Merge commit 'v2.6.37-rc1' into for-2.6.37

author: Mark Brown <broonie@opensource.wolfsonmicro.com> 2010-11-02 09:41:56 -0400
committer: Mark Brown <broonie@opensource.wolfsonmicro.com> 2010-11-02 09:41:56 -0400
commit: 29c798fecb9b846b363b0a02fa662ff42fc19426 (patch)
tree: e708d6aca8f098e69571780f702325b221b66694 /Documentation
parent: cb9906229595941d632fc4022b05da4f9533856a (diff)
parent: c8ddb2713c624f432fa5fe3c7ecffcdda46ea0d4 (diff)
124 files changed, 5548 insertions, 1453 deletions
diff --git a/Documentation/ABI/obsolete/dv1394 b/Documentation/ABI/obsolete/dv1394
deleted file mode 100644
index 2ee36864ca10..000000000000
--- a/Documentation/ABI/obsolete/dv1394
+++ /dev/null
@@ -1,9 +0,0 @@
-What:           dv1394 (a.k.a. "OHCI-DV I/O support" for FireWire)
-Contact:        linux1394-devel@lists.sourceforge.net
-Description:
-        New application development should use raw1394 + userspace libraries
-        instead, notably libiec61883 which is functionally equivalent.
-Users:
-        ffmpeg/libavformat (used by a variety of media players)
-        dvgrab v1.x (replaced by dvgrab2 on top of raw1394 and resp. libraries)
diff --git a/Documentation/ABI/removed/dv1394 b/Documentation/ABI/removed/dv1394
new file mode 100644
index 000000000000..c2310b6676f4
--- /dev/null
+++ b/Documentation/ABI/removed/dv1394
@@ -0,0 +1,14 @@
+What:           dv1394 (a.k.a. "OHCI-DV I/O support" for FireWire)
+Date:           May 2010 (scheduled), finally removed in kernel v2.6.37
+Contact:        linux1394-devel@lists.sourceforge.net
+Description:
+        /dev/dv1394/* were character device files, one for each FireWire
+        controller and for NTSC and PAL respectively, from which DV data
+        could be received by read() or transmitted by write().  A few
+        ioctl()s allowed limited control.
+        This special-purpose interface has been superseded by libraw1394 +
+        libiec61883 which are functionally equivalent, support HDV, and
+        transparently work on top of the newer firewire kernel drivers.
+Users:
+        ffmpeg/libavformat (if configured for DV1394)
diff --git a/Documentation/ABI/removed/raw1394 b/Documentation/ABI/removed/raw1394
new file mode 100644
index 000000000000..490aa1efc4ae
--- /dev/null
+++ b/Documentation/ABI/removed/raw1394
@@ -0,0 +1,15 @@
+What:           raw1394 (a.k.a. "Raw IEEE1394 I/O support" for FireWire)
+Date:           May 2010 (scheduled), finally removed in kernel v2.6.37
+Contact:        linux1394-devel@lists.sourceforge.net
+Description:
+        /dev/raw1394 was a character device file that allowed low-level
+        access to FireWire buses.  Its major drawbacks were its inability
+        to implement sensible device security policies, and its low level
+        of abstraction that required userspace clients do duplicate much
+        of the kernel's ieee1394 core functionality.
+        Replaced by /dev/fw*, i.e. the <linux/firewire-cdev.h> ABI of
+        firewire-core.
+Users:
+        libraw1394 (works with firewire-cdev too, transparent to library ABI
+        users)
diff --git a/Documentation/ABI/removed/raw1394_legacy_isochronous b/Documentation/ABI/removed/raw1394_legacy_isochronous
deleted file mode 100644
index 1b629622d883..000000000000
--- a/Documentation/ABI/removed/raw1394_legacy_isochronous
+++ /dev/null
@@ -1,16 +0,0 @@
-What:           legacy isochronous ABI of raw1394 (1st generation iso ABI)
-Date:           June 2007 (scheduled), removed in kernel v2.6.23
-Contact:        linux1394-devel@lists.sourceforge.net
-Description:
-        The two request types RAW1394_REQ_ISO_SEND, RAW1394_REQ_ISO_LISTEN have
-        been deprecated for quite some time.  They are very inefficient as they
-        come with high interrupt load and several layers of callbacks for each
-        packet.  Because of these deficiencies, the video1394 and dv1394 drivers
-        and the 3rd-generation isochronous ABI in raw1394 (rawiso) were created.
-Users:
-        libraw1394 users via the long deprecated API raw1394_iso_write,
-        raw1394_start_iso_write, raw1394_start_iso_rcv, raw1394_stop_iso_rcv
-        libdc1394, which optionally uses these old libraw1394 calls
-        alternatively to the more efficient video1394 ABI
diff --git a/Documentation/ABI/removed/video1394 b/Documentation/ABI/removed/video1394
new file mode 100644
index 000000000000..c39c25aee77b
--- /dev/null
+++ b/Documentation/ABI/removed/video1394
@@ -0,0 +1,16 @@
+What:           video1394 (a.k.a. "OHCI-1394 Video support" for FireWire)
+Date:           May 2010 (scheduled), finally removed in kernel v2.6.37
+Contact:        linux1394-devel@lists.sourceforge.net
+Description:
+        /dev/video1394/* were character device files, one for each FireWire
+        controller, which were used for isochronous I/O.  It was added as an
+        alternative to raw1394's isochronous I/O functionality which had
+        performance issues in its first generation.  Any video1394 user had
+        to use raw1394 + libraw1394 too because video1394 did not provide
+        asynchronous I/O for device discovery and configuration.
+        Replaced by /dev/fw*, i.e. the <linux/firewire-cdev.h> ABI of
+        firewire-core.
+Users:
+        libdc1394 (works with firewire-cdev too, transparent to library ABI
+        users)
diff --git a/Documentation/ABI/testing/sysfs-ata b/Documentation/ABI/testing/sysfs-ata
new file mode 100644
index 000000000000..0a932155cbba
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-ata
@@ -0,0 +1,99 @@
+What:           /sys/class/ata_...
+Date:           August 2008
+Contact:        Gwendal Grignou<gwendal@google.com>
+Description:
+Provide a place in sysfs for storing the ATA topology of the system.  This allows
+retrieving various information about ATA objects.
+Files under /sys/class/ata_port
+-------------------------------
+        For each port, a directory ataX is created where X is the ata_port_id of
+        the port. The device parent is the ata host device.
+idle_irq (read)
+        Number of IRQ received by the port while idle [some ata HBA only].
+nr_pmp_links (read)
+        If a SATA Port Multiplier (PM) is connected, number of link behind it.
+Files under /sys/class/ata_link
+-------------------------------
+        Behind each port, there is a ata_link. If there is a SATA PM in the
+        topology, 15 ata_link objects are created.
+        If a link is behind a port, the directory name is linkX, where X is
+        ata_port_id of the port.
+        If a link is behind a PM, its name is linkX.Y where X is ata_port_id
+        of the parent port and Y the PM port.
+hw_sata_spd_limit
+        Maximum speed supported by the connected SATA device.
+sata_spd_limit
+        Maximum speed imposed by libata.
+sata_spd
+        Current speed of the link [1.5, 3Gps,...].
+Files under /sys/class/ata_device
+---------------------------------
+        Behind each link, up to two ata device are created.
+        The name of the directory is devX[.Y].Z where:
+        - X is ata_port_id of the port where the device is connected,
+        - Y the port of the PM if any, and
+        - Z the device id: for PATA, there is usually 2 devices [0,1],
+        only 1 for SATA.
+class
+        Device class. Can be "ata" for disk, "atapi" for packet device,
+        "pmp" for PM, or "none" if no device was found behind the link.
+dma_mode
+        Transfer modes supported by the device when in DMA mode.
+        Mostly used by PATA device.
+pio_mode
+        Transfer modes supported by the device when in PIO mode.
+        Mostly used by PATA device.
+xfer_mode
+        Current transfer mode.
+id
+        Cached result of IDENTIFY command, as described in ATA8 7.16 and 7.17.
+        Only valid if the device is not a PM.
+gscr
+        Cached result of the dump of PM GSCR register.
+        Valid registers are:
+        0:      SATA_PMP_GSCR_PROD_ID,
+        1:      SATA_PMP_GSCR_REV,
+        2:      SATA_PMP_GSCR_PORT_INFO,
+        32:     SATA_PMP_GSCR_ERROR,
+        33:     SATA_PMP_GSCR_ERROR_EN,
+        64:     SATA_PMP_GSCR_FEAT,
+        96:     SATA_PMP_GSCR_FEAT_EN,
+        130:    SATA_PMP_GSCR_SII_GPIO
+        Only valid if the device is a PM.
+spdn_cnt
+        Number of time libata decided to lower the speed of link due to errors.
+ering
+        Formatted output of the error ring of the device.
diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram
new file mode 100644
index 000000000000..c8b3b48ec62c
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-block-zram
@@ -0,0 +1,99 @@
+What:           /sys/block/zram<id>/disksize
+Date:           August 2010
+Contact:        Nitin Gupta <ngupta@vflare.org>
+Description:
+                The disksize file is read-write and specifies the disk size
+                which represents the limit on the *uncompressed* worth of data
+                that can be stored in this disk.
+What:           /sys/block/zram<id>/initstate
+Date:           August 2010
+Contact:        Nitin Gupta <ngupta@vflare.org>
+Description:
+                The disksize file is read-only and shows the initialization
+                state of the device.
+What:           /sys/block/zram<id>/reset
+Date:           August 2010
+Contact:        Nitin Gupta <ngupta@vflare.org>
+Description:
+                The disksize file is write-only and allows resetting the
+                device. The reset operation frees all the memory assocaited
+                with this device.
+What:           /sys/block/zram<id>/num_reads
+Date:           August 2010
+Contact:        Nitin Gupta <ngupta@vflare.org>
+Description:
+                The num_reads file is read-only and specifies the number of
+                reads (failed or successful) done on this device.
+What:           /sys/block/zram<id>/num_writes
+Date:           August 2010
+Contact:        Nitin Gupta <ngupta@vflare.org>
+Description:
+                The num_writes file is read-only and specifies the number of
+                writes (failed or successful) done on this device.
+What:           /sys/block/zram<id>/invalid_io
+Date:           August 2010
+Contact:        Nitin Gupta <ngupta@vflare.org>
+Description:
+                The invalid_io file is read-only and specifies the number of
+                non-page-size-aligned I/O requests issued to this device.
+What:           /sys/block/zram<id>/notify_free
+Date:           August 2010
+Contact:        Nitin Gupta <ngupta@vflare.org>
+Description:
+                The notify_free file is read-only and specifies the number of
+                swap slot free notifications received by this device. These
+                notifications are send to a swap block device when a swap slot
+                is freed. This statistic is applicable only when this disk is
+                being used as a swap disk.
+What:           /sys/block/zram<id>/discard
+Date:           August 2010
+Contact:        Nitin Gupta <ngupta@vflare.org>
+Description:
+                The discard file is read-only and specifies the number of
+                discard requests received by this device. These requests
+                provide information to block device regarding blocks which are
+                no longer used by filesystem.
+What:           /sys/block/zram<id>/zero_pages
+Date:           August 2010
+Contact:        Nitin Gupta <ngupta@vflare.org>
+Description:
+                The zero_pages file is read-only and specifies number of zero
+                filled pages written to this disk. No memory is allocated for
+                such pages.
+What:           /sys/block/zram<id>/orig_data_size
+Date:           August 2010
+Contact:        Nitin Gupta <ngupta@vflare.org>
+Description:
+                The orig_data_size file is read-only and specifies uncompressed
+                size of data stored in this disk. This excludes zero-filled
+                pages (zero_pages) since no memory is allocated for them.
+                Unit: bytes
+What:           /sys/block/zram<id>/compr_data_size
+Date:           August 2010
+Contact:        Nitin Gupta <ngupta@vflare.org>
+Description:
+                The compr_data_size file is read-only and specifies compressed
+                size of data stored in this disk. So, compression ratio can be
+                calculated using orig_data_size and this statistic.
+                Unit: bytes
+What:           /sys/block/zram<id>/mem_used_total
+Date:           August 2010
+Contact:        Nitin Gupta <ngupta@vflare.org>
+Description:
+                The mem_used_total file is read-only and specifies the amount
+                of memory, including allocator fragmentation and metadata
+                overhead, allocated for this disk. So, allocator space
+                efficiency can be calculated using compr_data_size and this
+                statistic.
+                Unit: bytes
+\ No newline at end of file
diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power
index 6123c523bfd7..7628cd1bc36a 100644
--- a/Documentation/ABI/testing/sysfs-devices-power
+++ b/Documentation/ABI/testing/sysfs-devices-power
@@ -77,3 +77,91 @@ Description:
                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.
+What:           /sys/devices/.../power/wakeup_count
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_count attribute contains the number
+                of signaled wakeup events associated with the device.  This
+                attribute is read-only.  If the device is not enabled to wake up
+                the system from sleep states, this attribute is empty.
+What:           /sys/devices/.../power/wakeup_active_count
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_active_count attribute contains the
+                number of times the processing of wakeup events associated with
+                the device was completed (at the kernel level).  This attribute
+                is read-only.  If the device is not enabled to wake up the
+                system from sleep states, this attribute is empty.
+What:           /sys/devices/.../power/wakeup_hit_count
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_hit_count attribute contains the
+                number of times the processing of a wakeup event associated with
+                the device might prevent the system from entering a sleep state.
+                This attribute is read-only.  If the device is not enabled to
+                wake up the system from sleep states, this attribute is empty.
+What:           /sys/devices/.../power/wakeup_active
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_active attribute contains either 1,
+                or 0, depending on whether or not a wakeup event associated with
+                the device is being processed (1).  This attribute is read-only.
+                If the device is not enabled to wake up the system from sleep
+                states, this attribute is empty.
+What:           /sys/devices/.../power/wakeup_total_time_ms
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_total_time_ms attribute contains
+                the total time of processing wakeup events associated with the
+                device, in milliseconds.  This attribute is read-only.  If the
+                device is not enabled to wake up the system from sleep states,
+                this attribute is empty.
+What:           /sys/devices/.../power/wakeup_max_time_ms
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_max_time_ms attribute contains
+                the maximum time of processing a single wakeup event associated
+                with the device, in milliseconds.  This attribute is read-only.
+                If the device is not enabled to wake up the system from sleep
+                states, this attribute is empty.
+What:           /sys/devices/.../power/wakeup_last_time_ms
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_last_time_ms attribute contains
+                the value of the monotonic clock corresponding to the time of
+                signaling the last wakeup event associated with the device, in
+                milliseconds.  This attribute is read-only.  If the device is
+                not enabled to wake up the system from sleep states, this
+                attribute is empty.
+What:           /sys/devices/.../power/autosuspend_delay_ms
+Date:           September 2010
+Contact:        Alan Stern <stern@rowland.harvard.edu>
+Description:
+                The /sys/devices/.../power/autosuspend_delay_ms attribute
+                contains the autosuspend delay value (in milliseconds).  Some
+                drivers do not want their device to suspend as soon as it
+                becomes idle at run time; they want the device to remain
+                inactive for a certain minimum period of time first.  That
+                period is called the autosuspend delay.  Negative values will
+                prevent the device from being suspended at run time (similar
+                to writing "on" to the power/control attribute).  Values >=
+                1000 will cause the autosuspend timer expiration to be rounded
+                up to the nearest second.
+                Not all drivers support this attribute.  If it isn't supported,
+                attempts to read or write it will yield I/O errors.
diff --git a/Documentation/ABI/testing/sysfs-devices-system-ibm-rtl b/Documentation/ABI/testing/sysfs-devices-system-ibm-rtl
new file mode 100644
index 000000000000..b82deeaec314
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-system-ibm-rtl
@@ -0,0 +1,22 @@
+What:           state
+Date:           Sep 2010
+KernelVersion:  2.6.37
+Contact:        Vernon Mauery <vernux@us.ibm.com>
+Description:    The state file allows a means by which to change in and
+                out of Premium Real-Time Mode (PRTM), as well as the
+                ability to query the current state.
+                    0 => PRTM off
+                    1 => PRTM enabled
+Users:          The ibm-prtm userspace daemon uses this interface.
+What:           version
+Date:           Sep 2010
+KernelVersion:  2.6.37
+Contact:        Vernon Mauery <vernux@us.ibm.com>
+Description:    The version file provides a means by which to query
+                the RTL table version that lives in the Extended
+                BIOS Data Area (EBDA).
+Users:          The ibm-prtm userspace daemon uses this interface.
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-roccat-pyra b/Documentation/ABI/testing/sysfs-driver-hid-roccat-pyra
new file mode 100644
index 000000000000..ad1125b02ff4
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-hid-roccat-pyra
@@ -0,0 +1,98 @@
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/actual_cpi
+Date:           August 2010
+Contact:        Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:    It is possible to switch the cpi setting of the mouse with the
+                press of a button.
+                When read, this file returns the raw number of the actual cpi
+                setting reported by the mouse. This number has to be further
+                processed to receive the real dpi value.
+                VALUE DPI
+                1     400
+                2     800
+                4     1600
+                This file is readonly.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/actual_profile
+Date:           August 2010
+Contact:        Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:    When read, this file returns the number of the actual profile in
+                range 0-4.
+                This file is readonly.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/firmware_version
+Date:           August 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>/profile_settings
+Date:           August 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 is split in settings and buttons.
+                profile_settings holds informations like resolution, sensitivity
+                and light effects.
+                When written, this file lets one write the respective profile
+                settings back to the mouse. The data has to be 13 bytes long.
+                The mouse will reject invalid data.
+                Which profile to write is determined by the profile number
+                contained in the data.
+                This file is writeonly.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/profile[1-5]_settings
+Date:           August 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 is split in settings and buttons.
+                profile_settings holds informations like resolution, sensitivity
+                and light effects.
+                When read, these files return the respective profile settings.
+                The returned data is 13 bytes in size.
+                This file is readonly.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/profile_buttons
+Date:           August 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 is split in settings and buttons.
+                profile_buttons holds informations about button layout.
+                When written, this file lets one write the respective profile
+                buttons back to the mouse. The data has to be 19 bytes long.
+                The mouse will reject invalid data.
+                Which profile to write is determined by the profile number
+                contained in the data.
+                This file is writeonly.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/profile[1-5]_buttons
+Date:           August 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 is split in settings and buttons.
+                profile_buttons holds informations about button layout.
+                When read, these files return the respective profile buttons.
+                The returned data is 19 bytes in size.
+                This file is readonly.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/startup_profile
+Date:           August 2010
+Contact:        Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:    The integer value of this attribute ranges from 0-4.
+                When read, this attribute returns the number of the profile
+                that's active when the mouse is powered on.
+                This file is readonly.
+What:           /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/settings
+Date:           August 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 3 bytes and holds information on the
+                startup_profile.
+                When written, this file lets write settings back to the mouse.
+                The data has to be 3 bytes long. The mouse will reject invalid
+                data.
diff --git a/Documentation/ABI/testing/sysfs-module b/Documentation/ABI/testing/sysfs-module
new file mode 100644
index 000000000000..cfcec3bffc0a
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-module
@@ -0,0 +1,12 @@
+What:           /sys/module/pch_phub/drivers/.../pch_mac
+Date:           August 2010
+KernelVersion:  2.6.35
+Contact:        masa-korg@dsn.okisemi.com
+Description:    Write/read GbE MAC address.
+What:           /sys/module/pch_phub/drivers/.../pch_firmware
+Date:           August 2010
+KernelVersion:  2.6.35
+Contact:        masa-korg@dsn.okisemi.com
+Description:    Write/read Option ROM data.
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index 2875f1f74a07..194ca446ac28 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -99,9 +99,38 @@ Description:
                dmesg -s 1000000 | grep 'hash matches'
+                If you do not get any matches (or they appear to be false
+                positives), it is possible that the last PM event point
+                referred to a device created by a loadable kernel module.  In
+                this case cat /sys/power/pm_trace_dev_match (see below) after
+                your system is started up and the kernel modules are loaded.
                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_trace_dev_match
+Date:           October 2010
+Contact:        James Hogan <james@albanarts.com>
+Description:
+                The /sys/power/pm_trace_dev_match file contains the name of the
+                device associated with the last PM event point saved in the RTC
+                across reboots when pm_trace has been used.  More precisely it
+                contains the list of current devices (including those
+                registered by loadable kernel modules since boot) which match
+                the device hash in the RTC at boot, with a newline after each
+                one.
+                The advantage of this file over the hash matches printed to the
+                kernel log (see /sys/power/pm_trace), is that it includes
+                devices created after boot by loadable kernel modules.
+                Due to the small hash size necessary to fit in the RTC, it is
+                possible that more than one device matches the hash, in which
+                case further investigation is required to determine which
+                device is causing the problem.  Note that genuine RTC clock
+                values (such as when pm_trace has not been used), can still
+                match a device and output it's name here.
 What:           /sys/power/pm_async
 Date:           January 2009
 Contact:        Rafael J. Wysocki <rjw@sisk.pl>
diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl
new file mode 100644
index 000000000000..19a1210c2530
--- /dev/null
+++ b/Documentation/DocBook/80211.tmpl
@@ -0,0 +1,495 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE set PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
+        "http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
+<set>
+  <setinfo>
+    <title>The 802.11 subsystems &ndash; for kernel developers</title>
+    <subtitle>
+      Explaining wireless 802.11 networking in the Linux kernel
+    </subtitle>
+    <copyright>
+      <year>2007-2009</year>
+      <holder>Johannes Berg</holder>
+    </copyright>
+    <authorgroup>
+      <author>
+        <firstname>Johannes</firstname>
+        <surname>Berg</surname>
+        <affiliation>
+          <address><email>johannes@sipsolutions.net</email></address>
+        </affiliation>
+      </author>
+    </authorgroup>
+    <legalnotice>
+      <para>
+        This documentation is free software; you can redistribute
+        it and/or modify it under the terms of the GNU General Public
+        License version 2 as published by the Free Software Foundation.
+      </para>
+      <para>
+        This documentation 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.
+      </para>
+      <para>
+        You should have received a copy of the GNU General Public
+        License along with this documentation; if not, write to the Free
+        Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+        MA 02111-1307 USA
+      </para>
+      <para>
+        For more details see the file COPYING in the source
+        distribution of Linux.
+      </para>
+    </legalnotice>
+    <abstract>
+      <para>
+        These books attempt to give a description of the
+        various subsystems that play a role in 802.11 wireless
+        networking in Linux. Since these books are for kernel
+        developers they attempts to document the structures
+        and functions used in the kernel as well as giving a
+        higher-level overview.
+      </para>
+      <para>
+        The reader is expected to be familiar with the 802.11
+        standard as published by the IEEE in 802.11-2007 (or
+        possibly later versions). References to this standard
+        will be given as "802.11-2007 8.1.5".
+      </para>
+    </abstract>
+  </setinfo>
+  <book id="cfg80211-developers-guide">
+    <bookinfo>
+      <title>The cfg80211 subsystem</title>
+      <abstract>
+!Pinclude/net/cfg80211.h Introduction
+      </abstract>
+    </bookinfo>
+      <chapter>
+      <title>Device registration</title>
+!Pinclude/net/cfg80211.h Device registration
+!Finclude/net/cfg80211.h ieee80211_band
+!Finclude/net/cfg80211.h ieee80211_channel_flags
+!Finclude/net/cfg80211.h ieee80211_channel
+!Finclude/net/cfg80211.h ieee80211_rate_flags
+!Finclude/net/cfg80211.h ieee80211_rate
+!Finclude/net/cfg80211.h ieee80211_sta_ht_cap
+!Finclude/net/cfg80211.h ieee80211_supported_band
+!Finclude/net/cfg80211.h cfg80211_signal_type
+!Finclude/net/cfg80211.h wiphy_params_flags
+!Finclude/net/cfg80211.h wiphy_flags
+!Finclude/net/cfg80211.h wiphy
+!Finclude/net/cfg80211.h wireless_dev
+!Finclude/net/cfg80211.h wiphy_new
+!Finclude/net/cfg80211.h wiphy_register
+!Finclude/net/cfg80211.h wiphy_unregister
+!Finclude/net/cfg80211.h wiphy_free
+!Finclude/net/cfg80211.h wiphy_name
+!Finclude/net/cfg80211.h wiphy_dev
+!Finclude/net/cfg80211.h wiphy_priv
+!Finclude/net/cfg80211.h priv_to_wiphy
+!Finclude/net/cfg80211.h set_wiphy_dev
+!Finclude/net/cfg80211.h wdev_priv
+      </chapter>
+      <chapter>
+      <title>Actions and configuration</title>
+!Pinclude/net/cfg80211.h Actions and configuration
+!Finclude/net/cfg80211.h cfg80211_ops
+!Finclude/net/cfg80211.h vif_params
+!Finclude/net/cfg80211.h key_params
+!Finclude/net/cfg80211.h survey_info_flags
+!Finclude/net/cfg80211.h survey_info
+!Finclude/net/cfg80211.h beacon_parameters
+!Finclude/net/cfg80211.h plink_actions
+!Finclude/net/cfg80211.h station_parameters
+!Finclude/net/cfg80211.h station_info_flags
+!Finclude/net/cfg80211.h rate_info_flags
+!Finclude/net/cfg80211.h rate_info
+!Finclude/net/cfg80211.h station_info
+!Finclude/net/cfg80211.h monitor_flags
+!Finclude/net/cfg80211.h mpath_info_flags
+!Finclude/net/cfg80211.h mpath_info
+!Finclude/net/cfg80211.h bss_parameters
+!Finclude/net/cfg80211.h ieee80211_txq_params
+!Finclude/net/cfg80211.h cfg80211_crypto_settings
+!Finclude/net/cfg80211.h cfg80211_auth_request
+!Finclude/net/cfg80211.h cfg80211_assoc_request
+!Finclude/net/cfg80211.h cfg80211_deauth_request
+!Finclude/net/cfg80211.h cfg80211_disassoc_request
+!Finclude/net/cfg80211.h cfg80211_ibss_params
+!Finclude/net/cfg80211.h cfg80211_connect_params
+!Finclude/net/cfg80211.h cfg80211_pmksa
+!Finclude/net/cfg80211.h cfg80211_send_rx_auth
+!Finclude/net/cfg80211.h cfg80211_send_auth_timeout
+!Finclude/net/cfg80211.h __cfg80211_auth_canceled
+!Finclude/net/cfg80211.h cfg80211_send_rx_assoc
+!Finclude/net/cfg80211.h cfg80211_send_assoc_timeout
+!Finclude/net/cfg80211.h cfg80211_send_deauth
+!Finclude/net/cfg80211.h __cfg80211_send_deauth
+!Finclude/net/cfg80211.h cfg80211_send_disassoc
+!Finclude/net/cfg80211.h __cfg80211_send_disassoc
+!Finclude/net/cfg80211.h cfg80211_ibss_joined
+!Finclude/net/cfg80211.h cfg80211_connect_result
+!Finclude/net/cfg80211.h cfg80211_roamed
+!Finclude/net/cfg80211.h cfg80211_disconnected
+!Finclude/net/cfg80211.h cfg80211_ready_on_channel
+!Finclude/net/cfg80211.h cfg80211_remain_on_channel_expired
+!Finclude/net/cfg80211.h cfg80211_new_sta
+!Finclude/net/cfg80211.h cfg80211_rx_mgmt
+!Finclude/net/cfg80211.h cfg80211_mgmt_tx_status
+!Finclude/net/cfg80211.h cfg80211_cqm_rssi_notify
+!Finclude/net/cfg80211.h cfg80211_michael_mic_failure
+      </chapter>
+      <chapter>
+      <title>Scanning and BSS list handling</title>
+!Pinclude/net/cfg80211.h Scanning and BSS list handling
+!Finclude/net/cfg80211.h cfg80211_ssid
+!Finclude/net/cfg80211.h cfg80211_scan_request
+!Finclude/net/cfg80211.h cfg80211_scan_done
+!Finclude/net/cfg80211.h cfg80211_bss
+!Finclude/net/cfg80211.h cfg80211_inform_bss_frame
+!Finclude/net/cfg80211.h cfg80211_inform_bss
+!Finclude/net/cfg80211.h cfg80211_unlink_bss
+!Finclude/net/cfg80211.h cfg80211_find_ie
+!Finclude/net/cfg80211.h ieee80211_bss_get_ie
+      </chapter>
+      <chapter>
+      <title>Utility functions</title>
+!Pinclude/net/cfg80211.h Utility functions
+!Finclude/net/cfg80211.h ieee80211_channel_to_frequency
+!Finclude/net/cfg80211.h ieee80211_frequency_to_channel
+!Finclude/net/cfg80211.h ieee80211_get_channel
+!Finclude/net/cfg80211.h ieee80211_get_response_rate
+!Finclude/net/cfg80211.h ieee80211_hdrlen
+!Finclude/net/cfg80211.h ieee80211_get_hdrlen_from_skb
+!Finclude/net/cfg80211.h ieee80211_radiotap_iterator
+      </chapter>
+      <chapter>
+      <title>Data path helpers</title>
+!Pinclude/net/cfg80211.h Data path helpers
+!Finclude/net/cfg80211.h ieee80211_data_to_8023
+!Finclude/net/cfg80211.h ieee80211_data_from_8023
+!Finclude/net/cfg80211.h ieee80211_amsdu_to_8023s
+!Finclude/net/cfg80211.h cfg80211_classify8021d
+      </chapter>
+      <chapter>
+      <title>Regulatory enforcement infrastructure</title>
+!Pinclude/net/cfg80211.h Regulatory enforcement infrastructure
+!Finclude/net/cfg80211.h regulatory_hint
+!Finclude/net/cfg80211.h wiphy_apply_custom_regulatory
+!Finclude/net/cfg80211.h freq_reg_info
+      </chapter>
+      <chapter>
+      <title>RFkill integration</title>
+!Pinclude/net/cfg80211.h RFkill integration
+!Finclude/net/cfg80211.h wiphy_rfkill_set_hw_state
+!Finclude/net/cfg80211.h wiphy_rfkill_start_polling
+!Finclude/net/cfg80211.h wiphy_rfkill_stop_polling
+      </chapter>
+      <chapter>
+      <title>Test mode</title>
+!Pinclude/net/cfg80211.h Test mode
+!Finclude/net/cfg80211.h cfg80211_testmode_alloc_reply_skb
+!Finclude/net/cfg80211.h cfg80211_testmode_reply
+!Finclude/net/cfg80211.h cfg80211_testmode_alloc_event_skb
+!Finclude/net/cfg80211.h cfg80211_testmode_event
+      </chapter>
+  </book>
+  <book id="mac80211-developers-guide">
+    <bookinfo>
+      <title>The mac80211 subsystem</title>
+      <abstract>
+!Pinclude/net/mac80211.h Introduction
+!Pinclude/net/mac80211.h Warning
+      </abstract>
+    </bookinfo>
+    <toc></toc>
+  <!--
+  Generally, this document shall be ordered by increasing complexity.
+  It is important to note that readers should be able to read only
+  the first few sections to get a working driver and only advanced
+  usage should require reading the full document.
+  -->
+    <part>
+      <title>The basic mac80211 driver interface</title>
+      <partintro>
+        <para>
+          You should read and understand the information contained
+          within this part of the book while implementing a driver.
+          In some chapters, advanced usage is noted, that may be
+          skipped at first.
+        </para>
+        <para>
+          This part of the book only covers station and monitor mode
+          functionality, additional information required to implement
+          the other modes is covered in the second part of the book.
+        </para>
+      </partintro>
+      <chapter id="basics">
+        <title>Basic hardware handling</title>
+        <para>TBD</para>
+        <para>
+          This chapter shall contain information on getting a hw
+          struct allocated and registered with mac80211.
+        </para>
+        <para>
+          Since it is required to allocate rates/modes before registering
+          a hw struct, this chapter shall also contain information on setting
+          up the rate/mode structs.
+        </para>
+        <para>
+          Additionally, some discussion about the callbacks and
+          the general programming model should be in here, including
+          the definition of ieee80211_ops which will be referred to
+          a lot.
+        </para>
+        <para>
+          Finally, a discussion of hardware capabilities should be done
+          with references to other parts of the book.
+        </para>
+  <!-- intentionally multiple !F lines to get proper order -->
+!Finclude/net/mac80211.h ieee80211_hw
+!Finclude/net/mac80211.h ieee80211_hw_flags
+!Finclude/net/mac80211.h SET_IEEE80211_DEV
+!Finclude/net/mac80211.h SET_IEEE80211_PERM_ADDR
+!Finclude/net/mac80211.h ieee80211_ops
+!Finclude/net/mac80211.h ieee80211_alloc_hw
+!Finclude/net/mac80211.h ieee80211_register_hw
+!Finclude/net/mac80211.h ieee80211_get_tx_led_name
+!Finclude/net/mac80211.h ieee80211_get_rx_led_name
+!Finclude/net/mac80211.h ieee80211_get_assoc_led_name
+!Finclude/net/mac80211.h ieee80211_get_radio_led_name
+!Finclude/net/mac80211.h ieee80211_unregister_hw
+!Finclude/net/mac80211.h ieee80211_free_hw
+      </chapter>
+      <chapter id="phy-handling">
+        <title>PHY configuration</title>
+        <para>TBD</para>
+        <para>
+          This chapter should describe PHY handling including
+          start/stop callbacks and the various structures used.
+        </para>
+!Finclude/net/mac80211.h ieee80211_conf
+!Finclude/net/mac80211.h ieee80211_conf_flags
+      </chapter>
+      <chapter id="iface-handling">
+        <title>Virtual interfaces</title>
+        <para>TBD</para>
+        <para>
+          This chapter should describe virtual interface basics
+          that are relevant to the driver (VLANs, MGMT etc are not.)
+          It should explain the use of the add_iface/remove_iface
+          callbacks as well as the interface configuration callbacks.
+        </para>
+        <para>Things related to AP mode should be discussed there.</para>
+        <para>
+          Things related to supporting multiple interfaces should be
+          in the appropriate chapter, a BIG FAT note should be here about
+          this though and the recommendation to allow only a single
+          interface in STA mode at first!
+        </para>
+!Finclude/net/mac80211.h ieee80211_vif
+      </chapter>
+      <chapter id="rx-tx">
+        <title>Receive and transmit processing</title>
+        <sect1>
+          <title>what should be here</title>
+          <para>TBD</para>
+          <para>
+            This should describe the receive and transmit
+            paths in mac80211/the drivers as well as
+            transmit status handling.
+          </para>
+        </sect1>
+        <sect1>
+          <title>Frame format</title>
+!Pinclude/net/mac80211.h Frame format
+        </sect1>
+        <sect1>
+          <title>Packet alignment</title>
+!Pnet/mac80211/rx.c Packet alignment
+        </sect1>
+        <sect1>
+          <title>Calling into mac80211 from interrupts</title>
+!Pinclude/net/mac80211.h Calling mac80211 from interrupts
+        </sect1>
+        <sect1>
+          <title>functions/definitions</title>
+!Finclude/net/mac80211.h ieee80211_rx_status
+!Finclude/net/mac80211.h mac80211_rx_flags
+!Finclude/net/mac80211.h ieee80211_tx_info
+!Finclude/net/mac80211.h ieee80211_rx
+!Finclude/net/mac80211.h ieee80211_rx_irqsafe
+!Finclude/net/mac80211.h ieee80211_tx_status
+!Finclude/net/mac80211.h ieee80211_tx_status_irqsafe
+!Finclude/net/mac80211.h ieee80211_rts_get
+!Finclude/net/mac80211.h ieee80211_rts_duration
+!Finclude/net/mac80211.h ieee80211_ctstoself_get
+!Finclude/net/mac80211.h ieee80211_ctstoself_duration
+!Finclude/net/mac80211.h ieee80211_generic_frame_duration
+!Finclude/net/mac80211.h ieee80211_wake_queue
+!Finclude/net/mac80211.h ieee80211_stop_queue
+!Finclude/net/mac80211.h ieee80211_wake_queues
+!Finclude/net/mac80211.h ieee80211_stop_queues
+        </sect1>
+      </chapter>
+      <chapter id="filters">
+        <title>Frame filtering</title>
+!Pinclude/net/mac80211.h Frame filtering
+!Finclude/net/mac80211.h ieee80211_filter_flags
+      </chapter>
+    </part>
+    <part id="advanced">
+      <title>Advanced driver interface</title>
+      <partintro>
+        <para>
+         Information contained within this part of the book is
+         of interest only for advanced interaction of mac80211
+         with drivers to exploit more hardware capabilities and
+         improve performance.
+        </para>
+      </partintro>
+      <chapter id="hardware-crypto-offload">
+        <title>Hardware crypto acceleration</title>
+!Pinclude/net/mac80211.h Hardware crypto acceleration
+  <!-- intentionally multiple !F lines to get proper order -->
+!Finclude/net/mac80211.h set_key_cmd
+!Finclude/net/mac80211.h ieee80211_key_conf
+!Finclude/net/mac80211.h ieee80211_key_flags
+      </chapter>
+      <chapter id="powersave">
+        <title>Powersave support</title>
+!Pinclude/net/mac80211.h Powersave support
+      </chapter>
+      <chapter id="beacon-filter">
+        <title>Beacon filter support</title>
+!Pinclude/net/mac80211.h Beacon filter support
+!Finclude/net/mac80211.h ieee80211_beacon_loss
+      </chapter>
+      <chapter id="qos">
+        <title>Multiple queues and QoS support</title>
+        <para>TBD</para>
+!Finclude/net/mac80211.h ieee80211_tx_queue_params
+      </chapter>
+      <chapter id="AP">
+        <title>Access point mode support</title>
+        <para>TBD</para>
+        <para>Some parts of the if_conf should be discussed here instead</para>
+        <para>
+          Insert notes about VLAN interfaces with hw crypto here or
+          in the hw crypto chapter.
+        </para>
+!Finclude/net/mac80211.h ieee80211_get_buffered_bc
+!Finclude/net/mac80211.h ieee80211_beacon_get
+      </chapter>
+      <chapter id="multi-iface">
+        <title>Supporting multiple virtual interfaces</title>
+        <para>TBD</para>
+        <para>
+          Note: WDS with identical MAC address should almost always be OK
+        </para>
+        <para>
+          Insert notes about having multiple virtual interfaces with
+          different MAC addresses here, note which configurations are
+          supported by mac80211, add notes about supporting hw crypto
+          with it.
+        </para>
+      </chapter>
+      <chapter id="hardware-scan-offload">
+        <title>Hardware scan offload</title>
+        <para>TBD</para>
+!Finclude/net/mac80211.h ieee80211_scan_completed
+      </chapter>
+    </part>
+    <part id="rate-control">
+      <title>Rate control interface</title>
+      <partintro>
+        <para>TBD</para>
+        <para>
+         This part of the book describes the rate control algorithm
+         interface and how it relates to mac80211 and drivers.
+        </para>
+      </partintro>
+      <chapter id="dummy">
+        <title>dummy chapter</title>
+        <para>TBD</para>
+      </chapter>
+    </part>
+    <part id="internal">
+      <title>Internals</title>
+      <partintro>
+        <para>TBD</para>
+        <para>
+         This part of the book describes mac80211 internals.
+        </para>
+      </partintro>
+      <chapter id="key-handling">
+        <title>Key handling</title>
+        <sect1>
+          <title>Key handling basics</title>
+!Pnet/mac80211/key.c Key handling basics
+        </sect1>
+        <sect1>
+          <title>MORE TBD</title>
+          <para>TBD</para>
+        </sect1>
+      </chapter>
+      <chapter id="rx-processing">
+        <title>Receive processing</title>
+        <para>TBD</para>
+      </chapter>
+      <chapter id="tx-processing">
+        <title>Transmit processing</title>
+        <para>TBD</para>
+      </chapter>
+      <chapter id="sta-info">
+        <title>Station info handling</title>
+        <sect1>
+          <title>Programming information</title>
+!Fnet/mac80211/sta_info.h sta_info
+!Fnet/mac80211/sta_info.h ieee80211_sta_info_flags
+        </sect1>
+        <sect1>
+          <title>STA information lifetime rules</title>
+!Pnet/mac80211/sta_info.c STA information lifetime rules
+        </sect1>
+      </chapter>
+      <chapter id="synchronisation">
+        <title>Synchronisation</title>
+        <para>TBD</para>
+        <para>Locking, lots of RCU</para>
+      </chapter>
+    </part>
+  </book>
+</set>
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index 34929f24c284..8b6e00a71034 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -12,7 +12,7 @@ DOCBOOKS := z8530book.xml mcabook.xml device-drivers.xml \
            kernel-api.xml filesystems.xml lsm.xml usb.xml kgdb.xml \
            gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
            genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
-            mac80211.xml debugobjects.xml sh.xml regulator.xml \
+            80211.xml debugobjects.xml sh.xml regulator.xml \
            alsa-driver-api.xml writing-an-alsa-driver.xml \
            tracepoint.xml media.xml drm.xml
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index feca0758391e..22edcbb9ddaf 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -51,8 +51,13 @@
     <sect1><title>Delaying, scheduling, and timer routines</title>
 !Iinclude/linux/sched.h
 !Ekernel/sched.c
+!Iinclude/linux/completion.h
 !Ekernel/timer.c
     </sect1>
+     <sect1><title>Wait queues and Wake events</title>
+!Iinclude/linux/wait.h
+!Ekernel/wait.c
+     </sect1>
     <sect1><title>High-resolution timers</title>
 !Iinclude/linux/ktime.h
 !Iinclude/linux/hrtimer.h
diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index 910c923a9b86..2861055afd7a 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -136,6 +136,7 @@
 #ifdef CONFIG_COMPAT
                .compat_ioctl = i915_compat_ioctl,
 #endif
+                .llseek = noop_llseek,
                },
        .pci_driver = {
                .name = DRIVER_NAME,
diff --git a/Documentation/DocBook/genericirq.tmpl b/Documentation/DocBook/genericirq.tmpl
index 1448b33fd222..fb10fd08c05c 100644
--- a/Documentation/DocBook/genericirq.tmpl
+++ b/Documentation/DocBook/genericirq.tmpl
@@ -28,7 +28,7 @@
  </authorgroup>
  <copyright>
-   <year>2005-2006</year>
+   <year>2005-2010</year>
   <holder>Thomas Gleixner</holder>
  </copyright>
  <copyright>
@@ -100,6 +100,10 @@
          <listitem><para>Edge type</para></listitem>
          <listitem><para>Simple type</para></listitem>
        </itemizedlist>
+        During the implementation we identified another type:
+        <itemizedlist>
+          <listitem><para>Fast EOI type</para></listitem>
+        </itemizedlist>
        In the SMP world of the __do_IRQ() super-handler another type
        was identified:
        <itemizedlist>
@@ -153,6 +157,7 @@
        is still available. This leads to a kind of duality for the time
        being. Over time the new model should be used in more and more
        architectures, as it enables smaller and cleaner IRQ subsystems.
+        It's deprecated for three years now and about to be removed.
        </para>
  </chapter>
  <chapter id="bugs">
@@ -217,6 +222,7 @@
          <itemizedlist>
          <listitem><para>handle_level_irq</para></listitem>
          <listitem><para>handle_edge_irq</para></listitem>
+          <listitem><para>handle_fasteoi_irq</para></listitem>
          <listitem><para>handle_simple_irq</para></listitem>
          <listitem><para>handle_percpu_irq</para></listitem>
          </itemizedlist>
@@ -233,33 +239,33 @@
                are used by the default flow implementations.
                The following helper functions are implemented (simplified excerpt):
                <programlisting>
-default_enable(irq)
+default_enable(struct irq_data *data)
 {
-        desc->chip->unmask(irq);
+        desc->chip->irq_unmask(data);
 }
-default_disable(irq)
+default_disable(struct irq_data *data)
 {
-        if (!delay_disable(irq))
+        if (!delay_disable(data))
-                desc->chip->mask(irq);
+                desc->chip->irq_mask(data);
 }
-default_ack(irq)
+default_ack(struct irq_data *data)
 {
-        chip->ack(irq);
+        chip->irq_ack(data);
 }
-default_mask_ack(irq)
+default_mask_ack(struct irq_data *data)
 {
-        if (chip->mask_ack) {
+        if (chip->irq_mask_ack) {
-                chip->mask_ack(irq);
+                chip->irq_mask_ack(data);
        } else {
-                chip->mask(irq);
+                chip->irq_mask(data);
-                chip->ack(irq);
+                chip->irq_ack(data);
        }
 }
-noop(irq)
+noop(struct irq_data *data))
 {
 }
@@ -278,12 +284,27 @@ noop(irq)
                <para>
                The following control flow is implemented (simplified excerpt):
                <programlisting>
-desc->chip->start();
+desc->chip->irq_mask();
 handle_IRQ_event(desc->action);
-desc->chip->end();
+desc->chip->irq_unmask();
                </programlisting>
                </para>
-            </sect3>
+            </sect3>
+            <sect3 id="Default_FASTEOI_IRQ_flow_handler">
+                <title>Default Fast EOI IRQ flow handler</title>
+                <para>
+                handle_fasteoi_irq provides a generic implementation
+                for interrupts, which only need an EOI at the end of
+                the handler
+                </para>
+                <para>
+                The following control flow is implemented (simplified excerpt):
+                <programlisting>
+handle_IRQ_event(desc->action);
+desc->chip->irq_eoi();
+                </programlisting>
+                </para>
+            </sect3>
            <sect3 id="Default_Edge_IRQ_flow_handler">
                <title>Default Edge IRQ flow handler</title>
                <para>
@@ -294,20 +315,19 @@ desc->chip->end();
                The following control flow is implemented (simplified excerpt):
                <programlisting>
 if (desc->status &amp; running) {
-        desc->chip->hold();
+        desc->chip->irq_mask();
        desc->status |= pending | masked;
        return;
 }
-desc->chip->start();
+desc->chip->irq_ack();
 desc->status |= running;
 do {
        if (desc->status &amp; masked)
-                desc->chip->enable();
+                desc->chip->irq_unmask();
        desc->status &amp;= ~pending;
        handle_IRQ_event(desc->action);
 } while (status &amp; pending);
 desc->status &amp;= ~running;
-desc->chip->end();
                </programlisting>
                </para>
            </sect3>
@@ -342,9 +362,9 @@ handle_IRQ_event(desc->action);
                <para>
                The following control flow is implemented (simplified excerpt):
                <programlisting>
-desc->chip->start();
 handle_IRQ_event(desc->action);
-desc->chip->end();
+if (desc->chip->irq_eoi)
+        desc->chip->irq_eoi();
                </programlisting>
                </para>
            </sect3>
@@ -375,8 +395,7 @@ desc->chip->end();
        mechanism. (It's necessary to enable CONFIG_HARDIRQS_SW_RESEND when
        you want to use the delayed interrupt disable feature and your
        hardware is not capable of retriggering an interrupt.)
-        The delayed interrupt disable can be runtime enabled, per interrupt,
+        The delayed interrupt disable is not configurable.
-        by setting the IRQ_DELAYED_DISABLE flag in the irq_desc status field.
        </para>
        </sect2>
    </sect1>
@@ -387,13 +406,13 @@ desc->chip->end();
        contains all the direct chip relevant functions, which
        can be utilized by the irq flow implementations.
          <itemizedlist>
-          <listitem><para>ack()</para></listitem>
+          <listitem><para>irq_ack()</para></listitem>
-          <listitem><para>mask_ack() - Optional, recommended for performance</para></listitem>
+          <listitem><para>irq_mask_ack() - Optional, recommended for performance</para></listitem>
-          <listitem><para>mask()</para></listitem>
+          <listitem><para>irq_mask()</para></listitem>
-          <listitem><para>unmask()</para></listitem>
+          <listitem><para>irq_unmask()</para></listitem>
-          <listitem><para>retrigger() - Optional</para></listitem>
+          <listitem><para>irq_retrigger() - Optional</para></listitem>
-          <listitem><para>set_type() - Optional</para></listitem>
+          <listitem><para>irq_set_type() - Optional</para></listitem>
-          <listitem><para>set_wake() - Optional</para></listitem>
+          <listitem><para>irq_set_wake() - Optional</para></listitem>
          </itemizedlist>
        These primitives are strictly intended to mean what they say: ack means
        ACK, masking means masking of an IRQ line, etc. It is up to the flow
@@ -458,6 +477,7 @@ desc->chip->end();
     <para>
     This chapter contains the autogenerated documentation of the internal functions.
     </para>
+!Ikernel/irq/irqdesc.c
 !Ikernel/irq/handle.c
 !Ikernel/irq/chip.c
  </chapter>
diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
index 6899f471fb15..7160652a8736 100644
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@@ -93,6 +93,12 @@ X!Ilib/string.c
 !Elib/crc32.c
 !Elib/crc-ccitt.c
     </sect1>
+     <sect1 id="idr"><title>idr/ida Functions</title>
+!Pinclude/linux/idr.h idr sync
+!Plib/idr.c IDA description
+!Elib/idr.c
+     </sect1>
  </chapter>
  <chapter id="mm">
@@ -257,7 +263,8 @@ X!Earch/x86/kernel/mca_32.c
 !Iblock/blk-sysfs.c
 !Eblock/blk-settings.c
 !Eblock/blk-exec.c
-!Eblock/blk-barrier.c
+!Eblock/blk-flush.c
+!Eblock/blk-lib.c
 !Eblock/blk-tag.c
 !Iblock/blk-tag.c
 !Eblock/blk-integrity.c
diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl
index a0d479d1e1dd..f66f4df18690 100644
--- a/Documentation/DocBook/kernel-locking.tmpl
+++ b/Documentation/DocBook/kernel-locking.tmpl
@@ -1645,7 +1645,9 @@ the amount of locking which needs to be done.
      all the readers who were traversing the list when we deleted the
      element are finished.  We use <function>call_rcu()</function> to
      register a callback which will actually destroy the object once
-      the readers are finished.
+      all pre-existing readers are finished.  Alternatively,
+      <function>synchronize_rcu()</function> may be used to block until
+      all pre-existing are finished.
    </para>
    <para>
      But how does Read Copy Update know when the readers are
@@ -1714,7 +1716,7 @@ the amount of locking which needs to be done.
 -        object_put(obj);
 +        list_del_rcu(&amp;obj-&gt;list);
         cache_num--;
-+        call_rcu(&amp;obj-&gt;rcu, cache_delete_rcu, obj);
+        call_rcu(&amp;obj-&gt;rcu, cache_delete_rcu);
 }
 /* Must be holding cache_lock */
@@ -1725,14 +1727,6 @@ the amount of locking which needs to be done.
         if (++cache_num > MAX_CACHE_SIZE) {
                 struct object *i, *outcast = NULL;
                 list_for_each_entry(i, &amp;cache, list) {
-@@ -85,6 +94,7 @@
-         obj-&gt;popularity = 0;
-         atomic_set(&amp;obj-&gt;refcnt, 1); /* The cache holds a reference */
-         spin_lock_init(&amp;obj-&gt;lock);
-+        INIT_RCU_HEAD(&amp;obj-&gt;rcu);
-         spin_lock_irqsave(&amp;cache_lock, flags);
-         __cache_add(obj);
 @@ -104,12 +114,11 @@
 struct object *cache_find(int id)
 {
diff --git a/Documentation/DocBook/kgdb.tmpl b/Documentation/DocBook/kgdb.tmpl
index 490d862c5f0d..d71b57fcf116 100644
--- a/Documentation/DocBook/kgdb.tmpl
+++ b/Documentation/DocBook/kgdb.tmpl
@@ -710,7 +710,18 @@ Task Addr       Pid   Parent [*] cpu State Thread     Command
        <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>
+        <itemizedlist>
+        <listitem><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>For an example of how to dynamically register
+        a new kdb command you can build the kdb_hello.ko kernel module
+        from samples/kdb/kdb_hello.c.  To build this example you can
+        set CONFIG_SAMPLES=y and CONFIG_SAMPLE_KDB=m in your kernel
+        config.  Later run "modprobe kdb_hello" and the next time you
+        enter the kdb shell, you can run the "hello"
+        command.</para></listitem>
+        </itemizedlist></listitem>
        <listitem><para>The implementation for kdb_printf() which
        emits messages directly to I/O drivers, bypassing the kernel
        log.</para></listitem>
diff --git a/Documentation/DocBook/mac80211.tmpl b/Documentation/DocBook/mac80211.tmpl
deleted file mode 100644
index affb15a344a1..000000000000
--- a/Documentation/DocBook/mac80211.tmpl
+++ /dev/null
@@ -1,337 +0,0 @@
-<?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="mac80211-developers-guide">
-  <bookinfo>
-    <title>The mac80211 subsystem for kernel developers</title>
-    <authorgroup>
-      <author>
-        <firstname>Johannes</firstname>
-        <surname>Berg</surname>
-        <affiliation>
-          <address><email>johannes@sipsolutions.net</email></address>
-        </affiliation>
-      </author>
-    </authorgroup>
-    <copyright>
-      <year>2007-2009</year>
-      <holder>Johannes Berg</holder>
-    </copyright>
-    <legalnotice>
-      <para>
-        This documentation is free software; you can redistribute
-        it and/or modify it under the terms of the GNU General Public
-        License version 2 as published by the Free Software Foundation.
-      </para>
-      <para>
-        This documentation 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.
-      </para>
-      <para>
-        You should have received a copy of the GNU General Public
-        License along with this documentation; if not, write to the Free
-        Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
-        MA 02111-1307 USA
-      </para>
-      <para>
-        For more details see the file COPYING in the source
-        distribution of Linux.
-      </para>
-    </legalnotice>
-    <abstract>
-!Pinclude/net/mac80211.h Introduction
-!Pinclude/net/mac80211.h Warning
-    </abstract>
-  </bookinfo>
-  <toc></toc>
-<!--
-Generally, this document shall be ordered by increasing complexity.
-It is important to note that readers should be able to read only
-the first few sections to get a working driver and only advanced
-usage should require reading the full document.
-->
-  <part>
-    <title>The basic mac80211 driver interface</title>
-    <partintro>
-      <para>
-        You should read and understand the information contained
-        within this part of the book while implementing a driver.
-        In some chapters, advanced usage is noted, that may be
-        skipped at first.
-      </para>
-      <para>
-        This part of the book only covers station and monitor mode
-        functionality, additional information required to implement
-        the other modes is covered in the second part of the book.
-      </para>
-    </partintro>
-    <chapter id="basics">
-      <title>Basic hardware handling</title>
-      <para>TBD</para>
-      <para>
-        This chapter shall contain information on getting a hw
-        struct allocated and registered with mac80211.
-      </para>
-      <para>
-        Since it is required to allocate rates/modes before registering
-        a hw struct, this chapter shall also contain information on setting
-        up the rate/mode structs.
-      </para>
-      <para>
-        Additionally, some discussion about the callbacks and
-        the general programming model should be in here, including
-        the definition of ieee80211_ops which will be referred to
-        a lot.
-      </para>
-      <para>
-        Finally, a discussion of hardware capabilities should be done
-        with references to other parts of the book.
-      </para>
-<!-- intentionally multiple !F lines to get proper order -->
-!Finclude/net/mac80211.h ieee80211_hw
-!Finclude/net/mac80211.h ieee80211_hw_flags
-!Finclude/net/mac80211.h SET_IEEE80211_DEV
-!Finclude/net/mac80211.h SET_IEEE80211_PERM_ADDR
-!Finclude/net/mac80211.h ieee80211_ops
-!Finclude/net/mac80211.h ieee80211_alloc_hw
-!Finclude/net/mac80211.h ieee80211_register_hw
-!Finclude/net/mac80211.h ieee80211_get_tx_led_name
-!Finclude/net/mac80211.h ieee80211_get_rx_led_name
-!Finclude/net/mac80211.h ieee80211_get_assoc_led_name
-!Finclude/net/mac80211.h ieee80211_get_radio_led_name
-!Finclude/net/mac80211.h ieee80211_unregister_hw
-!Finclude/net/mac80211.h ieee80211_free_hw
-    </chapter>
-    <chapter id="phy-handling">
-      <title>PHY configuration</title>
-      <para>TBD</para>
-      <para>
-        This chapter should describe PHY handling including
-        start/stop callbacks and the various structures used.
-      </para>
-!Finclude/net/mac80211.h ieee80211_conf
-!Finclude/net/mac80211.h ieee80211_conf_flags
-    </chapter>
-    <chapter id="iface-handling">
-      <title>Virtual interfaces</title>
-      <para>TBD</para>
-      <para>
-        This chapter should describe virtual interface basics
-        that are relevant to the driver (VLANs, MGMT etc are not.)
-        It should explain the use of the add_iface/remove_iface
-        callbacks as well as the interface configuration callbacks.
-      </para>
-      <para>Things related to AP mode should be discussed there.</para>
-      <para>
-        Things related to supporting multiple interfaces should be
-        in the appropriate chapter, a BIG FAT note should be here about
-        this though and the recommendation to allow only a single
-        interface in STA mode at first!
-      </para>
-!Finclude/net/mac80211.h ieee80211_vif
-    </chapter>
-    <chapter id="rx-tx">
-      <title>Receive and transmit processing</title>
-      <sect1>
-        <title>what should be here</title>
-        <para>TBD</para>
-        <para>
-          This should describe the receive and transmit
-          paths in mac80211/the drivers as well as
-          transmit status handling.
-        </para>
-      </sect1>
-      <sect1>
-        <title>Frame format</title>
-!Pinclude/net/mac80211.h Frame format
-      </sect1>
-      <sect1>
-        <title>Packet alignment</title>
-!Pnet/mac80211/rx.c Packet alignment
-      </sect1>
-      <sect1>
-        <title>Calling into mac80211 from interrupts</title>
-!Pinclude/net/mac80211.h Calling mac80211 from interrupts
-      </sect1>
-      <sect1>
-        <title>functions/definitions</title>
-!Finclude/net/mac80211.h ieee80211_rx_status
-!Finclude/net/mac80211.h mac80211_rx_flags
-!Finclude/net/mac80211.h ieee80211_tx_info
-!Finclude/net/mac80211.h ieee80211_rx
-!Finclude/net/mac80211.h ieee80211_rx_irqsafe
-!Finclude/net/mac80211.h ieee80211_tx_status
-!Finclude/net/mac80211.h ieee80211_tx_status_irqsafe
-!Finclude/net/mac80211.h ieee80211_rts_get
-!Finclude/net/mac80211.h ieee80211_rts_duration
-!Finclude/net/mac80211.h ieee80211_ctstoself_get
-!Finclude/net/mac80211.h ieee80211_ctstoself_duration
-!Finclude/net/mac80211.h ieee80211_generic_frame_duration
-!Finclude/net/mac80211.h ieee80211_wake_queue
-!Finclude/net/mac80211.h ieee80211_stop_queue
-!Finclude/net/mac80211.h ieee80211_wake_queues
-!Finclude/net/mac80211.h ieee80211_stop_queues
-      </sect1>
-    </chapter>
-    <chapter id="filters">
-      <title>Frame filtering</title>
-!Pinclude/net/mac80211.h Frame filtering
-!Finclude/net/mac80211.h ieee80211_filter_flags
-    </chapter>
-  </part>
-  <part id="advanced">
-    <title>Advanced driver interface</title>
-    <partintro>
-      <para>
-       Information contained within this part of the book is
-       of interest only for advanced interaction of mac80211
-       with drivers to exploit more hardware capabilities and
-       improve performance.
-      </para>
-    </partintro>
-    <chapter id="hardware-crypto-offload">
-      <title>Hardware crypto acceleration</title>
-!Pinclude/net/mac80211.h Hardware crypto acceleration
-<!-- intentionally multiple !F lines to get proper order -->
-!Finclude/net/mac80211.h set_key_cmd
-!Finclude/net/mac80211.h ieee80211_key_conf
-!Finclude/net/mac80211.h ieee80211_key_alg
-!Finclude/net/mac80211.h ieee80211_key_flags
-    </chapter>
-    <chapter id="powersave">
-      <title>Powersave support</title>
-!Pinclude/net/mac80211.h Powersave support
-    </chapter>
-    <chapter id="beacon-filter">
-      <title>Beacon filter support</title>
-!Pinclude/net/mac80211.h Beacon filter support
-!Finclude/net/mac80211.h ieee80211_beacon_loss
-    </chapter>
-    <chapter id="qos">
-      <title>Multiple queues and QoS support</title>
-      <para>TBD</para>
-!Finclude/net/mac80211.h ieee80211_tx_queue_params
-    </chapter>
-    <chapter id="AP">
-      <title>Access point mode support</title>
-      <para>TBD</para>
-      <para>Some parts of the if_conf should be discussed here instead</para>
-      <para>
-        Insert notes about VLAN interfaces with hw crypto here or
-        in the hw crypto chapter.
-      </para>
-!Finclude/net/mac80211.h ieee80211_get_buffered_bc
-!Finclude/net/mac80211.h ieee80211_beacon_get
-    </chapter>
-    <chapter id="multi-iface">
-      <title>Supporting multiple virtual interfaces</title>
-      <para>TBD</para>
-      <para>
-        Note: WDS with identical MAC address should almost always be OK
-      </para>
-      <para>
-        Insert notes about having multiple virtual interfaces with
-        different MAC addresses here, note which configurations are
-        supported by mac80211, add notes about supporting hw crypto
-        with it.
-      </para>
-    </chapter>
-    <chapter id="hardware-scan-offload">
-      <title>Hardware scan offload</title>
-      <para>TBD</para>
-!Finclude/net/mac80211.h ieee80211_scan_completed
-    </chapter>
-  </part>
-  <part id="rate-control">
-    <title>Rate control interface</title>
-    <partintro>
-      <para>TBD</para>
-      <para>
-       This part of the book describes the rate control algorithm
-       interface and how it relates to mac80211 and drivers.
-      </para>
-    </partintro>
-    <chapter id="dummy">
-      <title>dummy chapter</title>
-      <para>TBD</para>
-    </chapter>
-  </part>
-  <part id="internal">
-    <title>Internals</title>
-    <partintro>
-      <para>TBD</para>
-      <para>
-       This part of the book describes mac80211 internals.
-      </para>
-    </partintro>
-    <chapter id="key-handling">
-      <title>Key handling</title>
-      <sect1>
-        <title>Key handling basics</title>
-!Pnet/mac80211/key.c Key handling basics
-      </sect1>
-      <sect1>
-        <title>MORE TBD</title>
-        <para>TBD</para>
-      </sect1>
-    </chapter>
-    <chapter id="rx-processing">
-      <title>Receive processing</title>
-      <para>TBD</para>
-    </chapter>
-    <chapter id="tx-processing">
-      <title>Transmit processing</title>
-      <para>TBD</para>
-    </chapter>
-    <chapter id="sta-info">
-      <title>Station info handling</title>
-      <sect1>
-        <title>Programming information</title>
-!Fnet/mac80211/sta_info.h sta_info
-!Fnet/mac80211/sta_info.h ieee80211_sta_info_flags
-      </sect1>
-      <sect1>
-        <title>STA information lifetime rules</title>
-!Pnet/mac80211/sta_info.c STA information lifetime rules
-      </sect1>
-    </chapter>
-    <chapter id="synchronisation">
-      <title>Synchronisation</title>
-      <para>TBD</para>
-      <para>Locking, lots of RCU</para>
-    </chapter>
-  </part>
-</book>
diff --git a/Documentation/DocBook/media-entities.tmpl b/Documentation/DocBook/media-entities.tmpl
index 6ae97157b1c7..be34dcbe0d90 100644
--- a/Documentation/DocBook/media-entities.tmpl
+++ b/Documentation/DocBook/media-entities.tmpl
@@ -250,6 +250,9 @@
 <!ENTITY sub-yuv422p SYSTEM "v4l/pixfmt-yuv422p.xml">
 <!ENTITY sub-yuyv SYSTEM "v4l/pixfmt-yuyv.xml">
 <!ENTITY sub-yvyu SYSTEM "v4l/pixfmt-yvyu.xml">
+<!ENTITY sub-srggb10 SYSTEM "v4l/pixfmt-srggb10.xml">
+<!ENTITY sub-srggb8 SYSTEM "v4l/pixfmt-srggb8.xml">
+<!ENTITY sub-y10 SYSTEM "v4l/pixfmt-y10.xml">
 <!ENTITY sub-pixfmt SYSTEM "v4l/pixfmt.xml">
 <!ENTITY sub-cropcap SYSTEM "v4l/vidioc-cropcap.xml">
 <!ENTITY sub-dbg-g-register SYSTEM "v4l/vidioc-dbg-g-register.xml">
@@ -347,6 +350,9 @@
 <!ENTITY yuv422p SYSTEM "v4l/pixfmt-yuv422p.xml">
 <!ENTITY yuyv SYSTEM "v4l/pixfmt-yuyv.xml">
 <!ENTITY yvyu SYSTEM "v4l/pixfmt-yvyu.xml">
+<!ENTITY srggb10 SYSTEM "v4l/pixfmt-srggb10.xml">
+<!ENTITY srggb8 SYSTEM "v4l/pixfmt-srggb8.xml">
+<!ENTITY y10 SYSTEM "v4l/pixfmt-y10.xml">
 <!ENTITY cropcap SYSTEM "v4l/vidioc-cropcap.xml">
 <!ENTITY dbg-g-register SYSTEM "v4l/vidioc-dbg-g-register.xml">
 <!ENTITY encoder-cmd SYSTEM "v4l/vidioc-encoder-cmd.xml">
diff --git a/Documentation/DocBook/v4l/compat.xml b/Documentation/DocBook/v4l/compat.xml
index 54447f0d0784..c9ce61d981f5 100644
--- a/Documentation/DocBook/v4l/compat.xml
+++ b/Documentation/DocBook/v4l/compat.xml
@@ -21,11 +21,15 @@ API.</para>
      <title>Opening and Closing Devices</title>
      <para>For compatibility reasons the character device file names
-recommended for V4L2 video capture, overlay, radio, teletext and raw
+recommended for V4L2 video capture, overlay, radio and raw
 vbi capture devices did not change from those used by V4L. They are
 listed in <xref linkend="devices" /> and below in <xref
          linkend="v4l-dev" />.</para>
+      <para>The teletext devices (minor range 192-223) have been removed in
+V4L2 and no longer exist. There is no hardware available anymore for handling
+pure teletext. Instead raw or sliced VBI is used.</para>
      <para>The V4L <filename>videodev</filename> module automatically
 assigns minor numbers to drivers in load order, depending on the
 registered device type. We recommend that V4L2 drivers by default
@@ -66,13 +70,6 @@ not compatible with V4L or V4L2.</para> </footnote>,
              <entry>64-127</entry>
            </row>
            <row>
-              <entry>Teletext decoder</entry>
-              <entry><para><filename>/dev/vtx</filename>,
-<filename>/dev/vtx0</filename> to
-<filename>/dev/vtx31</filename></para></entry>
-              <entry>192-223</entry>
-            </row>
-            <row>
              <entry>Raw VBI capture</entry>
              <entry><para><filename>/dev/vbi</filename>,
 <filename>/dev/vbi0</filename> to
@@ -2345,6 +2342,17 @@ more information.</para>
        </listitem>
      </orderedlist>
    </section>
+    <section>
+      <title>V4L2 in Linux 2.6.37</title>
+      <orderedlist>
+        <listitem>
+          <para>Remove the vtx (videotext/teletext) API. This API was no longer
+used and no hardware exists to verify the API. Nor were any userspace applications found
+that used it. It was originally scheduled for removal in 2.6.35.
+          </para>
+        </listitem>
+      </orderedlist>
+    </section>
    <section id="other">
      <title>Relation of V4L2 to other Linux multimedia APIs</title>
diff --git a/Documentation/DocBook/v4l/controls.xml b/Documentation/DocBook/v4l/controls.xml
index 8408caaee276..2fae3e87ce73 100644
--- a/Documentation/DocBook/v4l/controls.xml
+++ b/Documentation/DocBook/v4l/controls.xml
@@ -312,10 +312,17 @@ minimum value disables backlight compensation.</entry>
            information and bits 24-31 must be zero.</entry>
          </row>
          <row>
+            <entry><constant>V4L2_CID_ILLUMINATORS_1</constant>
+                <constant>V4L2_CID_ILLUMINATORS_2</constant></entry>
+            <entry>boolean</entry>
+            <entry>Switch on or off the illuminator 1 or 2 of the device
+                (usually a microscope).</entry>
+          </row>
+          <row>
            <entry><constant>V4L2_CID_LASTP1</constant></entry>
            <entry></entry>
            <entry>End of the predefined control IDs (currently
-<constant>V4L2_CID_BG_COLOR</constant> + 1).</entry>
+<constant>V4L2_CID_ILLUMINATORS_2</constant> + 1).</entry>
          </row>
          <row>
            <entry><constant>V4L2_CID_PRIVATE_BASE</constant></entry>
@@ -357,9 +364,6 @@ enumerate_menu (void)
              querymenu.index++) {
                if (0 == ioctl (fd, &VIDIOC-QUERYMENU;, &amp;querymenu)) {
                        printf ("  %s\n", querymenu.name);
-                } else {
-                        perror ("VIDIOC_QUERYMENU");
-                        exit (EXIT_FAILURE);
                }
        }
 }
diff --git a/Documentation/DocBook/v4l/dev-rds.xml b/Documentation/DocBook/v4l/dev-rds.xml
index 0869d701b1e5..360d2737e649 100644
--- a/Documentation/DocBook/v4l/dev-rds.xml
+++ b/Documentation/DocBook/v4l/dev-rds.xml
@@ -3,15 +3,16 @@
      <para>The Radio Data System transmits supplementary
 information in binary format, for example the station name or travel
 information, on an inaudible audio subcarrier of a radio program. This
-interface is aimed at devices capable of receiving and decoding RDS
+interface is aimed at devices capable of receiving and/or transmitting RDS
 information.</para>
      <para>For more information see the core RDS standard <xref linkend="en50067" />
 and the RBDS standard <xref linkend="nrsc4" />.</para>
      <para>Note that the RBDS standard as is used in the USA is almost identical
-to the RDS standard. Any RDS decoder can also handle RBDS. Only some of the fields
+to the RDS standard. Any RDS decoder/encoder can also handle RBDS. Only some of the
-have slightly different meanings. See the RBDS standard for more information.</para>
+fields have slightly different meanings. See the RBDS standard for more
+information.</para>
      <para>The RBDS standard also specifies support for MMBS (Modified Mobile Search).
 This is a proprietary format which seems to be discontinued. The RDS interface does not
@@ -21,16 +22,25 @@ be needed, then please contact the linux-media mailing list: &v4l-ml;.</para>
  <section>
    <title>Querying Capabilities</title>
-    <para>Devices supporting the RDS capturing API
+    <para>Devices supporting the RDS capturing API set
-set the <constant>V4L2_CAP_RDS_CAPTURE</constant> flag in
+the <constant>V4L2_CAP_RDS_CAPTURE</constant> flag in
 the <structfield>capabilities</structfield> field of &v4l2-capability;
-returned by the &VIDIOC-QUERYCAP; ioctl.
+returned by the &VIDIOC-QUERYCAP; ioctl.  Any tuner that supports RDS
-Any tuner that supports RDS will set the
+will set the <constant>V4L2_TUNER_CAP_RDS</constant> flag in
-<constant>V4L2_TUNER_CAP_RDS</constant> flag in the <structfield>capability</structfield>
+the <structfield>capability</structfield> field of &v4l2-tuner;.  If
-field of &v4l2-tuner;.
+the driver only passes RDS blocks without interpreting the data
-Whether an RDS signal is present can be detected by looking at
+the <constant>V4L2_TUNER_SUB_RDS_BLOCK_IO</constant> flag has to be
-the <structfield>rxsubchans</structfield> field of &v4l2-tuner;: the
+set, see <link linkend="reading-rds-data">Reading RDS data</link>.
-<constant>V4L2_TUNER_SUB_RDS</constant> will be set if RDS data was detected.</para>
+For future use the
+flag <constant>V4L2_TUNER_SUB_RDS_CONTROLS</constant> has also been
+defined. However, a driver for a radio tuner with this capability does
+not yet exist, so if you are planning to write such a driver you
+should discuss this on the linux-media mailing list: &v4l-ml;.</para>
+    <para> Whether an RDS signal is present can be detected by looking
+at the <structfield>rxsubchans</structfield> field of &v4l2-tuner;:
+the <constant>V4L2_TUNER_SUB_RDS</constant> will be set if RDS data
+was detected.</para>
    <para>Devices supporting the RDS output API
 set the <constant>V4L2_CAP_RDS_OUTPUT</constant> flag in
@@ -40,16 +50,31 @@ Any modulator that supports RDS will set the
 <constant>V4L2_TUNER_CAP_RDS</constant> flag in the <structfield>capability</structfield>
 field of &v4l2-modulator;.
 In order to enable the RDS transmission one must set the <constant>V4L2_TUNER_SUB_RDS</constant>
-bit in the <structfield>txsubchans</structfield> field of &v4l2-modulator;.</para>
+bit in the <structfield>txsubchans</structfield> field of &v4l2-modulator;.
+If the driver only passes RDS blocks without interpreting the data
+the <constant>V4L2_TUNER_SUB_RDS_BLOCK_IO</constant> flag has to be set. If the
+tuner is capable of handling RDS entities like program identification codes and radio
+text, the flag <constant>V4L2_TUNER_SUB_RDS_CONTROLS</constant> should be set,
+see <link linkend="writing-rds-data">Writing RDS data</link> and
+<link linkend="fm-tx-controls">FM Transmitter Control Reference</link>.</para>
  </section>
-  <section>
+  <section  id="reading-rds-data">
    <title>Reading RDS data</title>
      <para>RDS data can be read from the radio device
-with the &func-read; function. The data is packed in groups of three bytes,
+with the &func-read; function. The data is packed in groups of three bytes.</para>
+  </section>
+  <section  id="writing-rds-data">
+    <title>Writing RDS data</title>
+      <para>RDS data can be written to the radio device
+with the &func-write; function. The data is packed in groups of three bytes,
 as follows:</para>
+  </section>
+  <section>
    <table frame="none" pgwide="1" id="v4l2-rds-data">
      <title>struct
 <structname>v4l2_rds_data</structname></title>
@@ -111,48 +136,57 @@ as follows:</para>
        <tbody valign="top">
          <row>
            <entry>V4L2_RDS_BLOCK_MSK</entry>
+            <entry> </entry>
            <entry>7</entry>
            <entry>Mask for bits 0-2 to get the block ID.</entry>
          </row>
          <row>
            <entry>V4L2_RDS_BLOCK_A</entry>
+            <entry> </entry>
            <entry>0</entry>
            <entry>Block A.</entry>
          </row>
          <row>
            <entry>V4L2_RDS_BLOCK_B</entry>
+            <entry> </entry>
            <entry>1</entry>
            <entry>Block B.</entry>
          </row>
          <row>
            <entry>V4L2_RDS_BLOCK_C</entry>
+            <entry> </entry>
            <entry>2</entry>
            <entry>Block C.</entry>
          </row>
          <row>
            <entry>V4L2_RDS_BLOCK_D</entry>
+            <entry> </entry>
            <entry>3</entry>
            <entry>Block D.</entry>
          </row>
          <row>
            <entry>V4L2_RDS_BLOCK_C_ALT</entry>
+            <entry> </entry>
            <entry>4</entry>
            <entry>Block C'.</entry>
          </row>
          <row>
            <entry>V4L2_RDS_BLOCK_INVALID</entry>
+            <entry>read-only</entry>
            <entry>7</entry>
            <entry>An invalid block.</entry>
          </row>
          <row>
            <entry>V4L2_RDS_BLOCK_CORRECTED</entry>
+            <entry>read-only</entry>
            <entry>0x40</entry>
            <entry>A bit error was detected but corrected.</entry>
          </row>
          <row>
            <entry>V4L2_RDS_BLOCK_ERROR</entry>
+            <entry>read-only</entry>
            <entry>0x80</entry>
-            <entry>An incorrectable error occurred.</entry>
+            <entry>An uncorrectable error occurred.</entry>
          </row>
        </tbody>
      </tgroup>
diff --git a/Documentation/DocBook/v4l/dev-teletext.xml b/Documentation/DocBook/v4l/dev-teletext.xml
index 76184e8ed618..414b1cfff9f4 100644
--- a/Documentation/DocBook/v4l/dev-teletext.xml
+++ b/Documentation/DocBook/v4l/dev-teletext.xml
@@ -1,35 +1,32 @@
  <title>Teletext Interface</title>
-  <para>This interface aims at devices receiving and demodulating
+  <para>This interface was aimed at devices receiving and demodulating
 Teletext data [<xref linkend="ets300706" />, <xref linkend="itu653" />], evaluating the
 Teletext packages and storing formatted pages in cache memory. Such
 devices are usually implemented as microcontrollers with serial
-interface (I<superscript>2</superscript>C) and can be found on older
+interface (I<superscript>2</superscript>C) and could be found on old
 TV cards, dedicated Teletext decoding cards and home-brew devices
 connected to the PC parallel port.</para>
-  <para>The Teletext API was designed by Martin Buck. It is defined in
+  <para>The Teletext API was designed by Martin Buck. It was defined in
 the kernel header file <filename>linux/videotext.h</filename>, the
 specification is available from <ulink url="ftp://ftp.gwdg.de/pub/linux/misc/videotext/">
 ftp://ftp.gwdg.de/pub/linux/misc/videotext/</ulink>. (Videotext is the name of
-the German public television Teletext service.) Conventional character
+the German public television Teletext service.)</para>
-device file names are <filename>/dev/vtx</filename> and
-<filename>/dev/vttuner</filename>, with device number 83, 0 and 83, 16
-respectively. A similar interface exists for the Philips SAA5249
-Teletext decoder [specification?] with character device file names
-<filename>/dev/tlkN</filename>, device number 102, N.</para>
  <para>Eventually the Teletext API was integrated into the V4L API
 with character device file names <filename>/dev/vtx0</filename> to
 <filename>/dev/vtx31</filename>, device major number 81, minor numbers
-192 to 223. For reference the V4L Teletext API specification is
+192 to 223.</para>
-reproduced here in full: "Teletext interfaces talk the existing VTX
-API." Teletext devices with major number 83 and 102 will be removed in
-Linux 2.6.</para>
-  <para>There are no plans to replace the Teletext API or to integrate
+  <para>However, teletext decoders were quickly replaced by more
-it into V4L2. Please write to the linux-media mailing list: &v4l-ml;
+generic VBI demodulators and those dedicated teletext decoders no longer exist.
-when the need arises.</para>
+For many years the vtx devices were still around, even though nobody used
+them. So the decision was made to finally remove support for the Teletext API in
+kernel 2.6.37.</para>
+  <para>Modern devices all use the <link linkend="raw-vbi">raw</link> or
+<link linkend="sliced">sliced</link> VBI API.</para>
  <!--
 Local Variables:
diff --git a/Documentation/DocBook/v4l/pixfmt-packed-rgb.xml b/Documentation/DocBook/v4l/pixfmt-packed-rgb.xml
index 26e879231088..4db272b8a0d3 100644
--- a/Documentation/DocBook/v4l/pixfmt-packed-rgb.xml
+++ b/Documentation/DocBook/v4l/pixfmt-packed-rgb.xml
@@ -739,7 +739,7 @@ defined in error. Drivers may interpret them as in <xref
            <entry>b<subscript>1</subscript></entry>
            <entry>b<subscript>0</subscript></entry>
          </row>
-          <row id="V4L2-PIX-FMT-BGR666">
+          <row><!-- id="V4L2-PIX-FMT-BGR666" -->
            <entry><constant>V4L2_PIX_FMT_BGR666</constant></entry>
            <entry>'BGRH'</entry>
            <entry></entry>
diff --git a/Documentation/DocBook/v4l/pixfmt-srggb10.xml b/Documentation/DocBook/v4l/pixfmt-srggb10.xml
new file mode 100644
index 000000000000..7b274092e60c
--- /dev/null
+++ b/Documentation/DocBook/v4l/pixfmt-srggb10.xml
@@ -0,0 +1,90 @@
+    <refentry>
+      <refmeta>
+        <refentrytitle>V4L2_PIX_FMT_SRGGB10 ('RG10'),
+         V4L2_PIX_FMT_SGRBG10 ('BA10'),
+         V4L2_PIX_FMT_SGBRG10 ('GB10'),
+         V4L2_PIX_FMT_SBGGR10 ('BG10'),
+         </refentrytitle>
+        &manvol;
+      </refmeta>
+      <refnamediv>
+        <refname id="V4L2-PIX-FMT-SRGGB10"><constant>V4L2_PIX_FMT_SRGGB10</constant></refname>
+        <refname id="V4L2-PIX-FMT-SGRBG10"><constant>V4L2_PIX_FMT_SGRBG10</constant></refname>
+        <refname id="V4L2-PIX-FMT-SGBRG10"><constant>V4L2_PIX_FMT_SGBRG10</constant></refname>
+        <refname id="V4L2-PIX-FMT-SBGGR10"><constant>V4L2_PIX_FMT_SBGGR10</constant></refname>
+        <refpurpose>10-bit Bayer formats expanded to 16 bits</refpurpose>
+      </refnamediv>
+      <refsect1>
+        <title>Description</title>
+        <para>The following four pixel formats are raw sRGB / Bayer formats with
+10 bits per colour. Each colour component is stored in a 16-bit word, with 6
+unused high bits filled with zeros. Each n-pixel row contains n/2 green samples
+and n/2 blue or red samples, with alternating red and blue rows. Bytes are
+stored in memory in little endian order. They are conventionally described
+as GRGR... BGBG..., RGRG... GBGB..., etc. Below is an example of one of these
+formats</para>
+    <example>
+      <title><constant>V4L2_PIX_FMT_SBGGR10</constant> 4 &times; 4
+pixel image</title>
+      <formalpara>
+        <title>Byte Order.</title>
+        <para>Each cell is one byte, high 6 bits in high bytes are 0.
+          <informaltable frame="none">
+            <tgroup cols="5" align="center">
+              <colspec align="left" colwidth="2*" />
+              <tbody valign="top">
+                <row>
+                  <entry>start&nbsp;+&nbsp;0:</entry>
+                  <entry>B<subscript>00low</subscript></entry>
+                  <entry>B<subscript>00high</subscript></entry>
+                  <entry>G<subscript>01low</subscript></entry>
+                  <entry>G<subscript>01high</subscript></entry>
+                  <entry>B<subscript>02low</subscript></entry>
+                  <entry>B<subscript>02high</subscript></entry>
+                  <entry>G<subscript>03low</subscript></entry>
+                  <entry>G<subscript>03high</subscript></entry>
+                </row>
+                <row>
+                  <entry>start&nbsp;+&nbsp;8:</entry>
+                  <entry>G<subscript>10low</subscript></entry>
+                  <entry>G<subscript>10high</subscript></entry>
+                  <entry>R<subscript>11low</subscript></entry>
+                  <entry>R<subscript>11high</subscript></entry>
+                  <entry>G<subscript>12low</subscript></entry>
+                  <entry>G<subscript>12high</subscript></entry>
+                  <entry>R<subscript>13low</subscript></entry>
+                  <entry>R<subscript>13high</subscript></entry>
+                </row>
+                <row>
+                  <entry>start&nbsp;+&nbsp;16:</entry>
+                  <entry>B<subscript>20low</subscript></entry>
+                  <entry>B<subscript>20high</subscript></entry>
+                  <entry>G<subscript>21low</subscript></entry>
+                  <entry>G<subscript>21high</subscript></entry>
+                  <entry>B<subscript>22low</subscript></entry>
+                  <entry>B<subscript>22high</subscript></entry>
+                  <entry>G<subscript>23low</subscript></entry>
+                  <entry>G<subscript>23high</subscript></entry>
+                </row>
+                <row>
+                  <entry>start&nbsp;+&nbsp;24:</entry>
+                  <entry>G<subscript>30low</subscript></entry>
+                  <entry>G<subscript>30high</subscript></entry>
+                  <entry>R<subscript>31low</subscript></entry>
+                  <entry>R<subscript>31high</subscript></entry>
+                  <entry>G<subscript>32low</subscript></entry>
+                  <entry>G<subscript>32high</subscript></entry>
+                  <entry>R<subscript>33low</subscript></entry>
+                  <entry>R<subscript>33high</subscript></entry>
+                </row>
+              </tbody>
+            </tgroup>
+          </informaltable>
+        </para>
+      </formalpara>
+    </example>
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/v4l/pixfmt-srggb8.xml b/Documentation/DocBook/v4l/pixfmt-srggb8.xml
new file mode 100644
index 000000000000..2570e3be3cf1
--- /dev/null
+++ b/Documentation/DocBook/v4l/pixfmt-srggb8.xml
@@ -0,0 +1,67 @@
+    <refentry id="V4L2-PIX-FMT-SRGGB8">
+      <refmeta>
+        <refentrytitle>V4L2_PIX_FMT_SRGGB8 ('RGGB')</refentrytitle>
+        &manvol;
+      </refmeta>
+      <refnamediv>
+        <refname><constant>V4L2_PIX_FMT_SRGGB8</constant></refname>
+        <refpurpose>Bayer RGB format</refpurpose>
+      </refnamediv>
+      <refsect1>
+        <title>Description</title>
+        <para>This is commonly the native format of digital cameras,
+reflecting the arrangement of sensors on the CCD device. Only one red,
+green or blue value is given for each pixel. Missing components must
+be interpolated from neighbouring pixels. From left to right the first
+row consists of a red and green value, the second row of a green and
+blue value. This scheme repeats to the right and down for every two
+columns and rows.</para>
+        <example>
+          <title><constant>V4L2_PIX_FMT_SRGGB8</constant> 4 &times; 4
+pixel image</title>
+          <formalpara>
+            <title>Byte Order.</title>
+            <para>Each cell is one byte.
+              <informaltable frame="none">
+                <tgroup cols="5" align="center">
+                  <colspec align="left" colwidth="2*" />
+                  <tbody valign="top">
+                    <row>
+                      <entry>start&nbsp;+&nbsp;0:</entry>
+                      <entry>R<subscript>00</subscript></entry>
+                      <entry>G<subscript>01</subscript></entry>
+                      <entry>R<subscript>02</subscript></entry>
+                      <entry>G<subscript>03</subscript></entry>
+                    </row>
+                    <row>
+                      <entry>start&nbsp;+&nbsp;4:</entry>
+                      <entry>G<subscript>10</subscript></entry>
+                      <entry>B<subscript>11</subscript></entry>
+                      <entry>G<subscript>12</subscript></entry>
+                      <entry>B<subscript>13</subscript></entry>
+                    </row>
+                    <row>
+                      <entry>start&nbsp;+&nbsp;8:</entry>
+                      <entry>R<subscript>20</subscript></entry>
+                      <entry>G<subscript>21</subscript></entry>
+                      <entry>R<subscript>22</subscript></entry>
+                      <entry>G<subscript>23</subscript></entry>
+                    </row>
+                    <row>
+                      <entry>start&nbsp;+&nbsp;12:</entry>
+                      <entry>G<subscript>30</subscript></entry>
+                      <entry>B<subscript>31</subscript></entry>
+                      <entry>G<subscript>32</subscript></entry>
+                      <entry>B<subscript>33</subscript></entry>
+                    </row>
+                  </tbody>
+                </tgroup>
+              </informaltable>
+            </para>
+          </formalpara>
+        </example>
+      </refsect1>
+    </refentry>
diff --git a/Documentation/DocBook/v4l/pixfmt-y10.xml b/Documentation/DocBook/v4l/pixfmt-y10.xml
new file mode 100644
index 000000000000..d065043db8d8
--- /dev/null
+++ b/Documentation/DocBook/v4l/pixfmt-y10.xml
@@ -0,0 +1,79 @@
+<refentry id="V4L2-PIX-FMT-Y10">
+  <refmeta>
+    <refentrytitle>V4L2_PIX_FMT_Y10 ('Y10 ')</refentrytitle>
+    &manvol;
+  </refmeta>
+  <refnamediv>
+    <refname><constant>V4L2_PIX_FMT_Y10</constant></refname>
+    <refpurpose>Grey-scale image</refpurpose>
+  </refnamediv>
+  <refsect1>
+    <title>Description</title>
+    <para>This is a grey-scale image with a depth of 10 bits per pixel. Pixels
+are stored in 16-bit words with unused high bits padded with 0. The least
+significant byte is stored at lower memory addresses (little-endian).</para>
+    <example>
+      <title><constant>V4L2_PIX_FMT_Y10</constant> 4 &times; 4
+pixel image</title>
+      <formalpara>
+        <title>Byte Order.</title>
+        <para>Each cell is one byte.
+          <informaltable frame="none">
+            <tgroup cols="9" align="center">
+              <colspec align="left" colwidth="2*" />
+              <tbody valign="top">
+                <row>
+                  <entry>start&nbsp;+&nbsp;0:</entry>
+                  <entry>Y'<subscript>00low</subscript></entry>
+                  <entry>Y'<subscript>00high</subscript></entry>
+                  <entry>Y'<subscript>01low</subscript></entry>
+                  <entry>Y'<subscript>01high</subscript></entry>
+                  <entry>Y'<subscript>02low</subscript></entry>
+                  <entry>Y'<subscript>02high</subscript></entry>
+                  <entry>Y'<subscript>03low</subscript></entry>
+                  <entry>Y'<subscript>03high</subscript></entry>
+                </row>
+                <row>
+                  <entry>start&nbsp;+&nbsp;8:</entry>
+                  <entry>Y'<subscript>10low</subscript></entry>
+                  <entry>Y'<subscript>10high</subscript></entry>
+                  <entry>Y'<subscript>11low</subscript></entry>
+                  <entry>Y'<subscript>11high</subscript></entry>
+                  <entry>Y'<subscript>12low</subscript></entry>
+                  <entry>Y'<subscript>12high</subscript></entry>
+                  <entry>Y'<subscript>13low</subscript></entry>
+                  <entry>Y'<subscript>13high</subscript></entry>
+                </row>
+                <row>
+                  <entry>start&nbsp;+&nbsp;16:</entry>
+                  <entry>Y'<subscript>20low</subscript></entry>
+                  <entry>Y'<subscript>20high</subscript></entry>
+                  <entry>Y'<subscript>21low</subscript></entry>
+                  <entry>Y'<subscript>21high</subscript></entry>
+                  <entry>Y'<subscript>22low</subscript></entry>
+                  <entry>Y'<subscript>22high</subscript></entry>
+                  <entry>Y'<subscript>23low</subscript></entry>
+                  <entry>Y'<subscript>23high</subscript></entry>
+                </row>
+                <row>
+                  <entry>start&nbsp;+&nbsp;24:</entry>
+                  <entry>Y'<subscript>30low</subscript></entry>
+                  <entry>Y'<subscript>30high</subscript></entry>
+                  <entry>Y'<subscript>31low</subscript></entry>
+                  <entry>Y'<subscript>31high</subscript></entry>
+                  <entry>Y'<subscript>32low</subscript></entry>
+                  <entry>Y'<subscript>32high</subscript></entry>
+                  <entry>Y'<subscript>33low</subscript></entry>
+                  <entry>Y'<subscript>33high</subscript></entry>
+                </row>
+              </tbody>
+            </tgroup>
+          </informaltable>
+        </para>
+      </formalpara>
+    </example>
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/v4l/pixfmt.xml b/Documentation/DocBook/v4l/pixfmt.xml
index c4ad0a8e42dc..d7c467187095 100644
--- a/Documentation/DocBook/v4l/pixfmt.xml
+++ b/Documentation/DocBook/v4l/pixfmt.xml
@@ -566,7 +566,9 @@ access the palette, this must be done with ioctls of the Linux framebuffer API.<
    &sub-sbggr8;
    &sub-sgbrg8;
    &sub-sgrbg8;
+    &sub-srggb8;
    &sub-sbggr16;
+    &sub-srggb10;
  </section>
  <section id="yuv-formats">
@@ -589,6 +591,7 @@ information.</para>
    &sub-packed-yuv;
    &sub-grey;
+    &sub-y10;
    &sub-y16;
    &sub-yuyv;
    &sub-uyvy;
@@ -685,6 +688,11 @@ http://www.ivtvdriver.org/</ulink></para><para>The format is documented in the
 kernel sources in the file <filename>Documentation/video4linux/cx2341x/README.hm12</filename>
 </para></entry>
          </row>
+          <row id="V4L2-PIX-FMT-CPIA1">
+            <entry><constant>V4L2_PIX_FMT_CPIA1</constant></entry>
+            <entry>'CPIA'</entry>
+            <entry>YUV format used by the gspca cpia1 driver.</entry>
+          </row>
          <row id="V4L2-PIX-FMT-SPCA501">
            <entry><constant>V4L2_PIX_FMT_SPCA501</constant></entry>
            <entry>'S501'</entry>
@@ -705,11 +713,6 @@ kernel sources in the file <filename>Documentation/video4linux/cx2341x/README.hm
            <entry>'S561'</entry>
            <entry>Compressed GBRG Bayer format used by the gspca driver.</entry>
          </row>
-          <row id="V4L2-PIX-FMT-SGRBG10">
-            <entry><constant>V4L2_PIX_FMT_SGRBG10</constant></entry>
-            <entry>'DA10'</entry>
-            <entry>10 bit raw Bayer, expanded to 16 bits.</entry>
-          </row>
          <row id="V4L2-PIX-FMT-SGRBG10DPCM8">
            <entry><constant>V4L2_PIX_FMT_SGRBG10DPCM8</constant></entry>
            <entry>'DB10'</entry>
@@ -770,6 +773,11 @@ kernel sources in the file <filename>Documentation/video4linux/cx2341x/README.hm
            <entry>'S920'</entry>
            <entry>YUV 4:2:0 format of the gspca sn9c20x driver.</entry>
          </row>
+          <row id="V4L2-PIX-FMT-SN9C2028">
+            <entry><constant>V4L2_PIX_FMT_SN9C2028</constant></entry>
+            <entry>'SONX'</entry>
+            <entry>Compressed GBRG bayer format of the gspca sn9c2028 driver.</entry>
+          </row>
          <row id="V4L2-PIX-FMT-STV0680">
            <entry><constant>V4L2_PIX_FMT_STV0680</constant></entry>
            <entry>'S680'</entry>
@@ -787,6 +795,20 @@ http://www.thedirks.org/winnov/</ulink></para></entry>
            <entry>'TM60'</entry>
            <entry><para>Used by Trident tm6000</para></entry>
          </row>
+          <row id="V4L2-PIX-FMT-CIT-YYVYUY">
+            <entry><constant>V4L2_PIX_FMT_CIT_YYVYUY</constant></entry>
+            <entry>'CITV'</entry>
+            <entry><para>Used by xirlink CIT, found at IBM webcams.</para>
+                   <para>Uses one line of Y then 1 line of VYUY</para>
+            </entry>
+          </row>
+          <row id="V4L2-PIX-FMT-KONICA420">
+            <entry><constant>V4L2_PIX_FMT_KONICA420</constant></entry>
+            <entry>'KONI'</entry>
+            <entry><para>Used by Konica webcams.</para>
+                   <para>YUV420 planar in blocks of 256 pixels.</para>
+            </entry>
+          </row>
          <row id="V4L2-PIX-FMT-YYUV">
            <entry><constant>V4L2_PIX_FMT_YYUV</constant></entry>
            <entry>'YYUV'</entry>
diff --git a/Documentation/DocBook/v4l/v4l2.xml b/Documentation/DocBook/v4l/v4l2.xml
index 7c3c098d5d08..839e93e875ae 100644
--- a/Documentation/DocBook/v4l/v4l2.xml
+++ b/Documentation/DocBook/v4l/v4l2.xml
@@ -99,6 +99,7 @@ Remote Controller chapter.</contrib>
      <year>2007</year>
      <year>2008</year>
      <year>2009</year>
+      <year>2010</year>
      <holder>Bill Dirks, Michael H. Schimek, Hans Verkuil, Martin
 Rubli, Andy Walls, Muralidharan Karicheri, Mauro Carvalho Chehab</holder>
    </copyright>
@@ -110,10 +111,17 @@ Rubli, Andy Walls, Muralidharan Karicheri, Mauro Carvalho Chehab</holder>
      <!-- Put document revisions here, newest first. -->
      <!-- API revisions (changes and additions of defines, enums,
 structs, ioctls) must be noted in more detail in the history chapter
-(compat.sgml), along with the possible impact on existing drivers and
+(compat.xml), along with the possible impact on existing drivers and
 applications. -->
      <revision>
+        <revnumber>2.6.37</revnumber>
+        <date>2010-08-06</date>
+        <authorinitials>hv</authorinitials>
+        <revremark>Removed obsolete vtx (videotext) API.</revremark>
+      </revision>
+      <revision>
        <revnumber>2.6.33</revnumber>
        <date>2009-12-03</date>
        <authorinitials>mk</authorinitials>
diff --git a/Documentation/DocBook/v4l/videodev2.h.xml b/Documentation/DocBook/v4l/videodev2.h.xml
index 865b06d9e679..325b23b6964c 100644
--- a/Documentation/DocBook/v4l/videodev2.h.xml
+++ b/Documentation/DocBook/v4l/videodev2.h.xml
@@ -154,23 +154,13 @@ enum <link linkend="v4l2-buf-type">v4l2_buf_type</link> {
        V4L2_BUF_TYPE_VBI_OUTPUT           = 5,
        V4L2_BUF_TYPE_SLICED_VBI_CAPTURE   = 6,
        V4L2_BUF_TYPE_SLICED_VBI_OUTPUT    = 7,
-#if 1 /*KEEP*/
+#if 1
        /* Experimental */
        V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY = 8,
 #endif
        V4L2_BUF_TYPE_PRIVATE              = 0x80,
 };
-enum <link linkend="v4l2-ctrl-type">v4l2_ctrl_type</link> {
-        V4L2_CTRL_TYPE_INTEGER       = 1,
-        V4L2_CTRL_TYPE_BOOLEAN       = 2,
-        V4L2_CTRL_TYPE_MENU          = 3,
-        V4L2_CTRL_TYPE_BUTTON        = 4,
-        V4L2_CTRL_TYPE_INTEGER64     = 5,
-        V4L2_CTRL_TYPE_CTRL_CLASS    = 6,
-        V4L2_CTRL_TYPE_STRING        = 7,
-};
 enum <link linkend="v4l2-tuner-type">v4l2_tuner_type</link> {
        V4L2_TUNER_RADIO             = 1,
        V4L2_TUNER_ANALOG_TV         = 2,
@@ -288,6 +278,7 @@ struct <link linkend="v4l2-pix-format">v4l2_pix_format</link> {
 #define <link linkend="V4L2-PIX-FMT-RGB565">V4L2_PIX_FMT_RGB565</link>  v4l2_fourcc('R', 'G', 'B', 'P') /* 16  RGB-5-6-5     */
 #define <link linkend="V4L2-PIX-FMT-RGB555X">V4L2_PIX_FMT_RGB555X</link> v4l2_fourcc('R', 'G', 'B', 'Q') /* 16  RGB-5-5-5 BE  */
 #define <link linkend="V4L2-PIX-FMT-RGB565X">V4L2_PIX_FMT_RGB565X</link> v4l2_fourcc('R', 'G', 'B', 'R') /* 16  RGB-5-6-5 BE  */
+#define <link linkend="V4L2-PIX-FMT-BGR666">V4L2_PIX_FMT_BGR666</link>  v4l2_fourcc('B', 'G', 'R', 'H') /* 18  BGR-6-6-6     */
 #define <link linkend="V4L2-PIX-FMT-BGR24">V4L2_PIX_FMT_BGR24</link>   v4l2_fourcc('B', 'G', 'R', '3') /* 24  BGR-8-8-8     */
 #define <link linkend="V4L2-PIX-FMT-RGB24">V4L2_PIX_FMT_RGB24</link>   v4l2_fourcc('R', 'G', 'B', '3') /* 24  RGB-8-8-8     */
 #define <link linkend="V4L2-PIX-FMT-BGR32">V4L2_PIX_FMT_BGR32</link>   v4l2_fourcc('B', 'G', 'R', '4') /* 32  BGR-8-8-8-8   */
@@ -295,6 +286,9 @@ struct <link linkend="v4l2-pix-format">v4l2_pix_format</link> {
 /* Grey formats */
 #define <link linkend="V4L2-PIX-FMT-GREY">V4L2_PIX_FMT_GREY</link>    v4l2_fourcc('G', 'R', 'E', 'Y') /*  8  Greyscale     */
+#define <link linkend="V4L2-PIX-FMT-Y4">V4L2_PIX_FMT_Y4</link>      v4l2_fourcc('Y', '0', '4', ' ') /*  4  Greyscale     */
+#define <link linkend="V4L2-PIX-FMT-Y6">V4L2_PIX_FMT_Y6</link>      v4l2_fourcc('Y', '0', '6', ' ') /*  6  Greyscale     */
+#define <link linkend="V4L2-PIX-FMT-Y10">V4L2_PIX_FMT_Y10</link>     v4l2_fourcc('Y', '1', '0', ' ') /* 10  Greyscale     */
 #define <link linkend="V4L2-PIX-FMT-Y16">V4L2_PIX_FMT_Y16</link>     v4l2_fourcc('Y', '1', '6', ' ') /* 16  Greyscale     */
 /* Palette formats */
@@ -330,7 +324,11 @@ struct <link linkend="v4l2-pix-format">v4l2_pix_format</link> {
 #define <link linkend="V4L2-PIX-FMT-SBGGR8">V4L2_PIX_FMT_SBGGR8</link>  v4l2_fourcc('B', 'A', '8', '1') /*  8  BGBG.. GRGR.. */
 #define <link linkend="V4L2-PIX-FMT-SGBRG8">V4L2_PIX_FMT_SGBRG8</link>  v4l2_fourcc('G', 'B', 'R', 'G') /*  8  GBGB.. RGRG.. */
 #define <link linkend="V4L2-PIX-FMT-SGRBG8">V4L2_PIX_FMT_SGRBG8</link>  v4l2_fourcc('G', 'R', 'B', 'G') /*  8  GRGR.. BGBG.. */
-#define <link linkend="V4L2-PIX-FMT-SGRBG10">V4L2_PIX_FMT_SGRBG10</link> v4l2_fourcc('B', 'A', '1', '0') /* 10bit raw bayer */
+#define <link linkend="V4L2-PIX-FMT-SRGGB8">V4L2_PIX_FMT_SRGGB8</link>  v4l2_fourcc('R', 'G', 'G', 'B') /*  8  RGRG.. GBGB.. */
+#define <link linkend="V4L2-PIX-FMT-SBGGR10">V4L2_PIX_FMT_SBGGR10</link> v4l2_fourcc('B', 'G', '1', '0') /* 10  BGBG.. GRGR.. */
+#define <link linkend="V4L2-PIX-FMT-SGBRG10">V4L2_PIX_FMT_SGBRG10</link> v4l2_fourcc('G', 'B', '1', '0') /* 10  GBGB.. RGRG.. */
+#define <link linkend="V4L2-PIX-FMT-SGRBG10">V4L2_PIX_FMT_SGRBG10</link> v4l2_fourcc('B', 'A', '1', '0') /* 10  GRGR.. BGBG.. */
+#define <link linkend="V4L2-PIX-FMT-SRGGB10">V4L2_PIX_FMT_SRGGB10</link> v4l2_fourcc('R', 'G', '1', '0') /* 10  RGRG.. GBGB.. */
        /* 10bit raw bayer DPCM compressed to 8 bits */
 #define <link linkend="V4L2-PIX-FMT-SGRBG10DPCM8">V4L2_PIX_FMT_SGRBG10DPCM8</link> v4l2_fourcc('B', 'D', '1', '0')
        /*
@@ -346,6 +344,7 @@ struct <link linkend="v4l2-pix-format">v4l2_pix_format</link> {
 #define <link linkend="V4L2-PIX-FMT-MPEG">V4L2_PIX_FMT_MPEG</link>     v4l2_fourcc('M', 'P', 'E', 'G') /* MPEG-1/2/4    */
 /*  Vendor-specific formats   */
+#define <link linkend="V4L2-PIX-FMT-CPIA1">V4L2_PIX_FMT_CPIA1</link>    v4l2_fourcc('C', 'P', 'I', 'A') /* cpia1 YUV */
 #define <link linkend="V4L2-PIX-FMT-WNVA">V4L2_PIX_FMT_WNVA</link>     v4l2_fourcc('W', 'N', 'V', 'A') /* Winnov hw compress */
 #define <link linkend="V4L2-PIX-FMT-SN9C10X">V4L2_PIX_FMT_SN9C10X</link>  v4l2_fourcc('S', '9', '1', '0') /* SN9C10x compression */
 #define <link linkend="V4L2-PIX-FMT-SN9C20X-I420">V4L2_PIX_FMT_SN9C20X_I420</link> v4l2_fourcc('S', '9', '2', '0') /* SN9C20x YUV 4:2:0 */
@@ -358,12 +357,15 @@ struct <link linkend="v4l2-pix-format">v4l2_pix_format</link> {
 #define <link linkend="V4L2-PIX-FMT-SPCA561">V4L2_PIX_FMT_SPCA561</link>  v4l2_fourcc('S', '5', '6', '1') /* compressed GBRG bayer */
 #define <link linkend="V4L2-PIX-FMT-PAC207">V4L2_PIX_FMT_PAC207</link>   v4l2_fourcc('P', '2', '0', '7') /* compressed BGGR bayer */
 #define <link linkend="V4L2-PIX-FMT-MR97310A">V4L2_PIX_FMT_MR97310A</link> v4l2_fourcc('M', '3', '1', '0') /* compressed BGGR bayer */
+#define <link linkend="V4L2-PIX-FMT-SN9C2028">V4L2_PIX_FMT_SN9C2028</link> v4l2_fourcc('S', 'O', 'N', 'X') /* compressed GBRG bayer */
 #define <link linkend="V4L2-PIX-FMT-SQ905C">V4L2_PIX_FMT_SQ905C</link>   v4l2_fourcc('9', '0', '5', 'C') /* compressed RGGB bayer */
 #define <link linkend="V4L2-PIX-FMT-PJPG">V4L2_PIX_FMT_PJPG</link>     v4l2_fourcc('P', 'J', 'P', 'G') /* Pixart 73xx JPEG */
 #define <link linkend="V4L2-PIX-FMT-OV511">V4L2_PIX_FMT_OV511</link>    v4l2_fourcc('O', '5', '1', '1') /* ov511 JPEG */
 #define <link linkend="V4L2-PIX-FMT-OV518">V4L2_PIX_FMT_OV518</link>    v4l2_fourcc('O', '5', '1', '8') /* ov518 JPEG */
-#define <link linkend="V4L2-PIX-FMT-TM6000">V4L2_PIX_FMT_TM6000</link>   v4l2_fourcc('T', 'M', '6', '0') /* tm5600/tm60x0 */
 #define <link linkend="V4L2-PIX-FMT-STV0680">V4L2_PIX_FMT_STV0680</link>  v4l2_fourcc('S', '6', '8', '0') /* stv0680 bayer */
+#define <link linkend="V4L2-PIX-FMT-TM6000">V4L2_PIX_FMT_TM6000</link>   v4l2_fourcc('T', 'M', '6', '0') /* tm5600/tm60x0 */
+#define <link linkend="V4L2-PIX-FMT-CIT-YYVYUY">V4L2_PIX_FMT_CIT_YYVYUY</link> v4l2_fourcc('C', 'I', 'T', 'V') /* one line of Y then 1 line of VYUY */
+#define <link linkend="V4L2-PIX-FMT-KONICA420">V4L2_PIX_FMT_KONICA420</link>  v4l2_fourcc('K', 'O', 'N', 'I') /* YUV420 planar in blocks of 256 pixels */
 /*
 *      F O R M A T   E N U M E R A T I O N
@@ -380,7 +382,7 @@ struct <link linkend="v4l2-fmtdesc">v4l2_fmtdesc</link> {
 #define V4L2_FMT_FLAG_COMPRESSED 0x0001
 #define V4L2_FMT_FLAG_EMULATED   0x0002
-#if 1 /*KEEP*/
+#if 1
        /* Experimental Frame Size and frame rate enumeration */
 /*
 *      F R A M E   S I Z E   E N U M E R A T I O N
@@ -544,6 +546,8 @@ struct <link linkend="v4l2-buffer">v4l2_buffer</link> {
 #define V4L2_BUF_FLAG_KEYFRAME  0x0008  /* Image is a keyframe (I-frame) */
 #define V4L2_BUF_FLAG_PFRAME    0x0010  /* Image is a P-frame */
 #define V4L2_BUF_FLAG_BFRAME    0x0020  /* Image is a B-frame */
+/* Buffer is ready, but the data contained within is corrupted. */
+#define V4L2_BUF_FLAG_ERROR     0x0040
 #define V4L2_BUF_FLAG_TIMECODE  0x0100  /* timecode field is valid */
 #define V4L2_BUF_FLAG_INPUT     0x0200  /* input field is valid */
@@ -934,6 +938,16 @@ struct <link linkend="v4l2-ext-controls">v4l2_ext_controls</link> {
 #define V4L2_CTRL_ID2CLASS(id)    ((id) &amp; 0x0fff0000UL)
 #define V4L2_CTRL_DRIVER_PRIV(id) (((id) &amp; 0xffff) &gt;= 0x1000)
+enum <link linkend="v4l2-ctrl-type">v4l2_ctrl_type</link> {
+        V4L2_CTRL_TYPE_INTEGER       = 1,
+        V4L2_CTRL_TYPE_BOOLEAN       = 2,
+        V4L2_CTRL_TYPE_MENU          = 3,
+        V4L2_CTRL_TYPE_BUTTON        = 4,
+        V4L2_CTRL_TYPE_INTEGER64     = 5,
+        V4L2_CTRL_TYPE_CTRL_CLASS    = 6,
+        V4L2_CTRL_TYPE_STRING        = 7,
+};
 /*  Used in the VIDIOC_QUERYCTRL ioctl for querying controls */
 struct <link linkend="v4l2-queryctrl">v4l2_queryctrl</link> {
        __u32                id;
@@ -1018,21 +1032,27 @@ 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_NEGATIVE = 3,
-        V4L2_COLORFX_EMBOSS     = 4,
+        V4L2_COLORFX_EMBOSS = 4,
-        V4L2_COLORFX_SKETCH     = 5,
+        V4L2_COLORFX_SKETCH = 5,
-        V4L2_COLORFX_SKY_BLUE   = 6,
+        V4L2_COLORFX_SKY_BLUE = 6,
        V4L2_COLORFX_GRASS_GREEN = 7,
        V4L2_COLORFX_SKIN_WHITEN = 8,
-        V4L2_COLORFX_VIVID      = 9.
+        V4L2_COLORFX_VIVID = 9,
 };
 #define V4L2_CID_AUTOBRIGHTNESS                 (V4L2_CID_BASE+32)
 #define V4L2_CID_BAND_STOP_FILTER               (V4L2_CID_BASE+33)
 #define V4L2_CID_ROTATE                         (V4L2_CID_BASE+34)
 #define V4L2_CID_BG_COLOR                       (V4L2_CID_BASE+35)
+#define V4L2_CID_CHROMA_GAIN                    (V4L2_CID_BASE+36)
+#define V4L2_CID_ILLUMINATORS_1                 (V4L2_CID_BASE+37)
+#define V4L2_CID_ILLUMINATORS_2                 (V4L2_CID_BASE+38)
 /* last CID + 1 */
-#define V4L2_CID_LASTP1                         (V4L2_CID_BASE+36)
+#define V4L2_CID_LASTP1                         (V4L2_CID_BASE+39)
 /*  MPEG-class control IDs defined by V4L2 */
 #define V4L2_CID_MPEG_BASE                      (V4L2_CTRL_CLASS_MPEG | 0x900)
@@ -1349,6 +1369,8 @@ struct <link linkend="v4l2-modulator">v4l2_modulator</link> {
 #define V4L2_TUNER_CAP_SAP              0x0020
 #define V4L2_TUNER_CAP_LANG1            0x0040
 #define V4L2_TUNER_CAP_RDS              0x0080
+#define V4L2_TUNER_CAP_RDS_BLOCK_IO     0x0100
+#define V4L2_TUNER_CAP_RDS_CONTROLS     0x0200
 /*  Flags for the 'rxsubchans' field */
 #define V4L2_TUNER_SUB_MONO             0x0001
@@ -1378,7 +1400,8 @@ struct <link linkend="v4l2-hw-freq-seek">v4l2_hw_freq_seek</link> {
        enum <link linkend="v4l2-tuner-type">v4l2_tuner_type</link>  type;
        __u32                 seek_upward;
        __u32                 wrap_around;
-        __u32                 reserved[8];
+        __u32                 spacing;
+        __u32                 reserved[7];
 };
 /*
@@ -1433,7 +1456,7 @@ struct <link linkend="v4l2-audioout">v4l2_audioout</link> {
 *
 *      NOTE: EXPERIMENTAL API
 */
-#if 1 /*KEEP*/
+#if 1
 #define V4L2_ENC_IDX_FRAME_I    (0)
 #define V4L2_ENC_IDX_FRAME_P    (1)
 #define V4L2_ENC_IDX_FRAME_B    (2)
@@ -1626,6 +1649,38 @@ struct <link linkend="v4l2-streamparm">v4l2_streamparm</link> {
 };
 /*
+ *      E V E N T S
+ */
+#define V4L2_EVENT_ALL                          0
+#define V4L2_EVENT_VSYNC                        1
+#define V4L2_EVENT_EOS                          2
+#define V4L2_EVENT_PRIVATE_START                0x08000000
+/* Payload for V4L2_EVENT_VSYNC */
+struct <link linkend="v4l2-event-vsync">v4l2_event_vsync</link> {
+        /* Can be V4L2_FIELD_ANY, _NONE, _TOP or _BOTTOM */
+        __u8 field;
+} __attribute__ ((packed));
+struct <link linkend="v4l2-event">v4l2_event</link> {
+        __u32                           type;
+        union {
+                struct <link linkend="v4l2-event-vsync">v4l2_event_vsync</link> vsync;
+                __u8                    data[64];
+        } u;
+        __u32                           pending;
+        __u32                           sequence;
+        struct timespec                 timestamp;
+        __u32                           reserved[9];
+};
+struct <link linkend="v4l2-event-subscription">v4l2_event_subscription</link> {
+        __u32                           type;
+        __u32                           reserved[7];
+};
+/*
 *      A D V A N C E D   D E B U G G I N G
 *
 *      NOTE: EXPERIMENTAL API, NEVER RELY ON THIS IN APPLICATIONS!
@@ -1720,7 +1775,7 @@ struct <link linkend="v4l2-dbg-chip-ident">v4l2_dbg_chip_ident</link> {
 #define VIDIOC_G_EXT_CTRLS      _IOWR('V', 71, struct <link linkend="v4l2-ext-controls">v4l2_ext_controls</link>)
 #define VIDIOC_S_EXT_CTRLS      _IOWR('V', 72, struct <link linkend="v4l2-ext-controls">v4l2_ext_controls</link>)
 #define VIDIOC_TRY_EXT_CTRLS    _IOWR('V', 73, struct <link linkend="v4l2-ext-controls">v4l2_ext_controls</link>)
-#if 1 /*KEEP*/
+#if 1
 #define VIDIOC_ENUM_FRAMESIZES  _IOWR('V', 74, struct <link linkend="v4l2-frmsizeenum">v4l2_frmsizeenum</link>)
 #define VIDIOC_ENUM_FRAMEINTERVALS _IOWR('V', 75, struct <link linkend="v4l2-frmivalenum">v4l2_frmivalenum</link>)
 #define VIDIOC_G_ENC_INDEX       _IOR('V', 76, struct <link linkend="v4l2-enc-idx">v4l2_enc_idx</link>)
@@ -1728,7 +1783,7 @@ struct <link linkend="v4l2-dbg-chip-ident">v4l2_dbg_chip_ident</link> {
 #define VIDIOC_TRY_ENCODER_CMD  _IOWR('V', 78, struct <link linkend="v4l2-encoder-cmd">v4l2_encoder_cmd</link>)
 #endif
-#if 1 /*KEEP*/
+#if 1
 /* Experimental, meant for debugging, testing and internal use.
   Only implemented if CONFIG_VIDEO_ADV_DEBUG is defined.
   You must be root to use these ioctls. Never use these in applications! */
@@ -1747,6 +1802,9 @@ struct <link linkend="v4l2-dbg-chip-ident">v4l2_dbg_chip_ident</link> {
 #define VIDIOC_QUERY_DV_PRESET  _IOR('V',  86, struct <link linkend="v4l2-dv-preset">v4l2_dv_preset</link>)
 #define VIDIOC_S_DV_TIMINGS     _IOWR('V', 87, struct <link linkend="v4l2-dv-timings">v4l2_dv_timings</link>)
 #define VIDIOC_G_DV_TIMINGS     _IOWR('V', 88, struct <link linkend="v4l2-dv-timings">v4l2_dv_timings</link>)
+#define VIDIOC_DQEVENT           _IOR('V', 89, struct <link linkend="v4l2-event">v4l2_event</link>)
+#define VIDIOC_SUBSCRIBE_EVENT   _IOW('V', 90, struct <link linkend="v4l2-event-subscription">v4l2_event_subscription</link>)
+#define VIDIOC_UNSUBSCRIBE_EVENT _IOW('V', 91, struct <link linkend="v4l2-event-subscription">v4l2_event_subscription</link>)
 /* Reminder: when adding new ioctls please add support for them to
   drivers/media/video/v4l2-compat-ioctl32.c as well! */
diff --git a/Documentation/DocBook/v4l/vidioc-g-dv-preset.xml b/Documentation/DocBook/v4l/vidioc-g-dv-preset.xml
index 3c6784e132f3..d733721a7519 100644
--- a/Documentation/DocBook/v4l/vidioc-g-dv-preset.xml
+++ b/Documentation/DocBook/v4l/vidioc-g-dv-preset.xml
@@ -16,8 +16,7 @@
        <funcdef>int <function>ioctl</function></funcdef>
        <paramdef>int <parameter>fd</parameter></paramdef>
        <paramdef>int <parameter>request</parameter></paramdef>
-        <paramdef>&v4l2-dv-preset;
+        <paramdef>struct v4l2_dv_preset *<parameter>argp</parameter></paramdef>
-*<parameter>argp</parameter></paramdef>
      </funcprototype>
    </funcsynopsis>
  </refsynopsisdiv>
diff --git a/Documentation/DocBook/v4l/vidioc-g-dv-timings.xml b/Documentation/DocBook/v4l/vidioc-g-dv-timings.xml
index ecc19576bb8f..d5ec6abf0ce2 100644
--- a/Documentation/DocBook/v4l/vidioc-g-dv-timings.xml
+++ b/Documentation/DocBook/v4l/vidioc-g-dv-timings.xml
@@ -16,8 +16,7 @@
        <funcdef>int <function>ioctl</function></funcdef>
        <paramdef>int <parameter>fd</parameter></paramdef>
        <paramdef>int <parameter>request</parameter></paramdef>
-        <paramdef>&v4l2-dv-timings;
+        <paramdef>struct v4l2_dv_timings *<parameter>argp</parameter></paramdef>
-*<parameter>argp</parameter></paramdef>
      </funcprototype>
    </funcsynopsis>
  </refsynopsisdiv>
diff --git a/Documentation/DocBook/v4l/vidioc-query-dv-preset.xml b/Documentation/DocBook/v4l/vidioc-query-dv-preset.xml
index 402229ee06f6..d272f7ab91b8 100644
--- a/Documentation/DocBook/v4l/vidioc-query-dv-preset.xml
+++ b/Documentation/DocBook/v4l/vidioc-query-dv-preset.xml
@@ -16,7 +16,7 @@ input</refpurpose>
        <funcdef>int <function>ioctl</function></funcdef>
        <paramdef>int <parameter>fd</parameter></paramdef>
        <paramdef>int <parameter>request</parameter></paramdef>
-        <paramdef>&v4l2-dv-preset; *<parameter>argp</parameter></paramdef>
+        <paramdef>struct v4l2_dv_preset *<parameter>argp</parameter></paramdef>
      </funcprototype>
    </funcsynopsis>
  </refsynopsisdiv>
diff --git a/Documentation/DocBook/v4l/vidioc-querycap.xml b/Documentation/DocBook/v4l/vidioc-querycap.xml
index 6ab7e25b31b6..d499da93a450 100644
--- a/Documentation/DocBook/v4l/vidioc-querycap.xml
+++ b/Documentation/DocBook/v4l/vidioc-querycap.xml
@@ -184,7 +184,7 @@ data.</entry>
          <row>
            <entry><constant>V4L2_CAP_RDS_CAPTURE</constant></entry>
            <entry>0x00000100</entry>
-            <entry>The device supports the <link linkend="rds">RDS</link> interface.</entry>
+            <entry>The device supports the <link linkend="rds">RDS</link> capture interface.</entry>
          </row>
          <row>
            <entry><constant>V4L2_CAP_VIDEO_OUTPUT_OVERLAY</constant></entry>
@@ -206,6 +206,11 @@ driver capabilities.</para></footnote></entry>
 hardware frequency seeking.</entry>
          </row>
          <row>
+            <entry><constant>V4L2_CAP_RDS_OUTPUT</constant></entry>
+            <entry>0x00000800</entry>
+            <entry>The device supports the <link linkend="rds">RDS</link> output interface.</entry>
+          </row>
+          <row>
            <entry><constant>V4L2_CAP_TUNER</constant></entry>
            <entry>0x00010000</entry>
            <entry>The device has some sort of tuner to
diff --git a/Documentation/DocBook/v4l/vidioc-queryctrl.xml b/Documentation/DocBook/v4l/vidioc-queryctrl.xml
index 8e0e055ac934..0d5e8283cf32 100644
--- a/Documentation/DocBook/v4l/vidioc-queryctrl.xml
+++ b/Documentation/DocBook/v4l/vidioc-queryctrl.xml
@@ -103,8 +103,12 @@ structure. The driver fills the rest of the structure or returns an
 <structfield>index</structfield> is invalid. Menu items are enumerated
 by calling <constant>VIDIOC_QUERYMENU</constant> with successive
 <structfield>index</structfield> values from &v4l2-queryctrl;
-<structfield>minimum</structfield> (0) to
+<structfield>minimum</structfield> to
-<structfield>maximum</structfield>, inclusive.</para>
+<structfield>maximum</structfield>, inclusive. Note that it is possible
+for <constant>VIDIOC_QUERYMENU</constant> to return an &EINVAL; for some
+indices between <structfield>minimum</structfield> and <structfield>maximum</structfield>.
+In that case that particular menu item is not supported by this driver. Also note that
+the <structfield>minimum</structfield> value is not necessarily 0.</para>
    <para>See also the examples in <xref linkend="control" />.</para>
@@ -139,7 +143,7 @@ string. This information is intended for the user.</entry>
            <entry><structfield>minimum</structfield></entry>
            <entry>Minimum value, inclusive. This field gives a lower
 bound for <constant>V4L2_CTRL_TYPE_INTEGER</constant> controls and the
-lowest valid index (always 0) for <constant>V4L2_CTRL_TYPE_MENU</constant> controls.
+lowest valid index for <constant>V4L2_CTRL_TYPE_MENU</constant> controls.
 For <constant>V4L2_CTRL_TYPE_STRING</constant> controls the minimum value
 gives the minimum length of the string. This length <emphasis>does not include the terminating
 zero</emphasis>. It may not be valid for any other type of control, including
@@ -279,7 +283,7 @@ values which are actually different on the hardware.</entry>
          </row>
          <row>
            <entry><constant>V4L2_CTRL_TYPE_MENU</constant></entry>
-            <entry>0</entry>
+            <entry>&ge; 0</entry>
            <entry>1</entry>
            <entry>N-1</entry>
            <entry>The control has a menu of N choices. The names of
@@ -405,8 +409,10 @@ writing a value will cause the device to carry out a given action
        <term><errorcode>EINVAL</errorcode></term>
        <listitem>
          <para>The &v4l2-queryctrl; <structfield>id</structfield>
-is invalid. The &v4l2-querymenu; <structfield>id</structfield> or
+is invalid. The &v4l2-querymenu; <structfield>id</structfield> is
-<structfield>index</structfield> is invalid.</para>
+invalid or <structfield>index</structfield> is out of range (less than
+<structfield>minimum</structfield> or greater than <structfield>maximum</structfield>)
+or this particular menu item is not supported by the driver.</para>
        </listitem>
      </varlistentry>
      <varlistentry>
diff --git a/Documentation/DocBook/v4l/vidioc-s-hw-freq-seek.xml b/Documentation/DocBook/v4l/vidioc-s-hw-freq-seek.xml
index 14b3ec7ed75b..c30dcc4232c0 100644
--- a/Documentation/DocBook/v4l/vidioc-s-hw-freq-seek.xml
+++ b/Documentation/DocBook/v4l/vidioc-s-hw-freq-seek.xml
@@ -51,7 +51,8 @@
    <para>Start a hardware frequency seek from the current frequency.
 To do this applications initialize the <structfield>tuner</structfield>,
-<structfield>type</structfield>, <structfield>seek_upward</structfield> and
+<structfield>type</structfield>, <structfield>seek_upward</structfield>,
+<structfield>spacing</structfield> and
 <structfield>wrap_around</structfield> fields, and zero out the
 <structfield>reserved</structfield> array of a &v4l2-hw-freq-seek; and
 call the <constant>VIDIOC_S_HW_FREQ_SEEK</constant> ioctl with a pointer
@@ -89,7 +90,12 @@ field and the &v4l2-tuner; <structfield>index</structfield> field.</entry>
          </row>
          <row>
            <entry>__u32</entry>
-            <entry><structfield>reserved</structfield>[8]</entry>
+            <entry><structfield>spacing</structfield></entry>
+            <entry>If non-zero, defines the hardware seek resolution in Hz. The driver selects the nearest value that is supported by the device. If spacing is zero a reasonable default value is used.</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>
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 790d1a812376..0c134f8afc6f 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -218,13 +218,22 @@ over a rather long period of time, but improvements are always welcome!
        include:
        a.      Keeping a count of the number of data-structure elements
-                used by the RCU-protected data structure, including those
+                used by the RCU-protected data structure, including
-                waiting for a grace period to elapse.  Enforce a limit
+                those waiting for a grace period to elapse.  Enforce a
-                on this number, stalling updates as needed to allow
+                limit on this number, stalling updates as needed to allow
-                previously deferred frees to complete.
+                previously deferred frees to complete.  Alternatively,
+                limit only the number awaiting deferred free rather than
-                Alternatively, limit only the number awaiting deferred
+                the total number of elements.
-                free rather than the total number of elements.
+                One way to stall the updates is to acquire the update-side
+                mutex.  (Don't try this with a spinlock -- other CPUs
+                spinning on the lock could prevent the grace period
+                from ever ending.)  Another way to stall the updates
+                is for the updates to use a wrapper function around
+                the memory allocator, so that this wrapper function
+                simulates OOM when there is too much memory awaiting an
+                RCU grace period.  There are of course many other
+                variations on this theme.
        b.      Limiting update rate.  For example, if updates occur only
                once per hour, then no explicit rate limiting is required,
@@ -365,3 +374,26 @@ over a rather long period of time, but improvements are always welcome!
        and the compiler to freely reorder code into and out of RCU
        read-side critical sections.  It is the responsibility of the
        RCU update-side primitives to deal with this.
+17.     Use CONFIG_PROVE_RCU, CONFIG_DEBUG_OBJECTS_RCU_HEAD, and
+        the __rcu sparse checks to validate your RCU code.  These
+        can help find problems as follows:
+        CONFIG_PROVE_RCU: check that accesses to RCU-protected data
+                structures are carried out under the proper RCU
+                read-side critical section, while holding the right
+                combination of locks, or whatever other conditions
+                are appropriate.
+        CONFIG_DEBUG_OBJECTS_RCU_HEAD: check that you don't pass the
+                same object to call_rcu() (or friends) before an RCU
+                grace period has elapsed since the last time that you
+                passed that same object to call_rcu() (or friends).
+        __rcu sparse checks: tag the pointer to the RCU-protected data
+                structure with __rcu, and sparse will warn you if you
+                access that pointer without the services of one of the
+                variants of rcu_dereference().
+        These debugging aids can help you find problems that are
+        otherwise extremely difficult to spot.
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 44c6dcc93d6d..862c08ef1fde 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -80,6 +80,24 @@ o	A CPU looping with bottom halves disabled.  This condition can
 o       For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
        without invoking schedule().
+o       A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
+        happen to preempt a low-priority task in the middle of an RCU
+        read-side critical section.   This is especially damaging if
+        that low-priority task is not permitted to run on any other CPU,
+        in which case the next RCU grace period can never complete, which
+        will eventually cause the system to run out of memory and hang.
+        While the system is in the process of running itself out of
+        memory, you might see stall-warning messages.
+o       A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
+        is running at a higher priority than the RCU softirq threads.
+        This will prevent RCU callbacks from ever being invoked,
+        and in a CONFIG_TREE_PREEMPT_RCU kernel will further prevent
+        RCU grace periods from ever completing.  Either way, the
+        system will eventually run out of memory and hang.  In the
+        CONFIG_TREE_PREEMPT_RCU case, you might see stall-warning
+        messages.
 o       A bug in the RCU implementation.
 o       A hardware failure.  This is quite unlikely, but has occurred
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index efd8cc95c06b..a851118775d8 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -125,6 +125,17 @@ o	"b" is the batch limit for this CPU.  If more than this number
        of RCU callbacks is ready to invoke, then the remainder will
        be deferred.
+o       "ci" is the number of RCU callbacks that have been invoked for
+        this CPU.  Note that ci+ql is the number of callbacks that have
+        been registered in absence of CPU-hotplug activity.
+o       "co" is the number of RCU callbacks that have been orphaned due to
+        this CPU going offline.
+o       "ca" is the number of RCU callbacks that have been adopted due to
+        other CPUs going offline.  Note that ci+co-ca+ql is the number of
+        RCU callbacks registered on this CPU.
 There is also an rcu/rcudata.csv file with the same information in
 comma-separated-variable spreadsheet format.
@@ -180,7 +191,7 @@ o	"s" is the "signaled" state that drives force_quiescent_state()'s
 o       "jfq" is the number of jiffies remaining for this grace period
        before force_quiescent_state() is invoked to help push things
-        along.  Note that CPUs in dyntick-idle mode thoughout the grace
+        along.  Note that CPUs in dyntick-idle mode throughout the grace
        period will not report on their own, but rather must be check by
        some other CPU via force_quiescent_state().
diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
index 6e25c2659e0a..a2976a6de033 100644
--- a/Documentation/accounting/getdelays.c
+++ b/Documentation/accounting/getdelays.c
@@ -21,6 +21,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/socket.h>
+#include <sys/wait.h>
 #include <signal.h>
 #include <linux/genetlink.h>
@@ -266,11 +267,13 @@ int main(int argc, char *argv[])
        int containerset = 0;
        char containerpath[1024];
        int cfd = 0;
+        int forking = 0;
+        sigset_t sigset;
        struct msgtemplate msg;
-        while (1) {
+        while (!forking) {
-                c = getopt(argc, argv, "qdiw:r:m:t:p:vlC:");
+                c = getopt(argc, argv, "qdiw:r:m:t:p:vlC:c:");
                if (c < 0)
                        break;
@@ -319,6 +322,28 @@ int main(int argc, char *argv[])
                                err(1, "Invalid pid\n");
                        cmd_type = TASKSTATS_CMD_ATTR_PID;
                        break;
+                case 'c':
+                        /* Block SIGCHLD for sigwait() later */
+                        if (sigemptyset(&sigset) == -1)
+                                err(1, "Failed to empty sigset");
+                        if (sigaddset(&sigset, SIGCHLD))
+                                err(1, "Failed to set sigchld in sigset");
+                        sigprocmask(SIG_BLOCK, &sigset, NULL);
+                        /* fork/exec a child */
+                        tid = fork();
+                        if (tid < 0)
+                                err(1, "Fork failed\n");
+                        if (tid == 0)
+                                if (execvp(argv[optind - 1],
+                                    &argv[optind - 1]) < 0)
+                                        exit(-1);
+                        /* Set the command type and avoid further processing */
+                        cmd_type = TASKSTATS_CMD_ATTR_PID;
+                        forking = 1;
+                        break;
                case 'v':
                        printf("debug on\n");
                        dbg = 1;
@@ -370,6 +395,15 @@ int main(int argc, char *argv[])
                goto err;
        }
+        /*
+         * If we forked a child, wait for it to exit. Cannot use waitpid()
+         * as all the delicious data would be reaped as part of the wait
+         */
+        if (tid && forking) {
+                int sig_received;
+                sigwait(&sigset, &sig_received);
+        }
        if (tid) {
                rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET,
                              cmd_type, &tid, sizeof(__u32));
diff --git a/Documentation/arm/00-INDEX b/Documentation/arm/00-INDEX
index 7f5fc3ba9c91..ecf7d04bca26 100644
--- a/Documentation/arm/00-INDEX
+++ b/Documentation/arm/00-INDEX
@@ -6,6 +6,8 @@ Interrupts
        - ARM Interrupt subsystem documentation
 IXP2000
        - Release Notes for Linux on Intel's IXP2000 Network Processor
+msm
+        - MSM specific documentation
 Netwinder
        - Netwinder specific documentation
 Porting
diff --git a/Documentation/arm/SA1100/FreeBird b/Documentation/arm/SA1100/FreeBird
index fb23b770aaf4..ab9193663b2b 100644
--- a/Documentation/arm/SA1100/FreeBird
+++ b/Documentation/arm/SA1100/FreeBird
@@ -1,6 +1,6 @@
-Freebird-1.1 is produced by Legned(C) ,Inc.
+Freebird-1.1 is produced by Legend(C), Inc.
 http://web.archive.org/web/*/http://www.legend.com.cn
-and software/linux mainatined by Coventive(C),Inc.
+and software/linux maintained by Coventive(C), Inc.
 (http://www.coventive.com)
 Based on the Nicolas's strongarm kernel tree.
diff --git a/Documentation/arm/msm/gpiomux.txt b/Documentation/arm/msm/gpiomux.txt
new file mode 100644
index 000000000000..67a81620adf6
--- /dev/null
+++ b/Documentation/arm/msm/gpiomux.txt
@@ -0,0 +1,176 @@
+This document provides an overview of the msm_gpiomux interface, which
+is used to provide gpio pin multiplexing and configuration on mach-msm
+targets.
+History
+=======
+The first-generation API for gpio configuration & multiplexing on msm
+is the function gpio_tlmm_config().  This function has a few notable
+shortcomings, which led to its deprecation and replacement by gpiomux:
+The 'disable' parameter:  Setting the second parameter to
+gpio_tlmm_config to GPIO_CFG_DISABLE tells the peripheral
+processor in charge of the subsystem to perform a look-up into a
+low-power table and apply the low-power/sleep setting for the pin.
+As the msm family evolved this became problematic. Not all pins
+have sleep settings, not all peripheral processors will accept requests
+to apply said sleep settings, and not all msm targets have their gpio
+subsystems managed by a peripheral processor. In order to get consistent
+behavior on all targets, drivers are forced to ignore this parameter,
+rendering it useless.
+The 'direction' flag: for all mux-settings other than raw-gpio (0),
+the output-enable bit of a gpio is hard-wired to a known
+input (usually VDD or ground).  For those settings, the direction flag
+is meaningless at best, and deceptive at worst.  In addition, using the
+direction flag to change output-enable (OE) directly can cause trouble in
+gpiolib, which has no visibility into gpio direction changes made
+in this way.  Direction control in gpio mode should be made through gpiolib.
+Key Features of gpiomux
+=======================
+- A consistent interface across all generations of msm.  Drivers can expect
+the same results on every target.
+- gpiomux plays nicely with gpiolib.  Functions that should belong to gpiolib
+are left to gpiolib and not duplicated here.  gpiomux is written with the
+intent that gpio_chips will call gpiomux reference-counting methods
+from their request() and free() hooks, providing full integration.
+- Tabular configuration.  Instead of having to call gpio_tlmm_config
+hundreds of times, gpio configuration is placed in a single table.
+- Per-gpio sleep.  Each gpio is individually reference counted, allowing only
+those lines which are in use to be put in high-power states.
+- 0 means 'do nothing': all flags are designed so that the default memset-zero
+equates to a sensible default of 'no configuration', preventing users
+from having to provide hundreds of 'no-op' configs for unused or
+unwanted lines.
+Usage
+=====
+To use gpiomux, provide configuration information for relevant gpio lines
+in the msm_gpiomux_configs table.  Since a 0 equates to "unconfigured",
+only those lines to be managed by gpiomux need to be specified.  Here
+is a completely fictional example:
+struct msm_gpiomux_config msm_gpiomux_configs[GPIOMUX_NGPIOS] = {
+        [12] = {
+                .active = GPIOMUX_VALID | GPIOMUX_DRV_8MA | GPIOMUX_FUNC_1,
+                .suspended = GPIOMUX_VALID | GPIOMUX_PULL_DOWN,
+        },
+        [34] = {
+                .suspended = GPIOMUX_VALID | GPIOMUX_PULL_DOWN,
+        },
+};
+To indicate that a gpio is in use, call msm_gpiomux_get() to increase
+its reference count.  To decrease the reference count, call msm_gpiomux_put().
+The effect of this configuration is as follows:
+When the system boots, gpios 12 and 34 will be initialized with their
+'suspended' configurations.  All other gpios, which were left unconfigured,
+will not be touched.
+When msm_gpiomux_get() is called on gpio 12 to raise its reference count
+above 0, its active configuration will be applied.  Since no other gpio
+line has a valid active configuration, msm_gpiomux_get() will have no
+effect on any other line.
+When msm_gpiomux_put() is called on gpio 12 or 34 to drop their reference
+count to 0, their suspended configurations will be applied.
+Since no other gpio line has a valid suspended configuration, no other
+gpio line will be effected by msm_gpiomux_put().  Since gpio 34 has no valid
+active configuration, this is effectively a no-op for gpio 34 as well,
+with one small caveat, see the section "About Output-Enable Settings".
+All of the GPIOMUX_VALID flags may seem like unnecessary overhead, but
+they address some important issues.  As unused entries (all those
+except 12 and 34) are zero-filled, gpiomux needs a way to distinguish
+the used fields from the unused.  In addition, the all-zero pattern
+is a valid configuration!  Therefore, gpiomux defines an additional bit
+which is used to indicate when a field is used.  This has the pleasant
+side-effect of allowing calls to msm_gpiomux_write to use '0' to indicate
+that a value should not be changed:
+  msm_gpiomux_write(0, GPIOMUX_VALID, 0);
+replaces the active configuration of gpio 0 with an all-zero configuration,
+but leaves the suspended configuration as it was.
+Static Configurations
+=====================
+To install a static configuration, which is applied at boot and does
+not change after that, install a configuration with a suspended component
+but no active component, as in the previous example:
+        [34] = {
+                .suspended = GPIOMUX_VALID | GPIOMUX_PULL_DOWN,
+        },
+The suspended setting is applied during boot, and the lack of any valid
+active setting prevents any other setting from being applied at runtime.
+If other subsystems attempting to access the line is a concern, one could
+*really* anchor the configuration down by calling msm_gpiomux_get on the
+line at initialization to move the line into active mode.  With the line
+held, it will never be re-suspended, and with no valid active configuration,
+no new configurations will be applied.
+But then, if having other subsystems grabbing for the line is truly a concern,
+it should be reserved with gpio_request instead, which carries an implicit
+msm_gpiomux_get.
+gpiomux and gpiolib
+===================
+It is expected that msm gpio_chips will call msm_gpiomux_get() and
+msm_gpiomux_put() from their request and free hooks, like this fictional
+example:
+static int request(struct gpio_chip *chip, unsigned offset)
+{
+        return msm_gpiomux_get(chip->base + offset);
+}
+static void free(struct gpio_chip *chip, unsigned offset)
+{
+        msm_gpiomux_put(chip->base + offset);
+}
+        ...somewhere in a gpio_chip declaration...
+        .request = request,
+        .free    = free,
+This provides important functionality:
+- It guarantees that a gpio line will have its 'active' config applied
+  when the line is requested, and will not be suspended while the line
+  remains requested; and
+- It guarantees that gpio-direction settings from gpiolib behave sensibly.
+  See "About Output-Enable Settings."
+This mechanism allows for "auto-request" of gpiomux lines via gpiolib
+when it is suitable.  Drivers wishing more exact control are, of course,
+free to also use msm_gpiomux_set and msm_gpiomux_get.
+About Output-Enable Settings
+============================
+Some msm targets do not have the ability to query the current gpio
+configuration setting.  This means that changes made to the output-enable
+(OE) bit by gpiolib cannot be consistently detected and preserved by gpiomux.
+Therefore, when gpiomux applies a configuration setting, any direction
+settings which may have been applied by gpiolib are lost and the default
+input settings are re-applied.
+For this reason, drivers should not assume that gpio direction settings
+continue to hold if they free and then re-request a gpio.  This seems like
+common sense - after all, anybody could have obtained the line in the
+meantime - but it needs saying.
+This also means that calls to msm_gpiomux_write will reset the OE bit,
+which means that if the gpio line is held by a client of gpiolib and
+msm_gpiomux_write is called, the direction setting has been lost and
+gpiolib's internal state has been broken.
+Release gpio lines before reconfiguring them.
diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX
index a406286f6f3e..d111e3b23db0 100644
--- a/Documentation/block/00-INDEX
+++ b/Documentation/block/00-INDEX
@@ -1,7 +1,5 @@
 00-INDEX
        - This file
-barrier.txt
-        - I/O Barriers
 biodoc.txt
        - Notes on the Generic Block Layer Rewrite in Linux 2.5
 capability.txt
@@ -16,3 +14,5 @@ stat.txt
        - Block layer statistics in /sys/block/<dev>/stat
 switching-sched.txt
        - Switching I/O schedulers at runtime
+writeback_cache_control.txt
+        - Control of volatile write back caches
diff --git a/Documentation/block/barrier.txt b/Documentation/block/barrier.txt
deleted file mode 100644
index 2c2f24f634e4..000000000000
--- a/Documentation/block/barrier.txt
+++ /dev/null
@@ -1,261 +0,0 @@
-I/O Barriers
-============
-Tejun Heo <htejun@gmail.com>, July 22 2005
-I/O barrier requests are used to guarantee ordering around the barrier
-requests.  Unless you're crazy enough to use disk drives for
-implementing synchronization constructs (wow, sounds interesting...),
-the ordering is meaningful only for write requests for things like
-journal checkpoints.  All requests queued before a barrier request
-must be finished (made it to the physical medium) before the barrier
-request is started, and all requests queued after the barrier request
-must be started only after the barrier request is finished (again,
-made it to the physical medium).
-In other words, I/O barrier requests have the following two properties.
-1. Request ordering
-Requests cannot pass the barrier request.  Preceding requests are
-processed before the barrier and following requests after.
-Depending on what features a drive supports, this can be done in one
-of the following three ways.
-i. For devices which have queue depth greater than 1 (TCQ devices) and
-support ordered tags, block layer can just issue the barrier as an
-ordered request and the lower level driver, controller and drive
-itself are responsible for making sure that the ordering constraint is
-met.  Most modern SCSI controllers/drives should support this.
-NOTE: SCSI ordered tag isn't currently used due to limitation in the
-      SCSI midlayer, see the following random notes section.
-ii. For devices which have queue depth greater than 1 but don't
-support ordered tags, block layer ensures that the requests preceding
-a barrier request finishes before issuing the barrier request.  Also,
-it defers requests following the barrier until the barrier request is
-finished.  Older SCSI controllers/drives and SATA drives fall in this
-category.
-iii. Devices which have queue depth of 1.  This is a degenerate case
-of ii.  Just keeping issue order suffices.  Ancient SCSI
-controllers/drives and IDE drives are in this category.
-2. Forced flushing to physical medium
-Again, if you're not gonna do synchronization with disk drives (dang,
-it sounds even more appealing now!), the reason you use I/O barriers
-is mainly to protect filesystem integrity when power failure or some
-other events abruptly stop the drive from operating and possibly make
-the drive lose data in its cache.  So, I/O barriers need to guarantee
-that requests actually get written to non-volatile medium in order.
-There are four cases,
-i. No write-back cache.  Keeping requests ordered is enough.
-ii. Write-back cache but no flush operation.  There's no way to
-guarantee physical-medium commit order.  This kind of devices can't to
-I/O barriers.
-iii. Write-back cache and flush operation but no FUA (forced unit
-access).  We need two cache flushes - before and after the barrier
-request.
-iv. Write-back cache, flush operation and FUA.  We still need one
-flush to make sure requests preceding a barrier are written to medium,
-but post-barrier flush can be avoided by using FUA write on the
-barrier itself.
-How to support barrier requests in drivers
------------------------------------------
-All barrier handling is done inside block layer proper.  All low level
-drivers have to are implementing its prepare_flush_fn and using one
-the following two functions to indicate what barrier type it supports
-and how to prepare flush requests.  Note that the term 'ordered' is
-used to indicate the whole sequence of performing barrier requests
-including draining and flushing.
-typedef void (prepare_flush_fn)(struct request_queue *q, struct request *rq);
-int blk_queue_ordered(struct request_queue *q, unsigned ordered,
-                      prepare_flush_fn *prepare_flush_fn);
-@q                      : the queue in question
-@ordered                : the ordered mode the driver/device supports
-@prepare_flush_fn       : this function should prepare @rq such that it
-                          flushes cache to physical medium when executed
-For example, SCSI disk driver's prepare_flush_fn looks like the
-following.
-static void sd_prepare_flush(struct request_queue *q, struct request *rq)
-{
-        memset(rq->cmd, 0, sizeof(rq->cmd));
-        rq->cmd_type = REQ_TYPE_BLOCK_PC;
-        rq->timeout = SD_TIMEOUT;
-        rq->cmd[0] = SYNCHRONIZE_CACHE;
-        rq->cmd_len = 10;
-}
-The following seven ordered modes are supported.  The following table
-shows which mode should be used depending on what features a
-device/driver supports.  In the leftmost column of table,
-QUEUE_ORDERED_ prefix is omitted from the mode names to save space.
-The table is followed by description of each mode.  Note that in the
-descriptions of QUEUE_ORDERED_DRAIN*, '=>' is used whereas '->' is
-used for QUEUE_ORDERED_TAG* descriptions.  '=>' indicates that the
-preceding step must be complete before proceeding to the next step.
-'->' indicates that the next step can start as soon as the previous
-step is issued.
-            write-back cache    ordered tag     flush           FUA
-----------------------------------------------------------------------
-NONE            yes/no          N/A             no              N/A
-DRAIN           no              no              N/A             N/A
-DRAIN_FLUSH     yes             no              yes             no
-DRAIN_FUA       yes             no              yes             yes
-TAG             no              yes             N/A             N/A
-TAG_FLUSH       yes             yes             yes             no
-TAG_FUA         yes             yes             yes             yes
-QUEUE_ORDERED_NONE
-        I/O barriers are not needed and/or supported.
-        Sequence: N/A
-QUEUE_ORDERED_DRAIN
-        Requests are ordered by draining the request queue and cache
-        flushing isn't needed.
-        Sequence: drain => barrier
-QUEUE_ORDERED_DRAIN_FLUSH
-        Requests are ordered by draining the request queue and both
-        pre-barrier and post-barrier cache flushings are needed.
-        Sequence: drain => preflush => barrier => postflush
-QUEUE_ORDERED_DRAIN_FUA
-        Requests are ordered by draining the request queue and
-        pre-barrier cache flushing is needed.  By using FUA on barrier
-        request, post-barrier flushing can be skipped.
-        Sequence: drain => preflush => barrier
-QUEUE_ORDERED_TAG
-        Requests are ordered by ordered tag and cache flushing isn't
-        needed.
-        Sequence: barrier
-QUEUE_ORDERED_TAG_FLUSH
-        Requests are ordered by ordered tag and both pre-barrier and
-        post-barrier cache flushings are needed.
-        Sequence: preflush -> barrier -> postflush
-QUEUE_ORDERED_TAG_FUA
-        Requests are ordered by ordered tag and pre-barrier cache
-        flushing is needed.  By using FUA on barrier request,
-        post-barrier flushing can be skipped.
-        Sequence: preflush -> barrier
-Random notes/caveats
--------------------
-* SCSI layer currently can't use TAG ordering even if the drive,
-controller and driver support it.  The problem is that SCSI midlayer
-request dispatch function is not atomic.  It releases queue lock and
-switch to SCSI host lock during issue and it's possible and likely to
-happen in time that requests change their relative positions.  Once
-this problem is solved, TAG ordering can be enabled.
-* Currently, no matter which ordered mode is used, there can be only
-one barrier request in progress.  All I/O barriers are held off by
-block layer until the previous I/O barrier is complete.  This doesn't
-make any difference for DRAIN ordered devices, but, for TAG ordered
-devices with very high command latency, passing multiple I/O barriers
-to low level *might* be helpful if they are very frequent.  Well, this
-certainly is a non-issue.  I'm writing this just to make clear that no
-two I/O barrier is ever passed to low-level driver.
-* Completion order.  Requests in ordered sequence are issued in order
-but not required to finish in order.  Barrier implementation can
-handle out-of-order completion of ordered sequence.  IOW, the requests
-MUST be processed in order but the hardware/software completion paths
-are allowed to reorder completion notifications - eg. current SCSI
-midlayer doesn't preserve completion order during error handling.
-* Requeueing order.  Low-level drivers are free to requeue any request
-after they removed it from the request queue with
-blkdev_dequeue_request().  As barrier sequence should be kept in order
-when requeued, generic elevator code takes care of putting requests in
-order around barrier.  See blk_ordered_req_seq() and
-ELEVATOR_INSERT_REQUEUE handling in __elv_add_request() for details.
-Note that block drivers must not requeue preceding requests while
-completing latter requests in an ordered sequence.  Currently, no
-error checking is done against this.
-* Error handling.  Currently, block layer will report error to upper
-layer if any of requests in an ordered sequence fails.  Unfortunately,
-this doesn't seem to be enough.  Look at the following request flow.
-QUEUE_ORDERED_TAG_FLUSH is in use.
- [0] [1] [2] [3] [pre] [barrier] [post] < [4] [5] [6] ... >
-                                          still in elevator
-Let's say request [2], [3] are write requests to update file system
-metadata (journal or whatever) and [barrier] is used to mark that
-those updates are valid.  Consider the following sequence.
- i.     Requests [0] ~ [post] leaves the request queue and enters
-        low-level driver.
- ii.    After a while, unfortunately, something goes wrong and the
-        drive fails [2].  Note that any of [0], [1] and [3] could have
-        completed by this time, but [pre] couldn't have been finished
-        as the drive must process it in order and it failed before
-        processing that command.
- iii.   Error handling kicks in and determines that the error is
-        unrecoverable and fails [2], and resumes operation.
- iv.    [pre] [barrier] [post] gets processed.
- v.     *BOOM* power fails
-The problem here is that the barrier request is *supposed* to indicate
-that filesystem update requests [2] and [3] made it safely to the
-physical medium and, if the machine crashes after the barrier is
-written, filesystem recovery code can depend on that.  Sadly, that
-isn't true in this case anymore.  IOW, the success of a I/O barrier
-should also be dependent on success of some of the preceding requests,
-where only upper layer (filesystem) knows what 'some' is.
-This can be solved by implementing a way to tell the block layer which
-requests affect the success of the following barrier request and
-making lower lever drivers to resume operation on error only after
-block layer tells it to do so.
-As the probability of this happening is very low and the drive should
-be faulty, implementing the fix is probably an overkill.  But, still,
-it's there.
-* In previous drafts of barrier implementation, there was fallback
-mechanism such that, if FUA or ordered TAG fails, less fancy ordered
-mode can be selected and the failed barrier request is retried
-automatically.  The rationale for this feature was that as FUA is
-pretty new in ATA world and ordered tag was never used widely, there
-could be devices which report to support those features but choke when
-actually given such requests.
- This was removed for two reasons 1. it's an overkill 2. it's
-impossible to implement properly when TAG ordering is used as low
-level drivers resume after an error automatically.  If it's ever
-needed adding it back and modifying low level drivers accordingly
-shouldn't be difficult.
diff --git a/Documentation/block/writeback_cache_control.txt b/Documentation/block/writeback_cache_control.txt
new file mode 100644
index 000000000000..83407d36630a
--- /dev/null
+++ b/Documentation/block/writeback_cache_control.txt
@@ -0,0 +1,86 @@
+Explicit volatile write back cache control
+=====================================
+Introduction
+------------
+Many storage devices, especially in the consumer market, come with volatile
+write back caches.  That means the devices signal I/O completion to the
+operating system before data actually has hit the non-volatile storage.  This
+behavior obviously speeds up various workloads, but it means the operating
+system needs to force data out to the non-volatile storage when it performs
+a data integrity operation like fsync, sync or an unmount.
+The Linux block layer provides two simple mechanisms that let filesystems
+control the caching behavior of the storage device.  These mechanisms are
+a forced cache flush, and the Force Unit Access (FUA) flag for requests.
+Explicit cache flushes
+----------------------
+The REQ_FLUSH flag can be OR ed into the r/w flags of a bio submitted from
+the filesystem and will make sure the volatile cache of the storage device
+has been flushed before the actual I/O operation is started.  This explicitly
+guarantees that previously completed write requests are on non-volatile
+storage before the flagged bio starts. In addition the REQ_FLUSH flag can be
+set on an otherwise empty bio structure, which causes only an explicit cache
+flush without any dependent I/O.  It is recommend to use
+the blkdev_issue_flush() helper for a pure cache flush.
+Forced Unit Access
+-----------------
+The REQ_FUA flag can be OR ed into the r/w flags of a bio submitted from the
+filesystem and will make sure that I/O completion for this request is only
+signaled after the data has been committed to non-volatile storage.
+Implementation details for filesystems
+--------------------------------------
+Filesystems can simply set the REQ_FLUSH and REQ_FUA bits and do not have to
+worry if the underlying devices need any explicit cache flushing and how
+the Forced Unit Access is implemented.  The REQ_FLUSH and REQ_FUA flags
+may both be set on a single bio.
+Implementation details for make_request_fn based block drivers
+--------------------------------------------------------------
+These drivers will always see the REQ_FLUSH and REQ_FUA bits as they sit
+directly below the submit_bio interface.  For remapping drivers the REQ_FUA
+bits need to be propagated to underlying devices, and a global flush needs
+to be implemented for bios with the REQ_FLUSH bit set.  For real device
+drivers that do not have a volatile cache the REQ_FLUSH and REQ_FUA bits
+on non-empty bios can simply be ignored, and REQ_FLUSH requests without
+data can be completed successfully without doing any work.  Drivers for
+devices with volatile caches need to implement the support for these
+flags themselves without any help from the block layer.
+Implementation details for request_fn based block drivers
+--------------------------------------------------------------
+For devices that do not support volatile write caches there is no driver
+support required, the block layer completes empty REQ_FLUSH requests before
+entering the driver and strips off the REQ_FLUSH and REQ_FUA bits from
+requests that have a payload.  For devices with volatile write caches the
+driver needs to tell the block layer that it supports flushing caches by
+doing:
+        blk_queue_flush(sdkp->disk->queue, REQ_FLUSH);
+and handle empty REQ_FLUSH requests in its prep_fn/request_fn.  Note that
+REQ_FLUSH requests with a payload are automatically turned into a sequence
+of an empty REQ_FLUSH request followed by the actual write by the block
+layer.  For devices that also support the FUA bit the block layer needs
+to be told to pass through the REQ_FUA bit using:
+        blk_queue_flush(sdkp->disk->queue, REQ_FLUSH | REQ_FUA);
+and the driver must handle write requests that have the REQ_FUA bit set
+in prep_fn/request_fn.  If the FUA bit is not natively supported the block
+layer turns it into an empty REQ_FLUSH request after the actual write.
diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt
index 6919d62591d9..d6da611f8f63 100644
--- a/Documentation/cgroups/blkio-controller.txt
+++ b/Documentation/cgroups/blkio-controller.txt
@@ -8,12 +8,17 @@ both at leaf nodes as well as at intermediate nodes in a storage hierarchy.
 Plan is to use the same cgroup based management interface for blkio controller
 and based on user options switch IO policies in the background.
-In the first phase, this patchset implements proportional weight time based
+Currently two IO control policies are implemented. First one is proportional
-division of disk policy. It is implemented in CFQ. Hence this policy takes
+weight time based division of disk policy. It is implemented in CFQ. Hence
-effect only on leaf nodes when CFQ is being used.
+this policy takes effect only on leaf nodes when CFQ is being used. The second
+one is throttling policy which can be used to specify upper IO rate limits
+on devices. This policy is implemented in generic block layer and can be
+used on leaf nodes as well as higher level logical devices like device mapper.
 HOWTO
 =====
+Proportional Weight division of bandwidth
+-----------------------------------------
 You can do a very simple testing of running two dd threads in two different
 cgroups. Here is what you can do.
@@ -55,6 +60,35 @@ cgroups. Here is what you can do.
  group dispatched to the disk. We provide fairness in terms of disk time, so
  ideally io.disk_time of cgroups should be in proportion to the weight.
+Throttling/Upper Limit policy
+-----------------------------
+- Enable Block IO controller
+        CONFIG_BLK_CGROUP=y
+- Enable throttling in block layer
+        CONFIG_BLK_DEV_THROTTLING=y
+- Mount blkio controller
+        mount -t cgroup -o blkio none /cgroup/blkio
+- Specify a bandwidth rate on particular device for root group. The format
+  for policy is "<major>:<minor>  <byes_per_second>".
+        echo "8:16  1048576" > /cgroup/blkio/blkio.read_bps_device
+  Above will put a limit of 1MB/second on reads happening for root group
+  on device having major/minor number 8:16.
+- Run dd to read a file and see if rate is throttled to 1MB/s or not.
+                # dd if=/mnt/common/zerofile of=/dev/null bs=4K count=1024
+                # iflag=direct
+        1024+0 records in
+        1024+0 records out
+        4194304 bytes (4.2 MB) copied, 4.0001 s, 1.0 MB/s
+ Limits for writes can be put using blkio.write_bps_device file.
 Various user visible config options
 ===================================
 CONFIG_BLK_CGROUP
@@ -68,8 +102,13 @@ CONFIG_CFQ_GROUP_IOSCHED
        - Enables group scheduling in CFQ. Currently only 1 level of group
          creation is allowed.
+CONFIG_BLK_DEV_THROTTLING
+        - Enable block device throttling support in block layer.
 Details of cgroup files
 =======================
+Proportional weight policy files
+--------------------------------
 - blkio.weight
        - Specifies per cgroup weight. This is default weight of the group
          on all the devices until and unless overridden by per device rule.
@@ -210,6 +249,67 @@ Details of cgroup files
          and minor number of the device and third field specifies the number
          of times a group was dequeued from a particular device.
+Throttling/Upper limit policy files
+-----------------------------------
+- blkio.throttle.read_bps_device
+        - Specifies upper limit on READ rate from the device. IO rate is
+          specified in bytes per second. Rules are per deivce. Following is
+          the format.
+  echo "<major>:<minor>  <rate_bytes_per_second>" > /cgrp/blkio.read_bps_device
+- blkio.throttle.write_bps_device
+        - Specifies upper limit on WRITE rate to the device. IO rate is
+          specified in bytes per second. Rules are per deivce. Following is
+          the format.
+  echo "<major>:<minor>  <rate_bytes_per_second>" > /cgrp/blkio.write_bps_device
+- blkio.throttle.read_iops_device
+        - Specifies upper limit on READ rate from the device. IO rate is
+          specified in IO per second. Rules are per deivce. Following is
+          the format.
+  echo "<major>:<minor>  <rate_io_per_second>" > /cgrp/blkio.read_iops_device
+- blkio.throttle.write_iops_device
+        - Specifies upper limit on WRITE rate to the device. IO rate is
+          specified in io per second. Rules are per deivce. Following is
+          the format.
+  echo "<major>:<minor>  <rate_io_per_second>" > /cgrp/blkio.write_iops_device
+Note: If both BW and IOPS rules are specified for a device, then IO is
+      subjectd to both the constraints.
+- blkio.throttle.io_serviced
+        - Number of IOs (bio) completed to/from the disk by the group (as
+          seen by throttling policy). 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_serviced does accounting as seen by CFQ and counts are in
+          number of requests (struct request). On the other hand,
+          blkio.throttle.io_serviced counts number of IO in terms of number
+          of bios as seen by throttling policy.  These bios can later be
+          merged by elevator and total number of requests completed can be
+          lesser.
+- blkio.throttle.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.
+          These numbers should roughly be same as blkio.io_service_bytes as
+          updated by CFQ. The difference between two is that
+          blkio.io_service_bytes will not be updated if CFQ is not operating
+          on request queue.
+Common files among various policies
+-----------------------------------
 - blkio.reset_stats
        - Writing an int to this file will result in resetting all the stats
          for that cgroup.
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index b34823ff1646..190018b0c649 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -18,7 +18,8 @@ CONTENTS:
  1.2 Why are cgroups needed ?
  1.3 How are cgroups implemented ?
  1.4 What does notify_on_release do ?
-  1.5 How do I use cgroups ?
+  1.5 What does clone_children do ?
+  1.6 How do I use cgroups ?
 2. Usage Examples and Syntax
  2.1 Basic Usage
  2.2 Attaching processes
@@ -293,7 +294,16 @@ notify_on_release in the root cgroup at system boot is disabled
 value of their parents notify_on_release setting. The default value of
 a cgroup hierarchy's release_agent path is empty.
-1.5 How do I use cgroups ?
+1.5 What does clone_children do ?
+---------------------------------
+If the clone_children flag is enabled (1) in a cgroup, then all
+cgroups created beneath will call the post_clone callbacks for each
+subsystem of the newly created cgroup. Usually when this callback is
+implemented for a subsystem, it copies the values of the parent
+subsystem, this is the case for the cpuset.
+1.6 How do I use cgroups ?
 --------------------------
 To start a new job that is to be contained within a cgroup, using
diff --git a/Documentation/coccinelle.txt b/Documentation/coccinelle.txt
index cd2b02837066..4a276ea7001c 100644
--- a/Documentation/coccinelle.txt
+++ b/Documentation/coccinelle.txt
@@ -24,6 +24,9 @@ of many distributions, e.g. :
 You can get the latest version released from the Coccinelle homepage at
 http://coccinelle.lip6.fr/
+Information and tips about Coccinelle are also provided on the wiki
+pages at http://cocci.ekstranet.diku.dk/wiki/doku.php
 Once you have it, run the following command:
        ./configure
@@ -41,20 +44,22 @@ A Coccinelle-specific target is defined in the top level
 Makefile. This target is named 'coccicheck' and calls the 'coccicheck'
 front-end in the 'scripts' directory.
-Four modes are defined: report, patch, context, and org. The mode to
+Four modes are defined: patch, report, context, and org. The mode to
 use is specified by setting the MODE variable with 'MODE=<mode>'.
+'patch' proposes a fix, when possible.
 'report' generates a list in the following format:
  file:line:column-column: message
-'patch' proposes a fix, when possible.
 'context' highlights lines of interest and their context in a
 diff-like style.Lines of interest are indicated with '-'.
 'org' generates a report in the Org mode format of Emacs.
-Note that not all semantic patches implement all modes.
+Note that not all semantic patches implement all modes. For easy use
+of Coccinelle, the default mode is "chain" which tries the previous
+modes in the order above until one succeeds.
 To make a report for every semantic patch, run the following command:
@@ -68,9 +73,9 @@ To produce patches, run:
 The coccicheck target applies every semantic patch available in the
-subdirectories of 'scripts/coccinelle' to the entire Linux kernel.
+sub-directories of 'scripts/coccinelle' to the entire Linux kernel.
-For each semantic patch, a changelog message is proposed.  It gives a
+For each semantic patch, a commit message is proposed.  It gives a
 description of the problem being checked by the semantic patch, and
 includes a reference to Coccinelle.
@@ -93,12 +98,35 @@ or
        make coccicheck COCCI=<my_SP.cocci> MODE=report
+ Using Coccinelle on (modified) files
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+To apply Coccinelle on a file basis, instead of a directory basis, the
+following command may be used:
+    make C=1 CHECK="scripts/coccicheck"
+To check only newly edited code, use the value 2 for the C flag, i.e.
+    make C=2 CHECK="scripts/coccicheck"
+This runs every semantic patch in scripts/coccinelle by default. The
+COCCI variable may additionally be used to only apply a single
+semantic patch as shown in the previous section.
+The "chain" mode is the default. You can select another one with the
+MODE variable explained above.
+In this mode, there is no information about semantic patches
+displayed, and no commit message proposed.
 Proposing new semantic patches
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 New semantic patches can be proposed and submitted by kernel
 developers. For sake of clarity, they should be organized in the
-subdirectories of 'scripts/coccinelle/'.
+sub-directories of 'scripts/coccinelle/'.
 Detailed description of the 'report' mode
@@ -111,7 +139,7 @@ Example:
 Running
-        make coccicheck MODE=report COCCI=scripts/coccinelle/err_cast.cocci
+        make coccicheck MODE=report COCCI=scripts/coccinelle/api/err_cast.cocci
 will execute the following part of the SmPL script.
@@ -149,7 +177,7 @@ identified.
 Example:
 Running
-        make coccicheck MODE=patch COCCI=scripts/coccinelle/err_cast.cocci
+        make coccicheck MODE=patch COCCI=scripts/coccinelle/api/err_cast.cocci
 will execute the following part of the SmPL script.
@@ -193,7 +221,7 @@ NOTE: The diff-like output generated is NOT an applicable patch. The
 Example:
 Running
-        make coccicheck MODE=context COCCI=scripts/coccinelle/err_cast.cocci
+        make coccicheck MODE=context COCCI=scripts/coccinelle/api/err_cast.cocci
 will execute the following part of the SmPL script.
@@ -228,7 +256,7 @@ diff -u -p /home/user/linux/crypto/ctr.c /tmp/nothing
 Example:
 Running
-        make coccicheck MODE=org COCCI=scripts/coccinelle/err_cast.cocci
+        make coccicheck MODE=org COCCI=scripts/coccinelle/api/err_cast.cocci
 will execute the following part of the SmPL script.
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index f1c5c4bccd3e..902d3151f527 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -14,25 +14,39 @@ to /proc/cpuinfo.
        identifier (rather than the kernel's).  The actual value is
        architecture and platform dependent.
-3) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+3) /sys/devices/system/cpu/cpuX/topology/book_id:
+        the book ID of cpuX. Typically it is the hardware platform's
+        identifier (rather than the kernel's).  The actual value is
+        architecture and platform dependent.
+4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
        internel kernel map of cpuX's hardware threads within the same
        core as cpuX
-4) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+5) /sys/devices/system/cpu/cpuX/topology/core_siblings:
        internal kernel map of cpuX's hardware threads within the same
        physical_package_id.
+6) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+        internal kernel map of cpuX's hardware threads within the same
+        book_id.
 To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 4 attributes.
+drivers/base/topology.c, is to export the 4 or 6 attributes. The two book
+related sysfs files will only be created if CONFIG_SCHED_BOOK is selected.
 For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
+#define topology_book_id(cpu)
 #define topology_thread_cpumask(cpu)
 #define topology_core_cpumask(cpu)
+#define topology_book_cpumask(cpu)
 The type of **_id is int.
 The type of siblings is (const) struct cpumask *.
@@ -45,6 +59,9 @@ not defined by include/asm-XXX/topology.h:
 3) thread_siblings: just the given CPU
 4) core_siblings: just the given CPU
+For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
+default definitions for topology_book_id() and topology_book_cpumask().
 Additionally, CPU topology information is provided under
 /sys/devices/system/cpu and includes these files.  The internal
 source for the output is in brackets ("[]").
diff --git a/Documentation/devices.txt b/Documentation/devices.txt
index d0d1df6cb5de..eccffe715229 100644
--- a/Documentation/devices.txt
+++ b/Documentation/devices.txt
@@ -239,6 +239,7 @@ Your cooperation is appreciated.
                  0 = /dev/tty          Current TTY device
                  1 = /dev/console      System console
                  2 = /dev/ptmx         PTY master multiplex
+                  3 = /dev/ttyprintk    User messages via printk TTY device
                 64 = /dev/cua0         Callout device for ttyS0
                    ...
                255 = /dev/cua191       Callout device for ttyS191
@@ -1495,9 +1496,6 @@ Your cooperation is appreciated.
                 64 = /dev/radio0       Radio device
                    ...
                127 = /dev/radio63      Radio device
-                192 = /dev/vtx0         Teletext device
-                    ...
-                223 = /dev/vtx31        Teletext device
                224 = /dev/vbi0         Vertical blank interrupt
                    ...
                255 = /dev/vbi31        Vertical blank interrupt
@@ -2519,6 +2517,12 @@ Your cooperation is appreciated.
                  8 = /dev/mmcblk1      Second SD/MMC card
                    ...
+                The start of next SD/MMC card can be configured with
+                CONFIG_MMC_BLOCK_MINORS, or overridden at boot/modprobe
+                time using the mmcblk.perdev_minors option. That would
+                bump the offset between each card to be the configured
+                value instead of the default 8.
 179 char        CCube DVXChip-based PCI products
                  0 = /dev/dvxirq0      First DVX device
                  1 = /dev/dvxirq1      Second DVX device
@@ -2553,7 +2557,10 @@ Your cooperation is appreciated.
                175 = /dev/usb/legousbtower15   16th USB Legotower device
                176 = /dev/usb/usbtmc1  First USB TMC device
                   ...
-                192 = /dev/usb/usbtmc16 16th USB TMC device
+                191 = /dev/usb/usbtmc16 16th USB TMC device
+                192 = /dev/usb/yurex1   First USB Yurex device
+                   ...
+                209 = /dev/usb/yurex16  16th USB Yurex device
                240 = /dev/usb/dabusb0  First daubusb device
                    ...
                243 = /dev/usb/dabusb3  Fourth dabusb device
diff --git a/Documentation/dvb/get_dvb_firmware b/Documentation/dvb/get_dvb_firmware
index 350959f4e41b..59690de8ebfe 100644
--- a/Documentation/dvb/get_dvb_firmware
+++ b/Documentation/dvb/get_dvb_firmware
@@ -26,7 +26,8 @@ use IO::Handle;
                "dec3000s", "vp7041", "dibusb", "nxt2002", "nxt2004",
                "or51211", "or51132_qam", "or51132_vsb", "bluebird",
                "opera1", "cx231xx", "cx18", "cx23885", "pvrusb2", "mpc718",
-                "af9015", "ngene", "az6027");
+                "af9015", "ngene", "az6027", "lme2510_lg", "lme2510c_s7395",
+                "lme2510c_s7395_old");
 # Check args
 syntax() if (scalar(@ARGV) != 1);
@@ -584,6 +585,49 @@ sub az6027{
    $firmware;
 }
+sub lme2510_lg {
+    my $sourcefile = "LMEBDA_DVBS.sys";
+    my $hash = "fc6017ad01e79890a97ec53bea157ed2";
+    my $outfile = "dvb-usb-lme2510-lg.fw";
+    my $hasho = "caa065d5fdbd2c09ad57b399bbf55cad";
+    checkstandard();
+    verify($sourcefile, $hash);
+    extract($sourcefile, 4168, 3841, $outfile);
+    verify($outfile, $hasho);
+    $outfile;
+}
+sub lme2510c_s7395 {
+    my $sourcefile = "US2A0D.sys";
+    my $hash = "b0155a8083fb822a3bd47bc360e74601";
+    my $outfile = "dvb-usb-lme2510c-s7395.fw";
+    my $hasho = "3a3cf1aeebd17b6ddc04cebe131e94cf";
+    checkstandard();
+    verify($sourcefile, $hash);
+    extract($sourcefile, 37248, 3720, $outfile);
+    verify($outfile, $hasho);
+    $outfile;
+}
+sub lme2510c_s7395_old {
+    my $sourcefile = "LMEBDA_DVBS7395C.sys";
+    my $hash = "7572ae0eb9cdf91baabd7c0ba9e09b31";
+    my $outfile = "dvb-usb-lme2510c-s7395.fw";
+    my $hasho = "90430c5b435eb5c6f88fd44a9d950674";
+    checkstandard();
+    verify($sourcefile, $hash);
+    extract($sourcefile, 4208, 3881, $outfile);
+    verify($outfile, $hasho);
+    $outfile;
+}
 # ---------------------------------------------------------------
 # Utilities
diff --git a/Documentation/dvb/lmedm04.txt b/Documentation/dvb/lmedm04.txt
new file mode 100644
index 000000000000..e175784b89bf
--- /dev/null
+++ b/Documentation/dvb/lmedm04.txt
@@ -0,0 +1,58 @@
+To extract firmware for the DM04/QQBOX you need to copy the
+following file(s) to this directory.
+for DM04+/QQBOX LME2510C (Sharp 7395 Tuner)
+-------------------------------------------
+The Sharp 7395 driver can be found in windows/system32/driver
+US2A0D.sys (dated 17 Mar 2009)
+and run
+./get_dvb_firmware lme2510c_s7395
+        will produce
+        dvb-usb-lme2510c-s7395.fw
+An alternative but older firmware can be found on the driver
+disk DVB-S_EN_3.5A in BDADriver/driver
+LMEBDA_DVBS7395C.sys (dated 18 Jan 2008)
+and run
+./get_dvb_firmware lme2510c_s7395_old
+        will produce
+        dvb-usb-lme2510c-s7395.fw
+--------------------------------------------------------------------
+The LG firmware can be found on the driver
+disk DM04+_5.1A[LG] in BDADriver/driver
+for DM04 LME2510 (LG Tuner)
+---------------------------
+LMEBDA_DVBS.sys (dated 13 Nov 2007)
+and run
+./get_dvb_firmware lme2510_lg
+        will produce
+        dvb-usb-lme2510-lg.fw
+Other LG firmware can be extracted manually from US280D.sys
+only found in windows/system32/driver.
+dd if=US280D.sys ibs=1 skip=42616 count=3668 of=dvb-usb-lme2510-lg.fw
+for DM04 LME2510C (LG Tuner)
+---------------------------
+dd if=US280D.sys ibs=1 skip=35200 count=3850 of=dvb-usb-lme2510c-lg.fw
+---------------------------------------------------------------------
+Copy the firmware file(s) to /lib/firmware
diff --git a/Documentation/dynamic-debug-howto.txt b/Documentation/dynamic-debug-howto.txt
index 674c5663d346..58ea64a96165 100644
--- a/Documentation/dynamic-debug-howto.txt
+++ b/Documentation/dynamic-debug-howto.txt
@@ -24,7 +24,7 @@ Dynamic debug has even more useful features:
   read to display the complete list of known debug statements, to help guide you
 Controlling dynamic debug Behaviour
-===============================
+===================================
 The behaviour of pr_debug()/dev_debug()s are controlled via writing to a
 control file in the 'debugfs' filesystem. Thus, you must first mount the debugfs
@@ -212,6 +212,26 @@ Note the regexp ^[-+=][scp]+$ matches a flags specification.
 Note also that there is no convenient syntax to remove all
 the flags at once, you need to use "-psc".
+Debug messages during boot process
+==================================
+To be able to activate debug messages during the boot process,
+even before userspace and debugfs exists, use the boot parameter:
+ddebug_query="QUERY"
+QUERY follows the syntax described above, but must not exceed 1023
+characters. The enablement of debug messages is done as an arch_initcall.
+Thus you can enable debug messages in all code processed after this
+arch_initcall via this boot parameter.
+On an x86 system for example ACPI enablement is a subsys_initcall and
+ddebug_query="file ec.c +p"
+will show early Embedded Controller transactions during ACPI setup if
+your machine (typically a laptop) has an Embedded Controller.
+PCI (or other devices) initialization also is a hot candidate for using
+this boot parameter for debugging purposes.
 Examples
 ========
diff --git a/Documentation/fb/viafb.txt b/Documentation/fb/viafb.txt
index f3e046a6a987..1a2e8aa3fbb1 100644
--- a/Documentation/fb/viafb.txt
+++ b/Documentation/fb/viafb.txt
@@ -197,6 +197,54 @@ Notes:
       example,
           # fbset -depth 16
+[Configure viafb via /proc]
+---------------------------
+    The following files exist in /proc/viafb
+    supported_output_devices
+        This read-only file contains a full ',' seperated list containing all
+        output devices that could be available on your platform. It is likely
+        that not all of those have a connector on your hardware but it should
+        provide a good starting point to figure out which of those names match
+        a real connector.
+        Example:
+        # cat /proc/viafb/supported_output_devices
+    iga1/output_devices
+    iga2/output_devices
+        These two files are readable and writable. iga1 and iga2 are the two
+        independent units that produce the screen image. Those images can be
+        forwarded to one or more output devices. Reading those files is a way
+        to query which output devices are currently used by an iga.
+        Example:
+        # cat /proc/viafb/iga1/output_devices
+        If there are no output devices printed the output of this iga is lost.
+        This can happen for example if only one (the other) iga is used.
+        Writing to these files allows adjusting the output devices during
+        runtime. One can add new devices, remove existing ones or switch
+        between igas. Essentially you can write a ',' seperated list of device
+        names (or a single one) in the same format as the output to those
+        files. You can add a '+' or '-' as a prefix allowing simple addition
+        and removal of devices. So a prefix '+' adds the devices from your list
+        to the already existing ones, '-' removes the listed devices from the
+        existing ones and if no prefix is given it replaces all existing ones
+        with the listed ones. If you remove devices they are expected to turn
+        off. If you add devices that are already part of the other iga they are
+        removed there and added to the new one.
+        Examples:
+        Add CRT as output device to iga1
+        # echo +CRT > /proc/viafb/iga1/output_devices
+        Remove (turn off) DVP1 and LVDS1 as output devices of iga2
+        # echo -DVP1,LVDS1 > /proc/viafb/iga2/output_devices
+        Replace all iga1 output devices by CRT
+        # echo CRT > /proc/viafb/iga1/output_devices
 [Bootup with viafb]:
 --------------------
    Add the following line to your grub.conf:
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 842aa9de84a6..d8f36f984faa 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -98,7 +98,7 @@ Who:	Pavel Machek <pavel@ucw.cz>
 ---------------------------
 What:   Video4Linux API 1 ioctls and from Video devices.
-When:   July 2009
+When:   kernel 2.6.38
 Files:  include/linux/videodev.h
 Check:  include/linux/videodev.h
 Why:    V4L1 AP1 was replaced by V4L2 API during migration from 2.4 to 2.6
@@ -116,6 +116,21 @@ Who:	Mauro Carvalho Chehab <mchehab@infradead.org>
 ---------------------------
+What:   Video4Linux obsolete drivers using V4L1 API
+When:   kernel 2.6.38
+Files:  drivers/staging/cpia/* drivers/staging/stradis/*
+Check:  drivers/staging/cpia/cpia.c drivers/staging/stradis/stradis.c
+Why:    There are some drivers still using V4L1 API, despite all efforts we've done
+        to migrate. Those drivers are for obsolete hardware that the old maintainer
+        didn't care (or not have the hardware anymore), and that no other developer
+        could find any hardware to buy. They probably have no practical usage today,
+        and people with such old hardware could probably keep using an older version
+        of the kernel. Those drivers will be moved to staging on 2.6.37 and, if nobody
+        care enough to port and test them with V4L2 API, they'll be removed on 2.6.38.
+Who:    Mauro Carvalho Chehab <mchehab@infradead.org>
+---------------------------
 What:   sys_sysctl
 When:   September 2010
 Option: CONFIG_SYSCTL_SYSCALL
@@ -386,34 +401,6 @@ Who:	Tejun Heo <tj@kernel.org>
 ----------------------------
-What:   Support for VMware's guest paravirtuliazation technique [VMI] will be
-        dropped.
-When:   2.6.37 or earlier.
-Why:    With the recent innovations in CPU hardware acceleration technologies
-        from Intel and AMD, VMware ran a few experiments to compare these
-        techniques to guest paravirtualization technique on VMware's platform.
-        These hardware assisted virtualization techniques have outperformed the
-        performance benefits provided by VMI in most of the workloads. VMware
-        expects that these hardware features will be ubiquitous in a couple of
-        years, as a result, VMware has started a phased retirement of this
-        feature from the hypervisor. We will be removing this feature from the
-        Kernel too. Right now we are targeting 2.6.37 but can retire earlier if
-        technical reasons (read opportunity to remove major chunk of pvops)
-        arise.
-        Please note that VMI has always been an optimization and non-VMI kernels
-        still work fine on VMware's platform.
-        Latest versions of VMware's product which support VMI are,
-        Workstation 7.0 and VSphere 4.0 on ESX side, future maintainence
-        releases for these products will continue supporting VMI.
-        For more details about VMI retirement take a look at this,
-        http://blogs.vmware.com/guestosguide/2009/09/vmi-retirement.html
-Who:    Alok N Kataria <akataria@vmware.com>
----------------------------
 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
@@ -498,29 +485,6 @@ 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
@@ -530,16 +494,6 @@ Who:	Thomas Gleixner <tglx@linutronix.de>
 ----------------------------
-What:   old ieee1394 subsystem (CONFIG_IEEE1394)
-When:   2.6.37
-Files:  drivers/ieee1394/ except init_ohci1394_dma.c
-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>
----------------------------
 What:   The acpi_sleep=s4_nonvs command line option
 When:   2.6.37
 Files:  arch/x86/kernel/acpi/sleep.c
@@ -564,3 +518,39 @@ Who:	FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
 ----------------------------
+What:   namespace cgroup (ns_cgroup)
+When:   2.6.38
+Why:    The ns_cgroup leads to some problems:
+        * cgroup creation is out-of-control
+        * cgroup name can conflict when pids are looping
+        * it is not possible to have a single process handling
+        a lot of namespaces without falling in a exponential creation time
+        * we may want to create a namespace without creating a cgroup
+        The ns_cgroup is replaced by a compatibility flag 'clone_children',
+        where a newly created cgroup will copy the parent cgroup values.
+        The userspace has to manually create a cgroup and add a task to
+        the 'tasks' file.
+Who:    Daniel Lezcano <daniel.lezcano@free.fr>
+----------------------------
+What:   iwlwifi disable_hw_scan module parameters
+When:   2.6.40
+Why:    Hareware scan is the prefer method for iwlwifi devices for
+        scanning operation. Remove software scan support for all the
+        iwlwifi devices.
+Who:    Wey-Yi Guy <wey-yi.w.guy@intel.com>
+----------------------------
+What:   access to nfsd auth cache through sys_nfsservctl or '.' files
+        in the 'nfsd' filesystem.
+When:   2.6.40
+Why:    This is a legacy interface which have been replaced by a more
+        dynamic cache.  Continuing to maintain this interface is an
+        unnecessary burden.
+Who:    NeilBrown <neilb@suse.de>
+----------------------------
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 4303614b5add..8c624a18f67d 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -96,8 +96,6 @@ seq_file.txt
        - how to use the seq_file API
 sharedsubtree.txt
        - a description of shared subtrees for namespaces.
-smbfs.txt
-        - info on using filesystems with the SMB protocol (Win 3.11 and NT).
 spufs.txt
        - info and mount options for the SPU filesystem used on Cell.
 sysfs-pci.txt
diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt
index f9765e8cf086..b22abba78fed 100644
--- a/Documentation/filesystems/9p.txt
+++ b/Documentation/filesystems/9p.txt
@@ -111,7 +111,7 @@ OPTIONS
                This can be used to share devices/named pipes/sockets between
                hosts.  This functionality will be expanded in later versions.
-  access        there are three access modes.
+  access        there are four access modes.
                        user  = if a user tries to access a file on v9fs
                                filesystem for the first time, v9fs sends an
                                attach command (Tattach) for that user.
@@ -120,6 +120,8 @@ OPTIONS
                                the files on the mounted filesystem
                        any   = v9fs does single attach and performs all
                                operations as one user
+                        client = ACL based access check on the 9p client
+                                 side for access validation
  cachetag      cache tag to use the specified persistent cache.
                cache tags for existing cache sessions can be listed at
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 2db4283efa8d..a91f30890011 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -322,7 +322,6 @@ fl_release_private:	yes	yes
 prototypes:
        int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
        void (*fl_notify)(struct file_lock *);  /* unblock callback */
-        void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
        void (*fl_release_private)(struct file_lock *);
        void (*fl_break)(struct file_lock *); /* break_lease callback */
@@ -330,7 +329,6 @@ locking rules:
                        BKL     may block
 fl_compare_owner:       yes     no
 fl_notify:              yes     no
-fl_copy_lock:           yes     no
 fl_release_private:     yes     yes
 fl_break:               yes     no
@@ -349,21 +347,36 @@ call this method upon the IO completion.
 --------------------------- block_device_operations -----------------------
 prototypes:
-        int (*open) (struct inode *, struct file *);
+        int (*open) (struct block_device *, fmode_t);
-        int (*release) (struct inode *, struct file *);
+        int (*release) (struct gendisk *, fmode_t);
-        int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
+        int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+        int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+        int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *);
        int (*media_changed) (struct gendisk *);
+        void (*unlock_native_capacity) (struct gendisk *);
        int (*revalidate_disk) (struct gendisk *);
+        int (*getgeo)(struct block_device *, struct hd_geometry *);
+        void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 locking rules:
-                        BKL     bd_sem
+                        BKL     bd_mutex
-open:                   yes     yes
+open:                   no      yes
-release:                yes     yes
+release:                no      yes
-ioctl:                  yes     no
+ioctl:                  no      no
+compat_ioctl:           no      no
+direct_access:          no      no
 media_changed:          no      no
+unlock_native_capacity: no      no
 revalidate_disk:        no      no
+getgeo:                 no      no
+swap_slot_free_notify:  no      no      (see below)
+media_changed, unlock_native_capacity and revalidate_disk are called only from
+check_disk_change().
+swap_slot_free_notify is called with swap_lock and sometimes the page lock
+held.
-The last two are called only from check_disk_change().
 --------------------------- file_operations -------------------------------
 prototypes:
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index e1def1786e50..6ab9442d7eeb 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -353,6 +353,20 @@ noauto_da_alloc		replacing existing files via patterns such as
                        system crashes before the delayed allocation
                        blocks are forced to disk.
+noinit_itable           Do not initialize any uninitialized inode table
+                        blocks in the background.  This feature may be
+                        used by installation CD's so that the install
+                        process can complete as quickly as possible; the
+                        inode table initialization process would then be
+                        deferred until the next time the  file system
+                        is unmounted.
+init_itable=n           The lazy itable init code will wait n times the
+                        number of milliseconds it took to zero out the
+                        previous block group's inode table.  This
+                        minimizes the impact on the systme performance
+                        while file system's inode table is being initialized.
 discard         Controls whether ext4 should issue discard/TRIM
 nodiscard(*)            commands to the underlying block device when
                        blocks are freed.  This is useful for SSD devices
diff --git a/Documentation/filesystems/nfs/00-INDEX b/Documentation/filesystems/nfs/00-INDEX
index 2f68cd688769..a57e12411d2a 100644
--- a/Documentation/filesystems/nfs/00-INDEX
+++ b/Documentation/filesystems/nfs/00-INDEX
@@ -12,5 +12,9 @@ nfs-rdma.txt
        - how to install and setup the Linux NFS/RDMA client and server software
 nfsroot.txt
        - short guide on setting up a diskless box with NFS root filesystem.
+pnfs.txt
+        - short explanation of some of the internals of the pnfs client code
 rpc-cache.txt
        - introduction to the caching mechanisms in the sunrpc layer.
+idmapper.txt
+        - information for configuring request-keys to be used by idmapper
diff --git a/Documentation/filesystems/nfs/idmapper.txt b/Documentation/filesystems/nfs/idmapper.txt
new file mode 100644
index 000000000000..b9b4192ea8b5
--- /dev/null
+++ b/Documentation/filesystems/nfs/idmapper.txt
@@ -0,0 +1,67 @@
+=========
+ID Mapper
+=========
+Id mapper is used by NFS to translate user and group ids into names, and to
+translate user and group names into ids.  Part of this translation involves
+performing an upcall to userspace to request the information.  Id mapper will
+user request-key to perform this upcall and cache the result.  The program
+/usr/sbin/nfs.idmap should be called by request-key, and will perform the
+translation and initialize a key with the resulting information.
+ NFS_USE_NEW_IDMAPPER must be selected when configuring the kernel to use this
+ feature.
+===========
+Configuring
+===========
+The file /etc/request-key.conf will need to be modified so /sbin/request-key can
+direct the upcall.  The following line should be added:
+#OP     TYPE    DESCRIPTION     CALLOUT INFO    PROGRAM ARG1 ARG2 ARG3 ...
+#====== ======= =============== =============== ===============================
+create  id_resolver     *       *               /usr/sbin/nfs.idmap %k %d 600
+This will direct all id_resolver requests to the program /usr/sbin/nfs.idmap.
+The last parameter, 600, defines how many seconds into the future the key will
+expire.  This parameter is optional for /usr/sbin/nfs.idmap.  When the timeout
+is not specified, nfs.idmap will default to 600 seconds.
+id mapper uses for key descriptions:
+          uid:  Find the UID for the given user
+          gid:  Find the GID for the given group
+         user:  Find the user  name for the given UID
+        group:  Find the group name for the given GID
+You can handle any of these individually, rather than using the generic upcall
+program.  If you would like to use your own program for a uid lookup then you
+would edit your request-key.conf so it look similar to this:
+#OP     TYPE    DESCRIPTION     CALLOUT INFO    PROGRAM ARG1 ARG2 ARG3 ...
+#====== ======= =============== =============== ===============================
+create  id_resolver     uid:*   *               /some/other/program %k %d 600
+create  id_resolver     *       *               /usr/sbin/nfs.idmap %k %d 600
+Notice that the new line was added above the line for the generic program.
+request-key will find the first matching line and corresponding program.  In
+this case, /some/other/program will handle all uid lookups and
+/usr/sbin/nfs.idmap will handle gid, user, and group lookups.
+See <file:Documentation/keys-request-keys.txt> for more information about the
+request-key function.
+=========
+nfs.idmap
+=========
+nfs.idmap is designed to be called by request-key, and should not be run "by
+hand".  This program takes two arguments, a serialized key and a key
+description.  The serialized key is first converted into a key_serial_t, and
+then passed as an argument to keyctl_instantiate (both are part of keyutils.h).
+The actual lookups are performed by functions found in nfsidmap.h.  nfs.idmap
+determines the correct function to call by looking at the first part of the
+description string.  For example, a uid lookup description will appear as
+"uid:user@domain".
+nfs.idmap will return 0 if the key was instantiated, and non-zero otherwise.
diff --git a/Documentation/filesystems/nfs/nfsroot.txt b/Documentation/filesystems/nfs/nfsroot.txt
index f2430a7974e1..90c71c6f0d00 100644
--- a/Documentation/filesystems/nfs/nfsroot.txt
+++ b/Documentation/filesystems/nfs/nfsroot.txt
@@ -159,6 +159,28 @@ ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>
                Default: any
+nfsrootdebug
+  This parameter enables debugging messages to appear in the kernel
+  log at boot time so that administrators can verify that the correct
+  NFS mount options, server address, and root path are passed to the
+  NFS client.
+rdinit=<executable file>
+  To specify which file contains the program that starts system
+  initialization, administrators can use this command line parameter.
+  The default value of this parameter is "/init".  If the specified
+  file exists and the kernel can execute it, root filesystem related
+  kernel command line parameters, including `nfsroot=', are ignored.
+  A description of the process of mounting the root file system can be
+  found in:
+    Documentation/early-userspace/README
 3.) Boot Loader
diff --git a/Documentation/filesystems/nfs/pnfs.txt b/Documentation/filesystems/nfs/pnfs.txt
new file mode 100644
index 000000000000..bc0b9cfe095b
--- /dev/null
+++ b/Documentation/filesystems/nfs/pnfs.txt
@@ -0,0 +1,48 @@
+Reference counting in pnfs:
+==========================
+The are several inter-related caches.  We have layouts which can
+reference multiple devices, each of which can reference multiple data servers.
+Each data server can be referenced by multiple devices.  Each device
+can be referenced by multiple layouts.  To keep all of this straight,
+we need to reference count.
+struct pnfs_layout_hdr
+----------------------
+The on-the-wire command LAYOUTGET corresponds to struct
+pnfs_layout_segment, usually referred to by the variable name lseg.
+Each nfs_inode may hold a pointer to a cache of of these layout
+segments in nfsi->layout, of type struct pnfs_layout_hdr.
+We reference the header for the inode pointing to it, across each
+outstanding RPC call that references it (LAYOUTGET, LAYOUTRETURN,
+LAYOUTCOMMIT), and for each lseg held within.
+Each header is also (when non-empty) put on a list associated with
+struct nfs_client (cl_layouts).  Being put on this list does not bump
+the reference count, as the layout is kept around by the lseg that
+keeps it in the list.
+deviceid_cache
+--------------
+lsegs reference device ids, which are resolved per nfs_client and
+layout driver type.  The device ids are held in a RCU cache (struct
+nfs4_deviceid_cache).  The cache itself is referenced across each
+mount.  The entries (struct nfs4_deviceid) themselves are held across
+the lifetime of each lseg referencing them.
+RCU is used because the deviceid is basically a write once, read many
+data structure.  The hlist size of 32 buckets needs better
+justification, but seems reasonable given that we can have multiple
+deviceid's per filesystem, and multiple filesystems per nfs_client.
+The hash code is copied from the nfsd code base.  A discussion of
+hashing and variations of this algorithm can be found at:
+http://groups.google.com/group/comp.lang.c/browse_thread/thread/9522965e2b8d3809
+data server cache
+-----------------
+file driver devices refer to data servers, which are kept in a module
+level cache.  Its reference is held over the lifetime of the deviceid
+pointing to it.
diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt
index 1f7ae144f6d8..5393e6611691 100644
--- a/Documentation/filesystems/ocfs2.txt
+++ b/Documentation/filesystems/ocfs2.txt
@@ -87,3 +87,10 @@ 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.
+coherency=full  (*)     Disallow concurrent O_DIRECT writes, cluster inode
+                        lock will be taken to force other nodes drop cache,
+                        therefore full cluster coherency is guaranteed even
+                        for O_DIRECT writes.
+coherency=buffered      Allow concurrent O_DIRECT writes without EX lock among
+                        nodes, which gains high performance at risk of getting
+                        stale data on other nodes.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index a6aca8740883..e73df2722ff3 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -136,6 +136,7 @@ Table 1-1: Process specific entries in /proc
 statm          Process memory status information
 status         Process status in human readable form
 wchan          If CONFIG_KALLSYMS is set, a pre-decoded wchan
+ pagemap        Page table
 stack          Report full stack trace, enable via CONFIG_STACKTRACE
 smaps          a extension based on maps, showing the memory consumption of
                each mapping
@@ -370,17 +371,24 @@ Shared_Dirty:          0 kB
 Private_Clean:         0 kB
 Private_Dirty:         0 kB
 Referenced:          892 kB
+Anonymous:             0 kB
 Swap:                  0 kB
 KernelPageSize:        4 kB
 MMUPageSize:           4 kB
-The first  of these lines shows  the same information  as is displayed for the
+The first of these lines shows the same information as is displayed for the
-mapping in /proc/PID/maps.  The remaining lines show  the size of the mapping,
+mapping in /proc/PID/maps.  The remaining lines show the size of the mapping
-the amount of the mapping that is currently resident in RAM, the "proportional
+(size), the amount of the mapping that is currently resident in RAM (RSS), the
-set size” (divide each shared page by the number of processes sharing it), the
+process' proportional share of this mapping (PSS), the number of clean and
-number of clean and dirty shared pages in the mapping, and the number of clean
+dirty private pages in the mapping.  Note that even a page which is part of a
-and dirty private pages in the mapping.  The "Referenced" indicates the amount
+MAP_SHARED mapping, but has only a single pte mapped, i.e.  is currently used
-of memory currently marked as referenced or accessed.
+by only one process, is accounted as private and not as shared.  "Referenced"
+indicates the amount of memory currently marked as referenced or accessed.
+"Anonymous" shows the amount of memory that does not belong to any file.  Even
+a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
+and a page is modified, the file page is replaced by a private anonymous copy.
+"Swap" shows how much would-be-anonymous memory is also used, but out on
+swap.
 This file is only present if the CONFIG_MMU kernel configuration option is
 enabled.
@@ -397,6 +405,9 @@ To clear the bits for the file mapped pages associated with the process
    > echo 3 > /proc/PID/clear_refs
 Any other value written to /proc/PID/clear_refs will have no effect.
+The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
+using /proc/kpageflags and number of times a page is mapped using
+/proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
 1.2 Kernel data
 ---------------
diff --git a/Documentation/filesystems/sharedsubtree.txt b/Documentation/filesystems/sharedsubtree.txt
index fc0e39af43c3..4ede421c9687 100644
--- a/Documentation/filesystems/sharedsubtree.txt
+++ b/Documentation/filesystems/sharedsubtree.txt
@@ -62,10 +62,10 @@ replicas continue to be exactly same.
        # mount /dev/sd0  /tmp/a
        #ls /tmp/a
-        t1 t2 t2
+        t1 t2 t3
        #ls /mnt/a
-        t1 t2 t2
+        t1 t2 t3
        Note that the mount has propagated to the mount at /mnt as well.
diff --git a/Documentation/filesystems/smbfs.txt b/Documentation/filesystems/smbfs.txt
deleted file mode 100644
index 194fb0decd2c..000000000000
--- a/Documentation/filesystems/smbfs.txt
+++ /dev/null
@@ -1,8 +0,0 @@
-Smbfs is a filesystem that implements the SMB protocol, which is the
-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 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/hwmon/it87 b/Documentation/hwmon/it87
index 8d08bf0d38ed..38425f0f2645 100644
--- a/Documentation/hwmon/it87
+++ b/Documentation/hwmon/it87
@@ -22,6 +22,10 @@ Supported chips:
    Prefix: 'it8720'
    Addresses scanned: from Super I/O config space (8 I/O ports)
    Datasheet: Not publicly available
+  * IT8721F/IT8758E
+    Prefix: 'it8721'
+    Addresses scanned: from Super I/O config space (8 I/O ports)
+    Datasheet: Not publicly available
  * SiS950   [clone of IT8705F]
    Prefix: 'it87'
    Addresses scanned: from Super I/O config space (8 I/O ports)
@@ -67,7 +71,7 @@ Description
 -----------
 This driver implements support for the IT8705F, IT8712F, IT8716F,
-IT8718F, IT8720F, IT8726F and SiS950 chips.
+IT8718F, IT8720F, IT8721F, IT8726F, IT8758E and SiS950 chips.
 These chips are 'Super I/O chips', supporting floppy disks, infrared ports,
 joysticks and other miscellaneous stuff. For hardware monitoring, they
@@ -86,14 +90,15 @@ the driver won't notice and report changes in the VID value. The two
 upper VID bits share their pins with voltage inputs (in5 and in6) so you
 can't have both on a given board.
-The IT8716F, IT8718F, IT8720F and later IT8712F revisions have support for
+The IT8716F, IT8718F, IT8720F, IT8721F/IT8758E and later IT8712F revisions
-2 additional fans. The additional fans are supported by the driver.
+have support for 2 additional fans. The additional fans are supported by the
+driver.
-The IT8716F, IT8718F and IT8720F, and late IT8712F and IT8705F also have
+The IT8716F, IT8718F, IT8720F and IT8721F/IT8758E, and late IT8712F and
-optional 16-bit tachometer counters for fans 1 to 3. This is better (no more
+IT8705F also have optional 16-bit tachometer counters for fans 1 to 3. This
-fan clock divider mess) but not compatible with the older chips and
+is better (no more fan clock divider mess) but not compatible with the older
-revisions. The 16-bit tachometer mode is enabled by the driver when one
+chips and revisions. The 16-bit tachometer mode is enabled by the driver when
-of the above chips is detected.
+one of the above chips is detected.
 The IT8726F is just bit enhanced IT8716F with additional hardware
 for AMD power sequencing. Therefore the chip will appear as IT8716F
@@ -115,7 +120,12 @@ alarm is triggered if the voltage has crossed a programmable minimum or
 maximum limit. Note that minimum in this case always means 'closest to
 zero'; this is important for negative voltage measurements. All voltage
 inputs can measure voltages between 0 and 4.08 volts, with a resolution of
-0.016 volt. The battery voltage in8 does not have limit registers.
+0.016 volt (except IT8721F/IT8758E: 0.012 volt.) The battery voltage in8 does
+not have limit registers.
+On the IT8721F/IT8758E, some voltage inputs are internal and scaled inside
+the chip (in7, in8 and optionally in3). The driver handles this transparently
+so user-space doesn't have to care.
 The VID lines (IT8712F/IT8716F/IT8718F/IT8720F) encode the core voltage value:
 the voltage level your processor should work with. This is hardcoded by
diff --git a/Documentation/hwmon/lm85 b/Documentation/hwmon/lm85
index b98e0e0d1910..239258a63c81 100644
--- a/Documentation/hwmon/lm85
+++ b/Documentation/hwmon/lm85
@@ -14,6 +14,10 @@ Supported chips:
    Prefix: 'adt7463'
    Addresses scanned: I2C 0x2c, 0x2d, 0x2e
    Datasheet: http://www.onsemi.com/PowerSolutions/product.do?id=ADT7463
+  * Analog Devices ADT7468
+    Prefix: 'adt7468'
+    Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+    Datasheet: http://www.onsemi.com/PowerSolutions/product.do?id=ADT7468
  * SMSC EMC6D100, SMSC EMC6D101
    Prefix: 'emc6d100'
    Addresses scanned: I2C 0x2c, 0x2d, 0x2e
@@ -34,7 +38,7 @@ Description
 -----------
 This driver implements support for the National Semiconductor LM85 and
-compatible chips including the Analog Devices ADM1027, ADT7463 and
+compatible chips including the Analog Devices ADM1027, ADT7463, ADT7468 and
 SMSC EMC6D10x chips family.
 The LM85 uses the 2-wire interface compatible with the SMBUS 2.0
@@ -87,14 +91,22 @@ To smooth the response of fans to changes in temperature, the LM85 has an
 optional filter for smoothing temperatures. The ADM1027 has the same
 config option but uses it to rate limit the changes to fan speed instead.
-The ADM1027 and ADT7463 have a 10-bit ADC and can therefore measure
+The ADM1027, ADT7463 and ADT7468 have a 10-bit ADC and can therefore
-temperatures with 0.25 degC resolution. They also provide an offset to the
+measure temperatures with 0.25 degC resolution. They also provide an offset
-temperature readings that is automatically applied during measurement.
+to the temperature readings that is automatically applied during
-This offset can be used to zero out any errors due to traces and placement.
+measurement. This offset can be used to zero out any errors due to traces
-The documentation says that the offset is in 0.25 degC steps, but in
+and placement. The documentation says that the offset is in 0.25 degC
-initial testing of the ADM1027 it was 1.00 degC steps. Analog Devices has
+steps, but in initial testing of the ADM1027 it was 1.00 degC steps. Analog
-confirmed this "bug". The ADT7463 is reported to work as described in the
+Devices has confirmed this "bug". The ADT7463 is reported to work as
-documentation. The current lm85 driver does not show the offset register.
+described in the documentation. The current lm85 driver does not show the
+offset register.
+The ADT7468 has a high-frequency PWM mode, where all PWM outputs are
+driven by a 22.5 kHz clock. This is a global mode, not per-PWM output,
+which means that setting any PWM frequency above 11.3 kHz will switch
+all 3 PWM outputs to a 22.5 kHz frequency. Conversely, setting any PWM
+frequency below 11.3 kHz will switch all 3 PWM outputs to a frequency
+between 10 and 100 Hz, which can then be tuned separately.
 See the vendor datasheets for more information. There is application note
 from National (AN-1260) with some additional information about the LM85.
@@ -125,17 +137,17 @@ datasheet for a complete description of the differences. Other than
 identifying the chip, the driver behaves no differently with regard to
 these two chips. The LM85B is recommended for new designs.
-The ADM1027 and ADT7463 chips have an optional SMBALERT output that can be
+The ADM1027, ADT7463 and ADT7468 chips have an optional SMBALERT output
-used to signal the chipset in case a limit is exceeded or the temperature
+that can be used to signal the chipset in case a limit is exceeded or the
-sensors fail. Individual sensor interrupts can be masked so they won't
+temperature sensors fail. Individual sensor interrupts can be masked so
-trigger SMBALERT. The SMBALERT output if configured replaces one of the other
+they won't trigger SMBALERT. The SMBALERT output if configured replaces one
-functions (PWM2 or IN0). This functionality is not implemented in current
+of the other functions (PWM2 or IN0). This functionality is not implemented
-driver.
+in current driver.
-The ADT7463 also has an optional THERM output/input which can be connected
+The ADT7463 and ADT7468 also have an optional THERM output/input which can
-to the processor PROC_HOT output. If available, the autofan control
+be connected to the processor PROC_HOT output. If available, the autofan
-dynamic Tmin feature can be enabled to keep the system temperature within
+control dynamic Tmin feature can be enabled to keep the system temperature
-spec (just?!) with the least possible fan noise.
+within spec (just?!) with the least possible fan noise.
 Configuration Notes
 -------------------
@@ -201,8 +213,8 @@ the temperatures to compensate for systemic errors in the
 measurements. These features are not currently supported by the lm85
 driver.
-In addition to the ADM1027 features, the ADT7463 also has Tmin control
+In addition to the ADM1027 features, the ADT7463 and ADT7468 also have
-and THERM asserted counts. Automatic Tmin control acts to adjust the
+Tmin control and THERM asserted counts. Automatic Tmin control acts to
-Tmin value to maintain the measured temperature sensor at a specified
+adjust the Tmin value to maintain the measured temperature sensor at a
-temperature. There isn't much documentation on this feature in the
+specified temperature. There isn't much documentation on this feature in
-ADT7463 data sheet. This is not supported by current driver.
+the ADT7463 data sheet. This is not supported by current driver.
diff --git a/Documentation/hwmon/lm90 b/Documentation/hwmon/lm90
index 6a03dd4bcc94..fa475c0a48a3 100644
--- a/Documentation/hwmon/lm90
+++ b/Documentation/hwmon/lm90
@@ -63,8 +63,8 @@ Supported chips:
    Datasheet: Publicly available at the Maxim website
               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/2578
  * Maxim MAX6659
-    Prefix: 'max6657'
+    Prefix: 'max6659'
-    Addresses scanned: I2C 0x4c, 0x4d (unsupported 0x4e)
+    Addresses scanned: I2C 0x4c, 0x4d, 0x4e
    Datasheet: Publicly available at the Maxim website
               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/2578
  * Maxim MAX6680
@@ -84,6 +84,21 @@ Supported chips:
    Addresses scanned: I2C 0x4c
    Datasheet: Publicly available at the Maxim website
               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3500
+  * Maxim MAX6695
+    Prefix: 'max6695'
+    Addresses scanned: I2C 0x18
+    Datasheet: Publicly available at the Maxim website
+               http://www.maxim-ic.com/datasheet/index.mvp/id/4199
+  * Maxim MAX6696
+    Prefix: 'max6695'
+    Addresses scanned: I2C 0x18, 0x19, 0x1a, 0x29, 0x2a, 0x2b,
+                           0x4c, 0x4d and 0x4e
+    Datasheet: Publicly available at the Maxim website
+               http://www.maxim-ic.com/datasheet/index.mvp/id/4199
+  * Winbond/Nuvoton W83L771W/G
+    Prefix: 'w83l771'
+    Addresses scanned: I2C 0x4c
+    Datasheet: No longer available
  * Winbond/Nuvoton W83L771AWG/ASG
    Prefix: 'w83l771'
    Addresses scanned: I2C 0x4c
@@ -101,10 +116,11 @@ well as the temperature of up to one external diode. It is compatible
 with many other devices, many of which are supported by this driver.
 Note that there is no easy way to differentiate between the MAX6657,
-MAX6658 and MAX6659 variants. The extra address and features of the
+MAX6658 and MAX6659 variants. The extra features of the MAX6659 are only
-MAX6659 are not supported by this driver. The MAX6680 and MAX6681 only
+supported by this driver if the chip is located at address 0x4d or 0x4e,
-differ in their pinout, therefore they obviously can't (and don't need to)
+or if the chip type is explicitly selected as max6659.
-be distinguished.
+The MAX6680 and MAX6681 only differ in their pinout, therefore they obviously
+can't (and don't need to) be distinguished.
 The specificity of this family of chipsets over the ADM1021/LM84
 family is that it features critical limits with hysteresis, and an
@@ -151,11 +167,21 @@ MAX6680 and MAX6681:
  * Selectable address
  * Remote sensor type selection
+MAX6695 and MAX6696:
+  * Better local resolution
+  * Selectable address (max6696)
+  * Second critical temperature limit
+  * Two remote sensors
+W83L771W/G
+  * The G variant is lead-free, otherwise similar to the W.
+  * Filter and alert configuration register at 0xBF
+  * Moving average (depending on conversion rate)
 W83L771AWG/ASG
+  * Successor of the W83L771W/G, same features.
  * 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
diff --git a/Documentation/hwmon/ltc4261 b/Documentation/hwmon/ltc4261
new file mode 100644
index 000000000000..eba2e2c4b94d
--- /dev/null
+++ b/Documentation/hwmon/ltc4261
@@ -0,0 +1,63 @@
+Kernel driver ltc4261
+=====================
+Supported chips:
+  * Linear Technology LTC4261
+    Prefix: 'ltc4261'
+    Addresses scanned: -
+    Datasheet:
+        http://cds.linear.com/docs/Datasheet/42612fb.pdf
+Author: Guenter Roeck <guenter.roeck@ericsson.com>
+Description
+-----------
+The LTC4261/LTC4261-2 negative voltage Hot Swap controllers allow a board
+to be safely inserted and removed from a live backplane.
+Usage Notes
+-----------
+This driver does not probe for LTC4261 devices, since there is no register
+which can be safely used to identify the chip. You will have to instantiate
+the devices explicitly.
+Example: the following will load the driver for an LTC4261 at address 0x10
+on I2C bus #1:
+$ modprobe ltc4261
+$ echo ltc4261 0x10 > /sys/bus/i2c/devices/i2c-1/new_device
+Sysfs entries
+-------------
+Voltage readings provided by this driver are reported as obtained from the ADC
+registers. If a set of voltage divider resistors is installed, calculate the
+real voltage by multiplying the reported value with (R1+R2)/R2, where R1 is the
+value of the divider resistor against the measured voltage and R2 is the value
+of the divider resistor against Ground.
+Current reading provided by this driver is reported as obtained from the ADC
+Current Sense register. The reported value assumes that a 1 mOhm sense resistor
+is installed. If a different sense resistor is installed, calculate the real
+current by dividing the reported value by the sense resistor value in mOhm.
+The chip has two voltage sensors, but only one set of voltage alarm status bits.
+In many many designs, those alarms are associated with the ADIN2 sensor, due to
+the proximity of the ADIN2 pin to the OV pin. ADIN2 is, however, not available
+on all chip variants. To ensure that the alarm condition is reported to the user,
+report it with both voltage sensors.
+in1_input               ADIN2 voltage (mV)
+in1_min_alarm           ADIN/ADIN2 Undervoltage alarm
+in1_max_alarm           ADIN/ADIN2 Overvoltage alarm
+in2_input               ADIN voltage (mV)
+in2_min_alarm           ADIN/ADIN2 Undervoltage alarm
+in2_max_alarm           ADIN/ADIN2 Overvoltage alarm
+curr1_input             SENSE current (mA)
+curr1_alarm             SENSE overcurrent alarm
diff --git a/Documentation/hwmon/pcf8591 b/Documentation/hwmon/pcf8591
index e76a7892f68e..ac020b3bb7b3 100644
--- a/Documentation/hwmon/pcf8591
+++ b/Documentation/hwmon/pcf8591
@@ -4,7 +4,7 @@ Kernel driver pcf8591
 Supported chips:
  * Philips/NXP PCF8591
    Prefix: 'pcf8591'
-    Addresses scanned: I2C 0x48 - 0x4f
+    Addresses scanned: none
    Datasheet: Publicly available at the NXP website
               http://www.nxp.com/pip/PCF8591_6.html
@@ -58,18 +58,16 @@ Module parameters
 Accessing PCF8591 via /sys interface
 -------------------------------------
-! Be careful !
+The PCF8591 is plainly impossible to detect! Thus the driver won't even
-The PCF8591 is plainly impossible to detect! Stupid chip.
+try. You have to explicitly instantiate the device at the relevant
-So every chip with address in the interval [0x48..0x4f] is
+address (in the interval [0x48..0x4f]) either through platform data, or
-detected as PCF8591. If you have other chips in this address
+using the sysfs interface. See Documentation/i2c/instantiating-devices
-range, the workaround is to load this module after the one
+for details.
-for your others chips.
-On detection (i.e. insmod, modprobe et al.), directories are being
+Directories are being created for each instantiated PCF8591:
-created for each detected PCF8591:
 /sys/bus/i2c/devices/<0>-<1>/
-where <0> is the bus the chip was detected on (e. g. i2c-0)
+where <0> is the bus the chip is connected to (e. g. i2c-0)
 and <1> the chip address ([48..4f])
 Inside these directories, there are such files:
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index 48ceabedf55d..645699010551 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -309,6 +309,20 @@ temp[1-*]_crit_hyst
                from the critical value.
                RW
+temp[1-*]_emergency
+                Temperature emergency max value, for chips supporting more than
+                two upper temperature limits. Must be equal or greater than
+                corresponding temp_crit values.
+                Unit: millidegree Celsius
+                RW
+temp[1-*]_emergency_hyst
+                Temperature hysteresis value for emergency limit.
+                Unit: millidegree Celsius
+                Must be reported as an absolute temperature, NOT a delta
+                from the emergency value.
+                RW
 temp[1-*]_lcrit Temperature critical min value, typically lower than
                corresponding temp_min values.
                Unit: millidegree Celsius
@@ -505,6 +519,7 @@ fan[1-*]_max_alarm
 temp[1-*]_min_alarm
 temp[1-*]_max_alarm
 temp[1-*]_crit_alarm
+temp[1-*]_emergency_alarm
                Limit alarm
                0: no alarm
                1: alarm
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index e307914a3eda..93fe76e56522 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -15,10 +15,14 @@ Supported adapters:
  * Intel 82801I (ICH9)
  * Intel EP80579 (Tolapai)
  * Intel 82801JI (ICH10)
-  * Intel 3400/5 Series (PCH)
+  * Intel 5/3400 Series (PCH)
  * Intel Cougar Point (PCH)
+  * Intel Patsburg (PCH)
   Datasheets: Publicly available at the Intel website
+On Intel Patsburg and later chipsets, both the normal host SMBus controller
+and the additional 'Integrated Device Function' controllers are supported.
 Authors: 
        Mark Studebaker <mdsxyz123@yahoo.com>
        Jean Delvare <khali@linux-fr.org>
diff --git a/Documentation/input/ntrig.txt b/Documentation/input/ntrig.txt
new file mode 100644
index 000000000000..be1fd981f73f
--- /dev/null
+++ b/Documentation/input/ntrig.txt
@@ -0,0 +1,126 @@
+N-Trig touchscreen Driver
+-------------------------
+        Copyright (c) 2008-2010 Rafi Rubin <rafi@seas.upenn.edu>
+        Copyright (c) 2009-2010 Stephane Chatty
+This driver provides support for N-Trig pen and multi-touch sensors.  Single
+and multi-touch events are translated to the appropriate protocols for
+the hid and input systems.  Pen events are sufficiently hid compliant and
+are left to the hid core.  The driver also provides additional filtering
+and utility functions accessible with sysfs and module parameters.
+This driver has been reported to work properly with multiple N-Trig devices
+attached.
+Parameters
+----------
+Note: values set at load time are global and will apply to all applicable
+devices.  Adjusting parameters with sysfs will override the load time values,
+but only for that one device.
+The following parameters are used to configure filters to reduce noise:
+activate_slack          number of fingers to ignore before processing events
+activation_height       size threshold to activate immediately
+activation_width
+min_height              size threshold bellow which fingers are ignored
+min_width               both to decide activation and during activity
+deactivate_slack        the number of "no contact" frames to ignore before
+                        propagating the end of activity events
+When the last finger is removed from the device, it sends a number of empty
+frames.  By holding off on deactivation for a few frames we can tolerate false
+erroneous disconnects, where the sensor may mistakenly not detect a finger that
+is still present.  Thus deactivate_slack addresses problems where a users might
+see breaks in lines during drawing, or drop an object during a long drag.
+Additional sysfs items
+----------------------
+These nodes just provide easy access to the ranges reported by the device.
+sensor_logical_height   the range for positions reported during activity
+sensor_logical_width
+sensor_physical_height  internal ranges not used for normal events but
+sensor_physical_width   useful for tuning
+All N-Trig devices with product id of 1 report events in the ranges of
+X: 0-9600
+Y: 0-7200
+However not all of these devices have the same physical dimensions.  Most
+seem to be 12" sensors (Dell Latitude XT and XT2 and the HP TX2), and
+at least one model (Dell Studio 17) has a 17" sensor.  The ratio of physical
+to logical sizes is used to adjust the size based filter parameters.
+Filtering
+---------
+With the release of the early multi-touch firmwares it became increasingly
+obvious that these sensors were prone to erroneous events.  Users reported
+seeing both inappropriately dropped contact and ghosts, contacts reported
+where no finger was actually touching the screen.
+Deactivation slack helps prevent dropped contact for single touch use, but does
+not address the problem of dropping one of more contacts while other contacts
+are still active.  Drops in the multi-touch context require additional
+processing and should be handled in tandem with tacking.
+As observed ghost contacts are similar to actual use of the sensor, but they
+seem to have different profiles.  Ghost activity typically shows up as small
+short lived touches.  As such, I assume that the longer the continuous stream
+of events the more likely those events are from a real contact, and that the
+larger the size of each contact the more likely it is real.  Balancing the
+goals of preventing ghosts and accepting real events quickly (to minimize
+user observable latency), the filter accumulates confidence for incoming
+events until it hits thresholds and begins propagating.  In the interest in
+minimizing stored state as well as the cost of operations to make a decision,
+I've kept that decision simple.
+Time is measured in terms of the number of fingers reported, not frames since
+the probability of multiple simultaneous ghosts is expected to drop off
+dramatically with increasing numbers.  Rather than accumulate weight as a
+function of size, I just use it as a binary threshold.  A sufficiently large
+contact immediately overrides the waiting period and leads to activation.
+Setting the activation size thresholds to large values will result in deciding
+primarily on activation slack.  If you see longer lived ghosts, turning up the
+activation slack while reducing the size thresholds may suffice to eliminate
+the ghosts while keeping the screen quite responsive to firm taps.
+Contacts continue to be filtered with min_height and min_width even after
+the initial activation filter is satisfied.  The intent is to provide
+a mechanism for filtering out ghosts in the form of an extra finger while
+you actually are using the screen.  In practice this sort of ghost has
+been far less problematic or relatively rare and I've left the defaults
+set to 0 for both parameters, effectively turning off that filter.
+I don't know what the optimal values are for these filters.  If the defaults
+don't work for you, please play with the parameters.  If you do find other
+values more comfortable, I would appreciate feedback.
+The calibration of these devices does drift over time.  If ghosts or contact
+dropping worsen and interfere with the normal usage of your device, try
+recalibrating it.
+Calibration
+-----------
+The N-Trig windows tools provide calibration and testing routines.  Also an
+unofficial unsupported set of user space tools including a calibrator is
+available at:
+http://code.launchpad.net/~rafi-seas/+junk/ntrig_calib
+Tracking
+--------
+As of yet, all tested N-Trig firmwares do not track fingers.  When multiple
+contacts are active they seem to be sorted primarily by Y position.
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 33223ff121d8..63ffd78824d8 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -259,7 +259,7 @@ Code  Seq#(hex)	Include File		Comments
 't'     00-7F   linux/if_ppp.h
 't'     80-8F   linux/isdn_ppp.h
 't'     90      linux/toshiba.h
-'u'     00-1F   linux/smb_fs.h
+'u'     00-1F   linux/smb_fs.h          gone
 'v'     all     linux/videodev.h        conflict!
 'v'     00-1F   linux/ext2_fs.h         conflict!
 'v'     00-1F   linux/fs.h              conflict!
@@ -278,7 +278,6 @@ Code  Seq#(hex)	Include File		Comments
                                        <mailto:oe@port.de>
 'z'     10-4F   drivers/s390/crypto/zcrypt_api.h        conflict!
 0x80    00-1F   linux/fb.h
-0x81    00-1F   linux/videotext.h
 0x88    00-3F   media/ovcamchip.h
 0x89    00-06   arch/x86/include/asm/sockios.h
 0x89    0B-DF   linux/sockios.h
diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt
index b472e4e0ba67..2fe93ca7c77c 100644
--- a/Documentation/kbuild/kconfig-language.txt
+++ b/Documentation/kbuild/kconfig-language.txt
@@ -322,7 +322,8 @@ mainmenu:
        "mainmenu" <prompt>
 This sets the config program's title bar if the config program chooses
-to use it.
+to use it. It should be placed at the top of the configuration, before any
+other statement.
 Kconfig hints
diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index c787ae512120..0ef00bd6e54d 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -776,6 +776,13 @@ This will delete the directory debian, including all subdirectories.
 Kbuild will assume the directories to be in the same relative path as the
 Makefile if no absolute path is specified (path does not start with '/').
+To exclude certain files from make clean, use the $(no-clean-files) variable.
+This is only a special case used in the top level Kbuild file:
+        Example:
+                #Kbuild
+                no-clean-files := $(bounds-file) $(offsets-file)
 Usually kbuild descends down in subdirectories due to "obj-* := dir/",
 but in the architecture makefiles where the kbuild infrastructure
 is not sufficient this sometimes needs to be explicit.
diff --git a/Documentation/kbuild/modules.txt b/Documentation/kbuild/modules.txt
index 0767cf69c69e..3fb39e0116b4 100644
--- a/Documentation/kbuild/modules.txt
+++ b/Documentation/kbuild/modules.txt
@@ -1,215 +1,185 @@
+Building External Modules
-In this document you will find information about:
+This document describes how to build an out-of-tree kernel module.
- how to build external modules
- how to make your module use the kbuild infrastructure
- how kbuild will install a kernel
- how to install modules in a non-standard location
 === Table of Contents
        === 1 Introduction
-        === 2 How to build external modules
+        === 2 How to Build External Modules
-           --- 2.1 Building external modules
+           --- 2.1 Command Syntax
-           --- 2.2 Available targets
+           --- 2.2 Options
-           --- 2.3 Available options
+           --- 2.3 Targets
-           --- 2.4 Preparing the kernel tree for module build
+           --- 2.4 Building Separate Files
-           --- 2.5 Building separate files for a module
+        === 3. Creating a Kbuild File for an External Module
-        === 3. Example commands
+           --- 3.1 Shared Makefile
-        === 4. Creating a kbuild file for an external module
+           --- 3.2 Separate Kbuild file and Makefile
-        === 5. Include files
+           --- 3.3 Binary Blobs
-           --- 5.1 How to include files from the kernel include dir
+           --- 3.4 Building Multiple Modules
-           --- 5.2 External modules using an include/ dir
+        === 4. Include Files
-           --- 5.3 External modules using several directories
+           --- 4.1 Kernel Includes
-        === 6. Module installation
+           --- 4.2 Single Subdirectory
-           --- 6.1 INSTALL_MOD_PATH
+           --- 4.3 Several Subdirectories
-           --- 6.2 INSTALL_MOD_DIR
+        === 5. Module Installation
-        === 7. Module versioning & Module.symvers
+           --- 5.1 INSTALL_MOD_PATH
-           --- 7.1 Symbols from the kernel (vmlinux + modules)
+           --- 5.2 INSTALL_MOD_DIR
-           --- 7.2 Symbols and external modules
+        === 6. Module Versioning
-           --- 7.3 Symbols from another external module
+           --- 6.1 Symbols From the Kernel (vmlinux + modules)
-        === 8. Tips & Tricks
+           --- 6.2 Symbols and External Modules
-           --- 8.1 Testing for CONFIG_FOO_BAR
+           --- 6.3 Symbols From Another External Module
+        === 7. Tips & Tricks
+           --- 7.1 Testing for CONFIG_FOO_BAR
 === 1. Introduction
-kbuild includes functionality for building modules both
+"kbuild" is the build system used by the Linux kernel. Modules must use
-within the kernel source tree and outside the kernel source tree.
+kbuild to stay compatible with changes in the build infrastructure and
-The latter is usually referred to as external or "out-of-tree"
+to pick up the right flags to "gcc." Functionality for building modules
-modules and is used both during development and for modules that
+both in-tree and out-of-tree is provided. The method for building
-are not planned to be included in the kernel tree.
+either is similar, and all modules are initially developed and built
+out-of-tree.
-What is covered within this file is mainly information to authors
+Covered in this document is information aimed at developers interested
-of modules. The author of an external module should supply
+in building out-of-tree (or "external") modules. The author of an
-a makefile that hides most of the complexity, so one only has to type
+external module should supply a makefile that hides most of the
-'make' to build the module. A complete example will be presented in
+complexity, so one only has to type "make" to build the module. This is
-chapter 4, "Creating a kbuild file for an external module".
+easily accomplished, and a complete example will be presented in
+section 3.
-=== 2. How to build external modules
+=== 2. How to Build External Modules
-kbuild offers functionality to build external modules, with the
+To build external modules, you must have a prebuilt kernel available
-prerequisite that there is a pre-built kernel available with full source.
+that contains the configuration and header files used in the build.
-A subset of the targets available when building the kernel is available
+Also, the kernel must have been built with modules enabled. If you are
-when building an external module.
+using a distribution kernel, there will be a package for the kernel you
+are running provided by your distribution.
--- 2.1 Building external modules
+An alternative is to use the "make" target "modules_prepare." This will
+make sure the kernel contains the information required. The target
+exists solely as a simple way to prepare a kernel source tree for
+building external modules.
-        Use the following command to build an external module:
+NOTE: "modules_prepare" will not build Module.symvers even if
+CONFIG_MODVERSIONS is set; therefore, a full kernel build needs to be
+executed to make module versioning work.
-                make -C <path-to-kernel> M=`pwd`
+--- 2.1 Command Syntax
-        For the running kernel use:
+        The command to build an external module is:
-                make -C /lib/modules/`uname -r`/build M=`pwd`
+                $ make -C <path_to_kernel_src> M=$PWD
-        For the above command to succeed, the kernel must have been
+        The kbuild system knows that an external module is being built
-        built with modules enabled.
+        due to the "M=<dir>" option given in the command.
-        To install the modules that were just built:
+        To build against the running kernel use:
-                make -C <path-to-kernel> M=`pwd` modules_install
+                $ make -C /lib/modules/`uname -r`/build M=$PWD
-        More complex examples will be shown later, the above should
+        Then to install the module(s) just built, add the target
-        be enough to get you started.
+        "modules_install" to the command:
--- 2.2 Available targets
+                $ make -C /lib/modules/`uname -r`/build M=$PWD modules_install
-        $KDIR refers to the path to the kernel source top-level directory
+--- 2.2 Options
-        make -C $KDIR M=`pwd`
+        ($KDIR refers to the path of the kernel source directory.)
-                Will build the module(s) located in current directory.
-                All output files will be located in the same directory
-                as the module source.
-                No attempts are made to update the kernel source, and it is
-                a precondition that a successful make has been executed
-                for the kernel.
-        make -C $KDIR M=`pwd` modules
+        make -C $KDIR M=$PWD
-                The modules target is implied when no target is given.
-                Same functionality as if no target was specified.
-                See description above.
-        make -C $KDIR M=`pwd` modules_install
+        -C $KDIR
-                Install the external module(s).
+                The directory where the kernel source is located.
-                Installation default is in /lib/modules/<kernel-version>/extra,
+                "make" will actually change to the specified directory
-                but may be prefixed with INSTALL_MOD_PATH - see separate
+                when executing and will change back when finished.
-                chapter.
-        make -C $KDIR M=`pwd` clean
+        M=$PWD
-                Remove all generated files for the module - the kernel
+                Informs kbuild that an external module is being built.
-                source directory is not modified.
+                The value given to "M" is the absolute path of the
+                directory where the external module (kbuild file) is
+                located.
-        make -C $KDIR M=`pwd` help
+--- 2.3 Targets
-                help will list the available target when building external
-                modules.
--- 2.3 Available options:
+        When building an external module, only a subset of the "make"
+        targets are available.
-        $KDIR refers to the path to the kernel source top-level directory
+        make -C $KDIR M=$PWD [target]
-        make -C $KDIR
+        The default will build the module(s) located in the current
-                Used to specify where to find the kernel source.
+        directory, so a target does not need to be specified. All
-                '$KDIR' represent the directory where the kernel source is.
+        output files will also be generated in this directory. No
-                Make will actually change directory to the specified directory
+        attempts are made to update the kernel source, and it is a
-                when executed but change back when finished.
+        precondition that a successful "make" has been executed for the
+        kernel.
-        make -C $KDIR M=`pwd`
+        modules
-                M= is used to tell kbuild that an external module is
+                The default target for external modules. It has the
-                being built.
+                same functionality as if no target was specified. See
-                The option given to M= is the directory where the external
+                description above.
-                module (kbuild file) is located.
-                When an external module is being built only a subset of the
-                usual targets are available.
-        make -C $KDIR SUBDIRS=`pwd`
+        modules_install
-                Same as M=. The SUBDIRS= syntax is kept for backwards
+                Install the external module(s). The default location is
-                compatibility.
+                /lib/modules/<kernel_release>/extra/, but a prefix may
+                be added with INSTALL_MOD_PATH (discussed in section 5).
--- 2.4 Preparing the kernel tree for module build
+        clean
+                Remove all generated files in the module directory only.
-        To make sure the kernel contains the information required to
+        help
-        build external modules the target 'modules_prepare' must be used.
+                List the available targets for external modules.
-        'modules_prepare' exists solely as a simple way to prepare
-        a kernel source tree for building external modules.
-        Note: modules_prepare will not build Module.symvers even if
-        CONFIG_MODVERSIONS is set. Therefore a full kernel build
-        needs to be executed to make module versioning work.
--- 2.5 Building separate files for a module
+--- 2.4 Building Separate Files
-        It is possible to build single files which are part of a module.
-        This works equally well for the kernel, a module and even for
-        external modules.
-        Examples (module foo.ko, consist of bar.o, baz.o):
-                make -C $KDIR M=`pwd` bar.lst
-                make -C $KDIR M=`pwd` bar.o
-                make -C $KDIR M=`pwd` foo.ko
-                make -C $KDIR M=`pwd` /
-=== 3. Example commands
-This example shows the actual commands to be executed when building
-an external module for the currently running kernel.
-In the example below, the distribution is supposed to use the
-facility to locate output files for a kernel compile in a different
-directory than the kernel source - but the examples will also work
-when the source and the output files are mixed in the same directory.
-# Kernel source
+        It is possible to build single files that are part of a module.
-/lib/modules/<kernel-version>/source -> /usr/src/linux-<version>
+        This works equally well for the kernel, a module, and even for
+        external modules.
-# Output from kernel compile
-/lib/modules/<kernel-version>/build -> /usr/src/linux-<version>-up
-Change to the directory where the kbuild file is located and execute
-the following commands to build the module:
-        cd /home/user/src/module
+        Example (The module foo.ko, consist of bar.o and baz.o):
-        make -C /usr/src/`uname -r`/source            \
+                make -C $KDIR M=$PWD bar.lst
-                O=/lib/modules/`uname-r`/build        \
+                make -C $KDIR M=$PWD baz.o
-                M=`pwd`
+                make -C $KDIR M=$PWD foo.ko
+                make -C $KDIR M=$PWD /
-Then, to install the module use the following command:
-        make -C /usr/src/`uname -r`/source            \
+=== 3. Creating a Kbuild File for an External Module
-                O=/lib/modules/`uname-r`/build        \
-                M=`pwd`                               \
-                modules_install
-If you look closely you will see that this is the same command as
+In the last section we saw the command to build a module for the
-listed before - with the directories spelled out.
+running kernel. The module is not actually built, however, because a
+build file is required. Contained in this file will be the name of
+the module(s) being built, along with the list of requisite source
+files. The file may be as simple as a single line:
-The above are rather long commands, and the following chapter
+        obj-m := <module_name>.o
-lists a few tricks to make it all easier.
+The kbuild system will build <module_name>.o from <module_name>.c,
+and, after linking, will result in the kernel module <module_name>.ko.
+The above line can be put in either a "Kbuild" file or a "Makefile."
+When the module is built from multiple sources, an additional line is
+needed listing the files:
-=== 4. Creating a kbuild file for an external module
+        <module_name>-y := <src1>.o <src2>.o ...
-kbuild is the build system for the kernel, and external modules
+NOTE: Further documentation describing the syntax used by kbuild is
-must use kbuild to stay compatible with changes in the build system
+located in Documentation/kbuild/makefiles.txt.
-and to pick up the right flags to gcc etc.
-The kbuild file used as input shall follow the syntax described
+The examples below demonstrate how to create a build file for the
-in Documentation/kbuild/makefiles.txt. This chapter will introduce a few
+module 8123.ko, which is built from the following files:
-more tricks to be used when dealing with external modules.
-In the following a Makefile will be created for a module with the
-following files:
        8123_if.c
        8123_if.h
        8123_pci.c
        8123_bin.o_shipped      <= Binary blob
--- 4.1 Shared Makefile for module and kernel
+--- 3.1 Shared Makefile
-        An external module always includes a wrapper Makefile supporting
+        An external module always includes a wrapper makefile that
-        building the module using 'make' with no arguments.
+        supports building the module using "make" with no arguments.
-        The Makefile provided will most likely include additional
+        This target is not used by kbuild; it is only for convenience.
-        functionality such as test targets etc. and this part shall
+        Additional functionality, such as test targets, can be included
-        be filtered away from kbuild since it may impact kbuild if
+        but should be filtered out from kbuild due to possible name
-        name clashes occurs.
+        clashes.
        Example 1:
                --> filename: Makefile
@@ -219,11 +189,11 @@ following files:
                8123-y := 8123_if.o 8123_pci.o 8123_bin.o
                else
-                # Normal Makefile
+                # normal makefile
+                KDIR ?= /lib/modules/`uname -r`/build
-                KERNELDIR := /lib/modules/`uname -r`/build
+                default:
-                all::
+                        $(MAKE) -C $(KDIR) M=$$PWD
-                        $(MAKE) -C $(KERNELDIR) M=`pwd` $@
                # Module specific targets
                genbin:
@@ -231,15 +201,20 @@ following files:
                endif
-        In example 1, the check for KERNELRELEASE is used to separate
+        The check for KERNELRELEASE is used to separate the two parts
-        the two parts of the Makefile. kbuild will only see the two
+        of the makefile. In the example, kbuild will only see the two
-        assignments whereas make will see everything except the two
+        assignments, whereas "make" will see everything except these
-        kbuild assignments.
+        two assignments. This is due to two passes made on the file:
+        the first pass is by the "make" instance run on the command
+        line; the second pass is by the kbuild system, which is
+        initiated by the parameterized "make" in the default target.
+--- 3.2 Separate Kbuild File and Makefile
-        In recent versions of the kernel, kbuild will look for a file named
+        In newer versions of the kernel, kbuild will first look for a
-        Kbuild and as second option look for a file named Makefile.
+        file named "Kbuild," and only if that is not found, will it
-        Utilising the Kbuild file makes us split up the Makefile in example 1
+        then look for a makefile. Utilizing a "Kbuild" file allows us
-        into two files as shown in example 2:
+        to split up the makefile from example 1 into two files:
        Example 2:
                --> filename: Kbuild
@@ -247,20 +222,21 @@ following files:
                8123-y := 8123_if.o 8123_pci.o 8123_bin.o
                --> filename: Makefile
-                KERNELDIR := /lib/modules/`uname -r`/build
+                KDIR ?= /lib/modules/`uname -r`/build
-                all::
-                        $(MAKE) -C $(KERNELDIR) M=`pwd` $@
+                default:
+                        $(MAKE) -C $(KDIR) M=$$PWD
                # Module specific targets
                genbin:
                        echo "X" > 8123_bin.o_shipped
+        The split in example 2 is questionable due to the simplicity of
+        each file; however, some external modules use makefiles
+        consisting of several hundred lines, and here it really pays
+        off to separate the kbuild part from the rest.
-        In example 2, we are down to two fairly simple files and for simple
+        The next example shows a backward compatible version.
-        files as used in this example the split is questionable. But some
-        external modules use Makefiles of several hundred lines and here it
-        really pays off to separate the kbuild part from the rest.
-        Example 3 shows a backward compatible version.
        Example 3:
                --> filename: Kbuild
@@ -269,13 +245,15 @@ following files:
                --> filename: Makefile
                ifneq ($(KERNELRELEASE),)
+                # kbuild part of makefile
                include Kbuild
                else
-                # Normal Makefile
+                # normal makefile
+                KDIR ?= /lib/modules/`uname -r`/build
-                KERNELDIR := /lib/modules/`uname -r`/build
+                default:
-                all::
+                        $(MAKE) -C $(KDIR) M=$$PWD
-                        $(MAKE) -C $(KERNELDIR) M=`pwd` $@
                # Module specific targets
                genbin:
@@ -283,260 +261,271 @@ following files:
                endif
-        The trick here is to include the Kbuild file from Makefile, so
+        Here the "Kbuild" file is included from the makefile. This
-        if an older version of kbuild picks up the Makefile, the Kbuild
+        allows an older version of kbuild, which only knows of
-        file will be included.
+        makefiles, to be used when the "make" and kbuild parts are
+        split into separate files.
--- 4.2 Binary blobs included in a module
+--- 3.3 Binary Blobs
-        Some external modules needs to include a .o as a blob. kbuild
+        Some external modules need to include an object file as a blob.
-        has support for this, but requires the blob file to be named
+        kbuild has support for this, but requires the blob file to be
-        <filename>_shipped. In our example the blob is named
+        named <filename>_shipped. When the kbuild rules kick in, a copy
-        8123_bin.o_shipped and when the kbuild rules kick in the file
+        of <filename>_shipped is created with _shipped stripped off,
-        8123_bin.o is created as a simple copy off the 8213_bin.o_shipped file
+        giving us <filename>. This shortened filename can be used in
-        with the _shipped part stripped of the filename.
+        the assignment to the module.
-        This allows the 8123_bin.o filename to be used in the assignment to
-        the module.
+        Throughout this section, 8123_bin.o_shipped has been used to
+        build the kernel module 8123.ko; it has been included as
+        8123_bin.o.
-        Example 4:
-                obj-m  := 8123.o
                8123-y := 8123_if.o 8123_pci.o 8123_bin.o
-        In example 4, there is no distinction between the ordinary .c/.h files
+        Although there is no distinction between the ordinary source
-        and the binary file. But kbuild will pick up different rules to create
+        files and the binary file, kbuild will pick up different rules
-        the .o file.
+        when creating the object file for the module.
+--- 3.4 Building Multiple Modules
+        kbuild supports building multiple modules with a single build
+        file. For example, if you wanted to build two modules, foo.ko
+        and bar.ko, the kbuild lines would be:
-=== 5. Include files
+                obj-m := foo.o bar.o
+                foo-y := <foo_srcs>
+                bar-y := <bar_srcs>
-Include files are a necessity when a .c file uses something from other .c
+        It is that simple!
-files (not strictly in the sense of C, but if good programming practice is
-used). Any module that consists of more than one .c file will have a .h file
-for one of the .c files.
- If the .h file only describes a module internal interface, then the .h file
-  shall be placed in the same directory as the .c files.
- If the .h files describe an interface used by other parts of the kernel
-  located in different directories, the .h files shall be located in
-  include/linux/ or other include/ directories as appropriate.
-One exception for this rule is larger subsystems that have their own directory
+=== 4. Include Files
-under include/ such as include/scsi. Another exception is arch-specific
-.h files which are located under include/asm-$(ARCH)/*.
-External modules have a tendency to locate include files in a separate include/
+Within the kernel, header files are kept in standard locations
-directory and therefore need to deal with this in their kbuild file.
+according to the following rule:
--- 5.1 How to include files from the kernel include dir
+        * If the header file only describes the internal interface of a
+          module, then the file is placed in the same directory as the
+          source files.
+        * If the header file describes an interface used by other parts
+          of the kernel that are located in different directories, then
+          the file is placed in include/linux/.
-        When a module needs to include a file from include/linux/, then one
+          NOTE: There are two notable exceptions to this rule: larger
-        just uses:
+          subsystems have their own directory under include/, such as
+          include/scsi; and architecture specific headers are located
+          under arch/$(ARCH)/include/.
-                #include <linux/modules.h>
+--- 4.1 Kernel Includes
-        kbuild will make sure to add options to gcc so the relevant
+        To include a header file located under include/linux/, simply
-        directories are searched.
+        use:
-        Likewise for .h files placed in the same directory as the .c file.
-                #include "8123_if.h"
+                #include <linux/module.h>
-        will do the job.
+        kbuild will add options to "gcc" so the relevant directories
+        are searched.
--- 5.2 External modules using an include/ dir
+--- 4.2 Single Subdirectory
-        External modules often locate their .h files in a separate include/
+        External modules tend to place header files in a separate
-        directory although this is not usual kernel style. When an external
+        include/ directory where their source is located, although this
-        module uses an include/ dir then kbuild needs to be told so.
+        is not the usual kernel style. To inform kbuild of the
-        The trick here is to use either EXTRA_CFLAGS (take effect for all .c
+        directory, use either ccflags-y or CFLAGS_<filename>.o.
-        files) or CFLAGS_$F.o (take effect only for a single file).
-        In our example, if we move 8123_if.h to a subdirectory named include/
+        Using the example from section 3, if we moved 8123_if.h to a
-        the resulting Kbuild file would look like:
+        subdirectory named include, the resulting kbuild file would
+        look like:
                --> filename: Kbuild
-                obj-m  := 8123.o
+                obj-m := 8123.o
-                EXTRA_CFLAGS := -Iinclude
+                ccflags-y := -Iinclude
                8123-y := 8123_if.o 8123_pci.o 8123_bin.o
-        Note that in the assignment there is no space between -I and the path.
+        Note that in the assignment there is no space between -I and
-        This is a kbuild limitation:  there must be no space present.
+        the path. This is a limitation of kbuild: there must be no
+        space present.
--- 5.3 External modules using several directories
+--- 4.3 Several Subdirectories
-        If an external module does not follow the usual kernel style, but
-        decides to spread files over several directories, then kbuild can
-        handle this too.
+        kbuild can handle files that are spread over several directories.
        Consider the following example:
-        |
+        .
-        +- src/complex_main.c
+        |__ src
-        |   +- hal/hardwareif.c
+        |   |__ complex_main.c
-        |   +- hal/include/hardwareif.h
+        |   |__ hal
-        +- include/complex.h
+        |       |__ hardwareif.c
+        |       |__ include
-        To build a single module named complex.ko, we then need the following
+        |           |__ hardwareif.h
+        |__ include
+            |__ complex.h
+        To build the module complex.ko, we then need the following
        kbuild file:
-        Kbuild:
+                --> filename: Kbuild
                obj-m := complex.o
                complex-y := src/complex_main.o
                complex-y += src/hal/hardwareif.o
-                EXTRA_CFLAGS := -I$(src)/include
+                ccflags-y := -I$(src)/include
-                EXTRA_CFLAGS += -I$(src)src/hal/include
+                ccflags-y += -I$(src)/src/hal/include
+        As you can see, kbuild knows how to handle object files located
+        in other directories. The trick is to specify the directory
+        relative to the kbuild file's location. That being said, this
+        is NOT recommended practice.
-        kbuild knows how to handle .o files located in another directory -
+        For the header files, kbuild must be explicitly told where to
-        although this is NOT recommended practice. The syntax is to specify
+        look. When kbuild executes, the current directory is always the
-        the directory relative to the directory where the Kbuild file is
+        root of the kernel tree (the argument to "-C") and therefore an
-        located.
+        absolute path is needed. $(src) provides the absolute path by
+        pointing to the directory where the currently executing kbuild
+        file is located.
-        To find the .h files, we have to explicitly tell kbuild where to look
-        for the .h files. When kbuild executes, the current directory is always
-        the root of the kernel tree (argument to -C) and therefore we have to
-        tell kbuild how to find the .h files using absolute paths.
-        $(src) will specify the absolute path to the directory where the
-        Kbuild file are located when being build as an external module.
-        Therefore -I$(src)/ is used to point out the directory of the Kbuild
-        file and any additional path are just appended.
-=== 6. Module installation
+=== 5. Module Installation
-Modules which are included in the kernel are installed in the directory:
+Modules which are included in the kernel are installed in the
+directory:
-        /lib/modules/$(KERNELRELEASE)/kernel
+        /lib/modules/$(KERNELRELEASE)/kernel/
-External modules are installed in the directory:
+And external modules are installed in:
-        /lib/modules/$(KERNELRELEASE)/extra
+        /lib/modules/$(KERNELRELEASE)/extra/
--- 6.1 INSTALL_MOD_PATH
+--- 5.1 INSTALL_MOD_PATH
-        Above are the default directories, but as always, some level of
+        Above are the default directories but as always some level of
-        customization is possible. One can prefix the path using the variable
+        customization is possible. A prefix can be added to the
-        INSTALL_MOD_PATH:
+        installation path using the variable INSTALL_MOD_PATH:
                $ make INSTALL_MOD_PATH=/frodo modules_install
-                => Install dir: /frodo/lib/modules/$(KERNELRELEASE)/kernel
+                => Install dir: /frodo/lib/modules/$(KERNELRELEASE)/kernel/
-        INSTALL_MOD_PATH may be set as an ordinary shell variable or as in the
-        example above, can be specified on the command line when calling make.
-        INSTALL_MOD_PATH has effect both when installing modules included in
-        the kernel as well as when installing external modules.
--- 6.2 INSTALL_MOD_DIR
+        INSTALL_MOD_PATH may be set as an ordinary shell variable or,
+        as shown above, can be specified on the command line when
+        calling "make." This has effect when installing both in-tree
+        and out-of-tree modules.
-        When installing external modules they are by default installed to a
+--- 5.2 INSTALL_MOD_DIR
-        directory under /lib/modules/$(KERNELRELEASE)/extra, but one may wish
-        to locate modules for a specific functionality in a separate
-        directory. For this purpose, one can use INSTALL_MOD_DIR to specify an
-        alternative name to 'extra'.
-                $ make INSTALL_MOD_DIR=gandalf -C KERNELDIR \
+        External modules are by default installed to a directory under
-                        M=`pwd` modules_install
+        /lib/modules/$(KERNELRELEASE)/extra/, but you may wish to
-                => Install dir: /lib/modules/$(KERNELRELEASE)/gandalf
+        locate modules for a specific functionality in a separate
+        directory. For this purpose, use INSTALL_MOD_DIR to specify an
+        alternative name to "extra."
+                $ make INSTALL_MOD_DIR=gandalf -C $KDIR \
+                       M=$PWD modules_install
+                => Install dir: /lib/modules/$(KERNELRELEASE)/gandalf/
-=== 7. Module versioning & Module.symvers
-Module versioning is enabled by the CONFIG_MODVERSIONS tag.
+=== 6. Module Versioning
-Module versioning is used as a simple ABI consistency check. The Module
+Module versioning is enabled by the CONFIG_MODVERSIONS tag, and is used
-versioning creates a CRC value of the full prototype for an exported symbol and
+as a simple ABI consistency check. A CRC value of the full prototype
-when a module is loaded/used then the CRC values contained in the kernel are
+for an exported symbol is created. When a module is loaded/used, the
-compared with similar values in the module. If they are not equal, then the
+CRC values contained in the kernel are compared with similar values in
-kernel refuses to load the module.
+the module; if they are not equal, the kernel refuses to load the
+module.
-Module.symvers contains a list of all exported symbols from a kernel build.
+Module.symvers contains a list of all exported symbols from a kernel
+build.
--- 7.1 Symbols from the kernel (vmlinux + modules)
+--- 6.1 Symbols From the Kernel (vmlinux + modules)
-        During a kernel build, a file named Module.symvers will be generated.
+        During a kernel build, a file named Module.symvers will be
-        Module.symvers contains all exported symbols from the kernel and
+        generated. Module.symvers contains all exported symbols from
-        compiled modules. For each symbols, the corresponding CRC value
+        the kernel and compiled modules. For each symbol, the
-        is stored too.
+        corresponding CRC value is also stored.
        The syntax of the Module.symvers file is:
-                <CRC>       <Symbol>           <module>
+                <CRC>       <Symbol>           <module>
-        Sample:
                0x2d036834  scsi_remove_host   drivers/scsi/scsi_mod
-        For a kernel build without CONFIG_MODVERSIONS enabled, the crc
+        For a kernel build without CONFIG_MODVERSIONS enabled, the CRC
-        would read: 0x00000000
+        would read 0x00000000.
        Module.symvers serves two purposes:
-        1) It lists all exported symbols both from vmlinux and all modules
+        1) It lists all exported symbols from vmlinux and all modules.
-        2) It lists the CRC if CONFIG_MODVERSIONS is enabled
+        2) It lists the CRC if CONFIG_MODVERSIONS is enabled.
--- 7.2 Symbols and external modules
+--- 6.2 Symbols and External Modules
-        When building an external module, the build system needs access to
+        When building an external module, the build system needs access
-        the symbols from the kernel to check if all external symbols are
+        to the symbols from the kernel to check if all external symbols
-        defined. This is done in the MODPOST step and to obtain all
+        are defined. This is done in the MODPOST step. modpost obtains
-        symbols, modpost reads Module.symvers from the kernel.
+        the symbols by reading Module.symvers from the kernel source
-        If a Module.symvers file is present in the directory where
+        tree. If a Module.symvers file is present in the directory
-        the external module is being built, this file will be read too.
+        where the external module is being built, this file will be
-        During the MODPOST step, a new Module.symvers file will be written
+        read too. During the MODPOST step, a new Module.symvers file
-        containing all exported symbols that were not defined in the kernel.
+        will be written containing all exported symbols that were not
+        defined in the kernel.
--- 7.3 Symbols from another external module
+--- 6.3 Symbols From Another External Module
-        Sometimes, an external module uses exported symbols from another
-        external module. Kbuild needs to have full knowledge on all symbols
+        Sometimes, an external module uses exported symbols from
-        to avoid spitting out warnings about undefined symbols.
+        another external module. kbuild needs to have full knowledge of
-        Three solutions exist to let kbuild know all symbols of more than
+        all symbols to avoid spitting out warnings about undefined
-        one external module.
+        symbols. Three solutions exist for this situation.
-        The method with a top-level kbuild file is recommended but may be
-        impractical in certain situations.
+        NOTE: The method with a top-level kbuild file is recommended
+        but may be impractical in certain situations.
-        Use a top-level Kbuild file
-                If you have two modules: 'foo' and 'bar', and 'foo' needs
+        Use a top-level kbuild file
-                symbols from 'bar', then one can use a common top-level kbuild
+                If you have two modules, foo.ko and bar.ko, where
-                file so both modules are compiled in same build.
+                foo.ko needs symbols from bar.ko, you can use a
+                common top-level kbuild file so both modules are
-                Consider following directory layout:
+                compiled in the same build. Consider the following
-                ./foo/ <= contains the foo module
+                directory layout:
-                ./bar/ <= contains the bar module
-                The top-level Kbuild file would then look like:
+                ./foo/ <= contains foo.ko
+                ./bar/ <= contains bar.ko
-                #./Kbuild: (this file may also be named Makefile)
+                The top-level kbuild file would then look like:
+                #./Kbuild (or ./Makefile):
                        obj-y := foo/ bar/
-                Executing:
+                And executing
-                        make -C $KDIR M=`pwd`
+                        $ make -C $KDIR M=$PWD
-                will then do the expected and compile both modules with full
+                will then do the expected and compile both modules with
-                knowledge on symbols from both modules.
+                full knowledge of symbols from either module.
        Use an extra Module.symvers file
-                When an external module is built, a Module.symvers file is
+                When an external module is built, a Module.symvers file
-                generated containing all exported symbols which are not
+                is generated containing all exported symbols which are
-                defined in the kernel.
+                not defined in the kernel. To get access to symbols
-                To get access to symbols from module 'bar', one can copy the
+                from bar.ko, copy the Module.symvers file from the
-                Module.symvers file from the compilation of the 'bar' module
+                compilation of bar.ko to the directory where foo.ko is
-                to the directory where the 'foo' module is built.
+                built. During the module build, kbuild will read the
-                During the module build, kbuild will read the Module.symvers
+                Module.symvers file in the directory of the external
-                file in the directory of the external module and when the
+                module, and when the build is finished, a new
-                build is finished, a new Module.symvers file is created
+                Module.symvers file is created containing the sum of
-                containing the sum of all symbols defined and not part of the
+                all symbols defined and not part of the kernel.
-                kernel.
+        Use "make" variable KBUILD_EXTRA_SYMBOLS
-        Use make variable KBUILD_EXTRA_SYMBOLS in the Makefile
+                If it is impractical to copy Module.symvers from
-                If it is impractical to copy Module.symvers from another
+                another module, you can assign a space separated list
-                module, you can assign a space separated list of files to
+                of files to KBUILD_EXTRA_SYMBOLS in your build file.
-                KBUILD_EXTRA_SYMBOLS in your Makfile. These files will be
+                These files will be loaded by modpost during the
-                loaded by modpost during the initialisation of its symbol
+                initialization of its symbol tables.
-                tables.
-=== 8. Tips & Tricks
+=== 7. Tips & Tricks
--- 8.1 Testing for CONFIG_FOO_BAR
+--- 7.1 Testing for CONFIG_FOO_BAR
-        Modules often need to check for certain CONFIG_ options to decide if
+        Modules often need to check for certain CONFIG_ options to
-        a specific feature shall be included in the module. When kbuild is used
+        decide if a specific feature is included in the module. In
-        this is done by referencing the CONFIG_ variable directly.
+        kbuild this is done by referencing the CONFIG_ variable
+        directly.
                #fs/ext2/Makefile
                obj-$(CONFIG_EXT2_FS) += ext2.o
@@ -544,9 +533,9 @@ Module.symvers contains a list of all exported symbols from a kernel build.
                ext2-y := balloc.o bitmap.o dir.o
                ext2-$(CONFIG_EXT2_FS_XATTR) += xattr.o
-        External modules have traditionally used grep to check for specific
+        External modules have traditionally used "grep" to check for
-        CONFIG_ settings directly in .config. This usage is broken.
+        specific CONFIG_ settings directly in .config. This usage is
-        As introduced before, external modules shall use kbuild when building
+        broken. As introduced before, external modules should use
-        and therefore can use the same methods as in-kernel modules when
+        kbuild for building and can therefore use the same methods as
-        testing for CONFIG_ definitions.
+        in-tree modules when testing for CONFIG_ definitions.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 8dd7248508a9..ed45e9802aa8 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -43,10 +43,11 @@ parameter is applicable:
        AVR32   AVR32 architecture is enabled.
        AX25    Appropriate AX.25 support is enabled.
        BLACKFIN Blackfin architecture is enabled.
-        DRM     Direct Rendering Management support is enabled.
        EDD     BIOS Enhanced Disk Drive Services (EDD) is enabled
        EFI     EFI Partitioning (GPT) is enabled
        EIDE    EIDE/ATAPI support is enabled.
+        DRM     Direct Rendering Management support is enabled.
+        DYNAMIC_DEBUG Build in debug messages and enable them at runtime
        FB      The frame buffer device is enabled.
        GCOV    GCOV profiling is enabled.
        HW      Appropriate hardware is enabled.
@@ -455,7 +456,7 @@ and is between 256 and 4096 characters. It is defined in the file
                        [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
                                pxa_timer,timer3,32k_counter,timer0_1
                        [AVR32] avr32
-                        [X86-32] pit,hpet,tsc,vmi-timer;
+                        [X86-32] pit,hpet,tsc;
                                scx200_hrt on Geode; cyclone on IBM x440
                        [MIPS] MIPS
                        [PARISC] cr16
@@ -570,6 +571,10 @@ and is between 256 and 4096 characters. It is defined in the file
                        Format: <port#>,<type>
                        See also Documentation/input/joystick-parport.txt
+        ddebug_query=   [KNL,DYNAMIC_DEBUG] Enable debug messages at early boot
+                        time. See Documentation/dynamic-debug-howto.txt for
+                        details.
        debug           [KNL] Enable kernel debugging (events log level).
        debug_locks_verbose=
@@ -1126,9 +1131,13 @@ and is between 256 and 4096 characters. It is defined in the file
        kvm.oos_shadow= [KVM] Disable out-of-sync shadow paging.
                        Default is 1 (enabled)
-        kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM.
+        kvm.mmu_audit=  [KVM] This is a R/W parameter which allows audit
+                        KVM MMU at runtime.
                        Default is 0 (off)
+        kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM.
+                        Default is 1 (enabled)
        kvm-amd.npt=    [KVM,AMD] Disable nested paging (virtualized MMU)
                        for all guests.
                        Default is 1 (enabled) if in 64bit or 32bit-PAE mode
@@ -1532,12 +1541,15 @@ and is between 256 and 4096 characters. It is defined in the file
                        1 to enable accounting
                        Default value is 0.
-        nfsaddrs=       [NFS]
+        nfsaddrs=       [NFS] Deprecated.  Use ip= instead.
                        See Documentation/filesystems/nfs/nfsroot.txt.
        nfsroot=        [NFS] nfs root filesystem for disk-less boxes.
                        See Documentation/filesystems/nfs/nfsroot.txt.
+        nfsrootdebug    [NFS] enable nfsroot debugging messages.
+                        See Documentation/filesystems/nfs/nfsroot.txt.
        nfs.callback_tcpport=
                        [NFS] set the TCP port on which the NFSv4 callback
                        channel should listen.
@@ -1693,6 +1705,8 @@ and is between 256 and 4096 characters. It is defined in the file
        nojitter        [IA64] Disables jitter checking for ITC timers.
+        no-kvmclock     [X86,KVM] Disable paravirtualized KVM clock driver
        nolapic         [X86-32,APIC] Do not enable or use the local APIC.
        nolapic_timer   [X86-32,APIC] Do not use the local APIC timer.
@@ -1713,7 +1727,7 @@ and is between 256 and 4096 characters. It is defined in the file
        norandmaps      Don't use address space randomization.  Equivalent to
                        echo 0 > /proc/sys/kernel/randomize_va_space
-        noreplace-paravirt      [X86-32,PV_OPS] Don't patch paravirt_ops
+        noreplace-paravirt      [X86,IA-64,PV_OPS] Don't patch paravirt_ops
        noreplace-smp   [X86-32,SMP] Don't replace SMP instructions
                        with UP alternatives
@@ -2153,9 +2167,19 @@ and is between 256 and 4096 characters. It is defined in the file
                        Reserves a hole at the top of the kernel virtual
                        address space.
+        reservelow=     [X86]
+                        Format: nn[K]
+                        Set the amount of memory to reserve for BIOS at
+                        the bottom of the address space.
        reset_devices   [KNL] Force drivers to reset the underlying device
                        during initialization.
+        resource_alloc_from_bottom
+                        Allocate new resources from the beginning of available
+                        space, not the end.  If you need to use this, please
+                        report a bug.
        resume=         [SWSUSP]
                        Specify the partition device for software suspend
@@ -2165,6 +2189,11 @@ and is between 256 and 4096 characters. It is defined in the file
                        in <PAGE_SIZE> units (needed only for swap files).
                        See  Documentation/power/swsusp-and-swap-files.txt
+        hibernate=      [HIBERNATION]
+                noresume        Don't check if there's a hibernation image
+                                present during boot.
+                nocompress      Don't compress/decompress hibernation images.
        retain_initrd   [RAM] Keep initrd memory after extraction
        rhash_entries=  [KNL,NET]
@@ -2360,6 +2389,15 @@ and is between 256 and 4096 characters. It is defined in the file
        switches=       [HW,M68k]
+        sysfs.deprecated=0|1 [KNL]
+                        Enable/disable old style sysfs layout for old udev
+                        on older distributions. When this option is enabled
+                        very new udev will not work anymore. When this option
+                        is disabled (or CONFIG_SYSFS_DEPRECATED not compiled)
+                        in older udev will not work anymore.
+                        Default depends on CONFIG_SYSFS_DEPRECATED_V2 set in
+                        the kernel configuration.
        sysrq_always_enabled
                        [KNL]
                        Ignore sysrq setting - this boot parameter will
@@ -2408,7 +2446,7 @@ and is between 256 and 4096 characters. It is defined in the file
                        topology informations if the hardware supports these.
                        The scheduler will make use of these informations and
                        e.g. base its process migration decisions on it.
-                        Default is off.
+                        Default is on.
        tp720=          [HW,PS2]
@@ -2435,6 +2473,10 @@ and is between 256 and 4096 characters. It is defined in the file
                        disables clocksource verification at runtime.
                        Used to enable high-resolution timer mode on older
                        hardware, and in virtualized environment.
+                        [x86] noirqtime: Do not use TSC to do irq accounting.
+                        Used to run time disable IRQ_TIME_ACCOUNTING on any
+                        platforms where RDTSC is slow and this accounting
+                        can add overhead.
        turbografx.map[2|3]=    [HW,JOY]
                        TurboGraFX parallel port interface
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 1762b81fcdf2..741fe66d6eca 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -542,9 +542,11 @@ Kprobes does not use mutexes or allocate memory except during
 registration and unregistration.
 Probe handlers are run with preemption disabled.  Depending on the
-architecture, handlers may also run with interrupts disabled.  In any
+architecture and optimization state, handlers may also run with
-case, your handler should not yield the CPU (e.g., by attempting to
+interrupts disabled (e.g., kretprobe handlers and optimized kprobe
-acquire a semaphore).
+handlers run without interrupt disabled on x86/x86-64).  In any case,
+your handler should not yield the CPU (e.g., by attempting to acquire
+a semaphore).
 Since a return probe is implemented by replacing the return
 address with the trampoline's address, stack backtraces and calls
diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index 5f5b64982b1a..b336266bea5e 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -320,13 +320,13 @@ struct kvm_translation {
 4.15 KVM_INTERRUPT
 Capability: basic
-Architectures: x86
+Architectures: x86, ppc
 Type: vcpu ioctl
 Parameters: struct kvm_interrupt (in)
 Returns: 0 on success, -1 on error
 Queues a hardware interrupt vector to be injected.  This is only
-useful if in-kernel local APIC is not used.
+useful if in-kernel local APIC or equivalent is not used.
 /* for KVM_INTERRUPT */
 struct kvm_interrupt {
@@ -334,8 +334,37 @@ struct kvm_interrupt {
        __u32 irq;
 };
+X86:
 Note 'irq' is an interrupt vector, not an interrupt pin or line.
+PPC:
+Queues an external interrupt to be injected. This ioctl is overleaded
+with 3 different irq values:
+a) KVM_INTERRUPT_SET
+  This injects an edge type external interrupt into the guest once it's ready
+  to receive interrupts. When injected, the interrupt is done.
+b) KVM_INTERRUPT_UNSET
+  This unsets any pending interrupt.
+  Only available with KVM_CAP_PPC_UNSET_IRQ.
+c) KVM_INTERRUPT_SET_LEVEL
+  This injects a level type external interrupt into the guest context. The
+  interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET
+  is triggered.
+  Only available with KVM_CAP_PPC_IRQ_LEVEL.
+Note that any value for 'irq' other than the ones stated above is invalid
+and incurs unexpected behavior.
 4.16 KVM_DEBUG_GUEST
 Capability: basic
@@ -1013,8 +1042,9 @@ number is just right, the 'nent' field is adjusted to the number of valid
 entries in the 'entries' array, which is then filled.
 The entries returned are the host cpuid as returned by the cpuid instruction,
-with unknown or unsupported features masked out.  The fields in each entry
+with unknown or unsupported features masked out.  Some features (for example,
-are defined as follows:
+x2apic), may not be present in the host cpu, but are exposed by kvm if it can
+emulate them efficiently. The fields in each entry are defined as follows:
  function: the eax value used to obtain the entry
  index: the ecx value used to obtain the entry (for entries that are
@@ -1032,6 +1062,29 @@ are defined as follows:
   eax, ebx, ecx, edx: the values returned by the cpuid instruction for
         this function/index combination
+4.46 KVM_PPC_GET_PVINFO
+Capability: KVM_CAP_PPC_GET_PVINFO
+Architectures: ppc
+Type: vm ioctl
+Parameters: struct kvm_ppc_pvinfo (out)
+Returns: 0 on success, !0 on error
+struct kvm_ppc_pvinfo {
+        __u32 flags;
+        __u32 hcall[4];
+        __u8  pad[108];
+};
+This ioctl fetches PV specific information that need to be passed to the guest
+using the device tree or other means from vm context.
+For now the only implemented piece of information distributed here is an array
+of 4 instructions that make up a hypercall.
+If any additional field gets added to this structure later on, a bit for that
+additional piece of information will be set in the flags bitmap.
 5. The kvm_run structure
 Application code obtains a pointer to the kvm_run structure by
diff --git a/Documentation/kvm/ppc-pv.txt b/Documentation/kvm/ppc-pv.txt
new file mode 100644
index 000000000000..a7f2244b3be9
--- /dev/null
+++ b/Documentation/kvm/ppc-pv.txt
@@ -0,0 +1,196 @@
+The PPC KVM paravirtual interface
+=================================
+The basic execution principle by which KVM on PowerPC works is to run all kernel
+space code in PR=1 which is user space. This way we trap all privileged
+instructions and can emulate them accordingly.
+Unfortunately that is also the downfall. There are quite some privileged
+instructions that needlessly return us to the hypervisor even though they
+could be handled differently.
+This is what the PPC PV interface helps with. It takes privileged instructions
+and transforms them into unprivileged ones with some help from the hypervisor.
+This cuts down virtualization costs by about 50% on some of my benchmarks.
+The code for that interface can be found in arch/powerpc/kernel/kvm*
+Querying for existence
+======================
+To find out if we're running on KVM or not, we leverage the device tree. When
+Linux is running on KVM, a node /hypervisor exists. That node contains a
+compatible property with the value "linux,kvm".
+Once you determined you're running under a PV capable KVM, you can now use
+hypercalls as described below.
+KVM hypercalls
+==============
+Inside the device tree's /hypervisor node there's a property called
+'hypercall-instructions'. This property contains at most 4 opcodes that make
+up the hypercall. To call a hypercall, just call these instructions.
+The parameters are as follows:
+        Register        IN                      OUT
+        r0              -                       volatile
+        r3              1st parameter           Return code
+        r4              2nd parameter           1st output value
+        r5              3rd parameter           2nd output value
+        r6              4th parameter           3rd output value
+        r7              5th parameter           4th output value
+        r8              6th parameter           5th output value
+        r9              7th parameter           6th output value
+        r10             8th parameter           7th output value
+        r11             hypercall number        8th output value
+        r12             -                       volatile
+Hypercall definitions are shared in generic code, so the same hypercall numbers
+apply for x86 and powerpc alike with the exception that each KVM hypercall
+also needs to be ORed with the KVM vendor code which is (42 << 16).
+Return codes can be as follows:
+        Code            Meaning
+        0               Success
+        12              Hypercall not implemented
+        <0              Error
+The magic page
+==============
+To enable communication between the hypervisor and guest there is a new shared
+page that contains parts of supervisor visible register state. The guest can
+map this shared page using the KVM hypercall KVM_HC_PPC_MAP_MAGIC_PAGE.
+With this hypercall issued the guest always gets the magic page mapped at the
+desired location in effective and physical address space. For now, we always
+map the page to -4096. This way we can access it using absolute load and store
+functions. The following instruction reads the first field of the magic page:
+        ld      rX, -4096(0)
+The interface is designed to be extensible should there be need later to add
+additional registers to the magic page. If you add fields to the magic page,
+also define a new hypercall feature to indicate that the host can give you more
+registers. Only if the host supports the additional features, make use of them.
+The magic page has the following layout as described in
+arch/powerpc/include/asm/kvm_para.h:
+struct kvm_vcpu_arch_shared {
+        __u64 scratch1;
+        __u64 scratch2;
+        __u64 scratch3;
+        __u64 critical;         /* Guest may not get interrupts if == r1 */
+        __u64 sprg0;
+        __u64 sprg1;
+        __u64 sprg2;
+        __u64 sprg3;
+        __u64 srr0;
+        __u64 srr1;
+        __u64 dar;
+        __u64 msr;
+        __u32 dsisr;
+        __u32 int_pending;      /* Tells the guest if we have an interrupt */
+};
+Additions to the page must only occur at the end. Struct fields are always 32
+or 64 bit aligned, depending on them being 32 or 64 bit wide respectively.
+Magic page features
+===================
+When mapping the magic page using the KVM hypercall KVM_HC_PPC_MAP_MAGIC_PAGE,
+a second return value is passed to the guest. This second return value contains
+a bitmap of available features inside the magic page.
+The following enhancements to the magic page are currently available:
+  KVM_MAGIC_FEAT_SR             Maps SR registers r/w in the magic page
+For enhanced features in the magic page, please check for the existence of the
+feature before using them!
+MSR bits
+========
+The MSR contains bits that require hypervisor intervention and bits that do
+not require direct hypervisor intervention because they only get interpreted
+when entering the guest or don't have any impact on the hypervisor's behavior.
+The following bits are safe to be set inside the guest:
+  MSR_EE
+  MSR_RI
+  MSR_CR
+  MSR_ME
+If any other bit changes in the MSR, please still use mtmsr(d).
+Patched instructions
+====================
+The "ld" and "std" instructions are transormed to "lwz" and "stw" instructions
+respectively on 32 bit systems with an added offset of 4 to accomodate for big
+endianness.
+The following is a list of mapping the Linux kernel performs when running as
+guest. Implementing any of those mappings is optional, as the instruction traps
+also act on the shared page. So calling privileged instructions still works as
+before.
+From                    To
+====                    ==
+mfmsr   rX              ld      rX, magic_page->msr
+mfsprg  rX, 0           ld      rX, magic_page->sprg0
+mfsprg  rX, 1           ld      rX, magic_page->sprg1
+mfsprg  rX, 2           ld      rX, magic_page->sprg2
+mfsprg  rX, 3           ld      rX, magic_page->sprg3
+mfsrr0  rX              ld      rX, magic_page->srr0
+mfsrr1  rX              ld      rX, magic_page->srr1
+mfdar   rX              ld      rX, magic_page->dar
+mfdsisr rX              lwz     rX, magic_page->dsisr
+mtmsr   rX              std     rX, magic_page->msr
+mtsprg  0, rX           std     rX, magic_page->sprg0
+mtsprg  1, rX           std     rX, magic_page->sprg1
+mtsprg  2, rX           std     rX, magic_page->sprg2
+mtsprg  3, rX           std     rX, magic_page->sprg3
+mtsrr0  rX              std     rX, magic_page->srr0
+mtsrr1  rX              std     rX, magic_page->srr1
+mtdar   rX              std     rX, magic_page->dar
+mtdsisr rX              stw     rX, magic_page->dsisr
+tlbsync                 nop
+mtmsrd  rX, 0           b       <special mtmsr section>
+mtmsr   rX              b       <special mtmsr section>
+mtmsrd  rX, 1           b       <special mtmsrd section>
+[Book3S only]
+mtsrin  rX, rY          b       <special mtsrin section>
+[BookE only]
+wrteei  [0|1]           b       <special wrteei section>
+Some instructions require more logic to determine what's going on than a load
+or store instruction can deliver. To enable patching of those, we keep some
+RAM around where we can live translate instructions to. What happens is the
+following:
+        1) copy emulation code to memory
+        2) patch that code to fit the emulated instruction
+        3) patch that code to return to the original pc + 4
+        4) patch the original instruction to branch to the new code
+That way we can inject an arbitrary amount of code as replacement for a single
+instruction. This allows us to check for pending interrupts when setting EE=1
+for example.
diff --git a/Documentation/kvm/timekeeping.txt b/Documentation/kvm/timekeeping.txt
new file mode 100644
index 000000000000..0c5033a58c9e
--- /dev/null
+++ b/Documentation/kvm/timekeeping.txt
@@ -0,0 +1,612 @@
+        Timekeeping Virtualization for X86-Based Architectures
+        Zachary Amsden <zamsden@redhat.com>
+        Copyright (c) 2010, Red Hat.  All rights reserved.
+1) Overview
+2) Timing Devices
+3) TSC Hardware
+4) Virtualization Problems
+=========================================================================
+1) Overview
+One of the most complicated parts of the X86 platform, and specifically,
+the virtualization of this platform is the plethora of timing devices available
+and the complexity of emulating those devices.  In addition, virtualization of
+time introduces a new set of challenges because it introduces a multiplexed
+division of time beyond the control of the guest CPU.
+First, we will describe the various timekeeping hardware available, then
+present some of the problems which arise and solutions available, giving
+specific recommendations for certain classes of KVM guests.
+The purpose of this document is to collect data and information relevant to
+timekeeping which may be difficult to find elsewhere, specifically,
+information relevant to KVM and hardware-based virtualization.
+=========================================================================
+2) Timing Devices
+First we discuss the basic hardware devices available.  TSC and the related
+KVM clock are special enough to warrant a full exposition and are described in
+the following section.
+2.1) i8254 - PIT
+One of the first timer devices available is the programmable interrupt timer,
+or PIT.  The PIT has a fixed frequency 1.193182 MHz base clock and three
+channels which can be programmed to deliver periodic or one-shot interrupts.
+These three channels can be configured in different modes and have individual
+counters.  Channel 1 and 2 were not available for general use in the original
+IBM PC, and historically were connected to control RAM refresh and the PC
+speaker.  Now the PIT is typically integrated as part of an emulated chipset
+and a separate physical PIT is not used.
+The PIT uses I/O ports 0x40 - 0x43.  Access to the 16-bit counters is done
+using single or multiple byte access to the I/O ports.  There are 6 modes
+available, but not all modes are available to all timers, as only timer 2
+has a connected gate input, required for modes 1 and 5.  The gate line is
+controlled by port 61h, bit 0, as illustrated in the following diagram.
+ --------------             ----------------
+|              |           |                |
+|  1.1932 MHz  |---------->| CLOCK      OUT | ---------> IRQ 0
+|    Clock     |   |       |                |
+ --------------    |    +->| GATE  TIMER 0  |
+                   |        ----------------
+                   |
+                   |        ----------------
+                   |       |                |
+                   |------>| CLOCK      OUT | ---------> 66.3 KHZ DRAM
+                   |       |                |            (aka /dev/null)
+                   |    +->| GATE  TIMER 1  |
+                   |        ----------------
+                   |
+                   |        ----------------
+                   |       |                |
+                   |------>| CLOCK      OUT | ---------> Port 61h, bit 5
+                           |                |      |
+Port 61h, bit 0 ---------->| GATE  TIMER 2  |       \_.----   ____
+                            ----------------         _|    )--|LPF|---Speaker
+                                                    / *----   \___/
+Port 61h, bit 1 -----------------------------------/
+The timer modes are now described.
+Mode 0: Single Timeout.   This is a one-shot software timeout that counts down
+ when the gate is high (always true for timers 0 and 1).  When the count
+ reaches zero, the output goes high.
+Mode 1: Triggered One-shot.  The output is intially set high.  When the gate
+ line is set high, a countdown is initiated (which does not stop if the gate is
+ lowered), during which the output is set low.  When the count reaches zero,
+ the output goes high.
+Mode 2: Rate Generator.  The output is initially set high.  When the countdown
+ reaches 1, the output goes low for one count and then returns high.  The value
+ is reloaded and the countdown automatically resumes.  If the gate line goes
+ low, the count is halted.  If the output is low when the gate is lowered, the
+ output automatically goes high (this only affects timer 2).
+Mode 3: Square Wave.   This generates a high / low square wave.  The count
+ determines the length of the pulse, which alternates between high and low
+ when zero is reached.  The count only proceeds when gate is high and is
+ automatically reloaded on reaching zero.  The count is decremented twice at
+ each clock to generate a full high / low cycle at the full periodic rate.
+ If the count is even, the clock remains high for N/2 counts and low for N/2
+ counts; if the clock is odd, the clock is high for (N+1)/2 counts and low
+ for (N-1)/2 counts.  Only even values are latched by the counter, so odd
+ values are not observed when reading.  This is the intended mode for timer 2,
+ which generates sine-like tones by low-pass filtering the square wave output.
+Mode 4: Software Strobe.  After programming this mode and loading the counter,
+ the output remains high until the counter reaches zero.  Then the output
+ goes low for 1 clock cycle and returns high.  The counter is not reloaded.
+ Counting only occurs when gate is high.
+Mode 5: Hardware Strobe.  After programming and loading the counter, the
+ output remains high.  When the gate is raised, a countdown is initiated
+ (which does not stop if the gate is lowered).  When the counter reaches zero,
+ the output goes low for 1 clock cycle and then returns high.  The counter is
+ not reloaded.
+In addition to normal binary counting, the PIT supports BCD counting.  The
+command port, 0x43 is used to set the counter and mode for each of the three
+timers.
+PIT commands, issued to port 0x43, using the following bit encoding:
+Bit 7-4: Command (See table below)
+Bit 3-1: Mode (000 = Mode 0, 101 = Mode 5, 11X = undefined)
+Bit 0  : Binary (0) / BCD (1)
+Command table:
+0000 - Latch Timer 0 count for port 0x40
+        sample and hold the count to be read in port 0x40;
+        additional commands ignored until counter is read;
+        mode bits ignored.
+0001 - Set Timer 0 LSB mode for port 0x40
+        set timer to read LSB only and force MSB to zero;
+        mode bits set timer mode
+0010 - Set Timer 0 MSB mode for port 0x40
+        set timer to read MSB only and force LSB to zero;
+        mode bits set timer mode
+0011 - Set Timer 0 16-bit mode for port 0x40
+        set timer to read / write LSB first, then MSB;
+        mode bits set timer mode
+0100 - Latch Timer 1 count for port 0x41 - as described above
+0101 - Set Timer 1 LSB mode for port 0x41 - as described above
+0110 - Set Timer 1 MSB mode for port 0x41 - as described above
+0111 - Set Timer 1 16-bit mode for port 0x41 - as described above
+1000 - Latch Timer 2 count for port 0x42 - as described above
+1001 - Set Timer 2 LSB mode for port 0x42 - as described above
+1010 - Set Timer 2 MSB mode for port 0x42 - as described above
+1011 - Set Timer 2 16-bit mode for port 0x42 as described above
+1101 - General counter latch
+        Latch combination of counters into corresponding ports
+        Bit 3 = Counter 2
+        Bit 2 = Counter 1
+        Bit 1 = Counter 0
+        Bit 0 = Unused
+1110 - Latch timer status
+        Latch combination of counter mode into corresponding ports
+        Bit 3 = Counter 2
+        Bit 2 = Counter 1
+        Bit 1 = Counter 0
+        The output of ports 0x40-0x42 following this command will be:
+        Bit 7 = Output pin
+        Bit 6 = Count loaded (0 if timer has expired)
+        Bit 5-4 = Read / Write mode
+            01 = MSB only
+            10 = LSB only
+            11 = LSB / MSB (16-bit)
+        Bit 3-1 = Mode
+        Bit 0 = Binary (0) / BCD mode (1)
+2.2) RTC
+The second device which was available in the original PC was the MC146818 real
+time clock.  The original device is now obsolete, and usually emulated by the
+system chipset, sometimes by an HPET and some frankenstein IRQ routing.
+The RTC is accessed through CMOS variables, which uses an index register to
+control which bytes are read.  Since there is only one index register, read
+of the CMOS and read of the RTC require lock protection (in addition, it is
+dangerous to allow userspace utilities such as hwclock to have direct RTC
+access, as they could corrupt kernel reads and writes of CMOS memory).
+The RTC generates an interrupt which is usually routed to IRQ 8.  The interrupt
+can function as a periodic timer, an additional once a day alarm, and can issue
+interrupts after an update of the CMOS registers by the MC146818 is complete.
+The type of interrupt is signalled in the RTC status registers.
+The RTC will update the current time fields by battery power even while the
+system is off.  The current time fields should not be read while an update is
+in progress, as indicated in the status register.
+The clock uses a 32.768kHz crystal, so bits 6-4 of register A should be
+programmed to a 32kHz divider if the RTC is to count seconds.
+This is the RAM map originally used for the RTC/CMOS:
+Location    Size    Description
+------------------------------------------
+00h         byte    Current second (BCD)
+01h         byte    Seconds alarm (BCD)
+02h         byte    Current minute (BCD)
+03h         byte    Minutes alarm (BCD)
+04h         byte    Current hour (BCD)
+05h         byte    Hours alarm (BCD)
+06h         byte    Current day of week (BCD)
+07h         byte    Current day of month (BCD)
+08h         byte    Current month (BCD)
+09h         byte    Current year (BCD)
+0Ah         byte    Register A
+                       bit 7   = Update in progress
+                       bit 6-4 = Divider for clock
+                                  000 = 4.194 MHz
+                                  001 = 1.049 MHz
+                                  010 = 32 kHz
+                                  10X = test modes
+                                  110 = reset / disable
+                                  111 = reset / disable
+                       bit 3-0 = Rate selection for periodic interrupt
+                                  000 = periodic timer disabled
+                                  001 = 3.90625 uS
+                                  010 = 7.8125 uS
+                                  011 = .122070 mS
+                                  100 = .244141 mS
+                                     ...
+                                 1101 = 125 mS
+                                 1110 = 250 mS
+                                 1111 = 500 mS
+0Bh         byte    Register B
+                       bit 7   = Run (0) / Halt (1)
+                       bit 6   = Periodic interrupt enable
+                       bit 5   = Alarm interrupt enable
+                       bit 4   = Update-ended interrupt enable
+                       bit 3   = Square wave interrupt enable
+                       bit 2   = BCD calendar (0) / Binary (1)
+                       bit 1   = 12-hour mode (0) / 24-hour mode (1)
+                       bit 0   = 0 (DST off) / 1 (DST enabled)
+OCh         byte    Register C (read only)
+                       bit 7   = interrupt request flag (IRQF)
+                       bit 6   = periodic interrupt flag (PF)
+                       bit 5   = alarm interrupt flag (AF)
+                       bit 4   = update interrupt flag (UF)
+                       bit 3-0 = reserved
+ODh         byte    Register D (read only)
+                       bit 7   = RTC has power
+                       bit 6-0 = reserved
+32h         byte    Current century BCD (*)
+  (*) location vendor specific and now determined from ACPI global tables
+2.3) APIC
+On Pentium and later processors, an on-board timer is available to each CPU
+as part of the Advanced Programmable Interrupt Controller.  The APIC is
+accessed through memory-mapped registers and provides interrupt service to each
+CPU, used for IPIs and local timer interrupts.
+Although in theory the APIC is a safe and stable source for local interrupts,
+in practice, many bugs and glitches have occurred due to the special nature of
+the APIC CPU-local memory-mapped hardware.  Beware that CPU errata may affect
+the use of the APIC and that workarounds may be required.  In addition, some of
+these workarounds pose unique constraints for virtualization - requiring either
+extra overhead incurred from extra reads of memory-mapped I/O or additional
+functionality that may be more computationally expensive to implement.
+Since the APIC is documented quite well in the Intel and AMD manuals, we will
+avoid repetition of the detail here.  It should be pointed out that the APIC
+timer is programmed through the LVT (local vector timer) register, is capable
+of one-shot or periodic operation, and is based on the bus clock divided down
+by the programmable divider register.
+2.4) HPET
+HPET is quite complex, and was originally intended to replace the PIT / RTC
+support of the X86 PC.  It remains to be seen whether that will be the case, as
+the de facto standard of PC hardware is to emulate these older devices.  Some
+systems designated as legacy free may support only the HPET as a hardware timer
+device.
+The HPET spec is rather loose and vague, requiring at least 3 hardware timers,
+but allowing implementation freedom to support many more.  It also imposes no
+fixed rate on the timer frequency, but does impose some extremal values on
+frequency, error and slew.
+In general, the HPET is recommended as a high precision (compared to PIT /RTC)
+time source which is independent of local variation (as there is only one HPET
+in any given system).  The HPET is also memory-mapped, and its presence is
+indicated through ACPI tables by the BIOS.
+Detailed specification of the HPET is beyond the current scope of this
+document, as it is also very well documented elsewhere.
+2.5) Offboard Timers
+Several cards, both proprietary (watchdog boards) and commonplace (e1000) have
+timing chips built into the cards which may have registers which are accessible
+to kernel or user drivers.  To the author's knowledge, using these to generate
+a clocksource for a Linux or other kernel has not yet been attempted and is in
+general frowned upon as not playing by the agreed rules of the game.  Such a
+timer device would require additional support to be virtualized properly and is
+not considered important at this time as no known operating system does this.
+=========================================================================
+3) TSC Hardware
+The TSC or time stamp counter is relatively simple in theory; it counts
+instruction cycles issued by the processor, which can be used as a measure of
+time.  In practice, due to a number of problems, it is the most complicated
+timekeeping device to use.
+The TSC is represented internally as a 64-bit MSR which can be read with the
+RDMSR, RDTSC, or RDTSCP (when available) instructions.  In the past, hardware
+limitations made it possible to write the TSC, but generally on old hardware it
+was only possible to write the low 32-bits of the 64-bit counter, and the upper
+32-bits of the counter were cleared.  Now, however, on Intel processors family
+0Fh, for models 3, 4 and 6, and family 06h, models e and f, this restriction
+has been lifted and all 64-bits are writable.  On AMD systems, the ability to
+write the TSC MSR is not an architectural guarantee.
+The TSC is accessible from CPL-0 and conditionally, for CPL > 0 software by
+means of the CR4.TSD bit, which when enabled, disables CPL > 0 TSC access.
+Some vendors have implemented an additional instruction, RDTSCP, which returns
+atomically not just the TSC, but an indicator which corresponds to the
+processor number.  This can be used to index into an array of TSC variables to
+determine offset information in SMP systems where TSCs are not synchronized.
+The presence of this instruction must be determined by consulting CPUID feature
+bits.
+Both VMX and SVM provide extension fields in the virtualization hardware which
+allows the guest visible TSC to be offset by a constant.  Newer implementations
+promise to allow the TSC to additionally be scaled, but this hardware is not
+yet widely available.
+3.1) TSC synchronization
+The TSC is a CPU-local clock in most implementations.  This means, on SMP
+platforms, the TSCs of different CPUs may start at different times depending
+on when the CPUs are powered on.  Generally, CPUs on the same die will share
+the same clock, however, this is not always the case.
+The BIOS may attempt to resynchronize the TSCs during the poweron process and
+the operating system or other system software may attempt to do this as well.
+Several hardware limitations make the problem worse - if it is not possible to
+write the full 64-bits of the TSC, it may be impossible to match the TSC in
+newly arriving CPUs to that of the rest of the system, resulting in
+unsynchronized TSCs.  This may be done by BIOS or system software, but in
+practice, getting a perfectly synchronized TSC will not be possible unless all
+values are read from the same clock, which generally only is possible on single
+socket systems or those with special hardware support.
+3.2) TSC and CPU hotplug
+As touched on already, CPUs which arrive later than the boot time of the system
+may not have a TSC value that is synchronized with the rest of the system.
+Either system software, BIOS, or SMM code may actually try to establish the TSC
+to a value matching the rest of the system, but a perfect match is usually not
+a guarantee.  This can have the effect of bringing a system from a state where
+TSC is synchronized back to a state where TSC synchronization flaws, however
+small, may be exposed to the OS and any virtualization environment.
+3.3) TSC and multi-socket / NUMA
+Multi-socket systems, especially large multi-socket systems are likely to have
+individual clocksources rather than a single, universally distributed clock.
+Since these clocks are driven by different crystals, they will not have
+perfectly matched frequency, and temperature and electrical variations will
+cause the CPU clocks, and thus the TSCs to drift over time.  Depending on the
+exact clock and bus design, the drift may or may not be fixed in absolute
+error, and may accumulate over time.
+In addition, very large systems may deliberately slew the clocks of individual
+cores.  This technique, known as spread-spectrum clocking, reduces EMI at the
+clock frequency and harmonics of it, which may be required to pass FCC
+standards for telecommunications and computer equipment.
+It is recommended not to trust the TSCs to remain synchronized on NUMA or
+multiple socket systems for these reasons.
+3.4) TSC and C-states
+C-states, or idling states of the processor, especially C1E and deeper sleep
+states may be problematic for TSC as well.  The TSC may stop advancing in such
+a state, resulting in a TSC which is behind that of other CPUs when execution
+is resumed.  Such CPUs must be detected and flagged by the operating system
+based on CPU and chipset identifications.
+The TSC in such a case may be corrected by catching it up to a known external
+clocksource.
+3.5) TSC frequency change / P-states
+To make things slightly more interesting, some CPUs may change frequency.  They
+may or may not run the TSC at the same rate, and because the frequency change
+may be staggered or slewed, at some points in time, the TSC rate may not be
+known other than falling within a range of values.  In this case, the TSC will
+not be a stable time source, and must be calibrated against a known, stable,
+external clock to be a usable source of time.
+Whether the TSC runs at a constant rate or scales with the P-state is model
+dependent and must be determined by inspecting CPUID, chipset or vendor
+specific MSR fields.
+In addition, some vendors have known bugs where the P-state is actually
+compensated for properly during normal operation, but when the processor is
+inactive, the P-state may be raised temporarily to service cache misses from
+other processors.  In such cases, the TSC on halted CPUs could advance faster
+than that of non-halted processors.  AMD Turion processors are known to have
+this problem.
+3.6) TSC and STPCLK / T-states
+External signals given to the processor may also have the effect of stopping
+the TSC.  This is typically done for thermal emergency power control to prevent
+an overheating condition, and typically, there is no way to detect that this
+condition has happened.
+3.7) TSC virtualization - VMX
+VMX provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP
+instructions, which is enough for full virtualization of TSC in any manner.  In
+addition, VMX allows passing through the host TSC plus an additional TSC_OFFSET
+field specified in the VMCS.  Special instructions must be used to read and
+write the VMCS field.
+3.8) TSC virtualization - SVM
+SVM provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP
+instructions, which is enough for full virtualization of TSC in any manner.  In
+addition, SVM allows passing through the host TSC plus an additional offset
+field specified in the SVM control block.
+3.9) TSC feature bits in Linux
+In summary, there is no way to guarantee the TSC remains in perfect
+synchronization unless it is explicitly guaranteed by the architecture.  Even
+if so, the TSCs in multi-sockets or NUMA systems may still run independently
+despite being locally consistent.
+The following feature bits are used by Linux to signal various TSC attributes,
+but they can only be taken to be meaningful for UP or single node systems.
+X86_FEATURE_TSC                 : The TSC is available in hardware
+X86_FEATURE_RDTSCP              : The RDTSCP instruction is available
+X86_FEATURE_CONSTANT_TSC        : The TSC rate is unchanged with P-states
+X86_FEATURE_NONSTOP_TSC         : The TSC does not stop in C-states
+X86_FEATURE_TSC_RELIABLE        : TSC sync checks are skipped (VMware)
+4) Virtualization Problems
+Timekeeping is especially problematic for virtualization because a number of
+challenges arise.  The most obvious problem is that time is now shared between
+the host and, potentially, a number of virtual machines.  Thus the virtual
+operating system does not run with 100% usage of the CPU, despite the fact that
+it may very well make that assumption.  It may expect it to remain true to very
+exacting bounds when interrupt sources are disabled, but in reality only its
+virtual interrupt sources are disabled, and the machine may still be preempted
+at any time.  This causes problems as the passage of real time, the injection
+of machine interrupts and the associated clock sources are no longer completely
+synchronized with real time.
+This same problem can occur on native harware to a degree, as SMM mode may
+steal cycles from the naturally on X86 systems when SMM mode is used by the
+BIOS, but not in such an extreme fashion.  However, the fact that SMM mode may
+cause similar problems to virtualization makes it a good justification for
+solving many of these problems on bare metal.
+4.1) Interrupt clocking
+One of the most immediate problems that occurs with legacy operating systems
+is that the system timekeeping routines are often designed to keep track of
+time by counting periodic interrupts.  These interrupts may come from the PIT
+or the RTC, but the problem is the same: the host virtualization engine may not
+be able to deliver the proper number of interrupts per second, and so guest
+time may fall behind.  This is especially problematic if a high interrupt rate
+is selected, such as 1000 HZ, which is unfortunately the default for many Linux
+guests.
+There are three approaches to solving this problem; first, it may be possible
+to simply ignore it.  Guests which have a separate time source for tracking
+'wall clock' or 'real time' may not need any adjustment of their interrupts to
+maintain proper time.  If this is not sufficient, it may be necessary to inject
+additional interrupts into the guest in order to increase the effective
+interrupt rate.  This approach leads to complications in extreme conditions,
+where host load or guest lag is too much to compensate for, and thus another
+solution to the problem has risen: the guest may need to become aware of lost
+ticks and compensate for them internally.  Although promising in theory, the
+implementation of this policy in Linux has been extremely error prone, and a
+number of buggy variants of lost tick compensation are distributed across
+commonly used Linux systems.
+Windows uses periodic RTC clocking as a means of keeping time internally, and
+thus requires interrupt slewing to keep proper time.  It does use a low enough
+rate (ed: is it 18.2 Hz?) however that it has not yet been a problem in
+practice.
+4.2) TSC sampling and serialization
+As the highest precision time source available, the cycle counter of the CPU
+has aroused much interest from developers.  As explained above, this timer has
+many problems unique to its nature as a local, potentially unstable and
+potentially unsynchronized source.  One issue which is not unique to the TSC,
+but is highlighted because of its very precise nature is sampling delay.  By
+definition, the counter, once read is already old.  However, it is also
+possible for the counter to be read ahead of the actual use of the result.
+This is a consequence of the superscalar execution of the instruction stream,
+which may execute instructions out of order.  Such execution is called
+non-serialized.  Forcing serialized execution is necessary for precise
+measurement with the TSC, and requires a serializing instruction, such as CPUID
+or an MSR read.
+Since CPUID may actually be virtualized by a trap and emulate mechanism, this
+serialization can pose a performance issue for hardware virtualization.  An
+accurate time stamp counter reading may therefore not always be available, and
+it may be necessary for an implementation to guard against "backwards" reads of
+the TSC as seen from other CPUs, even in an otherwise perfectly synchronized
+system.
+4.3) Timespec aliasing
+Additionally, this lack of serialization from the TSC poses another challenge
+when using results of the TSC when measured against another time source.  As
+the TSC is much higher precision, many possible values of the TSC may be read
+while another clock is still expressing the same value.
+That is, you may read (T,T+10) while external clock C maintains the same value.
+Due to non-serialized reads, you may actually end up with a range which
+fluctuates - from (T-1.. T+10).  Thus, any time calculated from a TSC, but
+calibrated against an external value may have a range of valid values.
+Re-calibrating this computation may actually cause time, as computed after the
+calibration, to go backwards, compared with time computed before the
+calibration.
+This problem is particularly pronounced with an internal time source in Linux,
+the kernel time, which is expressed in the theoretically high resolution
+timespec - but which advances in much larger granularity intervals, sometimes
+at the rate of jiffies, and possibly in catchup modes, at a much larger step.
+This aliasing requires care in the computation and recalibration of kvmclock
+and any other values derived from TSC computation (such as TSC virtualization
+itself).
+4.4) Migration
+Migration of a virtual machine raises problems for timekeeping in two ways.
+First, the migration itself may take time, during which interrupts cannot be
+delivered, and after which, the guest time may need to be caught up.  NTP may
+be able to help to some degree here, as the clock correction required is
+typically small enough to fall in the NTP-correctable window.
+An additional concern is that timers based off the TSC (or HPET, if the raw bus
+clock is exposed) may now be running at different rates, requiring compensation
+in some way in the hypervisor by virtualizing these timers.  In addition,
+migrating to a faster machine may preclude the use of a passthrough TSC, as a
+faster clock cannot be made visible to a guest without the potential of time
+advancing faster than usual.  A slower clock is less of a problem, as it can
+always be caught up to the original rate.  KVM clock avoids these problems by
+simply storing multipliers and offsets against the TSC for the guest to convert
+back into nanosecond resolution values.
+4.5) Scheduling
+Since scheduling may be based on precise timing and firing of interrupts, the
+scheduling algorithms of an operating system may be adversely affected by
+virtualization.  In theory, the effect is random and should be universally
+distributed, but in contrived as well as real scenarios (guest device access,
+causes of virtualization exits, possible context switch), this may not always
+be the case.  The effect of this has not been well studied.
+In an attempt to work around this, several implementations have provided a
+paravirtualized scheduler clock, which reveals the true amount of CPU time for
+which a virtual machine has been running.
+4.6) Watchdogs
+Watchdog timers, such as the lock detector in Linux may fire accidentally when
+running under hardware virtualization due to timer interrupts being delayed or
+misinterpretation of the passage of real time.  Usually, these warnings are
+spurious and can be ignored, but in some circumstances it may be necessary to
+disable such detection.
+4.7) Delays and precision timing
+Precise timing and delays may not be possible in a virtualized system.  This
+can happen if the system is controlling physical hardware, or issues delays to
+compensate for slower I/O to and from devices.  The first issue is not solvable
+in general for a virtualized system; hardware control software can't be
+adequately virtualized without a full real-time operating system, which would
+require an RT aware virtualization platform.
+The second issue may cause performance problems, but this is unlikely to be a
+significant issue.  In many cases these delays may be eliminated through
+configuration or paravirtualization.
+4.8) Covert channels and leaks
+In addition to the above problems, time information will inevitably leak to the
+guest about the host in anything but a perfect implementation of virtualized
+time.  This may allow the guest to infer the presence of a hypervisor (as in a
+red-pill type detection), and it may allow information to leak between guests
+by using CPU utilization itself as a signalling channel.  Preventing such
+problems would require completely isolated virtual time which may not track
+real time any longer.  This may be useful in certain security or QA contexts,
+but in general isn't recommended for real-world deployment scenarios.
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 8a6a8c6d4980..dc73bc54cc4e 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -1640,15 +1640,6 @@ static void blk_request(struct virtqueue *vq)
        off = out->sector * 512;
        /*
-         * The block device implements "barriers", where the Guest indicates
-         * that it wants all previous writes to occur before this write.  We
-         * don't have a way of asking our kernel to do a barrier, so we just
-         * synchronize all the data in the file.  Pretty poor, no?
-         */
-        if (out->type & VIRTIO_BLK_T_BARRIER)
-                fdatasync(vblk->fd);
-        /*
         * In general the virtio block driver is allowed to try SCSI commands.
         * It'd be nice if we supported eject, for example, but we don't.
         */
@@ -1680,6 +1671,13 @@ static void blk_request(struct virtqueue *vq)
                        /* Die, bad Guest, die. */
                        errx(1, "Write past end %llu+%u", off, ret);
                }
+                wlen = sizeof(*in);
+                *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
+        } else if (out->type & VIRTIO_BLK_T_FLUSH) {
+                /* Flush */
+                ret = fdatasync(vblk->fd);
+                verbose("FLUSH fdatasync: %i\n", ret);
                wlen = sizeof(*in);
                *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
        } else {
@@ -1703,15 +1701,6 @@ static void blk_request(struct virtqueue *vq)
                }
        }
-        /*
-         * OK, so we noted that it was pretty poor to use an fdatasync as a
-         * barrier.  But Christoph Hellwig points out that we need a sync
-         * *afterwards* as well: "Barriers specify no reordering to the front
-         * or the back."  And Jens Axboe confirmed it, so here we are:
-         */
-        if (out->type & VIRTIO_BLK_T_BARRIER)
-                fdatasync(vblk->fd);
        /* Finished that request. */
        add_used(vq, head, wlen);
 }
@@ -1736,8 +1725,8 @@ static void setup_block_file(const char *filename)
        vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE);
        vblk->len = lseek64(vblk->fd, 0, SEEK_END);
-        /* We support barriers. */
+        /* We support FLUSH. */
-        add_feature(dev, VIRTIO_BLK_F_BARRIER);
+        add_feature(dev, VIRTIO_BLK_F_FLUSH);
        /* Tell Guest how many sectors this device has. */
        conf.capacity = cpu_to_le64(vblk->len / 512);
diff --git a/Documentation/misc-devices/apds990x.txt b/Documentation/misc-devices/apds990x.txt
new file mode 100644
index 000000000000..d5408cade32f
--- /dev/null
+++ b/Documentation/misc-devices/apds990x.txt
@@ -0,0 +1,111 @@
+Kernel driver apds990x
+======================
+Supported chips:
+Avago APDS990X
+Data sheet:
+Not freely available
+Author:
+Samu Onkalo <samu.p.onkalo@nokia.com>
+Description
+-----------
+APDS990x is a combined ambient light and proximity sensor. ALS and proximity
+functionality are highly connected. ALS measurement path must be running
+while the proximity functionality is enabled.
+ALS produces raw measurement values for two channels: Clear channel
+(infrared + visible light) and IR only. However, threshold comparisons happen
+using clear channel only. Lux value and the threshold level on the HW
+might vary quite much depending the spectrum of the light source.
+Driver makes necessary conversions to both directions so that user handles
+only lux values. Lux value is calculated using information from the both
+channels. HW threshold level is calculated from the given lux value to match
+with current type of the lightning. Sometimes inaccuracy of the estimations
+lead to false interrupt, but that doesn't harm.
+ALS contains 4 different gain steps. Driver automatically
+selects suitable gain step. After each measurement, reliability of the results
+is estimated and new measurement is trigged if necessary.
+Platform data can provide tuned values to the conversion formulas if
+values are known. Otherwise plain sensor default values are used.
+Proximity side is little bit simpler. There is no need for complex conversions.
+It produces directly usable values.
+Driver controls chip operational state using pm_runtime framework.
+Voltage regulators are controlled based on chip operational state.
+SYSFS
+-----
+chip_id
+        RO - shows detected chip type and version
+power_state
+        RW - enable / disable chip. Uses counting logic
+             1 enables the chip
+             0 disables the chip
+lux0_input
+        RO - measured lux value
+             sysfs_notify called when threshold interrupt occurs
+lux0_sensor_range
+        RO - lux0_input max value. Actually never reaches since sensor tends
+             to saturate much before that. Real max value varies depending
+             on the light spectrum etc.
+lux0_rate
+        RW - measurement rate in Hz
+lux0_rate_avail
+        RO - supported measurement rates
+lux0_calibscale
+        RW - calibration value. Set to neutral value by default.
+             Output results are multiplied with calibscale / calibscale_default
+             value.
+lux0_calibscale_default
+        RO - neutral calibration value
+lux0_thresh_above_value
+        RW - HI level threshold value. All results above the value
+             trigs an interrupt. 65535 (i.e. sensor_range) disables the above
+             interrupt.
+lux0_thresh_below_value
+        RW - LO level threshold value. All results below the value
+             trigs an interrupt. 0 disables the below interrupt.
+prox0_raw
+        RO - measured proximity value
+             sysfs_notify called when threshold interrupt occurs
+prox0_sensor_range
+        RO - prox0_raw max value (1023)
+prox0_raw_en
+        RW - enable / disable proximity - uses counting logic
+             1 enables the proximity
+             0 disables the proximity
+prox0_reporting_mode
+        RW - trigger / periodic. In "trigger" mode the driver tells two possible
+             values: 0 or prox0_sensor_range value. 0 means no proximity,
+             1023 means proximity. This causes minimal number of interrupts.
+             In "periodic" mode the driver reports all values above
+             prox0_thresh_above. This causes more interrupts, but it can give
+             _rough_ estimate about the distance.
+prox0_reporting_mode_avail
+        RO - accepted values to prox0_reporting_mode (trigger, periodic)
+prox0_thresh_above_value
+        RW - threshold level which trigs proximity events.
diff --git a/Documentation/misc-devices/bh1770glc.txt b/Documentation/misc-devices/bh1770glc.txt
new file mode 100644
index 000000000000..7d64c014dc70
--- /dev/null
+++ b/Documentation/misc-devices/bh1770glc.txt
@@ -0,0 +1,116 @@
+Kernel driver bh1770glc
+=======================
+Supported chips:
+ROHM BH1770GLC
+OSRAM SFH7770
+Data sheet:
+Not freely available
+Author:
+Samu Onkalo <samu.p.onkalo@nokia.com>
+Description
+-----------
+BH1770GLC and SFH7770 are combined ambient light and proximity sensors.
+ALS and proximity parts operates on their own, but they shares common I2C
+interface and interrupt logic. In principle they can run on their own,
+but ALS side results are used to estimate reliability of the proximity sensor.
+ALS produces 16 bit lux values. The chip contains interrupt logic to produce
+low and high threshold interrupts.
+Proximity part contains IR-led driver up to 3 IR leds. The chip measures
+amount of reflected IR light and produces proximity result. Resolution is
+8 bit. Driver supports only one channel. Driver uses ALS results to estimate
+reliability of the proximity results. Thus ALS is always running while
+proximity detection is needed.
+Driver uses threshold interrupts to avoid need for polling the values.
+Proximity low interrupt doesn't exists in the chip. This is simulated
+by using a delayed work. As long as there is proximity threshold above
+interrupts the delayed work is pushed forward. So, when proximity level goes
+below the threshold value, there is no interrupt and the delayed work will
+finally run. This is handled as no proximity indication.
+Chip state is controlled via runtime pm framework when enabled in config.
+Calibscale factor is used to hide differences between the chips. By default
+value set to neutral state meaning factor of 1.00. To get proper values,
+calibrated source of light is needed as a reference. Calibscale factor is set
+so that measurement produces about the expected lux value.
+SYSFS
+-----
+chip_id
+        RO - shows detected chip type and version
+power_state
+        RW - enable / disable chip. Uses counting logic
+             1 enables the chip
+             0 disables the chip
+lux0_input
+        RO - measured lux value
+             sysfs_notify called when threshold interrupt occurs
+lux0_sensor_range
+        RO - lux0_input max value
+lux0_rate
+        RW - measurement rate in Hz
+lux0_rate_avail
+        RO - supported measurement rates
+lux0_thresh_above_value
+        RW - HI level threshold value. All results above the value
+             trigs an interrupt. 65535 (i.e. sensor_range) disables the above
+             interrupt.
+lux0_thresh_below_value
+        RW - LO level threshold value. All results below the value
+             trigs an interrupt. 0 disables the below interrupt.
+lux0_calibscale
+        RW - calibration value. Set to neutral value by default.
+             Output results are multiplied with calibscale / calibscale_default
+             value.
+lux0_calibscale_default
+        RO - neutral calibration value
+prox0_raw
+        RO - measured proximity value
+             sysfs_notify called when threshold interrupt occurs
+prox0_sensor_range
+        RO - prox0_raw max value
+prox0_raw_en
+        RW - enable / disable proximity - uses counting logic
+             1 enables the proximity
+             0 disables the proximity
+prox0_thresh_above_count
+        RW - number of proximity interrupts needed before triggering the event
+prox0_rate_above
+        RW - Measurement rate (in Hz) when the level is above threshold
+             i.e. when proximity on has been reported.
+prox0_rate_below
+        RW - Measurement rate (in Hz) when the level is below threshold
+             i.e. when proximity off has been reported.
+prox0_rate_avail
+        RO - Supported proximity measurement rates in Hz
+prox0_thresh_above0_value
+        RW - threshold level which trigs proximity events.
+             Filtered by persistence filter (prox0_thresh_above_count)
+prox0_thresh_above1_value
+        RW - threshold level which trigs event immediately
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index d2b62b71b617..5dc638791d97 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -765,6 +765,14 @@ xmit_hash_policy
        does not exist, and the layer2 policy is the only policy.  The
        layer2+3 value was added for bonding version 3.2.2.
+resend_igmp
+        Specifies the number of IGMP membership reports to be issued after
+        a failover event. One membership report is issued immediately after
+        the failover, subsequent packets are sent in each 200ms interval.
+        The valid range is 0 - 255; the default value is 1. This option
+        was added for bonding version 3.7.0.
 3. Configuring Bonding Devices
 ==============================
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
index cd79735013f9..5b04b67ddca2 100644
--- a/Documentation/networking/can.txt
+++ b/Documentation/networking/can.txt
@@ -22,6 +22,7 @@ This file contains
      4.1.2 RAW socket option CAN_RAW_ERR_FILTER
      4.1.3 RAW socket option CAN_RAW_LOOPBACK
      4.1.4 RAW socket option CAN_RAW_RECV_OWN_MSGS
+      4.1.5 RAW socket returned message flags
    4.2 Broadcast Manager protocol sockets (SOCK_DGRAM)
    4.3 connected transport protocols (SOCK_SEQPACKET)
    4.4 unconnected transport protocols (SOCK_DGRAM)
@@ -471,6 +472,17 @@ solution for a couple of reasons:
    setsockopt(s, SOL_CAN_RAW, CAN_RAW_RECV_OWN_MSGS,
               &recv_own_msgs, sizeof(recv_own_msgs));
+  4.1.5 RAW socket returned message flags
+  When using recvmsg() call, the msg->msg_flags may contain following flags:
+    MSG_DONTROUTE: set when the received frame was created on the local host.
+    MSG_CONFIRM: set when the frame was sent via the socket it is received on.
+      This flag can be interpreted as a 'transmission confirmation' when the
+      CAN driver supports the echo of frames on driver level, see 3.2 and 6.2.
+      In order to receive such messages, CAN_RAW_RECV_OWN_MSGS must be set.
  4.2 Broadcast Manager protocol sockets (SOCK_DGRAM)
  4.3 connected transport protocols (SOCK_SEQPACKET)
  4.4 unconnected transport protocols (SOCK_DGRAM)
diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt
index a62fdf7a6bff..271d524a4c8d 100644
--- a/Documentation/networking/dccp.txt
+++ b/Documentation/networking/dccp.txt
@@ -1,18 +1,20 @@
 DCCP protocol
-============
+=============
 Contents
 ========
 - Introduction
 - Missing features
 - Socket options
+- Sysctl variables
+- IOCTLs
+- Other tunables
 - Notes
 Introduction
 ============
 Datagram Congestion Control Protocol (DCCP) is an unreliable, connection
 oriented protocol designed to solve issues present in UDP and TCP, particularly
 for real-time and multimedia (streaming) traffic.
@@ -29,9 +31,9 @@ It has a base protocol and pluggable congestion control IDs (CCIDs).
 DCCP is a Proposed Standard (RFC 2026), and the homepage for DCCP as a protocol
 is at http://www.ietf.org/html.charters/dccp-charter.html
 Missing features
 ================
 The Linux DCCP implementation does not currently support all the features that are
 specified in RFCs 4340...42.
@@ -45,7 +47,6 @@ http://linux-net.osdl.org/index.php/DCCP_Testing#Experimental_DCCP_source_tree
 Socket options
 ==============
 DCCP_SOCKOPT_SERVICE sets the service. The specification mandates use of
 service codes (RFC 4340, sec. 8.1.2); if this socket option is not set,
 the socket will fall back to 0 (which means that no meaningful service code
@@ -112,6 +113,7 @@ DCCP_SOCKOPT_CCID_TX_INFO
 On unidirectional connections it is useful to close the unused half-connection
 via shutdown (SHUT_WR or SHUT_RD): this will reduce per-packet processing costs.
 Sysctl variables
 ================
 Several DCCP default parameters can be managed by the following sysctls
@@ -155,15 +157,30 @@ sync_ratelimit = 125 ms
        sequence-invalid packets on the same socket (RFC 4340, 7.5.4). The unit
        of this parameter is milliseconds; a value of 0 disables rate-limiting.
 IOCTLS
 ======
 FIONREAD
        Works as in udp(7): returns in the `int' argument pointer the size of
        the next pending datagram in bytes, or 0 when no datagram is pending.
+Other tunables
+==============
+Per-route rto_min support
+        CCID-2 supports the RTAX_RTO_MIN per-route setting for the minimum value
+        of the RTO timer. This setting can be modified via the 'rto_min' option
+        of iproute2; for example:
+                > ip route change 10.0.0.0/24   rto_min 250j dev wlan0
+                > ip route add    10.0.0.254/32 rto_min 800j dev wlan0
+                > ip route show dev wlan0
+        CCID-3 also supports the rto_min setting: it is used to define the lower
+        bound for the expiry of the nofeedback timer. This can be useful on LANs
+        with very low RTTs (e.g., loopback, Gbit ethernet).
 Notes
 =====
 DCCP does not travel through NAT successfully at present on many boxes. This is
 because the checksum covers the pseudo-header as per TCP and UDP. Linux NAT
 support for DCCP has been added.
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index f350c69b2bb4..c7165f4cb792 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1014,6 +1014,12 @@ conf/interface/*:
 accept_ra - BOOLEAN
        Accept Router Advertisements; autoconfigure using them.
+        Possible values are:
+                0 Do not accept Router Advertisements.
+                1 Accept Router Advertisements if forwarding is disabled.
+                2 Overrule forwarding behaviour. Accept Router Advertisements
+                  even if forwarding is enabled.
        Functional default: enabled if local forwarding is disabled.
                            disabled if local forwarding is enabled.
@@ -1075,7 +1081,12 @@ forwarding - BOOLEAN
        Note: It is recommended to have the same setting on all
        interfaces; mixed router/host scenarios are rather uncommon.
-        FALSE:
+        Possible values are:
+                0 Forwarding disabled
+                1 Forwarding enabled
+                2 Forwarding enabled (Hybrid Mode)
+        FALSE (0):
        By default, Host behaviour is assumed.  This means:
@@ -1085,18 +1096,24 @@ forwarding - BOOLEAN
           Advertisements (and do autoconfiguration).
        4. If accept_redirects is TRUE (default), accept Redirects.
-        TRUE:
+        TRUE (1):
        If local forwarding is enabled, Router behaviour is assumed.
        This means exactly the reverse from the above:
        1. IsRouter flag is set in Neighbour Advertisements.
        2. Router Solicitations are not sent.
-        3. Router Advertisements are ignored.
+        3. Router Advertisements are ignored unless accept_ra is 2.
        4. Redirects are ignored.
-        Default: FALSE if global forwarding is disabled (default),
+        TRUE (2):
-                 otherwise TRUE.
+        Hybrid mode. Same behaviour as TRUE, except for:
+        2. Router Solicitations are being sent when necessary.
+        Default: 0 (disabled) if global forwarding is disabled (default),
+                 otherwise 1 (enabled).
 hop_limit - INTEGER
        Default Hop Limit to set.
diff --git a/Documentation/networking/phonet.txt b/Documentation/networking/phonet.txt
index 6e8ce09f9c73..24ad2adba6e5 100644
--- a/Documentation/networking/phonet.txt
+++ b/Documentation/networking/phonet.txt
@@ -112,6 +112,22 @@ However, connect() and getpeername() are not supported, as they did
 not seem useful with Phonet usages (could be added easily).
+Resource subscription
+---------------------
+A Phonet datagram socket can be subscribed to any number of 8-bits
+Phonet resources, as follow:
+  uint32_t res = 0xXX;
+  ioctl(fd, SIOCPNADDRESOURCE, &res);
+Subscription is similarly cancelled using the SIOCPNDELRESOURCE I/O
+control request, or when the socket is closed.
+Note that no more than one socket can be subcribed to any given
+resource at a time. If not, ioctl() will return EBUSY.
 Phonet Pipe protocol
 --------------------
@@ -166,6 +182,46 @@ The pipe protocol provides two socket options at the SOL_PNPIPE level:
    or zero if encapsulation is off.
+Phonet Pipe-controller Implementation
+-------------------------------------
+Phonet Pipe-controller is enabled by selecting the CONFIG_PHONET_PIPECTRLR Kconfig
+option. It is useful when communicating with those Nokia Modems which do not
+implement Pipe controller in them e.g. Nokia Slim Modem used in ST-Ericsson
+U8500 platform.
+The implementation is based on the Data Connection Establishment Sequence
+depicted in 'Nokia Wireless Modem API - Wireless_modem_user_guide.pdf'
+document.
+It allows a phonet sequenced socket (host-pep) to initiate a Pipe connection
+between itself and a remote pipe-end point (e.g. modem).
+The implementation adds socket options at SOL_PNPIPE level:
+ PNPIPE_PIPE_HANDLE
+        It accepts an integer argument for setting value of pipe handle.
+  PNPIPE_ENABLE accepts one integer value (int). If set to zero, the pipe
+    is disabled. If the value is non-zero, the pipe is enabled. If the pipe
+    is not (yet) connected, ENOTCONN is error is returned.
+The implementation also adds socket 'connect'. On calling the 'connect', pipe
+will be created between the source socket and the destination, and the pipe
+state will be set to PIPE_DISABLED.
+After a pipe has been created and enabled successfully, the Pipe data can be
+exchanged between the host-pep and remote-pep (modem).
+User-space would typically follow below sequence with Pipe controller:-
+-socket
+-bind
+-setsockopt for PNPIPE_PIPE_HANDLE
+-connect
+-setsockopt for PNPIPE_ENCAP_IP
+-setsockopt for PNPIPE_ENABLE
 Authors
 -------
diff --git a/Documentation/networking/phy.txt b/Documentation/networking/phy.txt
index 88bb71b46da4..9eb1ba52013d 100644
--- a/Documentation/networking/phy.txt
+++ b/Documentation/networking/phy.txt
@@ -177,18 +177,6 @@ Doing it all yourself
 
   A convenience function to print out the PHY status neatly.
- int phy_clear_interrupt(struct phy_device *phydev);
- int phy_config_interrupt(struct phy_device *phydev, u32 interrupts);
-   
-   Clear the PHY's interrupt, and configure which ones are allowed,
-   respectively.  Currently only supports all on, or all off.
- 
- int phy_enable_interrupts(struct phy_device *phydev);
- int phy_disable_interrupts(struct phy_device *phydev);
-   Functions which enable/disable PHY interrupts, clearing them
-   before and after, respectively.
 int phy_start_interrupts(struct phy_device *phydev);
 int phy_stop_interrupts(struct phy_device *phydev);
@@ -213,12 +201,6 @@ Doing it all yourself
   Fills the phydev structure with up-to-date information about the current
   settings in the PHY.
- void phy_sanitize_settings(struct phy_device *phydev)
-   
-   Resolves differences between currently desired settings, and
-   supported settings for the given PHY device.  Does not make
-   the changes in the hardware, though.
 int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd);
 int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd);
diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt
index e8c8f4f06c67..98097d8cb910 100644
--- a/Documentation/networking/timestamping.txt
+++ b/Documentation/networking/timestamping.txt
@@ -172,15 +172,19 @@ struct skb_shared_hwtstamps {
 };
 Time stamps for outgoing packets are to be generated as follows:
- In hard_start_xmit(), check if skb_tx(skb)->hardware is set no-zero.
+- In hard_start_xmit(), check if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)
-  If yes, then the driver is expected to do hardware time stamping.
+  is set no-zero. If yes, then the driver is expected 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 setting the field
+  that the driver is doing the time stamping by setting the flag
-  skb_tx(skb)->in_progress non-zero. You might want to keep a pointer
+  SKBTX_IN_PROGRESS in skb_shinfo(skb)->tx_flags , e.g. with
-  to the associated skb for the next step and not free the skb. A driver
-  not supporting hardware time stamping doesn't do that. A driver must
+      skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-  never touch sk_buff::tstamp! It is used to store software generated
-  time stamps by the network subsystem.
+  You might want to keep a pointer to the associated skb for the next step
+  and not free the skb. A driver not supporting hardware time stamping doesn't
+  do that. A driver must 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
@@ -191,6 +195,6 @@ Time stamps for outgoing packets are to be generated as follows:
  this would occur at a later time in the processing pipeline than other
  software time stamping and therefore could lead to unexpected deltas
  between time stamps.
- If the driver did not call set skb_tx(skb)->in_progress, then
+- If the driver did not set the SKBTX_IN_PROGRESS flag (see above), then
  dev_hard_start_xmit() checks whether software time stamping
  is wanted as fallback and potentially generates the time stamp.
diff --git a/Documentation/pcmcia/driver-changes.txt b/Documentation/pcmcia/driver-changes.txt
index 26c0f9c00545..dd04361dd361 100644
--- a/Documentation/pcmcia/driver-changes.txt
+++ b/Documentation/pcmcia/driver-changes.txt
@@ -1,4 +1,29 @@
 This file details changes in 2.6 which affect PCMCIA card driver authors:
+* pcmcia_loop_config() and autoconfiguration (as of 2.6.36)
+   If struct pcmcia_device *p_dev->config_flags is set accordingly,
+   pcmcia_loop_config() now sets up certain configuration values
+   automatically, though the driver may still override the settings
+   in the callback function. The following autoconfiguration options
+   are provided at the moment:
+        CONF_AUTO_CHECK_VCC : check for matching Vcc
+        CONF_AUTO_SET_VPP   : set Vpp
+        CONF_AUTO_AUDIO     : auto-enable audio line, if required
+        CONF_AUTO_SET_IO    : set ioport resources (->resource[0,1])
+        CONF_AUTO_SET_IOMEM : set first iomem resource (->resource[2])
+* pcmcia_request_configuration -> pcmcia_enable_device (as of 2.6.36)
+   pcmcia_request_configuration() got renamed to pcmcia_enable_device(),
+   as it mirrors pcmcia_disable_device(). Configuration settings are now
+   stored in struct pcmcia_device, e.g. in the fields config_flags,
+   config_index, config_base, vpp.
+* pcmcia_request_window changes (as of 2.6.36)
+   Instead of win_req_t, drivers are now requested to fill out
+   struct pcmcia_device *p_dev->resource[2,3,4,5] for up to four ioport
+   ranges. After a call to pcmcia_request_window(), the regions found there
+   are reserved and may be used immediately -- until pcmcia_release_window()
+   is called.
 * pcmcia_request_io changes (as of 2.6.36)
   Instead of io_req_t, drivers are now requested to fill out
   struct pcmcia_device *p_dev->resource[0,1] for up to two ioport
diff --git a/Documentation/power/00-INDEX b/Documentation/power/00-INDEX
index fb742c213c9e..45e9d4a91284 100644
--- a/Documentation/power/00-INDEX
+++ b/Documentation/power/00-INDEX
@@ -14,6 +14,8 @@ interface.txt
        - Power management user interface in /sys/power
 notifiers.txt
        - Registering suspend notifiers in device drivers
+opp.txt
+        - Operating Performance Point library
 pci.txt
        - How the PCI Subsystem Does Power Management
 pm_qos_interface.txt
diff --git a/Documentation/power/interface.txt b/Documentation/power/interface.txt
index e67211fe0ee2..c537834af005 100644
--- a/Documentation/power/interface.txt
+++ b/Documentation/power/interface.txt
@@ -57,7 +57,7 @@ smallest image possible.  In particular, if "0" is written to this file, the
 suspend image will be as small as possible.
 Reading from this file will display the current image size limit, which
-is set to 500 MB by default.
+is set to 2/5 of available RAM by default.
 /sys/power/pm_trace controls the code which saves the last PM event point in
 the RTC across reboots, so that you can debug a machine that just hangs
diff --git a/Documentation/power/opp.txt b/Documentation/power/opp.txt
new file mode 100644
index 000000000000..44d87ad3cea9
--- /dev/null
+++ b/Documentation/power/opp.txt
@@ -0,0 +1,375 @@
+*=============*
+* OPP Library *
+*=============*
+(C) 2009-2010 Nishanth Menon <nm@ti.com>, Texas Instruments Incorporated
+Contents
+--------
+1. Introduction
+2. Initial OPP List Registration
+3. OPP Search Functions
+4. OPP Availability Control Functions
+5. OPP Data Retrieval Functions
+6. Cpufreq Table Generation
+7. Data Structures
+1. Introduction
+===============
+Complex SoCs of today consists of a multiple sub-modules working in conjunction.
+In an operational system executing varied use cases, not all modules in the SoC
+need to function at their highest performing frequency all the time. To
+facilitate this, sub-modules in a SoC are grouped into domains, allowing some
+domains to run at lower voltage and frequency while other domains are loaded
+more. The set of discrete tuples consisting of frequency and voltage pairs that
+the device will support per domain are called Operating Performance Points or
+OPPs.
+OPP library provides a set of helper functions to organize and query the OPP
+information. The library is located in drivers/base/power/opp.c and the header
+is located in include/linux/opp.h. OPP library can be enabled by enabling
+CONFIG_PM_OPP from power management menuconfig menu. OPP library depends on
+CONFIG_PM as certain SoCs such as Texas Instrument's OMAP framework allows to
+optionally boot at a certain OPP without needing cpufreq.
+Typical usage of the OPP library is as follows:
+(users)         -> registers a set of default OPPs              -> (library)
+SoC framework   -> modifies on required cases certain OPPs      -> OPP layer
+                -> queries to search/retrieve information       ->
+OPP layer expects each domain to be represented by a unique device pointer. SoC
+framework registers a set of initial OPPs per device with the OPP layer. This
+list is expected to be an optimally small number typically around 5 per device.
+This initial list contains a set of OPPs that the framework expects to be safely
+enabled by default in the system.
+Note on OPP Availability:
+------------------------
+As the system proceeds to operate, SoC framework may choose to make certain
+OPPs available or not available on each device based on various external
+factors. Example usage: Thermal management or other exceptional situations where
+SoC framework might choose to disable a higher frequency OPP to safely continue
+operations until that OPP could be re-enabled if possible.
+OPP library facilitates this concept in it's implementation. The following
+operational functions operate only on available opps:
+opp_find_freq_{ceil, floor}, opp_get_voltage, opp_get_freq, opp_get_opp_count
+and opp_init_cpufreq_table
+opp_find_freq_exact is meant to be used to find the opp pointer which can then
+be used for opp_enable/disable functions to make an opp available as required.
+WARNING: Users of OPP library should refresh their availability count using
+get_opp_count if opp_enable/disable functions are invoked for a device, the
+exact mechanism to trigger these or the notification mechanism to other
+dependent subsystems such as cpufreq are left to the discretion of the SoC
+specific framework which uses the OPP library. Similar care needs to be taken
+care to refresh the cpufreq table in cases of these operations.
+WARNING on OPP List locking mechanism:
+-------------------------------------------------
+OPP library uses RCU for exclusivity. RCU allows the query functions to operate
+in multiple contexts and this synchronization mechanism is optimal for a read
+intensive operations on data structure as the OPP library caters to.
+To ensure that the data retrieved are sane, the users such as SoC framework
+should ensure that the section of code operating on OPP queries are locked
+using RCU read locks. The opp_find_freq_{exact,ceil,floor},
+opp_get_{voltage, freq, opp_count} fall into this category.
+opp_{add,enable,disable} are updaters which use mutex and implement it's own
+RCU locking mechanisms. opp_init_cpufreq_table acts as an updater and uses
+mutex to implment RCU updater strategy. These functions should *NOT* be called
+under RCU locks and other contexts that prevent blocking functions in RCU or
+mutex operations from working.
+2. Initial OPP List Registration
+================================
+The SoC implementation calls opp_add function iteratively to add OPPs per
+device. It is expected that the SoC framework will register the OPP entries
+optimally- typical numbers range to be less than 5. The list generated by
+registering the OPPs is maintained by OPP library throughout the device
+operation. The SoC framework can subsequently control the availability of the
+OPPs dynamically using the opp_enable / disable functions.
+opp_add - Add a new OPP for a specific domain represented by the device pointer.
+        The OPP is defined using the frequency and voltage. Once added, the OPP
+        is assumed to be available and control of it's availability can be done
+        with the opp_enable/disable functions. OPP library internally stores
+        and manages this information in the opp struct. This function may be
+        used by SoC framework to define a optimal list as per the demands of
+        SoC usage environment.
+        WARNING: Do not use this function in interrupt context.
+        Example:
+         soc_pm_init()
+         {
+                /* Do things */
+                r = opp_add(mpu_dev, 1000000, 900000);
+                if (!r) {
+                        pr_err("%s: unable to register mpu opp(%d)\n", r);
+                        goto no_cpufreq;
+                }
+                /* Do cpufreq things */
+         no_cpufreq:
+                /* Do remaining things */
+         }
+3. OPP Search Functions
+=======================
+High level framework such as cpufreq operates on frequencies. To map the
+frequency back to the corresponding OPP, OPP library provides handy functions
+to search the OPP list that OPP library internally manages. These search
+functions return the matching pointer representing the opp if a match is
+found, else returns error. These errors are expected to be handled by standard
+error checks such as IS_ERR() and appropriate actions taken by the caller.
+opp_find_freq_exact - Search for an OPP based on an *exact* frequency and
+        availability. This function is especially useful to enable an OPP which
+        is not available by default.
+        Example: In a case when SoC framework detects a situation where a
+        higher frequency could be made available, it can use this function to
+        find the OPP prior to call the opp_enable to actually make it available.
+         rcu_read_lock();
+         opp = opp_find_freq_exact(dev, 1000000000, false);
+         rcu_read_unlock();
+         /* dont operate on the pointer.. just do a sanity check.. */
+         if (IS_ERR(opp)) {
+                pr_err("frequency not disabled!\n");
+                /* trigger appropriate actions.. */
+         } else {
+                opp_enable(dev,1000000000);
+         }
+        NOTE: This is the only search function that operates on OPPs which are
+        not available.
+opp_find_freq_floor - Search for an available OPP which is *at most* the
+        provided frequency. This function is useful while searching for a lesser
+        match OR operating on OPP information in the order of decreasing
+        frequency.
+        Example: To find the highest opp for a device:
+         freq = ULONG_MAX;
+         rcu_read_lock();
+         opp_find_freq_floor(dev, &freq);
+         rcu_read_unlock();
+opp_find_freq_ceil - Search for an available OPP which is *at least* the
+        provided frequency. This function is useful while searching for a
+        higher match OR operating on OPP information in the order of increasing
+        frequency.
+        Example 1: To find the lowest opp for a device:
+         freq = 0;
+         rcu_read_lock();
+         opp_find_freq_ceil(dev, &freq);
+         rcu_read_unlock();
+        Example 2: A simplified implementation of a SoC cpufreq_driver->target:
+         soc_cpufreq_target(..)
+         {
+                /* Do stuff like policy checks etc. */
+                /* Find the best frequency match for the req */
+                rcu_read_lock();
+                opp = opp_find_freq_ceil(dev, &freq);
+                rcu_read_unlock();
+                if (!IS_ERR(opp))
+                        soc_switch_to_freq_voltage(freq);
+                else
+                        /* do something when we cant satisfy the req */
+                /* do other stuff */
+         }
+4. OPP Availability Control Functions
+=====================================
+A default OPP list registered with the OPP library may not cater to all possible
+situation. The OPP library provides a set of functions to modify the
+availability of a OPP within the OPP list. This allows SoC frameworks to have
+fine grained dynamic control of which sets of OPPs are operationally available.
+These functions are intended to *temporarily* remove an OPP in conditions such
+as thermal considerations (e.g. don't use OPPx until the temperature drops).
+WARNING: Do not use these functions in interrupt context.
+opp_enable - Make a OPP available for operation.
+        Example: Lets say that 1GHz OPP is to be made available only if the
+        SoC temperature is lower than a certain threshold. The SoC framework
+        implementation might choose to do something as follows:
+         if (cur_temp < temp_low_thresh) {
+                /* Enable 1GHz if it was disabled */
+                rcu_read_lock();
+                opp = opp_find_freq_exact(dev, 1000000000, false);
+                rcu_read_unlock();
+                /* just error check */
+                if (!IS_ERR(opp))
+                        ret = opp_enable(dev, 1000000000);
+                else
+                        goto try_something_else;
+         }
+opp_disable - Make an OPP to be not available for operation
+        Example: Lets say that 1GHz OPP is to be disabled if the temperature
+        exceeds a threshold value. The SoC framework implementation might
+        choose to do something as follows:
+         if (cur_temp > temp_high_thresh) {
+                /* Disable 1GHz if it was enabled */
+                rcu_read_lock();
+                opp = opp_find_freq_exact(dev, 1000000000, true);
+                rcu_read_unlock();
+                /* just error check */
+                if (!IS_ERR(opp))
+                        ret = opp_disable(dev, 1000000000);
+                else
+                        goto try_something_else;
+         }
+5. OPP Data Retrieval Functions
+===============================
+Since OPP library abstracts away the OPP information, a set of functions to pull
+information from the OPP structure is necessary. Once an OPP pointer is
+retrieved using the search functions, the following functions can be used by SoC
+framework to retrieve the information represented inside the OPP layer.
+opp_get_voltage - Retrieve the voltage represented by the opp pointer.
+        Example: At a cpufreq transition to a different frequency, SoC
+        framework requires to set the voltage represented by the OPP using
+        the regulator framework to the Power Management chip providing the
+        voltage.
+         soc_switch_to_freq_voltage(freq)
+         {
+                /* do things */
+                rcu_read_lock();
+                opp = opp_find_freq_ceil(dev, &freq);
+                v = opp_get_voltage(opp);
+                rcu_read_unlock();
+                if (v)
+                        regulator_set_voltage(.., v);
+                /* do other things */
+         }
+opp_get_freq - Retrieve the freq represented by the opp pointer.
+        Example: Lets say the SoC framework uses a couple of helper functions
+        we could pass opp pointers instead of doing additional parameters to
+        handle quiet a bit of data parameters.
+         soc_cpufreq_target(..)
+         {
+                /* do things.. */
+                 max_freq = ULONG_MAX;
+                 rcu_read_lock();
+                 max_opp = opp_find_freq_floor(dev,&max_freq);
+                 requested_opp = opp_find_freq_ceil(dev,&freq);
+                 if (!IS_ERR(max_opp) && !IS_ERR(requested_opp))
+                        r = soc_test_validity(max_opp, requested_opp);
+                 rcu_read_unlock();
+                /* do other things */
+         }
+         soc_test_validity(..)
+         {
+                 if(opp_get_voltage(max_opp) < opp_get_voltage(requested_opp))
+                         return -EINVAL;
+                 if(opp_get_freq(max_opp) < opp_get_freq(requested_opp))
+                         return -EINVAL;
+                /* do things.. */
+         }
+opp_get_opp_count - Retrieve the number of available opps for a device
+        Example: Lets say a co-processor in the SoC needs to know the available
+        frequencies in a table, the main processor can notify as following:
+         soc_notify_coproc_available_frequencies()
+         {
+                /* Do things */
+                rcu_read_lock();
+                num_available = opp_get_opp_count(dev);
+                speeds = kzalloc(sizeof(u32) * num_available, GFP_KERNEL);
+                /* populate the table in increasing order */
+                freq = 0;
+                while (!IS_ERR(opp = opp_find_freq_ceil(dev, &freq))) {
+                        speeds[i] = freq;
+                        freq++;
+                        i++;
+                }
+                rcu_read_unlock();
+                soc_notify_coproc(AVAILABLE_FREQs, speeds, num_available);
+                /* Do other things */
+         }
+6. Cpufreq Table Generation
+===========================
+opp_init_cpufreq_table - cpufreq framework typically is initialized with
+        cpufreq_frequency_table_cpuinfo which is provided with the list of
+        frequencies that are available for operation. This function provides
+        a ready to use conversion routine to translate the OPP layer's internal
+        information about the available frequencies into a format readily
+        providable to cpufreq.
+        WARNING: Do not use this function in interrupt context.
+        Example:
+         soc_pm_init()
+         {
+                /* Do things */
+                r = opp_init_cpufreq_table(dev, &freq_table);
+                if (!r)
+                        cpufreq_frequency_table_cpuinfo(policy, freq_table);
+                /* Do other things */
+         }
+        NOTE: This function is available only if CONFIG_CPU_FREQ is enabled in
+        addition to CONFIG_PM as power management feature is required to
+        dynamically scale voltage and frequency in a system.
+7. Data Structures
+==================
+Typically an SoC contains multiple voltage domains which are variable. Each
+domain is represented by a device pointer. The relationship to OPP can be
+represented as follows:
+SoC
+ |- device 1
+ |      |- opp 1 (availability, freq, voltage)
+ |      |- opp 2 ..
+ ...    ...
+ |      `- opp n ..
+ |- device 2
+ ...
+ `- device m
+OPP library maintains a internal list that the SoC framework populates and
+accessed by various functions as described above. However, the structures
+representing the actual OPPs and domains are internal to the OPP library itself
+to allow for suitable abstraction reusable across systems.
+struct opp - The internal data structure of OPP library which is used to
+        represent an OPP. In addition to the freq, voltage, availability
+        information, it also contains internal book keeping information required
+        for the OPP library to operate on.  Pointer to this structure is
+        provided back to the users such as SoC framework to be used as a
+        identifier for OPP in the interactions with OPP layer.
+        WARNING: The struct opp pointer should not be parsed or modified by the
+        users. The defaults of for an instance is populated by opp_add, but the
+        availability of the OPP can be modified by opp_enable/disable functions.
+struct device - This is used to identify a domain to the OPP layer. The
+        nature of the device and it's implementation is left to the user of
+        OPP library such as the SoC framework.
+Overall, in a simplistic view, the data structure operations is represented as
+following:
+Initialization / modification:
+            +-----+        /- opp_enable
+opp_add --> | opp | <-------
+  |         +-----+        \- opp_disable
+  \-------> domain_info(device)
+Search functions:
+             /-- opp_find_freq_ceil  ---\   +-----+
+domain_info<---- opp_find_freq_exact -----> | opp |
+             \-- opp_find_freq_floor ---/   +-----+
+Retrieval functions:
+-----+     /- opp_get_voltage
+| opp | <---
+-----+     \- opp_get_freq
+domain_info <- opp_get_opp_count
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 55b859b3bc72..489e9bacd165 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -1,6 +1,7 @@
 Run-time Power Management Framework for I/O Devices
 (C) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+(C) 2010 Alan Stern <stern@rowland.harvard.edu>
 1. Introduction
@@ -157,7 +158,8 @@ rules:
    to execute it, the other callbacks will not be executed for the same device.
  * A request to execute ->runtime_resume() will cancel any pending or
-    scheduled requests to execute the other callbacks for the same device.
+    scheduled requests to execute the other callbacks for the same device,
+    except for scheduled autosuspends.
 3. Run-time PM Device Fields
@@ -165,7 +167,7 @@ The following device run-time PM fields are present in 'struct dev_pm_info', as
 defined in include/linux/pm.h:
  struct timer_list suspend_timer;
-    - timer used for scheduling (delayed) suspend request
+    - timer used for scheduling (delayed) suspend and autosuspend requests
  unsigned long timer_expires;
    - timer expiration time, in jiffies (if this is different from zero, the
@@ -230,6 +232,28 @@ defined in include/linux/pm.h:
      interface; it may only be modified with the help of the pm_runtime_allow()
      and pm_runtime_forbid() helper functions
+  unsigned int no_callbacks;
+    - indicates that the device does not use the run-time PM callbacks (see
+      Section 8); it may be modified only by the pm_runtime_no_callbacks()
+      helper function
+  unsigned int use_autosuspend;
+    - indicates that the device's driver supports delayed autosuspend (see
+      Section 9); it may be modified only by the
+      pm_runtime{_dont}_use_autosuspend() helper functions
+  unsigned int timer_autosuspends;
+    - indicates that the PM core should attempt to carry out an autosuspend
+      when the timer expires rather than a normal suspend
+  int autosuspend_delay;
+    - the delay time (in milliseconds) to be used for autosuspend
+  unsigned long last_busy;
+    - the time (in jiffies) when the pm_runtime_mark_last_busy() helper
+      function was last called for this device; used in calculating inactivity
+      periods for autosuspend
 All of the above fields are members of the 'power' member of 'struct device'.
 4. Run-time PM Device Helper Functions
@@ -255,6 +279,12 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
      error code on failure, where -EAGAIN or -EBUSY means it is safe to attempt
      to suspend the device again in future
+  int pm_runtime_autosuspend(struct device *dev);
+    - same as pm_runtime_suspend() except that the autosuspend delay is taken
+      into account; if pm_runtime_autosuspend_expiration() says the delay has
+      not yet expired then an autosuspend is scheduled for the appropriate time
+      and 0 is returned
  int pm_runtime_resume(struct device *dev);
    - 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
@@ -267,6 +297,11 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
      device (the request is represented by a work item in pm_wq); returns 0 on
      success or error code if the request has not been queued up
+  int pm_request_autosuspend(struct device *dev);
+    - schedule the execution of the subsystem-level suspend callback for the
+      device when the autosuspend delay has expired; if the delay has already
+      expired then the work item is queued up immediately
  int pm_schedule_suspend(struct device *dev, unsigned int delay);
    - schedule the execution of the subsystem-level suspend callback for the
      device in future, where 'delay' is the time to wait before queuing up a
@@ -298,12 +333,20 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
    - decrement the device's usage counter
  int pm_runtime_put(struct device *dev);
-    - decrement the device's usage counter, run pm_request_idle(dev) and return
+    - decrement the device's usage counter; if the result is 0 then run
-      its result
+      pm_request_idle(dev) and return its result
+  int pm_runtime_put_autosuspend(struct device *dev);
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_request_autosuspend(dev) and return its result
  int pm_runtime_put_sync(struct device *dev);
-    - decrement the device's usage counter, run pm_runtime_idle(dev) and return
+    - decrement the device's usage counter; if the result is 0 then run
-      its result
+      pm_runtime_idle(dev) and return its result
+  int pm_runtime_put_sync_autosuspend(struct device *dev);
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_runtime_autosuspend(dev) and return its result
  void pm_runtime_enable(struct device *dev);
    - enable the run-time PM helper functions to run the device bus type's
@@ -349,19 +392,51 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
      counter (used by the /sys/devices/.../power/control interface to
      effectively prevent the device from being power managed at run time)
+  void pm_runtime_no_callbacks(struct device *dev);
+    - set the power.no_callbacks flag for the device and remove the run-time
+      PM attributes from /sys/devices/.../power (or prevent them from being
+      added when the device is registered)
+  void pm_runtime_mark_last_busy(struct device *dev);
+    - set the power.last_busy field to the current time
+  void pm_runtime_use_autosuspend(struct device *dev);
+    - set the power.use_autosuspend flag, enabling autosuspend delays
+  void pm_runtime_dont_use_autosuspend(struct device *dev);
+    - clear the power.use_autosuspend flag, disabling autosuspend delays
+  void pm_runtime_set_autosuspend_delay(struct device *dev, int delay);
+    - set the power.autosuspend_delay value to 'delay' (expressed in
+      milliseconds); if 'delay' is negative then run-time suspends are
+      prevented
+  unsigned long pm_runtime_autosuspend_expiration(struct device *dev);
+    - calculate the time when the current autosuspend delay period will expire,
+      based on power.last_busy and power.autosuspend_delay; if the delay time
+      is 1000 ms or larger then the expiration time is rounded up to the
+      nearest second; returns 0 if the delay period has already expired or
+      power.use_autosuspend isn't set, otherwise returns the expiration time
+      in jiffies
 It is safe to execute the following helper functions from interrupt context:
 pm_request_idle()
+pm_request_autosuspend()
 pm_schedule_suspend()
 pm_request_resume()
 pm_runtime_get_noresume()
 pm_runtime_get()
 pm_runtime_put_noidle()
 pm_runtime_put()
+pm_runtime_put_autosuspend()
+pm_runtime_enable()
 pm_suspend_ignore_children()
 pm_runtime_set_active()
 pm_runtime_set_suspended()
-pm_runtime_enable()
+pm_runtime_suspended()
+pm_runtime_mark_last_busy()
+pm_runtime_autosuspend_expiration()
 5. Run-time PM Initialization, Device Probing and Removal
@@ -524,3 +599,141 @@ 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).
+8. "No-Callback" Devices
+Some "devices" are only logical sub-devices of their parent and cannot be
+power-managed on their own.  (The prototype example is a USB interface.  Entire
+USB devices can go into low-power mode or send wake-up requests, but neither is
+possible for individual interfaces.)  The drivers for these devices have no
+need of run-time PM callbacks; if the callbacks did exist, ->runtime_suspend()
+and ->runtime_resume() would always return 0 without doing anything else and
+->runtime_idle() would always call pm_runtime_suspend().
+Subsystems can tell the PM core about these devices by calling
+pm_runtime_no_callbacks().  This should be done after the device structure is
+initialized and before it is registered (although after device registration is
+also okay).  The routine will set the device's power.no_callbacks flag and
+prevent the non-debugging run-time PM sysfs attributes from being created.
+When power.no_callbacks is set, the PM core will not invoke the
+->runtime_idle(), ->runtime_suspend(), or ->runtime_resume() callbacks.
+Instead it will assume that suspends and resumes always succeed and that idle
+devices should be suspended.
+As a consequence, the PM core will never directly inform the device's subsystem
+or driver about run-time power changes.  Instead, the driver for the device's
+parent must take responsibility for telling the device's driver when the
+parent's power state changes.
+9. Autosuspend, or automatically-delayed suspends
+Changing a device's power state isn't free; it requires both time and energy.
+A device should be put in a low-power state only when there's some reason to
+think it will remain in that state for a substantial time.  A common heuristic
+says that a device which hasn't been used for a while is liable to remain
+unused; following this advice, drivers should not allow devices to be suspended
+at run-time until they have been inactive for some minimum period.  Even when
+the heuristic ends up being non-optimal, it will still prevent devices from
+"bouncing" too rapidly between low-power and full-power states.
+The term "autosuspend" is an historical remnant.  It doesn't mean that the
+device is automatically suspended (the subsystem or driver still has to call
+the appropriate PM routines); rather it means that run-time suspends will
+automatically be delayed until the desired period of inactivity has elapsed.
+Inactivity is determined based on the power.last_busy field.  Drivers should
+call pm_runtime_mark_last_busy() to update this field after carrying out I/O,
+typically just before calling pm_runtime_put_autosuspend().  The desired length
+of the inactivity period is a matter of policy.  Subsystems can set this length
+initially by calling pm_runtime_set_autosuspend_delay(), but after device
+registration the length should be controlled by user space, using the
+/sys/devices/.../power/autosuspend_delay_ms attribute.
+In order to use autosuspend, subsystems or drivers must call
+pm_runtime_use_autosuspend() (preferably before registering the device), and
+thereafter they should use the various *_autosuspend() helper functions instead
+of the non-autosuspend counterparts:
+        Instead of: pm_runtime_suspend    use: pm_runtime_autosuspend;
+        Instead of: pm_schedule_suspend   use: pm_request_autosuspend;
+        Instead of: pm_runtime_put        use: pm_runtime_put_autosuspend;
+        Instead of: pm_runtime_put_sync   use: pm_runtime_put_sync_autosuspend.
+Drivers may also continue to use the non-autosuspend helper functions; they
+will behave normally, not taking the autosuspend delay into account.
+Similarly, if the power.use_autosuspend field isn't set then the autosuspend
+helper functions will behave just like the non-autosuspend counterparts.
+The implementation is well suited for asynchronous use in interrupt contexts.
+However such use inevitably involves races, because the PM core can't
+synchronize ->runtime_suspend() callbacks with the arrival of I/O requests.
+This synchronization must be handled by the driver, using its private lock.
+Here is a schematic pseudo-code example:
+        foo_read_or_write(struct foo_priv *foo, void *data)
+        {
+                lock(&foo->private_lock);
+                add_request_to_io_queue(foo, data);
+                if (foo->num_pending_requests++ == 0)
+                        pm_runtime_get(&foo->dev);
+                if (!foo->is_suspended)
+                        foo_process_next_request(foo);
+                unlock(&foo->private_lock);
+        }
+        foo_io_completion(struct foo_priv *foo, void *req)
+        {
+                lock(&foo->private_lock);
+                if (--foo->num_pending_requests == 0) {
+                        pm_runtime_mark_last_busy(&foo->dev);
+                        pm_runtime_put_autosuspend(&foo->dev);
+                } else {
+                        foo_process_next_request(foo);
+                }
+                unlock(&foo->private_lock);
+                /* Send req result back to the user ... */
+        }
+        int foo_runtime_suspend(struct device *dev)
+        {
+                struct foo_priv foo = container_of(dev, ...);
+                int ret = 0;
+                lock(&foo->private_lock);
+                if (foo->num_pending_requests > 0) {
+                        ret = -EBUSY;
+                } else {
+                        /* ... suspend the device ... */
+                        foo->is_suspended = 1;
+                }
+                unlock(&foo->private_lock);
+                return ret;
+        }
+        int foo_runtime_resume(struct device *dev)
+        {
+                struct foo_priv foo = container_of(dev, ...);
+                lock(&foo->private_lock);
+                /* ... resume the device ... */
+                foo->is_suspended = 0;
+                pm_runtime_mark_last_busy(&foo->dev);
+                if (foo->num_pending_requests > 0)
+                        foo_process_requests(foo);
+                unlock(&foo->private_lock);
+                return 0;
+        }
+The important point is that after foo_io_completion() asks for an autosuspend,
+the foo_runtime_suspend() callback may race with foo_read_or_write().
+Therefore foo_runtime_suspend() has to check whether there are any pending I/O
+requests (while holding the private lock) before allowing the suspend to
+proceed.
+In addition, the power.autosuspend_delay field can be changed by user space at
+any time.  If a driver cares about this, it can call
+pm_runtime_autosuspend_expiration() from within the ->runtime_suspend()
+callback while holding its private lock.  If the function returns a nonzero
+value then the delay has not yet expired and the callback should return
+-EAGAIN.
diff --git a/Documentation/power/s2ram.txt b/Documentation/power/s2ram.txt
index 514b94fc931e..1bdfa0443773 100644
--- a/Documentation/power/s2ram.txt
+++ b/Documentation/power/s2ram.txt
@@ -49,6 +49,13 @@ machine that doesn't boot) is:
   device (lspci and /sys/devices/pci* is your friend), and see if you can
   fix it, disable it, or trace into its resume function.
+   If no device matches the hash (or any matches appear to be false positives),
+   the culprit may be a device from a loadable kernel module that is not loaded
+   until after the hash is checked. You can check the hash against the current
+   devices again after more modules are loaded using sysfs:
+        cat /sys/power/pm_trace_dev_match
 For example, the above happens to be the VGA device on my EVO, which I
 used to run with "radeonfb" (it's an ATI Radeon mobility). It turns out
 that "radeonfb" simply cannot resume that device - it tries to set the
diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt
index 9d60ab717a7b..ea718891a665 100644
--- a/Documentation/power/swsusp.txt
+++ b/Documentation/power/swsusp.txt
@@ -66,7 +66,8 @@ swsusp saves the state of the machine into active swaps and then reboots or
 powerdowns.  You must explicitly specify the swap partition to resume from with
 ``resume='' kernel option. If signature is found it loads and restores saved
 state. If the option ``noresume'' is specified as a boot parameter, it skips
-the resuming.
+the resuming.  If the option ``hibernate=nocompress'' is specified as a boot
+parameter, it saves hibernation image without compression.
 In the meantime while the system is suspended you should not add/remove any
 of the hardware, write to the filesystems, etc.
diff --git a/Documentation/powerpc/dts-bindings/fsl/spi.txt b/Documentation/powerpc/dts-bindings/fsl/spi.txt
index 80510c018eea..777abd7399d5 100644
--- a/Documentation/powerpc/dts-bindings/fsl/spi.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/spi.txt
@@ -1,7 +1,9 @@
 * SPI (Serial Peripheral Interface)
 Required properties:
- cell-index : SPI controller index.
+- cell-index : QE SPI subblock index.
+                0: QE subblock SPI1
+                1: QE subblock SPI2
 - compatible : should be "fsl,spi".
 - mode : the SPI operation mode, it can be "cpu" or "cpu-qe".
 - reg : Offset and length of the register set for the device
@@ -29,3 +31,23 @@ Example:
                gpios = <&gpio 18 1     // device reg=<0>
                         &gpio 19 1>;   // device reg=<1>
        };
+* eSPI (Enhanced Serial Peripheral Interface)
+Required properties:
+- compatible : should be "fsl,mpc8536-espi".
+- reg : Offset and length of the register set for the device.
+- interrupts : should contain eSPI interrupt, the device has one interrupt.
+- fsl,espi-num-chipselects : the number of the chipselect signals.
+Example:
+        spi@110000 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                compatible = "fsl,mpc8536-espi";
+                reg = <0x110000 0x1000>;
+                interrupts = <53 0x2>;
+                interrupt-parent = <&mpic>;
+                fsl,espi-num-chipselects = <4>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/usb.txt b/Documentation/powerpc/dts-bindings/fsl/usb.txt
index b00152402694..bd5723f0b67e 100644
--- a/Documentation/powerpc/dts-bindings/fsl/usb.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/usb.txt
@@ -8,6 +8,7 @@ and additions :
 Required properties :
 - compatible : Should be "fsl-usb2-mph" for multi port host USB
   controllers, or "fsl-usb2-dr" for dual role USB controllers
+   or "fsl,mpc5121-usb2-dr" for dual role USB controllers of MPC5121
 - phy_type : For multi port host USB controllers, should be one of
   "ulpi", or "serial". For dual role USB controllers, should be
   one of "ulpi", "utmi", "utmi_wide", or "serial".
@@ -33,6 +34,12 @@ Recommended properties :
 - interrupt-parent : the phandle for the interrupt controller that
   services interrupts for this device.
+Optional properties :
+ - fsl,invert-drvvbus : boolean; for MPC5121 USB0 only. Indicates the
+   port power polarity of internal PHY signal DRVVBUS is inverted.
+ - fsl,invert-pwr-fault : boolean; for MPC5121 USB0 only. Indicates
+   the PWR_FAULT signal polarity is inverted.
 Example multi port host USB controller device node :
        usb@22000 {
                compatible = "fsl-usb2-mph";
@@ -57,3 +64,18 @@ Example dual role USB controller device node :
                dr_mode = "otg";
                phy = "ulpi";
        };
+Example dual role USB controller device node for MPC5121ADS:
+        usb@4000 {
+                compatible = "fsl,mpc5121-usb2-dr";
+                reg = <0x4000 0x1000>;
+                #address-cells = <1>;
+                #size-cells = <0>;
+                interrupt-parent = < &ipic >;
+                interrupts = <44 0x8>;
+                dr_mode = "otg";
+                phy_type = "utmi_wide";
+                fsl,invert-drvvbus;
+                fsl,invert-pwr-fault;
+        };
diff --git a/Documentation/scsi/ChangeLog.megaraid_sas b/Documentation/scsi/ChangeLog.megaraid_sas
index 30023568805e..00301ed9c371 100644
--- a/Documentation/scsi/ChangeLog.megaraid_sas
+++ b/Documentation/scsi/ChangeLog.megaraid_sas
@@ -1,3 +1,50 @@
+1 Release Date    : Thur.  May 03, 2010 09:12:45 PST 2009 -
+                        (emaild-id:megaraidlinux@lsi.com)
+                        Bo Yang
+2 Current Version : 00.00.04.31-rc1
+3 Older Version   : 00.00.04.17.1-rc1
+1.      Add the Online Controller Reset (OCR) to the Driver.
+        OCR is the new feature for megaraid_sas driver which
+        will allow the fw to do the chip reset which will not
+        affact the OS behavious.
+        To add the OCR support, driver need to do:
+                a). reset the controller chips -- Xscale and Gen2 which
+                will change the function calls and add the reset function
+                related to this two chips.
+                b). during the reset, driver will store the pending cmds
+                which not returned by FW to driver's pending queue.  Driver
+                will re-issue those pending cmds again to FW after the OCR
+                finished.
+                c). In driver's timeout routine, driver will report to
+                OS as reset. Also driver's queue routine will block the
+                cmds until the OCR finished.
+                d). in Driver's ISR routine, if driver get the FW state as
+                state change, FW in Failure status and FW support online controller
+                reset (OCR), driver will start to do the controller reset.
+                e). In driver's IOCTL routine, the application cmds will wait for the
+                OCR to finish, then issue the cmds to FW.
+                f). Before driver kill adapter, driver will do last chance of
+                OCR to see if driver can bring back the FW.
+2.      Add the support update flag to the driver to tell LSI megaraid_sas
+        application which driver will support the device update.  So application
+        will not need to do the device update after application add/del the device
+        from the system.
+3.      In driver's timeout routine, driver will do three time reset if fw is in
+        failed state.  Driver will kill adapter if can't bring back FW after the
+        this three times reset.
+4.      Add the input parameter max_sectors to 1MB support to our GEN2 controller.
+        customer can use the input paramenter max_sectors to add 1MB support to GEN2
+        controller.
 1 Release Date    : Thur.  Oct 29, 2009 09:12:45 PST 2009 -
                        (emaild-id:megaraidlinux@lsi.com)
                        Bo Yang
diff --git a/Documentation/scsi/st.txt b/Documentation/scsi/st.txt
index 40752602c050..691ca292c24d 100644
--- a/Documentation/scsi/st.txt
+++ b/Documentation/scsi/st.txt
@@ -2,7 +2,7 @@ This file contains brief information about the SCSI tape driver.
 The driver is currently maintained by Kai Mäkisara (email
 Kai.Makisara@kolumbus.fi)
-Last modified: Sun Feb 24 21:59:07 2008 by kai.makisara
+Last modified: Sun Aug 29 18:25:47 2010 by kai.makisara
 BASICS
@@ -85,6 +85,17 @@ writing and the last operation has been a write. Two filemarks can be
 optionally written. In both cases end of data is signified by
 returning zero bytes for two consecutive reads.
+Writing filemarks without the immediate bit set in the SCSI command block acts
+as a synchronization point, i.e., all remaining data form the drive buffers is
+written to tape before the command returns. This makes sure that write errors
+are caught at that point, but this takes time. In some applications, several
+consecutive files must be written fast. The MTWEOFI operation can be used to
+write the filemarks without flushing the drive buffer. Writing filemark at
+close() is always flushing the drive buffers. However, if the previous
+operation is MTWEOFI, close() does not write a filemark. This can be used if
+the program wants to close/open the tape device between files and wants to
+skip waiting.
 If rewind, offline, bsf, or seek is done and previous tape operation was
 write, a filemark is written before moving tape.
@@ -301,6 +312,8 @@ MTBSR   Space backward over count records.
 MTFSS   Space forward over count setmarks.
 MTBSS   Space backward over count setmarks.
 MTWEOF  Write count filemarks.
+MTWEOFI Write count filemarks with immediate bit set (i.e., does not
+        wait until data is on tape)
 MTWSM   Write count setmarks.
 MTREW   Rewind tape.
 MTOFFL  Set device off line (often rewind plus eject).
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index b606c2c4dd37..30289fab86eb 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -80,8 +80,10 @@ dirty_background_bytes
 Contains the amount of dirty memory at which the pdflush background writeback
 daemon will start writeback.
-If dirty_background_bytes is written, dirty_background_ratio becomes a function
+Note: dirty_background_bytes is the counterpart of dirty_background_ratio. Only
-of its value (dirty_background_bytes / the amount of dirtyable system memory).
+one of them may be specified at a time. When one sysctl is written it is
+immediately taken into account to evaluate the dirty memory limits and the
+other appears as 0 when read.
 ==============================================================
@@ -97,8 +99,10 @@ dirty_bytes
 Contains the amount of dirty memory at which a process generating disk writes
 will itself start writeback.
-If dirty_bytes is written, dirty_ratio becomes a function of its value
+Note: dirty_bytes is the counterpart of dirty_ratio. Only one of them may be
-(dirty_bytes / the amount of dirtyable system memory).
+specified at a time. When one sysctl is written it is immediately taken into
+account to evaluate the dirty memory limits and the other appears as 0 when
+read.
 Note: the minimum value allowed for dirty_bytes is two pages (in bytes); any
 value lower than this limit will be ignored and the old configuration will be
diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
index 5c17196c8fe9..312e3754e8c5 100644
--- a/Documentation/sysrq.txt
+++ b/Documentation/sysrq.txt
@@ -75,7 +75,7 @@ On all -  write a character to /proc/sysrq-trigger.  e.g.:
 'f'     - Will call oom_kill to kill a memory hog process.
-'g'     - Used by kgdb on ppc and sh platforms.
+'g'     - Used by kgdb (kernel debugger)
 'h'     - Will display help (actually any other key than those listed
          here will display help. but 'h' is easy to remember :-)
@@ -110,12 +110,15 @@ On all -  write a character to /proc/sysrq-trigger.  e.g.:
 'u'     - Will attempt to remount all mounted filesystems read-only.
-'v'     - Dumps Voyager SMP processor info to your console.
+'v'     - Forcefully restores framebuffer console
+'v'     - Causes ETM buffer dump [ARM-specific]
 'w'     - Dumps tasks that are in uninterruptable (blocked) state.
 'x'     - Used by xmon interface on ppc/powerpc platforms.
+'y'     - Show global CPU Registers [SPARC-64 specific]
 'z'     - Dump the ftrace buffer
 '0'-'9' - Sets the console log level, controlling which kernel messages
diff --git a/Documentation/timers/hpet_example.c b/Documentation/timers/hpet_example.c
index 4bfafb7bc4c5..9a3e7012c190 100644
--- a/Documentation/timers/hpet_example.c
+++ b/Documentation/timers/hpet_example.c
@@ -97,6 +97,33 @@ hpet_open_close(int argc, const char **argv)
 void
 hpet_info(int argc, const char **argv)
 {
+        struct hpet_info        info;
+        int                     fd;
+        if (argc != 1) {
+                fprintf(stderr, "hpet_info: device-name\n");
+                return;
+        }
+        fd = open(argv[0], O_RDONLY);
+        if (fd < 0) {
+                fprintf(stderr, "hpet_info: open of %s failed\n", argv[0]);
+                return;
+        }
+        if (ioctl(fd, HPET_INFO, &info) < 0) {
+                fprintf(stderr, "hpet_info: failed to get info\n");
+                goto out;
+        }
+        fprintf(stderr, "hpet_info: hi_irqfreq 0x%lx hi_flags 0x%lx ",
+                info.hi_ireqfreq, info.hi_flags);
+        fprintf(stderr, "hi_hpet %d hi_timer %d\n",
+                info.hi_hpet, info.hi_timer);
+out:
+        close(fd);
+        return;
 }
 void
diff --git a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
index 1b55146d1c8d..b3e73ddb1567 100644
--- a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
+++ b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
@@ -46,7 +46,7 @@ use constant HIGH_KSWAPD_LATENCY		=> 20;
 use constant HIGH_KSWAPD_REWAKEUP               => 21;
 use constant HIGH_NR_SCANNED                    => 22;
 use constant HIGH_NR_TAKEN                      => 23;
-use constant HIGH_NR_RECLAIM                    => 24;
+use constant HIGH_NR_RECLAIMED                  => 24;
 use constant HIGH_NR_CONTIG_DIRTY               => 25;
 my %perprocesspid;
@@ -58,11 +58,13 @@ my $opt_read_procstat;
 my $total_wakeup_kswapd;
 my ($total_direct_reclaim, $total_direct_nr_scanned);
 my ($total_direct_latency, $total_kswapd_latency);
+my ($total_direct_nr_reclaimed);
 my ($total_direct_writepage_file_sync, $total_direct_writepage_file_async);
 my ($total_direct_writepage_anon_sync, $total_direct_writepage_anon_async);
 my ($total_kswapd_nr_scanned, $total_kswapd_wake);
 my ($total_kswapd_writepage_file_sync, $total_kswapd_writepage_file_async);
 my ($total_kswapd_writepage_anon_sync, $total_kswapd_writepage_anon_async);
+my ($total_kswapd_nr_reclaimed);
 # Catch sigint and exit on request
 my $sigint_report = 0;
@@ -104,7 +106,7 @@ my $regex_kswapd_wake_default = 'nid=([0-9]*) order=([0-9]*)';
 my $regex_kswapd_sleep_default = 'nid=([0-9]*)';
 my $regex_wakeup_kswapd_default = 'nid=([0-9]*) zid=([0-9]*) order=([0-9]*)';
 my $regex_lru_isolate_default = 'isolate_mode=([0-9]*) order=([0-9]*) nr_requested=([0-9]*) nr_scanned=([0-9]*) nr_taken=([0-9]*) contig_taken=([0-9]*) contig_dirty=([0-9]*) contig_failed=([0-9]*)';
-my $regex_lru_shrink_inactive_default = 'lru=([A-Z_]*) nr_scanned=([0-9]*) nr_reclaimed=([0-9]*) priority=([0-9]*)';
+my $regex_lru_shrink_inactive_default = 'nid=([0-9]*) zid=([0-9]*) nr_scanned=([0-9]*) nr_reclaimed=([0-9]*) priority=([0-9]*) flags=([A-Z_|]*)';
 my $regex_lru_shrink_active_default = 'lru=([A-Z_]*) nr_scanned=([0-9]*) nr_rotated=([0-9]*) priority=([0-9]*)';
 my $regex_writepage_default = 'page=([0-9a-f]*) pfn=([0-9]*) flags=([A-Z_|]*)';
@@ -203,8 +205,8 @@ $regex_lru_shrink_inactive = generate_traceevent_regex(
                        "vmscan/mm_vmscan_lru_shrink_inactive",
                        $regex_lru_shrink_inactive_default,
                        "nid", "zid",
-                        "lru",
+                        "nr_scanned", "nr_reclaimed", "priority",
-                        "nr_scanned", "nr_reclaimed", "priority");
+                        "flags");
 $regex_lru_shrink_active = generate_traceevent_regex(
                        "vmscan/mm_vmscan_lru_shrink_active",
                        $regex_lru_shrink_active_default,
@@ -375,6 +377,16 @@ EVENT_PROCESS:
                        my $nr_contig_dirty = $7;
                        $perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned;
                        $perprocesspid{$process_pid}->{HIGH_NR_CONTIG_DIRTY} += $nr_contig_dirty;
+                } elsif ($tracepoint eq "mm_vmscan_lru_shrink_inactive") {
+                        $details = $5;
+                        if ($details !~ /$regex_lru_shrink_inactive/o) {
+                                print "WARNING: Failed to parse mm_vmscan_lru_shrink_inactive as expected\n";
+                                print "         $details\n";
+                                print "         $regex_lru_shrink_inactive/o\n";
+                                next;
+                        }
+                        my $nr_reclaimed = $4;
+                        $perprocesspid{$process_pid}->{HIGH_NR_RECLAIMED} += $nr_reclaimed;
                } elsif ($tracepoint eq "mm_vmscan_writepage") {
                        $details = $5;
                        if ($details !~ /$regex_writepage/o) {
@@ -464,8 +476,8 @@ sub dump_stats {
        # Print out process activity
        printf("\n");
-        printf("%-" . $max_strlen . "s %8s %10s   %8s   %8s %8s %8s %8s\n", "Process", "Direct",  "Wokeup", "Pages",   "Pages",   "Pages",     "Time");
+        printf("%-" . $max_strlen . "s %8s %10s   %8s %8s  %8s %8s %8s %8s\n", "Process", "Direct",  "Wokeup", "Pages",   "Pages",   "Pages",   "Pages",     "Time");
-        printf("%-" . $max_strlen . "s %8s %10s   %8s   %8s %8s %8s %8s\n", "details", "Rclms",   "Kswapd", "Scanned", "Sync-IO", "ASync-IO",  "Stalled");
+        printf("%-" . $max_strlen . "s %8s %10s   %8s %8s  %8s %8s %8s %8s\n", "details", "Rclms",   "Kswapd", "Scanned", "Rclmed",  "Sync-IO", "ASync-IO",  "Stalled");
        foreach $process_pid (keys %stats) {
                if (!$stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}) {
@@ -475,6 +487,7 @@ sub dump_stats {
                $total_direct_reclaim += $stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN};
                $total_wakeup_kswapd += $stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD};
                $total_direct_nr_scanned += $stats{$process_pid}->{HIGH_NR_SCANNED};
+                $total_direct_nr_reclaimed += $stats{$process_pid}->{HIGH_NR_RECLAIMED};
                $total_direct_writepage_file_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC};
                $total_direct_writepage_anon_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC};
                $total_direct_writepage_file_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC};
@@ -489,11 +502,12 @@ sub dump_stats {
                        $index++;
                }
-                printf("%-" . $max_strlen . "s %8d %10d   %8u   %8u %8u %8.3f",
+                printf("%-" . $max_strlen . "s %8d %10d   %8u %8u  %8u %8u %8.3f",
                        $process_pid,
                        $stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN},
                        $stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD},
                        $stats{$process_pid}->{HIGH_NR_SCANNED},
+                        $stats{$process_pid}->{HIGH_NR_RECLAIMED},
                        $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC},
                        $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC},
                        $this_reclaim_delay / 1000);
@@ -529,8 +543,8 @@ sub dump_stats {
        # Print out kswapd activity
        printf("\n");
-        printf("%-" . $max_strlen . "s %8s %10s   %8s   %8s %8s %8s\n", "Kswapd",   "Kswapd",  "Order",     "Pages",   "Pages",  "Pages");
+        printf("%-" . $max_strlen . "s %8s %10s   %8s   %8s %8s %8s\n", "Kswapd",   "Kswapd",  "Order",     "Pages",   "Pages",   "Pages",  "Pages");
-        printf("%-" . $max_strlen . "s %8s %10s   %8s   %8s %8s %8s\n", "Instance", "Wakeups", "Re-wakeup", "Scanned", "Sync-IO", "ASync-IO");
+        printf("%-" . $max_strlen . "s %8s %10s   %8s   %8s %8s %8s\n", "Instance", "Wakeups", "Re-wakeup", "Scanned", "Rclmed",  "Sync-IO", "ASync-IO");
        foreach $process_pid (keys %stats) {
                if (!$stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}) {
@@ -539,16 +553,18 @@ sub dump_stats {
                $total_kswapd_wake += $stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE};
                $total_kswapd_nr_scanned += $stats{$process_pid}->{HIGH_NR_SCANNED};
+                $total_kswapd_nr_reclaimed += $stats{$process_pid}->{HIGH_NR_RECLAIMED};
                $total_kswapd_writepage_file_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC};
                $total_kswapd_writepage_anon_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC};
                $total_kswapd_writepage_file_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC};
                $total_kswapd_writepage_anon_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC};
-                printf("%-" . $max_strlen . "s %8d %10d   %8u   %8i %8u",
+                printf("%-" . $max_strlen . "s %8d %10d   %8u %8u  %8i %8u",
                        $process_pid,
                        $stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE},
                        $stats{$process_pid}->{HIGH_KSWAPD_REWAKEUP},
                        $stats{$process_pid}->{HIGH_NR_SCANNED},
+                        $stats{$process_pid}->{HIGH_NR_RECLAIMED},
                        $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC},
                        $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC});
@@ -579,6 +595,7 @@ sub dump_stats {
        print "\nSummary\n";
        print "Direct reclaims:                         $total_direct_reclaim\n";
        print "Direct reclaim pages scanned:            $total_direct_nr_scanned\n";
+        print "Direct reclaim pages reclaimed:          $total_direct_nr_reclaimed\n";
        print "Direct reclaim write file sync I/O:      $total_direct_writepage_file_sync\n";
        print "Direct reclaim write anon sync I/O:      $total_direct_writepage_anon_sync\n";
        print "Direct reclaim write file async I/O:     $total_direct_writepage_file_async\n";
@@ -588,6 +605,7 @@ sub dump_stats {
        print "\n";
        print "Kswapd wakeups:                          $total_kswapd_wake\n";
        print "Kswapd pages scanned:                    $total_kswapd_nr_scanned\n";
+        print "Kswapd pages reclaimed:                  $total_kswapd_nr_reclaimed\n";
        print "Kswapd reclaim write file sync I/O:      $total_kswapd_writepage_file_sync\n";
        print "Kswapd reclaim write anon sync I/O:      $total_kswapd_writepage_anon_sync\n";
        print "Kswapd reclaim write file async I/O:     $total_kswapd_writepage_file_async\n";
@@ -612,6 +630,7 @@ sub aggregate_perprocesspid() {
                $perprocess{$process}->{MM_VMSCAN_WAKEUP_KSWAPD} += $perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD};
                $perprocess{$process}->{HIGH_KSWAPD_REWAKEUP} += $perprocesspid{$process_pid}->{HIGH_KSWAPD_REWAKEUP};
                $perprocess{$process}->{HIGH_NR_SCANNED} += $perprocesspid{$process_pid}->{HIGH_NR_SCANNED};
+                $perprocess{$process}->{HIGH_NR_RECLAIMED} += $perprocesspid{$process_pid}->{HIGH_NR_RECLAIMED};
                $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC};
                $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC};
                $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC};
diff --git a/Documentation/usb/proc_usb_info.txt b/Documentation/usb/proc_usb_info.txt
index fafcd4723260..afe596d5f201 100644
--- a/Documentation/usb/proc_usb_info.txt
+++ b/Documentation/usb/proc_usb_info.txt
@@ -1,12 +1,17 @@
 /proc/bus/usb filesystem output
 ===============================
-(version 2003.05.30)
+(version 2010.09.13)
 The usbfs filesystem for USB devices is traditionally mounted at
 /proc/bus/usb.  It provides the /proc/bus/usb/devices file, as well as
 the /proc/bus/usb/BBB/DDD files.
+In many modern systems the usbfs filsystem isn't used at all.  Instead
+USB device nodes are created under /dev/usb/ or someplace similar.  The
+"devices" file is available in debugfs, typically as
+/sys/kernel/debug/usb/devices.
 **NOTE**: If /proc/bus/usb appears empty, and a host controller
          driver has been linked, then you need to mount the
@@ -106,8 +111,8 @@ Legend:
 Topology info:
-T:  Bus=dd Lev=dd Prnt=dd Port=dd Cnt=dd Dev#=ddd Spd=ddd MxCh=dd
+T:  Bus=dd Lev=dd Prnt=dd Port=dd Cnt=dd Dev#=ddd Spd=dddd MxCh=dd
-|   |      |      |       |       |      |        |       |__MaxChildren
+|   |      |      |       |       |      |        |        |__MaxChildren
 |   |      |      |       |       |      |        |__Device Speed in Mbps
 |   |      |      |       |       |      |__DeviceNumber
 |   |      |      |       |       |__Count of devices at this level
@@ -120,8 +125,13 @@ T:  Bus=dd Lev=dd Prnt=dd Port=dd Cnt=dd Dev#=ddd Spd=ddd MxCh=dd
    Speed may be:
        1.5     Mbit/s for low speed USB
        12      Mbit/s for full speed USB
-        480     Mbit/s for high speed USB (added for USB 2.0)
+        480     Mbit/s for high speed USB (added for USB 2.0);
+                  also used for Wireless USB, which has no fixed speed
+        5000    Mbit/s for SuperSpeed USB (added for USB 3.0)
+    For reasons lost in the mists of time, the Port number is always
+    too low by 1.  For example, a device plugged into port 4 will
+    show up with "Port=03".
 Bandwidth info:
 B:  Alloc=ddd/ddd us (xx%), #Int=ddd, #Iso=ddd
@@ -291,7 +301,7 @@ Here's an example, from a system which has a UHCI root hub,
 an external hub connected to the root hub, and a mouse and
 a serial converter connected to the external hub.
-T:  Bus=00 Lev=00 Prnt=00 Port=00 Cnt=00 Dev#=  1 Spd=12  MxCh= 2
+T:  Bus=00 Lev=00 Prnt=00 Port=00 Cnt=00 Dev#=  1 Spd=12   MxCh= 2
 B:  Alloc= 28/900 us ( 3%), #Int=  2, #Iso=  0
 D:  Ver= 1.00 Cls=09(hub  ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
 P:  Vendor=0000 ProdID=0000 Rev= 0.00
@@ -301,21 +311,21 @@ C:* #Ifs= 1 Cfg#= 1 Atr=40 MxPwr=  0mA
 I:  If#= 0 Alt= 0 #EPs= 1 Cls=09(hub  ) Sub=00 Prot=00 Driver=hub
 E:  Ad=81(I) Atr=03(Int.) MxPS=   8 Ivl=255ms
-T:  Bus=00 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12  MxCh= 4
+T:  Bus=00 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12   MxCh= 4
 D:  Ver= 1.00 Cls=09(hub  ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
 P:  Vendor=0451 ProdID=1446 Rev= 1.00
 C:* #Ifs= 1 Cfg#= 1 Atr=e0 MxPwr=100mA
 I:  If#= 0 Alt= 0 #EPs= 1 Cls=09(hub  ) Sub=00 Prot=00 Driver=hub
 E:  Ad=81(I) Atr=03(Int.) MxPS=   1 Ivl=255ms
-T:  Bus=00 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=1.5 MxCh= 0
+T:  Bus=00 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=1.5  MxCh= 0
 D:  Ver= 1.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
 P:  Vendor=04b4 ProdID=0001 Rev= 0.00
 C:* #Ifs= 1 Cfg#= 1 Atr=80 MxPwr=100mA
 I:  If#= 0 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=02 Driver=mouse
 E:  Ad=81(I) Atr=03(Int.) MxPS=   3 Ivl= 10ms
-T:  Bus=00 Lev=02 Prnt=02 Port=02 Cnt=02 Dev#=  4 Spd=12  MxCh= 0
+T:  Bus=00 Lev=02 Prnt=02 Port=02 Cnt=02 Dev#=  4 Spd=12   MxCh= 0
 D:  Ver= 1.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
 P:  Vendor=0565 ProdID=0001 Rev= 1.08
 S:  Manufacturer=Peracom Networks, Inc.
@@ -330,12 +340,12 @@ E:  Ad=82(I) Atr=03(Int.) MxPS=   8 Ivl=  8ms
 Selecting only the "T:" and "I:" lines from this (for example, by using
 "procusb ti"), we have:
-T:  Bus=00 Lev=00 Prnt=00 Port=00 Cnt=00 Dev#=  1 Spd=12  MxCh= 2
+T:  Bus=00 Lev=00 Prnt=00 Port=00 Cnt=00 Dev#=  1 Spd=12   MxCh= 2
-T:  Bus=00 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12  MxCh= 4
+T:  Bus=00 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12   MxCh= 4
 I:  If#= 0 Alt= 0 #EPs= 1 Cls=09(hub  ) Sub=00 Prot=00 Driver=hub
-T:  Bus=00 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=1.5 MxCh= 0
+T:  Bus=00 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=1.5  MxCh= 0
 I:  If#= 0 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=02 Driver=mouse
-T:  Bus=00 Lev=02 Prnt=02 Port=02 Cnt=02 Dev#=  4 Spd=12  MxCh= 0
+T:  Bus=00 Lev=02 Prnt=02 Port=02 Cnt=02 Dev#=  4 Spd=12   MxCh= 0
 I:  If#= 0 Alt= 0 #EPs= 3 Cls=00(>ifc ) Sub=00 Prot=00 Driver=serial
diff --git a/Documentation/video4linux/CARDLIST.cx88 b/Documentation/video4linux/CARDLIST.cx88
index f2510541373b..42517d9121de 100644
--- a/Documentation/video4linux/CARDLIST.cx88
+++ b/Documentation/video4linux/CARDLIST.cx88
@@ -83,3 +83,4 @@
 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]
+ 85 -> Twinhan VP-1027 DVB-S                               [1822:0023]
diff --git a/Documentation/video4linux/CARDLIST.em28xx b/Documentation/video4linux/CARDLIST.em28xx
index 5c568757c301..ac2616a62fc3 100644
--- a/Documentation/video4linux/CARDLIST.em28xx
+++ b/Documentation/video4linux/CARDLIST.em28xx
@@ -31,6 +31,7 @@
 30 -> Videology 20K14XUSB USB2.0               (em2820/em2840)
 31 -> Usbgear VD204v9                          (em2821)
 32 -> Supercomp USB 2.0 TV                     (em2821)
+ 33 -> Elgato Video Capture                     (em2860)        [0fd9:0033]
 34 -> Terratec Cinergy A Hybrid XS             (em2860)        [0ccd:004f]
 35 -> Typhoon DVD Maker                        (em2860)
 36 -> NetGMBH Cam                              (em2860)
@@ -45,7 +46,7 @@
 45 -> Pinnacle PCTV DVB-T                      (em2870)
 46 -> Compro, VideoMate U3                     (em2870)        [185b:2870]
 47 -> KWorld DVB-T 305U                        (em2880)        [eb1a:e305]
- 48 -> KWorld DVB-T 310U                        (em2880)        [eb1a:e310]
+ 48 -> KWorld DVB-T 310U                        (em2880)
 49 -> MSI DigiVox A/D                          (em2880)        [eb1a:e310]
 50 -> MSI DigiVox A/D II                       (em2880)        [eb1a:e320]
 51 -> Terratec Hybrid XS Secam                 (em2880)        [0ccd:004c]
diff --git a/Documentation/video4linux/CARDLIST.saa7134 b/Documentation/video4linux/CARDLIST.saa7134
index 4000c29fcfb6..8d9afc7d8014 100644
--- a/Documentation/video4linux/CARDLIST.saa7134
+++ b/Documentation/video4linux/CARDLIST.saa7134
@@ -126,7 +126,7 @@
 125 -> Beholder BeholdTV 409                    [0000:4090]
 126 -> Beholder BeholdTV 505 FM                 [5ace:5050]
 127 -> Beholder BeholdTV 507 FM / BeholdTV 509 FM [5ace:5070,5ace:5090]
-128 -> Beholder BeholdTV Columbus TVFM          [0000:5201]
+128 -> Beholder BeholdTV Columbus TV/FM         [0000:5201]
 129 -> Beholder BeholdTV 607 FM                 [5ace:6070]
 130 -> Beholder BeholdTV M6                     [5ace:6190]
 131 -> Twinhan Hybrid DTV-DVB 3056 PCI          [1822:0022]
diff --git a/Documentation/video4linux/bttv/MAKEDEV b/Documentation/video4linux/bttv/MAKEDEV
index 9d112f7fd5f7..093c0cd18042 100644
--- a/Documentation/video4linux/bttv/MAKEDEV
+++ b/Documentation/video4linux/bttv/MAKEDEV
@@ -19,7 +19,6 @@ function makedev () {
 echo "*** new device names ***"
 makedev video 0
 makedev radio 64
-makedev vtx 192
 makedev vbi 224
 #echo "*** old device names (for compatibility only) ***"
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
index 56ba7bba7168..6a562eeeb4cd 100644
--- a/Documentation/video4linux/gspca.txt
+++ b/Documentation/video4linux/gspca.txt
@@ -302,12 +302,14 @@ sonixj		0c45:60fb	Surfer NoName
 sonixj          0c45:60fc       LG-LIC300
 sonixj          0c45:60fe       Microdia Audio
 sonixj          0c45:6100       PC Camera (SN9C128)
+sonixj          0c45:6102       PC Camera (SN9C128)
 sonixj          0c45:610a       PC Camera (SN9C128)
 sonixj          0c45:610b       PC Camera (SN9C128)
 sonixj          0c45:610c       PC Camera (SN9C128)
 sonixj          0c45:610e       PC Camera (SN9C128)
 sonixj          0c45:6128       Microdia/Sonix SNP325
 sonixj          0c45:612a       Avant Camera
+sonixj          0c45:612b       Speed-Link REFLECT2
 sonixj          0c45:612c       Typhoon Rasy Cam 1.3MPix
 sonixj          0c45:6130       Sonix Pccam
 sonixj          0c45:6138       Sn9c120 Mo4000
diff --git a/Documentation/video4linux/v4l2-framework.txt b/Documentation/video4linux/v4l2-framework.txt
index e831aaca66f8..f22f35c271f3 100644
--- a/Documentation/video4linux/v4l2-framework.txt
+++ b/Documentation/video4linux/v4l2-framework.txt
@@ -44,8 +44,8 @@ All drivers have the following structure:
 2) A way of initializing and commanding sub-devices (if any).
-3) Creating V4L2 device nodes (/dev/videoX, /dev/vbiX, /dev/radioX and
+3) Creating V4L2 device nodes (/dev/videoX, /dev/vbiX and /dev/radioX)
-   /dev/vtxX) and keeping track of device-node specific data.
+   and keeping track of device-node specific data.
 4) Filehandle-specific structs containing per-filehandle data;
@@ -192,6 +192,11 @@ You also need a way to go from the low-level struct to v4l2_subdev. For the
 common i2c_client struct the i2c_set_clientdata() call is used to store a
 v4l2_subdev pointer, for other busses you may have to use other methods.
+Bridges might also need to store per-subdev private data, such as a pointer to
+bridge-specific per-subdev private data. The v4l2_subdev structure provides
+host private data for that purpose that can be accessed with
+v4l2_get_subdev_hostdata() and v4l2_set_subdev_hostdata().
 From the bridge driver perspective you load the sub-device module and somehow
 obtain the v4l2_subdev pointer. For i2c devices this is easy: you call
 i2c_get_clientdata(). For other busses something similar needs to be done.
@@ -448,6 +453,10 @@ You should also set these fields:
 - ioctl_ops: if you use the v4l2_ioctl_ops to simplify ioctl maintenance
  (highly recommended to use this and it might become compulsory in the
  future!), then set this to your v4l2_ioctl_ops struct.
+- lock: leave to NULL if you want to do all the locking in the driver.
+  Otherwise you give it a pointer to a struct mutex_lock and before any
+  of the v4l2_file_operations is called this lock will be taken by the
+  core and released afterwards.
 - parent: you only set this if v4l2_device was registered with NULL as
  the parent device struct. This only happens in cases where one hardware
  device has multiple PCI devices that all share the same v4l2_device core.
@@ -464,6 +473,22 @@ If you use v4l2_ioctl_ops, then you should set either .unlocked_ioctl or
 The v4l2_file_operations struct is a subset of file_operations. The main
 difference is that the inode argument is omitted since it is never used.
+v4l2_file_operations and locking
+--------------------------------
+You can set a pointer to a mutex_lock in struct video_device. Usually this
+will be either a top-level mutex or a mutex per device node. If you want
+finer-grained locking then you have to set it to NULL and do you own locking.
+If a lock is specified then all file operations will be serialized on that
+lock. If you use videobuf then you must pass the same lock to the videobuf
+queue initialize function: if videobuf has to wait for a frame to arrive, then
+it will temporarily unlock the lock and relock it afterwards. If your driver
+also waits in the code, then you should do the same to allow other processes
+to access the device node while the first process is waiting for something.
+The implementation of a hotplug disconnect should also take the lock before
+calling v4l2_device_disconnect.
 video_device registration
 -------------------------
@@ -483,7 +508,6 @@ types exist:
 VFL_TYPE_GRABBER: videoX for video input/output devices
 VFL_TYPE_VBI: vbiX for vertical blank data (i.e. closed captions, teletext)
 VFL_TYPE_RADIO: radioX for radio tuners
-VFL_TYPE_VTX: vtxX for teletext devices (deprecated, don't use)
 The last argument gives you a certain amount of control over the device
 device node number used (i.e. the X in videoX). Normally you will pass -1
@@ -547,9 +571,8 @@ from /dev).
 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
-device nodes open. So after the unregister all file operations will return
+device nodes open. So after the unregister all file operations (except
-an error as well, except for the ioctl and unlocked_ioctl file operations:
+release, of course) will return an error as well.
-those will still be passed on since some buffer ioctls may still be needed.
 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.
diff --git a/Documentation/vm/highmem.txt b/Documentation/vm/highmem.txt
new file mode 100644
index 000000000000..4324d24ffacd
--- /dev/null
+++ b/Documentation/vm/highmem.txt
@@ -0,0 +1,162 @@
+                             ====================
+                             HIGH MEMORY HANDLING
+                             ====================
+By: Peter Zijlstra <a.p.zijlstra@chello.nl>
+Contents:
+ (*) What is high memory?
+ (*) Temporary virtual mappings.
+ (*) Using kmap_atomic.
+ (*) Cost of temporary mappings.
+ (*) i386 PAE.
+====================
+WHAT IS HIGH MEMORY?
+====================
+High memory (highmem) is used when the size of physical memory approaches or
+exceeds the maximum size of virtual memory.  At that point it becomes
+impossible for the kernel to keep all of the available physical memory mapped
+at all times.  This means the kernel needs to start using temporary mappings of
+the pieces of physical memory that it wants to access.
+The part of (physical) memory not covered by a permanent mapping is what we
+refer to as 'highmem'.  There are various architecture dependent constraints on
+where exactly that border lies.
+In the i386 arch, for example, we choose to map the kernel into every process's
+VM space so that we don't have to pay the full TLB invalidation costs for
+kernel entry/exit.  This means the available virtual memory space (4GiB on
+i386) has to be divided between user and kernel space.
+The traditional split for architectures using this approach is 3:1, 3GiB for
+userspace and the top 1GiB for kernel space:
+                +--------+ 0xffffffff
+                | Kernel |
+                +--------+ 0xc0000000
+                |        |
+                | User   |
+                |        |
+                +--------+ 0x00000000
+This means that the kernel can at most map 1GiB of physical memory at any one
+time, but because we need virtual address space for other things - including
+temporary maps to access the rest of the physical memory - the actual direct
+map will typically be less (usually around ~896MiB).
+Other architectures that have mm context tagged TLBs can have separate kernel
+and user maps.  Some hardware (like some ARMs), however, have limited virtual
+space when they use mm context tags.
+==========================
+TEMPORARY VIRTUAL MAPPINGS
+==========================
+The kernel contains several ways of creating temporary mappings:
+ (*) vmap().  This can be used to make a long duration mapping of multiple
+     physical pages into a contiguous virtual space.  It needs global
+     synchronization to unmap.
+ (*) kmap().  This permits a short duration mapping of a single page.  It needs
+     global synchronization, but is amortized somewhat.  It is also prone to
+     deadlocks when using in a nested fashion, and so it is not recommended for
+     new code.
+ (*) kmap_atomic().  This permits a very short duration mapping of a single
+     page.  Since the mapping is restricted to the CPU that issued it, it
+     performs well, but the issuing task is therefore required to stay on that
+     CPU until it has finished, lest some other task displace its mappings.
+     kmap_atomic() may also be used by interrupt contexts, since it is does not
+     sleep and the caller may not sleep until after kunmap_atomic() is called.
+     It may be assumed that k[un]map_atomic() won't fail.
+=================
+USING KMAP_ATOMIC
+=================
+When and where to use kmap_atomic() is straightforward.  It is used when code
+wants to access the contents of a page that might be allocated from high memory
+(see __GFP_HIGHMEM), for example a page in the pagecache.  The API has two
+functions, and they can be used in a manner similar to the following:
+        /* Find the page of interest. */
+        struct page *page = find_get_page(mapping, offset);
+        /* Gain access to the contents of that page. */
+        void *vaddr = kmap_atomic(page);
+        /* Do something to the contents of that page. */
+        memset(vaddr, 0, PAGE_SIZE);
+        /* Unmap that page. */
+        kunmap_atomic(vaddr);
+Note that the kunmap_atomic() call takes the result of the kmap_atomic() call
+not the argument.
+If you need to map two pages because you want to copy from one page to
+another you need to keep the kmap_atomic calls strictly nested, like:
+        vaddr1 = kmap_atomic(page1);
+        vaddr2 = kmap_atomic(page2);
+        memcpy(vaddr1, vaddr2, PAGE_SIZE);
+        kunmap_atomic(vaddr2);
+        kunmap_atomic(vaddr1);
+==========================
+COST OF TEMPORARY MAPPINGS
+==========================
+The cost of creating temporary mappings can be quite high.  The arch has to
+manipulate the kernel's page tables, the data TLB and/or the MMU's registers.
+If CONFIG_HIGHMEM is not set, then the kernel will try and create a mapping
+simply with a bit of arithmetic that will convert the page struct address into
+a pointer to the page contents rather than juggling mappings about.  In such a
+case, the unmap operation may be a null operation.
+If CONFIG_MMU is not set, then there can be no temporary mappings and no
+highmem.  In such a case, the arithmetic approach will also be used.
+========
+i386 PAE
+========
+The i386 arch, under some circumstances, will permit you to stick up to 64GiB
+of RAM into your 32-bit machine.  This has a number of consequences:
+ (*) Linux needs a page-frame structure for each page in the system and the
+     pageframes need to live in the permanent mapping, which means:
+ (*) you can have 896M/sizeof(struct page) page-frames at most; with struct
+     page being 32-bytes that would end up being something in the order of 112G
+     worth of pages; the kernel, however, needs to store more than just
+     page-frames in that memory...
+ (*) PAE makes your page tables larger - which slows the system down as more
+     data has to be accessed to traverse in TLB fills and the like.  One
+     advantage is that PAE has more PTE bits and can provide advanced features
+     like NX and PAT.
+The general recommendation is that you don't use more than 8GiB on a 32-bit
+machine - although more might work for you and your workload, you're pretty
+much on your own - don't expect kernel developers to really care much if things
+come apart.
diff --git a/Documentation/vm/numa_memory_policy.txt b/Documentation/vm/numa_memory_policy.txt
index 6690fc34ef6d..4e7da6543424 100644
--- a/Documentation/vm/numa_memory_policy.txt
+++ b/Documentation/vm/numa_memory_policy.txt
@@ -424,7 +424,7 @@ a command line tool, numactl(8), exists that allows one to:
 + set the shared policy for a shared memory segment via mbind(2)
-The numactl(8) tool is packages with the run-time version of the library
+The numactl(8) tool is packaged with the run-time version of the library
 containing the memory policy system call wrappers.  Some distributions
 package the headers and compile-time libraries in a separate development
 package.
diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt
index e4498a2872c3..996a27d9b8db 100644
--- a/Documentation/workqueue.txt
+++ b/Documentation/workqueue.txt
@@ -196,11 +196,11 @@ resources, scheduled and executed.
        suspend operations.  Work items on the wq are drained and no
        new work item starts execution until thawed.
-  WQ_RESCUER
+  WQ_MEM_RECLAIM
        All wq which might be used in the memory reclaim paths _MUST_
-        have this flag set.  This reserves one worker exclusively for
+        have this flag set.  The wq is guaranteed to have at least one
-        the execution of this wq under memory pressure.
+        execution context regardless of memory pressure.
  WQ_HIGHPRI
@@ -356,11 +356,11 @@ If q1 has WQ_CPU_INTENSIVE set,
 6. Guidelines
-* Do not forget to use WQ_RESCUER if a wq may process work items which
+* Do not forget to use WQ_MEM_RECLAIM if a wq may process work items
-  are used during memory reclaim.  Each wq with WQ_RESCUER set has one
+  which are used during memory reclaim.  Each wq with WQ_MEM_RECLAIM
-  rescuer thread reserved for it.  If there is dependency among
+  set has an execution context reserved for it.  If there is
-  multiple work items used during memory reclaim, they should be
+  dependency among multiple work items used during memory reclaim,
-  queued to separate wq each with WQ_RESCUER.
+  they should be queued to separate wq each with WQ_MEM_RECLAIM.
 * Unless strict ordering is required, there is no need to use ST wq.
@@ -368,12 +368,13 @@ If q1 has WQ_CPU_INTENSIVE set,
  recommended.  In most use cases, concurrency level usually stays
  well under the default limit.
-* A wq serves as a domain for forward progress guarantee (WQ_RESCUER),
+* A wq serves as a domain for forward progress guarantee
-  flush and work item attributes.  Work items which are not involved
+  (WQ_MEM_RECLAIM, flush and work item attributes.  Work items which
-  in memory reclaim and don't need to be flushed as a part of a group
+  are not involved in memory reclaim and don't need to be flushed as a
-  of work items, and don't require any special attribute, can use one
+  part of a group of work items, and don't require any special
-  of the system wq.  There is no difference in execution
+  attribute, can use one of the system wq.  There is no difference in
-  characteristics between using a dedicated wq and a system wq.
+  execution characteristics between using a dedicated wq and a system
+  wq.
 * Unless work items are expected to consume a huge amount of CPU
  cycles, using a bound wq is usually beneficial due to the increased
diff --git a/Documentation/x86/x86_64/kernel-stacks b/Documentation/x86/x86_64/kernel-stacks
index 5ad65d51fb95..a01eec5d1d0b 100644
--- a/Documentation/x86/x86_64/kernel-stacks
+++ b/Documentation/x86/x86_64/kernel-stacks
@@ -18,9 +18,9 @@ specialized stacks contain no useful data.  The main CPU stacks are:
  Used for external hardware interrupts.  If this is the first external
  hardware interrupt (i.e. not a nested hardware interrupt) then the
  kernel switches from the current task to the interrupt stack.  Like
-  the split thread and interrupt stacks on i386 (with CONFIG_4KSTACKS),
+  the split thread and interrupt stacks on i386, this gives more room
-  this gives more room for kernel interrupt processing without having
+  for kernel interrupt processing without having to increase the size
-  to increase the size of every per thread stack.
+  of every per thread stack.
  The interrupt stack is also used when processing a softirq.
author	Mark Brown <broonie@opensource.wolfsonmicro.com>	2010-11-02 09:41:56 -0400
committer	Mark Brown <broonie@opensource.wolfsonmicro.com>	2010-11-02 09:41:56 -0400
commit	29c798fecb9b846b363b0a02fa662ff42fc19426 (patch)
tree	e708d6aca8f098e69571780f702325b221b66694 /Documentation
parent	cb9906229595941d632fc4022b05da4f9533856a (diff)
parent	c8ddb2713c624f432fa5fe3c7ecffcdda46ea0d4 (diff)