only by the USB core.)
-Drivers must not modify intf->pm_usage_count directly; its value
+Drivers need not be concerned about balancing changes to the usage
-should be changed only be using the functions listed above.  Drivers
+counter; the USB core will undo any remaining "get"s when a driver
-are responsible for insuring that the overall change to pm_usage_count
+is unbound from its interface.  As a corollary, drivers must not call
-during their lifetime balances out to 0 (it may be necessary for the
+any of the usb_autopm_* functions after their diconnect() routine has
-disconnect method to call usb_autopm_put_interface() one or more times
+returned.
-to fulfill this requirement).  The first two routines use the PM mutex
-in struct usb_device for mutual exclusion; drivers using the async
+Drivers using the async routines are responsible for their own
-routines are responsible for their own synchronization and mutual
+synchronization and mutual exclusion.
-exclusion.
+        usb_autopm_get_interface() increments the usage counter and
-        usb_autopm_get_interface() increments pm_usage_count and
+        does an autoresume if the device is suspended.  If the
-        attempts an autoresume if the new value is > 0 and the
+        autoresume fails, the counter is decremented back.
-        device is suspended.
+        usb_autopm_put_interface() decrements the usage counter and
-        usb_autopm_put_interface() decrements pm_usage_count and
+        attempts an autosuspend if the new value is = 0.
-        attempts an autosuspend if the new value is <= 0 and the
-        device isn't suspended.
        usb_autopm_get_interface_async() and
        usb_autopm_put_interface_async() do almost the same things as
-        their non-async counterparts.  The differences are: they do
+        their non-async counterparts.  The big difference is that they
-        not acquire the PM mutex, and they use a workqueue to do their
+        use a workqueue to do the resume or suspend part of their
        jobs.  As a result they can be called in an atomic context,
        such as an URB's completion handler, but when they return the
-        device will not generally not yet be in the desired state.
+        device will generally not yet be in the desired state.
        usb_autopm_get_interface_no_resume() and
        usb_autopm_put_interface_no_suspend() merely increment or
-        decrement the pm_usage_count value; they do not attempt to
+        decrement the usage counter; they do not attempt to carry out
-        carry out an autoresume or an autosuspend.  Hence they can be
+        an autoresume or an autosuspend.  Hence they can be called in
-        called in an atomic context.
+        an atomic context.
-The conventional usage pattern is that a driver calls
+The simplest usage pattern is that a driver calls
 usb_autopm_get_interface() in its open routine and
-usb_autopm_put_interface() in its close or release routine.  But
+usb_autopm_put_interface() in its close or release routine.  But other
-other patterns are possible.
+patterns are possible.
 The autosuspend attempts mentioned above will often fail for one
-reason or another.  For example, the power/level attribute might be
+reason or another.  For example, the power/control attribute might be
 set to "on", or another interface in the same device might not be
 idle.  This is perfectly normal.  If the reason for failure was that
-the device hasn't been idle for long enough, a delayed workqueue
+the device hasn't been idle for long enough, a timer is scheduled to
-routine is automatically set up to carry out the operation when the
+carry out the operation automatically when the autosuspend idle-delay
-autosuspend idle-delay has expired.
+has expired.
 Autoresume attempts also can fail, although failure would mean that
 the device is no longer present or operating properly.  Unlike
-autosuspend, there's no delay for an autoresume.
+autosuspend, there's no idle-delay for an autoresume.
        Other parts of the driver interface
        -----------------------------------
+Drivers can enable autosuspend for their devices by calling
+        usb_enable_autosuspend(struct usb_device *udev);
+in their probe() routine, if they know that the device is capable of
+suspending and resuming correctly.  This is exactly equivalent to
+writing "auto" to the device's power/control attribute.  Likewise,
+drivers can disable autosuspend by calling
+        usb_disable_autosuspend(struct usb_device *udev);
+This is exactly the same as writing "on" to the power/control attribute.
 Sometimes a driver needs to make sure that remote wakeup is enabled
 during autosuspend.  For example, there's not much point
 autosuspending a keyboard if the user can't cause the keyboard to do a
@@ -395,26 +415,27 @@ though, setting this flag won't cause the kernel to autoresume it.
 Normally a driver would set this flag in its probe method, at which
 time the device is guaranteed not to be autosuspended.)
-The synchronous usb_autopm_* routines have to run in a sleepable
+If a driver does its I/O asynchronously in interrupt context, it
-process context; they must not be called from an interrupt handler or
+should call usb_autopm_get_interface_async() before starting output and
-while holding a spinlock.  In fact, the entire autosuspend mechanism
+usb_autopm_put_interface_async() when the output queue drains.  When
-is not well geared toward interrupt-driven operation.  However there
+it receives an input event, it should call
-is one thing a driver can do in an interrupt handler:
        usb_mark_last_busy(struct usb_device *udev);
-This sets udev->last_busy to the current time.  udev->last_busy is the
+in the event handler.  This sets udev->last_busy to the current time.
-field used for idle-delay calculations; updating it will cause any
+udev->last_busy is the field used for idle-delay calculations;
-pending autosuspend to be moved back.  The usb_autopm_* routines will
+updating it will cause any pending autosuspend to be moved back.  Most
-also set the last_busy field to the current time.
+of the usb_autopm_* routines will also set the last_busy field to the
+current time.
-Calling urb_mark_last_busy() from within an URB completion handler is
-subject to races: The kernel may have just finished deciding the
+Asynchronous operation is always subject to races.  For example, a
-device has been idle for long enough but not yet gotten around to
+driver may call one of the usb_autopm_*_interface_async() routines at
-calling the driver's suspend method.  The driver would have to be
+a time when the core has just finished deciding the device has been
-responsible for synchronizing its suspend method with its URB
+idle for long enough but not yet gotten around to calling the driver's
-completion handler and causing the autosuspend to fail with -EBUSY if
+suspend method.  The suspend method must be responsible for
-an URB had completed too recently.
+synchronizing with the output request routine and the URB completion
+handler; it should cause autosuspends to fail with -EBUSY if the
+driver needs to use the device.
 External suspend calls should never be allowed to fail in this way,
 only autosuspend calls.  The driver can tell them apart by checking
@@ -422,75 +443,23 @@ the PM_EVENT_AUTO bit in the message.event argument to the suspend
 method; this bit will be set for internal PM events (autosuspend) and
 clear for external PM events.
-Many of the ingredients in the autosuspend framework are oriented
-towards interfaces: The usb_interface structure contains the
-pm_usage_cnt field, and the usb_autopm_* routines take an interface
-pointer as their argument.  But somewhat confusingly, a few of the
-pieces (i.e., usb_mark_last_busy()) use the usb_device structure
-instead.  Drivers need to keep this straight; they can call
-interface_to_usbdev() to find the device structure for a given
-interface.
-        Locking requirements
+        Mutual exclusion
-        --------------------
+        ----------------
-All three suspend/resume methods are always called while holding the
+For external events -- but not necessarily for autosuspend or
-usb_device's PM mutex.  For external events -- but not necessarily for
+autoresume -- the device semaphore (udev->dev.sem) will be held when a
-autosuspend or autoresume -- the device semaphore (udev->dev.sem) will
+suspend or resume method is called.  This implies that external
-also be held.  This implies that external suspend/resume events are
+suspend/resume events are mutually exclusive with calls to probe,
-mutually exclusive with calls to probe, disconnect, pre_reset, and
+disconnect, pre_reset, and post_reset; the USB core guarantees that
-post_reset; the USB core guarantees that this is true of internal
+this is true of autosuspend/autoresume events as well.
-suspend/resume events as well.
 If a driver wants to block all suspend/resume calls during some
-critical section, it can simply acquire udev->pm_mutex. Note that
+critical section, the best way is to lock the device and call
-calls to resume may be triggered indirectly. Block IO due to memory
+usb_autopm_get_interface() (and do the reverse at the end of the
-allocations can make the vm subsystem resume a device. Thus while
+critical section).  Holding the device semaphore will block all
-holding this lock you must not allocate memory with GFP_KERNEL or
+external PM calls, and the usb_autopm_get_interface() will prevent any
-GFP_NOFS.
+internal PM calls, even if it fails.  (Exercise: Why?)
-Alternatively, if the critical section might call some of the
-usb_autopm_* routines, the driver can avoid deadlock by doing:
-        down(&udev->dev.sem);
-        rc = usb_autopm_get_interface(intf);
-and at the end of the critical section:
-        if (!rc)
-                usb_autopm_put_interface(intf);
-        up(&udev->dev.sem);
-Holding the device semaphore will block all external PM calls, and the
-usb_autopm_get_interface() will prevent any internal PM calls, even if
-it fails.  (Exercise: Why?)
-The rules for locking order are:
-        Never acquire any device semaphore while holding any PM mutex.
-        Never acquire udev->pm_mutex while holding the PM mutex for
-        a device that isn't a descendant of udev.
-In other words, PM mutexes should only be acquired going up the device
-tree, and they should be acquired only after locking all the device
-semaphores you need to hold.  These rules don't matter to drivers very
-much; they usually affect just the USB core.
-Still, drivers do need to be careful.  For example, many drivers use a
-private mutex to synchronize their normal I/O activities with their
-disconnect method.  Now if the driver supports autosuspend then it
-must call usb_autopm_put_interface() from somewhere -- maybe from its
-close method.  It should make the call while holding the private mutex,
-since a driver shouldn't call any of the usb_autopm_* functions for an
-interface from which it has been unbound.
-But the usb_autpm_* routines always acquire the device's PM mutex, and
-consequently the locking order has to be: private mutex first, PM
-mutex second.  Since the suspend method is always called with the PM
-mutex held, it mustn't try to acquire the private mutex.  It has to
-synchronize with the driver's I/O activities in some other way.
        Interaction between dynamic PM and system PM
@@ -499,22 +468,11 @@ synchronize with the driver's I/O activities in some other way.
 Dynamic power management and system power management can interact in
 a couple of ways.
-Firstly, a device may already be manually suspended or autosuspended
+Firstly, a device may already be autosuspended when a system suspend
-when a system suspend occurs.  Since system suspends are supposed to
+occurs.  Since system suspends are supposed to be as transparent as
-be as transparent as possible, the device should remain suspended
+possible, the device should remain suspended following the system
-following the system resume.  The 2.6.23 kernel obeys this principle
+resume.  But this theory may not work out well in practice; over time
-for manually suspended devices but not for autosuspended devices; they
+the kernel's behavior in this regard has changed.
-do get resumed when the system wakes up.  (Presumably they will be
-autosuspended again after their idle-delay time expires.)  In later
-kernels this behavior will be fixed.
-(There is an exception.  If a device would undergo a reset-resume
-instead of a normal resume, and the device is enabled for remote
-wakeup, then the reset-resume takes place even if the device was
-already suspended when the system suspend began.  The justification is
-that a reset-resume is a kind of remote-wakeup event.  Or to put it
-another way, a device which needs a reset won't be able to generate
-normal remote-wakeup signals, so it ought to be resumed immediately.)
 Secondly, a dynamic power-management event may occur as a system
 suspend is underway.  The window for this is short, since system
diff --git a/Documentation/usb/usb-serial.txt b/Documentation/usb/usb-serial.txt
index ff2c1ff57ba2..f4d214510259 100644
--- a/Documentation/usb/usb-serial.txt
+++ b/Documentation/usb/usb-serial.txt
@@ -194,6 +194,10 @@ FTDI Single Port Serial Driver
  This is a single port DB-25 serial adapter.
+  Devices supported include:
+                -TripNav TN-200 USB GPS
+                -Navis Engineering Bureau CH-4711 USB GPS
  For any questions or problems with this driver, please contact Bill Ryder.
@@ -216,7 +220,7 @@ Cypress M8 CY4601 Family Serial Driver
    Devices supported:
-                -DeLorme's USB Earthmate (SiRF Star II lp arch)
+                -DeLorme's USB Earthmate GPS (SiRF Star II lp arch)
                -Cypress HID->COM RS232 adapter
        
                Note: Cypress Semiconductor claims no affiliation with the
@@ -392,9 +396,10 @@ REINER SCT cyberJack pinpad/e-com USB chipcard reader
 Prolific PL2303 Driver
  This driver supports any device that has the PL2303 chip from Prolific
-  in it.  This includes a number of single port USB to serial
+  in it.  This includes a number of single port USB to serial converters,
-  converters and USB GPS devices.  Devices from Aten (the UC-232) and
+  more than 70% of USB GPS devices (in 2010), and some USB UPSes. Devices
-  IO-Data work with this driver, as does the DCU-11 mobile-phone cable.
+  from Aten (the UC-232) and IO-Data work with this driver, as does
+  the DCU-11 mobile-phone cable.
  For any questions or problems with this driver, please contact Greg
  Kroah-Hartman at greg@kroah.com
@@ -435,6 +440,22 @@ Winchiphead CH341 Driver
  For any questions or problems with this driver, please contact
  frank@kingswood-consulting.co.uk.
+Moschip MCS7720, MCS7715 driver
+  These chips are present in devices sold by various manufacturers, such as Syba
+  and Cables Unlimited.  There may be others.  The 7720 provides two serial
+  ports, and the 7715 provides one serial and one standard PC parallel port.
+  Support for the 7715's parallel port is enabled by a separate option, which
+  will not appear unless parallel port support is first enabled at the top-level
+  of the Device Drivers config menu.  Currently only compatibility mode is
+  supported on the parallel port (no ECP/EPP).
+  TODO:
+    - Implement ECP/EPP modes for the parallel port.
+    - Baud rates higher than 115200 are currently broken.
+    - Devices with a single serial port based on the Moschip MCS7703 may work
+      with this driver with a simple addition to the usb_device_id table.  I
+      don't have one of these devices, so I can't say for sure.
 Generic Serial driver
diff --git a/Documentation/video4linux/CARDLIST.bttv b/Documentation/video4linux/CARDLIST.bttv
index f11c583295e9..4739d5684305 100644
--- a/Documentation/video4linux/CARDLIST.bttv
+++ b/Documentation/video4linux/CARDLIST.bttv
@@ -100,7 +100,7 @@
 99 -> AD-TVK503
 100 -> Hercules Smart TV Stereo
 101 -> Pace TV & Radio Card
-102 -> IVC-200                                             [0000:a155,0001:a155,0002:a155,0003:a155,0100:a155,0101:a155,0102:a155,0103:a155]
+102 -> IVC-200                                             [0000:a155,0001:a155,0002:a155,0003:a155,0100:a155,0101:a155,0102:a155,0103:a155,0800:a155,0801:a155,0802:a155,0803:a155]
 103 -> Grand X-Guard / Trust 814PCI                        [0304:0102]
 104 -> Nebula Electronics DigiTV                           [0071:0101]
 105 -> ProVideo PV143                                      [aa00:1430,aa00:1431,aa00:1432,aa00:1433,aa03:1433]
diff --git a/Documentation/video4linux/CARDLIST.cx23885 b/Documentation/video4linux/CARDLIST.cx23885
index 7539e8fa1ffd..16ca030e1185 100644
--- a/Documentation/video4linux/CARDLIST.cx23885
+++ b/Documentation/video4linux/CARDLIST.cx23885
@@ -26,3 +26,4 @@
 25 -> Compro VideoMate E800                               [1858:e800]
 26 -> Hauppauge WinTV-HVR1290                             [0070:8551]
 27 -> Mygica X8558 PRO DMB-TH                             [14f1:8578]
+ 28 -> LEADTEK WinFast PxTV1200                            [107d:6f22]
diff --git a/Documentation/video4linux/CARDLIST.cx88 b/Documentation/video4linux/CARDLIST.cx88
index 7ec3c4e4b60f..f2510541373b 100644
--- a/Documentation/video4linux/CARDLIST.cx88
+++ b/Documentation/video4linux/CARDLIST.cx88
@@ -82,3 +82,4 @@
 81 -> Leadtek WinFast DTV1800 Hybrid                      [107d:6654]
 82 -> WinFast DTV2000 H rev. J                            [107d:6f2b]
 83 -> Prof 7301 DVB-S/S2                                  [b034:3034]
+ 84 -> Samsung SMT 7020 DVB-S                              [18ac:dc00,18ac:dccd]
diff --git a/Documentation/video4linux/CARDLIST.em28xx b/Documentation/video4linux/CARDLIST.em28xx
index 0c166ff003a0..3a623aaeae5f 100644
--- a/Documentation/video4linux/CARDLIST.em28xx
+++ b/Documentation/video4linux/CARDLIST.em28xx
@@ -1,5 +1,5 @@
  0 -> Unknown EM2800 video grabber             (em2800)        [eb1a:2800]
-  1 -> Unknown EM2750/28xx video grabber        (em2820/em2840) [eb1a:2710,eb1a:2820,eb1a:2821,eb1a:2860,eb1a:2861,eb1a:2862,eb1a:2870,eb1a:2881,eb1a:2883,eb1a:2868]
+  1 -> Unknown EM2750/28xx video grabber        (em2820/em2840) [eb1a:2710,eb1a:2820,eb1a:2821,eb1a:2860,eb1a:2861,eb1a:2862,eb1a:2863,eb1a:2870,eb1a:2881,eb1a:2883,eb1a:2868]
  2 -> Terratec Cinergy 250 USB                 (em2820/em2840) [0ccd:0036]
  3 -> Pinnacle PCTV USB 2                      (em2820/em2840) [2304:0208]
  4 -> Hauppauge WinTV USB 2                    (em2820/em2840) [2040:4200,2040:4201]
@@ -27,6 +27,7 @@
 26 -> Hercules Smart TV USB 2.0                (em2820/em2840)
 27 -> Pinnacle PCTV USB 2 (Philips FM1216ME)   (em2820/em2840)
 28 -> Leadtek Winfast USB II Deluxe            (em2820/em2840)
+ 29 -> EM2860/TVP5150 Reference Design          (em2860)
 30 -> Videology 20K14XUSB USB2.0               (em2820/em2840)
 31 -> Usbgear VD204v9                          (em2821)
 32 -> Supercomp USB 2.0 TV                     (em2821)
@@ -70,3 +71,4 @@
 72 -> Gadmei UTV330+                           (em2861)
 73 -> Reddo DVB-C USB TV Box                   (em2870)
 74 -> Actionmaster/LinXcel/Digitus VC211A      (em2800)
+ 75 -> Dikom DK300                              (em2882)
diff --git a/Documentation/video4linux/CARDLIST.saa7134 b/Documentation/video4linux/CARDLIST.saa7134
index fce1e7eb0474..070f2576707e 100644
--- a/Documentation/video4linux/CARDLIST.saa7134
+++ b/Documentation/video4linux/CARDLIST.saa7134
@@ -174,3 +174,7 @@
 173 -> Zolid Hybrid TV Tuner PCI                [1131:2004]
 174 -> Asus Europa Hybrid OEM                   [1043:4847]
 175 -> Leadtek Winfast DTV1000S                 [107d:6655]
+176 -> Beholder BeholdTV 505 RDS                [0000:5051]
+177 -> Hawell HW-404M7
+179 -> Beholder BeholdTV H7                     [5ace:7190]
+180 -> Beholder BeholdTV A7                     [5ace:7090]
diff --git a/Documentation/video4linux/CARDLIST.tuner b/Documentation/video4linux/CARDLIST.tuner
index e0d298fe8830..9b2e0dd6017e 100644
--- a/Documentation/video4linux/CARDLIST.tuner
+++ b/Documentation/video4linux/CARDLIST.tuner
@@ -81,3 +81,4 @@ tuner=80 - Philips FQ1216LME MK3 PAL/SECAM w/active loopthrough
 tuner=81 - Partsnic (Daewoo) PTI-5NF05
 tuner=82 - Philips CU1216L
 tuner=83 - NXP TDA18271
+tuner=84 - Sony BTF-Pxn01Z
diff --git a/Documentation/video4linux/README.tlg2300 b/Documentation/video4linux/README.tlg2300
new file mode 100644
index 000000000000..416ccb93d8c9
--- /dev/null
+++ b/Documentation/video4linux/README.tlg2300
@@ -0,0 +1,47 @@
+tlg2300 release notes
+====================
+This is a v4l2/dvb device driver for the tlg2300 chip.
+current status
+==============
+video
+        - support mmap and read().(no overlay)
+audio
+        - The driver will register a ALSA card for the audio input.
+vbi
+        - Works for almost TV norms.
+dvb-t
+        - works for DVB-T
+FM
+        - Works for radio.
+---------------------------------------------------------------------------
+TESTED APPLICATIONS:
+-VLC1.0.4 test the video and dvb. The GUI is friendly to use.
+-Mplayer test the video.
+-Mplayer test the FM. The mplayer should be compiled with --enable-radio and
+         --enable-radio-capture.
+        The command runs as this(The alsa audio registers to card 1):
+        #mplayer radio://103.7/capture/ -radio adevice=hw=1,0:arate=48000 \
+                -rawaudio rate=48000:channels=2
+---------------------------------------------------------------------------
+KNOWN PROBLEMS:
+about preemphasis:
+        You can set the preemphasis for radio by the following command:
+        #v4l2-ctl -d /dev/radio0 --set-ctrl=pre_emphasis_settings=1
+        "pre_emphasis_settings=1" means that you select the 50us. If you want
+        to select the 75us, please use "pre_emphasis_settings=2"
diff --git a/Documentation/video4linux/extract_xc3028.pl b/Documentation/video4linux/extract_xc3028.pl
index 2cb816047fc1..47877deae6d7 100644
--- a/Documentation/video4linux/extract_xc3028.pl
+++ b/Documentation/video4linux/extract_xc3028.pl
@@ -5,12 +5,18 @@
 #
 # In order to use, you need to:
 #       1) Download the windows driver with something like:
+#       Version 2.4
+#               wget http://www.twinhan.com/files/AW/BDA T/20080303_V1.0.6.7.zip
+#               or wget http://www.stefanringel.de/pub/20080303_V1.0.6.7.zip
+#       Version 2.7
 #               wget http://www.steventoth.net/linux/xc5000/HVR-12x0-14x0-17x0_1_25_25271_WHQL.zip
-#       2) Extract the file hcw85bda.sys from the zip into the current dir:
+#       2) Extract the files from the zip into the current dir:
+#               unzip -j 20080303_V1.0.6.7.zip 20080303_v1.0.6.7/UDXTTM6000.sys
 #               unzip -j HVR-12x0-14x0-17x0_1_25_25271_WHQL.zip Driver85/hcw85bda.sys
 #       3) run the script:
 #               ./extract_xc3028.pl
-#       4) copy the generated file:
+#       4) copy the generated files:
+#               cp xc3028-v24.fw /lib/firmware
 #               cp xc3028-v27.fw /lib/firmware
 #use strict;
@@ -135,7 +141,7 @@ sub write_hunk_fix_endian($$)
        }
 }
-sub main_firmware($$$$)
+sub main_firmware_24($$$$)
 {
        my $out;
        my $j=0;
@@ -146,8 +152,774 @@ sub main_firmware($$$$)
        for ($j = length($name); $j <32; $j++) {
                $name = $name.chr(0);
+        }
+        open OUTFILE, ">$outfile";
+        syswrite(OUTFILE, $name);
+        write_le16($version);
+        write_le16($nr_desc);
+        #
+        # Firmware 0, type: BASE FW   F8MHZ (0x00000003), id: (0000000000000000), size: 6635
+        #
+        write_le32(0x00000003);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(6635);                       # Size
+        write_hunk_fix_endian(257752, 6635);
+        #
+        # Firmware 1, type: BASE FW   F8MHZ MTS (0x00000007), id: (0000000000000000), size: 6635
+        #
+        write_le32(0x00000007);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(6635);                       # Size
+        write_hunk_fix_endian(264392, 6635);
+        #
+        # Firmware 2, type: BASE FW   FM (0x00000401), id: (0000000000000000), size: 6525
+        #
+        write_le32(0x00000401);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(6525);                       # Size
+        write_hunk_fix_endian(271040, 6525);
+        #
+        # Firmware 3, type: BASE FW   FM INPUT1 (0x00000c01), id: (0000000000000000), size: 6539
+        #
+        write_le32(0x00000c01);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(6539);                       # Size
+        write_hunk_fix_endian(277568, 6539);
+        #
+        # Firmware 4, type: BASE FW   (0x00000001), id: (0000000000000000), size: 6633
+        #
+        write_le32(0x00000001);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(6633);                       # Size
+        write_hunk_fix_endian(284120, 6633);
+        #
+        # Firmware 5, type: BASE FW   MTS (0x00000005), id: (0000000000000000), size: 6617
+        #
+        write_le32(0x00000005);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(6617);                       # Size
+        write_hunk_fix_endian(290760, 6617);
+        #
+        # Firmware 6, type: STD FW    (0x00000000), id: PAL/BG A2/A (0000000100000007), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x00000001, 0x00000007);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(297384, 161);
+        #
+        # Firmware 7, type: STD FW    MTS (0x00000004), id: PAL/BG A2/A (0000000100000007), size: 169
+        #
+        write_le32(0x00000004);                 # Type
+        write_le64(0x00000001, 0x00000007);     # ID
+        write_le32(169);                        # Size
+        write_hunk_fix_endian(297552, 169);
+        #
+        # Firmware 8, type: STD FW    (0x00000000), id: PAL/BG A2/B (0000000200000007), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x00000002, 0x00000007);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(297728, 161);
+        #
+        # Firmware 9, type: STD FW    MTS (0x00000004), id: PAL/BG A2/B (0000000200000007), size: 169
+        #
+        write_le32(0x00000004);                 # Type
+        write_le64(0x00000002, 0x00000007);     # ID
+        write_le32(169);                        # Size
+        write_hunk_fix_endian(297896, 169);
+        #
+        # Firmware 10, type: STD FW    (0x00000000), id: PAL/BG NICAM/A (0000000400000007), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x00000004, 0x00000007);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(298072, 161);
+        #
+        # Firmware 11, type: STD FW    MTS (0x00000004), id: PAL/BG NICAM/A (0000000400000007), size: 169
+        #
+        write_le32(0x00000004);                 # Type
+        write_le64(0x00000004, 0x00000007);     # ID
+        write_le32(169);                        # Size
+        write_hunk_fix_endian(298240, 169);
+        #
+        # Firmware 12, type: STD FW    (0x00000000), id: PAL/BG NICAM/B (0000000800000007), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x00000008, 0x00000007);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(298416, 161);
+        #
+        # Firmware 13, type: STD FW    MTS (0x00000004), id: PAL/BG NICAM/B (0000000800000007), size: 169
+        #
+        write_le32(0x00000004);                 # Type
+        write_le64(0x00000008, 0x00000007);     # ID
+        write_le32(169);                        # Size
+        write_hunk_fix_endian(298584, 169);
+        #
+        # Firmware 14, type: STD FW    (0x00000000), id: PAL/DK A2 (00000003000000e0), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x00000003, 0x000000e0);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(298760, 161);
+        #
+        # Firmware 15, type: STD FW    MTS (0x00000004), id: PAL/DK A2 (00000003000000e0), size: 169
+        #
+        write_le32(0x00000004);                 # Type
+        write_le64(0x00000003, 0x000000e0);     # ID
+        write_le32(169);                        # Size
+        write_hunk_fix_endian(298928, 169);
+        #
+        # Firmware 16, type: STD FW    (0x00000000), id: PAL/DK NICAM (0000000c000000e0), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x0000000c, 0x000000e0);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(299104, 161);
+        #
+        # Firmware 17, type: STD FW    MTS (0x00000004), id: PAL/DK NICAM (0000000c000000e0), size: 169
+        #
+        write_le32(0x00000004);                 # Type
+        write_le64(0x0000000c, 0x000000e0);     # ID
+        write_le32(169);                        # Size
+        write_hunk_fix_endian(299272, 169);
+        #
+        # Firmware 18, type: STD FW    (0x00000000), id: SECAM/K1 (0000000000200000), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x00000000, 0x00200000);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(299448, 161);
+        #
+        # Firmware 19, type: STD FW    MTS (0x00000004), id: SECAM/K1 (0000000000200000), size: 169
+        #
+        write_le32(0x00000004);                 # Type
+        write_le64(0x00000000, 0x00200000);     # ID
+        write_le32(169);                        # Size
+        write_hunk_fix_endian(299616, 169);
+        #
+        # Firmware 20, type: STD FW    (0x00000000), id: SECAM/K3 (0000000004000000), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x00000000, 0x04000000);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(299792, 161);
+        #
+        # Firmware 21, type: STD FW    MTS (0x00000004), id: SECAM/K3 (0000000004000000), size: 169
+        #
+        write_le32(0x00000004);                 # Type
+        write_le64(0x00000000, 0x04000000);     # ID
+        write_le32(169);                        # Size
+        write_hunk_fix_endian(299960, 169);
+        #
+        # Firmware 22, type: STD FW    D2633 DTV6 ATSC (0x00010030), id: (0000000000000000), size: 149
+        #
+        write_le32(0x00010030);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(149);                        # Size
+        write_hunk_fix_endian(300136, 149);
+        #
+        # Firmware 23, type: STD FW    D2620 DTV6 QAM (0x00000068), id: (0000000000000000), size: 149
+        #
+        write_le32(0x00000068);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(149);                        # Size
+        write_hunk_fix_endian(300296, 149);
+        #
+        # Firmware 24, type: STD FW    D2633 DTV6 QAM (0x00000070), id: (0000000000000000), size: 149
+        #
+        write_le32(0x00000070);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(149);                        # Size
+        write_hunk_fix_endian(300448, 149);
+        #
+        # Firmware 25, type: STD FW    D2620 DTV7 (0x00000088), id: (0000000000000000), size: 149
+        #
+        write_le32(0x00000088);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(149);                        # Size
+        write_hunk_fix_endian(300608, 149);
+        #
+        # Firmware 26, type: STD FW    D2633 DTV7 (0x00000090), id: (0000000000000000), size: 149
+        #
+        write_le32(0x00000090);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(149);                        # Size
+        write_hunk_fix_endian(300760, 149);
+        #
+        # Firmware 27, type: STD FW    D2620 DTV78 (0x00000108), id: (0000000000000000), size: 149
+        #
+        write_le32(0x00000108);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(149);                        # Size
+        write_hunk_fix_endian(300920, 149);
+        #
+        # Firmware 28, type: STD FW    D2633 DTV78 (0x00000110), id: (0000000000000000), size: 149
+        #
+        write_le32(0x00000110);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(149);                        # Size
+        write_hunk_fix_endian(301072, 149);
+        #
+        # Firmware 29, type: STD FW    D2620 DTV8 (0x00000208), id: (0000000000000000), size: 149
+        #
+        write_le32(0x00000208);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(149);                        # Size
+        write_hunk_fix_endian(301232, 149);
+        #
+        # Firmware 30, type: STD FW    D2633 DTV8 (0x00000210), id: (0000000000000000), size: 149
+        #
+        write_le32(0x00000210);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(149);                        # Size
+        write_hunk_fix_endian(301384, 149);
+        #
+        # Firmware 31, type: STD FW    FM (0x00000400), id: (0000000000000000), size: 135
+        #
+        write_le32(0x00000400);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le32(135);                        # Size
+        write_hunk_fix_endian(301554, 135);
+        #
+        # Firmware 32, type: STD FW    (0x00000000), id: PAL/I (0000000000000010), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x00000000, 0x00000010);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(301688, 161);
+        #
+        # Firmware 33, type: STD FW    MTS (0x00000004), id: PAL/I (0000000000000010), size: 169
+        #
+        write_le32(0x00000004);                 # Type
+        write_le64(0x00000000, 0x00000010);     # ID
+        write_le32(169);                        # Size
+        write_hunk_fix_endian(301856, 169);
+        #
+        # Firmware 34, type: STD FW    (0x00000000), id: SECAM/L AM (0000001000400000), size: 169
+        #
+        #
+        # Firmware 35, type: STD FW    (0x00000000), id: SECAM/L NICAM (0000000c00400000), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x0000000c, 0x00400000);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(302032, 161);
+        #
+        # Firmware 36, type: STD FW    (0x00000000), id: SECAM/Lc (0000000000800000), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x00000000, 0x00800000);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(302200, 161);
+        #
+        # Firmware 37, type: STD FW    (0x00000000), id: NTSC/M Kr (0000000000008000), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x00000000, 0x00008000);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(302368, 161);
+        #
+        # Firmware 38, type: STD FW    LCD (0x00001000), id: NTSC/M Kr (0000000000008000), size: 161
+        #
+        write_le32(0x00001000);                 # Type
+        write_le64(0x00000000, 0x00008000);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(302536, 161);
+        #
+        # Firmware 39, type: STD FW    LCD NOGD (0x00003000), id: NTSC/M Kr (0000000000008000), size: 161
+        #
+        write_le32(0x00003000);                 # Type
+        write_le64(0x00000000, 0x00008000);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(302704, 161);
+        #
+        # Firmware 40, type: STD FW    MTS (0x00000004), id: NTSC/M Kr (0000000000008000), size: 169
+        #
+        write_le32(0x00000004);                 # Type
+        write_le64(0x00000000, 0x00008000);     # ID
+        write_le32(169);                        # Size
+        write_hunk_fix_endian(302872, 169);
+        #
+        # Firmware 41, type: STD FW    (0x00000000), id: NTSC PAL/M PAL/N (000000000000b700), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x00000000, 0x0000b700);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(303048, 161);
+        #
+        # Firmware 42, type: STD FW    LCD (0x00001000), id: NTSC PAL/M PAL/N (000000000000b700), size: 161
+        #
+        write_le32(0x00001000);                 # Type
+        write_le64(0x00000000, 0x0000b700);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(303216, 161);
+        #
+        # Firmware 43, type: STD FW    LCD NOGD (0x00003000), id: NTSC PAL/M PAL/N (000000000000b700), size: 161
+        #
+        write_le32(0x00003000);                 # Type
+        write_le64(0x00000000, 0x0000b700);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(303384, 161);
+        #
+        # Firmware 44, type: STD FW    (0x00000000), id: NTSC/M Jp (0000000000002000), size: 161
+        #
+        write_le32(0x00000000);                 # Type
+        write_le64(0x00000000, 0x00002000);     # ID
+        write_le32(161);                        # Size
+        write_hunk_fix_endian(303552, 161);
+        #
+        # Firmware 45, type: STD FW    MTS (0x00000004), id: NTSC PAL/M PAL/N (000000000000b700), size: 169
+        #
+        write_le32(0x00000004);                 # Type
+        write_le64(0x00000000, 0x0000b700);     # ID
+        write_le32(169);                        # Size
+        write_hunk_fix_endian(303720, 169);
+        #
+        # Firmware 46, type: STD FW    MTS LCD (0x00001004), id: NTSC PAL/M PAL/N (000000000000b700), size: 169
+        #
+        write_le32(0x00001004);                 # Type
+        write_le64(0x00000000, 0x0000b700);     # ID
+        write_le32(169);                        # Size
+        write_hunk_fix_endian(303896, 169);
+        #
+        # Firmware 47, type: STD FW    MTS LCD NOGD (0x00003004), id: NTSC PAL/M PAL/N (000000000000b700), size: 169
+        #
+        write_le32(0x00003004);                 # Type
+        write_le64(0x00000000, 0x0000b700);     # ID
+        write_le32(169);                        # Size
+        write_hunk_fix_endian(304072, 169);
+        #
+        # Firmware 48, type: SCODE FW  HAS IF (0x60000000), IF = 3.28 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(3280);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(309048, 192);
+        #
+        # Firmware 49, type: SCODE FW  HAS IF (0x60000000), IF = 3.30 MHz id: (0000000000000000), size: 192
+        #
+#       write_le32(0x60000000);                 # Type
+#       write_le64(0x00000000, 0x00000000);     # ID
+#       write_le16(3300);                       # IF
+#       write_le32(192);                        # Size
+#       write_hunk(304440, 192);
+        #
+        # Firmware 50, type: SCODE FW  HAS IF (0x60000000), IF = 3.44 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(3440);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(309432, 192);
+        #
+        # Firmware 51, type: SCODE FW  HAS IF (0x60000000), IF = 3.46 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(3460);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(309624, 192);
+        #
+        # Firmware 52, type: SCODE FW  DTV6 ATSC OREN36 HAS IF (0x60210020), IF = 3.80 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60210020);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(3800);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(306936, 192);
+        #
+        # Firmware 53, type: SCODE FW  HAS IF (0x60000000), IF = 4.00 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(4000);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(309240, 192);
+        #
+        # Firmware 54, type: SCODE FW  DTV6 ATSC TOYOTA388 HAS IF (0x60410020), IF = 4.08 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60410020);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(4080);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(307128, 192);
+        #
+        # Firmware 55, type: SCODE FW  HAS IF (0x60000000), IF = 4.20 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(4200);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(308856, 192);
+        #
+        # Firmware 56, type: SCODE FW  MONO HAS IF (0x60008000), IF = 4.32 MHz id: NTSC/M Kr (0000000000008000), size: 192
+        #
+        write_le32(0x60008000);                 # Type
+        write_le64(0x00000000, 0x00008000);     # ID
+        write_le16(4320);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(305208, 192);
+        #
+        # Firmware 57, type: SCODE FW  HAS IF (0x60000000), IF = 4.45 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(4450);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(309816, 192);
+        #
+        # Firmware 58, type: SCODE FW  MTS LCD NOGD MONO IF HAS IF (0x6002b004), IF = 4.50 MHz id: NTSC PAL/M PAL/N (000000000000b700), size: 192
+        #
+        write_le32(0x6002b004);                 # Type
+        write_le64(0x00000000, 0x0000b700);     # ID
+        write_le16(4500);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(304824, 192);
+        #
+        # Firmware 59, type: SCODE FW  LCD NOGD IF HAS IF (0x60023000), IF = 4.60 MHz id: NTSC/M Kr (0000000000008000), size: 192
+        #
+        write_le32(0x60023000);                 # Type
+        write_le64(0x00000000, 0x00008000);     # ID
+        write_le16(4600);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(305016, 192);
+        #
+        # Firmware 60, type: SCODE FW  DTV6 QAM DTV7 DTV78 DTV8 ZARLINK456 HAS IF (0x620003e0), IF = 4.76 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x620003e0);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(4760);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(304440, 192);
+        #
+        # Firmware 61, type: SCODE FW  HAS IF (0x60000000), IF = 4.94 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(4940);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(308664, 192);
+        #
+        # Firmware 62, type: SCODE FW  HAS IF (0x60000000), IF = 5.26 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(5260);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(307704, 192);
+        #
+        # Firmware 63, type: SCODE FW  MONO HAS IF (0x60008000), IF = 5.32 MHz id: PAL/BG A2 NICAM (0000000f00000007), size: 192
+        #
+        write_le32(0x60008000);                 # Type
+        write_le64(0x0000000f, 0x00000007);     # ID
+        write_le16(5320);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(307896, 192);
+        #
+        # Firmware 64, type: SCODE FW  DTV7 DTV78 DTV8 DIBCOM52 CHINA HAS IF (0x65000380), IF = 5.40 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x65000380);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(5400);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(304248, 192);
+        #
+        # Firmware 65, type: SCODE FW  DTV6 ATSC OREN538 HAS IF (0x60110020), IF = 5.58 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60110020);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(5580);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(306744, 192);
+        #
+        # Firmware 66, type: SCODE FW  HAS IF (0x60000000), IF = 5.64 MHz id: PAL/BG A2 (0000000300000007), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x00000003, 0x00000007);     # ID
+        write_le16(5640);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(305592, 192);
+        #
+        # Firmware 67, type: SCODE FW  HAS IF (0x60000000), IF = 5.74 MHz id: PAL/BG NICAM (0000000c00000007), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x0000000c, 0x00000007);     # ID
+        write_le16(5740);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(305784, 192);
+        #
+        # Firmware 68, type: SCODE FW  HAS IF (0x60000000), IF = 5.90 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(5900);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(307512, 192);
+        #
+        # Firmware 69, type: SCODE FW  MONO HAS IF (0x60008000), IF = 6.00 MHz id: PAL/DK PAL/I SECAM/K3 SECAM/L SECAM/Lc NICAM (0000000c04c000f0), size: 192
+        #
+        write_le32(0x60008000);                 # Type
+        write_le64(0x0000000c, 0x04c000f0);     # ID
+        write_le16(6000);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(305576, 192);
+        #
+        # Firmware 70, type: SCODE FW  DTV6 QAM ATSC LG60 F6MHZ HAS IF (0x68050060), IF = 6.20 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x68050060);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(6200);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(306552, 192);
+        #
+        # Firmware 71, type: SCODE FW  HAS IF (0x60000000), IF = 6.24 MHz id: PAL/I (0000000000000010), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x00000000, 0x00000010);     # ID
+        write_le16(6240);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(305400, 192);
+        #
+        # Firmware 72, type: SCODE FW  MONO HAS IF (0x60008000), IF = 6.32 MHz id: SECAM/K1 (0000000000200000), size: 192
+        #
+        write_le32(0x60008000);                 # Type
+        write_le64(0x00000000, 0x00200000);     # ID
+        write_le16(6320);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(308472, 192);
+        #
+        # Firmware 73, type: SCODE FW  HAS IF (0x60000000), IF = 6.34 MHz id: SECAM/K1 (0000000000200000), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x00000000, 0x00200000);     # ID
+        write_le16(6340);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(306360, 192);
+        #
+        # Firmware 74, type: SCODE FW  MONO HAS IF (0x60008000), IF = 6.50 MHz id: PAL/DK SECAM/K3 SECAM/L NICAM (0000000c044000e0), size: 192
+        #
+        write_le32(0x60008000);                 # Type
+        write_le64(0x0000000c, 0x044000e0);     # ID
+        write_le16(6500);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(308280, 192);
+        #
+        # Firmware 75, type: SCODE FW  DTV6 ATSC ATI638 HAS IF (0x60090020), IF = 6.58 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60090020);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(6580);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(304632, 192);
+        #
+        # Firmware 76, type: SCODE FW  HAS IF (0x60000000), IF = 6.60 MHz id: PAL/DK A2 (00000003000000e0), size: 192
+        #
+        write_le32(0x60000000);                 # Type
+        write_le64(0x00000003, 0x000000e0);     # ID
+        write_le16(6600);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(306168, 192);
+        #
+        # Firmware 77, type: SCODE FW  MONO HAS IF (0x60008000), IF = 6.68 MHz id: PAL/DK A2 (00000003000000e0), size: 192
+        #
+        write_le32(0x60008000);                 # Type
+        write_le64(0x00000003, 0x000000e0);     # ID
+        write_le16(6680);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(308088, 192);
+        #
+        # Firmware 78, type: SCODE FW  DTV6 ATSC TOYOTA794 HAS IF (0x60810020), IF = 8.14 MHz id: (0000000000000000), size: 192
+        #
+        write_le32(0x60810020);                 # Type
+        write_le64(0x00000000, 0x00000000);     # ID
+        write_le16(8140);                       # IF
+        write_le32(192);                        # Size
+        write_hunk(307320, 192);
+        #
+        # Firmware 79, type: SCODE FW  HAS IF (0x60000000), IF = 8.20 MHz id: (0000000000000000), size: 192
+        #
+#       write_le32(0x60000000);                 # Type
+#       write_le64(0x00000000, 0x00000000);     # ID
+#       write_le16(8200);                       # IF
+#       write_le32(192);                        # Size
+#       write_hunk(308088, 192);
 }
+sub main_firmware_27($$$$)
+{
+        my $out;
+        my $j=0;
+        my $outfile = shift;
+        my $name    = shift;
+        my $version = shift;
+        my $nr_desc = shift;
+        for ($j = length($name); $j <32; $j++) {
+                $name = $name.chr(0);
+        }
        open OUTFILE, ">$outfile";
        syswrite(OUTFILE, $name);
        write_le16($version);
@@ -906,20 +1678,39 @@ sub main_firmware($$$$)
        write_hunk(812856, 192);
 }
 sub extract_firmware {
-        my $sourcefile = "hcw85bda.sys";
+        my $sourcefile_24 = "UDXTTM6000.sys";
-        my $hash = "0e44dbf63bb0169d57446aec21881ff2";
+        my $hash_24 = "cb9deb5508a5e150af2880f5b0066d78";
-        my $outfile = "xc3028-v27.fw";
+        my $outfile_24 = "xc3028-v24.fw";
-        my $name = "xc2028 firmware";
+        my $name_24 = "xc2028 firmware";
-        my $version = 519;
+        my $version_24 = 516;
-        my $nr_desc = 80;
+        my $nr_desc_24 = 77;
+        my $out;
+        my $sourcefile_27 = "hcw85bda.sys";
+        my $hash_27 = "0e44dbf63bb0169d57446aec21881ff2";
+        my $outfile_27 = "xc3028-v27.fw";
+        my $name_27 = "xc2028 firmware";
+        my $version_27 = 519;
+        my $nr_desc_27 = 80;
        my $out;
-        verify($sourcefile, $hash);
+        if (-e $sourcefile_24) {
+                verify($sourcefile_24, $hash_24);
+                open INFILE, "<$sourcefile_24";
+                main_firmware_24($outfile_24, $name_24, $version_24, $nr_desc_24);
+                close INFILE;
+        }
-        open INFILE, "<$sourcefile";
+        if (-e $sourcefile_27) {
-        main_firmware($outfile, $name, $version, $nr_desc);
+                verify($sourcefile_27, $hash_27);
-        close INFILE;
+                open INFILE, "<$sourcefile_27";
+                main_firmware_27($outfile_27, $name_27, $version_27, $nr_desc_27);
+                close INFILE;
+        }
 }
 extract_firmware;
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
index 1800a62cf135..8f3f5d33327c 100644
--- a/Documentation/video4linux/gspca.txt
+++ b/Documentation/video4linux/gspca.txt
@@ -42,6 +42,7 @@ ov519		041e:4064	Creative Live! VISTA VF0420
 ov519           041e:4067       Creative Live! Cam Video IM (VF0350)
 ov519           041e:4068       Creative Live! VISTA VF0470
 spca561         0458:7004       Genius VideoCAM Express V2
+sn9c2028        0458:7005       Genius Smart 300, version 2
 sunplus         0458:7006       Genius Dsc 1.3 Smart
 zc3xx           0458:7007       Genius VideoCam V2
 zc3xx           0458:700c       Genius VideoCam V3
@@ -49,6 +50,8 @@ zc3xx		0458:700f	Genius VideoCam Web V2
 sonixj          0458:7025       Genius Eye 311Q
 sn9c20x         0458:7029       Genius Look 320s
 sonixj          0458:702e       Genius Slim 310 NB
+sn9c20x         0458:704a       Genius Slim 1320
+sn9c20x         0458:704c       Genius i-Look 1321
 sn9c20x         045e:00f4       LifeCam VX-6000 (SN9C20x + OV9650)
 sonixj          045e:00f5       MicroSoft VX3000
 sonixj          045e:00f7       MicroSoft VX1000
@@ -109,6 +112,7 @@ sunplus		04a5:3003	Benq DC 1300
 sunplus         04a5:3008       Benq DC 1500
 sunplus         04a5:300a       Benq DC 3410
 spca500         04a5:300c       Benq DC 1016
+benq            04a5:3035       Benq DC E300
 finepix         04cb:0104       Fujifilm FinePix 4800
 finepix         04cb:0109       Fujifilm FinePix A202
 finepix         04cb:010b       Fujifilm FinePix A203
@@ -142,6 +146,7 @@ sunplus		04fc:5360	Sunplus Generic
 spca500         04fc:7333       PalmPixDC85
 sunplus         04fc:ffff       Pure DigitalDakota
 spca501         0506:00df       3Com HomeConnect Lite
+sunplus         052b:1507       Megapixel 5 Pretec DC-1007
 sunplus         052b:1513       Megapix V4
 sunplus         052b:1803       MegaImage VI
 tv8532          0545:808b       Veo Stingray
@@ -151,6 +156,7 @@ sunplus		0546:3191	Polaroid Ion 80
 sunplus         0546:3273       Polaroid PDC2030
 ov519           054c:0154       Sonny toy4
 ov519           054c:0155       Sonny toy5
+cpia1           0553:0002       CPIA CPiA (version1) based cameras
 zc3xx           055f:c005       Mustek Wcam300A
 spca500         055f:c200       Mustek Gsmart 300
 sunplus         055f:c211       Kowa Bs888e Microcamera
@@ -188,8 +194,7 @@ spca500		06bd:0404	Agfa CL20
 spca500         06be:0800       Optimedia
 sunplus         06d6:0031       Trust 610 LCD PowerC@m Zoom
 spca506         06e1:a190       ADS Instant VCD
-ov534           06f8:3002       Hercules Blog Webcam
+ov534_9         06f8:3003       Hercules Dualpix HD Weblog
-ov534           06f8:3003       Hercules Dualpix HD Weblog
 sonixj          06f8:3004       Hercules Classic Silver
 sonixj          06f8:3008       Hercules Deluxe Optical Glass
 pac7302         06f8:3009       Hercules Classic Link
@@ -204,6 +209,7 @@ sunplus		0733:2221	Mercury Digital Pro 3.1p
 sunplus         0733:3261       Concord 3045 spca536a
 sunplus         0733:3281       Cyberpix S550V
 spca506         0734:043b       3DeMon USB Capture aka
+cpia1           0813:0001       QX3 camera
 ov519           0813:0002       Dual Mode USB Camera Plus
 spca500         084d:0003       D-Link DSC-350
 spca500         08ca:0103       Aiptek PocketDV
@@ -225,7 +231,8 @@ sunplus		08ca:2050	Medion MD 41437
 sunplus         08ca:2060       Aiptek PocketDV5300
 tv8532          0923:010f       ICM532 cams
 mars            093a:050f       Mars-Semi Pc-Camera
-mr97310a        093a:010f       Sakar Digital no. 77379
+mr97310a        093a:010e       All known CIF cams with this ID
+mr97310a        093a:010f       All known VGA cams with this ID
 pac207          093a:2460       Qtec Webcam 100
 pac207          093a:2461       HP Webcam
 pac207          093a:2463       Philips SPC 220 NC
@@ -300,11 +307,14 @@ sonixj		0c45:6138	Sn9c120 Mo4000
 sonixj          0c45:613a       Microdia Sonix PC Camera
 sonixj          0c45:613b       Surfer SN-206
 sonixj          0c45:613c       Sonix Pccam168
+sonixj          0c45:6142       Hama PC-Webcam AC-150
 sonixj          0c45:6143       Sonix Pccam168
 sonixj          0c45:6148       Digitus DA-70811/ZSMC USB PC Camera ZS211/Microdia
+sonixj          0c45:614a       Frontech E-Ccam (JIL-2225)
 sn9c20x         0c45:6240       PC Camera (SN9C201 + MT9M001)
 sn9c20x         0c45:6242       PC Camera (SN9C201 + MT9M111)
 sn9c20x         0c45:6248       PC Camera (SN9C201 + OV9655)
+sn9c20x         0c45:624c       PC Camera (SN9C201 + MT9M112)
 sn9c20x         0c45:624e       PC Camera (SN9C201 + SOI968)
 sn9c20x         0c45:624f       PC Camera (SN9C201 + OV9650)
 sn9c20x         0c45:6251       PC Camera (SN9C201 + OV9650)
@@ -317,6 +327,7 @@ sn9c20x		0c45:627f	PC Camera (SN9C201 + OV9650)
 sn9c20x         0c45:6280       PC Camera (SN9C202 + MT9M001)
 sn9c20x         0c45:6282       PC Camera (SN9C202 + MT9M111)
 sn9c20x         0c45:6288       PC Camera (SN9C202 + OV9655)
+sn9c20x         0c45:628c       PC Camera (SN9C201 + MT9M112)
 sn9c20x         0c45:628e       PC Camera (SN9C202 + SOI968)
 sn9c20x         0c45:628f       PC Camera (SN9C202 + OV9650)
 sn9c20x         0c45:62a0       PC Camera (SN9C202 + OV7670)
@@ -324,6 +335,10 @@ sn9c20x		0c45:62b0	PC Camera (SN9C202 + MT9V011/MT9V111/MT9V112)
 sn9c20x         0c45:62b3       PC Camera (SN9C202 + OV9655)
 sn9c20x         0c45:62bb       PC Camera (SN9C202 + OV7660)
 sn9c20x         0c45:62bc       PC Camera (SN9C202 + HV7131R)
+sn9c2028        0c45:8001       Wild Planet Digital Spy Camera
+sn9c2028        0c45:8003       Sakar #11199, #6637x, #67480 keychain cams
+sn9c2028        0c45:8008       Mini-Shotz ms-350
+sn9c2028        0c45:800a       Vivitar Vivicam 3350B
 sunplus         0d64:0303       Sunplus FashionCam DXG
 ov519           0e96:c001       TRUST 380 USB2 SPACEC@M
 etoms           102c:6151       Qcam Sangha CIF
@@ -341,10 +356,11 @@ spca501		1776:501c	Arowana 300K CMOS Camera
 t613            17a1:0128       TASCORP JPEG Webcam, NGS Cyclops
 vc032x          17ef:4802       Lenovo Vc0323+MI1310_SOC
 pac207          2001:f115       D-Link DSB-C120
-sq905c          2770:9050       sq905c
+sq905c          2770:9050       Disney pix micro (CIF)
-sq905c          2770:905c       DualCamera
+sq905c          2770:9052       Disney pix micro 2 (VGA)
-sq905           2770:9120       Argus Digital Camera DC1512
+sq905c          2770:905c       All 11 known cameras with this ID
-sq905c          2770:913d       sq905c
+sq905           2770:9120       All 24 known cameras with this ID
+sq905c          2770:913d       All 4 known cameras with this ID
 spca500         2899:012c       Toptro Industrial
 ov519           8020:ef04       ov519
 spca508         8086:0110       Intel Easy PC Camera
diff --git a/Documentation/video4linux/sh_mobile_ceu_camera.txt b/Documentation/video4linux/sh_mobile_ceu_camera.txt
index 2ae16349a78d..cb47e723af74 100644
--- a/Documentation/video4linux/sh_mobile_ceu_camera.txt
+++ b/Documentation/video4linux/sh_mobile_ceu_camera.txt
@@ -17,18 +17,18 @@ Generic scaling / cropping scheme
 -2-- -\
 |      --\
 |         --\
-+-5-- -\     -- -3--
+-5-- .      -- -3-- -\
-|       ---\
+|      `...            -\
-|           --- -4-- -\
+|          `... -4-- .   - -7..
-|                      -\
+|                     `.
-|                        - -6--
+|                       `. .6--
 |
-|                        - -6'-
+|                        . .6'-
-|                      -/
+|                      .´
-|           --- -4'- -/
+|           ... -4'- .´
-|       ---/
+|       ...´             - -7'.
-+-5'- -/
+-5'- .´               -/
-|            -- -3'-
+|            -- -3'- -/
 |         --/
 |      --/
 -2'- -/
@@ -36,7 +36,11 @@ Generic scaling / cropping scheme
 |
 -1'-
-Produced by user requests:
+In the above chart minuses and slashes represent "real" data amounts, points and
+accents represent "useful" data, basically, CEU scaled amd cropped output,
+mapped back onto the client's source plane.
+Such a configuration can be produced by user requests:
 S_CROP(left / top = (5) - (1), width / height = (5') - (5))
 S_FMT(width / height = (6') - (6))
@@ -106,52 +110,30 @@ window:
 S_CROP
 ------
-If old scale applied to new crop is invalid produce nearest new scale possible
+The API at http://v4l2spec.bytesex.org/spec/x1904.htm says:
-1. Calculate current combined scales.
-        scale_comb = (((4') - (4)) / ((6') - (6))) * (((2') - (2)) / ((3') - (3)))
-2. Apply iterative sensor S_CROP for new input window.
-3. If old combined scales applied to new crop produce an impossible user window,
-adjust scales to produce nearest possible window.
-        width_u_out = ((5') - (5)) / scale_comb
-        if (width_u_out > max)
+"...specification does not define an origin or units. However by convention
-                scale_comb = ((5') - (5)) / max;
+drivers should horizontally count unscaled samples relative to 0H."
-        else if (width_u_out < min)
-                scale_comb = ((5') - (5)) / min;
-4. Issue G_CROP to retrieve actual input window.
+We choose to follow the advise and interpret cropping units as client input
+pixels.
-5. Using actual input window and calculated combined scales calculate sensor
+Cropping is performed in the following 6 steps:
-target output window.
-        width_s_out = ((3') - (3)) = ((2') - (2)) / scale_comb
-6. Apply iterative S_FMT for new sensor target output window.
-7. Issue G_FMT to retrieve the actual sensor output window.
-8. Calculate sensor scales.
-        scale_s = ((3') - (3)) / ((2') - (2))
-9. Calculate sensor output subwindow to be cropped on CEU by applying sensor
+1. Request exactly user rectangle from the sensor.
-scales to the requested window.
-        width_ceu = ((5') - (5)) / scale_s
+2. If smaller - iterate until a larger one is obtained. Result: sensor cropped
+   to 2 : 2', target crop 5 : 5', current output format 6' - 6.
-10. Use CEU cropping for above calculated window.
+3. In the previous step the sensor has tried to preserve its output frame as
+   good as possible, but it could have changed. Retrieve it again.
-11. Calculate CEU scales from sensor scales from results of (10) and user window
+4. Sensor scaled to 3 : 3'. Sensor's scale is (2' - 2) / (3' - 3). Calculate
-from (3)
+   intermediate window: 4' - 4 = (5' - 5) * (3' - 3) / (2' - 2)
-        scale_ceu = calc_scale(((5') - (5)), &width_u_out)
+5. Calculate and apply host scale = (6' - 6) / (4' - 4)
-12. Apply CEU scales.
+6. Calculate and apply host crop: 6 - 7 = (5 - 2) * (6' - 6) / (5' - 5)
 --
 Author: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
diff --git a/Documentation/video4linux/v4l2-framework.txt b/Documentation/video4linux/v4l2-framework.txt
index 74d677c8b036..e831aaca66f8 100644
--- a/Documentation/video4linux/v4l2-framework.txt
+++ b/Documentation/video4linux/v4l2-framework.txt
@@ -545,12 +545,11 @@ unregister them:
 This will remove the device nodes from sysfs (causing udev to remove them
 from /dev).
-After video_unregister_device() returns no new opens can be done.
+After video_unregister_device() returns no new opens can be done. However,
+in the case of USB devices some application might still have one of these
-However, in the case of USB devices some application might still have one
+device nodes open. So after the unregister all file operations will return
-of these device nodes open. You should block all new accesses to read,
+an error as well, except for the ioctl and unlocked_ioctl file operations:
-write, poll, etc. except possibly for certain ioctl operations like
+those will still be passed on since some buffer ioctls may still be needed.
-queueing buffers.
 When the last user of the video device node exits, then the vdev->release()
 callback is called and you can do the final cleanup there.
@@ -599,99 +598,145 @@ video_device::minor fields.
 video buffer helper functions
 -----------------------------
-The v4l2 core API provides a standard method for dealing with video
+The v4l2 core API provides a set of standard methods (called "videobuf")
-buffers. Those methods allow a driver to implement read(), mmap() and
+for dealing with video buffers. Those methods allow a driver to implement
-overlay() on a consistent way.
+read(), mmap() and overlay() in a consistent way.  There are currently
+methods for using video buffers on devices that supports DMA with
-There are currently methods for using video buffers on devices that
+scatter/gather method (videobuf-dma-sg), DMA with linear access
-supports DMA with scatter/gather method (videobuf-dma-sg), DMA with
+(videobuf-dma-contig), and vmalloced buffers, mostly used on USB drivers
-linear access (videobuf-dma-contig), and vmalloced buffers, mostly
+(videobuf-vmalloc).
-used on USB drivers (videobuf-vmalloc).
+Please see Documentation/video4linux/videobuf for more information on how
-Any driver using videobuf should provide operations (callbacks) for
+to use the videobuf layer.
-four handlers:
+struct v4l2_fh
-ops->buf_setup   - calculates the size of the video buffers and avoid they
+--------------
-                   to waste more than some maximum limit of RAM;
-ops->buf_prepare - fills the video buffer structs and calls
+struct v4l2_fh provides a way to easily keep file handle specific data
-                   videobuf_iolock() to alloc and prepare mmaped memory;
+that is used by the V4L2 framework. Using v4l2_fh is optional for
-ops->buf_queue   - advices the driver that another buffer were
+drivers.
-                   requested (by read() or by QBUF);
-ops->buf_release - frees any buffer that were allocated.
+The users of v4l2_fh (in the V4L2 framework, not the driver) know
+whether a driver uses v4l2_fh as its file->private_data pointer by
-In order to use it, the driver need to have a code (generally called at
+testing the V4L2_FL_USES_V4L2_FH bit in video_device->flags.
-interrupt context) that will properly handle the buffer request lists,
-announcing that a new buffer were filled.
+Useful functions:
-The irq handling code should handle the videobuf task lists, in order
+- v4l2_fh_init()
-to advice videobuf that a new frame were filled, in order to honor to a
-request. The code is generally like this one:
+  Initialise the file handle. This *MUST* be performed in the driver's
-        if (list_empty(&dma_q->active))
+  v4l2_file_operations->open() handler.
-                return;
+- v4l2_fh_add()
-        buf = list_entry(dma_q->active.next, struct vbuffer, vb.queue);
+  Add a v4l2_fh to video_device file handle list. May be called after
-        if (!waitqueue_active(&buf->vb.done))
+  initialising the file handle.
-                return;
+- v4l2_fh_del()
-        /* Some logic to handle the buf may be needed here */
+  Unassociate the file handle from video_device(). The file handle
-        list_del(&buf->vb.queue);
+  exit function may now be called.
-        do_gettimeofday(&buf->vb.ts);
-        wake_up(&buf->vb.done);
+- v4l2_fh_exit()
-Those are the videobuffer functions used on drivers, implemented on
+  Uninitialise the file handle. After uninitialisation the v4l2_fh
-videobuf-core:
+  memory can be freed.
- Videobuf init functions
+struct v4l2_fh is allocated as a part of the driver's own file handle
-  videobuf_queue_sg_init()
+structure and is set to file->private_data in the driver's open
-      Initializes the videobuf infrastructure. This function should be
+function by the driver. Drivers can extract their own file handle
-      called before any other videobuf function on drivers that uses DMA
+structure by using the container_of macro. Example:
-      Scatter/Gather buffers.
+struct my_fh {
-  videobuf_queue_dma_contig_init
+        int blah;
-      Initializes the videobuf infrastructure. This function should be
+        struct v4l2_fh fh;
-      called before any other videobuf function on drivers that need DMA
+};
-      contiguous buffers.
+...
-  videobuf_queue_vmalloc_init()
-      Initializes the videobuf infrastructure. This function should be
+int my_open(struct file *file)
-      called before any other videobuf function on USB (and other drivers)
+{
-      that need a vmalloced type of videobuf.
+        struct my_fh *my_fh;
+        struct video_device *vfd;
- videobuf_iolock()
+        int ret;
-  Prepares the videobuf memory for the proper method (read, mmap, overlay).
+        ...
- videobuf_queue_is_busy()
-  Checks if a videobuf is streaming.
+        ret = v4l2_fh_init(&my_fh->fh, vfd);
+        if (ret)
- videobuf_queue_cancel()
+                return ret;
-  Stops video handling.
+        v4l2_fh_add(&my_fh->fh);
- videobuf_mmap_free()
-  frees mmap buffers.
+        file->private_data = &my_fh->fh;
- videobuf_stop()
+        ...
-  Stops video handling, ends mmap and frees mmap and other buffers.
+}
- V4L2 api functions. Those functions correspond to VIDIOC_foo ioctls:
+int my_release(struct file *file)
-   videobuf_reqbufs(), videobuf_querybuf(), videobuf_qbuf(),
+{
-   videobuf_dqbuf(), videobuf_streamon(), videobuf_streamoff().
+        struct v4l2_fh *fh = file->private_data;
+        struct my_fh *my_fh = container_of(fh, struct my_fh, fh);
- V4L1 api function (corresponds to VIDIOCMBUF ioctl):
-   videobuf_cgmbuf()
+        ...
-      This function is used to provide backward compatibility with V4L1
+}
-      API.
+V4L2 events
- Some help functions for read()/poll() operations:
+-----------
-   videobuf_read_stream()
-      For continuous stream read()
+The V4L2 events provide a generic way to pass events to user space.
-   videobuf_read_one()
+The driver must use v4l2_fh to be able to support V4L2 events.
-      For snapshot read()
-   videobuf_poll_stream()
+Useful functions:
-      polling help function
+- v4l2_event_alloc()
-The better way to understand it is to take a look at vivi driver. One
-of the main reasons for vivi is to be a videobuf usage example. the
+  To use events, the driver must allocate events for the file handle. By
-vivi_thread_tick() does the task that the IRQ callback would do on PCI
+  calling the function more than once, the driver may assure that at least n
-drivers (or the irq callback on USB).
+  events in total have been allocated. The function may not be called in
+  atomic context.
+- v4l2_event_queue()
+  Queue events to video device. The driver's only responsibility is to fill
+  in the type and the data fields. The other fields will be filled in by
+  V4L2.
+- v4l2_event_subscribe()
+  The video_device->ioctl_ops->vidioc_subscribe_event must check the driver
+  is able to produce events with specified event id. Then it calls
+  v4l2_event_subscribe() to subscribe the event.
+- v4l2_event_unsubscribe()
+  vidioc_unsubscribe_event in struct v4l2_ioctl_ops. A driver may use
+  v4l2_event_unsubscribe() directly unless it wants to be involved in
+  unsubscription process.
+  The special type V4L2_EVENT_ALL may be used to unsubscribe all events. The
+  drivers may want to handle this in a special way.
+- v4l2_event_pending()
+  Returns the number of pending events. Useful when implementing poll.
+Drivers do not initialise events directly. The events are initialised
+through v4l2_fh_init() if video_device->ioctl_ops->vidioc_subscribe_event is
+non-NULL. This *MUST* be performed in the driver's
+v4l2_file_operations->open() handler.
+Events are delivered to user space through the poll system call. The driver
+can use v4l2_fh->events->wait wait_queue_head_t as the argument for
+poll_wait().
+There are standard and private events. New standard events must use the
+smallest available event type. The drivers must allocate their events from
+their own class starting from class base. Class base is
+V4L2_EVENT_PRIVATE_START + n * 1000 where n is the lowest available number.
+The first event type in the class is reserved for future use, so the first
+available event type is 'class base + 1'.
+An example on how the V4L2 events may be used can be found in the OMAP
+3 ISP driver available at <URL:http://gitorious.org/omap3camera> as of
+writing this.
diff --git a/Documentation/video4linux/videobuf b/Documentation/video4linux/videobuf
new file mode 100644
index 000000000000..17a1f9abf260
--- /dev/null
+++ b/Documentation/video4linux/videobuf
@@ -0,0 +1,360 @@
+An introduction to the videobuf layer
+Jonathan Corbet <corbet@lwn.net>
+Current as of 2.6.33
+The videobuf layer functions as a sort of glue layer between a V4L2 driver
+and user space.  It handles the allocation and management of buffers for
+the storage of video frames.  There is a set of functions which can be used
+to implement many of the standard POSIX I/O system calls, including read(),
+poll(), and, happily, mmap().  Another set of functions can be used to
+implement the bulk of the V4L2 ioctl() calls related to streaming I/O,
+including buffer allocation, queueing and dequeueing, and streaming
+control.  Using videobuf imposes a few design decisions on the driver
+author, but the payback comes in the form of reduced code in the driver and
+a consistent implementation of the V4L2 user-space API.
+Buffer types
+Not all video devices use the same kind of buffers.  In fact, there are (at
+least) three common variations:
+ - Buffers which are scattered in both the physical and (kernel) virtual
+   address spaces.  (Almost) all user-space buffers are like this, but it
+   makes great sense to allocate kernel-space buffers this way as well when
+   it is possible.  Unfortunately, it is not always possible; working with
+   this kind of buffer normally requires hardware which can do
+   scatter/gather DMA operations.
+ - Buffers which are physically scattered, but which are virtually
+   contiguous; buffers allocated with vmalloc(), in other words.  These
+   buffers are just as hard to use for DMA operations, but they can be
+   useful in situations where DMA is not available but virtually-contiguous
+   buffers are convenient.
+ - Buffers which are physically contiguous.  Allocation of this kind of
+   buffer can be unreliable on fragmented systems, but simpler DMA
+   controllers cannot deal with anything else.
+Videobuf can work with all three types of buffers, but the driver author
+must pick one at the outset and design the driver around that decision.
+[It's worth noting that there's a fourth kind of buffer: "overlay" buffers
+which are located within the system's video memory.  The overlay
+functionality is considered to be deprecated for most use, but it still
+shows up occasionally in system-on-chip drivers where the performance
+benefits merit the use of this technique.  Overlay buffers can be handled
+as a form of scattered buffer, but there are very few implementations in
+the kernel and a description of this technique is currently beyond the
+scope of this document.]
+Data structures, callbacks, and initialization
+Depending on which type of buffers are being used, the driver should
+include one of the following files:
+    <media/videobuf-dma-sg.h>           /* Physically scattered */
+    <media/videobuf-vmalloc.h>          /* vmalloc() buffers    */
+    <media/videobuf-dma-contig.h>       /* Physically contiguous */
+The driver's data structure describing a V4L2 device should include a
+struct videobuf_queue instance for the management of the buffer queue,
+along with a list_head for the queue of available buffers.  There will also
+need to be an interrupt-safe spinlock which is used to protect (at least)
+the queue.
+The next step is to write four simple callbacks to help videobuf deal with
+the management of buffers:
+    struct videobuf_queue_ops {
+        int (*buf_setup)(struct videobuf_queue *q,
+                         unsigned int *count, unsigned int *size);
+        int (*buf_prepare)(struct videobuf_queue *q,
+                           struct videobuf_buffer *vb,
+                           enum v4l2_field field);
+        void (*buf_queue)(struct videobuf_queue *q,
+                          struct videobuf_buffer *vb);
+        void (*buf_release)(struct videobuf_queue *q,
+                            struct videobuf_buffer *vb);
+    };
+buf_setup() is called early in the I/O process, when streaming is being
+initiated; its purpose is to tell videobuf about the I/O stream.  The count
+parameter will be a suggested number of buffers to use; the driver should
+check it for rationality and adjust it if need be.  As a practical rule, a
+minimum of two buffers are needed for proper streaming, and there is
+usually a maximum (which cannot exceed 32) which makes sense for each
+device.  The size parameter should be set to the expected (maximum) size
+for each frame of data.
+Each buffer (in the form of a struct videobuf_buffer pointer) will be
+passed to buf_prepare(), which should set the buffer's size, width, height,
+and field fields properly.  If the buffer's state field is
+VIDEOBUF_NEEDS_INIT, the driver should pass it to:
+    int videobuf_iolock(struct videobuf_queue* q, struct videobuf_buffer *vb,
+                        struct v4l2_framebuffer *fbuf);
+Among other things, this call will usually allocate memory for the buffer.
+Finally, the buf_prepare() function should set the buffer's state to
+VIDEOBUF_PREPARED.
+When a buffer is queued for I/O, it is passed to buf_queue(), which should
+put it onto the driver's list of available buffers and set its state to
+VIDEOBUF_QUEUED.  Note that this function is called with the queue spinlock
+held; if it tries to acquire it as well things will come to a screeching
+halt.  Yes, this is the voice of experience.  Note also that videobuf may
+wait on the first buffer in the queue; placing other buffers in front of it
+could again gum up the works.  So use list_add_tail() to enqueue buffers.
+Finally, buf_release() is called when a buffer is no longer intended to be
+used.  The driver should ensure that there is no I/O active on the buffer,
+then pass it to the appropriate free routine(s):
+    /* Scatter/gather drivers */
+    int videobuf_dma_unmap(struct videobuf_queue *q,
+                           struct videobuf_dmabuf *dma);
+    int videobuf_dma_free(struct videobuf_dmabuf *dma);
+    /* vmalloc drivers */
+    void videobuf_vmalloc_free (struct videobuf_buffer *buf);
+    /* Contiguous drivers */
+    void videobuf_dma_contig_free(struct videobuf_queue *q,
+                                  struct videobuf_buffer *buf);
+One way to ensure that a buffer is no longer under I/O is to pass it to:
+    int videobuf_waiton(struct videobuf_buffer *vb, int non_blocking, int intr);
+Here, vb is the buffer, non_blocking indicates whether non-blocking I/O
+should be used (it should be zero in the buf_release() case), and intr
+controls whether an interruptible wait is used.
+File operations
+At this point, much of the work is done; much of the rest is slipping
+videobuf calls into the implementation of the other driver callbacks.  The
+first step is in the open() function, which must initialize the
+videobuf queue.  The function to use depends on the type of buffer used:
+    void videobuf_queue_sg_init(struct videobuf_queue *q,
+                                struct videobuf_queue_ops *ops,
+                                struct device *dev,
+                                spinlock_t *irqlock,
+                                enum v4l2_buf_type type,
+                                enum v4l2_field field,
+                                unsigned int msize,
+                                void *priv);
+    void videobuf_queue_vmalloc_init(struct videobuf_queue *q,
+                                struct videobuf_queue_ops *ops,
+                                struct device *dev,
+                                spinlock_t *irqlock,
+                                enum v4l2_buf_type type,
+                                enum v4l2_field field,
+                                unsigned int msize,
+                                void *priv);
+    void videobuf_queue_dma_contig_init(struct videobuf_queue *q,
+                                       struct videobuf_queue_ops *ops,
+                                       struct device *dev,
+                                       spinlock_t *irqlock,
+                                       enum v4l2_buf_type type,
+                                       enum v4l2_field field,
+                                       unsigned int msize,
+                                       void *priv);
+In each case, the parameters are the same: q is the queue structure for the
+device, ops is the set of callbacks as described above, dev is the device
+structure for this video device, irqlock is an interrupt-safe spinlock to
+protect access to the data structures, type is the buffer type used by the
+device (cameras will use V4L2_BUF_TYPE_VIDEO_CAPTURE, for example), field
+describes which field is being captured (often V4L2_FIELD_NONE for
+progressive devices), msize is the size of any containing structure used
+around struct videobuf_buffer, and priv is a private data pointer which
+shows up in the priv_data field of struct videobuf_queue.  Note that these
+are void functions which, evidently, are immune to failure.
+V4L2 capture drivers can be written to support either of two APIs: the
+read() system call and the rather more complicated streaming mechanism.  As
+a general rule, it is necessary to support both to ensure that all
+applications have a chance of working with the device.  Videobuf makes it
+easy to do that with the same code.  To implement read(), the driver need
+only make a call to one of:
+    ssize_t videobuf_read_one(struct videobuf_queue *q,
+                              char __user *data, size_t count,
+                              loff_t *ppos, int nonblocking);
+    ssize_t videobuf_read_stream(struct videobuf_queue *q,
+                                 char __user *data, size_t count,
+                                 loff_t *ppos, int vbihack, int nonblocking);
+Either one of these functions will read frame data into data, returning the
+amount actually read; the difference is that videobuf_read_one() will only
+read a single frame, while videobuf_read_stream() will read multiple frames
+if they are needed to satisfy the count requested by the application.  A
+typical driver read() implementation will start the capture engine, call
+one of the above functions, then stop the engine before returning (though a
+smarter implementation might leave the engine running for a little while in
+anticipation of another read() call happening in the near future).
+The poll() function can usually be implemented with a direct call to:
+    unsigned int videobuf_poll_stream(struct file *file,
+                                      struct videobuf_queue *q,
+                                      poll_table *wait);
+Note that the actual wait queue eventually used will be the one associated
+with the first available buffer.
+When streaming I/O is done to kernel-space buffers, the driver must support
+the mmap() system call to enable user space to access the data.  In many
+V4L2 drivers, the often-complex mmap() implementation simplifies to a
+single call to:
+    int videobuf_mmap_mapper(struct videobuf_queue *q,
+                             struct vm_area_struct *vma);
+Everything else is handled by the videobuf code.
+The release() function requires two separate videobuf calls:
+    void videobuf_stop(struct videobuf_queue *q);
+    int videobuf_mmap_free(struct videobuf_queue *q);
+The call to videobuf_stop() terminates any I/O in progress - though it is
+still up to the driver to stop the capture engine.  The call to
+videobuf_mmap_free() will ensure that all buffers have been unmapped; if
+so, they will all be passed to the buf_release() callback.  If buffers
+remain mapped, videobuf_mmap_free() returns an error code instead.  The
+purpose is clearly to cause the closing of the file descriptor to fail if
+buffers are still mapped, but every driver in the 2.6.32 kernel cheerfully
+ignores its return value.
+ioctl() operations
+The V4L2 API includes a very long list of driver callbacks to respond to
+the many ioctl() commands made available to user space.  A number of these
+- those associated with streaming I/O - turn almost directly into videobuf
+calls.  The relevant helper functions are:
+    int videobuf_reqbufs(struct videobuf_queue *q,
+                         struct v4l2_requestbuffers *req);
+    int videobuf_querybuf(struct videobuf_queue *q, struct v4l2_buffer *b);
+    int videobuf_qbuf(struct videobuf_queue *q, struct v4l2_buffer *b);
+    int videobuf_dqbuf(struct videobuf_queue *q, struct v4l2_buffer *b,
+                       int nonblocking);
+    int videobuf_streamon(struct videobuf_queue *q);
+    int videobuf_streamoff(struct videobuf_queue *q);
+    int videobuf_cgmbuf(struct videobuf_queue *q, struct video_mbuf *mbuf,
+                        int count);
+So, for example, a VIDIOC_REQBUFS call turns into a call to the driver's
+vidioc_reqbufs() callback which, in turn, usually only needs to locate the
+proper struct videobuf_queue pointer and pass it to videobuf_reqbufs().
+These support functions can replace a great deal of buffer management
+boilerplate in a lot of V4L2 drivers.
+The vidioc_streamon() and vidioc_streamoff() functions will be a bit more
+complex, of course, since they will also need to deal with starting and
+stopping the capture engine.  videobuf_cgmbuf(), called from the driver's
+vidiocgmbuf() function, only exists if the V4L1 compatibility module has
+been selected with CONFIG_VIDEO_V4L1_COMPAT, so its use must be surrounded
+with #ifdef directives.
+Buffer allocation
+Thus far, we have talked about buffers, but have not looked at how they are
+allocated.  The scatter/gather case is the most complex on this front.  For
+allocation, the driver can leave buffer allocation entirely up to the
+videobuf layer; in this case, buffers will be allocated as anonymous
+user-space pages and will be very scattered indeed.  If the application is
+using user-space buffers, no allocation is needed; the videobuf layer will
+take care of calling get_user_pages() and filling in the scatterlist array.
+If the driver needs to do its own memory allocation, it should be done in
+the vidioc_reqbufs() function, *after* calling videobuf_reqbufs().  The
+first step is a call to:
+    struct videobuf_dmabuf *videobuf_to_dma(struct videobuf_buffer *buf);
+The returned videobuf_dmabuf structure (defined in
+<media/videobuf-dma-sg.h>) includes a couple of relevant fields:
+    struct scatterlist  *sglist;
+    int                 sglen;
+The driver must allocate an appropriately-sized scatterlist array and
+populate it with pointers to the pieces of the allocated buffer; sglen
+should be set to the length of the array.
+Drivers using the vmalloc() method need not (and cannot) concern themselves
+with buffer allocation at all; videobuf will handle those details.  The
+same is normally true of contiguous-DMA drivers as well; videobuf will
+allocate the buffers (with dma_alloc_coherent()) when it sees fit.  That
+means that these drivers may be trying to do high-order allocations at any
+time, an operation which is not always guaranteed to work.  Some drivers
+play tricks by allocating DMA space at system boot time; videobuf does not
+currently play well with those drivers.
+As of 2.6.31, contiguous-DMA drivers can work with a user-supplied buffer,
+as long as that buffer is physically contiguous.  Normal user-space
+allocations will not meet that criterion, but buffers obtained from other
+kernel drivers, or those contained within huge pages, will work with these
+drivers.
+Filling the buffers
+The final part of a videobuf implementation has no direct callback - it's
+the portion of the code which actually puts frame data into the buffers,
+usually in response to interrupts from the device.  For all types of
+drivers, this process works approximately as follows:
+ - Obtain the next available buffer and make sure that somebody is actually
+   waiting for it.
+ - Get a pointer to the memory and put video data there.
+ - Mark the buffer as done and wake up the process waiting for it.
+Step (1) above is done by looking at the driver-managed list_head structure
+- the one which is filled in the buf_queue() callback.  Because starting
+the engine and enqueueing buffers are done in separate steps, it's possible
+for the engine to be running without any buffers available - in the
+vmalloc() case especially.  So the driver should be prepared for the list
+to be empty.  It is equally possible that nobody is yet interested in the
+buffer; the driver should not remove it from the list or fill it until a
+process is waiting on it.  That test can be done by examining the buffer's
+done field (a wait_queue_head_t structure) with waitqueue_active().
+A buffer's state should be set to VIDEOBUF_ACTIVE before being mapped for
+DMA; that ensures that the videobuf layer will not try to do anything with
+it while the device is transferring data.
+For scatter/gather drivers, the needed memory pointers will be found in the
+scatterlist structure described above.  Drivers using the vmalloc() method
+can get a memory pointer with:
+    void *videobuf_to_vmalloc(struct videobuf_buffer *buf);
+For contiguous DMA drivers, the function to use is:
+    dma_addr_t videobuf_to_dma_contig(struct videobuf_buffer *buf);
+The contiguous DMA API goes out of its way to hide the kernel-space address
+of the DMA buffer from drivers.
+The final step is to set the size field of the relevant videobuf_buffer
+structure to the actual size of the captured image, set state to
+VIDEOBUF_DONE, then call wake_up() on the done queue.  At this point, the
+buffer is owned by the videobuf layer and the driver should not touch it
+again.
+Developers who are interested in more information can go into the relevant
+header files; there are a few low-level functions declared there which have
+not been talked about here.  Also worthwhile is the vivi driver
+(drivers/media/video/vivi.c), which is maintained as an example of how V4L2
+drivers should be written.  Vivi only uses the vmalloc() API, but it's good
+enough to get started with.  Note also that all of these calls are exported
+GPL-only, so they will not be available to non-GPL kernel modules.
diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX
index e57d6a9dd32b..dca82d7c83d8 100644
--- a/Documentation/vm/00-INDEX
+++ b/Documentation/vm/00-INDEX
@@ -4,23 +4,35 @@ active_mm.txt
        - An explanation from Linus about tsk->active_mm vs tsk->mm.
 balance
        - various information on memory balancing.
+hugepage-mmap.c
+        - Example app using huge page memory with the mmap system call.
+hugepage-shm.c
+        - Example app using huge page memory with Sys V shared memory system calls.
 hugetlbpage.txt
        - a brief summary of hugetlbpage support in the Linux kernel.
+hwpoison.txt
+        - explains what hwpoison is
 ksm.txt
        - how to use the Kernel Samepage Merging feature.
 locking
        - info on how locking and synchronization is done in the Linux vm code.
+map_hugetlb.c
+        - an example program that uses the MAP_HUGETLB mmap flag.
 numa
        - information about NUMA specific code in the Linux vm.
 numa_memory_policy.txt
        - documentation of concepts and APIs of the 2.6 memory policy support.
 overcommit-accounting
        - description of the Linux kernels overcommit handling modes.
+page-types.c
+        - Tool for querying page flags
 page_migration
        - description of page migration in NUMA systems.
+pagemap.txt
+        - pagemap, from the userspace perspective
 slabinfo.c
        - source code for a tool to get reports about slabs.
 slub.txt
        - a short users guide for SLUB.
-map_hugetlb.c
+unevictable-lru.txt
-        - an example program that uses the MAP_HUGETLB mmap flag.
+        - Unevictable LRU infrastructure
diff --git a/Documentation/vm/Makefile b/Documentation/vm/Makefile
index 5bd269b3731a..9dcff328b964 100644
--- a/Documentation/vm/Makefile
+++ b/Documentation/vm/Makefile
@@ -2,7 +2,7 @@
 obj- := dummy.o
 # List of programs to build
-hostprogs-y := slabinfo page-types
+hostprogs-y := slabinfo page-types hugepage-mmap hugepage-shm map_hugetlb
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
diff --git a/Documentation/vm/hugepage-mmap.c b/Documentation/vm/hugepage-mmap.c
new file mode 100644
index 000000000000..db0dd9a33d54
--- /dev/null
+++ b/Documentation/vm/hugepage-mmap.c
@@ -0,0 +1,91 @@
+/*
+ * hugepage-mmap:
+ *
+ * Example of using huge page memory in a user application using the mmap
+ * system call.  Before running this application, make sure that the
+ * administrator has mounted the hugetlbfs filesystem (on some directory
+ * like /mnt) using the command mount -t hugetlbfs nodev /mnt. In this
+ * example, the app is requesting memory of size 256MB that is backed by
+ * huge pages.
+ *
+ * For the ia64 architecture, the Linux kernel reserves Region number 4 for
+ * huge pages.  That means that if one requires a fixed address, a huge page
+ * aligned address starting with 0x800000... will be required.  If a fixed
+ * address is not required, the kernel will select an address in the proper
+ * range.
+ * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
+ */
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+#define FILE_NAME "/mnt/hugepagefile"
+#define LENGTH (256UL*1024*1024)
+#define PROTECTION (PROT_READ | PROT_WRITE)
+/* Only ia64 requires this */
+#ifdef __ia64__
+#define ADDR (void *)(0x8000000000000000UL)
+#define FLAGS (MAP_SHARED | MAP_FIXED)
+#else
+#define ADDR (void *)(0x0UL)
+#define FLAGS (MAP_SHARED)
+#endif
+static void check_bytes(char *addr)
+{
+        printf("First hex is %x\n", *((unsigned int *)addr));
+}
+static void write_bytes(char *addr)
+{
+        unsigned long i;
+        for (i = 0; i < LENGTH; i++)
+                *(addr + i) = (char)i;
+}
+static void read_bytes(char *addr)
+{
+        unsigned long i;
+        check_bytes(addr);
+        for (i = 0; i < LENGTH; i++)
+                if (*(addr + i) != (char)i) {
+                        printf("Mismatch at %lu\n", i);
+                        break;
+                }
+}
+int main(void)
+{
+        void *addr;
+        int fd;
+        fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755);
+        if (fd < 0) {
+                perror("Open failed");
+                exit(1);
+        }
+        addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, fd, 0);
+        if (addr == MAP_FAILED) {
+                perror("mmap");
+                unlink(FILE_NAME);
+                exit(1);
+        }
+        printf("Returned address is %p\n", addr);
+        check_bytes(addr);
+        write_bytes(addr);
+        read_bytes(addr);
+        munmap(addr, LENGTH);
+        close(fd);
+        unlink(FILE_NAME);
+        return 0;
+}
diff --git a/Documentation/vm/hugepage-shm.c b/Documentation/vm/hugepage-shm.c
new file mode 100644
index 000000000000..07956d8592c9
--- /dev/null
+++ b/Documentation/vm/hugepage-shm.c
@@ -0,0 +1,98 @@
+/*
+ * hugepage-shm:
+ *
+ * Example of using huge page memory in a user application using Sys V shared
+ * memory system calls.  In this example the app is requesting 256MB of
+ * memory that is backed by huge pages.  The application uses the flag
+ * SHM_HUGETLB in the shmget system call to inform the kernel that it is
+ * requesting huge pages.
+ *
+ * For the ia64 architecture, the Linux kernel reserves Region number 4 for
+ * huge pages.  That means that if one requires a fixed address, a huge page
+ * aligned address starting with 0x800000... will be required.  If a fixed
+ * address is not required, the kernel will select an address in the proper
+ * range.
+ * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
+ *
+ * Note: The default shared memory limit is quite low on many kernels,
+ * you may need to increase it via:
+ *
+ * echo 268435456 > /proc/sys/kernel/shmmax
+ *
+ * This will increase the maximum size per shared memory segment to 256MB.
+ * The other limit that you will hit eventually is shmall which is the
+ * total amount of shared memory in pages. To set it to 16GB on a system
+ * with a 4kB pagesize do:
+ *
+ * echo 4194304 > /proc/sys/kernel/shmall
+ */
+#include <stdlib.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/ipc.h>
+#include <sys/shm.h>
+#include <sys/mman.h>
+#ifndef SHM_HUGETLB
+#define SHM_HUGETLB 04000
+#endif
+#define LENGTH (256UL*1024*1024)
+#define dprintf(x)  printf(x)
+/* Only ia64 requires this */
+#ifdef __ia64__
+#define ADDR (void *)(0x8000000000000000UL)
+#define SHMAT_FLAGS (SHM_RND)
+#else
+#define ADDR (void *)(0x0UL)
+#define SHMAT_FLAGS (0)
+#endif
+int main(void)
+{
+        int shmid;
+        unsigned long i;
+        char *shmaddr;
+        if ((shmid = shmget(2, LENGTH,
+                            SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W)) < 0) {
+                perror("shmget");
+                exit(1);
+        }
+        printf("shmid: 0x%x\n", shmid);
+        shmaddr = shmat(shmid, ADDR, SHMAT_FLAGS);
+        if (shmaddr == (char *)-1) {
+                perror("Shared memory attach failure");
+                shmctl(shmid, IPC_RMID, NULL);
+                exit(2);
+        }
+        printf("shmaddr: %p\n", shmaddr);
+        dprintf("Starting the writes:\n");
+        for (i = 0; i < LENGTH; i++) {
+                shmaddr[i] = (char)(i);
+                if (!(i % (1024 * 1024)))
+                        dprintf(".");
+        }
+        dprintf("\n");
+        dprintf("Starting the Check...");
+        for (i = 0; i < LENGTH; i++)
+                if (shmaddr[i] != (char)i)
+                        printf("\nIndex %lu mismatched\n", i);
+        dprintf("Done.\n");
+        if (shmdt((const void *)shmaddr) != 0) {
+                perror("Detach failure");
+                shmctl(shmid, IPC_RMID, NULL);
+                exit(3);
+        }
+        shmctl(shmid, IPC_RMID, NULL);
+        return 0;
+}
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt
index bc31636973e3..457634c1e03e 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/vm/hugetlbpage.txt
@@ -299,176 +299,11 @@ map_hugetlb.c.
 *******************************************************************
 /*
- * Example of using huge page memory in a user application using Sys V shared
+ * hugepage-shm:  see Documentation/vm/hugepage-shm.c
- * memory system calls.  In this example the app is requesting 256MB of
- * memory that is backed by huge pages.  The application uses the flag
- * SHM_HUGETLB in the shmget system call to inform the kernel that it is
- * requesting huge pages.
- *
- * For the ia64 architecture, the Linux kernel reserves Region number 4 for
- * huge pages.  That means that if one requires a fixed address, a huge page
- * aligned address starting with 0x800000... will be required.  If a fixed
- * address is not required, the kernel will select an address in the proper
- * range.
- * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
- *
- * Note: The default shared memory limit is quite low on many kernels,
- * you may need to increase it via:
- *
- * echo 268435456 > /proc/sys/kernel/shmmax
- *
- * This will increase the maximum size per shared memory segment to 256MB.
- * The other limit that you will hit eventually is shmall which is the
- * total amount of shared memory in pages. To set it to 16GB on a system
- * with a 4kB pagesize do:
- *
- * echo 4194304 > /proc/sys/kernel/shmall
 */
-#include <stdlib.h>
-#include <stdio.h>
-#include <sys/types.h>
-#include <sys/ipc.h>
-#include <sys/shm.h>
-#include <sys/mman.h>
-#ifndef SHM_HUGETLB
-#define SHM_HUGETLB 04000
-#endif
-#define LENGTH (256UL*1024*1024)
-#define dprintf(x)  printf(x)
-#define ADDR (void *)(0x0UL)    /* let kernel choose address */
-#define SHMAT_FLAGS (0)
-int main(void)
-{
-        int shmid;
-        unsigned long i;
-        char *shmaddr;
-        if ((shmid = shmget(2, LENGTH,
-                            SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W)) < 0) {
-                perror("shmget");
-                exit(1);
-        }
-        printf("shmid: 0x%x\n", shmid);
-        shmaddr = shmat(shmid, ADDR, SHMAT_FLAGS);
-        if (shmaddr == (char *)-1) {
-                perror("Shared memory attach failure");
-                shmctl(shmid, IPC_RMID, NULL);
-                exit(2);
-        }
-        printf("shmaddr: %p\n", shmaddr);
-        dprintf("Starting the writes:\n");
-        for (i = 0; i < LENGTH; i++) {
-                shmaddr[i] = (char)(i);
-                if (!(i % (1024 * 1024)))
-                        dprintf(".");
-        }
-        dprintf("\n");
-        dprintf("Starting the Check...");
-        for (i = 0; i < LENGTH; i++)
-                if (shmaddr[i] != (char)i)
-                        printf("\nIndex %lu mismatched\n", i);
-        dprintf("Done.\n");
-        if (shmdt((const void *)shmaddr) != 0) {
-                perror("Detach failure");
-                shmctl(shmid, IPC_RMID, NULL);
-                exit(3);
-        }
-        shmctl(shmid, IPC_RMID, NULL);
-        return 0;
-}
 *******************************************************************
 /*
- * Example of using huge page memory in a user application using the mmap
+ * hugepage-mmap:  see Documentation/vm/hugepage-mmap.c
- * system call.  Before running this application, make sure that the
- * administrator has mounted the hugetlbfs filesystem (on some directory
- * like /mnt) using the command mount -t hugetlbfs nodev /mnt. In this
- * example, the app is requesting memory of size 256MB that is backed by
- * huge pages.
- *
- * For the ia64 architecture, the Linux kernel reserves Region number 4 for
- * huge pages.  That means that if one requires a fixed address, a huge page
- * aligned address starting with 0x800000... will be required.  If a fixed
- * address is not required, the kernel will select an address in the proper
- * range.
- * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
 */
-#include <stdlib.h>
-#include <stdio.h>
-#include <unistd.h>
-#include <sys/mman.h>
-#include <fcntl.h>
-#define FILE_NAME "/mnt/hugepagefile"
-#define LENGTH (256UL*1024*1024)
-#define PROTECTION (PROT_READ | PROT_WRITE)
-#define ADDR (void *)(0x0UL)    /* let kernel choose address */
-#define FLAGS (MAP_SHARED)
-void check_bytes(char *addr)
-{
-        printf("First hex is %x\n", *((unsigned int *)addr));
-}
-void write_bytes(char *addr)
-{
-        unsigned long i;
-        for (i = 0; i < LENGTH; i++)
-                *(addr + i) = (char)i;
-}
-void read_bytes(char *addr)
-{
-        unsigned long i;
-        check_bytes(addr);
-        for (i = 0; i < LENGTH; i++)
-                if (*(addr + i) != (char)i) {
-                        printf("Mismatch at %lu\n", i);
-                        break;
-                }
-}
-int main(void)
-{
-        void *addr;
-        int fd;
-        fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755);
-        if (fd < 0) {
-                perror("Open failed");
-                exit(1);
-        }
-        addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, fd, 0);
-        if (addr == MAP_FAILED) {
-                perror("mmap");
-                unlink(FILE_NAME);
-                exit(1);
-        }
-        printf("Returned address is %p\n", addr);
-        check_bytes(addr);
-        write_bytes(addr);
-        read_bytes(addr);
-        munmap(addr, LENGTH);
-        close(fd);
-        unlink(FILE_NAME);
-        return 0;
-}
diff --git a/Documentation/vm/map_hugetlb.c b/Documentation/vm/map_hugetlb.c
index e2bdae37f499..eda1a6d3578a 100644
--- a/Documentation/vm/map_hugetlb.c
+++ b/Documentation/vm/map_hugetlb.c
@@ -19,7 +19,7 @@
 #define PROTECTION (PROT_READ | PROT_WRITE)
 #ifndef MAP_HUGETLB
-#define MAP_HUGETLB 0x40
+#define MAP_HUGETLB 0x40000 /* arch specific */
 #endif
 /* Only ia64 requires this */
@@ -31,12 +31,12 @@
 #define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
 #endif
-void check_bytes(char *addr)
+static void check_bytes(char *addr)
 {
        printf("First hex is %x\n", *((unsigned int *)addr));
 }
-void write_bytes(char *addr)
+static void write_bytes(char *addr)
 {
        unsigned long i;
@@ -44,7 +44,7 @@ void write_bytes(char *addr)
                *(addr + i) = (char)i;
 }
-void read_bytes(char *addr)
+static void read_bytes(char *addr)
 {
        unsigned long i;
diff --git a/Documentation/vm/numa b/Documentation/vm/numa
index e93ad9425e2a..a200a386429d 100644
--- a/Documentation/vm/numa
+++ b/Documentation/vm/numa
@@ -1,41 +1,149 @@
 Started Nov 1999 by Kanoj Sarcar <kanoj@sgi.com>
-The intent of this file is to have an uptodate, running commentary 
+What is NUMA?
-from different people about NUMA specific code in the Linux vm.
+This question can be answered from a couple of perspectives:  the
-What is NUMA? It is an architecture where the memory access times
+hardware view and the Linux software view.
-for different regions of memory from a given processor varies
-according to the "distance" of the memory region from the processor.
+From the hardware perspective, a NUMA system is a computer platform that
-Each region of memory to which access times are the same from any 
+comprises multiple components or assemblies each of which may contain 0
-cpu, is called a node. On such architectures, it is beneficial if
+or more CPUs, local memory, and/or IO buses.  For brevity and to
-the kernel tries to minimize inter node communications. Schemes
+disambiguate the hardware view of these physical components/assemblies
-for this range from kernel text and read-only data replication
+from the software abstraction thereof, we'll call the components/assemblies
-across nodes, and trying to house all the data structures that
+'cells' in this document.
-key components of the kernel need on memory on that node.
+Each of the 'cells' may be viewed as an SMP [symmetric multi-processor] subset
-Currently, all the numa support is to provide efficient handling
+of the system--although some components necessary for a stand-alone SMP system
-of widely discontiguous physical memory, so architectures which 
+may not be populated on any given cell.   The cells of the NUMA system are
-are not NUMA but can have huge holes in the physical address space
+connected together with some sort of system interconnect--e.g., a crossbar or
-can use the same code. All this code is bracketed by CONFIG_DISCONTIGMEM.
+point-to-point link are common types of NUMA system interconnects.  Both of
+these types of interconnects can be aggregated to create NUMA platforms with
-The initial port includes NUMAizing the bootmem allocator code by
+cells at multiple distances from other cells.
-encapsulating all the pieces of information into a bootmem_data_t
-structure. Node specific calls have been added to the allocator. 
+For Linux, the NUMA platforms of interest are primarily what is known as Cache
-In theory, any platform which uses the bootmem allocator should 
+Coherent NUMA or ccNUMA systems.   With ccNUMA systems, all memory is visible
-be able to put the bootmem and mem_map data structures anywhere
+to and accessible from any CPU attached to any cell and cache coherency
-it deems best.
+is handled in hardware by the processor caches and/or the system interconnect.
-Each node's page allocation data structures have also been encapsulated
+Memory access time and effective memory bandwidth varies depending on how far
-into a pg_data_t. The bootmem_data_t is just one part of this. To 
+away the cell containing the CPU or IO bus making the memory access is from the
-make the code look uniform between NUMA and regular UMA platforms, 
+cell containing the target memory.  For example, access to memory by CPUs
-UMA platforms have a statically allocated pg_data_t too (contig_page_data).
+attached to the same cell will experience faster access times and higher
-For the sake of uniformity, the function num_online_nodes() is also defined
+bandwidths than accesses to memory on other, remote cells.  NUMA platforms
-for all platforms. As we run benchmarks, we might decide to NUMAize 
+can have cells at multiple remote distances from any given cell.
-more variables like low_on_memory, nr_free_pages etc into the pg_data_t.
+Platform vendors don't build NUMA systems just to make software developers'
-The NUMA aware page allocation code currently tries to allocate pages 
+lives interesting.  Rather, this architecture is a means to provide scalable
-from different nodes in a round robin manner.  This will be changed to 
+memory bandwidth.  However, to achieve scalable memory bandwidth, system and
-do concentratic circle search, starting from current node, once the 
+application software must arrange for a large majority of the memory references
-NUMA port achieves more maturity. The call alloc_pages_node has been 
+[cache misses] to be to "local" memory--memory on the same cell, if any--or
-added, so that drivers can make the call and not worry about whether 
+to the closest cell with memory.
-it is running on a NUMA or UMA platform.
+This leads to the Linux software view of a NUMA system:
+Linux divides the system's hardware resources into multiple software
+abstractions called "nodes".  Linux maps the nodes onto the physical cells
+of the hardware platform, abstracting away some of the details for some
+architectures.  As with physical cells, software nodes may contain 0 or more
+CPUs, memory and/or IO buses.  And, again, memory accesses to memory on
+"closer" nodes--nodes that map to closer cells--will generally experience
+faster access times and higher effective bandwidth than accesses to more
+remote cells.
+For some architectures, such as x86, Linux will "hide" any node representing a
+physical cell that has no memory attached, and reassign any CPUs attached to
+that cell to a node representing a cell that does have memory.  Thus, on
+these architectures, one cannot assume that all CPUs that Linux associates with
+a given node will see the same local memory access times and bandwidth.
+In addition, for some architectures, again x86 is an example, Linux supports
+the emulation of additional nodes.  For NUMA emulation, linux will carve up
+the existing nodes--or the system memory for non-NUMA platforms--into multiple
+nodes.  Each emulated node will manage a fraction of the underlying cells'
+physical memory.  NUMA emluation is useful for testing NUMA kernel and
+application features on non-NUMA platforms, and as a sort of memory resource
+management mechanism when used together with cpusets.
+[see Documentation/cgroups/cpusets.txt]
+For each node with memory, Linux constructs an independent memory management
+subsystem, complete with its own free page lists, in-use page lists, usage
+statistics and locks to mediate access.  In addition, Linux constructs for
+each memory zone [one or more of DMA, DMA32, NORMAL, HIGH_MEMORY, MOVABLE],
+an ordered "zonelist".  A zonelist specifies the zones/nodes to visit when a
+selected zone/node cannot satisfy the allocation request.  This situation,
+when a zone has no available memory to satisfy a request, is called
+"overflow" or "fallback".
+Because some nodes contain multiple zones containing different types of
+memory, Linux must decide whether to order the zonelists such that allocations
+fall back to the same zone type on a different node, or to a different zone
+type on the same node.  This is an important consideration because some zones,
+such as DMA or DMA32, represent relatively scarce resources.  Linux chooses
+a default zonelist order based on the sizes of the various zone types relative
+to the total memory of the node and the total memory of the system.  The
+default zonelist order may be overridden using the numa_zonelist_order kernel
+boot parameter or sysctl.  [see Documentation/kernel-parameters.txt and
+Documentation/sysctl/vm.txt]
+By default, Linux will attempt to satisfy memory allocation requests from the
+node to which the CPU that executes the request is assigned.  Specifically,
+Linux will attempt to allocate from the first node in the appropriate zonelist
+for the node where the request originates.  This is called "local allocation."
+If the "local" node cannot satisfy the request, the kernel will examine other
+nodes' zones in the selected zonelist looking for the first zone in the list
+that can satisfy the request.
+Local allocation will tend to keep subsequent access to the allocated memory
+"local" to the underlying physical resources and off the system interconnect--
+as long as the task on whose behalf the kernel allocated some memory does not
+later migrate away from that memory.  The Linux scheduler is aware of the
+NUMA topology of the platform--embodied in the "scheduling domains" data
+structures [see Documentation/scheduler/sched-domains.txt]--and the scheduler
+attempts to minimize task migration to distant scheduling domains.  However,
+the scheduler does not take a task's NUMA footprint into account directly.
+Thus, under sufficient imbalance, tasks can migrate between nodes, remote
+from their initial node and kernel data structures.
+System administrators and application designers can restrict a task's migration
+to improve NUMA locality using various CPU affinity command line interfaces,
+such as taskset(1) and numactl(1), and program interfaces such as
+sched_setaffinity(2).  Further, one can modify the kernel's default local
+allocation behavior using Linux NUMA memory policy.
+[see Documentation/vm/numa_memory_policy.]
+System administrators can restrict the CPUs and nodes' memories that a non-
+privileged user can specify in the scheduling or NUMA commands and functions
+using control groups and CPUsets.  [see Documentation/cgroups/CPUsets.txt]
+On architectures that do not hide memoryless nodes, Linux will include only
+zones [nodes] with memory in the zonelists.  This means that for a memoryless
+node the "local memory node"--the node of the first zone in CPU's node's
+zonelist--will not be the node itself.  Rather, it will be the node that the
+kernel selected as the nearest node with memory when it built the zonelists.
+So, default, local allocations will succeed with the kernel supplying the
+closest available memory.  This is a consequence of the same mechanism that
+allows such allocations to fallback to other nearby nodes when a node that
+does contain memory overflows.
+Some kernel allocations do not want or cannot tolerate this allocation fallback
+behavior.  Rather they want to be sure they get memory from the specified node
+or get notified that the node has no free memory.  This is usually the case when
+a subsystem allocates per CPU memory resources, for example.
+A typical model for making such an allocation is to obtain the node id of the
+node to which the "current CPU" is attached using one of the kernel's
+numa_node_id() or CPU_to_node() functions and then request memory from only
+the node id returned.  When such an allocation fails, the requesting subsystem
+may revert to its own fallback path.  The slab kernel memory allocator is an
+example of this.  Or, the subsystem may choose to disable or not to enable
+itself on allocation failure.  The kernel profiling subsystem is an example of
+this.
+If the architecture supports--does not hide--memoryless nodes, then CPUs
+attached to memoryless nodes would always incur the fallback path overhead
+or some subsystems would fail to initialize if they attempted to allocated
+memory exclusively from a node without memory.  To support such
+architectures transparently, kernel subsystems can use the numa_mem_id()
+or cpu_to_mem() function to locate the "local memory node" for the calling or
+specified CPU.  Again, this is the same node from which default, local page
+allocations will be attempted.
diff --git a/Documentation/vm/numa_memory_policy.txt b/Documentation/vm/numa_memory_policy.txt
index be45dbb9d7f2..6690fc34ef6d 100644
--- a/Documentation/vm/numa_memory_policy.txt
+++ b/Documentation/vm/numa_memory_policy.txt
@@ -45,7 +45,7 @@ most general to most specific:
        to establish the task policy for a child task exec()'d from an
        executable image that has no awareness of memory policy.  See the
        MEMORY POLICY APIS section, below, for an overview of the system call
-        that a task may use to set/change it's task/process policy.
+        that a task may use to set/change its task/process policy.
        In a multi-threaded task, task policies apply only to the thread
        [Linux kernel task] that installs the policy and any threads
@@ -301,7 +301,7 @@ decrement this reference count, respectively.  mpol_put() will only free
 the structure back to the mempolicy kmem cache when the reference count
 goes to zero.
-When a new memory policy is allocated, it's reference count is initialized
+When a new memory policy is allocated, its reference count is initialized
 to '1', representing the reference held by the task that is installing the
 new policy.  When a pointer to a memory policy structure is stored in another
 structure, another reference is added, as the task's reference will be dropped
diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt
index b37300edf27c..07375e73981a 100644
--- a/Documentation/vm/slub.txt
+++ b/Documentation/vm/slub.txt
@@ -41,6 +41,7 @@ Possible debug options are
        P               Poisoning (object and padding)
        U               User tracking (free and alloc)
        T               Trace (please only use on single slabs)
+        A               Toggle failslab filter mark for the cache
        O               Switch debugging off for caches that would have
                        caused higher minimum slab orders
        -               Switch all debugging off (useful if the kernel is
diff --git a/Documentation/volatile-considered-harmful.txt b/Documentation/volatile-considered-harmful.txt
index 991c26a6ef64..db0cb228d64a 100644
--- a/Documentation/volatile-considered-harmful.txt
+++ b/Documentation/volatile-considered-harmful.txt
@@ -63,9 +63,9 @@ way to perform a busy wait is:
        cpu_relax();
 The cpu_relax() call can lower CPU power consumption or yield to a
-hyperthreaded twin processor; it also happens to serve as a memory barrier,
+hyperthreaded twin processor; it also happens to serve as a compiler
-so, once again, volatile is unnecessary.  Of course, busy-waiting is
+barrier, so, once again, volatile is unnecessary.  Of course, busy-
-generally an anti-social act to begin with.
+waiting is generally an anti-social act to begin with.
 There are still a few rare situations where volatile makes sense in the
 kernel:
diff --git a/Documentation/voyager.txt b/Documentation/voyager.txt
deleted file mode 100644
index 2749af552cdf..000000000000
--- a/Documentation/voyager.txt
+++ /dev/null
@@ -1,95 +0,0 @@
-Running Linux on the Voyager Architecture
-=========================================
-For full details and current project status, see
-http://www.hansenpartnership.com/voyager
-The voyager architecture was designed by NCR in the mid 80s to be a
-fully SMP capable RAS computing architecture built around intel's 486
-chip set.  The voyager came in three levels of architectural
-sophistication: 3,4 and 5 --- 1 and 2 never made it out of prototype.
-The linux patches support only the Level 5 voyager architecture (any
-machine class 3435 and above).
-The Voyager Architecture
------------------------
-Voyager machines consist of a Baseboard with a 386 diagnostic
-processor, a Power Supply Interface (PSI) a Primary and possibly
-Secondary Microchannel bus and between 2 and 20 voyager slots.  The
-voyager slots can be populated with memory and cpu cards (up to 4GB
-memory and from 1 486 to 32 Pentium Pro processors).  Internally, the
-voyager has a dual arbitrated system bus and a configuration and test
-bus (CAT).  The voyager bus speed is 40MHz.  Therefore (since all
-voyager cards are dual ported for each system bus) the maximum
-transfer rate is 320Mb/s but only if you have your slot configuration
-tuned (only memory cards can communicate with both busses at once, CPU
-cards utilise them one at a time).
-Voyager SMP
-----------
-Since voyager was the first intel based SMP system, it is slightly
-more primitive than the Intel IO-APIC approach to SMP.  Voyager allows
-arbitrary interrupt routing (including processor affinity routing) of
-all 16 PC type interrupts.  However it does this by using a modified
-5259 master/slave chip set instead of an APIC bus.  Additionally,
-voyager supports Cross Processor Interrupts (CPI) equivalent to the
-APIC IPIs.  There are two routed voyager interrupt lines provided to
-each slot.
-Processor Cards
---------------
-These come in single, dyadic and quad configurations (the quads are
-problematic--see later).  The maximum configuration is 8 quad cards
-for 32 way SMP.
-Quad Processors
---------------
-Because voyager only supplies two interrupt lines to each Processor
-card, the Quad processors have to be configured (and Bootstrapped) in
-as a pair of Master/Slave processors.
-In fact, most Quad cards only accept one VIC interrupt line, so they
-have one interrupt handling processor (called the VIC extended
-processor) and three non-interrupt handling processors.
-Current Status
--------------
-The System will boot on Mono, Dyad and Quad cards.  There was
-originally a Quad boot problem which has been fixed by proper gdt
-alignment in the initial boot loader.  If you still cannot get your
-voyager system to boot, email me at:
-<J.E.J.Bottomley@HansenPartnership.com>
-The Quad cards now support using the separate Quad CPI vectors instead
-of going through the VIC mailbox system.
-The Level 4 architecture (3430 and 3360 Machines) should also work
-fine.
-Dump Switch
-----------
-The voyager dump switch sends out a broadcast NMI which the voyager
-code intercepts and does a task dump.
-Power Switch
------------
-The front panel power switch is intercepted by the kernel and should
-cause a system shutdown and power off.
-A Note About Mixed CPU Systems
------------------------------
-Linux isn't designed to handle mixed CPU systems very well.  In order
-to get everything going you *must* make sure that your lowest
-capability CPU is used for booting.  Also, mixing CPU classes
-(e.g. 486 and 586) is really not going to work very well at all.
diff --git a/Documentation/w1/w1.generic b/Documentation/w1/w1.generic
index e3333eec4320..212f4ac31c01 100644
--- a/Documentation/w1/w1.generic
+++ b/Documentation/w1/w1.generic
@@ -25,7 +25,7 @@ When a w1 master driver registers with the w1 subsystem, the following occurs:
 - sysfs entries for that w1 master are created
 - the w1 bus is periodically searched for new slave devices
-When a device is found on the bus, w1 core checks if driver for it's family is
+When a device is found on the bus, w1 core checks if driver for its family is
 loaded. If so, the family driver is attached to the slave.
 If there is no driver for the family, default one is assigned, which allows to perform
 almost any kind of operations. Each logical operation is a transaction
diff --git a/Documentation/watchdog/00-INDEX b/Documentation/watchdog/00-INDEX
index c3ea47e507fe..ee994513a9b1 100644
--- a/Documentation/watchdog/00-INDEX
+++ b/Documentation/watchdog/00-INDEX
@@ -1,10 +1,15 @@
 00-INDEX
        - this file.
+hpwdt.txt
+        - information on the HP iLO2 NMI watchdog
 pcwd-watchdog.txt
        - documentation for Berkshire Products PC Watchdog ISA cards.
 src/
        - directory holding watchdog related example programs.
 watchdog-api.txt
        - description of the Linux Watchdog driver API.
+watchdog-parameters.txt
+        - information on driver parameters (for drivers other than
+          the ones that have driver-specific files here)
 wdt.txt
        - description of the Watchdog Timer Interfaces for Linux.
diff --git a/Documentation/watchdog/src/watchdog-simple.c b/Documentation/watchdog/src/watchdog-simple.c
index 4cf72f3fa8e9..ba45803a2216 100644
--- a/Documentation/watchdog/src/watchdog-simple.c
+++ b/Documentation/watchdog/src/watchdog-simple.c
@@ -17,9 +17,6 @@ int main(void)
                        ret = -1;
                        break;
                }
-                ret = fsync(fd);
-                if (ret)
-                        break;
                sleep(10);
        }
        close(fd);
diff --git a/Documentation/watchdog/src/watchdog-test.c b/Documentation/watchdog/src/watchdog-test.c
index a750532ffcf8..63fdc34ceb98 100644
--- a/Documentation/watchdog/src/watchdog-test.c
+++ b/Documentation/watchdog/src/watchdog-test.c
@@ -31,6 +31,8 @@ static void keep_alive(void)
 */
 int main(int argc, char *argv[])
 {
+    int flags;
    fd = open("/dev/watchdog", O_WRONLY);
    if (fd == -1) {
@@ -41,12 +43,14 @@ int main(int argc, char *argv[])
    if (argc > 1) {
        if (!strncasecmp(argv[1], "-d", 2)) {
-            ioctl(fd, WDIOC_SETOPTIONS, WDIOS_DISABLECARD);
+            flags = WDIOS_DISABLECARD;
+            ioctl(fd, WDIOC_SETOPTIONS, &flags);
            fprintf(stderr, "Watchdog card disabled.\n");
            fflush(stderr);
            exit(0);
        } else if (!strncasecmp(argv[1], "-e", 2)) {
-            ioctl(fd, WDIOC_SETOPTIONS, WDIOS_ENABLECARD);
+            flags = WDIOS_ENABLECARD;
+            ioctl(fd, WDIOC_SETOPTIONS, &flags);
            fprintf(stderr, "Watchdog card enabled.\n");
            fflush(stderr);
            exit(0);
diff --git a/Documentation/watchdog/watchdog-api.txt b/Documentation/watchdog/watchdog-api.txt
index 4cc4ba9d7150..eb7132ed8bbc 100644
--- a/Documentation/watchdog/watchdog-api.txt
+++ b/Documentation/watchdog/watchdog-api.txt
@@ -222,11 +222,10 @@ returned value is the temperature in degrees fahrenheit.
    ioctl(fd, WDIOC_GETTEMP, &temperature);
 Finally the SETOPTIONS ioctl can be used to control some aspects of
-the cards operation; right now the pcwd driver is the only one
+the cards operation.
-supporting this ioctl.
    int options = 0;
-    ioctl(fd, WDIOC_SETOPTIONS, options);
+    ioctl(fd, WDIOC_SETOPTIONS, &options);
 The following options are available:
diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt
new file mode 100644
index 000000000000..41c95cc1dc1f
--- /dev/null
+++ b/Documentation/watchdog/watchdog-parameters.txt
@@ -0,0 +1,390 @@
+This file provides information on the module parameters of many of
+the Linux watchdog drivers.  Watchdog driver parameter specs should
+be listed here unless the driver has its own driver-specific information
+file.
+See Documentation/kernel-parameters.txt for information on
+providing kernel parameters for builtin drivers versus loadable
+modules.
+-------------------------------------------------
+acquirewdt:
+wdt_stop: Acquire WDT 'stop' io port (default 0x43)
+wdt_start: Acquire WDT 'start' io port (default 0x443)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+advantechwdt:
+wdt_stop: Advantech WDT 'stop' io port (default 0x443)
+wdt_start: Advantech WDT 'start' io port (default 0x443)
+timeout: Watchdog timeout in seconds. 1<= timeout <=63, default=60.
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+alim1535_wdt:
+timeout: Watchdog timeout in seconds. (0 < timeout < 18000, default=60
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+alim7101_wdt:
+timeout: Watchdog timeout in seconds. (1<=timeout<=3600, default=30
+use_gpio: Use the gpio watchdog (required by old cobalt boards).
+        default=0/off/no
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+ar7_wdt:
+margin: Watchdog margin in seconds (default=60)
+nowayout: Disable watchdog shutdown on close
+        (default=kernel config parameter)
+-------------------------------------------------
+at32ap700x_wdt:
+timeout: Timeout value. Limited to be 1 or 2 seconds. (default=2)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+at91rm9200_wdt:
+wdt_time: Watchdog time in seconds. (default=5)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+at91sam9_wdt:
+heartbeat: Watchdog heartbeats in seconds. (default = 15)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+bcm47xx_wdt:
+wdt_time: Watchdog time in seconds. (default=30)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+bfin_wdt:
+timeout: Watchdog timeout in seconds. (1<=timeout<=((2^32)/SCLK), default=20)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+coh901327_wdt:
+margin: Watchdog margin in seconds (default 60s)
+-------------------------------------------------
+cpu5wdt:
+port: base address of watchdog card, default is 0x91
+verbose: be verbose, default is 0 (no)
+ticks: count down ticks, default is 10000
+-------------------------------------------------
+cpwd:
+wd0_timeout: Default watchdog0 timeout in 1/10secs
+wd1_timeout: Default watchdog1 timeout in 1/10secs
+wd2_timeout: Default watchdog2 timeout in 1/10secs
+-------------------------------------------------
+davinci_wdt:
+heartbeat: Watchdog heartbeat period in seconds from 1 to 600, default 60
+-------------------------------------------------
+ep93xx_wdt:
+nowayout: Watchdog cannot be stopped once started
+timeout: Watchdog timeout in seconds. (1<=timeout<=3600, default=TBD)
+-------------------------------------------------
+eurotechwdt:
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+io: Eurotech WDT io port (default=0x3f0)
+irq: Eurotech WDT irq (default=10)
+ev: Eurotech WDT event type (default is `int')
+-------------------------------------------------
+gef_wdt:
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+geodewdt:
+timeout: Watchdog timeout in seconds. 1<= timeout <=131, default=60.
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+i6300esb:
+heartbeat: Watchdog heartbeat in seconds. (1<heartbeat<2046, default=30)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+iTCO_wdt:
+heartbeat: Watchdog heartbeat in seconds.
+        (2<heartbeat<39 (TCO v1) or 613 (TCO v2), default=30)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+iTCO_vendor_support:
+vendorsupport: iTCO vendor specific support mode, default=0 (none),
+        1=SuperMicro Pent3, 2=SuperMicro Pent4+, 911=Broken SMI BIOS
+-------------------------------------------------
+ib700wdt:
+timeout: Watchdog timeout in seconds. 0<= timeout <=30, default=30.
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+ibmasr:
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+indydog:
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+iop_wdt:
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+it8712f_wdt:
+margin: Watchdog margin in seconds (default 60)
+nowayout: Disable watchdog shutdown on close
+        (default=kernel config parameter)
+-------------------------------------------------
+it87_wdt:
+nogameport: Forbid the activation of game port, default=0
+exclusive: Watchdog exclusive device open, default=1
+timeout: Watchdog timeout in seconds, default=60
+testmode: Watchdog test mode (1 = no reboot), default=0
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+ixp2000_wdt:
+heartbeat: Watchdog heartbeat in seconds (default 60s)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+ixp4xx_wdt:
+heartbeat: Watchdog heartbeat in seconds (default 60s)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+ks8695_wdt:
+wdt_time: Watchdog time in seconds. (default=5)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+machzwd:
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+action: after watchdog resets, generate:
+        0 = RESET(*)  1 = SMI  2 = NMI  3 = SCI
+-------------------------------------------------
+max63xx_wdt:
+heartbeat: Watchdog heartbeat period in seconds from 1 to 60, default 60
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+nodelay: Force selection of a timeout setting without initial delay
+        (max6373/74 only, default=0)
+-------------------------------------------------
+mixcomwd:
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+mpc8xxx_wdt:
+timeout: Watchdog timeout in ticks. (0<timeout<65536, default=65535)
+reset: Watchdog Interrupt/Reset Mode. 0 = interrupt, 1 = reset
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+mpcore_wdt:
+mpcore_margin: MPcore timer margin in seconds.
+        (0 < mpcore_margin < 65536, default=60)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+mpcore_noboot: MPcore watchdog action, set to 1 to ignore reboots,
+        0 to reboot (default=0
+-------------------------------------------------
+mv64x60_wdt:
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+nuc900_wdt:
+heartbeat: Watchdog heartbeats in seconds.
+        (default = 15)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+omap_wdt:
+timer_margin: initial watchdog timeout (in seconds)
+-------------------------------------------------
+orion_wdt:
+heartbeat: Initial watchdog heartbeat in seconds
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+pc87413_wdt:
+io: pc87413 WDT I/O port (default: io).
+timeout: Watchdog timeout in minutes (default=timeout).
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+pika_wdt:
+heartbeat: Watchdog heartbeats in seconds. (default = 15)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+pnx4008_wdt:
+heartbeat: Watchdog heartbeat period in seconds from 1 to 60, default 19
+nowayout: Set to 1 to keep watchdog running after device release
+-------------------------------------------------
+pnx833x_wdt:
+timeout: Watchdog timeout in Mhz. (68Mhz clock), default=2040000000 (30 seconds)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+start_enabled: Watchdog is started on module insertion (default=1)
+-------------------------------------------------
+rc32434_wdt:
+timeout: Watchdog timeout value, in seconds (default=20)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+riowd:
+riowd_timeout: Watchdog timeout in minutes (default=1)
+-------------------------------------------------
+s3c2410_wdt:
+tmr_margin: Watchdog tmr_margin in seconds. (default=15)
+tmr_atboot: Watchdog is started at boot time if set to 1, default=0
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+soft_noboot: Watchdog action, set to 1 to ignore reboots, 0 to reboot
+debug: Watchdog debug, set to >1 for debug, (default 0)
+-------------------------------------------------
+sa1100_wdt:
+margin: Watchdog margin in seconds (default 60s)
+-------------------------------------------------
+sb_wdog:
+timeout: Watchdog timeout in microseconds (max/default 8388607 or 8.3ish secs)
+-------------------------------------------------
+sbc60xxwdt:
+wdt_stop: SBC60xx WDT 'stop' io port (default 0x45)
+wdt_start: SBC60xx WDT 'start' io port (default 0x443)
+timeout: Watchdog timeout in seconds. (1<=timeout<=3600, default=30)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+sbc7240_wdt:
+timeout: Watchdog timeout in seconds. (1<=timeout<=255, default=30)
+nowayout: Disable watchdog when closing device file
+-------------------------------------------------
+sbc8360:
+timeout: Index into timeout table (0-63) (default=27 (60s))
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+sbc_epx_c3:
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+sbc_fitpc2_wdt:
+margin: Watchdog margin in seconds (default 60s)
+nowayout: Watchdog cannot be stopped once started
+-------------------------------------------------
+sc1200wdt:
+isapnp: When set to 0 driver ISA PnP support will be disabled (default=1)
+io: io port
+timeout: range is 0-255 minutes, default is 1
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+sc520_wdt:
+timeout: Watchdog timeout in seconds. (1 <= timeout <= 3600, default=30)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+sch311x_wdt:
+force_id: Override the detected device ID
+therm_trip: Should a ThermTrip trigger the reset generator
+timeout: Watchdog timeout in seconds. 1<= timeout <=15300, default=60
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+scx200_wdt:
+margin: Watchdog margin in seconds
+nowayout: Disable watchdog shutdown on close
+-------------------------------------------------
+shwdt:
+clock_division_ratio: Clock division ratio. Valid ranges are from 0x5 (1.31ms)
+        to 0x7 (5.25ms). (default=7)
+heartbeat: Watchdog heartbeat in seconds. (1 <= heartbeat <= 3600, default=30
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+smsc37b787_wdt:
+timeout: range is 1-255 units, default is 60
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+softdog:
+soft_margin: Watchdog soft_margin in seconds.
+        (0 < soft_margin < 65536, default=60)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+soft_noboot: Softdog action, set to 1 to ignore reboots, 0 to reboot
+        (default=0)
+-------------------------------------------------
+stmp3xxx_wdt:
+heartbeat: Watchdog heartbeat period in seconds from 1 to 4194304, default 19
+-------------------------------------------------
+ts72xx_wdt:
+timeout: Watchdog timeout in seconds. (1 <= timeout <= 8, default=8)
+nowayout: Disable watchdog shutdown on close
+-------------------------------------------------
+twl4030_wdt:
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+txx9wdt:
+timeout: Watchdog timeout in seconds. (0<timeout<N, default=60)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+w83627hf_wdt:
+wdt_io: w83627hf/thf WDT io port (default 0x2E)
+timeout: Watchdog timeout in seconds. 1 <= timeout <= 255, default=60.
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+w83697hf_wdt:
+wdt_io: w83697hf/hg WDT io port (default 0x2e, 0 = autodetect)
+timeout: Watchdog timeout in seconds. 1<= timeout <=255 (default=60)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+early_disable: Watchdog gets disabled at boot time (default=1)
+-------------------------------------------------
+w83697ug_wdt:
+wdt_io: w83697ug/uf WDT io port (default 0x2e)
+timeout: Watchdog timeout in seconds. 1<= timeout <=255 (default=60)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+w83877f_wdt:
+timeout: Watchdog timeout in seconds. (1<=timeout<=3600, default=30)
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+w83977f_wdt:
+timeout: Watchdog timeout in seconds (15..7635), default=45)
+testmode: Watchdog testmode (1 = no reboot), default=0
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+wafer5823wdt:
+timeout: Watchdog timeout in seconds. 1 <= timeout <= 255, default=60.
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+wdt285:
+soft_margin: Watchdog timeout in seconds (default=60)
+-------------------------------------------------
+wdt977:
+timeout: Watchdog timeout in seconds (60..15300, default=60)
+testmode: Watchdog testmode (1 = no reboot), default=0
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+wm831x_wdt:
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
+wm8350_wdt:
+nowayout: Watchdog cannot be stopped once started
+        (default=kernel config parameter)
+-------------------------------------------------
diff --git a/Documentation/watchdog/wdt.txt b/Documentation/watchdog/wdt.txt
index 03fd756d976d..061c2e35384f 100644
--- a/Documentation/watchdog/wdt.txt
+++ b/Documentation/watchdog/wdt.txt
@@ -14,14 +14,22 @@ reboot will depend on the state of the machines and interrupts. The hardware
 boards physically pull the machine down off their own onboard timers and
 will reboot from almost anything.
-A second temperature monitoring interface is available on the WDT501P cards
+A second temperature monitoring interface is available on the WDT501P cards.
 This provides /dev/temperature. This is the machine internal temperature in
 degrees Fahrenheit. Each read returns a single byte giving the temperature.
 The third interface logs kernel messages on additional alert events.
-The wdt card cannot be safely probed for. Instead you need to pass
+The ICS ISA-bus wdt card cannot be safely probed for. Instead you need to
-wdt=ioaddr,irq as a boot parameter - eg "wdt=0x240,11".
+pass IO address and IRQ boot parameters.  E.g.:
+        wdt.io=0x240 wdt.irq=11
+Other "wdt" driver parameters are:
+        heartbeat       Watchdog heartbeat in seconds (default 60)
+        nowayout        Watchdog cannot be stopped once started (kernel
+                                build parameter)
+        tachometer      WDT501-P Fan Tachometer support (0=disable, default=0)
+        type            WDT501-P Card type (500 or 501, default=500)
 Features
 --------
@@ -40,4 +48,3 @@ Minor numbers are however allocated for it.
 Example Watchdog Driver:  see Documentation/watchdog/src/watchdog-simple.c
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 29a6ff8bc7d3..7fbbaf85f5b7 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -166,19 +166,13 @@ NUMA
  numa=noacpi   Don't parse the SRAT table for NUMA setup
-  numa=fake=CMDLINE
+  numa=fake=<size>[MG]
-                If a number, fakes CMDLINE nodes and ignores NUMA setup of the
+                If given as a memory unit, fills all system RAM with nodes of
-                actual machine.  Otherwise, system memory is configured
+                size interleaved over physical nodes.
-                depending on the sizes and coefficients listed.  For example:
-                        numa=fake=2*512,1024,4*256,*128
+  numa=fake=<N>
-                gives two 512M nodes, a 1024M node, four 256M nodes, and the
+                If given as an integer, fills all system RAM with N fake nodes
-                rest split into 128M chunks.  If the last character of CMDLINE
+                interleaved over physical nodes.
-                is a *, the remaining memory is divided up equally among its
-                coefficient:
-                        numa=fake=2*512,2*
-                gives two 512M nodes and the rest split into two nodes.
-                Otherwise, the remaining system RAM is allocated to an
-                additional node.
 ACPI